[Perf, Test] (MG_Util): libfork execution engine for the shader compile pool, runtime-selectable

Adds libfork v3.8.0 (3rdparty submodule, header-only, wired like the asio
precedent) as a second execution engine behind ShaderCompilePool, selected
per process by MOBILEGL_ASYNC_POOL=asio|libfork (default asio; unknown
values warn and fall back). The engine boundary is deliberately tiny: the
queue, the concurrency budget and its clamping, the suspension latch,
cancel request-vs-outcome, the stopped-is-synchronous fallback and the
drain all stay in the shared Impl - an engine only answers how a
budget-cleared job reaches a worker.

The libfork engine runs detached root tasks as CHAINS: a finished body
takes the next queued job in the same coroutine on the same worker, so
the refills a worker posts are absorbed without a scheduler round trip
(the naive dispatch-thread shape measured 4x worse than asio on short
jobs). Absorption is bounded at one job per live chain - unbounded
absorption serialized bursts posted from inside the pool, which is the
shipped shape (one compile settling fans out link jobs via SubmitAfter
and the adoption map), caught by the review and pinned by a permanent
peak-concurrency regression test (pre-fix: libfork peak 1 vs asio peak 4
on a 16-job worker-posted burst). External submissions go through a
round-robin adaptor instead of lf::lazy_pool::schedule, which both
avoids a data race on lazy_pool's unsynchronized xoshiro under
concurrent submits and beats birthday-collision placement by ~1.3x at
budget == thread count.

The measured answer to "does asio scale poorly": no - the executor was
never the bottleneck. On real pack corpora extracted from the trace
fixtures (BSL 61 shaders, Complementary 277), interleaved best-of-5 per
cell, the engines are within noise of each other at every thread count
(complementary: 4965/2506/1376/824 ms at 1/2/4/8 threads for asio;
libfork within 1%), both ~6x at 8 threads. perf counters show the
flattening past 4 threads is machine-level (instructions flat at 22.1e9
from 1 to 16 threads - no added work, no lock spinning - while cycles
and LLC misses double: memory-stall bound), and the separating control
- N fully independent single-threaded processes with no shared
scheduler at all - scales WORSE than the pool (5.27x vs 5.94x at 8).
The pool microbenchmark does favor libfork on pure dispatch (518 vs
530 ns/job at 1 worker, growing with worker count), but a real compile
body is 1-100 ms, so dispatch is under 0.1% either way. asio therefore
stays the default; this branch exists to make the comparison
reproducible (MG_Test/Util/AsyncPoolBench drives either engine over a
corpus directory) and to keep the alternative viable.

613/613 unit tests in all four combos ({asio, libfork} x {async default
on, kill switch}), integration scenarios byte-identical between engines
on both backends.

.github/scripts/fetch-trace-fixture-lfs.sh

@@ -9,17 +9,45 @@ fi
 case_name="$1"
 fixture_dir="${2:-tools/trace_replay/fixtures}"
 python_bin="${PYTHON:-python3}"
-mirror_base="${MOBILEGL_TRACE_FIXTURE_MIRROR_BASE:-https://repo.miawa.cn/mgl/tools/trace_replay/fixtures}"
+# Fixture mirrors, tried in order before falling back to Git LFS. Override the
+# whole list with MOBILEGL_TRACE_FIXTURE_MIRROR_BASES (whitespace separated);
+# MOBILEGL_TRACE_FIXTURE_MIRROR_BASE still works and is tried first.
+default_mirror_bases=(
+  "https://git.hit.moe/swung0x48/MobileGL/media/branch/dev/tools/trace_replay/fixtures"
+  "https://repo.miawa.cn/mgl/tools/trace_replay/fixtures"
+)
+if [ -n "${MOBILEGL_TRACE_FIXTURE_MIRROR_BASES:-}" ]; then
+  read -r -a mirror_bases <<< "${MOBILEGL_TRACE_FIXTURE_MIRROR_BASES}"
+else
+  mirror_bases=("${default_mirror_bases[@]}")
+fi
+if [ -n "${MOBILEGL_TRACE_FIXTURE_MIRROR_BASE:-}" ]; then
+  mirror_bases=("${MOBILEGL_TRACE_FIXTURE_MIRROR_BASE}" "${mirror_bases[@]}")
+fi
+# Optional bearer token for mirrors that require authentication (private Gitea).
+mirror_token="${MOBILEGL_TRACE_FIXTURE_MIRROR_TOKEN:-}"
+download_attempts="${MOBILEGL_TRACE_FIXTURE_DOWNLOAD_ATTEMPTS:-5}"
+retry_delay="${MOBILEGL_TRACE_FIXTURE_RETRY_DELAY:-2}"
 
 if ! command -v "${python_bin}" >/dev/null 2>&1 && command -v python >/dev/null 2>&1; then
   python_bin=python
 fi
 
+if ! [[ "${download_attempts}" =~ ^[1-9][0-9]*$ ]]; then
+  echo "MOBILEGL_TRACE_FIXTURE_DOWNLOAD_ATTEMPTS must be a positive integer: ${download_attempts}" >&2
+  exit 2
+fi
+if ! [[ "${retry_delay}" =~ ^[0-9]+$ ]]; then
+  echo "MOBILEGL_TRACE_FIXTURE_RETRY_DELAY must be a non-negative integer: ${retry_delay}" >&2
+  exit 2
+fi
+
 fixture_list="$("${python_bin}" tools/trace_replay/trace_cases.py \
   --format fixture-files \
   --case "${case_name}" \
   --fixture-root "${fixture_dir}")"
-mapfile -t files <<< "${fixture_list}"
+# Strip CR so the script also works when python emits CRLF (Git Bash on Windows).
+mapfile -t files < <(printf '%s\n' "${fixture_list}" | tr -d '\r')
 
 include="$(IFS=,; echo "${files[*]}")"
 if [ "${case_name}" = "OpenRA" ]; then
@@ -34,34 +62,185 @@ if [ "${case_name}" = "OpenRA" ]; then
   exit 0
 fi
 
+get_lfs_metadata() {
+  local file="$1"
+  local pointer
+  local expected_oid
+  local expected_size
+
+  if ! pointer="$(git show "HEAD:${file}" 2>/dev/null)"; then
+    echo "failed to read tracked fixture metadata: ${file}" >&2
+    return 1
+  fi
+  if ! grep -q '^version https://git-lfs.github.com/spec/v1$' <<< "${pointer}"; then
+    echo "tracked fixture is not a Git LFS pointer: ${file}" >&2
+    return 1
+  fi
+
+  expected_oid="$(awk '$1 == "oid" && $2 ~ /^sha256:/ { sub(/^sha256:/, "", $2); print $2 }' <<< "${pointer}")"
+  expected_size="$(awk '$1 == "size" { print $2 }' <<< "${pointer}")"
+  if ! [[ "${expected_oid}" =~ ^[0-9a-f]{64}$ ]] || ! [[ "${expected_size}" =~ ^[0-9]+$ ]]; then
+    echo "invalid Git LFS pointer metadata: ${file}" >&2
+    return 1
+  fi
+
+  printf '%s %s\n' "${expected_oid}" "${expected_size}"
+}
+
+verify_fixture_file() {
+  local downloaded_file="$1"
+  local display_name="$2"
+  local expected_oid="$3"
+  local expected_size="$4"
+  local actual_oid
+  local actual_size
+
+  if [ ! -f "${downloaded_file}" ]; then
+    echo "fixture file is missing: ${display_name}" >&2
+    return 1
+  fi
+
+  actual_size="$(wc -c < "${downloaded_file}" | tr -d '[:space:]')"
+  if [ "${actual_size}" != "${expected_size}" ]; then
+    echo "fixture size mismatch for ${display_name}: expected ${expected_size}, got ${actual_size}" >&2
+    return 1
+  fi
+
+  actual_oid="$(sha256sum "${downloaded_file}" | awk '{ print $1 }')"
+  if [ "${actual_oid}" != "${expected_oid}" ]; then
+    echo "fixture SHA-256 mismatch for ${display_name}: expected ${expected_oid}, got ${actual_oid}" >&2
+    return 1
+  fi
+}
+
+fetch_file_from_mirror() {
+  local file="$1"
+  local url="$2"
+  local metadata
+  local expected_oid
+  local expected_size
+  local tmp_file="${file}.tmp"
+  local attempt
+  local partial_size
+  local curl_status
+  local curl_auth
+
+  metadata="$(get_lfs_metadata "${file}")" || return 1
+  read -r expected_oid expected_size <<< "${metadata}"
+
+  if [ -f "${tmp_file}" ]; then
+    partial_size="$(wc -c < "${tmp_file}" | tr -d '[:space:]')"
+    if [ "${partial_size}" -gt "${expected_size}" ]; then
+      echo "Discarding oversized partial fixture ${tmp_file}: ${partial_size} > ${expected_size}" >&2
+      rm -f "${tmp_file}"
+    elif [ "${partial_size}" = "${expected_size}" ]; then
+      if verify_fixture_file "${tmp_file}" "${file}" "${expected_oid}" "${expected_size}"; then
+        mv "${tmp_file}" "${file}"
+        return 0
+      fi
+      rm -f "${tmp_file}"
+    fi
+  fi
+
+  for ((attempt = 1; attempt <= download_attempts; attempt++)); do
+    partial_size=0
+    if [ -f "${tmp_file}" ]; then
+      partial_size="$(wc -c < "${tmp_file}" | tr -d '[:space:]')"
+    fi
+
+    if [ "${partial_size}" -gt 0 ]; then
+      echo "Resuming mirror download for ${file} at byte ${partial_size} (attempt ${attempt}/${download_attempts})"
+    else
+      echo "Starting mirror download for ${file} (attempt ${attempt}/${download_attempts})"
+    fi
+
+    curl_auth=()
+    if [ -n "${mirror_token}" ]; then
+      curl_auth=(--header "Authorization: token ${mirror_token}")
+    fi
+    if curl -L --fail --show-error --continue-at - "${curl_auth[@]}" --output "${tmp_file}" "${url}"; then
+      if verify_fixture_file "${tmp_file}" "${file}" "${expected_oid}" "${expected_size}"; then
+        mv "${tmp_file}" "${file}"
+        return 0
+      fi
+      echo "Mirror download failed integrity verification; retrying from the beginning: ${file}" >&2
+      rm -f "${tmp_file}"
+    else
+      curl_status=$?
+      partial_size=0
+      if [ -f "${tmp_file}" ]; then
+        partial_size="$(wc -c < "${tmp_file}" | tr -d '[:space:]')"
+      fi
+
+      if [ "${partial_size}" = "${expected_size}" ]; then
+        if verify_fixture_file "${tmp_file}" "${file}" "${expected_oid}" "${expected_size}"; then
+          mv "${tmp_file}" "${file}"
+          return 0
+        fi
+        rm -f "${tmp_file}"
+        partial_size=0
+      elif [ "${partial_size}" -gt "${expected_size}" ]; then
+        echo "Discarding oversized partial fixture ${tmp_file}: ${partial_size} > ${expected_size}" >&2
+        rm -f "${tmp_file}"
+        partial_size=0
+      elif [ "${curl_status}" -eq 33 ]; then
+        echo "Mirror refused the resume request; retrying from the beginning: ${file}" >&2
+        rm -f "${tmp_file}"
+        partial_size=0
+      fi
+
+      echo "Mirror download attempt ${attempt}/${download_attempts} failed with curl exit ${curl_status}; retained ${partial_size} bytes for resume: ${file}" >&2
+    fi
+
+    if [ "${attempt}" -lt "${download_attempts}" ]; then
+      sleep "${retry_delay}"
+    fi
+  done
+
+  rm -f "${tmp_file}"
+  return 1
+}
+
+# Files no mirror could serve, even after retrying every mirror. Only these fall
+# back to Git LFS, so a mirror that served the rest of the case still spares
+# GitHub the bandwidth for those files.
+mirror_failures=()
+
 fetch_from_mirror() {
   mkdir -p "${fixture_dir}"
   for file in "${files[@]}"; do
     local name
     local url
+    local base
+    local fetched=0
     name="$(basename "${file}")"
-    url="${mirror_base%/}/${name}"
-    echo "Fetching trace fixture from mirror: ${url}"
-    if ! curl -L --fail --retry 3 --retry-delay 2 -o "${file}.tmp" "${url}"; then
-      rm -f "${file}.tmp"
-      return 1
+    for base in "${mirror_bases[@]}"; do
+      url="${base%/}/${name}"
+      echo "Fetching trace fixture from mirror: ${url}"
+      if fetch_file_from_mirror "${file}" "${url}"; then
+        fetched=1
+        break
+      fi
+      echo "Mirror did not serve ${name}; trying the next mirror" >&2
+    done
+    if [ "${fetched}" -ne 1 ]; then
+      mirror_failures+=("${file}")
     fi
-    mv "${file}.tmp" "${file}"
   done
+  [ "${#mirror_failures[@]}" -eq 0 ]
 }
 
 if fetch_from_mirror; then
   echo "Fetched trace fixture files for ${case_name} from mirror: ${include}"
 else
-  echo "Mirror fetch failed for ${case_name}; falling back to Git LFS: ${include}"
+  fallback_include="$(IFS=,; echo "${mirror_failures[*]}")"
+  echo "All mirrors failed for ${#mirror_failures[@]} of ${#files[@]} file(s) of ${case_name}; falling back to Git LFS: ${fallback_include}"
   git lfs install --local
-  git lfs pull --include="${include}" --exclude=""
+  git lfs pull --include="${fallback_include}" --exclude=""
 fi
 
 for file in "${files[@]}"; do
-  test -s "${file}"
-  if head -n 1 "${file}" | grep -q "version https://git-lfs.github.com/spec/v1"; then
-    echo "failed to hydrate LFS fixture: ${file}" >&2
-    exit 1
-  fi
+  metadata="$(get_lfs_metadata "${file}")"
+  read -r expected_oid expected_size <<< "${metadata}"
+  verify_fixture_file "${file}" "${file}" "${expected_oid}" "${expected_size}"
 done

.github/workflows/apk.yml

@@ -227,6 +227,8 @@ jobs:
     env:
       AVD_NAME: mobilegl-ci
       ANDROID_AVD_HOME: ${{ github.workspace }}/.android/avd
+      ANDROID_HOME: ${{ github.workspace }}/.android/sdk
+      ANDROID_SDK_ROOT: ${{ github.workspace }}/.android/sdk
     steps:
       - name: Checkout repo
         uses: actions/checkout@v6
@@ -245,11 +247,11 @@ jobs:
         with:
           path: |
             ${{ env.ANDROID_AVD_HOME }}
-            /usr/local/lib/android/sdk/emulator
-            /usr/local/lib/android/sdk/platform-tools
-            /usr/local/lib/android/sdk/platforms/android-35
-            /usr/local/lib/android/sdk/system-images/android-35/google_apis/x86_64
-          key: ${{ runner.os }}-mobilegl-avd-api35-google_apis-x86_64-pixel_6-v1-${{ hashFiles('android-plugin/run-avd-ci.sh') }}
+            ${{ env.ANDROID_SDK_ROOT }}/emulator
+            ${{ env.ANDROID_SDK_ROOT }}/platform-tools
+            ${{ env.ANDROID_SDK_ROOT }}/platforms/android-35
+            ${{ env.ANDROID_SDK_ROOT }}/system-images/android-35/google_apis/x86_64
+          key: ${{ runner.os }}-mobilegl-avd-api35-google_apis-x86_64-pixel_6-v2-${{ hashFiles('android-plugin/run-avd-ci.sh') }}
 
       - name: Create AVD
         if: steps.android-avd-cache.outputs.cache-hit != 'true'
@@ -274,6 +276,8 @@ jobs:
     env:
       AVD_NAME: mobilegl-ci
       ANDROID_AVD_HOME: ${{ github.workspace }}/.android/avd
+      ANDROID_HOME: ${{ github.workspace }}/.android/sdk
+      ANDROID_SDK_ROOT: ${{ github.workspace }}/.android/sdk
     strategy:
       fail-fast: false
       max-parallel: 4
@@ -288,7 +292,7 @@ jobs:
       - name: Set Swap Space
         uses: pierotofy/set-swap-space@v1.0
         with:
-          swap-size-gb: 16
+          swap-size-gb: 8
 
       - name: Checkout repo
         uses: actions/checkout@v6
@@ -324,11 +328,11 @@ jobs:
         with:
           path: |
             ${{ env.ANDROID_AVD_HOME }}
-            /usr/local/lib/android/sdk/emulator
-            /usr/local/lib/android/sdk/platform-tools
-            /usr/local/lib/android/sdk/platforms/android-35
-            /usr/local/lib/android/sdk/system-images/android-35/google_apis/x86_64
-          key: ${{ runner.os }}-mobilegl-avd-api35-google_apis-x86_64-pixel_6-v1-${{ hashFiles('android-plugin/run-avd-ci.sh') }}
+            ${{ env.ANDROID_SDK_ROOT }}/emulator
+            ${{ env.ANDROID_SDK_ROOT }}/platform-tools
+            ${{ env.ANDROID_SDK_ROOT }}/platforms/android-35
+            ${{ env.ANDROID_SDK_ROOT }}/system-images/android-35/google_apis/x86_64
+          key: ${{ runner.os }}-mobilegl-avd-api35-google_apis-x86_64-pixel_6-v2-${{ hashFiles('android-plugin/run-avd-ci.sh') }}
 
       - name: Download retrace APK
         uses: actions/download-artifact@v8
@@ -378,27 +382,51 @@ jobs:
           if [ "${{ matrix.case.coherent_as_flush || false }}" = "true" ]; then
             extra_retrace_args+=(--coherent-as-flush)
           fi
-          timeout "$(( ${{ matrix.case.timeout_seconds }} + 300 ))" sh android-plugin/trace-replay-ci.sh \
-            --apk-file "${apk_file}" \
-            --package top.mobilegl.plugin.trace \
-            --backend "${{ matrix.backend.name }}" \
-            --result-root android-retrace-result \
-            --fixture-root android-retrace-fixture \
-            --case "${{ matrix.case.name }}" \
-            --trace-archive "${{ matrix.case.trace_archive }}" \
-            --trace-file "${{ matrix.case.trace_file }}" \
-            --golden "${{ matrix.case.golden }}" \
-            --alternate-golden "${{ matrix.case.alternate_golden || '' }}" \
-            --target-call "${{ matrix.case.target_call }}" \
-            --width "${{ matrix.case.width }}" \
-            --height "${{ matrix.case.height }}" \
-            --ssim-threshold "${{ matrix.case.ssim_threshold || '0.99' }}" \
-            --crop-x "${{ matrix.case.crop_x }}" \
-            --crop-y "${{ matrix.case.crop_y }}" \
-            --crop-width "${{ matrix.case.crop_width }}" \
-            --crop-height "${{ matrix.case.crop_height }}" \
-            --timeout-seconds "${{ matrix.case.timeout_seconds }}" \
-            "${extra_retrace_args[@]}"
+
+          run_retrace() {
+            timeout "$(( ${{ matrix.case.timeout_seconds }} + 300 ))" sh android-plugin/trace-replay-ci.sh \
+              --apk-file "${apk_file}" \
+              --package top.mobilegl.plugin.trace \
+              --backend "${{ matrix.backend.name }}" \
+              --result-root android-retrace-result \
+              --fixture-root android-retrace-fixture \
+              --case "${{ matrix.case.name }}" \
+              --trace-archive "${{ matrix.case.trace_archive }}" \
+              --trace-file "${{ matrix.case.trace_file }}" \
+              --golden "${{ matrix.case.golden }}" \
+              --alternate-golden "${{ matrix.case.alternate_golden || '' }}" \
+              --target-call "${{ matrix.case.target_call }}" \
+              --width "${{ matrix.case.width }}" \
+              --height "${{ matrix.case.height }}" \
+              --ssim-threshold "${{ matrix.case.ssim_threshold || '0.99' }}" \
+              --crop-x "${{ matrix.case.crop_x }}" \
+              --crop-y "${{ matrix.case.crop_y }}" \
+              --crop-width "${{ matrix.case.crop_width }}" \
+              --crop-height "${{ matrix.case.crop_height }}" \
+              --timeout-seconds "${{ matrix.case.timeout_seconds }}" \
+              "${extra_retrace_args[@]}"
+          }
+
+          retrace_status=0
+          run_retrace || retrace_status=$?
+          if [ "${retrace_status}" -eq 75 ]; then
+            echo "::warning::Android emulator infrastructure failed; restarting it and retrying this retrace once."
+            sh android-plugin/run-avd-ci.sh stop \
+              --avd-name "${AVD_NAME}" \
+              --emulator-log "${EMULATOR_LOG}" \
+              --pid-file "${EMULATOR_PID_FILE}"
+            adb kill-server || true
+            sleep 2
+            sh android-plugin/run-avd-ci.sh start \
+              --avd-name "${AVD_NAME}" \
+              --gpu "${{ matrix.backend.gpu }}" \
+              --emulator-log "${EMULATOR_LOG}" \
+              --pid-file "${EMULATOR_PID_FILE}" \
+              --boot-timeout 300
+            run_retrace
+          elif [ "${retrace_status}" -ne 0 ]; then
+            exit "${retrace_status}"
+          fi
 
       - name: Collect retrace summary inputs
         if: always()

.github/workflows/test.yml

@@ -107,6 +107,7 @@ jobs:
             --exclude='build.ninja' \
             --exclude='cmake_install.cmake' \
             -czf ci-artifacts/mobilegl-linux-runtime.tgz \
+            "${BUILD_DIR}/CTestTestfile.cmake" \
             "${BUILD_DIR}/MobileGL/MG_Test" \
             "${BUILD_DIR}/MobileGL/MG_Benchmark" \
             "${SHARED_LIBS[@]}"
@@ -156,12 +157,12 @@ jobs:
           PY
 
       - name: Test
-        working-directory: build-linux/MobileGL/MG_Test
+        working-directory: build-linux
         run: |
           if [ "${{ secrets.ACTIONS_STEP_DEBUG }}" = "true" ]; then
-            ctest -V
+            ctest -V -L unit --no-tests=error
           else
-            ctest --output-on-failure
+            ctest --output-on-failure -L unit --no-tests=error
           fi
 
   benchmark:
@@ -176,9 +177,13 @@ jobs:
         uses: lukka/get-cmake@v4.3.3
 
       - name: Install runtime dependencies
+        # libegl-mesa0 is the EGL vendor library itself: DriverBench brings up a
+        # real GL context, and libegl1 is only glvnd's dispatch. It normally
+        # arrives as a Recommends of libegl1, which is too quiet a dependency for
+        # the one job that needs a working driver.
         run: |
           sudo apt-get update
-          sudo apt-get install -y libvulkan1 libegl1 libgles2 libgl1-mesa-dri mesa-vulkan-drivers
+          sudo apt-get install -y libvulkan1 libegl1 libegl-mesa0 libgles2 libgl1-mesa-dri mesa-vulkan-drivers
 
       - name: Download Linux runtime
         uses: actions/download-artifact@v8
@@ -202,8 +207,8 @@ jobs:
           PY
 
       - name: Benchmark
-        working-directory: build-linux/MobileGL/MG_Benchmark
-        run: ctest -V -C Release
+        working-directory: build-linux
+        run: ctest -V -C Release -L benchmark --no-tests=error
 
   build-retrace:
     runs-on: ubuntu-latest
@@ -454,6 +459,15 @@ jobs:
           if [ '${{ matrix.backend }}' = 'DirectVulkan' ]; then
             export MOBILEGL_MAGMA_R11G11B10F_FALLBACK=1
           fi
+          # The blended depth-write quirk auto-enables only on Qualcomm, which no CI
+          # runner has, so force it on for the OIT case it exists to fix. ForceOn
+          # bypasses only the vendor gate, so this exercises the real strip on
+          # lavapipe. The Android AVD lane deliberately leaves it off, keeping the
+          # unstripped path covered for the same trace.
+          if [ '${{ matrix.backend }}' = 'DirectVulkan' ] \
+             && [ '${{ matrix.case }}' = 'improved-transparency-minecraft-26.3' ]; then
+            export MOBILEGL_MAGMA_DISABLE_BLENDED_DEPTH_WRITE=1
+          fi
           ctest -V --no-tests=error -R '^MobileGLTraceReplay\.${{ matrix.case }}\.${{ matrix.backend }}$'
 
       - name: Upload actual image

.gitignore

@@ -25,3 +25,5 @@ MobileGL/MG*/cmake-build*
 /android-plugin/app/src/trace/jniLibs
 /android-plugin/local.properties
 tools/trace_replay/work/
+__pycache__/
+*.py[cod]

.gitmodules

@@ -31,3 +31,9 @@
 [submodule "3rdparty/apitrace"]
 	path = 3rdparty/apitrace
 	url = https://github.com/MobileGL-Dev/apitrace.git
+[submodule "3rdparty/asio"]
+	path = 3rdparty/asio
+	url = https://github.com/chriskohlhoff/asio.git
+[submodule "3rdparty/libfork"]
+	path = 3rdparty/libfork
+	url = https://github.com/ConorWilliams/libfork.git

CMakeLists.txt

@@ -4,6 +4,11 @@ project("MobileGL")
 
 option(MOBILEGL_BUILD_TEST        "Build MobileGL tests"                             ON )
 option(MOBILEGL_BUILD_BENCHMARK   "Build MobileGL benchmarks"                        ON )
+# Headless end-to-end GPU scenarios (MobileGL/MG_IntegrationTest). They need a
+# real GPU/ICD to do anything, so they are off by default for CI; every scenario
+# skips cleanly where there is none. Registered under the `integration-gpu`
+# ctest label so a run can select or exclude them.
+option(MOBILEGL_BUILD_INTEGRATION_TEST "Build MobileGL headless GPU integration tests" OFF)
 option(MOBILEGL_FORCE_RELEASE_OPT "Enable Release optimization flags in Debug build" ON )
 option(MOBILEGL_ENABLE_TRACY      "Enable tracy for profiling"                       OFF)
 option(MOBILEGL_BUILD_TRACE_REPLAY "Build desktop apitrace replay runner"            OFF)
@@ -17,7 +22,9 @@ if (ANDROID)
     set(MOBILEGL_BUILD_BENCHMARK  OFF CACHE BOOL "Build MobileGL benchmarks" FORCE)
 endif()
 
-if (NOT CMAKE_BUILD_TYPE STREQUAL "Debug" OR MOBILEGL_FORCE_RELEASE_OPT)
+option(MOBILEGL_ENABLE_LTO "Build with ThinLTO/IPO" OFF)
+
+if ((NOT CMAKE_BUILD_TYPE STREQUAL "Debug" OR MOBILEGL_FORCE_RELEASE_OPT) AND MOBILEGL_ENABLE_LTO)
     # Check if ThinLTO or LTO is suppported
     include(CheckIPOSupported)
     include(CheckCCompilerFlag)
@@ -147,6 +154,9 @@ set(SOURCE_FILES
 
     MobileGL/MG_Util/Debug/Log.cpp
 
+    MobileGL/MG_Util/Async/JobNode.cpp
+    MobileGL/MG_Util/Async/ShaderCompilePool.cpp
+
     MobileGL/MG_Util/Math/VectorTypes.cpp
     MobileGL/MG_Util/Metrics/TextureMetrics.cpp
 
@@ -180,6 +190,7 @@ set(SOURCE_FILES
 
     MobileGL/MG_Util/Classifiers/TextureEnumClassifier.cpp
 
+    MobileGL/MG_Util/ShaderTranspiler/CompileEnv.cpp
     MobileGL/MG_Util/ShaderTranspiler/ShaderCompiler.cpp
     MobileGL/MG_Util/ShaderTranspiler/SpvcSession.cpp
     MobileGL/MG_Util/ShaderTranspiler/ShaderSourceProcessor.cpp
@@ -187,9 +198,16 @@ set(SOURCE_FILES
     MobileGL/MG_Util/ShaderTranspiler/SpirvPasses/FlattenInterfaceStructPass.cpp
     MobileGL/MG_Util/ShaderTranspiler/SpirvPasses/EliminateFloatEqualsZeroPass.cpp
     MobileGL/MG_Util/ShaderTranspiler/SpirvPasses/RenameSamplerFunctionParameterPass.cpp
+    MobileGL/MG_Util/ShaderTranspiler/SpirvPasses/RenameBuiltinShadowingFunctionsPass.cpp
     MobileGL/MG_Util/ShaderTranspiler/SpirvPasses/DecomposeWorkgroupVec3Pass.cpp
+    MobileGL/MG_Util/ShaderTranspiler/SpirvPasses/DecoratePositionInvariantPass.cpp
     MobileGL/MG_Util/ShaderTranspiler/SpirvPasses/LowerDrawParametersPass.cpp
+    MobileGL/MG_Util/ShaderTranspiler/SpirvPasses/PackDoubleVertexInputsPass.cpp
     MobileGL/MG_Util/ShaderTranspiler/SpirvPasses/RebaseInstanceIndexPass.cpp
+    MobileGL/MG_Util/ShaderTranspiler/SpirvPasses/NormalizeRectCoordinatesPass.cpp
+    MobileGL/MG_Util/ShaderTranspiler/SpirvPasses/StripUboMemberRelaxedPrecisionPass.cpp
+    MobileGL/MG_Util/ShaderTranspiler/SpirvPasses/StripNoPerspectivePass.cpp
+    MobileGL/MG_Util/ShaderTranspiler/SpirvPasses/EmulateNoPerspectivePass.cpp
 
     MobileGL/MG_Util/BackendLoaders/OpenGL/Loader.cpp
     MobileGL/MG_Util/BackendLoaders/Vulkan/Loader.cpp
@@ -200,6 +218,7 @@ set(SOURCE_FILES
     MobileGL/MG_Util/Texture/TextureFormatProcessor.cpp
 
     MobileGL/MG_Impl/GLXImpl/Exporting/Definitions.cpp
+    MobileGL/MG_Impl/GLXImpl/GLXImpl.cpp
     MobileGL/MG_Impl/GLXImpl/LookUp/LookUp.cpp
 
     MobileGL/MG_Impl/EGLImpl/Exporting/Definitions.cpp
@@ -213,6 +232,8 @@ set(SOURCE_FILES
     MobileGL/MG_Impl/GLImpl/Framebuffer/Validators.cpp
     MobileGL/MG_Impl/GLImpl/Framebuffer/GL_Framebuffer.cpp
     MobileGL/MG_Impl/GLImpl/Program/GL_Program.cpp
+    MobileGL/MG_Impl/GLImpl/Program/ProgramInterface.cpp
+    MobileGL/MG_Impl/GLImpl/Program/GL_ProgramPipeline.cpp
     MobileGL/MG_Impl/GLImpl/Texture/GL_Texture.cpp
     MobileGL/MG_Impl/GLImpl/Texture/Validators.cpp
     MobileGL/MG_Impl/GLImpl/Texture/ProxyTexture.cpp
@@ -235,6 +256,7 @@ set(SOURCE_FILES
     MobileGL/MG_Backend/DirectGLES/BackendObject_DirectGLES.cpp
     MobileGL/MG_Backend/DirectGLES/Utils.cpp
     MobileGL/MG_Backend/DirectGLES/Managers.cpp
+    MobileGL/MG_Backend/DirectGLES/MultiDraw.cpp
 
     MobileGL/MG_Backend/DirectVulkan/DirectVulkan.cpp
     MobileGL/MG_Backend/DirectVulkan/BackendObject_DirectVulkan.cpp
@@ -273,7 +295,11 @@ set(SOURCE_FILES
     MobileGL/MG_State/GLState/TextureState/TextureUnit.cpp
     MobileGL/MG_State/GLState/TextureState/TextureState.cpp
     MobileGL/MG_State/GLState/ProgramState/ProgramObject.cpp
+    MobileGL/MG_State/GLState/ProgramState/ProgramLinkTask.cpp
+    MobileGL/MG_State/GLState/ProgramState/ShaderCompileTask.cpp
     MobileGL/MG_State/GLState/ProgramState/ShaderObject.cpp
+    MobileGL/MG_State/GLState/ProgramState/ShaderPreprocessCache.cpp
+    MobileGL/MG_State/GLState/ProgramState/ShaderCompileAdoptionMap.cpp
     MobileGL/MG_State/GLState/ProgramState/ProgramState.cpp
     MobileGL/MG_State/GLState/RenderState/RenderState.cpp
     MobileGL/MG_State/GLState/FramebufferState/FramebufferObject.cpp
@@ -296,9 +322,22 @@ endif()
 if (ANDROID)
     list(APPEND SOURCE_FILES
         MobileGL/MG_Util/SelfTest/DriverPostJni.cpp
+        MobileGL/MG_Util/SelfTest/DriverBenchJni.cpp
     )
 endif()
 
+if (WIN32)
+    list(APPEND SOURCE_FILES
+        MobileGL/MG_Impl/WGLImpl/WGLImpl.cpp
+        MobileGL/MG_Impl/WGLImpl/Exporting/Definitions.cpp
+    )
+endif()
+
+# The shader-compile pool runs standalone Asio on real threads. This host's glibc (>= 2.34)
+# merged pthread into libc, so it links without asking, but the NDK and musl are not
+# guaranteed to be as forgiving - ask for it explicitly rather than rely on the accident.
+find_package(Threads REQUIRED)
+
 set(MOBILEGL_LINK_LIBRARIES
         glslang::glslang
         spirv-cross-c
@@ -308,12 +347,17 @@ set(MOBILEGL_LINK_LIBRARIES
         GPUOpen::VulkanMemoryAllocator
         Vulkan::UtilityHeaders
         spirv-reflect-static
+        Threads::Threads
 )
 
 set(MOBILEGL_COMPILE_DEF
         -DVMA_STATIC_VULKAN_FUNCTIONS=0
         -DVMA_DYNAMIC_VULKAN_FUNCTIONS=1
         -DVMA_VULKAN_VERSION=1001000
+        # Header-only Asio, no Boost, no deprecated interfaces. Set on the definition list
+        # rather than per-target so the shared library and the _s static target agree.
+        -DASIO_STANDALONE
+        -DASIO_NO_DEPRECATED
 )
 
 message(STATUS "MOBILEGL_COMPILE_DEF=${MOBILEGL_COMPILE_DEF}")
@@ -325,12 +369,31 @@ set(MOBILEGL_INCLUDE_DIR
         ${spirv-tools_SOURCE_DIR}/include
         ${spirv-tools_BINARY_DIR}
         ${SPIRV-Headers_SOURCE_DIR}/include
+        # Header-only submodule: no add_subdirectory, no link target. Only
+        # MG_Util/Async/ShaderCompilePool.cpp includes it, and it stays behind that file's
+        # pimpl so no consumer target needs this path.
+        ${CMAKE_SOURCE_DIR}/3rdparty/asio/asio/include
+        # The second shader-compile execution engine (MOBILEGL_ASYNC_POOL=libfork), on the
+        # same terms as Asio above: header-only, no add_subdirectory (its CMakeLists only
+        # declares an INTERFACE target plus install/test scaffolding we do not want), no link
+        # target, and reachable from exactly one translation unit. libfork's own
+        # target_compile_features asks for cxx_std_23, which this project already sets
+        # globally, so its C++20 coroutines need no per-source standard override.
+        ${CMAKE_SOURCE_DIR}/3rdparty/libfork/include
 )
 
-add_library(${CMAKE_PROJECT_NAME} SHARED 
+add_library(${CMAKE_PROJECT_NAME} SHARED
     ${SOURCE_FILES}
 )
 
+if (WIN32)
+    # The wgl* entry points are exported via .def (see the comment in wgl.def);
+    # only the shared library links it.
+    target_sources(${CMAKE_PROJECT_NAME} PRIVATE
+        MobileGL/MG_Impl/WGLImpl/Exporting/wgl.def
+    )
+endif()
+
 if (CMAKE_BUILD_TYPE STREQUAL "Debug")
     set_target_properties(${CMAKE_PROJECT_NAME} PROPERTIES
         C_VISIBILITY_PRESET default
@@ -373,6 +436,18 @@ if(UNIX AND NOT APPLE AND NOT ANDROID)
     endforeach()
 endif()
 
+if(WIN32)
+    # Drop-in for the classic GL loader path: a copy named opengl32.dll placed
+    # next to a host executable is what LoadLibrary("opengl32.dll") and gdi32's
+    # pixel-format forwarding will resolve.
+    add_custom_command(TARGET ${CMAKE_PROJECT_NAME} POST_BUILD
+        COMMAND ${CMAKE_COMMAND} -E copy_if_different
+                "$<TARGET_FILE:${CMAKE_PROJECT_NAME}>"
+                "$<TARGET_FILE_DIR:${CMAKE_PROJECT_NAME}>/opengl32.dll"
+        COMMENT "Creating opengl32.dll drop-in copy"
+    )
+endif()
+
 if(NOT ANDROID)
     add_library(${CMAKE_PROJECT_NAME}_s STATIC 
         ${SOURCE_FILES}
@@ -424,8 +499,21 @@ if (ANDROID)
 endif()
 
 if (APPLE AND NOT MOBILEGL_IOS)
+    # MobileGL statically embeds glslang, SPIRV-Tools, and SPIRV-Cross. When
+    # this dylib is injected with DYLD_INSERT_LIBRARIES, exporting those C++
+    # symbols interposes incompatible copies embedded by host libraries such
+    # as shaderc. Keep only the public GL/EGL/CGL loader surface globally
+    # visible; GetProcAddress can still return pointers to hidden internals.
+    set(MOBILEGL_MACOS_EXPORTED_SYMBOLS
+        "${CMAKE_CURRENT_SOURCE_DIR}/MobileGL/MG_Impl/DyldInterpose/ExportedSymbols.txt")
+    target_link_options(${CMAKE_PROJECT_NAME} PRIVATE
+        "LINKER:-exported_symbols_list,${MOBILEGL_MACOS_EXPORTED_SYMBOLS}")
+    set_property(TARGET ${CMAKE_PROJECT_NAME} APPEND PROPERTY
+        LINK_DEPENDS "${MOBILEGL_MACOS_EXPORTED_SYMBOLS}")
+
     target_link_libraries(${CMAKE_PROJECT_NAME} PUBLIC
         "-framework Cocoa"
+        "-framework CoreVideo"
         "-framework QuartzCore"
         "-framework Foundation"
         "-framework OpenGL"
@@ -433,6 +521,7 @@ if (APPLE AND NOT MOBILEGL_IOS)
     if(TARGET ${CMAKE_PROJECT_NAME}_s)
         target_link_libraries(${CMAKE_PROJECT_NAME}_s PUBLIC
             "-framework Cocoa"
+            "-framework CoreVideo"
             "-framework QuartzCore"
             "-framework Foundation"
             "-framework OpenGL"
@@ -475,16 +564,30 @@ if (NOT ANDROID AND NOT MOBILEGL_IOS)
 endif ()
 
 if (NOT ANDROID)
+    # Enable testing in the top-level scope so a CTestTestfile.cmake is emitted
+    # at the build-tree root. This lets `ctest` be invoked from the top-level
+    # build directory (IDE "run all tests", CI) and discover every test in the
+    # subdirectories below, instead of having to descend into each
+    # MG_Test/MG_Benchmark subdirectory. Tests are tagged with CTest labels
+    # (unit / benchmark / integration), so e.g. `ctest -L unit` selects just
+    # the unit suite.
+    enable_testing()
+
     if (MOBILEGL_BUILD_TEST)
         add_subdirectory(MobileGL/MG_Test)
     endif()
 
+    # After MG_Test so googletest is already available when the unit tests are
+    # built; the module fetches its own copy when they are not.
+    if (MOBILEGL_BUILD_INTEGRATION_TEST)
+        add_subdirectory(MobileGL/MG_IntegrationTest)
+    endif()
+
     if (MOBILEGL_BUILD_BENCHMARK)
         add_subdirectory(MobileGL/MG_Benchmark)
     endif()
 
     if (MOBILEGL_BUILD_TRACE_REPLAY)
-        enable_testing()
         add_subdirectory(tools/trace_replay)
     endif()
 endif()

MobileGL/Config.h

@@ -14,12 +14,48 @@ namespace MobileGL::MG_Config {
     inline const String ProjectName = "MobileGL";
     inline const String CoreName = "MobileGL Core";
     inline const String CoreVendor = "MobileGL-Dev (BZLZHH, Swung0x48, Tungsten)";
-    inline const Version CoreVersion = {26, 7, 0, "-dev", VersionType::Development};
+    inline const Version CoreVersion = {26, 8, 0, "-dev", VersionType::Development};
     inline const VersionStringFormatAttrib DefaultVersionStringFormatAttrib = {2, 2, 0, true, true};
     inline const Uint64 CacheVersion = 0;
 
     extern BackendType ActiveBackendType;
 
+    // Tri-state override for device-specific quirks: Auto lets the detected device decide,
+    // ForceOn/ForceOff bypass the detection in either direction. ForceOn only bypasses the
+    // device gate - each quirk keeps its structural safety checks.
+    enum class QuirkOverride : Uint8 {
+        Auto = 0,
+        ForceOn,
+        ForceOff,
+    };
+
+    // Preferred DirectVulkan dispatch tier for the glMultiDraw* families. A preference,
+    // never a demand: the renderer clamps it to what the device supports at device
+    // creation, falling down the chain ext -> indirect -> unroll with one log line.
+    enum class MultiDrawMode : Uint8 {
+        Auto = 0, // unset: best supported tier
+        Ext,      // VK_EXT_multi_draw: one vkCmdDrawMultiEXT / vkCmdDrawMultiIndexedEXT
+        Indirect, // multiDrawIndirect feature: one vkCmdDraw*Indirect over a transient command array
+        Unroll,   // one vkCmdDraw* per sub-draw
+    };
+
+    // Preferred DirectGLES emulation tier for glMultiDrawElements(BaseVertex). GLES has no
+    // such entry point in core, so every tier below is an emulation; they differ only in
+    // which driver capability they lean on and how many driver calls a batch costs. Like
+    // the Magma knob this is a preference, clamped at resolution time to what the ES
+    // driver actually supports, with one log line when it falls back.
+    enum class GLESMultiDrawMode : Uint8 {
+        Auto = 0,      // unset: best supported tier
+        Ext,           // one glMultiDrawElementsBaseVertexEXT
+        MultiIndirect, // one glMultiDrawElementsIndirectEXT over a scratch command buffer
+        Indirect,      // one glDrawElementsIndirect per sub-draw over that same buffer
+        BaseVertex,    // one glDrawElementsBaseVertex per sub-draw
+        DrawElements,  // baseVertex folded into a scratch index buffer on the CPU, then plain
+                       // glDrawElements per sub-draw (for drivers with no base-vertex draw at all)
+        Compute,       // a compute shader flattens every sub-draw into one rebased index buffer,
+                       // drawn by a single glDrawElements
+    };
+
     // Feature toggles parsed once from environment variables in MG_ConfigLoader::Init()
     // (ConfigLoader.cpp), before the accepted-env map is destroyed. All Bool fields share
     // one truthy rule: the variable is set, non-empty, not "0", and not "false"
@@ -30,6 +66,12 @@ namespace MobileGL::MG_Config {
     //   - DISPLAY: X11 session variable, not MobileGL configuration.
     //   - MOBILEGL_LOG_FILE_PATH: log-file init runs before MG_ConfigLoader::Init
     //     (see MG_Util/Debug/Log.cpp).
+    //   - MOBILEGL_ASYNC_POOL: a ShaderCompilePool is constructed by binaries that never call
+    //     MobileGL::Initialize() and so never run MG_ConfigLoader::Init - MG_Test's
+    //     JobNodeTest builds pools directly, and it is the suite that runs the whole async
+    //     matrix against both execution engines. Mirroring it here would resolve to the
+    //     default in exactly the tests that exist to tell the engines apart (see
+    //     MG_Util/Async/ShaderCompilePool.cpp, DetectAsyncPoolEngine).
     struct FeaturesTable {
         // MOBILEGL_DISABLE_TIMERQUERY: do not advertise or use GPU timer queries.
         Bool DisableTimerQuery = false;
@@ -61,6 +103,45 @@ namespace MobileGL::MG_Config {
         // per-draw glBufferSubData path instead of the persistent-mapped ring allocator
         // (negative control / driver-bug escape hatch).
         Bool DisableUboRing = false;
+        // MOBILEGL_RELAXED_SEMANTICS: relax strict core-profile rules (e.g. VAO-0 draws,
+        // texture-name reuse after delete) even on contexts that explicitly requested a core
+        // profile. Without it, relaxed semantics still apply to every context that did not
+        // explicitly request a core profile via EGL_CONTEXT_OPENGL_PROFILE_MASK / a >=3.1
+        // version request.
+        Bool RelaxedSemantics = false;
+        // MOBILEGL_QUIRK_SUBGROUP_PREFIX_SCAN: overrides the shader-source quirk that
+        // rewrites the recognized workgroup prefix-scan template on Qualcomm devices with
+        // subgroups wider than 32 lanes (see ShaderSourceProcessor's quirk registry).
+        QuirkOverride SubgroupPrefixScanQuirk = QuirkOverride::Auto;
+        // MOBILEGL_MAGMA_DISABLE_BLENDED_DEPTH_WRITE: overrides the DirectVulkan quirk that
+        // strips depth writes from accumulation-blended pipelines (MIN/MAX or additive
+        // ONE+ONE - the multi-pass depth-equality signature) on drivers without
+        // cross-pipeline vertex position invariance. Sorted-transparency "over" blends,
+        // gl_FragDepth writers, and fully color-masked attachments are exempt (see
+        // PipelineFactory::ShouldSuppressDepthWrite). Auto detects Qualcomm.
+        QuirkOverride MagmaDisableBlendedDepthWriteQuirk = QuirkOverride::Auto;
+        // MOBILEGL_DISABLE_ROBUST_BUFFER_ACCESS: leave the Vulkan robustBufferAccess device
+        // feature off. It is enabled by default to match GL's defined out-of-range fetch
+        // behavior; this escape hatch exists to measure or dodge its GPU cost on a device.
+        Bool DisableRobustBufferAccess = false;
+        // MOBILEGL_MAGMA_MULTIDRAW_MODE: preferred DirectVulkan multi-draw dispatch tier
+        // ("ext" | "indirect" | "unroll", see MultiDrawMode). Clamped to device support;
+        // unset picks the best supported tier.
+        MultiDrawMode MagmaMultiDrawMode = MultiDrawMode::Auto;
+        // MOBILEGL_ESPRYT_MULTIDRAW_MODE: preferred DirectGLES glMultiDrawElements emulation
+        // tier ("ext" | "multiindirect" | "indirect" | "basevertex" | "drawelements" |
+        // "compute", see GLESMultiDrawMode). Clamped to driver support; unset picks the best
+        // supported tier, which never includes "compute" - see the note on its resolution.
+        GLESMultiDrawMode EsprytMultiDrawMode = GLESMultiDrawMode::Auto;
+        // MOBILEGL_ASYNC_SHADER_COMPILE: overrides asynchronous shader compilation. Unset
+        // keeps the built-in default (MG_Util::Async::kAsyncShaderCompileDefault); falsy
+        // forces every glCompileShader/glLinkProgram to run synchronously on the calling
+        // thread AND withdraws GL_KHR_parallel_shader_compile, so the single switch reverts
+        // both the threading and the application-visible behaviour change.
+        QuirkOverride AsyncShaderCompile = QuirkOverride::Auto;
+        // MOBILEGL_ASYNC_SHADER_COMPILE_THREADS: shader-compile worker count. 0 (unset) means
+        // auto, which is min(4, big cores); an explicit value is honoured as given.
+        Uint32 AsyncShaderCompileThreads = 0;
     };
     extern FeaturesTable Features;
 } // namespace MobileGL::MG_Config

MobileGL/ConfigLoader.cpp

@@ -86,6 +86,58 @@ namespace MobileGL::MG_ConfigLoader {
         return it != acceptedEnvVariablesMap->end() && IsTruthyValue(it->second);
     }
 
+    // Quirk overrides are tri-state: an unset variable keeps device auto-detection, a truthy
+    // value forces the quirk on, anything else set ("0", "false", "") forces it off.
+    inline MG_Config::QuirkOverride QueryEnvQuirkOverride(const String& key) {
+        auto it = acceptedEnvVariablesMap->find(key);
+        if (it == acceptedEnvVariablesMap->end()) {
+            return MG_Config::QuirkOverride::Auto;
+        }
+        return IsTruthyValue(it->second) ? MG_Config::QuirkOverride::ForceOn
+                                         : MG_Config::QuirkOverride::ForceOff;
+    }
+
+    // Multi-draw mode is a named-value preference: unset keeps Auto (best supported tier),
+    // a recognized name selects that tier as the ceiling, anything else warns and keeps Auto.
+    inline MG_Config::MultiDrawMode QueryEnvMultiDrawMode(const String& key) {
+        auto it = acceptedEnvVariablesMap->find(key);
+        if (it == acceptedEnvVariablesMap->end()) {
+            return MG_Config::MultiDrawMode::Auto;
+        }
+        String lowered = it->second;
+        std::transform(lowered.begin(), lowered.end(), lowered.begin(),
+                       [](unsigned char c) { return static_cast<char>(std::tolower(c)); });
+        if (lowered == "ext") return MG_Config::MultiDrawMode::Ext;
+        if (lowered == "indirect") return MG_Config::MultiDrawMode::Indirect;
+        if (lowered == "unroll") return MG_Config::MultiDrawMode::Unroll;
+        if (lowered.empty() || lowered == "auto") return MG_Config::MultiDrawMode::Auto;
+        MGLOG_W("Config: Ignoring invalid env variable %s='%s'; expected ext|indirect|unroll|auto, using auto",
+                key.c_str(), it->second.c_str());
+        return MG_Config::MultiDrawMode::Auto;
+    }
+
+    // Same contract as QueryEnvMultiDrawMode, over the DirectGLES tier names.
+    inline MG_Config::GLESMultiDrawMode QueryEnvGLESMultiDrawMode(const String& key) {
+        auto it = acceptedEnvVariablesMap->find(key);
+        if (it == acceptedEnvVariablesMap->end()) {
+            return MG_Config::GLESMultiDrawMode::Auto;
+        }
+        String lowered = it->second;
+        std::transform(lowered.begin(), lowered.end(), lowered.begin(),
+                       [](unsigned char c) { return static_cast<char>(std::tolower(c)); });
+        if (lowered == "ext") return MG_Config::GLESMultiDrawMode::Ext;
+        if (lowered == "multiindirect") return MG_Config::GLESMultiDrawMode::MultiIndirect;
+        if (lowered == "indirect") return MG_Config::GLESMultiDrawMode::Indirect;
+        if (lowered == "basevertex") return MG_Config::GLESMultiDrawMode::BaseVertex;
+        if (lowered == "drawelements") return MG_Config::GLESMultiDrawMode::DrawElements;
+        if (lowered == "compute") return MG_Config::GLESMultiDrawMode::Compute;
+        if (lowered.empty() || lowered == "auto") return MG_Config::GLESMultiDrawMode::Auto;
+        MGLOG_W("Config: Ignoring invalid env variable %s='%s'; expected "
+                "ext|multiindirect|indirect|basevertex|drawelements|compute|auto, using auto",
+                key.c_str(), it->second.c_str());
+        return MG_Config::GLESMultiDrawMode::Auto;
+    }
+
     inline Uint32 QueryEnvUint32(const String& key, Uint32 defaultValue, Uint32 minValue, Uint32 maxValue) {
         auto it = acceptedEnvVariablesMap->find(key);
         if (it == acceptedEnvVariablesMap->end()) {
@@ -122,6 +174,15 @@ namespace MobileGL::MG_ConfigLoader {
         features.CoherentAsFlush = QueryEnvFlag("MOBILEGL_COHERENT_AS_FLUSH");
         features.TraceSkipAutodestroy = QueryEnvFlag("MOBILEGL_TRACE_SKIP_AUTODESTROY");
         features.DisableUboRing = QueryEnvFlag("MOBILEGL_DISABLE_UBO_RING");
+        features.RelaxedSemantics = QueryEnvFlag("MOBILEGL_RELAXED_SEMANTICS");
+        features.SubgroupPrefixScanQuirk = QueryEnvQuirkOverride("MOBILEGL_QUIRK_SUBGROUP_PREFIX_SCAN");
+        features.MagmaDisableBlendedDepthWriteQuirk =
+            QueryEnvQuirkOverride("MOBILEGL_MAGMA_DISABLE_BLENDED_DEPTH_WRITE");
+        features.DisableRobustBufferAccess = QueryEnvFlag("MOBILEGL_DISABLE_ROBUST_BUFFER_ACCESS");
+        features.MagmaMultiDrawMode = QueryEnvMultiDrawMode("MOBILEGL_MAGMA_MULTIDRAW_MODE");
+        features.EsprytMultiDrawMode = QueryEnvGLESMultiDrawMode("MOBILEGL_ESPRYT_MULTIDRAW_MODE");
+        features.AsyncShaderCompile = QueryEnvQuirkOverride("MOBILEGL_ASYNC_SHADER_COMPILE");
+        features.AsyncShaderCompileThreads = QueryEnvUint32("MOBILEGL_ASYNC_SHADER_COMPILE_THREADS", 0, 0, 64);
     }
 
     inline void InitBackendType() {

MobileGL/Defines.h

@@ -34,6 +34,7 @@
 #define MOBILEGL_EGL_API MOBILEGL_API
 #define MOBILEGL_CGL_API MOBILEGL_API
 #define MOBILEGL_NSOPENGL_API MOBILEGL_API
+#define MOBILEGL_WGL_API MOBILEGL_API
 
 // ====================== MobileGL configurations ======================= //
 #ifndef MOBILEGL_LOG_ACTIVE_LEVEL

MobileGL/GlobalObjects.cpp

@@ -14,7 +14,13 @@ namespace MobileGL {
     } // namespace MG_Config
 
     namespace MG_Backend {
-        UniquePtr<BackendObject> pActiveBackendObject;
+        // Leak-at-exit storage: the UniquePtr itself lives on the heap and is
+        // never destroyed by the runtime, so process exit runs no backend
+        // destructors (static destruction order across TUs is undefined).
+        // Deterministic teardown happens inside the EGL lifecycle instead:
+        // the last eglTerminate calls MobileGL::Destroy(), which .reset()s
+        // these singletons while the process is still healthy.
+        UniquePtr<BackendObject>& pActiveBackendObject = *new UniquePtr<BackendObject>();
         GlobalBackendFunctionsTable gBackendFunctionsTable;
     } // namespace MG_Backend
 } // namespace MobileGL

MobileGL/Init.cpp

@@ -9,14 +9,27 @@
 #include "Init.h"
 #include "Config.h"
 #include <MG_Backend/BackendObjects.h>
+#include <MG_Backend/DirectVulkan/DirectVulkan.h>
 #include <MG_State/GLState/Core.h>
 #include <MG_State/EGLState/Core.h>
 #include <MG_Impl/GLImpl/Texture/ProxyTexture.h>
 #include <MG_Impl/GLImpl/Framebuffer/GL_Framebuffer.h>
+#include <MG_Impl/GLImpl/Sync/GL_Sync.h>
+#include <MG_Util/Async/ShaderCompilePool.h>
+#include <MG_Util/ShaderTranspiler/ShaderCompiler.h>
+
+#include <atomic>
+#include <mutex>
 
 namespace MobileGL {
     namespace {
-        Bool g_isInitialized = false;
+        std::atomic<Bool> g_isInitialized = false;
+        thread_local Bool tl_initializing = false;
+
+        std::mutex& InitMutex() {
+            static std::mutex mutex;
+            return mutex;
+        }
 
         void DestroyImpl(Bool logLifecycle) {
             if (!g_isInitialized) {
@@ -26,12 +39,33 @@ namespace MobileGL {
             if (logLifecycle) {
                 MGLOG_I("MobileGL closing...");
             }
-            glslang::FinalizeProcess();
+            // First, before anything else is torn down. In-flight compile/link jobs own
+            // their own inputs and are safe against everything below EXCEPT glslang's
+            // process globals and the TShader/TProgram objects hanging off pGLContext,
+            // both of which this function is about to destroy. This is the one
+            // cancellation path in the whole design that waits.
+            MG_Util::Async::ShaderCompilePool::Get().StopAndDrain();
+            // GL syncs die with their contexts, and every context is gone by the
+            // time full teardown runs: drain the live-sync registry while the
+            // backend function table can still release the backend handles (and
+            // before a re-initialized library could pair them with the wrong
+            // backend's DeleteSync).
+            MG_Impl::GLImpl::DestroyAllSyncObjects();
             MG_Backend::pActiveBackendObject.reset();
             MG_State::pGLContext.reset();
             MG_State::pEGLContext.reset();
             MG_Impl::GLImpl::TextureImpl::pProxyTextureManager.reset();
             MG_Impl::GLImpl::FramebufferImpl::pDefaultFramebufferInfo.reset();
+            // Must run AFTER pGLContext.reset(). FinalizeProcess -> ShFinalize deletes
+            // glslang's process-wide pool allocator and every cached built-in symbol table,
+            // while the TShader/TProgram objects owned by the shader and program objects
+            // still reference levels adopted from those tables. Finalizing first left live
+            // glslang objects pointing at freed memory for the rest of the teardown.
+            glslang::FinalizeProcess();
+            // Immediately after, and never apart from it: FinalizeProcess just deleted the
+            // built-in symbol tables the prewarm latch stands for, so leaving it set would
+            // make the next Initialize() skip a prewarm it genuinely needs.
+            MG_Util::ShaderTranspiler::ShaderCompiler::ResetPrewarmLatch();
             MG_Backend::gBackendFunctionsTable = {};
             g_isInitialized = false;
             if (logLifecycle) {
@@ -59,45 +93,55 @@ namespace MobileGL {
         MG_Impl::Init();
         MGLOG_D("MG_Impl initialized");
         glslang::InitializeProcess();
+        // On the GL thread, before any worker can exist. glslang builds its built-in symbol
+        // tables lazily under a process-wide lock held for the whole build, so without this
+        // the first concurrent compiles of a shaderpack all serialize behind the very first
+        // parse and asynchronous compilation looks like it is doing nothing.
+        //
+        // Gated on the flag, because the problem it solves only exists when there are
+        // workers: with compilation synchronous, nothing ever contends for that lock and the
+        // three throwaway parses buy nothing - they just add to every eglInitialize. Read the
+        // flag here rather than inside PrewarmBuiltins so ShaderCompiler keeps no dependency
+        // on the async subsystem (ProgramUtilTest compiles that file without it).
+        if (MG_Util::Async::AsyncShaderCompileEnabled()) {
+            MG_Util::ShaderTranspiler::ShaderCompiler::PrewarmBuiltins();
+        }
         MGLOG_D("glslang initialized");
         g_isInitialized = true;
         MGLOG_I("MobileGL initialized");
     }
 
+    void EnsureInitialized() {
+        if (g_isInitialized.load(std::memory_order_acquire)) {
+            return;
+        }
+        // Re-entrant call while this thread is already inside Initialize()
+        // (e.g. an init step routing back through a public entry point).
+        if (tl_initializing) {
+            return;
+        }
+        const std::lock_guard<std::mutex> lock(InitMutex());
+        if (g_isInitialized.load(std::memory_order_acquire)) {
+            return;
+        }
+        tl_initializing = true;
+        Initialize();
+        tl_initializing = false;
+    }
+
     void Destroy() {
         DestroyImpl(true);
     }
 
-#if defined(__linux__) || defined(__APPLE__)
-    __attribute__((constructor)) static void AutoInit() {
-        Initialize();
-    }
-
-    __attribute__((destructor)) static void AutoDestroy() {
-        if (MG_Config::Features.TraceSkipAutodestroy) {
-            return;
-        }
-#if defined(__APPLE__)
-        // macOS injected dylibs can run destructors after logging/backend static state is already torn down.
-        return;
-#else
-        DestroyImpl(false);
-#endif
-    }
-#endif
-
-#ifdef _WIN32
-    BOOL WINAPI DllMain(HMODULE hModule, DWORD ul_reason_for_call, LPVOID lpReserved) {
-        switch (ul_reason_for_call) {
-        case DLL_PROCESS_ATTACH:
-            Initialize();
-            break;
-
-        case DLL_PROCESS_DETACH:
-            Destroy();
-            break;
-        }
-        return TRUE;
-    }
-#endif
+    // MobileGL's lifecycle is owned entirely by the host-API layers
+    // (EGL/WGL/CGL): initialization happens lazily on the first entry point
+    // via EnsureInitialized(), and full teardown happens deterministically
+    // when the last EGL display is terminated with nothing current (EGLImpl
+    // calls Destroy()). There is intentionally no backend-initializing static
+    // constructor, no static destructor, and no DllMain: the global singletons
+    // use leak-at-exit storage (see GlobalObjects.cpp), so a process that exits
+    // without eglTerminate simply leaks them to the OS instead of running
+    // backend destructors during static teardown. macOS has a lightweight
+    // dyld constructor that installs NSOpenGL dispatch hooks only; full backend
+    // initialization still enters here from the first hooked CGL context.
 } // namespace MobileGL

MobileGL/Init.h

@@ -11,6 +11,13 @@
 
 namespace MobileGL {
     void Initialize();
+    // Thread-safe, idempotent, and re-entrant wrapper around Initialize().
+    // Host layers (EGL/WGL/CGL entry points) call this lazily on first use so
+    // full backend initialization never depends on ELF/DLL static constructors,
+    // and so a fresh init can follow a full Destroy() (e.g. after the last
+    // eglTerminate). The macOS dyld bootstrap installs only lightweight
+    // NSOpenGL method hooks.
+    void EnsureInitialized();
     void Destroy();
 
     namespace MG_Util::Debug {

MobileGL/MG_Backend/BackendObject.h

@@ -145,6 +145,10 @@ namespace MobileGL {
                                             GLenum buffer, GLint drawbuffer, const GLfloat* value);
             void (*ClearNamedFramebufferfi)(const SharedPtr<MG_State::GLState::FramebufferObject>& framebuffer,
                                             GLenum buffer, GLint drawbuffer, GLfloat depth, GLint stencil);
+            void (*ClearNamedFramebufferiv)(const SharedPtr<MG_State::GLState::FramebufferObject>& framebuffer,
+                                            GLenum buffer, GLint drawbuffer, const GLint* value);
+            void (*ClearNamedFramebufferuiv)(const SharedPtr<MG_State::GLState::FramebufferObject>& framebuffer,
+                                             GLenum buffer, GLint drawbuffer, const GLuint* value);
             void (*BlitFramebuffer)(GLint srcX0, GLint srcY0, GLint srcX1, GLint srcY1, GLint dstX0, GLint dstY0,
                                     GLint dstX1, GLint dstY1, GLbitfield mask, GLenum filter);
             void (*BlitNamedFramebuffer)(const SharedPtr<MG_State::GLState::FramebufferObject>& readFramebuffer,
@@ -177,15 +181,18 @@ namespace MobileGL {
             void (*GetIntegeri_v)(GLenum target, GLuint index, GLint* data);
             void (*GetInteger64i_v)(GLenum target, GLuint index, GLint64* data);
             void (*GetProgramiv)(GLuint program, GLenum pname, GLint* params);
-            void (*GetProgramInterfaceiv)(GLuint program, GLenum programInterface, GLenum pname, GLint* params);
-            GLuint (*GetProgramResourceIndex)(GLuint program, GLenum programInterface, const GLchar* name);
-            void (*GetProgramResourceName)(GLuint program, GLenum programInterface, GLuint index, GLsizei bufSize,
-                                           GLsizei* length, GLchar* name);
-            void (*GetProgramResourceiv)(GLuint program, GLenum programInterface, GLuint index, GLsizei propCount,
-                                         const GLenum* props, GLsizei bufSize, GLsizei* length, GLint* params);
-            GLint (*GetProgramResourceLocation)(GLuint program, GLenum programInterface, const GLchar* name);
-            GLint (*GetProgramResourceLocationIndex)(GLuint program, GLenum programInterface, const GLchar* name);
-            void (*ShaderStorageBlockBinding)(GLuint program, GLuint storageBlockIndex, GLuint storageBlockBinding);
+            // The GL program interface (glGetProgramInterfaceiv / glGetProgramResource*) is NOT
+            // a backend query: it describes the program the application wrote, in the
+            // application's namespace, which neither backend program is in. It is answered
+            // entirely by MG_Impl/GLImpl/Program/ProgramInterface from the frontend reflection.
+            // Takes the block's GL NAME, not glShaderStorageBlockBinding's index. The index
+            // the application passes is the frontend interface-query enumeration's, and no
+            // backend shares that index space: DirectVulkan enumerates SPIR-V descriptor
+            // bindings and DirectGLES asks a real driver about SPIRV-Cross-generated ESSL.
+            // The name is the one coordinate all three agree on, so the frontend resolves the
+            // index against its own enumeration and each backend maps the name to its own.
+            void (*ShaderStorageBlockBinding)(GLuint program, const GLchar* storageBlockName,
+                                              GLuint storageBlockBinding);
             // GL fence sync objects. All entries are optional (may be null); the
             // frontend then falls back to always-signaled sync semantics.
             // FenceSync may itself return null when the backend cannot create a
@@ -220,6 +227,31 @@ namespace MobileGL {
             // and leave the query readable later.
             Bool (*GetQueryResult64)(BackendQueryHandle query, Bool wait, Uint64* outNanoseconds);
             void (*DeleteBackendQuery)(BackendQueryHandle query);
+            // GL_SAMPLES_PASSED occlusion queries (optional; null = unsupported,
+            // the frontend then rejects the target). Results/deletion flow through
+            // GetQueryResult64 / DeleteBackendQuery like timer queries.
+            BackendQueryHandle (*BeginOcclusionQuery)();
+            void (*EndOcclusionQuery)(BackendQueryHandle query);
+            // Transform feedback primitive queries backed by real GPU query pools
+            // (optional; null = frontend falls back to CPU accounting).
+            BackendQueryHandle (*BeginXfbPrimitivesQuery)(Bool generated);
+            void (*EndXfbPrimitivesQuery)(BackendQueryHandle query);
+            // Transform feedback capture spans, for backends whose own GL/ES driver
+            // performs the capture (DirectGLES). Both optional; null means the backend
+            // drives capture from its draw recording instead (DirectVulkan). End is
+            // called while the frontend capture state is still active, so the backend
+            // can still see the capture program and buffer bindings.
+            // GL_PATCH_VERTICES; ES 3.2 spells it the same way.
+            void (*PatchParameteri)(GLenum pname, GLint value);
+            void (*BeginTransformFeedback)(GLenum primitiveMode);
+            void (*EndTransformFeedback)();
+            // ARB_transform_feedback2. A backend that leaves these null keeps the single
+            // implicit capture span the frontend has always modelled; the frontend state
+            // (paused flag, per-object bindings) is tracked either way.
+            void (*PauseTransformFeedback)();
+            void (*ResumeTransformFeedback)();
+            void (*BindTransformFeedback)(GLuint name);
+            void (*DeleteTransformFeedback)(GLuint name);
             Int64 (*GetGpuTimestampNs)(); // glGetInteger64v(GL_TIMESTAMP); 0 if unsupported
         };
         struct GlobalBackendFunctionsTable {
@@ -230,8 +262,26 @@ namespace MobileGL {
             void (*SetSwapInterval)(Int interval);
         };
 
+        // Coarse GPU vendor identity for gating device-specific quirks. Detected from the
+        // Vulkan physical-device vendorID or the GLES GL_VENDOR/GL_RENDERER strings; stays
+        // Unknown when detection is inconclusive, in which case auto-gated quirks stay off.
+        enum class GpuVendorKind : Uint8 {
+            Unknown = 0,
+            Qualcomm,
+            Arm,
+            Nvidia,
+            Amd,
+            Intel,
+            ImgTec,
+            // Software rasterizers (llvmpipe/lavapipe, SwiftShader).
+            Software,
+        };
+
         struct DynamicBackendParameters {
             SizeT UniformBufferOffsetAlignment = 256;
+            // GL_MAX_TEXTURE_MAX_ANISOTROPY_EXT. 1.0 means the backend cannot filter anisotropically,
+            // which is also why the extension is not advertised in that case.
+            Float MaxTextureMaxAnisotropy = 1.0f;
             Float AliasedLineWidthRangeMin = 1.0f;
             Float AliasedLineWidthRangeMax = 1.0f;
             Float SmoothLineWidthRangeMin = 1.0f;
@@ -254,6 +304,13 @@ namespace MobileGL {
             Int MaxIntegerSamples = 1;
             Int MaxSamples = 1;
             Int MaxSampleMaskWords = 1;
+            // Tessellation limits; defaults are the GL 4.0 core minimums.
+            Int MaxPatchVertices = 32;
+            Int MaxTessGenLevel = 64;
+            // GL_MIN/MAX_PROGRAM_TEXTURE_GATHER_OFFSET. Defaults are the GL 4.0 core
+            // minimums, which every ES 3.1 driver also guarantees.
+            Int MinProgramTextureGatherOffset = -8;
+            Int MaxProgramTextureGatherOffset = 7;
             Int MaxTextureImageUnits = 32;
             Int MaxVertexTextureImageUnits = 32;
             Int MaxComputeTextureImageUnits = 32;
@@ -265,10 +322,15 @@ namespace MobileGL {
             Int MaxComputeWorkGroupInvocations = 128;
             Int MaxShaderStorageBufferBindings = 8;
             Int MaxTextureBufferSize = 65536;
+            // GL_TEXTURE_BUFFER_OFFSET_ALIGNMENT; 1 means the offset is unconstrained.
+            Int TextureBufferOffsetAlignment = 1;
             Int MaxUniformBufferBindings = 24;
             Int MaxUniformBlockSize = 16384;
             Int MaxImageUnits = 8;
             Int MaxCombinedImageUniforms = 8;
+            Int MaxVertexImageUniforms = 0;
+            Int MaxGeometryImageUniforms = 0;
+            Int MaxFragmentImageUniforms = 8;
             Int MaxComputeImageUniforms = 8;
             Int MaxDrawBuffers = 8;
             Int MaxColorAttachments = 8;
@@ -279,19 +341,69 @@ namespace MobileGL {
             Float ViewportBoundsRangeMin = 0.0f;
             Float ViewportBoundsRangeMax = 0.0f;
             Int ViewportSubpixelBits = 0;
+            // GL 4.x fragment-interpolation offset limits. These defaults are the
+            // core minimums and are replaced by live GLES/Vulkan device limits.
+            Float MinFragmentInterpolationOffset = -0.5f;
+            // For four fractional bits the greatest required legal offset is
+            // 0.5 - 2^-4 = 0.4375 (GL 4.6 table 23.70).
+            Float MaxFragmentInterpolationOffset = 0.4375f;
+            Int FragmentInterpolationOffsetBits = 4;
             Bool SupportsWideLines = false;
+            // Whether a framebuffer whose depth and stencil attachments are distinct
+            // images can be rendered to. GL only requires support when both refer to the
+            // same image and lets an implementation answer GL_FRAMEBUFFER_UNSUPPORTED
+            // otherwise, which is what DirectVulkan (one combined attachment) and the
+            // real ES drivers behind DirectGLES both do. Defaults to true so a backend
+            // that never sets it keeps the permissive behaviour.
+            Bool SupportsDistinctDepthStencilAttachments = true;
+            // Whether attaching a single layer of a 3D or array texture to a framebuffer actually
+            // renders to that layer. DirectGLES hands the layer straight to
+            // glFramebufferTextureLayer, so it does; DirectVulkan maps a GL layer onto a Vulkan
+            // array layer with no notion of a 3D depth slice, so it does not yet. Defaults to false
+            // so a backend that never sets it gets the conservative answer.
+            // Which layered texture targets this backend can attach ONE layer of to a framebuffer
+            // and then really clear, render and read back that layer. Bit (1u << TextureTarget) is
+            // set for each supported target. Deliberately per target rather than one flag: the three
+            // ways a GL layer maps onto Vulkan are independent capabilities. A 2D or 2D multisample
+            // array layer IS a VkImage array layer and needs nothing extra; a 3D texture's layer is
+            // a z slice, which needs a 2D-array-compatible image and a per-slice clear that
+            // vkCmdClearColorImage cannot express; a cube map array needs an image shape and the
+            // imageCubeArray feature before it can be attached at any layer at all. Defaults to 0 so
+            // a backend that never sets it gets the conservative answer.
+            Uint32 PerLayerFramebufferAttachmentTargets = 0;
+
+            static constexpr Uint32 PerLayerFramebufferAttachmentBit(TextureTarget target) {
+                return (static_cast<Int>(target) >= 0 &&
+                        static_cast<Int>(target) < static_cast<Int>(TextureTarget::TextureTargetCount))
+                           ? (1u << static_cast<Uint32>(target))
+                           : 0u;
+            }
+
+            Bool SupportsPerLayerFramebufferAttachment(TextureTarget target) const {
+                const Uint32 bit = PerLayerFramebufferAttachmentBit(target);
+                return bit != 0 && (PerLayerFramebufferAttachmentTargets & bit) != 0;
+            }
+            // Whether glVertexAttribLFormat / glVertexArrayAttribLFormat can be honoured, i.e.
+            // whether a 64-bit vertex attribute can actually reach a shader unconverted. Detected,
+            // never assumed: DirectVulkan needs VkPhysicalDeviceFeatures::shaderFloat64 (the
+            // attribute travels as its 32-bit word pair, so no VK_FORMAT_R64* is required, but the
+            // bitcast result is Float64); DirectGLES can never have it, ESSL having no fp64 type at
+            // all. Defaults to false so a backend that never sets it gets the conservative answer.
+            Bool SupportsFloat64VertexAttributes = false;
             SizeT MaxShaderStorageBlockSize = 128 * 1024 * 1024;
             Uint32 SubgroupSize = 0;
             Uint32 SubgroupSupportedStages = 0;
             Uint32 SubgroupSupportedFeatures = 0;
             Bool SubgroupQuadOperationsInAllStages = false;
+            GpuVendorKind GpuVendor = GpuVendorKind::Unknown;
         };
 
         enum class WindowBackend {
             Android,
             X11,
             MetalLayer,
-            // TODO: Wayland, Windows, etc.
+            Win32, // Handle is an HWND
+            // TODO: Wayland, etc.
             WindowBackendCount,
             Unknown = -1
         };

MobileGL/MG_Backend/BackendObjects.h

@@ -13,6 +13,6 @@
 #include "DirectVulkan/BackendObject_DirectVulkan.h"
 
 namespace MobileGL::MG_Backend {
-    extern UniquePtr<BackendObject> pActiveBackendObject;
+    extern UniquePtr<BackendObject>& pActiveBackendObject;
     extern GlobalBackendFunctionsTable gBackendFunctionsTable;
 } // namespace MobileGL::MG_Backend

MobileGL/MG_Backend/DirectGLES/BackendObject_DirectGLES.cpp

@@ -18,8 +18,10 @@
 #include <MG_Util/Converters/MGToGL/TextureEnumConverter.h>
 #include <MG_Util/Converters/MGToStr/TextureEnumConverter.h>
 #include <MG_Util/Texture/TextureFormatProcessor.h>
+#include <MG_Util/Async/ShaderCompilePool.h>
 #include <Config.h>
 #include <algorithm>
+#include <cmath>
 #include <format>
 
 namespace MobileGL::MG_Backend::DirectGLES {
@@ -31,8 +33,7 @@ namespace MobileGL::MG_Backend::DirectGLES {
 
         void ClearGLErrors(const MG_External::GLESFunctionsTable& gl) {
             if (!gl.glGetError) return;
-            while (gl.glGetError() != GL_NO_ERROR) {
-            }
+            while (gl.glGetError() != GL_NO_ERROR) {}
         }
 
         Bool CheckNoGLError(const MG_External::GLESFunctionsTable& gl) {
@@ -76,8 +77,7 @@ namespace MobileGL::MG_Backend::DirectGLES {
         }
 
         Bool IsGLESProbeMultisampleTarget(TextureTarget target) {
-            return target == TextureTarget::Texture2DMultisample ||
-                   target == TextureTarget::Texture2DMultisampleArray;
+            return target == TextureTarget::Texture2DMultisample || target == TextureTarget::Texture2DMultisampleArray;
         }
 
         GLenum GetFramebufferAttachment(TextureInternalFormat format) {
@@ -114,8 +114,8 @@ namespace MobileGL::MG_Backend::DirectGLES {
             GLenum normalizedInternalFormat = glFormat;
             GLenum imageFormat = GL_RGBA;
             GLenum imageType = GL_UNSIGNED_BYTE;
-            MG_Util::TextureFormatProcessor::NormalizePixelFormat(
-                glFormat, PixelFormatNormalizeOptionBit::None, &normalizedInternalFormat, &imageFormat, &imageType);
+            MG_Util::TextureFormatProcessor::NormalizePixelFormat(glFormat, PixelFormatNormalizeOptionBit::None,
+                                                                  &normalizedInternalFormat, &imageFormat, &imageType);
             return imageFormat != GL_RED_INTEGER && imageFormat != GL_RG_INTEGER && imageFormat != GL_RGB_INTEGER &&
                    imageFormat != GL_RGBA_INTEGER && !MG_Util::IsDepthFormatInternalFormat(format) &&
                    !MG_Util::IsStencilFormatInternalFormat(format);
@@ -153,9 +153,9 @@ namespace MobileGL::MG_Backend::DirectGLES {
         GLESProbeFormatInfo BuildNativeProbeFormatInfo(GLenum requestedInternalFormat) {
             GLESProbeFormatInfo info;
             info.InternalFormat = requestedInternalFormat;
-            MG_Util::TextureFormatProcessor::NormalizePixelFormat(
-                requestedInternalFormat, PixelFormatNormalizeOptionBit::None, nullptr, &info.ImageFormat,
-                &info.ImageType);
+            MG_Util::TextureFormatProcessor::NormalizePixelFormat(requestedInternalFormat,
+                                                                  PixelFormatNormalizeOptionBit::None, nullptr,
+                                                                  &info.ImageFormat, &info.ImageType);
             return info;
         }
 
@@ -209,6 +209,12 @@ namespace MobileGL::MG_Backend::DirectGLES {
             if (options & PixelFormatNormalizeOptionBit::NoDepthComponent32) {
                 reasons.push_back("GL_DEPTH_COMPONENT32 native probe failed on OpenGL ES");
             }
+            if (options & PixelFormatNormalizeOptionBit::NoThreeChannelRenderTarget) {
+                reasons.push_back("no colour-renderable three-channel format on OpenGL ES");
+            }
+            if (options & PixelFormatNormalizeOptionBit::NoSnorm16RenderTarget) {
+                reasons.push_back("EXT_render_snorm not supported");
+            }
 
             String reason;
             for (SizeT i = 0; i < reasons.size(); ++i) {
@@ -226,20 +232,16 @@ namespace MobileGL::MG_Backend::DirectGLES {
             return MG_Util::ConvertGLEnumToString(internalFormat);
         }
 
-        void LogGLESFormatCaveat(TextureInternalFormat logicalFormat,
-                                 SizeT targetIndex,
+        void LogGLESFormatCaveat(TextureInternalFormat logicalFormat, SizeT targetIndex,
                                  const GLESProbeFormatInfo& fallbackInfo) {
             MGLOG_D("Caveat: %s %s not fully supported. Reason: %s. Fallback: %s",
                     GetFormatCapabilityTargetName(targetIndex).c_str(),
-                    MG_Util::ConvertTextureInternalFormatToString(logicalFormat).c_str(),
-                    fallbackInfo.Reason.c_str(),
+                    MG_Util::ConvertTextureInternalFormatToString(logicalFormat).c_str(), fallbackInfo.Reason.c_str(),
                     ConvertFallbackInternalFormatToString(fallbackInfo.InternalFormat).c_str());
         }
 
-        Bool BuildFallbackProbeFormatInfo(GLenum requestedInternalFormat,
-                                          Flags<PixelFormatNormalizeOptionBit> options,
-                                          Bool forced,
-                                          GLESProbeFormatInfo& outInfo) {
+        Bool BuildFallbackProbeFormatInfo(GLenum requestedInternalFormat, Flags<PixelFormatNormalizeOptionBit> options,
+                                          Bool forced, GLESProbeFormatInfo& outInfo) {
             const Flags<PixelFormatNormalizeOptionBit> applicableOptions =
                 MG_Util::TextureFormatProcessor::GetApplicablePixelFormatNormalizeOptions(requestedInternalFormat,
                                                                                           options);
@@ -254,8 +256,7 @@ namespace MobileGL::MG_Backend::DirectGLES {
             return outInfo.InternalFormat != GL_UNKNOWN_MGL;
         }
 
-        FormatCapabilityFlags BuildTextureCapsFromProbe(TextureInternalFormat logicalFormat,
-                                                        TextureTarget target,
+        FormatCapabilityFlags BuildTextureCapsFromProbe(TextureInternalFormat logicalFormat, TextureTarget target,
                                                         Bool renderable) {
             FormatCapabilityFlags caps = GetTextureFeatureCaps(logicalFormat, target);
             if (renderable) {
@@ -269,16 +270,12 @@ namespace MobileGL::MG_Backend::DirectGLES {
             return caps;
         }
 
-        void AddFullFormatCaps(FormatCapabilityCache& cache,
-                               SizeT targetIndex,
-                               SizeT formatIndex,
+        void AddFullFormatCaps(FormatCapabilityCache& cache, SizeT targetIndex, SizeT formatIndex,
                                FormatCapabilityFlags caps) {
             cache.FullCaps[targetIndex][formatIndex] |= caps;
         }
 
-        Bool AddCaveatFormatCaps(FormatCapabilityCache& cache,
-                                 SizeT targetIndex,
-                                 SizeT formatIndex,
+        Bool AddCaveatFormatCaps(FormatCapabilityCache& cache, SizeT targetIndex, SizeT formatIndex,
                                  FormatCapabilityFlags caps) {
             Bool added = false;
             for (FormatCapability capability : kReportedFormatCapabilities) {
@@ -292,8 +289,7 @@ namespace MobileGL::MG_Backend::DirectGLES {
         }
 
         Int GetGLESFormatMaxSamples(const MG_External::GLESCapabilities& capabilities,
-                                    TextureInternalFormat logicalFormat,
-                                    GLenum imageFormat) {
+                                    TextureInternalFormat logicalFormat, GLenum imageFormat) {
             const Bool isDepth = MG_Util::IsDepthFormatInternalFormat(logicalFormat);
             const Bool isStencil = MG_Util::IsStencilFormatInternalFormat(logicalFormat);
             const Bool isInteger = imageFormat == GL_RED_INTEGER || imageFormat == GL_RG_INTEGER ||
@@ -307,10 +303,8 @@ namespace MobileGL::MG_Backend::DirectGLES {
             return capabilities.MaxColorTextureSamples;
         }
 
-        Bool ProbeFramebufferCompletenessForTexture(const MG_External::GLESFunctionsTable& gl,
-                                                   TextureTarget target,
-                                                   GLuint texture,
-                                                   TextureInternalFormat format) {
+        Bool ProbeFramebufferCompletenessForTexture(const MG_External::GLESFunctionsTable& gl, TextureTarget target,
+                                                    GLuint texture, TextureInternalFormat format) {
             GLuint framebuffer = 0;
             GLint prevFramebuffer = 0;
             if (!gl.glGenFramebuffers || !gl.glBindFramebuffer || !gl.glCheckFramebufferStatus ||
@@ -356,9 +350,44 @@ namespace MobileGL::MG_Backend::DirectGLES {
             return complete;
         }
 
-        Bool ProbeFramebufferCompletenessForRenderbuffer(const MG_External::GLESFunctionsTable& gl,
-                                                        GLuint renderbuffer,
-                                                        TextureInternalFormat format) {
+        // Whether the driver renders to a framebuffer whose depth and stencil come from
+        // two different renderbuffers. GL only requires support when both attachments are
+        // the same image, and ES drivers commonly answer GL_FRAMEBUFFER_UNSUPPORTED here;
+        // reporting COMPLETE from the frontend and then rendering into a framebuffer the
+        // driver refuses leaves the results silently empty.
+        Bool ProbeDistinctDepthStencilAttachments(const MG_External::GLESFunctionsTable& gl) {
+            if (!gl.glGenFramebuffers || !gl.glBindFramebuffer || !gl.glFramebufferRenderbuffer ||
+                !gl.glCheckFramebufferStatus || !gl.glDeleteFramebuffers || !gl.glGenRenderbuffers ||
+                !gl.glBindRenderbuffer || !gl.glRenderbufferStorage || !gl.glDeleteRenderbuffers) {
+                return true;
+            }
+
+            GLint prevFramebuffer = 0, prevRenderbuffer = 0;
+            gl.glGetIntegerv(GL_FRAMEBUFFER_BINDING, &prevFramebuffer);
+            gl.glGetIntegerv(GL_RENDERBUFFER_BINDING, &prevRenderbuffer);
+
+            GLuint framebuffer = 0;
+            GLuint renderbuffers[2] = {0, 0};
+            gl.glGenFramebuffers(1, &framebuffer);
+            gl.glGenRenderbuffers(2, renderbuffers);
+            gl.glBindRenderbuffer(GL_RENDERBUFFER, renderbuffers[0]);
+            gl.glRenderbufferStorage(GL_RENDERBUFFER, GL_DEPTH_COMPONENT16, 4, 4);
+            gl.glBindRenderbuffer(GL_RENDERBUFFER, renderbuffers[1]);
+            gl.glRenderbufferStorage(GL_RENDERBUFFER, GL_STENCIL_INDEX8, 4, 4);
+            gl.glBindFramebuffer(GL_FRAMEBUFFER, framebuffer);
+            gl.glFramebufferRenderbuffer(GL_FRAMEBUFFER, GL_DEPTH_ATTACHMENT, GL_RENDERBUFFER, renderbuffers[0]);
+            gl.glFramebufferRenderbuffer(GL_FRAMEBUFFER, GL_STENCIL_ATTACHMENT, GL_RENDERBUFFER, renderbuffers[1]);
+            const Bool supported = gl.glCheckFramebufferStatus(GL_FRAMEBUFFER) == GL_FRAMEBUFFER_COMPLETE;
+
+            gl.glBindFramebuffer(GL_FRAMEBUFFER, static_cast<GLuint>(prevFramebuffer));
+            gl.glBindRenderbuffer(GL_RENDERBUFFER, static_cast<GLuint>(prevRenderbuffer));
+            gl.glDeleteFramebuffers(1, &framebuffer);
+            gl.glDeleteRenderbuffers(2, renderbuffers);
+            return supported;
+        }
+
+        Bool ProbeFramebufferCompletenessForRenderbuffer(const MG_External::GLESFunctionsTable& gl, GLuint renderbuffer,
+                                                         TextureInternalFormat format) {
             GLuint framebuffer = 0;
             GLint prevFramebuffer = 0;
             if (!gl.glGenFramebuffers || !gl.glBindFramebuffer || !gl.glFramebufferRenderbuffer ||
@@ -425,16 +454,16 @@ namespace MobileGL::MG_Backend::DirectGLES {
                     }
                     break;
                 case TextureTarget::Texture3D:
-                    gl.glTexImage3D(glTarget, 0, static_cast<GLint>(internalFormat), 2, 2, 2, 0, imageFormat,
-                                    imageType, nullptr);
+                    gl.glTexImage3D(glTarget, 0, static_cast<GLint>(internalFormat), 2, 2, 2, 0, imageFormat, imageType,
+                                    nullptr);
                     break;
                 case TextureTarget::Texture2DArray:
-                    gl.glTexImage3D(glTarget, 0, static_cast<GLint>(internalFormat), 2, 2, 1, 0, imageFormat,
-                                    imageType, nullptr);
+                    gl.glTexImage3D(glTarget, 0, static_cast<GLint>(internalFormat), 2, 2, 1, 0, imageFormat, imageType,
+                                    nullptr);
                     break;
                 case TextureTarget::TextureCubeMapArray:
-                    gl.glTexImage3D(glTarget, 0, static_cast<GLint>(internalFormat), 2, 2, 6, 0, imageFormat,
-                                    imageType, nullptr);
+                    gl.glTexImage3D(glTarget, 0, static_cast<GLint>(internalFormat), 2, 2, 6, 0, imageFormat, imageType,
+                                    nullptr);
                     break;
                 default:
                     break;
@@ -455,11 +484,8 @@ namespace MobileGL::MG_Backend::DirectGLES {
             return created;
         }
 
-        Bool ProbeRenderbuffer(const MG_External::GLESFunctionsTable& gl,
-                               GLenum internalFormat,
-                               TextureInternalFormat logicalFormat,
-                               Bool multisample,
-                               Int samples) {
+        Bool ProbeRenderbuffer(const MG_External::GLESFunctionsTable& gl, GLenum internalFormat,
+                               TextureInternalFormat logicalFormat, Bool multisample, Int samples) {
             if (!gl.glGenRenderbuffers || !gl.glBindRenderbuffer || !gl.glDeleteRenderbuffers) {
                 return false;
             }
@@ -481,17 +507,16 @@ namespace MobileGL::MG_Backend::DirectGLES {
                 gl.glRenderbufferStorage(GL_RENDERBUFFER, internalFormat, 1, 1);
             }
             const Bool created = CheckNoGLError(gl);
-            const Bool complete = created && ProbeFramebufferCompletenessForRenderbuffer(gl, renderbuffer, logicalFormat);
+            const Bool complete =
+                created && ProbeFramebufferCompletenessForRenderbuffer(gl, renderbuffer, logicalFormat);
             gl.glBindRenderbuffer(GL_RENDERBUFFER, static_cast<GLuint>(prevRenderbuffer));
             gl.glDeleteRenderbuffers(1, &renderbuffer);
             ClearGLErrors(gl);
             return complete;
         }
 
-        Vector<Int> ProbeRenderbufferSampleCounts(const MG_External::GLESFunctionsTable& gl,
-                                                  GLenum internalFormat,
-                                                  TextureInternalFormat logicalFormat,
-                                                  Int maxSamples) {
+        Vector<Int> ProbeRenderbufferSampleCounts(const MG_External::GLESFunctionsTable& gl, GLenum internalFormat,
+                                                  TextureInternalFormat logicalFormat, Int maxSamples) {
             Vector<Int> sampleCounts;
             for (Int samples = std::max(maxSamples, 1); samples > 1; samples >>= 1) {
                 if (ProbeRenderbuffer(gl, internalFormat, logicalFormat, true, samples)) {
@@ -519,20 +544,84 @@ namespace MobileGL::MG_Backend::DirectGLES {
                 }
 
                 const GLESProbeFormatInfo nativeInfo = BuildNativeProbeFormatInfo(requestedInternalFormat);
-                GLESProbeFormatInfo fallbackInfo;
-                const Bool hasForcedFallback =
-                    BuildFallbackProbeFormatInfo(requestedInternalFormat, forcedOptions, true, fallbackInfo);
-                if (!hasForcedFallback) {
-                    BuildFallbackProbeFormatInfo(requestedInternalFormat, driverOptions, false, fallbackInfo);
+                GLESProbeFormatInfo outerFallbackInfo;
+                const Bool outerHasForcedFallback =
+                    BuildFallbackProbeFormatInfo(requestedInternalFormat, forcedOptions, true, outerFallbackInfo);
+                if (!outerHasForcedFallback) {
+                    BuildFallbackProbeFormatInfo(requestedInternalFormat, driverOptions, false, outerFallbackInfo);
                 }
 
                 for (SizeT targetIndex = 0; targetIndex < kFormatCapabilityTextureTargetCount; ++targetIndex) {
                     const auto target = static_cast<TextureTarget>(targetIndex);
+                    // Colour-attachable targets need a colour-renderable fallback; the ordinary
+                    // fallback for a three-channel format is another three-channel one, which ES
+                    // accepts as a texture but never as an attachment. Recompute the fallback per
+                    // target so those formats get widened where the target demands it.
+                    const Flags<PixelFormatNormalizeOptionBit> renderTargetOptions =
+                        TextureImpl::GetRenderTargetNormalizeOptions(capabilities, targetIndex);
+                    // Multisample storage has no three-channel form on ES at all, so its widening
+                    // is unconditional and skips the native probe (which cannot succeed). Every
+                    // other target keeps the widening on the DRIVER branch, behind the native
+                    // probe: `shouldProbeFallback = !nativeCreated || !nativeRenderable` below is
+                    // what makes the substitution conditional on the driver actually refusing, so
+                    // a driver that does render to a three-channel image keeps allocating it byte
+                    // for byte. That is a per-format runtime answer, NOT a desktop-vs-device
+                    // split: llvmpipe renders to GL_RGB16F but refuses GL_RGB8_SNORM, GL_SRGB8,
+                    // GL_RGB32F and the RGB integer formats, so the CI driver widens those eight
+                    // too. Re-run the retrace fixtures and the glcts suites on any change here.
+                    const Bool widenUnconditionally = IsGLESProbeMultisampleTarget(target);
+                    GLESProbeFormatInfo fallbackInfo = outerFallbackInfo;
+                    Bool hasForcedFallback = outerHasForcedFallback;
+                    if (renderTargetOptions) {
+                        // Folded into the forced options only when a forced fallback already
+                        // applies, so the render-target bits never *create* one: ANGLE's forced
+                        // GL_RGB8_SNORM -> GL_RGB16F is still three-channel and still needs
+                        // widening, but a non-ANGLE driver must not lose its native probe.
+                        const Flags<PixelFormatNormalizeOptionBit> forcedProbeOptions =
+                            (outerHasForcedFallback || widenUnconditionally) ? forcedOptions | renderTargetOptions
+                                                                             : forcedOptions;
+                        hasForcedFallback =
+                            BuildFallbackProbeFormatInfo(requestedInternalFormat, forcedProbeOptions, true,
+                                                         fallbackInfo);
+                        if (!hasForcedFallback) {
+                            BuildFallbackProbeFormatInfo(requestedInternalFormat,
+                                                         driverOptions | renderTargetOptions, false, fallbackInfo);
+                        }
+                        // HONEST STATUS OF THE FORCED PATH. A forced fallback is only ever built
+                        // for ANGLE (GetForcedPixelFormatNormalizeOptions returns nothing for any
+                        // other renderer), and it SKIPS the native probe entirely - the widened
+                        // format is asserted rather than measured on this device. That assertion
+                        // is validated on exactly one configuration, the android-angle retrace
+                        // golden; it is NOT covered by the headless llvmpipe suites, which take
+                        // the driver branch below and prove nothing about ANGLE's answers. So log
+                        // the choice at INFO rather than the usual MGLOG_D caveat: on any other
+                        // ANGLE device the device report is the only evidence there is of which
+                        // storage format the image really got. Once per format on the ordinary 2D
+                        // target - repeating it for all ten targets would bury the report.
+                        if (hasForcedFallback && target == TextureTarget::Texture2D &&
+                            (MG_Util::TextureFormatProcessor::GetApplicablePixelFormatNormalizeOptions(
+                                 requestedInternalFormat, renderTargetOptions) &
+                             PixelFormatNormalizeOptionBit::NoThreeChannelRenderTarget)) {
+                            MGLOG_I("Three-channel widening (FORCED path, no native probe): %s stored as %s. "
+                                    "Reason: %s. Device-validated on the android-angle golden only.",
+                                    MG_Util::ConvertTextureInternalFormatToString(logicalFormat).c_str(),
+                                    ConvertFallbackInternalFormatToString(fallbackInfo.InternalFormat).c_str(),
+                                    fallbackInfo.Reason.c_str());
+                        }
+                    }
+
+                    // 1D, 1D-array and rectangle textures live on an ES target (see
+                    // TextureImpl::MapToBackendTextureTarget), so they have to be probed there too -
+                    // probing the desktop-only target itself always failed, which left those slots
+                    // of the cache empty and stopped any fallback format from being selected for
+                    // them (a GL_DEPTH_COMPONENT32 1D texture then got no storage at all).
+                    const TextureTarget probeTarget = TextureImpl::MapToBackendTextureTarget(target);
+
                     Bool shouldProbeFallback = hasForcedFallback;
                     if (!hasForcedFallback) {
                         Bool nativeRenderable = false;
                         const Bool nativeCreated =
-                            ProbeTexture(gl, target, nativeInfo.InternalFormat, nativeInfo.ImageFormat,
+                            ProbeTexture(gl, probeTarget, nativeInfo.InternalFormat, nativeInfo.ImageFormat,
                                          nativeInfo.ImageType, logicalFormat, &nativeRenderable);
                         if (nativeCreated) {
                             AddFullFormatCaps(cache, targetIndex, formatIndex,
@@ -547,12 +636,12 @@ namespace MobileGL::MG_Backend::DirectGLES {
                     if (shouldProbeFallback && fallbackInfo.InternalFormat != GL_UNKNOWN_MGL) {
                         Bool fallbackRenderable = false;
                         const Bool fallbackCreated =
-                            ProbeTexture(gl, target, fallbackInfo.InternalFormat, fallbackInfo.ImageFormat,
+                            ProbeTexture(gl, probeTarget, fallbackInfo.InternalFormat, fallbackInfo.ImageFormat,
                                          fallbackInfo.ImageType, logicalFormat, &fallbackRenderable);
                         if (fallbackCreated) {
-                            if (AddCaveatFormatCaps(cache, targetIndex, formatIndex,
-                                                    BuildTextureCapsFromProbe(logicalFormat, target,
-                                                                              fallbackRenderable))) {
+                            if (AddCaveatFormatCaps(
+                                    cache, targetIndex, formatIndex,
+                                    BuildTextureCapsFromProbe(logicalFormat, target, fallbackRenderable))) {
                                 LogGLESFormatCaveat(logicalFormat, targetIndex, fallbackInfo);
                             }
                             if (IsGLESProbeMultisampleTarget(target)) {
@@ -563,8 +652,26 @@ namespace MobileGL::MG_Backend::DirectGLES {
                 }
 
                 const SizeT renderbufferTargetIndex = GetRenderbufferFormatCapabilityTargetIndex();
-                Bool shouldProbeFallbackRenderbuffer = hasForcedFallback;
-                if (!hasForcedFallback) {
+                // A renderbuffer exists only to be attached, so it needs the same three-channel
+                // widening the colour-attachable texture targets get - and on the same terms: the
+                // native storage is probed first, so a driver that renders to it keeps it.
+                const Flags<PixelFormatNormalizeOptionBit> renderbufferOptions =
+                    TextureImpl::GetRenderTargetNormalizeOptions(capabilities, renderbufferTargetIndex);
+                GLESProbeFormatInfo renderbufferFallbackInfo = outerFallbackInfo;
+                Bool renderbufferHasForcedFallback = outerHasForcedFallback;
+                if (renderbufferOptions) {
+                    const Flags<PixelFormatNormalizeOptionBit> forcedProbeOptions =
+                        outerHasForcedFallback ? forcedOptions | renderbufferOptions : forcedOptions;
+                    renderbufferHasForcedFallback = BuildFallbackProbeFormatInfo(
+                        requestedInternalFormat, forcedProbeOptions, true, renderbufferFallbackInfo);
+                    if (!renderbufferHasForcedFallback) {
+                        BuildFallbackProbeFormatInfo(requestedInternalFormat, driverOptions | renderbufferOptions,
+                                                     false, renderbufferFallbackInfo);
+                    }
+                }
+
+                Bool shouldProbeFallbackRenderbuffer = renderbufferHasForcedFallback;
+                if (!renderbufferHasForcedFallback) {
                     const Bool nativeRenderbufferComplete =
                         ProbeRenderbuffer(gl, nativeInfo.InternalFormat, logicalFormat, false, 1);
                     if (nativeRenderbufferComplete) {
@@ -578,16 +685,16 @@ namespace MobileGL::MG_Backend::DirectGLES {
                         shouldProbeFallbackRenderbuffer = true;
                     }
                 }
-                if (shouldProbeFallbackRenderbuffer && fallbackInfo.InternalFormat != GL_UNKNOWN_MGL &&
-                    ProbeRenderbuffer(gl, fallbackInfo.InternalFormat, logicalFormat, false, 1)) {
+                if (shouldProbeFallbackRenderbuffer && renderbufferFallbackInfo.InternalFormat != GL_UNKNOWN_MGL &&
+                    ProbeRenderbuffer(gl, renderbufferFallbackInfo.InternalFormat, logicalFormat, false, 1)) {
                     if (AddCaveatFormatCaps(cache, renderbufferTargetIndex, formatIndex,
                                             GetRenderbufferFeatureCaps(logicalFormat))) {
-                        LogGLESFormatCaveat(logicalFormat, renderbufferTargetIndex, fallbackInfo);
+                        LogGLESFormatCaveat(logicalFormat, renderbufferTargetIndex, renderbufferFallbackInfo);
                     }
                     const Int maxSamples =
-                        GetGLESFormatMaxSamples(capabilities, logicalFormat, fallbackInfo.ImageFormat);
-                    cache.SampleCounts[renderbufferTargetIndex][formatIndex] =
-                        ProbeRenderbufferSampleCounts(gl, fallbackInfo.InternalFormat, logicalFormat, maxSamples);
+                        GetGLESFormatMaxSamples(capabilities, logicalFormat, renderbufferFallbackInfo.ImageFormat);
+                    cache.SampleCounts[renderbufferTargetIndex][formatIndex] = ProbeRenderbufferSampleCounts(
+                        gl, renderbufferFallbackInfo.InternalFormat, logicalFormat, maxSamples);
                 }
             }
         }
@@ -603,11 +710,11 @@ namespace MobileGL::MG_Backend::DirectGLES {
                 .ExtraVendor = Nullopt,              // Extra vendor
                 .RendererGLInfo =
                     {
-                        .TargetGLVersion = {3, 3, 0},   // Target OpenGL Version
+                        .TargetGLVersion = {4, 0, 0},   // GL target version
                         .TargetGLSLVersion = {4, 6, 0}, // Target Shading Language Version
-                        // Baseline advertisement (no timer queries yet); reconciled once
-                        // the ES capabilities exist, see UpdateAdvertisedTimerQueryExtension.
-                        .Extensions = BuildAdvertisedExtensions(false),
+                        // Baseline advertisement (no timer queries / anisotropy yet); reconciled
+                        // once the ES capabilities exist, see UpdateAdvertisedCapabilityExtensions.
+                        .Extensions = BuildAdvertisedExtensions(false, false),
                         .IsCompatibilityProfile = false // Is Compatibility Profile
                     },
                 .StaticBackendCapability = {.AllowVSOnlyPrograms = false} // Backend Capability
@@ -627,14 +734,14 @@ namespace MobileGL::MG_Backend::DirectGLES {
         // thread can only observe the extension string after the
         // advertisement for its context has settled; rebuilding the whole
         // list keeps the re-run after a context recreation idempotent.
-        void UpdateAdvertisedTimerQueryExtension() {
-            MutableRendererInfo().RendererGLInfo.Extensions = BuildAdvertisedExtensions(AreTimerQueriesSupported());
+        void UpdateAdvertisedCapabilityExtensions(Bool anisotropicFilteringSupported) {
+            MutableRendererInfo().RendererGLInfo.Extensions =
+                BuildAdvertisedExtensions(AreTimerQueriesSupported(), anisotropicFilteringSupported);
         }
     } // namespace
 
     void PopulateFormatCapabilities(const MG_External::GLESFunctionsTable& gl,
-                                    const MG_External::GLESCapabilities& capabilities,
-                                    FormatCapabilityCache& cache) {
+                                    const MG_External::GLESCapabilities& capabilities, FormatCapabilityCache& cache) {
         PopulateFormatCapabilitiesImpl(gl, capabilities, cache);
     }
 
@@ -672,11 +779,11 @@ namespace MobileGL::MG_Backend::DirectGLES {
             return false;
         }
         DirectGLES::SetGLESCapabilities(m_GLESCapabilities);
-        // Now that g_GLESCapabilities knows about GL_EXT_disjoint_timer_query,
-        // reconcile the E_GL_ARB_timer_query advertisement (see the comment on
-        // UpdateAdvertisedTimerQueryExtension for why it cannot happen when
-        // the extension list is first built).
-        UpdateAdvertisedTimerQueryExtension();
+        // Now that g_GLESCapabilities knows about GL_EXT_disjoint_timer_query and
+        // GL_EXT_texture_filter_anisotropic, reconcile the advertisement (see the comment on
+        // UpdateAdvertisedCapabilityExtensions for why it cannot happen when the extension
+        // list is first built).
+        UpdateAdvertisedCapabilityExtensions(m_GLESCapabilities.SupportsTextureFilterAnisotropy);
         UpdateDynamicBackendParameters();
         PopulateFormatCapabilities(m_GLESFunctions, m_GLESCapabilities, MutableFormatCapabilities());
         PrintFormatCapabilities(GetFormatCapabilities());
@@ -698,11 +805,10 @@ namespace MobileGL::MG_Backend::DirectGLES {
             return false;
         }
 
-        if ((handle.Backend != WindowBackend::Android &&
-             handle.Backend != WindowBackend::X11 &&
-             handle.Backend != WindowBackend::MetalLayer) ||
+        if ((handle.Backend != WindowBackend::Android && handle.Backend != WindowBackend::X11 &&
+             handle.Backend != WindowBackend::MetalLayer && handle.Backend != WindowBackend::Win32) ||
             !handle.Handle) {
-            MGLOG_E("DirectGLES backend only supports Android, X11, and CAMetalLayer native windows");
+            MGLOG_E("DirectGLES backend only supports Android, X11, CAMetalLayer, and Win32 native windows");
             return false;
         }
 
@@ -818,24 +924,56 @@ namespace MobileGL::MG_Backend::DirectGLES {
         return MutableRendererInfo();
     }
 
-    Vector<GLExtension> BuildAdvertisedExtensions(Bool timerQueriesSupported) {
-        Vector<GLExtension> extensions = {V_OpenGL30, V_OpenGL31, V_OpenGL32,
-                                          V_OpenGL33, E_GL_ARB_draw_buffers_blend, E_GL_ARB_compute_shader,
-                                          E_GL_ARB_shader_storage_buffer_object, E_GL_ARB_shader_image_load_store,
-                                          E_GL_ARB_program_interface_query, E_GL_ARB_framebuffer_object,
-                                          E_GL_EXT_framebuffer_object, E_GL_ARB_depth_texture, E_GL_ARB_buffer_storage,
-                                          E_GL_ARB_texture_storage, E_GL_ARB_texture_storage_multisample,
-                                          E_GL_ARB_direct_state_access,
-                                          E_GL_ARB_multi_draw_indirect, E_GL_ARB_indirect_parameters,
-                                          E_GL_ARB_shader_draw_parameters, E_GL_ARB_gpu_shader5, E_GL_ARB_multi_bind,
-                                          E_GL_ARB_shading_language_420pack, E_GL_ARB_vertex_attrib_binding,
-                                          E_GL_ARB_shader_image_size};
+    Vector<GLExtension> BuildAdvertisedExtensions(Bool timerQueriesSupported, Bool anisotropicFilteringSupported) {
+        Vector<GLExtension> extensions = {
+            V_OpenGL30, V_OpenGL31, V_OpenGL32, V_OpenGL33, V_OpenGL40, E_GL_ARB_draw_buffers_blend,
+            E_GL_ARB_compute_shader, E_GL_ARB_shader_storage_buffer_object, E_GL_ARB_shader_image_load_store,
+            E_GL_ARB_program_interface_query, E_GL_ARB_framebuffer_object, E_GL_EXT_framebuffer_object,
+            E_GL_ARB_depth_texture, E_GL_ARB_buffer_storage, E_GL_ARB_texture_storage,
+            E_GL_ARB_texture_storage_multisample, E_GL_ARB_clear_texture, E_GL_ARB_direct_state_access,
+            E_GL_ARB_multi_draw_indirect, E_GL_ARB_indirect_parameters, E_GL_ARB_shader_draw_parameters,
+            E_GL_ARB_gpu_shader5, E_GL_ARB_multi_bind, E_GL_ARB_shading_language_420pack,
+            E_GL_ARB_vertex_attrib_binding,
+            // Both are core from GL 3.2/3.3 on and implemented here for
+            // every advertised version, but an app targeting 3.0/3.1
+            // only reaches them through the extension string - the CTS
+            // picks a whole different shader for draw_buffers without
+            // explicit_attrib_location. DirectVulkan advertises both.
+            E_GL_ARB_explicit_attrib_location, E_GL_ARB_texture_multisample, E_GL_ARB_shader_image_size,
+            // Advertised with GL_NUM_PROGRAM_BINARY_FORMATS = 0, which the
+            // extension explicitly permits. It is also the only thing that
+            // exposes glProgramParameteri before GL 4.1.
+            E_GL_ARB_get_program_binary};
+        // GL_KHR_parallel_shader_compile is MobileGL's own capability, not the host ES
+        // driver's: the compiler threads are MobileGL's, and glCompileShader/glLinkProgram
+        // are serviced entirely inside the frontend. Whether the device driver advertises
+        // the string is irrelevant here (the POST reports it separately, for the day the
+        // driver-side link is what gets parallelised).
+        //
+        // Gated on the async flag deliberately, and this is the whole reason the gate
+        // exists. Advertising the string is the one part of asynchronous compilation that a
+        // recorded trace can never cover: Iris and Sodium change their SUBMISSION SCHEDULE
+        // the moment they see it - they enqueue whole pipeline batches and poll
+        // GL_COMPLETION_STATUS_KHR instead of compiling one program at a time - so
+        // MOBILEGL_ASYNC_SHADER_COMPILE=0 has to withdraw the application-visible behaviour
+        // change as well as the threading, or the kill switch would only be half a switch.
+        if (MG_Util::Async::AsyncShaderCompileEnabled()) {
+            extensions.push_back(E_GL_KHR_parallel_shader_compile);
+        }
         // Only advertised when the device driver actually has usable timer queries
         // (GL_EXT_disjoint_timer_query plus its entry points) and the
         // MOBILEGL_DISABLE_TIMERQUERY escape hatch is off.
         if (timerQueriesSupported && !MG_Config::Features.DisableTimerQuery) {
             extensions.push_back(E_GL_ARB_timer_query);
         }
+        // Only advertised when the host ES driver actually filters anisotropically: the sampler
+        // state is accepted regardless, but forwarding it would be a no-op without the extension,
+        // and an app that trusts the string (LWJGL builds GLCapabilities from it) would silently
+        // get plain trilinear.
+        if (anisotropicFilteringSupported) {
+            extensions.push_back(E_GL_EXT_texture_filter_anisotropic);
+            extensions.push_back(E_GL_ARB_texture_filter_anisotropic);
+        }
         return extensions;
     }
 
@@ -882,12 +1020,6 @@ namespace MobileGL::MG_Backend::DirectGLES {
             funcsTable.GL.GetIntegeri_v = GetIntegeri_v;
             funcsTable.GL.GetInteger64i_v = GetInteger64i_v;
             funcsTable.GL.GetProgramiv = GetProgramiv;
-            funcsTable.GL.GetProgramInterfaceiv = GetProgramInterfaceiv;
-            funcsTable.GL.GetProgramResourceIndex = GetProgramResourceIndex;
-            funcsTable.GL.GetProgramResourceName = GetProgramResourceName;
-            funcsTable.GL.GetProgramResourceiv = GetProgramResourceiv;
-            funcsTable.GL.GetProgramResourceLocation = GetProgramResourceLocation;
-            funcsTable.GL.GetProgramResourceLocationIndex = GetProgramResourceLocationIndex;
             funcsTable.GL.ShaderStorageBlockBinding = ShaderStorageBlockBinding;
             funcsTable.GL.Clear = Clear;
             funcsTable.GL.ClearBufferfi = ClearBufferfi;
@@ -895,6 +1027,8 @@ namespace MobileGL::MG_Backend::DirectGLES {
             funcsTable.GL.ClearBufferuiv = ClearBufferuiv;
             funcsTable.GL.ClearBufferiv = ClearBufferiv;
             funcsTable.GL.ClearNamedFramebufferfv = ClearNamedFramebufferfv;
+            funcsTable.GL.ClearNamedFramebufferiv = ClearNamedFramebufferiv;
+            funcsTable.GL.ClearNamedFramebufferuiv = ClearNamedFramebufferuiv;
             funcsTable.GL.ClearNamedFramebufferfi = ClearNamedFramebufferfi;
             funcsTable.GL.BlitFramebuffer = BlitFramebuffer;
             funcsTable.GL.BlitNamedFramebuffer = BlitNamedFramebuffer;
@@ -924,11 +1058,30 @@ namespace MobileGL::MG_Backend::DirectGLES {
                 funcsTable.GL.BeginTimeElapsedQuery = BeginTimeElapsedQuery;
                 funcsTable.GL.EndTimeElapsedQuery = EndTimeElapsedQuery;
                 funcsTable.GL.QueryCounterTimestamp = QueryCounterTimestamp;
-                funcsTable.GL.IsQueryResultAvailable = IsQueryResultAvailable;
-                funcsTable.GL.GetQueryResult64 = GetQueryResult64;
-                funcsTable.GL.DeleteBackendQuery = DeleteBackendQuery;
                 funcsTable.GL.GetGpuTimestampNs = GetGpuTimestampNs;
             }
+            // Occlusion queries are core ES3 (independent of MOBILEGL_DISABLE_TIMERQUERY)
+            // and share the handle-based result/delete entries, which must exist even
+            // when the timer-query group above is disabled.
+            funcsTable.GL.BeginOcclusionQuery = BeginOcclusionQuery;
+            funcsTable.GL.EndOcclusionQuery = EndOcclusionQuery;
+            // Real driver primitive counters: the frontend's CPU accounting cannot see a
+            // geometry shader's amplification.
+            funcsTable.GL.BeginXfbPrimitivesQuery = BeginXfbPrimitivesQuery;
+            funcsTable.GL.EndXfbPrimitivesQuery = EndXfbPrimitivesQuery;
+            funcsTable.GL.IsQueryResultAvailable = IsQueryResultAvailable;
+            funcsTable.GL.GetQueryResult64 = GetQueryResult64;
+            funcsTable.GL.DeleteBackendQuery = DeleteBackendQuery;
+            // Transform feedback is captured by the real ES driver rather than
+            // reconstructed from the draw recording, so the frontend has to hand the
+            // span boundaries over.
+            funcsTable.GL.PatchParameteri = DirectGLES::PatchParameteri;
+            funcsTable.GL.BeginTransformFeedback = XfbImpl::BeginTransformFeedback;
+            funcsTable.GL.EndTransformFeedback = XfbImpl::EndTransformFeedback;
+            funcsTable.GL.PauseTransformFeedback = XfbImpl::PauseTransformFeedback;
+            funcsTable.GL.ResumeTransformFeedback = XfbImpl::ResumeTransformFeedback;
+            funcsTable.GL.BindTransformFeedback = XfbImpl::BindTransformFeedback;
+            funcsTable.GL.DeleteTransformFeedback = XfbImpl::DeleteTransformFeedback;
             funcsTableInitialized = true;
         }
         return funcsTable;
@@ -938,8 +1091,14 @@ namespace MobileGL::MG_Backend::DirectGLES {
         return m_dynamicParameters;
     }
 
+    void BackendObject_DirectGLES::ApplyGLESCapabilitiesForTesting(const MG_External::GLESCapabilities& capabilities) {
+        m_GLESCapabilities = capabilities;
+        UpdateDynamicBackendParameters();
+    }
+
     void BackendObject_DirectGLES::UpdateDynamicBackendParameters() {
         m_dynamicParameters.UniformBufferOffsetAlignment = m_GLESCapabilities.UniformBufferOffsetAlignment;
+        m_dynamicParameters.MaxTextureMaxAnisotropy = m_GLESCapabilities.MaxTextureMaxAnisotropy;
         m_dynamicParameters.AliasedLineWidthRangeMin = m_GLESCapabilities.AliasedLineWidthRangeMin;
         m_dynamicParameters.AliasedLineWidthRangeMax = m_GLESCapabilities.AliasedLineWidthRangeMax;
         m_dynamicParameters.SmoothLineWidthRangeMin = m_GLESCapabilities.SmoothLineWidthRangeMin;
@@ -962,6 +1121,10 @@ namespace MobileGL::MG_Backend::DirectGLES {
         m_dynamicParameters.MaxIntegerSamples = m_GLESCapabilities.MaxIntegerSamples;
         m_dynamicParameters.MaxSamples = m_GLESCapabilities.MaxSamples;
         m_dynamicParameters.MaxSampleMaskWords = m_GLESCapabilities.MaxSampleMaskWords;
+        m_dynamicParameters.MaxPatchVertices = m_GLESCapabilities.MaxPatchVertices;
+        m_dynamicParameters.MaxTessGenLevel = m_GLESCapabilities.MaxTessGenLevel;
+        m_dynamicParameters.MinProgramTextureGatherOffset = m_GLESCapabilities.MinProgramTextureGatherOffset;
+        m_dynamicParameters.MaxProgramTextureGatherOffset = m_GLESCapabilities.MaxProgramTextureGatherOffset;
         // Clamp the advertised sampler limits the same way the DirectVulkan backend does: per-stage
         // GL_MAX_TEXTURE_IMAGE_UNITS must never exceed host-side fixed arrays sized off it (e.g.
         // Minecraft's 128-entry Blaze3D GlStateManager.TEXTURES[], iterated by Iris), and the combined
@@ -989,13 +1152,51 @@ namespace MobileGL::MG_Backend::DirectGLES {
         m_dynamicParameters.MaxComputeWorkGroupInvocations = m_GLESCapabilities.MaxComputeWorkGroupInvocations;
         m_dynamicParameters.MaxShaderStorageBufferBindings = m_GLESCapabilities.MaxShaderStorageBufferBindings;
         m_dynamicParameters.MaxTextureBufferSize = m_GLESCapabilities.MaxTextureBufferSize;
+        m_dynamicParameters.TextureBufferOffsetAlignment = m_GLESCapabilities.TextureBufferOffsetAlignment;
         m_dynamicParameters.MaxUniformBufferBindings = m_GLESCapabilities.MaxUniformBufferBindings;
         m_dynamicParameters.MaxUniformBlockSize = m_GLESCapabilities.MaxUniformBlockSize;
-        const Int maxSupportedTextureUnits =
-            static_cast<Int>(MG_State::GLState::TextureState::MAX_TEXTURE_IMAGE_UNITS);
-        m_dynamicParameters.MaxImageUnits = std::min(m_GLESCapabilities.MaxImageUnits, maxSupportedTextureUnits);
-        m_dynamicParameters.MaxCombinedImageUniforms = m_GLESCapabilities.MaxCombinedImageUniforms;
-        m_dynamicParameters.MaxComputeImageUniforms = m_GLESCapabilities.MaxComputeImageUniforms;
+        const Int maxSupportedTextureUnits = static_cast<Int>(MG_State::GLState::TextureState::MAX_TEXTURE_IMAGE_UNITS);
+        m_dynamicParameters.MaxImageUnits =
+            std::max(std::min(m_GLESCapabilities.MaxImageUnits, maxSupportedTextureUnits), 0);
+        m_dynamicParameters.MaxCombinedImageUniforms = std::max(m_GLESCapabilities.MaxCombinedImageUniforms, 0);
+        const auto clampStageImageUniforms = [this](Int stageLimit) {
+            return std::min({std::max(stageLimit, 0), m_dynamicParameters.MaxImageUnits,
+                             m_dynamicParameters.MaxCombinedImageUniforms});
+        };
+        m_dynamicParameters.MaxVertexImageUniforms = clampStageImageUniforms(m_GLESCapabilities.MaxVertexImageUniforms);
+        m_dynamicParameters.MaxGeometryImageUniforms =
+            clampStageImageUniforms(m_GLESCapabilities.MaxGeometryImageUniforms);
+        m_dynamicParameters.MaxFragmentImageUniforms =
+            clampStageImageUniforms(m_GLESCapabilities.MaxFragmentImageUniforms);
+        m_dynamicParameters.MaxComputeImageUniforms =
+            clampStageImageUniforms(m_GLESCapabilities.MaxComputeImageUniforms);
+        m_dynamicParameters.SupportsDistinctDepthStencilAttachments =
+            ProbeDistinctDepthStencilAttachments(DirectGLES::g_GLESFuncs);
+        // SyncAttachmentObject routes a layered upload target to glFramebufferTextureLayer with the
+        // attachment's layer passed through, so this backend really does render to the layer it was
+        // given - provided the driver resolved the entry point at all.
+        // SyncAttachmentObject (Managers.cpp, the glFramebufferTextureLayer branch) routes exactly
+        // five upload targets to glFramebufferTextureLayer with the attachment's layer passed
+        // through, so this backend really does render to the layer it was given - provided the driver
+        // resolved the entry point at all. The cube map array is the one target that also needs
+        // ES-level support before it has any storage to attach.
+        m_dynamicParameters.PerLayerFramebufferAttachmentTargets = 0;
+        if (DirectGLES::g_GLESFuncs.glFramebufferTextureLayer != nullptr) {
+            using DynParams = MG_Backend::DynamicBackendParameters;
+            m_dynamicParameters.PerLayerFramebufferAttachmentTargets |=
+                DynParams::PerLayerFramebufferAttachmentBit(TextureTarget::Texture3D) |
+                DynParams::PerLayerFramebufferAttachmentBit(TextureTarget::Texture1DArray) |
+                DynParams::PerLayerFramebufferAttachmentBit(TextureTarget::Texture2DArray) |
+                DynParams::PerLayerFramebufferAttachmentBit(TextureTarget::Texture2DMultisampleArray);
+            if (m_GLESCapabilities.SupportsTextureCubeMapArray) {
+                m_dynamicParameters.PerLayerFramebufferAttachmentTargets |=
+                    DynParams::PerLayerFramebufferAttachmentBit(TextureTarget::TextureCubeMapArray);
+            }
+        }
+        // Not a driver question and never will be: OpenGL ES has no double-precision vertex format
+        // and ESSL has no fp64 type to consume one with, so a 64-bit vertex attribute has nowhere to
+        // land on this backend regardless of what the driver underneath happens to support.
+        m_dynamicParameters.SupportsFloat64VertexAttributes = false;
         m_dynamicParameters.MaxDrawBuffers = m_GLESCapabilities.MaxDrawBuffers;
         m_dynamicParameters.MaxColorAttachments = m_GLESCapabilities.MaxColorAttachments;
         m_dynamicParameters.MaxClipDistances = m_GLESCapabilities.MaxClipDistances;
@@ -1005,8 +1206,50 @@ namespace MobileGL::MG_Backend::DirectGLES {
         m_dynamicParameters.ViewportBoundsRangeMin = m_GLESCapabilities.ViewportBoundsRangeMin;
         m_dynamicParameters.ViewportBoundsRangeMax = m_GLESCapabilities.ViewportBoundsRangeMax;
         m_dynamicParameters.ViewportSubpixelBits = m_GLESCapabilities.ViewportSubpixelBits;
+        m_dynamicParameters.MinFragmentInterpolationOffset =
+            std::isfinite(m_GLESCapabilities.MinFragmentInterpolationOffset) &&
+                    m_GLESCapabilities.MinFragmentInterpolationOffset <= -0.5f
+                ? m_GLESCapabilities.MinFragmentInterpolationOffset
+                : -0.5f;
+        m_dynamicParameters.MaxFragmentInterpolationOffset = 0.4375f;
+        m_dynamicParameters.FragmentInterpolationOffsetBits = 4;
+        if (m_GLESCapabilities.FragmentInterpolationOffsetBits >= 4 &&
+            std::isfinite(m_GLESCapabilities.MaxFragmentInterpolationOffset)) {
+            const Float requiredMaxOffset =
+                0.5f - std::ldexp(1.0f, -m_GLESCapabilities.FragmentInterpolationOffsetBits);
+            if (m_GLESCapabilities.MaxFragmentInterpolationOffset >= requiredMaxOffset) {
+                m_dynamicParameters.MaxFragmentInterpolationOffset = m_GLESCapabilities.MaxFragmentInterpolationOffset;
+                m_dynamicParameters.FragmentInterpolationOffsetBits =
+                    m_GLESCapabilities.FragmentInterpolationOffsetBits;
+            }
+        }
         m_dynamicParameters.SupportsWideLines =
             m_GLESCapabilities.AliasedLineWidthRangeMax > 1.0f || m_GLESCapabilities.SmoothLineWidthRangeMax > 1.0f;
+
+        const auto containsAny = [](const String& haystack, std::initializer_list<const char*> needles) {
+            return std::any_of(needles.begin(), needles.end(),
+                               [&](const char* needle) { return haystack.find(needle) != String::npos; });
+        };
+        const String vendorAndRenderer =
+            m_GLESCapabilities.GLESVendorString + " " + m_GLESCapabilities.GLESRendererString;
+        if (containsAny(vendorAndRenderer, {"llvmpipe", "SwiftShader", "softpipe"})) {
+            // Check software rasterizers first: ANGLE-on-llvmpipe reports both.
+            m_dynamicParameters.GpuVendor = GpuVendorKind::Software;
+        } else if (containsAny(vendorAndRenderer, {"Qualcomm", "Adreno"})) {
+            m_dynamicParameters.GpuVendor = GpuVendorKind::Qualcomm;
+        } else if (containsAny(vendorAndRenderer, {"Mali", "ARM"})) {
+            m_dynamicParameters.GpuVendor = GpuVendorKind::Arm;
+        } else if (containsAny(vendorAndRenderer, {"NVIDIA"})) {
+            m_dynamicParameters.GpuVendor = GpuVendorKind::Nvidia;
+        } else if (containsAny(vendorAndRenderer, {"AMD", "Radeon"})) {
+            m_dynamicParameters.GpuVendor = GpuVendorKind::Amd;
+        } else if (containsAny(vendorAndRenderer, {"Intel"})) {
+            m_dynamicParameters.GpuVendor = GpuVendorKind::Intel;
+        } else if (containsAny(vendorAndRenderer, {"Imagination", "PowerVR"})) {
+            m_dynamicParameters.GpuVendor = GpuVendorKind::ImgTec;
+        } else {
+            m_dynamicParameters.GpuVendor = GpuVendorKind::Unknown;
+        }
     }
 
     const MG_External::GLESFunctionsTable& BackendObject_DirectGLES::GetGLESFunctions() const {

MobileGL/MG_Backend/DirectGLES/BackendObject_DirectGLES.h

@@ -41,6 +41,7 @@ namespace MobileGL::MG_Backend::DirectGLES {
 
         const MG_External::GLESFunctionsTable& GetGLESFunctions() const;
         const MG_External::EGLFunctionsTable& GetEGLFunctions() const;
+        void ApplyGLESCapabilitiesForTesting(const MG_External::GLESCapabilities& capabilities);
 
     private:
         void UpdateDynamicBackendParameters();
@@ -66,9 +67,9 @@ namespace MobileGL::MG_Backend::DirectGLES {
     const RendererInfo& GetRendererIdentity();
 
     // The full OpenGL extension list Espryt advertises (glGetString(GL_EXTENSIONS))
-    // for a device whose timer queries are (or are not) usable. The
-    // MOBILEGL_DISABLE_TIMERQUERY escape hatch is applied inside.
-    Vector<GLExtension> BuildAdvertisedExtensions(Bool timerQueriesSupported);
+    // for a device whose timer queries / anisotropic filtering are (or are not) usable.
+    // The MOBILEGL_DISABLE_TIMERQUERY escape hatch is applied inside.
+    Vector<GLExtension> BuildAdvertisedExtensions(Bool timerQueriesSupported, Bool anisotropicFilteringSupported);
 
     // Format: <OpenGL ES Renderer>, OpenGL ES <Major>.<Minor> — the exact string an
     // initialized backend returns from GetBackendAPIVersionString (and that ends up

MobileGL/MG_Backend/DirectGLES/DirectGLES.h

@@ -19,6 +19,10 @@
     operation Utils::CheckGLESError();
 
 namespace MobileGL::MG_Backend::DirectGLES {
+    // Re-establishes the frontend texture-unit bindings on the native ES context.
+    // Content uploads use scratch bindings, so draws and dispatches call this after
+    // texture synchronization.
+    void BindCurrentTextures();
     void ClearBufferfi(GLenum buffer, GLint drawbuffer, GLfloat depth, GLint stencil);
     void ClearBufferfv(GLenum buffer, GLint drawbuffer, const GLfloat* value);
     void ClearBufferuiv(GLenum buffer, GLint drawbuffer, const GLuint* value);
@@ -55,6 +59,10 @@ namespace MobileGL::MG_Backend::DirectGLES {
                                  GLenum buffer, GLint drawbuffer, const GLfloat* value);
     void ClearNamedFramebufferfi(const SharedPtr<MG_State::GLState::FramebufferObject>& framebuffer,
                                  GLenum buffer, GLint drawbuffer, GLfloat depth, GLint stencil);
+    void ClearNamedFramebufferiv(const SharedPtr<MG_State::GLState::FramebufferObject>& framebuffer,
+                                 GLenum buffer, GLint drawbuffer, const GLint* value);
+    void ClearNamedFramebufferuiv(const SharedPtr<MG_State::GLState::FramebufferObject>& framebuffer,
+                                  GLenum buffer, GLint drawbuffer, const GLuint* value);
     void BlitFramebuffer(GLint srcX0, GLint srcY0, GLint srcX1, GLint srcY1, GLint dstX0, GLint dstY0, GLint dstX1,
                          GLint dstY1, GLbitfield mask, GLenum filter);
     void BlitNamedFramebuffer(const SharedPtr<MG_State::GLState::FramebufferObject>& readFramebuffer,
@@ -84,15 +92,7 @@ namespace MobileGL::MG_Backend::DirectGLES {
     void GetIntegeri_v(GLenum target, GLuint index, GLint* data);
     void GetInteger64i_v(GLenum target, GLuint index, GLint64* data);
     void GetProgramiv(GLuint program, GLenum pname, GLint* params);
-    void GetProgramInterfaceiv(GLuint program, GLenum programInterface, GLenum pname, GLint* params);
-    GLuint GetProgramResourceIndex(GLuint program, GLenum programInterface, const GLchar* name);
-    void GetProgramResourceName(GLuint program, GLenum programInterface, GLuint index, GLsizei bufSize, GLsizei* length,
-                                GLchar* name);
-    void GetProgramResourceiv(GLuint program, GLenum programInterface, GLuint index, GLsizei propCount,
-                              const GLenum* props, GLsizei bufSize, GLsizei* length, GLint* params);
-    GLint GetProgramResourceLocation(GLuint program, GLenum programInterface, const GLchar* name);
-    GLint GetProgramResourceLocationIndex(GLuint program, GLenum programInterface, const GLchar* name);
-    void ShaderStorageBlockBinding(GLuint program, GLuint storageBlockIndex, GLuint storageBlockBinding);
+    void ShaderStorageBlockBinding(GLuint program, const GLchar* storageBlockName, GLuint storageBlockBinding);
     Bool InitWindowSurface(NativeWindowType window);
     Bool InitPbufferSurface(EGLint width, EGLint height);
     Bool MakeCurrent();
@@ -126,6 +126,16 @@ namespace MobileGL::MG_Backend::DirectGLES {
     BackendQueryHandle BeginTimeElapsedQuery();
     void EndTimeElapsedQuery(BackendQueryHandle query);
     BackendQueryHandle QueryCounterTimestamp();
+    // GL_ANY_SAMPLES_PASSED(_CONSERVATIVE) occlusion queries: core ES3, independent of
+    // GL_EXT_disjoint_timer_query and of MOBILEGL_DISABLE_TIMERQUERY. Results/deletion
+    // flow through GetQueryResult64/DeleteBackendQuery like the timer queries above.
+    BackendQueryHandle BeginOcclusionQuery();
+    void EndOcclusionQuery(BackendQueryHandle query);
+    // GL_TRANSFORM_FEEDBACK_PRIMITIVES_WRITTEN / GL_PRIMITIVES_GENERATED, also core ES
+    // (GL_PRIMITIVES_GENERATED from ES 3.2 on). Null when the target is unavailable, in
+    // which case the frontend falls back to counting primitives from the draw calls.
+    BackendQueryHandle BeginXfbPrimitivesQuery(Bool generated);
+    void EndXfbPrimitivesQuery(BackendQueryHandle query);
     Bool IsQueryResultAvailable(BackendQueryHandle query);
     // Returns true when a final value landed in *outNanoseconds (a zero for
     // null or stale-generation handles IS final: the frontend may cache it
@@ -142,6 +152,11 @@ namespace MobileGL::MG_Backend::DirectGLES {
     // A buffer retired during frame N is safe to recycle once CompletedFrameSerial() >= N.
     Uint64 CurrentFrameSerial();
     Uint64 CompletedFrameSerial();
+    // Block (up to timeoutNs) until the given frame serial provably retired on the
+    // GPU, using the per-frame fence ring. False when no usable fence covers the
+    // serial (fence-less context, foreign thread, or the slot was recycled);
+    // completion state is untouched in that case.
+    Bool WaitForFrameSerialCompleted(Uint64 serial, Uint64 timeoutNs);
     // Applies (or defers until the window surface exists) the app-requested
     // eglSwapInterval on the native EGL surface.
     void SetSwapInterval(Int interval);
@@ -150,6 +165,49 @@ namespace MobileGL::MG_Backend::DirectGLES {
     void SetGLESCapabilities(const MG_External::GLESCapabilities& capabilities);
     void DestroyEGLContext();
 
+    // Transform feedback capture spans, performed by the real ES driver. The
+    // capture set is declared on the backend program at link time; the driver-side
+    // begin is deferred to the first draw of the span (ES needs the capturing
+    // program current and the capture buffers bound), and the end also mirrors the
+    // captured bytes back into the frontend buffer shadows.
+    void PatchParameteri(GLenum pname, GLint value);
+
+    namespace XfbImpl {
+        Bool AreTransformFeedbacksSupported();
+        // True while a capture span is open on the current transform feedback object
+        // (frontend Begin seen and not paused), whether or not the deferred driver-side
+        // Begin has been issued yet. Draw paths that would restructure the primitive
+        // stream, or that need to dispatch compute mid-draw, decline while it is set.
+        Bool IsCaptureSpanOpen();
+        void BeginTransformFeedback(GLenum primitiveMode);
+        void EndTransformFeedback();
+        void PauseTransformFeedback();
+        void ResumeTransformFeedback();
+        void BindTransformFeedback(GLuint name);
+        void DeleteTransformFeedback(GLuint name);
+        void OnBackendContextDestroyed();
+    } // namespace XfbImpl
+
+    namespace RenderStateImpl {
+        // Pushes the frontend's render-state block to the ES driver, diffed against what was
+        // last pushed.
+        //
+        // `forColorClear` names the CALLER, and the only thing it changes is the colour write
+        // mask handed to the driver. A draw into a colour attachment the backend widened from
+        // three channels to four gets that buffer's alpha channel masked OFF, so nothing can
+        // move the stored alpha away from the 1.0 the application's three-channel format
+        // implies (see FramebufferImpl::g_alphaWidenedDrawBufferMask). A CLEAR is how that 1.0
+        // gets there in the first place, so it must be allowed to write alpha - hence the flag
+        // rather than an unconditional doctoring. It is part of the sync memo, so a clear
+        // followed by a draw re-pushes the mask instead of early-outing on an unchanged
+        // frontend version.
+        //
+        // The application's own colour mask is never modified: glGet(GL_COLOR_WRITEMASK)
+        // answers from the frontend state, which this function only reads.
+        void SyncRenderState(Bool forColorClear = false);
+        void InvalidateSyncedRenderState();
+    } // namespace RenderStateImpl
+
     extern MG_External::EGLFunctionsTable g_EGLFuncs;
     extern MG_External::GLESFunctionsTable g_GLESFuncs;
     extern MG_External::GLESCapabilities g_GLESCapabilities;

MobileGL/MG_Backend/DirectGLES/Managers.h

@@ -15,50 +15,132 @@
 #include "MG_State/GLState/TextureState/TextureEnum.h"
 #include <MG_State/GLState/TextureState/TextureObject.h>
 #include <MG_State/GLState/Core.h>
+#include <MG_Util/Converters/MGToGL/TextureEnumConverter.h>
 
 namespace MobileGL::MG_Backend::DirectGLES {
     String EmulateBaseInstanceInVertexShader(String source, GLenum shaderType);
     String PromoteDrawParameterGlobalsToUniforms(String source, GLenum shaderType);
 
+    // True once the process has entered exit(): past that point the EGL library and
+    // the driver may already be unloaded, so a backend twin's destructor must not
+    // call into g_GLESFuncs (the observed crash is a jump through an unmapped driver
+    // pointer from __run_exit_handlers) nor touch statics in other TUs (cross-TU
+    // destruction order is unspecified). Deliberate leak: the process is exiting and
+    // the driver reclaims GPU objects. The flag is set by a std::atexit handler that
+    // EnsureProcessTeardownSentinel() registers lazily on first registry use - by
+    // then every static everywhere has finished constructing, so this handler is
+    // guaranteed to run BEFORE any static destructor (atexit is LIFO). A destructor
+    // hook on the registry itself was tried first and is WRONG: tests and cache
+    // resets destroy temporary registry instances mid-run, which would latch the
+    // flag while the process is very much alive.
+    Bool InProcessTeardown();
+    void EnsureProcessTeardownSentinel();
+
+    // Which optional pieces of state a draw needs synchronized before it is issued.
+    // Index/indirect buffer syncs and the instancing-related work are skipped for
+    // draws that provably cannot read them.
+    enum class DrawSyncBit : Uint32 {
+        None = 0,
+        IndexBuffer = 1 << 0,
+        IndirectBuffer = 1 << 1,
+        Instancing = 1 << 2
+    };
+    // Deliberately the shared Flags<> rather than hand-written operators for this enum:
+    // a namespace-local operator| here would hide MobileGL::operator|(Bit, Bit) from
+    // every other scoped-enum flag set used inside this namespace.
+    using DrawSyncFlags = Flags<DrawSyncBit>;
+
+    // The GL-defined indirect command layouts, byte-identical to what the driver reads
+    // out of a GL_DRAW_INDIRECT_BUFFER. Also the staging layout the multi-draw emulation
+    // synthesizes commands into.
+    struct DrawElementsIndirectCommand {
+        Uint32 count = 0;
+        Uint32 instanceCount = 0;
+        Uint32 firstIndex = 0;
+        Int32 baseVertex = 0;
+        Uint32 baseInstance = 0;
+    };
+
+    struct DrawArraysIndirectCommand {
+        Uint32 count = 0;
+        Uint32 instanceCount = 0;
+        Uint32 first = 0;
+        Uint32 baseInstance = 0;
+    };
+
+    // Brings the whole draw-relevant frontend state onto the native ES context and binds
+    // the program; every GL draw entry point calls it exactly once before issuing draws.
+    void PrepareForDraw(DrawSyncFlags syncBits);
+    // GLES core supports only GL_PRIMITIVE_RESTART_FIXED_INDEX. Throws when the app enabled
+    // the arbitrary GL_PRIMITIVE_RESTART with a non-fixed index for this index type.
+    void CheckPrimitiveRestartSupported(GLenum indexType);
+    // Feed the current program's gl_BaseInstance / gl_DrawID emulation uniforms. Both are
+    // no-ops when the program does not read the corresponding builtin.
+    void SetCurrentBaseInstance(Uint32 baseInstance);
+    void SetCurrentDrawID(Uint32 drawId);
+    // True when the current program actually reads gl_DrawID, i.e. when a batched
+    // (single driver call) multi-draw tier would have to feed it one value for the whole
+    // batch and would therefore be wrong.
+    Bool CurrentProgramReadsDrawID();
+
     template <typename StateObject, typename BackendObject>
     class StateBackendObjectRegistry {
     public:
+
         using StatePtr = SharedPtr<StateObject>;
         using StateWeakPtr = std::weak_ptr<StateObject>;
         using BackendPtr = SharedPtr<BackendObject>;
-        using BackendMap = UnorderedMap<StateObject*, BackendPtr>;
-        using StateRefMap = UnorderedMap<StateObject*, StateWeakPtr>;
+
+        // The backend twin and the weak reference that decides whether the raw key still
+        // names the state object the twin was built for. Both live in one entry: a
+        // separate liveness map answered nothing the backend probe had not already found
+        // and cost a second hash lookup on every Find, which the draw path runs ~10 times.
+        struct Entry {
+            BackendPtr backend;
+            StateWeakPtr stateRef;
+        };
+        using BackendMap = UnorderedMap<StateObject*, Entry>;
         using iterator = typename BackendMap::iterator;
         using const_iterator = typename BackendMap::const_iterator;
 
         BackendPtr& GetOrCreate(const StatePtr& stateObj) {
             MOBILEGL_ASSERT(stateObj != nullptr, "State object must not be null");
 
-            auto* key = stateObj.get();
-            auto trackedStateIt = m_stateRefs.find(key);
-            if (trackedStateIt != m_stateRefs.end() && trackedStateIt->second.expired()) {
-                EraseByKey(key);
+            // Twin creation is the moment a driver-owned id starts needing a guarded
+            // destructor; cold path, so the once-guard costs nothing per draw.
+            EnsureProcessTeardownSentinel();
+            auto& entry = m_entries[stateObj.get()];
+            if (entry.stateRef.expired()) {
+                // The previous owner of this address is gone and the allocator handed it
+                // to a new object: its twin describes ids the new state object never made.
+                entry.backend.reset();
             }
-            m_stateRefs[key] = stateObj;
-            return m_backendObjects[key];
+            entry.stateRef = stateObj;
+            return entry.backend;
         }
 
-        iterator find(StateObject* stateObj) {
-            if (!IsAlive(stateObj)) {
-                EraseByKey(stateObj);
-                return m_backendObjects.end();
+        // Null when no live state object owns this key. The result points into the map, so
+        // it stays valid only until the next GetOrCreate/Find/CollectGarbage on this registry.
+        BackendPtr* Find(StateObject* stateObj) {
+            const auto entryIt = m_entries.find(stateObj);
+            if (entryIt == m_entries.end()) {
+                return nullptr;
             }
-            return m_backendObjects.find(stateObj);
+            if (entryIt->second.stateRef.expired()) {
+                m_entries.erase(entryIt);
+                return nullptr;
+            }
+            return &entryIt->second.backend;
         }
 
-        const_iterator find(StateObject* stateObj) const {
-            return const_cast<StateBackendObjectRegistry*>(this)->find(stateObj);
+        const BackendPtr* Find(StateObject* stateObj) const {
+            return const_cast<StateBackendObjectRegistry*>(this)->Find(stateObj);
         }
 
-        iterator begin() { return m_backendObjects.begin(); }
-        const_iterator begin() const { return m_backendObjects.begin(); }
-        iterator end() { return m_backendObjects.end(); }
-        const_iterator end() const { return m_backendObjects.end(); }
+        iterator begin() { return m_entries.begin(); }
+        const_iterator begin() const { return m_entries.begin(); }
+        iterator end() { return m_entries.end(); }
+        const_iterator end() const { return m_entries.end(); }
 
         void CollectGarbageIfNeeded() {
             ++m_gcTick;
@@ -72,19 +154,6 @@ namespace MobileGL::MG_Backend::DirectGLES {
         void CollectGarbageNow() { CollectGarbage(); }
 
     private:
-        bool IsAlive(StateObject* stateObj) const {
-            const auto trackedStateIt = m_stateRefs.find(stateObj);
-            if (trackedStateIt == m_stateRefs.end()) {
-                return false;
-            }
-            return !trackedStateIt->second.expired();
-        }
-
-        void EraseByKey(StateObject* stateObj) {
-            m_stateRefs.erase(stateObj);
-            m_backendObjects.erase(stateObj);
-        }
-
         void CollectGarbage() {
             if (m_isCollecting) {
                 return;
@@ -93,16 +162,15 @@ namespace MobileGL::MG_Backend::DirectGLES {
             m_isCollecting = true;
 
             Vector<StateObject*> staleKeys;
-            staleKeys.reserve(m_stateRefs.size());
-            for (const auto& [stateKey, stateWeakRef] : m_stateRefs) {
-                if (stateWeakRef.expired()) {
+            staleKeys.reserve(m_entries.size());
+            for (const auto& [stateKey, entry] : m_entries) {
+                if (entry.stateRef.expired()) {
                     staleKeys.push_back(stateKey);
                 }
             }
 
             for (auto* stateKey : staleKeys) {
-                m_stateRefs.erase(stateKey);
-                m_backendObjects.erase(stateKey);
+                m_entries.erase(stateKey);
             }
 
             m_isCollecting = false;
@@ -110,8 +178,7 @@ namespace MobileGL::MG_Backend::DirectGLES {
 
     private:
         static constexpr Uint32 kGCInterval = 1024;
-        StateRefMap m_stateRefs;
-        BackendMap m_backendObjects;
+        BackendMap m_entries;
         Uint32 m_gcTick = 0;
         Bool m_isCollecting = false;
     };
@@ -119,6 +186,43 @@ namespace MobileGL::MG_Backend::DirectGLES {
     namespace BufferImpl {
         const GLenum TempBufferTarget = GL_ARRAY_BUFFER;
 
+        // --- Buffer-mutation epoch -------------------------------------------------
+        // Manager-wide monotonic counter: it moves whenever ANY buffer resource may
+        // have gone from draw-clean to dirty. Draw-path memos read it once per pass
+        // (CurrentBufferMutationEpoch, acquire), re-run their IsBufferDrawClean
+        // probes only when it moved, and stamp the PRE-pass value after a pass in
+        // which every probe came up clean - so a concurrent bump lands strictly
+        // after the stamped value and forces a re-probe on the next pass no matter
+        // how the probe interleaved with the mutation. Conservative-correct: a bump
+        // never skips work, it only re-runs the probes once.
+        //
+        // Every clean->dirty transition path bumps it (BumpBufferMutationEpoch,
+        // release, AFTER the mutation lands so an acquire reader that still sees
+        // the old epoch cannot have missed the mutation):
+        //   * the frontend BufferBackendOps table - Respecify, SubData,
+        //     FlushMappedRange, AcquirePersistentMap, ReadbackFromGpu, OnDestroy -
+        //     which every frontend change-serial bump and every pending-range
+        //     queueing reaches while ops are registered (upload, orphan/respecify,
+        //     map flush/unmap writeback, persistent-map adoption, delete/pooling);
+        //   * backend-initiated shadow writebacks that bump the frontend change
+        //     serial without an op: transform-feedback capture readback
+        //     (XfbImpl::ReadbackCapturedRanges and the scatter path) and every
+        //     pack-PBO WritebackFromBackend site (glReadPixels/glGetTexImage);
+        //   * RegisterBufferBackendOps/UnregisterBufferBackendOps - while ops are
+        //     unregistered, frontend writes advance serials silently, so both edges
+        //     of that window re-open every memo;
+        //   * OnBackendContextDestroyed - the buffer context generation moved, so
+        //     every previously clean resource is invalid.
+        // NOT bumped (cleanliness provably unchanged): MarkGpuWritten (the backend
+        // copy is authoritative; IsBufferDrawClean does not consult it),
+        // NotifyContentWrite on a GPU-resident buffer (persistent-mapped resources
+        // are clean by construction), and EnsureBufferResource itself (it only
+        // repairs toward clean). A non-persistent map (draws on it are GL errors
+        // the frontend rejects) sets IsMapped without an op; persistent maps reach
+        // AcquirePersistentMap or (FLUSH_EXPLICIT) publish only via FlushMappedRange.
+        Uint64 CurrentBufferMutationEpoch();
+        void BumpBufferMutationEpoch();
+
         // The DirectGLES storage behind one frontend buffer. Owned (refcounted) by
         // the frontend BufferObject; immediate BufferBackendOps keep it current, so
         // draw-time "sync" reduces to ensuring the storage exists.
@@ -144,6 +248,12 @@ namespace MobileGL::MG_Backend::DirectGLES {
             Bool pendingRespecify = false;
             VecRange1D pendingRanges;
             std::mutex pendingMutex;
+            // Buffer-mutation epoch (see CurrentBufferMutationEpoch) at which this
+            // resource last probed IsBufferDrawClean == true, 0 = never (epochs start
+            // at 1). Written only on the draw thread; per-draw resource consumers
+            // (the UBO binding walk) skip the probe while their pre-pass epoch read
+            // matches, exactly like the per-VAO memo stamps.
+            Uint64 drawCleanEpoch = 0;
             // Zero-copy coherent persistent map (EXT_buffer_storage): the GL store is
             // immutable, persistently+coherently mapped, and persistentPtr is what the app
             // (and the frontend PipeResource) write into directly. While set, draw-time
@@ -169,6 +279,17 @@ namespace MobileGL::MG_Backend::DirectGLES {
         GLESBufferResource* EnsureBufferResource(const SharedPtr<MG_State::GLState::BufferObject>& bufferObject);
         // Existing resource or nullptr; performs no GL calls.
         GLESBufferResource* GetBufferResource(MG_State::GLState::BufferObject* bufferObject);
+        // True when EnsureBufferResource(frontend) would provably fall straight through
+        // every branch and do no work — i.e. `resource` is still the frontend's own
+        // resource, its id belongs to the live ES context, and either it is the
+        // zero-copy coherent persistent store (draw-time sync is a no-op by design) or
+        // the storage is initialized at the right size with no pending ops and a synced
+        // change serial while the buffer is not mapped (an active map may owe a
+        // per-draw persistent-range push, so it always takes the full path).
+        // `frontend` must be non-null and alive; the caller guarantees that by holding
+        // (or shadowing something that holds) a SharedPtr to it. Enables the per-VAO
+        // resolved-buffers memo to skip EnsureBufferResource on clean static buffers.
+        Bool IsBufferDrawClean(const MG_State::GLState::BufferObject* frontend, const GLESBufferResource* resource);
 
         // Deletes GL buffers whose owning frontend objects died (possibly on a
         // thread without a current ES context). Called from draw-time sync.
@@ -177,6 +298,21 @@ namespace MobileGL::MG_Backend::DirectGLES {
         // glBindBuffer with a redundant-bind cache for GL_ARRAY_BUFFER.
         void BindBufferId(GLenum target, Uint id);
         void InvalidateArrayBufferBindingCache();
+        // Redundant-bind caches for the driver-level GL_PIXEL_PACK/UNPACK_BUFFER
+        // bindings. Every backend readback (glReadPixels / pack-PBO map) and pixel
+        // upload site routes its binding through these so the shadow always matches
+        // the driver; the resting state between operations is 0, which keeps any
+        // path that implicitly assumes "no PBO bound" correct. Scrubbed when a
+        // buffer id is deleted/pooled (GL resets a deleted buffer's bindings to 0,
+        // and a recycled name matching the shadow would false-skip the rebind) and
+        // invalidated on MakeCurrent (context may reset).
+        void BindPixelPackBufferId(Uint id);
+        void BindPixelUnpackBufferId(Uint id);
+        void InvalidatePixelBufferBindingCaches();
+        // A GL buffer id is being deleted by code outside BufferImpl (e.g. the VAO
+        // client-attribute staging buffers): scrub every buffer-binding shadow that
+        // could false-skip when the name is recycled.
+        void NoteBufferIdDeleted(Uint id);
         // Redundant-bind cache for INDEXED buffer bindings (glBindBufferBase/Range on
         // GL_UNIFORM_BUFFER / GL_SHADER_STORAGE_BUFFER): skips the GL call when the
         // (id, range) already at that index matches, like the array-buffer/texture/
@@ -239,27 +375,137 @@ namespace MobileGL::MG_Backend::DirectGLES {
             Uint GetBackendVertexArrayId() const { return m_backendVAOId; }
             void Bind() const;
 
+            // Draw-path memo of SyncNeccessaryBuffers' attribute walk for this VAO: the
+            // distinct enabled-attribute buffers (deduped) and the index buffer, resolved
+            // to their backend resources once. Valid while the VAO's config version is
+            // unchanged — every attach/enable/disable/format mutation bumps it (the same
+            // invariant SyncToBackend's gate already leans on), and the VAO's attribute
+            // SharedPtrs pin each memoed frontend buffer for exactly that long, so the raw
+            // pointers cannot dangle on a hit. Per-buffer cleanliness is NOT memoed here:
+            // each hit re-checks IsBufferDrawClean (resource identity, context generation,
+            // pending ops, change serial) and falls back to EnsureBufferResource for just
+            // the dirty entries via their attribute index. The IBO entry is keyed on the
+            // slot's bound-object identity instead (its slot version is a wrapping Uint16
+            // and is not covered by the config version).
+            struct ResolvedDrawBuffers {
+                struct Entry {
+                    MG_State::GLState::BufferObject* frontend = nullptr;
+                    BufferImpl::GLESBufferResource* resource = nullptr;
+                    Uint8 attribIndex = 0;
+                };
+                Bool valid = false;
+                Uint32 configVersion = 0;
+                Uint count = 0;
+                Array<Entry, MG_State::GLState::VertexArrayObject::MAX_VERTEX_ATTRIBS> entries;
+                MG_State::GLState::BufferObject* iboFrontend = nullptr;
+                BufferImpl::GLESBufferResource* iboResource = nullptr;
+                // Buffer-mutation epoch (BufferImpl::CurrentBufferMutationEpoch) at which
+                // the LAST probe pass found every entry / the IBO clean; 0 = not stamped
+                // (epochs start at 1). While a stamp matches the pre-pass epoch read, the
+                // probes are skipped outright: any path that can dirty ANY buffer bumps
+                // the epoch (the exhaustive site list lives at the epoch declaration).
+                // The IBO stamp is only trusted together with the bound-object identity
+                // compare - the VAO's index slot can rebind with no epoch or config move.
+                Uint64 vboCleanEpoch = 0;
+                Uint64 iboCleanEpoch = 0;
+            };
+            ResolvedDrawBuffers& GetResolvedDrawBuffersMemo() { return m_resolvedDrawBuffers; }
+
+            // Memo for SyncCurrentVertexAttributeValues: which of a program's ACTIVE
+            // attribute locations lack an enabled array in this VAO (those read the
+            // context's current generic value instead of a buffer). Keyed on the VAO
+            // config version (enable/disable bumps it) and the program's active-location
+            // mask. Hosted per twin — the former function-static single entry missed on
+            // every draw once the app cycled VAOs, re-reading the cold attribute slots.
+            struct PendingAttribValueMask {
+                Bool valid = false;
+                Uint32 configVersion = 0;
+                Uint32 activeMask = 0;
+                Uint32 pendingMask = 0;
+            };
+            PendingAttribValueMask& GetPendingAttribValueMaskMemo() { return m_pendingAttribValueMask; }
+
         private:
+            ResolvedDrawBuffers m_resolvedDrawBuffers;
+            PendingAttribValueMask m_pendingAttribValueMask;
             Uint m_backendVAOId = 0;
             Array<Uint, MG_State::GLState::VertexArrayObject::MAX_VERTEX_ATTRIBS> m_clientAttributeBufferIds;
             Bool m_isInitialized = false;
             Uint16 m_syncedIndexBufferVersion = 0;
+            // Aggregate gate over the per-attribute walk below: the frontend bumps its config
+            // version on every per-attribute version bump (the three Bump*Version functions are
+            // its only writers), so an unchanged config version proves every per-attribute
+            // compare in SyncToBackend would come up clean. The index-buffer slot has its own
+            // version and is NOT covered. The Bool (not a sentinel value) marks "never synced".
+            Bool m_hasSyncedConfigVersion = false;
+            Uint32 m_syncedConfigVersion = 0;
             Array<MG_State::GLState::VertexAttributeVersion, MG_State::GLState::VertexArrayObject::MAX_VERTEX_ATTRIBS>
                 m_syncedAttributeVersions;
         };
 
         extern StateBackendObjectRegistry<MG_State::GLState::VertexArrayObject, BackendVertexArrayObject>
             g_backendVertexArrayObjects;
+
+        // Shadowed glBindVertexArray: every backend VAO bind goes through here so a
+        // draw's second bind of the same VAO (SyncToBackend, then PrepareForDraw's
+        // re-bind) reaches the driver once. Invalidate whenever the ES context is
+        // replaced - ids restart and the resting binding is 0 again.
+        void BindBackendVAOId(Uint id);
+        void InvalidateVAOBindingCache();
+        // ES resets the binding to 0 when the currently bound VAO is deleted.
+        void NoteVAOIdDeleted(Uint id);
     } // namespace VertexArrayImpl
 
     namespace TextureImpl {
         inline Bool IsSupportedTextureTarget(TextureTarget target) {
-            if (target == TextureTarget::Texture1D || target == TextureTarget::TextureRectangle ||
-                target == TextureTarget::Texture1DArray || target == TextureTarget::Texture2DArray)
-                return false;
+            // Every desktop-only target is stored on an ES one; see MapToBackendTextureTarget.
+            (void)target;
             return true;
         }
 
+        // ES has none of the desktop-only targets: 1D textures are stored as 2D (height 1), 1D
+        // arrays as 2D arrays (height 1, layers in depth), and rectangle textures as plain 2D -
+        // they are single-level and already clamp, so only the non-normalized coordinates differ.
+        // Must match the shader-side emulation: SPIRV-Cross handles 1D/1D-array itself, and
+        // ShaderCompiler::LowerRectImages rewrites rectangle images (declining any module
+        // whose lookups are not integer-coordinate, which SPIRV-Cross then still rejects).
+        inline TextureTarget MapToBackendTextureTarget(TextureTarget target) {
+            switch (target) {
+            case TextureTarget::Texture1D:
+            case TextureTarget::TextureRectangle:
+                return TextureTarget::Texture2D;
+            case TextureTarget::Texture1DArray:
+                return TextureTarget::Texture2DArray;
+            default:
+                return target;
+            }
+        }
+
+        inline GLenum ConvertTextureTargetToBackendGLEnum(TextureTarget target) {
+            return MG_Util::ConvertTextureTargetToGLEnum(MapToBackendTextureTarget(target));
+        }
+
+        inline GLenum ConvertTextureUploadTargetToBackendGLEnum(TextureUploadTarget uploadTarget) {
+            switch (uploadTarget) {
+            case TextureUploadTarget::Texture1D:
+            case TextureUploadTarget::TextureRectangle:
+                return GL_TEXTURE_2D;
+            case TextureUploadTarget::Texture1DArray:
+                return GL_TEXTURE_2D_ARRAY;
+            default:
+                return MG_Util::ConvertTextureUploadTargetToGLEnum(uploadTarget);
+            }
+        }
+
+        // 1D arrays store layers in the state-side height; the ES 2D-array image keeps height 1 and
+        // moves the layer count into depth.
+        inline IntVec3 GetBackendUploadSize(TextureTarget stateTarget, const IntVec3& texelSize) {
+            if (stateTarget == TextureTarget::Texture1DArray) {
+                return {texelSize.x(), 1, texelSize.y()};
+            }
+            return texelSize;
+        }
+
         inline Bool IsMultisampleTextureTarget(TextureTarget target) {
             return target == TextureTarget::Texture2DMultisample ||
                    target == TextureTarget::Texture2DMultisampleArray;
@@ -269,6 +515,25 @@ namespace MobileGL::MG_Backend::DirectGLES {
             return target == TextureTarget::Texture3D || target == TextureTarget::TextureCubeMap;
         }
 
+        // Components per texel the frontend format's client data carries, for the three-channel
+        // formats that can be widened to a four-channel colour-renderable target; 0 for everything
+        // else. See PrepareChannelWidenedUpload.
+        Uint GetWidenableClientComponentCount(TextureInternalFormat format);
+
+        // True when a widenable format's components are integer rather than normalized, which is
+        // what decides the synthetic alpha's value: GL_RGB8I and GL_RGB8_SNORM are both uploaded
+        // as GL_BYTE, but their 1.0 is 1 and 0x7F respectively.
+        Bool IsIntegerWidenableFormat(TextureInternalFormat format);
+
+        // Repacks three-component client data as four components with an alpha of 1.0 in
+        // `uploadType`, for a format the backend widened to keep a colour attachment renderable.
+        // Returns `data` untouched when no widening applies. Pure CPU and context-free so a unit
+        // test can exercise the exact packing the driver is handed; `widenedData` is the caller's
+        // scratch buffer and has to outlive the returned pointer.
+        const void* PrepareChannelWidenedUpload(Uint componentCount, const IntVec3& texelSize, const void* data,
+                                                SizeT byteSize, GLenum uploadType, Vector<Uint8>& widenedData,
+                                                Bool integerData = false);
+
         struct StateTextureBasicInfo { // Used for tracking texture state changes
             TextureInternalFormat internalFormat = TextureInternalFormat::Unknown;
             SizeT width = 0;
@@ -293,6 +558,12 @@ namespace MobileGL::MG_Backend::DirectGLES {
         class BackendTextureObject {
         public:
             BackendTextureObject();
+            // Deletes the GL texture (frontend glDeleteTextures used to leak every
+            // backend id for the context lifetime) and scrubs the binding/scratch-FBO
+            // shadows so a recycled name or heap address cannot false-skip a rebind.
+            ~BackendTextureObject();
+            BackendTextureObject(const BackendTextureObject&) = delete;
+            BackendTextureObject& operator=(const BackendTextureObject&) = delete;
             void SyncMipmapsToBackend(const SharedPtr<MG_State::GLState::ITextureObject>& stateTextureObject);
             void SyncBuiltinSamplerToBackend(const SharedPtr<MG_State::GLState::ITextureObject>& stateTextureObject);
             void SyncTextureParamsToBackend(const SharedPtr<MG_State::GLState::ITextureObject>& stateTextureObject);
@@ -300,14 +571,68 @@ namespace MobileGL::MG_Backend::DirectGLES {
             void Bind(GLenum target, Uint unit = TempTextureUnit);
             Uint GetBackendTextureId() const;
 
+            // Aggregate first-level clean gate for the per-draw trio
+            // SyncTextureParamsToBackend + SyncBuiltinSamplerToBackend +
+            // SyncMipmapsToBackend: EXACTLY the conjunction of their own early-outs
+            // (params version == synced params version; builtin-sampler version ==
+            // synced sampler version; and SyncMipmapsToBackend's cheap gate - stamped
+            // trio + content version + Mipmap storage). True means each of the three
+            // would provably return without work, so the caller may skip the calls;
+            // false only falls through to the three calls, whose own gates re-decide
+            // individually - this gate must never be MORE permissive than they are.
+            // `contextId`/`samplingGeneration` are the frontend context's current
+            // values, hoisted by the caller so a per-draw list walk reads them once
+            // instead of per texture. `t` must be the live frontend texture.
+            Bool IsDrawSyncClean(const MG_State::GLState::ITextureObject* t, Uint64 contextId,
+                                 Uint64 samplingGeneration) const {
+                if (!m_isInitialized || m_syncedShapeContextId == 0 || m_syncedShapeContextId != contextId ||
+                    m_syncedShapeGeneration != samplingGeneration) {
+                    return false;
+                }
+                const Uint16 paramsVersion = t->GetTextureParamsVersion();
+                if (m_syncedShapeParamsVersion != paramsVersion || m_syncedTextureParamsVersion != paramsVersion) {
+                    return false;
+                }
+                if (m_syncedContentVersion == 0 || m_syncedContentVersion != t->GetContentVersion()) {
+                    return false;
+                }
+                const auto& samplerObject = t->GetSamplerObject();
+                if (!samplerObject || m_syncedSamplerVersion != samplerObject->GetVersion()) {
+                    return false;
+                }
+                return t->GetStorageType() == TextureStorageType::Mipmap;
+            }
+
         private:
             void RecreateBackendTexture();
 
             Uint m_backendTextureId = 0;
+            // ES context generation the id was created under; a dtor running after
+            // that context died must not delete a foreign (recycled) name.
+            Uint m_contextGeneration = 0;
             Bool m_isInitialized = false;
             Bool m_imageBindableStorageRequired = false;
             Bool m_backendStorageImmutable = false;
             StateTextureBasicInfo m_prevTextureInfo;
+            // Frontend content version at the last completed mipmap sync. The per-draw
+            // clean probe compares this before rebuilding shape info and scanning
+            // per-level dirty flags; 0 never matches a real version (they start at 1).
+            Uint64 m_syncedContentVersion = 0;
+            // First-level clean gate for SyncMipmapsToBackend, checked before even the
+            // IsComplete()/shape-probe walk. Valid only as a trio with the content and
+            // texture-params versions: the context's sampling-resolution generation moves on
+            // EVERY texture-shape mutation (BumpShapeVersion is the only writer of shape and
+            // unconditionally bumps it), the content version on every CPU pixel mutation, and
+            // the params version covers SetSamples/SetFixedSampleLocations, which bump neither
+            // of the other two but feed the shape probe. The context id pins the generation to
+            // the context that produced it - generations restart at 0 with a new context, and a
+            // texture is owned by exactly one context (share groups are not implemented), so a
+            // mutation can never happen under a context this key does not name. 0 = never
+            // stamped (real context ids start at 1). Backend-side invalidation rides on
+            // m_isInitialized: RequireImageBindableStorage and RecreateBackendTexture clear it.
+            Uint64 m_syncedShapeContextId = 0;
+            Uint64 m_syncedShapeGeneration = 0;
+            Uint16 m_syncedShapeParamsVersion = 0;
             SamplerParameters m_cacheSamplerParameters;
             UintVec2 m_cacheLodRange = {0, 1000};
             FloatVec4 m_cacheBorderColor = {0.0f, 0.0f, 0.0f, 0.0f};
@@ -324,10 +649,17 @@ namespace MobileGL::MG_Backend::DirectGLES {
         SharedPtr<BackendTextureObject>& SyncTextureObjectToBackend(
             const SharedPtr<MG_State::GLState::ITextureObject>& textureObject,
             Bool imageBindableStorageRequired = false);
+        // Brings every texture the next draw reads - the touched units' bindings and the draw
+        // FBO's texture attachments - onto the backend, through the two borrowed-pair memos
+        // documented at their definitions. Declared here so tests can drive those memos directly.
+        void SyncNeccessaryTextures();
         extern Array<Array<BackendTextureObject*, (SizeT)TextureTarget::TextureTargetCount>,
                      MG_State::GLState::TextureState::MAX_TEXTURE_IMAGE_UNITS>
             g_boundTexturesCache;
         extern Uint g_activeTextureUnit;
+        // Bumped when the backend ES context is destroyed; texture ids stamped with
+        // an older generation belong to a dead context and must not be deleted.
+        extern Uint g_textureContextGeneration;
     } // namespace TextureImpl
 
     namespace FramebufferImpl {
@@ -336,6 +668,10 @@ namespace MobileGL::MG_Backend::DirectGLES {
             BackendFramebufferObject();
             void SyncToBackend(const SharedPtr<MG_State::GLState::FramebufferObject>& stateFBOObject,
                                FramebufferTarget asTarget);
+            // Apply only this FBO's read buffer (glReadBuffer) to the backend. Split out so it can
+            // still run when SyncCurrentFBO skips the READ-target sync because the same GL FBO is
+            // bound as both draw and read (otherwise glReadBuffer changes would be silently dropped).
+            void SyncReadBufferToBackend(const SharedPtr<MG_State::GLState::FramebufferObject>& stateFBOObject);
             void InvalidateSyncedState();
             Uint GetBackendFramebufferId() const { return m_backendFBOId; }
             void Bind(FramebufferTarget target) const;
@@ -359,6 +695,28 @@ namespace MobileGL::MG_Backend::DirectGLES {
                this array could be provided as data directly to ES `glDrawBuffers` function
              */
             GLenum m_backendDrawBuffers[MG_State::GLState::FramebufferObject::MAX_DRAW_BUFFERS] = {GL_NONE};
+
+            static constexpr Uint MAX_COLOR_ATTACHMENT_SLOTS =
+                static_cast<Uint>(FramebufferAttachmentType::Color31) -
+                static_cast<Uint>(FramebufferAttachmentType::Color0) + 1;
+            /* Where each frontend GL_COLOR_ATTACHMENTn image physically lives in the backend ES
+               framebuffer, as a GL_COLOR_ATTACHMENTm enum. ES only accepts glDrawBuffers bufs[s] ==
+               GL_COLOR_ATTACHMENTs, so a GL draw-buffer slot s naming attachment a forces a's image
+               under backend slot s. This table is the single owner of that decision and is kept a
+               PERMUTATION of the backend colour slots: every other attachment keeps its identity
+               slot when that slot survived, and is parked on the lowest free slot when it did not.
+               Deriving the point per-query from the draw-buffer array instead handed the identity
+               point to any attachment that was not a draw buffer - i.e. exactly the point a
+               relocated draw buffer had just taken over. The permutation is only true of the
+               PHYSICAL framebuffer because the attachment loop detaches a point whose frontend
+               owner is empty; do not remove that detach. */
+            GLenum m_backendColorSlots[MAX_COLOR_ATTACHMENT_SLOTS] = {GL_NONE};
+            /* Rebuild m_backendColorSlots from the frontend draw-buffer array. Returns true when any
+               attachment moved, i.e. when the physical attachments and the memoised read buffer have
+               to be re-applied. */
+            Bool RecomputeBackendColorSlots(
+                const MG_State::GLState::FramebufferObject::FramebufferAttachmentArray& stateDrawBuffers);
+
             FramebufferAttachmentType m_frontendReadBuffer = FramebufferAttachmentType::Color0;
             GLenum m_backendReadBuffer = GL_COLOR_ATTACHMENT0;
 
@@ -368,9 +726,187 @@ namespace MobileGL::MG_Backend::DirectGLES {
 
         extern StateBackendObjectRegistry<MG_State::GLState::FramebufferObject, BackendFramebufferObject>
             g_backendFramebufferObjects;
-        extern Array<Uint16, SizeT(FramebufferTarget::FramebufferTargetCount)> g_fboBindVersions;
+        // True when the read buffer names a fixed-point (norm/snorm) attachment that the
+        // backend actually stores in a floating-point format. GL clamps a read from a
+        // fixed-point colour buffer to [0,1] (GL_CLAMP_READ_COLOR defaults to
+        // GL_FIXED_ONLY); the substituted float storage would not, so the readback path
+        // has to apply the clamp itself.
+        Bool IsFixedPointFallbackReadAttachment();
+
+        // True when the read buffer names a three-channel attachment the backend actually stores
+        // in a four-channel format (the colour-renderable widening). A format without alpha reads
+        // back as 1.0, so the readback path has to overwrite the alpha the draw left behind -
+        // unconditionally, since this is the format's own semantics rather than the
+        // GL_CLAMP_READ_COLOR rule the clamp above implements.
+        Bool IsAlphaWidenedFallbackReadAttachment();
+
+        // True when this attachment's storage carries an alpha channel its frontend format does
+        // not (the three-channel colour-renderable widening).
+        Bool IsAlphaWidenedColorAttachment(const MG_State::GLState::FramebufferAttachmentObject& attachmentObject);
+
+        // Bit i set = DRAW BUFFER i of `fbo` resolves to a colour attachment the backend widened
+        // from three channels to four. Indexed by draw-buffer slot, not by attachment point,
+        // because that is what glColorMaski / glClearBufferfv address.
+        Uint32 ComputeAlphaWidenedDrawBufferMask(const MG_State::GLState::FramebufferObject& fbo);
+
+        // The same mask for whatever is currently bound to GL_DRAW_FRAMEBUFFER, recomputed by
+        // SyncCurrentFBO (BackendFramebufferObject::SyncToBackend for the DRAW target, and reset
+        // to 0 on the default framebuffer). Read by the draw/clear state sync, so it is only
+        // trustworthy after SyncCurrentFBO has run in the same entry point.
+        //
+        // WHY IT EXISTS (the dst-alpha discipline). A widened attachment has a real alpha channel
+        // the application's format does not, and GL says a missing channel reads as 1.0. Readback
+        // can paper over that (ForceWideReadAlphaToOne), but GL_DST_ALPHA /
+        // GL_ONE_MINUS_DST_ALPHA blending and glBlitFramebuffer read the STORED alpha inside the
+        // driver where no interception is possible. So the stored alpha is kept at 1.0 instead:
+        // a clear touching a widened buffer writes alpha 1.0, and every draw into it has its
+        // alpha write mask forced off, so nothing can ever move it again. The application's own
+        // colour mask is untouched - glGet(GL_COLOR_WRITEMASK) still reports what it set.
+        extern Uint32 g_alphaWidenedDrawBufferMask;
+
+        // Bit i set = DRAW BUFFER i of the framebuffer bound as DRAW resolves to a colour
+        // attachment with an INTEGER format. Recomputed beside the mask above and for its sake:
+        // glClearBufferfv on an integer colour buffer is GL_INVALID_OPERATION, so the
+        // per-draw-buffer clear route the widening needs has to stand down when one is present.
+        // (glClear on an integer colour buffer is left undefined by ES in the first place, and
+        // an application that wants a defined answer has to call glClearBufferuiv/iv - which does
+        // carry the widened alpha substitution.)
+        extern Uint32 g_integerColorDrawBufferMask;
+
+        // The colour a clear has to hand the driver for one draw buffer: the application's value,
+        // except that a widened attachment's alpha is replaced by the 1.0 its three-channel
+        // format implies. `one` is 1.0 encoded in the clear call's own component type - the
+        // integer clears carry the integer 1, the float clear carries 1.0f.
+        //
+        // Returns `value` itself when nothing is substituted, so the ordinary path allocates and
+        // copies nothing; `scratch` is the caller's buffer and has to outlive the returned
+        // pointer. Free of GL state on purpose, so the substitution can be unit-tested exactly as
+        // the driver sees it.
+        template <typename T>
+        const T* SubstituteWidenedClearAlpha(const T* value, Bool widened, T one, T (&scratch)[4]) {
+            if (!widened || value == nullptr) {
+                return value;
+            }
+            scratch[0] = value[0];
+            scratch[1] = value[1];
+            scratch[2] = value[2];
+            scratch[3] = one;
+            return scratch;
+        }
+
+        // What SyncCurrentFBO last pushed for each target, as a (binding, object, revision)
+        // triple; it re-syncs unless all three still match. Stamped by SyncCurrentFBO and
+        // ForceBindCurrentFBO, cleared by InvalidateFramebufferBindingCache. The three are
+        // only meaningful together - see SyncCurrentFBO.
+        //
+        // The binding slot's own version, which changes whenever a different object is bound
+        // to this target. Distinguishes a rebind from an in-place edit, and keeps the raw
+        // pointer below from matching an address the allocator recycled for a new FBO.
+        extern Array<Uint16, SizeT(FramebufferTarget::FramebufferTargetCount)> g_fboSyncedSlotVersions;
+        // Tracks the bound FBO's object version (bumped on any attachment/drawbuffer change)
+        // per target: re-attaching textures or changing draw buffers on an already-bound FBO
+        // must re-sync it even when the binding-slot version has not moved.
+        extern Array<Uint16, SizeT(FramebufferTarget::FramebufferTargetCount)> g_fboSyncedObjectVersions;
+        // Which object was synced. Raw and never dereferenced: only compared for identity.
+        extern Array<MG_State::GLState::FramebufferObject*, SizeT(FramebufferTarget::FramebufferTargetCount)>
+            g_fboSyncedObjects;
+
+        // Driver-level READ/DRAW framebuffer-binding shadow. Every backend
+        // glBindFramebuffer routes through BindFramebufferId so scoped helpers can
+        // save/restore the current binding without a glGetIntegerv round-trip (that
+        // query forces a driver pipeline sync) and so redundant rebinds no-op.
+        // Starts unknown; the first CurrentFramebufferBinding() query pins it from
+        // the driver once. Invalidated on MakeCurrent (context may reset).
+        // GL_FRAMEBUFFER binds both targets.
+        void BindFramebufferId(GLenum fbTarget, Uint id);
+        Uint CurrentFramebufferBinding(FramebufferTarget target);
+        void InvalidateFramebufferBindingCache();
     } // namespace FramebufferImpl
 
+    // Shared scratch framebuffers for the readback/copy/blit emulation paths, with a
+    // driver-side attachment shadow: repeated uses skip redundant detach/attach GL
+    // calls, and an attachment left by one use (e.g. a depth copy's DEPTH_STENCIL
+    // texture) is detached exactly when a later use of another aspect would
+    // otherwise inherit it (stale cross-aspect attachments made the shared temp FBO
+    // incomplete and silently degraded later readbacks).
+    namespace ScratchFBOImpl {
+        struct ScratchFramebuffer {
+            Uint id = 0;
+            // false => attachment state unknown; scrub every point on next use.
+            // A fresh FBO starts with nothing attached, so creation sets it true.
+            Bool attachmentsKnown = false;
+            Uint colorTex = 0;
+            GLenum colorTarget = 0;
+            GLint colorLevel = 0;
+            GLint colorLayer = -1; // >= 0 => attached via glFramebufferTextureLayer
+            Uint depthTex = 0;
+            GLenum depthTarget = 0;
+            GLint depthLevel = 0;
+            Bool depthHasStencil = false;
+            // Per-FBO read/draw buffer state (0 = unknown, set on first use).
+            GLenum readBuffer = 0;
+            GLenum drawBuffer = 0;
+        };
+        ScratchFramebuffer& TempFramebuffer();     // GetTexImage READ / CopyTex*Image2D depth DRAW
+        ScratchFramebuffer& BlitReadFramebuffer(); // texture-to-texture blit source
+        ScratchFramebuffer& BlitDrawFramebuffer(); // texture-to-texture blit destination
+        // Returns the GL id, generating it if needed (requires a current ES context).
+        Uint EnsureId(ScratchFramebuffer& fb);
+        // The fb must currently be bound at fbTarget (glReadBuffer/glDrawBuffers
+        // target the READ/DRAW binding respectively). Each Ensure* performs the
+        // minimal detach/attach set and keeps the shadow in sync; a failed attach
+        // records the point as detached so the completeness check fails instead of
+        // silently reading a stale attachment.
+        void EnsureColorAttachment2D(ScratchFramebuffer& fb, GLenum fbTarget, Uint tex, GLenum texTarget, GLint level);
+        void EnsureColorAttachmentLayer(ScratchFramebuffer& fb, GLenum fbTarget, Uint tex, GLint level, GLint layer);
+        void EnsureDepthAttachment2D(ScratchFramebuffer& fb, GLenum fbTarget, Uint tex, GLenum texTarget, GLint level,
+                                     Bool withStencil);
+        void EnsureNoColorAttachment(ScratchFramebuffer& fb, GLenum fbTarget);
+        void EnsureNoDepthAttachment(ScratchFramebuffer& fb, GLenum fbTarget);
+        void EnsureReadBuffer(ScratchFramebuffer& fb, GLenum readBuffer);
+        void EnsureDrawBuffer(ScratchFramebuffer& fb, GLenum drawBuffer);
+        // A 1x1 RGBA8-renderbuffer-complete FBO (GenerateMipmap needs a complete
+        // binding while respecifying texture storage). Attachment is set once at
+        // creation and never changes.
+        Uint EnsureCompleteTinyFramebufferId();
+        // A backend texture id is being deleted or respecified: a scratch FBO still
+        // referencing it would hold a dangling attachment (ES only auto-detaches
+        // from the *bound* framebuffer), and a recycled name could false-skip a
+        // re-attach; force a full scrub on next use.
+        void NoteTextureIdDeleted(Uint textureId);
+        // The ES context (and the scratch FBO ids with it) is going away.
+        void OnBackendContextDestroyed();
+    } // namespace ScratchFBOImpl
+
+    // Driver-level GL_PACK_* pixel-store shadow, the readback-side sibling of the
+    // upload path's ScopedDefaultUnpackState (Managers.cpp): the backend PACK state
+    // is written ONLY through ApplyPackState, so scoped helpers can save/restore it
+    // from the shadow instead of glGetIntegerv (which forces a driver pipeline
+    // sync), and redundant glPixelStorei calls no-op. The first Apply/Current call
+    // pins the driver to the shadow by writing all fields once. Invalidated on
+    // MakeCurrent (context may reset). PACK_IMAGE_HEIGHT/SKIP_IMAGES/SWAP_BYTES/
+    // LSB_FIRST have no ES equivalents; readbacks honor them on the CPU from the
+    // frontend context state instead.
+    namespace PixelStoreImpl {
+        struct PackState {
+            GLint Alignment = 4;
+            GLint RowLength = 0;
+            GLint SkipRows = 0;
+            GLint SkipPixels = 0;
+            Bool operator==(const PackState& o) const {
+                return Alignment == o.Alignment && RowLength == o.RowLength && SkipRows == o.SkipRows &&
+                       SkipPixels == o.SkipPixels;
+            }
+        };
+        void ApplyPackState(const PackState& desired);
+        PackState CurrentPackState();
+        void InvalidatePackStateCache();
+    } // namespace PixelStoreImpl
+
+    namespace SamplerImpl {
+        class BackendSamplerObject; // for PrgramImpl's sampler-pass memo rows below
+    }
+
     // Image uniforms take their unit from the layout(binding=N) qualifier baked into
     // the transpiled ESSL; unlike samplers they must not (and in ES cannot) be
     // assigned through glUniform1i.
@@ -409,6 +945,49 @@ namespace MobileGL::MG_Backend::DirectGLES {
                 Int backendLocation = -1;
                 GLenum uniformType = 0;
                 Int lastAssignedUnit = -1;
+                // Location of this sampler's emulated GL_TEXTURE_LOD_BIAS uniform
+                // (PrgramImpl::EmulateTextureLodBias), -1 when the shader has none.
+                // lastAssignedLodBias mirrors the value the program currently holds,
+                // so an unbiased shader issues no per-draw glUniform1f at all.
+                Int lodBiasLocation = -1;
+                Float lastAssignedLodBias = 0.0f;
+            };
+
+            // Memo of the whole per-draw sampler-uniform pass (glUniform1i unit
+            // assignments, lod-bias uniform, raw-depth-fetch substitution and the
+            // per-unit sampler-object binds) in BindCurrentProgramWithResources.
+            // The pass is a pure function of the keys below, and its only driver-side
+            // effect is the sampler binding of each sampled unit, so replaying it as
+            // "do nothing" additionally requires those bindings to still be on the
+            // driver - the per-entry row compare against g_boundSamplersCache (the
+            // shadow every sampler bind in this backend already routes through).
+            //
+            // Invalidation enumeration:
+            //  * sampler-uniform unit assignment (glUniform1i) and uniform-block
+            //    binding edits -> frontend backendStateVersion;
+            //  * any texture/sampler bind moving on any unit (incl. the high-water
+            //    mark moving) -> unitBindingsEpoch;
+            //  * any sampler parameter (incl. lod bias, compare mode) or texture
+            //    shape/format change -> samplingGeneration;
+            //  * another frontend context -> contextId (never-reused id);
+            //  * ES context recreation -> textureContextGeneration;
+            //  * relink / backend program rebuild -> SyncToBackend resets `valid`
+            //    (it rebuilds m_samplerUniformBindings, whose lastAssignedUnit /
+            //    lastAssignedLodBias dedup state this memo leans on);
+            //  * any other writer moving a sampled unit's sampler binding
+            //    (BindCurrentUnitSamplers on a unit-sampler change, scratch binds)
+            //    -> the row snapshot compare.
+            struct SamplerPassMemo {
+                static constexpr SizeT kMaxEntries = 16;
+                Bool valid = false;
+                Uint8 count = 0;
+                Uint64 contextId = 0;
+                Uint64 unitBindingsEpoch = 0;
+                Uint64 samplingGeneration = 0;
+                Uint32 backendStateVersion = 0;
+                Uint textureContextGeneration = 0;
+                Array<Uint8, kMaxEntries> units{};
+                Array<SamplerImpl::BackendSamplerObject*, kMaxEntries> rows{};
             };
 
             BackendProgramObjectImpl();
@@ -418,11 +997,19 @@ namespace MobileGL::MG_Backend::DirectGLES {
             void SetBaseInstance(Uint32 baseInstance) const;
             void SetBaseInstanceWordIndex(Int32 wordIndex) const;
             void SetDrawID(Uint32 drawId) const;
+            // True when the transpiled program kept a gl_DrawID uniform, i.e. SetDrawID
+            // actually reaches a shader read rather than being discarded.
+            Bool ReadsDrawID() const { return m_drawIdUniformLocation >= 0; }
             Int GetIndirectParamsBinding() const { return m_indirectParamsBinding; }
             Uint GetBackendProgramId() const { return m_backendProgramId; }
+            // False when the last SyncToBackend could not produce a usable program (a
+            // shader failed to transpile or compile, or the link itself failed). Use()
+            // must not leave the previously bound program current in that case.
+            Bool IsBackendProgramUsable() const { return m_backendProgramUsable; }
             Uint GetBackendGlobalUBOId() const { return m_backendGlobalUBOId; }
             Uint32 GetSnormFallbackClampOutputMask() const { return m_snormFallbackClampOutputMask; }
             Uint32 GetUnormFallbackClampOutputMask() const { return m_unormFallbackClampOutputMask; }
+            Uint GetFragColorBroadcastCount() const { return m_fragColorBroadcastCount; }
 
             Bool HasGlobalUboBlock() const { return m_globalUboBackendBlockIndex >= 0; }
             const Vector<Int>& GetUniformBlockBackendIndices() const { return m_uniformBlockBackendIndices; }
@@ -434,6 +1021,7 @@ namespace MobileGL::MG_Backend::DirectGLES {
             // reflected size when the transpiled block pads differently).
             Int GetGlobalUboBackendBlockSize() const { return m_globalUboBackendBlockSize; }
             BufferImpl::UboRingAllocation& GetGlobalUboRingAllocation() { return m_globalUboRingAllocation; }
+            SamplerPassMemo& GetSamplerPassMemo() { return m_samplerPassMemo; }
             // Frontend link version this backend program (and its resource caches) was
             // built from; a mismatch means every link-derived cache here is stale.
             Uint32 GetSyncedLinkVersion() const { return m_syncedLinkVersion; }
@@ -449,7 +1037,11 @@ namespace MobileGL::MG_Backend::DirectGLES {
             Int m_indirectParamsBinding = -1;
             Uint32 m_snormFallbackClampOutputMask = 0;
             Uint32 m_unormFallbackClampOutputMask = 0;
+            // Draw buffers a legacy gl_FragColor write has to reach (see
+            // PrgramImpl::BroadcastLegacyFragColor); 1 keeps the plain single-output shader.
+            Uint m_fragColorBroadcastCount = 1;
             Bool m_isInitialized = false;
+            Bool m_backendProgramUsable = false;
 
             Int m_globalUboBackendBlockIndex = -1;
             Int m_globalUboBackendBlockSize = 0;
@@ -458,16 +1050,37 @@ namespace MobileGL::MG_Backend::DirectGLES {
             Uint32 m_lastUploadedGlobalUboVersion = ~0u;
             BufferImpl::UboRingAllocation m_globalUboRingAllocation;
             Uint32 m_syncedLinkVersion = ~0u;
+            SamplerPassMemo m_samplerPassMemo;
         };
 
         extern Uint32 g_snormFallbackClampOutputMask;
         extern Uint32 g_unormFallbackClampOutputMask;
+        // Draw buffers the current draw framebuffer enables. Like the clamp masks above it
+        // is framebuffer state that the shader has to be compiled against, so a program
+        // whose snapshot no longer matches is relinked.
+        extern Uint g_fragColorBroadcastCount;
         // Backend id of the last glUseProgram issued through this backend; lets Use()
         // skip redundant rebinds. Reset to 0 wherever glUseProgram(0) is issued or the
         // ES context is recreated.
         extern Uint g_lastUsedBackendProgramId;
         extern StateBackendObjectRegistry<MG_State::GLState::ProgramObject, BackendProgramObjectImpl>
             g_backendProgramObjects;
+
+        // Points one shader storage block of an ALREADY-LINKED backend program at
+        // `binding`. `blockName` is the frontend interface-query spelling; the real
+        // driver's own index for it is looked up here, because the transpiled ESSL's
+        // block order is not the frontend's. Returns false when the block does not exist
+        // on the backend program (eliminated as unused, or the driver lacks the entry
+        // points), which is not an error - GL_BUFFER_BINDING is served from the frontend
+        // record either way.
+        Bool ApplyShaderStorageBlockBinding(Uint backendProgramId, const String& blockName, Uint binding);
+        // Replays every glShaderStorageBlockBinding recorded on the program onto a backend
+        // program that was just built. The frontend record is authoritative (only the
+        // shader's DECLARED binding survives in the SPIR-V), so without this replay any
+        // rebuild would silently revert rebound blocks. Mirrors DirectVulkan's
+        // reseed-on-rebuild in BuildProgramResourceCache.
+        void ReseedShaderStorageBlockBindings(Uint backendProgramId,
+                                              const MG_State::GLState::ProgramObject& stateProgramObject);
     } // namespace PrgramImpl
 
     namespace SamplerImpl {

MobileGL/MG_Backend/DirectGLES/MultiDraw.cpp

@@ -0,0 +1,894 @@
+// MobileGL - MobileGL/MG_Backend/DirectGLES/MultiDraw.cpp
+// Copyright (c) 2025-2026 MobileGL-Dev
+// Licensed under the GNU Lesser General Public License v3.0:
+//   https://www.gnu.org/licenses/gpl-3.0.txt
+//   https://www.gnu.org/licenses/lgpl-3.0.txt
+// SPDX-License-Identifier: LGPL-3.0-only
+// End of Source File Header
+
+#include "MultiDraw.h"
+#include "Managers.h"
+#include <MG_State/GLState/Core.h>
+#include <cstring>
+#include <limits>
+
+namespace MobileGL::MG_Backend::DirectGLES::MultiDrawImpl {
+    using MG_Config::GLESMultiDrawMode;
+
+    namespace {
+        // ---------------------------------------------------------------------------
+        // Batch shape
+        // ---------------------------------------------------------------------------
+
+        SizeT IndexTypeSize(GLenum type) {
+            switch (type) {
+            case GL_UNSIGNED_BYTE: return 1;
+            case GL_UNSIGNED_SHORT: return 2;
+            case GL_UNSIGNED_INT: return 4;
+            default: return 0;
+            }
+        }
+
+        // The all-ones value of an index type, which is what GL restarts on once
+        // primitive restart is in play. CheckPrimitiveRestartSupported has already
+        // rejected the arbitrary-index form of GL_PRIMITIVE_RESTART, so an enabled
+        // restart always restarts here and nowhere else.
+        Uint32 RestartSentinelFor(GLenum type) {
+            switch (type) {
+            case GL_UNSIGNED_BYTE: return 0xFFu;
+            case GL_UNSIGNED_SHORT: return 0xFFFFu;
+            default: return 0xFFFFFFFFu;
+            }
+        }
+
+        Bool RestartActive() {
+            return MG_State::pGLContext->IsCapabilityEnabled(CapabilityInput::PrimitiveRestart) ||
+                   MG_State::pGLContext->IsCapabilityEnabled(CapabilityInput::PrimitiveRestartFixedIndex);
+        }
+
+        // Vertices per primitive for the modes whose sub-draws may be concatenated into a
+        // single draw without changing the primitive stream. Zero for strip/loop/fan modes
+        // (concatenation would weld one sub-draw's last primitive to the next sub-draw's
+        // first) and for GL_PATCHES, whose primitive size is dynamic tessellation state.
+        Uint32 ConcatenablePrimitiveSize(GLenum mode) {
+            switch (mode) {
+            case GL_POINTS: return 1;
+            case GL_LINES: return 2;
+            case GL_TRIANGLES: return 3;
+            case GL_LINES_ADJACENCY: return 4;
+            case GL_TRIANGLES_ADJACENCY: return 6;
+            default: return 0;
+            }
+        }
+
+        // Beyond this an emulated batch would ask for a scratch allocation measured in
+        // hundreds of megabytes (and the scratch ring never shrinks again); decline and let
+        // a per-sub-draw tier handle it instead of trying and failing inside the driver.
+        constexpr SizeT kMaxFlattenedIndices = SizeT{1} << 24;
+
+        // The flattening dispatch is one invocation per output index. ES 3.1 only
+        // guarantees 65535 work groups per dimension, and exceeding it makes
+        // glDispatchCompute an INVALID_VALUE no-op - which would leave the draw reading an
+        // uninitialised index buffer rather than failing visibly. Cap the tier there
+        // instead of querying: 4.19M indices is far past any real multi-draw batch, and
+        // beyond it the per-sub-draw tiers are the better answer anyway.
+        constexpr SizeT kComputeWorkGroupSize = 64;
+        constexpr SizeT kMaxComputeWorkGroups = 65535;
+        constexpr SizeT kMaxComputeFlattenedIndices = kMaxComputeWorkGroups * kComputeWorkGroupSize;
+
+        Uint BoundDrawIndirectBufferId() {
+            const auto& indirect =
+                MG_State::pGLContext->GetBufferBindingSlot(BufferTarget::DrawIndirect).GetBoundObject();
+            if (!indirect) return 0;
+            const auto* resource = BufferImpl::EnsureBufferResource(indirect);
+            return resource ? resource->id : 0;
+        }
+
+        const SharedPtr<MG_State::GLState::BufferObject>& BoundIndexBuffer() {
+            static const SharedPtr<MG_State::GLState::BufferObject> none;
+            const auto& vao = MG_State::pGLContext->GetBoundVertexArray();
+            if (!vao) return none;
+            return vao->GetIndexBufferBindingSlot().GetBoundObject();
+        }
+
+        // The GL name PrepareForDraw left on GL_ELEMENT_ARRAY_BUFFER, i.e. what a tier
+        // that swaps in a scratch index buffer has to put back. Restoring the exact name
+        // matters beyond tidiness: the VAO twin memoises that it already synced this
+        // index binding and will not re-issue it on the next draw.
+        Uint BoundIndexBufferId() {
+            const auto& ibo = BoundIndexBuffer();
+            if (!ibo) return 0;
+            const auto* resource = BufferImpl::EnsureBufferResource(ibo);
+            return resource ? resource->id : 0;
+        }
+
+        // ---------------------------------------------------------------------------
+        // Scratch GL objects
+        //
+        // All of them belong to the ES context and are abandoned (not deleted) when it
+        // dies, exactly like XfbImpl's scatter buffer: the names are the dead context's
+        // to reclaim, and deleting them would target whatever the successor context
+        // handed out for the same name.
+        // ---------------------------------------------------------------------------
+
+        struct ScratchBuffer {
+            Uint id = 0;
+            SizeT capacity = 0;
+            SizeT cursor = 0; // ring buffers only: next free byte
+        };
+
+        ScratchBuffer g_indirectCommands; // synthesized DrawElementsIndirectCommand array
+        ScratchBuffer g_rebasedIndices;   // CPU-rebased index stream
+        ScratchBuffer g_drawInfo;         // compute tier: per-sub-draw descriptors
+        ScratchBuffer g_flattenedIndices; // compute tier: flattened index stream
+
+        Uint g_computeProgram = 0;
+        Bool g_computeProgramFailed = false;
+        GLint g_uElementSize = -1;
+        GLint g_uDrawCount = -1;
+        GLint g_uTotalIndices = -1;
+
+        // Reused staging, so a steady stream of batches allocates nothing.
+        Vector<DrawElementsIndirectCommand> g_commandStaging;
+        Vector<Uint32> g_indexStaging;
+        Vector<Uint32> g_drawInfoStaging;
+        Vector<GLint> g_zeroBaseVertices;
+
+        // Everything below stages through GL_ARRAY_BUFFER, the manager-wide staging target
+        // (BufferImpl::TempBufferTarget); binding it disturbs no VAO state.
+        Bool EnsureScratchName(ScratchBuffer& buffer) {
+            if (buffer.id != 0) return true;
+            GLuint id = 0;
+            g_GLESFuncs.glGenBuffers(1, &id);
+            if (id == 0) return false;
+            buffer.id = id;
+            buffer.capacity = 0;
+            buffer.cursor = 0;
+            return true;
+        }
+
+        // Whole-buffer upload, for the two buffers that are read from offset 0 because they
+        // are bound as storage blocks. Respecifies rather than sub-updates: glBufferData
+        // orphans the previous store, so the upload never waits on a dispatch still reading
+        // the old contents out of the same name.
+        Bool UploadScratch(ScratchBuffer& buffer, SizeT bytes, const void* data) {
+            if (bytes == 0) return true;
+            if (!EnsureScratchName(buffer)) return false;
+            BufferImpl::BindBufferId(BufferImpl::TempBufferTarget, buffer.id);
+            // Grow in powers of two so a batch that creeps up in size stops respecifying.
+            SizeT capacity = buffer.capacity == 0 ? bytes : buffer.capacity;
+            while (capacity < bytes) capacity *= 2;
+            g_GLESFuncs.glBufferData(BufferImpl::TempBufferTarget, static_cast<GLsizeiptr>(capacity), nullptr,
+                                     GL_STREAM_DRAW);
+            buffer.capacity = capacity;
+            buffer.cursor = 0;
+            if (data) {
+                g_GLESFuncs.glBufferSubData(BufferImpl::TempBufferTarget, 0, static_cast<GLsizeiptr>(bytes), data);
+            }
+            return true;
+        }
+
+        // Ring upload, for the buffers whose consumers can address a byte offset (indirect
+        // commands and rewritten index streams). Respecifying per batch is what an
+        // orphan-every-time scheme costs, and on a desktop-class driver that allocation
+        // dominated the tiers that use these buffers - a multi-draw of 32 sub-draws stages
+        // 640 bytes and paid for a fresh store to hold them. Bump-allocating instead means
+        // one respecify per wrap; every byte between two wraps is written exactly once, so
+        // nothing in flight is overwritten, and the wrap itself orphans.
+        constexpr SizeT kRingAlignment = 16; // >= 4, so both command and uint32-index offsets stay legal
+        constexpr SizeT kMinRingBytes = 1u << 16;
+
+        Bool UploadScratchRing(ScratchBuffer& buffer, SizeT bytes, const void* data, SizeT& outOffset) {
+            outOffset = 0;
+            if (bytes == 0) return true;
+            if (!EnsureScratchName(buffer)) return false;
+            BufferImpl::BindBufferId(BufferImpl::TempBufferTarget, buffer.id);
+
+            const SizeT aligned = (bytes + kRingAlignment - 1) & ~(kRingAlignment - 1);
+            if (buffer.capacity < aligned) {
+                SizeT capacity = buffer.capacity == 0 ? kMinRingBytes : buffer.capacity;
+                while (capacity < aligned) capacity *= 2;
+                g_GLESFuncs.glBufferData(BufferImpl::TempBufferTarget, static_cast<GLsizeiptr>(capacity), nullptr,
+                                         GL_STREAM_DRAW);
+                buffer.capacity = capacity;
+                buffer.cursor = 0;
+            } else if (buffer.cursor + aligned > buffer.capacity) {
+                g_GLESFuncs.glBufferData(BufferImpl::TempBufferTarget, static_cast<GLsizeiptr>(buffer.capacity),
+                                         nullptr, GL_STREAM_DRAW);
+                buffer.cursor = 0;
+            }
+
+            outOffset = buffer.cursor;
+            if (data) {
+                g_GLESFuncs.glBufferSubData(BufferImpl::TempBufferTarget, static_cast<GLintptr>(outOffset),
+                                            static_cast<GLsizeiptr>(bytes), data);
+            }
+            buffer.cursor += aligned;
+            return true;
+        }
+
+        // ---------------------------------------------------------------------------
+        // Tier resolution
+        // ---------------------------------------------------------------------------
+
+        // Best-first, and measured rather than assumed. MobileGlues orders its own Auto
+        // multiindirect -> indirect -> basevertex; on both ES drivers available here that
+        // is backwards, because staging a command buffer per batch costs more than the
+        // driver entries it saves. mc_sodium_multidraw (132 batches x 32 sub-draws),
+        // ns/op, median of three:
+        //
+        //                    NVIDIA ES 3.2   Mesa llvmpipe ES 3.2
+        //   ext                  n/a               19300
+        //   basevertex           2500              25200
+        //   multiindirect        5700              27600
+        //   drawelements         5600              28700
+        //   indirect             5800              31000
+        //
+        // Ring-allocating the command staging (instead of respecifying per batch) was
+        // tried first and moved the indirect tiers by less than noise, so the cost is the
+        // indirect draw path itself, not the upload. Only "ext" - a real multi-draw entry
+        // point rather than an indirect one - actually beats replaying the sub-draws.
+        //
+        // The compute tier is deliberately absent from the ladder: it rewrites the
+        // primitive stream rather than replaying it, and it measured slowest of all here,
+        // so it stays opt-in behind the env knob (the same call MobileGlues makes - its
+        // Auto never selects Compute either).
+        constexpr GLESMultiDrawMode kAutoLadder[] = {
+            GLESMultiDrawMode::Ext,      GLESMultiDrawMode::BaseVertex,   GLESMultiDrawMode::MultiIndirect,
+            GLESMultiDrawMode::Indirect, GLESMultiDrawMode::DrawElements,
+        };
+
+        Bool SupportsTier(GLESMultiDrawMode tier) {
+            return IsTierSupported(g_GLESCapabilities, g_GLESFuncs, tier);
+        }
+
+        GLESMultiDrawMode g_resolvedTier = GLESMultiDrawMode::Auto;
+        Bool g_tierResolved = false;
+        String g_tierResolution;
+
+        void ResolveTierOnce() {
+            if (g_tierResolved) return;
+            g_tierResolved = true;
+            g_resolvedTier =
+                ResolveTier(g_GLESCapabilities, g_GLESFuncs, MG_Config::Features.EsprytMultiDrawMode,
+                            &g_tierResolution);
+            MGLOG_I("DirectGLES multi-draw: %s", g_tierResolution.c_str());
+        }
+
+        // Which tiers have already announced themselves, one bit per GLESMultiDrawMode.
+        // The resolution line above says which tier was CHOSEN; this says which one a
+        // batch actually went through, and the two differ whenever a batch's shape
+        // demotes it. Worth a line each: a multi-draw path that resolves to a tier and
+        // then quietly runs a different one is exactly how "the batch drew nothing"
+        // hides.
+        Uint32 g_announcedTiers = 0;
+
+        void NoteTierExecuted(GLESMultiDrawMode tier) {
+            const Uint32 bit = 1u << static_cast<Uint32>(tier);
+            if (g_announcedTiers & bit) return;
+            g_announcedTiers |= bit;
+            MGLOG_I("DirectGLES multi-draw: first batch executed via tier \"%s\"", TierName(tier));
+        }
+
+        // The tier this particular batch can actually take. A tier is demoted here when
+        // the batch's own shape - not the driver - rules it out; the compute tier keeps
+        // its remaining feasibility checks inside its implementation, where the data it
+        // has to walk is already in hand.
+        GLESMultiDrawMode ResolveTierForBatch(Bool programReadsDrawID, Bool hasIndexBuffer) {
+            ResolveTierOnce();
+            GLESMultiDrawMode tier = g_resolvedTier;
+
+            // Batched tiers issue one driver entry for the whole batch, so the emulated
+            // gl_DrawID uniform can only hold one value across every sub-draw. A program
+            // that reads gl_DrawID gets an unrolled tier, which feeds each sub-draw its
+            // own index (the spec's value); nothing else observes the difference.
+            const Bool batched = tier == GLESMultiDrawMode::Ext || tier == GLESMultiDrawMode::MultiIndirect ||
+                                 tier == GLESMultiDrawMode::Compute;
+            if (batched && programReadsDrawID) {
+                tier = SupportsTier(GLESMultiDrawMode::BaseVertex) ? GLESMultiDrawMode::BaseVertex
+                                                                   : GLESMultiDrawMode::DrawElements;
+            }
+
+            // The indirect tiers describe each sub-draw as an element offset into the
+            // bound element array buffer. A client-memory index array has no such buffer,
+            // and indirect draws are not defined without one.
+            if (!hasIndexBuffer &&
+                (tier == GLESMultiDrawMode::MultiIndirect || tier == GLESMultiDrawMode::Indirect)) {
+                tier = SupportsTier(GLESMultiDrawMode::BaseVertex) ? GLESMultiDrawMode::BaseVertex
+                                                                   : GLESMultiDrawMode::DrawElements;
+            }
+            return tier;
+        }
+
+        // ---------------------------------------------------------------------------
+        // Index rewriting, shared by the two tiers that fold base vertices into indices
+        // ---------------------------------------------------------------------------
+
+        // Both of those tiers emit GL_UNSIGNED_INT regardless of the source type. Keeping
+        // the source width would be wrong, not merely tight: GL adds baseVertex to the
+        // index at full precision, so a GL_UNSIGNED_SHORT index plus a base vertex past
+        // 65535 addresses a vertex the source type cannot spell. Widening also gives the
+        // rewritten stream a restart sentinel (0xFFFFFFFF) that survives the rebase.
+        void RebaseIndices(const Uint8* source, SizeT sourceIndexCount, SizeT indexSize, Int32 baseVertex,
+                           Bool restartActive, Uint32 restartSentinel, Uint32* out) {
+            const Uint32 baseVertexBits = static_cast<Uint32>(baseVertex);
+            for (SizeT i = 0; i < sourceIndexCount; ++i) {
+                Uint32 value = 0;
+                switch (indexSize) {
+                case 1: value = source[i]; break;
+                case 2: {
+                    Uint16 narrow = 0;
+                    std::memcpy(&narrow, source + i * 2, sizeof(narrow));
+                    value = narrow;
+                    break;
+                }
+                default: std::memcpy(&value, source + i * 4, sizeof(value)); break;
+                }
+                // Unsigned wraparound is the defined behaviour for a negative base vertex.
+                out[i] = (restartActive && value == restartSentinel) ? 0xFFFFFFFFu : value + baseVertexBits;
+            }
+        }
+
+        // CPU-readable bytes of one sub-draw's indices, from the frontend shadow of the
+        // bound index buffer or straight from the client array. Null when the sub-draw
+        // would read outside the buffer.
+        const Uint8* ResolveSubDrawIndices(const SharedPtr<MG_State::GLState::BufferObject>& indexBuffer,
+                                           const Uint8* indexBufferBytes, SizeT indexBufferSize, const void* indices,
+                                           SizeT indexCount, SizeT indexSize) {
+            if (!indexBuffer) {
+                return static_cast<const Uint8*>(indices);
+            }
+            if (!indexBufferBytes) return nullptr;
+            const SizeT byteOffset = reinterpret_cast<SizeT>(indices);
+            const SizeT byteEnd = byteOffset + indexCount * indexSize;
+            if (byteEnd > indexBufferSize || byteEnd < byteOffset) return nullptr;
+            return indexBufferBytes + byteOffset;
+        }
+
+        // ---------------------------------------------------------------------------
+        // Tier: Ext - one glMultiDrawElementsBaseVertexEXT
+        // ---------------------------------------------------------------------------
+
+        Bool RunExt(GLenum mode, const GLsizei* count, GLenum type, const GLvoid* const* indices, GLsizei drawcount,
+                    const GLint* basevertex) {
+            if (!SupportsTier(GLESMultiDrawMode::Ext)) return false;
+            const GLint* baseVertices = basevertex;
+            if (!baseVertices) {
+                // glMultiDrawElements: every base vertex is 0, but the entry point still
+                // wants an array. One permanently-zero vector serves every such batch.
+                if (g_zeroBaseVertices.size() < static_cast<SizeT>(drawcount)) {
+                    g_zeroBaseVertices.resize(static_cast<SizeT>(drawcount), 0);
+                }
+                baseVertices = g_zeroBaseVertices.data();
+            }
+            g_GLESFuncs.glMultiDrawElementsBaseVertexEXT(mode, count, type, indices, drawcount, baseVertices);
+            NoteTierExecuted(GLESMultiDrawMode::Ext);
+            return true;
+        }
+
+        // ---------------------------------------------------------------------------
+        // Tiers: MultiIndirect / Indirect - synthesized indirect commands
+        // ---------------------------------------------------------------------------
+
+        Bool RunIndirect(GLenum mode, const GLsizei* count, GLenum type, const GLvoid* const* indices,
+                         GLsizei drawcount, const GLint* basevertex, Bool batched, Bool feedDrawID) {
+            if (!SupportsTier(batched ? GLESMultiDrawMode::MultiIndirect : GLESMultiDrawMode::Indirect)) return false;
+            const SizeT indexSize = IndexTypeSize(type);
+            if (indexSize == 0) return false;
+            // Indirect commands address indices as an element offset into the bound element
+            // array buffer, and an indirect draw is not defined without one.
+            const auto& indexBuffer = BoundIndexBuffer();
+            if (!indexBuffer) return false;
+
+            g_commandStaging.resize(static_cast<SizeT>(drawcount));
+            for (GLsizei i = 0; i < drawcount; ++i) {
+                const SizeT byteOffset = reinterpret_cast<SizeT>(indices[i]);
+                // firstIndex counts elements, so an offset that is not a whole number of
+                // them cannot be expressed as a command at all.
+                if (byteOffset % indexSize != 0) return false;
+                auto& command = g_commandStaging[static_cast<SizeT>(i)];
+                command.count = count[i] > 0 ? static_cast<Uint32>(count[i]) : 0u;
+                command.instanceCount = 1;
+                command.firstIndex = static_cast<Uint32>(byteOffset / indexSize);
+                command.baseVertex = basevertex ? basevertex[i] : 0;
+                command.baseInstance = 0;
+            }
+
+            const SizeT commandBytes = g_commandStaging.size() * sizeof(DrawElementsIndirectCommand);
+            SizeT commandBase = 0;
+            if (!UploadScratchRing(g_indirectCommands, commandBytes, g_commandStaging.data(), commandBase)) {
+                return false;
+            }
+
+            // Every synthesized command carries baseInstance 0. Say so through the direct
+            // path, which also clears the indirect-params word index a preceding real
+            // indirect draw may have left pointing into its own command buffer.
+            SetCurrentBaseInstance(0);
+
+            const Uint previousIndirectBinding = BoundDrawIndirectBufferId();
+            BufferImpl::BindBufferId(GL_DRAW_INDIRECT_BUFFER, g_indirectCommands.id);
+            if (batched) {
+                g_GLESFuncs.glMultiDrawElementsIndirectEXT(mode, type, reinterpret_cast<const void*>(commandBase),
+                                                           drawcount, 0);
+            } else {
+                for (GLsizei i = 0; i < drawcount; ++i) {
+                    if (feedDrawID) SetCurrentDrawID(static_cast<Uint32>(i));
+                    const SizeT commandOffset = commandBase + static_cast<SizeT>(i) * sizeof(DrawElementsIndirectCommand);
+                    g_GLESFuncs.glDrawElementsIndirect(mode, type, reinterpret_cast<const void*>(commandOffset));
+                }
+                if (feedDrawID) SetCurrentDrawID(0);
+            }
+            BufferImpl::BindBufferId(GL_DRAW_INDIRECT_BUFFER, previousIndirectBinding);
+            NoteTierExecuted(batched ? GLESMultiDrawMode::MultiIndirect : GLESMultiDrawMode::Indirect);
+            return true;
+        }
+
+        // ---------------------------------------------------------------------------
+        // Tier: BaseVertex - the per-sub-draw replay
+        // ---------------------------------------------------------------------------
+
+        Bool RunBaseVertexLoop(GLenum mode, const GLsizei* count, GLenum type, const GLvoid* const* indices,
+                               GLsizei drawcount, const GLint* basevertex, Bool feedDrawID) {
+            if (!SupportsTier(GLESMultiDrawMode::BaseVertex)) return false;
+            for (GLsizei i = 0; i < drawcount; ++i) {
+                if (count[i] <= 0) continue;
+                if (feedDrawID) SetCurrentDrawID(static_cast<Uint32>(i));
+                g_GLESFuncs.glDrawElementsBaseVertex(mode, count[i], type, indices[i],
+                                                     basevertex ? basevertex[i] : 0);
+            }
+            if (feedDrawID) SetCurrentDrawID(0);
+            NoteTierExecuted(GLESMultiDrawMode::BaseVertex);
+            return true;
+        }
+
+        // ---------------------------------------------------------------------------
+        // Tier: DrawElements - base vertices folded into a scratch index stream
+        // ---------------------------------------------------------------------------
+
+        Bool RunRebasedDrawElements(GLenum mode, const GLsizei* count, GLenum type, const GLvoid* const* indices,
+                                    GLsizei drawcount, const GLint* basevertex, Bool feedDrawID) {
+            const SizeT indexSize = IndexTypeSize(type);
+            if (indexSize == 0) return false;
+
+            SizeT total = 0;
+            for (GLsizei i = 0; i < drawcount; ++i) {
+                if (count[i] > 0) total += static_cast<SizeT>(count[i]);
+            }
+            if (total == 0) return true;
+            if (total > kMaxFlattenedIndices) return false;
+
+            const auto& indexBuffer = BoundIndexBuffer();
+            const Uint8* indexBufferBytes = nullptr;
+            SizeT indexBufferSize = 0;
+            if (indexBuffer) {
+                // The shadow is the source of truth for CPU reads, but a persistent map or
+                // a shader write may have moved past it since the last sync.
+                indexBuffer->SyncPersistentMappedRange();
+                indexBuffer->SyncGpuWrites();
+                indexBufferBytes = indexBuffer->MappedData();
+                indexBufferSize = indexBuffer->GetSize();
+            }
+
+            const Bool restartActive = RestartActive();
+            const Uint32 restartSentinel = RestartSentinelFor(type);
+            g_indexStaging.resize(total);
+            SizeT cursor = 0;
+            for (GLsizei i = 0; i < drawcount; ++i) {
+                if (count[i] <= 0) continue;
+                const SizeT subDrawCount = static_cast<SizeT>(count[i]);
+                const Uint8* source = ResolveSubDrawIndices(indexBuffer, indexBufferBytes, indexBufferSize, indices[i],
+                                                            subDrawCount, indexSize);
+                if (!source) {
+                    MGLOG_E("DirectGLES multi-draw (drawelements tier): sub-draw %d reads outside the bound index "
+                            "buffer; skipping the batch",
+                            i);
+                    return false;
+                }
+                RebaseIndices(source, subDrawCount, indexSize, basevertex ? basevertex[i] : 0, restartActive,
+                              restartSentinel, g_indexStaging.data() + cursor);
+                cursor += subDrawCount;
+            }
+
+            SizeT indexBase = 0;
+            if (!UploadScratchRing(g_rebasedIndices, total * sizeof(Uint32), g_indexStaging.data(), indexBase)) {
+                return false;
+            }
+
+            const Uint previousIndexBinding = BoundIndexBufferId();
+            BufferImpl::BindBufferId(GL_ELEMENT_ARRAY_BUFFER, g_rebasedIndices.id);
+            cursor = 0;
+            for (GLsizei i = 0; i < drawcount; ++i) {
+                if (count[i] <= 0) continue;
+                if (feedDrawID) SetCurrentDrawID(static_cast<Uint32>(i));
+                g_GLESFuncs.glDrawElements(mode, count[i], GL_UNSIGNED_INT,
+                                           reinterpret_cast<const void*>(indexBase + cursor * sizeof(Uint32)));
+                cursor += static_cast<SizeT>(count[i]);
+            }
+            if (feedDrawID) SetCurrentDrawID(0);
+            BufferImpl::BindBufferId(GL_ELEMENT_ARRAY_BUFFER, previousIndexBinding);
+            NoteTierExecuted(GLESMultiDrawMode::DrawElements);
+            return true;
+        }
+
+        // ---------------------------------------------------------------------------
+        // Tier: Compute - the whole batch flattened into one rebased index stream
+        // ---------------------------------------------------------------------------
+
+        // One index per invocation. The sub-draw an output slot belongs to is found by
+        // binary search over the inclusive prefix sums of the sub-draw counts, which is
+        // why the descriptors are sorted by construction. Sub-draws with a zero count
+        // repeat the previous prefix sum and are therefore skipped by the search.
+        //
+        // Three storage blocks, not the five the shape suggests: ES 3.1 only guarantees
+        // four per compute stage, so the per-sub-draw descriptors share one buffer.
+        constexpr const char* kFlattenComputeSource = R"(#version 310 es
+layout(local_size_x = 64) in;
+
+uniform uint uElementSize;
+uniform uint uDrawCount;
+uniform uint uTotalIndices;
+
+layout(std430, binding = 0) readonly buffer SourceIndices { uint sourceWords[]; };
+layout(std430, binding = 1) readonly buffer DrawInfo { uint drawInfo[]; };
+layout(std430, binding = 2) writeonly buffer FlatIndices { uint flatIndices[]; };
+
+uint ReadSourceIndex(uint element) {
+    if (uElementSize == 4u) {
+        return sourceWords[element];
+    }
+    if (uElementSize == 2u) {
+        uint word = sourceWords[element >> 1u];
+        return (word >> ((element & 1u) * 16u)) & 0xFFFFu;
+    }
+    uint word = sourceWords[element >> 2u];
+    return (word >> ((element & 3u) * 8u)) & 0xFFu;
+}
+
+void main() {
+    uint outIndex = gl_GlobalInvocationID.x;
+    if (outIndex >= uTotalIndices) {
+        return;
+    }
+
+    uint low = 0u;
+    uint high = uDrawCount - 1u;
+    while (low < high) {
+        uint mid = low + (high - low) / 2u;
+        if (drawInfo[mid * 3u + 2u] > outIndex) {
+            high = mid;
+        } else {
+            low = mid + 1u;
+        }
+    }
+
+    uint localIndex = outIndex - (low == 0u ? 0u : drawInfo[(low - 1u) * 3u + 2u]);
+    // Unsigned wraparound is the defined behaviour for a negative base vertex. No
+    // restart sentinel handling: the tier declines outright while restart is enabled.
+    flatIndices[outIndex] = ReadSourceIndex(localIndex + drawInfo[low * 3u]) + drawInfo[low * 3u + 1u];
+}
+)";
+
+        struct FlattenedStream {
+            Uint bufferId = 0;
+            SizeT indexCount = 0;
+        };
+
+        Bool EnsureComputeProgram() {
+            if (g_computeProgram != 0) return true;
+            if (g_computeProgramFailed) return false;
+            g_computeProgramFailed = true; // cleared again only on a complete success
+
+            const GLuint shader = g_GLESFuncs.glCreateShader(GL_COMPUTE_SHADER);
+            if (shader == 0) {
+                MGLOG_E("DirectGLES multi-draw (compute tier): glCreateShader(GL_COMPUTE_SHADER) failed");
+                return false;
+            }
+            const char* source = kFlattenComputeSource;
+            g_GLESFuncs.glShaderSource(shader, 1, &source, nullptr);
+            g_GLESFuncs.glCompileShader(shader);
+            GLint status = GL_FALSE;
+            g_GLESFuncs.glGetShaderiv(shader, GL_COMPILE_STATUS, &status);
+            if (status != GL_TRUE) {
+                char log[1024] = {};
+                g_GLESFuncs.glGetShaderInfoLog(shader, sizeof(log) - 1, nullptr, log);
+                MGLOG_E("DirectGLES multi-draw (compute tier): index-flattening shader failed to compile: %s", log);
+                g_GLESFuncs.glDeleteShader(shader);
+                return false;
+            }
+
+            const GLuint program = g_GLESFuncs.glCreateProgram();
+            if (program == 0) {
+                MGLOG_E("DirectGLES multi-draw (compute tier): glCreateProgram failed");
+                g_GLESFuncs.glDeleteShader(shader);
+                return false;
+            }
+            g_GLESFuncs.glAttachShader(program, shader);
+            g_GLESFuncs.glLinkProgram(program);
+            g_GLESFuncs.glDeleteShader(shader);
+            g_GLESFuncs.glGetProgramiv(program, GL_LINK_STATUS, &status);
+            if (status != GL_TRUE) {
+                char log[1024] = {};
+                g_GLESFuncs.glGetProgramInfoLog(program, sizeof(log) - 1, nullptr, log);
+                MGLOG_E("DirectGLES multi-draw (compute tier): index-flattening program failed to link: %s", log);
+                g_GLESFuncs.glDeleteProgram(program);
+                return false;
+            }
+
+            g_computeProgram = program;
+            g_uElementSize = g_GLESFuncs.glGetUniformLocation(program, "uElementSize");
+            g_uDrawCount = g_GLESFuncs.glGetUniformLocation(program, "uDrawCount");
+            g_uTotalIndices = g_GLESFuncs.glGetUniformLocation(program, "uTotalIndices");
+            g_computeProgramFailed = false;
+            MGLOG_I("DirectGLES multi-draw: index-flattening compute program ready (id %u)", program);
+            return true;
+        }
+
+        // Builds the flattened stream, or leaves `out` empty when this batch's shape rules
+        // the tier out. Runs BEFORE PrepareForDraw - see the call site - so it may leave
+        // the compute program current and the first storage points unbound; the
+        // preparation that follows re-establishes both.
+        void FlattenWithCompute(GLenum mode, const GLsizei* count, GLenum type, const GLvoid* const* indices,
+                                GLsizei drawcount, const GLint* basevertex, FlattenedStream& out) {
+            if (!SupportsTier(GLESMultiDrawMode::Compute)) return;
+            const SizeT indexSize = IndexTypeSize(type);
+            if (indexSize == 0) return;
+
+            // Merging sub-draws into a single draw only reproduces the original primitive
+            // stream for list-shaped modes: a strip, loop or fan would gain primitives
+            // spanning the seam between two sub-draws.
+            const Uint32 primitiveSize = ConcatenablePrimitiveSize(mode);
+            if (primitiveSize == 0) return;
+
+            // Primitive restart defeats the whole-multiple-of-a-primitive argument below,
+            // even for a list mode. A restart ends the current primitive, so a sub-draw of
+            // six GL_TRIANGLES indices with a restart after the third emits ONE triangle
+            // and drops the two leftover vertices - and once concatenated those leftovers
+            // find a third vertex in the next sub-draw and become a triangle that GL never
+            // draws. Splicing separator sentinels into the flattened stream could fix it,
+            // at the cost of a per-sub-draw offset the prefix-sum layout does not carry;
+            // declining is the honest trade for a tier that is already opt-in.
+            if (RestartActive()) return;
+
+            // The shader reads the source indices as a storage buffer, so there has to be
+            // a real buffer to read - a client-memory index array has none.
+            const auto& indexBuffer = BoundIndexBuffer();
+            if (!indexBuffer) return;
+
+            // A dispatch inside an open capture span is not legal, and the span would also
+            // observe one merged draw rather than the batch it asked for.
+            if (XfbImpl::IsCaptureSpanOpen()) return;
+
+            auto* sourceResource = BufferImpl::EnsureBufferResource(indexBuffer);
+            if (!sourceResource || sourceResource->id == 0) return;
+            const SizeT sourceSize = indexBuffer->GetSize();
+            // std430 addresses the source as uint[]; a tail shorter than a word is not
+            // reachable, so a narrow index type needs a word-multiple buffer.
+            if (indexSize < 4 && (sourceSize % 4) != 0) return;
+
+            g_drawInfoStaging.resize(3 * static_cast<SizeT>(drawcount));
+            SizeT total = 0;
+            for (GLsizei i = 0; i < drawcount; ++i) {
+                const SizeT subDrawCount = count[i] > 0 ? static_cast<SizeT>(count[i]) : 0;
+                // GL drops a trailing partial primitive per sub-draw; concatenation would
+                // instead splice it onto the next sub-draw's first vertices.
+                if (subDrawCount % primitiveSize != 0) return;
+                const SizeT byteOffset = reinterpret_cast<SizeT>(indices[i]);
+                if (byteOffset % indexSize != 0) return;
+                if (subDrawCount != 0) {
+                    const SizeT byteEnd = byteOffset + subDrawCount * indexSize;
+                    if (byteEnd > sourceSize || byteEnd < byteOffset) return;
+                }
+                total += subDrawCount;
+                if (total > kMaxComputeFlattenedIndices) return;
+                const SizeT slot = 3 * static_cast<SizeT>(i);
+                g_drawInfoStaging[slot] = static_cast<Uint32>(byteOffset / indexSize);
+                g_drawInfoStaging[slot + 1] = static_cast<Uint32>(basevertex ? basevertex[i] : 0);
+                g_drawInfoStaging[slot + 2] = static_cast<Uint32>(total);
+            }
+            if (total == 0) return; // nothing to draw; the ordinary tiers no-op just as well
+
+            if (!EnsureComputeProgram()) return;
+            if (!UploadScratch(g_drawInfo, g_drawInfoStaging.size() * sizeof(Uint32), g_drawInfoStaging.data())) {
+                return;
+            }
+            if (!UploadScratch(g_flattenedIndices, total * sizeof(Uint32), nullptr)) return;
+
+            BufferImpl::BindBufferBaseCached(GL_SHADER_STORAGE_BUFFER, 0, sourceResource->id);
+            BufferImpl::BindBufferBaseCached(GL_SHADER_STORAGE_BUFFER, 1, g_drawInfo.id);
+            BufferImpl::BindBufferBaseCached(GL_SHADER_STORAGE_BUFFER, 2, g_flattenedIndices.id);
+
+            g_GLESFuncs.glUseProgram(g_computeProgram);
+            PrgramImpl::g_lastUsedBackendProgramId = g_computeProgram;
+            if (g_uElementSize >= 0) g_GLESFuncs.glUniform1ui(g_uElementSize, static_cast<GLuint>(indexSize));
+            if (g_uDrawCount >= 0) g_GLESFuncs.glUniform1ui(g_uDrawCount, static_cast<GLuint>(drawcount));
+            if (g_uTotalIndices >= 0) g_GLESFuncs.glUniform1ui(g_uTotalIndices, static_cast<GLuint>(total));
+
+            g_GLESFuncs.glDispatchCompute(
+                static_cast<GLuint>((total + kComputeWorkGroupSize - 1) / kComputeWorkGroupSize), 1, 1);
+            g_GLESFuncs.glMemoryBarrier(GL_SHADER_STORAGE_BARRIER_BIT | GL_ELEMENT_ARRAY_BARRIER_BIT);
+
+            // Hand the storage points back to their GL default. PrepareForDraw re-syncs
+            // only the points the app has actually touched, so leaving a scratch buffer on
+            // an untouched point would keep it visible to the next shader that declares one.
+            for (Uint point = 0; point < 3; ++point) {
+                BufferImpl::BindBufferBaseCached(GL_SHADER_STORAGE_BUFFER, point, 0);
+            }
+
+            NoteTierExecuted(GLESMultiDrawMode::Compute);
+            out.bufferId = g_flattenedIndices.id;
+            out.indexCount = total;
+        }
+    } // namespace
+
+    // -------------------------------------------------------------------------------
+    // Public surface
+    // -------------------------------------------------------------------------------
+
+    Bool IsTierSupported(const MG_External::GLESCapabilities& caps, const MG_External::GLESFunctionsTable& funcs,
+                         GLESMultiDrawMode tier) {
+        const Bool esAtLeast31 =
+            caps.GLESVersion.Major > 3 || (caps.GLESVersion.Major == 3 && caps.GLESVersion.Minor >= 1);
+        switch (tier) {
+        case GLESMultiDrawMode::Ext:
+            return caps.SupportsMultiDrawElementsBaseVertex;
+        case GLESMultiDrawMode::MultiIndirect:
+            return caps.SupportsMultiDrawIndirect && esAtLeast31 && funcs.glDrawElementsIndirect != nullptr;
+        case GLESMultiDrawMode::Indirect:
+            return esAtLeast31 && funcs.glDrawElementsIndirect != nullptr;
+        case GLESMultiDrawMode::BaseVertex:
+            return caps.SupportsDrawElementsBaseVertex;
+        case GLESMultiDrawMode::DrawElements:
+            // Plain glDrawElements over a rewritten index stream: ES 2 core, so this is
+            // the floor every other tier can fall back to.
+            return true;
+        case GLESMultiDrawMode::Compute:
+            // Three storage blocks, which is inside the four ES 3.1 guarantees per stage.
+            return caps.SupportsComputeShader && caps.MaxComputeShaderStorageBlocks >= 3 &&
+                   funcs.glBindBufferBase != nullptr;
+        case GLESMultiDrawMode::Auto:
+            break;
+        }
+        return false;
+    }
+
+    GLESMultiDrawMode ResolveTier(const MG_External::GLESCapabilities& caps,
+                                  const MG_External::GLESFunctionsTable& funcs, GLESMultiDrawMode requested,
+                                  String* explanation) {
+        const auto bestAuto = [&]() {
+            for (const GLESMultiDrawMode tier : kAutoLadder) {
+                if (IsTierSupported(caps, funcs, tier)) return tier;
+            }
+            return GLESMultiDrawMode::DrawElements;
+        };
+
+        GLESMultiDrawMode resolved = GLESMultiDrawMode::DrawElements;
+        String line;
+        if (requested == GLESMultiDrawMode::Auto) {
+            resolved = bestAuto();
+            line = String("auto -> ") + TierName(resolved);
+        } else if (IsTierSupported(caps, funcs, requested)) {
+            resolved = requested;
+            line = String("MOBILEGL_ESPRYT_MULTIDRAW_MODE=") + TierName(requested) + " -> " + TierName(resolved);
+        } else {
+            resolved = bestAuto();
+            line = String("MOBILEGL_ESPRYT_MULTIDRAW_MODE=") + TierName(requested) +
+                   " requested but unsupported by this driver -> " + TierName(resolved);
+        }
+
+        if (explanation) {
+            String supported;
+            for (const GLESMultiDrawMode tier : kAutoLadder) {
+                if (!IsTierSupported(caps, funcs, tier)) continue;
+                if (!supported.empty()) supported += ", ";
+                supported += TierName(tier);
+            }
+            if (IsTierSupported(caps, funcs, GLESMultiDrawMode::Compute)) {
+                supported += supported.empty() ? "compute (opt-in)" : ", compute (opt-in)";
+            }
+            *explanation = line + " (driver supports: " + supported + ")";
+        }
+        return resolved;
+    }
+
+    const char* TierName(GLESMultiDrawMode tier) {
+        switch (tier) {
+        case GLESMultiDrawMode::Auto: return "auto";
+        case GLESMultiDrawMode::Ext: return "ext";
+        case GLESMultiDrawMode::MultiIndirect: return "multiindirect";
+        case GLESMultiDrawMode::Indirect: return "indirect";
+        case GLESMultiDrawMode::BaseVertex: return "basevertex";
+        case GLESMultiDrawMode::DrawElements: return "drawelements";
+        case GLESMultiDrawMode::Compute: return "compute";
+        }
+        return "unknown";
+    }
+
+    GLESMultiDrawMode ResolvedTier() {
+        ResolveTierOnce();
+        return g_resolvedTier;
+    }
+
+    String DescribeTierResolution() {
+        ResolveTierOnce();
+        return g_tierResolution;
+    }
+
+    void OnBackendContextDestroyed() {
+        g_indirectCommands = {};
+        g_rebasedIndices = {};
+        g_drawInfo = {};
+        g_flattenedIndices = {};
+        g_computeProgram = 0;
+        g_computeProgramFailed = false;
+        g_uElementSize = -1;
+        g_uDrawCount = -1;
+        g_uTotalIndices = -1;
+    }
+
+    void DrawElementsBatch(GLenum mode, const GLsizei* count, GLenum type, const GLvoid* const* indices,
+                           GLsizei drawcount, const GLint* basevertex) {
+        if (drawcount <= 0 || !count || !indices) return;
+        // State-independent and possibly throwing, so it runs before any GL work.
+        CheckPrimitiveRestartSupported(type);
+
+        const Bool hasIndexBuffer = BoundIndexBuffer() != nullptr;
+
+        // The compute tier dispatches BEFORE the draw state is established: doing it
+        // afterwards would mean unpicking the program, SSBO and index bindings
+        // PrepareForDraw just made, and a dispatch inside an open transform feedback
+        // span is not legal at all. On success it hands back a flattened index stream.
+        FlattenedStream flattened;
+        if (ResolvedTier() == GLESMultiDrawMode::Compute && !CurrentProgramReadsDrawID()) {
+            FlattenWithCompute(mode, count, type, indices, drawcount, basevertex, flattened);
+        }
+
+        PrepareForDraw(DrawSyncBit::IndexBuffer);
+
+        if (flattened.indexCount != 0) {
+            const Uint previousIndexBinding = BoundIndexBufferId();
+            BufferImpl::BindBufferId(GL_ELEMENT_ARRAY_BUFFER, flattened.bufferId);
+            g_GLESFuncs.glDrawElements(mode, static_cast<GLsizei>(flattened.indexCount), GL_UNSIGNED_INT, nullptr);
+            BufferImpl::BindBufferId(GL_ELEMENT_ARRAY_BUFFER, previousIndexBinding);
+            return;
+        }
+
+        const Bool feedDrawID = CurrentProgramReadsDrawID();
+        const GLESMultiDrawMode tier = ResolveTierForBatch(feedDrawID, hasIndexBuffer);
+
+        Bool drawn = false;
+        switch (tier) {
+        case GLESMultiDrawMode::Ext:
+            drawn = RunExt(mode, count, type, indices, drawcount, basevertex);
+            break;
+        case GLESMultiDrawMode::MultiIndirect:
+            drawn = RunIndirect(mode, count, type, indices, drawcount, basevertex, /*batched=*/true, feedDrawID);
+            break;
+        case GLESMultiDrawMode::Indirect:
+            drawn = RunIndirect(mode, count, type, indices, drawcount, basevertex, /*batched=*/false, feedDrawID);
+            break;
+        case GLESMultiDrawMode::BaseVertex:
+            drawn = RunBaseVertexLoop(mode, count, type, indices, drawcount, basevertex, feedDrawID);
+            break;
+        case GLESMultiDrawMode::DrawElements:
+            drawn = RunRebasedDrawElements(mode, count, type, indices, drawcount, basevertex, feedDrawID);
+            break;
+        case GLESMultiDrawMode::Compute:
+            // Its pre-pass ran above; reaching here means it declined this batch's shape.
+            break;
+        case GLESMultiDrawMode::Auto:
+            break; // resolution never yields Auto
+        }
+
+        // Every tier above may decline a batch whose shape it cannot express. The two
+        // below are the floor: a base-vertex replay where the driver has one, and the
+        // rewritten index stream where it does not. Both are safe for any batch these
+        // entry points can receive.
+        if (!drawn) drawn = RunBaseVertexLoop(mode, count, type, indices, drawcount, basevertex, feedDrawID);
+        if (!drawn) drawn = RunRebasedDrawElements(mode, count, type, indices, drawcount, basevertex, feedDrawID);
+        if (!drawn) {
+            MGLOG_E("DirectGLES multi-draw: no usable tier for a %d sub-draw batch (mode 0x%x, type 0x%x); "
+                    "the batch was dropped",
+                    drawcount, mode, type);
+        }
+    }
+} // namespace MobileGL::MG_Backend::DirectGLES::MultiDrawImpl

MobileGL/MG_Backend/DirectGLES/MultiDraw.h

@@ -0,0 +1,64 @@
+// MobileGL - MobileGL/MG_Backend/DirectGLES/MultiDraw.h
+// Copyright (c) 2025-2026 MobileGL-Dev
+// Licensed under the GNU Lesser General Public License v3.0:
+//   https://www.gnu.org/licenses/gpl-3.0.txt
+//   https://www.gnu.org/licenses/lgpl-3.0.txt
+// SPDX-License-Identifier: LGPL-3.0-only
+// End of Source File Header
+
+#pragma once
+#include <Includes.h>
+#include <Config.h>
+#include "DirectGLES.h"
+
+// Emulation of the desktop glMultiDrawElements / glMultiDrawElementsBaseVertex entry
+// points on OpenGL ES, which has neither in core.
+//
+// Every strategy below is an emulation; they differ only in which driver capability
+// they lean on and in how many driver entries a batch of N sub-draws costs. The design
+// follows MobileGlues (MobileGL-Dev/MobileGlues, gl/multidraw.cpp) tier for tier, plus
+// the native GL_EXT_multi_draw_arrays interaction that MobileGL already had:
+//
+//   Ext           one glMultiDrawElementsBaseVertexEXT           1 driver entry
+//   MultiIndirect one glMultiDrawElementsIndirectEXT             1 driver entry + 1 upload
+//   Indirect      N x glDrawElementsIndirect                     N + 1 upload
+//   BaseVertex    N x glDrawElementsBaseVertex                   N
+//   DrawElements  N x glDrawElements over CPU-rebased indices    N + 1 upload
+//   Compute       1 x glDrawElements over a GPU-flattened,       1 dispatch + 1 entry
+//                 rebased index stream
+//
+// Which one runs is resolved once per ES context from the driver's capabilities,
+// capped by MOBILEGL_ESPRYT_MULTIDRAW_MODE, and can additionally be demoted per batch
+// when the batch's own shape rules a tier out (see ResolveTierForBatch in the .cpp).
+namespace MobileGL::MG_Backend::DirectGLES::MultiDrawImpl {
+    // The tier this ES context resolved to, computed on first use and stable after.
+    MG_Config::GLESMultiDrawMode ResolvedTier();
+    // "multiindirect", "compute", ... - stable identifiers, also used by the POST row.
+    const char* TierName(MG_Config::GLESMultiDrawMode tier);
+    // One line naming the resolved tier, the tiers the driver can support, and the env
+    // clamp if one applied. For DriverPost and the startup log.
+    String DescribeTierResolution();
+
+    // The resolution itself, as a pure function of a capability set: the backend feeds
+    // it the live ES context's capabilities, DriverPost feeds it the ones it probed
+    // standalone, and both therefore report the same tier. `explanation`, when non-null,
+    // receives the "requested -> resolved (driver supports: ...)" line.
+    MG_Config::GLESMultiDrawMode ResolveTier(const MG_External::GLESCapabilities& caps,
+                                             const MG_External::GLESFunctionsTable& funcs,
+                                             MG_Config::GLESMultiDrawMode requested, String* explanation);
+    // Whether one tier is runnable on the given capability set, for per-row POST output.
+    Bool IsTierSupported(const MG_External::GLESCapabilities& caps, const MG_External::GLESFunctionsTable& funcs,
+                         MG_Config::GLESMultiDrawMode tier);
+
+    // Runs `drawcount` indexed sub-draws as one glMultiDrawElements(BaseVertex) call
+    // would. `basevertex` is null for the plain glMultiDrawElements entry point (every
+    // base vertex is 0). Owns the whole draw, preparation included: callers must not
+    // have run PrepareForDraw, because the compute tier has to dispatch before the
+    // draw state is established.
+    void DrawElementsBatch(GLenum mode, const GLsizei* count, GLenum type, const GLvoid* const* indices,
+                           GLsizei drawcount, const GLint* basevertex);
+
+    // The ES context is gone: every scratch buffer and the compute program belonged to
+    // it, so drop the names without deleting them (the dead context reclaims them).
+    void OnBackendContextDestroyed();
+} // namespace MobileGL::MG_Backend::DirectGLES::MultiDrawImpl

MobileGL/MG_Backend/DirectGLES/Utils.cpp

@@ -18,6 +18,13 @@
 #include <MG_Util/Converters/GLToStr/GLEnumConverter.h>
 #include <MG_Util/Converters/MGToGL/TextureEnumConverter.h>
 #include <MG_Util/Converters/MGToGL/FramebufferEnumConverter.h>
+#include <MG_Util/Math/HalfFloat.h>
+#include <MG_Util/Math/SmallFloat.h>
+
+#include <cmath>
+#include <cctype>
+#include <cstring>
+#include <regex>
 
 namespace MobileGL::MG_Backend::DirectGLES {
     namespace {
@@ -41,15 +48,17 @@ namespace MobileGL::MG_Backend::DirectGLES {
             return options;
         }
 
-        Flags<PixelFormatNormalizeOptionBit> GetRuntimeFallbackNormalizeOptions(GLenum requestedInternalFormat) {
+        Flags<PixelFormatNormalizeOptionBit>
+        GetRuntimeFallbackNormalizeOptions(GLenum requestedInternalFormat,
+                                           Flags<PixelFormatNormalizeOptionBit> extraOptions) {
             using namespace MG_Util::TextureFormatProcessor;
-            const Flags<PixelFormatNormalizeOptionBit> forcedOptions =
-                GetApplicablePixelFormatNormalizeOptions(requestedInternalFormat, GetForcedPixelFormatNormalizeOptions());
+            const Flags<PixelFormatNormalizeOptionBit> forcedOptions = GetApplicablePixelFormatNormalizeOptions(
+                requestedInternalFormat, GetForcedPixelFormatNormalizeOptions() | extraOptions);
             if (forcedOptions) {
                 return forcedOptions;
             }
-            return GetApplicablePixelFormatNormalizeOptions(requestedInternalFormat,
-                                                            GetDriverPixelFormatNormalizeOptions());
+            return GetApplicablePixelFormatNormalizeOptions(
+                requestedInternalFormat, GetDriverPixelFormatNormalizeOptions() | extraOptions);
         }
 
         Bool HasCachedFormatCapability(TextureInternalFormat internalFormat,
@@ -109,13 +118,61 @@ namespace MobileGL::MG_Backend::DirectGLES {
             const GLenum requestedInternalFormat = MG_Util::ConvertTextureInternalFormatToGLEnum(internalFormat);
             Flags<PixelFormatNormalizeOptionBit> options;
             if (!pActiveBackendObject || ShouldUseCaveatFormat(internalFormat, targetIndex)) {
-                options = GetRuntimeFallbackNormalizeOptions(requestedInternalFormat);
+                options = GetRuntimeFallbackNormalizeOptions(
+                    requestedInternalFormat,
+                    TextureImpl::GetRenderTargetNormalizeOptions(g_GLESCapabilities, targetIndex));
             }
             NormalizePixelFormat(requestedInternalFormat, options, outInternalFormat, outFormat, outType);
         }
     } // namespace
 
     namespace TextureImpl {
+        // Every image that can back a colour attachment needs a colour-renderable storage format,
+        // and ES has no renderable three-channel format at all: a three-channel float fallback is
+        // a legal ES texture but neither legal multisample storage nor a legal attachment, so
+        // GL_RGB8_SNORM / GL_RGB16F / ... have to be widened to four channels for any of them.
+        // This used to cover the multisample pair alone, on the grounds that only those can never
+        // be uploaded to; the transfer paths now expand three-channel client data themselves
+        // (Managers.cpp PrepareFallbackUpload) and hide the added alpha again on sample and
+        // readback, so the same substitution is available everywhere.
+        //
+        // The widening only ever *happens* where the driver refuses the native form (see
+        // PopulateFormatCapabilitiesImpl: outside multisample storage it rides the driver branch,
+        // behind the native probe), so a driver that does render to a three-channel image keeps
+        // allocating it byte for byte.
+        //
+        // Do NOT read that as "nothing changes off-device". Measured on Mesa 26.1.6 llvmpipe
+        // (the headless CI driver), an ES 3.2 GL_TEXTURE_2D colour attachment is COMPLETE for
+        // GL_RGB8 and GL_RGB16F but INCOMPLETE_ATTACHMENT for GL_RGB8_SNORM, GL_SRGB8 and every
+        // RGB integer format, and UNSUPPORTED for GL_RGB32F. Those eight formats therefore DO
+        // take the widened path on llvmpipe, which is where the retrace fixtures and the glcts
+        // green suites run - the substitution is driver-conditional, not desktop-exempt.
+        //
+        // A buffer texture is the one image that can never be an attachment; its storage is the
+        // buffer object's, and widening it would misdescribe the application's data.
+        Bool TargetRequiresRenderableFormat(SizeT targetIndex) {
+            if (targetIndex >= kFormatCapabilityTargetCount) {
+                return false;
+            }
+            if (targetIndex == kFormatCapabilityRenderbufferTargetIndex) {
+                return true;
+            }
+            return static_cast<TextureTarget>(targetIndex) != TextureTarget::TextureBuffer;
+        }
+
+        Flags<PixelFormatNormalizeOptionBit> GetRenderTargetNormalizeOptions(
+            const MG_External::GLESCapabilities& capabilities, SizeT targetIndex) {
+            Flags<PixelFormatNormalizeOptionBit> options;
+            if (!TargetRequiresRenderableFormat(targetIndex)) {
+                return options;
+            }
+            options |= PixelFormatNormalizeOptionBit::NoThreeChannelRenderTarget;
+            if (!capabilities.SupportsRenderSnorm || !capabilities.SupportsNorm16Texture) {
+                options |= PixelFormatNormalizeOptionBit::NoSnorm16RenderTarget;
+            }
+            return options;
+        }
+
         void GenerateTextureFormatInfo(TextureInternalFormat internalFormat, GLenum* outInternalFormat,
                                        GLenum* outFormat, GLenum* outType, TextureTarget target) {
 #ifdef TRACY_ENABLE
@@ -144,6 +201,31 @@ namespace MobileGL::MG_Backend::DirectGLES {
         Bool ShouldUseCaveatRenderbufferFormat(TextureInternalFormat internalFormat) {
             return ShouldUseCaveatFormat(internalFormat, GetRenderbufferFormatCapabilityTargetIndex());
         }
+
+        namespace {
+            Bool BackendFormatAddsAlpha(TextureInternalFormat internalFormat, SizeT targetIndex) {
+                if (!TargetRequiresRenderableFormat(targetIndex)) {
+                    return false;
+                }
+                if (pActiveBackendObject && !ShouldUseCaveatFormat(internalFormat, targetIndex)) {
+                    return false;
+                }
+                const GLenum requestedInternalFormat = MG_Util::ConvertTextureInternalFormatToGLEnum(internalFormat);
+                const Flags<PixelFormatNormalizeOptionBit> options = GetRuntimeFallbackNormalizeOptions(
+                    requestedInternalFormat, GetRenderTargetNormalizeOptions(g_GLESCapabilities, targetIndex));
+                return static_cast<Bool>(options & PixelFormatNormalizeOptionBit::NoThreeChannelRenderTarget);
+            }
+        } // namespace
+
+        Bool BackendTextureFormatAddsAlpha(TextureInternalFormat internalFormat, TextureTarget target) {
+            const SizeT targetIndex =
+                target == TextureTarget::Unknown ? kFormatCapabilityTargetCount : GetFormatCapabilityTargetIndex(target);
+            return BackendFormatAddsAlpha(internalFormat, targetIndex);
+        }
+
+        Bool BackendRenderbufferFormatAddsAlpha(TextureInternalFormat internalFormat) {
+            return BackendFormatAddsAlpha(internalFormat, GetRenderbufferFormatCapabilityTargetIndex());
+        }
     } // namespace TextureImpl
     namespace PrgramImpl {
         String ProcessOutColorLocations(const String& glslCode) {
@@ -272,6 +354,55 @@ namespace MobileGL::MG_Backend::DirectGLES {
             return glslCode;
         }
 
+        String BroadcastLegacyFragColor(String glslCode, GLenum shaderType, Uint drawBufferCount) {
+#ifdef TRACY_ENABLE
+            ZoneScopedC(TRACY_ZONECOLOR_BACKEND);
+#endif
+            // The name is the marker: ShaderSourceProcessor only emits it when the source
+            // wrote gl_FragColor, and such a shader can have no other output.
+            static const char* const kLoweredName = "mg_FragColor";
+            if (shaderType != GL_FRAGMENT_SHADER || drawBufferCount <= 1) {
+                return glslCode;
+            }
+            static const std::regex declRegex(
+                R"(layout\s*\(\s*location\s*=\s*0\s*\)\s*out\s+((?:lowp|mediump|highp)\s+)?vec4\s+mg_FragColor\s*;)");
+            std::smatch declMatch;
+            if (!std::regex_search(glslCode, declMatch, declRegex)) {
+                return glslCode;
+            }
+            const String precision = declMatch[1].matched ? declMatch[1].str() : String();
+
+            String replicaDecls;
+            String replicaCopies;
+            for (Uint location = 1; location < drawBufferCount; ++location) {
+                const String name = String(kLoweredName) + "_" + std::to_string(location);
+                replicaDecls += "\nlayout(location = " + std::to_string(location) + ") out " + precision + "vec4 " +
+                                name + ";";
+                replicaCopies += "\n    " + name + " = " + kLoweredName + ";";
+            }
+
+            static const std::regex mainRegex(R"(void\s+main\s*\([^)]*\)\s*\{)");
+            std::smatch mainMatch;
+            if (!std::regex_search(glslCode, mainMatch, mainRegex)) {
+                return glslCode;
+            }
+            SizeT bracePos = static_cast<SizeT>(mainMatch.position(0) + mainMatch.length(0) - 1);
+            Int depth = 0;
+            for (SizeT pos = bracePos; pos < glslCode.size(); ++pos) {
+                if (glslCode[pos] == '{') {
+                    ++depth;
+                } else if (glslCode[pos] == '}') {
+                    --depth;
+                    if (depth == 0) {
+                        glslCode.insert(pos, replicaCopies + "\n");
+                        break;
+                    }
+                }
+            }
+            glslCode.insert(static_cast<SizeT>(declMatch.position(0)) + declMatch[0].str().size(), replicaDecls);
+            return glslCode;
+        }
+
         String ForceFlatIntegerVaryings(const String& glslCode, GLenum shaderType) {
 #ifdef TRACY_ENABLE
             ZoneScopedC(TRACY_ZONECOLOR_BACKEND);
@@ -338,6 +469,167 @@ namespace MobileGL::MG_Backend::DirectGLES {
             }
             return result;
         }
+
+        namespace {
+            // How a lookup carries its level of detail, and how many arguments it takes
+            // before the optional bias.
+            struct LodLookupForm {
+                const char* name;
+                Int requiredArgs; // arguments before the optional bias (implicit form)
+                Int explicitLodArg; // index of the explicit LOD argument, -1 for implicit
+            };
+
+            // texelFetch* is deliberately absent: an integer fetch names its level directly
+            // and takes no LOD bias. textureGather has no bias either. textureGrad* derives
+            // the LOD from gradients and offers no argument to fold a bias into, so it is
+            // left alone rather than rewritten incorrectly.
+            constexpr LodLookupForm LOD_LOOKUP_FORMS[] = {
+                {"textureProjLodOffset", 0, 2}, {"textureProjOffset", 4, -1}, {"textureProjLod", 0, 2},
+                {"textureLodOffset", 0, 2},     {"textureOffset", 3, -1},     {"textureProj", 2, -1},
+                {"textureLod", 0, 2},           {"texture", 2, -1},
+            };
+
+            // Sampler types with no mip chain, or whose GLSL lookups have no bias overload
+            // at all (the array-shadow forms), so nothing can or should be folded in.
+            Bool IsBiasableSamplerType(const String& samplerType) {
+                if (samplerType.find("MS") != String::npos) return false;      // multisample
+                if (samplerType.find("Buffer") != String::npos) return false;  // texture buffer
+                if (samplerType.find("Rect") != String::npos) return false;    // rectangle: no mips
+                if (samplerType == "sampler2DArrayShadow") return false;
+                if (samplerType == "samplerCubeArrayShadow") return false;
+                return true;
+            }
+
+            Bool IsIdentifierChar(char c) { return std::isalnum(static_cast<unsigned char>(c)) || c == '_'; }
+
+            // Byte offsets of the top-level argument separators and of the closing paren,
+            // starting from the '(' at openParen. Empty when the parentheses do not balance.
+            Vector<SizeT> SplitCallArguments(const String& code, SizeT openParen) {
+                Vector<SizeT> marks;
+                Int depth = 0;
+                for (SizeT i = openParen; i < code.size(); ++i) {
+                    const char c = code[i];
+                    if (c == '(' || c == '[') {
+                        ++depth;
+                    } else if (c == ']') {
+                        --depth;
+                    } else if (c == ')') {
+                        --depth;
+                        if (depth == 0) {
+                            marks.push_back(i);
+                            return marks;
+                        }
+                    } else if (c == ',' && depth == 1) {
+                        marks.push_back(i);
+                    }
+                }
+                return {};
+            }
+        } // namespace
+
+        String EmulateTextureLodBias(const String& glslCode) {
+#ifdef TRACY_ENABLE
+            ZoneScopedC(TRACY_ZONECOLOR_BACKEND);
+#endif
+            if (glslCode.find("sampler") == String::npos || glslCode.find("texture") == String::npos) {
+                return glslCode;
+            }
+
+            // Collect the mip-capable sampler uniforms this shader declares.
+            static const std::regex samplerDeclRegex(
+                R"(uniform\s+(?:(?:highp|mediump|lowp)\s+)?([iu]?sampler[A-Za-z0-9]*)\s+([A-Za-z_][A-Za-z0-9_]*)\s*;)");
+            UnorderedMap<String, String> samplerNames; // name -> bias uniform name
+            for (std::sregex_iterator it(glslCode.begin(), glslCode.end(), samplerDeclRegex), end; it != end; ++it) {
+                const String samplerType = (*it)[1].str();
+                if (!IsBiasableSamplerType(samplerType)) continue;
+                const String name = (*it)[2].str();
+                samplerNames.emplace(name, String(LOD_BIAS_UNIFORM_PREFIX) + name);
+            }
+            if (samplerNames.empty()) {
+                return glslCode;
+            }
+
+            // Rewrite the lookups. Right-to-left so earlier offsets stay valid, and only for
+            // samplers named directly as the first argument (SPIRV-Cross never produces an
+            // expression there for ES output, which has no separate sampler objects).
+            String result = glslCode;
+            Vector<String> usedSamplers;
+            for (SizeT scan = result.size(); scan-- > 0;) {
+                if (result[scan] != 't') continue;
+                if (scan > 0 && IsIdentifierChar(result[scan - 1])) continue;
+
+                const LodLookupForm* form = nullptr;
+                SizeT openParen = 0;
+                for (const auto& candidate : LOD_LOOKUP_FORMS) {
+                    const SizeT nameLength = std::strlen(candidate.name);
+                    if (result.compare(scan, nameLength, candidate.name) != 0) continue;
+                    SizeT after = result.find_first_not_of(" \t", scan + nameLength);
+                    if (after == String::npos || result[after] != '(') continue;
+                    form = &candidate;
+                    openParen = after;
+                    break;
+                }
+                if (form == nullptr) continue;
+
+                const Vector<SizeT> marks = SplitCallArguments(result, openParen);
+                if (marks.empty()) continue;
+                const SizeT argCount = marks.size();
+                const SizeT closeParen = marks.back();
+
+                // First argument must be one of our samplers.
+                const SizeT firstArgStart = result.find_first_not_of(" \t", openParen + 1);
+                SizeT firstArgEnd = marks.front();
+                while (firstArgEnd > firstArgStart && (result[firstArgEnd - 1] == ' ' || result[firstArgEnd - 1] == '\t')) {
+                    --firstArgEnd;
+                }
+                if (firstArgStart == String::npos || firstArgEnd <= firstArgStart) continue;
+                const String samplerName = result.substr(firstArgStart, firstArgEnd - firstArgStart);
+                const auto samplerIt = samplerNames.find(samplerName);
+                if (samplerIt == samplerNames.end()) continue;
+
+                const String& biasName = samplerIt->second;
+                if (form->explicitLodArg >= 0) {
+                    // Explicit LOD: the bias adds to it, as Vulkan does for
+                    // OpImageSampleExplicitLod and as the CTS reference expects.
+                    const SizeT lodIndex = static_cast<SizeT>(form->explicitLodArg);
+                    if (argCount <= lodIndex) continue;
+                    const SizeT lodStart = marks[lodIndex - 1] + 1;
+                    const SizeT lodEnd = marks[lodIndex];
+                    result.insert(lodEnd, String(") + ") + biasName + ")");
+                    result.insert(lodStart, "((");
+                } else {
+                    const SizeT required = static_cast<SizeT>(form->requiredArgs);
+                    if (argCount == required) {
+                        result.insert(closeParen, String(", ") + biasName);
+                    } else if (argCount == required + 1) {
+                        const SizeT biasStart = marks[argCount - 2] + 1;
+                        result.insert(closeParen, String(") + ") + biasName + ")");
+                        result.insert(biasStart, "((");
+                    } else {
+                        continue;
+                    }
+                }
+                usedSamplers.push_back(samplerName);
+            }
+            if (usedSamplers.empty()) {
+                return glslCode;
+            }
+
+            // Declare the bias uniforms that were actually referenced, right after the
+            // sampler declaration line they belong to.
+            for (const auto& samplerName : usedSamplers) {
+                const String& biasName = samplerNames[samplerName];
+                if (result.find(String("float ") + biasName + ";") != String::npos) continue;
+                const std::regex declRegex(
+                    R"(uniform\s+(?:(?:highp|mediump|lowp)\s+)?[iu]?sampler[A-Za-z0-9]*\s+)" + samplerName + R"(\s*;)");
+                std::smatch match;
+                if (!std::regex_search(result, match, declRegex)) continue;
+                const SizeT declEnd = static_cast<SizeT>(match.position(0)) + match[0].str().size();
+                result.insert(declEnd, String("\nuniform highp float ") + biasName + ";");
+            }
+            return result;
+        }
+
     } // namespace PrgramImpl
 
     namespace Utils {
@@ -448,4 +740,412 @@ namespace MobileGL::MG_Backend::DirectGLES {
             }
         }
     } // namespace Utils
+
+    // ---- Client-format readback conversion helpers -------------------------------------------------
+    // ReadPixels/GetTexImage read a guaranteed wide RGBA(_INTEGER) layout from the ES driver and repack
+    // it on the CPU into the client's (format, type) layout. Everything here is pure byte shuffling so
+    // unit tests can assert the exact packed words; field positions follow GL 3.3 table 3.6 and mirror
+    // the GL CTS packed_pixels oracle (glcPackedPixelsTests.cpp pack_UNSIGNED_* helpers).
+    namespace ReadbackImpl {
+        using MG_Util::DecodeHalfBitsToFloat;
+        using MG_Util::EncodeFloatToHalfBits;
+
+        Bool GetReadbackChannelMapping(GLenum format, ReadbackChannelMapping& outMapping) {
+            switch (format) {
+            case GL_RED:          outMapping = {{0, 0, 0, 0}, 1, false}; return true;
+            case GL_RED_INTEGER:  outMapping = {{0, 0, 0, 0}, 1, true};  return true;
+            // Desktop-GL single-channel client formats (GL CTS packed_pixels rgba8_format_green/blue):
+            // the destination holds one component sourced from the named channel of the wide RGBA read.
+            // GL_ALPHA is mapped here from the raw enum because the state layer folds it into Red for the
+            // legacy alpha-texture upload hack.
+            case GL_GREEN:         outMapping = {{1, 0, 0, 0}, 1, false}; return true;
+            case GL_GREEN_INTEGER: outMapping = {{1, 0, 0, 0}, 1, true};  return true;
+            case GL_BLUE:          outMapping = {{2, 0, 0, 0}, 1, false}; return true;
+            case GL_BLUE_INTEGER:  outMapping = {{2, 0, 0, 0}, 1, true};  return true;
+            case GL_ALPHA:         outMapping = {{3, 0, 0, 0}, 1, false}; return true;
+            case GL_ALPHA_INTEGER: outMapping = {{3, 0, 0, 0}, 1, true};  return true;
+            case GL_RG:           outMapping = {{0, 1, 0, 0}, 2, false}; return true;
+            case GL_RG_INTEGER:   outMapping = {{0, 1, 0, 0}, 2, true};  return true;
+            case GL_RGB:          outMapping = {{0, 1, 2, 0}, 3, false}; return true;
+            case GL_RGB_INTEGER:  outMapping = {{0, 1, 2, 0}, 3, true};  return true;
+            case GL_BGR:          outMapping = {{2, 1, 0, 0}, 3, false}; return true;
+            case GL_BGR_INTEGER:  outMapping = {{2, 1, 0, 0}, 3, true};  return true;
+            case GL_RGBA:         outMapping = {{0, 1, 2, 3}, 4, false}; return true;
+            case GL_RGBA_INTEGER: outMapping = {{0, 1, 2, 3}, 4, true};  return true;
+            case GL_BGRA:         outMapping = {{2, 1, 0, 3}, 4, false}; return true;
+            case GL_BGRA_INTEGER: outMapping = {{2, 1, 0, 3}, 4, true};  return true;
+            default:
+                return false;
+            }
+        }
+
+        Bool GetPackedReadbackLayout(GLenum type, PackedReadbackLayout& out) {
+            switch (type) {
+            // Non-REV types pack the first format component starting at the most significant bit,
+            // *_REV types starting at the least significant bit (GL CTS pack_UNSIGNED_SHORT_5_6_5:
+            // R bits 15-11; pack_UNSIGNED_SHORT_1_5_5_5_REV: R bits 4-0, A bit 15).
+            case GL_UNSIGNED_BYTE_3_3_2:          out = {3, {3, 3, 2, 0},    {5, 2, 0, 0},    1, false}; return true;
+            case GL_UNSIGNED_BYTE_2_3_3_REV:      out = {3, {3, 3, 2, 0},    {0, 3, 6, 0},    1, false}; return true;
+            case GL_UNSIGNED_SHORT_5_6_5:         out = {3, {5, 6, 5, 0},    {11, 5, 0, 0},   2, false}; return true;
+            case GL_UNSIGNED_SHORT_5_6_5_REV:     out = {3, {5, 6, 5, 0},    {0, 5, 11, 0},   2, false}; return true;
+            case GL_UNSIGNED_SHORT_4_4_4_4:       out = {4, {4, 4, 4, 4},    {12, 8, 4, 0},   2, false}; return true;
+            case GL_UNSIGNED_SHORT_4_4_4_4_REV:   out = {4, {4, 4, 4, 4},    {0, 4, 8, 12},   2, false}; return true;
+            case GL_UNSIGNED_SHORT_5_5_5_1:       out = {4, {5, 5, 5, 1},    {11, 6, 1, 0},   2, false}; return true;
+            case GL_UNSIGNED_SHORT_1_5_5_5_REV:   out = {4, {5, 5, 5, 1},    {0, 5, 10, 15},  2, false}; return true;
+            case GL_UNSIGNED_INT_8_8_8_8:         out = {4, {8, 8, 8, 8},    {24, 16, 8, 0},  4, false}; return true;
+            case GL_UNSIGNED_INT_8_8_8_8_REV:     out = {4, {8, 8, 8, 8},    {0, 8, 16, 24},  4, false}; return true;
+            case GL_UNSIGNED_INT_10_10_10_2:      out = {4, {10, 10, 10, 2}, {22, 12, 2, 0},  4, false}; return true;
+            case GL_UNSIGNED_INT_2_10_10_10_REV:  out = {4, {10, 10, 10, 2}, {0, 10, 20, 30}, 4, false}; return true;
+            // Packed-float RGB types: fields hold unsigned small floats; 5_9_9_9_REV's shared 5-bit
+            // exponent (bits 31-27) is emitted by EncodeSharedExponentRGB9E5, not a component field.
+            case GL_UNSIGNED_INT_10F_11F_11F_REV: out = {3, {11, 11, 10, 0}, {0, 11, 22, 0},  4, true};  return true;
+            case GL_UNSIGNED_INT_5_9_9_9_REV:     out = {3, {9, 9, 9, 0},    {0, 9, 18, 0},   4, true};  return true;
+            default:
+                return false;
+            }
+        }
+
+        SizeT GetReadbackComponentSize(GLenum type) {
+            PackedReadbackLayout packedLayout{};
+            if (GetPackedReadbackLayout(type, packedLayout)) {
+                return packedLayout.byteSize;
+            }
+            switch (type) {
+            case GL_UNSIGNED_BYTE:
+            case GL_BYTE:
+                return 1;
+            case GL_UNSIGNED_SHORT:
+            case GL_SHORT:
+            case GL_HALF_FLOAT:
+                return 2;
+            case GL_UNSIGNED_INT:
+            case GL_INT:
+            case GL_FLOAT:
+                return 4;
+            default:
+                return 0;
+            }
+        }
+
+        SizeT GetReadbackDstPixelSize(const ReadbackChannelMapping& mapping, GLenum type) {
+            PackedReadbackLayout packedLayout{};
+            if (GetPackedReadbackLayout(type, packedLayout)) {
+                if (packedLayout.fieldCount != mapping.channelCount) {
+                    return 0; // 3-field packed types pair with 3-component formats only, 4 with 4
+                }
+                if (mapping.isInteger && packedLayout.isFloatPacked) {
+                    return 0; // packed-float RGB types never pair with integer formats
+                }
+                return packedLayout.byteSize;
+            }
+            if (mapping.isInteger && (type == GL_FLOAT || type == GL_HALF_FLOAT)) {
+                return 0;
+            }
+            const SizeT componentSize = GetReadbackComponentSize(type);
+            return componentSize == 0 ? 0 : static_cast<SizeT>(mapping.channelCount) * componentSize;
+        }
+
+        namespace {
+            void WritePackedReadbackWord(Uint8* dst, Uint32 word, SizeT byteSize) {
+                switch (byteSize) {
+                case 1: {
+                    const auto out = static_cast<Uint8>(word);
+                    Memcpy(dst, &out, sizeof(out));
+                    break;
+                }
+                case 2: {
+                    const auto out = static_cast<Uint16>(word);
+                    Memcpy(dst, &out, sizeof(out));
+                    break;
+                }
+                default:
+                    Memcpy(dst, &word, sizeof(word));
+                    break;
+                }
+            }
+        } // namespace
+
+        // Shared encoders live in MG_Util/Math/SmallFloat.h so the upload conversion
+        // (PixelStoreProcessor) uses byte-identical packing; kept exported here for unit tests.
+        Uint32 EncodeFloatToUnsignedF11(Float value) { return MG_Util::EncodeFloatToUnsignedF11(value); }
+        Uint32 EncodeFloatToUnsignedF10(Float value) { return MG_Util::EncodeFloatToUnsignedF10(value); }
+        Uint32 EncodeSharedExponentRGB9E5(const Float rgb[3]) { return MG_Util::EncodeSharedExponentRGB9E5(rgb); }
+
+        void ConvertWideReadbackRow(const Uint8* src, Uint8* dst, SizeT width, GLenum wideType,
+                                    const ReadbackChannelMapping& mapping, GLenum type) {
+            PackedReadbackLayout packedLayout{};
+            const Bool isPacked = GetPackedReadbackLayout(type, packedLayout);
+            const SizeT dstComponentSize = GetReadbackComponentSize(type);
+            const SizeT dstPixelBytes = GetReadbackDstPixelSize(mapping, type);
+            const SizeT srcPixelBytes = 4 * GetReadbackComponentSize(wideType);
+
+            for (SizeT col = 0; col < width; ++col) {
+                const Uint8* srcPixel = src + col * srcPixelBytes;
+                Uint8* dstPixel = dst + col * dstPixelBytes;
+                if (mapping.isInteger) {
+                    Int64 srcValues[4];
+                    for (Int c = 0; c < 4; ++c) {
+                        srcValues[c] = wideType == GL_INT
+                                           ? static_cast<Int64>(reinterpret_cast<const Int32*>(srcPixel)[c])
+                                           : static_cast<Int64>(reinterpret_cast<const Uint32*>(srcPixel)[c]);
+                    }
+                    if (isPacked) {
+                        // Integer sources clamp each component to the unsigned range of its field
+                        // (GL 3.3 section 4.3.1 final conversion).
+                        Uint32 word = 0;
+                        for (Int ch = 0; ch < packedLayout.fieldCount; ++ch) {
+                            const Int64 fieldMax = (Int64{1} << packedLayout.width[ch]) - 1;
+                            const auto v = static_cast<Uint32>(
+                                std::clamp<Int64>(srcValues[mapping.sourceChannel[ch]], 0, fieldMax));
+                            word |= v << packedLayout.shift[ch];
+                        }
+                        WritePackedReadbackWord(dstPixel, word, packedLayout.byteSize);
+                    } else {
+                        for (Int ch = 0; ch < mapping.channelCount; ++ch) {
+                            const Int64 v = srcValues[mapping.sourceChannel[ch]];
+                            Uint8* dstComponent = dstPixel + static_cast<SizeT>(ch) * dstComponentSize;
+                            switch (type) {
+                            case GL_UNSIGNED_BYTE:
+                                *dstComponent = static_cast<Uint8>(std::clamp<Int64>(v, 0, 255));
+                                break;
+                            case GL_BYTE: {
+                                const auto out = static_cast<Int8>(std::clamp<Int64>(v, -128, 127));
+                                Memcpy(dstComponent, &out, sizeof(out));
+                                break;
+                            }
+                            case GL_UNSIGNED_SHORT: {
+                                const auto out = static_cast<Uint16>(std::clamp<Int64>(v, 0, 65535));
+                                Memcpy(dstComponent, &out, sizeof(out));
+                                break;
+                            }
+                            case GL_SHORT: {
+                                const auto out = static_cast<Int16>(std::clamp<Int64>(v, -32768, 32767));
+                                Memcpy(dstComponent, &out, sizeof(out));
+                                break;
+                            }
+                            case GL_UNSIGNED_INT: {
+                                const auto out = static_cast<Uint32>(std::clamp<Int64>(v, 0, 4294967295LL));
+                                Memcpy(dstComponent, &out, sizeof(out));
+                                break;
+                            }
+                            case GL_INT: {
+                                const auto out =
+                                    static_cast<Int32>(std::clamp<Int64>(v, -2147483648LL, 2147483647LL));
+                                Memcpy(dstComponent, &out, sizeof(out));
+                                break;
+                            }
+                            default:
+                                break;
+                            }
+                        }
+                    }
+                } else {
+                    Float srcValues[4];
+                    switch (wideType) {
+                    case GL_UNSIGNED_BYTE:
+                        for (Int c = 0; c < 4; ++c) {
+                            srcValues[c] = static_cast<Float>(srcPixel[c]) / 255.0f;
+                        }
+                        break;
+                    case GL_BYTE:
+                        for (Int c = 0; c < 4; ++c) {
+                            srcValues[c] = std::max(
+                                static_cast<Float>(reinterpret_cast<const Int8*>(srcPixel)[c]) / 127.0f, -1.0f);
+                        }
+                        break;
+                    case GL_UNSIGNED_SHORT:
+                        for (Int c = 0; c < 4; ++c) {
+                            srcValues[c] =
+                                static_cast<Float>(reinterpret_cast<const Uint16*>(srcPixel)[c]) / 65535.0f;
+                        }
+                        break;
+                    case GL_SHORT:
+                        for (Int c = 0; c < 4; ++c) {
+                            srcValues[c] = std::max(
+                                static_cast<Float>(reinterpret_cast<const Int16*>(srcPixel)[c]) / 32767.0f, -1.0f);
+                        }
+                        break;
+                    case GL_HALF_FLOAT:
+                        for (Int c = 0; c < 4; ++c) {
+                            srcValues[c] = DecodeHalfBitsToFloat(reinterpret_cast<const Uint16*>(srcPixel)[c]);
+                        }
+                        break;
+                    default: // GL_FLOAT
+                        for (Int c = 0; c < 4; ++c) {
+                            srcValues[c] = reinterpret_cast<const Float*>(srcPixel)[c];
+                        }
+                        break;
+                    }
+                    if (isPacked) {
+                        Uint32 word = 0;
+                        if (packedLayout.isFloatPacked) {
+                            const Float fields[3] = {srcValues[mapping.sourceChannel[0]],
+                                                     srcValues[mapping.sourceChannel[1]],
+                                                     srcValues[mapping.sourceChannel[2]]};
+                            word = type == GL_UNSIGNED_INT_5_9_9_9_REV
+                                       ? EncodeSharedExponentRGB9E5(fields)
+                                       : (EncodeFloatToUnsignedF11(fields[0]) << packedLayout.shift[0]) |
+                                             (EncodeFloatToUnsignedF11(fields[1]) << packedLayout.shift[1]) |
+                                             (EncodeFloatToUnsignedF10(fields[2]) << packedLayout.shift[2]);
+                        } else {
+                            // Normalized encode: round(clamp(v, 0, 1) * (2^bits - 1)) into each field.
+                            for (Int ch = 0; ch < packedLayout.fieldCount; ++ch) {
+                                const auto fieldMax = static_cast<Float>((1u << packedLayout.width[ch]) - 1u);
+                                const auto v = static_cast<Uint32>(std::llround(
+                                    std::clamp(srcValues[mapping.sourceChannel[ch]], 0.0f, 1.0f) * fieldMax));
+                                word |= v << packedLayout.shift[ch];
+                            }
+                        }
+                        WritePackedReadbackWord(dstPixel, word, packedLayout.byteSize);
+                    } else {
+                        for (Int ch = 0; ch < mapping.channelCount; ++ch) {
+                            const Float v = srcValues[mapping.sourceChannel[ch]];
+                            Uint8* dstComponent = dstPixel + static_cast<SizeT>(ch) * dstComponentSize;
+                            switch (type) {
+                            case GL_UNSIGNED_BYTE:
+                                *dstComponent =
+                                    static_cast<Uint8>(std::llround(std::clamp(v, 0.0f, 1.0f) * 255.0));
+                                break;
+                            case GL_BYTE: {
+                                const auto out =
+                                    static_cast<Int8>(std::llround(std::clamp(v, -1.0f, 1.0f) * 127.0));
+                                Memcpy(dstComponent, &out, sizeof(out));
+                                break;
+                            }
+                            case GL_UNSIGNED_SHORT: {
+                                const auto out =
+                                    static_cast<Uint16>(std::llround(std::clamp(v, 0.0f, 1.0f) * 65535.0));
+                                Memcpy(dstComponent, &out, sizeof(out));
+                                break;
+                            }
+                            case GL_SHORT: {
+                                const auto out =
+                                    static_cast<Int16>(std::llround(std::clamp(v, -1.0f, 1.0f) * 32767.0));
+                                Memcpy(dstComponent, &out, sizeof(out));
+                                break;
+                            }
+                            case GL_UNSIGNED_INT: {
+                                const auto out = static_cast<Uint32>(
+                                    std::llround(static_cast<Double>(std::clamp(v, 0.0f, 1.0f)) * 4294967295.0));
+                                Memcpy(dstComponent, &out, sizeof(out));
+                                break;
+                            }
+                            case GL_INT: {
+                                const auto out = static_cast<Int32>(
+                                    std::llround(static_cast<Double>(std::clamp(v, -1.0f, 1.0f)) * 2147483647.0));
+                                Memcpy(dstComponent, &out, sizeof(out));
+                                break;
+                            }
+                            case GL_FLOAT:
+                                Memcpy(dstComponent, &v, sizeof(v));
+                                break;
+                            case GL_HALF_FLOAT: {
+                                const Uint16 out = EncodeFloatToHalfBits(v);
+                                Memcpy(dstComponent, &out, sizeof(out));
+                                break;
+                            }
+                            default:
+                                break;
+                            }
+                        }
+                    }
+                }
+            }
+        }
+
+        static SizeT AlignReadbackRow(SizeT rowBytes, Int alignment) {
+            const SizeT align = alignment > 0 ? static_cast<SizeT>(alignment) : 1;
+            return (rowBytes + align - 1) / align * align;
+        }
+
+    // Repacks wide RGBA(_INTEGER) rows into the client's (format, type) layout, honoring the
+        // client-side PACK parameters and the bound pixel-pack buffer. `wide` holds
+        // `sliceHeight * sliceCount` rows of `width` texels (slice-major, tightly stacked),
+        // 4 components x GetReadbackComponentSize(wideType) bytes each.
+        // applyPackImageParams: GL_PACK_IMAGE_HEIGHT / GL_PACK_SKIP_IMAGES apply only to GetTexImage
+        // of 3D/array images; ReadPixels and 2D GetTexImage ignore them (GL 3.3 sections 4.3.1, 6.1.4).
+        // Per the GL addressing rules, slice k row j lands at
+        // SKIP_IMAGES*imageStride + SKIP_ROWS*rowStride + SKIP_PIXELS*pixelBytes
+        //   + k*imageStride + j*rowStride, with imageStride = max(IMAGE_HEIGHT, sliceHeight)*rowStride.
+        Bool StoreWideRowsToClient(const Uint8* wide, GLenum wideType, GLsizei width, GLsizei sliceHeight,
+                                   GLsizei sliceCount, const ReadbackChannelMapping& mapping, GLenum type,
+                                   void* pixels, Bool applyPackImageParams) {
+        const SizeT dstPixelBytes = GetReadbackDstPixelSize(mapping, type);
+        if (dstPixelBytes == 0) {
+            return false;
+        }
+        PackedReadbackLayout packedLayout{};
+        const Bool isPackedType = GetPackedReadbackLayout(type, packedLayout);
+        const SizeT dstComponentSize = GetReadbackComponentSize(type);
+
+        const auto& pixelPackBufferObject =
+            MG_State::pGLContext->GetBufferBindingSlot(BufferTarget::PixelPack).GetBoundObject();
+
+        // Destination layout is computed from the client-side PACK parameters; only the actual pixel
+        // rows are written so skip regions of the destination stay untouched.
+        const auto packParams = MG_State::pGLContext->GetPixelStoreParameters(false);
+        const SizeT rowPixels = static_cast<SizeT>(packParams.RowLength > 0 ? packParams.RowLength : width);
+        const SizeT dstRowStride = AlignReadbackRow(rowPixels * dstPixelBytes, packParams.Alignment);
+        const SizeT imageRows =
+            applyPackImageParams && packParams.ImageHeight > 0
+                ? static_cast<SizeT>(packParams.ImageHeight)
+                : static_cast<SizeT>(sliceHeight);
+        const SizeT dstImageStride = imageRows * dstRowStride;
+        const SizeT skipImages =
+            applyPackImageParams ? static_cast<SizeT>(std::max(packParams.SkipImages, 0)) : SizeT{0};
+        const SizeT dstSkipOffset = skipImages * dstImageStride +
+                                    static_cast<SizeT>(std::max(packParams.SkipRows, 0)) * dstRowStride +
+                                    static_cast<SizeT>(std::max(packParams.SkipPixels, 0)) * dstPixelBytes;
+        const SizeT dstRowBytes = static_cast<SizeT>(width) * dstPixelBytes;
+
+        const SizeT pboBaseOffset = reinterpret_cast<SizeT>(pixels); // with a PBO, `pixels` is an offset
+        if (pixelPackBufferObject) {
+            const SizeT requiredSize = pboBaseOffset + dstSkipOffset +
+                                    static_cast<SizeT>(sliceCount - 1) * dstImageStride +
+                                    static_cast<SizeT>(sliceHeight - 1) * dstRowStride + dstRowBytes;
+            if (requiredSize > pixelPackBufferObject->GetSize()) {
+                MGLOG_E("Readback conversion: pixel pack buffer is too small");
+                return true;
+            }
+        }
+
+        const SizeT srcComponentSize = GetReadbackComponentSize(wideType);
+        const SizeT srcPixelBytes = 4 * srcComponentSize;
+        Vector<Uint8> convertedRow(dstRowBytes);
+
+        for (GLsizei slice = 0; slice < sliceCount; ++slice) {
+            for (GLsizei row = 0; row < sliceHeight; ++row) {
+                const SizeT flatRow = static_cast<SizeT>(slice) * static_cast<SizeT>(sliceHeight) +
+                                   static_cast<SizeT>(row);
+                const Uint8* srcRow = wide + flatRow * static_cast<SizeT>(width) * srcPixelBytes;
+                ConvertWideReadbackRow(srcRow, convertedRow.data(), static_cast<SizeT>(width), wideType,
+                                                  mapping, type);
+
+                if (packParams.SwapBytes) {
+                    const SizeT groupSize = isPackedType ? packedLayout.byteSize : dstComponentSize;
+                    if (groupSize > 1) {
+                        for (SizeT offset = 0; offset + groupSize <= dstRowBytes; offset += groupSize) {
+                            std::reverse(convertedRow.data() + offset, convertedRow.data() + offset + groupSize);
+                        }
+                    }
+                }
+
+                const SizeT dstOffset = dstSkipOffset + static_cast<SizeT>(slice) * dstImageStride +
+                                     static_cast<SizeT>(row) * dstRowStride;
+                if (pixelPackBufferObject) {
+                    pixelPackBufferObject->WritebackFromBackend({convertedRow.data(), dstRowBytes},
+                                                             pboBaseOffset + dstOffset);
+                } else {
+                    Memcpy(static_cast<Uint8*>(pixels) + dstOffset, convertedRow.data(), dstRowBytes);
+                }
+            }
+        }
+            if (pixelPackBufferObject) {
+                // WritebackFromBackend bumps change serials with no backend op; re-open
+                // the buffer draw-clean memos (once for the whole row loop).
+                BufferImpl::BumpBufferMutationEpoch();
+            }
+            return true;
+        }
+    } // namespace ReadbackImpl
 } // namespace MobileGL::MG_Backend::DirectGLES

MobileGL/MG_Backend/DirectGLES/Utils.h

@@ -9,6 +9,8 @@
 #pragma once
 #include <Includes.h>
 #include <MG_State/GLState/Core.h>
+#include <MG_Util/BackendLoaders/OpenGL/Loader.h>
+#include <MG_Util/Texture/TextureFormatProcessor.h>
 
 namespace MobileGL::MG_Backend::DirectGLES {
     namespace DebugImpl {
@@ -34,24 +36,113 @@ namespace MobileGL::MG_Backend::DirectGLES {
     } // namespace VertexArrayImpl
 
     namespace TextureImpl {
+        // Whether images on this format-capability target can back a colour attachment, and so
+        // need a colour-renderable storage format even when the frontend asked for a
+        // three-channel one ES never renders to. Shared by the capability probe (which passes the
+        // capabilities it has just queried, before the globals are published) and by the
+        // allocation path (which reads the active backend's), so the format the cache was probed
+        // with is always the format the image is created with.
+        Bool TargetRequiresRenderableFormat(SizeT targetIndex);
+        Flags<PixelFormatNormalizeOptionBit> GetRenderTargetNormalizeOptions(
+            const MG_External::GLESCapabilities& capabilities, SizeT targetIndex);
+
         void GenerateTextureFormatInfo(TextureInternalFormat internalFormat, GLenum* outInternalFormat,
                                        GLenum* outFormat, GLenum* outType,
                                        TextureTarget target = TextureTarget::Unknown);
         void GenerateRenderbufferFormatInfo(TextureInternalFormat internalFormat, GLenum* outInternalFormat,
                                             GLenum* outFormat, GLenum* outType);
         Bool ShouldUseCaveatTextureFormat(TextureInternalFormat internalFormat, TextureTarget target);
+
+        // True when the format the image is actually created with has an alpha channel the
+        // frontend format does not (the three-channel colour-renderable widening). GL reads such
+        // a channel back as 1.0, so any swizzle source of ALPHA has to be answered with ONE and
+        // any readback of the image has to overwrite the alpha the draw happened to leave there.
+        Bool BackendTextureFormatAddsAlpha(TextureInternalFormat internalFormat, TextureTarget target);
+        Bool BackendRenderbufferFormatAddsAlpha(TextureInternalFormat internalFormat);
         Bool ShouldUseCaveatRenderbufferFormat(TextureInternalFormat internalFormat);
     } // namespace TextureImpl
 
     namespace FramebufferImpl {} // namespace FramebufferImpl
 
+    // Pure CPU helpers of the client-format readback conversion (ReadPixels/GetTexImage repack a wide
+    // RGBA(_INTEGER) read into the caller's (format, type) layout). Kept context-free so unit tests can
+    // exercise the exact packing the GL CTS packed_pixels oracle compares against.
+    namespace ReadbackImpl {
+        struct ReadbackChannelMapping {
+            Int sourceChannel[4]; // RGBA source channel feeding each destination component
+            Int channelCount;     // destination component count
+            Bool isInteger;
+        };
+        Bool GetReadbackChannelMapping(GLenum format, ReadbackChannelMapping& outMapping);
+
+        // Byte size of one destination component of `type`; packed types report the packed word size.
+        // 0 = type not supported by the conversion path.
+        SizeT GetReadbackComponentSize(GLenum type);
+
+        // Bit-field layout of a GL packed pixel type. width/shift are indexed in the client format's
+        // component order (matching ReadbackChannelMapping); shift is the LSB position of the field in
+        // the packed word: non-REV types pack the first component from the MSB, *_REV types from the
+        // LSB (GL 3.3 table 3.6; field positions mirror the GL CTS glcPackedPixelsTests pack_* oracle).
+        struct PackedReadbackLayout {
+            Int fieldCount;     // format components stored in the packed word
+            Int width[4];       // bit width of each component's field
+            Int shift[4];       // LSB bit position of each component's field
+            SizeT byteSize;     // packed word size in bytes (1, 2 or 4)
+            Bool isFloatPacked; // 10F_11F_11F_REV / 5_9_9_9_REV: fields hold unsigned small floats
+        };
+        Bool GetPackedReadbackLayout(GLenum type, PackedReadbackLayout& out);
+
+        // Unsigned small-float encoders (EXT_packed_float / EXT_texture_shared_exponent semantics).
+        Uint32 EncodeFloatToUnsignedF11(Float value);
+        Uint32 EncodeFloatToUnsignedF10(Float value);
+        Uint32 EncodeSharedExponentRGB9E5(const Float rgb[3]);
+
+        // Destination bytes per pixel for a (format mapping, type) readback pair; 0 when the pair is
+        // not convertible (unknown type, packed field count != format component count, floating-point
+        // or packed-float type with an integer format).
+        SizeT GetReadbackDstPixelSize(const ReadbackChannelMapping& mapping, GLenum type);
+
+        // Repacks one row of wide RGBA(_INTEGER) texels (4 components of wideType each) into the
+        // client's (format, type) layout. src holds width * 4 * GetReadbackComponentSize(wideType)
+        // bytes, dst receives width * GetReadbackDstPixelSize(mapping, type) bytes.
+        void ConvertWideReadbackRow(const Uint8* src, Uint8* dst, SizeT width, GLenum wideType,
+                                    const ReadbackChannelMapping& mapping, GLenum type);
+
+        // Stores wide RGBA(_INTEGER) rows into the client pointer or the bound PACK pixel buffer,
+        // honoring the client-side PACK pixel-store parameters (row length, alignment, skips,
+        // swap-bytes, and - when applyPackImageParams - image height/skip images). Shared by the
+        // DirectGLES and DirectVulkan readback conversion paths.
+        Bool StoreWideRowsToClient(const Uint8* wide, GLenum wideType, GLsizei width, GLsizei sliceHeight,
+                                   GLsizei sliceCount, const ReadbackChannelMapping& mapping, GLenum type,
+                                   void* pixels, Bool applyPackImageParams);
+    } // namespace ReadbackImpl
+
     namespace PrgramImpl {
         String ProcessOutColorLocations(const String& glslCode);
         String ForceSupporterOutput(const String& glslCode);
         String ClampNormFallbackOutputs(String glslCode, GLenum shaderType, Uint32 snormOutputMask,
                                         Uint32 unormOutputMask);
         String ForceFlatIntegerVaryings(const String& glslCode, GLenum shaderType);
+        // Legacy GLSL's gl_FragColor is broadcast to every enabled draw buffer (GL 4.6
+        // 15.2.3), but ShaderSourceProcessor lowers it to the single output mg_FragColor,
+        // which only ever reaches draw buffer 0. Replicates it across `drawBufferCount`
+        // outputs and copies the value into them at the end of main. A no-op for
+        // drawBufferCount <= 1, i.e. for everything but a framebuffer that actually
+        // enables several draw buffers, so the ordinary single-target shader is untouched.
+        String BroadcastLegacyFragColor(String glslCode, GLenum shaderType, Uint drawBufferCount);
         String RemoveLayoutBinding(const String& glslCode);
+        // Prefix of the per-sampler float uniform that carries GL_TEXTURE_LOD_BIAS into
+        // the shader (see EmulateTextureLodBias); the suffix is the sampler's own name.
+        constexpr const char* LOD_BIAS_UNIFORM_PREFIX = "mg_lodBias_";
+        // ES has no per-texture/sampler LOD bias at all (GL_TEXTURE_LOD_BIAS is desktop
+        // only; Vulkan spells it VkSamplerCreateInfo::mipLodBias), so it has to reach the
+        // shader as a uniform and be folded into every lookup's level of detail. Declares
+        // one `uniform highp float mg_lodBias_<sampler>;` per mip-capable sampler and adds
+        // it to the bias / explicit-LOD argument of every lookup that takes one. Draws push
+        // the bound texture's (or sampler object's) value into it; a shader whose samplers
+        // all have a zero bias is therefore unaffected. Returns the source unchanged when
+        // there is nothing to rewrite.
+        String EmulateTextureLodBias(const String& glslCode);
     } // namespace PrgramImpl
 
     namespace Utils {

MobileGL/MG_Backend/DirectVulkan/BackendObject_DirectVulkan.cpp

@@ -16,8 +16,10 @@
 #include "MG_Util/Converters/MGToStr/TextureEnumConverter.h"
 #include "MG_Util/Converters/MGToVk/TextureEnumConverter.h"
 #include "MG_Util/Texture/TextureFormatProcessor.h"
+#include "MG_Util/Async/ShaderCompilePool.h"
 
 #include <Config.h>
+#include <cmath>
 #include <cstdlib>
 #include <cstring>
 
@@ -40,13 +42,11 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         Bool IsLayeredTarget(TextureTarget target) {
             return target == TextureTarget::Texture3D || target == TextureTarget::Texture1DArray ||
                    target == TextureTarget::Texture2DArray || target == TextureTarget::TextureCubeMap ||
-                   target == TextureTarget::TextureCubeMapArray ||
-                   target == TextureTarget::Texture2DMultisampleArray;
+                   target == TextureTarget::TextureCubeMapArray || target == TextureTarget::Texture2DMultisampleArray;
         }
 
         Bool IsMultisampleTarget(TextureTarget target) {
-            return target == TextureTarget::Texture2DMultisample ||
-                   target == TextureTarget::Texture2DMultisampleArray;
+            return target == TextureTarget::Texture2DMultisample || target == TextureTarget::Texture2DMultisampleArray;
         }
 
         Bool IsTextureBufferTarget(TextureTarget target) {
@@ -58,8 +58,8 @@ namespace MobileGL::MG_Backend::DirectVulkan {
             GLenum normalizedInternalFormat = glFormat;
             GLenum imageFormat = GL_RGBA;
             GLenum imageType = GL_UNSIGNED_BYTE;
-            MG_Util::TextureFormatProcessor::NormalizePixelFormat(
-                glFormat, PixelFormatNormalizeOptionBit::None, &normalizedInternalFormat, &imageFormat, &imageType);
+            MG_Util::TextureFormatProcessor::NormalizePixelFormat(glFormat, PixelFormatNormalizeOptionBit::None,
+                                                                  &normalizedInternalFormat, &imageFormat, &imageType);
             return imageFormat == GL_RED_INTEGER || imageFormat == GL_RG_INTEGER || imageFormat == GL_RGB_INTEGER ||
                    imageFormat == GL_RGBA_INTEGER;
         }
@@ -80,8 +80,7 @@ namespace MobileGL::MG_Backend::DirectVulkan {
             return caps;
         }
 
-        FormatCapabilityFlags BuildVulkanCaps(TextureInternalFormat logicalFormat,
-                                              TextureTarget target,
+        FormatCapabilityFlags BuildVulkanCaps(TextureInternalFormat logicalFormat, TextureTarget target,
                                               VkFormatFeatureFlags features) {
             FormatCapabilityFlags caps;
             const Bool isDepth = MG_Util::IsDepthFormatInternalFormat(logicalFormat);
@@ -100,8 +99,7 @@ namespace MobileGL::MG_Backend::DirectVulkan {
             const Bool sampled = (features & VK_FORMAT_FEATURE_SAMPLED_IMAGE_BIT) != 0;
             const Bool linearFilter = (features & VK_FORMAT_FEATURE_SAMPLED_IMAGE_FILTER_LINEAR_BIT) != 0;
             const Bool colorRenderable = (features & VK_FORMAT_FEATURE_COLOR_ATTACHMENT_BIT) != 0;
-            const Bool depthStencilRenderable =
-                (features & VK_FORMAT_FEATURE_DEPTH_STENCIL_ATTACHMENT_BIT) != 0;
+            const Bool depthStencilRenderable = (features & VK_FORMAT_FEATURE_DEPTH_STENCIL_ATTACHMENT_BIT) != 0;
             const Bool renderable = (isDepth || isStencil) ? depthStencilRenderable : colorRenderable;
 
             if (sampled || renderable) {
@@ -140,6 +138,20 @@ namespace MobileGL::MG_Backend::DirectVulkan {
             case TextureInternalFormat::RGB:
             case TextureInternalFormat::RGB8:
                 return TextureInternalFormat::RGBA8;
+            // Legacy low-bit-depth formats with no (or rarely supported) native Vulkan
+            // encoding; a wider normalized fallback keeps at least the required precision.
+            case TextureInternalFormat::R3G3B2:
+            case TextureInternalFormat::RGB4:
+            case TextureInternalFormat::RGB5:
+            case TextureInternalFormat::RGBA2:
+            case TextureInternalFormat::RGBA4:
+            case TextureInternalFormat::RGB5A1:
+                return TextureInternalFormat::RGBA8;
+            case TextureInternalFormat::RGB10:
+                return TextureInternalFormat::RGB10A2;
+            case TextureInternalFormat::RGB12:
+            case TextureInternalFormat::RGBA12:
+                return TextureInternalFormat::RGBA16;
             case TextureInternalFormat::SRGB8:
                 return TextureInternalFormat::SRGB8Alpha8;
             case TextureInternalFormat::RGB8Snorm:
@@ -184,21 +196,20 @@ namespace MobileGL::MG_Backend::DirectVulkan {
 
         Bool HasNewCaveatFormatCaps(FormatCapabilityFlags nativeCaps, FormatCapabilityFlags fallbackCaps) {
             for (FormatCapability capability : kReportedFormatCapabilities) {
-                if (HasFormatCapability(fallbackCaps, capability) &&
-                    !HasFormatCapability(nativeCaps, capability)) {
+                if (HasFormatCapability(fallbackCaps, capability) && !HasFormatCapability(nativeCaps, capability)) {
                     return true;
                 }
             }
             return false;
         }
 
-        void LogVulkanFormatCaveat(TextureInternalFormat logicalFormat,
-                                   SizeT targetIndex,
+        void LogVulkanFormatCaveat(TextureInternalFormat logicalFormat, SizeT targetIndex,
                                    TextureInternalFormat fallbackFormat) {
-            MGLOG_D("Caveat: %s %s not fully supported. Reason: native Vulkan format is not fully supported. Fallback: %s",
-                    GetFormatCapabilityTargetName(targetIndex).c_str(),
-                    MG_Util::ConvertTextureInternalFormatToString(logicalFormat).c_str(),
-                    MG_Util::ConvertTextureInternalFormatToString(fallbackFormat).c_str());
+            MGLOG_D(
+                "Caveat: %s %s not fully supported. Reason: native Vulkan format is not fully supported. Fallback: %s",
+                GetFormatCapabilityTargetName(targetIndex).c_str(),
+                MG_Util::ConvertTextureInternalFormatToString(logicalFormat).c_str(),
+                MG_Util::ConvertTextureInternalFormatToString(fallbackFormat).c_str());
         }
 
         Vector<Int> BuildSampleCounts(Int maxSamples) {
@@ -242,15 +253,15 @@ namespace MobileGL::MG_Backend::DirectVulkan {
 
                 for (SizeT targetIndex = 0; targetIndex < kFormatCapabilityTextureTargetCount; ++targetIndex) {
                     const auto target = static_cast<TextureTarget>(targetIndex);
-                    const VkFormatFeatureFlags nativeFeatures =
-                        IsTextureBufferTarget(target) ? nativeProperties.bufferFeatures
-                                                      : nativeProperties.optimalTilingFeatures;
+                    const VkFormatFeatureFlags nativeFeatures = IsTextureBufferTarget(target)
+                                                                    ? nativeProperties.bufferFeatures
+                                                                    : nativeProperties.optimalTilingFeatures;
                     FormatCapabilityFlags nativeCaps = BuildVulkanCaps(logicalFormat, target, nativeFeatures);
                     cache.FullCaps[targetIndex][formatIndex] |= nativeCaps;
 
-                    const VkFormatFeatureFlags fallbackFeatures =
-                        IsTextureBufferTarget(target) ? fallbackProperties.bufferFeatures
-                                                      : fallbackProperties.optimalTilingFeatures;
+                    const VkFormatFeatureFlags fallbackFeatures = IsTextureBufferTarget(target)
+                                                                      ? fallbackProperties.bufferFeatures
+                                                                      : fallbackProperties.optimalTilingFeatures;
                     FormatCapabilityFlags fallbackCaps = BuildVulkanCaps(logicalFormat, target, fallbackFeatures);
                     if (fallbackFormat != VK_FORMAT_UNDEFINED && fallbackFormat != nativeFormat) {
                         cache.CaveatCaps[targetIndex][formatIndex] |= fallbackCaps;
@@ -285,9 +296,8 @@ namespace MobileGL::MG_Backend::DirectVulkan {
                 cache.FullCaps[renderbufferTargetIndex][formatIndex] |= renderbufferCaps;
 
                 if (fallbackFormat != VK_FORMAT_UNDEFINED && fallbackFormat != nativeFormat) {
-                    FormatCapabilityFlags fallbackRenderbufferCaps =
-                        BuildVulkanCaps(logicalFormat, TextureTarget::Texture2D,
-                                        fallbackProperties.optimalTilingFeatures);
+                    FormatCapabilityFlags fallbackRenderbufferCaps = BuildVulkanCaps(
+                        logicalFormat, TextureTarget::Texture2D, fallbackProperties.optimalTilingFeatures);
                     fallbackRenderbufferCaps &= FormatCapability::Creatable;
                     if ((fallbackProperties.optimalTilingFeatures &
                          (VK_FORMAT_FEATURE_COLOR_ATTACHMENT_BIT | VK_FORMAT_FEATURE_DEPTH_STENCIL_ATTACHMENT_BIT)) !=
@@ -296,8 +306,7 @@ namespace MobileGL::MG_Backend::DirectVulkan {
                         fallbackRenderbufferCaps |= FormatCapability::MultisampleRenderbuffer;
                     }
                     cache.CaveatCaps[renderbufferTargetIndex][formatIndex] |= fallbackRenderbufferCaps;
-                    if (fallbackLogicalFormat &&
-                        HasNewCaveatFormatCaps(renderbufferCaps, fallbackRenderbufferCaps)) {
+                    if (fallbackLogicalFormat && HasNewCaveatFormatCaps(renderbufferCaps, fallbackRenderbufferCaps)) {
                         LogVulkanFormatCaveat(logicalFormat, renderbufferTargetIndex, *fallbackLogicalFormat);
                     }
                 }
@@ -314,14 +323,13 @@ namespace MobileGL::MG_Backend::DirectVulkan {
 
     void PopulateFormatCapabilities(VkPhysicalDevice physicalDevice,
                                     PFN_vkGetPhysicalDeviceFormatProperties getFormatProperties,
-                                    const MG_External::VulkanCapabilities& capabilities,
-                                    FormatCapabilityCache& cache) {
+                                    const MG_External::VulkanCapabilities& capabilities, FormatCapabilityCache& cache) {
         PopulateFormatCapabilitiesImpl(physicalDevice, getFormatProperties, capabilities, cache);
     }
 
     BackendObject_DirectVulkan::~BackendObject_DirectVulkan() = default;
 
-    BackendObject_DirectVulkan::BackendObject_DirectVulkan(): m_rendererInfo{GetRendererIdentity()} {}
+    BackendObject_DirectVulkan::BackendObject_DirectVulkan() : m_rendererInfo{GetRendererIdentity()} {}
 
     Bool BackendObject_DirectVulkan::InitWindowSurface() {
         if (!m_windowHandle.Handle) {
@@ -395,10 +403,9 @@ namespace MobileGL::MG_Backend::DirectVulkan {
             MGLOG_E("DirectVulkan backend not initialized");
             return false;
         }
-        if (!handle.Handle || (handle.Backend != WindowBackend::Android &&
-                               handle.Backend != WindowBackend::X11 &&
-                               handle.Backend != WindowBackend::MetalLayer)) {
-            MGLOG_E("DirectVulkan backend only supports Android, X11, and CAMetalLayer native windows");
+        if (!handle.Handle || (handle.Backend != WindowBackend::Android && handle.Backend != WindowBackend::X11 &&
+                               handle.Backend != WindowBackend::MetalLayer && handle.Backend != WindowBackend::Win32)) {
+            MGLOG_E("DirectVulkan backend only supports Android, X11, CAMetalLayer, and Win32 native windows");
             return false;
         }
 
@@ -454,6 +461,9 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         // treat them as signaled/available with zero results from here on.
         BumpRendererGeneration();
         pVulkanRenderer.reset();
+        // The reflection cache is file-scope, not renderer-owned; without this the
+        // deleted programs' reflection strings survive full context teardown.
+        ClearProgramResourceCaches();
         BackendObject::ReleaseEGLResources();
     }
 
@@ -463,6 +473,9 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         // treat them as signaled/available with zero results from here on.
         BumpRendererGeneration();
         pVulkanRenderer.reset();
+        // The reflection cache is file-scope, not renderer-owned; without this the
+        // deleted programs' reflection strings survive full context teardown.
+        ClearProgramResourceCaches();
     }
 
     const RendererInfo& BackendObject_DirectVulkan::GetRendererInfo() const {
@@ -482,40 +495,63 @@ namespace MobileGL::MG_Backend::DirectVulkan {
             .RendererName = "Magma",
             .BackendName = "Direct (Vulkan)",
             .ExtraVendor = Nullopt,
-            .RendererGLInfo =
-                {
-                    .TargetGLVersion = {3, 3, 0},
-                    .TargetGLSLVersion = {4, 6, 0},
-                    // Baseline advertisement (no shader subgroup, no timer queries); a
-                    // live backend reconciles its copy in UpdateAdvertisedExtensions.
-                    .Extensions = BuildAdvertisedExtensions(false, false),
-                    .IsCompatibilityProfile = false
-                },
+            .RendererGLInfo = {.TargetGLVersion = {4, 0, 0},
+                               .TargetGLSLVersion = {4, 6, 0},
+                               // Baseline advertisement (no shader subgroup, no timer queries); a
+                               // live backend reconciles its copy in UpdateAdvertisedExtensions.
+                               .Extensions = BuildAdvertisedExtensions(false, false, false),
+                               .IsCompatibilityProfile = false},
             .StaticBackendCapability = {.AllowVSOnlyPrograms = false}};
         return rendererInfo;
     }
 
-    Vector<GLExtension> BuildAdvertisedExtensions(Bool shaderSubgroupSupported, Bool timerQueriesSupported) {
-        Vector<GLExtension> extensions = {V_OpenGL30, V_OpenGL31, V_OpenGL32,
-                                          V_OpenGL33, E_GL_ARB_draw_buffers_blend, E_GL_ARB_compute_shader,
-                                          E_GL_ARB_shader_storage_buffer_object, E_GL_ARB_shader_image_load_store,
-                                          E_GL_ARB_program_interface_query, E_GL_ARB_framebuffer_object,
-                                          E_GL_ARB_multi_draw_indirect, E_GL_ARB_indirect_parameters,
-                                          E_GL_EXT_framebuffer_object, E_GL_ARB_depth_texture, E_GL_ARB_buffer_storage,
-                                          E_GL_ARB_texture_storage, E_GL_ARB_texture_storage_multisample,
-                                          E_GL_ARB_direct_state_access,
-                                          E_GL_ARB_shader_draw_parameters, E_GL_ARB_gpu_shader_int64, E_GL_KHR_debug,
-                                          E_GL_ARB_gpu_shader5, E_GL_ARB_multi_bind, E_GL_ARB_shading_language_420pack,
-                                          E_GL_ARB_vertex_attrib_binding, E_GL_ARB_shader_image_size};
+    Vector<GLExtension> BuildAdvertisedExtensions(Bool shaderSubgroupSupported, Bool timerQueriesSupported,
+                                                  Bool anisotropicFilteringSupported) {
+        Vector<GLExtension> extensions = {
+            V_OpenGL30, V_OpenGL31, V_OpenGL32, V_OpenGL33, V_OpenGL40, E_GL_ARB_draw_buffers_blend,
+            E_GL_ARB_compute_shader, E_GL_ARB_shader_storage_buffer_object, E_GL_ARB_shader_image_load_store,
+            E_GL_ARB_program_interface_query, E_GL_ARB_framebuffer_object, E_GL_ARB_multi_draw_indirect,
+            E_GL_ARB_indirect_parameters, E_GL_EXT_framebuffer_object, E_GL_ARB_depth_texture, E_GL_ARB_buffer_storage,
+            E_GL_ARB_texture_storage, E_GL_ARB_texture_storage_multisample, E_GL_ARB_texture_multisample,
+            E_GL_ARB_clear_texture, E_GL_ARB_direct_state_access, E_GL_ARB_shader_draw_parameters,
+            E_GL_ARB_gpu_shader_int64, E_GL_KHR_debug, E_GL_ARB_gpu_shader5, E_GL_ARB_multi_bind,
+            E_GL_ARB_shading_language_420pack, E_GL_ARB_vertex_attrib_binding, E_GL_ARB_shader_image_size,
+            E_GL_ARB_explicit_attrib_location,
+            // Advertised with GL_NUM_PROGRAM_BINARY_FORMATS = 0, which the
+            // extension explicitly permits. It is also the only thing that
+            // exposes glProgramParameteri before GL 4.1.
+            E_GL_ARB_get_program_binary};
         if (shaderSubgroupSupported && !MG_Config::Features.DisableSubgroup) {
             extensions.push_back(E_GL_KHR_shader_subgroup);
         }
+        // GL_KHR_parallel_shader_compile is MobileGL's own capability, not the Vulkan
+        // device's: the compiler threads belong to MobileGL's shader pool and
+        // glCompileShader/glLinkProgram are serviced entirely inside the frontend, so there
+        // is no device feature to condition this on.
+        //
+        // Gated on the async flag deliberately, and this is the whole reason the gate
+        // exists. Advertising the string is the one part of asynchronous compilation that a
+        // recorded trace can never cover: Iris and Sodium change their SUBMISSION SCHEDULE
+        // the moment they see it - they enqueue whole pipeline batches and poll
+        // GL_COMPLETION_STATUS_KHR instead of compiling one program at a time - so
+        // MOBILEGL_ASYNC_SHADER_COMPILE=0 has to withdraw the application-visible behaviour
+        // change as well as the threading, or the kill switch would only be half a switch.
+        if (MG_Util::Async::AsyncShaderCompileEnabled()) {
+            extensions.push_back(E_GL_KHR_parallel_shader_compile);
+        }
         // GL_ARB_timer_query gates MC's F3 GPU% (LWJGL checks the extension string);
         // only advertised when the device actually supports timestamp queries and the
         // MOBILEGL_DISABLE_TIMERQUERY escape hatch is off.
         if (timerQueriesSupported && !MG_Config::Features.DisableTimerQuery) {
             extensions.push_back(E_GL_ARB_timer_query);
         }
+        // Only advertised when the samplerAnisotropy device feature was granted: without it the
+        // sampler state is accepted but never applied, and an app trusting the string (LWJGL builds
+        // GLCapabilities from it) would think it enabled anisotropic filtering.
+        if (anisotropicFilteringSupported) {
+            extensions.push_back(E_GL_EXT_texture_filter_anisotropic);
+            extensions.push_back(E_GL_ARB_texture_filter_anisotropic);
+        }
         return extensions;
     }
 
@@ -562,6 +598,8 @@ namespace MobileGL::MG_Backend::DirectVulkan {
             funcsTable.GL.ClearBufferiv = ClearBufferiv;
             funcsTable.GL.ClearNamedFramebufferfv = ClearNamedFramebufferfv;
             funcsTable.GL.ClearNamedFramebufferfi = ClearNamedFramebufferfi;
+            funcsTable.GL.ClearNamedFramebufferiv = ClearNamedFramebufferiv;
+            funcsTable.GL.ClearNamedFramebufferuiv = ClearNamedFramebufferuiv;
             funcsTable.GL.BlitFramebuffer = BlitFramebuffer;
             funcsTable.GL.BlitNamedFramebuffer = BlitNamedFramebuffer;
             funcsTable.GL.CopyTexImage2D = CopyTexImage2D;
@@ -579,12 +617,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
             funcsTable.GL.GetIntegeri_v = GetIntegeri_v;
             funcsTable.GL.GetInteger64i_v = GetInteger64i_v;
             funcsTable.GL.GetProgramiv = GetProgramiv;
-            funcsTable.GL.GetProgramInterfaceiv = GetProgramInterfaceiv;
-            funcsTable.GL.GetProgramResourceIndex = GetProgramResourceIndex;
-            funcsTable.GL.GetProgramResourceName = GetProgramResourceName;
-            funcsTable.GL.GetProgramResourceiv = GetProgramResourceiv;
-            funcsTable.GL.GetProgramResourceLocation = GetProgramResourceLocation;
-            funcsTable.GL.GetProgramResourceLocationIndex = GetProgramResourceLocationIndex;
             funcsTable.GL.ShaderStorageBlockBinding = ShaderStorageBlockBinding;
             funcsTable.GL.FenceSync = FenceSync;
             funcsTable.GL.ClientWaitSync = ClientWaitSync;
@@ -605,6 +637,15 @@ namespace MobileGL::MG_Backend::DirectVulkan {
                 funcsTable.GL.DeleteBackendQuery = DeleteBackendQuery;
                 funcsTable.GL.GetGpuTimestampNs = GetGpuTimestampNs;
             }
+            // Occlusion queries share the handle-based result/delete entries, which must
+            // exist even when timer queries are disabled.
+            funcsTable.GL.BeginOcclusionQuery = BeginOcclusionQuery;
+            funcsTable.GL.EndOcclusionQuery = EndOcclusionQuery;
+            funcsTable.GL.BeginXfbPrimitivesQuery = BeginXfbPrimitivesQuery;
+            funcsTable.GL.EndXfbPrimitivesQuery = EndXfbPrimitivesQuery;
+            funcsTable.GL.IsQueryResultAvailable = IsQueryResultAvailable;
+            funcsTable.GL.GetQueryResult64 = GetQueryResult64;
+            funcsTable.GL.DeleteBackendQuery = DeleteBackendQuery;
             funcsTableInitialized = true;
         }
         return funcsTable;
@@ -630,7 +671,8 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         // run without a renderer; no timer query is advertised then. Rebuilding
         // the whole list keeps re-runs idempotent.
         m_rendererInfo.RendererGLInfo.Extensions = BuildAdvertisedExtensions(
-            m_vulkanCaps.SupportsShaderSubgroup, pVulkanRenderer && pVulkanRenderer->IsTimerQuerySupported());
+            m_vulkanCaps.SupportsShaderSubgroup, pVulkanRenderer && pVulkanRenderer->IsTimerQuerySupported(),
+            pVulkanRenderer && pVulkanRenderer->IsSamplerAnisotropySupported());
     }
 
     void BackendObject_DirectVulkan::UpdateDynamicBackendParameters() {
@@ -680,6 +722,11 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         m_dynamicParameters.UniformBufferOffsetAlignment = m_vulkanCaps.UniformBufferOffsetAlignment;
         m_dynamicParameters.AliasedLineWidthRangeMin = m_vulkanCaps.AliasedLineWidthRangeMin;
         m_dynamicParameters.AliasedLineWidthRangeMax = m_vulkanCaps.AliasedLineWidthRangeMax;
+        // Without the samplerAnisotropy feature the limit is unusable, so report 1.0 (no anisotropy)
+        // rather than a maximum the sampler manager will never apply.
+        m_dynamicParameters.MaxTextureMaxAnisotropy =
+            (pVulkanRenderer && pVulkanRenderer->IsSamplerAnisotropySupported()) ? m_vulkanCaps.MaxSamplerAnisotropy
+                                                                                 : 1.0f;
         m_dynamicParameters.SmoothLineWidthRangeMin = m_vulkanCaps.SmoothLineWidthRangeMin;
         m_dynamicParameters.SmoothLineWidthRangeMax = m_vulkanCaps.SmoothLineWidthRangeMax;
         m_dynamicParameters.SmoothLineWidthGranularity = m_vulkanCaps.SmoothLineWidthGranularity;
@@ -700,8 +747,7 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         m_dynamicParameters.MaxIntegerSamples = m_vulkanCaps.MaxIntegerSamples;
         m_dynamicParameters.MaxSamples = m_vulkanCaps.MaxSamples;
         m_dynamicParameters.MaxSampleMaskWords = m_vulkanCaps.MaxSampleMaskWords;
-        const Int maxSupportedTextureUnits =
-            static_cast<Int>(MG_State::GLState::TextureState::MAX_TEXTURE_IMAGE_UNITS);
+        const Int maxSupportedTextureUnits = static_cast<Int>(MG_State::GLState::TextureState::MAX_TEXTURE_IMAGE_UNITS);
         // GL_MAX_TEXTURE_IMAGE_UNITS is a *per-stage* sampler limit. Adreno/Qualcomm report a huge
         // maxPerStageDescriptorSampledImages (descriptor-indexing scale), so clamping it only to our
         // combined array capacity (192) still advertises 192 per stage. Host code treats this value as
@@ -711,8 +757,7 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         // limits while keeping the combined limit at our texture-unit array capacity.
         constexpr Int maxPerStageTextureUnits =
             static_cast<Int>(MG_State::GLState::TextureState::MAX_PER_STAGE_TEXTURE_IMAGE_UNITS);
-        m_dynamicParameters.MaxTextureImageUnits =
-            std::min(m_vulkanCaps.MaxTextureImageUnits, maxPerStageTextureUnits);
+        m_dynamicParameters.MaxTextureImageUnits = std::min(m_vulkanCaps.MaxTextureImageUnits, maxPerStageTextureUnits);
         m_dynamicParameters.MaxVertexTextureImageUnits =
             std::min(m_vulkanCaps.MaxVertexTextureImageUnits, maxPerStageTextureUnits);
         m_dynamicParameters.MaxComputeTextureImageUnits =
@@ -721,22 +766,35 @@ namespace MobileGL::MG_Backend::DirectVulkan {
             std::min(m_vulkanCaps.MaxCombinedTextureImageUnits, maxSupportedTextureUnits);
         // Never advertise more attributes than the state layer can store: the current-value array and
         // the Uint32 attribute masks the draw path passes around are both bounded by MAX_VERTEX_ATTRIBS.
-        m_dynamicParameters.MaxVertexAttribs =
-            std::min(m_vulkanCaps.MaxVertexAttribs,
-                     static_cast<Int>(MG_State::GLState::VertexArrayObject::MAX_VERTEX_ATTRIBS));
+        m_dynamicParameters.MaxVertexAttribs = std::min(
+            m_vulkanCaps.MaxVertexAttribs, static_cast<Int>(MG_State::GLState::VertexArrayObject::MAX_VERTEX_ATTRIBS));
         m_dynamicParameters.MaxComputeShaderStorageBlocks = m_vulkanCaps.MaxComputeShaderStorageBlocks;
         m_dynamicParameters.MaxCombinedShaderStorageBlocks = m_vulkanCaps.MaxCombinedShaderStorageBlocks;
         m_dynamicParameters.MaxComputeUniformBlocks = m_vulkanCaps.MaxComputeUniformBlocks;
         m_dynamicParameters.MaxComputeWorkGroupInvocations = m_vulkanCaps.MaxComputeWorkGroupInvocations;
         m_dynamicParameters.MaxShaderStorageBufferBindings = m_vulkanCaps.MaxShaderStorageBufferBindings;
         m_dynamicParameters.MaxTextureBufferSize = m_vulkanCaps.MaxTextureBufferSize;
+        m_dynamicParameters.TextureBufferOffsetAlignment = m_vulkanCaps.TextureBufferOffsetAlignment;
         m_dynamicParameters.MaxUniformBufferBindings = m_vulkanCaps.MaxUniformBufferBindings;
         m_dynamicParameters.MaxUniformBlockSize = m_vulkanCaps.MaxUniformBlockSize;
-        m_dynamicParameters.MaxImageUnits = std::min(m_vulkanCaps.MaxImageUnits, maxSupportedTextureUnits);
-        m_dynamicParameters.MaxCombinedImageUniforms = m_vulkanCaps.MaxCombinedImageUniforms;
-        m_dynamicParameters.MaxComputeImageUniforms = m_vulkanCaps.MaxComputeImageUniforms;
-        const Int maxSupportedDrawBuffers =
-            static_cast<Int>(MG_State::GLState::FramebufferObject::MAX_DRAW_BUFFERS);
+        m_dynamicParameters.MaxImageUnits = std::max(std::min(m_vulkanCaps.MaxImageUnits, maxSupportedTextureUnits), 0);
+        m_dynamicParameters.MaxCombinedImageUniforms = std::max(m_vulkanCaps.MaxCombinedImageUniforms, 0);
+        const Int maxPerStageImageUniforms =
+            std::min(m_dynamicParameters.MaxImageUnits, m_dynamicParameters.MaxCombinedImageUniforms);
+        // Vulkan uses one descriptor limit for every stage, but non-compute stores/atomics are
+        // optional device features. VulkanRenderer enables each feature whenever the physical
+        // device reports it, so these are the exact limits the logical device can compile and run.
+        m_dynamicParameters.MaxVertexImageUniforms =
+            m_vulkanCaps.SupportsVertexPipelineStoresAndAtomics ? maxPerStageImageUniforms : 0;
+        m_dynamicParameters.MaxGeometryImageUniforms =
+            m_vulkanCaps.SupportsVertexPipelineStoresAndAtomics && m_vulkanCaps.SupportsGeometryShader
+                ? maxPerStageImageUniforms
+                : 0;
+        m_dynamicParameters.MaxFragmentImageUniforms =
+            m_vulkanCaps.SupportsFragmentStoresAndAtomics ? maxPerStageImageUniforms : 0;
+        m_dynamicParameters.MaxComputeImageUniforms =
+            std::min(std::max(m_vulkanCaps.MaxComputeImageUniforms, 0), maxPerStageImageUniforms);
+        const Int maxSupportedDrawBuffers = static_cast<Int>(MG_State::GLState::FramebufferObject::MAX_DRAW_BUFFERS);
         m_dynamicParameters.MaxDrawBuffers = std::min(m_vulkanCaps.MaxDrawBuffers, maxSupportedDrawBuffers);
         m_dynamicParameters.MaxColorAttachments = std::min(m_vulkanCaps.MaxColorAttachments, maxSupportedDrawBuffers);
         m_dynamicParameters.MaxClipDistances = m_vulkanCaps.MaxClipDistances;
@@ -746,13 +804,53 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         m_dynamicParameters.ViewportBoundsRangeMin = m_vulkanCaps.ViewportBoundsRangeMin;
         m_dynamicParameters.ViewportBoundsRangeMax = m_vulkanCaps.ViewportBoundsRangeMax;
         m_dynamicParameters.ViewportSubpixelBits = m_vulkanCaps.ViewportSubpixelBits;
+        m_dynamicParameters.MinFragmentInterpolationOffset =
+            std::isfinite(m_vulkanCaps.MinFragmentInterpolationOffset) &&
+                    m_vulkanCaps.MinFragmentInterpolationOffset <= -0.5f
+                ? m_vulkanCaps.MinFragmentInterpolationOffset
+                : -0.5f;
+        m_dynamicParameters.MaxFragmentInterpolationOffset = 0.4375f;
+        m_dynamicParameters.FragmentInterpolationOffsetBits = 4;
+        if (m_vulkanCaps.FragmentInterpolationOffsetBits >= 4 &&
+            std::isfinite(m_vulkanCaps.MaxFragmentInterpolationOffset)) {
+            const Float requiredMaxOffset = 0.5f - std::ldexp(1.0f, -m_vulkanCaps.FragmentInterpolationOffsetBits);
+            if (m_vulkanCaps.MaxFragmentInterpolationOffset >= requiredMaxOffset) {
+                m_dynamicParameters.MaxFragmentInterpolationOffset = m_vulkanCaps.MaxFragmentInterpolationOffset;
+                m_dynamicParameters.FragmentInterpolationOffsetBits = m_vulkanCaps.FragmentInterpolationOffsetBits;
+            }
+        }
         m_dynamicParameters.SupportsWideLines = m_vulkanCaps.SupportsWideLines;
+        // A 2D or 2D multisample array texture is a VK_IMAGE_TYPE_2D image whose GL depth IS its
+        // arrayLayers, so a GL layer is a Vulkan array layer with nothing to translate.
+        // ResolveAttachmentBaseArrayLayer already passes the attachment's layer through. The other
+        // layered targets are declared separately as their own machinery lands.
+        {
+            using DynParams = MG_Backend::DynamicBackendParameters;
+            m_dynamicParameters.PerLayerFramebufferAttachmentTargets |=
+                DynParams::PerLayerFramebufferAttachmentBit(TextureTarget::Texture2DArray) |
+                DynParams::PerLayerFramebufferAttachmentBit(TextureTarget::Texture2DMultisampleArray);
+            // A cube map array is one 2D image with arrayLayers = 6 * cubeCount, so a GL layer is a
+            // Vulkan array layer here too - but the image cannot be created without imageCubeArray.
+            // A 3D texture's GL layer is a z slice, which only a 2D view over a 2D-array-compatible
+            // image can name. Optimistic: a format that refuses the flag is caught at image creation
+            // and declines the slice view there, which the clear path handles as a soft miss.
+            if (m_vulkanCaps.Supports2DArrayCompatible3DImages) {
+                m_dynamicParameters.PerLayerFramebufferAttachmentTargets |=
+                    DynParams::PerLayerFramebufferAttachmentBit(TextureTarget::Texture3D);
+            }
+            if (m_vulkanCaps.SupportsImageCubeArray) {
+                m_dynamicParameters.PerLayerFramebufferAttachmentTargets |=
+                    DynParams::PerLayerFramebufferAttachmentBit(TextureTarget::TextureCubeMapArray);
+            }
+        }
+        m_dynamicParameters.SupportsFloat64VertexAttributes = m_vulkanCaps.SupportsShaderFloat64;
         m_dynamicParameters.MaxShaderStorageBlockSize =
             std::min(m_vulkanCaps.MaxShaderStorageBlockSize, kMaxAdvertisedShaderStorageBlockSize);
         if (m_vulkanCaps.SupportsShaderSubgroup) {
             m_dynamicParameters.SubgroupSize = m_vulkanCaps.SubgroupSize;
             m_dynamicParameters.SubgroupSupportedStages = mapShaderStages(m_vulkanCaps.SubgroupSupportedStages);
-            m_dynamicParameters.SubgroupSupportedFeatures = mapSubgroupFeatures(m_vulkanCaps.SubgroupSupportedOperations);
+            m_dynamicParameters.SubgroupSupportedFeatures =
+                mapSubgroupFeatures(m_vulkanCaps.SubgroupSupportedOperations);
             m_dynamicParameters.SubgroupQuadOperationsInAllStages = m_vulkanCaps.SubgroupQuadOperationsInAllStages;
         } else {
             m_dynamicParameters.SubgroupSize = 0;
@@ -762,8 +860,34 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         }
         if (m_dynamicParameters.MaxShaderStorageBlockSize != m_vulkanCaps.MaxShaderStorageBlockSize) {
             MGLOG_I("DirectVulkan: clamped GL_MAX_SHADER_STORAGE_BLOCK_SIZE from %zu to %zu",
-                    m_vulkanCaps.MaxShaderStorageBlockSize,
-                    m_dynamicParameters.MaxShaderStorageBlockSize);
+                    m_vulkanCaps.MaxShaderStorageBlockSize, m_dynamicParameters.MaxShaderStorageBlockSize);
+        }
+        switch (m_vulkanCaps.VendorId) {
+        case 0x5143u: // VK_VENDOR_ID: Qualcomm
+            m_dynamicParameters.GpuVendor = GpuVendorKind::Qualcomm;
+            break;
+        case 0x13B5u: // ARM
+            m_dynamicParameters.GpuVendor = GpuVendorKind::Arm;
+            break;
+        case 0x10DEu: // NVIDIA
+            m_dynamicParameters.GpuVendor = GpuVendorKind::Nvidia;
+            break;
+        case 0x1002u: // AMD
+            m_dynamicParameters.GpuVendor = GpuVendorKind::Amd;
+            break;
+        case 0x8086u: // Intel
+            m_dynamicParameters.GpuVendor = GpuVendorKind::Intel;
+            break;
+        case 0x1010u: // Imagination
+            m_dynamicParameters.GpuVendor = GpuVendorKind::ImgTec;
+            break;
+        case 0x10005u: // Mesa software (lavapipe)
+        case 0x1AE0u:  // Google (SwiftShader)
+            m_dynamicParameters.GpuVendor = GpuVendorKind::Software;
+            break;
+        default:
+            m_dynamicParameters.GpuVendor = GpuVendorKind::Unknown;
+            break;
         }
     }
 } // namespace MobileGL::MG_Backend::DirectVulkan

MobileGL/MG_Backend/DirectVulkan/BackendObject_DirectVulkan.h

@@ -73,7 +73,8 @@ namespace MobileGL::MG_Backend::DirectVulkan {
     // a device with the given raw capabilities. The MOBILEGL_DISABLE_SUBGROUP and
     // MOBILEGL_DISABLE_TIMERQUERY escape hatches are applied inside, so callers pass
     // the detected device support (passing an already-gated value is harmless).
-    Vector<GLExtension> BuildAdvertisedExtensions(Bool shaderSubgroupSupported, Bool timerQueriesSupported);
+    Vector<GLExtension> BuildAdvertisedExtensions(Bool shaderSubgroupSupported, Bool timerQueriesSupported,
+                                                  Bool anisotropicFilteringSupported);
 
     // Format: <GPU Name>, Vulkan <Vulkan Version>, Driver <Driver Version> — the exact
     // string an initialized backend returns from GetBackendAPIVersionString (and that

MobileGL/MG_Backend/DirectVulkan/DirectVulkan.cpp

@@ -16,11 +16,13 @@
 #include "MG_Util/Metrics/TextureMetrics.h"
 #include "MG_Util/Miscellany/IndexGenerator.h"
 #include <atomic>
+#include <bit>
 #include <cstring>
 #include <spirv_reflect.h>
 
 namespace MobileGL::MG_Backend::DirectVulkan {
-    UniquePtr<VulkanRenderer> pVulkanRenderer = nullptr;
+    // Leak-at-exit storage; see GlobalObjects.cpp.
+    UniquePtr<VulkanRenderer>& pVulkanRenderer = *new UniquePtr<VulkanRenderer>();
 
     namespace {
         // Generation of the live VulkanRenderer instance, mirroring
@@ -60,6 +62,12 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         };
 
         struct ProgramResourceCache {
+            // Lifetime id of the program the cached reflection belongs to. GL names are
+            // recycled (IndexGenerator hands freed indices straight back), and a
+            // recreated program's backendStateVersion restarts at the same small values,
+            // so the version alone can collide; the never-reused lifetime id makes the
+            // slot's ownership unambiguous.
+            Uint64 programLifetimeId = 0;
             Uint32 backendStateVersion = 0;
             Vector<StorageBlockResource> storageBlocks;
             Vector<BufferVariableResource> bufferVariables;
@@ -81,6 +89,11 @@ namespace MobileGL::MG_Backend::DirectVulkan {
             Uint32 baseInstance = 0;
         };
 
+        // Keyed by GL program name so the freed-name reuse in IndexGenerator bounds the
+        // map at the peak-simultaneous-program high-water mark; each slot's ownership is
+        // checked against the program's lifetime id before it is served (see
+        // GetProgramResourceCache). Cleared wholesale at EGL teardown via
+        // ClearProgramResourceCaches.
         UnorderedMap<GLuint, ProgramResourceCache> g_programResourceCaches;
 
         void ClearReadPixelsOutput(GLsizei width, GLsizei height, GLenum format, GLenum type, void* pixels) {
@@ -141,13 +154,19 @@ namespace MobileGL::MG_Backend::DirectVulkan {
 
         ProgramResourceCache& GetProgramResourceCache(const MG_State::GLState::ProgramObject& program) {
             auto& cache = g_programResourceCaches[program.GetExternalIndex()];
+            const Uint64 programLifetimeId = program.GetLifetimeId();
             const Uint32 backendStateVersion = program.GetBackendStateVersion();
-            if (cache.backendStateVersion == backendStateVersion &&
+            // The lifetime id must match too: a new program that reuses a deleted
+            // program's name and happens to land on the same backendStateVersion (both
+            // count from zero) would otherwise be served the dead program's reflection.
+            if (cache.programLifetimeId == programLifetimeId &&
+                cache.backendStateVersion == backendStateVersion &&
                 (!cache.storageBlocks.empty() || !cache.bufferVariables.empty())) {
                 return cache;
             }
 
             cache = {};
+            cache.programLifetimeId = programLifetimeId;
             cache.backendStateVersion = backendStateVersion;
 
             Vector<SpvReflectShaderModule> modules;
@@ -213,6 +232,13 @@ namespace MobileGL::MG_Backend::DirectVulkan {
                     StorageBlockResource block{};
                     block.name = blockName;
                     block.binding = binding->binding;
+                    // glShaderStorageBlockBinding survives every rebuild of this cache: the
+                    // authoritative record of a rebound block lives on the program (it is what
+                    // GL_BUFFER_BINDING reports), and only the shader's declared binding is
+                    // recoverable from the SPIR-V. Without this, any unrelated state-version
+                    // bump would silently revert the block to its declared binding.
+                    const Int rebound = program.GetShaderStorageBlockBindingOverride(blockName);
+                    if (rebound >= 0) block.binding = static_cast<Uint32>(rebound);
                     block.dataSize = static_cast<GLint>(binding->block.size);
                     const GLuint blockIndex = static_cast<GLuint>(cache.storageBlocks.size());
                     AddBufferVariablesRecursive(binding->block, blockName, blockIndex, cache.bufferVariables,
@@ -237,18 +263,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
             return programObject.get();
         }
 
-        void CopyResourceName(const String& source, GLsizei bufSize, GLsizei* length, GLchar* name) {
-            const GLsizei writtenLength = static_cast<GLsizei>(source.size());
-            if (length) {
-                *length = writtenLength;
-            }
-            if (name && bufSize > 0) {
-                const GLsizei copyLength = std::min<GLsizei>(bufSize - 1, writtenLength);
-                std::memcpy(name, source.data(), static_cast<SizeT>(copyLength));
-                name[copyLength] = '\0';
-            }
-        }
-
         const Uint8* ResolveIndirectCommandBytes(const void* indirect, SizeT requiredBytes, const char* label) {
             auto drawBuffer = MG_State::pGLContext->GetBufferBindingSlot(BufferTarget::DrawIndirect).GetBoundObject();
             if (drawBuffer) {
@@ -269,109 +283,34 @@ namespace MobileGL::MG_Backend::DirectVulkan {
             return reinterpret_cast<const Uint8*>(indirect);
         }
 
-        Vector<GLuint> GetUniformBlockActiveVariables(const MG_State::GLState::ProgramObject& program,
-                                                      GLuint blockIndex) {
-            Vector<GLuint> activeVariables;
-            const Uint uniformCount = program.GetUniformCount();
-            activeVariables.reserve(uniformCount);
-            for (Uint uniformIndex = 0; uniformIndex < uniformCount; ++uniformIndex) {
-                if (program.GetActiveUniformBlockIndex(uniformIndex) == static_cast<Int>(blockIndex)) {
-                    activeVariables.push_back(uniformIndex);
-                }
-            }
-            return activeVariables;
-        }
-
-        GLuint FindProgramInputIndex(const MG_State::GLState::ProgramObject& program, const String& name) {
-            const Int activeCount = program.GetActiveAttributesCount();
-            for (Int index = 0; index < activeCount; ++index) {
-                if (program.GetActiveAttribName(index) == name) {
-                    return static_cast<GLuint>(index);
-                }
-            }
-            return GL_INVALID_INDEX;
-        }
-
-        GLuint FindProgramOutputIndex(const MG_State::GLState::ProgramObject& program, const String& name) {
-            const Int activeCount = program.GetActiveFragmentOutputCount();
-            for (Int index = 0; index < activeCount; ++index) {
-                if (program.GetActiveFragmentOutputName(index) == name) {
-                    return static_cast<GLuint>(index);
-                }
-            }
-            return GL_INVALID_INDEX;
-        }
-
-        GLint GetProgramOutputLocation(const MG_State::GLState::ProgramObject& program, const String& name) {
-            const Int activeCount = program.GetActiveFragmentOutputCount();
-            for (Int index = 0; index < activeCount; ++index) {
-                if (program.GetActiveFragmentOutputName(index) == name) {
-                    return program.GetFragmentOutputLocation(index);
-                }
-            }
-            return -1;
-        }
-
-        GLint GetProgramResourceActiveCount(const MG_State::GLState::ProgramObject& program, GLenum programInterface,
-                                            const ProgramResourceCache& cache) {
-            switch (programInterface) {
-            case GL_SHADER_STORAGE_BLOCK:
-                return static_cast<GLint>(cache.storageBlocks.size());
-            case GL_BUFFER_VARIABLE:
-                return static_cast<GLint>(cache.bufferVariables.size());
-            case GL_UNIFORM_BLOCK:
-                return program.GetActiveUniformBlocksCount();
-            case GL_UNIFORM:
-                return static_cast<GLint>(program.GetUniformCount());
-            case GL_PROGRAM_INPUT:
-                return program.GetActiveAttributesCount();
-            case GL_PROGRAM_OUTPUT:
-                return program.GetActiveFragmentOutputCount();
-            default:
-                return 0;
-            }
-        }
-
-        GLint GetProgramResourceMaxNameLength(const MG_State::GLState::ProgramObject& program, GLenum programInterface,
-                                              const ProgramResourceCache& cache) {
-            switch (programInterface) {
-            case GL_SHADER_STORAGE_BLOCK: {
-                SizeT maxLength = 0;
-                for (const auto& block : cache.storageBlocks) maxLength = std::max(maxLength, block.name.size() + 1);
-                return static_cast<GLint>(maxLength);
-            }
-            case GL_BUFFER_VARIABLE: {
-                SizeT maxLength = 0;
-                for (const auto& var : cache.bufferVariables) maxLength = std::max(maxLength, var.name.size() + 1);
-                return static_cast<GLint>(maxLength);
-            }
-            case GL_UNIFORM_BLOCK:
-                return program.GetActiveUniformBlocksMaxNameLength() + 1;
-            case GL_UNIFORM:
-                return program.GetUniformMaxLength() + 1;
-            case GL_PROGRAM_INPUT:
-                return program.GetActiveAttributesMaxLength() + 1;
-            case GL_PROGRAM_OUTPUT: {
-                SizeT maxLength = 0;
-                const Int activeCount = program.GetActiveFragmentOutputCount();
-                for (Int index = 0; index < activeCount; ++index) {
-                    maxLength = std::max(maxLength, program.GetActiveFragmentOutputName(index).size() + 1);
-                }
-                return static_cast<GLint>(maxLength);
-            }
-            default:
-                return 0;
-            }
-        }
     } // namespace
 
+    void ClearProgramResourceCaches() {
+        // Called from EGL teardown while the backend's m_eglStateMutex is held; GL
+        // calls are serialized in this codebase (contexts migrate threads but never
+        // run concurrently), so no other thread can be inside the unsynchronized map.
+        // Live programs in another context self-heal: their entry rebuilds from the
+        // retained generated SPIR-V on the next resource query.
+        g_programResourceCaches.clear();
+    }
+
     GLuint GetShaderStorageBlockIndex(const MG_State::GLState::ProgramObject& program, const String& name) {
         auto& cache = GetProgramResourceCache(program);
-        const auto it = std::find_if(cache.storageBlocks.begin(), cache.storageBlocks.end(),
-            [&](const StorageBlockResource& block) { return block.name == name; });
-        return it == cache.storageBlocks.end()
-            ? GL_INVALID_INDEX
-            : static_cast<GLuint>(std::distance(cache.storageBlocks.begin(), it));
+        auto find = [&cache](const String& key) {
+            return std::find_if(cache.storageBlocks.begin(), cache.storageBlocks.end(),
+                [&](const StorageBlockResource& block) { return block.name == key; });
+        };
+        auto it = find(name);
+        if (it == cache.storageBlocks.end()) {
+            // Cache names are normalized (NormalizeDescriptorName drops the array suffix), so
+            // an arrayed block that GL enumerates per element - "B[0]", "B[1]" - is one entry
+            // here, spelled "B". Retry against the bare name before giving up.
+            const auto bracket = name.rfind('[');
+            if (bracket == String::npos || name.empty() || name.back() != ']') return GL_INVALID_INDEX;
+            it = find(name.substr(0, bracket));
+            if (it == cache.storageBlocks.end()) return GL_INVALID_INDEX;
+        }
+        return static_cast<GLuint>(std::distance(cache.storageBlocks.begin(), it));
     }
 
     GLuint GetShaderStorageBlockBinding(const MG_State::GLState::ProgramObject& program, GLuint blockIndex) {
@@ -413,6 +352,20 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         pVulkanRenderer->ClearNamedFramebufferfv(framebuffer, buffer, drawbuffer, value);
     }
 
+    void ClearNamedFramebufferiv(const SharedPtr<MG_State::GLState::FramebufferObject>& framebuffer, GLenum buffer,
+                                 GLint drawbuffer, const GLint* value) {
+        MOBILEGL_ASSERT(pVulkanRenderer, "DirectVulkan::ClearNamedFramebufferiv called with null VulkanRenderer");
+        MOBILEGL_ASSERT(MG_State::pGLContext, "DirectVulkan::ClearNamedFramebufferiv called with null GL context");
+        pVulkanRenderer->ClearNamedFramebufferiv(framebuffer, buffer, drawbuffer, value);
+    }
+
+    void ClearNamedFramebufferuiv(const SharedPtr<MG_State::GLState::FramebufferObject>& framebuffer, GLenum buffer,
+                                  GLint drawbuffer, const GLuint* value) {
+        MOBILEGL_ASSERT(pVulkanRenderer, "DirectVulkan::ClearNamedFramebufferuiv called with null VulkanRenderer");
+        MOBILEGL_ASSERT(MG_State::pGLContext, "DirectVulkan::ClearNamedFramebufferuiv called with null GL context");
+        pVulkanRenderer->ClearNamedFramebufferuiv(framebuffer, buffer, drawbuffer, value);
+    }
+
     void ClearNamedFramebufferfi(const SharedPtr<MG_State::GLState::FramebufferObject>& framebuffer, GLenum buffer,
                                  GLint drawbuffer, GLfloat depth, GLint stencil) {
         MOBILEGL_ASSERT(pVulkanRenderer, "DirectVulkan::ClearNamedFramebufferfi called with null VulkanRenderer");
@@ -832,357 +785,9 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         }
     }
 
-    void GetProgramInterfaceiv(GLuint program, GLenum programInterface, GLenum pname, GLint* params) {
-        if (!params) return;
+    void ShaderStorageBlockBinding(GLuint program, const GLchar* storageBlockName, GLuint storageBlockBinding) {
         auto* programObject = TryGetDirectVulkanProgram(program);
-        if (!programObject) return;
-        auto& cache = GetProgramResourceCache(*programObject);
-        switch (pname) {
-        case GL_ACTIVE_RESOURCES:
-            *params = GetProgramResourceActiveCount(*programObject, programInterface, cache);
-            return;
-        case GL_MAX_NAME_LENGTH:
-            *params = GetProgramResourceMaxNameLength(*programObject, programInterface, cache);
-            return;
-        case GL_MAX_NUM_ACTIVE_VARIABLES:
-            if (programInterface == GL_SHADER_STORAGE_BLOCK) {
-                SizeT maxCount = 0;
-                for (const auto& block : cache.storageBlocks) {
-                    maxCount = std::max(maxCount, block.activeVariables.size());
-                }
-                *params = static_cast<GLint>(maxCount);
-            } else if (programInterface == GL_UNIFORM_BLOCK) {
-                GLint maxCount = 0;
-                const Int activeBlocks = programObject->GetActiveUniformBlocksCount();
-                for (Int index = 0; index < activeBlocks; ++index) {
-                    maxCount = std::max(maxCount, programObject->GetUniformBlockActiveUniformCount(index));
-                }
-                *params = maxCount;
-            } else {
-                *params = 0;
-            }
-            return;
-        default:
-            *params = 0;
-            return;
-        }
-    }
-
-    GLuint GetProgramResourceIndex(GLuint program, GLenum programInterface, const GLchar* name) {
-        if (!name) return GL_INVALID_INDEX;
-        auto* programObject = TryGetDirectVulkanProgram(program);
-        if (!programObject) return GL_INVALID_INDEX;
-        auto& cache = GetProgramResourceCache(*programObject);
-        const String resourceName = name;
-        if (programInterface == GL_SHADER_STORAGE_BLOCK) {
-            return GetShaderStorageBlockIndex(*programObject, name);
-        }
-        if (programInterface == GL_BUFFER_VARIABLE) {
-            const auto it = std::find_if(cache.bufferVariables.begin(), cache.bufferVariables.end(),
-                [&](const BufferVariableResource& var) { return var.name == resourceName; });
-            return it == cache.bufferVariables.end()
-                ? GL_INVALID_INDEX
-                : static_cast<GLuint>(std::distance(cache.bufferVariables.begin(), it));
-        }
-        if (programInterface == GL_UNIFORM_BLOCK) {
-            return programObject->GetUniformBlockIndex(name);
-        }
-        if (programInterface == GL_UNIFORM) {
-            const Int activeUniformIndex = programObject->GetActiveUniformIndex(resourceName);
-            return activeUniformIndex >= 0 ? static_cast<GLuint>(activeUniformIndex) : GL_INVALID_INDEX;
-        }
-        if (programInterface == GL_PROGRAM_INPUT) {
-            return FindProgramInputIndex(*programObject, resourceName);
-        }
-        if (programInterface == GL_PROGRAM_OUTPUT) {
-            return FindProgramOutputIndex(*programObject, resourceName);
-        }
-        return GL_INVALID_INDEX;
-    }
-
-    void GetProgramResourceName(GLuint program, GLenum programInterface, GLuint index, GLsizei bufSize,
-                                GLsizei* length, GLchar* name) {
-        auto* programObject = TryGetDirectVulkanProgram(program);
-        if (!programObject) return;
-        auto& cache = GetProgramResourceCache(*programObject);
-        if (programInterface == GL_SHADER_STORAGE_BLOCK && index < cache.storageBlocks.size()) {
-            CopyResourceName(cache.storageBlocks[index].name, bufSize, length, name);
-            return;
-        }
-        if (programInterface == GL_BUFFER_VARIABLE && index < cache.bufferVariables.size()) {
-            CopyResourceName(cache.bufferVariables[index].name, bufSize, length, name);
-            return;
-        }
-        if (programInterface == GL_UNIFORM_BLOCK && programObject->IsActiveUniformBlock(index)) {
-            CopyResourceName(programObject->GetUniformBlockName(index), bufSize, length, name);
-            return;
-        }
-        if (programInterface == GL_UNIFORM && index < programObject->GetUniformCount()) {
-            CopyResourceName(programObject->GetActiveUniformName(index), bufSize, length, name);
-            return;
-        }
-        if (programInterface == GL_PROGRAM_INPUT && index < static_cast<GLuint>(programObject->GetActiveAttributesCount())) {
-            CopyResourceName(programObject->GetActiveAttribName(index), bufSize, length, name);
-            return;
-        }
-        if (programInterface == GL_PROGRAM_OUTPUT &&
-            index < static_cast<GLuint>(programObject->GetActiveFragmentOutputCount())) {
-            CopyResourceName(programObject->GetActiveFragmentOutputName(index), bufSize, length, name);
-            return;
-        }
-        if (length) *length = 0;
-        if (name && bufSize > 0) name[0] = '\0';
-    }
-
-    void GetProgramResourceiv(GLuint program, GLenum programInterface, GLuint index, GLsizei propCount,
-                              const GLenum* props, GLsizei bufSize, GLsizei* length, GLint* params) {
-        auto* programObject = TryGetDirectVulkanProgram(program);
-        if (!programObject || !props || !params || bufSize <= 0) return;
-        auto& cache = GetProgramResourceCache(*programObject);
-        GLsizei written = 0;
-        auto writeValue = [&](GLint value) {
-            if (written < bufSize) {
-                params[written++] = value;
-            }
-        };
-
-        for (GLsizei propIndex = 0; propIndex < propCount; ++propIndex) {
-            const GLenum prop = props[propIndex];
-            if (programInterface == GL_SHADER_STORAGE_BLOCK && index < cache.storageBlocks.size()) {
-                const auto& block = cache.storageBlocks[index];
-                switch (prop) {
-                case GL_NAME_LENGTH:
-                    writeValue(static_cast<GLint>(block.name.size() + 1));
-                    break;
-                case GL_BUFFER_BINDING:
-                    writeValue(static_cast<GLint>(block.binding));
-                    break;
-                case GL_BUFFER_DATA_SIZE:
-                    writeValue(block.dataSize);
-                    break;
-                case GL_NUM_ACTIVE_VARIABLES:
-                    writeValue(static_cast<GLint>(block.activeVariables.size()));
-                    break;
-                case GL_ACTIVE_VARIABLES:
-                    for (const auto variable : block.activeVariables) writeValue(static_cast<GLint>(variable));
-                    break;
-                default:
-                    writeValue(0);
-                    break;
-                }
-            } else if (programInterface == GL_BUFFER_VARIABLE && index < cache.bufferVariables.size()) {
-                const auto& var = cache.bufferVariables[index];
-                switch (prop) {
-                case GL_NAME_LENGTH:
-                    writeValue(static_cast<GLint>(var.name.size() + 1));
-                    break;
-                case GL_TYPE:
-                    writeValue(GL_FLOAT);
-                    break;
-                case GL_ARRAY_SIZE:
-                    writeValue(1);
-                    break;
-                case GL_OFFSET:
-                    writeValue(var.offset);
-                    break;
-                case GL_BLOCK_INDEX:
-                    writeValue(static_cast<GLint>(var.blockIndex));
-                    break;
-                case GL_ARRAY_STRIDE:
-                case GL_MATRIX_STRIDE:
-                case GL_TOP_LEVEL_ARRAY_SIZE:
-                case GL_TOP_LEVEL_ARRAY_STRIDE:
-                case GL_IS_ROW_MAJOR:
-                    writeValue(0);
-                    break;
-                default:
-                    writeValue(0);
-                    break;
-                }
-            } else if (programInterface == GL_UNIFORM_BLOCK &&
-                       programObject->IsActiveUniformBlock(index)) {
-                const auto activeVariables = GetUniformBlockActiveVariables(*programObject, index);
-                switch (prop) {
-                case GL_NAME_LENGTH:
-                    writeValue(static_cast<GLint>(programObject->GetUniformBlockName(index).size() + 1));
-                    break;
-                case GL_BUFFER_BINDING:
-                    writeValue(static_cast<GLint>(programObject->GetUniformBlockBinding(index)));
-                    break;
-                case GL_BUFFER_DATA_SIZE:
-                    writeValue(static_cast<GLint>(programObject->GetUBOSizeAt(index)));
-                    break;
-                case GL_NUM_ACTIVE_VARIABLES:
-                    writeValue(static_cast<GLint>(activeVariables.size()));
-                    break;
-                case GL_ACTIVE_VARIABLES:
-                    for (const GLuint variableIndex : activeVariables) {
-                        writeValue(static_cast<GLint>(variableIndex));
-                    }
-                    break;
-                case GL_REFERENCED_BY_VERTEX_SHADER:
-                    writeValue(programObject->IsUniformBlockReferencedByStage(index, EShLangVertex) ? GL_TRUE
-                                                                                                     : GL_FALSE);
-                    break;
-                case GL_REFERENCED_BY_FRAGMENT_SHADER:
-                    writeValue(programObject->IsUniformBlockReferencedByStage(index, EShLangFragment) ? GL_TRUE
-                                                                                                       : GL_FALSE);
-                    break;
-                case GL_REFERENCED_BY_COMPUTE_SHADER:
-                    writeValue(programObject->IsUniformBlockReferencedByStage(index, EShLangCompute) ? GL_TRUE
-                                                                                                      : GL_FALSE);
-                    break;
-                case GL_REFERENCED_BY_GEOMETRY_SHADER:
-                case GL_REFERENCED_BY_TESS_CONTROL_SHADER:
-                case GL_REFERENCED_BY_TESS_EVALUATION_SHADER:
-                    writeValue(GL_FALSE);
-                    break;
-                default:
-                    writeValue(0);
-                    break;
-                }
-            } else if (programInterface == GL_UNIFORM && index < programObject->GetUniformCount()) {
-                const auto& uniformName = programObject->GetActiveUniformName(index);
-                const GLint location = programObject->GetUniformLocation(uniformName);
-                switch (prop) {
-                case GL_NAME_LENGTH:
-                    writeValue(static_cast<GLint>(uniformName.size() + 1));
-                    break;
-                case GL_TYPE:
-                    writeValue(static_cast<GLint>(programObject->GetActiveUniformType(index)));
-                    break;
-                case GL_ARRAY_SIZE:
-                    writeValue(programObject->GetActiveUniformArraySize(index));
-                    break;
-                case GL_BLOCK_INDEX:
-                    writeValue(programObject->GetActiveUniformBlockIndex(index));
-                    break;
-                case GL_LOCATION:
-                    writeValue(location);
-                    break;
-                case GL_OFFSET:
-                    writeValue(location >= 0 && programObject->IsValidUniformLocation(location)
-                                   ? static_cast<GLint>(programObject->GetUniformOffset(location))
-                                   : 0);
-                    break;
-                case GL_ARRAY_STRIDE:
-                case GL_MATRIX_STRIDE:
-                case GL_IS_ROW_MAJOR:
-                case GL_TOP_LEVEL_ARRAY_SIZE:
-                case GL_TOP_LEVEL_ARRAY_STRIDE:
-                case GL_REFERENCED_BY_VERTEX_SHADER:
-                case GL_REFERENCED_BY_FRAGMENT_SHADER:
-                case GL_REFERENCED_BY_COMPUTE_SHADER:
-                case GL_REFERENCED_BY_GEOMETRY_SHADER:
-                case GL_REFERENCED_BY_TESS_CONTROL_SHADER:
-                case GL_REFERENCED_BY_TESS_EVALUATION_SHADER:
-                    writeValue(0);
-                    break;
-                default:
-                    writeValue(0);
-                    break;
-                }
-            } else if (programInterface == GL_PROGRAM_INPUT &&
-                       index < static_cast<GLuint>(programObject->GetActiveAttributesCount())) {
-                const auto& resourceName = programObject->GetActiveAttribName(index);
-                switch (prop) {
-                case GL_NAME_LENGTH:
-                    writeValue(static_cast<GLint>(resourceName.size() + 1));
-                    break;
-                case GL_TYPE:
-                    writeValue(static_cast<GLint>(programObject->GetActiveAttribType(index)));
-                    break;
-                case GL_ARRAY_SIZE:
-                    writeValue(programObject->GetActiveAttribArraySize(index));
-                    break;
-                case GL_LOCATION:
-                    writeValue(programObject->GetAttributeLocation(resourceName));
-                    break;
-                case GL_REFERENCED_BY_VERTEX_SHADER:
-                    writeValue(GL_TRUE);
-                    break;
-                case GL_REFERENCED_BY_FRAGMENT_SHADER:
-                case GL_REFERENCED_BY_COMPUTE_SHADER:
-                case GL_REFERENCED_BY_GEOMETRY_SHADER:
-                case GL_REFERENCED_BY_TESS_CONTROL_SHADER:
-                case GL_REFERENCED_BY_TESS_EVALUATION_SHADER:
-                case GL_IS_PER_PATCH:
-                case GL_LOCATION_INDEX:
-                    writeValue(0);
-                    break;
-                default:
-                    writeValue(0);
-                    break;
-                }
-            } else if (programInterface == GL_PROGRAM_OUTPUT &&
-                       index < static_cast<GLuint>(programObject->GetActiveFragmentOutputCount())) {
-                const auto& resourceName = programObject->GetActiveFragmentOutputName(index);
-                switch (prop) {
-                case GL_NAME_LENGTH:
-                    writeValue(static_cast<GLint>(resourceName.size() + 1));
-                    break;
-                case GL_TYPE:
-                    writeValue(static_cast<GLint>(programObject->GetFragmentOutputType(index)));
-                    break;
-                case GL_ARRAY_SIZE:
-                    writeValue(programObject->GetActiveFragmentOutputArraySize(index));
-                    break;
-                case GL_LOCATION:
-                    writeValue(programObject->GetFragmentOutputLocation(index));
-                    break;
-                case GL_LOCATION_INDEX:
-                    writeValue(0);
-                    break;
-                case GL_REFERENCED_BY_FRAGMENT_SHADER:
-                    writeValue(GL_TRUE);
-                    break;
-                case GL_REFERENCED_BY_VERTEX_SHADER:
-                case GL_REFERENCED_BY_COMPUTE_SHADER:
-                case GL_REFERENCED_BY_GEOMETRY_SHADER:
-                case GL_REFERENCED_BY_TESS_CONTROL_SHADER:
-                case GL_REFERENCED_BY_TESS_EVALUATION_SHADER:
-                case GL_IS_PER_PATCH:
-                    writeValue(0);
-                    break;
-                default:
-                    writeValue(0);
-                    break;
-                }
-            } else {
-                writeValue(0);
-            }
-        }
-        if (length) *length = written;
-    }
-
-    GLint GetProgramResourceLocation(GLuint program, GLenum programInterface, const GLchar* name) {
-        auto* programObject = TryGetDirectVulkanProgram(program);
-        if (!programObject || !name) return -1;
-        if (programInterface == GL_UNIFORM) {
-            return programObject->GetUniformLocation(name);
-        }
-        if (programInterface == GL_PROGRAM_INPUT) {
-            return programObject->GetAttributeLocation(name);
-        }
-        if (programInterface == GL_PROGRAM_OUTPUT) {
-            return GetProgramOutputLocation(*programObject, name);
-        }
-        return -1;
-    }
-
-    GLint GetProgramResourceLocationIndex(GLuint program, GLenum programInterface, const GLchar* name) {
-        auto* programObject = TryGetDirectVulkanProgram(program);
-        if (!programObject || !name) return -1;
-        if (programInterface == GL_PROGRAM_OUTPUT) {
-            return GetProgramOutputLocation(*programObject, name) >= 0 ? 0 : -1;
-        }
-        return -1;
-    }
-
-    void ShaderStorageBlockBinding(GLuint program, GLuint storageBlockIndex, GLuint storageBlockBinding) {
-        auto* programObject = TryGetDirectVulkanProgram(program);
-        if (!programObject) return;
-        auto& cache = GetProgramResourceCache(*programObject);
+        if (!programObject || storageBlockName == nullptr) return;
         const Int maxBindings = pActiveBackendObject
             ? pActiveBackendObject->GetDynamicParameters().MaxShaderStorageBufferBindings
             : 0;
@@ -1192,13 +797,14 @@ namespace MobileGL::MG_Backend::DirectVulkan {
                 MakeUnique<GenericErrorInfo>("DirectVulkan", __func__, "Shader storage binding is out of range."));
             return;
         }
-        if (storageBlockIndex >= cache.storageBlocks.size()) {
-            MG_State::pGLContext->RecordError(
-                ErrorCode::InvalidValue,
-                MakeUnique<GenericErrorInfo>("DirectVulkan", __func__, "Shader storage block index is not active."));
-            return;
-        }
-        cache.storageBlocks[storageBlockIndex].binding = storageBlockBinding;
+        // The frontend already validated that the name denotes an active block, and has
+        // already recorded the new binding on the program - which is what reseeds this cache
+        // whenever it is rebuilt. Writing the entry here as well keeps an ALREADY-BUILT cache
+        // (the common case: the very next draw reads it) from having to be thrown away.
+        auto& cache = GetProgramResourceCache(*programObject);
+        const GLuint blockIndex = GetShaderStorageBlockIndex(*programObject, storageBlockName);
+        if (blockIndex == GL_INVALID_INDEX) return;
+        cache.storageBlocks[blockIndex].binding = storageBlockBinding;
     }
     void ReadPixels(GLint x, GLint y, GLsizei width, GLsizei height, GLenum format, GLenum type, void* pixels) {
         MOBILEGL_ASSERT(pVulkanRenderer, "DirectVulkan::ReadPixels called with null VulkanRenderer");
@@ -1223,10 +829,76 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         pVulkanRenderer->Clear(mask);
     }
 
+    // Vulkan has no LINE_LOOP topology; rewrite the draw as an indexed LINE_STRIP
+    // whose synthesized index list revisits the first vertex at the end.
+    static void DrawLineLoopAsIndexedStrip(const Vector<Uint32>& closedIndices, GLint basevertex) {
+        DrawIndexedCmd payload{};
+        payload.mode = GL_LINE_STRIP;
+        payload.indexBufferView.indexType = GL_UNSIGNED_INT;
+        payload.indexBufferView.indexByteOffset = reinterpret_cast<SizeT>(closedIndices.data());
+        payload.indexBufferView.indexByteSize = closedIndices.size() * sizeof(Uint32);
+        payload.indexBufferView.forceClientMemory = true;
+        payload.params.indexCount = static_cast<Uint32>(closedIndices.size());
+        payload.params.instanceCount = 1;
+        payload.params.vertexOffset = basevertex;
+        pVulkanRenderer->DrawElements(payload);
+    }
+
+    // Resolve a DrawElements index list (bound element-array buffer or client
+    // memory) into uint32 values with the loop-closing first index appended.
+    static Bool BuildClosedLineLoopIndices(GLsizei count, GLenum type, const void* indices,
+                                           Vector<Uint32>& outIndices) {
+        const SizeT indexSize = MG_Util::GetGLTypeSize(type);
+        if (indexSize == 0 || count < 2) {
+            return false;
+        }
+        const Uint8* indexBytes = nullptr;
+        const auto& vao = *MG_State::pGLContext->GetBoundVertexArray();
+        const auto& indexBufferShared = vao.GetIndexBufferBindingSlot().GetBoundObject();
+        if (indexBufferShared != nullptr) {
+            const SizeT offset = reinterpret_cast<SizeT>(indices);
+            const SizeT bufferSize = indexBufferShared->GetSize();
+            if (indexBufferShared->MappedData() == nullptr || offset > bufferSize ||
+                static_cast<SizeT>(count) * indexSize > bufferSize - offset) {
+                return false;
+            }
+            indexBufferShared->SyncPersistentMappedRange();
+            indexBytes = indexBufferShared->MappedData() + offset;
+        } else {
+            indexBytes = static_cast<const Uint8*>(indices);
+            if (indexBytes == nullptr) {
+                return false;
+            }
+        }
+        outIndices.resize(static_cast<SizeT>(count) + 1);
+        for (GLsizei i = 0; i < count; ++i) {
+            switch (indexSize) {
+            case 1: outIndices[i] = indexBytes[i]; break;
+            case 2: outIndices[i] = reinterpret_cast<const Uint16*>(indexBytes)[i]; break;
+            default: outIndices[i] = reinterpret_cast<const Uint32*>(indexBytes)[i]; break;
+            }
+        }
+        outIndices[count] = outIndices[0];
+        return true;
+    }
+
     void DrawArrays(GLenum mode, GLint first, GLsizei count) {
         MOBILEGL_ASSERT(pVulkanRenderer, "DirectVulkan::DrawArrays called with null VulkanRenderer");
         MOBILEGL_ASSERT(MG_State::pGLContext, "DirectVulkan::DrawArrays called with null GL context");
 
+        if (mode == GL_LINE_LOOP) {
+            if (count < 2) {
+                return;
+            }
+            Vector<Uint32> closedIndices(static_cast<SizeT>(count) + 1);
+            for (GLsizei i = 0; i < count; ++i) {
+                closedIndices[i] = static_cast<Uint32>(first + i);
+            }
+            closedIndices[count] = static_cast<Uint32>(first);
+            DrawLineLoopAsIndexedStrip(closedIndices, 0);
+            return;
+        }
+
         DrawCmd payload{};
         payload.mode = mode;
         payload.params.firstVertex = first;
@@ -1239,6 +911,14 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         MOBILEGL_ASSERT(pVulkanRenderer, "DirectVulkan::DrawElements called with null VulkanRenderer");
         MOBILEGL_ASSERT(MG_State::pGLContext, "DirectVulkan::DrawElements called with null GL context");
 
+        if (mode == GL_LINE_LOOP) {
+            Vector<Uint32> closedIndices;
+            if (BuildClosedLineLoopIndices(count, type, indices, closedIndices)) {
+                DrawLineLoopAsIndexedStrip(closedIndices, 0);
+            }
+            return;
+        }
+
         DrawIndexedCmd payload{};
         payload.mode = mode;
         payload.indexBufferView.indexType = type;
@@ -1277,57 +957,31 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         pVulkanRenderer->MultiDrawArrays(payload);
     }
 
-    void MultiDrawElements(GLenum mode, const GLsizei* count, GLenum type, const GLvoid* const* indices,
-                           GLsizei drawcount) {
-        MOBILEGL_ASSERT(pVulkanRenderer, "DirectVulkan::MultiDrawElements called with null VulkanRenderer");
-        MOBILEGL_ASSERT(MG_State::pGLContext, "DirectVulkan::MultiDrawElements called with null GL context");
-
-        // Vector<DrawElementCmd> cmds;
-        // cmds.reserve(static_cast<SizeT>(drawcount));
-        // for (GLsizei i = 0; i < drawcount; ++i) {
-        //     if (count[i] == 0) {
-        //         continue;
-        //     }
-        //
-        //     DrawElementCmd payload{};
-        //     payload.mode = mode;
-        //     payload.firstVertex = 0;
-        //     payload.indexCount = count[i];
-        //     payload.indexType = type;
-        //     payload.indexByteOffset = reinterpret_cast<SizeT>(indices[i]);
-        //     cmds.push_back(payload);
-        // }
-        //
-        // if (cmds.empty()) {
-        //     return;
-        // }
-        // pVulkanRenderer->MultiDrawElements(cmds);
-    }
-
-    void DrawElementsBaseVertex(GLenum mode, GLsizei count, GLenum type, const GLvoid* indices, GLint basevertex) {
-        MOBILEGL_ASSERT(pVulkanRenderer, "DirectVulkan::DrawElementsBaseVertex called with null VulkanRenderer");
-        MOBILEGL_ASSERT(MG_State::pGLContext, "DirectVulkan::DrawElementsBaseVertex called with null GL context");
-        DrawIndexedCmd payload{};
-        payload.mode = mode;
-        payload.indexBufferView.indexType = type;
-        payload.indexBufferView.indexByteOffset = reinterpret_cast<SizeT>(indices);
-        payload.indexBufferView.indexByteSize = count * MG_Util::GetGLTypeSize(type);
-        payload.params.indexCount = count;
-        payload.params.instanceCount = 1;
-        payload.params.firstIndex = 0;
-        payload.params.vertexOffset = basevertex;
-        payload.params.firstInstance = 0;
-        pVulkanRenderer->DrawElements(payload);
-    }
-
-    void MultiDrawElementsBaseVertex(GLenum mode, const GLsizei* count, GLenum type, const GLvoid* const* indices,
-                                     GLsizei drawcount, const GLint* basevertex) {
-        MOBILEGL_ASSERT(pVulkanRenderer, "DirectVulkan::MultiDrawElements called with null VulkanRenderer");
-        MOBILEGL_ASSERT(MG_State::pGLContext, "DirectVulkan::MultiDrawElements called with null GL context");
+    // Shared body of glMultiDrawElements (basevertex == nullptr) and
+    // glMultiDrawElementsBaseVertex: identical calls except for the per-draw
+    // vertex offset, which VkMultiDrawIndexedInfoEXT / VkDrawIndexedIndirectCommand /
+    // vkCmdDrawIndexed all carry natively.
+    static void MultiDrawElementsImpl(GLenum mode, const GLsizei* count, GLenum type, const GLvoid* const* indices,
+                                      GLsizei drawcount, const GLint* basevertex) {
+        if (drawcount <= 0) {
+            return;
+        }
         MultiDrawIndexedCmd payload{};
         payload.mode = mode;
         payload.indexBufferView.indexType = type;
 
+        // Loop-invariant: the index type is fixed for the whole multi-draw, so resolve
+        // its byte size once instead of twice per sub-draw (a cross-TU switch that
+        // showed up in per-frame profiles of sodium-style 132x32 multi-draws). Index
+        // sizes are 1/2/4, so the per-sub-draw offset division below reduces to a
+        // shift - the hardware divide was the hottest instruction of this loop.
+        const SizeT indexSize = MG_Util::GetGLTypeSize(type);
+        if (indexSize == 0) {
+            MGLOG_E("MultiDrawElements skipped: unsupported index type 0x%x", type);
+            return;
+        }
+        const Uint32 indexSizeShift = static_cast<Uint32>(std::countr_zero(indexSize));
+
         // TODO: allocate draw cmd buf elsewhere
         static Vector<DrawIndexedCmdParam> params;
         params.clear();
@@ -1342,15 +996,15 @@ namespace MobileGL::MG_Backend::DirectVulkan {
 
             payload.indexBufferView.indexByteOffset = 0;
             payload.indexBufferView.indexByteSize =
-                    std::max(reinterpret_cast<SizeT>(indices[i]) + count[i] * MG_Util::GetGLTypeSize(type),
+                    std::max(reinterpret_cast<SizeT>(indices[i]) + count[i] * indexSize,
                              payload.indexBufferView.indexByteSize);
 
             auto& param = params[i];
 
             param.indexCount = count[i];
             param.instanceCount = 1;
-            param.firstIndex = reinterpret_cast<SizeT>(indices[i]) / MG_Util::GetGLTypeSize(type);
-            param.vertexOffset = basevertex[i];
+            param.firstIndex = reinterpret_cast<SizeT>(indices[i]) >> indexSizeShift;
+            param.vertexOffset = basevertex != nullptr ? basevertex[i] : 0;
             param.firstInstance = 0;
         }
         payload.drawCount = drawcount;
@@ -1358,6 +1012,43 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         pVulkanRenderer->MultiDrawElements(payload);
     }
 
+    void MultiDrawElements(GLenum mode, const GLsizei* count, GLenum type, const GLvoid* const* indices,
+                           GLsizei drawcount) {
+        MOBILEGL_ASSERT(pVulkanRenderer, "DirectVulkan::MultiDrawElements called with null VulkanRenderer");
+        MOBILEGL_ASSERT(MG_State::pGLContext, "DirectVulkan::MultiDrawElements called with null GL context");
+        MultiDrawElementsImpl(mode, count, type, indices, drawcount, nullptr);
+    }
+
+    void DrawElementsBaseVertex(GLenum mode, GLsizei count, GLenum type, const GLvoid* indices, GLint basevertex) {
+        MOBILEGL_ASSERT(pVulkanRenderer, "DirectVulkan::DrawElementsBaseVertex called with null VulkanRenderer");
+        MOBILEGL_ASSERT(MG_State::pGLContext, "DirectVulkan::DrawElementsBaseVertex called with null GL context");
+        if (mode == GL_LINE_LOOP) {
+            Vector<Uint32> closedIndices;
+            if (BuildClosedLineLoopIndices(count, type, indices, closedIndices)) {
+                DrawLineLoopAsIndexedStrip(closedIndices, basevertex);
+            }
+            return;
+        }
+        DrawIndexedCmd payload{};
+        payload.mode = mode;
+        payload.indexBufferView.indexType = type;
+        payload.indexBufferView.indexByteOffset = reinterpret_cast<SizeT>(indices);
+        payload.indexBufferView.indexByteSize = count * MG_Util::GetGLTypeSize(type);
+        payload.params.indexCount = count;
+        payload.params.instanceCount = 1;
+        payload.params.firstIndex = 0;
+        payload.params.vertexOffset = basevertex;
+        payload.params.firstInstance = 0;
+        pVulkanRenderer->DrawElements(payload);
+    }
+
+    void MultiDrawElementsBaseVertex(GLenum mode, const GLsizei* count, GLenum type, const GLvoid* const* indices,
+                                     GLsizei drawcount, const GLint* basevertex) {
+        MOBILEGL_ASSERT(pVulkanRenderer, "DirectVulkan::MultiDrawElementsBaseVertex called with null VulkanRenderer");
+        MOBILEGL_ASSERT(MG_State::pGLContext, "DirectVulkan::MultiDrawElementsBaseVertex called with null GL context");
+        MultiDrawElementsImpl(mode, count, type, indices, drawcount, basevertex);
+    }
+
     void BlitFramebuffer(GLint srcX0, GLint srcY0, GLint srcX1, GLint srcY1, GLint dstX0, GLint dstY0, GLint dstX1,
                          GLint dstY1, GLbitfield mask, GLenum filter) {
         MOBILEGL_ASSERT(pVulkanRenderer, "DirectVulkan::BlitFramebuffer called with null VulkanRenderer");
@@ -1456,8 +1147,12 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         // records are shared (SharedPtr) with the owning pool's pending list,
         // so deleting the query while results are still in flight is safe.
         struct VulkanTimerQuery {
+            enum class Kind : Uint8 { Timer, Occlusion, XfbWritten, XfbGenerated };
+            Kind kind = Kind::Timer;
             SharedPtr<VkTimerQueryManager::TimestampRecord> begin;
             SharedPtr<VkTimerQueryManager::TimestampRecord> end;
+            // Kind::Occlusion - pool slots recorded between Begin/End; summed at result time.
+            Vector<Uint32> occlusionSlots;
             // Renderer generation the records were written under (see
             // g_rendererGeneration). A stale generation resolves as available
             // with a final zero result: the records' pool indices and frame
@@ -1466,6 +1161,12 @@ namespace MobileGL::MG_Backend::DirectVulkan {
             // (and, via the SharedPtrs, the records), never pool slots, so
             // stale queries are always safe to delete.
             Uint64 rendererGeneration = 0;
+            // Kind::XfbGenerated - the frontend's paused-draw primitive counter when the
+            // query began. VK_QUERY_TYPE_TRANSFORM_FEEDBACK_STREAM_EXT counts only what the
+            // capture saw, so a draw made while the span was paused is invisible to it -
+            // but GL_PRIMITIVES_GENERATED counts what the last vertex processing stage
+            // emitted regardless. The delta closes that gap at result time.
+            Uint64 pausedPrimitiveSnapshot = 0;
         };
     } // namespace
 
@@ -1547,6 +1248,30 @@ namespace MobileGL::MG_Backend::DirectVulkan {
             // ever be produced, so resolve with a final 0.
             return true;
         }
+        if (query->kind == VulkanTimerQuery::Kind::Occlusion) {
+            Uint64 samples = 0;
+            if (!pVulkanRenderer->ResolveOcclusionQueryResult(query->occlusionSlots, samples)) {
+                return false;
+            }
+            query->occlusionSlots.clear(); // slots are recycled by the resolve
+            *outNanoseconds = samples;
+            return true;
+        }
+        if (query->kind == VulkanTimerQuery::Kind::XfbWritten ||
+            query->kind == VulkanTimerQuery::Kind::XfbGenerated) {
+            Uint64 primitives = 0;
+            if (!pVulkanRenderer->ResolveXfbQueryResult(query->occlusionSlots,
+                                                        query->kind == VulkanTimerQuery::Kind::XfbGenerated,
+                                                        primitives)) {
+                return false;
+            }
+            if (query->kind == VulkanTimerQuery::Kind::XfbGenerated && MG_State::pGLContext != nullptr) {
+                primitives += MG_State::pGLContext->GetTransformFeedbackPausedPrimitiveCounter() -
+                              query->pausedPrimitiveSnapshot;
+            }
+            *outNanoseconds = primitives;
+            return true;
+        }
         // With wait, mirrors ClientWaitSync: a query ended this frame cannot
         // complete until Present submits the commands, so the wait refuses to
         // block on the current unsubmitted serial. Returning false keeps the
@@ -1579,6 +1304,49 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         delete static_cast<VulkanTimerQuery*>(handle);
     }
 
+    BackendQueryHandle BeginXfbPrimitivesQuery(Bool generated) {
+        MOBILEGL_ASSERT(pVulkanRenderer, "DirectVulkan::BeginXfbPrimitivesQuery called with null VulkanRenderer");
+        if (!pVulkanRenderer->StartXfbQueryCapture(generated ? 1u : 0u)) {
+            return nullptr;
+        }
+        auto* query = new VulkanTimerQuery{};
+        query->kind = generated ? VulkanTimerQuery::Kind::XfbGenerated : VulkanTimerQuery::Kind::XfbWritten;
+        query->rendererGeneration = GetRendererGeneration();
+        query->pausedPrimitiveSnapshot =
+            MG_State::pGLContext ? MG_State::pGLContext->GetTransformFeedbackPausedPrimitiveCounter() : 0;
+        return query;
+    }
+
+    void EndXfbPrimitivesQuery(BackendQueryHandle handle) {
+        auto* query = static_cast<VulkanTimerQuery*>(handle);
+        MOBILEGL_ASSERT(pVulkanRenderer, "DirectVulkan::EndXfbPrimitivesQuery called with null VulkanRenderer");
+        if (query == nullptr || query->rendererGeneration != GetRendererGeneration()) {
+            return;
+        }
+        pVulkanRenderer->StopXfbQueryCapture(
+            query->kind == VulkanTimerQuery::Kind::XfbGenerated ? 1u : 0u, query->occlusionSlots);
+    }
+
+    BackendQueryHandle BeginOcclusionQuery() {
+        MOBILEGL_ASSERT(pVulkanRenderer, "DirectVulkan::BeginOcclusionQuery called with null VulkanRenderer");
+        if (!pVulkanRenderer->StartOcclusionQueryCapture()) {
+            return nullptr;
+        }
+        auto* query = new VulkanTimerQuery{};
+        query->kind = VulkanTimerQuery::Kind::Occlusion;
+        query->rendererGeneration = GetRendererGeneration();
+        return query;
+    }
+
+    void EndOcclusionQuery(BackendQueryHandle handle) {
+        auto* query = static_cast<VulkanTimerQuery*>(handle);
+        MOBILEGL_ASSERT(pVulkanRenderer, "DirectVulkan::EndOcclusionQuery called with null VulkanRenderer");
+        if (query == nullptr || query->rendererGeneration != GetRendererGeneration()) {
+            return;
+        }
+        pVulkanRenderer->StopOcclusionQueryCapture(query->occlusionSlots);
+    }
+
     Int64 GetGpuTimestampNs() {
         // Vulkan cannot synchronously sample the GPU clock: timestamps only
         // exist as vkCmdWriteTimestamp results read back later, and

MobileGL/MG_Backend/DirectVulkan/DirectVulkan.h

@@ -12,7 +12,7 @@
 #include "Renderer/VulkanRenderer.h"
 
 namespace MobileGL::MG_Backend::DirectVulkan {
-    extern UniquePtr<VulkanRenderer> pVulkanRenderer;
+    extern UniquePtr<VulkanRenderer>& pVulkanRenderer;
 
     // Generation of the live VulkanRenderer instance, mirroring DirectGLES's
     // g_syncContextGeneration. BackendObject_DirectVulkan bumps it wherever
@@ -23,12 +23,22 @@ namespace MobileGL::MG_Backend::DirectVulkan {
     Uint64 GetRendererGeneration();
     void BumpRendererGeneration();
 
+    // Drops every cached program-resource reflection entry (CPU-side strings/vectors
+    // only, no Vulkan handles). Called at EGL teardown next to the renderer reset;
+    // safe because GL calls are serialized in this codebase, and any still-live
+    // program rebuilds its entry from the retained generated SPIR-V on demand.
+    void ClearProgramResourceCaches();
+
     void ClearBufferfi(GLenum buffer, GLint drawbuffer, GLfloat depth, GLint stencil);
     void ClearBufferfv(GLenum buffer, GLint drawbuffer, const GLfloat* value);
     void ClearBufferuiv(GLenum buffer, GLint drawbuffer, const GLuint* value);
     void ClearBufferiv(GLenum buffer, GLint drawbuffer, const GLint* value);
     void ClearNamedFramebufferfv(const SharedPtr<MG_State::GLState::FramebufferObject>& framebuffer, GLenum buffer,
                                  GLint drawbuffer, const GLfloat* value);
+    void ClearNamedFramebufferiv(const SharedPtr<MG_State::GLState::FramebufferObject>& framebuffer, GLenum buffer,
+                                 GLint drawbuffer, const GLint* value);
+    void ClearNamedFramebufferuiv(const SharedPtr<MG_State::GLState::FramebufferObject>& framebuffer, GLenum buffer,
+                                  GLint drawbuffer, const GLuint* value);
     void ClearNamedFramebufferfi(const SharedPtr<MG_State::GLState::FramebufferObject>& framebuffer, GLenum buffer,
                                  GLint drawbuffer, GLfloat depth, GLint stencil);
     void Clear(GLbitfield mask);
@@ -87,15 +97,7 @@ namespace MobileGL::MG_Backend::DirectVulkan {
     void GetIntegeri_v(GLenum target, GLuint index, GLint* data);
     void GetInteger64i_v(GLenum target, GLuint index, GLint64* data);
     void GetProgramiv(GLuint program, GLenum pname, GLint* params);
-    void GetProgramInterfaceiv(GLuint program, GLenum programInterface, GLenum pname, GLint* params);
-    GLuint GetProgramResourceIndex(GLuint program, GLenum programInterface, const GLchar* name);
-    void GetProgramResourceName(GLuint program, GLenum programInterface, GLuint index, GLsizei bufSize,
-                                GLsizei* length, GLchar* name);
-    void GetProgramResourceiv(GLuint program, GLenum programInterface, GLuint index, GLsizei propCount,
-                              const GLenum* props, GLsizei bufSize, GLsizei* length, GLint* params);
-    GLint GetProgramResourceLocation(GLuint program, GLenum programInterface, const GLchar* name);
-    GLint GetProgramResourceLocationIndex(GLuint program, GLenum programInterface, const GLchar* name);
-    void ShaderStorageBlockBinding(GLuint program, GLuint storageBlockIndex, GLuint storageBlockBinding);
+    void ShaderStorageBlockBinding(GLuint program, const GLchar* storageBlockName, GLuint storageBlockBinding);
     void ReadPixels(GLint x, GLint y, GLsizei width, GLsizei height, GLenum format, GLenum type, void* pixels);
     void GetTexImage(GLenum target, GLint level, GLenum format, GLenum type, GLvoid* pixels);
     void GetTextureImage(const SharedPtr<MG_State::GLState::ITextureObject>& texture, TextureUploadTarget uploadTarget,
@@ -117,6 +119,10 @@ namespace MobileGL::MG_Backend::DirectVulkan {
     // only while a live renderer exists whose device can actually time.
     Bool IsTimerQuerySupported();
     BackendQueryHandle BeginTimeElapsedQuery();
+    BackendQueryHandle BeginXfbPrimitivesQuery(Bool generated);
+    void EndXfbPrimitivesQuery(BackendQueryHandle query);
+    BackendQueryHandle BeginOcclusionQuery();
+    void EndOcclusionQuery(BackendQueryHandle query);
     void EndTimeElapsedQuery(BackendQueryHandle query);
     BackendQueryHandle QueryCounterTimestamp();
     Bool IsQueryResultAvailable(BackendQueryHandle query);

MobileGL/MG_Backend/DirectVulkan/Renderer/FrameContext.cpp

@@ -16,18 +16,19 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         m_device = device;
         m_commandPool = commandPool;
 
-        Vector<VkCommandBuffer> commandBuffers(frameCount, VK_NULL_HANDLE);
+        Vector<VkCommandBuffer> commandBuffers(frameCount * 2, VK_NULL_HANDLE);
         VkCommandBufferAllocateInfo allocInfo{};
         allocInfo.sType = VK_STRUCTURE_TYPE_COMMAND_BUFFER_ALLOCATE_INFO;
         allocInfo.commandPool = commandPool;
         allocInfo.level = VK_COMMAND_BUFFER_LEVEL_PRIMARY;
-        allocInfo.commandBufferCount = frameCount;
+        allocInfo.commandBufferCount = frameCount * 2;
         VkResult result = vkAllocateCommandBuffers(device, &allocInfo, commandBuffers.data());
         if (result != VK_SUCCESS) {
             return result;
         }
         for (Uint32 i = 0; i < frameCount; ++i) {
             m_frames[i].commandBuffer = commandBuffers[i];
+            m_frames[i].preCommandBuffer = commandBuffers[frameCount + i];
         }
 
         VkSemaphoreCreateInfo semaphoreInfo{VK_STRUCTURE_TYPE_SEMAPHORE_CREATE_INFO};
@@ -47,9 +48,10 @@ namespace MobileGL::MG_Backend::DirectVulkan {
 
     void FrameContext::Destroy(VkDevice device, VkCommandPool commandPool) {
         const Uint32 frameCount = static_cast<Uint32>(m_frames.size());
-        Vector<VkCommandBuffer> commandBuffers(frameCount, VK_NULL_HANDLE);
+        Vector<VkCommandBuffer> commandBuffers(frameCount * 2, VK_NULL_HANDLE);
         for (Uint32 i = 0; i < frameCount; ++i) {
             commandBuffers[i] = m_frames[i].commandBuffer;
+            commandBuffers[frameCount + i] = m_frames[i].preCommandBuffer;
         }
 
         for (Uint32 i = 0; i < frameCount; ++i) {
@@ -60,7 +62,7 @@ namespace MobileGL::MG_Backend::DirectVulkan {
             for (auto& frame : m_frames) {
                 FreeRetiredCommandBuffers(frame);
             }
-            vkFreeCommandBuffers(device, commandPool, frameCount, commandBuffers.data());
+            vkFreeCommandBuffers(device, commandPool, frameCount * 2, commandBuffers.data());
         }
         m_frames.clear();
         currentFrameIndex = 0;
@@ -87,6 +89,8 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         currentFrameIndex = (currentFrameIndex + 1) % static_cast<Uint32>(m_frames.size());
         GetCurrent().isCommandRecording = false;
         GetCurrent().hasCommandBufferRecorded = false;
+        GetCurrent().isPreCommandRecording = false;
+        GetCurrent().hasPreCommandBufferRecorded = false;
     }
 
     VkCommandBuffer& FrameContext::BeginCommandRecording(VkCommandBufferUsageFlags flags,
@@ -118,6 +122,41 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         frame.hasCommandBufferRecorded = true;
     }
 
+    VkCommandBuffer FrameContext::BeginPreCommandRecording() {
+        auto& frame = GetCurrent();
+        if (frame.isPreCommandRecording) {
+            return frame.preCommandBuffer;
+        }
+        MOBILEGL_ASSERT(!frame.hasPreCommandBufferRecorded,
+                        "BeginPreCommandRecording: a recorded pre stream is still awaiting submission");
+        VK_VERIFY(vkResetCommandBuffer(frame.preCommandBuffer, 0), "BeginPreCommandRecording, vkResetCommandBuffer");
+        VkCommandBufferBeginInfo beginInfo{};
+        beginInfo.sType = VK_STRUCTURE_TYPE_COMMAND_BUFFER_BEGIN_INFO;
+        VK_VERIFY(vkBeginCommandBuffer(frame.preCommandBuffer, &beginInfo),
+                  "BeginPreCommandRecording, vkBeginCommandBuffer");
+        frame.isPreCommandRecording = true;
+        return frame.preCommandBuffer;
+    }
+
+    void FrameContext::EndPreCommandRecordingIfOpen() {
+        auto& frame = GetCurrent();
+        if (!frame.isPreCommandRecording) {
+            return;
+        }
+        VK_VERIFY(vkEndCommandBuffer(frame.preCommandBuffer), "EndPreCommandRecordingIfOpen, vkEndCommandBuffer");
+        frame.isPreCommandRecording = false;
+        frame.hasPreCommandBufferRecorded = true;
+    }
+
+    void FrameContext::AbandonPreCommandRecording() {
+        auto& frame = GetCurrent();
+        if (frame.isPreCommandRecording) {
+            VK_VERIFY(vkEndCommandBuffer(frame.preCommandBuffer), "AbandonPreCommandRecording, vkEndCommandBuffer");
+        }
+        frame.isPreCommandRecording = false;
+        frame.hasPreCommandBufferRecorded = false;
+    }
+
     VkResult FrameContext::InitializeSwapchainSemaphores(VkDevice device, Uint32 swapchainImageCount) {
         DestroySwapchainSemaphores(device);
         if (swapchainImageCount == 0) {
@@ -150,12 +189,30 @@ namespace MobileGL::MG_Backend::DirectVulkan {
 
     Bool FrameContext::TransitionToPresent(VkImage image, VkImageLayout oldLayout, VkImageLayout presentLayout) {
         auto& frame = GetCurrent();
-        if (frame.hasCommandBufferRecorded || frame.isCommandRecording || oldLayout == presentLayout ||
-            oldLayout == VK_IMAGE_LAYOUT_SHARED_PRESENT_KHR) {
+        if (oldLayout == presentLayout || oldLayout == VK_IMAGE_LAYOUT_SHARED_PRESENT_KHR) {
             return false;
         }
 
-        auto& commandBuffer = BeginCommandRecording();
+        // The barrier belongs in the frame's own recording. Bailing out because
+        // something was already recorded (the previous behaviour) dropped the
+        // transition entirely for every frame that never ran a default-framebuffer
+        // render pass - the only other thing that carries the image to
+        // PRESENT_SRC_KHR, via that pass's finalLayout - so the swapchain image was
+        // handed to the WSI still in the layout it was acquired in.
+        // A closed-but-unsubmitted buffer can only come from a submit that already
+        // failed (SubmitPendingCommandBuffer leaves the flag set on error), and
+        // appending to it is illegal while reopening would reset the frame's own
+        // commands away. The device is gone on that path anyway - stay silent-safe
+        // rather than trade a lost device for a barrier into a closed buffer.
+        if (frame.hasCommandBufferRecorded) {
+            MGLOG_E("TransitionToPresent: command buffer already closed; skipping the present barrier");
+            return false;
+        }
+
+        // Reopening a recording here would vkResetCommandBuffer this frame's own
+        // commands away, so append to the open one and let the caller close it.
+        const Bool openedRecording = !frame.isCommandRecording;
+        VkCommandBuffer commandBuffer = openedRecording ? BeginCommandRecording() : frame.commandBuffer;
 
         VkImageMemoryBarrier presentBarrier{};
         presentBarrier.sType = VK_STRUCTURE_TYPE_IMAGE_MEMORY_BARRIER;
@@ -174,7 +231,9 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         vkCmdPipelineBarrier(commandBuffer, VK_PIPELINE_STAGE_TOP_OF_PIPE_BIT, VK_PIPELINE_STAGE_BOTTOM_OF_PIPE_BIT, 0, 0,
                              nullptr, 0, nullptr, 1, &presentBarrier);
 
-        EndCommandRecording();
+        if (openedRecording) {
+            EndCommandRecording();
+        }
         return true;
     }
 
@@ -182,17 +241,27 @@ namespace MobileGL::MG_Backend::DirectVulkan {
                                                                Uint32 swapchainImageIndex) const {
         const auto& frame = GetCurrent();
         MOBILEGL_ASSERT(!frame.isCommandRecording, "GetSubmitInfo called while command buffer recording is still active");
+        MOBILEGL_ASSERT(!frame.isPreCommandRecording,
+                        "GetSubmitInfo called while the pre-pass stream is still recording");
         AssertValidSwapchainImageIndex(swapchainImageIndex);
         SubmitInfoPacket packet{};
         packet.waitSemaphore = frame.imageAvailableSemaphore;
         packet.signalSemaphore = m_swapchainImageRenderFinishedSemaphores[swapchainImageIndex];
-        packet.commandBuffer = frame.commandBuffer;
+
+        Uint32 commandBufferCount = 0;
+        // The pre-pass stream executes strictly before the frame's commands.
+        if (frame.hasPreCommandBufferRecorded) {
+            packet.commandBuffers[commandBufferCount++] = frame.preCommandBuffer;
+        }
+        if (shouldSubmitCommandBuffer) {
+            packet.commandBuffers[commandBufferCount++] = frame.commandBuffer;
+        }
 
         packet.submitInfo.waitSemaphoreCount = frame.imageAvailableSemaphoreConsumed ? 0U : 1U;
         packet.submitInfo.pWaitSemaphores = frame.imageAvailableSemaphoreConsumed ? nullptr : &packet.waitSemaphore;
         packet.submitInfo.pWaitDstStageMask = frame.imageAvailableSemaphoreConsumed ? nullptr : &packet.waitDstStageMask;
-        packet.submitInfo.commandBufferCount = shouldSubmitCommandBuffer ? 1U : 0U;
-        packet.submitInfo.pCommandBuffers = shouldSubmitCommandBuffer ? &packet.commandBuffer : nullptr;
+        packet.submitInfo.commandBufferCount = commandBufferCount;
+        packet.submitInfo.pCommandBuffers = commandBufferCount > 0 ? packet.commandBuffers : nullptr;
         packet.submitInfo.signalSemaphoreCount = 1;
         packet.submitInfo.pSignalSemaphores = &packet.signalSemaphore;
         return packet;
@@ -227,12 +296,21 @@ namespace MobileGL::MG_Backend::DirectVulkan {
 
         result = vkAcquireNextImageKHR(device, swapchain, timeout, frame.imageAvailableSemaphore, acquireFence,
                                        &outImageIndex);
-        if (result != VK_SUCCESS) {
+        // VK_SUBOPTIMAL_KHR is a success code: an image *was* acquired and
+        // imageAvailableSemaphore *will* be signaled. Bailing out on it skipped both
+        // the consumed-flag reset (leaving a stale "already consumed", so the next
+        // submit never waited on the pending signal) and the fence reset (leaving
+        // the slot's fence signaled for the next submit to reuse). Only a genuine
+        // failure - VK_ERROR_OUT_OF_DATE_KHR and friends, where nothing is acquired
+        // and nothing is signaled - skips the bookkeeping.
+        if (result != VK_SUCCESS && result != VK_SUBOPTIMAL_KHR) {
             return result;
         }
 
         frame.imageAvailableSemaphoreConsumed = false;
-        return vkResetFences(device, 1, &frame.imageInFlightFence);
+        const VkResult resetResult = vkResetFences(device, 1, &frame.imageInFlightFence);
+        // Hand the acquire's own code back so the caller can schedule a rebuild.
+        return resetResult == VK_SUCCESS ? result : resetResult;
     }
 
     Uint32 FrameContext::GetCurrentFrameIndex() const {
@@ -247,12 +325,14 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         m_recordingObserver = observer;
     }
 
-    VkResult FrameContext::RetireCurrentCommandBuffer() {
+    VkResult FrameContext::RetireCurrentCommandBuffer(Bool retirePreCommandBuffer) {
         MOBILEGL_ASSERT(m_device != VK_NULL_HANDLE && m_commandPool != VK_NULL_HANDLE,
                         "RetireCurrentCommandBuffer requires an initialized FrameContext");
         auto& frame = GetCurrent();
         MOBILEGL_ASSERT(!frame.isCommandRecording,
                         "RetireCurrentCommandBuffer called while the command buffer is still recording");
+        MOBILEGL_ASSERT(!frame.isPreCommandRecording,
+                        "RetireCurrentCommandBuffer called while the pre-pass stream is still recording");
 
         VkCommandBufferAllocateInfo allocInfo{};
         allocInfo.sType = VK_STRUCTURE_TYPE_COMMAND_BUFFER_ALLOCATE_INFO;
@@ -260,11 +340,23 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         allocInfo.level = VK_COMMAND_BUFFER_LEVEL_PRIMARY;
         allocInfo.commandBufferCount = 1;
         VkCommandBuffer replacement = VK_NULL_HANDLE;
-        const VkResult result = vkAllocateCommandBuffers(m_device, &allocInfo, &replacement);
+        VkResult result = vkAllocateCommandBuffers(m_device, &allocInfo, &replacement);
         if (result != VK_SUCCESS) {
             return result;
         }
-        frame.retiredCommandBuffers.push_back(frame.commandBuffer);
+        if (retirePreCommandBuffer) {
+            VkCommandBuffer preReplacement = VK_NULL_HANDLE;
+            result = vkAllocateCommandBuffers(m_device, &allocInfo, &preReplacement);
+            if (result != VK_SUCCESS) {
+                vkFreeCommandBuffers(m_device, m_commandPool, 1, &replacement);
+                return result;
+            }
+            frame.retiredCommandBuffers.push_back({frame.preCommandBuffer, frame.lastSubmitIndex});
+            frame.preCommandBuffer = preReplacement;
+        }
+        // lastSubmitIndex was just written by the renderer for the submission
+        // that carried this command buffer.
+        frame.retiredCommandBuffers.push_back({frame.commandBuffer, frame.lastSubmitIndex});
         frame.commandBuffer = replacement;
         return VK_SUCCESS;
     }
@@ -274,12 +366,40 @@ namespace MobileGL::MG_Backend::DirectVulkan {
             return;
         }
         if (m_device != VK_NULL_HANDLE && m_commandPool != VK_NULL_HANDLE) {
-            vkFreeCommandBuffers(m_device, m_commandPool, static_cast<Uint32>(frame.retiredCommandBuffers.size()),
-                                 frame.retiredCommandBuffers.data());
+            for (const auto& retired : frame.retiredCommandBuffers) {
+                vkFreeCommandBuffers(m_device, m_commandPool, 1, &retired.commandBuffer);
+            }
         }
         frame.retiredCommandBuffers.clear();
     }
 
+    void FrameContext::FreeRetiredCommandBuffersCompletedUpTo(Uint64 completedSubmitIndex) {
+        if (m_device == VK_NULL_HANDLE || m_commandPool == VK_NULL_HANDLE) {
+            return;
+        }
+        for (auto& frame : m_frames) {
+            // Retired buffers are appended in submit order, so the completed
+            // ones form a prefix.
+            SizeT completedCount = 0;
+            while (completedCount < frame.retiredCommandBuffers.size() &&
+                   frame.retiredCommandBuffers[completedCount].submitIndex <= completedSubmitIndex) {
+                vkFreeCommandBuffers(m_device, m_commandPool, 1,
+                                     &frame.retiredCommandBuffers[completedCount].commandBuffer);
+                ++completedCount;
+            }
+            if (completedCount > 0) {
+                frame.retiredCommandBuffers.erase(frame.retiredCommandBuffers.begin(),
+                                                  frame.retiredCommandBuffers.begin() + completedCount);
+            }
+        }
+    }
+
+    void FrameContext::FreeAllRetiredCommandBuffers() {
+        for (auto& frame : m_frames) {
+            FreeRetiredCommandBuffers(frame);
+        }
+    }
+
     void FrameContext::AssertValidFrameIndex(Uint32 frameIndex) const {
         MOBILEGL_ASSERT(frameIndex < m_frames.size(), "FrameContext index out of range");
     }

MobileGL/MG_Backend/DirectVulkan/Renderer/FrameContext.h

@@ -29,7 +29,9 @@ namespace MobileGL::MG_Backend::DirectVulkan {
             VkPipelineStageFlags waitDstStageMask = VK_PIPELINE_STAGE_TOP_OF_PIPE_BIT;
             VkSemaphore waitSemaphore = VK_NULL_HANDLE;
             VkSemaphore signalSemaphore = VK_NULL_HANDLE;
-            VkCommandBuffer commandBuffer = VK_NULL_HANDLE;
+            // [0] = pre-pass command buffer (when recorded), then the frame
+            // command buffer; submitInfo.pCommandBuffers points here.
+            VkCommandBuffer commandBuffers[2] = {VK_NULL_HANDLE, VK_NULL_HANDLE};
             VkSubmitInfo submitInfo{VK_STRUCTURE_TYPE_SUBMIT_INFO};
         };
 
@@ -40,17 +42,35 @@ namespace MobileGL::MG_Backend::DirectVulkan {
             VkPresentInfoKHR presentInfo{VK_STRUCTURE_TYPE_PRESENT_INFO_KHR};
         };
 
+        // A command buffer submitted mid-frame (FlushPendingCommands), tagged
+        // with the submit-tracker index it was submitted under so it can be
+        // freed as soon as that submission is observed complete - without
+        // waiting for the slot's fence to be waited again (present-less flush
+        // loops never wait it).
+        struct RetiredCommandBuffer {
+            VkCommandBuffer commandBuffer = VK_NULL_HANDLE;
+            Uint64 submitIndex = 0;
+        };
+
         struct FrameData {
             VkCommandBuffer commandBuffer = VK_NULL_HANDLE;
+            // Pre-pass work stream: out-of-pass commands (deferred clear
+            // materialization, sampled-layout transitions) for resources the
+            // frame's recording has not touched yet. Submitted immediately
+            // BEFORE commandBuffer in the same vkQueueSubmit, so recording
+            // into it never has to split the frame's active render pass.
+            VkCommandBuffer preCommandBuffer = VK_NULL_HANDLE;
             VkSemaphore imageAvailableSemaphore = VK_NULL_HANDLE;
             VkFence imageInFlightFence = VK_NULL_HANDLE;
             Bool isCommandRecording = false;
             Bool hasCommandBufferRecorded = false;
+            Bool isPreCommandRecording = false;
+            Bool hasPreCommandBufferRecorded = false;
             Bool imageAvailableSemaphoreConsumed = false;
-            // Command buffers submitted mid-frame (FlushPendingCommands) whose
-            // execution is only known complete once this slot's fence has been
-            // waited again; freed at that point.
-            Vector<VkCommandBuffer> retiredCommandBuffers;
+            // Command buffers submitted mid-frame (FlushPendingCommands),
+            // appended in submit order; freed once their submission is known
+            // complete (fence wait or completion poll).
+            Vector<RetiredCommandBuffer> retiredCommandBuffers;
             // Submit-tracker index of this slot's most recent queue submission
             // (written by the renderer at submit time).
             Uint64 lastSubmitIndex = 0;
@@ -67,6 +87,14 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         VkCommandBuffer& BeginCommandRecording(VkCommandBufferUsageFlags flags = 0,
                                                const VkCommandBufferInheritanceInfo* pInheritanceInfo = nullptr);
         void EndCommandRecording();
+        // Lazily opens the pre-pass work stream (see FrameData::preCommandBuffer).
+        VkCommandBuffer BeginPreCommandRecording();
+        // Closes the pre stream if open, marking it for submission ahead of the
+        // frame command buffer. Safe to call when it never opened.
+        void EndPreCommandRecordingIfOpen();
+        // Drops an in-progress or recorded-but-unsubmitted pre stream (dropped
+        // frame recordings, swapchain recreation).
+        void AbandonPreCommandRecording();
         VkResult InitializeSwapchainSemaphores(VkDevice device, Uint32 swapchainImageCount);
         void DestroySwapchainSemaphores(VkDevice device);
         Bool TransitionToPresent(VkImage image, VkImageLayout oldLayout,
@@ -79,8 +107,18 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         // Parks the current (already ended and submitted) command buffer on the
         // slot's retired list and installs a freshly allocated one, so recording
         // can restart while the submitted buffer is still executing. Retired
-        // buffers are freed after the slot's fence is next waited.
-        VkResult RetireCurrentCommandBuffer();
+        // buffers are freed after the slot's fence is next waited, or as soon
+        // as their submission is observed complete.
+        VkResult RetireCurrentCommandBuffer(Bool retirePreCommandBuffer = false);
+
+        // Frees every retired command buffer whose tagged submission index is
+        // known complete. Driven by the renderer's submit tracker on completion
+        // events (fence waits and non-blocking polls), so present-less flush
+        // loops reclaim their buffers without any extra wait.
+        void FreeRetiredCommandBuffersCompletedUpTo(Uint64 completedSubmitIndex);
+        // Frees every slot's retired command buffers. Only valid when the
+        // caller has proven every queue submission complete.
+        void FreeAllRetiredCommandBuffers();
 
         Uint32 GetCurrentFrameIndex() const;
         Uint32 GetFrameCount() const;

MobileGL/MG_Backend/DirectVulkan/Renderer/PipelineFactory.cpp

@@ -8,6 +8,8 @@
 
 #include "PipelineFactory.h"
 
+#include <algorithm>
+
 namespace MobileGL::MG_Backend::DirectVulkan {
     static const char* PrimitiveTopologyToString(VkPrimitiveTopology topology) {
         switch (topology) {
@@ -108,6 +110,81 @@ namespace MobileGL::MG_Backend::DirectVulkan {
                   "vkCreatePipelineCache");
     }
 
+    // Must be called once, before any pipeline is created: the flag is not part of the
+    // pipeline hash, so flipping it mid-life would serve cached pipelines built under the
+    // old value.
+    void PipelineFactory::SetSuppressBlendedDepthWrite(Bool enabled) {
+        s_suppressBlendedDepthWrite = enabled;
+    }
+
+    Bool PipelineFactory::ShouldSuppressBlendedDepthWriteForDevice(MG_Config::QuirkOverride quirkOverride,
+                                                                   Uint32 vendorId) {
+        static constexpr Uint32 kVendorIdQualcomm = 0x5143;
+        switch (quirkOverride) {
+        case MG_Config::QuirkOverride::ForceOn:
+            return true;
+        case MG_Config::QuirkOverride::ForceOff:
+            return false;
+        case MG_Config::QuirkOverride::Auto:
+        default:
+            return vendorId == kVendorIdQualcomm;
+        }
+    }
+
+    namespace {
+        // MIN/MAX extremum blending: the signature of a depth-bounds accumulation pass
+        // (MC 26.3 OIT writes vec4(-linD, linD, deviceZ, 0) under GL_MAX while writing
+        // depth for its equality chain). MIN/MAX ignore blend factors per the Vulkan spec.
+        //
+        // Deliberately the ONLY shape stripped. A quirk should touch as little unrelated
+        // content as possible, and a trace sweep of every fixture showed the wider
+        // alternatives all cost more than they fix:
+        //   - additive ONE+ONE with a depth write matched zero draws of the 26.3 chain
+        //     (its transmittance/accumulate passes disable depth writes themselves) - the
+        //     only real content it caught was harmless additive glow effects (Create);
+        //   - sorted-transparency "over" blends (SRC_ALPHA-style) are order-dependent,
+        //     drawn once per surface, and rely on their depth writes for occlusion;
+        //   - separate-alpha accumulation over an over-blending color channel has no
+        //     known pairing with a depth-equality chain (color channel only, see tests).
+        // If a future workload pairs another blend shape with an equality chain, widen
+        // this with that evidence in hand rather than pre-emptively.
+        Bool IsAccumulationBlend(const VkPipelineColorBlendAttachmentState& attachment) {
+            return attachment.colorBlendOp == VK_BLEND_OP_MIN ||
+                   attachment.colorBlendOp == VK_BLEND_OP_MAX;
+        }
+    } // namespace
+
+    Bool PipelineFactory::ShouldSuppressDepthWrite(const PipelineCreatePayload& payload) {
+        if (!payload.depthWriteEnable) {
+            return false;
+        }
+        // A shader that assigns gl_FragDepth supplies depth itself rather than taking the
+        // pipeline's interpolated Z, so a driver that varies the vertex position math
+        // between pipelines cannot desynchronize it. (A gl_FragDepth = gl_FragCoord.z
+        // passthrough is the exception that stays exposed; no known content pairs one with
+        // an equality chain, and 26.3's composite is a genuine computed-depth writer.)
+        if (payload.fragmentReplacesDepth) {
+            return false;
+        }
+        for (Uint32 i = 0; i < payload.colorAttachmentCount; ++i) {
+            const VkPipelineColorBlendAttachmentState& attachment = payload.colorBlendAttachments[i];
+            if (attachment.blendEnable != VK_TRUE) {
+                continue;
+            }
+            // All color writes masked: blending is moot (depth-prepass pattern that left
+            // GL_BLEND enabled); stripping the depth write would delete the whole prepass.
+            if (attachment.colorWriteMask == 0) {
+                continue;
+            }
+            // Any attachment qualifies, not just attachment 0: the 26.3 transmittance pass
+            // accumulates into a 2-target MRT and must stay stripped.
+            if (IsAccumulationBlend(attachment)) {
+                return true;
+            }
+        }
+        return false;
+    }
+
     PipelineFactory::~PipelineFactory() {
         DestroyAll();
         if (m_pipelineCache != VK_NULL_HANDLE) {
@@ -128,9 +205,12 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         XXHASH_VERIFY(XXH64_update(m_hashState, &payload.topology, sizeof(payload.topology)));
         XXHASH_VERIFY(
             XXH64_update(m_hashState, &payload.primitiveRestartEnable, sizeof(payload.primitiveRestartEnable)));
+        XXHASH_VERIFY(XXH64_update(m_hashState, &payload.patchControlPoints, sizeof(payload.patchControlPoints)));
         XXHASH_VERIFY(XXH64_update(m_hashState, &payload.polygonMode, sizeof(payload.polygonMode)));
         XXHASH_VERIFY(XXH64_update(m_hashState, &payload.cullMode, sizeof(payload.cullMode)));
         XXHASH_VERIFY(XXH64_update(m_hashState, &payload.frontFace, sizeof(payload.frontFace)));
+        XXHASH_VERIFY(
+            XXH64_update(m_hashState, &payload.provokingVertexMode, sizeof(payload.provokingVertexMode)));
         XXHASH_VERIFY(XXH64_update(m_hashState, &payload.depthTestEnable, sizeof(payload.depthTestEnable)));
         XXHASH_VERIFY(XXH64_update(m_hashState, &payload.depthWriteEnable, sizeof(payload.depthWriteEnable)));
         XXHASH_VERIFY(XXH64_update(m_hashState, &payload.depthBiasEnable, sizeof(payload.depthBiasEnable)));
@@ -152,6 +232,8 @@ namespace MobileGL::MG_Backend::DirectVulkan {
             XXH64_update(m_hashState, &payload.backStencilDepthFailOp, sizeof(payload.backStencilDepthFailOp)));
         XXHASH_VERIFY(
             XXH64_update(m_hashState, &payload.backStencilCompareOp, sizeof(payload.backStencilCompareOp)));
+        XXHASH_VERIFY(
+            XXH64_update(m_hashState, &payload.fragmentReplacesDepth, sizeof(payload.fragmentReplacesDepth)));
         if (payload.colorAttachmentCount > 0) {
             XXHASH_VERIFY(XXH64_update(
                 m_hashState,
@@ -165,23 +247,108 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         const HashType hash = ComputeHash(payload);
         auto it = m_cache.find(hash);
         if (it != m_cache.end()) {
-            return it->second;
+            it->second.lastUsedFrame = m_frameCounter;
+            return it->second.pipeline;
         }
 
         VkPipeline pipeline = CreatePipeline(payload);
-        m_cache.emplace(hash, pipeline);
+        m_cache.emplace(hash, PipelineCacheEntry{pipeline, payload.programHash, payload.renderPass,
+                                                 m_frameCounter});
         return pipeline;
     }
 
     void PipelineFactory::DestroyAll() {
         for (auto& pair : m_cache) {
-            if (pair.second != VK_NULL_HANDLE) {
-                vkDestroyPipeline(m_device, pair.second, nullptr);
+            if (pair.second.pipeline != VK_NULL_HANDLE) {
+                vkDestroyPipeline(m_device, pair.second.pipeline, nullptr);
             }
         }
         m_cache.clear();
     }
 
+    Uint32 PipelineFactory::OnFrameBoundary() {
+        ++m_frameCounter;
+
+        // Sweep cadence and retire age mirror VkRenderPassManager::OnPresent: an entry
+        // idle for more than kRetireAgeFrames frame boundaries cannot be referenced by
+        // any in-flight command buffer (frames-in-flight <= MOBILEGL_MAGMA_FRAMESINFLIGHT),
+        // so immediate vkDestroyPipeline is safe. The caller must drop its "last
+        // pipeline" memo when this returns non-zero: the memo can return a cached
+        // handle without touching this cache, so an evicted pipeline may still be
+        // memoized (present-less flush loops never reset the memo per frame).
+        constexpr Uint64 kSweepInterval = 256;
+        constexpr Uint64 kRetireAgeFrames = 1024;
+        if ((m_frameCounter % kSweepInterval) != 0) {
+            return 0;
+        }
+
+        Uint32 evicted = 0;
+        for (auto it = m_cache.begin(); it != m_cache.end();) {
+            if (m_frameCounter - it->second.lastUsedFrame > kRetireAgeFrames) {
+                if (it->second.pipeline != VK_NULL_HANDLE) {
+                    vkDestroyPipeline(m_device, it->second.pipeline, nullptr);
+                }
+                it = m_cache.erase(it);
+                ++evicted;
+            } else {
+                ++it;
+            }
+        }
+        if (evicted > 0) {
+            MGLOG_D("PipelineFactory::OnFrameBoundary: evicted %u idle pipelines (%zu remain)", evicted,
+                    m_cache.size());
+        }
+        return evicted;
+    }
+
+    Uint32 PipelineFactory::EvictByRenderPasses(const Vector<VkRenderPass>& renderPasses) {
+        if (renderPasses.empty() || m_cache.empty()) {
+            return 0;
+        }
+        // Sorted-batch membership test keeps a mass eviction (shader-pack switch,
+        // dimension exit) at one O(cache * log batch) scan instead of one full scan
+        // per dying pass.
+        Vector<VkRenderPass> sortedPasses = renderPasses;
+        std::sort(sortedPasses.begin(), sortedPasses.end());
+        Uint32 evicted = 0;
+        for (auto it = m_cache.begin(); it != m_cache.end();) {
+            if (std::binary_search(sortedPasses.begin(), sortedPasses.end(), it->second.renderPass)) {
+                if (it->second.pipeline != VK_NULL_HANDLE) {
+                    vkDestroyPipeline(m_device, it->second.pipeline, nullptr);
+                }
+                it = m_cache.erase(it);
+                ++evicted;
+            } else {
+                ++it;
+            }
+        }
+        if (evicted > 0) {
+            MGLOG_D("PipelineFactory::EvictByRenderPasses: evicted %u pipelines for %zu destroyed render passes",
+                    evicted, sortedPasses.size());
+        }
+        return evicted;
+    }
+
+    Uint32 PipelineFactory::EvictByProgramHash(HashType programHash) {
+        Uint32 evicted = 0;
+        for (auto it = m_cache.begin(); it != m_cache.end();) {
+            if (it->second.programHash == programHash) {
+                if (it->second.pipeline != VK_NULL_HANDLE) {
+                    vkDestroyPipeline(m_device, it->second.pipeline, nullptr);
+                }
+                it = m_cache.erase(it);
+                ++evicted;
+            } else {
+                ++it;
+            }
+        }
+        if (evicted > 0) {
+            MGLOG_D("PipelineFactory::EvictByProgramHash: evicted %u pipelines for program hash 0x%llx",
+                    evicted, static_cast<unsigned long long>(programHash));
+        }
+        return evicted;
+    }
+
     VkPipeline PipelineFactory::CreatePipeline(const PipelineCreatePayload& payload) const {
         MOBILEGL_ASSERT(payload.stages != nullptr && !payload.stages->empty(), "PipelineFactory: stages are empty");
         MOBILEGL_ASSERT(payload.vertexInputState != nullptr, "PipelineFactory: vertexInputState is null");
@@ -216,6 +383,11 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         ia.topology = payload.topology;
         ia.primitiveRestartEnable = payload.primitiveRestartEnable ? VK_TRUE : VK_FALSE;
 
+        // Only a patch topology has a tessellation stage to configure; leaving the pointer null
+        // otherwise is what the spec expects.
+        VkPipelineTessellationStateCreateInfo tessellation{VK_STRUCTURE_TYPE_PIPELINE_TESSELLATION_STATE_CREATE_INFO};
+        tessellation.patchControlPoints = payload.patchControlPoints;
+
         VkPipelineViewportStateCreateInfo vpci{VK_STRUCTURE_TYPE_PIPELINE_VIEWPORT_STATE_CREATE_INFO};
         vpci.viewportCount = 1;
         vpci.scissorCount = 1;
@@ -227,6 +399,17 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         raster.depthBiasEnable = payload.depthBiasEnable ? VK_TRUE : VK_FALSE;
         raster.rasterizerDiscardEnable = payload.rasterizerDiscardEnable ? VK_TRUE : VK_FALSE;
         raster.lineWidth = 1.0f;
+        // Only chain the struct when the mode is not Vulkan's implicit default: a device without
+        // VK_EXT_provoking_vertex enabled must never see this pNext entry, and the renderer's
+        // selector already collapses to FIRST in exactly that case - so a device without the
+        // extension produces a byte-identical VkGraphicsPipelineCreateInfo to before.
+        VkPipelineRasterizationProvokingVertexStateCreateInfoEXT provokingVertexState{
+            VK_STRUCTURE_TYPE_PIPELINE_RASTERIZATION_PROVOKING_VERTEX_STATE_CREATE_INFO_EXT};
+        if (payload.provokingVertexMode != VK_PROVOKING_VERTEX_MODE_FIRST_VERTEX_EXT) {
+            provokingVertexState.provokingVertexMode = payload.provokingVertexMode;
+            provokingVertexState.pNext = raster.pNext;
+            raster.pNext = &provokingVertexState;
+        }
 
         VkPipelineMultisampleStateCreateInfo ms{VK_STRUCTURE_TYPE_PIPELINE_MULTISAMPLE_STATE_CREATE_INFO};
         ms.rasterizationSamples = payload.rasterizationSamples;
@@ -258,6 +441,17 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         for (Uint32 i = 0; i < payload.colorAttachmentCount; ++i) {
             colorAttachments[i] = payload.colorBlendAttachments[i];
         }
+        // Suppress depth writes on accumulation-blended pipelines when the active driver
+        // cannot keep vertex positions invariant across the pipelines of a multi-pass
+        // depth-equality chain (see SetSuppressBlendedDepthWrite). The decision is narrowed
+        // in ShouldSuppressDepthWrite: sorted-transparency "over" blends (vanilla MC water),
+        // gl_FragDepth writers, and masked-out attachments keep their depth writes.
+        // This bakes the decision into the pipeline, which only works because depth write is
+        // static state here - adding VK_DYNAMIC_STATE_DEPTH_WRITE_ENABLE to kDynamicStates
+        // would let the record-time value override it and silently disable the quirk.
+        if (s_suppressBlendedDepthWrite && ShouldSuppressDepthWrite(payload)) {
+            depthStencil.depthWriteEnable = VK_FALSE;
+        }
         VkPipelineColorBlendStateCreateInfo blend{VK_STRUCTURE_TYPE_PIPELINE_COLOR_BLEND_STATE_CREATE_INFO};
         blend.logicOpEnable = payload.logicOpEnable ? VK_TRUE : VK_FALSE;
         blend.logicOp = payload.logicOp;
@@ -269,6 +463,8 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         gpi.pStages = payload.stages->data();
         gpi.pVertexInputState = payload.vertexInputState;
         gpi.pInputAssemblyState = &ia;
+        gpi.pTessellationState =
+            payload.topology == VK_PRIMITIVE_TOPOLOGY_PATCH_LIST ? &tessellation : nullptr;
         gpi.pViewportState = &vpci;
         gpi.pRasterizationState = &raster;
         gpi.pMultisampleState = &ms;

MobileGL/MG_Backend/DirectVulkan/Renderer/PipelineFactory.h

@@ -30,9 +30,16 @@ namespace MobileGL::MG_Backend::DirectVulkan {
             Uint32 subpass = 0;
             VkPrimitiveTopology topology = VK_PRIMITIVE_TOPOLOGY_TRIANGLE_LIST;
             Bool primitiveRestartEnable = false;
+            // GL_PATCH_VERTICES; only read for a PATCH_LIST topology.
+            Uint32 patchControlPoints = 3;
             VkPolygonMode polygonMode = VK_POLYGON_MODE_FILL;
             VkCullModeFlags cullMode = VK_CULL_MODE_BACK_BIT;
             VkFrontFace frontFace = VK_FRONT_FACE_CLOCKWISE;
+            // GL's provoking vertex, baked into the pipeline (VK_EXT_provoking_vertex). It selects
+            // which vertex a flat varying takes AND the vertex order transform feedback records for
+            // strips/fans, so it is part of the pipeline's identity, not dynamic state. Defaults to
+            // Vulkan's own convention, which is what a device without the extension gets.
+            VkProvokingVertexModeEXT provokingVertexMode = VK_PROVOKING_VERTEX_MODE_FIRST_VERTEX_EXT;
             Bool depthTestEnable = false;
             Bool depthWriteEnable = false;
             Bool depthBiasEnable = false;
@@ -49,6 +56,9 @@ namespace MobileGL::MG_Backend::DirectVulkan {
             VkStencilOp backStencilPassOp = VK_STENCIL_OP_KEEP;
             VkStencilOp backStencilDepthFailOp = VK_STENCIL_OP_KEEP;
             VkCompareOp backStencilCompareOp = VK_COMPARE_OP_ALWAYS;
+            // The fragment module writes gl_FragDepth (SPIR-V DepthReplacing); exempts the
+            // pipeline from the blended depth-write quirk (see ShouldSuppressDepthWrite).
+            Bool fragmentReplacesDepth = false;
             Array<VkPipelineColorBlendAttachmentState, kMaxColorAttachments> colorBlendAttachments{};
             const Vector<VkPipelineShaderStageCreateInfo>* stages = nullptr;
             const VkPipelineVertexInputStateCreateInfo* vertexInputState = nullptr;
@@ -62,13 +72,69 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         VkPipeline GetOrCreatePipeline(const PipelineCreatePayload& payload);
         void DestroyAll();
 
+        // Frame boundary hook: ages the pipeline cache and destroys long-unused entries
+        // (their command buffers retired many frames ago), mirroring
+        // VkRenderPassManager::OnPresent's sweep. Returns the number of pipelines
+        // destroyed so the caller can drop any memoized VkPipeline handle.
+        Uint32 OnFrameBoundary();
+        // Destroys every cached pipeline hashed on one of `renderPasses`. Only safe
+        // when the caller guarantees GPU idleness for them - the render-pass manager
+        // calls this (via the renderer) for passes its own >1024-boundary-idle sweep
+        // just evicted, and a pipeline hashed on those handles is only ever bound by
+        // draws that also hit the render-pass entries. Also closes the handle-recycling
+        // hazard: a recycled VkRenderPass value must never serve a stale pipeline.
+        // Batched: one cache scan regardless of how many passes died in the sweep.
+        // Returns the number destroyed (callers invalidate memos when non-zero).
+        Uint32 EvictByRenderPasses(const Vector<VkRenderPass>& renderPasses);
+        // Destroys every cached pipeline built from the program with content hash
+        // `programHash`. Called from the ProgramFactory eviction path, which proves the
+        // same >1024-boundary idleness (the program's pipelines are only bound by draws
+        // that stamp its factory entry). Returns the number destroyed.
+        Uint32 EvictByProgramHash(HashType programHash);
+
+        // Driver quirk: suppress depth writes on accumulation-blended pipelines. Multi-pass
+        // depth-equality rendering (a blended prepass writes depth that later passes re-test
+        // with an equality-inclusive compare on the re-rasterized geometry) requires
+        // cross-pipeline position invariance that some mobile compilers do not provide, even
+        // with the SPIR-V Invariant decoration; whole primitives then drop out of the later
+        // passes. Only MIN/MAX extremum blends are stripped - the signature of such a
+        // chain's depth-bounds pass (MC 26.3 OIT), and per a fixture-wide trace sweep the
+        // only depth-writing shape the chain actually uses - so every other blend
+        // (sorted-transparency "over" like vanilla MC water, additive glows, ...) keeps
+        // its depth writes. Set at renderer initialization based on the active driver.
+        static void SetSuppressBlendedDepthWrite(Bool enabled);
+        static Bool IsSuppressBlendedDepthWriteEnabled() { return s_suppressBlendedDepthWrite; }
+        // Device gate for the quirk: ForceOn/ForceOff bypass detection, Auto enables it on
+        // the known-affected vendor (Qualcomm).
+        static Bool ShouldSuppressBlendedDepthWriteForDevice(MG_Config::QuirkOverride quirkOverride,
+                                                             Uint32 vendorId);
+        // Pure per-pipeline strip decision (exempts gl_FragDepth writers, masked-out and
+        // non-accumulation blends); combined with the device flag in CreatePipeline. Static
+        // and payload-only so tests can pin the contract without a VkDevice.
+        static Bool ShouldSuppressDepthWrite(const PipelineCreatePayload& payload);
+
     private:
+        struct PipelineCacheEntry {
+            VkPipeline pipeline = VK_NULL_HANDLE;
+            // The hashed inputs the eviction paths key on: programHash ties the entry to
+            // its ProgramFactory entry, renderPass records the exact handle the hash
+            // folded in (the hash is one-way, so targeted eviction needs them verbatim).
+            HashType programHash = 0;
+            VkRenderPass renderPass = VK_NULL_HANDLE;
+            // Frame-boundary counter value of the last GetOrCreatePipeline hit; drives
+            // cache eviction (see OnFrameBoundary).
+            Uint64 lastUsedFrame = 0;
+        };
+
         VkPipeline CreatePipeline(const PipelineCreatePayload& payload) const;
 
         VkDevice m_device = VK_NULL_HANDLE;
         const VulkanRendererConfig& m_config;
         VkPipelineCache m_pipelineCache = VK_NULL_HANDLE;
-        UnorderedMap<HashType, VkPipeline> m_cache;
+        UnorderedMap<HashType, PipelineCacheEntry> m_cache;
+        // Monotonic frame-boundary counter (bumped in OnFrameBoundary) for cache aging.
+        Uint64 m_frameCounter = 0;
         static inline XXH64_state_t* m_hashState = XXH64_createState();
+        static inline Bool s_suppressBlendedDepthWrite = false;
     };
 } // namespace MobileGL::MG_Backend::DirectVulkan

MobileGL/MG_Backend/DirectVulkan/Renderer/ProgramFactory.h

@@ -14,8 +14,16 @@
 #include "MG_State/GLState/TextureState/TextureEnum.h"
 
 #include <Includes.h>
+#include <spirv_reflect.h>
 
 namespace MobileGL::MG_Backend::DirectVulkan {
+    enum class SamplerNumericDomain : Uint8 {
+        Unknown = 0,
+        Float,
+        SignedInteger,
+        UnsignedInteger,
+    };
+
     class ProgramFactory {
     public:
         enum class DescriptorBindingKind : Uint8 {
@@ -34,6 +42,16 @@ namespace MobileGL::MG_Backend::DirectVulkan {
             SurfaceRotate90 = 1 << 2,
             SurfaceRotate180 = 1 << 3,
             SurfaceRotate270 = 1 << 4,
+            // Rewrites the fragment stage's implicit-LOD image samples to explicit LOD 0.
+            // Only ever set for a draw whose every sampler binding is clamped to a single mip
+            // level, which makes the two forms produce identical texels (the implicit lambda is
+            // clamped into [minLod, maxLod] = [0, 0] regardless of derivatives or bias).
+            ExplicitLod0Sampling = 1 << 5,
+            // Decorates the last vertex-processing stage's captured varyings with
+            // XfbBuffer/XfbStride/Offset (VK_EXT_transform_feedback). Set only for draws
+            // recorded while GL transform feedback is active, so plain draws keep the
+            // undecorated variant.
+            XfbCapture = 1 << 6,
         };
         using CompileOptionFlags = Flags<CompileOptionBit>;
         using HashType = Uint64;
@@ -49,13 +67,31 @@ namespace MobileGL::MG_Backend::DirectVulkan {
             VkDescriptorSetLayout descriptorSetLayout = VK_NULL_HANDLE;
             VkPipelineLayout pipelineLayout = VK_NULL_HANDLE;
             Vector<DescriptorBindingKind> bindingKinds;
+            // The bindings this program actually declares, ascending. bindingKinds is sized to the
+            // 256-binding cap while a real GL program uses 1-8, so the per-draw descriptor walk was
+            // scanning 256 slots to find a handful. MUST stay ascending: Vulkan consumes
+            // pDynamicOffsets in binding order and the writer pushes them in iteration order, so an
+            // unordered list would silently mis-pair dynamic offsets with their uniform blocks.
+            Vector<Uint32> activeBindings;
             Vector<Uint32> dynamicBindings;
             Vector<Int> uniformBlockIndexByBinding;
+            // Descriptor count per binding (1 except for UBO instance arrays, which occupy one
+            // binding with descriptorCount = N).
+            Vector<Uint16> bindingDescriptorCounts;
+            // Per-element GL uniform block indices for arrayed UBO bindings (count > 1);
+            // element 0 of a non-arrayed binding stays in uniformBlockIndexByBinding.
+            UnorderedMap<Uint32, Vector<Int>> arrayedUniformBlockIndicesByBinding;
             Vector<String> samplerNameByBinding;
             Vector<Int> samplerUniformLocationByBinding;
             Vector<TextureTarget> samplerTextureTargetByBinding;
+            Vector<SamplerNumericDomain> samplerNumericDomainByBinding;
+            Vector<VkFormat> storageImageFormatByBinding;
+            Vector<Bool> storageImageUsesBindingFormatByBinding;
             Vector<String> storageBlockNameByBinding;
             Vector<Int> storageBlockIndexByBinding;
+            // Set once during ReflectLayout so the per-draw path can skip the whole
+            // storage-image preparation for the overwhelming majority of programs.
+            Bool hasStorageImages = false;
             Int globalUboBinding = -1;
             Uint32 activeVertexInputLocationMask = 0;
             Array<GLenum, kMaxVertexInputLocations> vertexInputTypes{};
@@ -64,6 +100,14 @@ namespace MobileGL::MG_Backend::DirectVulkan {
             ShaderStage rasterizationProducerStage = ShaderStage::Unknown;
             Uint32 producerOutputComponentCount = 0;
             Uint32 fragmentInputComponentCount = 0;
+            // The fragment module declares the DepthReplacing execution mode (writes
+            // gl_FragDepth); shader-computed depth is immune to the cross-pipeline
+            // position-invariance quirk (see PipelineFactory::ShouldSuppressDepthWrite).
+            Bool fragmentReplacesDepth = false;
+            // Frame-boundary counter value of the last GetOrCreateProgram hit; drives
+            // cache eviction (see OnFrameBoundary). Mutable: the draw snapshot's memoised
+            // entry pointer re-stamps use through a const reference (StampProgramUse).
+            mutable Uint64 lastUsedFrame = 0;
 
             static inline VkDevice s_device = VK_NULL_HANDLE;
 
@@ -77,13 +121,21 @@ namespace MobileGL::MG_Backend::DirectVulkan {
                 descriptorSetLayout = other.descriptorSetLayout;
                 pipelineLayout = other.pipelineLayout;
                 bindingKinds = std::move(other.bindingKinds);
+                activeBindings = std::move(other.activeBindings);
                 dynamicBindings = std::move(other.dynamicBindings);
                 uniformBlockIndexByBinding = std::move(other.uniformBlockIndexByBinding);
+                bindingDescriptorCounts = std::move(other.bindingDescriptorCounts);
+                arrayedUniformBlockIndicesByBinding = std::move(other.arrayedUniformBlockIndicesByBinding);
                 samplerNameByBinding = std::move(other.samplerNameByBinding);
                 samplerUniformLocationByBinding = std::move(other.samplerUniformLocationByBinding);
                 samplerTextureTargetByBinding = std::move(other.samplerTextureTargetByBinding);
+                samplerNumericDomainByBinding = std::move(other.samplerNumericDomainByBinding);
+                storageImageFormatByBinding = std::move(other.storageImageFormatByBinding);
+                storageImageUsesBindingFormatByBinding =
+                    std::move(other.storageImageUsesBindingFormatByBinding);
                 storageBlockNameByBinding = std::move(other.storageBlockNameByBinding);
                 storageBlockIndexByBinding = std::move(other.storageBlockIndexByBinding);
+                hasStorageImages = other.hasStorageImages;
                 globalUboBinding = other.globalUboBinding;
                 activeVertexInputLocationMask = other.activeVertexInputLocationMask;
                 vertexInputTypes = other.vertexInputTypes;
@@ -92,15 +144,20 @@ namespace MobileGL::MG_Backend::DirectVulkan {
                 rasterizationProducerStage = other.rasterizationProducerStage;
                 producerOutputComponentCount = other.producerOutputComponentCount;
                 fragmentInputComponentCount = other.fragmentInputComponentCount;
+                fragmentReplacesDepth = other.fragmentReplacesDepth;
+                lastUsedFrame = other.lastUsedFrame;
                 other.hash = 0;
                 other.descriptorSetLayout = VK_NULL_HANDLE;
                 other.pipelineLayout = VK_NULL_HANDLE;
+                other.hasStorageImages = false;
                 other.globalUboBinding = -1;
                 other.activeVertexInputLocationMask = 0;
                 other.activeFragmentOutputLocationMask = 0;
                 other.rasterizationProducerStage = ShaderStage::Unknown;
                 other.producerOutputComponentCount = 0;
                 other.fragmentInputComponentCount = 0;
+                other.fragmentReplacesDepth = false;
+                other.lastUsedFrame = 0;
             }
             VkProgramObject& operator=(VkProgramObject&& other) noexcept {
                 if (this == &other) {
@@ -113,13 +170,21 @@ namespace MobileGL::MG_Backend::DirectVulkan {
                 descriptorSetLayout = other.descriptorSetLayout;
                 pipelineLayout = other.pipelineLayout;
                 bindingKinds = std::move(other.bindingKinds);
+                activeBindings = std::move(other.activeBindings);
                 dynamicBindings = std::move(other.dynamicBindings);
                 uniformBlockIndexByBinding = std::move(other.uniformBlockIndexByBinding);
+                bindingDescriptorCounts = std::move(other.bindingDescriptorCounts);
+                arrayedUniformBlockIndicesByBinding = std::move(other.arrayedUniformBlockIndicesByBinding);
                 samplerNameByBinding = std::move(other.samplerNameByBinding);
                 samplerUniformLocationByBinding = std::move(other.samplerUniformLocationByBinding);
                 samplerTextureTargetByBinding = std::move(other.samplerTextureTargetByBinding);
+                samplerNumericDomainByBinding = std::move(other.samplerNumericDomainByBinding);
+                storageImageFormatByBinding = std::move(other.storageImageFormatByBinding);
+                storageImageUsesBindingFormatByBinding =
+                    std::move(other.storageImageUsesBindingFormatByBinding);
                 storageBlockNameByBinding = std::move(other.storageBlockNameByBinding);
                 storageBlockIndexByBinding = std::move(other.storageBlockIndexByBinding);
+                hasStorageImages = other.hasStorageImages;
                 globalUboBinding = other.globalUboBinding;
                 activeVertexInputLocationMask = other.activeVertexInputLocationMask;
                 vertexInputTypes = other.vertexInputTypes;
@@ -128,15 +193,20 @@ namespace MobileGL::MG_Backend::DirectVulkan {
                 rasterizationProducerStage = other.rasterizationProducerStage;
                 producerOutputComponentCount = other.producerOutputComponentCount;
                 fragmentInputComponentCount = other.fragmentInputComponentCount;
+                fragmentReplacesDepth = other.fragmentReplacesDepth;
+                lastUsedFrame = other.lastUsedFrame;
                 other.hash = 0;
                 other.descriptorSetLayout = VK_NULL_HANDLE;
                 other.pipelineLayout = VK_NULL_HANDLE;
+                other.hasStorageImages = false;
                 other.globalUboBinding = -1;
                 other.activeVertexInputLocationMask = 0;
                 other.activeFragmentOutputLocationMask = 0;
                 other.rasterizationProducerStage = ShaderStage::Unknown;
                 other.producerOutputComponentCount = 0;
                 other.fragmentInputComponentCount = 0;
+                other.fragmentReplacesDepth = false;
+                other.lastUsedFrame = 0;
                 return *this;
             }
 
@@ -166,10 +236,24 @@ namespace MobileGL::MG_Backend::DirectVulkan {
             }
         };
 
+        // Notified when the OnFrameBoundary sweep destroys an aged-out cache entry,
+        // carrying the entry's content hash and the VkDescriptorSetLayout it owned.
+        // Dependent caches (compute pipelines, PipelineFactory entries, UniformManager's
+        // per-layout descriptor sets) must purge in the same step: after vkDestroy the
+        // layout handle value may be recycled for an unrelated layout, and the program
+        // hash may be re-inserted by a later rebuild of the same content.
+        class IEvictionObserver {
+        public:
+            virtual ~IEvictionObserver() = default;
+            virtual void OnProgramEvicted(HashType programHash, VkDescriptorSetLayout descriptorSetLayout) = 0;
+        };
+
         explicit ProgramFactory(VkDevice device, const VulkanRendererConfig& config, Uint32 maxBindings = 16,
-                                Bool shaderDrawParametersEnabled = false)
+                                Bool shaderDrawParametersEnabled = false,
+                                Bool unformattedFloatStorageImagesEnabled = false)
             : m_device(device), m_maxBindings(maxBindings), m_config(config),
-              m_shaderDrawParametersEnabled(shaderDrawParametersEnabled) {
+              m_shaderDrawParametersEnabled(shaderDrawParametersEnabled),
+              m_unformattedFloatStorageImagesEnabled(unformattedFloatStorageImagesEnabled) {
             VkProgramObject::s_device = device;
         }
         ~ProgramFactory() = default;
@@ -179,7 +263,34 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         const VkProgramObject& GetOrCreateProgram(
             const MG_State::GLState::ProgramObject& program, CompileOptionFlags flags);
 
+        // Bumped whenever m_cache's STRUCTURE changes (any insert or erase): the cache is
+        // an open-addressing map holding entries by value, so both moves existing entries.
+        // A caller that memoised a VkProgramObject* may keep dereferencing it only while
+        // this is unchanged; on a bump it must re-run GetOrCreateProgram.
+        Uint64 GetCacheStructureEpoch() const { return m_cacheStructureEpoch; }
+        // A memoised entry pointer bypasses GetOrCreateProgram, whose per-lookup stamp is
+        // what keeps an in-use entry out of OnFrameBoundary's idle sweep - so such a
+        // caller must re-stamp the entry itself, at least once per frame boundary.
+        void StampProgramUse(const VkProgramObject& entry) const { entry.lastUsedFrame = m_frameCounter; }
+
+        // Observer may be null (no notifications). Not owned.
+        void SetEvictionObserver(IEvictionObserver* observer) { m_evictionObserver = observer; }
+        // Frame boundary hook: ages the program cache and evicts long-unused entries
+        // (their command buffers retired many frames ago), mirroring
+        // VkRenderPassManager::OnPresent's sweep.
+        void OnFrameBoundary();
+
         static VkShaderStageFlagBits ToVkStage(ShaderStage stage);
+        static VkFormat ConvertSpirvImageFormatToVkFormat(SpvImageFormat format);
+        static SamplerNumericDomain UniformTypeToSamplerNumericDomain(GLenum glType);
+        // True when any entry point declares the DepthReplacing execution mode, i.e. the
+        // shader assigns gl_FragDepth. Exposed so the blended depth-write quirk's exemption
+        // can be pinned by tests. A false negative loses the exemption, so such a shader is
+        // stripped conservatively and forfeits its depth write.
+        static Bool ReflectedFragmentReplacesDepth(const SpvReflectShaderModule& reflectModule);
+        // True when an entry point reads the InstanceIndex builtin. Only gates a diagnostic:
+        // without shaderDrawParameters such a shader cannot have gl_InstanceID rebased.
+        static Bool ReflectedReadsInstanceIndexBuiltin(const SpvReflectShaderModule& reflectModule);
 
     private:
         struct ProgramLookupCache {
@@ -206,7 +317,15 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         // True when the device enabled shaderDrawParameters; gates the InstanceIndex rebase pass
         // (which needs the DrawParameters capability / gl_BaseInstance builtin).
         Bool m_shaderDrawParametersEnabled = false;
+        // True only when the logical device enabled both
+        // shaderStorageImageReadWithoutFormat and shaderStorageImageWriteWithoutFormat.
+        Bool m_unformattedFloatStorageImagesEnabled = false;
         mutable ProgramLookupCache m_lastLookup;
+        // Monotonic frame-boundary counter (bumped in OnFrameBoundary) for cache aging.
+        Uint64 m_frameCounter = 0;
+        // See GetCacheStructureEpoch(). Starts at 1 so a zero-initialized memo can never match.
+        Uint64 m_cacheStructureEpoch = 1;
+        IEvictionObserver* m_evictionObserver = nullptr;
         static inline XXH64_state_t* m_hashState = XXH64_createState();
     };
 } // namespace MobileGL::MG_Backend::DirectVulkan

MobileGL/MG_Backend/DirectVulkan/Renderer/SwapchainObject.cpp

@@ -247,6 +247,11 @@ namespace MobileGL::MG_Backend::DirectVulkan {
 
         m_surfaceFormat = {createInfo.imageFormat, createInfo.imageColorSpace};
         m_extent = createInfo.imageExtent;
+        // The surface-space extent this swapchain was built from, i.e. before the
+        // quarter-turn swap above. Out-of-date checks must compare in THIS space: comparing a
+        // freshly queried currentExtent against the swapped m_extent flips axes every rotation
+        // and makes the comparison alternate forever.
+        m_surfaceExtent = defaultFramebufferExtent;
         m_preTransform = createInfo.preTransform;
 
         VK_VERIFY(vkCreateSwapchainKHR(device, &createInfo, nullptr, &m_swapchain));
@@ -257,6 +262,9 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         m_images.resize(imageCount, VK_NULL_HANDLE);
         VK_VERIFY(vkGetSwapchainImagesKHR(device, m_swapchain, &imageCount, m_images.data()));
         m_imageLayouts.assign(imageCount, VK_IMAGE_LAYOUT_UNDEFINED);
+        // Fresh swapchain images hold garbage until a render pass stores into them.
+        m_imageContentDefined.assign(imageCount, false);
+        m_depthStencilContentDefined.assign(imageCount, false);
 
         CreateImageViews(device);
         CreateDepthStencilResources(device, physicalDevice);
@@ -428,9 +436,39 @@ namespace MobileGL::MG_Backend::DirectVulkan {
 
         m_images.clear();
         m_imageLayouts.clear();
+        m_imageContentDefined.clear();
+        m_depthStencilContentDefined.clear();
         m_preTransform = VK_SURFACE_TRANSFORM_IDENTITY_BIT_KHR;
     }
 
+    Bool SwapchainObject::IsImageContentDefined(Uint32 index) const {
+        MOBILEGL_ASSERT(index < m_imageContentDefined.size(), "Swapchain image content index out of range");
+        return m_imageContentDefined[index];
+    }
+
+    void SwapchainObject::SetImageContentDefined(Uint32 index, Bool defined) {
+        MOBILEGL_ASSERT(index < m_imageContentDefined.size(), "Swapchain image content index out of range");
+        m_imageContentDefined[index] = defined;
+    }
+
+    Bool SwapchainObject::IsDepthStencilContentDefined(Uint32 index) const {
+        MOBILEGL_ASSERT(index < m_depthStencilContentDefined.size(),
+                        "Swapchain depth/stencil content index out of range");
+        return m_depthStencilContentDefined[index];
+    }
+
+    void SwapchainObject::SetDepthStencilContentDefined(Uint32 index, Bool defined) {
+        MOBILEGL_ASSERT(index < m_depthStencilContentDefined.size(),
+                        "Swapchain depth/stencil content index out of range");
+        m_depthStencilContentDefined[index] = defined;
+    }
+
+    void SwapchainObject::SetAllDepthStencilContentUndefined() {
+        for (SizeT i = 0; i < m_depthStencilContentDefined.size(); ++i) {
+            m_depthStencilContentDefined[i] = false;
+        }
+    }
+
     VkImage SwapchainObject::GetImage(Uint32 index) const {
         MOBILEGL_ASSERT(index < m_images.size(), "Swapchain image index out of range");
         return m_images[index];

MobileGL/MG_Backend/DirectVulkan/Renderer/SwapchainObject.h

@@ -35,6 +35,9 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         VkSwapchainKHR GetHandle() const { return m_swapchain; }
         const VkSurfaceFormatKHR& GetSurfaceFormat() const { return m_surfaceFormat; }
         VkExtent2D GetExtent() const { return m_extent; }
+        // Surface-space extent (before the pre-rotation quarter-turn swap) this swapchain was
+        // created from - the value to compare a freshly queried currentExtent against.
+        VkExtent2D GetSurfaceExtent() const { return m_surfaceExtent; }
         VkSurfaceTransformFlagBitsKHR GetPreTransform() const { return m_preTransform; }
         const Vector<VkImage>& GetImages() const { return m_images; }
         const Vector<VkImageView>& GetImageViews() const { return m_imageViews; }
@@ -49,6 +52,21 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         void SetImageLayout(Uint32 index, VkImageLayout layout);
         SizeT GetImageCount() const { return m_images.size(); }
 
+        // EGL content-validity tracking for the default framebuffer. A color
+        // buffer's content is undefined once its image has been presented
+        // (EGL_BUFFER_DESTROYED swap behaviour, the implementation default),
+        // and every ancillary (depth/stencil) buffer's content is undefined
+        // after ANY swap regardless of swap behaviour (EGL 1.5 §3.10.1). The
+        // render-pass manager turns an undefined attachment's tile load into
+        // LOAD_OP_DONT_CARE. Flags start false (a fresh swapchain image holds
+        // garbage) and a render pass storing into an attachment sets it back
+        // to defined.
+        Bool IsImageContentDefined(Uint32 index) const;
+        void SetImageContentDefined(Uint32 index, Bool defined);
+        Bool IsDepthStencilContentDefined(Uint32 index) const;
+        void SetDepthStencilContentDefined(Uint32 index, Bool defined);
+        void SetAllDepthStencilContentUndefined();
+
     private:
         void CreateImageViews(VkDevice device);
         void CreateDepthStencilResources(VkDevice device, VkPhysicalDevice physicalDevice);
@@ -63,6 +81,7 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         VkSwapchainKHR m_swapchain = VK_NULL_HANDLE;
         VkSurfaceFormatKHR m_surfaceFormat{};
         VkExtent2D m_extent{};
+        VkExtent2D m_surfaceExtent{};
         VkSurfaceTransformFlagBitsKHR m_preTransform = VK_SURFACE_TRANSFORM_IDENTITY_BIT_KHR;
         Vector<VkImage> m_images;
         Vector<VkImageView> m_imageViews;
@@ -73,5 +92,7 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         Vector<VkDeviceMemory> m_depthStencilImageMemories;
         Vector<VkImageView> m_depthStencilImageViews;
         Vector<VkImageLayout> m_depthStencilImageLayouts;
+        Vector<Bool> m_imageContentDefined;
+        Vector<Bool> m_depthStencilContentDefined;
     };
 } // namespace MobileGL::MG_Backend::DirectVulkan

MobileGL/MG_Backend/DirectVulkan/Renderer/UniformManager.h

@@ -39,15 +39,72 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         void Shutdown();
 
         void BeginFrame(Uint32 frameIndex);
+        // A command buffer (re)began recording: descriptor bindings recorded into
+        // the previous buffer do not carry over, so drop the bind-dedup shadow.
+        void OnCommandBufferBoundary() { m_lastBindValid = false; }
+        // A ProgramFactory eviction just destroyed this layout: purge every frame
+        // slot's cached descriptor sets for it, so a recycled handle value can never
+        // stale-hit sets written for the dead layout's bindings. The sets are
+        // vkFreeDescriptorSets'd back to their pools (created with
+        // FREE_DESCRIPTOR_SET_BIT) and the pool accounting is credited, so program
+        // churn recycles pool capacity instead of abandoning it. GPU-safe: the layout
+        // only dies after >1024 idle frame boundaries, so no in-flight command buffer
+        // references its sets. This is the only eviction path for the per-layout
+        // caches - a live layout's entry must never be purged (its sets would be
+        // unreachable pool slots), so there is deliberately no age-based sweep here.
+        void OnDescriptorSetLayoutDestroyed(VkDescriptorSetLayout descriptorSetLayout);
+        // One record per visited CombinedImageSampler binding (post fallback substitution,
+        // in binding order): the resolved texture and effective sampler, as never-reused
+        // lifetime ids so a freed-and-reallocated object at the same heap address can only
+        // MISS a comparison, never false-hit it (same ABA rule as SamplerResolveMemo).
+        struct SampledBindingRecord {
+            Uint64 textureLifetimeId = 0;
+            Uint64 samplerLifetimeId = 0;
+        };
         Bool CollectSampledTextures(const MG_State::GLState::ProgramObject& program,
                                     const ProgramFactory::VkProgramObject& programObj,
-                                    Vector<MG_State::GLState::ITextureObject*>& outTextures);
+                                    Vector<MG_State::GLState::ITextureObject*>& outTextures,
+                                    Vector<SampledBindingRecord>* outBindingRecords = nullptr);
+        // Shadow-compare for the SetupDraw fast path: re-runs the CollectSampledTextures
+        // walk and reports whether every visited binding still resolves to the recorded
+        // (texture, effective sampler) pair. A texture bind generation bump alone (e.g. a
+        // redundant glBindSampler, which always bumps it) does not prove the sampled set
+        // moved; this walk does, without rebuilding the set or falling off the fast path.
+        Bool SampledBindingsUnchanged(const MG_State::GLState::ProgramObject& program,
+                                      const ProgramFactory::VkProgramObject& programObj,
+                                      const Vector<SampledBindingRecord>& previousRecords) const;
+        Bool CollectStorageImageTextures(const MG_State::GLState::ProgramObject& program,
+                                         const ProgramFactory::VkProgramObject& programObj,
+                                         Vector<MG_State::GLState::ITextureObject*>& outTextures) const;
+        // samplerDescriptorsUnchangedHint: the caller (SetupDraw fast path) proved that
+        // every input of every combined-image-sampler resolution is unchanged since the
+        // previous draw's resolve - same (texture, sampler) per binding, texture params
+        // sum, sampling-resolution generation (sampler params + texture shape), image
+        // epochs AND per-resource layout values - so the per-binding cached
+        // VkDescriptorImageInfo may be reused without re-running the resolve chain.
         Bool BindProgramUniformBuffers(VkCommandBuffer commandBuffer,
                                        const MG_State::GLState::ProgramObject& program,
                                        const ProgramFactory::VkProgramObject& programObj,
                                        Uint32 frameIndex,
                                        VkPipelineBindPoint bindPoint = VK_PIPELINE_BIND_POINT_GRAPHICS,
-                                       const SamplerBindingOverride* samplerBindingOverride = nullptr);
+                                       const SamplerBindingOverride* samplerBindingOverride = nullptr,
+                                       Bool samplerDescriptorsUnchangedHint = false);
+
+        // Pure format-policy helper kept public for host regression tests. Formatted storage
+        // images use their shader qualifier; transformed float images use glBindImageTexture's
+        // format and never silently fall back to the backing image format.
+        static VkFormat ResolveStorageImageViewFormat(VkFormat reflectedFormat, GLenum bindingFormat,
+                                                      VkFormat resourceFormat, Bool useBindingFormat);
+
+        // True when the program reads at least one sampler and every one of them is bound to a
+        // texture whose GL level range is a single level. Such a sampler resolves to
+        // minLod = maxLod = 0 (see VkSamplerManager::GetOrCreateSampler), so an implicit-LOD sample
+        // and an explicit LOD 0 sample must read the same texel - which is what makes the
+        // ExplicitLod0Sampling SPIR-V rewrite safe to request. Deliberately conservative: it reads
+        // only GL state, so a texture that ends up single-level for another reason (one uploaded
+        // level under a wide level range) merely misses the rewrite.
+        static Bool ProgramSamplesOnlySingleLevelTextures(const MG_State::GLState::ProgramObject& program,
+                                                          const ProgramFactory::VkProgramObject& programObj);
 
     private:
         struct DescriptorPoolBucket {
@@ -56,8 +113,16 @@ namespace MobileGL::MG_Backend::DirectVulkan {
             Uint32 allocatedSets = 0;
         };
 
+        // A cached descriptor set together with the pool it was allocated from, so a
+        // layout-destroyed purge can vkFreeDescriptorSets it back and credit the
+        // owning bucket's accounting.
+        struct CachedDescriptorSet {
+            VkDescriptorSet set = VK_NULL_HANDLE;
+            VkDescriptorPool pool = VK_NULL_HANDLE;
+        };
+
         struct DescriptorSetCacheEntry {
-            Vector<VkDescriptorSet> sets;
+            Vector<CachedDescriptorSet> sets;
             Uint32 cursor = 0;
         };
 
@@ -73,6 +138,15 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         static Bool ResolveSamplerTexture(const MG_State::GLState::ProgramObject& program,
                                    const ProgramFactory::VkProgramObject& programObj, Uint32 binding,
                                    SharedPtr<MG_State::GLState::ITextureObject>& outTexture);
+        // Shared per-binding resolution for CollectSampledTextures and
+        // SampledBindingsUnchanged, so membership and comparison can never diverge:
+        // texture after the fallback substitution (may still be null when no fallback
+        // exists), effective sampler = unit override else the texture's own sampler.
+        // False = the binding is skipped (unbound with a non-2D fallback target).
+        Bool ResolveSampledBinding(const MG_State::GLState::ProgramObject& program,
+                                   const ProgramFactory::VkProgramObject& programObj, Uint32 binding,
+                                   MG_State::GLState::ITextureObject*& outTexture,
+                                   const MG_State::GLState::SamplerObject*& outSampler) const;
         // Raw-pointer variant for the per-draw sampled-texture walk (CollectSampledTextures):
         // the bound texture stays alive through the draw via GL binding state, so callers that
         // only need the pointer skip the SharedPtr copy's atomic refcount churn.
@@ -80,9 +154,13 @@ namespace MobileGL::MG_Backend::DirectVulkan {
             const MG_State::GLState::ProgramObject& program,
             const ProgramFactory::VkProgramObject& programObj, Uint32 binding);
         SharedPtr<MG_State::GLState::ITextureObject> GetFallbackTexture(TextureTarget target) const;
+        // trustUnchangedHint: reuse this binding's cached VkDescriptorImageInfo outright
+        // (see BindProgramUniformBuffers' samplerDescriptorsUnchangedHint for the proof
+        // obligations the caller carries).
         Bool ResolveSamplerDescriptor(VkCommandBuffer commandBuffer, const MG_State::GLState::ProgramObject& program,
                                       const ProgramFactory::VkProgramObject& programObj, Uint32 binding,
-                                      VkDescriptorImageInfo& outImageInfo) const;
+                                      VkDescriptorImageInfo& outImageInfo,
+                                      Bool trustUnchangedHint = false) const;
         Bool ResolveSamplerDescriptorOverride(const SamplerBindingOverride& samplerBindingOverride,
                                               VkDescriptorImageInfo& outImageInfo) const;
         Bool ResolveTexelBufferDescriptor(const MG_State::GLState::ProgramObject& program,
@@ -107,7 +185,22 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         };
         Bool ResolveUniformBufferPayload(const MG_State::GLState::ProgramObject& program,
                                          const ProgramFactory::VkProgramObject& programObj, Uint32 binding,
-                                         UboBindResult& out) const;
+                                         Uint32 arrayElement, UboBindResult& out) const;
+        // Shared resolution of one dynamic-UBO binding element into the
+        // (buffer, range, dynamicOffset) triple the descriptor consumes: direct
+        // bind, global-slice reuse, or transient upload. Used by the full walk
+        // and by the dynamic-offset-only rebind (see FastRebindMemo).
+        Bool ResolveDynamicUboDescriptor(const MG_State::GLState::ProgramObject& program,
+                                         const ProgramFactory::VkProgramObject& programObj, Uint32 binding,
+                                         Uint32 arrayElement, Uint32 frameIndex, VkBuffer& outBuffer,
+                                         VkDeviceSize& outRange, Uint32& outDynamicOffset);
+        // The vkCmdBindDescriptorSets tail shared by the full walk and the
+        // dynamic-offset-only rebind: skips the driver call when this exact
+        // binding is already live on the command buffer (see the bind-dedup
+        // shadow below), otherwise binds and refreshes the shadow.
+        void BindDescriptorSetDeduped(VkCommandBuffer commandBuffer, VkPipelineBindPoint bindPoint,
+                                      VkPipelineLayout pipelineLayout, VkDescriptorSet descriptorSet,
+                                      const Vector<Uint32>& dynamicOffsets);
         Bool CreateDescriptorPool(Uint32 maxSets, VkDescriptorPool& outPool) const;
         Bool GrowFrameDescriptorPool(FrameResources& frame, Uint32 frameIndex);
         VkResult AllocateDescriptorSetsFromActivePool(
@@ -138,14 +231,82 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         Vector<VkBufferView> m_texelBufferViewsScratch;
         Vector<Uint32> m_dynamicOffsetsScratch;
 
-        // Descriptor-set reuse across consecutive draws (see BindProgramUniformBuffers).
-        // When a draw's resolved descriptor content is byte-identical to the previous
-        // draw's, reuse the same VkDescriptorSet and skip AcquireDescriptorSet +
-        // vkUpdateDescriptorSets - only the bind-time dynamic offsets differ. Reset each
-        // frame in BeginFrame because the frame's descriptor sets are recycled there.
-        VkDescriptorSet m_lastBoundDescriptorSet = VK_NULL_HANDLE;
-        Uint64 m_lastDescriptorSignature = 0;
-        Bool m_hasLastDescriptor = false;
+        // Descriptor-set reuse across recent draws (see BindProgramUniformBuffers).
+        // When a draw's resolved descriptor content is byte-identical to one memoized
+        // earlier, reuse that VkDescriptorSet and skip AcquireDescriptorSet +
+        // vkUpdateDescriptorSets - only the bind-time dynamic offsets differ. Four
+        // entries with round-robin replacement rather than one: draws alternating
+        // between two programs (MC's chunk<->entity ping-pong) would thrash a single
+        // slot into a full re-allocate+write every draw. Reset each frame in BeginFrame
+        // because the frame's descriptor sets are recycled there.
+        struct DescriptorReuseEntry {
+            Uint64 signature = 0;
+            VkDescriptorSet set = VK_NULL_HANDLE;
+            Bool valid = false;
+        };
+        static constexpr Uint32 kDescriptorReuseMemoSize = 4;
+        DescriptorReuseEntry m_descriptorReuseMemo[kDescriptorReuseMemoSize];
+        Uint32 m_descriptorReuseMemoNext = 0;
+
+        // Dynamic-offset-only rebind (see BindProgramUniformBuffers): records the
+        // descriptor set selected by the last cacheable full walk of a program
+        // whose active bindings are exactly one dynamic UBO (single descriptor)
+        // plus combined-image samplers. When the next call proves every sampler
+        // descriptor input unchanged (samplerDescriptorsUnchangedHint) and the
+        // UBO re-resolves to the SAME VkBuffer+range - only the dynamic offset
+        // moved, the per-draw glUniform case - the walk collapses to: resolve one
+        // offset, rebind the recorded set with new pDynamicOffsets (Vulkan allows
+        // rebinding the same set with different dynamic offsets).
+        // Invalidation inventory: BeginFrame clears it (the frame's sets are
+        // recycled) and the frameIndex field guards cross-frame confusion on top;
+        // OnDescriptorSetLayoutDestroyed clears it (the set may be freed); a
+        // sampler-override walk clears it (mirrors m_descriptorReuseMemo); a
+        // program relink bumps the backend state version and thus programObj.hash
+        // so the key misses; the program lifetime id is never reused, so a
+        // deleted-and-recreated program misses; a texture/sampler/binding change
+        // drops the hint upstream; an arena wrap or growth resolves a different
+        // VkBuffer and misses. AcquireDescriptorSet's per-frame cursor only
+        // advances, so the recorded set is never re-written within its frame.
+        struct FastRebindMemo {
+            Bool valid = false;
+            Uint32 frameIndex = 0;
+            Uint64 programLifetimeId = 0;
+            ProgramFactory::HashType programHash = 0;
+            Uint32 uboBinding = 0;
+            VkBuffer uboBuffer = VK_NULL_HANDLE;
+            VkDeviceSize uboRange = 0;
+            VkDescriptorSet set = VK_NULL_HANDLE;
+        };
+        FastRebindMemo m_fastRebindMemo;
+
+        // vkCmdBindDescriptorSets dedup: consecutive draws with a static uniform
+        // block resolve to the same set AND the same dynamic offsets, so the
+        // driver call can be skipped outright. Command-buffer-scope state; reset
+        // via OnCommandBufferBoundary whenever a recording (re)begins. Keyed on
+        // layout+bind point, so a pipeline-layout switch always rebinds.
+        static constexpr Uint32 kMaxShadowedDynamicOffsets = 8;
+        Bool m_lastBindValid = false;
+        VkDescriptorSet m_lastBindSet = VK_NULL_HANDLE;
+        VkPipelineLayout m_lastBindLayout = VK_NULL_HANDLE;
+        VkPipelineBindPoint m_lastBindPoint = VK_PIPELINE_BIND_POINT_GRAPHICS;
+        Uint32 m_lastBindOffsetCount = 0;
+        Uint32 m_lastBindOffsets[kMaxShadowedDynamicOffsets] = {};
+
+        // Global-UBO transient-slice reuse: MC leaves the default uniform block
+        // untouched across long GUI/terrain runs, so the per-draw re-upload of
+        // the same bytes can reuse the slice uploaded earlier THIS frame (frame
+        // serial guards arena recycling; the content version guards writes).
+        struct GlobalUboSliceMemo {
+            Uint64 programLifetimeId = 0;
+            Uint64 frameSerial = 0;
+            Uint32 uboContentVersion = 0;
+            VkBuffer buffer = VK_NULL_HANDLE;
+            VkDeviceSize offset = 0;
+            VkDeviceSize range = 0;
+        };
+        static constexpr Uint32 kGlobalUboMemoSize = 4;
+        GlobalUboSliceMemo m_globalUboMemo[kGlobalUboMemoSize];
+        Uint32 m_globalUboMemoNext = 0;
 
         // Per-binding fast path over VkSamplerManager's content-hashed sampler cache, which
         // stays the source of truth: its key hashes all sampler+texture state, so two distinct
@@ -163,11 +324,40 @@ namespace MobileGL::MG_Backend::DirectVulkan {
             Uint64 samplerLifetimeId = 0;
             Uint64 textureLifetimeId = 0;
             VkSampler sampler = VK_NULL_HANDLE;
+            Uint32 viewLevelCount = 0;
             Uint16 samplerVersion = 0;
             Uint16 textureParamsVersion = 0;
+            Bool forceNearestFiltering = false;
             Bool valid = false;
+            // ResolveSampledImageViewFormat is pure in (image format, numeric domain), but a
+            // domain mismatch walks a ~184-entry format table. Memo the resolution per binding
+            // so a reinterpreted sampler pays that scan once, not once per draw.
+            VkFormat viewFormatSource = VK_FORMAT_UNDEFINED;
+            SamplerNumericDomain viewFormatDomain = SamplerNumericDomain::Unknown;
+            VkFormat viewFormat = VK_FORMAT_UNDEFINED;
+            Bool viewFormatValid = false;
+            // Whole resolved descriptor from this binding's last full resolve. Reused
+            // ONLY under ResolveSamplerDescriptor's trustUnchangedHint, whose caller
+            // proves every resolve input unchanged; cleared with the per-frame reset
+            // (the cached VkSampler outlives a frame only via a fresh resolve, which
+            // also re-stamps it against VkSamplerManager's frame-boundary sweep).
+            VkDescriptorImageInfo info{};
+            Bool infoValid = false;
         };
         mutable Vector<SamplerResolveMemo> m_samplerResolveMemo;
+        // Exclusive upper bound on the entries of m_samplerResolveMemo that any resolve
+        // has ever written. The vector is sized to the DEVICE binding cap (256 on desktop
+        // NVIDIA), but a program declares 1-8 bindings, so the per-frame reset below was
+        // memsetting ~22 KB of never-touched entries every frame - a measurable slice of
+        // the per-frame fixed cost on draw-light frames. Every site that can turn any of
+        // an entry's *Valid flags on raises this mark first, so entries at or above it are
+        // provably still in their constructed (all-invalid) state and clearing them is a
+        // no-op. Never lowered except by Initialize/Shutdown, which rebuild the vector.
+        mutable Uint32 m_samplerResolveMemoHighWater = 0;
+        void NoteSamplerResolveMemoTouched(Uint32 binding) const {
+            if (binding >= m_samplerResolveMemoHighWater) {
+                m_samplerResolveMemoHighWater = binding + 1;
+            }
+        }
     };
 } // namespace MobileGL::MG_Backend::DirectVulkan
-

MobileGL/MG_Backend/DirectVulkan/Renderer/VertexInputStateFactory.cpp

@@ -29,10 +29,22 @@ namespace MobileGL::MG_Backend::DirectVulkan {
             XXHASH_VERIFY(XXH64_update(m_hashState, &attr.Stride, sizeof(attr.Stride)));
             XXHASH_VERIFY(XXH64_update(m_hashState, &attr.Offset, sizeof(attr.Offset)));
             XXHASH_VERIFY(XXH64_update(m_hashState, &attr.IsInteger, sizeof(attr.IsInteger)));
+            XXHASH_VERIFY(XXH64_update(m_hashState, &attr.IsLong, sizeof(attr.IsLong)));
             XXHASH_VERIFY(XXH64_update(m_hashState, &attr.IsBgra, sizeof(attr.IsBgra)));
             XXHASH_VERIFY(XXH64_update(m_hashState, &attr.Divisor, sizeof(attr.Divisor)));
 
-            const SizeT bufferKey = reinterpret_cast<SizeT>(attr.Buffer.get());
+            // The bound buffer's IDENTITY is a component of the key, and it has to be the
+            // buffer's never-reused lifetime id - NOT its heap address, which this used to
+            // hash. An address is recycled by the allocator, so a deleted-and-recreated
+            // buffer reproduces it; combined with a byte-identical attribute layout that
+            // reproduces the WHOLE content hash, and the hash is what
+            // TryBindResolvedVertexBindings accepts as proof that a memoised binding still
+            // reads the buffer it was resolved from. It did not: a destroyed buffer's GPU
+            // slice was bound for its successor's draw, which is how a transform-feedback
+            // capture came back holding a dead VAO's vertex data (0,0,0,1 - the previous
+            // test's positions) instead of its own.
+            // Zero for client memory (no buffer), which is a distinct identity of its own.
+            const Uint64 bufferKey = attr.Buffer ? attr.Buffer->GetLifetimeId() : 0;
             XXHASH_VERIFY(XXH64_update(m_hashState, &bufferKey, sizeof(bufferKey)));
         }
 
@@ -51,14 +63,33 @@ namespace MobileGL::MG_Backend::DirectVulkan {
 
     const VertexInputStateFactory::BackendVertexInputState& VertexInputStateFactory::GetOrCreateVertexInputState(
         const MG_State::GLState::VertexArrayObject& vao) {
-        return GetOrCreateVertexInputState(vao, GetOrComputeHash(vao));
+        // Per-draw fast path: the VAO carries a pointer to its resolved entry,
+        // valid while its config version and the cache's eviction epoch both
+        // match - no re-hash, no map lookup.
+        const void* memoState = nullptr;
+        Uint64 memoEpoch = 0;
+        if (vao.GetBackendStateMemo(memoState, memoEpoch) && memoEpoch == m_evictionEpoch) {
+            const auto* entry = static_cast<const BackendVertexInputState*>(memoState);
+            entry->lastUsedFrameBoundary = m_frameBoundaryCounter;
+            return *entry;
+        }
+        const BackendVertexInputState& entry = GetOrCreateVertexInputState(vao, GetOrComputeHash(vao));
+        vao.SetBackendStateMemo(&entry, m_evictionEpoch);
+        // Also mirror the layout identity and the two per-draw masks into the VAO's aux
+        // memo (pure VALUES derived from the VAO configuration, so config-version
+        // guarding alone is sound). The draw fast path reads them from the VAO object it
+        // already touched instead of chasing into this entry - see PackVertexInputAuxMemo.
+        vao.SetBackendAuxMemo(entry.layoutHash,
+                              PackVertexInputAuxMasks(entry.unsupportedAttribMask, entry.attributeLocationMask));
+        return entry;
     }
 
     const VertexInputStateFactory::BackendVertexInputState& VertexInputStateFactory::GetOrCreateVertexInputState(
         const MG_State::GLState::VertexArrayObject& vao, HashType hash) {
         auto it = m_cache.find(hash);
         if (it != m_cache.end()) {
-            return it->second;
+            it->second->lastUsedFrameBoundary = m_frameBoundaryCounter;
+            return *it->second;
         }
 
         VertexInputStateBuilder builder;
@@ -66,6 +97,8 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         Vector<SizeT> bindingBaseOffsets;
         Vector<Uint32> bindingAttributeLocations;
         Vector<Bool> bindingUsesClientMemory;
+        Vector<VertexStreamConversion> bindingConversions;
+        Vector<VkVertexInputBindingDivisorDescriptionEXT> bindingDivisors;
         Uint32 unsupportedAttribMask = 0;
 
         for (Uint32 location = 0; location < MG_State::GLState::VertexArrayObject::MAX_VERTEX_ATTRIBS; ++location) {
@@ -74,8 +107,9 @@ namespace MobileGL::MG_Backend::DirectVulkan {
                 continue;
             }
 
-            const auto vkFormat = ToVkVertexFormat(attr.Type, attr.Size, attr.Normalized, attr.IsInteger, attr.IsBgra);
-            if (vkFormat == VK_FORMAT_UNDEFINED) {
+            const VkFormat sourceVkFormat =
+                ToVkVertexFormat(attr.Type, attr.Size, attr.Normalized, attr.IsInteger, attr.IsBgra, attr.IsLong);
+            if (sourceVkFormat == VK_FORMAT_UNDEFINED) {
                 MGLOG_E("Unsupported vertex attribute layout (location=%u, type=%s, size=%d): the array is "
                         "enabled but cannot be mapped to a VkFormat",
                         location, MG_Util::ConvertDataTypeToString(attr.Type).c_str(), attr.Size);
@@ -83,6 +117,33 @@ namespace MobileGL::MG_Backend::DirectVulkan {
                 continue;
             }
 
+            VkFormat vkFormat = sourceVkFormat;
+            VertexStreamConversion conversion = VertexStreamConversion::None;
+            if (!SupportsVertexBufferFormat(vkFormat)) {
+                if (IsScaledIntegerVertexFormat(vkFormat)) {
+                    const VkFormat fallbackFormat = ToFloat32VertexFormat(attr.Size);
+                    if (fallbackFormat != VK_FORMAT_UNDEFINED && SupportsVertexBufferFormat(fallbackFormat)) {
+                        vkFormat = fallbackFormat;
+                        conversion = VertexStreamConversion::ScaledIntegerToFloat32;
+                        MGLOG_W("Vertex attribute location=%u format=%d lacks "
+                                "VK_FORMAT_FEATURE_VERTEX_BUFFER_BIT; using float32 stream format=%d "
+                                "(type=%s size=%d normalized=%s integer=%s)",
+                                location, static_cast<Int>(sourceVkFormat), static_cast<Int>(vkFormat),
+                                MG_Util::ConvertDataTypeToString(attr.Type).c_str(), attr.Size,
+                                attr.Normalized ? "true" : "false", attr.IsInteger ? "true" : "false");
+                    }
+                }
+
+                if (conversion == VertexStreamConversion::None) {
+                    MGLOG_E("Unsupported Vulkan vertex format (location=%u, format=%d, type=%s, size=%d): "
+                            "VK_FORMAT_FEATURE_VERTEX_BUFFER_BIT is unavailable and no semantic fallback exists",
+                            location, static_cast<Int>(sourceVkFormat),
+                            MG_Util::ConvertDataTypeToString(attr.Type).c_str(), attr.Size);
+                    unsupportedAttribMask |= (1u << location);
+                    continue;
+                }
+            }
+
             const SizeT attribByteSize = GetAttributeByteSize(attr.Type, attr.Size, attr.IsBgra);
             if (attribByteSize == 0) {
                 MGLOG_E("Vertex attribute with unknown component size (location=%u, type=%s): the array is "
@@ -92,8 +153,33 @@ namespace MobileGL::MG_Backend::DirectVulkan {
                 continue;
             }
 
-            const Uint32 stride =
+            const Uint32 sourceStride =
                 attr.Stride > 0 ? static_cast<Uint32>(attr.Stride) : static_cast<Uint32>(attribByteSize);
+            const Bool packedAttribute = attr.Type == DataType::Int2101010Rev ||
+                                         attr.Type == DataType::Uint2101010Rev;
+            const SizeT requiredAlignment = packedAttribute ? attribByteSize : GetComponentSize(attr.Type);
+            // For a client-memory array attr.Offset holds the raw client pointer, and the
+            // draw path re-uploads the data to a 16-aligned transient slice with attribute
+            // offset 0, so only the stride can violate Vulkan's fetch alignment there.
+            const Bool clientMemoryAttribute = attr.Buffer == nullptr;
+            if (conversion == VertexStreamConversion::None && requiredAlignment > 1 &&
+                ((sourceStride % requiredAlignment) != 0 ||
+                 (!clientMemoryAttribute && (attr.Offset % requiredAlignment) != 0))) {
+                // GL accepts arbitrary byte strides and offsets. Core Vulkan vertex fetches do not
+                // unless VK_EXT_legacy_vertex_attributes is available, so deinterleave this one
+                // attribute into a tightly packed transient stream without changing its format.
+                conversion = VertexStreamConversion::Repack;
+                MGLOG_W("Vertex attribute location=%u uses Vulkan-incompatible alignment "
+                        "(offset=%zu stride=%u required=%zu); using a tightly packed stream",
+                        location, attr.Offset, sourceStride, requiredAlignment);
+            }
+
+            Uint32 stride = sourceStride;
+            if (conversion == VertexStreamConversion::Repack) {
+                stride = static_cast<Uint32>(attribByteSize);
+            } else if (conversion == VertexStreamConversion::ScaledIntegerToFloat32) {
+                stride = static_cast<Uint32>(attr.Size * static_cast<Int>(sizeof(Float)));
+            }
             const VkVertexInputRate inputRate =
                 (attr.Divisor == 0) ? VK_VERTEX_INPUT_RATE_VERTEX : VK_VERTEX_INPUT_RATE_INSTANCE;
 
@@ -103,29 +189,102 @@ namespace MobileGL::MG_Backend::DirectVulkan {
             bindingBaseOffsets.push_back(attr.Buffer ? attr.Offset : 0);
             bindingAttributeLocations.push_back(location);
             bindingUsesClientMemory.push_back(attr.Buffer == nullptr);
+            bindingConversions.push_back(conversion);
             builder.AddBinding(binding, stride, inputRate);
             builder.AddAttribute(location, binding, vkFormat, 0);
+            // Divisor 1 is what VK_VERTEX_INPUT_RATE_INSTANCE already means; only anything
+            // else needs the extension to say it.
+            if (inputRate == VK_VERTEX_INPUT_RATE_INSTANCE && attr.Divisor != 1) {
+                bindingDivisors.push_back({binding, static_cast<Uint32>(attr.Divisor)});
+            }
         }
 
         const auto& state = builder.Build();
 
-        auto& entry = m_cache[hash];
+        auto& slot = m_cache[hash];
+        if (!slot) {
+            slot = MakeUnique<BackendVertexInputState>();
+        }
+        BackendVertexInputState& entry = *slot;
         entry.hash = hash;
+        entry.lastUsedFrameBoundary = m_frameBoundaryCounter;
+        entry.bindingDivisors = Move(bindingDivisors);
         entry.bindings = builder.GetBindings();
         entry.attributes = builder.GetAttributes();
+        // See the layoutHash declaration: hash only the resolved layout, never
+        // buffer identities, so identical layouts across VAOs/buffers agree.
+        XXHASH_VERIFY(XXH64_reset(m_hashState, 0));
+        for (const auto& binding : entry.bindings) {
+            XXHASH_VERIFY(XXH64_update(m_hashState, &binding.binding, sizeof(binding.binding)));
+            XXHASH_VERIFY(XXH64_update(m_hashState, &binding.stride, sizeof(binding.stride)));
+            XXHASH_VERIFY(XXH64_update(m_hashState, &binding.inputRate, sizeof(binding.inputRate)));
+        }
+        for (const auto& attribute : entry.attributes) {
+            XXHASH_VERIFY(XXH64_update(m_hashState, &attribute.location, sizeof(attribute.location)));
+            XXHASH_VERIFY(XXH64_update(m_hashState, &attribute.binding, sizeof(attribute.binding)));
+            XXHASH_VERIFY(XXH64_update(m_hashState, &attribute.format, sizeof(attribute.format)));
+            XXHASH_VERIFY(XXH64_update(m_hashState, &attribute.offset, sizeof(attribute.offset)));
+        }
+        for (const auto& divisor : entry.bindingDivisors) {
+            XXHASH_VERIFY(XXH64_update(m_hashState, &divisor.binding, sizeof(divisor.binding)));
+            XXHASH_VERIFY(XXH64_update(m_hashState, &divisor.divisor, sizeof(divisor.divisor)));
+        }
+        XXHASH_VERIFY(XXH64_update(m_hashState, &unsupportedAttribMask, sizeof(unsupportedAttribMask)));
+        entry.layoutHash = XXH64_digest(m_hashState);
+        entry.attributeLocationMask = 0;
+        for (const auto& attribute : entry.attributes) {
+            if (attribute.location < 32u) {
+                entry.attributeLocationMask |= (1u << attribute.location);
+            }
+        }
         entry.bindingBufferKeys = std::move(bindingBufferKeys);
         entry.bindingBaseOffsets = std::move(bindingBaseOffsets);
         entry.bindingAttributeLocations = std::move(bindingAttributeLocations);
         entry.bindingUsesClientMemory = std::move(bindingUsesClientMemory);
+        entry.bindingConversions = std::move(bindingConversions);
         entry.unsupportedAttribMask = unsupportedAttribMask;
         entry.state = state;
         entry.state.pVertexBindingDescriptions = entry.bindings.empty() ? nullptr : entry.bindings.data();
         entry.state.pVertexAttributeDescriptions = entry.attributes.empty() ? nullptr : entry.attributes.data();
+        if (!entry.bindingDivisors.empty()) {
+            entry.divisorState.vertexBindingDivisorCount = static_cast<Uint32>(entry.bindingDivisors.size());
+            entry.divisorState.pVertexBindingDivisors = entry.bindingDivisors.data();
+            entry.state.pNext = &entry.divisorState;
+        } else {
+            entry.state.pNext = nullptr;
+        }
         return entry;
     }
 
+    void VertexInputStateFactory::OnFrameBoundary() {
+        ++m_frameBoundaryCounter;
+
+        // Sweep occasionally; evict entries whose last hit is far in the past.
+        // Erasure happens only here, never mid-frame: the draw path holds a
+        // reference into the current entry across its setup, and unordered_map
+        // erase would invalidate it. Entries are CPU-side only, so no GPU-idle
+        // proof is needed; an evicted entry that is used again is simply rebuilt
+        // from the VAO state (same hash, same content).
+        constexpr Uint64 kSweepInterval = 256;
+        constexpr Uint64 kRetireAgeBoundaries = 1024;
+        if ((m_frameBoundaryCounter % kSweepInterval) != 0) {
+            return;
+        }
+
+        for (auto it = m_cache.begin(); it != m_cache.end();) {
+            if (m_frameBoundaryCounter - it->second->lastUsedFrameBoundary > kRetireAgeBoundaries) {
+                it = m_cache.erase(it);
+                // Invalidate every VAO's state-pointer memo: the erased node's
+                // address may be reused by a future insert.
+                ++m_evictionEpoch;
+            } else {
+                ++it;
+            }
+        }
+    }
+
     VkFormat VertexInputStateFactory::ToVkVertexFormat(DataType type, Int size, Bool normalized, Bool isInteger,
-                                                       Bool isBgra) {
+                                                       Bool isBgra, Bool isLong) {
         if (isBgra) {
             // GL_BGRA: four reversed-order components, always normalized (enforced at validation), only
             // legal with GL_UNSIGNED_BYTE or a 2_10_10_10 type. The reversed VkFormats put the
@@ -150,6 +309,22 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         case DataType::Int2101010Rev:
             if (isInteger || size != 4) return VK_FORMAT_UNDEFINED;
             return normalized ? VK_FORMAT_A2B10G10R10_SNORM_PACK32 : VK_FORMAT_A2B10G10R10_SSCALED_PACK32;
+        case DataType::Float64:
+            // A 64-bit attribute is fetched as its 32-bit word pair and bitcast back to double in the
+            // shader (PackDoubleVertexInputsPass does the shader half). That is bit-exact and, unlike
+            // VK_FORMAT_R64*_SFLOAT, needs no format capability: lavapipe reports bufferFeatures = 0
+            // for every R64 float format, so a native 64-bit vertex fetch is simply unavailable there
+            // while shaderFloat64 is not. Both halves key off nothing but the attribute being long,
+            // so they always agree without extra plumbing.
+            if (!isLong || isInteger || normalized) return VK_FORMAT_UNDEFINED;
+            switch (size) {
+            case 1: return VK_FORMAT_R32G32_UINT;
+            case 2: return VK_FORMAT_R32G32B32A32_UINT;
+            // A dvec3/dvec4 input is 6/8 uint32 components: no single VkFormat, and GL spreads it
+            // over two attribute locations, which the location-per-VAO-index model here does not
+            // express. Declined rather than fetched wrong.
+            default: return VK_FORMAT_UNDEFINED;
+            }
         case DataType::Float32:
             switch (size) {
             case 1: return VK_FORMAT_R32_SFLOAT;
@@ -282,4 +457,47 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         const SizeT componentSize = GetComponentSize(type);
         return componentSize == 0 ? 0 : componentSize * static_cast<SizeT>(size);
     }
+
+    Bool VertexInputStateFactory::IsScaledIntegerVertexFormat(VkFormat format) {
+        switch (format) {
+        case VK_FORMAT_R8_USCALED:
+        case VK_FORMAT_R8_SSCALED:
+        case VK_FORMAT_R8G8_USCALED:
+        case VK_FORMAT_R8G8_SSCALED:
+        case VK_FORMAT_R8G8B8_USCALED:
+        case VK_FORMAT_R8G8B8_SSCALED:
+        case VK_FORMAT_R8G8B8A8_USCALED:
+        case VK_FORMAT_R8G8B8A8_SSCALED:
+        case VK_FORMAT_R16_USCALED:
+        case VK_FORMAT_R16_SSCALED:
+        case VK_FORMAT_R16G16_USCALED:
+        case VK_FORMAT_R16G16_SSCALED:
+        case VK_FORMAT_R16G16B16_USCALED:
+        case VK_FORMAT_R16G16B16_SSCALED:
+        case VK_FORMAT_R16G16B16A16_USCALED:
+        case VK_FORMAT_R16G16B16A16_SSCALED:
+            return true;
+        default:
+            return false;
+        }
+    }
+
+    VkFormat VertexInputStateFactory::ToFloat32VertexFormat(Int componentCount) {
+        switch (componentCount) {
+        case 1: return VK_FORMAT_R32_SFLOAT;
+        case 2: return VK_FORMAT_R32G32_SFLOAT;
+        case 3: return VK_FORMAT_R32G32B32_SFLOAT;
+        case 4: return VK_FORMAT_R32G32B32A32_SFLOAT;
+        default: return VK_FORMAT_UNDEFINED;
+        }
+    }
+
+    Bool VertexInputStateFactory::SupportsVertexBufferFormat(VkFormat format) const {
+        if (m_physicalDevice == VK_NULL_HANDLE || format == VK_FORMAT_UNDEFINED) {
+            return false;
+        }
+        VkFormatProperties properties{};
+        vkGetPhysicalDeviceFormatProperties(m_physicalDevice, format, &properties);
+        return (properties.bufferFeatures & VK_FORMAT_FEATURE_VERTEX_BUFFER_BIT) != 0;
+    }
 } // namespace MobileGL::MG_Backend::DirectVulkan

MobileGL/MG_Backend/DirectVulkan/Renderer/VertexInputStateFactory.h

@@ -19,28 +19,66 @@ namespace MobileGL::MG_Backend::DirectVulkan {
     public:
         using HashType = Uint64;
 
+        enum class VertexStreamConversion : Uint8 {
+            None = 0,
+            Repack,
+            ScaledIntegerToFloat32,
+        };
+
         struct BackendVertexInputState {
             HashType hash = 0;
+            // Hash of the resolved Vulkan vertex layout only (bindings, attributes,
+            // unsupported mask) - NO buffer identities. `hash` mixes each bound
+            // buffer's never-reused LIFETIME ID, so per-chunk VBOs mint a fresh
+            // identity per buffer; keying pipelines on that minted one VkPipeline per
+            // chunk section for an identical layout, defeating pipeline reuse and the
+            // per-draw memo. Pipelines depend only on the layout, so they key on this
+            // instead.
+            HashType layoutHash = 0;
+            // Frame boundary of the last cache hit; entries idle past the
+            // OnFrameBoundary retirement age are evicted (CPU heap only).
+            // Mutable: the VAO's state-pointer memo fast path stamps it through
+            // a const entry reference.
+            mutable Uint64 lastUsedFrameBoundary = 0;
             Vector<VkVertexInputBindingDescription> bindings;
             Vector<VkVertexInputAttributeDescription> attributes;
             Vector<SizeT> bindingBufferKeys;
             Vector<SizeT> bindingBaseOffsets;
             Vector<Uint32> bindingAttributeLocations;
             Vector<Bool> bindingUsesClientMemory;
+            Vector<VertexStreamConversion> bindingConversions;
             // Locations whose array is ENABLED but whose GL format has no VkFormat mapping. They are
             // absent from `attributes`, so without this mask the draw path cannot tell them apart from
             // a genuinely disabled array and would silently feed the shader the current attribute value.
             Uint32 unsupportedAttribMask = 0;
+            // Bitmask of `attributes[i].location` - the draw path needs it up to
+            // three times per draw, so it is baked once at build time.
+            Uint32 attributeLocationMask = 0;
+            // Per-binding glVertexAttribDivisor values other than 1. Vulkan's instance input
+            // rate advances once per instance and nothing else, so anything else has to be
+            // stated through VK_EXT_vertex_attribute_divisor. Empty when every instanced
+            // binding uses divisor 1, which is what the plain input rate already means.
+            Vector<VkVertexInputBindingDivisorDescriptionEXT> bindingDivisors;
+            VkPipelineVertexInputDivisorStateCreateInfoEXT divisorState{
+                VK_STRUCTURE_TYPE_PIPELINE_VERTEX_INPUT_DIVISOR_STATE_CREATE_INFO_EXT
+            };
             VkPipelineVertexInputStateCreateInfo state{
                 VK_STRUCTURE_TYPE_PIPELINE_VERTEX_INPUT_STATE_CREATE_INFO
             };
         };
 
-        explicit VertexInputStateFactory(const VulkanRendererConfig& config):
-            m_config(config) {}
+        VertexInputStateFactory(const VulkanRendererConfig& config, VkPhysicalDevice physicalDevice):
+            m_config(config), m_physicalDevice(physicalDevice) {}
         ~VertexInputStateFactory() = default;
         VertexInputStateFactory(const VertexInputStateFactory&) = delete;
 
+        // The VAO aux-memo payload GetOrCreateVertexInputState(vao) stamps: aux0 is the
+        // entry's layoutHash, aux1 packs (unsupportedAttribMask << 32) | attributeLocationMask.
+        // Readers that find the aux memo valid can use these without resolving the entry.
+        static Uint64 PackVertexInputAuxMasks(Uint32 unsupportedAttribMask, Uint32 attributeLocationMask) {
+            return (static_cast<Uint64>(unsupportedAttribMask) << 32) | attributeLocationMask;
+        }
+
         HashType ComputeHash(const MG_State::GLState::VertexArrayObject& vao) const;
         // Memoized ComputeHash: reuses the VAO's cached hash while its config version
         // is unchanged. Use this on per-draw paths.
@@ -48,6 +86,16 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         const BackendVertexInputState& GetOrCreateVertexInputState(
             const MG_State::GLState::VertexArrayObject& vao, HashType hash);
         const BackendVertexInputState& GetOrCreateVertexInputState(const MG_State::GLState::VertexArrayObject& vao);
+        // Frame boundary hook: ages the cache and evicts entries not hit for many
+        // frames. The key mixes each bound buffer's never-reused lifetime id, so
+        // buffer/VAO churn keeps minting fresh keys - and does so by construction,
+        // not by luck: a recreated buffer can no longer land back on its dead
+        // predecessor's key. Without eviction the map grows for the whole session.
+        // Entries hold no Vulkan handles (pipeline creation copies the descriptions)
+        // and the draw path's entry reference never spans a frame boundary, so
+        // eviction here needs no GPU-idle proof. Self-gated: one counter bump and
+        // compare except on sweep boundaries.
+        void OnFrameBoundary();
         static SizeT GetComponentSize(DataType type);
         // Tightly-packed byte size of one vertex element for this attribute: componentSize * size for
         // normal types, and 4 (one packed word) for the 2_10_10_10 types and GL_BGRA. Returns 0 for
@@ -55,10 +103,27 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         static SizeT GetAttributeByteSize(DataType type, Int size, Bool isBgra);
 
     private:
-        static VkFormat ToVkVertexFormat(DataType type, Int size, Bool normalized, Bool isInteger, Bool isBgra = false);
+        static VkFormat ToVkVertexFormat(DataType type, Int size, Bool normalized, Bool isInteger, Bool isBgra = false,
+                                         Bool isLong = false);
+        static Bool IsScaledIntegerVertexFormat(VkFormat format);
+        static VkFormat ToFloat32VertexFormat(Int componentCount);
+        Bool SupportsVertexBufferFormat(VkFormat format) const;
 
         const VulkanRendererConfig& m_config;
-        UnorderedMap<HashType, BackendVertexInputState> m_cache;
+        VkPhysicalDevice m_physicalDevice = VK_NULL_HANDLE;
+        // Values are heap-allocated: FastSTL::unordered_map is open-addressing,
+        // so INSERT invalidates references to stored values. The draw path (and
+        // the VAOs' state-pointer memos) hold entry pointers across inserts;
+        // only the unique_ptr cell moves, never the pointee.
+        UnorderedMap<HashType, UniquePtr<BackendVertexInputState>> m_cache;
+        // Monotonic frame-boundary counter (bumped in OnFrameBoundary) for cache aging.
+        Uint64 m_frameBoundaryCounter = 0;
+        // Bumped whenever any cache entry is erased. VAOs memo a raw pointer to
+        // their heap-allocated entry (stable across map insert/rehash by
+        // construction); a memo is honored only while its recorded epoch
+        // matches, so an evicted entry can never be dereferenced through a
+        // stale memo.
+        Uint64 m_evictionEpoch = 1;
         static inline XXH64_state_t* m_hashState = XXH64_createState();
     };
 } // namespace MobileGL::MG_Backend::DirectVulkan

MobileGL/MG_Backend/DirectVulkan/Renderer/VkBufferManager.cpp

@@ -7,6 +7,8 @@
 // End of Source File Header
 
 #include "VkBufferManager.h"
+#include "../DirectVulkan.h"
+#include "VulkanRenderer.h"
 
 namespace MobileGL::MG_Backend::DirectVulkan {
     namespace {
@@ -22,6 +24,10 @@ namespace MobileGL::MG_Backend::DirectVulkan {
             VK_BUFFER_USAGE_UNIFORM_BUFFER_BIT | VK_BUFFER_USAGE_STORAGE_BUFFER_BIT |
             VK_BUFFER_USAGE_INDIRECT_BUFFER_BIT | VK_BUFFER_USAGE_UNIFORM_TEXEL_BUFFER_BIT |
             VK_BUFFER_USAGE_TRANSFER_SRC_BIT;
+        // Appended to kPersistentBackedUsage when VK_EXT_transform_feedback is enabled
+        // (see VkBufferManagerInitInfo::transformFeedbackUsageEnabled).
+        constexpr VkBufferUsageFlags kTransformFeedbackUsage =
+            VK_BUFFER_USAGE_TRANSFORM_FEEDBACK_BUFFER_BIT_EXT;
         // The app writes into the persistent map with no explicit flush, so its memory must
         // be host-coherent (Adreno host-visible memory is; requiring it keeps us portable).
         constexpr VkMemoryPropertyFlags kPersistentBackedRequiredFlags =
@@ -53,6 +59,18 @@ namespace MobileGL::MG_Backend::DirectVulkan {
             }
         }
 
+        // The CPU is about to read a buffer a shader wrote. Its bytes live in coherent
+        // host-visible GPU storage (EnsureGpuResidentStorage adopts it when the buffer is
+        // bound as a shader storage buffer), so nothing needs copying - but coherence only
+        // says the writes are visible once they have happened, so the work has to retire
+        // first.
+        void Ops_ReadbackFromGpu(BufferObject& bufferObject) {
+            (void)bufferObject;
+            if (pVulkanRenderer) {
+                pVulkanRenderer->FinishPendingGpuWork();
+            }
+        }
+
         void* Ops_AcquirePersistentMap(BufferObject& bufferObject) {
             if (g_activeBufferManager) {
                 return g_activeBufferManager->AcquirePersistentMap(bufferObject);
@@ -76,6 +94,7 @@ namespace MobileGL::MG_Backend::DirectVulkan {
             .FlushMappedRange = Ops_FlushMappedRange,
             .OnDestroy = Ops_OnDestroy,
             .AcquirePersistentMap = Ops_AcquirePersistentMap,
+            .ReadbackFromGpu = Ops_ReadbackFromGpu,
         };
     } // namespace
 
@@ -141,6 +160,15 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         m_transientUploadArena.BeginFrame(frameIndex);
     }
 
+    void VkBufferManager::CollectAllDeferredReleases() {
+        for (Uint32 frameIndex = 0; frameIndex < m_deferredBufferReleases.size(); ++frameIndex) {
+            CollectDeferredReleases(frameIndex);
+        }
+        for (Uint32 frameIndex = 0; frameIndex < m_transientUploadArena.GetFrameCount(); ++frameIndex) {
+            m_transientUploadArena.CollectDeferredReleases(frameIndex);
+        }
+    }
+
     void VkBufferManager::NotifyDeviceIdle() {
         // Everything submitted so far has completed. Work recorded for the
         // current frame has not been submitted yet, so the current serial
@@ -197,21 +225,32 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         return static_cast<VkBufferResource*>(bufferObject.GetBackendResource().get());
     }
 
-    SharedPtr<VkBufferResource> VkBufferManager::GetOrCreateResource(
+    VkBufferResource* VkBufferManager::GetOrCreateResource(
         const SharedPtr<MG_State::GLState::BufferObject>& bufferObject) {
-        auto existing = std::static_pointer_cast<VkBufferResource>(bufferObject->GetBackendResource());
+        // Return by raw pointer: the resource is owned for its whole lifetime by the BufferObject's
+        // backend-resource SharedPtr (already set, or set below), so callers that only dereference
+        // it avoid a static_pointer_cast + SharedPtr refcount inc/dec on every per-draw buffer bind.
+        const auto& existing = bufferObject->GetBackendResource();
         if (existing) {
-            return existing;
+            return static_cast<VkBufferResource*>(existing.get());
         }
         auto resource = MakeShared<VkBufferResource>();
+        VkBufferResource* raw = resource.get();
         bufferObject->SetBackendResource(resource);
         TrackLiveResource(resource);
-        return resource;
+        return raw;
     }
 
     void VkBufferManager::TrackLiveResource(const SharedPtr<VkBufferResource>& resource) {
-        if (m_liveResources.size() >= kLiveResourcePruneThreshold) {
+        // Sweep on a doubling watermark rather than on every insert past the threshold. The old
+        // form walked the whole vector for each new buffer once the list passed 256, and when the
+        // buffers are all live the walk removes nothing and the list grows by one - so creating N
+        // live buffers cost ~N^2/2 expired() checks. Reclamation semantics are unchanged: the sweep
+        // still removes exactly the expired entries, just less often and with the same bound on how
+        // much dead weight can accumulate (at most as many entries as were live at the last sweep).
+        if (m_liveResources.size() >= std::max<SizeT>(kLiveResourcePruneThreshold, 2 * m_liveResourcesLastPruned)) {
             std::erase_if(m_liveResources, [](const WeakPtr<VkBufferResource>& weak) { return weak.expired(); });
+            m_liveResourcesLastPruned = m_liveResources.size();
         }
         m_liveResources.push_back(resource);
     }
@@ -219,6 +258,7 @@ namespace MobileGL::MG_Backend::DirectVulkan {
     void VkBufferManager::ReleaseAllLiveResources() {
         for (auto& weak : m_liveResources) {
             if (auto resource = weak.lock()) {
+                BumpSliceEpoch(*resource);
                 resource->buffer.Destroy();
                 resource->storageSize = 0;
                 resource->usageFlags = 0;
@@ -233,6 +273,9 @@ namespace MobileGL::MG_Backend::DirectVulkan {
 
     Bool VkBufferManager::CreateResidentStorage(VkBufferResource& resource, VkDeviceSize size,
                                                 VkBufferUsageFlags usage, VkMemoryPropertyFlags requiredFlags) {
+        // The only place a resident VkBuffer handle is minted, so every resident slice
+        // change funnels through here (callers release the old handle first).
+        BumpSliceEpoch(resource);
         // Staged range copies write resident storage with vkCmdCopyBuffer.
         usage |= VK_BUFFER_USAGE_TRANSFER_DST_BIT;
         const Bool created = resource.buffer.Create({
@@ -319,6 +362,10 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         if (!resource) {
             return; // lazy: AcquireResidentSlice performs a full upload on creation
         }
+        // A respecify can change the size, the usage hint (so the resident/streamed
+        // route), and the contents at once; retire every memo before deciding what to
+        // do about the storage.
+        BumpSliceEpoch(*resource);
         // Any cached streaming slice refers to the previous contents.
         resource->transientFrameSerial = 0;
         if (!resource->buffer.IsValid()) {
@@ -351,6 +398,9 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         if (!resource) {
             return;
         }
+        // Drops the streaming memo below and may end in a storage swap or a deferred
+        // full re-upload, so no memoised slice survives this.
+        BumpSliceEpoch(*resource);
         resource->transientFrameSerial = 0;
         if (!resource->buffer.IsValid() || resource->pendingFullUpload) {
             return;
@@ -383,6 +433,7 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         if (!resource) {
             return;
         }
+        BumpSliceEpoch(*resource);
         resource->transientFrameSerial = 0;
         if (!resource->buffer.IsValid() || resource->pendingFullUpload) {
             return;
@@ -442,6 +493,13 @@ namespace MobileGL::MG_Backend::DirectVulkan {
             TrackLiveResource(resource);
         }
 
+        // Bumped for the request, not just for the storage it may create. This is the
+        // one call the frontend makes when a buffer becomes persistently mapped for
+        // writing (BufferObject::AcquireMemoryRange), and a map the backend declines
+        // keeps mutating its shadow with no further API call - so it is what lets
+        // GetSliceEpochCounter stand for "no buffer needs a persistent-map range push".
+        BumpSliceEpoch(*resource);
+
         // Idempotent: an already-backed buffer returns the same mapped base.
         if (resource->persistentMapped && resource->buffer.IsValid() && resource->storageSize == size) {
             return resource->buffer.GetMappedData();
@@ -452,7 +510,10 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         // it from the current shadow - MappedData() is still the shadow here because the
         // frontend adopts (and drops) the shadow only after this returns.
         DeferRelease(std::move(resource->buffer));
-        if (!CreateResidentStorage(*resource, size, kPersistentBackedUsage, kPersistentBackedRequiredFlags)) {
+        const VkBufferUsageFlags persistentUsage =
+            kPersistentBackedUsage |
+            (m_initInfo.transformFeedbackUsageEnabled ? kTransformFeedbackUsage : 0);
+        if (!CreateResidentStorage(*resource, size, persistentUsage, kPersistentBackedRequiredFlags)) {
             resource->persistentMapped = false;
             resource->storageSize = 0;
             resource->usageFlags = 0;
@@ -526,6 +587,16 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         auto resource = GetOrCreateResource(bufferObject);
         bufferObject->SyncPersistentMappedRange();
 
+        // A persistently mapped resource's storage IS the application's copy of the bytes -
+        // the frontend adopted it in place of the shadow and hands out pointers into it, and
+        // a shader can have written bytes the shadow never saw (a transform feedback
+        // capture). Streaming a second copy would feed this draw the stale shadow, and the
+        // downgrade below would release the storage the application still points at,
+        // breaking the "never recreated" promise AcquirePersistentMap makes.
+        if (resource->persistentMapped) {
+            return AcquireResidentSlice(kind, bufferObject, outSlice);
+        }
+
         const VkDeviceSize size = static_cast<VkDeviceSize>(bufferObject->GetSize());
         if (size == 0) {
             MGLOG_E("VkBufferManager::AcquireStreamedSlice failed: buffer size is zero");
@@ -539,6 +610,41 @@ namespace MobileGL::MG_Backend::DirectVulkan {
             return true;
         }
 
+        // Idle-content promotion: see the field comments in VkBufferResource. The
+        // streak counts frame BOUNDARIES survived unchanged (the same-frame memo
+        // above swallows repeat draws), so a promotion needs the content stable
+        // for kStreamedPromotionStreak whole frames - one no-op frame does not
+        // trigger the resident round-trip, whose creation upload is itself a
+        // staged copy worth avoiding for content that is about to change again.
+        constexpr Uint32 kStreamedPromotionStreak = 2;
+        if (resource->promotedResident) {
+            if (resource->promotedChangeSerial == changeSerial &&
+                static_cast<VkDeviceSize>(bufferObject->GetSize()) == size) {
+                return AcquireResidentSlice(kind, bufferObject, outSlice);
+            }
+            resource->promotedResident = false;
+            resource->unchangedStreak = 0;
+        } else if (resource->transientChangeSerial == changeSerial && resource->transientSize == size &&
+                   resource->transientFrameSerial != 0) {
+            if (++resource->unchangedStreak >= kStreamedPromotionStreak) {
+                // Promotion moves the buffer off the arena and onto resident storage.
+                resource->promotedResident = true;
+                resource->promotedChangeSerial = changeSerial;
+                BumpSliceEpoch(*resource);
+                if (AcquireResidentSlice(kind, bufferObject, outSlice)) {
+                    return true;
+                }
+                resource->promotedResident = false; // resident creation failed: stream as before
+            }
+        } else {
+            resource->unchangedStreak = 0;
+        }
+
+        // A fresh arena allocation: a different slice than the last call handed back,
+        // and (below) the point where a promoted buffer's resident storage is released.
+        // The stable-promotion exit above returns before this, so a buffer the app has
+        // stopped touching keeps one slice for as long as it keeps its resident storage.
+        BumpSliceEpoch(*resource);
         if (!m_transientUploadArena.Upload(m_currentFrameIndex, bufferObject->MappedData(), size, 16,
                                            outSlice)) {
             return false;

MobileGL/MG_Backend/DirectVulkan/Renderer/VkBufferManager.h

@@ -31,6 +31,9 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         VmaMemoryUsage transientMemoryUsage = VMA_MEMORY_USAGE_AUTO;
         VmaAllocationCreateFlags transientAllocationFlags = VMA_ALLOCATION_CREATE_HOST_ACCESS_SEQUENTIAL_WRITE_BIT;
         Bool transientPersistentMapping = false;
+        // VK_EXT_transform_feedback is enabled: persistent-map storage additionally
+        // carries the transform feedback usage so capture targets can bind directly.
+        Bool transformFeedbackUsageEnabled = false;
     };
 
     // The DirectVulkan storage behind one frontend buffer (pipe_resource analogue).
@@ -54,11 +57,33 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         // never orphaned or recreated. Draw-time acquire binds it directly, no re-upload.
         Bool persistentMapped = false;
 
+        // Bumped from a manager-wide counter every time anything that decides which
+        // BufferSlice an Acquire*Slice call hands back changes: storage created or
+        // released, a full re-upload becoming due, a promotion/demotion between
+        // resident and streamed storage, or a new per-frame arena slice. Callers that
+        // memoise a resolved slice compare this to prove the memo still describes the
+        // buffer. The counter is manager-wide (never per-resource) so a freshly
+        // created resource - including one that replaces a destroyed resource at the
+        // same address - can never reproduce a value some memo already holds. 0 means
+        // "no slice has ever been handed out", which no memo can match.
+        Uint64 sliceEpoch = 0;
+
         // Cached transient (streaming) slice for the current frame.
         BufferSlice transientSlice{};
         Uint64 transientFrameSerial = 0;
         Uint64 transientChangeSerial = 0;
         VkDeviceSize transientSize = 0;
+
+        // Streaming re-copies the whole store into the per-frame arena on every
+        // frame, which is right for genuinely per-frame data but pure waste for a
+        // Dynamic-hinted buffer the app stopped touching. After the content
+        // survives kStreamedPromotionStreak frame boundaries unchanged it is
+        // promoted to resident storage (one final upload, then zero per-frame
+        // cost); the first content change demotes it back to streaming, and the
+        // streaming path's existing downgrade releases the resident store.
+        Uint32 unchangedStreak = 0;
+        Bool promotedResident = false;
+        Uint64 promotedChangeSerial = 0;
     };
 
     // Supplies a command buffer that is recording and outside any render pass,
@@ -77,6 +102,11 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         // Recreate all per-frame transient arenas
         Bool RecreateTransientArenas(Uint32 frameCount);
         void BeginFrame(Uint32 frameIndex);
+        // Drains every frame slot's deferred buffer/resource releases (and the
+        // transient arena's parked superseded blocks). Only valid when the
+        // caller has proven every queue submission complete; used by the
+        // present-less frame-boundary drain.
+        void CollectAllDeferredReleases();
         // All previously submitted GPU work has completed (vkDeviceWaitIdle).
         void NotifyDeviceIdle();
         // A frame slot's submission fence has been waited: every serial up to
@@ -113,6 +143,11 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         void OnResourceDestroyed(SharedPtr<MG_State::GLState::BackendBufferResource>&& resource);
 
         Uint64 GetFrameSerial() const { return m_frameSerial; }
+        // Highest value handed to any VkBufferResource::sliceEpoch. Unchanged since a
+        // memo was taken means no buffer this manager owns changed which slice it hands
+        // back, and none was persistently mapped, in between - so a memo of resolved
+        // slices needs no per-buffer re-check. See AcquirePersistentMap for the mapping half.
+        Uint64 GetSliceEpochCounter() const { return m_sliceEpochCounter; }
         // Highest frame serial whose GPU work is known complete; serials at or
         // below it may be considered signaled. Drives IsResourceBusy and the
         // backend GL fence objects.
@@ -124,7 +159,7 @@ namespace MobileGL::MG_Backend::DirectVulkan {
     private:
         Bool InitializeTransientArenas();
         static VkBufferUsageFlags GetVkBufferUsage(BufferKind kind);
-        SharedPtr<VkBufferResource> GetOrCreateResource(const SharedPtr<MG_State::GLState::BufferObject>& bufferObject);
+        VkBufferResource* GetOrCreateResource(const SharedPtr<MG_State::GLState::BufferObject>& bufferObject);
         static VkBufferResource* ResourceOf(MG_State::GLState::BufferObject& bufferObject);
         Bool CreateResidentStorage(VkBufferResource& resource, VkDeviceSize size, VkBufferUsageFlags usage,
                                    VkMemoryPropertyFlags requiredFlags = 0);
@@ -139,6 +174,8 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         void DestroyAllDeferredReleases();
         void TrackLiveResource(const SharedPtr<VkBufferResource>& resource);
         void ReleaseAllLiveResources();
+        // See VkBufferResource::sliceEpoch.
+        void BumpSliceEpoch(VkBufferResource& resource) { resource.sliceEpoch = ++m_sliceEpochCounter; }
 
         VkBufferManagerInitInfo m_initInfo{};
         BufferArena m_transientUploadArena;
@@ -146,8 +183,14 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         Vector<Vector<VkBufferObject>> m_deferredBufferReleases;
         Vector<Vector<SharedPtr<VkBufferResource>>> m_deferredResourceReleases;
         Vector<WeakPtr<VkBufferResource>> m_liveResources;
+    // Size m_liveResources had just after the last sweep; the next sweep waits for it to double.
+    SizeT m_liveResourcesLastPruned = 0;
         Uint32 m_currentFrameIndex = 0;
         Uint64 m_frameSerial = 1;
         Uint64 m_completedSerialFloor = 0;
+        // Never reset (not even by Shutdown): a value handed to a resource must stay
+        // unique for the process, or a memo taken before a re-initialize could match
+        // a different resource's state after it.
+        Uint64 m_sliceEpochCounter = 0;
     };
 } // namespace MobileGL::MG_Backend::DirectVulkan

MobileGL/MG_Backend/DirectVulkan/Renderer/VkBufferObject.cpp

@@ -157,16 +157,23 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         return true;
     }
 
-    BufferSlice VkBufferObject::GetSlice(VkDeviceSize offset, VkDeviceSize size) const {
-        MOBILEGL_ASSERT(offset <= m_size, "VkBufferObject::GetSlice offset out of range");
-        const VkDeviceSize resolvedSize = (size == VK_WHOLE_SIZE) ? (m_size - offset) : size;
-        MOBILEGL_ASSERT(offset + resolvedSize <= m_size, "VkBufferObject::GetSlice range out of bounds");
+    Bool VkBufferObject::Invalidate(VkDeviceSize size, VkDeviceSize offset) {
+        MOBILEGL_ASSERT(IsValid(), "VkBufferObject::Invalidate called on invalid buffer");
+        MOBILEGL_ASSERT(IsMapped(), "VkBufferObject::Invalidate requires mapped memory");
+        MOBILEGL_ASSERT(offset <= m_size, "VkBufferObject::Invalidate offset out of range");
 
-        BufferSlice slice{};
-        slice.buffer = m_buffer;
-        slice.offset = offset;
-        slice.size = resolvedSize;
-        slice.mapped = (m_mappedData != nullptr) ? static_cast<Uint8*>(m_mappedData) + offset : nullptr;
-        return slice;
+        const VkDeviceSize resolvedSize = size == VK_WHOLE_SIZE ? m_size - offset : size;
+        MOBILEGL_ASSERT(offset + resolvedSize <= m_size, "VkBufferObject::Invalidate range out of bounds");
+        if (resolvedSize == 0) {
+            return true;
+        }
+
+        const VkResult result = vmaInvalidateAllocation(m_allocator, m_allocation, offset, resolvedSize);
+        if (result != VK_SUCCESS) {
+            MGLOG_E("VkBufferObject::Invalidate failed: vmaInvalidateAllocation returned %d", result);
+            return false;
+        }
+        return true;
     }
+
 } // namespace MobileGL::MG_Backend::DirectVulkan

MobileGL/MG_Backend/DirectVulkan/Renderer/VkBufferObject.h

@@ -44,10 +44,24 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         void* Map();
         void Unmap();
         Bool Upload(const void* data, VkDeviceSize size, VkDeviceSize offset = 0);
+        Bool Invalidate(VkDeviceSize size = VK_WHOLE_SIZE, VkDeviceSize offset = 0);
 
         VkBuffer GetHandle() const { return m_buffer; }
         VkDeviceSize GetSize() const { return m_size; }
-        BufferSlice GetSlice(VkDeviceSize offset = 0, VkDeviceSize size = VK_WHOLE_SIZE) const;
+        // Inline: runs on the per-draw acquire path (a resident buffer bind is a
+        // GetSlice per binding), where an out-of-line call was measurable.
+        BufferSlice GetSlice(VkDeviceSize offset = 0, VkDeviceSize size = VK_WHOLE_SIZE) const {
+            MOBILEGL_ASSERT(offset <= m_size, "VkBufferObject::GetSlice offset out of range");
+            const VkDeviceSize resolvedSize = (size == VK_WHOLE_SIZE) ? (m_size - offset) : size;
+            MOBILEGL_ASSERT(offset + resolvedSize <= m_size, "VkBufferObject::GetSlice range out of bounds");
+
+            BufferSlice slice{};
+            slice.buffer = m_buffer;
+            slice.offset = offset;
+            slice.size = resolvedSize;
+            slice.mapped = (m_mappedData != nullptr) ? static_cast<Uint8*>(m_mappedData) + offset : nullptr;
+            return slice;
+        }
         void* GetMappedData() const { return m_mappedData; }
         Bool IsMapped() const { return m_mappedData != nullptr; }
         Bool IsValid() const { return m_allocator != nullptr && m_buffer != VK_NULL_HANDLE && m_allocation != nullptr; }

MobileGL/MG_Backend/DirectVulkan/Renderer/VkClearManager.cpp

@@ -8,15 +8,75 @@
 
 #include "VkClearManager.h"
 
+#include "MG_State/GLState/Core.h"
 #include "MG_Util/Converters/MGToStr/FramebufferEnumConverter.h"
 #include "MG_Util/Converters/MGToStr/TextureEnumConverter.h"
 
+#include <algorithm>
+#include <cmath>
+
 namespace MobileGL::MG_Backend::DirectVulkan {
     static Bool IsCubeMapFaceUploadTarget(TextureUploadTarget target) {
         return target >= TextureUploadTarget::CubeMapPositiveX &&
                target <= TextureUploadTarget::CubeMapNegativeZ;
     }
 
+    VkClearColorValue MakeVkClearColorValue(const ClearAttachmentPayload& payload, Bool formatLacksAlpha) {
+        VkClearColorValue clearValue{};
+        switch (payload.colorEncoding) {
+        case ClearColorEncoding::Int:
+            clearValue.int32[0] = payload.colorInt.x();
+            clearValue.int32[1] = payload.colorInt.y();
+            clearValue.int32[2] = payload.colorInt.z();
+            clearValue.int32[3] = formatLacksAlpha ? 1 : payload.colorInt.w();
+            break;
+        case ClearColorEncoding::Uint:
+            clearValue.uint32[0] = payload.colorUint.x();
+            clearValue.uint32[1] = payload.colorUint.y();
+            clearValue.uint32[2] = payload.colorUint.z();
+            clearValue.uint32[3] = formatLacksAlpha ? 1u : payload.colorUint.w();
+            break;
+        case ClearColorEncoding::Float:
+            clearValue.float32[0] = payload.color.x();
+            clearValue.float32[1] = payload.color.y();
+            clearValue.float32[2] = payload.color.z();
+            clearValue.float32[3] = formatLacksAlpha ? 1.0f : payload.color.w();
+            break;
+        }
+        return clearValue;
+    }
+
+    void PreCompensateSrgbClearColor(ClearAttachmentPayload& payload, VkFormat destinationFormat) {
+        if (payload.colorEncoding != ClearColorEncoding::Float) return;
+        // With GL_FRAMEBUFFER_SRGB enabled GL performs the encoding itself, so the driver doing it
+        // is exactly right and there is nothing to undo.
+        if (MG_State::pGLContext->IsCapabilityEnabled(MobileGL::CapabilityInput::FramebufferSrgb)) return;
+        if (ResolveSrgbAttachmentWriteFormat(destinationFormat, false) == destinationFormat) return;
+
+        // sRGB -> linear (GL 4.6 core 8.24), applied to the colour channels only: alpha is stored
+        // linearly in an sRGB format and must pass through untouched.
+        const auto toLinear = [](Float encoded) {
+            const Float value = std::clamp(encoded, 0.0f, 1.0f);
+            return value <= 0.04045f ? value / 12.92f : std::pow((value + 0.055f) / 1.055f, 2.4f);
+        };
+        payload.color = FloatVec4(toLinear(payload.color.x()), toLinear(payload.color.y()),
+                                  toLinear(payload.color.z()), payload.color.w());
+    }
+
+    void ForceOpaqueClearAlpha(ClearAttachmentPayload& payload) {
+        switch (payload.colorEncoding) {
+        case ClearColorEncoding::Int:
+            payload.colorInt = IntVec4(payload.colorInt.x(), payload.colorInt.y(), payload.colorInt.z(), 1);
+            break;
+        case ClearColorEncoding::Uint:
+            payload.colorUint = UintVec4(payload.colorUint.x(), payload.colorUint.y(), payload.colorUint.z(), 1u);
+            break;
+        case ClearColorEncoding::Float:
+            payload.color = FloatVec4(payload.color.x(), payload.color.y(), payload.color.z(), 1.0f);
+            break;
+        }
+    }
+
     static Bool PendingClearMatchesTextureIdentity(const PendingClearKey& key, const TextureIdentity& identity) {
         return key.texture == identity.texture && key.textureLifetimeId == identity.lifetimeId;
     }
@@ -93,6 +153,7 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         const std::lock_guard<std::mutex> lock(m_mutex);
         m_pendingClears.clear();
         m_aliveObjects.clear();
+        m_pendingCount.store(static_cast<Uint32>(m_pendingClears.size()), std::memory_order_relaxed);
     }
 
     TextureIdentity VkClearManager::MakeTextureIdentity(MG_State::GLState::ITextureObject* texture) {
@@ -127,6 +188,7 @@ namespace MobileGL::MG_Backend::DirectVulkan {
             m_pendingClears.erase(key);
         }
         m_aliveObjects.erase(identity);
+        m_pendingCount.store(static_cast<Uint32>(m_pendingClears.size()), std::memory_order_relaxed);
     }
 
     Bool VkClearManager::LockTextureIdentityLocked(const TextureIdentity& identity,
@@ -221,6 +283,7 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         m_aliveObjects[MakeTextureIdentity(texture.get())] = texture;
         auto& pending = m_pendingClears[key];
         MergeClearPayload(pending, clearPayload);
+        m_pendingCount.store(static_cast<Uint32>(m_pendingClears.size()), std::memory_order_relaxed);
     }
 
     void VkClearManager::QueueClear(const ClearAttachmentPayload& clearPayload,
@@ -238,6 +301,7 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         m_aliveObjects[MakeTextureIdentity(texture.get())] = texture;
         auto& pending = m_pendingClears[key];
         MergeClearPayload(pending, clearPayload);
+        m_pendingCount.store(static_cast<Uint32>(m_pendingClears.size()), std::memory_order_relaxed);
     }
 
     Bool VkClearManager::HasPendingClear(MG_State::GLState::ITextureObject* texture) {
@@ -245,6 +309,10 @@ namespace MobileGL::MG_Backend::DirectVulkan {
             return false;
         }
 
+        if (m_pendingCount.load(std::memory_order_relaxed) == 0) {
+            return false;  // per-draw hot path: nothing pending anywhere
+        }
+
         const Uint64 lifetimeId = texture->GetLifetimeId();
         const std::lock_guard<std::mutex> lock(m_mutex);
         for (auto it = m_pendingClears.begin(); it != m_pendingClears.end(); ++it) {
@@ -260,6 +328,9 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         if (key.texture == nullptr) {
             return false;
         }
+        if (m_pendingCount.load(std::memory_order_relaxed) == 0) {
+            return false;  // per-draw hot path: nothing pending anywhere
+        }
 
         const std::lock_guard<std::mutex> lock(m_mutex);
         if (m_pendingClears.find(key) == m_pendingClears.end()) {
@@ -287,6 +358,9 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         if (key.texture == nullptr) {
             return false;
         }
+        if (m_pendingCount.load(std::memory_order_relaxed) == 0) {
+            return false;  // per-draw hot path: nothing pending anywhere
+        }
 
         const std::lock_guard<std::mutex> lock(m_mutex);
         if (!LockTextureLocked(key, outTexture)) {
@@ -325,6 +399,9 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         if (texture == nullptr) {
             return false;
         }
+        if (m_pendingCount.load(std::memory_order_relaxed) == 0) {
+            return false;  // per-draw hot path: nothing pending anywhere
+        }
 
         const Uint64 lifetimeId = texture->GetLifetimeId();
         const std::lock_guard<std::mutex> lock(m_mutex);
@@ -345,6 +422,9 @@ namespace MobileGL::MG_Backend::DirectVulkan {
             return;
         }
 
+        if (m_pendingCount.load(std::memory_order_relaxed) == 0) {
+            return;  // per-draw hot path: nothing pending anywhere
+        }
         const TextureIdentity identity = MakeTextureIdentity(texture);
         MGLOG_D("%s: Pop all pending clears for texture %d", __func__, texture->GetExternalIndex());
         const std::lock_guard<std::mutex> lock(m_mutex);
@@ -361,6 +441,7 @@ namespace MobileGL::MG_Backend::DirectVulkan {
             auto it = m_pendingClears.find(key);
             if (it != m_pendingClears.end()) {
                 m_pendingClears.erase(it);
+            m_pendingCount.store(static_cast<Uint32>(m_pendingClears.size()), std::memory_order_relaxed);
             }
         }
 

MobileGL/MG_Backend/DirectVulkan/Renderer/VkClearManager.h

@@ -14,6 +14,7 @@
 #include "MG_Util/Math/VectorTypes.h"
 
 #include <Includes.h>
+#include <atomic>
 #include <unordered_map>
 
 namespace MobileGL::MG_Backend::DirectVulkan {
@@ -23,13 +24,41 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         Uint32 stencil{};
     };
 
+    // A colour clear reaches us from one of glClear/ClearBufferfv, ClearBufferiv or
+    // ClearBufferuiv, and Vulkan reads VkClearColorValue's union according to the destination
+    // image's format rather than converting between the members - a float written where an
+    // integer format is expected is reinterpreted bit for bit, not rounded. Remember which entry
+    // point supplied the value so the member written when the clear is materialized matches.
+    enum class ClearColorEncoding : Uint8 { Float, Int, Uint };
+
     struct ClearAttachmentPayload {
         GLbitfield mask = 0;
         FloatVec4 color = FloatVec4(0.0f, 0.0f, 0.0f, 0.0f);
+        ClearColorEncoding colorEncoding = ClearColorEncoding::Float;
+        IntVec4 colorInt = IntVec4(0, 0, 0, 0);
+        UintVec4 colorUint = UintVec4(0u, 0u, 0u, 0u);
         Float depth = 1.0f;
         Uint32 stencil = 0;
     };
 
+    // Builds the clear value for `payload` in the union member its encoding calls for.
+    // `formatLacksAlpha` applies GL's rule that a format without an alpha channel reads as one,
+    // expressed in whichever type matches (GL 4.6 core 15.2.3).
+    VkClearColorValue MakeVkClearColorValue(const ClearAttachmentPayload& payload, Bool formatLacksAlpha);
+
+    // Applies that same rule in place, for the paths that have to bake it into the payload before
+    // the destination is known.
+    void ForceOpaqueClearAlpha(ClearAttachmentPayload& payload);
+
+    // vkCmdClearColorImage names the image, so the driver applies the destination format's transfer
+    // function to whatever value it is handed. Every other write path in this backend goes through
+    // the UNORM twin view while GL_FRAMEBUFFER_SRGB is off (ResolveSrgbAttachmentWriteFormat) and
+    // therefore stores the raw value GL asked for. Rewrites `payload` to the linear colour whose
+    // encoding is that raw value, so a direct image clear of an sRGB destination agrees with them.
+    // A no-op for every other format, for integer clear encodings, and when GL is doing the
+    // encoding itself.
+    void PreCompensateSrgbClearColor(ClearAttachmentPayload& payload, VkFormat destinationFormat);
+
     struct PendingClearKey {
         MG_State::GLState::ITextureObject* texture = nullptr;
         Uint64 textureLifetimeId = 0;
@@ -120,7 +149,19 @@ namespace MobileGL::MG_Backend::DirectVulkan {
                                SharedPtr<MG_State::GLState::ITextureObject>& outTexture);
 
         Uint8 m_gcCounter = 0;
+    public:
+        // Lock-free probe for the consecutive-draw fast path: any pending clear
+        // forces the full SetupDraw path (which materializes/consumes it).
+        Bool HasAnyPendingClears() const { return m_pendingCount.load(std::memory_order_relaxed) != 0; }
+
+    private:
         mutable std::mutex m_mutex;
+        // Lock-free mirror of m_pendingClears.size(), maintained under m_mutex
+        // by every mutation. The per-draw probes (HasPendingClear/GetPending*)
+        // read it before taking the lock: during draw batches the pending set
+        // is almost always empty, so this turns several locked map probes per
+        // draw into one relaxed load.
+        std::atomic<Uint32> m_pendingCount{0};
         std::unordered_map<PendingClearKey, ClearAttachmentPayload, PendingClearKeyHash> m_pendingClears;
         std::unordered_map<TextureIdentity, WeakPtr<MG_State::GLState::ITextureObject>, TextureIdentityHash> m_aliveObjects;
     };

MobileGL/MG_Backend/DirectVulkan/Renderer/VkRenderPassManager.cpp

@@ -16,31 +16,21 @@
 
 namespace MobileGL::MG_Backend::DirectVulkan {
     static Bool TryResolveSampleCountFlagBits(Int requestedSamples, VkSampleCountFlagBits& outSampleCount) {
-        switch (requestedSamples <= 0 ? 1 : requestedSamples) {
-        case 1:
+        // GL promises "at least the requested samples", so a non-power-of-two
+        // request (legal in GL, e.g. 3) rounds up to the next Vulkan bit.
+        if (requestedSamples <= 1) {
             outSampleCount = VK_SAMPLE_COUNT_1_BIT;
             return true;
-        case 2:
-            outSampleCount = VK_SAMPLE_COUNT_2_BIT;
-            return true;
-        case 4:
-            outSampleCount = VK_SAMPLE_COUNT_4_BIT;
-            return true;
-        case 8:
-            outSampleCount = VK_SAMPLE_COUNT_8_BIT;
-            return true;
-        case 16:
-            outSampleCount = VK_SAMPLE_COUNT_16_BIT;
-            return true;
-        case 32:
-            outSampleCount = VK_SAMPLE_COUNT_32_BIT;
-            return true;
-        case 64:
-            outSampleCount = VK_SAMPLE_COUNT_64_BIT;
-            return true;
-        default:
+        }
+        if (requestedSamples > 64) {
             return false;
         }
+        Uint32 bit = 1;
+        while (bit < static_cast<Uint32>(requestedSamples)) {
+            bit <<= 1;
+        }
+        outSampleCount = static_cast<VkSampleCountFlagBits>(bit);
+        return true;
     }
 
     static VkImageAspectFlags ResolveImageAspectMaskForFormat(VkFormat format) {
@@ -60,7 +50,11 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         }
     }
 
-    static Float ResolveColorClearAlpha(const MG_State::GLState::ITextureObject* texture, Float requestedAlpha) {
+    static Bool ColorFormatLacksAlpha(const MG_State::GLState::ITextureObject* texture) {
+        return texture != nullptr && MG_Util::GetBaseInternalFormatComponentCount(texture->GetFormat()) == 3;
+    }
+
+    [[maybe_unused]] static Float ResolveColorClearAlpha(const MG_State::GLState::ITextureObject* texture, Float requestedAlpha) {
         if (texture != nullptr && MG_Util::GetBaseInternalFormatComponentCount(texture->GetFormat()) == 3) {
             return 1.0f;
         }
@@ -93,9 +87,20 @@ namespace MobileGL::MG_Backend::DirectVulkan {
     static VkImageViewType ResolveAttachmentViewType(
         const MG_State::GLState::FramebufferAttachmentObject& attachment,
         const VkTextureManager::TextureResource& resource) {
-        return !attachment.IsLayered() && IsCubeMapFaceUploadTarget(attachment.GetTextureUploadTarget()) ?
-            VK_IMAGE_VIEW_TYPE_2D :
-            resource.viewType;
+        if (attachment.IsLayered()) {
+            return resource.viewType;
+        }
+        // A non-layered attachment names ONE layer, so the view over it is a plain 2D view whatever
+        // the image's own view type is. The cube-face upload targets always meant this; a cube map
+        // array attached through glFramebufferTextureLayer means it too, and a CUBE_ARRAY view over
+        // a single layer is not a legal attachment. The CUBE arm is inert today - no frontend path
+        // produces a non-layered cube attachment without a face upload target - and is kept for
+        // symmetry with CUBE_ARRAY.
+        if (IsCubeMapFaceUploadTarget(attachment.GetTextureUploadTarget()) ||
+            resource.viewType == VK_IMAGE_VIEW_TYPE_CUBE_ARRAY || resource.viewType == VK_IMAGE_VIEW_TYPE_CUBE) {
+            return VK_IMAGE_VIEW_TYPE_2D;
+        }
+        return resource.viewType;
     }
 
     static MG_State::GLState::ITextureObject* ResolveCompleteColorAttachmentTexture(
@@ -166,6 +171,9 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         if (view != VK_NULL_HANDLE) {
             vkDestroyImageView(device, view, nullptr);
         }
+        if (unormTwinView != VK_NULL_HANDLE) {
+            vkDestroyImageView(device, unormTwinView, nullptr);
+        }
         if (image != VK_NULL_HANDLE && allocation != nullptr) {
             vmaDestroyImage(allocator, image, allocation);
         }
@@ -173,6 +181,7 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         image = VK_NULL_HANDLE;
         allocation = nullptr;
         view = VK_NULL_HANDLE;
+        unormTwinView = VK_NULL_HANDLE;
         layout = VK_IMAGE_LAYOUT_UNDEFINED;
         format = VK_FORMAT_UNDEFINED;
         aspect = VK_IMAGE_ASPECT_NONE;
@@ -180,6 +189,7 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         sampleCount = VK_SAMPLE_COUNT_1_BIT;
         internalFormat = TextureInternalFormat::Unknown;
         samples = 0;
+        deadSinceFrame = kNeverObservedDead;
     }
 
     VkRenderPassManager::VkRenderPassManager(VkDevice device,
@@ -206,6 +216,7 @@ namespace MobileGL::MG_Backend::DirectVulkan {
             resource.Destroy(m_device, m_allocator);
         }
         m_renderbufferResources.clear();
+        CollectDeferredRenderbufferReleases(/*destroyAll=*/true); // caller guarantees device idle
         m_pendingRenderbufferClears.clear();
         RenderPassEntry::s_textureResourcesScratch.clear();
         s_activeRenderPass = {};
@@ -213,22 +224,80 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         m_rpFastValid = false;
     }
 
-    void VkRenderPassManager::CollectRenderbufferGarbage() {
-        Vector<MG_State::GLState::RenderbufferObject*> deadRenderbuffers;
-        deadRenderbuffers.reserve(m_renderbufferResources.size());
-        for (auto& [renderbuffer, resource] : m_renderbufferResources) {
-            const auto liveRenderbuffer = resource.renderbuffer.lock();
-            if (!liveRenderbuffer || liveRenderbuffer.get() != renderbuffer) {
-                deadRenderbuffers.emplace_back(renderbuffer);
-            }
+    Uint64 VkRenderPassManager::RetireAgeFrames() const {
+        // MaxFramesInFlight + 2 covers the frame ring plus one boundary for the
+        // recording-to-submit gap and one because OnPresent runs ahead of Present's
+        // fence wait; the floor of 8 keeps a margin over the default ring of 3 while
+        // still releasing multi-MB attachment memory promptly (the render-pass cache's
+        // 1024-frame retirement would pin it for no additional safety).
+        return std::max<Uint64>(8, static_cast<Uint64>(m_config.MaxFramesInFlight) + 2);
+    }
+
+    void VkRenderPassManager::DeferRenderbufferBackingRelease(RenderbufferResource& resource) {
+        // The superseded backing may still be referenced by in-flight command buffers
+        // (glRenderbufferStorage can respecify a renderbuffer drawn this very frame),
+        // so it is parked and destroyed only after RetireAgeFrames() boundaries.
+        if (resource.image == VK_NULL_HANDLE && resource.view == VK_NULL_HANDLE) {
+            return;
         }
-        for (auto* renderbuffer : deadRenderbuffers) {
-            auto resourceIt = m_renderbufferResources.find(renderbuffer);
-            if (resourceIt != m_renderbufferResources.end()) {
-                resourceIt->second.Destroy(m_device, m_allocator);
-                m_renderbufferResources.erase(resourceIt);
+        m_deferredRenderbufferReleases.push_back(
+            {resource.image, resource.allocation, resource.view, resource.unormTwinView, m_frameCounter});
+        resource.image = VK_NULL_HANDLE;
+        resource.allocation = nullptr;
+        resource.view = VK_NULL_HANDLE;
+        resource.unormTwinView = VK_NULL_HANDLE;
+    }
+
+    void VkRenderPassManager::CollectDeferredRenderbufferReleases(Bool destroyAll) {
+        if (m_deferredRenderbufferReleases.empty()) {
+            return;
+        }
+        const Uint64 retireAgeFrames = RetireAgeFrames();
+        std::erase_if(m_deferredRenderbufferReleases, [&](DeferredRenderbufferRelease& release) {
+            if (!destroyAll && m_frameCounter - release.deferredAtFrame < retireAgeFrames) {
+                return false;
             }
-            m_pendingRenderbufferClears.erase(renderbuffer);
+            if (release.view != VK_NULL_HANDLE) {
+                vkDestroyImageView(m_device, release.view, nullptr);
+            }
+            if (release.unormTwinView != VK_NULL_HANDLE) {
+                vkDestroyImageView(m_device, release.unormTwinView, nullptr);
+            }
+            if (release.image != VK_NULL_HANDLE) {
+                vmaDestroyImage(m_allocator, release.image, release.allocation);
+            }
+            return true;
+        });
+    }
+
+    void VkRenderPassManager::CollectRenderbufferGarbage() {
+        // Two-phase reclamation: a dead renderbuffer's VkImage may still be referenced by
+        // command buffers submitted up to frames-in-flight frames ago (it was legally
+        // attached and drawn right up to its deletion), so the first observation of an
+        // expired weak reference only stamps the current frame counter; Destroy runs once
+        // enough frame boundaries have passed that the stamping frame's submission fence
+        // has provably been waited (see RetireAgeFrames).
+        const Uint64 retireAgeFrames = RetireAgeFrames();
+        for (auto it = m_renderbufferResources.begin(); it != m_renderbufferResources.end();) {
+            auto& resource = it->second;
+            const auto liveRenderbuffer = resource.renderbuffer.lock();
+            if (liveRenderbuffer && liveRenderbuffer.get() == it->first) {
+                resource.deadSinceFrame = RenderbufferResource::kNeverObservedDead;
+                ++it;
+                continue;
+            }
+            if (resource.deadSinceFrame == RenderbufferResource::kNeverObservedDead) {
+                resource.deadSinceFrame = m_frameCounter;
+                ++it;
+                continue;
+            }
+            if (m_frameCounter - resource.deadSinceFrame < retireAgeFrames) {
+                ++it;
+                continue;
+            }
+            m_pendingRenderbufferClears.erase(it->first);
+            resource.Destroy(m_device, m_allocator);
+            it = m_renderbufferResources.erase(it);
         }
     }
 
@@ -249,12 +318,94 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         }
 
         const auto internalFormat = renderbuffer->GetInternalFormat();
-        const VkFormat format = MG_Util::ConvertTextureInternalFormatToVkEnum(internalFormat);
+        // Three-channel color formats widen to their RGBA twin exactly like textures do
+        // (VkTextureManager::ResolveTextureFormatInfo): blits/resolves between a
+        // renderbuffer and a texture of the same GL format then see one VkFormat.
+        const VkFormat format = [&]() -> VkFormat {
+            switch (internalFormat) {
+            case TextureInternalFormat::RGB:
+            case TextureInternalFormat::RGB8:
+            case TextureInternalFormat::R3G3B2:
+            case TextureInternalFormat::RGB4:
+            case TextureInternalFormat::RGB5:
+                return VK_FORMAT_R8G8B8A8_UNORM;
+            case TextureInternalFormat::SRGB8:
+                return VK_FORMAT_R8G8B8A8_SRGB;
+            case TextureInternalFormat::RGB8Snorm:
+                return VK_FORMAT_R8G8B8A8_SNORM;
+            case TextureInternalFormat::RGB10:
+            case TextureInternalFormat::RGB12:
+            case TextureInternalFormat::RGB16:
+                return VK_FORMAT_R16G16B16A16_UNORM;
+            case TextureInternalFormat::RGB16Snorm:
+                return VK_FORMAT_R16G16B16A16_SNORM;
+            case TextureInternalFormat::RGB16F:
+                return VK_FORMAT_R16G16B16A16_SFLOAT;
+            case TextureInternalFormat::RGB32F:
+                return VK_FORMAT_R32G32B32A32_SFLOAT;
+            case TextureInternalFormat::RGB8I:
+                return VK_FORMAT_R8G8B8A8_SINT;
+            case TextureInternalFormat::RGB8UI:
+                return VK_FORMAT_R8G8B8A8_UINT;
+            case TextureInternalFormat::RGB16I:
+                return VK_FORMAT_R16G16B16A16_SINT;
+            case TextureInternalFormat::RGB16UI:
+                return VK_FORMAT_R16G16B16A16_UINT;
+            case TextureInternalFormat::RGB32I:
+                return VK_FORMAT_R32G32B32A32_SINT;
+            case TextureInternalFormat::RGB32UI:
+                return VK_FORMAT_R32G32B32A32_UINT;
+            default:
+                return MG_Util::ConvertTextureInternalFormatToVkEnum(internalFormat);
+            }
+        }();
         const VkImageAspectFlags aspect = ResolveImageAspectMaskForFormat(format);
-        if ((aspect & VK_IMAGE_ASPECT_COLOR_BIT) != 0) {
-            MGLOG_E("GetOrCreateRenderbufferResource: color renderbuffer %u is not supported by DirectVulkan render passes yet",
-                    renderbuffer->GetExternalIndex());
-            return nullptr;
+        // Renderbuffers are never sampled (GL has no way to bind one to a sampler), so the
+        // usage set is attachment + transfer: transfer covers readback (vkCmdCopyImageToBuffer),
+        // BlitFramebuffer, CopyTexImage sources, and out-of-render-pass clear materialization.
+        const VkImageUsageFlags imageUsage =
+            ((aspect & VK_IMAGE_ASPECT_COLOR_BIT) != 0 ? VK_IMAGE_USAGE_COLOR_ATTACHMENT_BIT
+                                                       : VK_IMAGE_USAGE_DEPTH_STENCIL_ATTACHMENT_BIT) |
+            VK_IMAGE_USAGE_TRANSFER_SRC_BIT | VK_IMAGE_USAGE_TRANSFER_DST_BIT;
+
+        // GL allows the implementation to allocate more samples than requested
+        // (glRenderbufferStorageMultisample only promises "at least"), and devices
+        // like llvmpipe expose 1x/4x but not 2x. Round the request up to the
+        // nearest supported count for this format.
+        if (renderbuffer->GetSamples() > 0) {
+            auto supportedIt = m_attachmentSampleCountsByFormat.find(format);
+            if (supportedIt == m_attachmentSampleCountsByFormat.end()) {
+                VkImageFormatProperties formatProperties{};
+                VkSampleCountFlags supported = VK_SAMPLE_COUNT_1_BIT;
+                if (vkGetPhysicalDeviceImageFormatProperties(m_physicalDevice, format, VK_IMAGE_TYPE_2D,
+                                                             VK_IMAGE_TILING_OPTIMAL, imageUsage, 0,
+                                                             &formatProperties) == VK_SUCCESS) {
+                    supported = formatProperties.sampleCounts;
+                }
+                supportedIt = m_attachmentSampleCountsByFormat.emplace(format, supported).first;
+            }
+            const VkSampleCountFlags supported = supportedIt->second;
+            if ((supported & sampleCount) == 0) {
+                // Smallest supported count above the request, else the largest below it.
+                Uint32 rounded = 0;
+                for (Uint32 bit = static_cast<Uint32>(sampleCount) << 1; bit <= VK_SAMPLE_COUNT_64_BIT; bit <<= 1) {
+                    if ((supported & bit) != 0) {
+                        rounded = bit;
+                        break;
+                    }
+                }
+                if (rounded == 0) {
+                    for (Uint32 bit = static_cast<Uint32>(sampleCount) >> 1; bit != 0; bit >>= 1) {
+                        if ((supported & bit) != 0) {
+                            rounded = bit;
+                            break;
+                        }
+                    }
+                }
+                if (rounded != 0) {
+                    sampleCount = static_cast<VkSampleCountFlagBits>(rounded);
+                }
+            }
         }
 
         auto& resource = m_renderbufferResources[renderbuffer.get()];
@@ -268,9 +419,15 @@ namespace MobileGL::MG_Backend::DirectVulkan {
             resource.samples != renderbuffer->GetSamples();
         if (!needsCreate) {
             resource.renderbuffer = renderbuffer;
+            // A new renderbuffer at a recycled address may adopt a compatible entry that
+            // was already stamped dead; it is alive again, so cancel the aging.
+            resource.deadSinceFrame = RenderbufferResource::kNeverObservedDead;
             return &resource;
         }
 
+        // Respecify: park the old backing for aged destruction instead of destroying
+        // inline - it may still be referenced by in-flight command buffers.
+        DeferRenderbufferBackingRelease(resource);
         resource.Destroy(m_device, m_allocator);
         resource.renderbuffer = renderbuffer;
 
@@ -285,9 +442,15 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         imageInfo.format = format;
         imageInfo.tiling = VK_IMAGE_TILING_OPTIMAL;
         imageInfo.initialLayout = VK_IMAGE_LAYOUT_UNDEFINED;
-        imageInfo.usage = VK_IMAGE_USAGE_DEPTH_STENCIL_ATTACHMENT_BIT;
+        imageInfo.usage = imageUsage;
         imageInfo.samples = sampleCount;
         imageInfo.sharingMode = VK_SHARING_MODE_EXCLUSIVE;
+        // sRGB renderbuffers attach through their UNORM twin while GL_FRAMEBUFFER_SRGB
+        // is disabled, which needs a format-reinterpreting second view.
+        const Bool hasUnormTwin = ResolveSrgbAttachmentWriteFormat(format, false) != format;
+        if (hasUnormTwin) {
+            imageInfo.flags |= VK_IMAGE_CREATE_MUTABLE_FORMAT_BIT;
+        }
 
         VkImageFormatProperties imageFormatProperties{};
         const VkResult imageFormatResult = vkGetPhysicalDeviceImageFormatProperties(
@@ -322,6 +485,11 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         viewInfo.subresourceRange.layerCount = 1;
         VK_VERIFY(vkCreateImageView(m_device, &viewInfo, nullptr, &resource.view),
                   "vkCreateImageView(renderbuffer)");
+        if (hasUnormTwin) {
+            viewInfo.format = ResolveSrgbAttachmentWriteFormat(format, false);
+            VK_VERIFY(vkCreateImageView(m_device, &viewInfo, nullptr, &resource.unormTwinView),
+                      "vkCreateImageView(renderbuffer unorm twin)");
+        }
 
         resource.layout = VK_IMAGE_LAYOUT_UNDEFINED;
         resource.format = format;
@@ -373,7 +541,13 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         pending.renderbuffer = renderbuffer;
         pending.payload.mask |= clearPayload.mask;
         if ((clearPayload.mask & GL_COLOR_BUFFER_BIT) != 0) {
+            // The whole colour description, not just the float vector: an integer clear keeps its
+            // value in colorInt/colorUint, and dropping the encoding here would leave the pending
+            // clear reading as an all-zero float one.
             pending.payload.color = clearPayload.color;
+            pending.payload.colorEncoding = clearPayload.colorEncoding;
+            pending.payload.colorInt = clearPayload.colorInt;
+            pending.payload.colorUint = clearPayload.colorUint;
         }
         if ((clearPayload.mask & GL_DEPTH_BUFFER_BIT) != 0) {
             pending.payload.depth = clearPayload.depth;
@@ -386,6 +560,18 @@ namespace MobileGL::MG_Backend::DirectVulkan {
     void VkRenderPassManager::QueueRenderbufferClear(
         GLbitfield mask, const ClearFramebufferPayload& clearPayload,
         const MG_State::GLState::FramebufferObject& drawFbo) {
+        if ((mask & GL_COLOR_BUFFER_BIT) != 0) {
+            // Color renderbuffer draw buffers take the framebuffer-level clear too; texture
+            // attachments are skipped by the per-attachment overload's IsRenderbuffer guard.
+            for (const auto attachmentType : drawFbo.GetDrawBuffers()) {
+                if (attachmentType == FramebufferAttachmentType::None) {
+                    continue;
+                }
+                QueueRenderbufferClear(
+                    ClearAttachmentPayload{.mask = GL_COLOR_BUFFER_BIT, .color = clearPayload.color},
+                    drawFbo.GetAttachment(attachmentType));
+            }
+        }
         if ((mask & GL_DEPTH_BUFFER_BIT) != 0) {
             QueueRenderbufferClear(
                 ClearAttachmentPayload{.mask = GL_DEPTH_BUFFER_BIT, .depth = clearPayload.depth},
@@ -406,12 +592,18 @@ namespace MobileGL::MG_Backend::DirectVulkan {
     }
 
     VkRenderPassManager::HashType VkRenderPassManager::ComputeHash(
-        const MG_State::GLState::FramebufferObject& fbo, Uint32 swapchainImageIndex, Bool includePendingClear) {
+        const MG_State::GLState::FramebufferObject& fbo, Uint32 swapchainImageIndex, Bool includePendingClear,
+        Bool includeDefaultFboDepthStencil) {
         XXHASH_VERIFY(XXH64_reset(m_hashState, m_config.CacheVersion));
         const Bool isDefaultFbo = fbo.IsDefaultFramebuffer();
         if (isDefaultFbo) {
             XXHASH_VERIFY(XXH64_update(m_hashState, &swapchainImageIndex, sizeof(swapchainImageIndex)));
         }
+        // sRGB attachments switch between their sRGB and UNORM-twin views with this
+        // capability (ResolveSrgbAttachmentWriteFormat), changing the render pass formats.
+        const Bool framebufferSrgbEnabled =
+            MG_State::pGLContext->IsCapabilityEnabled(MobileGL::CapabilityInput::FramebufferSrgb);
+        XXHASH_VERIFY(XXH64_update(m_hashState, &framebufferSrgbEnabled, sizeof(framebufferSrgbEnabled)));
         auto& drawBuffers = fbo.GetDrawBuffers();
         XXHASH_VERIFY(XXH64_update(m_hashState, drawBuffers.data(), drawBuffers.size() * sizeof(drawBuffers[0])));
         auto readBuffer = fbo.GetReadBuffer();
@@ -485,9 +677,17 @@ namespace MobileGL::MG_Backend::DirectVulkan {
                          attachment <= FramebufferAttachmentType::BackRight);
                     if (isDefaultColorAttachment) {
                         currentLayout = m_swapchainObject.GetImageLayout(swapchainImageIndex);
+                        // Content validity feeds the attachment's loadOp (see the
+                        // creation path), so it must key the cache as well.
+                        if (!m_swapchainObject.IsImageContentDefined(swapchainImageIndex)) {
+                            currentLayout = VK_IMAGE_LAYOUT_UNDEFINED;
+                        }
                     } else if (attachment == FramebufferAttachmentType::Depth ||
                                attachment == FramebufferAttachmentType::Stencil) {
                         currentLayout = m_swapchainObject.GetDepthStencilImageLayout(swapchainImageIndex);
+                        if (!m_swapchainObject.IsDepthStencilContentDefined(swapchainImageIndex)) {
+                            currentLayout = VK_IMAGE_LAYOUT_UNDEFINED;
+                        }
                     }
                 } else {
                     auto* textureResource = m_textureManager.SyncTextureAndGetDescriptor(*texture);
@@ -542,14 +742,49 @@ namespace MobileGL::MG_Backend::DirectVulkan {
             combineFramebufferAttachmentObjHash(drawbuf);
         }
 
-        combineFramebufferAttachmentObjHash(FramebufferAttachmentType::Depth);
-        combineFramebufferAttachmentObjHash(FramebufferAttachmentType::Stencil);
+        // The depth-less default-FBO flavor omits the depth/stencil attachment
+        // entirely, so it must hash differently from the depth-full flavor.
+        const Bool depthStencilIncluded = !isDefaultFbo || includeDefaultFboDepthStencil;
+        XXHASH_VERIFY(XXH64_update(m_hashState, &depthStencilIncluded, sizeof(depthStencilIncluded)));
+        if (depthStencilIncluded) {
+            combineFramebufferAttachmentObjHash(FramebufferAttachmentType::Depth);
+            combineFramebufferAttachmentObjHash(FramebufferAttachmentType::Stencil);
+        }
 
         return XXH64_digest(m_hashState);
     }
 
     RenderPassEntry& VkRenderPassManager::GetOrCreateRenderPass(const MG_State::GLState::FramebufferObject& fbo,
-                                                                Uint32 swapchainImageIndex) {
+                                                                Uint32 swapchainImageIndex,
+                                                                Bool drawUsesDepthStencil) {
+        // Resolve the default-FBO depth flavor (see the header comment): keep the
+        // depth attachment when the caller needs it, when a depth/stencil clear is
+        // pending, or when the active pass already carries it (escalate-only, so
+        // alternating depth-less draws never split an established depth pass).
+        Bool includeDefaultFboDepthStencil = true;
+        if (fbo.IsDefaultFramebuffer()) {
+            Bool activeDefaultHasDepthStencil = false;
+            if (const auto* active = GetActiveRenderPass()) {
+                Bool activeIsSwapchainPass = false;
+                Bool activeHasSwapchainDepthStencil = false;
+                for (const auto& tracked : active->trackedAttachmentLayouts) {
+                    activeIsSwapchainPass |= tracked.target == TrackedAttachmentTarget::SwapchainColor;
+                    activeHasSwapchainDepthStencil |=
+                        tracked.target == TrackedAttachmentTarget::SwapchainDepthStencil;
+                }
+                activeDefaultHasDepthStencil = activeIsSwapchainPass && activeHasSwapchainDepthStencil;
+            }
+            const auto& defaultDepthAtt = fbo.GetAttachment(FramebufferAttachmentType::Depth);
+            const auto& defaultStencilAtt = fbo.GetAttachment(FramebufferAttachmentType::Stencil);
+            const Bool pendingDepthStencilClear =
+                (defaultDepthAtt.IsTexture() && m_clearManager.HasPendingClear(defaultDepthAtt)) ||
+                HasPendingRenderbufferClear(defaultDepthAtt) ||
+                (defaultStencilAtt.IsTexture() && m_clearManager.HasPendingClear(defaultStencilAtt)) ||
+                HasPendingRenderbufferClear(defaultStencilAtt);
+            includeDefaultFboDepthStencil =
+                drawUsesDepthStencil || activeDefaultHasDepthStencil || pendingDepthStencilClear;
+        }
+
         auto hasPendingClearOnFramebuffer = [&]() -> Bool {
             const auto& drawBuffers = fbo.GetDrawBuffers();
             for (auto attachment : drawBuffers) {
@@ -599,14 +834,16 @@ namespace MobileGL::MG_Backend::DirectVulkan {
             m_rpFastFboVersion == fbo.GetObjectVersion() && m_rpFastSwapchainIndex == swapchainImageIndex &&
             m_rpFastTexEpoch == m_textureManager.GetTextureImageEpoch() &&
             m_rpFastRbEpoch == m_renderbufferImageEpoch &&
+            (!fbo.IsDefaultFramebuffer() || m_rpFastHadDepthStencil == includeDefaultFboDepthStencil) &&
             m_rpFastRenderPassHash == activeRenderPass->hash && !hasPendingClearOnFramebuffer()) {
             auto activeIt = m_renderPasses.find(activeRenderPass->hash);
             if (activeIt != m_renderPasses.end()) {
+                activeIt->second.lastUsedFrame = m_frameCounter;
                 return activeIt->second;
             }
         }
 
-        auto compatibilityHash = ComputeHash(fbo, swapchainImageIndex, false);
+        auto compatibilityHash = ComputeHash(fbo, swapchainImageIndex, false, includeDefaultFboDepthStencil);
         if (activeRenderPass != nullptr &&
             activeRenderPass->CompatibleWith(compatibilityHash) &&
             !hasPendingClearOnFramebuffer()) {
@@ -623,12 +860,16 @@ namespace MobileGL::MG_Backend::DirectVulkan {
             m_rpFastTexEpoch = m_textureManager.GetTextureImageEpoch();
             m_rpFastRbEpoch = m_renderbufferImageEpoch;
             m_rpFastRenderPassHash = activeRenderPass->hash;
+            m_rpFastHadDepthStencil = activeIt->second.hasDepthStencilAttachment;
+            activeIt->second.lastUsedFrame = m_frameCounter;
             return activeIt->second;
         }
-        auto hash = ComputeHash(fbo, swapchainImageIndex, true);
+        auto hash = ComputeHash(fbo, swapchainImageIndex, true, includeDefaultFboDepthStencil);
         auto it = m_renderPasses.find(hash);
-        if (it != m_renderPasses.end())
+        if (it != m_renderPasses.end()) {
+            it->second.lastUsedFrame = m_frameCounter;
             return it->second;
+        }
 
         Bool isDefaultFbo = fbo.IsDefaultFramebuffer();
         // Color attachment
@@ -678,6 +919,86 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         // assuming default FBO has the right param
         for (Uint32 i = 0; i < colorAttachmentSlotCount; ++i) {
             auto drawbuf = drawbufs[i];
+
+            // Renderbuffer color attachments mirror the texture path below, with the
+            // resource (image/view/format/layout) coming from the render-pass manager's
+            // renderbuffer store instead of the texture manager.
+            if (drawbuf != FramebufferAttachmentType::None && !isDefaultFbo) {
+                const auto& rbAtt = fbo.GetAttachment(drawbuf);
+                if (rbAtt.IsRenderbuffer() && rbAtt.IsComplete()) {
+                    const auto& renderbuffer = rbAtt.GetRenderbuffer();
+                    auto* rbResource = GetOrCreateRenderbufferResource(renderbuffer);
+                    if (rbResource == nullptr || (rbResource->aspect & VK_IMAGE_ASPECT_COLOR_BIT) == 0) {
+                        MGLOG_E("GetOrCreateRenderPass: draw buffer slot %u on FBO %u has an unsupported color "
+                                "renderbuffer %u; using VK_ATTACHMENT_UNUSED",
+                                i, fbo.GetExternalIndex(), renderbuffer->GetExternalIndex());
+                        continue;
+                    }
+
+                    const Uint32 rbAttachmentIndex = static_cast<Uint32>(attachmentDescriptions.size());
+                    attachmentDescriptions.emplace_back();
+                    VkAttachmentDescription& rbDesc = attachmentDescriptions.back();
+
+                    ClearAttachmentPayload rbClearPayload{};
+                    Bool rbHasClear = GetPendingRenderbufferClear(renderbuffer.get(), rbClearPayload) &&
+                                      (rbClearPayload.mask & GL_COLOR_BUFFER_BIT) != 0;
+                    if (rbHasClear &&
+                        MG_Util::GetBaseInternalFormatComponentCount(renderbuffer->GetInternalFormat()) == 3) {
+                        // RGB renderbuffers are backed by an RGBA image; the missing alpha reads as 1.
+                        ForceOpaqueClearAlpha(rbClearPayload);
+                    }
+
+                    const VkImageLayout trackedRbLayout = rbResource->layout;
+                    const Bool rbFramebufferSrgb =
+                        MG_State::pGLContext->IsCapabilityEnabled(MobileGL::CapabilityInput::FramebufferSrgb);
+                    const VkFormat rbAttachmentFormat =
+                        ResolveSrgbAttachmentWriteFormat(rbResource->format, rbFramebufferSrgb);
+                    rbDesc.flags = 0;
+                    rbDesc.format = rbAttachmentFormat;
+                    rbDesc.samples = rbResource->sampleCount;
+                    rbDesc.loadOp = rbHasClear ? VK_ATTACHMENT_LOAD_OP_CLEAR :
+                                    (trackedRbLayout == VK_IMAGE_LAYOUT_UNDEFINED ? VK_ATTACHMENT_LOAD_OP_DONT_CARE
+                                                                                  : VK_ATTACHMENT_LOAD_OP_LOAD);
+                    rbDesc.storeOp = VK_ATTACHMENT_STORE_OP_STORE;
+                    rbDesc.stencilLoadOp = VK_ATTACHMENT_LOAD_OP_DONT_CARE;
+                    rbDesc.stencilStoreOp = VK_ATTACHMENT_STORE_OP_DONT_CARE;
+                    rbDesc.initialLayout = (rbHasClear || trackedRbLayout == VK_IMAGE_LAYOUT_UNDEFINED) ?
+                        VK_IMAGE_LAYOUT_UNDEFINED : trackedRbLayout;
+                    rbDesc.finalLayout = VK_IMAGE_LAYOUT_COLOR_ATTACHMENT_OPTIMAL;
+                    adoptRenderPassSampleCount(rbResource->sampleCount, "color",
+                                               static_cast<Int>(renderbuffer->GetExternalIndex()));
+
+                    if (rbHasClear) {
+                        pendingClearAttachments.emplace_back(PendingClearAttachmentInfo {
+                            .attachmentIndex = rbAttachmentIndex,
+                            .colorAttachmentSlot = i,
+                            .renderbuffer = renderbuffer.get(),
+                            .hasInlinePayload = true,
+                            .inlinePayload = rbClearPayload,
+                        });
+                    }
+
+                    if (width == 0)
+                        width = static_cast<Int>(rbResource->extent.width);
+                    if (height == 0)
+                        height = static_cast<Int>(rbResource->extent.height);
+
+                    trackedAttachmentLayouts.emplace_back(TrackedAttachmentLayoutInfo {
+                        .target = TrackedAttachmentTarget::Renderbuffer,
+                        .renderbuffer = renderbuffer,
+                        .finalLayout = rbDesc.finalLayout,
+                    });
+                    textureResources.emplace_back(nullptr);
+                    attachmentViews.emplace_back(rbAttachmentFormat != rbResource->format ? rbResource->unormTwinView
+                                                                                          : rbResource->view);
+                    MOBILEGL_ASSERT(attachmentViews.back() != VK_NULL_HANDLE,
+                                    "GetOrCreateRenderPass: renderbuffer view missing at color attachment %d", i);
+
+                    colorAttachmentRefs[i].attachment = rbAttachmentIndex;
+                    continue;
+                }
+            }
+
             auto* texture = ResolveCompleteColorAttachmentTexture(fbo, drawbuf, i);
             if (texture == nullptr)
                 continue;
@@ -696,6 +1017,10 @@ namespace MobileGL::MG_Backend::DirectVulkan {
                 case TextureTarget::Texture2D:
                 case TextureTarget::Texture2DArray:
                 case TextureTarget::Texture2DMultisample:
+                case TextureTarget::Texture2DMultisampleArray:
+                case TextureTarget::Texture3D:
+                case TextureTarget::TextureCubeMap:
+                case TextureTarget::TextureCubeMapArray:
                 case TextureTarget::TextureRectangle: {
                     desc.flags = 0;
                     desc.format = isDefaultFbo ?
@@ -718,6 +1043,7 @@ namespace MobileGL::MG_Backend::DirectVulkan {
                     if (hasClear) {
                         pendingClearAttachments.emplace_back(PendingClearAttachmentInfo {
                             .attachmentIndex = attachmentIndex,
+                            .colorAttachmentSlot = i,
                             .key = VkClearManager::MakePendingClearKey(att)
                         });
                     }
@@ -733,6 +1059,13 @@ namespace MobileGL::MG_Backend::DirectVulkan {
                         MOBILEGL_ASSERT(swapchainImageIndex < swapchainViews.size(),
                                         "GetOrCreateRenderPass: swapchain image index out of range");
                         trackedColorLayout = m_swapchainObject.GetImageLayout(swapchainImageIndex);
+                        // EGL: a presented color buffer's content is undefined when its
+                        // image comes back around (EGL_BUFFER_DESTROYED, the default
+                        // swap behaviour) - skip the tile load instead of reloading
+                        // stale pixels nobody may rely on.
+                        if (!hasClear && !m_swapchainObject.IsImageContentDefined(swapchainImageIndex)) {
+                            trackedColorLayout = VK_IMAGE_LAYOUT_UNDEFINED;
+                        }
                         trackedAttachmentLayouts.emplace_back(TrackedAttachmentLayoutInfo {
                             .target = TrackedAttachmentTarget::SwapchainColor,
                             .swapchainImageIndex = swapchainImageIndex,
@@ -746,12 +1079,15 @@ namespace MobileGL::MG_Backend::DirectVulkan {
                         MOBILEGL_ASSERT(textureResource,
                                         "GetOrCreateRenderPass: SyncTextureAndGetDescriptor failed at color attachment %d", i);
                         textureResources.emplace_back(textureResource);
-                        desc.format = textureResource->format;
+                        desc.format = ResolveSrgbAttachmentWriteFormat(
+                            textureResource->format,
+                            MG_State::pGLContext->IsCapabilityEnabled(MobileGL::CapabilityInput::FramebufferSrgb));
                         attachmentSampleCount = textureResource->sampleCount;
                         trackedColorLayout = textureResource->layout;
                         trackedAttachmentLayouts.emplace_back(TrackedAttachmentLayoutInfo {
                             .target = TrackedAttachmentTarget::Texture,
                             .texture = att.GetTexture(),
+                            .textureRaw = att.GetTexture().get(),
                             .textureMipLevel = attachmentMipLevel,
                             .finalLayout = desc.finalLayout,
                         });
@@ -815,6 +1151,12 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         };
         const auto* selectedDepthStencilAttachment = isUsableDepthStencilAttachment(depthAtt) ? &depthAtt :
                                                      (isUsableDepthStencilAttachment(stencilAtt) ? &stencilAtt : nullptr);
+        // Depth-less default-FBO flavor: nothing in this pass touches depth/stencil
+        // and their content is undefined anyway (EGL swap), so drop the attachment
+        // and its whole tile load + store.
+        if (isDefaultFbo && !includeDefaultFboDepthStencil) {
+            selectedDepthStencilAttachment = nullptr;
+        }
         const Bool hasDistinctDepthAndStencilAttachments =
             isUsableDepthStencilAttachment(depthAtt) && isUsableDepthStencilAttachment(stencilAtt) &&
             !sameDepthStencilAttachmentObject(depthAtt, stencilAtt);
@@ -833,6 +1175,12 @@ namespace MobileGL::MG_Backend::DirectVulkan {
             VkImageLayout trackedDepthLayout = isDefaultFbo ?
                 m_swapchainObject.GetDepthStencilImageLayout(swapchainImageIndex) :
                 VK_IMAGE_LAYOUT_DEPTH_STENCIL_ATTACHMENT_OPTIMAL;
+            // EGL 1.5 §3.10.1: every ancillary (depth/stencil) buffer's content is
+            // undefined after a swap, so the first default-FBO pass of a frame can
+            // skip the depth/stencil tile load outright.
+            if (isDefaultFbo && !m_swapchainObject.IsDepthStencilContentDefined(swapchainImageIndex)) {
+                trackedDepthLayout = VK_IMAGE_LAYOUT_UNDEFINED;
+            }
             depthAttachmentDescription.flags = 0;
             VkSampleCountFlagBits depthAttachmentSampleCount = VK_SAMPLE_COUNT_1_BIT;
             Int depthAttachmentId = 0;
@@ -916,6 +1264,7 @@ namespace MobileGL::MG_Backend::DirectVulkan {
                 trackedAttachmentLayouts.emplace_back(TrackedAttachmentLayoutInfo {
                     .target = TrackedAttachmentTarget::Texture,
                     .texture = selectedDepthStencilAttachment->GetTexture(),
+                    .textureRaw = selectedDepthStencilAttachment->GetTexture().get(),
                     .textureMipLevel = attachmentMipLevel,
                     .finalLayout = depthAttachmentDescription.finalLayout,
                 });
@@ -961,6 +1310,22 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         }
         const Bool hasDepthStencilAttachment = depthAttachmentRef.attachment != VK_ATTACHMENT_UNUSED;
 
+        // Declare only the used colour-reference span. The GL draw-buffer array
+        // always spans 8 slots, so passes used to declare colorAttachmentCount=8
+        // with trailing VK_ATTACHMENT_UNUSED holes - and Adreno configures its
+        // per-pixel render-backend/export path from the DECLARED count, so every
+        // fragment of every pass paid the 8-target export cost (measured on
+        // Adreno 650 / MC 26.2: 11.9 -> 7.5 ms of GPU time per frame, with the
+        // single-quad swapchain blit pass alone dropping 1.26 -> 0.40 ms).
+        // Interior GL_NONE holes keep their slots so fragment-output locations
+        // still line up; a fragment output at a location past the trimmed count
+        // is discarded, which is exactly GL's semantic for writing to a draw
+        // buffer set to GL_NONE.
+        while (!colorAttachmentRefs.empty() &&
+               colorAttachmentRefs.back().attachment == VK_ATTACHMENT_UNUSED) {
+            colorAttachmentRefs.pop_back();
+        }
+
         // Subpass
         VkSubpassDescription subpassDesc;
         subpassDesc.flags = 0;
@@ -974,6 +1339,52 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         subpassDesc.preserveAttachmentCount = 0;
         subpassDesc.pPreserveAttachments = nullptr;
 
+        // External subpass dependencies. Without them there is NO execution/memory
+        // dependency between consecutive render passes (or a pass and a transfer)
+        // touching the same attachments when the image layout does not change — the
+        // layout-transition helper no-ops on identical layouts and no other barrier
+        // exists. Tile-based GPUs then race tile loads against the previous pass's
+        // stores (multi-pass FBO chains like MC 26.3's OIT flicker on Adreno).
+        // Conservative both-ways dependencies: prior writes (attachment output,
+        // depth/stencil, transfer, shader) are made visible to this pass's loads,
+        // and this pass's attachment writes to subsequent sampling/transfer/loads.
+        VkSubpassDependency subpassDependencies[2];
+        subpassDependencies[0] = {};
+        subpassDependencies[0].srcSubpass = VK_SUBPASS_EXTERNAL;
+        subpassDependencies[0].dstSubpass = 0;
+        subpassDependencies[0].srcStageMask = VK_PIPELINE_STAGE_COLOR_ATTACHMENT_OUTPUT_BIT |
+                                              VK_PIPELINE_STAGE_LATE_FRAGMENT_TESTS_BIT |
+                                              VK_PIPELINE_STAGE_FRAGMENT_SHADER_BIT | VK_PIPELINE_STAGE_TRANSFER_BIT;
+        subpassDependencies[0].srcAccessMask = VK_ACCESS_COLOR_ATTACHMENT_WRITE_BIT |
+                                               VK_ACCESS_DEPTH_STENCIL_ATTACHMENT_WRITE_BIT |
+                                               VK_ACCESS_SHADER_WRITE_BIT | VK_ACCESS_TRANSFER_WRITE_BIT;
+        subpassDependencies[0].dstStageMask = VK_PIPELINE_STAGE_EARLY_FRAGMENT_TESTS_BIT |
+                                              VK_PIPELINE_STAGE_LATE_FRAGMENT_TESTS_BIT |
+                                              VK_PIPELINE_STAGE_FRAGMENT_SHADER_BIT |
+                                              VK_PIPELINE_STAGE_COLOR_ATTACHMENT_OUTPUT_BIT;
+        subpassDependencies[0].dstAccessMask =
+            VK_ACCESS_COLOR_ATTACHMENT_READ_BIT | VK_ACCESS_COLOR_ATTACHMENT_WRITE_BIT |
+            VK_ACCESS_DEPTH_STENCIL_ATTACHMENT_READ_BIT | VK_ACCESS_DEPTH_STENCIL_ATTACHMENT_WRITE_BIT |
+            VK_ACCESS_SHADER_READ_BIT;
+        subpassDependencies[0].dependencyFlags = 0;
+        subpassDependencies[1] = {};
+        subpassDependencies[1].srcSubpass = 0;
+        subpassDependencies[1].dstSubpass = VK_SUBPASS_EXTERNAL;
+        subpassDependencies[1].srcStageMask =
+            VK_PIPELINE_STAGE_COLOR_ATTACHMENT_OUTPUT_BIT | VK_PIPELINE_STAGE_LATE_FRAGMENT_TESTS_BIT;
+        subpassDependencies[1].srcAccessMask =
+            VK_ACCESS_COLOR_ATTACHMENT_WRITE_BIT | VK_ACCESS_DEPTH_STENCIL_ATTACHMENT_WRITE_BIT;
+        subpassDependencies[1].dstStageMask = VK_PIPELINE_STAGE_EARLY_FRAGMENT_TESTS_BIT |
+                                              VK_PIPELINE_STAGE_LATE_FRAGMENT_TESTS_BIT |
+                                              VK_PIPELINE_STAGE_FRAGMENT_SHADER_BIT |
+                                              VK_PIPELINE_STAGE_COLOR_ATTACHMENT_OUTPUT_BIT |
+                                              VK_PIPELINE_STAGE_TRANSFER_BIT;
+        subpassDependencies[1].dstAccessMask =
+            VK_ACCESS_COLOR_ATTACHMENT_READ_BIT | VK_ACCESS_COLOR_ATTACHMENT_WRITE_BIT |
+            VK_ACCESS_DEPTH_STENCIL_ATTACHMENT_READ_BIT | VK_ACCESS_DEPTH_STENCIL_ATTACHMENT_WRITE_BIT |
+            VK_ACCESS_SHADER_READ_BIT | VK_ACCESS_TRANSFER_READ_BIT | VK_ACCESS_TRANSFER_WRITE_BIT;
+        subpassDependencies[1].dependencyFlags = 0;
+
         // Render Pass
         VkRenderPassCreateInfo renderPassCreateInfo;
         renderPassCreateInfo.sType = VK_STRUCTURE_TYPE_RENDER_PASS_CREATE_INFO;
@@ -983,8 +1394,8 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         renderPassCreateInfo.pAttachments = attachmentDescriptions.data();
         renderPassCreateInfo.subpassCount = 1;
         renderPassCreateInfo.pSubpasses = &subpassDesc;
-        renderPassCreateInfo.dependencyCount = 0;
-        renderPassCreateInfo.pDependencies = nullptr;
+        renderPassCreateInfo.dependencyCount = 2;
+        renderPassCreateInfo.pDependencies = subpassDependencies;
 
         VkRenderPass renderPass = VK_NULL_HANDLE;
         VK_VERIFY(vkCreateRenderPass(m_device, &renderPassCreateInfo, nullptr, &renderPass));
@@ -1015,7 +1426,7 @@ namespace MobileGL::MG_Backend::DirectVulkan {
             hasDepthStencilAttachment,
             renderPassSampleCount,
             extent,
-            static_cast<Int>(framebufferLayers) };
+            framebufferLayers };
         MGLOG_D("VkRenderPassManager::GetOrCreateRenderPass: hash=0x%llx compatibilityHash=0x%llx attachmentCount=%u colorAttachmentCount=%u samples=%d extent=%dx%d",
                 static_cast<unsigned long long>(hash),
                 static_cast<unsigned long long>(compatibilityHash),
@@ -1025,9 +1436,54 @@ namespace MobileGL::MG_Backend::DirectVulkan {
                 extent.x(),
                 extent.y());
         auto [insertedIt, _] = m_renderPasses.emplace(hash, Move(renderPassEntry));
+        insertedIt->second.lastUsedFrame = m_frameCounter;
         return insertedIt->second;
     }
 
+    void VkRenderPassManager::OnPresent() {
+        ++m_frameCounter;
+
+        // Runs every frame boundary, ahead of the render-pass sweep gate below: the walk
+        // is O(#renderbuffer resources) — single digits in practice — and per-frame
+        // invocation keeps dead-resource reclaim latency at the aging bound instead of
+        // coupling it to renderbuffer *use* (the GetOrCreateRenderbufferResource call
+        // site never runs again once an app stops using renderbuffers).
+        CollectRenderbufferGarbage();
+        CollectDeferredRenderbufferReleases(/*destroyAll=*/false);
+
+        // Sweep occasionally; evict entries whose last use is far past every
+        // in-flight frame so their VkRenderPass/VkFramebuffer can be destroyed
+        // safely (RenderPassEntry's destructor releases the handles).
+        constexpr Uint64 kSweepInterval = 256;
+        constexpr Uint64 kRetireAgeFrames = 1024;
+        if ((m_frameCounter % kSweepInterval) != 0) {
+            return;
+        }
+
+        // Collect the dying handles and notify once after the loop: pipelines hashed
+        // on them share the entries' >kRetireAgeFrames idleness (they are only bound
+        // by draws that hit those entries), so the observer may destroy them
+        // immediately - and a single batched notification costs one pipeline-cache
+        // scan instead of one per evicted pass.
+        Vector<VkRenderPass> destroyedRenderPasses;
+        const Uint64 activeHash = s_hasActiveRenderPass ? s_activeRenderPass.hash : 0;
+        for (auto it = m_renderPasses.begin(); it != m_renderPasses.end();) {
+            const Bool isActive = s_hasActiveRenderPass && it->first == activeHash;
+            if (!isActive && m_frameCounter - it->second.lastUsedFrame > kRetireAgeFrames) {
+                if (m_rpFastValid && m_rpFastRenderPassHash == it->first) {
+                    m_rpFastValid = false;
+                }
+                destroyedRenderPasses.push_back(it->second.renderPass);
+                it = m_renderPasses.erase(it);
+            } else {
+                ++it;
+            }
+        }
+        if (!destroyedRenderPasses.empty() && m_evictionObserver != nullptr) {
+            m_evictionObserver->OnRenderPassesDestroyed(destroyedRenderPasses);
+        }
+    }
+
     Bool VkRenderPassManager::BeginRenderPass(VkCommandBuffer commandBuffer, RenderPassEntry& renderPassEntry) {
         // TODO: Transition all the attachments into proper layout before starting the render pass
         VkRenderPassBeginInfo renderPassBeginInfo;
@@ -1059,12 +1515,8 @@ namespace MobileGL::MG_Backend::DirectVulkan {
                 }
             }
             if ((clearPayload.mask & GL_COLOR_BUFFER_BIT) != 0) {
-                clearValues[pending.attachmentIndex].color = {
-                    clearPayload.color.x(),
-                    clearPayload.color.y(),
-                    clearPayload.color.z(),
-                    ResolveColorClearAlpha(liveTexture.get(), clearPayload.color.w())
-                };
+                clearValues[pending.attachmentIndex].color =
+                    MakeVkClearColorValue(clearPayload, ColorFormatLacksAlpha(liveTexture.get()));
             }
             if ((clearPayload.mask & GL_DEPTH_BUFFER_BIT) != 0) {
                 clearValues[pending.attachmentIndex].depthStencil.depth = clearPayload.depth;
@@ -1078,6 +1530,17 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         renderPassBeginInfo.pClearValues = clearValues.data();
 
         vkCmdBeginRenderPass(commandBuffer, &renderPassBeginInfo, VK_SUBPASS_CONTENTS_INLINE);
+        // Pre-pass stream bookkeeping: this pass's attachment images are now
+        // referenced by the open frame recording.
+        if (s_textureManager != nullptr) {
+            for (const auto& tracked : renderPassEntry.trackedAttachmentLayouts) {
+                if (tracked.target == TrackedAttachmentTarget::Texture) {
+                    if (const auto texture = tracked.texture.lock()) {
+                        s_textureManager->StampTextureRecordingUse(texture.get());
+                    }
+                }
+            }
+        }
         for (const auto& pending: renderPassEntry.pendingClearAttachments) {
             if (pending.hasInlinePayload) {
                 if (s_renderPassManager != nullptr) {
@@ -1130,11 +1593,15 @@ namespace MobileGL::MG_Backend::DirectVulkan {
                     case TrackedAttachmentTarget::SwapchainColor:
                         MOBILEGL_ASSERT(s_swapchainObject != nullptr, "EndRenderPass: swapchain object is null");
                         s_swapchainObject->SetImageLayout(trackedAttachment.swapchainImageIndex, trackedAttachment.finalLayout);
+                        // The pass stored into the attachment: its content is defined
+                        // until the image is next presented.
+                        s_swapchainObject->SetImageContentDefined(trackedAttachment.swapchainImageIndex, true);
                         break;
                     case TrackedAttachmentTarget::SwapchainDepthStencil:
                         MOBILEGL_ASSERT(s_swapchainObject != nullptr, "EndRenderPass: swapchain object is null");
                         s_swapchainObject->SetDepthStencilImageLayout(trackedAttachment.swapchainImageIndex,
                                                                       trackedAttachment.finalLayout);
+                        s_swapchainObject->SetDepthStencilContentDefined(trackedAttachment.swapchainImageIndex, true);
                         break;
                     default:
                         MOBILEGL_ASSERT(false, "EndRenderPass: unsupported tracked attachment target=%d",

MobileGL/MG_Backend/DirectVulkan/Renderer/VkRenderPassManager.h

@@ -16,6 +16,7 @@
 #include "MG_State/GLState/FramebufferState/FramebufferObject.h"
 
 #include <Includes.h>
+#include <unordered_map>
 #include <vk_mem_alloc.h>
 
 namespace MobileGL::MG_Backend::DirectVulkan {
@@ -27,7 +28,12 @@ namespace MobileGL::MG_Backend::DirectVulkan {
     };
 
     struct PendingClearAttachmentInfo {
+        // Index into the render pass attachment descriptions (VkRenderPassBeginInfo::pClearValues space).
         Uint32 attachmentIndex = 0;
+        // Index into the subpass pColorAttachments (VkClearAttachment::colorAttachment space) — the GL
+        // draw-buffer slot. Differs from attachmentIndex when earlier slots are GL_NONE/incomplete.
+        // Only meaningful for color clears.
+        Uint32 colorAttachmentSlot = 0;
         PendingClearKey key{};
         MG_State::GLState::RenderbufferObject* renderbuffer = nullptr;
         Bool hasInlinePayload = false;
@@ -37,6 +43,11 @@ namespace MobileGL::MG_Backend::DirectVulkan {
     struct TrackedAttachmentLayoutInfo {
         TrackedAttachmentTarget target = TrackedAttachmentTarget::Texture;
         WeakPtr<MG_State::GLState::ITextureObject> texture;
+        // Identity-compare shortcut for the per-draw "does the active pass use
+        // this sampled texture" probe: comparing this against a LIVE texture's
+        // address needs no weak_ptr::lock (two refcount atomics per probe).
+        // May dangle once the texture dies - compare only, never dereference.
+        MG_State::GLState::ITextureObject* textureRaw = nullptr;
         WeakPtr<MG_State::GLState::RenderbufferObject> renderbuffer;
         Uint32 textureMipLevel = 0;
         Uint32 swapchainImageIndex = 0;
@@ -68,7 +79,10 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         Bool hasDepthStencilAttachment = false;
         VkSampleCountFlagBits sampleCount = VK_SAMPLE_COUNT_1_BIT;
         IntVec2 extent = {0, 0};
-        Uint32 subpass = 0;
+        // VkFramebufferCreateInfo::layers of the entry's framebuffer (>1 for layered GL attachments).
+        Uint32 layers = 1;
+        // Frame counter value of the last GetOrCreateRenderPass hit; drives cache eviction.
+        Uint64 lastUsedFrame = 0;
 
         RenderPassEntry() = default;
         RenderPassEntry(const RenderPassEntry&) = delete;
@@ -84,7 +98,8 @@ namespace MobileGL::MG_Backend::DirectVulkan {
             std::swap(hasDepthStencilAttachment, that.hasDepthStencilAttachment);
             std::swap(sampleCount, that.sampleCount);
             std::swap(extent, that.extent);
-            std::swap(subpass, that.subpass);
+            std::swap(layers, that.layers);
+            std::swap(lastUsedFrame, that.lastUsedFrame);
         }
         RenderPassEntry(
             Uint64 hash,
@@ -97,7 +112,7 @@ namespace MobileGL::MG_Backend::DirectVulkan {
             Uint32 colorAttachmentCount,
             Bool hasDepthStencilAttachment,
             VkSampleCountFlagBits sampleCount,
-            IntVec2 extent, int subpass):
+            IntVec2 extent, Uint32 layers):
             hash(hash),
             renderPass(renderpass),
             framebuffer(framebuffer),
@@ -109,7 +124,7 @@ namespace MobileGL::MG_Backend::DirectVulkan {
             hasDepthStencilAttachment(hasDepthStencilAttachment),
             sampleCount(sampleCount),
             extent(extent),
-            subpass(subpass)
+            layers(layers)
         {}
 
         ~RenderPassEntry() {
@@ -148,24 +163,61 @@ namespace MobileGL::MG_Backend::DirectVulkan {
     class VkRenderPassManager {
     public:
         using HashType = Uint64;
+
+        // Notified once per OnPresent sweep with every aged-out entry's VkRenderPass
+        // value: pipelines are hashed on the raw handle, and once destroyed the value
+        // may be recycled for an incompatible pass, so dependent caches must purge
+        // everything keyed on them before any new pass can be created (the sweep and
+        // the notification run back-to-back with no creation in between; observers
+        // compare the values, never dereference them). Batched so a mass-idle cohort
+        // (shader-pack switch, dimension exit) costs the observer one pipeline-cache
+        // scan, not one per dying pass. The wholesale paths
+        // (Shutdown/RecreateSwapchain) do not notify - their callers already drop
+        // every pipeline outright.
+        class IEvictionObserver {
+        public:
+            virtual ~IEvictionObserver() = default;
+            virtual void OnRenderPassesDestroyed(const Vector<VkRenderPass>& renderPasses) = 0;
+        };
+
         VkRenderPassManager(VkDevice device,
             VkPhysicalDevice physicalDevice, VmaAllocator allocator, const VulkanRendererConfig& config,
             VkClearManager& clearManager, VkTextureManager& textureManager, SwapchainObject& swapchainObject);
         ~VkRenderPassManager();
 
+        // Observer may be null (no notifications). Not owned.
+        void SetEvictionObserver(IEvictionObserver* observer) { m_evictionObserver = observer; }
+
         Bool Initialize();
         void Shutdown();
 
         HashType ComputeHash(
             const MG_State::GLState::FramebufferObject& fbo,
             Uint32 swapchainImageIndex,
-            Bool includePendingClear = true);
-        RenderPassEntry& GetOrCreateRenderPass(const MG_State::GLState::FramebufferObject& fbo, Uint32 swapchainImageIndex);
+            Bool includePendingClear = true,
+            Bool includeDefaultFboDepthStencil = true);
+        // drawUsesDepthStencil: whether the operation about to run inside the pass
+        // reads or writes the depth/stencil buffer (depth test or stencil test
+        // enabled, or a depth/stencil clear). Only consulted for the DEFAULT
+        // framebuffer: EGL undefines its ancillary buffers at every swap, so a
+        // default-FBO pass whose draws provably never touch depth/stencil is
+        // created WITHOUT the depth attachment - on a tiler that skips the whole
+        // depth tile load AND store. The flavor only escalates: once a pass with
+        // depth is active, later depth-less draws keep using it, and a depth-using
+        // draw against a depth-less active pass resolves to a new (incompatible)
+        // entry, which the caller's compatibility check turns into a pass split;
+        // the new pass's depth loads DONT_CARE (content was undefined all along).
+        RenderPassEntry& GetOrCreateRenderPass(const MG_State::GLState::FramebufferObject& fbo,
+                                               Uint32 swapchainImageIndex,
+                                               Bool drawUsesDepthStencil = true);
         void QueueRenderbufferClear(GLbitfield mask, const ClearFramebufferPayload& clearPayload,
                                     const MG_State::GLState::FramebufferObject& drawFbo);
         void QueueRenderbufferClear(const ClearAttachmentPayload& clearPayload,
                                     const MG_State::GLState::FramebufferAttachmentObject& attachment);
         void PopPendingRenderbufferClear(MG_State::GLState::RenderbufferObject* renderbuffer);
+        // Frame boundary hook: ages the render-pass cache and evicts long-unused
+        // entries (their command buffers retired many frames ago).
+        void OnPresent();
         static Bool BeginRenderPass(VkCommandBuffer commandBuffer, RenderPassEntry& renderPassEntry);
         static Bool EndRenderPass(VkCommandBuffer commandBuffer);
         static ActiveRenderPassInfo* GetActiveRenderPass();
@@ -178,12 +230,22 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         VkTextureManager& m_textureManager;
         SwapchainObject& m_swapchainObject;
         UnorderedMap<Uint64, RenderPassEntry> m_renderPasses;
+        // Monotonic frame counter (bumped in OnPresent) for render-pass cache aging.
+        Uint64 m_frameCounter = 0;
+        IEvictionObserver* m_evictionObserver = nullptr;
 
         // Bumped whenever a renderbuffer VkImage is (re)created; together with the texture
         // manager's image epoch this invalidates the render-pass fast path on any attachment
         // image recreation.
         Uint64 m_renderbufferImageEpoch = 1;
 
+    public:
+        // Bumped whenever a renderbuffer backing is (re)created; consecutive-draw
+        // snapshots include it so an attachment respecify forces a re-resolve.
+        Uint64 GetRenderbufferImageEpoch() const { return m_renderbufferImageEpoch; }
+
+    private:
+
         // Per-draw fast-path memo for GetOrCreateRenderPass (dirty-flag state tracking): when the
         // framebuffer state is provably unchanged since the last resolution, the active render pass
         // is reused WITHOUT recomputing the expensive per-draw hash. Invalidated by FBO switch /
@@ -196,12 +258,26 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         Uint64 m_rpFastTexEpoch = 0;
         Uint64 m_rpFastRbEpoch = 0;
         Uint64 m_rpFastRenderPassHash = 0;
+        // Whether the memoized entry carries a depth/stencil attachment; a
+        // default-FBO resolution whose effective depth request differs must
+        // miss the memo (the depth-less/depth-full flavors hash differently).
+        Bool m_rpFastHadDepthStencil = false;
 
+    public:
         struct RenderbufferResource {
+            // deadSinceFrame sentinel: the owning weak reference has not been observed
+            // expired. Dead resources age past every in-flight frame before Destroy
+            // (see CollectRenderbufferGarbage); the GPU may still reference the image
+            // for frames-in-flight frames after the GL object dies.
+            static constexpr Uint64 kNeverObservedDead = UINT64_MAX;
+
             WeakPtr<MG_State::GLState::RenderbufferObject> renderbuffer;
             VkImage image = VK_NULL_HANDLE;
             VmaAllocation allocation = nullptr;
             VkImageView view = VK_NULL_HANDLE;
+            // UNORM reinterpretation of an sRGB image, used as the attachment view while
+            // GL_FRAMEBUFFER_SRGB is disabled (raw writes). Null for non-sRGB formats.
+            VkImageView unormTwinView = VK_NULL_HANDLE;
             VkImageLayout layout = VK_IMAGE_LAYOUT_UNDEFINED;
             VkFormat format = VK_FORMAT_UNDEFINED;
             VkImageAspectFlags aspect = VK_IMAGE_ASPECT_NONE;
@@ -209,25 +285,71 @@ namespace MobileGL::MG_Backend::DirectVulkan {
             VkSampleCountFlagBits sampleCount = VK_SAMPLE_COUNT_1_BIT;
             TextureInternalFormat internalFormat = TextureInternalFormat::Unknown;
             Int samples = 0;
+            // m_frameCounter value at which the weak reference was first seen expired.
+            Uint64 deadSinceFrame = kNeverObservedDead;
 
             void Destroy(VkDevice device, VmaAllocator allocator);
         };
 
+        // Public so the renderer's blit/copy/readback bindings can source renderbuffer
+        // attachments the same way texture attachments go through the texture manager.
+        RenderbufferResource* GetOrCreateRenderbufferResource(
+            const SharedPtr<MG_State::GLState::RenderbufferObject>& renderbuffer);
+        Bool GetPendingRenderbufferClear(MG_State::GLState::RenderbufferObject* renderbuffer,
+                                         ClearAttachmentPayload& outPayload) const;
+
+    private:
         struct PendingRenderbufferClear {
             WeakPtr<MG_State::GLState::RenderbufferObject> renderbuffer;
             ClearAttachmentPayload payload{};
         };
 
-        UnorderedMap<MG_State::GLState::RenderbufferObject*, RenderbufferResource> m_renderbufferResources;
+        // A superseded renderbuffer backing (glRenderbufferStorage respecify) parked
+        // until enough frame boundaries have passed that no in-flight command buffer
+        // can still reference it; destroyed in OnPresent (see RetireAgeFrames).
+        struct DeferredRenderbufferRelease {
+            VkImage image = VK_NULL_HANDLE;
+            VmaAllocation allocation = nullptr;
+            VkImageView view = VK_NULL_HANDLE;
+            VkImageView unormTwinView = VK_NULL_HANDLE;
+            Uint64 deferredAtFrame = 0;
+        };
+
+        // Node-based std::unordered_map, deliberately not FastSTL's open-addressing UnorderedMap:
+        // callers cache a RenderbufferResource* - or a bare &resource->layout - and then make further
+        // calls that touch this map. BlitFramebuffer is the one that bit: it resolves the source and
+        // destination colour bindings (ResolveColorBlitBinding caches &rbResource->layout), then
+        // materializes the source's pending clear, which looks that same resource up again. FastSTL's
+        // operator[] runs its load-factor check before find_key and reallocates the whole bucket array
+        // when occupancy crosses it, so even a plain lookup relocates every element; erase only
+        // tombstones and never decrements the occupancy, so the doubling keeps firing. After a
+        // relocation the cached pointer names freed storage still holding the pre-clear
+        // VK_IMAGE_LAYOUT_UNDEFINED, and BlitFramebuffer bails out at "source image layout is
+        // undefined", silently dropping the blit - renderbuffers_storage_multisample read back zero
+        // instead of the clear colour on exactly the iterations that grew the table.
+        //
+        // Reordering the materialize ahead of the resolves - the fix ReadPixels got - does not cover
+        // this: the destination resolve still runs after the source pointer is taken. The depth blit,
+        // GetOrCreateRenderPass's depthRenderbufferResource and ReadDepthStencilPixels cache the same
+        // kind of pointer, so the invariant belongs in the container rather than in a per-call-site
+        // ordering rule. m_textureResources is node-based for the same reason. This buys stability
+        // across rehash and insert only - erase still invalidates the erased element, which is safe
+        // here because a renderbuffer that is an FBO attachment is held alive by that attachment.
+        std::unordered_map<MG_State::GLState::RenderbufferObject*, RenderbufferResource> m_renderbufferResources;
         UnorderedMap<MG_State::GLState::RenderbufferObject*, PendingRenderbufferClear> m_pendingRenderbufferClears;
+        Vector<DeferredRenderbufferRelease> m_deferredRenderbufferReleases;
+        // Supported sample counts per attachment format, so per-draw resource lookups
+        // do not repeat vkGetPhysicalDeviceImageFormatProperties.
+        UnorderedMap<VkFormat, VkSampleCountFlags> m_attachmentSampleCountsByFormat;
 
-        RenderbufferResource* GetOrCreateRenderbufferResource(
-            const SharedPtr<MG_State::GLState::RenderbufferObject>& renderbuffer);
-        Bool GetPendingRenderbufferClear(MG_State::GLState::RenderbufferObject* renderbuffer,
-                                         ClearAttachmentPayload& outPayload) const;
         Bool HasPendingRenderbufferClear(
             const MG_State::GLState::FramebufferAttachmentObject& attachment) const;
         void CollectRenderbufferGarbage();
+        // Frame-boundary margin after which a resource last referenced by a retired
+        // GL object (or superseded backing) is provably past every in-flight frame.
+        Uint64 RetireAgeFrames() const;
+        void DeferRenderbufferBackingRelease(RenderbufferResource& resource);
+        void CollectDeferredRenderbufferReleases(Bool destroyAll);
 
         static inline XXH64_state_t* m_hashState = XXH64_createState();
         static inline ActiveRenderPassInfo s_activeRenderPass{};

MobileGL/MG_Backend/DirectVulkan/Renderer/VkSamplerManager.cpp

@@ -51,6 +51,18 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         Float ResolveEffectiveMinLod(const MG_State::GLState::SamplerObject& sampler, Float effectiveMaxLod) {
             return std::min(sampler.GetMinLod(), effectiveMaxLod);
         }
+
+        // A single-level view can only ever deliver the base level, but the LOD clamp must not be
+        // collapsed to exactly 0: both GL and Vulkan pick magFilter over minFilter from the
+        // *clamped* lambda, so maxLod = 0 would make every fragment magnify and quietly retire the
+        // min filter. 0.25 is the value VkSamplerCreateInfo's own note prescribes for emulating
+        // GL's non-mipmapped minification - large enough for lambda to stay positive, small enough
+        // that a NEAREST mip mode still rounds down to level 0. Clamped rather than assigned, so a
+        // texture whose GL_TEXTURE_MAX_LOD really is 0 keeps magnifying as GL says it must.
+        Float ResolveSingleLevelMaxLod(const MG_State::GLState::SamplerObject& sampler, Bool singleLevelView) {
+            const Float maxLod = ResolveEffectiveMaxLod(sampler);
+            return singleLevelView ? std::min(maxLod, 0.25f) : maxLod;
+        }
     } // namespace
 
     Bool VkSamplerManager::Initialize(const InitInfo& initInfo) {
@@ -58,11 +70,26 @@ namespace MobileGL::MG_Backend::DirectVulkan {
 
         m_device = initInfo.device;
         m_config = initInfo.config;
+        m_samplerAnisotropySupported = initInfo.samplerAnisotropySupported;
+        m_maxSamplerAnisotropy = std::max(initInfo.maxSamplerAnisotropy, 1.0f);
         MOBILEGL_ASSERT(m_device != VK_NULL_HANDLE && m_config != nullptr,
                         "VkSamplerManager::Initialize failed: invalid initialization info");
         return true;
     }
 
+    Float VkSamplerManager::ResolveEffectiveMaxAnisotropy(const MG_State::GLState::SamplerObject& sampler,
+                                                           Bool forceNearestFiltering) const {
+        if (!m_samplerAnisotropySupported) return 1.0f;
+        if (forceNearestFiltering) return 1.0f;
+        // VUID-VkSamplerCreateInfo-anisotropyEnable-01071/01072: anisotropy requires both filters to
+        // be LINEAR and the value to sit within [1, limits.maxSamplerAnisotropy].
+        if (sampler.GetMinFilter() != SamplerFilterMode::Linear ||
+            sampler.GetMagFilter() != SamplerFilterMode::Linear) {
+            return 1.0f;
+        }
+        return std::clamp(sampler.GetMaxAnisotropy(), 1.0f, m_maxSamplerAnisotropy);
+    }
+
     void VkSamplerManager::Shutdown() {
         for (auto& [_, sampler] : m_samplers) {
             if (m_device != VK_NULL_HANDLE && sampler.handle != VK_NULL_HANDLE) {
@@ -74,13 +101,44 @@ namespace MobileGL::MG_Backend::DirectVulkan {
 
         m_device = VK_NULL_HANDLE;
         m_config = nullptr;
+        m_frameBoundaryCounter = 0;
+    }
+
+    void VkSamplerManager::OnFrameBoundary() {
+        ++m_frameBoundaryCounter;
+
+        // Sweep occasionally; destroy samplers whose last use is far past every
+        // in-flight frame. Destroy and erase must stay atomic, or Shutdown would
+        // double-free the handle; an evicted key that recurs simply re-creates
+        // its sampler on the next miss.
+        constexpr Uint64 kSweepInterval = 256;
+        constexpr Uint64 kRetireAgeBoundaries = 1024;
+        if ((m_frameBoundaryCounter % kSweepInterval) != 0) {
+            return;
+        }
+
+        for (auto it = m_samplers.begin(); it != m_samplers.end();) {
+            auto& entry = it->second;
+            if (m_frameBoundaryCounter - entry.lastUsedFrameBoundary > kRetireAgeBoundaries) {
+                if (m_device != VK_NULL_HANDLE && entry.handle != VK_NULL_HANDLE) {
+                    vkDestroySampler(m_device, entry.handle, nullptr);
+                }
+                it = m_samplers.erase(it);
+            } else {
+                ++it;
+            }
+        }
     }
 
     Uint64 VkSamplerManager::BuildSamplerKey(const MG_State::GLState::SamplerObject& sampler,
-                                             const MG_State::GLState::ITextureObject& texture) const {
+                                             const MG_State::GLState::ITextureObject& texture,
+                                             Bool forceNearestFiltering, Bool singleLevelView) const {
         MOBILEGL_ASSERT(m_config != nullptr, "VkSamplerManager::BuildSamplerKey: m_config is null");
         XXHASH_VERIFY(XXH64_reset(m_hashState, m_config->CacheVersion));
 
+        XXHASH_VERIFY(XXH64_update(m_hashState, &forceNearestFiltering, sizeof(forceNearestFiltering)));
+        XXHASH_VERIFY(XXH64_update(m_hashState, &singleLevelView, sizeof(singleLevelView)));
+
         const auto minFilter = sampler.GetMinFilter();
         XXHASH_VERIFY(XXH64_update(m_hashState, &minFilter, sizeof(minFilter)));
         const auto magFilter = sampler.GetMagFilter();
@@ -93,15 +151,20 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         XXHASH_VERIFY(XXH64_update(m_hashState, &wrapT, sizeof(wrapT)));
         const auto wrapR = sampler.GetWrapR();
         XXHASH_VERIFY(XXH64_update(m_hashState, &wrapR, sizeof(wrapR)));
-        const auto maxLod = ResolveEffectiveMaxLod(sampler);
+        const auto maxLod = ResolveSingleLevelMaxLod(sampler, singleLevelView);
         const auto minLod = ResolveEffectiveMinLod(sampler, maxLod);
         XXHASH_VERIFY(XXH64_update(m_hashState, &minLod, sizeof(minLod)));
         XXHASH_VERIFY(XXH64_update(m_hashState, &maxLod, sizeof(maxLod)));
         const auto lodBias = sampler.GetLodBias();
         XXHASH_VERIFY(XXH64_update(m_hashState, &lodBias, sizeof(lodBias)));
+        // The RESOLVED value, not the GL request: samplers that only differ in an anisotropy Vulkan
+        // will not apply (NEAREST filtering, or requests past the device limit) must still share one
+        // VkSampler, while two samplers that really do differ must not collide onto the first one's.
+        const auto maxAnisotropy = ResolveEffectiveMaxAnisotropy(sampler, forceNearestFiltering);
+        XXHASH_VERIFY(XXH64_update(m_hashState, &maxAnisotropy, sizeof(maxAnisotropy)));
         const auto compareMode = sampler.GetCompareMode();
         XXHASH_VERIFY(XXH64_update(m_hashState, &compareMode, sizeof(compareMode)));
-        const auto compareFunc = ResolveCompareFunc(sampler, texture);
+        const auto compareFunc = sampler.GetSamplerCompareFunc();
         XXHASH_VERIFY(XXH64_update(m_hashState, &compareFunc, sizeof(compareFunc)));
         const auto borderColor = ResolveVkBorderColor(sampler, texture);
         XXHASH_VERIFY(XXH64_update(m_hashState, &borderColor, sizeof(borderColor)));
@@ -109,27 +172,44 @@ namespace MobileGL::MG_Backend::DirectVulkan {
     }
 
     VkSampler VkSamplerManager::GetOrCreateSampler(const MG_State::GLState::SamplerObject& sampler,
-                                                   const MG_State::GLState::ITextureObject& texture) {
-        const Uint64 key = BuildSamplerKey(sampler, texture);
+                                                   const MG_State::GLState::ITextureObject& texture,
+                                                   Bool forceNearestFiltering, Uint32 viewLevelCount) {
+        // A view that exposes a single mip level has no second level to blend with, so GL's
+        // *_MIPMAP_* minification filters degenerate to plain filtering on the base level -
+        // sampling is unchanged by pinning the Vulkan sampler to NEAREST mip mode at LOD 0.
+        // It is not cosmetic: MobileGL backs such a view with a fully allocated mip chain whose
+        // tail is never written, and a LINEAR mip mode lets the texture unit issue the level+1
+        // fetch anyway. On Adreno that fetch lands in uninitialized UBWC pages (or past the
+        // allocation for a genuinely single-level image) and faults the GPU - the same failure
+        // the default-framebuffer blit shader had to work around with an explicit-LOD sample.
+        const Bool singleLevelView = viewLevelCount == 1;
+        const Uint64 key = BuildSamplerKey(sampler, texture, forceNearestFiltering, singleLevelView);
         auto it = m_samplers.find(key);
         if (it != m_samplers.end()) {
+            it->second.lastUsedFrameBoundary = m_frameBoundaryCounter;
             return it->second.handle;
         }
 
         VkSamplerCreateInfo samplerInfo{};
         samplerInfo.sType = VK_STRUCTURE_TYPE_SAMPLER_CREATE_INFO;
-        samplerInfo.magFilter = ToVkFilter(sampler.GetMagFilter());
-        samplerInfo.minFilter = ToVkFilter(sampler.GetMinFilter());
-        samplerInfo.mipmapMode = ToVkMipmapMode(sampler.GetMipmapMode());
+        samplerInfo.magFilter = forceNearestFiltering ? VK_FILTER_NEAREST : ToVkFilter(sampler.GetMagFilter());
+        samplerInfo.minFilter = forceNearestFiltering ? VK_FILTER_NEAREST : ToVkFilter(sampler.GetMinFilter());
+        samplerInfo.mipmapMode = (forceNearestFiltering || singleLevelView)
+                                     ? VK_SAMPLER_MIPMAP_MODE_NEAREST
+                                     : ToVkMipmapMode(sampler.GetMipmapMode());
         samplerInfo.addressModeU = ToVkAddressMode(sampler.GetWrapS());
         samplerInfo.addressModeV = ToVkAddressMode(sampler.GetWrapT());
         samplerInfo.addressModeW = ToVkAddressMode(sampler.GetWrapR());
         samplerInfo.mipLodBias = sampler.GetLodBias();
-        samplerInfo.anisotropyEnable = VK_FALSE;
-        samplerInfo.maxAnisotropy = 1.0f;
+        // Must use the same resolver as BuildSamplerKey - a divergence would either collide two
+        // different samplers or silently create duplicates.
+        const Float maxAnisotropy = ResolveEffectiveMaxAnisotropy(sampler, forceNearestFiltering);
+        samplerInfo.anisotropyEnable = maxAnisotropy > 1.0f ? VK_TRUE : VK_FALSE;
+        samplerInfo.maxAnisotropy = maxAnisotropy;
         samplerInfo.compareEnable = sampler.GetCompareMode() == SamplerCompareMode::CompareToTexture ? VK_TRUE : VK_FALSE;
-        samplerInfo.compareOp = ToVkCompareOp(ResolveCompareFunc(sampler, texture));
-        samplerInfo.maxLod = ResolveEffectiveMaxLod(sampler);
+        samplerInfo.compareOp = ToVkCompareOp(sampler.GetSamplerCompareFunc());
+        // Must match BuildSamplerKey's resolution exactly.
+        samplerInfo.maxLod = ResolveSingleLevelMaxLod(sampler, singleLevelView);
         samplerInfo.minLod = ResolveEffectiveMinLod(sampler, samplerInfo.maxLod);
         samplerInfo.borderColor = ResolveVkBorderColor(sampler, texture);
         samplerInfo.unnormalizedCoordinates = VK_FALSE;
@@ -141,6 +221,7 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         entry.handle = vkSampler;
         entry.externalIndex = sampler.GetExternalIndex();
         entry.version = sampler.GetVersion();
+        entry.lastUsedFrameBoundary = m_frameBoundaryCounter;
         m_samplers[key] = entry;
         return vkSampler;
     }
@@ -200,24 +281,15 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         }
     }
 
-    SamplerCompareFunc VkSamplerManager::ResolveCompareFunc(const MG_State::GLState::SamplerObject& sampler,
-                                                            const MG_State::GLState::ITextureObject& texture) {
-        const auto compareFunc = sampler.GetSamplerCompareFunc();
-        if (sampler.GetCompareMode() == SamplerCompareMode::CompareToTexture &&
-            IsDepthTextureFormat(texture.GetFormat()) && compareFunc == SamplerCompareFunc::Always) {
-            return SamplerCompareFunc::LessEqual;
-        }
-
-        return compareFunc;
-    }
-
     VkBorderColor VkSamplerManager::ResolveVkBorderColor(const MG_State::GLState::SamplerObject& sampler,
                                                          const MG_State::GLState::ITextureObject& texture) {
         if (!UsesBorderColor(sampler)) {
             return VK_BORDER_COLOR_FLOAT_TRANSPARENT_BLACK;
         }
 
-        const auto& borderColor = texture.GetBorderColor();
+        // Border colour is sampler state: a bound sampler object supplies its own, and a texture
+        // with none reaches the very same value through the sampler object it owns.
+        const auto& borderColor = sampler.GetBorderColor();
         const Bool isDepthTexture = IsDepthTextureFormat(texture.GetFormat());
 
         if (isDepthTexture) {

MobileGL/MG_Backend/DirectVulkan/Renderer/VkSamplerManager.h

@@ -24,35 +24,67 @@ public:
     struct InitInfo {
         VkDevice device = VK_NULL_HANDLE;
         const VulkanRendererConfig* config = nullptr;
+        // The samplerAnisotropy device feature was requested and granted at vkCreateDevice.
+        Bool samplerAnisotropySupported = false;
+        // VkPhysicalDeviceLimits::maxSamplerAnisotropy.
+        Float maxSamplerAnisotropy = 1.0f;
     };
 
     Bool Initialize(const InitInfo& initInfo);
     void Shutdown();
 
+    // viewLevelCount is the mip-level count of the image view this sampler will be paired
+    // with; 0 means "unknown, do not narrow". See GetOrCreateSampler for why it matters.
     VkSampler GetOrCreateSampler(const MG_State::GLState::SamplerObject& sampler,
-                                 const MG_State::GLState::ITextureObject& texture);
+                                 const MG_State::GLState::ITextureObject& texture,
+                                 Bool forceNearestFiltering = false,
+                                 Uint32 viewLevelCount = 0);
+    // Frame boundary hook: ages the sampler cache and destroys samplers not used
+    // for many frames. The key hashes continuous float state (lodBias, LOD clamps,
+    // anisotropy), so an app animating those would otherwise mint an unbounded
+    // stream of never-destroyed VkSamplers and eventually exhaust the device's
+    // maxSamplerAllocationCount. A sampler idle for over a thousand frame
+    // boundaries cannot be referenced by any in-flight command buffer (frames in
+    // flight are single digits), and every descriptor set the GPU consumes is
+    // written that same frame with live handles (the per-binding resolve memo and
+    // descriptor-set reuse are both frame-reset), so destruction here needs no
+    // fence wait. Self-gated: one counter bump and compare except on sweep
+    // boundaries.
+    void OnFrameBoundary();
 
 private:
     struct SamplerCacheEntry {
         VkSampler handle = VK_NULL_HANDLE;
         Uint externalIndex = 0;
         Uint16 version = 0;
+        // Frame boundary of the last cache hit; entries idle past the
+        // OnFrameBoundary retirement age have their VkSampler destroyed.
+        Uint64 lastUsedFrameBoundary = 0;
     };
 
     Uint64 BuildSamplerKey(const MG_State::GLState::SamplerObject& sampler,
-                           const MG_State::GLState::ITextureObject& texture) const;
+                           const MG_State::GLState::ITextureObject& texture,
+                           Bool forceNearestFiltering, Bool singleLevelView) const;
     static VkFilter ToVkFilter(SamplerFilterMode mode);
     static VkSamplerMipmapMode ToVkMipmapMode(SamplerMipmapMode mode);
     static VkSamplerAddressMode ToVkAddressMode(SamplerWrapMode mode);
     static VkCompareOp ToVkCompareOp(SamplerCompareFunc func);
-    static SamplerCompareFunc ResolveCompareFunc(const MG_State::GLState::SamplerObject& sampler,
-                                                 const MG_State::GLState::ITextureObject& texture);
     static VkBorderColor ResolveVkBorderColor(const MG_State::GLState::SamplerObject& sampler,
                                               const MG_State::GLState::ITextureObject& texture);
+    // The anisotropy Vulkan will actually apply: 1.0 (i.e. disabled) unless the feature is on and
+    // the sampler filters linearly both ways, otherwise the GL request clamped to the device limit.
+    // GL happily carries GL_TEXTURE_MAX_ANISOTROPY on a NEAREST sampler (Blaze3D's blocks do exactly
+    // that) while Vulkan forbids anisotropyEnable there, so the GL value must never be forwarded raw.
+    Float ResolveEffectiveMaxAnisotropy(const MG_State::GLState::SamplerObject& sampler,
+                                        Bool forceNearestFiltering) const;
 
     VkDevice m_device = VK_NULL_HANDLE;
     const VulkanRendererConfig* m_config = nullptr;
+    Bool m_samplerAnisotropySupported = false;
+    Float m_maxSamplerAnisotropy = 1.0f;
     UnorderedMap<Uint64, SamplerCacheEntry> m_samplers;
+    // Monotonic frame-boundary counter (bumped in OnFrameBoundary) for cache aging.
+    Uint64 m_frameBoundaryCounter = 0;
     static inline XXH64_state_t* m_hashState = XXH64_createState();
 };
 } // namespace MobileGL::MG_Backend::DirectVulkan

MobileGL/MG_Backend/DirectVulkan/Renderer/VkTextureManager.h

@@ -13,18 +13,24 @@
 #include <MG_State/GLState/TextureState/TextureObject.h>
 #include <vk_mem_alloc.h>
 #include <unordered_map>
+#include <unordered_set>
 
 namespace MobileGL::MG_State::GLState {
 class ITextureObject;
 }
 
 namespace MobileGL::MG_Backend::DirectVulkan {
+enum class SamplerNumericDomain : Uint8;
+
 class VkTextureManager {
 public:
     // Monotonic epoch bumped whenever a texture VkImage is (re)created. The render-pass
     // manager keys its per-draw fast path on this so an attachment's image recreation
     // invalidates the cached render pass (dirty-flag tracking; portable to Vulkan 1.1).
     Uint64 GetTextureImageEpoch() const { return m_textureImageEpoch; }
+    // Bumped whenever any tracked texture resource is erased; cached
+    // TextureResource pointers are valid only while this is unchanged.
+    Uint64 GetResourceEraseEpoch() const { return m_resourceEraseEpoch; }
 
     struct TextureIdentity {
         MG_State::GLState::ITextureObject* texture = nullptr;
@@ -50,6 +56,20 @@ public:
         VkCommandPool commandPool = VK_NULL_HANDLE;
         VkQueue graphicsQueue = VK_NULL_HANDLE;
         Uint32 frameCount = 0;
+        // VK_KHR_image_format_list is enabled: MUTABLE_FORMAT images can name the exact set of
+        // formats they will be viewed as, which is what lets a tiler keep them compressed.
+        Bool imageFormatListSupported = false;
+        // Union of shader stages sampled-read barriers may name on this device; the renderer
+        // builds it from the enabled features because geometry/tessellation stage bits are
+        // invalid in a barrier when their feature is off.
+        VkPipelineStageFlags sampledReadStageMask = VK_PIPELINE_STAGE_VERTEX_SHADER_BIT |
+                                                    VK_PIPELINE_STAGE_FRAGMENT_SHADER_BIT |
+                                                    VK_PIPELINE_STAGE_COMPUTE_SHADER_BIT;
+        // Family of `graphicsQueue`; the manager creates its own command pool
+        // on it for the recycled upload-batch command buffers, so their parked
+        // allocations never sit in (and fragment) the renderer's shared pool
+        // that frame command buffers churn through every frame.
+        Uint32 graphicsQueueFamilyIndex = 0;
     };
 
     struct TextureResource {
@@ -58,12 +78,16 @@ public:
             Uint32 baseArrayLayer = 0;
             Uint32 layerCount = 1;
             VkImageViewType viewType = VK_IMAGE_VIEW_TYPE_2D;
+            // May differ from the image format: sRGB images attach through their UNORM
+            // twin while GL_FRAMEBUFFER_SRGB is disabled.
+            VkFormat viewFormat = VK_FORMAT_UNDEFINED;
 
             Bool operator==(const AttachmentViewKey& other) const {
                 return mipLevel == other.mipLevel &&
                        baseArrayLayer == other.baseArrayLayer &&
                        layerCount == other.layerCount &&
-                       viewType == other.viewType;
+                       viewType == other.viewType &&
+                       viewFormat == other.viewFormat;
             }
         };
 
@@ -74,6 +98,63 @@ public:
                 hash ^= std::hash<Uint32>{}(key.layerCount) + 0x9e3779b9u + (hash << 6) + (hash >> 2);
                 hash ^= std::hash<Uint32>{}(static_cast<Uint32>(key.viewType)) +
                         0x9e3779b9u + (hash << 6) + (hash >> 2);
+                hash ^= std::hash<Uint32>{}(static_cast<Uint32>(key.viewFormat)) +
+                        0x9e3779b9u + (hash << 6) + (hash >> 2);
+                return hash;
+            }
+        };
+
+        struct StorageImageViewKey {
+            Uint32 mipLevel = 0;
+            Uint32 baseArrayLayer = 0;
+            Uint32 layerCount = 1;
+            VkImageViewType viewType = VK_IMAGE_VIEW_TYPE_2D;
+            VkFormat format = VK_FORMAT_UNDEFINED;
+
+            Bool operator==(const StorageImageViewKey& other) const {
+                return mipLevel == other.mipLevel &&
+                       baseArrayLayer == other.baseArrayLayer &&
+                       layerCount == other.layerCount &&
+                       viewType == other.viewType &&
+                       format == other.format;
+            }
+        };
+
+        struct SampledImageViewKey {
+            Uint32 baseMipLevel = 0;
+            Uint32 levelCount = 1;
+            VkImageViewType viewType = VK_IMAGE_VIEW_TYPE_2D;
+            VkFormat format = VK_FORMAT_UNDEFINED;
+
+            Bool operator==(const SampledImageViewKey& other) const {
+                return baseMipLevel == other.baseMipLevel &&
+                       levelCount == other.levelCount &&
+                       viewType == other.viewType &&
+                       format == other.format;
+            }
+        };
+
+        struct SampledImageViewKeyHash {
+            SizeT operator()(const SampledImageViewKey& key) const {
+                SizeT hash = std::hash<Uint32>{}(key.baseMipLevel);
+                hash ^= std::hash<Uint32>{}(key.levelCount) + 0x9e3779b9u + (hash << 6) + (hash >> 2);
+                hash ^= std::hash<Uint32>{}(static_cast<Uint32>(key.viewType)) +
+                        0x9e3779b9u + (hash << 6) + (hash >> 2);
+                hash ^= std::hash<Uint32>{}(static_cast<Uint32>(key.format)) +
+                        0x9e3779b9u + (hash << 6) + (hash >> 2);
+                return hash;
+            }
+        };
+
+        struct StorageImageViewKeyHash {
+            SizeT operator()(const StorageImageViewKey& key) const {
+                SizeT hash = std::hash<Uint32>{}(key.mipLevel);
+                hash ^= std::hash<Uint32>{}(key.baseArrayLayer) + 0x9e3779b9u + (hash << 6) + (hash >> 2);
+                hash ^= std::hash<Uint32>{}(key.layerCount) + 0x9e3779b9u + (hash << 6) + (hash >> 2);
+                hash ^= std::hash<Uint32>{}(static_cast<Uint32>(key.viewType)) +
+                        0x9e3779b9u + (hash << 6) + (hash >> 2);
+                hash ^= std::hash<Uint32>{}(static_cast<Uint32>(key.format)) +
+                        0x9e3779b9u + (hash << 6) + (hash >> 2);
                 return hash;
             }
         };
@@ -85,6 +166,8 @@ public:
         Vector<VkImageView> perMipViews;
         Vector<VkImageView> perMipSampledViews;
         UnorderedMap<AttachmentViewKey, VkImageView, AttachmentViewKeyHash> attachmentViews;
+        UnorderedMap<SampledImageViewKey, VkImageView, SampledImageViewKeyHash> alternateSampledViews;
+        UnorderedMap<StorageImageViewKey, VkImageView, StorageImageViewKeyHash> storageImageViews;
         VkImageLayout layout = VK_IMAGE_LAYOUT_UNDEFINED;
         VkExtent2D extent = {0, 0};
         Uint32 depth = 1;
@@ -96,7 +179,26 @@ public:
         VkImageAspectFlags aspect = VK_IMAGE_ASPECT_NONE;
         VkImageViewType viewType = VK_IMAGE_VIEW_TYPE_2D;
         VkSampleCountFlagBits sampleCount = VK_SAMPLE_COUNT_1_BIT;
+        VkImageCreateFlags imageCreateFlags = 0;
+        // Usage the live image was created with. STORAGE is only requested for textures that
+        // have actually been bound to a GL image unit, because on Adreno a storage-capable
+        // image loses UBWC bandwidth compression; a later image binding upgrades the usage
+        // and recreates the image, so the resolved usage has to be part of the compatibility
+        // check that decides whether the existing image can be kept.
+        VkImageUsageFlags usageFlags = 0;
+        // True once this image was (re)resolved while the texture was already marked as an
+        // image-unit texture. Distinguishes "not upgraded yet" from "cannot be upgraded"
+        // (a format whose optimalTilingFeatures lack STORAGE_IMAGE never gains the bit), so
+        // NeedsStorageImagePreparation cannot ask for a recreate that will never happen.
+        Bool storageUsageResolved = false;
         Uint16 syncedTextureParamsVersion = 0;
+        // Recording generation (VkTextureManager::GetRecordingGeneration) of the last
+        // command referencing this image that was recorded into the CURRENT frame
+        // command buffer. An image untouched by the open recording may have its
+        // out-of-pass work (deferred clears, sampled-layout transitions) recorded
+        // into the frame's PRE command buffer - which executes strictly before the
+        // frame's commands - instead of splitting the active render pass.
+        Uint64 lastRecordingGeneration = 0;
         // Snapshot of ITextureObject::GetContentVersion() at the last successful sync;
         // lets SyncTexture skip the whole re-check/re-upload when content is unchanged.
         Uint64 syncedContentVersion = 0;
@@ -115,6 +217,8 @@ public:
             std::swap(this->perMipViews, that.perMipViews);
             std::swap(this->perMipSampledViews, that.perMipSampledViews);
             std::swap(this->attachmentViews, that.attachmentViews);
+            std::swap(this->alternateSampledViews, that.alternateSampledViews);
+            std::swap(this->storageImageViews, that.storageImageViews);
             std::swap(this->layout, that.layout);
             std::swap(this->extent, that.extent);
             std::swap(this->depth, that.depth);
@@ -126,7 +230,11 @@ public:
             std::swap(this->aspect, that.aspect);
             std::swap(this->viewType, that.viewType);
             std::swap(this->sampleCount, that.sampleCount);
+            std::swap(this->imageCreateFlags, that.imageCreateFlags);
+            std::swap(this->usageFlags, that.usageFlags);
+            std::swap(this->storageUsageResolved, that.storageUsageResolved);
             std::swap(this->syncedTextureParamsVersion, that.syncedTextureParamsVersion);
+            std::swap(this->lastRecordingGeneration, that.lastRecordingGeneration);
             std::swap(this->syncedContentVersion, that.syncedContentVersion);
             std::swap(this->syncedMipLevelCount, that.syncedMipLevelCount);
         }
@@ -153,6 +261,16 @@ public:
                     vkDestroyImageView(s_device, attachmentView, nullptr);
                 }
             }
+            for (const auto& [_, sampledView] : alternateSampledViews) {
+                if (sampledView != VK_NULL_HANDLE) {
+                    vkDestroyImageView(s_device, sampledView, nullptr);
+                }
+            }
+            for (const auto& [_, storageImageView] : storageImageViews) {
+                if (storageImageView != VK_NULL_HANDLE) {
+                    vkDestroyImageView(s_device, storageImageView, nullptr);
+                }
+            }
             if (image != VK_NULL_HANDLE && allocation != nullptr) {
                 vmaDestroyImage(s_allocator, image, allocation);
             }
@@ -161,6 +279,8 @@ public:
             perMipViews.clear();
             perMipSampledViews.clear();
             attachmentViews.clear();
+            alternateSampledViews.clear();
+            storageImageViews.clear();
             image = VK_NULL_HANDLE;
             allocation = nullptr;
             layout = VK_IMAGE_LAYOUT_UNDEFINED;
@@ -174,6 +294,9 @@ public:
             aspect = VK_IMAGE_ASPECT_NONE;
             viewType = VK_IMAGE_VIEW_TYPE_2D;
             sampleCount = VK_SAMPLE_COUNT_1_BIT;
+            imageCreateFlags = 0;
+            usageFlags = 0;
+            storageUsageResolved = false;
             syncedTextureParamsVersion = 0;
             syncedContentVersion = 0;
             syncedMipLevelCount = 0;
@@ -190,6 +313,18 @@ public:
     Bool Initialize(const InitInfo& initInfo);
     void Shutdown();
     void BeginFrame(Uint32 frameIndex);
+    // Submits the accumulated texture-upload batch (one command buffer, one
+    // vkQueueSubmit, one pooled fence) if any uploads are pending. MUST run
+    // before any other vkQueueSubmit on the shared graphics queue whose
+    // commands may consume an image the batch writes - the frame command
+    // buffer submit (mid-frame flush, readback, Present) and the
+    // preserve-on-recreate copy are the existing callers. No-op when the
+    // batch is empty.
+    void FlushPendingUploads();
+    // Drains every frame slot's deferred image/view releases. Only valid when
+    // the caller has proven every queue submission complete; used by the
+    // present-less frame-boundary drain.
+    void CollectAllDeferredReleases();
 
     TextureResource* SyncTextureAndGetDescriptor(
         MG_State::GLState::ITextureObject& texture);
@@ -198,6 +333,9 @@ public:
                                                     Uint32 baseArrayLayer, Uint32 layerCount,
                                                     VkImageViewType viewType);
     VkImageView GetOrCreateSampledViewAtMipLevel(MG_State::GLState::ITextureObject& texture, Uint32 mipLevel);
+    VkImageView GetOrCreateSampledImageView(MG_State::GLState::ITextureObject& texture, VkFormat format);
+    VkImageView GetOrCreateStorageImageView(MG_State::GLState::ITextureObject& texture, Uint32 mipLevel,
+                                            VkFormat format, Bool layered, Int32 layer);
     void UpdateTrackedImageLayout(MG_State::GLState::ITextureObject* texture, VkImageLayout newLayout);
     void UpdateTrackedImageLayoutAfterAttachmentWrite(VkCommandBuffer commandBuffer,
                                                       MG_State::GLState::ITextureObject* texture,
@@ -206,7 +344,45 @@ public:
     Bool TransitionTextureForSampling(VkCommandBuffer commandBuffer, MG_State::GLState::ITextureObject& texture);
     Bool TransitionTextureForStorageImage(VkCommandBuffer commandBuffer, MG_State::GLState::ITextureObject& texture);
 
+    // Recording-generation bookkeeping for the pre-pass command stream. The
+    // generation advances every time the frame command buffer (re)begins
+    // recording; a resource whose stamp does not match was not referenced by
+    // any command in the open recording, so its out-of-pass work may safely
+    // execute ahead of the whole recording (in the pre command buffer).
+    void AdvanceRecordingGeneration() { ++m_recordingGeneration; }
+    void StampResourceRecordingUse(TextureResource& resource) const {
+        resource.lastRecordingGeneration = m_recordingGeneration;
+    }
+    // Map-lookup variant for callers that only hold the GL texture object.
+    void StampTextureRecordingUse(MG_State::GLState::ITextureObject* texture);
+    Bool WasTouchedThisRecording(const TextureResource& resource) const {
+        return resource.lastRecordingGeneration == m_recordingGeneration;
+    }
+    // Records that this texture is bound to a GL image unit, so its image must carry
+    // VK_IMAGE_USAGE_STORAGE_BIT. Must be called before NeedsStorageImagePreparation, and
+    // therefore before the render pass is committed: an image that has to be upgraded is
+    // recreated, which is illegal inside a render pass. Sticky for the texture's lifetime -
+    // GL lets an image binding come and go, and re-creating the image every time it does
+    // would cost far more than the compression it wins back.
+    void MarkStorageImageTexture(MG_State::GLState::ITextureObject& texture);
+    // True when this texture is marked but its live image predates the mark, i.e. the next sync
+    // will recreate it with STORAGE usage and copy the old contents forward. Callers use this to
+    // submit their pending recording first, so that copy cannot read pre-flush content.
+    Bool NeedsStorageUsageUpgrade(MG_State::GLState::ITextureObject& texture) const;
+    // The same ordering question for the other recreate-and-preserve trigger: true when this
+    // texture's live image carries a shorter mip chain than a full one, so defining the missing
+    // levels recreates it and copies the old contents forward.
+    Bool NeedsMipChainGrowth(MG_State::GLState::ITextureObject& texture) const;
+    // Non-mutating probe for the per-draw storage-image fast path: true when preparing this
+    // texture as a storage image may need work that is illegal inside a render pass (resource
+    // creation, dirty-content upload, or a layout transition to GENERAL). Unknown state reports
+    // true - a false positive merely ends the render pass, a false negative would skip a barrier.
+    Bool NeedsStorageImagePreparation(MG_State::GLState::ITextureObject& texture) const;
+
     static VkImageAspectFlags ResolveSampledImageViewAspectMask(VkImageAspectFlags imageAspect);
+    static VkFormat ResolveSampledImageViewFormat(VkFormat imageFormat, SamplerNumericDomain numericDomain);
+    static Bool AreSampledImageViewFormatsCompatible(VkFormat imageFormat, VkFormat viewFormat);
+    static Bool AreStorageImageViewFormatsCompatible(VkFormat imageFormat, VkFormat viewFormat);
 
     static Bool TransitionImageLayout(VkCommandBuffer commandBuffer, VkImage image, VkImageLayout& trackedLayout,
                                VkImageLayout newLayout, VkPipelineStageFlags srcStageMask,
@@ -243,6 +419,9 @@ public:
 private:
     // Bumped in SyncTextureResource right after vmaCreateImage(texture). See GetTextureImageEpoch().
     Uint64 m_textureImageEpoch = 1;
+    // See AdvanceRecordingGeneration. Starts above every resource's default
+    // stamp of 0 so a fresh resource counts as untouched.
+    Uint64 m_recordingGeneration = 1;
 
     Bool SyncTexture(MG_State::GLState::ITextureObject &texture,
                      TextureResource &outResource);
@@ -255,7 +434,8 @@ private:
                                 VkImageViewType viewType, Uint32 baseMipLevel, Uint32 levelCount,
                                 Uint32 baseArrayLayer,
                                 Uint32 layerCount,
-                                const VkComponentMapping* components = nullptr) const;
+                                const VkComponentMapping* components = nullptr,
+                                VkImageUsageFlags viewUsage = 0) const;
     Bool UploadDirtyMipLevels(MG_State::GLState::TextureObjectMipmap &mipmapTexture,
                       TextureUploadTarget uploadTarget,
                       TextureResource &outResource);
@@ -272,18 +452,31 @@ private:
     void DeferViewRelease(VkImageView view);
     void CollectDeferredReleases(Uint32 frameIndex);
     void DestroyDeferredReleases();
+    // Frees the fence/command buffer/staging buffer of every in-flight texture
+    // upload whose fence has signaled (submission order = completion order on
+    // the single queue, so the scan stops at the first still-pending entry).
+    // waitAll blocks on every entry - Shutdown's drain.
+    void ReclaimCompletedUploads(Bool waitAll = false);
     static TextureIdentity MakeTextureIdentity(MG_State::GLState::ITextureObject* texture);
     void EraseTrackedTexture(const TextureIdentity& identity);
     void PruneStaleTextureAliases(MG_State::GLState::ITextureObject* texture);
+    SizeT PruneDeadTextures();
 
     VkDevice m_device = VK_NULL_HANDLE;
     VkPhysicalDevice m_physicalDevice = VK_NULL_HANDLE;
     VmaAllocator m_allocator = nullptr;
     VkCommandPool m_commandPool = VK_NULL_HANDLE;
+    // Dedicated pool for the recycled upload-batch command buffers (see
+    // InitInfo::graphicsQueueFamilyIndex).
+    VkCommandPool m_uploadCommandPool = VK_NULL_HANDLE;
     VkQueue m_graphicsQueue = VK_NULL_HANDLE;
+    Bool m_imageFormatListSupported = false;
     Uint32 m_currentFrameIndex = 0;
 
     Uint8 m_gcCounter = 0;
+    // Frame-boundary GC gate: counts BeginFrame calls, not draws, so texture churn
+    // through non-draw paths (FBO clears, readbacks) still reaches the prune.
+    Uint32 m_gcFrameCounter = 0;
     // Active only between BeginDrawSyncScope/EndDrawSyncScope; identities of
     // textures already fully synced in the current draw (small N -> flat scan).
     Bool m_drawSyncScopeActive = false;
@@ -296,9 +489,92 @@ private:
         TextureResource* resource = nullptr;
     };
     Vector<DrawSyncedTexture> m_drawSyncedThisDraw;
+    // Cross-draw sampled-texture memo: the same few textures (atlas, lightmap)
+    // are resolved on every draw, so cache their resource pointers and skip the
+    // alive/resource map lookups. Node-based std::unordered_map keeps the
+    // pointees stable across inserts; erases bump m_resourceEraseEpoch, which
+    // every memo entry must match. SyncTexture still runs on memo hits, so
+    // content/param freshness is unaffected. A dead-then-reused texture address
+    // cannot false-hit: the new object carries a new lifetime id.
+    struct SyncedTextureMemoEntry {
+        const MG_State::GLState::ITextureObject* texture = nullptr;
+        Uint64 lifetimeId = 0;
+        Uint64 eraseEpoch = 0;
+        TextureResource* resource = nullptr;
+    };
+    static constexpr Uint32 kSyncedTextureMemoSize = 8;
+    SyncedTextureMemoEntry m_syncedTextureMemo[kSyncedTextureMemoSize];
+    Uint32 m_syncedTextureMemoNext = 0;
+    Uint64 m_resourceEraseEpoch = 1;
+    // Formats whose mutable-image probe failed on this device; their images are created
+    // without MUTABLE_FORMAT_BIT so repeat syncs neither re-probe nor flag-mismatch.
+    std::unordered_set<VkFormat> m_mutableFormatUnsupported;
+    // Formats whose 3D images refused VK_IMAGE_CREATE_2D_ARRAY_COMPATIBLE_BIT. Per format+usage,
+    // exactly like the mutable-format verdict above, so it is answered at image creation and
+    // remembered rather than probed once globally.
+    std::unordered_set<VkFormat> m_2dArrayCompatibleUnsupported;
     std::unordered_map<TextureIdentity, WeakPtr<MG_State::GLState::ITextureObject>, TextureIdentityHash> m_aliveObjects;
     std::unordered_map<TextureIdentity, TextureResource, TextureIdentityHash> m_textureResources;
+    // Textures that have been bound to a GL image unit (see MarkStorageImageTexture).
+    std::unordered_set<TextureIdentity, TextureIdentityHash> m_storageImageTextures;
+    // Supported multisample counts per format, so repeat texture syncs do not
+    // re-query vkGetPhysicalDeviceImageFormatProperties.
+    std::unordered_map<VkFormat, VkSampleCountFlags> m_multisampleCountsByFormat;
     Vector<Vector<TextureResource>> m_deferredReleases;
     Vector<Vector<VkImageView>> m_deferredViewReleases;
+
+    // --- Batched upload machinery ---
+    // Uploads within a frame are recorded into ONE shared command buffer and
+    // submitted with ONE vkQueueSubmit at FlushPendingUploads (the renderer
+    // flushes before every frame-command-buffer submit). Staging memory comes
+    // from a pool of persistently-mapped, reusable blocks instead of a
+    // vmaCreateBuffer per upload.
+    struct UploadStagingBlock {
+        VkBuffer buffer = VK_NULL_HANDLE;
+        VmaAllocation allocation = nullptr;
+        Uint8* mapped = nullptr; // persistently mapped for the block's lifetime
+        VkDeviceSize capacity = 0;
+        VkDeviceSize cursor = 0; // bump cursor while the block backs the open batch
+    };
+    // Opens the batch command buffer lazily (allocates/reuses + begins recording).
+    VkCommandBuffer EnsureUploadBatchOpen();
+    // Bump-allocates `size` staging bytes for the open batch, growing onto a
+    // new/pooled block when the current one cannot fit. Returns the write
+    // pointer; outBuffer/outBaseOffset locate the space for copy commands.
+    Uint8* AcquireUploadStagingSpace(VkDeviceSize size, VkBuffer& outBuffer, VkDeviceSize& outBaseOffset);
+    void RecycleUploadStagingBlock(UploadStagingBlock&& block);
+    // Drops a recorded-but-unsubmitted batch on the floor. Shutdown only: the
+    // device is being torn down, so the lost texel data is unobservable.
+    void DiscardPendingUploadBatch();
+    void DestroyUploadPools();
+
+    Vector<UploadStagingBlock> m_freeUploadStagingBlocks;
+    VkDeviceSize m_freeUploadStagingBytes = 0;
+    Vector<VkCommandBuffer> m_freeUploadCommandBuffers;
+    Vector<VkFence> m_freeUploadFences;
+    Bool m_uploadBatchOpen = false;
+    VkCommandBuffer m_uploadBatchCommandBuffer = VK_NULL_HANDLE;
+    // Blocks whose staging bytes the open batch's copies reference (last =
+    // the block the bump cursor is currently allocating from).
+    Vector<UploadStagingBlock> m_uploadBatchBlocks;
+    // Images the open batch writes; consulted for the rare re-upload-after-
+    // draw flush and by DeferResourceRelease (an unsubmitted command buffer
+    // referencing a deferred-released image would escape every fence-based
+    // destruction proof, so the batch is flushed before the image is parked).
+    Vector<VkImage> m_uploadBatchImages;
+    VkDeviceSize m_uploadBatchStagingBytes = 0;
+
+    // Texture uploads are submitted out-of-band but NOT waited on (waiting
+    // behind the queue serialized the CPU against the previous frame's GPU
+    // work every time an animated atlas re-uploaded). Each flushed batch's
+    // transients are parked here and RECYCLED (fence reset to the fence pool,
+    // command buffer reset to the CB pool, staging blocks back to the block
+    // pool) once the batch fence signals.
+    struct PendingUploadReclaim {
+        VkFence fence = VK_NULL_HANDLE;
+        VkCommandBuffer commandBuffer = VK_NULL_HANDLE;
+        Vector<UploadStagingBlock> stagingBlocks;
+    };
+    Vector<PendingUploadReclaim> m_pendingUploadReclaims;
 };
 } // namespace MobileGL::MG_Backend::DirectVulkan

MobileGL/MG_Backend/DirectVulkan/Renderer/VulkanRenderer.h

@@ -51,6 +51,12 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         Uint32 instanceCount = 1;
         Uint32 firstVertex = 0;
         Uint32 firstInstance = 0;
+        // Indexed-draw metadata for bounding vertex-stream conversion. baseVertex is the
+        // draw's base-vertex offset; indexRangeIsExactView is true only when the draw
+        // fetches exactly the indices its IndexBufferView describes (direct DrawElements;
+        // multi/indirect forms leave it false because the CPU cannot bound their ranges).
+        Int32 baseVertex = 0;
+        Bool indexRangeIsExactView = false;
     };
 
     struct DrawIndexedCmdParam {
@@ -70,6 +76,10 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         GLenum indexType = GL_UNSIGNED_SHORT;
         SizeT indexByteOffset = 0;
         SizeT indexByteSize = 0;
+        // Interpret indexByteOffset as a raw client pointer even when an element
+        // array buffer is bound (backend-synthesized index lists, e.g. the
+        // GL_LINE_LOOP -> LINE_STRIP rewrite).
+        Bool forceClientMemory = false;
     };
 
     struct DrawIndexedCmd {
@@ -108,7 +118,10 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         }
     };
 
-    class VulkanRenderer : public IBufferCopyCommandProvider, public FrameContext::IRecordingObserver {
+    class VulkanRenderer : public IBufferCopyCommandProvider,
+                           public FrameContext::IRecordingObserver,
+                           public VkRenderPassManager::IEvictionObserver,
+                           public ProgramFactory::IEvictionObserver {
     public:
         VulkanRenderer(NativeWindowType window, const VulkanRendererConfig& cfg = {});
         ~VulkanRenderer();
@@ -125,12 +138,42 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         // recording, before any render pass.
         void OnFrameCommandRecordingBegan(VkCommandBuffer commandBuffer) override;
 
+        // VkRenderPassManager::IEvictionObserver: the render-pass aging sweep just
+        // destroyed these VkRenderPasses; evict every graphics pipeline hashed on a
+        // dying handle (they share its >1024-boundary idleness, so immediate
+        // destruction is safe) and drop the last-pipeline memo if any went.
+        void OnRenderPassesDestroyed(const Vector<VkRenderPass>& renderPasses) override;
+
+        // ProgramFactory::IEvictionObserver: an aged-out program entry was
+        // destroyed; evict its compute pipeline and graphics pipelines (same
+        // idleness guarantee - they are only bound through draws/dispatches that
+        // stamp the program entry) and purge the descriptor-set cache entries
+        // keyed by its now-recyclable VkDescriptorSetLayout handle.
+        void OnProgramEvicted(ProgramFactory::HashType programHash,
+                              VkDescriptorSetLayout descriptorSetLayout) override;
+
         Bool SetupDraw(FrameContext::FrameData& frame, GLenum mode, Flags<DrawSetupAspect> aspects,
                        const DrawCmdParam& drawParams,
                        const IndexBufferView* pIndexBufferView = nullptr);
+        // ANGLE-style consecutive-draw fast path: SetupDraw snapshots the fully
+        // resolved draw configuration; the next draw whose cheap version/identity
+        // checks all match skips the resolution half (LOD probe, sampled-set
+        // walk, render-pass and pipeline resolution) and jumps straight to the
+        // per-draw tail. Returns false (leaving no side effects that the full
+        // path cannot redo idempotently) whenever anything might have changed.
+        Bool TrySetupDrawFastPath(FrameContext::FrameData& frame, GLenum mode, Flags<DrawSetupAspect> aspects,
+                                  const DrawCmdParam& drawParams, const IndexBufferView* pIndexBufferView);
         void ClearAttachmentsOnActiveRenderPass(VkCommandBuffer commandBuffer,
                                                 const RenderPassEntry& compatibleRenderPassEntry);
 
+        enum class ScissoredClearPrep {
+            NotNeeded,  // scissor covers the whole target — take the deferred whole-surface path instead
+            NoOp,       // nothing to clear (degenerate target or empty scissor rect)
+            Ready,      // a render pass is active; record vkCmdClearAttachments with the returned rect
+        };
+        ScissoredClearPrep PrepareScissoredClear(const MG_State::GLState::FramebufferObject& framebuffer,
+                                                 VkClearRect& outClearRect);
+
         void Clear(GLbitfield mask);
         void ClearBufferfi(GLenum buffer, GLint drawbuffer, GLfloat depth, GLint stencil);
         void ClearBufferfv(GLenum buffer, GLint drawbuffer, const GLfloat* value);
@@ -138,6 +181,10 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         void ClearBufferiv(GLenum buffer, GLint drawbuffer, const GLint* value);
         void ClearNamedFramebufferfv(const SharedPtr<MG_State::GLState::FramebufferObject>& framebuffer,
                                      GLenum buffer, GLint drawbuffer, const GLfloat* value);
+        void ClearNamedFramebufferiv(const SharedPtr<MG_State::GLState::FramebufferObject>& framebuffer,
+                                     GLenum buffer, GLint drawbuffer, const GLint* value);
+        void ClearNamedFramebufferuiv(const SharedPtr<MG_State::GLState::FramebufferObject>& framebuffer,
+                                      GLenum buffer, GLint drawbuffer, const GLuint* value);
         void ClearNamedFramebufferfi(const SharedPtr<MG_State::GLState::FramebufferObject>& framebuffer,
                                      GLenum buffer, GLint drawbuffer, GLfloat depth, GLint stencil);
         void BlitFramebuffer(GLint srcX0, GLint srcY0, GLint srcX1, GLint srcY1,
@@ -157,6 +204,30 @@ namespace MobileGL::MG_Backend::DirectVulkan {
                               GLsizei srcWidth, GLsizei srcHeight, GLsizei srcDepth);
         void GenerateMipmap(GLenum target);
         void ReadPixels(GLint x, GLint y, GLsizei width, GLsizei height, GLenum format, GLenum type, void* pixels);
+        // GL_DEPTH_COMPONENT / GL_DEPTH_STENCIL / GL_STENCIL_INDEX readback from the
+        // read framebuffer's depth/stencil attachment (per-aspect buffer copies with
+        // CPU repacking into the requested client layout).
+        void ReadDepthStencilPixels(MG_State::GLState::FramebufferObject& readFbo, GLint x, GLint y, GLsizei width,
+                                    GLsizei height, GLenum format, GLenum type, void* pixels);
+        // Copy-and-repack core shared by depth-stencil ReadPixels and GetTexImage;
+        // expects command recording to be active and any render pass already ended.
+        void ReadDepthStencilImageToClient(VkImage image, VkFormat vkFormat, VkImageLayout* trackedLayout,
+                                           VkImageAspectFlags imageAspect, Uint32 mipLevel, Uint32 baseArrayLayer,
+                                           GLint x, GLint y, GLsizei width, GLsizei height, GLenum format, GLenum type,
+                                           void* pixels);
+        // Same-extent depth blit between images of different depth formats: host
+        // round-trip with a per-texel re-encode (see BlitNamedFramebuffer).
+        Bool BlitDepthAcrossFormats(FrameContext::FrameData& frame, VkImage srcImage, VkFormat srcFormat,
+                                    VkImageLayout* srcTrackedLayout, Uint32 srcMipLevel, Uint32 srcBaseArrayLayer,
+                                    VkImage dstImage, VkFormat dstFormat, VkImageLayout* dstTrackedLayout,
+                                    Uint32 dstMipLevel, Uint32 dstBaseArrayLayer, GLint srcX, GLint srcY, GLint dstX,
+                                    GLint dstY, GLint width, GLint height, VkImageLayout srcRestoreLayout,
+                                    VkImageLayout dstRestoreLayout, Bool stencilAspect);
+        static SizeT GetReadbackTexelSize(VkFormat sourceFormat);
+        static Bool ConvertReadbackPixels(const Uint8* sourcePixels, VkFormat sourceFormat,
+                                          GLsizei width, GLsizei height, GLenum destinationFormat,
+                                          GLenum destinationType, SizeT destinationRowStride,
+                                          Uint8* destinationPixels);
         void GetTexImage(GLenum target, GLint level, GLenum format, GLenum type, GLvoid* pixels);
         void GetTextureImage(const SharedPtr<MG_State::GLState::ITextureObject>& texture,
                              TextureUploadTarget uploadTarget, GLint level, GLenum format, GLenum type,
@@ -219,6 +290,9 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         // frontend. Timestamp support (queue timestampValidBits > 0 and a
         // non-zero timestampPeriod) is cached at device creation.
         Bool IsTimerQuerySupported() const;
+        // The samplerAnisotropy device feature was granted, so GL_TEXTURE_MAX_ANISOTROPY_EXT is
+        // honored rather than accepted-and-ignored.
+        Bool IsSamplerAnisotropySupported() const { return m_samplerAnisotropyFeatureEnabled; }
         // Ensures the frame command buffer is recording (same lazy pattern as
         // SetupDraw) and writes a bottom-of-pipe timestamp into the current
         // frame's pool. Null when unsupported or the pool is exhausted.
@@ -234,10 +308,35 @@ namespace MobileGL::MG_Backend::DirectVulkan {
                                       const VkTimerQueryManager::TimestampRecord& end) const;
         Uint64 GetTimerQueryTimestampNs(const VkTimerQueryManager::TimestampRecord& record) const;
 
+        // GL_SAMPLES_PASSED occlusion queries: every app draw between Start and Stop is
+        // wrapped in a Vulkan occlusion query slot; the result is the slot sum. Requires
+        // hostQueryReset for slot recycling - Start fails (frontend keeps the query
+        // unsupported) when the device lacks it.
+        Bool StartOcclusionQueryCapture();
+        void StopOcclusionQueryCapture(Vector<Uint32>& outSlots);
+        // Flushes pending commands, waits, sums the slots, and recycles them.
+        Bool ResolveOcclusionQueryResult(const Vector<Uint32>& slots, Uint64& outSamples);
+
         void RequestSwapchainResize(Uint32 width, Uint32 height);
-        void RecreateSwapchain();
+        // Re-query the surface and report whether the live swapchain no longer matches it
+        // (size or orientation). This - not a VK_SUBOPTIMAL_KHR result - is what decides a
+        // rebuild, so a surface the driver merely considers suboptimal cannot thrash.
+        Bool SwapchainIsOutOfDate();
+        // Returns false when the surface is zero-area (minimized/hidden window):
+        // no new swapchain is installed and presentation must stay suspended.
+        Bool RecreateSwapchain();
 
     private:
+        // Tiered emission for an already-set-up multi-draw batch (state bound, index
+        // buffer bound for the indexed form). Tier 1: VK_EXT_multi_draw. Tier 2: one
+        // vkCmdDraw(Indexed)Indirect over a transient command array. Tier 3: unrolled
+        // vkCmdDraw(Indexed) loop. Tier eligibility is per-batch (uniform instance
+        // state for tier 1, firstInstance/feature legality for tier 2); every tier
+        // consumes the same param span, so contiguous-run merging done by the caller
+        // benefits all of them.
+        void EmitMultiDrawIndexed(VkCommandBuffer commandBuffer, const DrawIndexedCmdParam* pParams, Uint32 drawCount);
+        void EmitMultiDraw(VkCommandBuffer commandBuffer, const DrawCmdParam* pParams, Uint32 drawCount);
+
         struct BlitUniformData {
             float srcRect[4] = {0.f, 0.f, 1.f, 1.f};
             float dstRect[4] = {0.f, 0.f, 1.f, 1.f};
@@ -275,6 +374,10 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         void QueueClearBufferPayloadForFramebuffer(const MG_State::GLState::FramebufferObject& framebuffer,
                                                   GLenum buffer, GLint drawbuffer,
                                                   const ClearAttachmentPayload& clearPayload);
+        void RecordScissoredClearBuffer(const MG_State::GLState::FramebufferObject& framebuffer,
+                                        GLenum buffer, GLint drawbuffer,
+                                        const ClearAttachmentPayload& clearPayload,
+                                        const VkClearRect& clearRect);
 
         // ---- Submission fence tracking (GL sync objects) ----
         // One record per vkQueueSubmit still in flight, in ascending submit
@@ -317,24 +420,61 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         VkFence AcquirePooledSubmitFence();
         void DestroySubmitFencePool();
         Bool HasPendingRecordedWork() const;
+        // Frame-boundary housekeeping for paths that never reach Present's
+        // tail (present-less readback loops, suspended presentation, blocking
+        // sync waits): runs the same per-frame drains Present performs, but
+        // only when every queue submission has been observed complete AND no
+        // recorded-but-unsubmitted commands exist - i.e. when CPU-GPU overlap
+        // is provably already zero. Never blocks (non-blocking fence poll
+        // only), so the presenting path's frames-in-flight pipelining is
+        // untouched. Returns true when the drain ran.
+        Bool TryDrainFrameTransients();
 
         Vector<SubmitRecord> m_inFlightSubmits;
         Vector<VkFence> m_freeSubmitFences;
         Uint64 m_submitCounter = 0;
         Uint64 m_completedSubmitCounter = 0;
+        // Drains since the last Present, gating the drain's frame-boundary-equivalent
+        // work (arena rewind + cache aging): a presenting app's mid-frame
+        // readbacks/waits must neither churn the transient caches nor accelerate the
+        // aging clocks, while present-less loops still cross a boundary every few
+        // iterations. Reset in Present.
+        Uint32 m_drainsSinceLastPresent = 0;
 
         NativeWindowType m_window = 0;
         void* m_platformDisplay = nullptr;
         void* m_platformLibrary = nullptr;
         void* m_platformCloseDisplay = nullptr;
+        // Some real ICDs (e.g. NVIDIA's proprietary Linux driver) don't implement
+        // VK_EXT_headless_surface at all. Detected once in CreateInstance() from the
+        // enumerated instance extensions; when false, CreateSurface() falls back to a
+        // hidden Xlib window instead of vkCreateHeadlessSurfaceEXT.
+        Bool m_headlessSurfaceSupported = true;
+        // Set when CreateSurface() had to create its own Xlib window for the fallback
+        // above (rather than being handed one by the caller), so Shutdown() knows it
+        // owns that window and must destroy it.
+        Bool m_ownsFallbackXlibWindow = false;
+        // Android has the same shortfall: no Mali/Adreno driver seen so far exposes
+        // VK_EXT_headless_surface, so a windowless (EGL pbuffer) context gets an
+        // AImageReader's ANativeWindow to hand the WSI instead. Nothing is ever
+        // displayed - the reader's images are simply never acquired. Owned here, so
+        // Shutdown() deletes it.
+        void* m_fallbackImageReader = nullptr;
         VulkanRendererConfig m_config;
         Bool m_swapchainResizeRequested = false;
+        // Presentation is suspended while the window is zero-area (minimized): the
+        // swapchain is unusable/out of date, so Present drops frames instead of
+        // submitting on a signaled fence / presenting never-acquired images.
+        Bool m_presentSuspended = false;
 
         // Vulkan objects
         Bool m_validationLayersEnabled = false;
         Vector<VkExtensionProperties> m_extensions;
         VkInstance m_instance = VK_NULL_HANDLE;
         VkDebugUtilsMessengerEXT m_debugMessenger = VK_NULL_HANDLE;
+        // Fallback reporting channel for drivers that ship the validation layers but
+        // only expose the older VK_EXT_debug_report (Adreno 650 / Vulkan 1.1.128).
+        VkDebugReportCallbackEXT m_debugReportCallback = VK_NULL_HANDLE;
         PhysicalDevice m_physicalDevice;
         VkDevice m_device = VK_NULL_HANDLE;
         VmaAllocator m_allocator = nullptr;
@@ -347,8 +487,28 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         Bool m_indexTypeUint8ExtensionEnabled = false;
         Bool m_logicOpFeatureEnabled = false;
         Bool m_multiDrawIndirectFeatureEnabled = false;
+        // drawIndirectFirstInstance gates indirect commands whose firstInstance != 0;
+        // cached at device creation because the tier-2 multi-draw path (a transient
+        // VkDrawIndexedIndirectCommand array) is illegal for such a sub-draw without it.
+        Bool m_drawIndirectFirstInstanceFeatureEnabled = false;
+        // VK_EXT_multi_draw: native batched submission for the CPU-side glMultiDraw*
+        // families (tier 1 of the multi-draw dispatch).
+        Bool m_multiDrawExtensionEnabled = false;
+        Uint32 m_maxMultiDrawCount = 0;
+        // Multi-draw dispatch tiers, resolved once at device creation from device support
+        // clamped by MOBILEGL_MAGMA_MULTIDRAW_MODE (a preference, never a demand):
+        //   tier 1 (ext):      one vkCmdDrawMulti(Indexed)EXT           - m_multiDrawAllowExt
+        //   tier 2 (indirect): one vkCmdDraw(Indexed)Indirect batch     - m_multiDrawAllowIndirect
+        //   tier 3 (unroll):   one vkCmdDraw(Indexed) per sub-draw      - always available
+        // m_multiDrawForceUnrollIndirect additionally forces the GPU-parameter
+        // glMultiDraw*Indirect paths onto their per-command loop (mode=unroll only).
+        Bool m_multiDrawAllowExt = false;
+        Bool m_multiDrawAllowIndirect = false;
+        Bool m_multiDrawForceUnrollIndirect = false;
+        Bool m_samplerAnisotropyFeatureEnabled = false;
         Bool m_shaderDrawParametersExtensionEnabled = false;
         Bool m_shaderDrawParametersFeatureEnabled = false;
+        Bool m_unformattedFloatStorageImagesEnabled = false;
         // fillModeNonSolid gates VK_POLYGON_MODE_LINE/_POINT (glPolygonMode); independentBlend gates
         // per-draw-buffer color write masks (glColorMaski). Both are cached at device creation and
         // drive a runtime fallback when the device lacks them.
@@ -359,6 +519,13 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         // needs no feature). Both cached at device creation and drive a hard-fail-at-draw when absent.
         Bool m_dualSrcBlendFeatureEnabled = false;
         Bool m_primitiveTopologyListRestartFeatureEnabled = false;
+        // Union of shader stages sampled-read barriers may name; built at device creation
+        // because geometry/tessellation stage bits are invalid in a barrier when their
+        // feature is off (VUID-vkCmdPipelineBarrier-srcStageMask-04090/-04091), and
+        // ALL_GRAPHICS would also serialize against non-shader stages.
+        VkPipelineStageFlags m_sampledReadStageMask = VK_PIPELINE_STAGE_VERTEX_SHADER_BIT |
+                                                      VK_PIPELINE_STAGE_FRAGMENT_SHADER_BIT |
+                                                      VK_PIPELINE_STAGE_COMPUTE_SHADER_BIT;
         // Cached at device creation from the graphics queue family properties
         // and device limits; drives timer-query support.
         Uint32 m_timestampValidBits = 0;
@@ -369,6 +536,102 @@ namespace MobileGL::MG_Backend::DirectVulkan {
                                                                  VkDeviceSize countBufferOffset, Uint32 maxDrawCount,
                                                                  Uint32 stride);
         static inline PFNDrawIndexedIndirectCountFunc s_vkCmdDrawIndexedIndirectCount = nullptr;
+        // VK_EXT_multi_draw entry points, loaded at device creation when the extension
+        // (and its multiDraw feature) is enabled; null otherwise.
+        static inline PFN_vkCmdDrawMultiEXT s_vkCmdDrawMultiEXT = nullptr;
+        static inline PFN_vkCmdDrawMultiIndexedEXT s_vkCmdDrawMultiIndexedEXT = nullptr;
+
+        // VK_EXT_transform_feedback (GL transform feedback capture)
+        Bool m_transformFeedbackFeatureEnabled = false;
+        // VK_EXT_provoking_vertex. Vulkan's built-in convention is "provoking vertex first"; GL's
+        // default is LAST_VERTEX_CONVENTION, and GL derives BOTH flat shading and the transform
+        // feedback vertex order from it. provokingVertexLast alone fixes flat shading and the
+        // input-assembler capture order and has no dependency on transform feedback; only
+        // transformFeedbackPreservesProvokingVertex does.
+        Bool m_provokingVertexLastEnabled = false;
+        // transformFeedbackPreservesProvokingVertex was actually enabled at device creation. Kept
+        // separate because it is the only thing that arms
+        // VUID-VkGraphicsPipelineCreateInfo-topology-04884, the rule that forbids a TRIANGLE_FAN
+        // pipeline from asking for LAST on a device that cannot preserve a fan's provoking vertex.
+        Bool m_provokingVertexXfbPreserveEnabled = false;
+        // provokingVertexModePerPipeline: when VK_FALSE every pipeline in one render pass instance
+        // must agree on the mode, so glProvokingVertex(GL_FIRST_VERTEX_CONVENTION) cannot be honoured
+        // per draw and every pipeline takes GL's default (LAST) instead.
+        Bool m_provokingVertexModePerPipeline = false;
+        // transformFeedbackPreservesTriangleFanProvokingVertex.
+        Bool m_provokingVertexFanPreserved = false;
+        // Per-pipeline provoking-vertex mode. capturesXfbFromGeometryStage must be a LINK-TIME
+        // property of the program, never the dynamic "is transform feedback active" flag: the
+        // 8-entry m_pipelineMemo and the SetupDrawSnapshot fast path key on programObj.hash and
+        // the pipeline-state value hash, neither of which moves when glBeginTransformFeedback is
+        // called, so a dynamic input here would hand back a stale VkPipeline.
+        VkProvokingVertexModeEXT SelectProvokingVertexMode(VkPrimitiveTopology topology,
+                                                          Bool capturesXfbFromGeometryStage) const;
+        // VK_EXT_vertex_attribute_divisor: without it every non-zero glVertexAttribDivisor
+        // behaves as 1, because that is all Vulkan's instance input rate can express.
+        Bool m_vertexAttributeDivisorEnabled = false;
+        static inline PFN_vkCmdBindTransformFeedbackBuffersEXT s_vkCmdBindTransformFeedbackBuffersEXT = nullptr;
+        static inline PFN_vkCmdBeginTransformFeedbackEXT s_vkCmdBeginTransformFeedbackEXT = nullptr;
+        static inline PFN_vkCmdEndTransformFeedbackEXT s_vkCmdEndTransformFeedbackEXT = nullptr;
+        // Counter buffers (one 4-byte slot per capture binding) let consecutive
+        // draws within one glBeginTransformFeedback append GL-style. Transform feedback
+        // objects can each hold an open, paused span at the same time, so the counters are
+        // per object: one group of four slots each, handed out on first use.
+        static constexpr SizeT kXfbCounterObjectSlots = 16;
+        VkBufferObject m_xfbCounterBuffer;
+        UnorderedMap<Uint, Uint32> m_xfbCounterSlotByObject;
+        Uint32 m_xfbNextCounterSlot = 0;
+        // Set for a slot once a captured draw has been recorded into its span; selects
+        // counter-buffer resume on the next captured draw of the same span.
+        Array<Bool, kXfbCounterObjectSlots> m_xfbCountersValid{};
+        Array<Uint64, kXfbCounterObjectSlots> m_xfbLastSeenGeneration{};
+        // Counter slot group of the bound transform feedback object.
+        Uint32 CurrentXfbCounterSlot();
+        // Wraps a recorded draw with BeginTransformFeedbackEXT/EndTransformFeedbackEXT
+        // when GL transform feedback is active; binds capture buffers on demand.
+        Bool BeginXfbCaptureForDraw(FrameContext::FrameData& frame);
+        void EndXfbCaptureForDraw(FrameContext::FrameData& frame, Bool began);
+        // Makes the captured bytes visible to whatever reads them next. Deferred rather than
+        // recorded next to the capture, because the capturing draw runs inside a render pass
+        // that declares no self-dependency.
+        void MakeXfbWritesVisible();
+        Bool m_xfbWritesPendingVisibility = false;
+        // Wrap one app draw in an occlusion-query slot while a GL_SAMPLES_PASSED
+        // query is active. Returns whether a slot was begun (End must mirror it).
+        Bool BeginOcclusionForDraw(VkCommandBuffer commandBuffer);
+        void EndOcclusionForDraw(VkCommandBuffer commandBuffer, Bool began);
+        Bool m_occlusionQueryPreciseEnabled = false;
+        Bool m_hostQueryResetEnabled = false;
+        PFN_vkResetQueryPool s_vkResetQueryPool = nullptr;
+        VkQueryPool m_occlusionQueryPool = VK_NULL_HANDLE;
+        static constexpr Uint32 kOcclusionQuerySlots = 8192;
+        Uint32 m_occlusionSlotCursor = 0;
+        Bool m_occlusionCaptureActive = false;
+        Vector<Uint32> m_occlusionActiveSlots;
+        // Transform feedback primitive queries: one pool slot per captured draw yields
+        // the (written, needed) pair; GL_TRANSFORM_FEEDBACK_PRIMITIVES_WRITTEN sums the
+        // first, GL_PRIMITIVES_GENERATED the second - exact with geometry shaders,
+        // unlike the CPU fallback accounting.
+        Bool m_xfbQueriesSupported = false;
+        PFN_vkCmdBeginQueryIndexedEXT s_vkCmdBeginQueryIndexedEXT = nullptr;
+        PFN_vkCmdEndQueryIndexedEXT s_vkCmdEndQueryIndexedEXT = nullptr;
+        VkQueryPool m_xfbQueryPool = VK_NULL_HANDLE;
+        static constexpr Uint32 kXfbQuerySlots = 8192;
+        Uint32 m_xfbQuerySlotCursor = 0;
+        Bool m_xfbQueryCaptureActive[2] = {false, false}; // [0]=written, [1]=generated
+        Vector<Uint32> m_xfbQueryActiveSlots[2];
+        Bool m_xfbQuerySlotOpen = false;
+        Uint32 m_xfbQueryOpenSlot = 0;
+
+    public:
+        // kind: 0 = PRIMITIVES_WRITTEN, 1 = PRIMITIVES_GENERATED.
+        Bool StartXfbQueryCapture(Uint32 kind);
+        void StopXfbQueryCapture(Uint32 kind, Vector<Uint32>& outSlots);
+        Bool ResolveXfbQueryResult(const Vector<Uint32>& slots, Bool wantGenerated, Uint64& outPrimitives);
+
+    private:
+        void BeginXfbQueryForDraw(VkCommandBuffer commandBuffer);
+        void EndXfbQueryForDraw(VkCommandBuffer commandBuffer);
 
         VkCommandPool m_commandPool = VK_NULL_HANDLE;
 
@@ -382,14 +645,64 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         // gather + synthetic vertex-input rebuild + payload hash + lookup) when the full pipeline
         // state is unchanged from the previous draw. The key provably covers every pipeline field.
         // Reset per-frame and on pipeline destruction so the cached handle can never dangle.
-        Bool m_lastPipelineValid = false;
-        GLenum m_lastPipelineMode = 0;
-        Uint64 m_lastPipelineProgramHash = 0;
-        Uint64 m_lastPipelineVertexInputHash = 0;
-        Uint64 m_lastPipelineRenderPassHash = 0;
-        Uint m_lastPipelineRenderStateVersion = 0;
-        ProgramFactory::CompileOptionFlags m_lastPipelineTransformFlags = {};
-        VkPipeline m_lastPipelineResult = VK_NULL_HANDLE;
+        // Small N-way pipeline-resolution memo (round-robin replacement). A
+        // single-entry memo thrashed on draw sequences that alternate a few
+        // pipelines (GUI text/quad program ping-pong), paying the full
+        // payload-hash lookup per draw; eight entries cover such working sets
+        // while keeping the hit path a trivial linear scan.
+        struct PipelineMemoEntry {
+            GLenum mode = 0;
+            Uint64 programHash = 0;
+            Uint64 vertexInputHash = 0;
+            Uint64 renderPassHash = 0;
+            // VALUE hash of the pipeline-relevant fixed-function state (see
+            // ComputePipelineStateHash), not the monotonic pipeline-state version:
+            // the version never repeats, so a per-draw GL_BLEND toggle would miss
+            // all entries forever even though the state alternates between two
+            // values the memo already holds.
+            Uint64 pipelineStateHash = 0;
+            ProgramFactory::CompileOptionFlags transformFlags = {};
+            VkPipeline pipeline = VK_NULL_HANDLE;
+        };
+        static constexpr Uint32 kPipelineMemoSize = 8;
+        PipelineMemoEntry m_pipelineMemo[kPipelineMemoSize];
+        Uint32 m_pipelineMemoCount = 0;
+        Uint32 m_pipelineMemoNext = 0;
+        // Hash of every fixed-function GL state the pipeline payload reads that the
+        // memo key's other fields (mode / program / vertex input / render pass /
+        // transform flags) do not already pin down. Equal hash under an equal rest
+        // of key => byte-identical PipelineCreatePayload. Cached per pipeline-state
+        // version: the version is monotonic and bumps on every pipeline-state
+        // change, so an unchanged (version, colorAttachmentCount) proves the state
+        // bytes are unchanged and the hash can be reused without re-reading them.
+        Uint64 ComputePipelineStateHash(Uint32 colorAttachmentCount) const;
+        Uint m_pipelineStateHashVersion = 0;
+        Uint32 m_pipelineStateHashColorCount = 0;
+        Uint64 m_pipelineStateHash = 0;
+        Bool m_pipelineStateHashValid = false;
+        // GetShaderTransformFlags memo. NOT pure in the pre-transform alone: the
+        // function also reads whether the bound DRAW framebuffer is the default one
+        // (only the default framebuffer gets the Y-flip and rotation bits - an FBO
+        // pass renders unflipped). Keyed on BOTH inputs; missing the FBO bit shipped
+        // an upside-down default-framebuffer pass after any render-to-texture
+        // (minecraft-1.17-main-menu retrace, whole frame flipped).
+        VkSurfaceTransformFlagBitsKHR m_baseTransformFlagsPreTransform =
+            VK_SURFACE_TRANSFORM_FLAG_BITS_MAX_ENUM_KHR;
+        Bool m_baseTransformFlagsIsDefaultFbo = false;
+        Bool m_baseTransformFlagsKeyValid = false;
+        Uint32 m_baseTransformFlagsCache = 0;
+        // isDefaultFbo must be the default-ness of the CURRENTLY bound draw framebuffer;
+        // every caller already has it in hand from its own guards.
+        Uint32 GetBaseTransformFlagsRaw(Bool isDefaultFbo);
+        // Drops every memoized pipeline handle. Required at command-buffer
+        // boundaries and whenever any pipeline may have been destroyed. Also drops
+        // the cached pipeline-state hash: the same boundaries can retire the GL
+        // context whose monotonic version the cache is keyed on.
+        void InvalidatePipelineMemo() {
+            m_pipelineMemoCount = 0;
+            m_pipelineMemoNext = 0;
+            m_pipelineStateHashValid = false;
+        }
         UnorderedMap<ProgramFactory::HashType, VkPipeline> m_computePipelines;
         UniquePtr<ProgramFactory> m_programFactory;
         UniquePtr<UniformManager> m_uniformManager;
@@ -418,16 +731,326 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         ProgramFactory::CompileOptionFlags m_lastSampledSetTransformFlags = {};
         Uint64 m_lastSampledSetBindGeneration = 0;
 
+        // Memo for the per-draw explicit-LOD-0 eligibility probe
+        // (ProgramSamplesOnlySingleLevelTextures): same key family as the
+        // sampled-set memo, plus the sampled textures' params-version sum so a
+        // level-range or filter change re-probes. On a hit the resolved
+        // transform flags are reused, which also collapses the two
+        // GetOrCreateProgram lookups into one.
+        Bool m_lastLodDecisionValid = false;
+        Uint64 m_lastLodProgramLifetimeId = 0;
+        Uint32 m_lastLodProgramVersion = 0;
+        Uint64 m_lastLodBindGeneration = 0;
+        Uint64 m_lastLodParamsSum = 0;
+        ProgramFactory::CompileOptionFlags m_lastLodBaseFlags = {};
+        ProgramFactory::CompileOptionFlags m_lastLodResultFlags = {};
+
+        // Snapshot behind TrySetupDrawFastPath. Values only: the program and
+        // render-pass caches are open-addressing maps whose entries move on
+        // insert, so no pointers into them are cached; the pipeline handle is
+        // protected by the command-buffer-boundary reset plus the mid-frame
+        // pipeline-destruction resets, and monotonic epochs guard everything
+        // that can be destroyed or recreated between draws.
+        struct SetupDrawSnapshot {
+            Bool valid = false;
+            Uint8 aspects = 0;
+            GLenum mode = 0;
+            Uint64 programLifetimeId = 0;
+            Uint32 programVersion = 0;
+            const void* vao = nullptr;
+            // Same rule as VaoDrawMemo::vaoLifetimeId: (address, config version) is not an
+            // identity, because a recycled address can arrive carrying a config version
+            // the dead VAO also had (two mutations to configure one attribute is the
+            // common shape), and "the VAO did not move" would then skip the layout
+            // re-resolve for a different VAO.
+            Uint64 vaoLifetimeId = 0;
+            Uint32 vaoConfigVersion = 0;
+            const void* drawFbo = nullptr;
+            Uint16 fboVersion = 0;
+            Bool drawFboIsDefault = false;
+            Uint renderStateVersion = 0;
+            Uint64 bindGeneration = 0;
+            Uint32 baseTransformFlags = 0;
+            Uint32 resolvedTransformFlags = 0;
+            Uint64 renderPassHash = 0;
+            Uint32 imageIndex = 0;
+            Uint64 textureEraseEpoch = 0;
+            Uint64 textureImageEpoch = 0;
+            Uint64 renderbufferImageEpoch = 0;
+            Uint64 sampledContentSum = 0;
+            Uint64 sampledParamsSum = 0;
+            // Guards the sampler-descriptor reuse hint: bumped by any sampler-object
+            // parameter or texture shape change (see GetSamplingResolutionGeneration),
+            // none of which the sums above cover.
+            Uint64 samplingResolutionGeneration = 0;
+            // Render-pass flavor input (DepthTest || StencilTest at snapshot time).
+            // A pipeline-state change that leaves this equal cannot change which
+            // render pass GetOrCreateRenderPass would pick, so the fast path may
+            // re-resolve just the pipeline against the active pass; a change that
+            // flips it must fall back to the full path's pass selection.
+            Bool drawUsesDepthStencil = false;
+            IntVec2 renderPassExtent = {0, 0};
+            // colorAttachmentCount of the snapshotting draw's render pass: the
+            // pipeline-state hash input, so the fast path can refresh that hash and
+            // probe the pipeline memo after a state change without re-fetching the
+            // render-pass entry (the pass itself is pinned by renderPassHash above).
+            Uint32 renderPassColorCount = 0;
+            VkPipeline pipeline = VK_NULL_HANDLE;
+            // layoutHash of the snapshotting draw's vertex-input state. The pipeline and
+            // the vertex-input pre-flight depend on the VAO only through this (plus the
+            // program, pinned separately), so a changed VAO whose aux memo carries the
+            // same layoutHash re-uses the snapshot's pipeline and pre-flight verdict
+            // outright - the VAO-cycling case Minecraft chunk rendering hits every draw.
+            Uint64 vaoLayoutHash = 0;
+            // Memoised ProgramFactory entry of the snapshotting draw, valid while
+            // (programLifetimeId, programVersion, resolvedTransformFlags) match - all
+            // checked above - AND the factory's cache structure epoch is unchanged (the
+            // cache is open-addressing and holds entries by value, so any insert/erase
+            // moves them). The fast path must re-stamp use through StampProgramUse when
+            // it bypasses GetOrCreateProgram, or the idle sweep could evict a live entry.
+            const ProgramFactory::VkProgramObject* programObj = nullptr;
+            Uint64 programFactoryEpoch = 0;
+            // Per-entry copies of the snapshotting draw's sampled set (the scratch
+            // vectors below hold only the LAST full-path draw's set, which with more
+            // than one snapshot entry is not necessarily this entry's program).
+            // sampledTextures/sampledResources carry the same epoch-guarded pointer
+            // lifetime rules as the scratch originals: textureEraseEpoch (checked
+            // every probe) declines the entry before any erased resource pointer
+            // could be dereferenced. sampledLayouts is the layout VALUE each
+            // resource held when this entry's descriptors were built (the
+            // descriptor-reuse hint needs the SAME layout, not just a sampleable
+            // one), and sampledBindingRecords feeds SampledBindingsUnchanged when
+            // the bind generation moved.
+            Vector<MG_State::GLState::ITextureObject*> sampledTextures;
+            Vector<VkTextureManager::TextureResource*> sampledResources;
+            Vector<VkImageLayout> sampledLayouts;
+            Vector<UniformManager::SampledBindingRecord> sampledBindingRecords;
+        };
+        // Program-keyed snapshot entries: program ping-pong (Sodium switches programs
+        // mid-frame every few draws) would otherwise evict the single snapshot on
+        // every switch and send every draw through the full path. Entries are found
+        // by programLifetimeId (MRU-first probe); every other guard stays per-probe,
+        // so a stale entry declines itself exactly like the old single snapshot did.
+        static constexpr Uint32 kSetupDrawSnapshotCount = 4;
+        SetupDrawSnapshot m_setupDrawSnapshots[kSetupDrawSnapshotCount];
+        Uint32 m_setupDrawSnapshotMru = 0;    // last entry that hit or was filled
+        Uint32 m_setupDrawSnapshotVictim = 0; // round-robin fill cursor when all entries are live
+        void InvalidateSetupDrawSnapshots() {
+            for (auto& snapshot : m_setupDrawSnapshots) {
+                snapshot.valid = false;
+            }
+        }
+
         // Per-draw scratch buffers (clear keeps capacity) — these paths run for every
         // draw call and must not allocate.
         Vector<MG_State::GLState::ITextureObject*> m_sampledTexturesScratch;
+        // Per-binding (texture, effective sampler) lifetime-id records from the same
+        // CollectSampledTextures walk that filled m_sampledTexturesScratch. The fast
+        // path shadow-compares against them (SampledBindingsUnchanged) when the
+        // texture bind generation moved, so a redundant glBindSampler/glBindTexture
+        // storm that resolves to the same bindings keeps the fast path.
+        Vector<UniformManager::SampledBindingRecord> m_sampledBindingRecordsScratch;
+        // Parallel to m_sampledTexturesScratch, refilled by every SetupDraw's
+        // first sampled-texture loop: the resolved backend resources, so the
+        // post-transition loop can skip re-resolving textures whose layout is
+        // already sampleable.
+        Vector<VkTextureManager::TextureResource*> m_sampledResourcesScratch;
+        Vector<MG_State::GLState::ITextureObject*> m_storageImageTexturesScratch;
         Vector<VkBuffer> m_vertexBuffersScratch;
         Vector<VkDeviceSize> m_vertexOffsetsScratch;
         Vector<VkVertexInputAttributeDescription> m_patchedAttributesScratch;
+        Vector<Float> m_vertexConversionScratch;
+        Vector<Uint8> m_vertexRepackScratch;
+
+        struct ConvertedVertexStreamKey {
+            const MG_State::GLState::BufferObject* buffer = nullptr;
+            Uint64 changeSerial = 0;
+            SizeT baseOffset = 0;
+            Uint32 sourceStride = 0;
+            DataType type = DataType::Float32;
+            Int size = 0;
+            Bool normalized = false;
+            Bool isInteger = false;
+            VertexInputStateFactory::VertexStreamConversion conversion =
+                VertexInputStateFactory::VertexStreamConversion::None;
+
+            Bool operator==(const ConvertedVertexStreamKey& other) const {
+                return buffer == other.buffer && changeSerial == other.changeSerial &&
+                       baseOffset == other.baseOffset && sourceStride == other.sourceStride &&
+                       type == other.type && size == other.size && normalized == other.normalized &&
+                       isInteger == other.isInteger && conversion == other.conversion;
+            }
+        };
+
+        struct ConvertedVertexStreamKeyHash {
+            SizeT operator()(const ConvertedVertexStreamKey& key) const {
+                SizeT hash = std::hash<const void*>{}(key.buffer);
+                auto combine = [&hash](SizeT value) {
+                    hash ^= value + static_cast<SizeT>(0x9e3779b97f4a7c15ull) + (hash << 6) + (hash >> 2);
+                };
+                combine(std::hash<Uint64>{}(key.changeSerial));
+                combine(std::hash<SizeT>{}(key.baseOffset));
+                combine(std::hash<Uint32>{}(key.sourceStride));
+                combine(std::hash<Uint32>{}(static_cast<Uint32>(key.type)));
+                combine(std::hash<Int>{}(key.size));
+                combine(std::hash<Bool>{}(key.normalized));
+                combine(std::hash<Bool>{}(key.isInteger));
+                combine(std::hash<Uint32>{}(static_cast<Uint32>(key.conversion)));
+                return hash;
+            }
+        };
+
+        struct ConvertedVertexStream {
+            BufferSlice slice;
+            // Number of source elements the cached slice covers. A draw needing a prefix of
+            // this range reuses the slice (converted streams are tightly packed); a draw
+            // needing more reconverts and replaces the entry, so per (buffer, layout) a
+            // frame converts at most the largest range any draw asked for.
+            SizeT elementCount = 0;
+            // Pins the source buffer for the frame so its heap address cannot be reused by
+            // a new BufferObject while this pointer-keyed entry is alive.
+            SharedPtr<const MG_State::GLState::BufferObject> sourcePin;
+        };
+        UnorderedMap<ConvertedVertexStreamKey, ConvertedVertexStream, ConvertedVertexStreamKeyHash>
+            m_convertedVertexStreams;
+
+        // One VAO's resolved vkCmdBindVertexBuffers arguments, reusable by a later draw
+        // that would resolve them to the same thing. Consecutive draws in a chunk-renderer
+        // frame keep the program and the vertex layout and only swap the VAO, so a
+        // per-VAO memo turns the second and later draws through each VAO into a validate
+        // plus (usually skipped) rebind.
+        //
+        // Only whole-buffer bindings are memoised. Client-memory and format-converted
+        // streams re-upload from a range that depends on the draw's own vertex/index
+        // range, and synthetic bindings carry glVertexAttrib* values that are not part
+        // of any key here; a layout using any of them is never stored.
+        // Field order is hit-path cache locality, hot to cold: the per-draw validate
+        // reads the scalars and the EBO memo head, then only the first bindingCount
+        // elements of vkBuffers/vkOffsets; the per-binding revalidation arrays at the
+        // tail are touched once per frame at most.
+        struct ResolvedVertexBindings {
+            // Must equal DynamicStateShadow::kMaxShadowedVertexBindings (static_assert in
+            // the .cpp): past that width the bind shadow cannot skip a redundant bind
+            // either, so a wider layout resolves per draw. Minecraft-shaped layouts use four.
+            static constexpr Uint32 kMaxBindings = 8;
+
+            // Frame serial of the last completed resolve OR cross-frame revalidation.
+            // Zero until a resolve completes, and reset to zero before one starts, so a
+            // resolve that bails out midway cannot leave a half-filled entry matchable.
+            // Unlike the original frame-scoped memo, an entry whose buffers are all
+            // resident and unmapped is revalidated across frames (per-binding slice
+            // epoch compares) instead of re-resolved - see TryBindResolvedVertexBindings.
+            Uint64 frameSerial = 0;
+            // Identity of the resolved Vulkan layout: the VAO's content hash
+            // (VertexInputStateFactory::GetOrComputeHash - the same value the factory
+            // keys its entries on) fixes bindings.size(), each binding's base offset,
+            // which bindings are client/converted, and (through the mixed-in buffer
+            // addresses) which buffer each binding reads. Compared against the VAO's
+            // own hash memo on the hit path, so a hit never touches the factory entry.
+            VertexInputStateFactory::HashType vertexInputHash = 0;
+            // The program's vertex input layout: decides the synthetic-binding set and
+            // hence the total binding count.
+            Uint32 activeAttribMask = 0;
+            Uint32 bindingCount = 0;
+            // VkBufferManager::GetSliceEpochCounter() at resolve time. Still equal means
+            // no buffer anywhere changed its slice or was persistently mapped since, which
+            // settles every per-binding question below in one compare.
+            Uint64 sliceEpochCounter = 0;
+            // Any bound buffer already carrying a host map when the slice was resolved.
+            // Such a buffer can mutate its shadow with no API call, so it has to be
+            // re-pushed per draw and the one-compare path above cannot apply.
+            Bool anyBufferMapped = true;
+
+            // Resident element-buffer slice memo (skips the per-draw AcquireResidentSlice
+            // for the VAO's EBO, which cold-chases 500+ distinct resources in a
+            // chunk-cycling frame). Self-validating exactly like the bindings above: a hit
+            // requires the LIVE bound EBO pointer to equal indexBuffer AND either an
+            // unmoved manager-wide slice-epoch counter (nothing anywhere changed slices
+            // or gained a host map, the same one-compare rescue the vertex half uses) or
+            // that buffer's resource still carrying indexSliceEpoch (epochs are minted
+            // from a process-lifetime counter, so a recycled address can never
+            // revalidate). Restart-substituted and streamed EBOs are never stored.
+            // indexFrameSerial tracks the last frame the resource's GPU-use serial was
+            // stamped through this memo; 0 means no index memo. Independent of the
+            // vertex half: both are (pointer, epoch)-validated, so neither can serve
+            // stale state for the other.
+            const MG_State::GLState::BufferObject* indexBuffer = nullptr;
+            Uint64 indexSliceEpoch = 0;
+            // GetSliceEpochCounter() when the resource's epoch was last verified; only
+            // meaningful while indexFrameSerial matches the current frame serial.
+            Uint64 indexSliceEpochCounter = 0;
+            VkBuffer indexVkBuffer = VK_NULL_HANDLE;
+            VkDeviceSize indexSliceOffset = 0;
+            Uint64 indexFrameSerial = 0;
+
+            // Bound per draw (first bindingCount elements).
+            VkBuffer vkBuffers[kMaxBindings] = {};
+            VkDeviceSize vkOffsets[kMaxBindings] = {};
+            // Per binding: the VAO attribute location its buffer comes from, that buffer,
+            // and the buffer's VkBufferManager slice epoch when the slice was resolved.
+            // Only read by the per-frame revalidation and the something-moved fallback.
+            Uint8 attributeLocations[kMaxBindings] = {};
+            const MG_State::GLState::BufferObject* buffers[kMaxBindings] = {};
+            Uint64 sliceEpochs[kMaxBindings] = {};
+        };
+        // One direct-mapped slot of the per-VAO draw-memo table below. A slot belongs to
+        // the object whose (vaoKey, vaoLifetimeId) pair it carries: the address alone
+        // only picks the slot, and the never-reused lifetime id is what proves the slot
+        // is THIS VAO's, so the successor allocated onto a destroyed VAO's address
+        // always misses. That identity check is load-bearing and the content-hash
+        // validations below do NOT stand in for it - a recycled address under a
+        // byte-identical configuration reproduces the content hash exactly, which is
+        // how a destroyed VAO's resolved bindings were once handed to its successor's
+        // draw. The slot is still never dereferenced through vaoKey, and every fact it
+        // carries is still validated against live state before use:
+        //  - layoutHash/layoutAuxMasks are valid only while contentHash equals the LIVE
+        //    VAO's own hash memo (which the VAO's config version guards), so a config
+        //    change or a buffer rebind misses even for the same object.
+        //  - bindings revalidates per draw exactly as before (frame serial, content
+        //    hash, per-binding live buffer pointers and slice epochs).
+        struct alignas(64) VaoDrawMemo {
+            const MG_State::GLState::VertexArrayObject* vaoKey = nullptr;
+            // The VAO's never-reused lifetime id, checked alongside vaoKey. The pointer
+            // ALONE is not an identity: a deleted VAO's heap address is handed straight
+            // back by the next glGenVertexArrays-shaped allocation, and the successor then
+            // matched this slot and inherited the dead object's memos. Both stated
+            // defences failed with it, because both reduce to the content hash and the
+            // content hash's buffer-identity component was itself a recycled heap address.
+            Uint64 vaoLifetimeId = 0;
+            // The VAO content hash (VertexInputStateFactory::GetOrComputeHash) the two
+            // layout facts below were derived from; 0 while nothing valid is stored.
+            Uint64 contentHash = 0;
+            Bool layoutFactsValid = false;
+            // The resolved layout identity + packed (unsupported, location) masks -
+            // the exact values GetBackendAuxMemo used to serve, moved here so the
+            // per-draw probe stays inside this table's one hot line instead of
+            // touching a second cold line of every cycled VAO object.
+            Uint64 layoutHash = 0;
+            Uint64 layoutAuxMasks = 0;
+            ResolvedVertexBindings bindings;
+        };
+        // Fixed-size, allocated on first use, never rehashed or swept: entries are
+        // recycled in place on slot collisions (two-slot probe, older frame serial
+        // evicted), and stale entries self-invalidate through the compares above. A
+        // fixed table also makes every VaoDrawMemo/ResolvedVertexBindings pointer
+        // stable for the duration of a draw, which the EBO memo handoff
+        // (m_currentDrawResolvedEntry) relies on.
+        static constexpr Uint32 kVaoDrawMemoSlotCount = 2048; // power of two
+        Vector<VaoDrawMemo> m_vaoDrawMemoTable;
+        // Finds the slot holding `vao`, or recycles the older of its two candidate
+        // slots into an empty memo keyed on `vao`. Never returns null.
+        VaoDrawMemo* LookupVaoDrawMemo(const MG_State::GLState::VertexArrayObject* vao);
+        // The current draw's memo entry, set by UploadAndBindVertexBuffers and consumed
+        // by the same draw's UploadAndBindIndexBuffer (the EBO memo lives in the same
+        // entry). Valid ONLY within that window: the next draw's lookup can recycle the
+        // slot. Null when the draw's layout is not memoisable.
+        ResolvedVertexBindings* m_currentDrawResolvedEntry = nullptr;
 
         void CreateInstance();
         VkResult SetupDebugMessenger();
         VkResult DestroyDebugMessenger();
+        VkResult SetupDebugReportCallback();
+        void DestroyDebugReportCallback();
         VkDebugUtilsMessengerCreateInfoEXT PopulateDebugMessengerCreateInfo();
         void CreateSurface();
         void PickPhysicalDevice();
@@ -446,10 +1069,32 @@ namespace MobileGL::MG_Backend::DirectVulkan {
             const RenderPassEntry& renderPassEntry);
         VkPipeline GetOrCreateComputePipeline(const ProgramFactory::VkProgramObject& programObj);
         void DestroyComputePipelines();
+        // Takes the frame rather than a command buffer: a first-time storage-usage upgrade has to
+        // flush the pending recording (see the body), which retires the current command buffer.
+        Bool PrepareStorageImageTextures(
+            FrameContext::FrameData& frame,
+            const MG_State::GLState::ProgramObject& program,
+            const ProgramFactory::VkProgramObject& programObj);
+
+        // The per-draw dynamic-state tail (viewport, scissor, blend constants, depth
+        // bias, line width, stencil), gated behind one render-state-parameters-version
+        // compare per command buffer - see the gate fields in DynamicStateShadow.
+        void ApplyDynamicDrawStateTail(FrameContext::FrameData& frame, const IntVec2& extent, Bool isDefaultFbo);
 
         Bool UploadAndBindVertexBuffers(VkCommandBuffer commandBuffer, const MG_State::GLState::VertexArrayObject& vao,
                                         const ProgramFactory::VkProgramObject& programObj,
-                                        const DrawCmdParam& drawParams);
+                                        const DrawCmdParam& drawParams,
+                                        const IndexBufferView* pIndexBufferView);
+        // Binds `entry`'s memoised buffers when every input it was resolved from is
+        // still live and unchanged, else returns false and leaves nothing bound.
+        // vaoContentHash is the VAO's memoised content hash (GetBackendHashMemo), which
+        // pins the layout AND the bound buffers without resolving the factory entry.
+        // Non-const entry: a cross-frame revalidation refreshes its serial/epoch stamps.
+        Bool TryBindResolvedVertexBindings(VkCommandBuffer commandBuffer,
+                                           const MG_State::GLState::VertexArrayObject& vao,
+                                           ResolvedVertexBindings& entry,
+                                           Uint64 vaoContentHash,
+                                           Uint32 activeAttribMask, Uint64 frameSerial);
         Bool UploadAndBindIndexBuffer(FrameContext::FrameData& frame,
                                      const MG_State::GLState::VertexArrayObject& vao,
                                       const IndexBufferView* pIndexBufferView = nullptr);
@@ -465,8 +1110,16 @@ namespace MobileGL::MG_Backend::DirectVulkan {
                                                    GLint srcX0, GLint srcY0, GLint srcX1, GLint srcY1,
                                                    GLint dstX0, GLint dstY0, GLint dstX1, GLint dstY1,
                                                    GLenum filter);
+        // Clears one z slice of a VK_IMAGE_TYPE_3D colour image. See the call site in
+        // MaterializePendingClearForTexture for why a transfer clear cannot do this.
+        Bool ClearDepthSliceWithRenderPass(VkCommandBuffer commandBuffer,
+                                           MG_State::GLState::ITextureObject& texture, Uint32 mipLevel,
+                                           Uint32 depthSlice, const VkClearValue& clearValue);
         Bool MaterializePendingClearForTexture(VkCommandBuffer commandBuffer,
                                                MG_State::GLState::ITextureObject& texture);
+        Bool MaterializePendingClearForRenderbuffer(
+            VkCommandBuffer commandBuffer,
+            const SharedPtr<MG_State::GLState::RenderbufferObject>& renderbuffer);
         VkPipeline GetOrCreateBlitPipeline(const RenderPassEntry& renderPassEntry);
         Bool GenerateDepthMipmapWithShader(FrameContext::FrameData& frame,
                                            MG_State::GLState::ITextureObject& texture,
@@ -478,6 +1131,14 @@ namespace MobileGL::MG_Backend::DirectVulkan {
                                            VkImageLayout finalLayout);
         Bool SubmitReadbackCommandsAndWait(FrameContext::FrameData& frame);
 
+    public:
+        // Submits whatever is recorded and waits for it. The CPU is about to read memory
+        // a shader wrote (a mapped shader storage buffer), and coherent host-visible
+        // storage only guarantees visibility once the work that produced it has retired.
+        Bool FinishPendingGpuWork();
+
+    private:
+
         void ShutdownSwapchain();
 
         // Static functions
@@ -501,6 +1162,10 @@ namespace MobileGL::MG_Backend::DirectVulkan {
                                                  const PhysicalDevice& compareWithDevice,
                                                  PhysicalDevice& outBetterDevice);
         static constexpr const char* s_validationLayerNames[] = {"VK_LAYER_KHRONOS_validation"};
+        // VK_KHR_image_format_list: lets MUTABLE_FORMAT images declare their exact view-format
+        // set so the driver can keep bandwidth compression (see CreateLogicalDeviceAndQueues).
+        Bool m_imageFormatListExtensionEnabled = false;
+
         static constexpr const char* s_deviceExtensionNames[] = {VK_KHR_SWAPCHAIN_EXTENSION_NAME};
         static Bool CheckValidationLayerSupport();
 

MobileGL/MG_Backend/DirectVulkan/VkIncludes.h

@@ -52,19 +52,48 @@ namespace MobileGL::MG_Backend::DirectVulkan {
     }
 } // namespace MobileGL::MG_Backend::DirectVulkan
 
+namespace MobileGL::MG_Backend::DirectVulkan {
+    // GL renders into sRGB color attachments RAW while GL_FRAMEBUFFER_SRGB is disabled
+    // (the core-profile default); Vulkan sRGB attachments always encode on write. The
+    // attachment view (and render pass format) therefore drops to the UNORM twin
+    // whenever the capability is off. Sampled views keep the sRGB format (decode on
+    // sample is unconditional in GL).
+    inline VkFormat ResolveSrgbAttachmentWriteFormat(VkFormat format, bool framebufferSrgbEnabled) {
+        if (framebufferSrgbEnabled) return format;
+        switch (format) {
+        case VK_FORMAT_R8G8B8A8_SRGB:
+            return VK_FORMAT_R8G8B8A8_UNORM;
+        case VK_FORMAT_B8G8R8A8_SRGB:
+            return VK_FORMAT_B8G8R8A8_UNORM;
+        default:
+            return format;
+        }
+    }
+} // namespace MobileGL::MG_Backend::DirectVulkan
+
+// The context line (__VA_ARGS__ = its own format string + args) must be a SEPARATE log
+// call: appending its format to the base format while its arguments precede the base
+// arguments makes every conversion read the wrong slot (a %s pulling an int crashes).
 #define VK_VERIFY(expr, ...)                                                                                           \
     do {                                                                                                               \
         VkResult _vk_verify_result = (expr);                                                                           \
         if (_vk_verify_result != VK_SUCCESS) {                                                                         \
-            MGLOG_F("Vulkan error %s (%d) at %s:%d" __VA_OPT__(" - ") __VA_ARGS__,                                  \
+            __VA_OPT__(MGLOG_F(__VA_ARGS__);)                                                                          \
+            MGLOG_F("Vulkan error %s (%d) at %s:%d",                                                                   \
                     MobileGL::MG_Backend::DirectVulkan::VkResultToString(_vk_verify_result),                          \
                     _vk_verify_result, __FILE__, __LINE__);                                                            \
         }                                                                                                              \
-        MOBILEGL_ASSERT(_vk_verify_result == VK_SUCCESS, "Vulkan error %s (%d) at %s:%d" __VA_OPT__(" - ") __VA_ARGS__, MobileGL::MG_Backend::DirectVulkan::VkResultToString(_vk_verify_result), _vk_verify_result, __FILE__, __LINE__);  \
+        MOBILEGL_ASSERT(_vk_verify_result == VK_SUCCESS, "Vulkan error %s (%d) at %s:%d",                              \
+                        MobileGL::MG_Backend::DirectVulkan::VkResultToString(_vk_verify_result),                       \
+                        _vk_verify_result, __FILE__, __LINE__);                                                        \
     } while (0)
 
 #define XXHASH_VERIFY(expr, ...)                                                                                       \
     do {                                                                                                               \
         XXH_errorcode _xxh_verify_result = (expr);                                                                     \
-        MOBILEGL_ASSERT(_xxh_verify_result == XXH_OK, "XXHash error %d at %s:%d" __VA_OPT__(" - ") __VA_ARGS__, _xxh_verify_result, __FILE__, __LINE__);  \
+        if (_xxh_verify_result != XXH_OK) {                                                                            \
+            __VA_OPT__(MGLOG_F(__VA_ARGS__);)                                                                          \
+        }                                                                                                              \
+        MOBILEGL_ASSERT(_xxh_verify_result == XXH_OK, "XXHash error %d at %s:%d", _xxh_verify_result, __FILE__,        \
+                        __LINE__);                                                                                     \
     } while (0)

MobileGL/MG_Benchmark/Buffer/CMakeLists.txt

@@ -16,4 +16,5 @@ target_link_libraries(
         ${LINK_LIBRARIES}
 )
 
-add_test(NAME BufferBench COMMAND BufferBench --benchmark_counters_tabular=true)
+add_test(NAME BufferBench COMMAND BufferBench --benchmark_counters_tabular=true)
+set_tests_properties(BufferBench PROPERTIES LABELS benchmark)

MobileGL/MG_Benchmark/CMakeLists.txt

@@ -38,6 +38,8 @@ target_link_libraries(
 )
 
 add_test(NAME SanityBench COMMAND SanityBench --benchmark_counters_tabular=true)
+set_tests_properties(SanityBench PROPERTIES LABELS benchmark)
 
 add_subdirectory(Program)
-add_subdirectory(Buffer)
+add_subdirectory(Buffer)
+add_subdirectory(Driver)

MobileGL/MG_Benchmark/Driver/CMakeLists.txt

@@ -0,0 +1,15 @@
+cmake_minimum_required(VERSION 3.24)
+
+# A real, headless EGL client, deliberately NOT linked against MobileGL: it
+# dlopens one EGL provider at runtime ($DRIVERBENCH_EGL_LIB - the system
+# libEGL.so.1 for the native driver, or a libMobileGL.so path for either
+# MobileGL backend), so the same binary measures all three stacks.
+if (NOT UNIX OR APPLE OR ANDROID)
+    return()
+endif()
+
+add_executable(DriverBench DriverBench.c)
+target_link_libraries(DriverBench PRIVATE dl)
+
+add_test(NAME DriverBench COMMAND DriverBench draw_tiny)
+set_tests_properties(DriverBench PROPERTIES LABELS benchmark)

MobileGL/MG_Benchmark/Driver/DriverBench.c

@@ -0,0 +1,501 @@
+/* MobileGL - MobileGL/MG_Benchmark/Driver/DriverBench.c
+ * Copyright (c) 2025-2026 MobileGL-Dev
+ * Licensed under the GNU Lesser General Public License v3.0:
+ *   https://www.gnu.org/licenses/gpl-3.0.txt
+ *   https://www.gnu.org/licenses/lgpl-3.0.txt
+ * SPDX-License-Identifier: LGPL-3.0-only
+ * End of Source File Header
+ *
+ * Headless, EGL-based driver benchmark shaped like Minecraft's GL usage.
+ * Unlike the MobileGL_s microbenches next door this exercises a full GL
+ * stack: it dlopens ONE EGL provider ($DRIVERBENCH_EGL_LIB - the system
+ * libEGL.so.1 for the native driver, or a libMobileGL.so path for either
+ * MobileGL backend selected with MOBILEGL_BACKEND_TYPE), creates a desktop-GL
+ * context on a small pbuffer, renders into its own FBO and paces frames with
+ * glFinish. No window system is required: the default display is tried first
+ * so a desktop run reaches the real driver, and a headless box (CI, a build
+ * server) falls back to EGL_MESA_platform_surfaceless - see
+ * run_driver_bench.sh.
+ *
+ * Every case models one hot pattern from captured Minecraft traces:
+ *   draw_tiny        back-to-back glDrawElements, shared state (chunk batch)
+ *   draw_uniform     per-draw vec3 offset uniform + draw (chunk sections)
+ *   draw_multi_vao   per-draw VAO/VBO switch + draw (per-section buffers)
+ *   tex_pingpong     per-draw texture bind churn on one unit
+ *   program_pingpong alternate two programs + mat4 upload (chunk<->entity)
+ *   chunk_upload     glBufferData(NULL) orphan + glBufferSubData + draw
+ *   atlas_sprite     N 16x16 glTexSubImage2D into a 1024x512 atlas + draw
+ *   lightmap         full 16x16 lightmap respecify per frame + draw
+ *   scene_mix        composite frame built from the knobs below
+ *
+ * Output: one CSV line per case:
+ *   case,frames,ops_per_frame,median_frame_ms,ns_per_op,fps
+ */
+#include <dlfcn.h>
+#include <stdint.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <time.h>
+
+/* ---- EGL constants ---- */
+typedef void* EGLDisplay;
+typedef void* EGLConfig;
+typedef void* EGLContext;
+typedef void* EGLSurface;
+typedef int EGLint;
+typedef unsigned int EGLBoolean;
+typedef unsigned int EGLenum;
+#define EGL_DEFAULT_DISPLAY ((void*)0)
+#define EGL_NO_CONTEXT ((EGLContext)0)
+#define EGL_NO_SURFACE ((EGLSurface)0)
+#define EGL_FALSE 0
+#define EGL_SURFACE_TYPE 0x3033
+#define EGL_PBUFFER_BIT 0x0001
+#define EGL_RENDERABLE_TYPE 0x3040
+#define EGL_OPENGL_BIT 0x0008
+#define EGL_RED_SIZE 0x3024
+#define EGL_GREEN_SIZE 0x3023
+#define EGL_BLUE_SIZE 0x3022
+#define EGL_DEPTH_SIZE 0x3025
+#define EGL_WIDTH 0x3057
+#define EGL_HEIGHT 0x3056
+#define EGL_NONE 0x3038
+#define EGL_OPENGL_API 0x30A2
+#define EGL_OPENGL_ES_API 0x30A0
+#define EGL_OPENGL_ES3_BIT 0x0040
+#define EGL_CONTEXT_CLIENT_VERSION 0x3098
+#define EGL_CONTEXT_MAJOR_VERSION 0x3098
+#define EGL_CONTEXT_MINOR_VERSION 0x30FB
+#define EGL_CONTEXT_OPENGL_PROFILE_MASK 0x30FD
+#define EGL_CONTEXT_OPENGL_CORE_PROFILE_BIT 0x00000001
+#define EGL_PLATFORM_SURFACELESS_MESA 0x31DD
+
+/* ---- GL constants ---- */
+#define GL_COLOR_BUFFER_BIT 0x00004000
+#define GL_DEPTH_BUFFER_BIT 0x00000100
+#define GL_TRIANGLES 0x0004
+#define GL_UNSIGNED_INT 0x1405
+#define GL_SHORT 0x1402
+#define GL_FLOAT 0x1406
+#define GL_UNSIGNED_BYTE 0x1401
+#define GL_ARRAY_BUFFER 0x8892
+#define GL_ELEMENT_ARRAY_BUFFER 0x8893
+#define GL_STATIC_DRAW 0x88E4
+#define GL_TEXTURE_2D 0x0DE1
+#define GL_TEXTURE0 0x84C0
+#define GL_RGBA 0x1908
+#define GL_RGBA8 0x8058
+#define GL_DEPTH_COMPONENT24 0x81A6
+#define GL_TEXTURE_MIN_FILTER 0x2801
+#define GL_TEXTURE_MAG_FILTER 0x2800
+#define GL_NEAREST 0x2600
+#define GL_NEAREST_MIPMAP_LINEAR 0x2702
+#define GL_DEPTH_TEST 0x0B71
+#define GL_BLEND 0x0BE2
+#define GL_SRC_ALPHA 0x0302
+#define GL_ONE_MINUS_SRC_ALPHA 0x0303
+#define GL_ONE 1
+#define GL_ZERO 0
+#define GL_VERTEX_SHADER 0x8B31
+#define GL_FRAGMENT_SHADER 0x8B30
+#define GL_COMPILE_STATUS 0x8B81
+#define GL_LINK_STATUS 0x8B82
+#define GL_VERSION 0x1F02
+#define GL_RENDERER 0x1F01
+#define GL_NO_ERROR 0
+#define GL_FRAMEBUFFER 0x8D40
+#define GL_RENDERBUFFER 0x8D41
+#define GL_COLOR_ATTACHMENT0 0x8CE0
+#define GL_DEPTH_ATTACHMENT 0x8D00
+#define GL_FRAMEBUFFER_COMPLETE 0x8CD5
+#define GL_SYNC_GPU_COMMANDS_COMPLETE 0x9117
+#define GL_SYNC_FLUSH_COMMANDS_BIT 0x00000001
+#define GL_UNIFORM_BUFFER 0x8A11
+#define GL_UNIFORM_BUFFER_OFFSET_ALIGNMENT 0x8A34
+#define GL_DYNAMIC_DRAW 0x88E8
+#define GL_STREAM_DRAW 0x88E0
+#define GL_UNPACK_ALIGNMENT 0x0CF5
+#define GL_UNPACK_ROW_LENGTH 0x0CF2
+#define GL_UNPACK_SKIP_ROWS 0x0CF3
+#define GL_UNPACK_SKIP_PIXELS 0x0CF4
+#define GL_TEXTURE_WRAP_S 0x2802
+#define GL_TEXTURE_WRAP_T 0x2803
+#define GL_CLAMP_TO_EDGE 0x812F
+#define GL_REPEAT 0x2901
+
+typedef unsigned int GLuint;
+typedef int GLint;
+typedef int GLsizei;
+typedef unsigned int GLenum;
+typedef char GLchar;
+typedef unsigned char GLboolean;
+typedef long GLsizeiptr;
+typedef long GLintptr;
+
+/* ---- resolved entry points ---- */
+static void* (*g_eglGetProcAddress)(const char*);
+static void* g_provider;
+
+#define GLF(ret, name, args) static ret(*name) args;
+GLF(void, glClear, (unsigned))
+GLF(void, glClearColor, (float, float, float, float))
+GLF(void, glEnable, (GLenum))
+GLF(void, glDisable, (GLenum))
+GLF(void, glBlendFuncSeparate, (GLenum, GLenum, GLenum, GLenum))
+GLF(void, glDrawBuffers, (GLsizei, const GLenum*))
+GLF(void, glViewport, (GLint, GLint, GLsizei, GLsizei))
+GLF(const unsigned char*, glGetString, (GLenum))
+GLF(GLenum, glGetError, (void))
+GLF(void, glFinish, (void))
+GLF(void, glFlush, (void))
+GLF(void, glGenBuffers, (GLsizei, GLuint*))
+GLF(void, glBindBuffer, (GLenum, GLuint))
+GLF(void, glBufferData, (GLenum, GLsizeiptr, const void*, GLenum))
+GLF(void, glBufferSubData, (GLenum, GLintptr, GLsizeiptr, const void*))
+GLF(void, glGenVertexArrays, (GLsizei, GLuint*))
+GLF(void, glBindVertexArray, (GLuint))
+GLF(void, glEnableVertexAttribArray, (GLuint))
+GLF(void, glVertexAttribPointer, (GLuint, GLint, GLenum, GLboolean, GLsizei, const void*))
+GLF(void, glGenTextures, (GLsizei, GLuint*))
+GLF(void, glBindTexture, (GLenum, GLuint))
+GLF(void, glActiveTexture, (GLenum))
+GLF(void, glTexImage2D, (GLenum, GLint, GLint, GLsizei, GLsizei, GLint, GLenum, GLenum, const void*))
+GLF(void, glTexSubImage2D, (GLenum, GLint, GLint, GLint, GLsizei, GLsizei, GLenum, GLenum, const void*))
+GLF(void, glTexParameteri, (GLenum, GLenum, GLint))
+GLF(void, glPixelStorei, (GLenum, GLint))
+GLF(void, glGetIntegerv, (GLenum, GLint*))
+GLF(void, glGenerateMipmap, (GLenum))
+GLF(GLuint, glCreateShader, (GLenum))
+GLF(void, glShaderSource, (GLuint, GLsizei, const GLchar* const*, const GLint*))
+GLF(void, glCompileShader, (GLuint))
+GLF(void, glGetShaderiv, (GLuint, GLenum, GLint*))
+GLF(void, glGetShaderInfoLog, (GLuint, GLsizei, GLsizei*, GLchar*))
+GLF(GLuint, glCreateProgram, (void))
+GLF(void, glAttachShader, (GLuint, GLuint))
+GLF(void, glLinkProgram, (GLuint))
+GLF(void, glGetProgramiv, (GLuint, GLenum, GLint*))
+GLF(void, glUseProgram, (GLuint))
+GLF(GLint, glGetUniformLocation, (GLuint, const GLchar*))
+GLF(void, glUniform1i, (GLint, GLint))
+GLF(void, glUniform3f, (GLint, float, float, float))
+GLF(void, glUniformMatrix4fv, (GLint, GLsizei, GLboolean, const float*))
+GLF(void, glDrawElements, (GLenum, GLsizei, GLenum, const void*))
+GLF(void, glBindAttribLocation, (GLuint, GLuint, const GLchar*))
+GLF(void, glUniform3fv, (GLint, GLsizei, const float*))
+GLF(void, glDrawArrays, (GLenum, GLint, GLsizei))
+GLF(void, glDrawElementsBaseVertex, (GLenum, GLsizei, GLenum, const void*, GLint))
+GLF(void, glMultiDrawElementsBaseVertex,
+    (GLenum, const GLsizei*, GLenum, const void* const*, GLsizei, const GLint*))
+GLF(void, glBindBufferRange, (GLenum, GLuint, GLuint, GLintptr, GLsizeiptr))
+GLF(void, glBindBufferBase, (GLenum, GLuint, GLuint))
+GLF(GLuint, glGetUniformBlockIndex, (GLuint, const GLchar*))
+GLF(void, glUniformBlockBinding, (GLuint, GLuint, GLuint))
+GLF(void, glGenSamplers, (GLsizei, GLuint*))
+GLF(void, glBindSampler, (GLuint, GLuint))
+GLF(void, glSamplerParameteri, (GLuint, GLenum, GLint))
+GLF(void, glGenFramebuffers, (GLsizei, GLuint*))
+GLF(void, glBindFramebuffer, (GLenum, GLuint))
+GLF(void, glGenRenderbuffers, (GLsizei, GLuint*))
+GLF(void, glBindRenderbuffer, (GLenum, GLuint))
+GLF(void, glRenderbufferStorage, (GLenum, GLenum, GLsizei, GLsizei))
+GLF(void, glFramebufferRenderbuffer, (GLenum, GLenum, GLenum, GLuint))
+GLF(GLenum, glCheckFramebufferStatus, (GLenum))
+GLF(void*, glFenceSync, (GLenum, unsigned))
+GLF(GLenum, glClientWaitSync, (void*, unsigned, unsigned long long))
+GLF(void, glDeleteSync, (void*))
+
+static uint64_t now_ns(void) {
+    struct timespec ts;
+    clock_gettime(CLOCK_MONOTONIC, &ts);
+    return (uint64_t)ts.tv_sec * 1000000000ull + (uint64_t)ts.tv_nsec;
+}
+
+static int cmp_u64(const void* a, const void* b) {
+    uint64_t x = *(const uint64_t*)a, y = *(const uint64_t*)b;
+    return x < y ? -1 : x > y;
+}
+
+
+/* Scene, cases and the case table live next door so the Android plugin's
+ * in-process benchmark runs byte-identical bodies. */
+static void bench_gl_failed(const char* what, const char* detail) {
+    fprintf(stderr, "FAIL: %s %s\n", what, detail ? detail : "");
+    exit(1);
+}
+
+/* GLES has glDrawElementsBaseVertex (3.2 core) but no multi-draw form of it, so
+ * against a native mobile driver the multi-draw case issues the same sub-draws
+ * one at a time - which is what the extension folds up, and what an application
+ * without it would have to write. Desktop GL and MobileGL take the real call. */
+static void bench_multi_draw_elements_base_vertex(GLenum mode, const GLsizei* counts, GLenum type,
+                                                  const void* const* offsets, GLsizei drawCount,
+                                                  const GLint* baseVertices) {
+    if (glMultiDrawElementsBaseVertex) {
+        glMultiDrawElementsBaseVertex(mode, counts, type, offsets, drawCount, baseVertices);
+        return;
+    }
+    for (GLsizei i = 0; i < drawCount; ++i) {
+        glDrawElementsBaseVertex(mode, counts[i], type, offsets[i], baseVertices[i]);
+    }
+}
+
+#include "DriverBenchCases.inc"
+
+/* ---- bench driver: fence-paced frames on the offscreen FBO ----------------
+ * Frames are closed with a real fence wait, not glFinish: MobileGL implements
+ * glFinish and glFlush as no-ops (MG_Impl/GLImpl/Exporting/Definitions.cpp),
+ * so a glFinish-paced loop would time only the CPU-side submit on a MobileGL
+ * backend while timing submit-plus-GPU on the native driver - the two numbers
+ * would not describe the same work. A sync object is honoured by every stack
+ * measured here.
+ */
+typedef void (*case_fn)(int frame, long a, long b);
+static int g_warmup = 30, g_frames = 120;
+
+static void end_frame_wait(void) {
+    if (glFenceSync && glClientWaitSync && glDeleteSync) {
+        void* sync = glFenceSync(GL_SYNC_GPU_COMMANDS_COMPLETE, 0);
+        if (sync) {
+            glClientWaitSync(sync, GL_SYNC_FLUSH_COMMANDS_BIT, 1000000000ull);
+            glDeleteSync(sync);
+            return;
+        }
+    }
+    glFinish();
+}
+
+static void run_case(const char* name, case_fn body, long a, long b, long opsPerFrame) {
+    static uint64_t samples[4096];
+    if (g_frames > 4096) g_frames = 4096;
+    end_frame_wait();
+    for (int i = 0; i < g_warmup; ++i) {
+        glClear(GL_COLOR_BUFFER_BIT | GL_DEPTH_BUFFER_BIT);
+        body(i, a, b);
+        end_frame_wait();
+    }
+    for (int i = 0; i < g_frames; ++i) {
+        uint64_t t0 = now_ns();
+        glClear(GL_COLOR_BUFFER_BIT | GL_DEPTH_BUFFER_BIT);
+        body(i, a, b);
+        end_frame_wait();
+        samples[i] = now_ns() - t0;
+    }
+    qsort(samples, g_frames, sizeof(uint64_t), cmp_u64);
+    uint64_t med = samples[g_frames / 2];
+    double frameMs = med / 1e6;
+    double nsPerOp = opsPerFrame > 0 ? (double)med / (double)opsPerFrame : 0.0;
+    printf("%s,%d,%ld,%.3f,%.1f,%.1f\n", name, g_frames, opsPerFrame, frameMs, nsPerOp,
+           1e9 / (double)med);
+    fflush(stdout);
+    if (glGetError() != GL_NO_ERROR) fprintf(stderr, "WARN: GL error after %s\n", name);
+}
+
+/* A display that needs no window system. eglGetPlatformDisplay is EGL 1.5
+ * core and eglGetPlatformDisplayEXT is the EGL_EXT_platform_base spelling
+ * older loaders ship; both are client entry points, so they resolve before
+ * any display exists. Only the attribute-list types differ between the two
+ * and this passes none, so one cast covers both. */
+static EGLDisplay surfaceless_display(void) {
+    void* fn = dlsym(g_provider, "eglGetPlatformDisplay");
+    if (!fn) fn = g_eglGetProcAddress("eglGetPlatformDisplay");
+    if (!fn) fn = dlsym(g_provider, "eglGetPlatformDisplayEXT");
+    if (!fn) fn = g_eglGetProcAddress("eglGetPlatformDisplayEXT");
+    if (!fn) return NULL;
+    return ((EGLDisplay(*)(EGLenum, void*, const void*))fn)(EGL_PLATFORM_SURFACELESS_MESA,
+                                                            EGL_DEFAULT_DISPLAY, NULL);
+}
+
+/* ---- EGL bootstrap: one provider library, pbuffer, desktop-GL context ---- */
+static int boot_egl(void) {
+    const char* libpath = getenv("DRIVERBENCH_EGL_LIB");
+    if (!libpath) libpath = "libEGL.so.1";
+    g_provider = dlopen(libpath, RTLD_LAZY | RTLD_LOCAL);
+    if (!g_provider) {
+        fprintf(stderr, "FAIL: dlopen %s: %s\n", libpath, dlerror());
+        return 1;
+    }
+#define ESYM(name) \
+    void* p_##name = dlsym(g_provider, #name); \
+    if (!p_##name) { fprintf(stderr, "FAIL: dlsym %s\n", #name); return 1; }
+    ESYM(eglGetDisplay)
+    ESYM(eglInitialize)
+    ESYM(eglChooseConfig)
+    ESYM(eglBindAPI)
+    ESYM(eglCreateContext)
+    ESYM(eglCreatePbufferSurface)
+    ESYM(eglMakeCurrent)
+    ESYM(eglGetProcAddress)
+    ESYM(eglGetError)
+    g_eglGetProcAddress = (void* (*)(const char*))p_eglGetProcAddress;
+
+    EGLint (*getError)(void) = (EGLint(*)(void))p_eglGetError;
+    EGLBoolean (*initialize)(EGLDisplay, EGLint*, EGLint*) =
+        (EGLBoolean(*)(EGLDisplay, EGLint*, EGLint*))p_eglInitialize;
+
+    /* The default display first: it is the one a windowed app would get, and
+     * on a desktop it is the one that reaches the real GPU - which is the
+     * driver this bench exists to measure. It does need a window system,
+     * though; Mesa's default platform is X11, so with no $DISPLAY (CI, a
+     * build server, ssh without forwarding) eglInitialize fails. Fall back to
+     * EGL_MESA_platform_surfaceless rather than give up: every case draws into
+     * the FBO built by build_resources(), so no window is needed for any of
+     * the work being timed. */
+    EGLint maj = 0, min = 0;
+    const char* how = "default display";
+    EGLDisplay dpy = ((EGLDisplay(*)(void*))p_eglGetDisplay)(EGL_DEFAULT_DISPLAY);
+    if (!dpy || !initialize(dpy, &maj, &min)) {
+        dpy = surfaceless_display();
+        how = "surfaceless display";
+        if (!dpy || !initialize(dpy, &maj, &min)) {
+            fprintf(stderr, "FAIL: eglInitialize (0x%x)\n", getError());
+            return 1;
+        }
+    }
+    fprintf(stderr, "EGL %d.%d via %s (%s)\n", maj, min, libpath, how);
+
+    // Desktop GL first (that is what MobileGL exposes and what the cases are
+    // written against), GLES 3 second so the same binary can measure a device's
+    // native driver as the baseline. The .inc picks ESSL shader sources when the
+    // context turns out to be ES.
+    EGLBoolean (*chooseConfig)(EGLDisplay, const EGLint*, EGLConfig*, EGLint, EGLint*) =
+        (EGLBoolean(*)(EGLDisplay, const EGLint*, EGLConfig*, EGLint, EGLint*))p_eglChooseConfig;
+    EGLContext (*createContext)(EGLDisplay, EGLConfig, EGLContext, const EGLint*) =
+        (EGLContext(*)(EGLDisplay, EGLConfig, EGLContext, const EGLint*))p_eglCreateContext;
+    EGLBoolean (*bindApi)(EGLenum) = (EGLBoolean(*)(EGLenum))p_eglBindAPI;
+
+    EGLConfig cfg = NULL;
+    EGLint ncfg = 0;
+    EGLContext ctx = EGL_NO_CONTEXT;
+
+    if (bindApi(EGL_OPENGL_API)) {
+        const EGLint cfgAttribs[] = {EGL_SURFACE_TYPE, EGL_PBUFFER_BIT, EGL_RED_SIZE, 8,
+                                     EGL_DEPTH_SIZE, 24, EGL_RENDERABLE_TYPE, EGL_OPENGL_BIT, EGL_NONE};
+        if (chooseConfig(dpy, cfgAttribs, &cfg, 1, &ncfg) && ncfg >= 1) {
+            const EGLint ctxAttribs[] = {EGL_CONTEXT_MAJOR_VERSION, 3, EGL_CONTEXT_MINOR_VERSION, 2,
+                                         EGL_CONTEXT_OPENGL_PROFILE_MASK,
+                                         EGL_CONTEXT_OPENGL_CORE_PROFILE_BIT, EGL_NONE};
+            ctx = createContext(dpy, cfg, EGL_NO_CONTEXT, ctxAttribs);
+            if (ctx == EGL_NO_CONTEXT) ctx = createContext(dpy, cfg, EGL_NO_CONTEXT, NULL);
+        }
+    }
+    if (ctx == EGL_NO_CONTEXT) {
+        if (!bindApi(EGL_OPENGL_ES_API)) {
+            fprintf(stderr, "FAIL: neither OpenGL nor OpenGL ES is bindable on this provider\n");
+            return 1;
+        }
+        const EGLint esCfgAttribs[] = {EGL_SURFACE_TYPE, EGL_PBUFFER_BIT, EGL_RED_SIZE, 8,
+                                       EGL_GREEN_SIZE, 8, EGL_BLUE_SIZE, 8, EGL_DEPTH_SIZE, 24,
+                                       EGL_RENDERABLE_TYPE, EGL_OPENGL_ES3_BIT, EGL_NONE};
+        ncfg = 0;
+        if (!chooseConfig(dpy, esCfgAttribs, &cfg, 1, &ncfg) || ncfg < 1) {
+            // EGL_SURFACE_TYPE 0 matches any config: a stack that offers no
+            // pbuffer at all is still usable through the surfaceless context
+            // path below.
+            const EGLint relaxed[] = {EGL_SURFACE_TYPE, 0, EGL_RED_SIZE, 8, EGL_NONE};
+            if (!chooseConfig(dpy, relaxed, &cfg, 1, &ncfg) || ncfg < 1) {
+                fprintf(stderr, "FAIL: eglChooseConfig\n");
+                return 1;
+            }
+        }
+        const EGLint esCtxAttribs[] = {EGL_CONTEXT_CLIENT_VERSION, 3, EGL_NONE};
+        ctx = createContext(dpy, cfg, EGL_NO_CONTEXT, esCtxAttribs);
+    }
+    if (ctx == EGL_NO_CONTEXT) {
+        fprintf(stderr, "FAIL: eglCreateContext (0x%x)\n", getError());
+        return 1;
+    }
+
+    /* The pbuffer only exists to have something to make current - nothing is
+     * ever drawn to it. Where there is no pbuffer config, EGL_NO_SURFACE is
+     * exactly what EGL_KHR_surfaceless_context takes, so the same call covers
+     * both. */
+    const EGLint pbAttribs[] = {EGL_WIDTH, 64, EGL_HEIGHT, 64, EGL_NONE};
+    EGLSurface surf = ((EGLSurface(*)(EGLDisplay, EGLConfig, const EGLint*))p_eglCreatePbufferSurface)(
+        dpy, cfg, pbAttribs);
+    if (surf == EGL_NO_SURFACE)
+        fprintf(stderr, "no pbuffer (0x%x), using a surfaceless context\n", getError());
+    if (!((EGLBoolean(*)(EGLDisplay, EGLSurface, EGLSurface, EGLContext))p_eglMakeCurrent)(dpy, surf,
+                                                                                          surf, ctx)) {
+        fprintf(stderr, "FAIL: eglMakeCurrent (0x%x)\n", getError());
+        return 1;
+    }
+
+    /* Core GL entry points: eglGetProcAddress first (EGL 1.5 serves core
+     * functions), provider dlsym as fallback (both glvnd and MobileGL export
+     * the gl* symbols directly). */
+#define RESOLVE(name)                                                              \
+    do {                                                                           \
+        *(void**)&name = g_eglGetProcAddress(#name);                               \
+        if (!name) *(void**)&name = dlsym(g_provider, #name);                      \
+        if (!name) { fprintf(stderr, "FAIL: resolve %s\n", #name); return 1; }     \
+    } while (0)
+    RESOLVE(glClear); RESOLVE(glClearColor); RESOLVE(glEnable); RESOLVE(glViewport);
+    RESOLVE(glDisable); RESOLVE(glBlendFuncSeparate); RESOLVE(glDrawBuffers);
+    RESOLVE(glGetString); RESOLVE(glGetError); RESOLVE(glFinish); RESOLVE(glFlush);
+    RESOLVE(glGenBuffers); RESOLVE(glBindBuffer); RESOLVE(glBufferData); RESOLVE(glBufferSubData);
+    RESOLVE(glGenVertexArrays); RESOLVE(glBindVertexArray); RESOLVE(glEnableVertexAttribArray);
+    RESOLVE(glVertexAttribPointer); RESOLVE(glGenTextures); RESOLVE(glBindTexture);
+    RESOLVE(glActiveTexture); RESOLVE(glTexImage2D); RESOLVE(glTexSubImage2D);
+    RESOLVE(glTexParameteri); RESOLVE(glGenerateMipmap); RESOLVE(glCreateShader);
+    RESOLVE(glPixelStorei); RESOLVE(glGetIntegerv);
+    RESOLVE(glShaderSource); RESOLVE(glCompileShader); RESOLVE(glGetShaderiv);
+    RESOLVE(glGetShaderInfoLog); RESOLVE(glCreateProgram); RESOLVE(glAttachShader);
+    RESOLVE(glLinkProgram); RESOLVE(glGetProgramiv); RESOLVE(glUseProgram);
+    RESOLVE(glGetUniformLocation); RESOLVE(glUniform1i); RESOLVE(glUniform3f);
+    RESOLVE(glUniformMatrix4fv); RESOLVE(glDrawElements); RESOLVE(glBindAttribLocation);
+    RESOLVE(glUniform3fv); RESOLVE(glDrawArrays); RESOLVE(glDrawElementsBaseVertex);
+    RESOLVE(glBindBufferRange); RESOLVE(glBindBufferBase);
+    RESOLVE(glGetUniformBlockIndex); RESOLVE(glUniformBlockBinding);
+    RESOLVE(glGenSamplers); RESOLVE(glBindSampler); RESOLVE(glSamplerParameteri);
+    RESOLVE(glGenFramebuffers); RESOLVE(glBindFramebuffer); RESOLVE(glGenRenderbuffers);
+    RESOLVE(glBindRenderbuffer); RESOLVE(glRenderbufferStorage); RESOLVE(glFramebufferRenderbuffer);
+    RESOLVE(glCheckFramebufferStatus);
+    // Optional: end_frame_wait() falls back to glFinish when a stack has no
+    // sync objects, so resolve without failing the run.
+    *(void**)&glFenceSync = g_eglGetProcAddress("glFenceSync");
+    if (!glFenceSync) *(void**)&glFenceSync = dlsym(g_provider, "glFenceSync");
+    *(void**)&glClientWaitSync = g_eglGetProcAddress("glClientWaitSync");
+    if (!glClientWaitSync) *(void**)&glClientWaitSync = dlsym(g_provider, "glClientWaitSync");
+    *(void**)&glDeleteSync = g_eglGetProcAddress("glDeleteSync");
+    if (!glDeleteSync) *(void**)&glDeleteSync = dlsym(g_provider, "glDeleteSync");
+    // Desktop-only: GLES 3.2 has DrawElementsBaseVertex but no multi-draw form,
+    // so bench_multi_draw_elements_base_vertex() emulates it when this is null.
+    *(void**)&glMultiDrawElementsBaseVertex = g_eglGetProcAddress("glMultiDrawElementsBaseVertex");
+    if (!glMultiDrawElementsBaseVertex)
+        *(void**)&glMultiDrawElementsBaseVertex = dlsym(g_provider, "glMultiDrawElementsBaseVertex");
+
+    fprintf(stderr, "renderer: %s\n", glGetString(GL_RENDERER));
+    fprintf(stderr, "version:  %s\n", glGetString(GL_VERSION));
+    return 0;
+}
+
+int main(int argc, char** argv) {
+    long draws = 2048;
+    if (getenv("DRIVERBENCH_DRAWS")) draws = atol(getenv("DRIVERBENCH_DRAWS"));
+    if (getenv("DRIVERBENCH_FRAMES")) g_frames = atoi(getenv("DRIVERBENCH_FRAMES"));
+    if (getenv("DRIVERBENCH_SPRITES")) g_mixSprites = atol(getenv("DRIVERBENCH_SPRITES"));
+
+    if (boot_egl()) return 1;
+    build_resources();
+
+    printf("case,frames,ops_per_frame,median_frame_ms,ns_per_op,fps\n");
+    for (int i = 0; i < kBenchCaseCount; ++i) {
+        const BenchCaseDesc* c = &kBenchCases[i];
+        if (argc > 1) {
+            int wanted = 0;
+            for (int j = 1; j < argc; ++j)
+                if (strcmp(argv[j], c->name) == 0) wanted = 1;
+            if (!wanted) continue;
+        }
+        // The generic cases scale with DRIVERBENCH_DRAWS; the mc_* rates are
+        // measured and must not move, or the numbers stop being comparable.
+        long a = c->a, ops = c->opsPerFrame;
+        if (strncmp(c->name, "mc_", 3) != 0 && a > 100) {
+            a = draws * a / 2048;
+            ops = c->opsPerFrame * draws / 2048;
+        }
+        run_case(c->name, c->fn, a, c->b, ops);
+    }
+    return 0;
+}

MobileGL/MG_Benchmark/Driver/DriverBenchCases.inc

@@ -0,0 +1,640 @@
+/* MobileGL - MobileGL/MG_Benchmark/Driver/DriverBenchCases.inc
+ * Copyright (c) 2025-2026 MobileGL-Dev
+ * Licensed under the GNU Lesser General Public License v3.0:
+ *   https://www.gnu.org/licenses/gpl-3.0.txt
+ *   https://www.gnu.org/licenses/lgpl-3.0.txt
+ * SPDX-License-Identifier: LGPL-3.0-only
+ * End of Source File Header
+ *
+ * The benchmark scene and its cases, with no harness and no GL loader: the
+ * includer supplies both. DriverBench.c drives it through function pointers
+ * resolved from one EGL provider; MG_Util/SelfTest/DriverBenchJni.cpp drives
+ * it through MobileGL's own frontend entry points inside the Android plugin.
+ * Sharing the bodies is the point - a number from the phone and a number from
+ * the desktop have to describe the same work.
+ *
+ * The includer must have declared, before including this file: the GL types
+ * and enums used below, and callable gl* entry points with the standard
+ * signatures. bench_gl_failed() is called (and must be defined) when shader
+ * compilation or linking fails, so a caller can report the failure instead of
+ * dying inside a benchmark.
+ */
+
+/* ---- shared scene resources (Minecraft-shaped) ---- */
+#define MAX_SECTIONS 512
+static GLuint g_progChunk, g_progEntity;
+static GLint g_uOffsetChunk, g_uMvpChunk, g_uMvpEntity;
+static GLuint g_vao[MAX_SECTIONS], g_vbo[MAX_SECTIONS];
+static GLuint g_sharedIbo;
+static GLuint g_texAtlas, g_texLight, g_texEntity;
+static int g_quadsPerSection = 128; /* 128 quads = 512 verts, 768 indices */
+static unsigned char* g_scratch;
+/* Uniform ring + sampler for the 26.2-shaped cases (see the case block below). */
+static GLuint g_uboRing;
+static GLint g_uboAlign = 256;
+static size_t g_uboSlot = 256;
+static GLuint g_sampler;
+/* Two small offscreen targets for the 26.2-style render-pass churn case. */
+static GLuint g_passFbo[2];
+static GLuint g_passColor[2];
+static float g_mvp[16] = {0.002f, 0, 0, 0, 0, 0.002f, 0, 0, 0, 0, -0.001f, 0, -1.f, -1.f, 0.f, 1.f};
+
+/* Minecraft chunk vertex: pos 3f, color 4ub, uv 2f, packed light 2s -> 32 B */
+#define VERT_STRIDE 32
+static void fill_section_vertices(unsigned char* dst, int quads, unsigned seed) {
+    for (int q = 0; q < quads * 4; ++q) {
+        float* f = (float*)(dst + q * VERT_STRIDE);
+        unsigned r = seed = seed * 1664525u + 1013904223u;
+        f[0] = (float)(q & 31) * 8.0f + (float)(r & 7);
+        f[1] = (float)((q >> 5) & 31) * 8.0f;
+        f[2] = (float)(q % 7) * 0.1f;
+        dst[q * VERT_STRIDE + 12] = (unsigned char)r;
+        dst[q * VERT_STRIDE + 13] = (unsigned char)(r >> 8);
+        dst[q * VERT_STRIDE + 14] = (unsigned char)(r >> 16);
+        dst[q * VERT_STRIDE + 15] = 255;
+        f[4] = (float)(r & 1023) / 1024.0f;
+        f[5] = (float)((r >> 10) & 511) / 512.0f;
+        ((short*)(dst + q * VERT_STRIDE + 24))[0] = 15 << 4;
+        ((short*)(dst + q * VERT_STRIDE + 24))[1] = 15 << 4;
+    }
+}
+
+static GLuint make_shader(GLenum kind, const char* src) {
+    GLuint sh = glCreateShader(kind);
+    glShaderSource(sh, 1, &src, NULL);
+    glCompileShader(sh);
+    GLint ok = 0;
+    glGetShaderiv(sh, GL_COMPILE_STATUS, &ok);
+    if (!ok) {
+        char log[1024];
+        glGetShaderInfoLog(sh, sizeof log, NULL, log);
+        bench_gl_failed("shader compile", log);
+        return 0;
+    }
+    return sh;
+}
+
+static GLuint make_program(const char* vs_src, const char* fs_src) {
+    GLuint prog = glCreateProgram();
+    glAttachShader(prog, make_shader(GL_VERTEX_SHADER, vs_src));
+    glAttachShader(prog, make_shader(GL_FRAGMENT_SHADER, fs_src));
+    glBindAttribLocation(prog, 0, "aPos");
+    glBindAttribLocation(prog, 1, "aColor");
+    glBindAttribLocation(prog, 2, "aUv");
+    glBindAttribLocation(prog, 3, "aLight");
+    glLinkProgram(prog);
+    GLint ok = 0;
+    glGetProgramiv(prog, GL_LINK_STATUS, &ok);
+    if (!ok) {
+        bench_gl_failed("program link", "");
+        return 0;
+    }
+    return prog;
+}
+
+static const char* kChunkVs =
+    "#version 150 core\n"
+    "in vec3 aPos; in vec4 aColor; in vec2 aUv; in vec2 aLight;\n"
+    "uniform mat4 uMvp; uniform vec3 uOffset;\n"
+    "out vec4 vColor; out vec2 vUv; out vec2 vLight;\n"
+    "void main(){ gl_Position = uMvp * vec4(aPos + uOffset, 1.0);\n"
+    "  vColor = aColor; vUv = aUv; vLight = aLight * (1.0/256.0); }\n";
+static const char* kChunkFs =
+    "#version 150 core\n"
+    "in vec4 vColor; in vec2 vUv; in vec2 vLight; out vec4 o;\n"
+    "uniform sampler2D uAtlas; uniform sampler2D uLight;\n"
+    "void main(){ o = texture(uAtlas, vUv) * vColor * texture(uLight, vLight); }\n";
+static const char* kEntityVs =
+    "#version 150 core\n"
+    "in vec3 aPos; in vec4 aColor; in vec2 aUv; in vec2 aLight;\n"
+    "uniform mat4 uMvp; uniform mat4 uModel;\n"
+    "out vec4 vColor; out vec2 vUv;\n"
+    "void main(){ gl_Position = uMvp * uModel * vec4(aPos, 1.0); vColor = aColor; vUv = aUv; }\n";
+static const char* kEntityFs =
+    "#version 150 core\n"
+    "in vec4 vColor; in vec2 vUv; out vec4 o; uniform sampler2D uTex;\n"
+    "void main(){ o = texture(uTex, vUv) * vColor; }\n";
+
+// ESSL 3.20 twins of the four shaders above. The bodies are identical; only the
+// version line and the precision qualifiers differ, so the two paths compile the
+// same work. Needed because this bench also runs against a device's native GLES
+// driver as the baseline MobileGL is measured against, and that driver rejects
+// desktop GLSL - while MobileGL is fed desktop GLSL on purpose, since translating
+// it is the thing under test.
+static const char* kChunkVsEs =
+    "#version 320 es\n"
+    "precision highp float;\n"
+    "in vec3 aPos; in vec4 aColor; in vec2 aUv; in vec2 aLight;\n"
+    "uniform mat4 uMvp; uniform vec3 uOffset;\n"
+    "out vec4 vColor; out vec2 vUv; out vec2 vLight;\n"
+    "void main(){ gl_Position = uMvp * vec4(aPos + uOffset, 1.0);\n"
+    "  vColor = aColor; vUv = aUv; vLight = aLight * (1.0/256.0); }\n";
+static const char* kChunkFsEs =
+    "#version 320 es\n"
+    "precision mediump float;\n"
+    "in vec4 vColor; in vec2 vUv; in vec2 vLight; out vec4 o;\n"
+    "uniform sampler2D uAtlas; uniform sampler2D uLight;\n"
+    "void main(){ o = texture(uAtlas, vUv) * vColor * texture(uLight, vLight); }\n";
+static const char* kEntityVsEs =
+    "#version 320 es\n"
+    "precision highp float;\n"
+    "in vec3 aPos; in vec4 aColor; in vec2 aUv; in vec2 aLight;\n"
+    "uniform mat4 uMvp; uniform mat4 uModel;\n"
+    "out vec4 vColor; out vec2 vUv;\n"
+    "void main(){ gl_Position = uMvp * uModel * vec4(aPos, 1.0); vColor = aColor; vUv = aUv; }\n";
+static const char* kEntityFsEs =
+    "#version 320 es\n"
+    "precision mediump float;\n"
+    "in vec4 vColor; in vec2 vUv; out vec4 o; uniform sampler2D uTex;\n"
+    "void main(){ o = texture(uTex, vUv) * vColor; }\n";
+
+// True once build_resources() has seen a GL_VERSION beginning with "OpenGL ES".
+static int g_isGlesContext = 0;
+
+static void setup_vao(GLuint vao, GLuint vbo, GLuint ibo) {
+    glBindVertexArray(vao);
+    glBindBuffer(GL_ARRAY_BUFFER, vbo);
+    glEnableVertexAttribArray(0);
+    glEnableVertexAttribArray(1);
+    glEnableVertexAttribArray(2);
+    glEnableVertexAttribArray(3);
+    glVertexAttribPointer(0, 3, GL_FLOAT, 0, VERT_STRIDE, (void*)0);
+    glVertexAttribPointer(1, 4, GL_UNSIGNED_BYTE, 1, VERT_STRIDE, (void*)12);
+    glVertexAttribPointer(2, 2, GL_FLOAT, 0, VERT_STRIDE, (void*)16);
+    glVertexAttribPointer(3, 2, GL_SHORT, 0, VERT_STRIDE, (void*)24);
+    glBindBuffer(GL_ELEMENT_ARRAY_BUFFER, ibo);
+}
+
+static GLuint g_mainFbo;
+
+static void build_resources(void) {
+    /* offscreen render target: 1280x720 RBO FBO, like CTS fbo surface mode */
+    GLuint fbo, rboColor, rboDepth;
+    glGenFramebuffers(1, &fbo);
+    g_mainFbo = fbo;
+    glBindFramebuffer(GL_FRAMEBUFFER, fbo);
+    glGenRenderbuffers(1, &rboColor);
+    glBindRenderbuffer(GL_RENDERBUFFER, rboColor);
+    glRenderbufferStorage(GL_RENDERBUFFER, GL_RGBA8, 1280, 720);
+    glFramebufferRenderbuffer(GL_FRAMEBUFFER, GL_COLOR_ATTACHMENT0, GL_RENDERBUFFER, rboColor);
+    glGenRenderbuffers(1, &rboDepth);
+    glBindRenderbuffer(GL_RENDERBUFFER, rboDepth);
+    glRenderbufferStorage(GL_RENDERBUFFER, GL_DEPTH_COMPONENT24, 1280, 720);
+    glFramebufferRenderbuffer(GL_FRAMEBUFFER, GL_DEPTH_ATTACHMENT, GL_RENDERBUFFER, rboDepth);
+    if (glCheckFramebufferStatus(GL_FRAMEBUFFER) != GL_FRAMEBUFFER_COMPLETE) {
+        bench_gl_failed("FBO incomplete", "");
+        return;
+    }
+
+    const char* versionString = (const char*)glGetString(GL_VERSION);
+    g_isGlesContext = versionString != NULL && strncmp(versionString, "OpenGL ES", 9) == 0;
+    g_progChunk = g_isGlesContext ? make_program(kChunkVsEs, kChunkFsEs) : make_program(kChunkVs, kChunkFs);
+    g_progEntity = g_isGlesContext ? make_program(kEntityVsEs, kEntityFsEs) : make_program(kEntityVs, kEntityFs);
+    glUseProgram(g_progChunk);
+    g_uMvpChunk = glGetUniformLocation(g_progChunk, "uMvp");
+    g_uOffsetChunk = glGetUniformLocation(g_progChunk, "uOffset");
+    glUniform1i(glGetUniformLocation(g_progChunk, "uAtlas"), 0);
+    glUniform1i(glGetUniformLocation(g_progChunk, "uLight"), 2);
+    glUniformMatrix4fv(g_uMvpChunk, 1, 0, g_mvp);
+    glUseProgram(g_progEntity);
+    g_uMvpEntity = glGetUniformLocation(g_progEntity, "uMvp");
+    glUniform1i(glGetUniformLocation(g_progEntity, "uTex"), 0);
+    glUniformMatrix4fv(g_uMvpEntity, 1, 0, g_mvp);
+    glUseProgram(g_progChunk);
+
+    /* shared quad index buffer, like Blaze3D's RenderSystem shared sequences */
+    int maxQuads = 4096;
+    unsigned* idx = (unsigned*)malloc((size_t)maxQuads * 6 * 4);
+    for (int q = 0; q < maxQuads; ++q) {
+        unsigned base = q * 4;
+        unsigned* p = idx + q * 6;
+        p[0] = base; p[1] = base + 1; p[2] = base + 2;
+        p[3] = base + 2; p[4] = base + 3; p[5] = base;
+    }
+    glGenBuffers(1, &g_sharedIbo);
+    glBindBuffer(GL_ELEMENT_ARRAY_BUFFER, g_sharedIbo);
+    glBufferData(GL_ELEMENT_ARRAY_BUFFER, maxQuads * 6 * 4, idx, GL_STATIC_DRAW);
+    free(idx);
+
+    g_scratch = (unsigned char*)malloc(4 * 1024 * 1024);
+    memset(g_scratch, 0x5a, 4 * 1024 * 1024);
+
+    glGenVertexArrays(MAX_SECTIONS, g_vao);
+    glGenBuffers(MAX_SECTIONS, g_vbo);
+    int bytes = g_quadsPerSection * 4 * VERT_STRIDE;
+    for (int i = 0; i < MAX_SECTIONS; ++i) {
+        fill_section_vertices(g_scratch, g_quadsPerSection, i * 7919u + 1);
+        glBindBuffer(GL_ARRAY_BUFFER, g_vbo[i]);
+        glBufferData(GL_ARRAY_BUFFER, bytes, g_scratch, GL_STATIC_DRAW);
+        setup_vao(g_vao[i], g_vbo[i], g_sharedIbo);
+    }
+
+    glGenTextures(1, &g_texAtlas);
+    glActiveTexture(GL_TEXTURE0);
+    glBindTexture(GL_TEXTURE_2D, g_texAtlas);
+    glTexImage2D(GL_TEXTURE_2D, 0, GL_RGBA8, 1024, 512, 0, GL_RGBA, GL_UNSIGNED_BYTE, g_scratch);
+    glTexParameteri(GL_TEXTURE_2D, GL_TEXTURE_MIN_FILTER, GL_NEAREST_MIPMAP_LINEAR);
+    glTexParameteri(GL_TEXTURE_2D, GL_TEXTURE_MAG_FILTER, GL_NEAREST);
+    glGenerateMipmap(GL_TEXTURE_2D);
+
+    glGenTextures(1, &g_texLight);
+    glActiveTexture(GL_TEXTURE0 + 2);
+    glBindTexture(GL_TEXTURE_2D, g_texLight);
+    glTexImage2D(GL_TEXTURE_2D, 0, GL_RGBA8, 16, 16, 0, GL_RGBA, GL_UNSIGNED_BYTE, g_scratch);
+    glTexParameteri(GL_TEXTURE_2D, GL_TEXTURE_MIN_FILTER, GL_NEAREST);
+    glTexParameteri(GL_TEXTURE_2D, GL_TEXTURE_MAG_FILTER, GL_NEAREST);
+
+    glGenTextures(1, &g_texEntity);
+    glActiveTexture(GL_TEXTURE0);
+    glBindTexture(GL_TEXTURE_2D, g_texEntity);
+    glTexImage2D(GL_TEXTURE_2D, 0, GL_RGBA8, 64, 64, 0, GL_RGBA, GL_UNSIGNED_BYTE, g_scratch);
+    glTexParameteri(GL_TEXTURE_2D, GL_TEXTURE_MIN_FILTER, GL_NEAREST);
+    glTexParameteri(GL_TEXTURE_2D, GL_TEXTURE_MAG_FILTER, GL_NEAREST);
+    glBindTexture(GL_TEXTURE_2D, g_texAtlas);
+
+    // Uniform ring the 26.2-style case sub-ranges into, sized like a real
+    // frame's worth of per-draw uniform slots.
+    GLint align = 256;
+    glGetIntegerv(GL_UNIFORM_BUFFER_OFFSET_ALIGNMENT, &align);
+    g_uboAlign = align > 0 ? align : 256;
+    g_uboSlot = (size_t)g_uboAlign;
+    glGenBuffers(1, &g_uboRing);
+    glBindBuffer(GL_UNIFORM_BUFFER, g_uboRing);
+    glBufferData(GL_UNIFORM_BUFFER, 4 * 1024 * 1024, g_scratch, GL_DYNAMIC_DRAW);
+    glBindBuffer(GL_UNIFORM_BUFFER, 0);
+
+    for (int i = 0; i < 2; ++i) {
+        glGenFramebuffers(1, &g_passFbo[i]);
+        glBindFramebuffer(GL_FRAMEBUFFER, g_passFbo[i]);
+        glGenRenderbuffers(1, &g_passColor[i]);
+        glBindRenderbuffer(GL_RENDERBUFFER, g_passColor[i]);
+        glRenderbufferStorage(GL_RENDERBUFFER, GL_RGBA8, 256, 256);
+        glFramebufferRenderbuffer(GL_FRAMEBUFFER, GL_COLOR_ATTACHMENT0, GL_RENDERBUFFER, g_passColor[i]);
+        if (glCheckFramebufferStatus(GL_FRAMEBUFFER) != GL_FRAMEBUFFER_COMPLETE) {
+            bench_gl_failed("pass FBO incomplete", "");
+            return;
+        }
+    }
+    /* back to the main offscreen target the harness set up */
+    glBindFramebuffer(GL_FRAMEBUFFER, g_mainFbo);
+
+    glGenSamplers(1, &g_sampler);
+    glSamplerParameteri(g_sampler, GL_TEXTURE_MIN_FILTER, GL_NEAREST);
+    glSamplerParameteri(g_sampler, GL_TEXTURE_MAG_FILTER, GL_NEAREST);
+
+    glEnable(GL_DEPTH_TEST);
+    glClearColor(0.3f, 0.5f, 0.9f, 1.0f);
+    glViewport(0, 0, 1280, 720);
+    const GLenum setupError = glGetError();
+    if (setupError != GL_NO_ERROR) {
+        char message[64];
+        snprintf(message, sizeof message, "0x%04x", setupError);
+        bench_gl_failed("GL error during resource setup", message);
+    }
+}
+
+static void case_draw_tiny(int frame, long a, long b) {
+    (void)frame; (void)b;
+    glBindVertexArray(g_vao[0]);
+    for (long i = 0; i < a; ++i) glDrawElements(GL_TRIANGLES, g_quadsPerSection * 6, GL_UNSIGNED_INT, 0);
+}
+
+static void case_draw_uniform(int frame, long a, long b) {
+    (void)frame; (void)b;
+    glBindVertexArray(g_vao[0]);
+    for (long i = 0; i < a; ++i) {
+        glUniform3f(g_uOffsetChunk, (float)(i & 15), (float)((i >> 4) & 15), 0.0f);
+        glDrawElements(GL_TRIANGLES, g_quadsPerSection * 6, GL_UNSIGNED_INT, 0);
+    }
+}
+
+static void case_draw_multi_vao(int frame, long a, long b) {
+    (void)frame; (void)b;
+    for (long i = 0; i < a; ++i) {
+        glBindVertexArray(g_vao[i % MAX_SECTIONS]);
+        glUniform3f(g_uOffsetChunk, (float)(i & 15), (float)((i >> 4) & 15), 0.0f);
+        glDrawElements(GL_TRIANGLES, g_quadsPerSection * 6, GL_UNSIGNED_INT, 0);
+    }
+}
+
+static void case_tex_pingpong(int frame, long a, long b) {
+    (void)frame; (void)b;
+    glBindVertexArray(g_vao[0]);
+    for (long i = 0; i < a; ++i) {
+        glBindTexture(GL_TEXTURE_2D, (i & 1) ? g_texEntity : g_texAtlas);
+        glDrawElements(GL_TRIANGLES, g_quadsPerSection * 6, GL_UNSIGNED_INT, 0);
+    }
+    glBindTexture(GL_TEXTURE_2D, g_texAtlas);
+}
+
+static void case_program_pingpong(int frame, long a, long b) {
+    (void)frame; (void)b;
+    glBindVertexArray(g_vao[0]);
+    for (long i = 0; i < a; ++i) {
+        if (i & 1) {
+            glUseProgram(g_progEntity);
+            glUniformMatrix4fv(g_uMvpEntity, 1, 0, g_mvp);
+        } else {
+            glUseProgram(g_progChunk);
+            glUniform3f(g_uOffsetChunk, (float)(i & 15), 0.0f, 0.0f);
+        }
+        glDrawElements(GL_TRIANGLES, g_quadsPerSection * 6, GL_UNSIGNED_INT, 0);
+    }
+    glUseProgram(g_progChunk);
+}
+
+/* a = uploads per frame, b = bytes per upload (0 => section size) */
+static void case_chunk_upload(int frame, long a, long b) {
+    if (b <= 0) b = g_quadsPerSection * 4 * VERT_STRIDE;
+    if (b > 4 * 1024 * 1024) b = 4 * 1024 * 1024;
+    for (long i = 0; i < a; ++i) {
+        int slot = (int)(((long)frame * a + i) % MAX_SECTIONS);
+        glBindBuffer(GL_ARRAY_BUFFER, g_vbo[slot]);
+        glBufferData(GL_ARRAY_BUFFER, b, NULL, GL_STATIC_DRAW); /* orphan */
+        glBufferSubData(GL_ARRAY_BUFFER, 0, b, g_scratch);
+        glBindVertexArray(g_vao[slot]);
+        glDrawElements(GL_TRIANGLES, g_quadsPerSection * 6, GL_UNSIGNED_INT, 0);
+    }
+}
+
+/* a = sprite updates per frame */
+static void case_atlas_sprite(int frame, long a, long b) {
+    (void)b;
+    glBindVertexArray(g_vao[0]);
+    glBindTexture(GL_TEXTURE_2D, g_texAtlas);
+    for (long i = 0; i < a; ++i) {
+        int x = (int)((frame * 13 + i * 17) % (1024 - 16));
+        int y = (int)((frame * 7 + i * 29) % (512 - 16));
+        glTexSubImage2D(GL_TEXTURE_2D, 0, x, y, 16, 16, GL_RGBA, GL_UNSIGNED_BYTE, g_scratch);
+    }
+    glDrawElements(GL_TRIANGLES, g_quadsPerSection * 6, GL_UNSIGNED_INT, 0);
+}
+
+/* a = lightmap updates (+draw) per frame */
+static void case_lightmap(int frame, long a, long b) {
+    (void)frame; (void)b;
+    glBindVertexArray(g_vao[0]);
+    for (long i = 0; i < a; ++i) {
+        glActiveTexture(GL_TEXTURE0 + 2);
+        glBindTexture(GL_TEXTURE_2D, g_texLight);
+        glTexSubImage2D(GL_TEXTURE_2D, 0, 0, 0, 16, 16, GL_RGBA, GL_UNSIGNED_BYTE, g_scratch);
+        glActiveTexture(GL_TEXTURE0);
+        glDrawElements(GL_TRIANGLES, g_quadsPerSection * 6, GL_UNSIGNED_INT, 0);
+    }
+}
+
+/* Composite: a = total draws, b = uploads per frame. Mix modeled on trace
+ * analysis: chunk draws with per-draw offset uniform across sections, 10%
+ * entity-style program flips, per-frame lightmap + sprite updates, b chunk
+ * re-uploads. */
+static long g_mixSprites = 8;
+static void case_scene_mix(int frame, long a, long b) {
+    glActiveTexture(GL_TEXTURE0 + 2);
+    glBindTexture(GL_TEXTURE_2D, g_texLight);
+    glTexSubImage2D(GL_TEXTURE_2D, 0, 0, 0, 16, 16, GL_RGBA, GL_UNSIGNED_BYTE, g_scratch);
+    glActiveTexture(GL_TEXTURE0);
+    glBindTexture(GL_TEXTURE_2D, g_texAtlas);
+    for (long i = 0; i < g_mixSprites; ++i) {
+        int x = (int)((frame * 13 + i * 17) % (1024 - 16));
+        int y = (int)((frame * 7 + i * 29) % (512 - 16));
+        glTexSubImage2D(GL_TEXTURE_2D, 0, x, y, 16, 16, GL_RGBA, GL_UNSIGNED_BYTE, g_scratch);
+    }
+    for (long i = 0; i < b; ++i) {
+        int slot = (int)(((long)frame * b + i) % MAX_SECTIONS);
+        long bytes = g_quadsPerSection * 4 * VERT_STRIDE;
+        glBindBuffer(GL_ARRAY_BUFFER, g_vbo[slot]);
+        glBufferData(GL_ARRAY_BUFFER, bytes, NULL, GL_STATIC_DRAW);
+        glBufferSubData(GL_ARRAY_BUFFER, 0, bytes, g_scratch);
+    }
+    long entityEvery = 10;
+    for (long i = 0; i < a; ++i) {
+        if (i % entityEvery == entityEvery - 1) {
+            glUseProgram(g_progEntity);
+            glUniformMatrix4fv(g_uMvpEntity, 1, 0, g_mvp);
+            glBindTexture(GL_TEXTURE_2D, g_texEntity);
+            glBindVertexArray(g_vao[i % MAX_SECTIONS]);
+            glDrawElements(GL_TRIANGLES, g_quadsPerSection * 6, GL_UNSIGNED_INT, 0);
+            glUseProgram(g_progChunk);
+            glBindTexture(GL_TEXTURE_2D, g_texAtlas);
+        } else {
+            glBindVertexArray(g_vao[i % MAX_SECTIONS]);
+            glUniform3f(g_uOffsetChunk, (float)(i & 15), (float)((i >> 4) & 15), 0.0f);
+            glDrawElements(GL_TRIANGLES, g_quadsPerSection * 6, GL_UNSIGNED_INT, 0);
+        }
+    }
+}
+
+/* ---- Trace-derived cases -------------------------------------------------
+ * Per-frame call mixes measured from the three captured Minecraft traces
+ * (render distance 32, 1280x720, hovering in-world). Each case reproduces one
+ * renderer's dominant per-draw sequence at its measured rate, so the number a
+ * backend posts here is directly comparable to what that game version asks of
+ * the driver every frame.
+ *
+ *   vanilla 1.21.1 : 5495 glDrawElements, 5490 glBindVertexArray,
+ *                    5487 glUniform3fv, 95 glTexSubImage2D (+382 glPixelStorei,
+ *                    247 glTexParameteri), 23 glBufferData per frame
+ *   fabric+sodium  : 132 glMultiDrawElementsBaseVertex, 279 glBindVertexArray,
+ *                    132 glUniform3f, 32 glBufferData per frame
+ *   26.2 snapshot  : 3401 glDrawElementsBaseVertex, each preceded by
+ *                    glBindBufferRange + glBindBuffer (3639/3412 per frame)
+ */
+/* vanilla: bind VAO, push the chunk offset, draw. a = draws per frame. */
+static void case_mc_vanilla_draw(int frame, long a, long b) {
+    (void)frame; (void)b;
+    float offset[3];
+    for (long i = 0; i < a; ++i) {
+        glBindVertexArray(g_vao[i % MAX_SECTIONS]);
+        offset[0] = (float)(i & 15);
+        offset[1] = (float)((i >> 4) & 15);
+        offset[2] = 0.0f;
+        glUniform3fv(g_uOffsetChunk, 1, offset);
+        glDrawElements(GL_TRIANGLES, g_quadsPerSection * 6, GL_UNSIGNED_INT, 0);
+    }
+}
+
+/* sodium: one multi-draw covers many chunk sections out of a shared buffer.
+ * a = multi-draws per frame, b = sub-draws inside each. */
+static void case_mc_sodium_multidraw(int frame, long a, long b) {
+    (void)frame;
+    enum { kMaxSub = 64 };
+    if (b <= 0 || b > kMaxSub) b = 32;
+    GLsizei counts[kMaxSub];
+    const void* offsets[kMaxSub];
+    GLint baseVertices[kMaxSub];
+    for (long s = 0; s < b; ++s) {
+        counts[s] = (GLsizei)(g_quadsPerSection * 6 / b);
+        offsets[s] = (const void*)(uintptr_t)(s * (g_quadsPerSection * 6 / b) * 4);
+        baseVertices[s] = 0;
+    }
+    for (long i = 0; i < a; ++i) {
+        glBindVertexArray(g_vao[i % MAX_SECTIONS]);
+        glBindVertexArray(g_vao[i % MAX_SECTIONS]); /* sodium rebinds ~2x per draw */
+        glUniform3f(g_uOffsetChunk, (float)(i & 15), (float)((i >> 4) & 15), 0.0f);
+        // Routed through the includer: GLES has no multi-draw-with-base-vertex, so
+        // a native-driver harness emulates it with the loop the extension folds up.
+        bench_multi_draw_elements_base_vertex(GL_TRIANGLES, counts, GL_UNSIGNED_INT, offsets,
+                                              (GLsizei)b, baseVertices);
+    }
+}
+
+/* 26.2: every draw rebinds a fresh uniform-buffer range out of a ring.
+ * a = draws per frame. */
+static void case_mc_ubo_range(int frame, long a, long b) {
+    (void)b;
+    const size_t slots = (4u * 1024u * 1024u) / g_uboSlot;
+    for (long i = 0; i < a; ++i) {
+        const size_t slot = (size_t)(((long)frame * a + i) % (long)slots);
+        glBindBufferRange(GL_UNIFORM_BUFFER, 0, g_uboRing, (GLintptr)(slot * g_uboSlot),
+                          (GLsizeiptr)g_uboSlot);
+        glBindBuffer(GL_UNIFORM_BUFFER, g_uboRing);
+        glDrawElementsBaseVertex(GL_TRIANGLES, g_quadsPerSection * 6, GL_UNSIGNED_INT, 0, 0);
+    }
+}
+
+/* vanilla's animated-sprite path: every upload is wrapped in the pixel-store
+ * and filter state Blaze3D re-sets around it. a = uploads per frame. */
+static void case_mc_tex_stream(int frame, long a, long b) {
+    (void)b;
+    glBindVertexArray(g_vao[0]);
+    glBindTexture(GL_TEXTURE_2D, g_texAtlas);
+    for (long i = 0; i < a; ++i) {
+        glPixelStorei(GL_UNPACK_ALIGNMENT, 4);
+        glPixelStorei(GL_UNPACK_ROW_LENGTH, 0);
+        glPixelStorei(GL_UNPACK_SKIP_ROWS, 0);
+        glPixelStorei(GL_UNPACK_SKIP_PIXELS, 0);
+        glTexParameteri(GL_TEXTURE_2D, GL_TEXTURE_WRAP_S, GL_CLAMP_TO_EDGE);
+        glTexParameteri(GL_TEXTURE_2D, GL_TEXTURE_WRAP_T, GL_CLAMP_TO_EDGE);
+        int x = (int)((frame * 13 + i * 17) % (1024 - 16));
+        int y = (int)((frame * 7 + i * 29) % (512 - 16));
+        glTexSubImage2D(GL_TEXTURE_2D, 0, x, y, 16, 16, GL_RGBA, GL_UNSIGNED_BYTE, g_scratch);
+    }
+    glDrawElements(GL_TRIANGLES, g_quadsPerSection * 6, GL_UNSIGNED_INT, 0);
+}
+
+/* Blaze3D re-resolves uniform locations by name every frame. a = lookups. */
+static void case_mc_uniform_lookup(int frame, long a, long b) {
+    (void)frame; (void)b;
+    static const char* names[4] = {"uMvp", "uOffset", "uAtlas", "uLight"};
+    volatile GLint sink = 0;
+    for (long i = 0; i < a; ++i) sink += glGetUniformLocation(g_progChunk, names[i & 3]);
+    (void)sink;
+    glBindVertexArray(g_vao[0]);
+    glDrawElements(GL_TRIANGLES, g_quadsPerSection * 6, GL_UNSIGNED_INT, 0);
+}
+
+/* 26.2 rebinds a sampler object per texture unit switch. a = switches. */
+static void case_mc_sampler_churn(int frame, long a, long b) {
+    (void)frame; (void)b;
+    glBindVertexArray(g_vao[0]);
+    for (long i = 0; i < a; ++i) {
+        glActiveTexture(GL_TEXTURE0 + (GLenum)(i & 3));
+        glBindTexture(GL_TEXTURE_2D, (i & 1) ? g_texEntity : g_texAtlas);
+        glBindSampler((GLuint)(i & 3), g_sampler);
+        glDrawElements(GL_TRIANGLES, g_quadsPerSection * 6, GL_UNSIGNED_INT, 0);
+    }
+    glActiveTexture(GL_TEXTURE0);
+}
+
+
+/* 26.2 switches render targets constantly: 132 glBindFramebuffer and 198
+ * glDrawBuffers per frame. Pass switching is where a Vulkan backend pays for
+ * render-pass breaks, so this case is the one to watch on Magma. a = passes. */
+static void case_mc_pass_switch(int frame, long a, long b) {
+    (void)frame; (void)b;
+    static const GLenum kColor0[1] = {GL_COLOR_ATTACHMENT0};
+    glBindVertexArray(g_vao[0]);
+    for (long i = 0; i < a; ++i) {
+        glBindFramebuffer(GL_FRAMEBUFFER, g_passFbo[i & 1]);
+        glDrawBuffers(1, kColor0);
+        glViewport(0, 0, 256, 256);
+        glDrawElements(GL_TRIANGLES, g_quadsPerSection * 6, GL_UNSIGNED_INT, 0);
+        glDrawElements(GL_TRIANGLES, g_quadsPerSection * 6, GL_UNSIGNED_INT, 0);
+    }
+    glBindFramebuffer(GL_FRAMEBUFFER, g_mainFbo);
+    glViewport(0, 0, 1280, 720);
+}
+
+/* Blaze3D toggles blend around batches: 46 glEnable/glDisable pairs and 28
+ * glBlendFuncSeparate per vanilla frame. a = toggle pairs. */
+static void case_mc_state_toggle(int frame, long a, long b) {
+    (void)frame; (void)b;
+    glBindVertexArray(g_vao[0]);
+    for (long i = 0; i < a; ++i) {
+        glEnable(GL_BLEND);
+        glBlendFuncSeparate(GL_SRC_ALPHA, GL_ONE_MINUS_SRC_ALPHA, GL_ONE, GL_ZERO);
+        glDrawElements(GL_TRIANGLES, g_quadsPerSection * 6, GL_UNSIGNED_INT, 0);
+        glDisable(GL_BLEND);
+        glDrawElements(GL_TRIANGLES, g_quadsPerSection * 6, GL_UNSIGNED_INT, 0);
+    }
+}
+
+/* 26.2 re-sets texture parameters relentlessly - 612 glTexParameteri per frame,
+ * almost always to the value already in place. Measures redundant-param
+ * filtering. a = parameter writes. */
+static void case_mc_tex_param(int frame, long a, long b) {
+    (void)frame; (void)b;
+    glBindVertexArray(g_vao[0]);
+    glBindTexture(GL_TEXTURE_2D, g_texAtlas);
+    for (long i = 0; i < a; i += 4) {
+        glTexParameteri(GL_TEXTURE_2D, GL_TEXTURE_WRAP_S, GL_CLAMP_TO_EDGE);
+        glTexParameteri(GL_TEXTURE_2D, GL_TEXTURE_WRAP_T, GL_CLAMP_TO_EDGE);
+        glTexParameteri(GL_TEXTURE_2D, GL_TEXTURE_MIN_FILTER, GL_NEAREST_MIPMAP_LINEAR);
+        glTexParameteri(GL_TEXTURE_2D, GL_TEXTURE_MAG_FILTER, GL_NEAREST);
+    }
+    glDrawElements(GL_TRIANGLES, g_quadsPerSection * 6, GL_UNSIGNED_INT, 0);
+}
+
+/* Sodium switches programs mid-frame far more than vanilla: 62 glUseProgram and
+ * 60 mat4 uploads per frame. a = program switches. */
+static void case_mc_use_program(int frame, long a, long b) {
+    (void)frame; (void)b;
+    glBindVertexArray(g_vao[0]);
+    for (long i = 0; i < a; ++i) {
+        if (i & 1) {
+            glUseProgram(g_progEntity);
+            glUniformMatrix4fv(g_uMvpEntity, 1, 0, g_mvp);
+        } else {
+            glUseProgram(g_progChunk);
+            glUniformMatrix4fv(g_uMvpChunk, 1, 0, g_mvp);
+        }
+        glDrawElements(GL_TRIANGLES, g_quadsPerSection * 6, GL_UNSIGNED_INT, 0);
+    }
+    glUseProgram(g_progChunk);
+}
+
+/* ---- the case table both harnesses iterate --------------------------------
+ * a/b are the case's own knobs; opsPerFrame is what one bench frame is
+ * normalised by, so ns_per_op compares across renderers. The mc_* rates are
+ * the per-frame call counts measured from the captured traces.
+ */
+typedef void (*bench_case_fn)(int frame, long a, long b);
+
+typedef struct {
+    const char* name;
+    bench_case_fn fn;
+    long a, b, opsPerFrame;
+} BenchCaseDesc;
+
+static const BenchCaseDesc kBenchCases[] = {
+    {"mc_vanilla_draw", case_mc_vanilla_draw, 5495, 0, 5495},
+    {"mc_sodium_multidraw", case_mc_sodium_multidraw, 132, 32, 132},
+    {"mc_ubo_range", case_mc_ubo_range, 3401, 0, 3401},
+    {"mc_tex_stream", case_mc_tex_stream, 95, 0, 95},
+    {"mc_uniform_lookup", case_mc_uniform_lookup, 41, 0, 41},
+    {"mc_sampler_churn", case_mc_sampler_churn, 306, 0, 306},
+    {"mc_pass_switch", case_mc_pass_switch, 132, 0, 132},
+    {"mc_state_toggle", case_mc_state_toggle, 46, 0, 46},
+    {"mc_tex_param", case_mc_tex_param, 612, 0, 612},
+    {"mc_use_program", case_mc_use_program, 62, 0, 62},
+    {"draw_tiny", case_draw_tiny, 2048, 0, 2048},
+    {"draw_uniform", case_draw_uniform, 2048, 0, 2048},
+    {"draw_multi_vao", case_draw_multi_vao, 2048, 0, 2048},
+    {"tex_pingpong", case_tex_pingpong, 1024, 0, 1024},
+    {"program_pingpong", case_program_pingpong, 512, 0, 512},
+    {"chunk_upload", case_chunk_upload, 24, 0, 24},
+    {"atlas_sprite", case_atlas_sprite, 32, 0, 32},
+    {"lightmap", case_lightmap, 4, 0, 4},
+    {"scene_mix", case_scene_mix, 2048, 12, 2048},
+};
+static const int kBenchCaseCount = (int)(sizeof kBenchCases / sizeof kBenchCases[0]);

MobileGL/MG_Benchmark/Driver/run_driver_bench.sh

@@ -0,0 +1,41 @@
+#!/bin/bash
+# Run the headless EGL DriverBench on one renderer:
+#   ./run_driver_bench.sh native            [bench args...]
+#   ./run_driver_bench.sh espryt <libMobileGL.so> [bench args...]
+#   ./run_driver_bench.sh magma  <libMobileGL.so> [bench args...]
+# The bench dlopens exactly one EGL provider (DRIVERBENCH_EGL_LIB): the system
+# libEGL.so.1 for native, or the given libMobileGL.so for a MobileGL backend -
+# no LD_LIBRARY_PATH shadowing, so MobileGL's own loader still finds the real
+# driver underneath.
+#
+# Pin the vendor libraries explicitly. A bare libEGL.so.1 on a glvnd system
+# picks whatever vendor eglGetDisplay(EGL_DEFAULT_DISPLAY) resolves first,
+# which is Mesa/llvmpipe here - a software rasteriser silently replacing the
+# GPU under a benchmark. Override MGL_EGL_VENDOR / MGL_VK_ICD to test another
+# driver.
+set -eu
+HERE=$(cd "$(dirname "$0")" && pwd)
+BENCH=${DRIVERBENCH_BIN:-$HERE/DriverBench}
+EGL_VENDOR=${MGL_EGL_VENDOR:-/usr/share/glvnd/egl_vendor.d/10_nvidia.json}
+VK_ICD=${MGL_VK_ICD:-/usr/share/vulkan/icd.d/nvidia_icd.x86_64.json}
+MODE=$1; shift
+
+export __EGL_VENDOR_LIBRARY_FILENAMES=$EGL_VENDOR
+export EGL_PLATFORM=${EGL_PLATFORM:-x11}
+
+case "$MODE" in
+  native)
+    export DRIVERBENCH_EGL_LIB=${DRIVERBENCH_EGL_LIB:-libEGL.so.1}
+    ;;
+  espryt)
+    export DRIVERBENCH_EGL_LIB=$(readlink -f "$1"); shift
+    export MOBILEGL_BACKEND_TYPE=DirectGLES
+    ;;
+  magma)
+    export DRIVERBENCH_EGL_LIB=$(readlink -f "$1"); shift
+    export MOBILEGL_BACKEND_TYPE=DirectVulkan
+    export VK_ICD_FILENAMES=$VK_ICD
+    ;;
+  *) echo "unknown mode: $MODE (native|espryt|magma)"; exit 1 ;;
+esac
+exec "$BENCH" "$@"

MobileGL/MG_Benchmark/Program/CMakeLists.txt

@@ -16,4 +16,5 @@ target_link_libraries(
         ${LINK_LIBRARIES}
 )
 
-add_test(NAME ProgramBench COMMAND ProgramBench --benchmark_counters_tabular=true)
+add_test(NAME ProgramBench COMMAND ProgramBench --benchmark_counters_tabular=true)
+set_tests_properties(ProgramBench PROPERTIES LABELS benchmark)

MobileGL/MG_Impl/CGLImpl/CGLImpl.cpp

@@ -24,6 +24,7 @@ namespace MobileGL::MG_Impl::CGLImpl {
             GLint Samples = 0;
             GLint Profile = kCGLOGLPVersion_3_2_Core;
             GLint RendererId = 0x4d474c;
+            GLint DisplayMask = 0;
         };
 
         struct ContextObject {
@@ -134,6 +135,9 @@ namespace MobileGL::MG_Impl::CGLImpl {
             case kCGLPFARendererID:
                 pixelFormat.RendererId = value;
                 break;
+            case kCGLPFADisplayMask:
+                pixelFormat.DisplayMask = value;
+                break;
             default:
                 break;
             }
@@ -343,6 +347,9 @@ namespace MobileGL::MG_Impl::CGLImpl {
         case kCGLPFARendererID:
             *value = pixelFormat->RendererId;
             return kCGLNoError;
+        case kCGLPFADisplayMask:
+            *value = pixelFormat->DisplayMask;
+            return kCGLNoError;
         case kCGLPFAOpenGLProfile:
             *value = pixelFormat->Profile;
             return kCGLNoError;
@@ -481,6 +488,32 @@ namespace MobileGL::MG_Impl::CGLImpl {
         return it == currentContexts.end() ? nullptr : it->second;
     }
 
+    CGLError SetVirtualScreen(CGLContextObj ctx, GLint screen) {
+        const std::lock_guard<std::recursive_mutex> lock(RegistryMutex());
+        auto* object = TryGetContext(ctx);
+        if (!object) {
+            return kCGLBadContext;
+        }
+        if (screen != 0) {
+            return kCGLBadValue;
+        }
+        object->VirtualScreen = screen;
+        return kCGLNoError;
+    }
+
+    CGLError GetVirtualScreen(CGLContextObj ctx, GLint* screen) {
+        const std::lock_guard<std::recursive_mutex> lock(RegistryMutex());
+        auto* object = TryGetContext(ctx);
+        if (!object) {
+            return kCGLBadContext;
+        }
+        if (!screen) {
+            return kCGLBadAddress;
+        }
+        *screen = object->VirtualScreen;
+        return kCGLNoError;
+    }
+
     CGLError SetParameter(CGLContextObj ctx, CGLContextParameter pname, const GLint* params) {
         const std::lock_guard<std::recursive_mutex> lock(RegistryMutex());
         auto* object = TryGetContext(ctx);

MobileGL/MG_Impl/CGLImpl/CGLImpl.h

@@ -32,6 +32,8 @@ namespace MobileGL::MG_Impl::CGLImpl {
 
     CGLError SetCurrentContext(CGLContextObj ctx);
     CGLContextObj GetCurrentContext();
+    CGLError SetVirtualScreen(CGLContextObj ctx, GLint screen);
+    CGLError GetVirtualScreen(CGLContextObj ctx, GLint* screen);
     CGLError SetParameter(CGLContextObj ctx, CGLContextParameter pname, const GLint* params);
     CGLError GetParameter(CGLContextObj ctx, CGLContextParameter pname, GLint* params);
     CGLError UpdateContext(CGLContextObj ctx);

MobileGL/MG_Impl/CGLImpl/Exporting/Definitions.cpp

@@ -71,6 +71,14 @@ MOBILEGL_CGL_API CGLContextObj CGLGetCurrentContext(void) {
     return MobileGL::MG_Impl::CGLImpl::GetCurrentContext();
 }
 
+MOBILEGL_CGL_API CGLError CGLSetVirtualScreen(CGLContextObj ctx, GLint screen) {
+    return MobileGL::MG_Impl::CGLImpl::SetVirtualScreen(ctx, screen);
+}
+
+MOBILEGL_CGL_API CGLError CGLGetVirtualScreen(CGLContextObj ctx, GLint* screen) {
+    return MobileGL::MG_Impl::CGLImpl::GetVirtualScreen(ctx, screen);
+}
+
 MOBILEGL_CGL_API CGLError CGLSetParameter(CGLContextObj ctx, CGLContextParameter pname, const GLint* params) {
     return MobileGL::MG_Impl::CGLImpl::SetParameter(ctx, pname, params);
 }

MobileGL/MG_Impl/DyldInterpose/DyldInterpose.cpp

@@ -10,8 +10,12 @@
 
 #if defined(__APPLE__)
 
+#include "MG_Impl/CGLImpl/CGLImpl.h"
 #include "MG_Impl/GetProcAddress.h"
 
+#include <CoreGraphics/CoreGraphics.h>
+#include <CoreVideo/CVDisplayLink.h>
+#include <cstdint>
 #include <dlfcn.h>
 
 namespace {
@@ -47,10 +51,52 @@ namespace {
         return dlsym(handle, symbol);
     }
 
+    CGDirectDisplayID DisplayForMask(GLint displayMask) {
+        constexpr std::uint32_t MaxDisplays = sizeof(CGOpenGLDisplayMask) * 8;
+        CGDirectDisplayID displays[MaxDisplays] = {};
+        std::uint32_t displayCount = 0;
+        if (displayMask != 0 &&
+            CGGetActiveDisplayList(MaxDisplays, displays, &displayCount) == kCGErrorSuccess) {
+            const auto mask = static_cast<CGOpenGLDisplayMask>(displayMask);
+            for (std::uint32_t i = 0; i < displayCount; ++i) {
+                if ((CGDisplayIDToOpenGLDisplayMask(displays[i]) & mask) != 0) {
+                    return displays[i];
+                }
+            }
+        }
+        return CGMainDisplayID();
+    }
+
+#pragma clang diagnostic push
+#pragma clang diagnostic ignored "-Wdeprecated-declarations"
+    CVReturn MobileGLCVDisplayLinkSetCurrentCGDisplayFromOpenGLContext(
+        CVDisplayLinkRef displayLink,
+        CGLContextObj context,
+        CGLPixelFormatObj pixelFormat) {
+        GLint virtualScreen = 0;
+        if (MobileGL::MG_Impl::CGLImpl::GetVirtualScreen(context, &virtualScreen) == kCGLNoError) {
+            GLint displayMask = 0;
+            if (!displayLink ||
+                MobileGL::MG_Impl::CGLImpl::DescribePixelFormat(
+                    pixelFormat, virtualScreen, kCGLPFADisplayMask, &displayMask) != kCGLNoError) {
+                return kCVReturnInvalidArgument;
+            }
+            return CVDisplayLinkSetCurrentCGDisplay(displayLink, DisplayForMask(displayMask));
+        }
+
+        using OriginalFunction = CVReturn (*)(CVDisplayLinkRef, CGLContextObj, CGLPixelFormatObj);
+        static const auto original = reinterpret_cast<OriginalFunction>(
+            dlsym(RTLD_NEXT, "CVDisplayLinkSetCurrentCGDisplayFromOpenGLContext"));
+        return original ? original(displayLink, context, pixelFormat) : kCVReturnError;
+    }
+
     __attribute__((used)) static const DyldInterposeEntry kMobileGLDyldInterpose[]
         __attribute__((section("__DATA,__interpose"))) = {
             {reinterpret_cast<const void*>(MobileGLDlsym), reinterpret_cast<const void*>(dlsym)},
+            {reinterpret_cast<const void*>(MobileGLCVDisplayLinkSetCurrentCGDisplayFromOpenGLContext),
+             reinterpret_cast<const void*>(CVDisplayLinkSetCurrentCGDisplayFromOpenGLContext)},
         };
+#pragma clang diagnostic pop
 } // namespace
 
 #endif

MobileGL/MG_Impl/DyldInterpose/ExportedSymbols.txt

@@ -0,0 +1,10 @@
+# Public CGL entry points.
+_CGL*
+
+# Public EGL entry points.
+_egl*
+
+# Public OpenGL and GLX entry points. OpenGL function names always use an
+# uppercase letter or digit after the "gl" prefix; excluding lowercase here
+# deliberately prevents glslang_* from matching this pattern.
+_gl[A-Z0-9]*

MobileGL/MG_Impl/EGLImpl/EGLImpl.cpp

@@ -8,6 +8,7 @@
 
 #include "EGLImpl.h"
 #include "../GetProcAddress.h"
+#include <Init.h>
 #include <MG_Backend/BackendObjects.h>
 #include <MG_State/EGLState/Core.h>
 #include <mutex>
@@ -25,6 +26,17 @@ namespace MobileGL::MG_Impl::EGLImpl {
             return MG_State::pEGLContext.get();
         }
 
+        // Entry points that can legitimately be an application's FIRST EGL
+        // call (display/proc-address/string queries) lazily bring MobileGL
+        // up here, so the library needs no static constructor and can
+        // re-initialize after the last eglTerminate tore everything down.
+        // Teardown-ish entry points keep using GetState() and fail benignly
+        // when MobileGL is not initialized.
+        EGLStateContext* GetStateEnsureInitialized() {
+            MobileGL::EnsureInitialized();
+            return GetState();
+        }
+
         MG_Backend::BackendObject* GetBackendObject(EGLStateContext* state) {
             auto* backendObject = MG_Backend::pActiveBackendObject.get();
             if (!backendObject && state) {
@@ -49,6 +61,8 @@ namespace MobileGL::MG_Impl::EGLImpl {
             return MG_Backend::WindowBackend::Android;
 #elif defined(__APPLE__)
             return MG_Backend::WindowBackend::MetalLayer;
+#elif defined(_WIN32)
+            return MG_Backend::WindowBackend::Win32;
 #elif defined(__linux__)
             return MG_Backend::WindowBackend::X11;
 #else
@@ -187,7 +201,7 @@ namespace MobileGL::MG_Impl::EGLImpl {
     }
 
     EGLBoolean Initialize(EGLDisplay dpy, EGLint* major, EGLint* minor) {
-        auto* state = GetState();
+        auto* state = GetStateEnsureInitialized();
         if (!state) {
             return EGL_FALSE;
         }
@@ -208,7 +222,7 @@ namespace MobileGL::MG_Impl::EGLImpl {
     }
 
     EGLDisplay GetDisplay(NativeDisplayType display) {
-        auto* state = GetState();
+        auto* state = GetStateEnsureInitialized();
         if (!state) {
             return EGL_NO_DISPLAY;
         }
@@ -313,6 +327,14 @@ namespace MobileGL::MG_Impl::EGLImpl {
         if (auto* backendObject = MG_Backend::pActiveBackendObject.get()) {
             backendObject->ReleaseEGLResources();
         }
+        // The last initialized display is gone and nothing is current on any
+        // thread: tear the whole library down deterministically inside the
+        // EGL lifecycle (backend, GL/EGL state, glslang). A later EGL call
+        // re-initializes lazily via GetStateEnsureInitialized(); process exit
+        // then has nothing left to destroy.
+        if (!state->HasAnyInitializedDisplay() && !state->HasAnyCurrentContext()) {
+            MobileGL::Destroy();
+        }
         return EGL_TRUE;
     }
 
@@ -345,7 +367,7 @@ namespace MobileGL::MG_Impl::EGLImpl {
     }
 
     EGLBoolean BindAPI(EGLenum api) {
-        auto* state = GetState();
+        auto* state = GetStateEnsureInitialized();
         if (!state) {
             return EGL_FALSE;
         }
@@ -378,7 +400,7 @@ namespace MobileGL::MG_Impl::EGLImpl {
     }
 
     char const* QueryString(EGLDisplay display, EGLint name) {
-        auto* state = GetState();
+        auto* state = GetStateEnsureInitialized();
         if (!state) {
             return nullptr;
         }
@@ -641,7 +663,7 @@ namespace MobileGL::MG_Impl::EGLImpl {
     EGLDisplay GetPlatformDisplay(EGLenum platform, void* native_display, const EGLAttrib* attrib_list) {
         (void)attrib_list;
 
-        auto* state = GetState();
+        auto* state = GetStateEnsureInitialized();
         if (!state) {
             return EGL_NO_DISPLAY;
         }
@@ -737,6 +759,7 @@ namespace MobileGL::MG_Impl::EGLImpl {
         if (!name) {
             return nullptr;
         }
+        MobileGL::EnsureInitialized();
 
         MGLOG_D("eglGetProcAddress(%s)", name);
         void* proc = MG_Impl::GetProcAddress(name);

MobileGL/MG_Impl/GLImpl/Buffer/GL_Buffer.cpp

@@ -8,6 +8,10 @@
 
 #include "GL_Buffer.h"
 #include "Validators.h"
+#include "../Texture/GL_Texture.h"
+#include "../Getter/GL_Getter.h"
+#include <MG_Util/Converters/GLToMG/TextureEnumConverter.h>
+#include <MG_Util/Metrics/TextureMetrics.h>
 #include <Config.h>
 #include <MG_State/GLState/Core.h>
 #include <MG_State/GLState/ErrorState/Error.h>
@@ -38,6 +42,7 @@ namespace MobileGL::MG_Impl::GLImpl {
             GetNamedBufferParameteriv,
             GetNamedBufferParameteri64v,
             GetNamedBufferPointerv,
+            GetNamedBufferSubData,
         };
 
         const char* GetBufferOpName(BufferOp op) {
@@ -76,6 +81,8 @@ namespace MobileGL::MG_Impl::GLImpl {
                 return "UnmapNamedBuffer";
             case BufferOp::FlushMappedNamedBufferRange:
                 return "FlushMappedNamedBufferRange";
+            case BufferOp::GetNamedBufferSubData:
+                return "GetNamedBufferSubData";
             case BufferOp::GetNamedBufferParameteriv:
                 return "GetNamedBufferParameteriv";
             case BufferOp::GetNamedBufferParameteri64v:
@@ -89,25 +96,64 @@ namespace MobileGL::MG_Impl::GLImpl {
 
         SharedPtr<MG_State::GLState::BufferObject> GetNamedBufferObject(GLuint buffer, BufferOp op);
 
+        // The size of one cleared element, which is what offset and size must be multiples of
+        // (GL 4.6 core 6.3). `internalformat` is restricted to the buffer-texture format table, and
+        // `format`/`type` describe the client-side pattern, so both are validated here and the
+        // caller only has to know how wide an element is.
         SizeT GetClearPatternSize(GLenum internalformat, GLenum format, GLenum type, BufferOp op) {
-            if (format != GL_RED_INTEGER) {
+            if (!IsBufferTextureInternalFormat(internalformat)) {
                 MG_State::pGLContext->RecordError(
                     ErrorCode::InvalidEnum,
-                    MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", GetBufferOpName(op),
-                                                 "Only GL_RED_INTEGER buffer clears are currently supported."));
+                    MakeUnique<GenericErrorInfo>(
+                        "MG_Impl/GLImpl", GetBufferOpName(op),
+                        std::format("internalformat 0x{:X} is not one of the sized formats a buffer clear accepts.",
+                                    internalformat)));
                 return 0;
             }
 
-            if (internalformat == GL_R8UI && type == GL_UNSIGNED_BYTE) return sizeof(GLubyte);
-            if (internalformat == GL_R32UI && type == GL_UNSIGNED_INT) return sizeof(GLuint);
+            // Unlike internalformat, a bad format or type here is INVALID_VALUE rather than
+            // INVALID_ENUM (GL 4.6 core 6.3) - the odd one out among the enum arguments.
+            const TextureInputFormat inputFormat = MG_Util::ConvertGLEnumToTextureInputFormat(format);
+            if (inputFormat == TextureInputFormat::Unknown) {
+                MG_State::pGLContext->RecordError(
+                    ErrorCode::InvalidValue,
+                    MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", GetBufferOpName(op),
+                                                 std::format("format 0x{:X} is not a pixel format.", format)));
+                return 0;
+            }
 
-            MG_State::pGLContext->RecordError(
-                ErrorCode::InvalidEnum,
-                MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", GetBufferOpName(op),
-                                             std::format("Unsupported clear format tuple: internalformat=0x{:X}, "
-                                                         "format=0x{:X}, type=0x{:X}",
-                                                         internalformat, format, type)));
-            return 0;
+            const TexturePixelDataType pixelType = MG_Util::ConvertGLEnumToTexturePixelDataType(type);
+            if (pixelType == TexturePixelDataType::Unknown) {
+                MG_State::pGLContext->RecordError(
+                    ErrorCode::InvalidValue,
+                    MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", GetBufferOpName(op),
+                                                 std::format("type 0x{:X} is not a pixel type.", type)));
+                return 0;
+            }
+
+            const TextureInternalFormat internal =
+                MG_Util::ConvertGLEnumToTextureInternalFormat(internalformat);
+            const SizeT elementSize = MG_Util::GetSizedInternalFormatSizeInBytes(internal);
+            if (elementSize == 0) {
+                MG_State::pGLContext->RecordError(
+                    ErrorCode::InvalidEnum,
+                    MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", GetBufferOpName(op),
+                                                 std::format("internalformat 0x{:X} has no known element size.",
+                                                             internalformat)));
+                return 0;
+            }
+
+            // The pattern is replicated verbatim, which is only the whole story while the client
+            // layout already matches the internal format - the case every entry point in practice
+            // uses, and the only one the conversion machinery here can express. Say so rather than
+            // quietly writing a differently-sized pattern.
+            const SizeT sourceSize = MG_Util::GetInputBytesPerPixel(inputFormat, pixelType);
+            if (sourceSize != elementSize) {
+                MGLOG_W("%s: clear pattern is %zu bytes but internalformat 0x%X stores %zu; "
+                        "converting between them is not implemented",
+                        GetBufferOpName(op), sourceSize, internalformat, elementSize);
+            }
+            return elementSize;
         }
 
         Bool ValidateBufferClearRange(const SharedPtr<MG_State::GLState::BufferObject>& bufferObject, GLintptr offset,
@@ -330,12 +376,21 @@ namespace MobileGL::MG_Impl::GLImpl {
                     } else if (access & BufferMappingAccessBit::Write) {
                         *params = GL_WRITE_ONLY;
                     } else {
-                        *params = 0;
+                        *params = GL_READ_WRITE;
                     }
                 } else {
-                    *params = 0;
+                    // Initial value, and what glUnmapBuffer restores (GL 4.6 core table 6.2).
+                    *params = GL_READ_WRITE;
                 }
                 break;
+            case GL_BUFFER_ACCESS_FLAGS:
+                // The MapBufferRange flags verbatim; glMapBuffer's access enum has already been
+                // normalised into the same bits. Zero while the buffer is not mapped.
+                *params = bufferObject->IsMapped()
+                    ? static_cast<GLint>(
+                          MG_Util::ConvertBufferMappingAccessToGLEnum(bufferObject->GetMappingAccess()))
+                    : 0;
+                break;
             case GL_BUFFER_MAPPED:
                 *params = bufferObject->IsMapped() ? GL_TRUE : GL_FALSE;
                 break;
@@ -441,7 +496,10 @@ namespace MobileGL::MG_Impl::GLImpl {
         for (SizeT i = 0; i < static_cast<SizeT>(n); ++i) {
             Uint bufferName = buffers[i];
             if (bufferName == 0) continue;
-            if (!BufferImpl::ValidateBufferName(bufferName, true)) continue;
+            // GL 3.3 core 2.9: names that do not correspond to an existing buffer are silently
+            // ignored here, so probe with the non-recording query - the shared validator would
+            // record INVALID_OPERATION, which is only correct on the bind path.
+            if (!MG_State::pGLContext->ValidateBufferName(bufferName)) continue;
             MG_State::pGLContext->MarkBufferObjectForDeletion(bufferName);
         }
     }
@@ -804,6 +862,10 @@ namespace MobileGL::MG_Impl::GLImpl {
 
         Range1D mappedRange = bufferObject->GetMappedRange();
         auto mappingAccess = bufferObject->GetMappingAccess();
+        // GL 4.6 6.5: the error is on OVERLAP with the mapped range, i.e. a half-open
+        // intersection test. There used to be a second test below this one asking only
+        // `offset + size >= mappedRange.start`, which rejects every write that starts
+        // before a mapped tail as well - it made a legal disjoint glBufferSubData fail.
         if (bufferObject->IsMapped() && !(mappingAccess & BufferMappingAccessBit::Persistent) &&
             (offset < mappedRange.end) && (offset + size > mappedRange.start)) {
             MG_State::pGLContext->RecordError(
@@ -814,18 +876,6 @@ namespace MobileGL::MG_Impl::GLImpl {
             return;
         }
 
-        if (bufferObject->IsMapped() && !(mappingAccess & BufferMappingAccessBit::Persistent)) {
-            Range1D mappedRange = bufferObject->GetMappedRange();
-            if (offset + size >= mappedRange.start) {
-                MG_State::pGLContext->RecordError(
-                    ErrorCode::InvalidOperation,
-                    MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", "BufferSubData_State",
-                                                 "Cannot modify a mapped buffer object unless it was "
-                                                 "mapped with GL_MAP_PERSISTENT_BIT."));
-                return;
-            }
-        }
-
         bufferObject->UploadSubData({(void*)data, (SizeT)size}, offset);
     }
 
@@ -875,6 +925,45 @@ namespace MobileGL::MG_Impl::GLImpl {
             return;
         }
 
+        bufferObject->SyncGpuWrites();
+        bufferObject->DownloadSubData(data, static_cast<SizeT>(offset), static_cast<SizeT>(size));
+    }
+
+    void GetNamedBufferSubData_State(GLuint buffer, GLintptr offset, GLsizeiptr size, void* data) {
+        if (!data) {
+            // Match GetBufferSubData_State: a null pointer is a caller bug, not a GL-specified error.
+            return;
+        }
+
+        if (size < 0 || offset < 0) {
+            MG_State::pGLContext->RecordError(
+                ErrorCode::InvalidValue,
+                MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", "GetNamedBufferSubData_State",
+                                             "Offset and size must be non-negative."));
+            return;
+        }
+
+        auto bufferObject = GetNamedBufferObject(buffer, BufferOp::GetNamedBufferSubData);
+        if (!bufferObject) return;
+
+        if (static_cast<SizeT>(offset) + static_cast<SizeT>(size) > bufferObject->GetSize()) {
+            MG_State::pGLContext->RecordError(
+                ErrorCode::InvalidValue,
+                MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", "GetNamedBufferSubData_State",
+                                             "Offset and size exceed buffer size."));
+            return;
+        }
+
+        if (bufferObject->IsMapped() &&
+            !(bufferObject->GetMappingAccess() & BufferMappingAccessBit::Persistent)) {
+            MG_State::pGLContext->RecordError(
+                ErrorCode::InvalidOperation,
+                MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", "GetNamedBufferSubData_State",
+                                             "Cannot read from a buffer object mapped without GL_MAP_PERSISTENT_BIT."));
+            return;
+        }
+
+        bufferObject->SyncGpuWrites();
         bufferObject->DownloadSubData(data, static_cast<SizeT>(offset), static_cast<SizeT>(size));
     }
 
@@ -917,6 +1006,11 @@ namespace MobileGL::MG_Impl::GLImpl {
     }
 
     void BufferStorage_State(GLenum target, GLsizeiptr size, const void* data, GLbitfield flags) {
+        // Error precedence: "no buffer is bound to target" outranks a bad size or bad
+        // flags, so the binding has to be resolved before either is validated.
+        auto bufferObject = GetBoundBufferObject(target, BufferOp::BufferStorage);
+        if (!bufferObject) return;
+
         if (size <= 0) {
             MG_State::pGLContext->RecordError(
                 ErrorCode::InvalidValue,
@@ -925,8 +1019,6 @@ namespace MobileGL::MG_Impl::GLImpl {
         }
         if (!ValidateStorageFlags(flags, BufferOp::BufferStorage)) return;
 
-        auto bufferObject = GetBoundBufferObject(target, BufferOp::BufferStorage);
-        if (!bufferObject) return;
         if (bufferObject->IsImmutableStorage()) {
             MG_State::pGLContext->RecordError(
                 ErrorCode::InvalidOperation,
@@ -961,6 +1053,10 @@ namespace MobileGL::MG_Impl::GLImpl {
     }
 
     void NamedBufferStorage_State(GLuint buffer, GLsizeiptr size, const void* data, GLbitfield flags) {
+        // Same precedence as BufferStorage_State: the buffer-name error comes first.
+        auto bufferObject = GetNamedBufferObject(buffer, BufferOp::NamedBufferStorage);
+        if (!bufferObject) return;
+
         if (size <= 0) {
             MG_State::pGLContext->RecordError(
                 ErrorCode::InvalidValue,
@@ -969,8 +1065,6 @@ namespace MobileGL::MG_Impl::GLImpl {
         }
         if (!ValidateStorageFlags(flags, BufferOp::NamedBufferStorage)) return;
 
-        auto bufferObject = GetNamedBufferObject(buffer, BufferOp::NamedBufferStorage);
-        if (!bufferObject) return;
         if (bufferObject->IsImmutableStorage()) {
             MG_State::pGLContext->RecordError(
                 ErrorCode::InvalidOperation,
@@ -1348,6 +1442,14 @@ namespace MobileGL::MG_Impl::GLImpl {
         BufferTarget bufferTarget = MG_Util::ConvertGLEnumToBufferTarget(target);
         if (!BufferImpl::ValidateBufferBindingPointTarget(bufferTarget)) return;
         if (!BufferImpl::ValidateBufferBindingPointIndex(bufferTarget, pointIndex)) return;
+        if (bufferTarget == BufferTarget::TransformFeedback && MG_State::pGLContext->IsTransformFeedbackActive()) {
+            MG_State::pGLContext->RecordError(
+                ErrorCode::InvalidOperation,
+                MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", __func__,
+                                             "Transform feedback buffer bindings cannot change while transform "
+                                             "feedback is active."));
+            return;
+        }
         MG_State::pGLContext->TouchBufferBindingPoint(bufferTarget, pointIndex);
 
         auto& point = MG_State::pGLContext->GetBufferBindingPoint(bufferTarget, pointIndex);
@@ -1355,6 +1457,7 @@ namespace MobileGL::MG_Impl::GLImpl {
         if (buffer == 0) {
             point.Bind(nullptr);
             point.SetRange(Range1D(0, 0));
+            GetBufferBindingSlot(bufferTarget).Bind(nullptr);
             return;
         }
 
@@ -1373,6 +1476,70 @@ namespace MobileGL::MG_Impl::GLImpl {
         } else {
             point.ClearRange();
         }
+        // The indexed bind also binds to the generic binding point of the same target
+        // (GL 4.6 core 6.1.1). Callers rely on it: the texture_gather tests set up their
+        // SSBO with BindBufferBase and then size it through glBufferData on the generic
+        // target alone, which would otherwise raise GL_INVALID_OPERATION and leave the
+        // buffer with no storage.
+        GetBufferBindingSlot(bufferTarget).Bind(bufferObject);
+    }
+
+    // GL 4.6 core 6.1.1: the constraints glBindBufferRange puts on the (offset, size) pair.
+    // Every one of them is INVALID_VALUE, and all of them are checked before a single piece
+    // of state is written - a rejected bind must leave the binding point exactly as it was.
+    // They apply only to a non-zero buffer: buffer 0 detaches the binding point and ignores
+    // offset and size, which is also how glBindBuffersRange spells "reset this element"
+    // (a NULL buffers array, or a zero entry inside one).
+    static Bool ValidateBufferRangeOffsetAndSize(GLenum target, GLintptr offset, GLsizeiptr size,
+                                                 const char* funcName) {
+        if (size <= 0) {
+            MG_State::pGLContext->RecordError(
+                ErrorCode::InvalidValue,
+                MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", funcName,
+                                             std::format("size ({}) must be greater than zero.", size)));
+            return false;
+        }
+        if (offset < 0) {
+            MG_State::pGLContext->RecordError(
+                ErrorCode::InvalidValue,
+                MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", funcName,
+                                             std::format("offset ({}) must not be negative.", offset)));
+            return false;
+        }
+        // GL_UNIFORM_BUFFER and GL_SHADER_STORAGE_BUFFER each constrain the offset to their own
+        // implementation-defined alignment, which glGetIntegerv already answers.
+        GLenum alignmentQuery = GL_NONE;
+        if (target == GL_SHADER_STORAGE_BUFFER) {
+            alignmentQuery = GL_SHADER_STORAGE_BUFFER_OFFSET_ALIGNMENT;
+        } else if (target == GL_UNIFORM_BUFFER) {
+            alignmentQuery = GL_UNIFORM_BUFFER_OFFSET_ALIGNMENT;
+        }
+        if (alignmentQuery != GL_NONE) {
+            GLint alignment = 0;
+            GetIntegerv(alignmentQuery, &alignment);
+            if (alignment > 0 && (offset % static_cast<GLintptr>(alignment)) != 0) {
+                MG_State::pGLContext->RecordError(
+                    ErrorCode::InvalidValue,
+                    MakeUnique<GenericErrorInfo>(
+                        "MG_Impl/GLImpl", funcName,
+                        std::format("offset ({}) must be a multiple of {} ({}).", offset,
+                                    MG_Util::ConvertGLEnumToString(alignmentQuery), alignment)));
+                return false;
+            }
+        }
+        // A transform feedback capture binding is addressed in 32-bit components, so BOTH the
+        // offset and the size must be multiples of 4.
+        if (target == GL_TRANSFORM_FEEDBACK_BUFFER && ((offset % 4) != 0 || (size % 4) != 0)) {
+            MG_State::pGLContext->RecordError(
+                ErrorCode::InvalidValue,
+                MakeUnique<GenericErrorInfo>(
+                    "MG_Impl/GLImpl", funcName,
+                    std::format("offset ({}) and size ({}) must both be multiples of 4 for "
+                                "GL_TRANSFORM_FEEDBACK_BUFFER.",
+                                offset, size)));
+            return false;
+        }
+        return true;
     }
 
     void BindBufferRange_State(GLenum target, GLuint index, GLuint buffer, GLintptr offset, GLsizeiptr size) {
@@ -1381,6 +1548,15 @@ namespace MobileGL::MG_Impl::GLImpl {
         BufferTarget bufferTarget = MG_Util::ConvertGLEnumToBufferTarget(target);
         if (!BufferImpl::ValidateBufferBindingPointTarget(bufferTarget)) return;
         if (!BufferImpl::ValidateBufferBindingPointIndex(bufferTarget, index)) return;
+        if (buffer != 0 && !ValidateBufferRangeOffsetAndSize(target, offset, size, __func__)) return;
+        if (bufferTarget == BufferTarget::TransformFeedback && MG_State::pGLContext->IsTransformFeedbackActive()) {
+            MG_State::pGLContext->RecordError(
+                ErrorCode::InvalidOperation,
+                MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", __func__,
+                                             "Transform feedback buffer bindings cannot change while transform "
+                                             "feedback is active."));
+            return;
+        }
         MG_State::pGLContext->TouchBufferBindingPoint(bufferTarget, index);
 
         auto& point = MG_State::pGLContext->GetBufferBindingPoint(bufferTarget, index);
@@ -1388,6 +1564,7 @@ namespace MobileGL::MG_Impl::GLImpl {
         if (buffer == 0) {
             point.Bind(nullptr);
             point.SetRange(Range1D(0, 0));
+            GetBufferBindingSlot(bufferTarget).Bind(nullptr);
             return;
         }
 
@@ -1405,6 +1582,8 @@ namespace MobileGL::MG_Impl::GLImpl {
         } else {
             point.ClearRange();
         }
+        // Also the generic binding point, exactly as BindBufferBase (GL 4.6 core 6.1.1).
+        GetBufferBindingSlot(bufferTarget).Bind(bufferObject);
     }
 
     /* @INSERTION_POINT:FUNCTION_IMPLEMENTATION@ */
@@ -1514,6 +1693,10 @@ namespace MobileGL::MG_Impl::GLImpl {
         BufferSubData_State(target, offset, size, data);
     }
 
+    void GetNamedBufferSubData(GLuint buffer, GLintptr offset, GLsizeiptr size, void* data) {
+        GetNamedBufferSubData_State(buffer, offset, size, data);
+    }
+
     void GetBufferSubData(GLenum target, GLintptr offset, GLsizeiptr size, void* data) {
         GetBufferSubData_State(target, offset, size, data);
     }
@@ -1539,15 +1722,32 @@ namespace MobileGL::MG_Impl::GLImpl {
     }
 
     // ARB_multi_bind: defined by the spec as equivalent to a loop over the single-bind entry
-    // points (with buffer 0 resetting the binding point).
+    // points (with buffer 0 resetting the binding point) - but only AFTER an up-front check
+    // of the whole [first, first + count) range. Looping straight into the single-bind entry
+    // points reports the single-bind INVALID_VALUE for an out-of-range index instead of the
+    // multi-bind INVALID_OPERATION, and binds the in-range prefix before failing.
+    static Bool ValidateMultiBindBufferRange(GLenum target, GLuint first, GLsizei count, const char* funcName) {
+        BufferTarget bufferTarget = MG_Util::ConvertGLEnumToBufferTarget(target);
+        if (!BufferImpl::ValidateBufferBindingPointTarget(bufferTarget)) return false;
+        return BufferImpl::ValidateBufferBindingPointRange(bufferTarget, first, count, funcName);
+    }
+
     void BindBuffersBase(GLenum target, GLuint first, GLsizei count, const GLuint* buffers) {
+        if (!ValidateMultiBindBufferRange(target, first, count, __func__)) return;
         for (GLsizei i = 0; i < count; ++i) {
             BindBufferBase_State(target, first + i, buffers ? buffers[i] : 0);
         }
     }
 
+    // The (offset, size) constraints are the one part of glBindBuffersRange that stays
+    // per-element: ARB_multi_bind checks them separately for each binding point, leaves that
+    // point unchanged on failure, and still applies the remaining elements - which is exactly
+    // what looping into BindBufferRange_State does. Only the [first, first + count) range is
+    // an up-front, all-or-nothing check. Elements that name buffer 0 (or a NULL buffers array)
+    // reset the binding point through BindBufferBase_State and carry no offset/size to check.
     void BindBuffersRange(GLenum target, GLuint first, GLsizei count, const GLuint* buffers, const GLintptr* offsets,
                           const GLsizeiptr* sizes) {
+        if (!ValidateMultiBindBufferRange(target, first, count, __func__)) return;
         for (GLsizei i = 0; i < count; ++i) {
             if (!buffers || buffers[i] == 0) {
                 BindBufferBase_State(target, first + i, 0);

MobileGL/MG_Impl/GLImpl/Buffer/GL_Buffer.h

@@ -41,6 +41,7 @@ namespace MobileGL::MG_Impl::GLImpl {
                            GLsizeiptr size);
     void BufferSubData(GLenum target, GLintptr offset, GLsizeiptr size, const void* data);
     void GetBufferSubData(GLenum target, GLintptr offset, GLsizeiptr size, void* data);
+    void GetNamedBufferSubData(GLuint buffer, GLintptr offset, GLsizeiptr size, void* data);
     void BufferData(GLenum target, GLsizeiptr size, const void* data, GLenum usage);
     void BindBuffer(GLenum target, GLuint buffer);
     void GenBuffers(GLsizei n, GLuint* buffers);

MobileGL/MG_Impl/GLImpl/Buffer/Validators.cpp

@@ -53,13 +53,46 @@ namespace MobileGL::MG_Impl::GLImpl::BufferImpl {
         return true;
     }
 
-    Bool ValidateBufferBindingPointIndex(BufferTarget target, Uint index) {
-        SizeT pointCount = MG_State::pGLContext->GetBufferBindingPointCount(target);
-        if (target == BufferTarget::ShaderStorage && MG_Backend::pActiveBackendObject) {
-            const Int backendCount =
-                MG_Backend::pActiveBackendObject->GetDynamicParameters().MaxShaderStorageBufferBindings;
-            pointCount = std::min(pointCount, static_cast<SizeT>(std::max(backendCount, 0)));
+    namespace {
+        // The GL-visible number of indexed binding points for `target`.
+        SizeT GetBufferBindingPointLimit(BufferTarget target) {
+            SizeT pointCount = MG_State::pGLContext->GetBufferBindingPointCount(target);
+            if (target == BufferTarget::ShaderStorage && MG_Backend::pActiveBackendObject) {
+                const Int backendCount =
+                    MG_Backend::pActiveBackendObject->GetDynamicParameters().MaxShaderStorageBufferBindings;
+                pointCount = std::min(pointCount, static_cast<SizeT>(std::max(backendCount, 0)));
+            }
+            if (target == BufferTarget::TransformFeedback) {
+                // GL_MAX_TRANSFORM_FEEDBACK_SEPARATE_ATTRIBS bounds the indexed capture
+                // binding points in GL 3.3 (no ARB_transform_feedback3).
+                pointCount = std::min<SizeT>(pointCount, 4);
+            }
+            return pointCount;
         }
+    } // namespace
+
+    Bool ValidateBufferBindingPointRange(BufferTarget target, Uint first, GLsizei count, const char* funcName) {
+        if (count < 0) {
+            MG_State::pGLContext->RecordError(
+                ErrorCode::InvalidValue, MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl/BufferImpl", funcName,
+                                                                      "count must be non-negative."));
+            return false;
+        }
+        const SizeT pointCount = GetBufferBindingPointLimit(target);
+        if (static_cast<Uint64>(first) + static_cast<Uint64>(count) > static_cast<Uint64>(pointCount)) {
+            MG_State::pGLContext->RecordError(
+                ErrorCode::InvalidOperation,
+                MakeUnique<GenericErrorInfo>(
+                    "MG_Impl/GLImpl/BufferImpl", funcName,
+                    std::format("first + count ({} + {}) exceeds the {} indexed binding points of target {}.", first,
+                                count, pointCount, MG_Util::ConvertBufferTargetToString(target))));
+            return false;
+        }
+        return true;
+    }
+
+    Bool ValidateBufferBindingPointIndex(BufferTarget target, Uint index) {
+        const SizeT pointCount = GetBufferBindingPointLimit(target);
 
         if (index < pointCount) {
             return true;
@@ -107,14 +140,10 @@ namespace MobileGL::MG_Impl::GLImpl::BufferImpl {
     }
 
     Bool ValidateBufferMappingAccess(Flags<BufferMappingAccessBit> accessBits) {
-        if (accessBits == BufferMappingAccessBit::Null) {
-            MG_State::pGLContext->RecordError(ErrorCode::InvalidEnum,
-                                              MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl/BufferImpl",
-                                                                           "ValidateBufferMappingAccess",
-                                                                           "Access bits cannot be null."));
-            return false;
-        }
-
+        // An empty mask is a legal value for a bitfield - it just fails the rule that a mapping
+        // must ask for read or write access, which is INVALID_OPERATION and belongs to the callers
+        // (both of them check it immediately after this). Rejecting it here as INVALID_ENUM
+        // reported the wrong error and hid theirs.
         const auto validBits = BufferMappingAccessBit::Read | BufferMappingAccessBit::Write |
                                BufferMappingAccessBit::InvalidateRange | BufferMappingAccessBit::InvalidateBuffer |
                                BufferMappingAccessBit::FlushExplicit | BufferMappingAccessBit::Unsynchronized |

MobileGL/MG_Impl/GLImpl/Buffer/Validators.h

@@ -17,4 +17,8 @@ namespace MobileGL::MG_Impl::GLImpl::BufferImpl {
     Bool ValidateBufferMappingAccess(Flags<BufferMappingAccessBit> accessBits);
     Bool ValidateBufferBindingPointTarget(BufferTarget target);
     Bool ValidateBufferBindingPointIndex(BufferTarget target, Uint index);
+    // ARB_multi_bind: glBindBuffersBase/Range validate the whole [first, first + count) range
+    // up front and report INVALID_OPERATION, where a single out-of-range index would be
+    // INVALID_VALUE. Naively looping the single-bind entry points reports the wrong class.
+    Bool ValidateBufferBindingPointRange(BufferTarget target, Uint first, GLsizei count, const char* funcName);
 } // namespace MobileGL::MG_Impl::GLImpl::BufferImpl

MobileGL/MG_Impl/GLImpl/Drawing/GL_Drawing.cpp

@@ -11,10 +11,11 @@
 #include <MG_State/GLState/Core.h>
 #include <MG_State/EGLState/Core.h>
 #include <MG_Backend/BackendObjects.h>
+#include "../Getter/GL_Getter.h"
 
 namespace MobileGL::MG_Impl::GLImpl {
     static Bool ValidateCurrentProgramForExecution(const char* functionName) {
-        const auto& currentProgram = MG_State::pGLContext->GetCurrentProgram();
+        const auto& currentProgram = MG_State::pGLContext->GetProgramForDraw();
         if (!currentProgram) {
             MG_State::pGLContext->RecordError(
                 ErrorCode::InvalidOperation,
@@ -36,7 +37,7 @@ namespace MobileGL::MG_Impl::GLImpl {
     static Bool ValidateCurrentProgramForCompute(const char* functionName) {
         if (!ValidateCurrentProgramForExecution(functionName)) return false;
 
-        const auto& currentProgram = MG_State::pGLContext->GetCurrentProgram();
+        const auto& currentProgram = MG_State::pGLContext->GetProgramForDraw();
         if (currentProgram->GetShaderIndexByStage(ShaderStage::Compute) < 0) {
             MG_State::pGLContext->RecordError(
                 ErrorCode::InvalidOperation,
@@ -48,7 +49,109 @@ namespace MobileGL::MG_Impl::GLImpl {
         return true;
     }
 
+    // Primitives a draw of `count` vertices in `mode` assembles (0 for
+    // incomplete primitives). Used for the CPU-side transform feedback
+    // primitive accounting.
+    static Uint64 CountPrimitivesForDraw(GLenum mode, GLsizei count) {
+        if (count <= 0) return 0;
+        switch (mode) {
+        case GL_POINTS: return static_cast<Uint64>(count);
+        case GL_LINES: return static_cast<Uint64>(count / 2);
+        case GL_LINE_STRIP: return count >= 2 ? static_cast<Uint64>(count - 1) : 0;
+        case GL_LINE_LOOP: return count >= 2 ? static_cast<Uint64>(count) : 0;
+        case GL_TRIANGLES: return static_cast<Uint64>(count / 3);
+        case GL_TRIANGLE_STRIP:
+        case GL_TRIANGLE_FAN: return count >= 3 ? static_cast<Uint64>(count - 2) : 0;
+        default: return 0;
+        }
+    }
+
+    // Accumulate the transform feedback primitive counter for a captured draw.
+    // Draws without a geometry stage write exactly the primitives they assemble,
+    // clamped by the capture buffers' remaining capacity (a full buffer stops
+    // recording whole primitives, which is what PRIMITIVES_WRITTEN reports).
+    // Geometry amplification is not modelled here.
+    static void AccountTransformFeedbackPrimitives(GLenum mode, GLsizei count) {
+        if (!MG_State::pGLContext->IsTransformFeedbackActive()) return;
+        // A paused span captures nothing, so a draw made while paused contributes to
+        // PRIMITIVES_GENERATED but not to TRANSFORM_FEEDBACK_PRIMITIVES_WRITTEN.
+        if (MG_State::pGLContext->IsTransformFeedbackPaused()) {
+            MG_State::pGLContext->AddTransformFeedbackPausedPrimitives(CountPrimitivesForDraw(mode, count));
+            return;
+        }
+        Uint64 primitives = CountPrimitivesForDraw(mode, count);
+        if (primitives == 0) return;
+        MG_State::pGLContext->AddTransformFeedbackInputPrimitives(primitives);
+
+        Uint64 verticesPerPrimitive = 1;
+        switch (mode) {
+        case GL_LINES:
+        case GL_LINE_STRIP:
+        case GL_LINE_LOOP:
+            verticesPerPrimitive = 2;
+            break;
+        case GL_TRIANGLES:
+        case GL_TRIANGLE_STRIP:
+        case GL_TRIANGLE_FAN:
+            verticesPerPrimitive = 3;
+            break;
+        default:
+            break;
+        }
+
+        const auto& program = MG_State::pGLContext->GetTransformFeedbackProgram();
+        if (program != nullptr) {
+            // Capacity in captured vertices = the tightest bound buffer.
+            Uint64 capacityVertices = ~0ull;
+            for (SizeT i = 0; i < program->GetTransformFeedbackBufferCount(); ++i) {
+                const Uint32 stride = program->GetTransformFeedbackStride(static_cast<Uint32>(i));
+                if (stride == 0) continue;
+                const auto& point = MG_State::pGLContext->GetBufferBindingPoint(BufferTarget::TransformFeedback,
+                                                                                static_cast<Uint>(i));
+                const Range1D range = point.GetRange();
+                const Uint64 bytes = range.end > range.start ? static_cast<Uint64>(range.end - range.start) : 0;
+                capacityVertices = std::min<Uint64>(capacityVertices, bytes / stride);
+            }
+            if (capacityVertices != ~0ull) {
+                const Uint64 usedVertices = MG_State::pGLContext->GetTransformFeedbackCapturedVertices();
+                const Uint64 remainingVertices = capacityVertices > usedVertices ? capacityVertices - usedVertices : 0;
+                primitives = std::min<Uint64>(primitives, remainingVertices / verticesPerPrimitive);
+            }
+        }
+        MG_State::pGLContext->AddTransformFeedbackPrimitives(primitives);
+        MG_State::pGLContext->AddTransformFeedbackCapturedVertices(primitives * verticesPerPrimitive);
+    }
+
+    // Every primitive mode a draw command accepts (GL 4.6 core table 10.1, plus
+    // GL_PATCHES for the tessellation pipeline). Anything else is GL_INVALID_ENUM.
+    static Bool IsAcceptedPrimitiveMode(GLenum mode) {
+        switch (mode) {
+        case GL_POINTS:
+        case GL_LINES:
+        case GL_LINE_LOOP:
+        case GL_LINE_STRIP:
+        case GL_LINES_ADJACENCY:
+        case GL_LINE_STRIP_ADJACENCY:
+        case GL_TRIANGLES:
+        case GL_TRIANGLE_STRIP:
+        case GL_TRIANGLE_FAN:
+        case GL_TRIANGLES_ADJACENCY:
+        case GL_TRIANGLE_STRIP_ADJACENCY:
+        case GL_PATCHES:
+            return true;
+        default:
+            return false;
+        }
+    }
+
     static Bool ValidatePrimitiveModeForBackend(const char* functionName, GLenum mode) {
+        if (!IsAcceptedPrimitiveMode(mode)) {
+            MG_State::pGLContext->RecordError(
+                ErrorCode::InvalidEnum,
+                MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", functionName, "mode is not an accepted primitive type."));
+            return false;
+        }
+
         const auto& activeBackendObject = MG_Backend::pActiveBackendObject;
         if (!activeBackendObject) {
             MG_State::pGLContext->RecordError(
@@ -57,17 +160,8 @@ namespace MobileGL::MG_Impl::GLImpl {
             return false;
         }
 
-        if (activeBackendObject->GetBackendType() == BackendType::DirectVulkan && mode == GL_LINE_LOOP) {
-            MG_State::pGLContext->RecordError(
-                ErrorCode::InvalidOperation,
-                MakeUnique<GenericErrorInfo>(
-                    "MG_Impl/GLImpl", functionName,
-                    "Primitive mode GL_LINE_LOOP is not supported by the DirectVulkan backend."));
-            return false;
-        }
-
         const auto& vao = MG_State::pGLContext->GetBoundVertexArray();
-        if (MG_State::pEGLContext->IsCurrentContextOpenGLCoreProfile() && vao && vao->GetExternalIndex() == 0) {
+        if (vao && vao->GetExternalIndex() == 0 && !MG_State::IsRelaxedSemanticsActive()) {
             MG_State::pGLContext->RecordError(
                 ErrorCode::InvalidOperation,
                 MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", functionName,
@@ -75,9 +169,133 @@ namespace MobileGL::MG_Impl::GLImpl {
             return false;
         }
 
+        // A geometry stage only accepts the primitive types that decompose into its declared
+        // input primitive (GL 4.6 core 11.3.1); anything else is INVALID_OPERATION. GL_PATCHES
+        // is the tessellation pipeline's input and reaches the geometry stage already
+        // converted, so it is not constrained here.
+        const auto& currentProgram = MG_State::pGLContext->GetProgramForDraw();
+        const GLenum gsInput = currentProgram ? currentProgram->GetGeometryInputType() : GL_NONE;
+        if (gsInput != GL_NONE && mode != GL_PATCHES) {
+            Bool compatible = false;
+            switch (gsInput) {
+            case GL_POINTS:
+                compatible = mode == GL_POINTS;
+                break;
+            case GL_LINES:
+                compatible = mode == GL_LINES || mode == GL_LINE_STRIP || mode == GL_LINE_LOOP;
+                break;
+            case GL_LINES_ADJACENCY:
+                compatible = mode == GL_LINES_ADJACENCY || mode == GL_LINE_STRIP_ADJACENCY;
+                break;
+            case GL_TRIANGLES:
+                compatible = mode == GL_TRIANGLES || mode == GL_TRIANGLE_STRIP || mode == GL_TRIANGLE_FAN;
+                break;
+            case GL_TRIANGLES_ADJACENCY:
+                compatible = mode == GL_TRIANGLES_ADJACENCY || mode == GL_TRIANGLE_STRIP_ADJACENCY;
+                break;
+            default:
+                break;
+            }
+            if (!compatible) {
+                MG_State::pGLContext->RecordError(
+                    ErrorCode::InvalidOperation,
+                    MakeUnique<GenericErrorInfo>(
+                        "MG_Impl/GLImpl", functionName,
+                        "Primitive mode is incompatible with the geometry shader's input primitive type."));
+                return false;
+            }
+        }
+
+        // While transform feedback is active the draw's primitive type must match
+        // the feedback primitive mode (GL 3.3 core 13.2.2). With a geometry shader
+        // the constraint moves to the shader's output primitive type instead, so
+        // the draw mode itself is unconstrained here. A paused span is exempt: it
+        // captures nothing, so there is nothing for the mode to be incompatible with
+        // (GL 4.6 core 13.2.3).
+        if (MG_State::pGLContext->IsTransformFeedbackActive() &&
+            !MG_State::pGLContext->IsTransformFeedbackPaused() &&
+            !(MG_State::pGLContext->GetTransformFeedbackProgram() &&
+              MG_State::pGLContext->GetTransformFeedbackProgram()->GetShaderIndexByStage(ShaderStage::Geometry) >= 0)) {
+            const GLenum feedbackMode = MG_State::pGLContext->GetTransformFeedbackPrimitiveMode();
+            Bool compatible = false;
+            switch (feedbackMode) {
+            case GL_POINTS:
+                compatible = mode == GL_POINTS;
+                break;
+            case GL_LINES:
+                compatible = mode == GL_LINES || mode == GL_LINE_STRIP || mode == GL_LINE_LOOP;
+                break;
+            case GL_TRIANGLES:
+                compatible = mode == GL_TRIANGLES || mode == GL_TRIANGLE_STRIP || mode == GL_TRIANGLE_FAN;
+                break;
+            default:
+                break;
+            }
+            if (!compatible) {
+                MG_State::pGLContext->RecordError(
+                    ErrorCode::InvalidOperation,
+                    MakeUnique<GenericErrorInfo>(
+                        "MG_Impl/GLImpl", functionName,
+                        "Primitive mode is incompatible with the active transform feedback primitive mode."));
+                return false;
+            }
+        }
+
         return true;
     }
 
+    // Byte size of the command structures the indirect draws read (GL 4.6 core 10.3.10).
+    constexpr SizeT kDrawArraysIndirectCommandBytes = 4 * sizeof(Uint32);
+    constexpr SizeT kDrawElementsIndirectCommandBytes = 5 * sizeof(Uint32);
+
+    // Shared preconditions of every *Indirect draw: `indirect` is a byte offset into the
+    // buffer bound to GL_DRAW_INDIRECT_BUFFER, must be 4-byte aligned, and the whole
+    // command has to lie inside that buffer.
+    static Bool ValidateIndirectDrawSource(const char* functionName, const void* indirect, SizeT commandBytes) {
+        const auto offset = reinterpret_cast<uintptr_t>(indirect);
+        if (offset % 4 != 0) {
+            MG_State::pGLContext->RecordError(
+                ErrorCode::InvalidValue,
+                MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", functionName,
+                                             "indirect offset must be a multiple of 4."));
+            return false;
+        }
+
+        const auto& buffer = MG_State::pGLContext->GetBufferBindingSlot(BufferTarget::DrawIndirect).GetBoundObject();
+        if (!buffer) {
+            MG_State::pGLContext->RecordError(
+                ErrorCode::InvalidOperation,
+                MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", functionName,
+                                             "No buffer is bound to GL_DRAW_INDIRECT_BUFFER."));
+            return false;
+        }
+
+        if (offset + commandBytes > buffer->GetSize()) {
+            MG_State::pGLContext->RecordError(
+                ErrorCode::InvalidOperation,
+                MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", functionName,
+                                             "The indirect command extends past the end of the bound "
+                                             "GL_DRAW_INDIRECT_BUFFER."));
+            return false;
+        }
+        return true;
+    }
+
+    // Index type accepted by the DrawElements family (GL 4.6 core 10.3.9).
+    static Bool ValidateDrawElementsIndexType(const char* functionName, GLenum type) {
+        switch (type) {
+        case GL_UNSIGNED_BYTE:
+        case GL_UNSIGNED_SHORT:
+        case GL_UNSIGNED_INT:
+            return true;
+        default:
+            MG_State::pGLContext->RecordError(
+                ErrorCode::InvalidEnum,
+                MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", functionName, "type is not an accepted index type."));
+            return false;
+        }
+    }
+
     void Clear_Backend(GLbitfield mask) {
 #ifdef TRACY_ENABLE
         ZoneScopedC(TRACY_ZONECOLOR_BACKEND);
@@ -256,6 +474,21 @@ namespace MobileGL::MG_Impl::GLImpl {
             return;
         }
         if (!ValidateCurrentProgramForCompute(__func__)) return;
+        // GL 4.6 core 19: each num_groups_* must be within GL_MAX_COMPUTE_WORK_GROUP_COUNT
+        // for its dimension. GetIntegeri_v already floors that at the spec minimum.
+        const GLuint numGroups[3] = {numGroupsX, numGroupsY, numGroupsZ};
+        for (GLuint dimension = 0; dimension < 3; ++dimension) {
+            GLint maxGroups = 0;
+            GetIntegeri_v(GL_MAX_COMPUTE_WORK_GROUP_COUNT, dimension, &maxGroups);
+            if (numGroups[dimension] > static_cast<GLuint>(std::max(maxGroups, 0))) {
+                MG_State::pGLContext->RecordError(
+                    ErrorCode::InvalidValue,
+                    MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", __func__,
+                                                 "num_groups exceeds GL_MAX_COMPUTE_WORK_GROUP_COUNT for dimension " +
+                                                     std::to_string(dimension) + "."));
+                return;
+            }
+        }
         dispatchCompute(numGroupsX, numGroupsY, numGroupsZ);
     }
 
@@ -269,9 +502,49 @@ namespace MobileGL::MG_Impl::GLImpl {
             return;
         }
         if (!ValidateCurrentProgramForCompute(__func__)) return;
+        // GL 4.6 core 19: `indirect` is a byte offset into GL_DISPATCH_INDIRECT_BUFFER -
+        // negative or misaligned is INVALID_VALUE, nothing bound is INVALID_OPERATION.
+        if (indirect < 0 || (indirect % 4) != 0) {
+            MG_State::pGLContext->RecordError(
+                ErrorCode::InvalidValue,
+                MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", __func__,
+                                             "indirect must be non-negative and a multiple of 4."));
+            return;
+        }
+        const auto& indirectBuffer =
+            MG_State::pGLContext->GetBufferBindingSlot(BufferTarget::DispatchIndirect).GetBoundObject();
+        if (!indirectBuffer) {
+            MG_State::pGLContext->RecordError(
+                ErrorCode::InvalidOperation,
+                MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", __func__,
+                                             "No buffer is bound to GL_DISPATCH_INDIRECT_BUFFER."));
+            return;
+        }
         dispatchComputeIndirect(indirect);
     }
 
+    void PatchParameteri(GLenum pname, GLint value) {
+        if (pname != GL_PATCH_VERTICES) {
+            MG_State::pGLContext->RecordError(
+                ErrorCode::InvalidEnum,
+                MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", __func__, "pname must be GL_PATCH_VERTICES."));
+            return;
+        }
+        GLint maxPatchVertices = 32;
+        GetIntegerv(GL_MAX_PATCH_VERTICES, &maxPatchVertices);
+        if (value <= 0 || value > maxPatchVertices) {
+            MG_State::pGLContext->RecordError(
+                ErrorCode::InvalidValue,
+                MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", __func__,
+                                             "value must be in [1, GL_MAX_PATCH_VERTICES]."));
+            return;
+        }
+        MG_State::pGLContext->SetPatchVertices(static_cast<Uint>(value));
+        if (const auto patchParameteri = MG_Backend::gBackendFunctionsTable.GL.PatchParameteri) {
+            patchParameteri(pname, value);
+        }
+    }
+
     void MemoryBarrier(GLbitfield barriers) {
         auto memoryBarrier = MG_Backend::gBackendFunctionsTable.GL.MemoryBarrier;
         if (!memoryBarrier) {
@@ -377,6 +650,8 @@ namespace MobileGL::MG_Impl::GLImpl {
     void DrawElementsIndirect(GLenum mode, GLenum type, const void* indirect) {
         if (!ValidateCurrentProgramForExecution(__func__)) return;
         if (!ValidatePrimitiveModeForBackend(__func__, mode)) return;
+        if (!ValidateDrawElementsIndexType(__func__, type)) return;
+        if (!ValidateIndirectDrawSource(__func__, indirect, kDrawElementsIndirectCommandBytes)) return;
         DrawElementsIndirect_Backend(mode, type, indirect);
     }
 
@@ -396,18 +671,21 @@ namespace MobileGL::MG_Impl::GLImpl {
     void DrawArraysIndirect(GLenum mode, const void* indirect) {
         if (!ValidateCurrentProgramForExecution(__func__)) return;
         if (!ValidatePrimitiveModeForBackend(__func__, mode)) return;
+        if (!ValidateIndirectDrawSource(__func__, indirect, kDrawArraysIndirectCommandBytes)) return;
         DrawArraysIndirect_Backend(mode, indirect);
     }
 
     void DrawElementsBaseVertex(GLenum mode, GLsizei count, GLenum type, const void* indices, GLint basevertex) {
         if (!ValidateCurrentProgramForExecution(__func__)) return;
         if (!ValidatePrimitiveModeForBackend(__func__, mode)) return;
+        AccountTransformFeedbackPrimitives(mode, count);
         DrawElementsBaseVertex_Backend(mode, count, type, indices, basevertex);
     }
 
     void DrawArrays(GLenum mode, GLint first, GLsizei count) {
         if (!ValidateCurrentProgramForExecution(__func__)) return;
         if (!ValidatePrimitiveModeForBackend(__func__, mode)) return;
+        AccountTransformFeedbackPrimitives(mode, count);
         DrawArrays_Backend(mode, first, count);
     }
 
@@ -444,7 +722,487 @@ namespace MobileGL::MG_Impl::GLImpl {
     void DrawElements(GLenum mode, GLsizei count, GLenum type, const void* indices) {
         if (!ValidateCurrentProgramForExecution(__func__)) return;
         if (!ValidatePrimitiveModeForBackend(__func__, mode)) return;
+        AccountTransformFeedbackPrimitives(mode, count);
         DrawElements_Backend(mode, count, type, indices);
     }
 
+    void BeginTransformFeedback(GLenum primitiveMode) {
+        if (primitiveMode != GL_POINTS && primitiveMode != GL_LINES && primitiveMode != GL_TRIANGLES) {
+            MG_State::pGLContext->RecordError(
+                ErrorCode::InvalidEnum,
+                MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", __func__,
+                                             "primitiveMode must be GL_POINTS, GL_LINES or GL_TRIANGLES."));
+            return;
+        }
+        if (MG_State::pGLContext->IsTransformFeedbackActive()) {
+            MG_State::pGLContext->RecordError(
+                ErrorCode::InvalidOperation,
+                MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", __func__, "Transform feedback is already active."));
+            return;
+        }
+        const auto& program = MG_State::pGLContext->GetProgramForDraw();
+        if (!program || !program->GetLinkStatus() || program->GetTransformFeedbackVaryingCount() == 0) {
+            MG_State::pGLContext->RecordError(
+                ErrorCode::InvalidOperation,
+                MakeUnique<GenericErrorInfo>(
+                    "MG_Impl/GLImpl", __func__,
+                    "No program with transform feedback varyings is active."));
+            return;
+        }
+        // Every capture buffer slot the program's mode uses must have a buffer bound. A slot
+        // of stride 0 - two consecutive gl_NextBuffer entries - captures nothing and so needs
+        // no binding.
+        const SizeT usedBufferCount = program->GetTransformFeedbackBufferCount();
+        for (SizeT i = 0; i < usedBufferCount; ++i) {
+            if (program->GetTransformFeedbackStride(static_cast<Uint32>(i)) == 0) continue;
+            const auto& point = MG_State::pGLContext->GetBufferBindingPoint(BufferTarget::TransformFeedback,
+                                                                            static_cast<Uint>(i));
+            if (point.GetBoundObject() == nullptr) {
+                MG_State::pGLContext->RecordError(
+                    ErrorCode::InvalidOperation,
+                    MakeUnique<GenericErrorInfo>(
+                        "MG_Impl/GLImpl", __func__,
+                        "Transform feedback buffer binding point " + std::to_string(i) + " has no buffer bound."));
+                return;
+            }
+        }
+        MG_State::pGLContext->BeginTransformFeedback(primitiveMode, program);
+        if (const auto beginXfb = MG_Backend::gBackendFunctionsTable.GL.BeginTransformFeedback) {
+            beginXfb(primitiveMode);
+        }
+    }
+
+    // Vulkan transform feedback captures triangle strips in plain (i, i+1, i+2)
+    // vertex order, but GL decomposes odd strip triangles as (i+1, i, i+2)
+    // (GL 4.6 table 10.1). With the geometry stage's statically-known strip
+    // lengths the captured records are reordered in place: swap the first two
+    // vertex records of every odd triangle within each emitted strip.
+    static void FixupGsStripCaptureOrder(const SharedPtr<MG_State::GLState::ProgramObject>& program,
+                                         Uint64 inputPrimitives) {
+        // Only Vulkan-order captures need this. A backend that runs the capture on its
+        // own GL/ES driver (it owns the span, hence the EndTransformFeedback entry) has
+        // already produced GL's vertex order, and reordering it again would corrupt it.
+        if (MG_Backend::gBackendFunctionsTable.GL.EndTransformFeedback != nullptr) {
+            return;
+        }
+        if (program == nullptr || !program->HasGsTriangleStripCaptureFixup() || inputPrimitives == 0) {
+            return;
+        }
+        const auto& stripTriangles = program->GetGsStripTriangles();
+
+        // Global triangle indices whose leading vertex pair must swap.
+        Vector<Uint64> swapTriangles;
+        Uint64 triangleBase = 0;
+        for (Uint64 input = 0; input < inputPrimitives; ++input) {
+            for (const Uint32 stripLength : stripTriangles) {
+                for (Uint32 t = 1; t < stripLength; t += 2) {
+                    swapTriangles.push_back(triangleBase + t);
+                }
+                triangleBase += stripLength;
+            }
+        }
+        if (swapTriangles.empty()) {
+            return;
+        }
+
+        for (SizeT bufferIndex = 0; bufferIndex < program->GetTransformFeedbackBufferCount(); ++bufferIndex) {
+            const Uint32 stride = program->GetTransformFeedbackStride(static_cast<Uint32>(bufferIndex));
+            if (stride == 0) continue;
+            const auto& bindingPoint =
+                MG_State::pGLContext->GetBufferBindingPoint(BufferTarget::TransformFeedback,
+                                                            static_cast<Uint>(bufferIndex));
+            const auto& buffer = bindingPoint.GetBoundObject();
+            if (buffer == nullptr) continue;
+            const Range1D range = bindingPoint.GetRange();
+            const Uint8* mapped = buffer->MappedData();
+            if (mapped == nullptr) continue;
+            // The geometry stage amplifies, so the CPU vertex counter does not bound
+            // the capture; the binding range's whole-triangle capacity does.
+            const Uint64 rangeBytes = range.end > range.start ? static_cast<Uint64>(range.end - range.start) : 0;
+            const Uint64 capturedTriangles = std::min<Uint64>(triangleBase, (rangeBytes / stride) / 3);
+
+            // Observed Vulkan capture order for odd strip triangles is (i, i+2, i+1)
+            // (winding preserved by swapping the trailing pair); GL wants
+            // (i+1, i, i+2), which is one rotation away: (a,b,c) -> (c,a,b).
+            Vector<Uint8> scratch(stride);
+            for (const Uint64 triangle : swapTriangles) {
+                if (triangle >= capturedTriangles) break;
+                const SizeT v0Offset = static_cast<SizeT>(range.start) + static_cast<SizeT>(triangle * 3) * stride;
+                const SizeT v1Offset = v0Offset + stride;
+                const SizeT v2Offset = v1Offset + stride;
+                Memcpy(scratch.data(), mapped + v2Offset, stride);
+                buffer->WritebackFromBackend({const_cast<Uint8*>(mapped) + v1Offset, stride}, v2Offset);
+                buffer->WritebackFromBackend({const_cast<Uint8*>(mapped) + v0Offset, stride}, v1Offset);
+                buffer->WritebackFromBackend({scratch.data(), stride}, v0Offset);
+            }
+        }
+    }
+
+    void EndTransformFeedback(void) {
+        if (!MG_State::pGLContext->IsTransformFeedbackActive()) {
+            MG_State::pGLContext->RecordError(
+                ErrorCode::InvalidOperation,
+                MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", __func__, "Transform feedback is not active."));
+            return;
+        }
+        const auto capturedProgram = MG_State::pGLContext->GetTransformFeedbackProgram();
+        const Uint64 inputPrimitives = MG_State::pGLContext->GetTransformFeedbackInputPrimitives();
+        // Closed while the capture state is still active: a backend that captures
+        // through its own driver reads the capture program and buffer bindings here.
+        if (const auto endXfb = MG_Backend::gBackendFunctionsTable.GL.EndTransformFeedback) {
+            endXfb();
+        }
+        MG_State::pGLContext->EndTransformFeedback();
+        // Captured results must be visible to MapBuffer/GetBufferSubData after
+        // End; the capture targets are host-coherent GPU memory, so completing
+        // the GPU work is all that is required.
+        auto& backendGL = MG_Backend::gBackendFunctionsTable.GL;
+        if (backendGL.FenceSync && backendGL.ClientWaitSync) {
+            if (auto sync = backendGL.FenceSync()) {
+                backendGL.ClientWaitSync(sync, GL_SYNC_FLUSH_COMMANDS_BIT, ~0ull);
+                if (backendGL.DeleteSync) {
+                    backendGL.DeleteSync(sync);
+                }
+            }
+        }
+        FixupGsStripCaptureOrder(capturedProgram, inputPrimitives);
+    }
+
+    void PauseTransformFeedback(void) {
+        if (!MG_State::pGLContext->IsTransformFeedbackActive() ||
+            MG_State::pGLContext->IsTransformFeedbackPaused()) {
+            MG_State::pGLContext->RecordError(
+                ErrorCode::InvalidOperation,
+                MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", __func__,
+                                             "Transform feedback is not active, or is already paused."));
+            return;
+        }
+        MG_State::pGLContext->SetTransformFeedbackPaused(true);
+        if (const auto pauseXfb = MG_Backend::gBackendFunctionsTable.GL.PauseTransformFeedback) {
+            pauseXfb();
+        }
+    }
+
+    void ResumeTransformFeedback(void) {
+        if (!MG_State::pGLContext->IsTransformFeedbackActive() ||
+            !MG_State::pGLContext->IsTransformFeedbackPaused()) {
+            MG_State::pGLContext->RecordError(
+                ErrorCode::InvalidOperation,
+                MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", __func__, "Transform feedback is not paused."));
+            return;
+        }
+        MG_State::pGLContext->SetTransformFeedbackPaused(false);
+        if (const auto resumeXfb = MG_Backend::gBackendFunctionsTable.GL.ResumeTransformFeedback) {
+            resumeXfb();
+        }
+    }
+
+    void GenTransformFeedbacks(GLsizei n, GLuint* ids) {
+        if (n < 0) {
+            MG_State::pGLContext->RecordError(
+                ErrorCode::InvalidValue,
+                MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", __func__, "n must be non-negative."));
+            return;
+        }
+        if (n == 0 || ids == nullptr) return;
+        Vector<Uint> names;
+        MG_State::pGLContext->GenTransformFeedbackNames(static_cast<Uint>(n), names);
+        Memcpy(ids, names.data(), static_cast<SizeT>(n) * sizeof(GLuint));
+    }
+
+    void CreateTransformFeedbacks(GLsizei n, GLuint* ids) {
+        if (n < 0) {
+            MG_State::pGLContext->RecordError(
+                ErrorCode::InvalidValue,
+                MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", __func__, "n must be non-negative."));
+            return;
+        }
+        if (n == 0 || ids == nullptr) return;
+        Vector<Uint> names;
+        MG_State::pGLContext->GenTransformFeedbackNames(static_cast<Uint>(n), names);
+        // Unlike glGenTransformFeedbacks, the names are objects immediately: there is no bind step
+        // to create them from (GL 4.6 core 13.2.1).
+        for (const Uint name : names) {
+            MG_State::pGLContext->CreateTransformFeedbackObject(name);
+        }
+        Memcpy(ids, names.data(), static_cast<SizeT>(n) * sizeof(GLuint));
+    }
+
+    namespace {
+        // Shared front half of the by-name transform feedback entry points: the object has to exist
+        // (INVALID_OPERATION otherwise) before anything else about the call is looked at.
+        Bool ValidateNamedTransformFeedback(GLuint xfb, const char* functionName) {
+            if (!MG_State::pGLContext->IsTransformFeedbackObject(xfb)) {
+                MG_State::pGLContext->RecordError(
+                    ErrorCode::InvalidOperation,
+                    MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", functionName,
+                                                 std::to_string(xfb) + " is not a transform feedback object."));
+                return false;
+            }
+            return true;
+        }
+
+        Bool ValidateTransformFeedbackBufferIndex(GLuint index, const char* functionName) {
+            if (index >= MG_State::GLState::GLContext::MAX_TRANSFORM_FEEDBACK_BUFFERS) {
+                MG_State::pGLContext->RecordError(
+                    ErrorCode::InvalidValue,
+                    MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", functionName,
+                                                 "index exceeds GL_MAX_TRANSFORM_FEEDBACK_BUFFERS."));
+                return false;
+            }
+            return true;
+        }
+
+        // A capture binding may not be changed while the object is capturing (GL 4.6 core 13.2.2).
+        Bool ValidateNamedTransformFeedbackNotActive(GLuint xfb, const char* functionName) {
+            if (MG_State::pGLContext->IsNamedTransformFeedbackActive(xfb)) {
+                MG_State::pGLContext->RecordError(
+                    ErrorCode::InvalidOperation,
+                    MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", functionName,
+                                                 "The transform feedback object is capturing."));
+                return false;
+            }
+            return true;
+        }
+
+        SharedPtr<MG_State::GLState::BufferObject> ResolveTransformFeedbackBuffer(GLuint buffer,
+                                                                                 const char* functionName) {
+            if (buffer == 0) return nullptr;
+            if (!MG_State::pGLContext->ValidateBufferName(buffer)) {
+                MG_State::pGLContext->RecordError(
+                    ErrorCode::InvalidOperation,
+                    MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", functionName,
+                                                 std::to_string(buffer) + " is not a buffer object."));
+                return nullptr;
+            }
+            return MG_State::pGLContext->GetBufferObject(buffer);
+        }
+    } // namespace
+
+    void TransformFeedbackBufferBase(GLuint xfb, GLuint index, GLuint buffer) {
+        if (!ValidateNamedTransformFeedback(xfb, __func__)) return;
+        if (!ValidateTransformFeedbackBufferIndex(index, __func__)) return;
+        if (!ValidateNamedTransformFeedbackNotActive(xfb, __func__)) return;
+        if (buffer != 0 && !MG_State::pGLContext->ValidateBufferName(buffer)) {
+            MG_State::pGLContext->RecordError(
+                ErrorCode::InvalidOperation,
+                MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", __func__,
+                                             std::to_string(buffer) + " is not a buffer object."));
+            return;
+        }
+        MG_State::pGLContext->SetNamedTransformFeedbackBinding(xfb, index,
+                                                               ResolveTransformFeedbackBuffer(buffer, __func__), {},
+                                                               false);
+    }
+
+    void TransformFeedbackBufferRange(GLuint xfb, GLuint index, GLuint buffer, GLintptr offset, GLsizeiptr size) {
+        if (!ValidateNamedTransformFeedback(xfb, __func__)) return;
+        if (!ValidateTransformFeedbackBufferIndex(index, __func__)) return;
+        if (!ValidateNamedTransformFeedbackNotActive(xfb, __func__)) return;
+        if (offset < 0 || size <= 0 || (offset % 4) != 0 || (size % 4) != 0) {
+            MG_State::pGLContext->RecordError(
+                ErrorCode::InvalidValue,
+                MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", __func__,
+                                             "offset and size must be non-negative multiples of 4."));
+            return;
+        }
+        if (buffer != 0 && !MG_State::pGLContext->ValidateBufferName(buffer)) {
+            MG_State::pGLContext->RecordError(
+                ErrorCode::InvalidOperation,
+                MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", __func__,
+                                             std::to_string(buffer) + " is not a buffer object."));
+            return;
+        }
+        auto bufferObject = ResolveTransformFeedbackBuffer(buffer, __func__);
+        const Range1D range{static_cast<SizeT>(offset), static_cast<SizeT>(offset) + static_cast<SizeT>(size)};
+        MG_State::pGLContext->SetNamedTransformFeedbackBinding(xfb, index, bufferObject, range,
+                                                               bufferObject != nullptr);
+    }
+
+    void GetTransformFeedbackiv(GLuint xfb, GLenum pname, GLint* param) {
+        if (!ValidateNamedTransformFeedback(xfb, __func__)) return;
+        if (!param) return;
+        switch (pname) {
+        case GL_TRANSFORM_FEEDBACK_ACTIVE:
+            *param = MG_State::pGLContext->IsNamedTransformFeedbackActive(xfb) ? GL_TRUE : GL_FALSE;
+            return;
+        case GL_TRANSFORM_FEEDBACK_PAUSED:
+            *param = MG_State::pGLContext->IsNamedTransformFeedbackPaused(xfb) ? GL_TRUE : GL_FALSE;
+            return;
+        default:
+            MG_State::pGLContext->RecordError(
+                ErrorCode::InvalidEnum,
+                MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", __func__,
+                                             "pname must be GL_TRANSFORM_FEEDBACK_ACTIVE or _PAUSED."));
+            return;
+        }
+    }
+
+    void GetTransformFeedbacki_v(GLuint xfb, GLenum pname, GLuint index, GLint* param) {
+        if (!ValidateNamedTransformFeedback(xfb, __func__)) return;
+        if (pname != GL_TRANSFORM_FEEDBACK_BUFFER_BINDING) {
+            MG_State::pGLContext->RecordError(
+                ErrorCode::InvalidEnum,
+                MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", __func__,
+                                             "pname must be GL_TRANSFORM_FEEDBACK_BUFFER_BINDING."));
+            return;
+        }
+        if (!ValidateTransformFeedbackBufferIndex(index, __func__)) return;
+        if (!param) return;
+        const auto binding = MG_State::pGLContext->GetNamedTransformFeedbackBinding(xfb, index);
+        *param = binding.Buffer ? static_cast<GLint>(binding.Buffer->GetExternalIndex()) : 0;
+    }
+
+    void GetTransformFeedbacki64_v(GLuint xfb, GLenum pname, GLuint index, GLint64* param) {
+        if (!ValidateNamedTransformFeedback(xfb, __func__)) return;
+        if (pname != GL_TRANSFORM_FEEDBACK_BUFFER_START && pname != GL_TRANSFORM_FEEDBACK_BUFFER_SIZE) {
+            MG_State::pGLContext->RecordError(
+                ErrorCode::InvalidEnum,
+                MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", __func__,
+                                             "pname must be GL_TRANSFORM_FEEDBACK_BUFFER_START or _SIZE."));
+            return;
+        }
+        if (!ValidateTransformFeedbackBufferIndex(index, __func__)) return;
+        if (!param) return;
+        const auto binding = MG_State::pGLContext->GetNamedTransformFeedbackBinding(xfb, index);
+        // glTransformFeedbackBufferBase leaves both at zero; only the range form sets them
+        // (GL 4.6 core table 23.48).
+        if (!binding.Buffer || !binding.HasExplicitRange) {
+            *param = 0;
+            return;
+        }
+        *param = (pname == GL_TRANSFORM_FEEDBACK_BUFFER_START)
+                     ? static_cast<GLint64>(binding.Range.start)
+                     : static_cast<GLint64>(binding.Range.end - binding.Range.start);
+    }
+
+    void DeleteTransformFeedbacks(GLsizei n, const GLuint* ids) {
+        if (n < 0) {
+            MG_State::pGLContext->RecordError(
+                ErrorCode::InvalidValue,
+                MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", __func__, "n must be non-negative."));
+            return;
+        }
+        if (ids == nullptr) return;
+        for (GLsizei i = 0; i < n; ++i) {
+            const GLuint id = ids[i];
+            // Unknown names and 0 are silently ignored; an object whose capture span is
+            // still open is not (GL 4.6 core 13.2.1).
+            if (id == 0 || !MG_State::pGLContext->ValidateTransformFeedbackName(id)) continue;
+            if (id == MG_State::pGLContext->GetBoundTransformFeedbackName() &&
+                MG_State::pGLContext->IsTransformFeedbackActive()) {
+                MG_State::pGLContext->RecordError(
+                    ErrorCode::InvalidOperation,
+                    MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", __func__,
+                                                 "Cannot delete a transform feedback object whose capture is active."));
+                continue;
+            }
+            if (const auto deleteXfb = MG_Backend::gBackendFunctionsTable.GL.DeleteTransformFeedback) {
+                deleteXfb(id);
+            }
+            MG_State::pGLContext->MarkTransformFeedbackObjectForDeletion(id);
+        }
+    }
+
+    void BindTransformFeedback(GLenum target, GLuint id) {
+        if (target != GL_TRANSFORM_FEEDBACK) {
+            MG_State::pGLContext->RecordError(
+                ErrorCode::InvalidEnum,
+                MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", __func__, "target must be GL_TRANSFORM_FEEDBACK."));
+            return;
+        }
+        // A running capture pins its object; only a paused one may be swapped out.
+        if (MG_State::pGLContext->IsTransformFeedbackActive() &&
+            !MG_State::pGLContext->IsTransformFeedbackPaused()) {
+            MG_State::pGLContext->RecordError(
+                ErrorCode::InvalidOperation,
+                MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", __func__,
+                                             "Transform feedback is active and not paused."));
+            return;
+        }
+        if (!MG_State::pGLContext->ValidateTransformFeedbackName(id)) {
+            MG_State::pGLContext->RecordError(
+                ErrorCode::InvalidOperation,
+                MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", __func__,
+                                             std::to_string(id) + " is not a transform feedback object name."));
+            return;
+        }
+        MG_State::pGLContext->BindTransformFeedbackObject(id);
+        if (const auto bindXfb = MG_Backend::gBackendFunctionsTable.GL.BindTransformFeedback) {
+            bindXfb(id);
+        }
+    }
+
+    GLboolean IsTransformFeedback(GLuint id) {
+        // Name 0 is the default object, and a name glGenTransformFeedbacks handed out only
+        // becomes the name of an object once it has been bound.
+        return MG_State::pGLContext->IsTransformFeedbackObject(id) ? GL_TRUE : GL_FALSE;
+    }
+
+    // glDrawTransformFeedback[Stream][Instanced]: replays the vertices the named object
+    // captured in its last completed span, as if by glDrawArraysInstanced with that count
+    // (GL 4.6 core 10.3.7).
+    static void DrawTransformFeedbackImpl(const char* functionName, GLenum mode, GLuint id, GLuint stream,
+                                          GLsizei instancecount) {
+        if (!ValidateCurrentProgramForExecution(functionName)) return;
+        if (!ValidatePrimitiveModeForBackend(functionName, mode)) return;
+        if (instancecount < 0) {
+            MG_State::pGLContext->RecordError(
+                ErrorCode::InvalidValue,
+                MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", functionName, "instancecount must be non-negative."));
+            return;
+        }
+        if (!MG_State::pGLContext->ValidateTransformFeedbackName(id)) {
+            MG_State::pGLContext->RecordError(
+                ErrorCode::InvalidValue,
+                MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", functionName,
+                                             std::to_string(id) + " is not a transform feedback object name."));
+            return;
+        }
+        // GL_MAX_VERTEX_STREAMS is 1, so stream 0 is the only one that exists.
+        if (stream != 0) {
+            MG_State::pGLContext->RecordError(
+                ErrorCode::InvalidValue,
+                MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", functionName,
+                                             "stream must be less than GL_MAX_VERTEX_STREAMS."));
+            return;
+        }
+        // Drawing from an object whose capture is currently open is legal and deliberate:
+        // it is how a transform feedback result is fed straight back into the next span
+        // (ARB_transform_feedback2 lists no such restriction).
+        if (!MG_State::pGLContext->HasTransformFeedbackCompletedSpan(id)) {
+            MG_State::pGLContext->RecordError(
+                ErrorCode::InvalidOperation,
+                MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", functionName,
+                                             "glEndTransformFeedback has never been called for this object."));
+            return;
+        }
+
+        const Uint64 vertices = MG_State::pGLContext->GetTransformFeedbackRecordedVertices(id);
+        if (vertices == 0) return;
+        const auto count = static_cast<GLsizei>(vertices);
+        AccountTransformFeedbackPrimitives(mode, count);
+        if (instancecount == 1) {
+            DrawArrays_Backend(mode, 0, count);
+        } else {
+            DrawArraysInstanced_Backend(mode, 0, count, instancecount);
+        }
+    }
+
+    void DrawTransformFeedback(GLenum mode, GLuint id) {
+        DrawTransformFeedbackImpl(__func__, mode, id, 0, 1);
+    }
+
+    void DrawTransformFeedbackInstanced(GLenum mode, GLuint id, GLsizei instancecount) {
+        DrawTransformFeedbackImpl(__func__, mode, id, 0, instancecount);
+    }
+
+    void DrawTransformFeedbackStream(GLenum mode, GLuint id, GLuint stream) {
+        DrawTransformFeedbackImpl(__func__, mode, id, stream, 1);
+    }
+
+    void DrawTransformFeedbackStreamInstanced(GLenum mode, GLuint id, GLuint stream, GLsizei instancecount) {
+        DrawTransformFeedbackImpl(__func__, mode, id, stream, instancecount);
+    }
+
 } // namespace MobileGL::MG_Impl::GLImpl

MobileGL/MG_Impl/GLImpl/Drawing/GL_Drawing.h

@@ -11,8 +11,27 @@
 
 namespace MobileGL::MG_Impl::GLImpl {
     /* @INSERTION_POINT:FUNCTION_DECLARATION@ */
+    void BeginTransformFeedback(GLenum primitiveMode);
+    void EndTransformFeedback(void);
+    void PauseTransformFeedback(void);
+    void ResumeTransformFeedback(void);
+    void GenTransformFeedbacks(GLsizei n, GLuint* ids);
+    void CreateTransformFeedbacks(GLsizei n, GLuint* ids);
+    void DeleteTransformFeedbacks(GLsizei n, const GLuint* ids);
+    void TransformFeedbackBufferBase(GLuint xfb, GLuint index, GLuint buffer);
+    void TransformFeedbackBufferRange(GLuint xfb, GLuint index, GLuint buffer, GLintptr offset, GLsizeiptr size);
+    void GetTransformFeedbackiv(GLuint xfb, GLenum pname, GLint* param);
+    void GetTransformFeedbacki_v(GLuint xfb, GLenum pname, GLuint index, GLint* param);
+    void GetTransformFeedbacki64_v(GLuint xfb, GLenum pname, GLuint index, GLint64* param);
+    void BindTransformFeedback(GLenum target, GLuint id);
+    GLboolean IsTransformFeedback(GLuint id);
+    void DrawTransformFeedback(GLenum mode, GLuint id);
+    void DrawTransformFeedbackInstanced(GLenum mode, GLuint id, GLsizei instancecount);
+    void DrawTransformFeedbackStream(GLenum mode, GLuint id, GLuint stream);
+    void DrawTransformFeedbackStreamInstanced(GLenum mode, GLuint id, GLuint stream, GLsizei instancecount);
     void DispatchCompute(GLuint numGroupsX, GLuint numGroupsY, GLuint numGroupsZ);
     void DispatchComputeIndirect(GLintptr indirect);
+    void PatchParameteri(GLenum pname, GLint value);
     void MemoryBarrier(GLbitfield barriers);
     void MemoryBarrierByRegion(GLbitfield barriers);
     void MultiDrawElementsIndirect(GLenum mode, GLenum type, const void* indirect, GLsizei drawcount, GLsizei stride);

MobileGL/MG_Impl/GLImpl/Exporting/Definitions.cpp

@@ -15,6 +15,7 @@
 #include "../Texture/GL_Texture.h"
 #include "../Drawing/GL_Drawing.h"
 #include "../Program/GL_Program.h"
+#include "../Program/GL_ProgramPipeline.h"
 #include "../RenderState/GL_RenderState.h"
 #include "../Framebuffer/GL_Framebuffer.h"
 #include "../VertexArray/GL_VertexArray.h"
@@ -236,12 +237,12 @@ DECLARE_GL_FUNCTION_HEAD(void, DeleteVertexArrays, GLsizei n, const GLuint* arra
 DECLARE_GL_FUNCTION_HEAD(void, GenVertexArrays, GLsizei n, GLuint* arrays) DECLARE_GL_FUNCTION_END_NO_RETURN(void, GenVertexArrays, n, arrays)
 DECLARE_GL_FUNCTION_HEAD(GLboolean, IsVertexArray, GLuint array) DECLARE_GL_FUNCTION_END(GLboolean, IsVertexArray, array)
 DECLARE_GL_FUNCTION_HEAD(void, GetIntegeri_v, GLenum target, GLuint index, GLint* data) DECLARE_GL_FUNCTION_END_NO_RETURN(void, GetIntegeri_v, target, index, data)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, BeginTransformFeedback, GLenum primitiveMode) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, BeginTransformFeedback, primitiveMode)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, EndTransformFeedback) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, EndTransformFeedback)
+DECLARE_GL_FUNCTION_HEAD(void, BeginTransformFeedback, GLenum primitiveMode) DECLARE_GL_FUNCTION_END_NO_RETURN(void, BeginTransformFeedback, primitiveMode)
+DECLARE_GL_FUNCTION_HEAD(void, EndTransformFeedback) DECLARE_GL_FUNCTION_END_NO_RETURN(void, EndTransformFeedback)
 DECLARE_GL_FUNCTION_HEAD(void, BindBufferRange, GLenum target, GLuint index, GLuint buffer, GLintptr offset, GLsizeiptr size) DECLARE_GL_FUNCTION_END_NO_RETURN(void, BindBufferRange, target, index, buffer, offset, size)
 DECLARE_GL_FUNCTION_HEAD(void, BindBufferBase, GLenum target, GLuint index, GLuint buffer) DECLARE_GL_FUNCTION_END_NO_RETURN(void, BindBufferBase, target, index, buffer)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, TransformFeedbackVaryings, GLuint program, GLsizei count, const GLchar* const* varyings, GLenum bufferMode) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, TransformFeedbackVaryings, program, count, varyings, bufferMode)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, GetTransformFeedbackVarying, GLuint program, GLuint index, GLsizei bufSize, GLsizei* length, GLsizei* size, GLenum* type, GLchar* name) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, GetTransformFeedbackVarying, program, index, bufSize, length, size, type, name)
+DECLARE_GL_FUNCTION_HEAD(void, TransformFeedbackVaryings, GLuint program, GLsizei count, const GLchar* const* varyings, GLenum bufferMode) DECLARE_GL_FUNCTION_END_NO_RETURN(void, TransformFeedbackVaryings, program, count, varyings, bufferMode)
+DECLARE_GL_FUNCTION_HEAD(void, GetTransformFeedbackVarying, GLuint program, GLuint index, GLsizei bufSize, GLsizei* length, GLsizei* size, GLenum* type, GLchar* name) DECLARE_GL_FUNCTION_END_NO_RETURN(void, GetTransformFeedbackVarying, program, index, bufSize, length, size, type, name)
 DECLARE_GL_FUNCTION_HEAD(void, VertexAttribIPointer, GLuint index, GLint size, GLenum type, GLsizei stride, const void* pointer) DECLARE_GL_FUNCTION_END_NO_RETURN(void, VertexAttribIPointer, index, size, type, stride, pointer)
 DECLARE_GL_FUNCTION_HEAD(void, GetVertexAttribIiv, GLuint index, GLenum pname, GLint* params) DECLARE_GL_FUNCTION_END_NO_RETURN(void, GetVertexAttribIiv, index, pname, params)
 DECLARE_GL_FUNCTION_HEAD(void, GetVertexAttribIuiv, GLuint index, GLenum pname, GLuint* params) DECLARE_GL_FUNCTION_END_NO_RETURN(void, GetVertexAttribIuiv, index, pname, params)
@@ -292,17 +293,17 @@ DECLARE_GL_FUNCTION_HEAD(void, SamplerParameterfv, GLuint sampler, GLenum pname,
 DECLARE_GL_FUNCTION_HEAD(void, GetSamplerParameteriv, GLuint sampler, GLenum pname, GLint* params) DECLARE_GL_FUNCTION_END_NO_RETURN(void, GetSamplerParameteriv, sampler, pname, params)
 DECLARE_GL_FUNCTION_HEAD(void, GetSamplerParameterfv, GLuint sampler, GLenum pname, GLfloat* params) DECLARE_GL_FUNCTION_END_NO_RETURN(void, GetSamplerParameterfv, sampler, pname, params)
 DECLARE_GL_FUNCTION_HEAD(void, VertexAttribDivisor, GLuint index, GLuint divisor) DECLARE_GL_FUNCTION_END_NO_RETURN(void, VertexAttribDivisor, index, divisor)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, BindTransformFeedback, GLenum target, GLuint id) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, BindTransformFeedback, target, id)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, DeleteTransformFeedbacks, GLsizei n, const GLuint* ids) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, DeleteTransformFeedbacks, n, ids)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, GenTransformFeedbacks, GLsizei n, GLuint* ids) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, GenTransformFeedbacks, n, ids)
-DECLARE_GL_FUNCTION_STUB_HEAD(GLboolean, IsTransformFeedback, GLuint id) DECLARE_GL_FUNCTION_STUB_END(GLboolean, IsTransformFeedback, id)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, PauseTransformFeedback) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, PauseTransformFeedback)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, ResumeTransformFeedback) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, ResumeTransformFeedback)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, GetProgramBinary, GLuint program, GLsizei bufSize, GLsizei* length, GLenum* binaryFormat, void* binary) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, GetProgramBinary, program, bufSize, length, binaryFormat, binary)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, ProgramBinary, GLuint program, GLenum binaryFormat, const void* binary, GLsizei length) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, ProgramBinary, program, binaryFormat, binary, length)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, ProgramParameteri, GLuint program, GLenum pname, GLint value) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, ProgramParameteri, program, pname, value)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, InvalidateFramebuffer, GLenum target, GLsizei numAttachments, const GLenum* attachments) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, InvalidateFramebuffer, target, numAttachments, attachments)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, InvalidateSubFramebuffer, GLenum target, GLsizei numAttachments, const GLenum* attachments, GLint x, GLint y, GLsizei width, GLsizei height) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, InvalidateSubFramebuffer, target, numAttachments, attachments, x, y, width, height)
+DECLARE_GL_FUNCTION_HEAD(void, BindTransformFeedback, GLenum target, GLuint id) DECLARE_GL_FUNCTION_END_NO_RETURN(void, BindTransformFeedback, target, id)
+DECLARE_GL_FUNCTION_HEAD(void, DeleteTransformFeedbacks, GLsizei n, const GLuint* ids) DECLARE_GL_FUNCTION_END_NO_RETURN(void, DeleteTransformFeedbacks, n, ids)
+DECLARE_GL_FUNCTION_HEAD(void, GenTransformFeedbacks, GLsizei n, GLuint* ids) DECLARE_GL_FUNCTION_END_NO_RETURN(void, GenTransformFeedbacks, n, ids)
+DECLARE_GL_FUNCTION_HEAD(GLboolean, IsTransformFeedback, GLuint id) DECLARE_GL_FUNCTION_END(GLboolean, IsTransformFeedback, id)
+DECLARE_GL_FUNCTION_HEAD(void, PauseTransformFeedback) DECLARE_GL_FUNCTION_END_NO_RETURN(void, PauseTransformFeedback)
+DECLARE_GL_FUNCTION_HEAD(void, ResumeTransformFeedback) DECLARE_GL_FUNCTION_END_NO_RETURN(void, ResumeTransformFeedback)
+DECLARE_GL_FUNCTION_HEAD(void, GetProgramBinary, GLuint program, GLsizei bufSize, GLsizei* length, GLenum* binaryFormat, void* binary) DECLARE_GL_FUNCTION_END_NO_RETURN(void, GetProgramBinary, program, bufSize, length, binaryFormat, binary)
+DECLARE_GL_FUNCTION_HEAD(void, ProgramBinary, GLuint program, GLenum binaryFormat, const void* binary, GLsizei length) DECLARE_GL_FUNCTION_END_NO_RETURN(void, ProgramBinary, program, binaryFormat, binary, length)
+DECLARE_GL_FUNCTION_HEAD(void, ProgramParameteri, GLuint program, GLenum pname, GLint value) DECLARE_GL_FUNCTION_END_NO_RETURN(void, ProgramParameteri, program, pname, value)
+DECLARE_GL_FUNCTION_HEAD(void, InvalidateFramebuffer, GLenum target, GLsizei numAttachments, const GLenum* attachments) DECLARE_GL_FUNCTION_END_NO_RETURN(void, InvalidateFramebuffer, target, numAttachments, attachments)
+DECLARE_GL_FUNCTION_HEAD(void, InvalidateSubFramebuffer, GLenum target, GLsizei numAttachments, const GLenum* attachments, GLint x, GLint y, GLsizei width, GLsizei height) DECLARE_GL_FUNCTION_END_NO_RETURN(void, InvalidateSubFramebuffer, target, numAttachments, attachments, x, y, width, height)
 DECLARE_GL_FUNCTION_HEAD(void, TexStorage2D, GLenum target, GLsizei levels, GLenum internalformat, GLsizei width, GLsizei height) DECLARE_GL_FUNCTION_END_NO_RETURN(void, TexStorage2D, target, levels, internalformat, width, height)
 DECLARE_GL_FUNCTION_HEAD(void, TexStorage3D, GLenum target, GLsizei levels, GLenum internalformat, GLsizei width, GLsizei height, GLsizei depth) DECLARE_GL_FUNCTION_END_NO_RETURN(void, TexStorage3D, target, levels, internalformat, width, height, depth)
 DECLARE_GL_FUNCTION_HEAD(void, GetInternalformativ, GLenum target, GLenum internalformat, GLenum pname, GLsizei bufSize, GLint* params) DECLARE_GL_FUNCTION_END_NO_RETURN(void, GetInternalformativ, target, internalformat, pname, bufSize, params)
@@ -310,21 +311,21 @@ DECLARE_GL_FUNCTION_HEAD(void, DispatchCompute, GLuint num_groups_x, GLuint num_
 DECLARE_GL_FUNCTION_HEAD(void, DispatchComputeIndirect, GLintptr indirect) DECLARE_GL_FUNCTION_END_NO_RETURN(void, DispatchComputeIndirect, indirect)
 DECLARE_GL_FUNCTION_HEAD(void, DrawArraysIndirect, GLenum mode, const void* indirect) DECLARE_GL_FUNCTION_END_NO_RETURN(void, DrawArraysIndirect, mode, indirect)
 DECLARE_GL_FUNCTION_HEAD(void, DrawElementsIndirect, GLenum mode, GLenum type, const void* indirect) DECLARE_GL_FUNCTION_END_NO_RETURN(void, DrawElementsIndirect, mode, type, indirect)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, FramebufferParameteri, GLenum target, GLenum pname, GLint param) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, FramebufferParameteri, target, pname, param)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, GetFramebufferParameteriv, GLenum target, GLenum pname, GLint* params) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, GetFramebufferParameteriv, target, pname, params)
+DECLARE_GL_FUNCTION_HEAD(void, FramebufferParameteri, GLenum target, GLenum pname, GLint param) DECLARE_GL_FUNCTION_END_NO_RETURN(void, FramebufferParameteri, target, pname, param)
+DECLARE_GL_FUNCTION_HEAD(void, GetFramebufferParameteriv, GLenum target, GLenum pname, GLint* params) DECLARE_GL_FUNCTION_END_NO_RETURN(void, GetFramebufferParameteriv, target, pname, params)
 DECLARE_GL_FUNCTION_HEAD(void, GetProgramInterfaceiv, GLuint program, GLenum programInterface, GLenum pname, GLint* params) DECLARE_GL_FUNCTION_END_NO_RETURN(void, GetProgramInterfaceiv, program, programInterface, pname, params)
 DECLARE_GL_FUNCTION_HEAD(GLuint, GetProgramResourceIndex, GLuint program, GLenum programInterface, const GLchar* name) DECLARE_GL_FUNCTION_END(GLuint, GetProgramResourceIndex, program, programInterface, name)
 DECLARE_GL_FUNCTION_HEAD(void, GetProgramResourceName, GLuint program, GLenum programInterface, GLuint index, GLsizei bufSize, GLsizei* length, GLchar* name) DECLARE_GL_FUNCTION_END_NO_RETURN(void, GetProgramResourceName, program, programInterface, index, bufSize, length, name)
 DECLARE_GL_FUNCTION_HEAD(void, GetProgramResourceiv, GLuint program, GLenum programInterface, GLuint index, GLsizei propCount, const GLenum* props, GLsizei bufSize, GLsizei* length, GLint* params) DECLARE_GL_FUNCTION_END_NO_RETURN(void, GetProgramResourceiv, program, programInterface, index, propCount, props, bufSize, length, params)
 DECLARE_GL_FUNCTION_HEAD(GLint, GetProgramResourceLocation, GLuint program, GLenum programInterface, const GLchar* name) DECLARE_GL_FUNCTION_END(GLint, GetProgramResourceLocation, program, programInterface, name)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, UseProgramStages, GLuint pipeline, GLbitfield stages, GLuint program) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, UseProgramStages, pipeline, stages, program)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, ActiveShaderProgram, GLuint pipeline, GLuint program) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, ActiveShaderProgram, pipeline, program)
-DECLARE_GL_FUNCTION_STUB_HEAD(GLuint, CreateShaderProgramv, GLenum type, GLsizei count, const GLchar* const* strings) DECLARE_GL_FUNCTION_STUB_END(GLuint, CreateShaderProgramv, type, count, strings)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, BindProgramPipeline, GLuint pipeline) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, BindProgramPipeline, pipeline)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, DeleteProgramPipelines, GLsizei n, const GLuint* pipelines) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, DeleteProgramPipelines, n, pipelines)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, GenProgramPipelines, GLsizei n, GLuint* pipelines) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, GenProgramPipelines, n, pipelines)
-DECLARE_GL_FUNCTION_STUB_HEAD(GLboolean, IsProgramPipeline, GLuint pipeline) DECLARE_GL_FUNCTION_STUB_END(GLboolean, IsProgramPipeline, pipeline)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, GetProgramPipelineiv, GLuint pipeline, GLenum pname, GLint* params) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, GetProgramPipelineiv, pipeline, pname, params)
+DECLARE_GL_FUNCTION_HEAD(void, UseProgramStages, GLuint pipeline, GLbitfield stages, GLuint program) DECLARE_GL_FUNCTION_END_NO_RETURN(void, UseProgramStages, pipeline, stages, program)
+DECLARE_GL_FUNCTION_HEAD(void, ActiveShaderProgram, GLuint pipeline, GLuint program) DECLARE_GL_FUNCTION_END_NO_RETURN(void, ActiveShaderProgram, pipeline, program)
+DECLARE_GL_FUNCTION_HEAD(GLuint, CreateShaderProgramv, GLenum type, GLsizei count, const GLchar* const* strings) DECLARE_GL_FUNCTION_END(GLuint, CreateShaderProgramv, type, count, strings)
+DECLARE_GL_FUNCTION_HEAD(void, BindProgramPipeline, GLuint pipeline) DECLARE_GL_FUNCTION_END_NO_RETURN(void, BindProgramPipeline, pipeline)
+DECLARE_GL_FUNCTION_HEAD(void, DeleteProgramPipelines, GLsizei n, const GLuint* pipelines) DECLARE_GL_FUNCTION_END_NO_RETURN(void, DeleteProgramPipelines, n, pipelines)
+DECLARE_GL_FUNCTION_HEAD(void, GenProgramPipelines, GLsizei n, GLuint* pipelines) DECLARE_GL_FUNCTION_END_NO_RETURN(void, GenProgramPipelines, n, pipelines)
+DECLARE_GL_FUNCTION_HEAD(GLboolean, IsProgramPipeline, GLuint pipeline) DECLARE_GL_FUNCTION_END(GLboolean, IsProgramPipeline, pipeline)
+DECLARE_GL_FUNCTION_HEAD(void, GetProgramPipelineiv, GLuint pipeline, GLenum pname, GLint* params) DECLARE_GL_FUNCTION_END_NO_RETURN(void, GetProgramPipelineiv, pipeline, pname, params)
 DECLARE_GL_FUNCTION_HEAD(void, ProgramUniform1i, GLuint program, GLint location, GLint v0) DECLARE_GL_FUNCTION_END_NO_RETURN(void, ProgramUniform1i, program, location, v0)
 DECLARE_GL_FUNCTION_HEAD(void, ProgramUniform2i, GLuint program, GLint location, GLint v0, GLint v1) DECLARE_GL_FUNCTION_END_NO_RETURN(void, ProgramUniform2i, program, location, v0, v1)
 DECLARE_GL_FUNCTION_HEAD(void, ProgramUniform3i, GLuint program, GLint location, GLint v0, GLint v1, GLint v2) DECLARE_GL_FUNCTION_END_NO_RETURN(void, ProgramUniform3i, program, location, v0, v1, v2)
@@ -358,8 +359,8 @@ DECLARE_GL_FUNCTION_HEAD(void, ProgramUniformMatrix2x4fv, GLuint program, GLint
 DECLARE_GL_FUNCTION_HEAD(void, ProgramUniformMatrix4x2fv, GLuint program, GLint location, GLsizei count, GLboolean transpose, const GLfloat* value) DECLARE_GL_FUNCTION_END_NO_RETURN(void, ProgramUniformMatrix4x2fv, program, location, count, transpose, value)
 DECLARE_GL_FUNCTION_HEAD(void, ProgramUniformMatrix3x4fv, GLuint program, GLint location, GLsizei count, GLboolean transpose, const GLfloat* value) DECLARE_GL_FUNCTION_END_NO_RETURN(void, ProgramUniformMatrix3x4fv, program, location, count, transpose, value)
 DECLARE_GL_FUNCTION_HEAD(void, ProgramUniformMatrix4x3fv, GLuint program, GLint location, GLsizei count, GLboolean transpose, const GLfloat* value) DECLARE_GL_FUNCTION_END_NO_RETURN(void, ProgramUniformMatrix4x3fv, program, location, count, transpose, value)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, ValidateProgramPipeline, GLuint pipeline) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, ValidateProgramPipeline, pipeline)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, GetProgramPipelineInfoLog, GLuint pipeline, GLsizei bufSize, GLsizei* length, GLchar* infoLog) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, GetProgramPipelineInfoLog, pipeline, bufSize, length, infoLog)
+DECLARE_GL_FUNCTION_HEAD(void, ValidateProgramPipeline, GLuint pipeline) DECLARE_GL_FUNCTION_END_NO_RETURN(void, ValidateProgramPipeline, pipeline)
+DECLARE_GL_FUNCTION_HEAD(void, GetProgramPipelineInfoLog, GLuint pipeline, GLsizei bufSize, GLsizei* length, GLchar* infoLog) DECLARE_GL_FUNCTION_END_NO_RETURN(void, GetProgramPipelineInfoLog, pipeline, bufSize, length, infoLog)
 DECLARE_GL_FUNCTION_HEAD(void, BindImageTexture, GLuint unit, GLuint texture, GLint level, GLboolean layered, GLint layer, GLenum access, GLenum format) DECLARE_GL_FUNCTION_END_NO_RETURN(void, BindImageTexture, unit, texture, level, layered, layer, access, format)
 DECLARE_GL_FUNCTION_HEAD(void, GetBooleani_v, GLenum target, GLuint index, GLboolean* data) DECLARE_GL_FUNCTION_END_NO_RETURN(void, GetBooleani_v, target, index, data)
 DECLARE_GL_FUNCTION_HEAD(void, MemoryBarrier, GLbitfield barriers) DECLARE_GL_FUNCTION_END_NO_RETURN(void, MemoryBarrier, barriers)
@@ -418,13 +419,13 @@ DECLARE_GL_FUNCTION_HEAD(void, DrawRangeElementsBaseVertex, GLenum mode, GLuint
 DECLARE_GL_FUNCTION_HEAD(void, DrawElementsInstancedBaseVertex, GLenum mode, GLsizei count, GLenum type, const void* indices, GLsizei instancecount, GLint basevertex) DECLARE_GL_FUNCTION_END_NO_RETURN(void, DrawElementsInstancedBaseVertex, mode, count, type, indices, instancecount, basevertex)
 DECLARE_GL_FUNCTION_HEAD(void, FramebufferTexture, GLenum target, GLenum attachment, GLuint texture, GLint level) DECLARE_GL_FUNCTION_END_NO_RETURN(void, FramebufferTexture, target, attachment, texture, level)
 DECLARE_GL_FUNCTION_STUB_HEAD(void, PrimitiveBoundingBox, GLfloat minX, GLfloat minY, GLfloat minZ, GLfloat minW, GLfloat maxX, GLfloat maxY, GLfloat maxZ, GLfloat maxW) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, PrimitiveBoundingBox, minX, minY, minZ, minW, maxX, maxY, maxZ, maxW)
-DECLARE_GL_FUNCTION_STUB_HEAD(GLenum, GetGraphicsResetStatus) DECLARE_GL_FUNCTION_STUB_END(GLenum, GetGraphicsResetStatus)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, ReadnPixels, GLint x, GLint y, GLsizei width, GLsizei height, GLenum format, GLenum type, GLsizei bufSize, void* data) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, ReadnPixels, x, y, width, height, format, type, bufSize, data)
+DECLARE_GL_FUNCTION_HEAD(GLenum, GetGraphicsResetStatus) DECLARE_GL_FUNCTION_END(GLenum, GetGraphicsResetStatus)
+DECLARE_GL_FUNCTION_HEAD(void, ReadnPixels, GLint x, GLint y, GLsizei width, GLsizei height, GLenum format, GLenum type, GLsizei bufSize, void* data) DECLARE_GL_FUNCTION_END_NO_RETURN(void, ReadnPixels, x, y, width, height, format, type, bufSize, data)
 DECLARE_GL_FUNCTION_STUB_HEAD(void, GetnUniformfv, GLuint program, GLint location, GLsizei bufSize, GLfloat* params) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, GetnUniformfv, program, location, bufSize, params)
 DECLARE_GL_FUNCTION_STUB_HEAD(void, GetnUniformiv, GLuint program, GLint location, GLsizei bufSize, GLint* params) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, GetnUniformiv, program, location, bufSize, params)
 DECLARE_GL_FUNCTION_STUB_HEAD(void, GetnUniformuiv, GLuint program, GLint location, GLsizei bufSize, GLuint* params) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, GetnUniformuiv, program, location, bufSize, params)
 DECLARE_GL_FUNCTION_STUB_HEAD(void, MinSampleShading, GLfloat value) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, MinSampleShading, value)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, PatchParameteri, GLenum pname, GLint value) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, PatchParameteri, pname, value)
+DECLARE_GL_FUNCTION_HEAD(void, PatchParameteri, GLenum pname, GLint value) DECLARE_GL_FUNCTION_END_NO_RETURN(void, PatchParameteri, pname, value)
 DECLARE_GL_FUNCTION_HEAD(void, TexParameterIiv, GLenum target, GLenum pname, const GLint* params) DECLARE_GL_FUNCTION_END_NO_RETURN(void, TexParameterIiv, target, pname, params)
 DECLARE_GL_FUNCTION_HEAD(void, TexParameterIuiv, GLenum target, GLenum pname, const GLuint* params) DECLARE_GL_FUNCTION_END_NO_RETURN(void, TexParameterIuiv, target, pname, params)
 DECLARE_GL_FUNCTION_HEAD(void, GetTexParameterIiv, GLenum target, GLenum pname, GLint* params) DECLARE_GL_FUNCTION_END_NO_RETURN(void, GetTexParameterIiv, target, pname, params)
@@ -434,7 +435,7 @@ DECLARE_GL_FUNCTION_HEAD(void, SamplerParameterIuiv, GLuint sampler, GLenum pnam
 DECLARE_GL_FUNCTION_HEAD(void, GetSamplerParameterIiv, GLuint sampler, GLenum pname, GLint* params) DECLARE_GL_FUNCTION_END_NO_RETURN(void, GetSamplerParameterIiv, sampler, pname, params)
 DECLARE_GL_FUNCTION_HEAD(void, GetSamplerParameterIuiv, GLuint sampler, GLenum pname, GLuint* params) DECLARE_GL_FUNCTION_END_NO_RETURN(void, GetSamplerParameterIuiv, sampler, pname, params)
 DECLARE_GL_FUNCTION_HEAD(void, TexBuffer, GLenum target, GLenum internalformat, GLuint buffer) DECLARE_GL_FUNCTION_END_NO_RETURN(void, TexBuffer, target, internalformat, buffer)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, TexBufferRange, GLenum target, GLenum internalformat, GLuint buffer, GLintptr offset, GLsizeiptr size) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, TexBufferRange, target, internalformat, buffer, offset, size)
+DECLARE_GL_FUNCTION_HEAD(void, TexBufferRange, GLenum target, GLenum internalformat, GLuint buffer, GLintptr offset, GLsizeiptr size) DECLARE_GL_FUNCTION_END_NO_RETURN(void, TexBufferRange, target, internalformat, buffer, offset, size)
 DECLARE_GL_FUNCTION_HEAD(void, TexStorage3DMultisample, GLenum target, GLsizei samples, GLenum internalformat, GLsizei width, GLsizei height, GLsizei depth, GLboolean fixedsamplelocations) DECLARE_GL_FUNCTION_END_NO_RETURN(void, TexStorage3DMultisample, target, samples, internalformat, width, height, depth, fixedsamplelocations)
 DECLARE_GL_FUNCTION_HEAD(void*, MapBufferRange, GLenum target, GLintptr offset, GLsizeiptr length, GLbitfield access) DECLARE_GL_FUNCTION_END(void*, MapBufferRange, target, offset, length, access)
 DECLARE_GL_FUNCTION_STUB_HEAD(void, ClearIndex, GLfloat c) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, ClearIndex, c)
@@ -909,24 +910,24 @@ DECLARE_GL_FUNCTION_STUB_HEAD(void, ColorP4ui, GLenum type, GLuint color) DECLAR
 DECLARE_GL_FUNCTION_STUB_HEAD(void, ColorP4uiv, GLenum type, const GLuint* color) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, ColorP4uiv, type, color)
 DECLARE_GL_FUNCTION_STUB_HEAD(void, SecondaryColorP3ui, GLenum type, GLuint color) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, SecondaryColorP3ui, type, color)
 DECLARE_GL_FUNCTION_STUB_HEAD(void, SecondaryColorP3uiv, GLenum type, const GLuint* color) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, SecondaryColorP3uiv, type, color)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, Uniform1d, GLint location, GLdouble x) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, Uniform1d, location, x)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, Uniform2d, GLint location, GLdouble x, GLdouble y) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, Uniform2d, location, x, y)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, Uniform3d, GLint location, GLdouble x, GLdouble y, GLdouble z) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, Uniform3d, location, x, y, z)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, Uniform4d, GLint location, GLdouble x, GLdouble y, GLdouble z, GLdouble w) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, Uniform4d, location, x, y, z, w)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, Uniform1dv, GLint location, GLsizei count, const GLdouble* value) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, Uniform1dv, location, count, value)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, Uniform2dv, GLint location, GLsizei count, const GLdouble* value) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, Uniform2dv, location, count, value)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, Uniform3dv, GLint location, GLsizei count, const GLdouble* value) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, Uniform3dv, location, count, value)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, Uniform4dv, GLint location, GLsizei count, const GLdouble* value) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, Uniform4dv, location, count, value)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, UniformMatrix2dv, GLint location, GLsizei count, GLboolean transpose, const GLdouble* value) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, UniformMatrix2dv, location, count, transpose, value)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, UniformMatrix3dv, GLint location, GLsizei count, GLboolean transpose, const GLdouble* value) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, UniformMatrix3dv, location, count, transpose, value)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, UniformMatrix4dv, GLint location, GLsizei count, GLboolean transpose, const GLdouble* value) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, UniformMatrix4dv, location, count, transpose, value)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, UniformMatrix2x3dv, GLint location, GLsizei count, GLboolean transpose, const GLdouble* value) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, UniformMatrix2x3dv, location, count, transpose, value)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, UniformMatrix2x4dv, GLint location, GLsizei count, GLboolean transpose, const GLdouble* value) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, UniformMatrix2x4dv, location, count, transpose, value)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, UniformMatrix3x2dv, GLint location, GLsizei count, GLboolean transpose, const GLdouble* value) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, UniformMatrix3x2dv, location, count, transpose, value)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, UniformMatrix3x4dv, GLint location, GLsizei count, GLboolean transpose, const GLdouble* value) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, UniformMatrix3x4dv, location, count, transpose, value)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, UniformMatrix4x2dv, GLint location, GLsizei count, GLboolean transpose, const GLdouble* value) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, UniformMatrix4x2dv, location, count, transpose, value)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, UniformMatrix4x3dv, GLint location, GLsizei count, GLboolean transpose, const GLdouble* value) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, UniformMatrix4x3dv, location, count, transpose, value)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, GetUniformdv, GLuint program, GLint location, GLdouble* params) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, GetUniformdv, program, location, params)
+DECLARE_GL_FUNCTION_HEAD(void, Uniform1d, GLint location, GLdouble x) DECLARE_GL_FUNCTION_END_NO_RETURN(void, Uniform1d, location, x)
+DECLARE_GL_FUNCTION_HEAD(void, Uniform2d, GLint location, GLdouble x, GLdouble y) DECLARE_GL_FUNCTION_END_NO_RETURN(void, Uniform2d, location, x, y)
+DECLARE_GL_FUNCTION_HEAD(void, Uniform3d, GLint location, GLdouble x, GLdouble y, GLdouble z) DECLARE_GL_FUNCTION_END_NO_RETURN(void, Uniform3d, location, x, y, z)
+DECLARE_GL_FUNCTION_HEAD(void, Uniform4d, GLint location, GLdouble x, GLdouble y, GLdouble z, GLdouble w) DECLARE_GL_FUNCTION_END_NO_RETURN(void, Uniform4d, location, x, y, z, w)
+DECLARE_GL_FUNCTION_HEAD(void, Uniform1dv, GLint location, GLsizei count, const GLdouble* value) DECLARE_GL_FUNCTION_END_NO_RETURN(void, Uniform1dv, location, count, value)
+DECLARE_GL_FUNCTION_HEAD(void, Uniform2dv, GLint location, GLsizei count, const GLdouble* value) DECLARE_GL_FUNCTION_END_NO_RETURN(void, Uniform2dv, location, count, value)
+DECLARE_GL_FUNCTION_HEAD(void, Uniform3dv, GLint location, GLsizei count, const GLdouble* value) DECLARE_GL_FUNCTION_END_NO_RETURN(void, Uniform3dv, location, count, value)
+DECLARE_GL_FUNCTION_HEAD(void, Uniform4dv, GLint location, GLsizei count, const GLdouble* value) DECLARE_GL_FUNCTION_END_NO_RETURN(void, Uniform4dv, location, count, value)
+DECLARE_GL_FUNCTION_HEAD(void, UniformMatrix2dv, GLint location, GLsizei count, GLboolean transpose, const GLdouble* value) DECLARE_GL_FUNCTION_END_NO_RETURN(void, UniformMatrix2dv, location, count, transpose, value)
+DECLARE_GL_FUNCTION_HEAD(void, UniformMatrix3dv, GLint location, GLsizei count, GLboolean transpose, const GLdouble* value) DECLARE_GL_FUNCTION_END_NO_RETURN(void, UniformMatrix3dv, location, count, transpose, value)
+DECLARE_GL_FUNCTION_HEAD(void, UniformMatrix4dv, GLint location, GLsizei count, GLboolean transpose, const GLdouble* value) DECLARE_GL_FUNCTION_END_NO_RETURN(void, UniformMatrix4dv, location, count, transpose, value)
+DECLARE_GL_FUNCTION_HEAD(void, UniformMatrix2x3dv, GLint location, GLsizei count, GLboolean transpose, const GLdouble* value) DECLARE_GL_FUNCTION_END_NO_RETURN(void, UniformMatrix2x3dv, location, count, transpose, value)
+DECLARE_GL_FUNCTION_HEAD(void, UniformMatrix2x4dv, GLint location, GLsizei count, GLboolean transpose, const GLdouble* value) DECLARE_GL_FUNCTION_END_NO_RETURN(void, UniformMatrix2x4dv, location, count, transpose, value)
+DECLARE_GL_FUNCTION_HEAD(void, UniformMatrix3x2dv, GLint location, GLsizei count, GLboolean transpose, const GLdouble* value) DECLARE_GL_FUNCTION_END_NO_RETURN(void, UniformMatrix3x2dv, location, count, transpose, value)
+DECLARE_GL_FUNCTION_HEAD(void, UniformMatrix3x4dv, GLint location, GLsizei count, GLboolean transpose, const GLdouble* value) DECLARE_GL_FUNCTION_END_NO_RETURN(void, UniformMatrix3x4dv, location, count, transpose, value)
+DECLARE_GL_FUNCTION_HEAD(void, UniformMatrix4x2dv, GLint location, GLsizei count, GLboolean transpose, const GLdouble* value) DECLARE_GL_FUNCTION_END_NO_RETURN(void, UniformMatrix4x2dv, location, count, transpose, value)
+DECLARE_GL_FUNCTION_HEAD(void, UniformMatrix4x3dv, GLint location, GLsizei count, GLboolean transpose, const GLdouble* value) DECLARE_GL_FUNCTION_END_NO_RETURN(void, UniformMatrix4x3dv, location, count, transpose, value)
+DECLARE_GL_FUNCTION_HEAD(void, GetUniformdv, GLuint program, GLint location, GLdouble* params) DECLARE_GL_FUNCTION_END_NO_RETURN(void, GetUniformdv, program, location, params)
 DECLARE_GL_FUNCTION_STUB_HEAD(GLint, GetSubroutineUniformLocation, GLuint program, GLenum shadertype, const GLchar* name) DECLARE_GL_FUNCTION_STUB_END(GLint, GetSubroutineUniformLocation, program, shadertype, name)
 DECLARE_GL_FUNCTION_STUB_HEAD(GLuint, GetSubroutineIndex, GLuint program, GLenum shadertype, const GLchar* name) DECLARE_GL_FUNCTION_STUB_END(GLuint, GetSubroutineIndex, program, shadertype, name)
 DECLARE_GL_FUNCTION_STUB_HEAD(void, GetActiveSubroutineUniformiv, GLuint program, GLenum shadertype, GLuint index, GLenum pname, GLint* values) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, GetActiveSubroutineUniformiv, program, shadertype, index, pname, values)
@@ -936,28 +937,28 @@ DECLARE_GL_FUNCTION_STUB_HEAD(void, UniformSubroutinesuiv, GLenum shadertype, GL
 DECLARE_GL_FUNCTION_STUB_HEAD(void, GetUniformSubroutineuiv, GLenum shadertype, GLint location, GLuint* params) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, GetUniformSubroutineuiv, shadertype, location, params)
 DECLARE_GL_FUNCTION_STUB_HEAD(void, GetProgramStageiv, GLuint program, GLenum shadertype, GLenum pname, GLint* values) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, GetProgramStageiv, program, shadertype, pname, values)
 DECLARE_GL_FUNCTION_STUB_HEAD(void, PatchParameterfv, GLenum pname, const GLfloat* values) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, PatchParameterfv, pname, values)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, DrawTransformFeedback, GLenum mode, GLuint id) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, DrawTransformFeedback, mode, id)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, DrawTransformFeedbackStream, GLenum mode, GLuint id, GLuint stream) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, DrawTransformFeedbackStream, mode, id, stream)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, BeginQueryIndexed, GLenum target, GLuint index, GLuint id) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, BeginQueryIndexed, target, index, id)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, EndQueryIndexed, GLenum target, GLuint index) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, EndQueryIndexed, target, index)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, GetQueryIndexediv, GLenum target, GLuint index, GLenum pname, GLint* params) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, GetQueryIndexediv, target, index, pname, params)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, ProgramUniform1d, GLuint program, GLint location, GLdouble v0) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, ProgramUniform1d, program, location, v0)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, ProgramUniform1dv, GLuint program, GLint location, GLsizei count, const GLdouble* value) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, ProgramUniform1dv, program, location, count, value)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, ProgramUniform2d, GLuint program, GLint location, GLdouble v0, GLdouble v1) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, ProgramUniform2d, program, location, v0, v1)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, ProgramUniform2dv, GLuint program, GLint location, GLsizei count, const GLdouble* value) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, ProgramUniform2dv, program, location, count, value)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, ProgramUniform3d, GLuint program, GLint location, GLdouble v0, GLdouble v1, GLdouble v2) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, ProgramUniform3d, program, location, v0, v1, v2)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, ProgramUniform3dv, GLuint program, GLint location, GLsizei count, const GLdouble* value) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, ProgramUniform3dv, program, location, count, value)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, ProgramUniform4d, GLuint program, GLint location, GLdouble v0, GLdouble v1, GLdouble v2, GLdouble v3) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, ProgramUniform4d, program, location, v0, v1, v2, v3)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, ProgramUniform4dv, GLuint program, GLint location, GLsizei count, const GLdouble* value) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, ProgramUniform4dv, program, location, count, value)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, ProgramUniformMatrix2dv, GLuint program, GLint location, GLsizei count, GLboolean transpose, const GLdouble* value) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, ProgramUniformMatrix2dv, program, location, count, transpose, value)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, ProgramUniformMatrix3dv, GLuint program, GLint location, GLsizei count, GLboolean transpose, const GLdouble* value) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, ProgramUniformMatrix3dv, program, location, count, transpose, value)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, ProgramUniformMatrix4dv, GLuint program, GLint location, GLsizei count, GLboolean transpose, const GLdouble* value) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, ProgramUniformMatrix4dv, program, location, count, transpose, value)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, ProgramUniformMatrix2x3dv, GLuint program, GLint location, GLsizei count, GLboolean transpose, const GLdouble* value) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, ProgramUniformMatrix2x3dv, program, location, count, transpose, value)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, ProgramUniformMatrix3x2dv, GLuint program, GLint location, GLsizei count, GLboolean transpose, const GLdouble* value) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, ProgramUniformMatrix3x2dv, program, location, count, transpose, value)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, ProgramUniformMatrix2x4dv, GLuint program, GLint location, GLsizei count, GLboolean transpose, const GLdouble* value) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, ProgramUniformMatrix2x4dv, program, location, count, transpose, value)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, ProgramUniformMatrix4x2dv, GLuint program, GLint location, GLsizei count, GLboolean transpose, const GLdouble* value) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, ProgramUniformMatrix4x2dv, program, location, count, transpose, value)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, ProgramUniformMatrix3x4dv, GLuint program, GLint location, GLsizei count, GLboolean transpose, const GLdouble* value) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, ProgramUniformMatrix3x4dv, program, location, count, transpose, value)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, ProgramUniformMatrix4x3dv, GLuint program, GLint location, GLsizei count, GLboolean transpose, const GLdouble* value) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, ProgramUniformMatrix4x3dv, program, location, count, transpose, value)
+DECLARE_GL_FUNCTION_HEAD(void, DrawTransformFeedback, GLenum mode, GLuint id) DECLARE_GL_FUNCTION_END_NO_RETURN(void, DrawTransformFeedback, mode, id)
+DECLARE_GL_FUNCTION_HEAD(void, DrawTransformFeedbackStream, GLenum mode, GLuint id, GLuint stream) DECLARE_GL_FUNCTION_END_NO_RETURN(void, DrawTransformFeedbackStream, mode, id, stream)
+DECLARE_GL_FUNCTION_HEAD(void, BeginQueryIndexed, GLenum target, GLuint index, GLuint id) DECLARE_GL_FUNCTION_END_NO_RETURN(void, BeginQueryIndexed, target, index, id)
+DECLARE_GL_FUNCTION_HEAD(void, EndQueryIndexed, GLenum target, GLuint index) DECLARE_GL_FUNCTION_END_NO_RETURN(void, EndQueryIndexed, target, index)
+DECLARE_GL_FUNCTION_HEAD(void, GetQueryIndexediv, GLenum target, GLuint index, GLenum pname, GLint* params) DECLARE_GL_FUNCTION_END_NO_RETURN(void, GetQueryIndexediv, target, index, pname, params)
+DECLARE_GL_FUNCTION_HEAD(void, ProgramUniform1d, GLuint program, GLint location, GLdouble v0) DECLARE_GL_FUNCTION_END_NO_RETURN(void, ProgramUniform1d, program, location, v0)
+DECLARE_GL_FUNCTION_HEAD(void, ProgramUniform1dv, GLuint program, GLint location, GLsizei count, const GLdouble* value) DECLARE_GL_FUNCTION_END_NO_RETURN(void, ProgramUniform1dv, program, location, count, value)
+DECLARE_GL_FUNCTION_HEAD(void, ProgramUniform2d, GLuint program, GLint location, GLdouble v0, GLdouble v1) DECLARE_GL_FUNCTION_END_NO_RETURN(void, ProgramUniform2d, program, location, v0, v1)
+DECLARE_GL_FUNCTION_HEAD(void, ProgramUniform2dv, GLuint program, GLint location, GLsizei count, const GLdouble* value) DECLARE_GL_FUNCTION_END_NO_RETURN(void, ProgramUniform2dv, program, location, count, value)
+DECLARE_GL_FUNCTION_HEAD(void, ProgramUniform3d, GLuint program, GLint location, GLdouble v0, GLdouble v1, GLdouble v2) DECLARE_GL_FUNCTION_END_NO_RETURN(void, ProgramUniform3d, program, location, v0, v1, v2)
+DECLARE_GL_FUNCTION_HEAD(void, ProgramUniform3dv, GLuint program, GLint location, GLsizei count, const GLdouble* value) DECLARE_GL_FUNCTION_END_NO_RETURN(void, ProgramUniform3dv, program, location, count, value)
+DECLARE_GL_FUNCTION_HEAD(void, ProgramUniform4d, GLuint program, GLint location, GLdouble v0, GLdouble v1, GLdouble v2, GLdouble v3) DECLARE_GL_FUNCTION_END_NO_RETURN(void, ProgramUniform4d, program, location, v0, v1, v2, v3)
+DECLARE_GL_FUNCTION_HEAD(void, ProgramUniform4dv, GLuint program, GLint location, GLsizei count, const GLdouble* value) DECLARE_GL_FUNCTION_END_NO_RETURN(void, ProgramUniform4dv, program, location, count, value)
+DECLARE_GL_FUNCTION_HEAD(void, ProgramUniformMatrix2dv, GLuint program, GLint location, GLsizei count, GLboolean transpose, const GLdouble* value) DECLARE_GL_FUNCTION_END_NO_RETURN(void, ProgramUniformMatrix2dv, program, location, count, transpose, value)
+DECLARE_GL_FUNCTION_HEAD(void, ProgramUniformMatrix3dv, GLuint program, GLint location, GLsizei count, GLboolean transpose, const GLdouble* value) DECLARE_GL_FUNCTION_END_NO_RETURN(void, ProgramUniformMatrix3dv, program, location, count, transpose, value)
+DECLARE_GL_FUNCTION_HEAD(void, ProgramUniformMatrix4dv, GLuint program, GLint location, GLsizei count, GLboolean transpose, const GLdouble* value) DECLARE_GL_FUNCTION_END_NO_RETURN(void, ProgramUniformMatrix4dv, program, location, count, transpose, value)
+DECLARE_GL_FUNCTION_HEAD(void, ProgramUniformMatrix2x3dv, GLuint program, GLint location, GLsizei count, GLboolean transpose, const GLdouble* value) DECLARE_GL_FUNCTION_END_NO_RETURN(void, ProgramUniformMatrix2x3dv, program, location, count, transpose, value)
+DECLARE_GL_FUNCTION_HEAD(void, ProgramUniformMatrix3x2dv, GLuint program, GLint location, GLsizei count, GLboolean transpose, const GLdouble* value) DECLARE_GL_FUNCTION_END_NO_RETURN(void, ProgramUniformMatrix3x2dv, program, location, count, transpose, value)
+DECLARE_GL_FUNCTION_HEAD(void, ProgramUniformMatrix2x4dv, GLuint program, GLint location, GLsizei count, GLboolean transpose, const GLdouble* value) DECLARE_GL_FUNCTION_END_NO_RETURN(void, ProgramUniformMatrix2x4dv, program, location, count, transpose, value)
+DECLARE_GL_FUNCTION_HEAD(void, ProgramUniformMatrix4x2dv, GLuint program, GLint location, GLsizei count, GLboolean transpose, const GLdouble* value) DECLARE_GL_FUNCTION_END_NO_RETURN(void, ProgramUniformMatrix4x2dv, program, location, count, transpose, value)
+DECLARE_GL_FUNCTION_HEAD(void, ProgramUniformMatrix3x4dv, GLuint program, GLint location, GLsizei count, GLboolean transpose, const GLdouble* value) DECLARE_GL_FUNCTION_END_NO_RETURN(void, ProgramUniformMatrix3x4dv, program, location, count, transpose, value)
+DECLARE_GL_FUNCTION_HEAD(void, ProgramUniformMatrix4x3dv, GLuint program, GLint location, GLsizei count, GLboolean transpose, const GLdouble* value) DECLARE_GL_FUNCTION_END_NO_RETURN(void, ProgramUniformMatrix4x3dv, program, location, count, transpose, value)
 DECLARE_GL_FUNCTION_STUB_HEAD(void, VertexAttribL1d, GLuint index, GLdouble x) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, VertexAttribL1d, index, x)
 DECLARE_GL_FUNCTION_STUB_HEAD(void, VertexAttribL2d, GLuint index, GLdouble x, GLdouble y) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, VertexAttribL2d, index, x, y)
 DECLARE_GL_FUNCTION_STUB_HEAD(void, VertexAttribL3d, GLuint index, GLdouble x, GLdouble y, GLdouble z) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, VertexAttribL3d, index, x, y, z)
@@ -976,14 +977,14 @@ DECLARE_GL_FUNCTION_STUB_HEAD(void, ScissorIndexed, GLuint index, GLint left, GL
 DECLARE_GL_FUNCTION_STUB_HEAD(void, ScissorIndexedv, GLuint index, const GLint* v) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, ScissorIndexedv, index, v)
 DECLARE_GL_FUNCTION_STUB_HEAD(void, DepthRangeArrayv, GLuint first, GLsizei count, const GLdouble* v) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, DepthRangeArrayv, first, count, v)
 DECLARE_GL_FUNCTION_STUB_HEAD(void, DepthRangeIndexed, GLuint index, GLdouble n, GLdouble f) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, DepthRangeIndexed, index, n, f)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, GetFloati_v, GLenum target, GLuint index, GLfloat* data) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, GetFloati_v, target, index, data)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, GetDoublei_v, GLenum target, GLuint index, GLdouble* data) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, GetDoublei_v, target, index, data)
+DECLARE_GL_FUNCTION_HEAD(void, GetFloati_v, GLenum target, GLuint index, GLfloat* data) DECLARE_GL_FUNCTION_END_NO_RETURN(void, GetFloati_v, target, index, data)
+DECLARE_GL_FUNCTION_HEAD(void, GetDoublei_v, GLenum target, GLuint index, GLdouble* data) DECLARE_GL_FUNCTION_END_NO_RETURN(void, GetDoublei_v, target, index, data)
 DECLARE_GL_FUNCTION_HEAD(void, DrawArraysInstancedBaseInstance, GLenum mode, GLint first, GLsizei count, GLsizei instancecount, GLuint baseinstance) DECLARE_GL_FUNCTION_END_NO_RETURN(void, DrawArraysInstancedBaseInstance, mode, first, count, instancecount, baseinstance)
 DECLARE_GL_FUNCTION_HEAD(void, DrawElementsInstancedBaseInstance, GLenum mode, GLsizei count, GLenum type, const void* indices, GLsizei instancecount, GLuint baseinstance) DECLARE_GL_FUNCTION_END_NO_RETURN(void, DrawElementsInstancedBaseInstance, mode, count, type, indices, instancecount, baseinstance)
 DECLARE_GL_FUNCTION_HEAD(void, DrawElementsInstancedBaseVertexBaseInstance, GLenum mode, GLsizei count, GLenum type, const void* indices, GLsizei instancecount, GLint basevertex, GLuint baseinstance) DECLARE_GL_FUNCTION_END_NO_RETURN(void, DrawElementsInstancedBaseVertexBaseInstance, mode, count, type, indices, instancecount, basevertex, baseinstance)
 DECLARE_GL_FUNCTION_STUB_HEAD(void, GetActiveAtomicCounterBufferiv, GLuint program, GLuint bufferIndex, GLenum pname, GLint* params) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, GetActiveAtomicCounterBufferiv, program, bufferIndex, pname, params)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, DrawTransformFeedbackInstanced, GLenum mode, GLuint id, GLsizei instancecount) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, DrawTransformFeedbackInstanced, mode, id, instancecount)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, DrawTransformFeedbackStreamInstanced, GLenum mode, GLuint id, GLuint stream, GLsizei instancecount) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, DrawTransformFeedbackStreamInstanced, mode, id, stream, instancecount)
+DECLARE_GL_FUNCTION_HEAD(void, DrawTransformFeedbackInstanced, GLenum mode, GLuint id, GLsizei instancecount) DECLARE_GL_FUNCTION_END_NO_RETURN(void, DrawTransformFeedbackInstanced, mode, id, instancecount)
+DECLARE_GL_FUNCTION_HEAD(void, DrawTransformFeedbackStreamInstanced, GLenum mode, GLuint id, GLuint stream, GLsizei instancecount) DECLARE_GL_FUNCTION_END_NO_RETURN(void, DrawTransformFeedbackStreamInstanced, mode, id, stream, instancecount)
 DECLARE_GL_FUNCTION_STUB_HEAD(void, ClearBufferData, GLenum target, GLenum internalformat, GLenum format, GLenum type, const void* data) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, ClearBufferData, target, internalformat, format, type, data)
 DECLARE_GL_FUNCTION_STUB_HEAD(void, ClearBufferSubData, GLenum target, GLenum internalformat, GLintptr offset, GLsizeiptr size, GLenum format, GLenum type, const void* data) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, ClearBufferSubData, target, internalformat, offset, size, format, type, data)
 DECLARE_GL_FUNCTION_STUB_HEAD(void, GetInternalformati64v, GLenum target, GLenum internalformat, GLenum pname, GLsizei count, GLint64* params) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, GetInternalformati64v, target, internalformat, pname, count, params)
@@ -996,10 +997,10 @@ DECLARE_GL_FUNCTION_HEAD(void, MultiDrawElementsIndirect, GLenum mode, GLenum ty
 DECLARE_GL_FUNCTION_HEAD(GLint, GetProgramResourceLocationIndex, GLuint program, GLenum programInterface, const GLchar* name) DECLARE_GL_FUNCTION_END(GLint, GetProgramResourceLocationIndex, program, programInterface, name)
 DECLARE_GL_FUNCTION_HEAD(void, ShaderStorageBlockBinding, GLuint program, GLuint storageBlockIndex, GLuint storageBlockBinding) DECLARE_GL_FUNCTION_END_NO_RETURN(void, ShaderStorageBlockBinding, program, storageBlockIndex, storageBlockBinding)
 DECLARE_GL_FUNCTION_STUB_HEAD(void, TextureView, GLuint texture, GLenum target, GLuint origtexture, GLenum internalformat, GLuint minlevel, GLuint numlevels, GLuint minlayer, GLuint numlayers) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, TextureView, texture, target, origtexture, internalformat, minlevel, numlevels, minlayer, numlayers)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, VertexAttribLFormat, GLuint attribindex, GLint size, GLenum type, GLuint relativeoffset) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, VertexAttribLFormat, attribindex, size, type, relativeoffset)
+DECLARE_GL_FUNCTION_HEAD(void, VertexAttribLFormat, GLuint attribindex, GLint size, GLenum type, GLuint relativeoffset) DECLARE_GL_FUNCTION_END_NO_RETURN(void, VertexAttribLFormat, attribindex, size, type, relativeoffset)
 DECLARE_GL_FUNCTION_HEAD(void, BufferStorage, GLenum target, GLsizeiptr size, const void* data, GLbitfield flags) DECLARE_GL_FUNCTION_END_NO_RETURN(void, BufferStorage, target, size, data, flags)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, ClearTexImage, GLuint texture, GLint level, GLenum format, GLenum type, const void* data) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, ClearTexImage, texture, level, format, type, data)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, ClearTexSubImage, GLuint texture, GLint level, GLint xoffset, GLint yoffset, GLint zoffset, GLsizei width, GLsizei height, GLsizei depth, GLenum format, GLenum type, const void* data) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, ClearTexSubImage, texture, level, xoffset, yoffset, zoffset, width, height, depth, format, type, data)
+DECLARE_GL_FUNCTION_HEAD(void, ClearTexImage, GLuint texture, GLint level, GLenum format, GLenum type, const void* data) DECLARE_GL_FUNCTION_END_NO_RETURN(void, ClearTexImage, texture, level, format, type, data)
+DECLARE_GL_FUNCTION_HEAD(void, ClearTexSubImage, GLuint texture, GLint level, GLint xoffset, GLint yoffset, GLint zoffset, GLsizei width, GLsizei height, GLsizei depth, GLenum format, GLenum type, const void* data) DECLARE_GL_FUNCTION_END_NO_RETURN(void, ClearTexSubImage, texture, level, xoffset, yoffset, zoffset, width, height, depth, format, type, data)
 DECLARE_GL_FUNCTION_HEAD(void, BindBuffersBase, GLenum target, GLuint first, GLsizei count, const GLuint* buffers) DECLARE_GL_FUNCTION_END_NO_RETURN(void, BindBuffersBase, target, first, count, buffers)
 DECLARE_GL_FUNCTION_HEAD(void, BindBuffersRange, GLenum target, GLuint first, GLsizei count, const GLuint* buffers, const GLintptr* offsets, const GLsizeiptr* sizes) DECLARE_GL_FUNCTION_END_NO_RETURN(void, BindBuffersRange, target, first, count, buffers, offsets, sizes)
 DECLARE_GL_FUNCTION_STUB_HEAD(void, BindTextures, GLuint first, GLsizei count, const GLuint* textures) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, BindTextures, first, count, textures)
@@ -1007,12 +1008,12 @@ DECLARE_GL_FUNCTION_HEAD(void, BindSamplers, GLuint first, GLsizei count, const
 DECLARE_GL_FUNCTION_STUB_HEAD(void, BindImageTextures, GLuint first, GLsizei count, const GLuint* textures) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, BindImageTextures, first, count, textures)
 DECLARE_GL_FUNCTION_HEAD(void, BindVertexBuffers, GLuint first, GLsizei count, const GLuint* buffers, const GLintptr* offsets, const GLsizei* strides) DECLARE_GL_FUNCTION_END_NO_RETURN(void, BindVertexBuffers, first, count, buffers, offsets, strides)
 DECLARE_GL_FUNCTION_STUB_HEAD(void, ClipControl, GLenum origin, GLenum depth) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, ClipControl, origin, depth)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, CreateTransformFeedbacks, GLsizei n, GLuint* ids) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, CreateTransformFeedbacks, n, ids)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, TransformFeedbackBufferBase, GLuint xfb, GLuint index, GLuint buffer) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, TransformFeedbackBufferBase, xfb, index, buffer)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, TransformFeedbackBufferRange, GLuint xfb, GLuint index, GLuint buffer, GLintptr offset, GLsizeiptr size) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, TransformFeedbackBufferRange, xfb, index, buffer, offset, size)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, GetTransformFeedbackiv, GLuint xfb, GLenum pname, GLint* param) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, GetTransformFeedbackiv, xfb, pname, param)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, GetTransformFeedbacki_v, GLuint xfb, GLenum pname, GLuint index, GLint* param) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, GetTransformFeedbacki_v, xfb, pname, index, param)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, GetTransformFeedbacki64_v, GLuint xfb, GLenum pname, GLuint index, GLint64* param) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, GetTransformFeedbacki64_v, xfb, pname, index, param)
+DECLARE_GL_FUNCTION_HEAD(void, CreateTransformFeedbacks, GLsizei n, GLuint* ids) DECLARE_GL_FUNCTION_END_NO_RETURN(void, CreateTransformFeedbacks, n, ids)
+DECLARE_GL_FUNCTION_HEAD(void, TransformFeedbackBufferBase, GLuint xfb, GLuint index, GLuint buffer) DECLARE_GL_FUNCTION_END_NO_RETURN(void, TransformFeedbackBufferBase, xfb, index, buffer)
+DECLARE_GL_FUNCTION_HEAD(void, TransformFeedbackBufferRange, GLuint xfb, GLuint index, GLuint buffer, GLintptr offset, GLsizeiptr size) DECLARE_GL_FUNCTION_END_NO_RETURN(void, TransformFeedbackBufferRange, xfb, index, buffer, offset, size)
+DECLARE_GL_FUNCTION_HEAD(void, GetTransformFeedbackiv, GLuint xfb, GLenum pname, GLint* param) DECLARE_GL_FUNCTION_END_NO_RETURN(void, GetTransformFeedbackiv, xfb, pname, param)
+DECLARE_GL_FUNCTION_HEAD(void, GetTransformFeedbacki_v, GLuint xfb, GLenum pname, GLuint index, GLint* param) DECLARE_GL_FUNCTION_END_NO_RETURN(void, GetTransformFeedbacki_v, xfb, pname, index, param)
+DECLARE_GL_FUNCTION_HEAD(void, GetTransformFeedbacki64_v, GLuint xfb, GLenum pname, GLuint index, GLint64* param) DECLARE_GL_FUNCTION_END_NO_RETURN(void, GetTransformFeedbacki64_v, xfb, pname, index, param)
 DECLARE_GL_FUNCTION_HEAD(void, CreateBuffers, GLsizei n, GLuint* buffers) DECLARE_GL_FUNCTION_END_NO_RETURN(void, CreateBuffers, n, buffers)
 DECLARE_GL_FUNCTION_HEAD(void, NamedBufferStorage, GLuint buffer, GLsizeiptr size, const void* data, GLbitfield flags) DECLARE_GL_FUNCTION_END_NO_RETURN(void, NamedBufferStorage, buffer, size, data, flags)
 DECLARE_GL_FUNCTION_HEAD(void, NamedBufferData, GLuint buffer, GLsizeiptr size, const void* data, GLenum usage) DECLARE_GL_FUNCTION_END_NO_RETURN(void, NamedBufferData, buffer, size, data, usage)
@@ -1025,32 +1026,32 @@ DECLARE_GL_FUNCTION_HEAD(void, FlushMappedNamedBufferRange, GLuint buffer, GLint
 DECLARE_GL_FUNCTION_HEAD(void, GetNamedBufferParameteriv, GLuint buffer, GLenum pname, GLint* params) DECLARE_GL_FUNCTION_END_NO_RETURN(void, GetNamedBufferParameteriv, buffer, pname, params)
 DECLARE_GL_FUNCTION_HEAD(void, GetNamedBufferParameteri64v, GLuint buffer, GLenum pname, GLint64* params) DECLARE_GL_FUNCTION_END_NO_RETURN(void, GetNamedBufferParameteri64v, buffer, pname, params)
 DECLARE_GL_FUNCTION_HEAD(void, GetNamedBufferPointerv, GLuint buffer, GLenum pname, void** params) DECLARE_GL_FUNCTION_END_NO_RETURN(void, GetNamedBufferPointerv, buffer, pname, params)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, GetNamedBufferSubData, GLuint buffer, GLintptr offset, GLsizeiptr size, void* data) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, GetNamedBufferSubData, buffer, offset, size, data)
+DECLARE_GL_FUNCTION_HEAD(void, GetNamedBufferSubData, GLuint buffer, GLintptr offset, GLsizeiptr size, void* data) DECLARE_GL_FUNCTION_END_NO_RETURN(void, GetNamedBufferSubData, buffer, offset, size, data)
 DECLARE_GL_FUNCTION_HEAD(void, CreateFramebuffers, GLsizei n, GLuint* framebuffers) DECLARE_GL_FUNCTION_END_NO_RETURN(void, CreateFramebuffers, n, framebuffers)
 DECLARE_GL_FUNCTION_HEAD(void, NamedFramebufferRenderbuffer, GLuint framebuffer, GLenum attachment, GLenum renderbuffertarget, GLuint renderbuffer) DECLARE_GL_FUNCTION_END_NO_RETURN(void, NamedFramebufferRenderbuffer, framebuffer, attachment, renderbuffertarget, renderbuffer)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, NamedFramebufferParameteri, GLuint framebuffer, GLenum pname, GLint param) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, NamedFramebufferParameteri, framebuffer, pname, param)
+DECLARE_GL_FUNCTION_HEAD(void, NamedFramebufferParameteri, GLuint framebuffer, GLenum pname, GLint param) DECLARE_GL_FUNCTION_END_NO_RETURN(void, NamedFramebufferParameteri, framebuffer, pname, param)
 DECLARE_GL_FUNCTION_HEAD(void, NamedFramebufferTexture, GLuint framebuffer, GLenum attachment, GLuint texture, GLint level) DECLARE_GL_FUNCTION_END_NO_RETURN(void, NamedFramebufferTexture, framebuffer, attachment, texture, level)
 DECLARE_GL_FUNCTION_HEAD(void, NamedFramebufferTextureLayer, GLuint framebuffer, GLenum attachment, GLuint texture, GLint level, GLint layer) DECLARE_GL_FUNCTION_END_NO_RETURN(void, NamedFramebufferTextureLayer, framebuffer, attachment, texture, level, layer)
 DECLARE_GL_FUNCTION_HEAD(void, NamedFramebufferDrawBuffer, GLuint framebuffer, GLenum buf) DECLARE_GL_FUNCTION_END_NO_RETURN(void, NamedFramebufferDrawBuffer, framebuffer, buf)
 DECLARE_GL_FUNCTION_HEAD(void, NamedFramebufferDrawBuffers, GLuint framebuffer, GLsizei n, const GLenum* bufs) DECLARE_GL_FUNCTION_END_NO_RETURN(void, NamedFramebufferDrawBuffers, framebuffer, n, bufs)
 DECLARE_GL_FUNCTION_HEAD(void, NamedFramebufferReadBuffer, GLuint framebuffer, GLenum src) DECLARE_GL_FUNCTION_END_NO_RETURN(void, NamedFramebufferReadBuffer, framebuffer, src)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, InvalidateNamedFramebufferData, GLuint framebuffer, GLsizei numAttachments, const GLenum* attachments) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, InvalidateNamedFramebufferData, framebuffer, numAttachments, attachments)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, InvalidateNamedFramebufferSubData, GLuint framebuffer, GLsizei numAttachments, const GLenum* attachments, GLint x, GLint y, GLsizei width, GLsizei height) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, InvalidateNamedFramebufferSubData, framebuffer, numAttachments, attachments, x, y, width, height)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, ClearNamedFramebufferiv, GLuint framebuffer, GLenum buffer, GLint drawbuffer, const GLint* value) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, ClearNamedFramebufferiv, framebuffer, buffer, drawbuffer, value)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, ClearNamedFramebufferuiv, GLuint framebuffer, GLenum buffer, GLint drawbuffer, const GLuint* value) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, ClearNamedFramebufferuiv, framebuffer, buffer, drawbuffer, value)
+DECLARE_GL_FUNCTION_HEAD(void, InvalidateNamedFramebufferData, GLuint framebuffer, GLsizei numAttachments, const GLenum* attachments) DECLARE_GL_FUNCTION_END_NO_RETURN(void, InvalidateNamedFramebufferData, framebuffer, numAttachments, attachments)
+DECLARE_GL_FUNCTION_HEAD(void, InvalidateNamedFramebufferSubData, GLuint framebuffer, GLsizei numAttachments, const GLenum* attachments, GLint x, GLint y, GLsizei width, GLsizei height) DECLARE_GL_FUNCTION_END_NO_RETURN(void, InvalidateNamedFramebufferSubData, framebuffer, numAttachments, attachments, x, y, width, height)
+DECLARE_GL_FUNCTION_HEAD(void, ClearNamedFramebufferiv, GLuint framebuffer, GLenum buffer, GLint drawbuffer, const GLint* value) DECLARE_GL_FUNCTION_END_NO_RETURN(void, ClearNamedFramebufferiv, framebuffer, buffer, drawbuffer, value)
+DECLARE_GL_FUNCTION_HEAD(void, ClearNamedFramebufferuiv, GLuint framebuffer, GLenum buffer, GLint drawbuffer, const GLuint* value) DECLARE_GL_FUNCTION_END_NO_RETURN(void, ClearNamedFramebufferuiv, framebuffer, buffer, drawbuffer, value)
 DECLARE_GL_FUNCTION_HEAD(void, ClearNamedFramebufferfv, GLuint framebuffer, GLenum buffer, GLint drawbuffer, const GLfloat* value) DECLARE_GL_FUNCTION_END_NO_RETURN(void, ClearNamedFramebufferfv, framebuffer, buffer, drawbuffer, value)
 DECLARE_GL_FUNCTION_HEAD(void, ClearNamedFramebufferfi, GLuint framebuffer, GLenum buffer, GLint drawbuffer, GLfloat depth, GLint stencil) DECLARE_GL_FUNCTION_END_NO_RETURN(void, ClearNamedFramebufferfi, framebuffer, buffer, drawbuffer, depth, stencil)
 DECLARE_GL_FUNCTION_HEAD(void, BlitNamedFramebuffer, GLuint readFramebuffer, GLuint drawFramebuffer, GLint srcX0, GLint srcY0, GLint srcX1, GLint srcY1, GLint dstX0, GLint dstY0, GLint dstX1, GLint dstY1, GLbitfield mask, GLenum filter) DECLARE_GL_FUNCTION_END_NO_RETURN(void, BlitNamedFramebuffer, readFramebuffer, drawFramebuffer, srcX0, srcY0, srcX1, srcY1, dstX0, dstY0, dstX1, dstY1, mask, filter)
 DECLARE_GL_FUNCTION_HEAD(GLenum, CheckNamedFramebufferStatus, GLuint framebuffer, GLenum target) DECLARE_GL_FUNCTION_END(GLenum, CheckNamedFramebufferStatus, framebuffer, target)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, GetNamedFramebufferParameteriv, GLuint framebuffer, GLenum pname, GLint* param) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, GetNamedFramebufferParameteriv, framebuffer, pname, param)
+DECLARE_GL_FUNCTION_HEAD(void, GetNamedFramebufferParameteriv, GLuint framebuffer, GLenum pname, GLint* param) DECLARE_GL_FUNCTION_END_NO_RETURN(void, GetNamedFramebufferParameteriv, framebuffer, pname, param)
 DECLARE_GL_FUNCTION_HEAD(void, GetNamedFramebufferAttachmentParameteriv, GLuint framebuffer, GLenum attachment, GLenum pname, GLint* params) DECLARE_GL_FUNCTION_END_NO_RETURN(void, GetNamedFramebufferAttachmentParameteriv, framebuffer, attachment, pname, params)
 DECLARE_GL_FUNCTION_HEAD(void, CreateRenderbuffers, GLsizei n, GLuint* renderbuffers) DECLARE_GL_FUNCTION_END_NO_RETURN(void, CreateRenderbuffers, n, renderbuffers)
 DECLARE_GL_FUNCTION_HEAD(void, NamedRenderbufferStorage, GLuint renderbuffer, GLenum internalformat, GLsizei width, GLsizei height) DECLARE_GL_FUNCTION_END_NO_RETURN(void, NamedRenderbufferStorage, renderbuffer, internalformat, width, height)
 DECLARE_GL_FUNCTION_HEAD(void, NamedRenderbufferStorageMultisample, GLuint renderbuffer, GLsizei samples, GLenum internalformat, GLsizei width, GLsizei height) DECLARE_GL_FUNCTION_END_NO_RETURN(void, NamedRenderbufferStorageMultisample, renderbuffer, samples, internalformat, width, height)
 DECLARE_GL_FUNCTION_HEAD(void, GetNamedRenderbufferParameteriv, GLuint renderbuffer, GLenum pname, GLint* params) DECLARE_GL_FUNCTION_END_NO_RETURN(void, GetNamedRenderbufferParameteriv, renderbuffer, pname, params)
 DECLARE_GL_FUNCTION_HEAD(void, CreateTextures, GLenum target, GLsizei n, GLuint* textures) DECLARE_GL_FUNCTION_END_NO_RETURN(void, CreateTextures, target, n, textures)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, TextureBuffer, GLuint texture, GLenum internalformat, GLuint buffer) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, TextureBuffer, texture, internalformat, buffer)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, TextureBufferRange, GLuint texture, GLenum internalformat, GLuint buffer, GLintptr offset, GLsizeiptr size) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, TextureBufferRange, texture, internalformat, buffer, offset, size)
+DECLARE_GL_FUNCTION_HEAD(void, TextureBuffer, GLuint texture, GLenum internalformat, GLuint buffer) DECLARE_GL_FUNCTION_END_NO_RETURN(void, TextureBuffer, texture, internalformat, buffer)
+DECLARE_GL_FUNCTION_HEAD(void, TextureBufferRange, GLuint texture, GLenum internalformat, GLuint buffer, GLintptr offset, GLsizeiptr size) DECLARE_GL_FUNCTION_END_NO_RETURN(void, TextureBufferRange, texture, internalformat, buffer, offset, size)
 DECLARE_GL_FUNCTION_HEAD(void, TextureStorage1D, GLuint texture, GLsizei levels, GLenum internalformat, GLsizei width) DECLARE_GL_FUNCTION_END_NO_RETURN(void, TextureStorage1D, texture, levels, internalformat, width)
 DECLARE_GL_FUNCTION_HEAD(void, TextureStorage2D, GLuint texture, GLsizei levels, GLenum internalformat, GLsizei width, GLsizei height) DECLARE_GL_FUNCTION_END_NO_RETURN(void, TextureStorage2D, texture, levels, internalformat, width, height)
 DECLARE_GL_FUNCTION_HEAD(void, TextureStorage3D, GLuint texture, GLsizei levels, GLenum internalformat, GLsizei width, GLsizei height, GLsizei depth) DECLARE_GL_FUNCTION_END_NO_RETURN(void, TextureStorage3D, texture, levels, internalformat, width, height, depth)
@@ -1062,9 +1063,9 @@ DECLARE_GL_FUNCTION_HEAD(void, TextureSubImage3D, GLuint texture, GLint level, G
 DECLARE_GL_FUNCTION_STUB_HEAD(void, CompressedTextureSubImage1D, GLuint texture, GLint level, GLint xoffset, GLsizei width, GLenum format, GLsizei imageSize, const void* data) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, CompressedTextureSubImage1D, texture, level, xoffset, width, format, imageSize, data)
 DECLARE_GL_FUNCTION_STUB_HEAD(void, CompressedTextureSubImage2D, GLuint texture, GLint level, GLint xoffset, GLint yoffset, GLsizei width, GLsizei height, GLenum format, GLsizei imageSize, const void* data) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, CompressedTextureSubImage2D, texture, level, xoffset, yoffset, width, height, format, imageSize, data)
 DECLARE_GL_FUNCTION_STUB_HEAD(void, CompressedTextureSubImage3D, GLuint texture, GLint level, GLint xoffset, GLint yoffset, GLint zoffset, GLsizei width, GLsizei height, GLsizei depth, GLenum format, GLsizei imageSize, const void* data) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, CompressedTextureSubImage3D, texture, level, xoffset, yoffset, zoffset, width, height, depth, format, imageSize, data)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, CopyTextureSubImage1D, GLuint texture, GLint level, GLint xoffset, GLint x, GLint y, GLsizei width) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, CopyTextureSubImage1D, texture, level, xoffset, x, y, width)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, CopyTextureSubImage2D, GLuint texture, GLint level, GLint xoffset, GLint yoffset, GLint x, GLint y, GLsizei width, GLsizei height) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, CopyTextureSubImage2D, texture, level, xoffset, yoffset, x, y, width, height)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, CopyTextureSubImage3D, GLuint texture, GLint level, GLint xoffset, GLint yoffset, GLint zoffset, GLint x, GLint y, GLsizei width, GLsizei height) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, CopyTextureSubImage3D, texture, level, xoffset, yoffset, zoffset, x, y, width, height)
+DECLARE_GL_FUNCTION_HEAD(void, CopyTextureSubImage1D, GLuint texture, GLint level, GLint xoffset, GLint x, GLint y, GLsizei width) DECLARE_GL_FUNCTION_END_NO_RETURN(void, CopyTextureSubImage1D, texture, level, xoffset, x, y, width)
+DECLARE_GL_FUNCTION_HEAD(void, CopyTextureSubImage2D, GLuint texture, GLint level, GLint xoffset, GLint yoffset, GLint x, GLint y, GLsizei width, GLsizei height) DECLARE_GL_FUNCTION_END_NO_RETURN(void, CopyTextureSubImage2D, texture, level, xoffset, yoffset, x, y, width, height)
+DECLARE_GL_FUNCTION_HEAD(void, CopyTextureSubImage3D, GLuint texture, GLint level, GLint xoffset, GLint yoffset, GLint zoffset, GLint x, GLint y, GLsizei width, GLsizei height) DECLARE_GL_FUNCTION_END_NO_RETURN(void, CopyTextureSubImage3D, texture, level, xoffset, yoffset, zoffset, x, y, width, height)
 DECLARE_GL_FUNCTION_HEAD(void, TextureParameterf, GLuint texture, GLenum pname, GLfloat param) DECLARE_GL_FUNCTION_END_NO_RETURN(void, TextureParameterf, texture, pname, param)
 DECLARE_GL_FUNCTION_HEAD(void, TextureParameterfv, GLuint texture, GLenum pname, const GLfloat* param) DECLARE_GL_FUNCTION_END_NO_RETURN(void, TextureParameterfv, texture, pname, param)
 DECLARE_GL_FUNCTION_HEAD(void, TextureParameteri, GLuint texture, GLenum pname, GLint param) DECLARE_GL_FUNCTION_END_NO_RETURN(void, TextureParameteri, texture, pname, param)
@@ -1074,7 +1075,7 @@ DECLARE_GL_FUNCTION_HEAD(void, TextureParameteriv, GLuint texture, GLenum pname,
 DECLARE_GL_FUNCTION_HEAD(void, GenerateTextureMipmap, GLuint texture) DECLARE_GL_FUNCTION_END_NO_RETURN(void, GenerateTextureMipmap, texture)
 DECLARE_GL_FUNCTION_HEAD(void, BindTextureUnit, GLuint unit, GLuint texture) DECLARE_GL_FUNCTION_END_NO_RETURN(void, BindTextureUnit, unit, texture)
 DECLARE_GL_FUNCTION_HEAD(void, GetTextureImage, GLuint texture, GLint level, GLenum format, GLenum type, GLsizei bufSize, void* pixels) DECLARE_GL_FUNCTION_END_NO_RETURN(void, GetTextureImage, texture, level, format, type, bufSize, pixels)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, GetCompressedTextureImage, GLuint texture, GLint level, GLsizei bufSize, void* pixels) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, GetCompressedTextureImage, texture, level, bufSize, pixels)
+DECLARE_GL_FUNCTION_HEAD(void, GetCompressedTextureImage, GLuint texture, GLint level, GLsizei bufSize, void* pixels) DECLARE_GL_FUNCTION_END_NO_RETURN(void, GetCompressedTextureImage, texture, level, bufSize, pixels)
 DECLARE_GL_FUNCTION_HEAD(void, GetTextureLevelParameterfv, GLuint texture, GLint level, GLenum pname, GLfloat* params) DECLARE_GL_FUNCTION_END_NO_RETURN(void, GetTextureLevelParameterfv, texture, level, pname, params)
 DECLARE_GL_FUNCTION_HEAD(void, GetTextureLevelParameteriv, GLuint texture, GLint level, GLenum pname, GLint* params) DECLARE_GL_FUNCTION_END_NO_RETURN(void, GetTextureLevelParameteriv, texture, level, pname, params)
 DECLARE_GL_FUNCTION_HEAD(void, GetTextureParameterfv, GLuint texture, GLenum pname, GLfloat* params) DECLARE_GL_FUNCTION_END_NO_RETURN(void, GetTextureParameterfv, texture, pname, params)
@@ -1090,18 +1091,18 @@ DECLARE_GL_FUNCTION_HEAD(void, VertexArrayVertexBuffers, GLuint vaobj, GLuint fi
 DECLARE_GL_FUNCTION_HEAD(void, VertexArrayAttribBinding, GLuint vaobj, GLuint attribindex, GLuint bindingindex) DECLARE_GL_FUNCTION_END_NO_RETURN(void, VertexArrayAttribBinding, vaobj, attribindex, bindingindex)
 DECLARE_GL_FUNCTION_HEAD(void, VertexArrayAttribFormat, GLuint vaobj, GLuint attribindex, GLint size, GLenum type, GLboolean normalized, GLuint relativeoffset) DECLARE_GL_FUNCTION_END_NO_RETURN(void, VertexArrayAttribFormat, vaobj, attribindex, size, type, normalized, relativeoffset)
 DECLARE_GL_FUNCTION_HEAD(void, VertexArrayAttribIFormat, GLuint vaobj, GLuint attribindex, GLint size, GLenum type, GLuint relativeoffset) DECLARE_GL_FUNCTION_END_NO_RETURN(void, VertexArrayAttribIFormat, vaobj, attribindex, size, type, relativeoffset)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, VertexArrayAttribLFormat, GLuint vaobj, GLuint attribindex, GLint size, GLenum type, GLuint relativeoffset) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, VertexArrayAttribLFormat, vaobj, attribindex, size, type, relativeoffset)
+DECLARE_GL_FUNCTION_HEAD(void, VertexArrayAttribLFormat, GLuint vaobj, GLuint attribindex, GLint size, GLenum type, GLuint relativeoffset) DECLARE_GL_FUNCTION_END_NO_RETURN(void, VertexArrayAttribLFormat, vaobj, attribindex, size, type, relativeoffset)
 DECLARE_GL_FUNCTION_HEAD(void, VertexArrayBindingDivisor, GLuint vaobj, GLuint bindingindex, GLuint divisor) DECLARE_GL_FUNCTION_END_NO_RETURN(void, VertexArrayBindingDivisor, vaobj, bindingindex, divisor)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, GetVertexArrayiv, GLuint vaobj, GLenum pname, GLint* param) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, GetVertexArrayiv, vaobj, pname, param)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, GetVertexArrayIndexediv, GLuint vaobj, GLuint index, GLenum pname, GLint* param) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, GetVertexArrayIndexediv, vaobj, index, pname, param)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, GetVertexArrayIndexed64iv, GLuint vaobj, GLuint index, GLenum pname, GLint64* param) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, GetVertexArrayIndexed64iv, vaobj, index, pname, param)
+DECLARE_GL_FUNCTION_HEAD(void, GetVertexArrayiv, GLuint vaobj, GLenum pname, GLint* param) DECLARE_GL_FUNCTION_END_NO_RETURN(void, GetVertexArrayiv, vaobj, pname, param)
+DECLARE_GL_FUNCTION_HEAD(void, GetVertexArrayIndexediv, GLuint vaobj, GLuint index, GLenum pname, GLint* param) DECLARE_GL_FUNCTION_END_NO_RETURN(void, GetVertexArrayIndexediv, vaobj, index, pname, param)
+DECLARE_GL_FUNCTION_HEAD(void, GetVertexArrayIndexed64iv, GLuint vaobj, GLuint index, GLenum pname, GLint64* param) DECLARE_GL_FUNCTION_END_NO_RETURN(void, GetVertexArrayIndexed64iv, vaobj, index, pname, param)
 DECLARE_GL_FUNCTION_HEAD(void, CreateSamplers, GLsizei n, GLuint* samplers) DECLARE_GL_FUNCTION_END_NO_RETURN(void, CreateSamplers, n, samplers)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, CreateProgramPipelines, GLsizei n, GLuint* pipelines) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, CreateProgramPipelines, n, pipelines)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, CreateQueries, GLenum target, GLsizei n, GLuint* ids) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, CreateQueries, target, n, ids)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, GetQueryBufferObjecti64v, GLuint id, GLuint buffer, GLenum pname, GLintptr offset) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, GetQueryBufferObjecti64v, id, buffer, pname, offset)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, GetQueryBufferObjectiv, GLuint id, GLuint buffer, GLenum pname, GLintptr offset) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, GetQueryBufferObjectiv, id, buffer, pname, offset)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, GetQueryBufferObjectui64v, GLuint id, GLuint buffer, GLenum pname, GLintptr offset) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, GetQueryBufferObjectui64v, id, buffer, pname, offset)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, GetQueryBufferObjectuiv, GLuint id, GLuint buffer, GLenum pname, GLintptr offset) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, GetQueryBufferObjectuiv, id, buffer, pname, offset)
+DECLARE_GL_FUNCTION_HEAD(void, CreateProgramPipelines, GLsizei n, GLuint* pipelines) DECLARE_GL_FUNCTION_END_NO_RETURN(void, CreateProgramPipelines, n, pipelines)
+DECLARE_GL_FUNCTION_HEAD(void, CreateQueries, GLenum target, GLsizei n, GLuint* ids) DECLARE_GL_FUNCTION_END_NO_RETURN(void, CreateQueries, target, n, ids)
+DECLARE_GL_FUNCTION_HEAD(void, GetQueryBufferObjecti64v, GLuint id, GLuint buffer, GLenum pname, GLintptr offset) DECLARE_GL_FUNCTION_END_NO_RETURN(void, GetQueryBufferObjecti64v, id, buffer, pname, offset)
+DECLARE_GL_FUNCTION_HEAD(void, GetQueryBufferObjectiv, GLuint id, GLuint buffer, GLenum pname, GLintptr offset) DECLARE_GL_FUNCTION_END_NO_RETURN(void, GetQueryBufferObjectiv, id, buffer, pname, offset)
+DECLARE_GL_FUNCTION_HEAD(void, GetQueryBufferObjectui64v, GLuint id, GLuint buffer, GLenum pname, GLintptr offset) DECLARE_GL_FUNCTION_END_NO_RETURN(void, GetQueryBufferObjectui64v, id, buffer, pname, offset)
+DECLARE_GL_FUNCTION_HEAD(void, GetQueryBufferObjectuiv, GLuint id, GLuint buffer, GLenum pname, GLintptr offset) DECLARE_GL_FUNCTION_END_NO_RETURN(void, GetQueryBufferObjectuiv, id, buffer, pname, offset)
 DECLARE_GL_FUNCTION_HEAD(void, GetTextureSubImage, GLuint texture, GLint level, GLint xoffset, GLint yoffset, GLint zoffset, GLsizei width, GLsizei height, GLsizei depth, GLenum format, GLenum type, GLsizei bufSize, void* pixels) DECLARE_GL_FUNCTION_END_NO_RETURN(void, GetTextureSubImage, texture, level, xoffset, yoffset, zoffset, width, height, depth, format, type, bufSize, pixels)
 DECLARE_GL_FUNCTION_STUB_HEAD(void, GetCompressedTextureSubImage, GLuint texture, GLint level, GLint xoffset, GLint yoffset, GLint zoffset, GLsizei width, GLsizei height, GLsizei depth, GLsizei bufSize, void* pixels) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, GetCompressedTextureSubImage, texture, level, xoffset, yoffset, zoffset, width, height, depth, bufSize, pixels)
 DECLARE_GL_FUNCTION_STUB_HEAD(void, GetnCompressedTexImage, GLenum target, GLint lod, GLsizei bufSize, void* pixels) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, GetnCompressedTexImage, target, lod, bufSize, pixels)
@@ -1272,7 +1273,7 @@ DECLARE_GL_FUNCTION_STUB_HEAD(void, MultiTexCoord4ivARB, GLenum target, const GL
 DECLARE_GL_FUNCTION_STUB_HEAD(void, MultiTexCoord4sARB, GLenum target, GLshort s, GLshort t, GLshort r, GLshort q) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, MultiTexCoord4sARB, target, s, t, r, q)
 DECLARE_GL_FUNCTION_STUB_HEAD(void, MultiTexCoord4svARB, GLenum target, const GLshort* v) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, MultiTexCoord4svARB, target, v)
 DECLARE_GL_FUNCTION_STUB_HEAD(void, GetQueryObjectivARB, GLuint id, GLenum pname, GLint* params) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, GetQueryObjectivARB, id, pname, params)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, MaxShaderCompilerThreadsARB, GLuint count) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, MaxShaderCompilerThreadsARB, count)
+DECLARE_GL_FUNCTION_HEAD(void, MaxShaderCompilerThreadsARB, GLuint count) DECLARE_GL_FUNCTION_END_NO_RETURN(void, MaxShaderCompilerThreadsARB, count)
 DECLARE_GL_FUNCTION_STUB_HEAD(void, PointParameterfARB, GLenum pname, GLfloat param) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, PointParameterfARB, pname, param)
 DECLARE_GL_FUNCTION_STUB_HEAD(void, PointParameterfvARB, GLenum pname, const GLfloat* params) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, PointParameterfvARB, pname, params)
 DECLARE_GL_FUNCTION_STUB_HEAD(void, GetnTexImageARB, GLenum target, GLint level, GLenum format, GLenum type, GLsizei bufSize, void* img) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, GetnTexImageARB, target, level, format, type, bufSize, img)
@@ -1380,7 +1381,7 @@ DECLARE_GL_FUNCTION_STUB_HEAD(void, WindowPos3ivARB, const GLint* v) DECLARE_GL_
 DECLARE_GL_FUNCTION_STUB_HEAD(void, WindowPos3sARB, GLshort x, GLshort y, GLshort z) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, WindowPos3sARB, x, y, z)
 DECLARE_GL_FUNCTION_STUB_HEAD(void, WindowPos3svARB, const GLshort* v) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, WindowPos3svARB, v)
 DECLARE_GL_FUNCTION_STUB_HEAD(void, BlendBarrierKHR, void) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, BlendBarrierKHR, )
-DECLARE_GL_FUNCTION_STUB_HEAD(void, MaxShaderCompilerThreadsKHR, GLuint count) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, MaxShaderCompilerThreadsKHR, count)
+DECLARE_GL_FUNCTION_HEAD(void, MaxShaderCompilerThreadsKHR, GLuint count) DECLARE_GL_FUNCTION_END_NO_RETURN(void, MaxShaderCompilerThreadsKHR, count)
 DECLARE_GL_FUNCTION_STUB_HEAD(void, MultiTexCoord1bOES, GLenum texture, GLbyte s) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, MultiTexCoord1bOES, texture, s)
 DECLARE_GL_FUNCTION_STUB_HEAD(void, MultiTexCoord1bvOES, GLenum texture, const GLbyte* coords) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, MultiTexCoord1bvOES, texture, coords)
 DECLARE_GL_FUNCTION_STUB_HEAD(void, MultiTexCoord2bOES, GLenum texture, GLbyte s, GLbyte t) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, MultiTexCoord2bOES, texture, s, t)
@@ -2583,7 +2584,10 @@ DECLARE_GL_FUNCTION_STUB_HEAD(void, TransformFeedbackStreamAttribsNV, GLsizei co
 DECLARE_GL_FUNCTION_STUB_HEAD(void, BindTransformFeedbackNV, GLenum target, GLuint id) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, BindTransformFeedbackNV, target, id)
 DECLARE_GL_FUNCTION_STUB_HEAD(void, DeleteTransformFeedbacksNV, GLsizei n, const GLuint* ids) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, DeleteTransformFeedbacksNV, n, ids)
 DECLARE_GL_FUNCTION_STUB_HEAD(void, GenTransformFeedbacksNV, GLsizei n, GLuint* ids) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, GenTransformFeedbacksNV, n, ids)
-DECLARE_GL_FUNCTION_STUB_HEAD(GLboolean, IsTransformFeedbackNV, GLuint id) DECLARE_GL_FUNCTION_STUB_END(GLboolean, IsTransformFeedbackNV, id)
+MOBILEGL_GL_API GLboolean glIsTransformFeedbackNV(GLuint id) {
+    MGLOG_W("Stub function: %s(...)", __FUNCTION__);
+    return GL_FALSE;
+}
 DECLARE_GL_FUNCTION_STUB_HEAD(void, PauseTransformFeedbackNV, void) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, PauseTransformFeedbackNV, )
 DECLARE_GL_FUNCTION_STUB_HEAD(void, ResumeTransformFeedbackNV, void) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, ResumeTransformFeedbackNV, )
 DECLARE_GL_FUNCTION_STUB_HEAD(void, DrawTransformFeedbackNV, GLenum mode, GLuint id) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, DrawTransformFeedbackNV, mode, id)

MobileGL/MG_Impl/GLImpl/Framebuffer/GL_Framebuffer.h

@@ -14,6 +14,8 @@
 namespace MobileGL::MG_Impl::GLImpl {
     /* @INSERTION_POINT:FUNCTION_DECLARATION@ */
     void ReadPixels(GLint x, GLint y, GLsizei width, GLsizei height, GLenum format, GLenum type, void* pixels);
+    void ReadnPixels(GLint x, GLint y, GLsizei width, GLsizei height, GLenum format, GLenum type, GLsizei bufSize,
+                     void* data);
     void ClearBufferfi(GLenum buffer, GLint drawbuffer, GLfloat depth, GLint stencil);
     void ClearBufferfv(GLenum buffer, GLint drawbuffer, const GLfloat* value);
     void ClearBufferuiv(GLenum buffer, GLint drawbuffer, const GLuint* value);
@@ -56,7 +58,19 @@ namespace MobileGL::MG_Impl::GLImpl {
     void NamedFramebufferReadBuffer(GLuint framebuffer, GLenum src);
     void ClearNamedFramebufferfv(GLuint framebuffer, GLenum buffer, GLint drawbuffer, const GLfloat* value);
     void ClearNamedFramebufferfi(GLuint framebuffer, GLenum buffer, GLint drawbuffer, GLfloat depth, GLint stencil);
+    void InvalidateNamedFramebufferData(GLuint framebuffer, GLsizei numAttachments, const GLenum* attachments);
+    void InvalidateNamedFramebufferSubData(GLuint framebuffer, GLsizei numAttachments, const GLenum* attachments,
+                                           GLint x, GLint y, GLsizei width, GLsizei height);
+    void InvalidateFramebuffer(GLenum target, GLsizei numAttachments, const GLenum* attachments);
+    void InvalidateSubFramebuffer(GLenum target, GLsizei numAttachments, const GLenum* attachments, GLint x, GLint y,
+                                  GLsizei width, GLsizei height);
+    void ClearNamedFramebufferiv(GLuint framebuffer, GLenum buffer, GLint drawbuffer, const GLint* value);
+    void ClearNamedFramebufferuiv(GLuint framebuffer, GLenum buffer, GLint drawbuffer, const GLuint* value);
     GLenum CheckNamedFramebufferStatus(GLuint framebuffer, GLenum target);
+    void GetFramebufferParameteriv(GLenum target, GLenum pname, GLint* params);
+    void FramebufferParameteri(GLenum target, GLenum pname, GLint param);
+    void GetNamedFramebufferParameteriv(GLuint framebuffer, GLenum pname, GLint* params);
+    void NamedFramebufferParameteri(GLuint framebuffer, GLenum pname, GLint param);
     void GetNamedFramebufferAttachmentParameteriv(GLuint framebuffer, GLenum attachment, GLenum pname, GLint* params);
     void BlitNamedFramebuffer(GLuint readFramebuffer, GLuint drawFramebuffer, GLint srcX0, GLint srcY0, GLint srcX1,
                               GLint srcY1, GLint dstX0, GLint dstY0, GLint dstX1, GLint dstY1, GLbitfield mask,
@@ -78,6 +92,6 @@ namespace MobileGL::MG_Impl::GLImpl {
             SharedPtr<MG_State::GLState::ITextureObject> stencilAttachment;
         };
 
-        extern UniquePtr<DefaultFramebufferInfo> pDefaultFramebufferInfo;
+        extern UniquePtr<DefaultFramebufferInfo>& pDefaultFramebufferInfo;
     } // namespace FramebufferImpl
 } // namespace MobileGL::MG_Impl::GLImpl

MobileGL/MG_Impl/GLImpl/Framebuffer/Validators.cpp

@@ -7,6 +7,7 @@
 // End of Source File Header
 
 #include "Validators.h"
+#include <MG_Backend/BackendObjects.h>
 #include <MG_State/GLState/Core.h>
 #include <MG_State/GLState/ErrorState/Error.h>
 #include <MG_Util/Converters/GLToStr/GLEnumConverter.h>
@@ -60,6 +61,26 @@ namespace MobileGL::MG_Impl::GLImpl::FramebufferImpl {
         return true;
     }
 
+    Bool ValidateColorAttachmentInRange(FramebufferAttachmentType attachment, const char* caller) {
+        const auto first = static_cast<SizeT>(FramebufferAttachmentType::Color0);
+        const auto index = static_cast<SizeT>(attachment);
+        if (index < first) return true;
+        const auto colorIndex = index - first;
+        const auto limit = static_cast<SizeT>(
+            MG_Backend::pActiveBackendObject ? MG_Backend::pActiveBackendObject->GetDynamicParameters()
+                                                   .MaxColorAttachments
+                                             : static_cast<Int>(MG_State::GLState::FramebufferObject::MAX_DRAW_BUFFERS));
+        if (colorIndex >= limit) {
+            MG_State::pGLContext->RecordError(
+                ErrorCode::InvalidOperation,
+                MakeUnique<GenericErrorInfo>(
+                    "MG_Impl/GLImpl/FramebufferImpl", caller,
+                    std::format("Colour attachment {} is beyond GL_MAX_COLOR_ATTACHMENTS ({}).", colorIndex, limit)));
+            return false;
+        }
+        return true;
+    }
+
     Bool ValidateRenderbufferTarget(RenderbufferTarget target) {
         if (target == RenderbufferTarget::Unknown) {
             using namespace MG_Util;
@@ -76,7 +97,13 @@ namespace MobileGL::MG_Impl::GLImpl::FramebufferImpl {
     }
 
     Bool ValidateRenderbufferName(Uint index, Bool allowZero) {
-        if (index == 0 && !allowZero) {
+        if (index == 0) {
+            // Zero is never a GenRenderbuffers name, so it must not reach the name-table lookup
+            // below: where it is allowed (glBindRenderbuffer / FramebufferRenderbuffer detach) it
+            // means "unbind", and looking it up would record a bogus INVALID_OPERATION - GL CTS's
+            // per-case state reset calls glBindRenderbuffer(GL_RENDERBUFFER, 0) after every case.
+            if (allowZero) return true;
+
             MG_State::pGLContext->RecordError(
                 ErrorCode::InvalidValue,
                 MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl/FramebufferImpl", "ValidateRenderbufferName",
@@ -91,4 +118,100 @@ namespace MobileGL::MG_Impl::GLImpl::FramebufferImpl {
                                          std::format("Renderbuffer name {} is not valid.", index)));
         return false;
     }
+
+    Bool ValidateFramebufferParameterPname(GLenum pname, Bool isDefaultFramebuffer, Bool forSetter,
+                                           const char* caller) {
+        Bool isDefaultParameter = false;
+        switch (pname) {
+        case GL_FRAMEBUFFER_DEFAULT_WIDTH:
+        case GL_FRAMEBUFFER_DEFAULT_HEIGHT:
+        case GL_FRAMEBUFFER_DEFAULT_LAYERS:
+        case GL_FRAMEBUFFER_DEFAULT_SAMPLES:
+        case GL_FRAMEBUFFER_DEFAULT_FIXED_SAMPLE_LOCATIONS:
+            isDefaultParameter = true;
+            break;
+        case GL_DOUBLEBUFFER:
+        case GL_IMPLEMENTATION_COLOR_READ_FORMAT:
+        case GL_IMPLEMENTATION_COLOR_READ_TYPE:
+        case GL_SAMPLES:
+        case GL_SAMPLE_BUFFERS:
+        case GL_STEREO:
+            // Queryable only; glFramebufferParameteri sets none of these.
+            if (forSetter) {
+                MG_State::pGLContext->RecordError(
+                    ErrorCode::InvalidEnum,
+                    MakeUnique<GenericErrorInfo>(
+                        "MG_Impl/GLImpl/FramebufferImpl", caller,
+                        std::format("pname {} is not settable on a framebuffer.",
+                                    MG_Util::ConvertGLEnumToString(pname))));
+                return false;
+            }
+            break;
+        default:
+            MG_State::pGLContext->RecordError(
+                ErrorCode::InvalidEnum,
+                MakeUnique<GenericErrorInfo>(
+                    "MG_Impl/GLImpl/FramebufferImpl", caller,
+                    std::format("pname {} is not a framebuffer parameter.",
+                                MG_Util::ConvertGLEnumToString(pname))));
+            return false;
+        }
+
+        // The default framebuffer has no DEFAULT_* state of its own - its shape comes from the
+        // surface - so those names are accepted enums it simply cannot answer or accept.
+        if (isDefaultFramebuffer && isDefaultParameter) {
+            MG_State::pGLContext->RecordError(
+                ErrorCode::InvalidOperation,
+                MakeUnique<GenericErrorInfo>(
+                    "MG_Impl/GLImpl/FramebufferImpl", caller,
+                    std::format("pname {} does not apply to the default framebuffer.",
+                                MG_Util::ConvertGLEnumToString(pname))));
+            return false;
+        }
+        return true;
+    }
+
+    Bool ValidateReadFramebufferForCopy(const char* caller) {
+        auto& framebufferObject =
+            MG_State::pGLContext->GetFramebufferBindingSlot(FramebufferTarget::Read).GetBoundObject();
+        if (!framebufferObject || !framebufferObject->CheckCompleteness()) {
+            MG_State::pGLContext->RecordError(
+                ErrorCode::InvalidFramebufferOperation,
+                MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl/FramebufferImpl", caller,
+                                             "Read framebuffer is not framebuffer complete."));
+            return false;
+        }
+
+        const FramebufferAttachmentType readBuffer = framebufferObject->GetReadBuffer();
+        if (readBuffer == FramebufferAttachmentType::None ||
+            !framebufferObject->GetAttachment(readBuffer).IsValid()) {
+            MG_State::pGLContext->RecordError(
+                ErrorCode::InvalidOperation,
+                MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl/FramebufferImpl", caller,
+                                             "Read buffer names no attachment of the read framebuffer."));
+            return false;
+        }
+
+        // SAMPLE_BUFFERS is one whenever the read buffer resolves to multisample storage. A
+        // multisample texture says so by its target - its sample count can legally be one - while a
+        // renderbuffer says so by having been given a non-zero sample count.
+        const auto& readAttachment = framebufferObject->GetAttachment(readBuffer);
+        Bool isMultisampled = false;
+        if (readAttachment.IsRenderbuffer() && readAttachment.GetRenderbuffer()) {
+            isMultisampled = readAttachment.GetRenderbuffer()->GetSamples() > 0;
+        } else if (readAttachment.IsTexture() && readAttachment.GetTexture()) {
+            const auto target = readAttachment.GetTexture()->GetTarget();
+            isMultisampled = target == TextureTarget::Texture2DMultisample ||
+                             target == TextureTarget::Texture2DMultisampleArray;
+        }
+        if (isMultisampled) {
+            MG_State::pGLContext->RecordError(
+                ErrorCode::InvalidOperation,
+                MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl/FramebufferImpl", caller,
+                                             "Cannot copy from a multisampled read framebuffer."));
+            return false;
+        }
+
+        return true;
+    }
 } // namespace MobileGL::MG_Impl::GLImpl::FramebufferImpl

MobileGL/MG_Impl/GLImpl/Framebuffer/Validators.h

@@ -14,6 +14,21 @@ namespace MobileGL::MG_Impl::GLImpl::FramebufferImpl {
     Bool ValidateFramebufferTarget(FramebufferTarget target);
     Bool ValidateFramebufferName(Uint index, Bool allowZero = true);
     Bool ValidateFramebufferAttachmentType(FramebufferAttachmentType attachment);
+    // GL_COLOR_ATTACHMENTn is a token per n up to 31, but only the first GL_MAX_COLOR_ATTACHMENTS of
+    // them name an attachment point of a framebuffer object; the rest are INVALID_OPERATION for the
+    // attaching entry points (GL 4.6 core 9.2.7). Non-colour attachments pass through unchanged.
+    Bool ValidateColorAttachmentInRange(FramebufferAttachmentType attachment, const char* caller);
     Bool ValidateRenderbufferTarget(RenderbufferTarget target);
     Bool ValidateRenderbufferName(Uint index, Bool allowZero = true);
+    // The read-framebuffer preconditions the CopyTexSubImage family shares (GL 4.6 core 8.6): the
+    // read framebuffer must be complete, its read buffer must name a real attachment, and it must
+    // not be multisampled. Incompleteness is INVALID_FRAMEBUFFER_OPERATION, the other two are
+    // INVALID_OPERATION.
+    Bool ValidateReadFramebufferForCopy(const char* caller);
+    // The pname sets of glGet/FramebufferParameteri (GL 4.6 core 9.2.3). Order matters and is part
+    // of the contract: a name outside the table is INVALID_ENUM, and only then is a name that the
+    // DEFAULT framebuffer does not answer INVALID_OPERATION. Testing the framebuffer kind first
+    // would turn GL_FRAMEBUFFER_DEFAULT_WIDTH on framebuffer zero into the wrong error.
+    Bool ValidateFramebufferParameterPname(GLenum pname, Bool isDefaultFramebuffer, Bool forSetter,
+                                           const char* caller);
 } // namespace MobileGL::MG_Impl::GLImpl::FramebufferImpl

MobileGL/MG_Impl/GLImpl/Getter/GL_Getter.cpp

@@ -23,6 +23,7 @@
 #include <MG_Util/Converters/MGToGL/RenderStateEnumConverter.h>
 #include <MG_State/GLState/FramebufferState/FramebufferObject.h>
 #include <MG_Util/Texture/TextureFormatProcessor.h>
+#include <MG_Util/Async/ShaderCompilePool.h>
 #include <MG_Backend/BackendObjects.h>
 
 namespace MobileGL::MG_Impl::GLImpl {
@@ -50,6 +51,14 @@ namespace MobileGL::MG_Impl::GLImpl {
         constexpr GLint kFrontendMaxTessControlAtomicCounters = 0;
         constexpr GLint kFrontendMaxTessEvaluationAtomicCounters = 0;
         constexpr GLint kFrontendMaxVertexAtomicCounters = 0;
+        // One atomic counter is a uint, and a buffer never has to hold more counters than the
+        // combined limit the frontend advertises. GL 4.6 table 23.63 floors this at 32 bytes.
+        constexpr GLint kFrontendMaxAtomicCounterBufferSize =
+            kFrontendMaxCombinedAtomicCounters * static_cast<GLint>(sizeof(GLuint));
+        // KHR_debug minima (GL 4.6 table 23.66); the debug entry points are stubs, but the
+        // limits they advertise still have to be legal.
+        constexpr GLint kFrontendMaxDebugGroupStackDepth = 64;
+        constexpr GLint kFrontendMaxDebugLoggedMessages = 1;
         constexpr GLint kFrontendMaxVertexUniformComponents = 4096;
         constexpr GLint kFrontendMaxVertexUniformVectors = 128;
         constexpr GLint kFrontendMaxVertexUniformBlocks = 14;
@@ -213,8 +222,13 @@ namespace MobileGL::MG_Impl::GLImpl {
 
             GLint maxSamples = 0;
             for (const auto& attachment : drawFbo->GetAllAttachmentObjects()) {
-                if (!attachment.IsRenderbuffer() || !attachment.GetRenderbuffer()) continue;
-                maxSamples = std::max(maxSamples, static_cast<GLint>(attachment.GetRenderbuffer()->GetSamples()));
+                if (attachment.IsRenderbuffer() && attachment.GetRenderbuffer()) {
+                    maxSamples = std::max(maxSamples, static_cast<GLint>(attachment.GetRenderbuffer()->GetSamples()));
+                } else if (attachment.IsTexture() && attachment.GetTexture()) {
+                    // Multisample texture attachments count too (GL_SAMPLE_BUFFERS must
+                    // report 1 for any multisampled draw framebuffer).
+                    maxSamples = std::max(maxSamples, static_cast<GLint>(attachment.GetTexture()->GetSamples()));
+                }
             }
             return maxSamples;
         }
@@ -258,6 +272,60 @@ namespace MobileGL::MG_Impl::GLImpl {
             return true;
         }
 
+        // GL_TEXTURE_BINDING_* is per-texture-unit state: glGetIntegerv answers for the
+        // active unit, glGetIntegeri_v answers for unit `index`. Both need the same
+        // pname -> target decode, so it lives here instead of being spelled out twice.
+        bool TryDecodeTextureUnitBindingPname(GLenum pname, TextureTarget& outTarget) {
+            switch (pname) {
+            case GL_TEXTURE_BINDING_1D: outTarget = TextureTarget::Texture1D; return true;
+            case GL_TEXTURE_BINDING_1D_ARRAY: outTarget = TextureTarget::Texture1DArray; return true;
+            case GL_TEXTURE_BINDING_2D: outTarget = TextureTarget::Texture2D; return true;
+            case GL_TEXTURE_BINDING_2D_ARRAY: outTarget = TextureTarget::Texture2DArray; return true;
+            case GL_TEXTURE_BINDING_2D_MULTISAMPLE: outTarget = TextureTarget::Texture2DMultisample; return true;
+            case GL_TEXTURE_BINDING_2D_MULTISAMPLE_ARRAY:
+                outTarget = TextureTarget::Texture2DMultisampleArray;
+                return true;
+            case GL_TEXTURE_BINDING_3D: outTarget = TextureTarget::Texture3D; return true;
+            case GL_TEXTURE_BINDING_BUFFER: outTarget = TextureTarget::TextureBuffer; return true;
+            case GL_TEXTURE_BINDING_CUBE_MAP: outTarget = TextureTarget::TextureCubeMap; return true;
+            case GL_TEXTURE_BINDING_CUBE_MAP_ARRAY: outTarget = TextureTarget::TextureCubeMapArray; return true;
+            case GL_TEXTURE_BINDING_RECTANGLE: outTarget = TextureTarget::TextureRectangle; return true;
+            default: return false;
+            }
+        }
+
+        GLint QueryTextureBindingOnUnit(Int unit, TextureTarget target) {
+            auto& textureUnit = MG_State::pGLContext->GetTextureUnitObject(unit);
+            const auto& obj = textureUnit.GetBindingSlot(target).GetBoundObject();
+            return obj ? static_cast<GLint>(obj->GetExternalIndex()) : 0;
+        }
+
+        GLint QuerySamplerBindingOnUnit(Int unit) {
+            const auto& textureUnit = MG_State::pGLContext->GetTextureUnitObject(unit);
+            const auto& sampler = textureUnit.GetSamplerObject();
+            return sampler ? static_cast<GLint>(sampler->GetExternalIndex()) : 0;
+        }
+
+        // The ARB_viewport_array indexed rectangles. MobileGL keeps exactly one viewport, one
+        // scissor box and one depth range, so every in-range index answers with that single
+        // value - but it has to come from the frontend state the non-indexed getters read.
+        // The generic path at the bottom of GetIntegeri_v is a raw backend passthrough that
+        // has no case for these, so routing them through it returned zeros.
+        Bool IsIndexedViewportQuery(GLenum target) {
+            return target == GL_VIEWPORT || target == GL_SCISSOR_BOX || target == GL_DEPTH_RANGE;
+        }
+
+        // ARB_viewport_array: `index` selects a viewport and MAX_VIEWPORTS bounds it.
+        Bool ValidateViewportQueryIndex(GLuint index, const char* caller) {
+            GLint maxViewports = 0;
+            GetIntegerv(GL_MAX_VIEWPORTS, &maxViewports);
+            if (index < static_cast<GLuint>(std::max(maxViewports, 1))) return true;
+            MG_State::pGLContext->RecordError(
+                ErrorCode::InvalidValue,
+                MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", caller, "Viewport index is out of range."));
+            return false;
+        }
+
         void CopyIntsToBooleans(const GLint* src, SizeT count, GLboolean* dst) {
             for (SizeT i = 0; i < count; ++i) {
                 dst[i] = src[i] ? GL_TRUE : GL_FALSE;
@@ -465,6 +533,14 @@ namespace MobileGL::MG_Impl::GLImpl {
         case GL_STENCIL_TEST:
             *params = MG_State::pGLContext->IsCapabilityEnabled(CapabilityInput::StencilTest) ? GL_TRUE : GL_FALSE;
             return;
+        case GL_MIN_FRAGMENT_INTERPOLATION_OFFSET:
+        case GL_MAX_FRAGMENT_INTERPOLATION_OFFSET:
+        case GL_FRAGMENT_INTERPOLATION_OFFSET_BITS: {
+            GLfloat value = 0.0f;
+            GetFloatv(pname, &value);
+            *params = value != 0.0f ? GL_TRUE : GL_FALSE;
+            return;
+        }
         default:
             break;
         }
@@ -520,6 +596,19 @@ namespace MobileGL::MG_Impl::GLImpl {
             params[1] = dynamicParameters.ViewportBoundsRangeMax;
             return;
         }
+        case GL_MIN_FRAGMENT_INTERPOLATION_OFFSET:
+        case GL_MAX_FRAGMENT_INTERPOLATION_OFFSET:
+        case GL_FRAGMENT_INTERPOLATION_OFFSET_BITS: {
+            const auto& dynamicParameters = MG_Backend::pActiveBackendObject->GetDynamicParameters();
+            if (pname == GL_MIN_FRAGMENT_INTERPOLATION_OFFSET) {
+                params[0] = dynamicParameters.MinFragmentInterpolationOffset;
+            } else if (pname == GL_MAX_FRAGMENT_INTERPOLATION_OFFSET) {
+                params[0] = dynamicParameters.MaxFragmentInterpolationOffset;
+            } else {
+                params[0] = static_cast<GLfloat>(dynamicParameters.FragmentInterpolationOffsetBits);
+            }
+            return;
+        }
         case GL_DEPTH_CLEAR_VALUE:
             params[0] = MG_State::pGLContext->GetClearDepth();
             return;
@@ -529,6 +618,13 @@ namespace MobileGL::MG_Impl::GLImpl {
             params[1] = dynamicParameters.AliasedLineWidthRangeMax;
             return;
         }
+        case GL_MAX_TEXTURE_MAX_ANISOTROPY_EXT: {
+            // EXT_texture_filter_anisotropic queries this as a float; the integer path below widens
+            // from here, so this case is the authoritative one.
+            const auto& dynamicParameters = MG_Backend::pActiveBackendObject->GetDynamicParameters();
+            params[0] = dynamicParameters.MaxTextureMaxAnisotropy;
+            return;
+        }
         case GL_ALIASED_POINT_SIZE_RANGE:
         case GL_POINT_SIZE_RANGE: {
             const auto& dynamicParameters = MG_Backend::pActiveBackendObject->GetDynamicParameters();
@@ -637,7 +733,71 @@ namespace MobileGL::MG_Impl::GLImpl {
             }
         }
 
+        // Per-texture-unit bindings: GL 4.6 core table 23.19 makes every GL_TEXTURE_BINDING_*
+        // and GL_SAMPLER_BINDING indexed by texture unit. Without this they fell through to
+        // the raw backend passthrough at the bottom, which knows nothing about the
+        // frontend's binding state.
+        if (TextureTarget textureBindingTarget = TextureTarget::Unknown;
+            TryDecodeTextureUnitBindingPname(target, textureBindingTarget) || target == GL_SAMPLER_BINDING) {
+            GLint maxUnits = 0;
+            GetIntegerv(GL_MAX_COMBINED_TEXTURE_IMAGE_UNITS, &maxUnits);
+            maxUnits = std::min<GLint>(maxUnits, MG_State::GLState::TextureState::MAX_TEXTURE_IMAGE_UNITS);
+            if (index >= static_cast<GLuint>(std::max(maxUnits, 0))) {
+                *data = 0;
+                MG_State::pGLContext->RecordError(
+                    ErrorCode::InvalidValue,
+                    MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", __func__, "Texture unit index is out of range."));
+                return;
+            }
+            *data = target == GL_SAMPLER_BINDING
+                ? QuerySamplerBindingOnUnit(static_cast<Int>(index))
+                : QueryTextureBindingOnUnit(static_cast<Int>(index), textureBindingTarget);
+            return;
+        }
+
         switch (target) {
+        // ARB_viewport_array queries the indexed rectangles through glGetIntegeri_v as well
+        // (gl4cMultiBindTests and the viewport_array group both do). The frontend keeps one
+        // viewport and one scissor box, so every in-range index reports that one.
+        case GL_VIEWPORT:
+        case GL_SCISSOR_BOX:
+            if (!ValidateViewportQueryIndex(index, __func__)) return;
+            GetIntegerv(target, data);
+            return;
+        // The vertex buffer binding points of the vertex array object that is bound. Indexed by
+        // binding point, not by attribute (GL 4.6 core 10.3.1).
+        case GL_VERTEX_BINDING_BUFFER:
+        case GL_VERTEX_BINDING_DIVISOR:
+        case GL_VERTEX_BINDING_OFFSET:
+        case GL_VERTEX_BINDING_STRIDE: {
+            if (index >= VertexArrayImpl::GetMaxVertexAttribBindings()) {
+                MG_State::pGLContext->RecordError(
+                    ErrorCode::InvalidValue,
+                    MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", __func__,
+                                                 "Vertex buffer binding index is out of range."));
+                return;
+            }
+            const auto& vao = MG_State::pGLContext->GetBoundVertexArray();
+            if (!vao) {
+                *data = 0;
+                return;
+            }
+            const auto& binding = vao->GetBindingPoint(index);
+            switch (target) {
+            case GL_VERTEX_BINDING_BUFFER:
+                *data = binding.Buffer ? static_cast<GLint>(binding.Buffer->GetExternalIndex()) : 0;
+                return;
+            case GL_VERTEX_BINDING_DIVISOR:
+                *data = static_cast<GLint>(binding.Divisor);
+                return;
+            case GL_VERTEX_BINDING_OFFSET:
+                *data = static_cast<GLint>(binding.Offset);
+                return;
+            default:
+                *data = static_cast<GLint>(binding.Stride);
+                return;
+            }
+        }
         case GL_IMAGE_BINDING_NAME:
         case GL_IMAGE_BINDING_LEVEL:
         case GL_IMAGE_BINDING_LAYERED:
@@ -715,6 +875,46 @@ namespace MobileGL::MG_Impl::GLImpl {
         getIntegeri(target, index, data);
     }
 
+    // GL_ARB_viewport_array's typed indexed getters. They were no-op stubs, which left the
+    // caller's output buffer holding whatever was on the stack. The multi-component indexed
+    // rectangles are answered from the frontend's own viewport/scissor/depth-range state, via
+    // the non-indexed getter of the matching type - GL_DEPTH_RANGE is float state, so putting
+    // it through the integer query would round it to 0/1. Everything else MobileGL answers
+    // indexed is scalar integer-domain state, where converting the integer query is exact.
+    void GetFloati_v(GLenum target, GLuint index, GLfloat* data) {
+        if (!data) {
+            MG_State::pGLContext->RecordError(
+                ErrorCode::InvalidValue,
+                MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", __func__, "data pointer cannot be null"));
+            return;
+        }
+        if (IsIndexedViewportQuery(target)) {
+            if (!ValidateViewportQueryIndex(index, __func__)) return;
+            GetFloatv(target, data);
+            return;
+        }
+        GLint ints[4] = {};
+        GetIntegeri_v(target, index, ints);
+        data[0] = static_cast<GLfloat>(ints[0]);
+    }
+
+    void GetDoublei_v(GLenum target, GLuint index, GLdouble* data) {
+        if (!data) {
+            MG_State::pGLContext->RecordError(
+                ErrorCode::InvalidValue,
+                MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", __func__, "data pointer cannot be null"));
+            return;
+        }
+        if (IsIndexedViewportQuery(target)) {
+            if (!ValidateViewportQueryIndex(index, __func__)) return;
+            GetDoublev(target, data);
+            return;
+        }
+        GLint ints[4] = {};
+        GetIntegeri_v(target, index, ints);
+        data[0] = static_cast<GLdouble>(ints[0]);
+    }
+
     void GetInteger64i_v(GLenum target, GLuint index, GLint64* data) {
         if (!data) {
             MG_State::pGLContext->RecordError(
@@ -891,6 +1091,13 @@ namespace MobileGL::MG_Impl::GLImpl {
             return;
         }
 
+        // Per-texture-unit bindings: the non-indexed query reports the active unit.
+        if (TextureTarget textureBindingTarget = TextureTarget::Unknown;
+            TryDecodeTextureUnitBindingPname(pname, textureBindingTarget)) {
+            *params = QueryTextureBindingOnUnit(MG_State::pGLContext->GetActiveTextureUnit(), textureBindingTarget);
+            return;
+        }
+
         switch (pname) {
         case GL_ACTIVE_TEXTURE:
             *params = MG_State::pGLContext->GetActiveTextureUnit() + GL_TEXTURE0;
@@ -997,12 +1204,37 @@ namespace MobileGL::MG_Impl::GLImpl {
             *params = obj ? static_cast<GLint>(obj->GetExternalIndex()) : 0;
             return;
         }
+        case GL_DRAW_INDIRECT_BUFFER_BINDING: {
+            auto& obj = MG_State::pGLContext->GetBufferBindingSlot(BufferTarget::DrawIndirect).GetBoundObject();
+            *params = obj ? static_cast<GLint>(obj->GetExternalIndex()) : 0;
+            return;
+        }
+        case GL_MAX_SHADER_COMPILER_THREADS_KHR:
+            // GL_KHR_parallel_shader_compile (GL_MAX_SHADER_COMPILER_THREADS_ARB is the same
+            // 0x91B0). The number of threads MobileGL's compile pool would actually use, so
+            // an application sizing its own submission batches gets a real answer.
+            //
+            // Zero when asynchronous compilation is off, which is the honest reply and the
+            // one the extension defines for an implementation with no compiler threads: the
+            // extension string is withdrawn in that configuration too, so a conforming
+            // application never reaches this query, and one that asks anyway is told there
+            // are none rather than being handed a thread count nothing will use.
+            *params = MG_Util::Async::AsyncShaderCompileEnabled()
+                          ? static_cast<GLint>(MG_Util::Async::ShaderCompilePool::Get().GetThreadCount())
+                          : 0;
+            return;
         case GL_MAX_DEBUG_GROUP_STACK_DEPTH:
-            *params = 0; // debug-group entrypoints are stubbed
+            // KHR_debug floors this at 64 even when the group entry points are stubs: the
+            // limit describes how deep glPushDebugGroup may nest, and 0 is not a legal answer.
+            *params = kFrontendMaxDebugGroupStackDepth;
             return;
         case GL_MAX_DEBUG_MESSAGE_LENGTH:
             *params = 1024; // debug-message entrypoints are stubbed, but KHR_debug requires a valid limit
             return;
+        case GL_MAX_DEBUG_LOGGED_MESSAGES:
+            // Size of the message log ring; KHR_debug requires at least 1.
+            *params = kFrontendMaxDebugLoggedMessages;
+            return;
         case GL_DEBUG_GROUP_STACK_DEPTH:
             *params = 0; // debug-group entrypoints are stubbed
             return;
@@ -1168,10 +1400,9 @@ namespace MobileGL::MG_Impl::GLImpl {
             *params = kFrontendMaxFragmentInputComponents;
             return;
         case GL_MAX_FRAGMENT_IMAGE_UNIFORMS:
-            // TODO: Track per-stage image uniform limits separately instead of reusing the compute/backend stage cap.
             *params = MG_Backend::pActiveBackendObject
-                          ? MG_Backend::pActiveBackendObject->GetDynamicParameters().MaxComputeImageUniforms
-                          : MG_Backend::DynamicBackendParameters{}.MaxComputeImageUniforms;
+                          ? MG_Backend::pActiveBackendObject->GetDynamicParameters().MaxFragmentImageUniforms
+                          : MG_Backend::DynamicBackendParameters{}.MaxFragmentImageUniforms;
             return;
         case GL_MAX_FRAGMENT_UNIFORM_COMPONENTS:
             *params = kFrontendMaxFragmentUniformComponents;
@@ -1201,7 +1432,9 @@ namespace MobileGL::MG_Impl::GLImpl {
             *params = kFrontendMaxGeometryTextureImageUnits;
             return;
         case GL_MAX_GEOMETRY_IMAGE_UNIFORMS:
-            *params = 0;
+            *params = MG_Backend::pActiveBackendObject
+                          ? MG_Backend::pActiveBackendObject->GetDynamicParameters().MaxGeometryImageUniforms
+                          : MG_Backend::DynamicBackendParameters{}.MaxGeometryImageUniforms;
             return;
         case GL_MAX_GEOMETRY_TOTAL_OUTPUT_COMPONENTS:
             *params = kFrontendMaxGeometryTotalOutputComponents;
@@ -1270,7 +1503,9 @@ namespace MobileGL::MG_Impl::GLImpl {
             *params = kFrontendMaxVertexAtomicCounters;
             return;
         case GL_MAX_VERTEX_IMAGE_UNIFORMS:
-            *params = 0;
+            *params = MG_Backend::pActiveBackendObject
+                          ? MG_Backend::pActiveBackendObject->GetDynamicParameters().MaxVertexImageUniforms
+                          : MG_Backend::DynamicBackendParameters{}.MaxVertexImageUniforms;
             return;
         case GL_MAX_VERTEX_SHADER_STORAGE_BLOCKS:
             *params = 16; // TODO
@@ -1357,7 +1592,7 @@ namespace MobileGL::MG_Impl::GLImpl {
             *params = 0; // program-binary entrypoints are stubbed
             return;
         case GL_PROGRAM_PIPELINE_BINDING:
-            *params = 0; // program-pipeline entrypoints are stubbed
+            *params = static_cast<GLint>(MG_State::pGLContext->GetBoundProgramPipelineName());
             return;
         case GL_PROGRAM_POINT_SIZE:
             *params = MG_State::pGLContext->IsCapabilityEnabled(CapabilityInput::ProgramPointSize) ? GL_TRUE : GL_FALSE;
@@ -1441,13 +1676,9 @@ namespace MobileGL::MG_Impl::GLImpl {
         case GL_SAMPLE_MASK_VALUE:
             *params = static_cast<GLint>(MG_State::pGLContext->GetSampleMaskValue());
             return;
-        case GL_SAMPLER_BINDING: {
-            Int unit = MG_State::pGLContext->GetActiveTextureUnit();
-            const auto& tu = MG_State::pGLContext->GetTextureUnitObject(unit);
-            const auto& sampler = tu.GetSamplerObject();
-            *params = sampler ? static_cast<GLint>(sampler->GetExternalIndex()) : 0;
+        case GL_SAMPLER_BINDING:
+            *params = QuerySamplerBindingOnUnit(MG_State::pGLContext->GetActiveTextureUnit());
             return;
-        }
         case GL_SAMPLES:
             *params = ResolveDrawFramebufferSampleCount();
             return;
@@ -1543,92 +1774,11 @@ namespace MobileGL::MG_Impl::GLImpl {
         case GL_STEREO:
             *params = 0; // stereo surfaces are not exposed
             return;
-        case GL_TEXTURE_BINDING_1D: {
-            Int unit = MG_State::pGLContext->GetActiveTextureUnit();
-            auto& tu = MG_State::pGLContext->GetTextureUnitObject(unit);
-            const auto& slot = tu.GetBindingSlot(TextureTarget::Texture1D);
-            const auto& obj = slot.GetBoundObject();
-            *params = obj ? static_cast<GLint>(obj->GetExternalIndex()) : 0;
-            return;
-        }
-        case GL_TEXTURE_BINDING_1D_ARRAY: {
-            Int unit = MG_State::pGLContext->GetActiveTextureUnit();
-            auto& tu = MG_State::pGLContext->GetTextureUnitObject(unit);
-            const auto& slot = tu.GetBindingSlot(TextureTarget::Texture1DArray);
-            const auto& obj = slot.GetBoundObject();
-            *params = obj ? static_cast<GLint>(obj->GetExternalIndex()) : 0;
-            return;
-        }
-        case GL_TEXTURE_BINDING_2D: {
-            Int unit = MG_State::pGLContext->GetActiveTextureUnit();
-            auto& tu = MG_State::pGLContext->GetTextureUnitObject(unit);
-            const auto& slot = tu.GetBindingSlot(TextureTarget::Texture2D);
-            const auto& obj = slot.GetBoundObject();
-            *params = obj ? static_cast<GLint>(obj->GetExternalIndex()) : 0;
-            MGLOG_D("Get GL_TEXTURE_BINDING_2D: %d", *params);
-            return;
-        }
-        case GL_TEXTURE_BINDING_2D_ARRAY: {
-            Int unit = MG_State::pGLContext->GetActiveTextureUnit();
-            auto& tu = MG_State::pGLContext->GetTextureUnitObject(unit);
-            const auto& slot = tu.GetBindingSlot(TextureTarget::Texture2DArray);
-            const auto& obj = slot.GetBoundObject();
-            *params = obj ? static_cast<GLint>(obj->GetExternalIndex()) : 0;
-            return;
-        }
-        case GL_TEXTURE_BINDING_2D_MULTISAMPLE: {
-            Int unit = MG_State::pGLContext->GetActiveTextureUnit();
-            auto& tu = MG_State::pGLContext->GetTextureUnitObject(unit);
-            const auto& slot = tu.GetBindingSlot(TextureTarget::Texture2DMultisample);
-            const auto& obj = slot.GetBoundObject();
-            *params = obj ? static_cast<GLint>(obj->GetExternalIndex()) : 0;
-            return;
-        }
-        case GL_TEXTURE_BINDING_2D_MULTISAMPLE_ARRAY: {
-            Int unit = MG_State::pGLContext->GetActiveTextureUnit();
-            auto& tu = MG_State::pGLContext->GetTextureUnitObject(unit);
-            const auto& slot = tu.GetBindingSlot(TextureTarget::Texture2DMultisampleArray);
-            const auto& obj = slot.GetBoundObject();
-            *params = obj ? static_cast<GLint>(obj->GetExternalIndex()) : 0;
-            return;
-        }
-        case GL_TEXTURE_BINDING_3D: {
-            Int unit = MG_State::pGLContext->GetActiveTextureUnit();
-            auto& tu = MG_State::pGLContext->GetTextureUnitObject(unit);
-            const auto& slot = tu.GetBindingSlot(TextureTarget::Texture3D);
-            const auto& obj = slot.GetBoundObject();
-            *params = obj ? static_cast<GLint>(obj->GetExternalIndex()) : 0;
-            return;
-        }
-        case GL_TEXTURE_BINDING_BUFFER: {
-            Int unit = MG_State::pGLContext->GetActiveTextureUnit();
-            auto& tu = MG_State::pGLContext->GetTextureUnitObject(unit);
-            const auto& slot = tu.GetBindingSlot(TextureTarget::TextureBuffer);
-            const auto& obj = slot.GetBoundObject();
-            *params = obj ? static_cast<GLint>(obj->GetExternalIndex()) : 0;
-            return;
-        }
-        case GL_TEXTURE_BINDING_CUBE_MAP: {
-            Int unit = MG_State::pGLContext->GetActiveTextureUnit();
-            auto& tu = MG_State::pGLContext->GetTextureUnitObject(unit);
-            const auto& slot = tu.GetBindingSlot(TextureTarget::TextureCubeMap);
-            const auto& obj = slot.GetBoundObject();
-            *params = obj ? static_cast<GLint>(obj->GetExternalIndex()) : 0;
-            return;
-        }
-        case GL_TEXTURE_BINDING_RECTANGLE: {
-            Int unit = MG_State::pGLContext->GetActiveTextureUnit();
-            auto& tu = MG_State::pGLContext->GetTextureUnitObject(unit);
-            const auto& slot = tu.GetBindingSlot(TextureTarget::TextureRectangle);
-            const auto& obj = slot.GetBoundObject();
-            *params = obj ? static_cast<GLint>(obj->GetExternalIndex()) : 0;
-            return;
-        }
         case GL_TEXTURE_COMPRESSION_HINT:
             *params = static_cast<GLint>(MG_State::pGLContext->GetHint(pname));
             return;
         case GL_TEXTURE_BUFFER_OFFSET_ALIGNMENT:
-            *params = 0; // texture-buffer range entrypoints are stubbed
+            *params = MG_Backend::pActiveBackendObject->GetDynamicParameters().TextureBufferOffsetAlignment;
             return;
         case GL_TIMESTAMP: {
             Int64 timestamp = 0;
@@ -1697,20 +1847,22 @@ namespace MobileGL::MG_Impl::GLImpl {
             *params = vao ? static_cast<GLint>(vao->GetExternalIndex()) : 0;
             return;
         }
+        // The vertex buffer binding points are per-binding-index state, so the non-indexed getter
+        // has nothing to answer with (GL 4.6 core table 23.4).
+        case GL_VERTEX_BINDING_BUFFER:
         case GL_VERTEX_BINDING_DIVISOR:
-            *params = 0; // vertex-binding entrypoints are stubbed
-            return;
         case GL_VERTEX_BINDING_OFFSET:
-            *params = 0; // vertex-binding entrypoints are stubbed
-            return;
         case GL_VERTEX_BINDING_STRIDE:
-            *params = 0; // vertex-binding entrypoints are stubbed
+            RecordIndexedOnlyGetterError(__func__, pname);
             return;
         case GL_MAX_VERTEX_ATTRIB_RELATIVE_OFFSET:
-            *params = 0; // vertex-binding entrypoints are stubbed
+            *params = static_cast<GLint>(VertexArrayImpl::GetMaxVertexAttribRelativeOffset());
             return;
         case GL_MAX_VERTEX_ATTRIB_BINDINGS:
-            *params = 0; // vertex-binding entrypoints are stubbed
+            *params = static_cast<GLint>(VertexArrayImpl::GetMaxVertexAttribBindings());
+            return;
+        case GL_MAX_VERTEX_ATTRIB_STRIDE:
+            *params = static_cast<GLint>(VertexArrayImpl::GetMaxVertexAttribStride());
             return;
         case GL_VIEWPORT: {
             const auto& vp = MG_State::pGLContext->GetViewport();
@@ -1727,7 +1879,11 @@ namespace MobileGL::MG_Impl::GLImpl {
             *params = 1024 * 1024; // TODO
             return;
         case GL_CONTEXT_PROFILE_MASK:
-            *params = GL_CONTEXT_CORE_PROFILE_BIT;
+            // Reports the requested context profile (EGL defaults 3.x contexts to core);
+            // MOBILEGL_RELAXED_SEMANTICS loosens behavior without changing the identity.
+            *params = MG_State::pEGLContext && MG_State::pEGLContext->IsCurrentContextOpenGLCompatibilityProfile()
+                          ? GL_CONTEXT_COMPATIBILITY_PROFILE_BIT
+                          : GL_CONTEXT_CORE_PROFILE_BIT;
             return;
         default:
             break;
@@ -1872,9 +2028,36 @@ namespace MobileGL::MG_Impl::GLImpl {
         case GL_MAX_SAMPLE_MASK_WORDS:
             *params = dynamicParameters.MaxSampleMaskWords;
             break;
+        case GL_PATCH_VERTICES:
+            *params = static_cast<GLint>(MG_State::pGLContext->GetPatchVertices());
+            break;
+        case GL_MAX_PATCH_VERTICES:
+            *params = dynamicParameters.MaxPatchVertices;
+            break;
+        case GL_MAX_TESS_GEN_LEVEL:
+            *params = dynamicParameters.MaxTessGenLevel;
+            break;
+        case GL_MIN_PROGRAM_TEXTURE_GATHER_OFFSET:
+            *params = dynamicParameters.MinProgramTextureGatherOffset;
+            break;
+        case GL_MAX_PROGRAM_TEXTURE_GATHER_OFFSET:
+            *params = dynamicParameters.MaxProgramTextureGatherOffset;
+            break;
         case GL_MAX_SHADER_STORAGE_BUFFER_BINDINGS:
             *params = static_cast<GLint>(GetIndexedBufferQueryPointCount(BufferTarget::ShaderStorage));
             break;
+        case GL_MAX_SHADER_STORAGE_BLOCK_SIZE:
+            // 64-bit state (see GetInteger64v); the 32-bit query saturates, per the GL
+            // state-query conversion rules.
+            *params = static_cast<GLint>(std::min<Uint64>(dynamicParameters.MaxShaderStorageBlockSize,
+                                                          static_cast<Uint64>(INT32_MAX)));
+            break;
+        case GL_MAX_ATOMIC_COUNTER_BUFFER_BINDINGS:
+            *params = static_cast<GLint>(GetIndexedBufferQueryPointCount(BufferTarget::AtomicCounter));
+            break;
+        case GL_MAX_ATOMIC_COUNTER_BUFFER_SIZE:
+            *params = kFrontendMaxAtomicCounterBufferSize;
+            break;
         case GL_MAX_TEXTURE_BUFFER_SIZE:
             *params = dynamicParameters.MaxTextureBufferSize;
             break;
@@ -1887,6 +2070,25 @@ namespace MobileGL::MG_Impl::GLImpl {
         case GL_MAX_TRANSFORM_FEEDBACK_SEPARATE_COMPONENTS:
             *params = kFrontendMaxTransformFeedbackSeparateComponents;
             break;
+        // ARB_transform_feedback3 limits. The GL CTS queries these before checking
+        // whether the extension is advertised and requires no GL error; desktop
+        // drivers all accept them, so answer with the separate-attrib capacity and
+        // the single vertex stream the backends provide.
+        case GL_MAX_TRANSFORM_FEEDBACK_BUFFERS:
+            *params = kFrontendMaxTransformFeedbackSeparateAttribs;
+            break;
+        case GL_MAX_VERTEX_STREAMS:
+            *params = 1;
+            break;
+        case GL_TRANSFORM_FEEDBACK_ACTIVE:
+            *params = MG_State::pGLContext->IsTransformFeedbackActive() ? 1 : 0;
+            break;
+        case GL_TRANSFORM_FEEDBACK_PAUSED:
+            *params = MG_State::pGLContext->IsTransformFeedbackPaused() ? 1 : 0;
+            break;
+        case GL_TRANSFORM_FEEDBACK_BINDING:
+            *params = static_cast<GLint>(MG_State::pGLContext->GetBoundTransformFeedbackName());
+            break;
         case GL_MAX_TEXTURE_IMAGE_UNITS:
             *params = dynamicParameters.MaxTextureImageUnits;
             break;
@@ -1894,7 +2096,13 @@ namespace MobileGL::MG_Impl::GLImpl {
             *params = dynamicParameters.MaxTextureSize;
             break;
         case GL_MAX_UNIFORM_BUFFER_BINDINGS:
-            *params = std::max(dynamicParameters.MaxUniformBufferBindings, kFrontendMinUniformBufferBindings);
+            // Never advertise more bindings than the state layer's indexed-binding array can track
+            // (BufferState::BufferBindingPointCount): glBindBufferBase rejects indices past that
+            // capacity, and the GL CTS per-case state reset calls glBindBufferBase on every
+            // advertised index and expects no error. The floor equals the GL 3.3 core minimum
+            // (36), so the clamp never under-advertises.
+            *params = std::clamp(dynamicParameters.MaxUniformBufferBindings, kFrontendMinUniformBufferBindings,
+                                 static_cast<GLint>(MG_State::GLState::BufferBindingPointCount));
             break;
         case GL_MAX_UNIFORM_BLOCK_SIZE:
             *params = dynamicParameters.MaxUniformBlockSize;
@@ -1937,6 +2145,15 @@ namespace MobileGL::MG_Impl::GLImpl {
         case GL_SUBPIXEL_BITS:
             *params = std::max(dynamicParameters.ViewportSubpixelBits, kFrontendSubpixelBits);
             break;
+        case GL_MIN_FRAGMENT_INTERPOLATION_OFFSET:
+            *params = static_cast<GLint>(std::lround(dynamicParameters.MinFragmentInterpolationOffset));
+            break;
+        case GL_MAX_FRAGMENT_INTERPOLATION_OFFSET:
+            *params = static_cast<GLint>(std::lround(dynamicParameters.MaxFragmentInterpolationOffset));
+            break;
+        case GL_FRAGMENT_INTERPOLATION_OFFSET_BITS:
+            *params = dynamicParameters.FragmentInterpolationOffsetBits;
+            break;
         case GL_UNIFORM_BUFFER_OFFSET_ALIGNMENT:
             *params = static_cast<Int>(dynamicParameters.UniformBufferOffsetAlignment);
             break;
@@ -1955,6 +2172,10 @@ namespace MobileGL::MG_Impl::GLImpl {
         case GL_MAX_SAMPLES:
             *params = std::max(dynamicParameters.MaxSamples, kFrontendMaxSamples);
             break;
+        case GL_MAX_TEXTURE_MAX_ANISOTROPY_EXT:
+            // Float state (see GetFloatv); rounded to nearest for the integer query per GL 3.3 6.1.2.
+            *params = static_cast<GLint>(std::lround(dynamicParameters.MaxTextureMaxAnisotropy));
+            break;
         default:
             MGLOG_E("glGetIntegerv: Invalid enum %s (0x%X)", MG_Util::ConvertGLEnumToString(pname).c_str(), pname);
             MG_State::pGLContext->RecordError(ErrorCode::InvalidEnum,
@@ -1972,4 +2193,12 @@ namespace MobileGL::MG_Impl::GLImpl {
         }
         return MG_Util::ConvertErrorCodeToGLEnum(error->get()->code);
     }
+
+    GLenum GetGraphicsResetStatus() {
+        // MobileGL does not implement robustness reset notification, so report GL_NO_ERROR
+        // ("no reset detected"). Returning the generic stub's (GLenum)1 makes dEQP read a lost
+        // device after every case (gl3cTestPackages.cpp:121) and, under the default
+        // --deqp-terminate-on-device-lost=enable, tear the whole CTS run down.
+        return GL_NO_ERROR;
+    }
 } // namespace MobileGL::MG_Impl::GLImpl

MobileGL/MG_Impl/GLImpl/Getter/GL_Getter.h

@@ -19,6 +19,9 @@ namespace MobileGL::MG_Impl::GLImpl {
     void GetIntegerv(GLenum pname, GLint* params);
     void GetInteger64v(GLenum pname, GLint64* params);
     void GetIntegeri_v(GLenum target, GLuint index, GLint* data);
+    void GetFloati_v(GLenum target, GLuint index, GLfloat* data);
+    void GetDoublei_v(GLenum target, GLuint index, GLdouble* data);
     void GetInteger64i_v(GLenum target, GLuint index, GLint64* data);
     GLenum GetError();
+    GLenum GetGraphicsResetStatus();
 } // namespace MobileGL::MG_Impl::GLImpl

MobileGL/MG_Impl/GLImpl/Program/GL_Program.h

@@ -42,6 +42,10 @@ namespace MobileGL::MG_Impl::GLImpl {
     GLboolean IsProgram(GLuint program);
     GLboolean IsShader(GLuint shader);
     void LinkProgram(GLuint program);
+    // GL_KHR_parallel_shader_compile / GL_ARB_parallel_shader_compile. Both names are the
+    // same entry point; see MaxShaderCompilerThreadsKHR_State for the semantics of count.
+    void MaxShaderCompilerThreadsKHR(GLuint count);
+    void MaxShaderCompilerThreadsARB(GLuint count);
     void ShaderSource(GLuint shader, GLsizei count, const GLchar* const* string, const GLint* length);
     void UseProgram(GLuint program);
     void Uniform1f(GLint location, GLfloat v0);
@@ -137,5 +141,47 @@ namespace MobileGL::MG_Impl::GLImpl {
     GLint GetProgramResourceLocation(GLuint program, GLenum programInterface, const GLchar* name);
     GLint GetProgramResourceLocationIndex(GLuint program, GLenum programInterface, const GLchar* name);
     void ShaderStorageBlockBinding(GLuint program, GLuint storageBlockIndex, GLuint storageBlockBinding);
+    void Uniform1d(GLint location, GLdouble v0);
+    void Uniform1dv(GLint location, GLsizei count, const GLdouble* value);
+    void ProgramUniform1d(GLuint program, GLint location, GLdouble v0);
+    void ProgramUniform1dv(GLuint program, GLint location, GLsizei count, const GLdouble* value);
+    void Uniform2d(GLint location, GLdouble v0, GLdouble v1);
+    void Uniform2dv(GLint location, GLsizei count, const GLdouble* value);
+    void ProgramUniform2d(GLuint program, GLint location, GLdouble v0, GLdouble v1);
+    void ProgramUniform2dv(GLuint program, GLint location, GLsizei count, const GLdouble* value);
+    void Uniform3d(GLint location, GLdouble v0, GLdouble v1, GLdouble v2);
+    void Uniform3dv(GLint location, GLsizei count, const GLdouble* value);
+    void ProgramUniform3d(GLuint program, GLint location, GLdouble v0, GLdouble v1, GLdouble v2);
+    void ProgramUniform3dv(GLuint program, GLint location, GLsizei count, const GLdouble* value);
+    void Uniform4d(GLint location, GLdouble v0, GLdouble v1, GLdouble v2, GLdouble v3);
+    void Uniform4dv(GLint location, GLsizei count, const GLdouble* value);
+    void ProgramUniform4d(GLuint program, GLint location, GLdouble v0, GLdouble v1, GLdouble v2, GLdouble v3);
+    void ProgramUniform4dv(GLuint program, GLint location, GLsizei count, const GLdouble* value);
+    void UniformMatrix2dv(GLint location, GLsizei count, GLboolean transpose, const GLdouble* value);
+    void ProgramUniformMatrix2dv(GLuint program, GLint location, GLsizei count, GLboolean transpose, const GLdouble* value);
+    void UniformMatrix3dv(GLint location, GLsizei count, GLboolean transpose, const GLdouble* value);
+    void ProgramUniformMatrix3dv(GLuint program, GLint location, GLsizei count, GLboolean transpose, const GLdouble* value);
+    void UniformMatrix4dv(GLint location, GLsizei count, GLboolean transpose, const GLdouble* value);
+    void ProgramUniformMatrix4dv(GLuint program, GLint location, GLsizei count, GLboolean transpose, const GLdouble* value);
+    void UniformMatrix2x3dv(GLint location, GLsizei count, GLboolean transpose, const GLdouble* value);
+    void ProgramUniformMatrix2x3dv(GLuint program, GLint location, GLsizei count, GLboolean transpose, const GLdouble* value);
+    void UniformMatrix2x4dv(GLint location, GLsizei count, GLboolean transpose, const GLdouble* value);
+    void ProgramUniformMatrix2x4dv(GLuint program, GLint location, GLsizei count, GLboolean transpose, const GLdouble* value);
+    void UniformMatrix3x2dv(GLint location, GLsizei count, GLboolean transpose, const GLdouble* value);
+    void ProgramUniformMatrix3x2dv(GLuint program, GLint location, GLsizei count, GLboolean transpose, const GLdouble* value);
+    void UniformMatrix3x4dv(GLint location, GLsizei count, GLboolean transpose, const GLdouble* value);
+    void ProgramUniformMatrix3x4dv(GLuint program, GLint location, GLsizei count, GLboolean transpose, const GLdouble* value);
+    void UniformMatrix4x2dv(GLint location, GLsizei count, GLboolean transpose, const GLdouble* value);
+    void ProgramUniformMatrix4x2dv(GLuint program, GLint location, GLsizei count, GLboolean transpose, const GLdouble* value);
+    void UniformMatrix4x3dv(GLint location, GLsizei count, GLboolean transpose, const GLdouble* value);
+    void ProgramUniformMatrix4x3dv(GLuint program, GLint location, GLsizei count, GLboolean transpose, const GLdouble* value);
+    void GetUniformdv(GLuint program, GLint location, GLdouble* params);
     void ValidateProgram(GLuint program);
+    void ProgramParameteri(GLuint program, GLenum pname, GLint value);
+    GLuint CreateShaderProgramv(GLenum type, GLsizei count, const GLchar* const* strings);
+    void GetProgramBinary(GLuint program, GLsizei bufSize, GLsizei* length, GLenum* binaryFormat, void* binary);
+    void ProgramBinary(GLuint program, GLenum binaryFormat, const void* binary, GLsizei length);
+    void TransformFeedbackVaryings(GLuint program, GLsizei count, const GLchar* const* varyings, GLenum bufferMode);
+    void GetTransformFeedbackVarying(GLuint program, GLuint index, GLsizei bufSize, GLsizei* length, GLsizei* size,
+                                     GLenum* type, GLchar* name);
 } // namespace MobileGL::MG_Impl::GLImpl

MobileGL/MG_Impl/GLImpl/Program/GL_ProgramPipeline.cpp

@@ -0,0 +1,231 @@
+// MobileGL - MobileGL/MG_Impl/GLImpl/Program/GL_ProgramPipeline.cpp
+// Copyright (c) 2025-2026 MobileGL-Dev
+// Licensed under the GNU Lesser General Public License v3.0:
+//   https://www.gnu.org/licenses/gpl-3.0.txt
+//   https://www.gnu.org/licenses/lgpl-3.0.txt
+// SPDX-License-Identifier: LGPL-3.0-only
+// End of Source File Header
+
+#include "GL_ProgramPipeline.h"
+
+#include <MG_State/GLState/Core.h>
+#include <MG_State/GLState/ErrorState/ErrorInfo.h>
+#include <MG_Util/Converters/GLToStr/GLEnumConverter.h>
+
+namespace MobileGL::MG_Impl::GLImpl {
+    namespace {
+        void RecordPipelineError(ErrorCode code, const char* function, String message) {
+            MG_State::pGLContext->RecordError(
+                code, MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", function, Move(message)));
+        }
+
+        // A pipeline name only names an object once it has been bound or created; querying a
+        // reserved-but-unmaterialised name is INVALID_OPERATION (GL 4.6 core 7.4).
+        const SharedPtr<MG_State::GLState::ProgramPipelineObject>* TryGetPipeline(GLuint pipeline,
+                                                                                 const char* function) {
+            if (!MG_State::pGLContext->IsProgramPipelineObject(pipeline)) {
+                RecordPipelineError(ErrorCode::InvalidOperation, function,
+                                    std::format("Program pipeline {} does not exist.", pipeline));
+                return nullptr;
+            }
+            return &MG_State::pGLContext->GetProgramPipelineObject(pipeline);
+        }
+
+        Bool ValidatePipelineCount(GLsizei n, const char* function) {
+            if (n < 0) {
+                RecordPipelineError(ErrorCode::InvalidValue, function, "n must be non-negative.");
+                return false;
+            }
+            return true;
+        }
+
+        // GL 4.6 core table 7.1 maps each stage bit onto a shader stage.
+        Bool TryResolveStageBit(GLbitfield bit, ShaderStage& outStage) {
+            switch (bit) {
+            case GL_VERTEX_SHADER_BIT: outStage = ShaderStage::Vertex; return true;
+            case GL_TESS_CONTROL_SHADER_BIT: outStage = ShaderStage::TessControl; return true;
+            case GL_TESS_EVALUATION_SHADER_BIT: outStage = ShaderStage::TessEval; return true;
+            case GL_GEOMETRY_SHADER_BIT: outStage = ShaderStage::Geometry; return true;
+            case GL_FRAGMENT_SHADER_BIT: outStage = ShaderStage::Fragment; return true;
+            case GL_COMPUTE_SHADER_BIT: outStage = ShaderStage::Compute; return true;
+            default: return false;
+            }
+        }
+
+        constexpr GLbitfield kAllStageBits = GL_VERTEX_SHADER_BIT | GL_TESS_CONTROL_SHADER_BIT |
+                                            GL_TESS_EVALUATION_SHADER_BIT | GL_GEOMETRY_SHADER_BIT |
+                                            GL_FRAGMENT_SHADER_BIT | GL_COMPUTE_SHADER_BIT;
+    } // namespace
+
+    void GenProgramPipelines(GLsizei n, GLuint* pipelines) {
+        if (!ValidatePipelineCount(n, __func__)) return;
+        if (n == 0 || !pipelines) return;
+
+        static thread_local Vector<GLuint> names;
+        MG_State::pGLContext->GenProgramPipelineNames(static_cast<Uint>(n), names);
+        Memcpy(pipelines, names.data(), static_cast<SizeT>(n) * sizeof(GLuint));
+    }
+
+    void CreateProgramPipelines(GLsizei n, GLuint* pipelines) {
+        if (!ValidatePipelineCount(n, __func__)) return;
+        if (n == 0 || !pipelines) return;
+
+        static thread_local Vector<GLuint> names;
+        MG_State::pGLContext->GenProgramPipelineNames(static_cast<Uint>(n), names);
+        for (GLsizei i = 0; i < n; ++i) {
+            pipelines[i] = names[static_cast<SizeT>(i)];
+            MG_State::pGLContext->CreateProgramPipelineObject(names[static_cast<SizeT>(i)]);
+        }
+    }
+
+    void DeleteProgramPipelines(GLsizei n, const GLuint* pipelines) {
+        if (!ValidatePipelineCount(n, __func__)) return;
+        if (!pipelines) return;
+
+        for (GLsizei i = 0; i < n; ++i) {
+            // Deleting zero, an unknown name, or a name that was only reserved is silently ignored.
+            MG_State::pGLContext->MarkProgramPipelineForDeletion(pipelines[i]);
+        }
+    }
+
+    void BindProgramPipeline(GLuint pipeline) {
+        if (pipeline != 0 && !MG_State::pGLContext->ValidateProgramPipelineName(pipeline)) {
+            RecordPipelineError(ErrorCode::InvalidOperation, __func__,
+                                std::format("Program pipeline name {} is not valid.", pipeline));
+            return;
+        }
+        MG_State::pGLContext->BindProgramPipelineObject(pipeline);
+    }
+
+    GLboolean IsProgramPipeline(GLuint pipeline) {
+        return MG_State::pGLContext->IsProgramPipelineObject(pipeline) ? GL_TRUE : GL_FALSE;
+    }
+
+    void GetProgramPipelineiv(GLuint pipeline, GLenum pname, GLint* params) {
+        const auto* pipelineObject = TryGetPipeline(pipeline, __func__);
+        if (!pipelineObject || !params) return;
+
+        const auto stageProgramName = [&](ShaderStage stage) -> GLint {
+            const auto& program = (*pipelineObject)->GetStageProgram(stage);
+            return program ? static_cast<GLint>(program->GetExternalIndex()) : 0;
+        };
+
+        switch (pname) {
+        case GL_ACTIVE_PROGRAM: {
+            const auto& active = (*pipelineObject)->GetActiveProgram();
+            *params = active ? static_cast<GLint>(active->GetExternalIndex()) : 0;
+            break;
+        }
+        case GL_VERTEX_SHADER: *params = stageProgramName(ShaderStage::Vertex); break;
+        case GL_TESS_CONTROL_SHADER: *params = stageProgramName(ShaderStage::TessControl); break;
+        case GL_TESS_EVALUATION_SHADER: *params = stageProgramName(ShaderStage::TessEval); break;
+        case GL_GEOMETRY_SHADER: *params = stageProgramName(ShaderStage::Geometry); break;
+        case GL_FRAGMENT_SHADER: *params = stageProgramName(ShaderStage::Fragment); break;
+        case GL_COMPUTE_SHADER: *params = stageProgramName(ShaderStage::Compute); break;
+        case GL_VALIDATE_STATUS: *params = (*pipelineObject)->GetValidateStatus() ? GL_TRUE : GL_FALSE; break;
+        case GL_INFO_LOG_LENGTH: {
+            // GL counts the null terminator, and reports 0 rather than 1 for an empty log.
+            const auto& log = (*pipelineObject)->GetInfoLog();
+            *params = log.empty() ? 0 : static_cast<GLint>(log.length()) + 1;
+            break;
+        }
+        default:
+            RecordPipelineError(ErrorCode::InvalidEnum, __func__,
+                                std::format("pname {} is not a program pipeline parameter.",
+                                            MG_Util::ConvertGLEnumToString(pname)));
+            break;
+        }
+    }
+
+    void GetProgramPipelineInfoLog(GLuint pipeline, GLsizei bufSize, GLsizei* length, GLchar* infoLog) {
+        const auto* pipelineObject = TryGetPipeline(pipeline, __func__);
+        if (!pipelineObject) return;
+        if (bufSize < 0) {
+            RecordPipelineError(ErrorCode::InvalidValue, __func__, "bufSize must be non-negative.");
+            return;
+        }
+        if (bufSize == 0 || !infoLog) {
+            if (length) *length = 0;
+            return;
+        }
+
+        const auto& log = (*pipelineObject)->GetInfoLog();
+        const auto copied = std::min<GLsizei>(bufSize - 1, static_cast<GLsizei>(log.length()));
+        if (copied > 0) Memcpy(infoLog, log.data(), static_cast<SizeT>(copied));
+        infoLog[copied] = '\0';
+        if (length) *length = copied;
+    }
+
+    void UseProgramStages(GLuint pipeline, GLbitfield stages, GLuint program) {
+        if (stages != GL_ALL_SHADER_BITS && (stages & ~kAllStageBits) != 0) {
+            RecordPipelineError(ErrorCode::InvalidValue, __func__, "stages names a bit that is not a shader stage.");
+            return;
+        }
+        const auto* pipelineObject = TryGetPipeline(pipeline, __func__);
+        if (!pipelineObject) return;
+
+        SharedPtr<MG_State::GLState::ProgramObject> programObject;
+        if (program != 0) {
+            if (!MG_State::pGLContext->ValidateProgramName(program)) {
+                RecordPipelineError(ErrorCode::InvalidValue, __func__,
+                                    std::format("{} is not the name of a program object.", program));
+                return;
+            }
+            programObject = MG_State::pGLContext->GetProgramObject(program);
+            if (!programObject) {
+                RecordPipelineError(ErrorCode::InvalidValue, __func__,
+                                    std::format("{} is not the name of a program object.", program));
+                return;
+            }
+            if (!programObject->GetLinkStatus()) {
+                RecordPipelineError(ErrorCode::InvalidOperation, __func__,
+                                    std::format("Program {} has not been linked successfully.", program));
+                return;
+            }
+        }
+
+        const GLbitfield selected = stages == GL_ALL_SHADER_BITS ? kAllStageBits : stages;
+        for (GLbitfield bit = 1; bit != 0 && bit <= kAllStageBits; bit <<= 1) {
+            if ((selected & bit) == 0) continue;
+            ShaderStage stage = ShaderStage::Unknown;
+            if (!TryResolveStageBit(bit, stage)) continue;
+            // program == 0 clears the stage, which is what a null program reference means here.
+            (*pipelineObject)->SetStageProgram(stage, programObject);
+        }
+    }
+
+    void ActiveShaderProgram(GLuint pipeline, GLuint program) {
+        const auto* pipelineObject = TryGetPipeline(pipeline, __func__);
+        if (!pipelineObject) return;
+
+        if (program == 0) {
+            (*pipelineObject)->SetActiveProgram(nullptr);
+            return;
+        }
+        if (!MG_State::pGLContext->ValidateProgramName(program)) {
+            RecordPipelineError(ErrorCode::InvalidValue, __func__,
+                                std::format("{} is not the name of a program object.", program));
+            return;
+        }
+        auto programObject = MG_State::pGLContext->GetProgramObject(program);
+        if (!programObject) {
+            RecordPipelineError(ErrorCode::InvalidValue, __func__,
+                                std::format("{} is not the name of a program object.", program));
+            return;
+        }
+        if (!programObject->GetLinkStatus()) {
+            RecordPipelineError(ErrorCode::InvalidOperation, __func__,
+                                std::format("Program {} has not been linked successfully.", program));
+            return;
+        }
+        (*pipelineObject)->SetActiveProgram(programObject);
+    }
+
+    void ValidateProgramPipeline(GLuint pipeline) {
+        const auto* pipelineObject = TryGetPipeline(pipeline, __func__);
+        if (!pipelineObject) return;
+        // Nothing here can fail today: MobileGL links each stage program on its own, so there is no
+        // cross-stage interface to re-check at validation time. The log stays empty, which GL allows.
+        (*pipelineObject)->SetValidateStatus(true);
+    }
+} // namespace MobileGL::MG_Impl::GLImpl

MobileGL/MG_Impl/GLImpl/Program/GL_ProgramPipeline.h

@@ -0,0 +1,23 @@
+// MobileGL - MobileGL/MG_Impl/GLImpl/Program/GL_ProgramPipeline.h
+// Copyright (c) 2025-2026 MobileGL-Dev
+// Licensed under the GNU Lesser General Public License v3.0:
+//   https://www.gnu.org/licenses/gpl-3.0.txt
+//   https://www.gnu.org/licenses/lgpl-3.0.txt
+// SPDX-License-Identifier: LGPL-3.0-only
+// End of Source File Header
+
+#pragma once
+#include <Includes.h>
+
+namespace MobileGL::MG_Impl::GLImpl {
+    void GenProgramPipelines(GLsizei n, GLuint* pipelines);
+    void CreateProgramPipelines(GLsizei n, GLuint* pipelines);
+    void DeleteProgramPipelines(GLsizei n, const GLuint* pipelines);
+    void BindProgramPipeline(GLuint pipeline);
+    GLboolean IsProgramPipeline(GLuint pipeline);
+    void GetProgramPipelineiv(GLuint pipeline, GLenum pname, GLint* params);
+    void GetProgramPipelineInfoLog(GLuint pipeline, GLsizei bufSize, GLsizei* length, GLchar* infoLog);
+    void UseProgramStages(GLuint pipeline, GLbitfield stages, GLuint program);
+    void ActiveShaderProgram(GLuint pipeline, GLuint program);
+    void ValidateProgramPipeline(GLuint pipeline);
+} // namespace MobileGL::MG_Impl::GLImpl

MobileGL/MG_Impl/GLImpl/Program/ProgramInterface.cpp

@@ -0,0 +1,841 @@
+// MobileGL - MobileGL/MG_Impl/GLImpl/Program/ProgramInterface.cpp
+// Copyright (c) 2025-2026 MobileGL-Dev
+// Licensed under the GNU Lesser General Public License v3.0:
+//   https://www.gnu.org/licenses/gpl-3.0.txt
+//   https://www.gnu.org/licenses/lgpl-3.0.txt
+// SPDX-License-Identifier: LGPL-3.0-only
+// End of Source File Header
+
+#include "ProgramInterface.h"
+
+#include <MG_State/GLState/ProgramState/ProgramObject.h>
+#include <MG_Util/ShaderTranspiler/Types.h>
+
+#include <cstring>
+
+namespace MobileGL::MG_Impl::GLImpl::ProgramInterface {
+    namespace {
+        // glslang folds atomic counters into synthesized blocks named
+        // "<getAtomicCounterBlockName()>_<binding>" (ParseContextBase.cpp), one per GL
+        // atomic-counter binding point. That block IS the GL_ATOMIC_COUNTER_BUFFER resource
+        // and its trailing number IS GL_BUFFER_BINDING; its members stay GL_UNIFORMs.
+        constexpr const char* kAtomicCounterBlockPrefix = "gl_AtomicCounterBlock";
+
+        enum class BlockKind {
+            Uniform,       // a real GL uniform block
+            GlobalUbo,     // the synthesized MGL_GLOBAL_UBO: GL sees its members as default-block
+            AtomicCounter, // gl_AtomicCounterBlock_<binding>
+            Storage,       // a shader storage block
+        };
+
+        // One row of any interface. Fields a given interface does not have keep the
+        // spec-mandated "not applicable" value, so a prop read never has to special-case
+        // the interface a second time.
+        struct Resource {
+            String name;
+            GLenum type = GL_NONE;
+            GLint arraySize = 1;
+            GLint location = -1;
+            GLint locationIndex = -1;
+            GLint blockIndex = -1;
+            GLint offset = -1;
+            GLint arrayStride = -1;
+            GLint matrixStride = -1;
+            GLint isRowMajor = 0;
+            GLint atomicCounterBufferIndex = -1;
+            GLint topLevelArraySize = 0;
+            GLint topLevelArrayStride = 0;
+            GLint bufferBinding = 0;
+            GLint bufferDataSize = 0;
+            GLint isPerPatch = 0;
+            GLint xfbBufferIndex = 0;
+            Uint32 stages = 0; // EShLanguageMask
+            Vector<GLuint> activeVariables;
+        };
+
+        using ResourceList = Vector<Resource>;
+
+        struct Model {
+            ResourceList uniforms;
+            ResourceList uniformBlocks;
+            ResourceList atomicCounterBuffers;
+            ResourceList bufferVariables;
+            ResourceList storageBlocks;
+            ResourceList programInputs;
+            ResourceList programOutputs;
+            ResourceList xfbVaryings;
+            Bool valid = false;
+        };
+
+        const ResourceList& EmptyList() {
+            static const ResourceList empty;
+            return empty;
+        }
+
+        // ---- name spelling (cluster 6) -------------------------------------------------
+
+        Bool EndsWithZeroSubscript(const String& name) {
+            return name.length() >= 3 && name.compare(name.length() - 3, 3, "[0]") == 0;
+        }
+
+        // The enumerated spelling of an array resource is "name[0]". glslang already applies
+        // that to uniforms and buffer variables (EShReflectionBasicArraySuffix), but never to
+        // stage inputs/outputs, so those get it here.
+        String WithArraySuffix(const String& name, const glslang::TType* type) {
+            if (type == nullptr || !type->isArray() || EndsWithZeroSubscript(name)) return name;
+            return name + "[0]";
+        }
+
+        // GL_ARRAY_SIZE: element count for a sized array, 0 for a runtime-sized one
+        // (a shader storage block's unsized trailing member), 1 for a non-array.
+        GLint ArraySizeOf(const glslang::TType* type, GLint reflectedSize) {
+            if (type != nullptr && type->isArray()) {
+                if (!type->isSizedArray()) return 0;
+                return type->getOuterArraySize();
+            }
+            return reflectedSize < 1 ? 1 : reflectedSize;
+        }
+
+        // Two spellings name the same resource when they are equal, or differ only by the
+        // "[0]" the enumeration appends to an array.
+        Bool NamesMatch(const String& resourceName, const String& query) {
+            if (resourceName == query) return true;
+            if (EndsWithZeroSubscript(resourceName) &&
+                resourceName.compare(0, resourceName.length() - 3, query) == 0) {
+                return true;
+            }
+            return EndsWithZeroSubscript(query) && query.compare(0, query.length() - 3, resourceName) == 0;
+        }
+
+        // Splits "base[k]" into ("base", k). GL 4.6 §7.3.1.1 requires the subscript to be a
+        // decimal integer with no white space and no leading zeros, which is exactly what
+        // separates array-names' "a[1]" (resolves) from "a[01]", "a[0 + 0]" and "a[ 0]" (do
+        // not). Returns false when there is no trailing subscript at all; sets `malformed`
+        // when there is one but it is not a strict decimal.
+        Bool SplitTrailingSubscript(const String& name, String& outBase, Uint& outElement, Bool& outMalformed) {
+            outMalformed = false;
+            if (name.empty() || name.back() != ']') return false;
+            const SizeT bracket = name.rfind('[');
+            if (bracket == String::npos) return false;
+            const SizeT first = bracket + 1;
+            const SizeT last = name.length() - 1; // one past the digits
+            if (first >= last) {
+                outMalformed = true;
+                return false;
+            }
+            // No leading zeros: "0" is the only spelling that may start with '0'.
+            if (name[first] == '0' && last - first > 1) {
+                outMalformed = true;
+                return false;
+            }
+            Uint element = 0;
+            for (SizeT i = first; i < last; ++i) {
+                if (name[i] < '0' || name[i] > '9') {
+                    outMalformed = true;
+                    return false;
+                }
+                element = element * 10 + static_cast<Uint>(name[i] - '0');
+                if (element > 0x0FFFFFFFu) {
+                    outMalformed = true;
+                    return false;
+                }
+            }
+            outBase = name.substr(0, bracket);
+            outElement = element;
+            return true;
+        }
+
+        // ---- block classification ------------------------------------------------------
+
+        Bool IsAtomicCounterBlockName(const String& name) {
+            return name.compare(0, std::strlen(kAtomicCounterBlockPrefix), kAtomicCounterBlockPrefix) == 0;
+        }
+
+        // "gl_AtomicCounterBlock_5" -> 5. The suffix is the GL binding the counters were
+        // declared with, which glslang does NOT keep in the block's own layout qualifier
+        // (that one is remapped to a plain buffer binding).
+        GLint AtomicCounterBlockBinding(const String& name) {
+            const SizeT underscore = name.rfind('_');
+            if (underscore == String::npos || underscore + 1 >= name.length()) return 0;
+            GLint binding = 0;
+            for (SizeT i = underscore + 1; i < name.length(); ++i) {
+                if (name[i] < '0' || name[i] > '9') return 0;
+                binding = binding * 10 + (name[i] - '0');
+            }
+            return binding;
+        }
+
+        // Element index of an arrayed block instance ("TrickyBuffer[1]" -> 1).
+        GLint BlockArrayElement(const String& name) {
+            String base;
+            Uint element = 0;
+            Bool malformed = false;
+            if (!SplitTrailingSubscript(name, base, element, malformed)) return 0;
+            return static_cast<GLint>(element);
+        }
+
+        BlockKind ClassifyBlock(const glslang::TObjectReflection& block) {
+            if (std::strstr(block.name.c_str(), MG_Util::ShaderTranspiler::GLOBAL_UBO_NAME) != nullptr) {
+                return BlockKind::GlobalUbo;
+            }
+            if (IsAtomicCounterBlockName(block.name)) return BlockKind::AtomicCounter;
+            const glslang::TType* type = block.getType();
+            if (type != nullptr && type->getQualifier().storage == glslang::EvqBuffer) return BlockKind::Storage;
+            return BlockKind::Uniform;
+        }
+
+        // std140/std430 column stride, the same vec4-rounded rule ProgramObject applies to
+        // uniform matrices. 0 for a non-matrix.
+        GLint MatrixStrideOf(const glslang::TType* type) {
+            if (type == nullptr || !type->isMatrix()) return 0;
+            const bool rowMajor = type->getQualifier().layoutMatrix == glslang::ElmRowMajor;
+            const int strideVectorComponents = rowMajor ? type->getMatrixCols() : type->getMatrixRows();
+            constexpr int scalarSize = 4;
+            const int vectorAlignment = (strideVectorComponents <= 1)    ? scalarSize
+                                        : (strideVectorComponents == 2) ? 2 * scalarSize
+                                                                        : 4 * scalarSize;
+            return (vectorAlignment + 15) & ~15;
+        }
+
+        GLint IsRowMajorOf(const glslang::TType* type) {
+            if (type == nullptr || !type->isMatrix()) return 0;
+            return type->getQualifier().layoutMatrix == glslang::ElmRowMajor ? 1 : 0;
+        }
+
+        GLint MappedLocation(Int rawLocation) {
+            // glslang parks "no location" at layoutLocationEnd; GL spells it -1.
+            if (rawLocation < 0 || rawLocation >= static_cast<Int>(glslang::TQualifier::layoutLocationEnd)) return -1;
+            return rawLocation;
+        }
+
+        // ---- model construction --------------------------------------------------------
+
+        void BuildBlocks(ProgramObject& program, const glslang::TProgram& reflection, Model& model,
+                         Vector<BlockKind>& blockKind, Vector<Int>& blockInterfaceIndex) {
+            const Int blockCount = const_cast<glslang::TProgram&>(reflection).getNumUniformBlocks();
+            blockKind.assign(blockCount, BlockKind::Uniform);
+            blockInterfaceIndex.assign(blockCount, -1);
+
+            for (Int tIndex = 0; tIndex < blockCount; ++tIndex) {
+                const auto& block = const_cast<glslang::TProgram&>(reflection).getUniformBlock(tIndex);
+                const BlockKind kind = ClassifyBlock(block);
+                blockKind[tIndex] = kind;
+                if (kind == BlockKind::AtomicCounter) {
+                    Resource resource;
+                    // GL_ATOMIC_COUNTER_BUFFER resources have no name (and GetProgramResource
+                    // Index/Name reject the interface outright, which is why this stays empty).
+                    resource.bufferBinding = AtomicCounterBlockBinding(block.name);
+                    resource.bufferDataSize = block.size;
+                    resource.stages = static_cast<Uint32>(block.stages);
+                    blockInterfaceIndex[tIndex] = static_cast<Int>(model.atomicCounterBuffers.size());
+                    model.atomicCounterBuffers.push_back(Move(resource));
+                } else if (kind == BlockKind::Storage) {
+                    Resource resource;
+                    resource.name = block.name;
+                    // glslang reports the DECLARED binding for every instance of an arrayed
+                    // block; GL gives element k the binding base + k. That is only the initial
+                    // value: GL_BUFFER_BINDING must report the CURRENT binding, so a later
+                    // glShaderStorageBlockBinding wins over the declaration (GL 4.6 §7.6.2 -
+                    // exactly the same rule GL_UNIFORM_BLOCK follows through
+                    // GetUniformBlockBinding below).
+                    const GLint declared = block.getBinding();
+                    resource.bufferBinding = declared < 0 ? 0 : declared + BlockArrayElement(block.name);
+                    const Int rebound = program.GetShaderStorageBlockBindingOverride(block.name);
+                    if (rebound >= 0) resource.bufferBinding = static_cast<GLint>(rebound);
+                    resource.bufferDataSize = block.size;
+                    resource.stages = static_cast<Uint32>(block.stages);
+                    blockInterfaceIndex[tIndex] = static_cast<Int>(model.storageBlocks.size());
+                    model.storageBlocks.push_back(Move(resource));
+                }
+            }
+
+            // GL_UNIFORM_BLOCK keeps the index space glUniformBlockBinding and
+            // glGetActiveUniformBlockiv already use, so an index handed out here is usable
+            // with them (which is exactly what the CTS does).
+            const Int glBlockCount = program.GetActiveUniformBlocksCount();
+            for (Int glIndex = 0; glIndex < glBlockCount; ++glIndex) {
+                Resource resource;
+                resource.name = program.GetUniformBlockName(glIndex);
+                resource.bufferBinding = static_cast<GLint>(program.GetUniformBlockBinding(glIndex));
+                resource.bufferDataSize = static_cast<GLint>(program.GetUBOSizeAt(glIndex));
+                const Int tIndex = program.TProgramBlockIndex(static_cast<Uint>(glIndex));
+                if (tIndex >= 0 && tIndex < blockCount) {
+                    resource.stages =
+                        static_cast<Uint32>(const_cast<glslang::TProgram&>(reflection).getUniformBlock(tIndex).stages);
+                }
+                model.uniformBlocks.push_back(Move(resource));
+            }
+        }
+
+        void BuildUniformsAndBufferVariables(ProgramObject& program, const glslang::TProgram& reflection, Model& model,
+                                             const Vector<BlockKind>& blockKind,
+                                             const Vector<Int>& blockInterfaceIndex) {
+            const Uint uniformCount = program.GetUniformCount();
+            for (Uint glIndex = 0; glIndex < uniformCount; ++glIndex) {
+                const Int tIndex = program.TProgramUniformIndex(glIndex);
+                const auto& refl = const_cast<glslang::TProgram&>(reflection).getUniform(tIndex);
+                const glslang::TType* type = refl.getType();
+                const Int owner = refl.index;
+                const BlockKind kind = (owner >= 0 && owner < static_cast<Int>(blockKind.size()))
+                                           ? blockKind[owner]
+                                           : BlockKind::GlobalUbo;
+
+                Resource resource;
+                resource.name = refl.name;
+                resource.type = static_cast<GLenum>(refl.glDefineType);
+                resource.arraySize = ArraySizeOf(type, refl.size);
+                resource.stages = static_cast<Uint32>(refl.stages);
+
+                if (kind == BlockKind::Storage) {
+                    resource.blockIndex = blockInterfaceIndex[owner];
+                    resource.offset = refl.offset;
+                    resource.arrayStride = refl.arrayStride;
+                    resource.matrixStride = MatrixStrideOf(type);
+                    resource.isRowMajor = IsRowMajorOf(type);
+                    // GL requires 1 for a member that is not inside a top-level array (and for
+                    // the top-level array itself); glslang leaves 0/-1 there.
+                    resource.topLevelArraySize = refl.topLevelArraySize > 0 ? refl.topLevelArraySize : 1;
+                    resource.topLevelArrayStride = refl.topLevelArrayStride;
+                    model.bufferVariables.push_back(Move(resource));
+                    continue;
+                }
+
+                if (kind == BlockKind::AtomicCounter) {
+                    // An atomic counter is a default-block uniform with no location and no
+                    // owning uniform block; what it does have is a buffer to point at.
+                    resource.type = GL_UNSIGNED_INT_ATOMIC_COUNTER;
+                    resource.blockIndex = -1;
+                    resource.offset = refl.offset;
+                    resource.arrayStride = refl.arrayStride;
+                    resource.matrixStride = 0;
+                    resource.atomicCounterBufferIndex = blockInterfaceIndex[owner];
+                    resource.location = -1;
+                } else {
+                    resource.blockIndex = program.GetActiveUniformBlockIndex(glIndex);
+                    resource.offset = program.GetActiveUniformOffset(glIndex);
+                    resource.arrayStride = program.GetActiveUniformArrayStride(glIndex);
+                    resource.matrixStride = program.GetActiveUniformMatrixStride(glIndex);
+                    resource.isRowMajor = program.GetActiveUniformIsRowMajor(glIndex);
+                    // A member of a named uniform block has no location, whatever the
+                    // frontend's own location table says (it hands one out to every uniform
+                    // so glUniform* can address block members through the global UBO).
+                    resource.location =
+                        resource.blockIndex >= 0 ? -1 : program.GetUniformLocation(refl.name);
+                }
+                model.uniforms.push_back(Move(resource));
+            }
+
+            // GL_ACTIVE_VARIABLES, both directions.
+            for (SizeT i = 0; i < model.uniforms.size(); ++i) {
+                const Resource& uniform = model.uniforms[i];
+                if (uniform.atomicCounterBufferIndex >= 0 &&
+                    uniform.atomicCounterBufferIndex < static_cast<GLint>(model.atomicCounterBuffers.size())) {
+                    model.atomicCounterBuffers[uniform.atomicCounterBufferIndex].activeVariables.push_back(
+                        static_cast<GLuint>(i));
+                }
+            }
+            for (SizeT blockIndex = 0; blockIndex < model.uniformBlocks.size(); ++blockIndex) {
+                // Members of an arrayed block are reflected once, against instance [0].
+                const Int owner = static_cast<Int>(program.GetUniformBlockMemberOwnerIndex(static_cast<Uint>(blockIndex)));
+                for (SizeT i = 0; i < model.uniforms.size(); ++i) {
+                    if (model.uniforms[i].blockIndex == owner) {
+                        model.uniformBlocks[blockIndex].activeVariables.push_back(static_cast<GLuint>(i));
+                    }
+                }
+            }
+            for (SizeT blockIndex = 0; blockIndex < model.storageBlocks.size(); ++blockIndex) {
+                for (SizeT i = 0; i < model.bufferVariables.size(); ++i) {
+                    if (model.bufferVariables[i].blockIndex == static_cast<GLint>(blockIndex)) {
+                        model.storageBlocks[blockIndex].activeVariables.push_back(static_cast<GLuint>(i));
+                    }
+                }
+            }
+        }
+
+        void BuildStageIO(ProgramObject& program, const glslang::TProgram& reflection, Model& model) {
+            auto& mutableReflection = const_cast<glslang::TProgram&>(reflection);
+
+            const Int inputCount = mutableReflection.getNumPipeInputs();
+            for (Int index = 0; index < inputCount; ++index) {
+                const auto& refl = mutableReflection.getPipeInput(index);
+                const glslang::TType* type = refl.getType();
+                Resource resource;
+                // The Vulkan-semantics parse reflects the vertex builtins under their SPIR-V
+                // names; GL enumerates the GL spellings.
+                const String& glName = ProgramObject::NormalizeBuiltinPipeInputName(refl.name);
+                resource.name = WithArraySuffix(glName, type);
+                resource.type = static_cast<GLenum>(refl.glDefineType);
+                resource.arraySize = ArraySizeOf(type, refl.size);
+                resource.location = program.GetAttributeLocation(refl.name);
+                if (resource.location < 0) resource.location = MappedLocation(static_cast<Int>(refl.layoutLocation()));
+                resource.isPerPatch = (type != nullptr && type->getQualifier().patch) ? 1 : 0;
+                resource.stages = static_cast<Uint32>(refl.stages);
+                model.programInputs.push_back(Move(resource));
+            }
+
+            const Int outputCount = mutableReflection.getNumPipeOutputs();
+            for (Int index = 0; index < outputCount; ++index) {
+                const auto& refl = mutableReflection.getPipeOutput(index);
+                const glslang::TType* type = refl.getType();
+                Resource resource;
+                resource.name = WithArraySuffix(refl.name, type);
+                resource.type = static_cast<GLenum>(refl.glDefineType);
+                resource.arraySize = ArraySizeOf(type, refl.size);
+                resource.location = MappedLocation(program.GetFragmentDataLocation(refl.name.c_str()));
+                if (resource.location < 0) {
+                    // A built-in output (gl_FragDepth, gl_SampleMask) and a non-fragment stage
+                    // output both have no location, and therefore no color index either.
+                    resource.locationIndex = -1;
+                } else {
+                    resource.locationIndex = program.GetFragmentDataIndex(refl.name.c_str());
+                    // glBindFragDataLocationIndexed wins; otherwise the shader's
+                    // layout(index = N), which the frag-data maps never saw.
+                    if (resource.locationIndex == 0 && type != nullptr && type->getQualifier().hasIndex()) {
+                        resource.locationIndex = static_cast<GLint>(type->getQualifier().layoutIndex);
+                    }
+                }
+                resource.isPerPatch = (type != nullptr && type->getQualifier().patch) ? 1 : 0;
+                resource.stages = static_cast<Uint32>(refl.stages);
+                model.programOutputs.push_back(Move(resource));
+            }
+        }
+
+        void BuildXfb(ProgramObject& program, Model& model) {
+            const auto& requested = program.GetTransformFeedbackInterfaceNames();
+            const auto& captured = program.GetTransformFeedbackVaryings();
+            for (const String& name : requested) {
+                Resource resource;
+                resource.name = name;
+                // ARB_transform_feedback3's layout controls are enumerated as resources of
+                // type NONE: gl_NextBuffer with array size 0, gl_SkipComponentsN with N.
+                if (name == "gl_NextBuffer") {
+                    resource.type = GL_NONE;
+                    resource.arraySize = 0;
+                } else if (name.size() == 18 && name.compare(0, 17, "gl_SkipComponents") == 0 && name[17] >= '1' &&
+                           name[17] <= '4') {
+                    resource.type = GL_NONE;
+                    resource.arraySize = name[17] - '0';
+                } else {
+                    resource.type = GL_NONE;
+                    resource.arraySize = 1;
+                    for (const auto& varying : captured) {
+                        if (varying.name != name) continue;
+                        resource.type = varying.type;
+                        resource.arraySize = varying.size < 1 ? 1 : varying.size;
+                        resource.offset = static_cast<GLint>(varying.offsetBytes);
+                        resource.xfbBufferIndex = static_cast<GLint>(varying.bufferIndex);
+                        break;
+                    }
+                }
+                model.xfbVaryings.push_back(Move(resource));
+            }
+        }
+
+        Model BuildModel(ProgramObject& program) {
+            Model model;
+            if (!program.GetLinkStatus()) return model;
+            const glslang::TProgram* reflection = program.GetReflection();
+            if (reflection == nullptr) return model;
+            model.valid = true;
+
+            Vector<BlockKind> blockKind;
+            Vector<Int> blockInterfaceIndex;
+            BuildBlocks(program, *reflection, model, blockKind, blockInterfaceIndex);
+            BuildUniformsAndBufferVariables(program, *reflection, model, blockKind, blockInterfaceIndex);
+            BuildStageIO(program, *reflection, model);
+            BuildXfb(program, model);
+            return model;
+        }
+
+        const ResourceList& Select(const Model& model, GLenum programInterface) {
+            switch (programInterface) {
+            case GL_UNIFORM:
+                return model.uniforms;
+            case GL_UNIFORM_BLOCK:
+                return model.uniformBlocks;
+            case GL_ATOMIC_COUNTER_BUFFER:
+                return model.atomicCounterBuffers;
+            case GL_BUFFER_VARIABLE:
+                return model.bufferVariables;
+            case GL_SHADER_STORAGE_BLOCK:
+                return model.storageBlocks;
+            case GL_PROGRAM_INPUT:
+                return model.programInputs;
+            case GL_PROGRAM_OUTPUT:
+                return model.programOutputs;
+            case GL_TRANSFORM_FEEDBACK_VARYING:
+                return model.xfbVaryings;
+            default:
+                // The subroutine interfaces are accepted by the API but nothing can populate
+                // them: glslang refuses `subroutine` when generating SPIR-V, so a program
+                // using one never links. Zero active resources is the honest answer.
+                return EmptyList();
+            }
+        }
+    } // namespace
+
+    Bool IsInterfaceEnum(GLenum programInterface) {
+        switch (programInterface) {
+        case GL_UNIFORM:
+        case GL_UNIFORM_BLOCK:
+        case GL_PROGRAM_INPUT:
+        case GL_PROGRAM_OUTPUT:
+        case GL_BUFFER_VARIABLE:
+        case GL_SHADER_STORAGE_BLOCK:
+        case GL_ATOMIC_COUNTER_BUFFER:
+        case GL_TRANSFORM_FEEDBACK_VARYING:
+        case GL_TRANSFORM_FEEDBACK_BUFFER:
+        case GL_VERTEX_SUBROUTINE:
+        case GL_TESS_CONTROL_SUBROUTINE:
+        case GL_TESS_EVALUATION_SUBROUTINE:
+        case GL_GEOMETRY_SUBROUTINE:
+        case GL_FRAGMENT_SUBROUTINE:
+        case GL_COMPUTE_SUBROUTINE:
+        case GL_VERTEX_SUBROUTINE_UNIFORM:
+        case GL_TESS_CONTROL_SUBROUTINE_UNIFORM:
+        case GL_TESS_EVALUATION_SUBROUTINE_UNIFORM:
+        case GL_GEOMETRY_SUBROUTINE_UNIFORM:
+        case GL_FRAGMENT_SUBROUTINE_UNIFORM:
+        case GL_COMPUTE_SUBROUTINE_UNIFORM:
+            return true;
+        default:
+            return false;
+        }
+    }
+
+    Bool IsNamedInterface(GLenum programInterface) {
+        // GL 4.6 §7.3.1.2: the two buffer interfaces have no resource names, and asking for
+        // one is INVALID_ENUM (deliberately asymmetric with GetProgramInterfaceiv, which
+        // does count them).
+        return IsInterfaceEnum(programInterface) && programInterface != GL_ATOMIC_COUNTER_BUFFER &&
+               programInterface != GL_TRANSFORM_FEEDBACK_BUFFER;
+    }
+
+    Bool InterfaceHasLocations(GLenum programInterface) {
+        switch (programInterface) {
+        case GL_UNIFORM:
+        case GL_PROGRAM_INPUT:
+        case GL_PROGRAM_OUTPUT:
+        case GL_VERTEX_SUBROUTINE_UNIFORM:
+        case GL_TESS_CONTROL_SUBROUTINE_UNIFORM:
+        case GL_TESS_EVALUATION_SUBROUTINE_UNIFORM:
+        case GL_GEOMETRY_SUBROUTINE_UNIFORM:
+        case GL_FRAGMENT_SUBROUTINE_UNIFORM:
+        case GL_COMPUTE_SUBROUTINE_UNIFORM:
+            return true;
+        default:
+            return false;
+        }
+    }
+
+    Bool IsResourceProp(GLenum prop) {
+        switch (prop) {
+        case GL_NAME_LENGTH:
+        case GL_TYPE:
+        case GL_ARRAY_SIZE:
+        case GL_OFFSET:
+        case GL_BLOCK_INDEX:
+        case GL_ARRAY_STRIDE:
+        case GL_MATRIX_STRIDE:
+        case GL_IS_ROW_MAJOR:
+        case GL_ATOMIC_COUNTER_BUFFER_INDEX:
+        case GL_BUFFER_BINDING:
+        case GL_BUFFER_DATA_SIZE:
+        case GL_NUM_ACTIVE_VARIABLES:
+        case GL_ACTIVE_VARIABLES:
+        case GL_REFERENCED_BY_VERTEX_SHADER:
+        case GL_REFERENCED_BY_TESS_CONTROL_SHADER:
+        case GL_REFERENCED_BY_TESS_EVALUATION_SHADER:
+        case GL_REFERENCED_BY_GEOMETRY_SHADER:
+        case GL_REFERENCED_BY_FRAGMENT_SHADER:
+        case GL_REFERENCED_BY_COMPUTE_SHADER:
+        case GL_TOP_LEVEL_ARRAY_SIZE:
+        case GL_TOP_LEVEL_ARRAY_STRIDE:
+        case GL_LOCATION:
+        case GL_LOCATION_INDEX:
+        case GL_IS_PER_PATCH:
+        case GL_LOCATION_COMPONENT:
+        case GL_TRANSFORM_FEEDBACK_BUFFER_INDEX:
+        case GL_TRANSFORM_FEEDBACK_BUFFER_STRIDE:
+        case GL_NUM_COMPATIBLE_SUBROUTINES:
+        case GL_COMPATIBLE_SUBROUTINES:
+            return true;
+        default:
+            return false;
+        }
+    }
+
+    // GL 4.6 Table 7.2, transcribed row by row: which interfaces each property applies to.
+    // Too tight a table turns a currently-answered prop into a fresh INVALID_OPERATION, so
+    // the rows below are deliberately no narrower than the spec's.
+    Bool InterfaceSupportsProp(GLenum programInterface, GLenum prop) {
+        const Bool isSubroutine =
+            programInterface == GL_VERTEX_SUBROUTINE || programInterface == GL_TESS_CONTROL_SUBROUTINE ||
+            programInterface == GL_TESS_EVALUATION_SUBROUTINE || programInterface == GL_GEOMETRY_SUBROUTINE ||
+            programInterface == GL_FRAGMENT_SUBROUTINE || programInterface == GL_COMPUTE_SUBROUTINE;
+        const Bool isSubroutineUniform =
+            programInterface == GL_VERTEX_SUBROUTINE_UNIFORM ||
+            programInterface == GL_TESS_CONTROL_SUBROUTINE_UNIFORM ||
+            programInterface == GL_TESS_EVALUATION_SUBROUTINE_UNIFORM ||
+            programInterface == GL_GEOMETRY_SUBROUTINE_UNIFORM ||
+            programInterface == GL_FRAGMENT_SUBROUTINE_UNIFORM || programInterface == GL_COMPUTE_SUBROUTINE_UNIFORM;
+
+        switch (prop) {
+        case GL_NAME_LENGTH:
+            return programInterface != GL_ATOMIC_COUNTER_BUFFER && programInterface != GL_TRANSFORM_FEEDBACK_BUFFER;
+        case GL_TYPE:
+        case GL_ARRAY_SIZE:
+            return programInterface == GL_UNIFORM || programInterface == GL_PROGRAM_INPUT ||
+                   programInterface == GL_PROGRAM_OUTPUT || programInterface == GL_BUFFER_VARIABLE ||
+                   programInterface == GL_TRANSFORM_FEEDBACK_VARYING ||
+                   (prop == GL_ARRAY_SIZE && isSubroutineUniform);
+        case GL_OFFSET:
+            return programInterface == GL_UNIFORM || programInterface == GL_BUFFER_VARIABLE ||
+                   programInterface == GL_TRANSFORM_FEEDBACK_VARYING;
+        case GL_BLOCK_INDEX:
+        case GL_ARRAY_STRIDE:
+        case GL_MATRIX_STRIDE:
+        case GL_IS_ROW_MAJOR:
+            return programInterface == GL_UNIFORM || programInterface == GL_BUFFER_VARIABLE;
+        case GL_ATOMIC_COUNTER_BUFFER_INDEX:
+            return programInterface == GL_UNIFORM;
+        case GL_BUFFER_BINDING:
+        case GL_NUM_ACTIVE_VARIABLES:
+        case GL_ACTIVE_VARIABLES:
+            // Table 7.2 lists GL_TRANSFORM_FEEDBACK_BUFFER on these three rows too. This
+            // implementation enumerates no resources on that interface, so the query still
+            // ends in an error - but INVALID_VALUE for the out-of-range index, not the
+            // INVALID_OPERATION a narrower table would invent.
+            return programInterface == GL_UNIFORM_BLOCK || programInterface == GL_ATOMIC_COUNTER_BUFFER ||
+                   programInterface == GL_SHADER_STORAGE_BLOCK ||
+                   programInterface == GL_TRANSFORM_FEEDBACK_BUFFER;
+        case GL_BUFFER_DATA_SIZE:
+            return programInterface == GL_UNIFORM_BLOCK || programInterface == GL_ATOMIC_COUNTER_BUFFER ||
+                   programInterface == GL_SHADER_STORAGE_BLOCK;
+        case GL_REFERENCED_BY_VERTEX_SHADER:
+        case GL_REFERENCED_BY_TESS_CONTROL_SHADER:
+        case GL_REFERENCED_BY_TESS_EVALUATION_SHADER:
+        case GL_REFERENCED_BY_GEOMETRY_SHADER:
+        case GL_REFERENCED_BY_FRAGMENT_SHADER:
+        case GL_REFERENCED_BY_COMPUTE_SHADER:
+            return programInterface == GL_UNIFORM || programInterface == GL_UNIFORM_BLOCK ||
+                   programInterface == GL_ATOMIC_COUNTER_BUFFER || programInterface == GL_BUFFER_VARIABLE ||
+                   programInterface == GL_SHADER_STORAGE_BLOCK || programInterface == GL_PROGRAM_INPUT ||
+                   programInterface == GL_PROGRAM_OUTPUT || isSubroutineUniform;
+        case GL_TOP_LEVEL_ARRAY_SIZE:
+        case GL_TOP_LEVEL_ARRAY_STRIDE:
+            return programInterface == GL_BUFFER_VARIABLE;
+        case GL_LOCATION:
+            return InterfaceHasLocations(programInterface);
+        case GL_LOCATION_INDEX:
+            return programInterface == GL_PROGRAM_OUTPUT;
+        case GL_IS_PER_PATCH:
+        case GL_LOCATION_COMPONENT:
+            return programInterface == GL_PROGRAM_INPUT || programInterface == GL_PROGRAM_OUTPUT;
+        case GL_TRANSFORM_FEEDBACK_BUFFER_INDEX:
+            return programInterface == GL_TRANSFORM_FEEDBACK_VARYING;
+        case GL_TRANSFORM_FEEDBACK_BUFFER_STRIDE:
+            return programInterface == GL_TRANSFORM_FEEDBACK_BUFFER;
+        case GL_NUM_COMPATIBLE_SUBROUTINES:
+        case GL_COMPATIBLE_SUBROUTINES:
+            return isSubroutineUniform;
+        default:
+            (void)isSubroutine;
+            return false;
+        }
+    }
+
+    Int GetActiveResourceCount(ProgramObject& program, GLenum programInterface) {
+        const Model model = BuildModel(program);
+        return static_cast<Int>(Select(model, programInterface).size());
+    }
+
+    Int GetMaxNameLength(ProgramObject& program, GLenum programInterface) {
+        if (!IsNamedInterface(programInterface)) return 0;
+        const Model model = BuildModel(program);
+        SizeT longest = 0;
+        for (const Resource& resource : Select(model, programInterface)) {
+            longest = std::max(longest, resource.name.length() + 1);
+        }
+        return static_cast<Int>(longest);
+    }
+
+    Int GetMaxNumActiveVariables(ProgramObject& program, GLenum programInterface) {
+        const Model model = BuildModel(program);
+        SizeT longest = 0;
+        for (const Resource& resource : Select(model, programInterface)) {
+            longest = std::max(longest, resource.activeVariables.size());
+        }
+        return static_cast<Int>(longest);
+    }
+
+    GLuint GetResourceIndex(ProgramObject& program, GLenum programInterface, const char* name) {
+        if (name == nullptr || name[0] == '\0') return GL_INVALID_INDEX;
+        const Model model = BuildModel(program);
+        const ResourceList& resources = Select(model, programInterface);
+        const String query = name;
+        // The layout controls of an interleaved capture are enumerable but not addressable
+        // by name (GL 4.6 §7.3.1.1).
+        if (programInterface == GL_TRANSFORM_FEEDBACK_VARYING &&
+            (query == "gl_NextBuffer" ||
+             (query.size() == 18 && query.compare(0, 17, "gl_SkipComponents") == 0))) {
+            return GL_INVALID_INDEX;
+        }
+        for (SizeT i = 0; i < resources.size(); ++i) {
+            if (NamesMatch(resources[i].name, query)) return static_cast<GLuint>(i);
+        }
+        return GL_INVALID_INDEX;
+    }
+
+    Bool GetResourceName(ProgramObject& program, GLenum programInterface, GLuint index, String& outName) {
+        const Model model = BuildModel(program);
+        const ResourceList& resources = Select(model, programInterface);
+        if (index >= resources.size()) return false;
+        outName = resources[index].name;
+        return true;
+    }
+
+    Bool GetResourceProp(ProgramObject& program, GLenum programInterface, GLuint index, GLenum prop,
+                         Vector<GLint>& outValues) {
+        const Model model = BuildModel(program);
+        const ResourceList& resources = Select(model, programInterface);
+        if (index >= resources.size()) return false;
+        const Resource& resource = resources[index];
+
+        const auto referencedBy = [&resource](EShLanguage stage) {
+            return (resource.stages & static_cast<Uint32>(1u << stage)) != 0 ? GL_TRUE : GL_FALSE;
+        };
+
+        switch (prop) {
+        case GL_NAME_LENGTH:
+            outValues.push_back(static_cast<GLint>(resource.name.length() + 1));
+            break;
+        case GL_TYPE:
+            outValues.push_back(static_cast<GLint>(resource.type));
+            break;
+        case GL_ARRAY_SIZE:
+            outValues.push_back(resource.arraySize);
+            break;
+        case GL_OFFSET:
+            outValues.push_back(resource.offset);
+            break;
+        case GL_BLOCK_INDEX:
+            outValues.push_back(resource.blockIndex);
+            break;
+        case GL_ARRAY_STRIDE:
+            outValues.push_back(resource.arrayStride);
+            break;
+        case GL_MATRIX_STRIDE:
+            outValues.push_back(resource.matrixStride);
+            break;
+        case GL_IS_ROW_MAJOR:
+            outValues.push_back(resource.isRowMajor);
+            break;
+        case GL_ATOMIC_COUNTER_BUFFER_INDEX:
+            outValues.push_back(resource.atomicCounterBufferIndex);
+            break;
+        case GL_BUFFER_BINDING:
+            outValues.push_back(resource.bufferBinding);
+            break;
+        case GL_BUFFER_DATA_SIZE:
+            outValues.push_back(resource.bufferDataSize);
+            break;
+        case GL_NUM_ACTIVE_VARIABLES:
+            outValues.push_back(static_cast<GLint>(resource.activeVariables.size()));
+            break;
+        case GL_ACTIVE_VARIABLES:
+            for (const GLuint variable : resource.activeVariables) outValues.push_back(static_cast<GLint>(variable));
+            break;
+        case GL_REFERENCED_BY_VERTEX_SHADER:
+            outValues.push_back(referencedBy(EShLangVertex));
+            break;
+        case GL_REFERENCED_BY_TESS_CONTROL_SHADER:
+            outValues.push_back(referencedBy(EShLangTessControl));
+            break;
+        case GL_REFERENCED_BY_TESS_EVALUATION_SHADER:
+            outValues.push_back(referencedBy(EShLangTessEvaluation));
+            break;
+        case GL_REFERENCED_BY_GEOMETRY_SHADER:
+            outValues.push_back(referencedBy(EShLangGeometry));
+            break;
+        case GL_REFERENCED_BY_FRAGMENT_SHADER:
+            outValues.push_back(referencedBy(EShLangFragment));
+            break;
+        case GL_REFERENCED_BY_COMPUTE_SHADER:
+            outValues.push_back(referencedBy(EShLangCompute));
+            break;
+        case GL_TOP_LEVEL_ARRAY_SIZE:
+            outValues.push_back(resource.topLevelArraySize);
+            break;
+        case GL_TOP_LEVEL_ARRAY_STRIDE:
+            outValues.push_back(resource.topLevelArrayStride);
+            break;
+        case GL_LOCATION:
+            outValues.push_back(resource.location);
+            break;
+        case GL_LOCATION_INDEX:
+            outValues.push_back(resource.locationIndex);
+            break;
+        case GL_IS_PER_PATCH:
+            outValues.push_back(resource.isPerPatch);
+            break;
+        case GL_LOCATION_COMPONENT:
+            outValues.push_back(0);
+            break;
+        case GL_TRANSFORM_FEEDBACK_BUFFER_INDEX:
+            outValues.push_back(resource.xfbBufferIndex);
+            break;
+        default:
+            outValues.push_back(0);
+            break;
+        }
+        return true;
+    }
+
+    GLint GetResourceLocation(ProgramObject& program, GLenum programInterface, const char* name) {
+        if (name == nullptr || name[0] == '\0') return -1;
+        const String query = name;
+
+        String base;
+        Uint element = 0;
+        Bool malformed = false;
+        const Bool subscripted = SplitTrailingSubscript(query, base, element, malformed);
+        if (malformed) return -1;
+
+        const Model model = BuildModel(program);
+        const ResourceList& resources = Select(model, programInterface);
+        for (const Resource& resource : resources) {
+            if (NamesMatch(resource.name, query)) return resource.location;
+        }
+        if (!subscripted || element == 0) return -1;
+        // "d[1]" addresses the second element of an array resource enumerated as "d[0]".
+        for (const Resource& resource : resources) {
+            if (!NamesMatch(resource.name, base)) continue;
+            if (resource.location < 0 || static_cast<GLint>(element) >= resource.arraySize) return -1;
+            return resource.location + static_cast<GLint>(element);
+        }
+        return -1;
+    }
+
+    GLint GetResourceLocationIndex(ProgramObject& program, GLenum programInterface, const char* name) {
+        if (programInterface != GL_PROGRAM_OUTPUT || name == nullptr || name[0] == '\0') return -1;
+        const String query = name;
+        String base;
+        Uint element = 0;
+        Bool malformed = false;
+        const Bool subscripted = SplitTrailingSubscript(query, base, element, malformed);
+        if (malformed) return -1;
+
+        const Model model = BuildModel(program);
+        for (const Resource& resource : model.programOutputs) {
+            if (NamesMatch(resource.name, query)) return resource.locationIndex;
+        }
+        if (!subscripted) return -1;
+        for (const Resource& resource : model.programOutputs) {
+            if (!NamesMatch(resource.name, base)) continue;
+            if (resource.location < 0 || static_cast<GLint>(element) >= resource.arraySize) return -1;
+            return resource.locationIndex;
+        }
+        return -1;
+    }
+} // namespace MobileGL::MG_Impl::GLImpl::ProgramInterface

MobileGL/MG_Impl/GLImpl/Program/ProgramInterface.h

@@ -0,0 +1,66 @@
+// MobileGL - MobileGL/MG_Impl/GLImpl/Program/ProgramInterface.h
+// Copyright (c) 2025-2026 MobileGL-Dev
+// Licensed under the GNU Lesser General Public License v3.0:
+//   https://www.gnu.org/licenses/gpl-3.0.txt
+//   https://www.gnu.org/licenses/lgpl-3.0.txt
+// SPDX-License-Identifier: LGPL-3.0-only
+// End of Source File Header
+
+#pragma once
+#include <Includes.h>
+
+namespace MobileGL::MG_State::GLState {
+    class ProgramObject;
+}
+
+// The GL program interface (ARB_program_interface_query / GL 4.3 §7.3.1) as a frontend
+// resource model.
+//
+// WHY IT IS HERE AND NOT IN A BACKEND. glGetProgramResource* describes the program the
+// APPLICATION wrote, in the application's namespace. Neither backend program is in that
+// namespace: DirectGLES compiles SPIRV-Cross-generated ESSL where default-block uniforms
+// live inside the synthesized MGL_GLOBAL_UBO (so a GL_UNIFORM location query against it is
+// structurally -1) and stage in/out names are rewritten; DirectVulkan has no GL-level
+// reflection at all and can only re-derive a partial, diverging copy. The one authoritative
+// source is the frontend glslang reflection a link already produced, which is the same
+// place glGetActiveUniform answers from. This layer generalizes that rule to every
+// interface, so the six entry points never consult gBackendFunctionsTable.
+//
+// NAMING RULES LIVE HERE, NOT IN ProgramObject. The interface query spells resources
+// differently from glGetActiveUniform / glGetActiveAttrib (an array is "name[0]", a lookup
+// accepts both "name" and "name[0]", a subscript must be a strict decimal). Those two
+// getters are what GL30-33 exercises and they must not move, so every normalization is
+// applied on the way in and out of THIS file.
+namespace MobileGL::MG_Impl::GLImpl::ProgramInterface {
+    using ProgramObject = MG_State::GLState::ProgramObject;
+
+    // <programInterface> is one of the GL 4.6 Table 7.1 interfaces.
+    Bool IsInterfaceEnum(GLenum programInterface);
+    // Interfaces whose resources have names (everything except GL_ATOMIC_COUNTER_BUFFER).
+    Bool IsNamedInterface(GLenum programInterface);
+    // <prop> is a property token GetProgramResourceiv knows at all (else GL_INVALID_ENUM).
+    Bool IsResourceProp(GLenum prop);
+    // <prop> applies to <programInterface> (else GL_INVALID_OPERATION).
+    Bool InterfaceSupportsProp(GLenum programInterface, GLenum prop);
+    // Interfaces GetProgramResourceLocation accepts (else GL_INVALID_ENUM).
+    Bool InterfaceHasLocations(GLenum programInterface);
+
+    // GL_ACTIVE_RESOURCES / GL_MAX_NAME_LENGTH / GL_MAX_NUM_ACTIVE_VARIABLES. All three
+    // report zero for an interface this implementation cannot enumerate and for a program
+    // that has not linked successfully - which is what the spec requires of a program with
+    // no active resources.
+    Int GetActiveResourceCount(ProgramObject& program, GLenum programInterface);
+    Int GetMaxNameLength(ProgramObject& program, GLenum programInterface);
+    Int GetMaxNumActiveVariables(ProgramObject& program, GLenum programInterface);
+
+    // GL_INVALID_INDEX when <name> names no active resource of the interface.
+    GLuint GetResourceIndex(ProgramObject& program, GLenum programInterface, const char* name);
+    // False when <index> is out of range for the interface (the caller raises INVALID_VALUE).
+    Bool GetResourceName(ProgramObject& program, GLenum programInterface, GLuint index, String& outName);
+    // Appends the value(s) of <prop> for the resource; GL_ACTIVE_VARIABLES appends several.
+    // False when <index> is out of range.
+    Bool GetResourceProp(ProgramObject& program, GLenum programInterface, GLuint index, GLenum prop,
+                         Vector<GLint>& outValues);
+    GLint GetResourceLocation(ProgramObject& program, GLenum programInterface, const char* name);
+    GLint GetResourceLocationIndex(ProgramObject& program, GLenum programInterface, const char* name);
+} // namespace MobileGL::MG_Impl::GLImpl::ProgramInterface

MobileGL/MG_Impl/GLImpl/Query/GL_Query.cpp

@@ -7,6 +7,7 @@
 // End of Source File Header
 
 #include "GL_Query.h"
+#include "../Getter/GL_Getter.h"
 #include <Config.h>
 #include <MG_Backend/BackendObjects.h>
 #include <MG_State/GLState/Core.h>
@@ -22,11 +23,16 @@ namespace MobileGL::MG_Impl::GLImpl {
         struct QueryObject {
             GLuint id = 0;
             GLenum target = 0; // 0 = gen'd but never used with BeginQuery/QueryCounter
+            // glCreateQueries makes the object outright; glGenQueries only reserves the name,
+            // and the object appears when the name is first used (GL 4.6 core 4.2.1).
+            Bool created = false;
             MG_Backend::BackendQueryHandle backendHandle = nullptr;
             Bool active = false;
             Bool ended = false;
             Bool resultCached = false;
             Uint64 cachedResult = 0;
+            // Transform feedback primitive counter at BeginQuery time.
+            Uint64 counterSnapshot = 0;
         };
 
         // Query calls may arrive from any thread (launchers migrate the context
@@ -41,6 +47,11 @@ namespace MobileGL::MG_Impl::GLImpl {
         GLuint g_nextQueryId = 1;
         // Id of the query currently active on GL_TIME_ELAPSED (0 = none).
         GLuint g_activeTimeElapsedQueryId = 0;
+        // Ids of the queries active on the transform feedback targets (0 = none).
+        GLuint g_activePrimitivesWrittenQueryId = 0;
+        GLuint g_activePrimitivesGeneratedQueryId = 0;
+        // Id of the query active on GL_SAMPLES_PASSED (0 = none).
+        GLuint g_activeSamplesPassedQueryId = 0;
 
         Bool TimerQueryDisabled() {
             return MG_Config::Features.DisableTimerQuery;
@@ -51,6 +62,34 @@ namespace MobileGL::MG_Impl::GLImpl {
                                               MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", function, message));
         }
 
+        // The by-buffer query getters write the result into a buffer object instead of client
+        // memory. Everything about the query itself - the name, whether it is still active, the
+        // parameter - is checked by GetQueryObjectValue; what is left is the destination, so this
+        // resolves the buffer and confirms the write lands inside it (GL 4.6 core 4.2.1).
+        Bool ResolveQueryResultDestination(GLuint buffer, GLintptr offset, SizeT writeSize, const char* function,
+                                           SharedPtr<MG_State::GLState::BufferObject>& outBuffer) {
+            if (offset < 0) {
+                RecordQueryError(ErrorCode::InvalidValue, function, "Offset cannot be negative.");
+                return false;
+            }
+            if (!MG_State::pGLContext->ValidateBufferObject(buffer)) {
+                RecordQueryError(ErrorCode::InvalidOperation, function, "Buffer object does not exist.");
+                return false;
+            }
+            auto bufferObject = MG_State::pGLContext->GetBufferObject(buffer);
+            if (!bufferObject) {
+                RecordQueryError(ErrorCode::InvalidOperation, function, "Buffer object does not exist.");
+                return false;
+            }
+            if (static_cast<SizeT>(offset) + writeSize > bufferObject->GetSize()) {
+                RecordQueryError(ErrorCode::InvalidOperation, function,
+                                 "The query result does not fit in the buffer object at this offset.");
+                return false;
+            }
+            outBuffer = bufferObject;
+            return true;
+        }
+
         // Callers must hold g_queryObjectsMutex.
         QueryObject* FindQueryObjectLocked(GLuint id) {
             const auto it = g_liveQueryObjects.find(id);
@@ -84,8 +123,13 @@ namespace MobileGL::MG_Impl::GLImpl {
         }
 
         // Shared GetQueryObject* implementation. Returns false when an error
-        // was recorded and no value should be written back.
-        Bool GetQueryObjectValue(GLuint id, GLenum pname, const char* function, Uint64& outValue) {
+        // was recorded and no value should be written back. `outValueProduced`, when given,
+        // additionally distinguishes "succeeded with a value" from "succeeded but the result is not
+        // ready" - the GL_QUERY_RESULT_NO_WAIT case, where GL_ARB_query_buffer_object says the
+        // destination is left alone rather than written with a placeholder.
+        Bool GetQueryObjectValue(GLuint id, GLenum pname, const char* function, Uint64& outValue,
+                                 Bool* outValueProduced = nullptr) {
+            if (outValueProduced) *outValueProduced = true;
             const std::lock_guard<std::mutex> lock(g_queryObjectsMutex);
             auto* queryObject = FindQueryObjectLocked(id);
             if (!queryObject) {
@@ -98,6 +142,41 @@ namespace MobileGL::MG_Impl::GLImpl {
             }
 
             switch (pname) {
+            case GL_QUERY_TARGET:
+                // The target a query was begun with (or created with, for glCreateQueries) - state
+                // the object has carried all along, GL 4.6 core table 23.35.
+                outValue = queryObject->target;
+                return true;
+            case GL_QUERY_RESULT_NO_WAIT: {
+                if (queryObject->resultCached) {
+                    outValue = queryObject->cachedResult;
+                    return true;
+                }
+                Uint64 result = 0;
+                const auto getQueryResult64 = MG_Backend::gBackendFunctionsTable.GL.GetQueryResult64;
+                if (queryObject->backendHandle && getQueryResult64 &&
+                    !getQueryResult64(queryObject->backendHandle, /*wait=*/false, &result)) {
+                    // Not ready. The whole point of the no-wait form is that the caller's
+                    // destination keeps whatever it already held.
+                    if (outValueProduced) *outValueProduced = false;
+                    outValue = 0;
+                    return true;
+                }
+                if (queryObject->target == GL_ANY_SAMPLES_PASSED ||
+                    queryObject->target == GL_ANY_SAMPLES_PASSED_CONSERVATIVE) {
+                    result = result != 0 ? 1 : 0;
+                }
+                if (queryObject->backendHandle) {
+                    if (const auto deleteBackendQuery = MG_Backend::gBackendFunctionsTable.GL.DeleteBackendQuery) {
+                        deleteBackendQuery(queryObject->backendHandle);
+                    }
+                    queryObject->backendHandle = nullptr;
+                }
+                queryObject->cachedResult = result;
+                queryObject->resultCached = true;
+                outValue = result;
+                return true;
+            }
             case GL_QUERY_RESULT_AVAILABLE: {
                 if (queryObject->resultCached || !queryObject->backendHandle) {
                     outValue = 1;
@@ -126,6 +205,11 @@ namespace MobileGL::MG_Impl::GLImpl {
                         outValue = 0;
                         return true;
                     }
+                    // ANY_SAMPLES_PASSED* report a boolean.
+                    if (queryObject->target == GL_ANY_SAMPLES_PASSED ||
+                        queryObject->target == GL_ANY_SAMPLES_PASSED_CONSERVATIVE) {
+                        result = result != 0 ? 1 : 0;
+                    }
                     // Final value produced (or no GetQueryResult64 hook: the
                     // query degrades to a zero result); the backend handle is
                     // consumed and the value cached for later reads.
@@ -144,6 +228,21 @@ namespace MobileGL::MG_Impl::GLImpl {
                 return false;
             }
         }
+
+        template <typename T>
+        void GetQueryBufferObject(GLuint id, GLuint buffer, GLenum pname, GLintptr offset, const char* function) {
+            SharedPtr<MG_State::GLState::BufferObject> bufferObject;
+            if (!ResolveQueryResultDestination(buffer, offset, sizeof(T), function, bufferObject)) return;
+
+            Uint64 value = 0;
+            Bool valueProduced = false;
+            if (!GetQueryObjectValue(id, pname, function, value, &valueProduced)) return;
+            // GL_QUERY_RESULT_NO_WAIT on a result that has not landed writes nothing at all.
+            if (!valueProduced) return;
+
+            const T narrowed = static_cast<T>(value);
+            bufferObject->UploadSubData({const_cast<T*>(&narrowed), sizeof(T)}, static_cast<SizeT>(offset));
+        }
     } // namespace
 
     void GenQueries(GLsizei n, GLuint* ids) {
@@ -164,6 +263,41 @@ namespace MobileGL::MG_Impl::GLImpl {
         }
     }
 
+    // glCreateQueries differs from glGenQueries in creating the objects outright, with their
+    // target already fixed and the rest of their state at the defaults (GL 4.6 core 4.2.1).
+    void CreateQueries(GLenum target, GLsizei n, GLuint* ids) {
+        switch (target) {
+        case GL_SAMPLES_PASSED:
+        case GL_ANY_SAMPLES_PASSED:
+        case GL_ANY_SAMPLES_PASSED_CONSERVATIVE:
+        case GL_TIME_ELAPSED:
+        case GL_TIMESTAMP:
+        case GL_PRIMITIVES_GENERATED:
+        case GL_TRANSFORM_FEEDBACK_PRIMITIVES_WRITTEN:
+            break;
+        default:
+            RecordQueryError(ErrorCode::InvalidEnum, __FUNCTION__, "Query target is not accepted.");
+            return;
+        }
+        if (n < 0) {
+            RecordQueryError(ErrorCode::InvalidValue, __FUNCTION__, "n cannot be negative.");
+            return;
+        }
+        if (!ids) {
+            return;
+        }
+        const std::lock_guard<std::mutex> lock(g_queryObjectsMutex);
+        for (GLsizei i = 0; i < n; ++i) {
+            const GLuint id = g_nextQueryId++;
+            auto* queryObject = new QueryObject;
+            queryObject->id = id;
+            queryObject->target = target;
+            queryObject->created = true;
+            g_liveQueryObjects[id] = queryObject;
+            ids[i] = id;
+        }
+    }
+
     void DeleteQueries(GLsizei n, const GLuint* ids) {
         if (n < 0) {
             RecordQueryError(ErrorCode::InvalidValue, __FUNCTION__, "n cannot be negative.");
@@ -180,7 +314,24 @@ namespace MobileGL::MG_Impl::GLImpl {
             }
             QueryObject* queryObject = it->second;
             if (queryObject->active) {
-                EndTimeElapsedQueryLocked(queryObject); // implicitly end before deletion
+                // Implicitly end before deletion, releasing the matching active slot.
+                if (queryObject->target == GL_SAMPLES_PASSED || queryObject->target == GL_ANY_SAMPLES_PASSED ||
+                    queryObject->target == GL_ANY_SAMPLES_PASSED_CONSERVATIVE) {
+                    if (const auto endOcclusionQuery = MG_Backend::gBackendFunctionsTable.GL.EndOcclusionQuery;
+                        endOcclusionQuery && queryObject->backendHandle) {
+                        endOcclusionQuery(queryObject->backendHandle);
+                    }
+                    queryObject->active = false;
+                    g_activeSamplesPassedQueryId = 0;
+                } else if (queryObject->target == GL_TRANSFORM_FEEDBACK_PRIMITIVES_WRITTEN ||
+                           queryObject->target == GL_PRIMITIVES_GENERATED) {
+                    queryObject->active = false;
+                    (queryObject->target == GL_TRANSFORM_FEEDBACK_PRIMITIVES_WRITTEN
+                         ? g_activePrimitivesWrittenQueryId
+                         : g_activePrimitivesGeneratedQueryId) = 0;
+                } else {
+                    EndTimeElapsedQueryLocked(queryObject);
+                }
             }
             if (queryObject->backendHandle) {
                 if (const auto deleteBackendQuery = MG_Backend::gBackendFunctionsTable.GL.DeleteBackendQuery) {
@@ -198,16 +349,23 @@ namespace MobileGL::MG_Impl::GLImpl {
             return GL_FALSE;
         }
         const std::lock_guard<std::mutex> lock(g_queryObjectsMutex);
-        // Gen'd ids count as query objects here: the registry creates live
-        // objects at GenQueries time.
-        return FindQueryObjectLocked(id) != nullptr ? GL_TRUE : GL_FALSE;
+        // A name from glGenQueries is not yet a query object: it becomes one when it is first
+        // used with BeginQuery/QueryCounter (which is what a non-zero target records), or
+        // immediately if it came from glCreateQueries.
+        const auto* queryObject = FindQueryObjectLocked(id);
+        return (queryObject != nullptr && (queryObject->created || queryObject->target != 0)) ? GL_TRUE : GL_FALSE;
     }
 
     void BeginQuery(GLenum target, GLuint id) {
-        if (target != GL_TIME_ELAPSED) {
-            // Only GL_TIME_ELAPSED timer queries are implemented (occlusion and
-            // primitive queries remain stubs); GL_TIMESTAMP is not a valid
-            // BeginQuery target either.
+        const Bool isTransformFeedbackQuery =
+            target == GL_TRANSFORM_FEEDBACK_PRIMITIVES_WRITTEN || target == GL_PRIMITIVES_GENERATED;
+        const Bool isOcclusionQuery =
+            (target == GL_SAMPLES_PASSED || target == GL_ANY_SAMPLES_PASSED ||
+             target == GL_ANY_SAMPLES_PASSED_CONSERVATIVE) &&
+            MG_Backend::gBackendFunctionsTable.GL.BeginOcclusionQuery != nullptr;
+        if (target != GL_TIME_ELAPSED && !isTransformFeedbackQuery && !isOcclusionQuery) {
+            // GL_TIMESTAMP is not a valid BeginQuery target; the occlusion targets
+            // need backend support.
             RecordQueryError(ErrorCode::InvalidEnum, __FUNCTION__, "Query target is not supported.");
             return;
         }
@@ -221,9 +379,13 @@ namespace MobileGL::MG_Impl::GLImpl {
             RecordQueryError(ErrorCode::InvalidOperation, __FUNCTION__, "Query object does not exist.");
             return;
         }
-        if (g_activeTimeElapsedQueryId != 0) {
+        GLuint& activeQueryId = isTransformFeedbackQuery
+            ? (target == GL_TRANSFORM_FEEDBACK_PRIMITIVES_WRITTEN ? g_activePrimitivesWrittenQueryId
+                                                                  : g_activePrimitivesGeneratedQueryId)
+            : (isOcclusionQuery ? g_activeSamplesPassedQueryId : g_activeTimeElapsedQueryId);
+        if (activeQueryId != 0) {
             RecordQueryError(ErrorCode::InvalidOperation, __FUNCTION__,
-                             "A query is already active on GL_TIME_ELAPSED.");
+                             "A query is already active on this target.");
             return;
         }
         if (queryObject->active) {
@@ -239,25 +401,72 @@ namespace MobileGL::MG_Impl::GLImpl {
         ResetQueryObjectLocked(queryObject); // discard any previous result
         queryObject->target = target;
         queryObject->active = true;
-        const auto beginTimeElapsedQuery = MG_Backend::gBackendFunctionsTable.GL.BeginTimeElapsedQuery;
-        queryObject->backendHandle =
-            (!TimerQueryDisabled() && beginTimeElapsedQuery) ? beginTimeElapsedQuery() : nullptr;
-        g_activeTimeElapsedQueryId = id;
+        if (isTransformFeedbackQuery) {
+            // Prefer real GPU transform-feedback queries (exact with geometry shaders);
+            // the CPU accounting delta stays as the fallback when the backend lacks them.
+            const auto beginXfbPrimitivesQuery = MG_Backend::gBackendFunctionsTable.GL.BeginXfbPrimitivesQuery;
+            queryObject->backendHandle =
+                beginXfbPrimitivesQuery ? beginXfbPrimitivesQuery(target == GL_PRIMITIVES_GENERATED) : nullptr;
+            queryObject->counterSnapshot = MG_State::pGLContext->GetTransformFeedbackPrimitiveCounter();
+        } else if (isOcclusionQuery) {
+            queryObject->backendHandle = MG_Backend::gBackendFunctionsTable.GL.BeginOcclusionQuery();
+        } else {
+            const auto beginTimeElapsedQuery = MG_Backend::gBackendFunctionsTable.GL.BeginTimeElapsedQuery;
+            queryObject->backendHandle =
+                (!TimerQueryDisabled() && beginTimeElapsedQuery) ? beginTimeElapsedQuery() : nullptr;
+        }
+        activeQueryId = id;
     }
 
     void EndQuery(GLenum target) {
-        if (target != GL_TIME_ELAPSED) {
+        const Bool isTransformFeedbackQuery =
+            target == GL_TRANSFORM_FEEDBACK_PRIMITIVES_WRITTEN || target == GL_PRIMITIVES_GENERATED;
+        const Bool isOcclusionQuery =
+            (target == GL_SAMPLES_PASSED || target == GL_ANY_SAMPLES_PASSED ||
+             target == GL_ANY_SAMPLES_PASSED_CONSERVATIVE) &&
+            MG_Backend::gBackendFunctionsTable.GL.BeginOcclusionQuery != nullptr;
+        if (target != GL_TIME_ELAPSED && !isTransformFeedbackQuery && !isOcclusionQuery) {
             RecordQueryError(ErrorCode::InvalidEnum, __FUNCTION__, "Query target is not supported.");
             return;
         }
         const std::lock_guard<std::mutex> lock(g_queryObjectsMutex);
-        if (g_activeTimeElapsedQueryId == 0) {
-            RecordQueryError(ErrorCode::InvalidOperation, __FUNCTION__, "No query is active on GL_TIME_ELAPSED.");
+        GLuint& activeQueryId = isTransformFeedbackQuery
+            ? (target == GL_TRANSFORM_FEEDBACK_PRIMITIVES_WRITTEN ? g_activePrimitivesWrittenQueryId
+                                                                  : g_activePrimitivesGeneratedQueryId)
+            : (isOcclusionQuery ? g_activeSamplesPassedQueryId : g_activeTimeElapsedQueryId);
+        if (activeQueryId == 0) {
+            RecordQueryError(ErrorCode::InvalidOperation, __FUNCTION__, "No query is active on this target.");
             return;
         }
-        auto* queryObject = FindQueryObjectLocked(g_activeTimeElapsedQueryId);
+        auto* queryObject = FindQueryObjectLocked(activeQueryId);
         if (!queryObject) {
-            g_activeTimeElapsedQueryId = 0; // should not happen; keep state consistent
+            activeQueryId = 0; // should not happen; keep state consistent
+            return;
+        }
+        if (isTransformFeedbackQuery) {
+            if (queryObject->backendHandle) {
+                if (const auto endXfbPrimitivesQuery = MG_Backend::gBackendFunctionsTable.GL.EndXfbPrimitivesQuery) {
+                    endXfbPrimitivesQuery(queryObject->backendHandle);
+                }
+                // Result comes from the GPU query at read time.
+            } else {
+                queryObject->cachedResult =
+                    MG_State::pGLContext->GetTransformFeedbackPrimitiveCounter() - queryObject->counterSnapshot;
+                queryObject->resultCached = true;
+            }
+            queryObject->active = false;
+            queryObject->ended = true;
+            activeQueryId = 0;
+            return;
+        }
+        if (isOcclusionQuery) {
+            if (const auto endOcclusionQuery = MG_Backend::gBackendFunctionsTable.GL.EndOcclusionQuery;
+                endOcclusionQuery && queryObject->backendHandle) {
+                endOcclusionQuery(queryObject->backendHandle);
+            }
+            queryObject->active = false;
+            queryObject->ended = true;
+            activeQueryId = 0;
             return;
         }
         EndTimeElapsedQueryLocked(queryObject);
@@ -303,9 +512,25 @@ namespace MobileGL::MG_Impl::GLImpl {
         switch (pname) {
         case GL_CURRENT_QUERY: {
             const std::lock_guard<std::mutex> lock(g_queryObjectsMutex);
-            // Only GL_TIME_ELAPSED queries can be active; GL_TIMESTAMP queries
-            // never are, and other targets remain unimplemented.
-            *params = target == GL_TIME_ELAPSED ? static_cast<GLint>(g_activeTimeElapsedQueryId) : 0;
+            switch (target) {
+            case GL_TIME_ELAPSED:
+                *params = static_cast<GLint>(g_activeTimeElapsedQueryId);
+                break;
+            case GL_SAMPLES_PASSED:
+            case GL_ANY_SAMPLES_PASSED:
+            case GL_ANY_SAMPLES_PASSED_CONSERVATIVE:
+                *params = static_cast<GLint>(g_activeSamplesPassedQueryId);
+                break;
+            case GL_TRANSFORM_FEEDBACK_PRIMITIVES_WRITTEN:
+                *params = static_cast<GLint>(g_activePrimitivesWrittenQueryId);
+                break;
+            case GL_PRIMITIVES_GENERATED:
+                *params = static_cast<GLint>(g_activePrimitivesGeneratedQueryId);
+                break;
+            default:
+                *params = 0;
+                break;
+            }
             return;
         }
         case GL_QUERY_COUNTER_BITS: {
@@ -313,7 +538,13 @@ namespace MobileGL::MG_Impl::GLImpl {
             // time: IsTimerQuerySupported is the dynamic truth (extension /
             // entry points / timestamp valid bits at call time, not at table
             // init), and the MOBILEGL_DISABLE_TIMERQUERY kill switch always
-            // wins. Non-timer targets remain unimplemented and report 0.
+            // wins.
+            if (target == GL_SAMPLES_PASSED || target == GL_ANY_SAMPLES_PASSED ||
+                target == GL_ANY_SAMPLES_PASSED_CONSERVATIVE) {
+                const Bool occlusionSupported = MG_Backend::gBackendFunctionsTable.GL.BeginOcclusionQuery != nullptr;
+                *params = occlusionSupported ? (target == GL_SAMPLES_PASSED ? 32 : 1) : 0;
+                return;
+            }
             const Bool timerTarget = target == GL_TIME_ELAPSED || target == GL_TIMESTAMP;
             const auto isTimerQuerySupported = MG_Backend::gBackendFunctionsTable.GL.IsTimerQuerySupported;
             const Bool supported =
@@ -327,9 +558,26 @@ namespace MobileGL::MG_Impl::GLImpl {
         }
     }
 
+    void GetQueryBufferObjectiv(GLuint id, GLuint buffer, GLenum pname, GLintptr offset) {
+        GetQueryBufferObject<GLint>(id, buffer, pname, offset, __FUNCTION__);
+    }
+
+    void GetQueryBufferObjectuiv(GLuint id, GLuint buffer, GLenum pname, GLintptr offset) {
+        GetQueryBufferObject<GLuint>(id, buffer, pname, offset, __FUNCTION__);
+    }
+
+    void GetQueryBufferObjecti64v(GLuint id, GLuint buffer, GLenum pname, GLintptr offset) {
+        GetQueryBufferObject<GLint64>(id, buffer, pname, offset, __FUNCTION__);
+    }
+
+    void GetQueryBufferObjectui64v(GLuint id, GLuint buffer, GLenum pname, GLintptr offset) {
+        GetQueryBufferObject<GLuint64>(id, buffer, pname, offset, __FUNCTION__);
+    }
+
     void GetQueryObjectiv(GLuint id, GLenum pname, GLint* params) {
         Uint64 value = 0;
-        if (!GetQueryObjectValue(id, pname, __FUNCTION__, value) || !params) {
+        Bool valueProduced = false;
+        if (!GetQueryObjectValue(id, pname, __FUNCTION__, value, &valueProduced) || !valueProduced || !params) {
             return;
         }
         constexpr Uint64 kMaxInt = static_cast<Uint64>(INT_MAX);
@@ -338,7 +586,8 @@ namespace MobileGL::MG_Impl::GLImpl {
 
     void GetQueryObjectuiv(GLuint id, GLenum pname, GLuint* params) {
         Uint64 value = 0;
-        if (!GetQueryObjectValue(id, pname, __FUNCTION__, value) || !params) {
+        Bool valueProduced = false;
+        if (!GetQueryObjectValue(id, pname, __FUNCTION__, value, &valueProduced) || !valueProduced || !params) {
             return;
         }
         *params = static_cast<GLuint>(value & 0xFFFFFFFFull);
@@ -346,7 +595,8 @@ namespace MobileGL::MG_Impl::GLImpl {
 
     void GetQueryObjecti64v(GLuint id, GLenum pname, GLint64* params) {
         Uint64 value = 0;
-        if (!GetQueryObjectValue(id, pname, __FUNCTION__, value) || !params) {
+        Bool valueProduced = false;
+        if (!GetQueryObjectValue(id, pname, __FUNCTION__, value, &valueProduced) || !valueProduced || !params) {
             return;
         }
         *params = static_cast<GLint64>(value);
@@ -354,9 +604,48 @@ namespace MobileGL::MG_Impl::GLImpl {
 
     void GetQueryObjectui64v(GLuint id, GLenum pname, GLuint64* params) {
         Uint64 value = 0;
-        if (!GetQueryObjectValue(id, pname, __FUNCTION__, value) || !params) {
+        Bool valueProduced = false;
+        if (!GetQueryObjectValue(id, pname, __FUNCTION__, value, &valueProduced) || !valueProduced || !params) {
             return;
         }
         *params = static_cast<GLuint64>(value);
     }
+
+    namespace {
+        // The indexed query entry points differ from the plain ones only in the vertex
+        // stream they address (GL 4.6 core 4.2.1): index must be below GL_MAX_VERTEX_STREAMS
+        // for the two transform feedback targets and zero for every other target. With a
+        // single vertex stream both bounds are 1, so a valid call is always index 0 and
+        // forwards to the unindexed implementation.
+        Bool ValidateQueryStreamIndex(const char* function, GLenum target, GLuint index) {
+            const Bool perStreamTarget =
+                target == GL_PRIMITIVES_GENERATED || target == GL_TRANSFORM_FEEDBACK_PRIMITIVES_WRITTEN;
+            GLint maxVertexStreams = 1;
+            if (perStreamTarget) {
+                GetIntegerv(GL_MAX_VERTEX_STREAMS, &maxVertexStreams);
+            }
+            if (index < static_cast<GLuint>(std::max(maxVertexStreams, 1))) {
+                return true;
+            }
+            RecordQueryError(ErrorCode::InvalidValue, function,
+                             perStreamTarget ? "index is not less than GL_MAX_VERTEX_STREAMS."
+                                             : "index must be zero for this query target.");
+            return false;
+        }
+    } // namespace
+
+    void BeginQueryIndexed(GLenum target, GLuint index, GLuint id) {
+        if (!ValidateQueryStreamIndex(__FUNCTION__, target, index)) return;
+        BeginQuery(target, id);
+    }
+
+    void EndQueryIndexed(GLenum target, GLuint index) {
+        if (!ValidateQueryStreamIndex(__FUNCTION__, target, index)) return;
+        EndQuery(target);
+    }
+
+    void GetQueryIndexediv(GLenum target, GLuint index, GLenum pname, GLint* params) {
+        if (!ValidateQueryStreamIndex(__FUNCTION__, target, index)) return;
+        GetQueryiv(target, pname, params);
+    }
 } // namespace MobileGL::MG_Impl::GLImpl

MobileGL/MG_Impl/GLImpl/Query/GL_Query.h

@@ -11,14 +11,22 @@
 
 namespace MobileGL::MG_Impl::GLImpl {
     void GenQueries(GLsizei n, GLuint* ids);
+    void CreateQueries(GLenum target, GLsizei n, GLuint* ids);
     void DeleteQueries(GLsizei n, const GLuint* ids);
     GLboolean IsQuery(GLuint id);
     void BeginQuery(GLenum target, GLuint id);
     void EndQuery(GLenum target);
     void GetQueryiv(GLenum target, GLenum pname, GLint* params);
+    void BeginQueryIndexed(GLenum target, GLuint index, GLuint id);
+    void EndQueryIndexed(GLenum target, GLuint index);
+    void GetQueryIndexediv(GLenum target, GLuint index, GLenum pname, GLint* params);
     void GetQueryObjectiv(GLuint id, GLenum pname, GLint* params);
     void GetQueryObjectuiv(GLuint id, GLenum pname, GLuint* params);
     void GetQueryObjecti64v(GLuint id, GLenum pname, GLint64* params);
     void GetQueryObjectui64v(GLuint id, GLenum pname, GLuint64* params);
+    void GetQueryBufferObjectiv(GLuint id, GLuint buffer, GLenum pname, GLintptr offset);
+    void GetQueryBufferObjectuiv(GLuint id, GLuint buffer, GLenum pname, GLintptr offset);
+    void GetQueryBufferObjecti64v(GLuint id, GLuint buffer, GLenum pname, GLintptr offset);
+    void GetQueryBufferObjectui64v(GLuint id, GLuint buffer, GLenum pname, GLintptr offset);
     void QueryCounter(GLuint id, GLenum target);
 } // namespace MobileGL::MG_Impl::GLImpl

MobileGL/MG_Impl/GLImpl/RenderState/GL_RenderState.cpp

@@ -649,7 +649,9 @@ namespace MobileGL::MG_Impl::GLImpl {
     }
 
     void ClearDepth_State(GLclampd depth) {
-        MG_State::pGLContext->SetClearDepth(static_cast<Float>(depth));
+        // GL 3.3 §4.2.3: the clear depth is clamped to [0,1] at specification time (Vulkan clear
+        // values additionally require it: VUID-VkClearDepthStencilValue-depth-00022).
+        MG_State::pGLContext->SetClearDepth(ClampUnitFloat(static_cast<Float>(depth)));
     }
 
     void ClearColor_State(GLfloat red, GLfloat green, GLfloat blue, GLfloat alpha) {

MobileGL/MG_Impl/GLImpl/Sampler/GL_Sampler.cpp

@@ -8,13 +8,20 @@
 
 #include "GL_Sampler.h"
 #include "Validators.h"
+#include "../Getter/GL_Getter.h"
 #include <MG_State/GLState/Core.h>
 #include <MG_Util/Converters/GLToMG/TextureEnumConverter.h>
 #include <MG_Util/Converters/MGToGL/TextureEnumConverter.h>
 
 namespace MobileGL::MG_Impl::GLImpl {
     namespace {
-        Bool ValidateSamplerParameterValue(GLenum pname, const void* param, Bool isFloat, Bool isInteger) {
+        Float ReadSamplerScalar(const void* param, Bool isFloat, Bool isUnsignedInteger) {
+            if (isFloat) return *(const GLfloat*)param;
+            if (isUnsignedInteger) return static_cast<Float>(*(const GLuint*)param);
+            return static_cast<Float>(*(const GLint*)param);
+        }
+
+        Bool ValidateSamplerParameterValue(GLenum pname, const void* param, Bool isFloat, Bool isUnsignedInteger) {
             if (param == nullptr) return false;
 
             switch (pname) {
@@ -22,6 +29,18 @@ namespace MobileGL::MG_Impl::GLImpl {
             case GL_TEXTURE_MAX_LOD:
             case GL_TEXTURE_LOD_BIAS:
                 return true;
+            // Four components, and GL puts no range on them - a border colour outside [0,1] is
+            // clamped when a fixed-point format is sampled, not rejected here. The scalar readers
+            // below would look at one component and invent an error.
+            case GL_TEXTURE_BORDER_COLOR:
+                return true;
+            case GL_TEXTURE_MAX_ANISOTROPY_EXT:
+                if (ReadSamplerScalar(param, isFloat, isUnsignedInteger) >= 1.0f) return true;
+                MG_State::pGLContext->RecordError(
+                    ErrorCode::InvalidValue,
+                    MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", "SetSamplerParam_State",
+                                                 "GL_TEXTURE_MAX_ANISOTROPY_EXT must be at least 1.0."));
+                return false;
             default:
                 break;
             }
@@ -29,14 +48,15 @@ namespace MobileGL::MG_Impl::GLImpl {
             if (isFloat) {
                 return SamplerImpl::ValidateSamplerFloatParam(pname, *(const GLfloat*)param);
             }
-            if (isInteger) {
+            if (isUnsignedInteger) {
                 return SamplerImpl::ValidateSamplerIntParam(pname, static_cast<GLint>(*(const GLuint*)param));
             }
             return SamplerImpl::ValidateSamplerIntParam(pname, *(const GLint*)param);
         }
     } // namespace
 
-    void SetSamplerParam_State(GLuint sampler, GLenum pname, const void* param, bool isFloat, bool isInteger) {
+    void SetSamplerParam_State(GLuint sampler, GLenum pname, const void* param, bool isFloat,
+                               bool isUnsignedInteger) {
         if (param == nullptr) return;
         if (!SamplerImpl::ValidateSamplerName(sampler)) return;
 
@@ -47,7 +67,7 @@ namespace MobileGL::MG_Impl::GLImpl {
         }
         auto& samplerObj = MG_State::pGLContext->GetSamplerObject(sampler);
         if (!SamplerImpl::ValidateSamplerObject(sampler)) return;
-        if (!ValidateSamplerParameterValue(pname, param, isFloat, isInteger)) return;
+        if (!ValidateSamplerParameterValue(pname, param, isFloat, isUnsignedInteger)) return;
 
         using namespace MG_Util;
         switch (pname) {
@@ -76,12 +96,29 @@ namespace MobileGL::MG_Impl::GLImpl {
         case GL_TEXTURE_LOD_BIAS:
             samplerObj->SetLodBias(*(const GLfloat*)param);
             break;
+        case GL_TEXTURE_MAX_ANISOTROPY_EXT:
+            samplerObj->SetMaxAnisotropy(ReadSamplerScalar(param, isFloat, isUnsignedInteger));
+            break;
         case GL_TEXTURE_COMPARE_MODE:
             samplerObj->SetCompareMode(MG_Util::ConvertGLEnumToSamplerCompareMode(*(const GLint*)param));
             break;
         case GL_TEXTURE_COMPARE_FUNC:
             samplerObj->SetSamplerCompareFunc(MG_Util::ConvertGLEnumToSamplerCompareFunc(*(const GLint*)param));
             break;
+        case GL_TEXTURE_BORDER_COLOR:
+            // The only four-component sampler parameter: the caller's form decides which
+            // representation is authoritative, and SamplerObject keeps the other two in step.
+            if (isFloat) {
+                const auto* values = (const GLfloat*)param;
+                samplerObj->SetBorderColor(FloatVec4(values[0], values[1], values[2], values[3]));
+            } else if (isUnsignedInteger) {
+                const auto* values = (const GLuint*)param;
+                samplerObj->SetBorderColorUI(UintVec4(values[0], values[1], values[2], values[3]));
+            } else {
+                const auto* values = (const GLint*)param;
+                samplerObj->SetBorderColorI(IntVec4(values[0], values[1], values[2], values[3]));
+            }
+            break;
         default:
             MG_State::pGLContext->RecordError(ErrorCode::InvalidEnum,
                                               MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", "SetSamplerParam_State",
@@ -89,7 +126,8 @@ namespace MobileGL::MG_Impl::GLImpl {
         }
     }
 
-    void GetSamplerParam_State(GLuint sampler, GLenum pname, void* params, bool isFloat, bool isInteger) {
+    void GetSamplerParam_State(GLuint sampler, GLenum pname, void* params, bool isFloat,
+                               bool isUnsignedInteger) {
         if (params == nullptr) return;
         if (!SamplerImpl::ValidateSamplerName(sampler)) return;
 
@@ -129,12 +167,46 @@ namespace MobileGL::MG_Impl::GLImpl {
         case GL_TEXTURE_LOD_BIAS:
             *(GLfloat*)params = samplerObj->GetLodBias();
             break;
+        case GL_TEXTURE_MAX_ANISOTROPY_EXT:
+            if (isFloat) {
+                *(GLfloat*)params = samplerObj->GetMaxAnisotropy();
+            } else if (isUnsignedInteger) {
+                *(GLuint*)params = static_cast<GLuint>(samplerObj->GetMaxAnisotropy());
+            } else {
+                *(GLint*)params = static_cast<GLint>(samplerObj->GetMaxAnisotropy());
+            }
+            break;
         case GL_TEXTURE_COMPARE_MODE:
             *(GLuint*)params = MG_Util::ConvertSamplerCompareModeToGLEnum(samplerObj->GetCompareMode());
             break;
         case GL_TEXTURE_COMPARE_FUNC:
             *(GLuint*)params = MG_Util::ConvertSamplerCompareFuncToGLEnum(samplerObj->GetSamplerCompareFunc());
             break;
+        case GL_TEXTURE_BORDER_COLOR: {
+            if (isFloat) {
+                const auto& color = samplerObj->GetBorderColor();
+                auto* out = (GLfloat*)params;
+                out[0] = color.x();
+                out[1] = color.y();
+                out[2] = color.z();
+                out[3] = color.w();
+            } else if (isUnsignedInteger) {
+                const auto& color = samplerObj->GetBorderColorUI();
+                auto* out = (GLuint*)params;
+                out[0] = color.x();
+                out[1] = color.y();
+                out[2] = color.z();
+                out[3] = color.w();
+            } else {
+                const auto& color = samplerObj->GetBorderColorI();
+                auto* out = (GLint*)params;
+                out[0] = color.x();
+                out[1] = color.y();
+                out[2] = color.z();
+                out[3] = color.w();
+            }
+            break;
+        }
         default:
             MG_State::pGLContext->RecordError(ErrorCode::InvalidEnum,
                                               MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", "GetSamplerParam_State",
@@ -158,6 +230,11 @@ namespace MobileGL::MG_Impl::GLImpl {
         static thread_local Vector<GLuint> names;
         MG_State::pGLContext->GenSamplerNames(count, names);
         Memcpy(samplers, names.data(), count * sizeof(GLuint));
+        // Unlike textures/buffers, glGenSamplers CREATES the sampler objects: each name
+        // is immediately a sampler (glIsSampler == GL_TRUE before any bind).
+        for (GLsizei i = 0; i < count; ++i) {
+            MG_State::pGLContext->CreateSamplerObject(names[i]);
+        }
     }
 
     void DeleteSamplers_State(GLsizei count, const GLuint* samplers) {
@@ -192,9 +269,20 @@ namespace MobileGL::MG_Impl::GLImpl {
         }
     }
 
+    // The number of texture units a sampler may be bound to. GL 3.3 core 3.8.2 names
+    // GL_MAX_COMBINED_TEXTURE_IMAGE_UNITS, which is what the backend advertises; the frontend's
+    // MAX_TEXTURE_IMAGE_UNITS is only the capacity of the unit array, so it is a clamp on the
+    // answer and never the answer itself - gating on it alone accepts every unit up to 192 no
+    // matter what the driver reports.
+    static GLint GetSamplerBindableTextureUnitCount() {
+        GLint maxTextureUnits = 0;
+        GetIntegerv(GL_MAX_COMBINED_TEXTURE_IMAGE_UNITS, &maxTextureUnits);
+        return std::min<GLint>(std::max(maxTextureUnits, 0), MG_State::GLState::TextureState::MAX_TEXTURE_IMAGE_UNITS);
+    }
+
     void BindSampler_State(GLuint unit, GLuint sampler) {
         MGLOG_D("BindSampler_State: unit = %u, sampler = %u", unit, sampler);
-        if (unit >= MG_State::GLState::TextureState::MAX_TEXTURE_IMAGE_UNITS) {
+        if (static_cast<Uint64>(unit) >= static_cast<Uint64>(GetSamplerBindableTextureUnitCount())) {
             MG_State::pGLContext->RecordError(
                 ErrorCode::InvalidValue,
                 MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", "BindSampler", "texture unit out of range"));
@@ -206,7 +294,16 @@ namespace MobileGL::MG_Impl::GLImpl {
         if (sampler == 0) {
             textureUnit.SetSamplerObject(nullptr);
         } else {
-            if (!SamplerImpl::ValidateSamplerName(sampler)) return;
+            // GL 3.3 core 3.8.2: BindSampler on a name GenSamplers never returned - or one already
+            // deleted - is INVALID_OPERATION. SamplerParameter* raises INVALID_VALUE for the same
+            // name, which is why this cannot go through the shared SamplerImpl validator.
+            if (!MG_State::pGLContext->ValidateSamplerName(sampler)) {
+                MG_State::pGLContext->RecordError(
+                    ErrorCode::InvalidOperation,
+                    MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", "BindSampler_State",
+                                                 std::format("Invalid sampler name {}", sampler)));
+                return;
+            }
             Bool doesSamplerObjectCreated = MG_State::pGLContext->ValidateSamplerObject(sampler);
             if (!doesSamplerObjectCreated) {
                 MG_State::pGLContext->CreateSamplerObject(sampler);
@@ -224,6 +321,20 @@ namespace MobileGL::MG_Impl::GLImpl {
                 MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", "BindSamplers", "count must be non-negative"));
             return;
         }
+        // ARB_multi_bind: the whole [first, first + count) range is checked up front and a
+        // range that runs past the last texture unit is INVALID_OPERATION - not the
+        // INVALID_VALUE the single-bind BindSampler_State reports per element, and nothing is
+        // bound when it fails. Both gates read the same limit (see
+        // GetSamplerBindableTextureUnitCount), so an out-of-range multi-bind can no longer slip
+        // past this check and be caught one element at a time with the wrong error class.
+        const GLint maxTextureUnits = GetSamplerBindableTextureUnitCount();
+        if (static_cast<Uint64>(first) + static_cast<Uint64>(count) > static_cast<Uint64>(maxTextureUnits)) {
+            MG_State::pGLContext->RecordError(
+                ErrorCode::InvalidOperation,
+                MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", "BindSamplers",
+                                             "first + count exceeds the number of texture units."));
+            return;
+        }
 
         for (GLsizei i = 0; i < count; ++i) {
             BindSampler_State(first + i, samplers ? samplers[i] : 0);
@@ -240,7 +351,7 @@ namespace MobileGL::MG_Impl::GLImpl {
     }
 
     void SamplerParameterIiv(GLuint sampler, GLenum pname, const GLint* param) {
-        SetSamplerParam_State(sampler, pname, param, false, true);
+        SetSamplerParam_State(sampler, pname, param, false, false);
     }
 
     void SamplerParameteriv(GLuint sampler, GLenum pname, const GLint* param) {
@@ -268,7 +379,7 @@ namespace MobileGL::MG_Impl::GLImpl {
     }
 
     void GetSamplerParameterIiv(GLuint sampler, GLenum pname, GLint* params) {
-        GetSamplerParam_State(sampler, pname, params, false, true);
+        GetSamplerParam_State(sampler, pname, params, false, false);
     }
 
     void GetSamplerParameterfv(GLuint sampler, GLenum pname, GLfloat* params) {

MobileGL/MG_Impl/GLImpl/Sampler/Validators.cpp

@@ -75,7 +75,11 @@ namespace MobileGL::MG_Impl::GLImpl::SamplerImpl {
             break;
 
         case GL_TEXTURE_COMPARE_FUNC:
-            if (param < GL_LEQUAL || param > GL_ALWAYS) {
+            // The eight depth-compare functions are contiguous from GL_NEVER (0x0200) to
+            // GL_ALWAYS (0x0207); GL_LEQUAL sits in the middle of that block, so starting
+            // the range there rejected NEVER/LESS/EQUAL and let GREATER/NOTEQUAL/GEQUAL
+            // through only by accident of them being above LEQUAL.
+            if (param < GL_NEVER || param > GL_ALWAYS) {
                 MG_State::pGLContext->RecordError(ErrorCode::InvalidEnum,
                                                   MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", "ValidateSamplerParam",
                                                                                "Invalid compare function parameter"));
@@ -99,6 +103,16 @@ namespace MobileGL::MG_Impl::GLImpl::SamplerImpl {
         case GL_TEXTURE_LOD_BIAS:
             return true;
 
+        case GL_TEXTURE_MAX_ANISOTROPY_EXT:
+            if (!(param >= 1.0f)) {
+                MG_State::pGLContext->RecordError(
+                    ErrorCode::InvalidValue,
+                    MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", "ValidateSamplerFloatParam",
+                                                 "GL_TEXTURE_MAX_ANISOTROPY_EXT must be at least 1.0."));
+                return false;
+            }
+            return true;
+
         case GL_TEXTURE_BORDER_COLOR:
             if (param < 0.0f || param > 1.0f) {
                 MG_State::pGLContext->RecordError(
@@ -125,6 +139,16 @@ namespace MobileGL::MG_Impl::GLImpl::SamplerImpl {
             }
             return true;
 
+        case GL_TEXTURE_MAX_ANISOTROPY_EXT:
+            if (param < 1) {
+                MG_State::pGLContext->RecordError(
+                    ErrorCode::InvalidValue,
+                    MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", "ValidateSamplerIntParam",
+                                                 "GL_TEXTURE_MAX_ANISOTROPY_EXT must be at least 1."));
+                return false;
+            }
+            return true;
+
         default:
             return ValidateSamplerParam(pname, static_cast<GLenum>(param));
         }

MobileGL/MG_Impl/GLImpl/Sync/GL_Sync.cpp

@@ -133,4 +133,33 @@ namespace MobileGL::MG_Impl::GLImpl {
             values[0] = value;
         }
     }
+
+    void DestroyAllSyncObjects() {
+        // Detach the registry under the lock, release outside it. Entries the app
+        // already deleted were erased by DeleteSync, so nothing here double-frees;
+        // a DeleteSync racing this sweep finds an empty registry and returns. A
+        // thread still blocked inside ClientWaitSync/GetSynciv during teardown
+        // holds a raw SyncObject* these deletes invalidate - the same undefined
+        // race an app-driven DeleteSync already has.
+        UnorderedMap<GLsync, SyncObject*> orphans;
+        {
+            const std::lock_guard<std::mutex> lock(g_syncObjectsMutex);
+            orphans.swap(g_liveSyncObjects);
+        }
+        if (orphans.empty()) {
+            return;
+        }
+        // Both backends' DeleteSync only free the heap wrapper once their GL
+        // context/renderer is gone (generation/current-thread guards), so this is
+        // safe after the backend has released its EGL resources - but not after
+        // the function table itself is cleared.
+        const auto backendDeleteSync = MG_Backend::gBackendFunctionsTable.GL.DeleteSync;
+        for (const auto& [_, syncObject] : orphans) {
+            if (backendDeleteSync && syncObject->backendHandle) {
+                backendDeleteSync(syncObject->backendHandle);
+            }
+            delete syncObject;
+        }
+        MGLOG_D("DestroyAllSyncObjects: reclaimed %zu sync object(s) the app left undeleted", orphans.size());
+    }
 } // namespace MobileGL::MG_Impl::GLImpl

MobileGL/MG_Impl/GLImpl/Sync/GL_Sync.h

@@ -16,4 +16,12 @@ namespace MobileGL::MG_Impl::GLImpl {
     void WaitSync(GLsync sync, GLbitfield flags, GLuint64 timeout);
     void DeleteSync(GLsync sync);
     void GetSynciv(GLsync sync, GLenum pname, GLsizei bufSize, GLsizei* length, GLint* values);
+    // Destroys every still-registered sync object exactly as DeleteSync would.
+    // GL requires syncs to die with their context; called only from full library
+    // teardown (DestroyImpl), where no context survives on any thread, so the
+    // process-global registry can be drained wholesale. Must run while the
+    // backend function table is still populated: each backend handle has to be
+    // released by the backend that created it, never by a later re-initialized
+    // one.
+    void DestroyAllSyncObjects();
 } // namespace MobileGL::MG_Impl::GLImpl

MobileGL/MG_Impl/GLImpl/Texture/GL_Texture.h

@@ -11,6 +11,13 @@
 
 namespace MobileGL::MG_Impl::GLImpl {
     /* @INSERTION_POINT:FUNCTION_DECLARATION@ */
+    // The sized internal formats a buffer texture accepts (GL 4.6 core table 8.16). The buffer
+    // clears take the same list, so it is shared rather than written out twice.
+    Bool IsBufferTextureInternalFormat(GLenum internalformat);
+
+    void ClearTexImage(GLuint texture, GLint level, GLenum format, GLenum type, const void* data);
+    void ClearTexSubImage(GLuint texture, GLint level, GLint xoffset, GLint yoffset, GLint zoffset, GLsizei width,
+                          GLsizei height, GLsizei depth, GLenum format, GLenum type, const void* data);
     void BindImageTexture(GLuint unit, GLuint texture, GLint level, GLboolean layered, GLint layer, GLenum access,
                           GLenum format);
     void GenerateMipmap(GLenum target);
@@ -39,6 +46,10 @@ namespace MobileGL::MG_Impl::GLImpl {
     void GenerateTextureMipmap(GLuint texture);
     void BindTextureUnit(GLuint unit, GLuint texture);
     void GetTextureImage(GLuint texture, GLint level, GLenum format, GLenum type, GLsizei bufSize, void* pixels);
+    void GetCompressedTextureImage(GLuint texture, GLint level, GLsizei bufSize, void* pixels);
+    void TexBufferRange(GLenum target, GLenum internalformat, GLuint buffer, GLintptr offset, GLsizeiptr size);
+    void TextureBuffer(GLuint texture, GLenum internalformat, GLuint buffer);
+    void TextureBufferRange(GLuint texture, GLenum internalformat, GLuint buffer, GLintptr offset, GLsizeiptr size);
     void GetTextureSubImage(GLuint texture, GLint level, GLint xoffset, GLint yoffset, GLint zoffset, GLsizei width,
                             GLsizei height, GLsizei depth, GLenum format, GLenum type, GLsizei bufSize, void* pixels);
     void GetTextureParameterfv(GLuint texture, GLenum pname, GLfloat* params);
@@ -95,6 +106,11 @@ namespace MobileGL::MG_Impl::GLImpl {
                            GLsizei width, GLsizei height);
     void CopyTexSubImage2D(GLenum target, GLint level, GLint xoffset, GLint yoffset, GLint x, GLint y, GLsizei width,
                            GLsizei height);
+    void CopyTextureSubImage1D(GLuint texture, GLint level, GLint xoffset, GLint x, GLint y, GLsizei width);
+    void CopyTextureSubImage3D(GLuint texture, GLint level, GLint xoffset, GLint yoffset, GLint zoffset, GLint x,
+                               GLint y, GLsizei width, GLsizei height);
+    void CopyTextureSubImage2D(GLuint texture, GLint level, GLint xoffset, GLint yoffset, GLint x, GLint y,
+                               GLsizei width, GLsizei height);
     void CopyTexSubImage1D(GLenum target, GLint level, GLint xoffset, GLint x, GLint y, GLsizei width);
     void CopyTexImage2D(GLenum target, GLint level, GLenum internalformat, GLint x, GLint y, GLsizei width,
                         GLsizei height, GLint border);

MobileGL/MG_Impl/GLImpl/Texture/ProxyTexture.cpp

@@ -14,7 +14,8 @@
 #include <MG_State/GLState/TextureState/TextureObjectStubs.h>
 
 namespace MobileGL::MG_Impl::GLImpl::TextureImpl {
-    UniquePtr<ProxyTextureManager> pProxyTextureManager;
+    // Leak-at-exit storage; see GlobalObjects.cpp.
+    UniquePtr<ProxyTextureManager>& pProxyTextureManager = *new UniquePtr<ProxyTextureManager>();
 
     Bool IsProxyTextureTarget(TextureUploadTarget target) {
         switch (target) {