[Fix] (MG_Backend/DirectVulkan, ShaderTranspiler, MG_Test, TraceReplay): make iterationRP retrace pass on 64-lane Vulkan devices with subgroup-width emulation and format-aware readback

# Conflicts:

.gitattributes

@@ -0,0 +1,4 @@
+tools/trace_replay/fixtures/*.tgz filter=lfs diff=lfs merge=lfs -text
+tools/trace_replay/fixtures/*.png filter=lfs diff=lfs merge=lfs -text
+tools/trace_replay/fixtures/openra.tgz -filter -diff -merge -text
+tools/trace_replay/fixtures/openra.0000031249.png -filter -diff -merge -text

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

@@ -0,0 +1,208 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+if [ "$#" -lt 1 ] || [ "$#" -gt 2 ]; then
+  echo "usage: $0 <trace-case> [fixture-dir]" >&2
+  exit 2
+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}"
+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}"
+
+include="$(IFS=,; echo "${files[*]}")"
+if [ "${case_name}" = "OpenRA" ]; then
+  echo "Fixture files for ${case_name} are stored in Git: ${include}"
+  for file in "${files[@]}"; do
+    test -s "${file}"
+    if head -n 1 "${file}" | grep -q "version https://git-lfs.github.com/spec/v1"; then
+      echo "fixture should not be stored as an LFS pointer: ${file}" >&2
+      exit 1
+    fi
+  done
+  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
+
+  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
+
+    if curl -L --fail --show-error --continue-at - --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 "${tmp_file}"
+  return 1
+}
+
+fetch_from_mirror() {
+  mkdir -p "${fixture_dir}"
+  for file in "${files[@]}"; do
+    local name
+    local url
+    name="$(basename "${file}")"
+    url="${mirror_base%/}/${name}"
+    echo "Fetching trace fixture from mirror: ${url}"
+    if ! fetch_file_from_mirror "${file}" "${url}"; then
+      return 1
+    fi
+  done
+}
+
+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: ${include}"
+  git lfs install --local
+  git lfs pull --include="${include}" --exclude=""
+fi
+
+for file in "${files[@]}"; do
+  metadata="$(get_lfs_metadata "${file}")"
+  read -r expected_oid expected_size <<< "${metadata}"
+  verify_fixture_file "${file}" "${file}" "${expected_oid}" "${expected_size}"
+done

.github/scripts/validate-plugin-apks.sh

@@ -0,0 +1,75 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+if [[ $# -ne 3 ]]; then
+  echo "Usage: $0 <aapt2> <plugin-apk> <trace-apk>" >&2
+  exit 64
+fi
+
+aapt2=$1
+plugin_apk=$2
+trace_apk=$3
+
+require() {
+  local needle=$1
+  local content=$2
+  local description=$3
+  if ! grep -Fq -- "$needle" <<<"$content"; then
+    echo "::error::Missing ${description}: ${needle}" >&2
+    exit 1
+  fi
+}
+
+for apk in "$plugin_apk" "$trace_apk"; do
+  [[ -f "$apk" ]] || { echo "::error::APK not found: $apk" >&2; exit 1; }
+done
+
+plugin_manifest=$("$aapt2" dump xmltree --file AndroidManifest.xml "$plugin_apk")
+plugin_resources=$("$aapt2" dump resources "$plugin_apk")
+plugin_resource_text=$(tr -d '"' <<<"$plugin_resources")
+trace_manifest=$("$aapt2" dump xmltree --file AndroidManifest.xml "$trace_apk")
+plugin_contents=$(unzip -Z1 "$plugin_apk")
+
+require 'top.mobilegl.plugin' "$plugin_manifest" 'plugin package name'
+require 'MobileGL' "$plugin_manifest" 'plugin label'
+require 'fclPlugin' "$plugin_manifest" 'legacy plugin marker'
+require 'fclPlugin_V2' "$plugin_manifest" 'V2 plugin marker'
+require 'LIBGL_ES=3:POJAV_RENDERER=opengles3:MOBILEGL_BACKEND_TYPE=DirectGLES' "$plugin_manifest" 'V1 DirectGLES fallback'
+require 'string/config' "$plugin_resources" 'V2 renderer configuration resource'
+require '{displayName:MobileGL,rendererId:opengles3' "$plugin_resource_text" 'V2 MobileGL entry and renderer ID'
+require 'rendererGLPath:**|libMobileGL.so' "$plugin_resource_text" 'V2 GL library path'
+require 'rendererEGLPath:**|libMobileGL.so' "$plugin_resource_text" 'V2 EGL library path'
+require 'key:LIBGL_ES,value:3' "$plugin_resource_text" 'V2 fixed LIBGL_ES variable'
+require 'key:MOBILEGL_BACKEND_TYPE' "$plugin_resource_text" 'V2 backend variable'
+require 'defaultValue:DirectGLES' "$plugin_resource_text" 'V2 DirectGLES default'
+require 'DirectVulkan' "$plugin_resource_text" 'V2 DirectVulkan option'
+require 'key:MOBILEGL_DISABLE_TIMERQUERY' "$plugin_resource_text" 'V2 timer-query toggle'
+require 'key:MOBILEGL_DISABLE_SUBGROUP' "$plugin_resource_text" 'V2 Vulkan subgroup toggle'
+require 'key:MOBILEGL_MAGMA_R11G11B10F_FALLBACK' "$plugin_resource_text" 'V2 Magma format fallback toggle'
+require 'key:MOBILEGL_MAGMA_FRAMESINFLIGHT' "$plugin_resource_text" 'V2 Magma frames-in-flight setting'
+require 'key:MOBILEGL_AVOID_SAMPLER_MIPMAP_MIN_FILTER' "$plugin_resource_text" 'V2 sampler workaround toggle'
+require 'key:MOBILEGL_COHERENT_AS_FLUSH' "$plugin_resource_text" 'V2 coherent-as-flush toggle'
+require 'key:MOBILEGL_USE_ANGLE' "$plugin_resource_text" 'V2 ANGLE toggle'
+
+if [[ $(grep -Fc 'fclPlugin_V2' <<<"$plugin_manifest") -ne 1 ]]; then
+  echo '::error::Plugin manifest must expose exactly one V2 descriptor' >&2
+  exit 1
+fi
+
+if ! grep -Eq '^lib/[^/]+/libMobileGL\.so$' <<<"$plugin_contents"; then
+  echo '::error::Plugin APK does not contain libMobileGL.so' >&2
+  exit 1
+fi
+
+require 'top.mobilegl.plugin.trace' "$trace_manifest" 'trace package name'
+require 'top.mobilegl.plugin.TRACE_REPLAY' "$trace_manifest" 'trace replay action'
+if grep -Fq 'fclPlugin' <<<"$trace_manifest"; then
+  echo '::error::Trace APK must not advertise renderer-plugin metadata' >&2
+  exit 1
+fi
+if grep -Fq 'android.intent.action.MAIN' <<<"$trace_manifest"; then
+  echo '::error::Trace APK must not expose a launcher activity' >&2
+  exit 1
+fi
+
+echo 'Validated unified MobileGL plugin APK and isolated trace APK.'

.github/workflows/apk.yml

@@ -0,0 +1,560 @@
+name: MobileGL APK
+
+on:
+  push:
+    branches:
+      - dev
+      - Feat/Backend-Direct-GLES
+      - Feat/Backend-Direct-Vulkan
+  workflow_dispatch:
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    env:
+      CCACHE_BASEDIR: ${{ github.workspace }}
+      CCACHE_COMPRESS: "true"
+      CCACHE_DIR: ${{ github.workspace }}/.ccache
+      CCACHE_MAXSIZE: 4G
+      CCACHE_NOHASHDIR: "true"
+      MOBILEGL_CMAKE_COMPILER_LAUNCHER: ccache
+
+    steps:
+      - name: Checkout repo
+        uses: actions/checkout@v6
+        with:
+          submodules: recursive
+
+      - name: Set artifact metadata
+        run: |
+          echo "date_today=$(date +'%Y-%m-%d')" >> "$GITHUB_ENV"
+
+      - name: Set up JDK
+        uses: actions/setup-java@v5
+        with:
+          distribution: zulu
+          java-version: '17'
+
+      - name: Setup Gradle
+        uses: gradle/actions/setup-gradle@v6
+        with:
+          gradle-version: 8.10.2
+
+      - name: Restore ccache
+        uses: actions/cache@v5
+        with:
+          path: .ccache
+          key: ${{ runner.os }}-apk-${{ github.job }}-ccache-${{ github.ref_name }}-${{ github.run_id }}
+          restore-keys: |
+            ${{ runner.os }}-apk-${{ github.job }}-ccache-${{ github.ref_name }}-
+            ${{ runner.os }}-apk-${{ github.job }}-ccache-
+
+      - name: Install ccache
+        run: |
+          sudo apt-get update
+          sudo apt-get install -y ccache
+          ccache --version
+
+      - name: Setup Android SDK
+        uses: android-actions/setup-android@v4
+        with:
+          accept-android-sdk-licenses: false
+
+      - name: Accept Android SDK licenses
+        run: yes | sdkmanager --licenses >/dev/null
+
+      - name: Install Android NDK
+        run: |
+          sdkmanager "ndk;27.3.13750724"
+          echo "ndk.dir=$ANDROID_HOME/ndk/27.3.13750724" >> android-plugin/local.properties
+
+      - name: Update glslang external sources
+        working-directory: 3rdparty/glslang
+        run: python update_glslang_sources.py
+
+      - name: Build plugin APK
+        run: gradle --no-daemon -p android-plugin :app:assemblePluginRelease -Pmobilegl.apkSuffix="${GITHUB_SHA}" -Pmobilegl.logLevel=MOBILEGL_LOG_LEVEL_INFO --parallel --max-workers "$(nproc)"
+        env:
+          SIGNING_STORE_PASSWORD: ${{ secrets.SIGNING_STORE_PASSWORD }}
+          SIGNING_KEY_ALIAS: ${{ secrets.SIGNING_KEY_ALIAS }}
+          SIGNING_KEY_PASSWORD: ${{ secrets.SIGNING_KEY_PASSWORD }}
+
+      - name: Download ANGLE x86_64 libraries
+        run: |
+          angle_dir="android-plugin/app/src/trace/jniLibs/x86_64"
+          rm -rf "${angle_dir}"
+          mkdir -p "${angle_dir}"
+
+          package_angle_variant() {
+            variant="$1"
+            commit="$2"
+            egl_sha="$3"
+            gles_sha="$4"
+            source_dir="${RUNNER_TEMP}/mobilegl-angle-${variant}"
+            base="https://raw.githubusercontent.com/FCL-Team/FoldCraftLauncher/${commit}/FCLauncher/src/main/jniLibs/x86_64"
+            mkdir -p "${source_dir}"
+            curl -L --fail --retry 3 -o "${source_dir}/libEGL_angle.so" "${base}/libEGL_angle.so"
+            curl -L --fail --retry 3 -o "${source_dir}/libGLESv2_angle.so" "${base}/libGLESv2_angle.so"
+            echo "${egl_sha}  ${source_dir}/libEGL_angle.so" | sha256sum -c -
+            echo "${gles_sha}  ${source_dir}/libGLESv2_angle.so" | sha256sum -c -
+            for library in libEGL_angle libGLESv2_angle; do
+              filename="${library}_${variant}.so"
+              cp "${source_dir}/${library}.so" "${angle_dir}/${filename}"
+            done
+          }
+
+          package_angle_variant \
+            ec889e6ea831 \
+            f2a3d510dffd8f6540a52e1a7d0c5787d151075b \
+            c41828768d089899fa058ec0bee711a91be88347f29bdb935223da6be1149c40 \
+            e4f820d99f94365c66df868c7740fef142fe5c0cd7c941790a9e30638857ca4d
+          package_angle_variant \
+            90a62123d794 \
+            bdcc96ac11c79001018ae4375eb73cb54a9f682f \
+            d0f4298ccc770cc801fc52e21733521646161e8a4adb3bd0052d9a1b57ee0ca8 \
+            66fdc867e552192d553d59095ea2e3cef4829de65c356f1fd826027b1905972e
+
+      - name: Build retrace APK
+        run: gradle --no-daemon -p android-plugin :app:assembleTraceRelease -Pmobilegl.apkSuffix="${GITHUB_SHA}" -Pmobilegl.abis=all -Pmobilegl.debuggableRelease=true -Pmobilegl.logLevel=MOBILEGL_LOG_LEVEL_INFO --parallel --max-workers "$(nproc)"
+        env:
+          SIGNING_STORE_PASSWORD: ${{ secrets.SIGNING_STORE_PASSWORD }}
+          SIGNING_KEY_ALIAS: ${{ secrets.SIGNING_KEY_ALIAS }}
+          SIGNING_KEY_PASSWORD: ${{ secrets.SIGNING_KEY_PASSWORD }}
+
+      - name: Show ccache stats
+        if: always()
+        run: ccache --show-stats
+
+      - name: Verify APK metadata and packaging
+        run: |
+          AAPT2="$(find "$ANDROID_HOME/build-tools" -name aapt2 -type f | sort -V | tail -n 1)"
+          plugin_apk="android-plugin/app/build/outputs/apk/plugin/release/MobileGL-plugin-release-${GITHUB_SHA}.apk"
+          trace_apk="android-plugin/app/build/outputs/apk/trace/release/MobileGL-plugin-trace-release-${GITHUB_SHA}.apk"
+          test -f "${plugin_apk}"
+          test -f "${trace_apk}"
+          bash .github/scripts/validate-plugin-apks.sh "$AAPT2" "$plugin_apk" "$trace_apk"
+
+      - name: Verify signed APKs
+        run: |
+          APKSIGNER="$(find "$ANDROID_HOME/build-tools" -name apksigner -type f | sort -V | tail -n 1)"
+          mapfile -t APKS < <(printf '%s\n' \
+            "android-plugin/app/build/outputs/apk/plugin/release/MobileGL-plugin-release-${GITHUB_SHA}.apk" \
+            "android-plugin/app/build/outputs/apk/trace/release/MobileGL-plugin-trace-release-${GITHUB_SHA}.apk")
+          for APK in "${APKS[@]}"; do
+            if [[ ! -f "$APK" ]]; then
+              echo "::error::Expected release APK was not produced: $APK"
+              exit 1
+            fi
+          done
+
+          for APK in "${APKS[@]}"; do
+            if [[ "$APK" == *-unsigned.apk ]]; then
+              echo "::error::Unsigned release APK produced: $APK"
+              exit 1
+            fi
+            "$APKSIGNER" verify --verbose "$APK"
+          done
+
+      - name: Upload plugin APK
+        uses: actions/upload-artifact@v7
+        with:
+          name: MobileGL-plugin-${{ env.date_today }}-${{ github.sha }}
+          path: android-plugin/app/build/outputs/apk/plugin/release/MobileGL-plugin-release-${{ github.sha }}.apk
+          archive: false
+          if-no-files-found: error
+
+      - name: Upload retrace APK
+        uses: actions/upload-artifact@v7
+        with:
+          name: MobileGL-retrace-apk-${{ env.date_today }}-${{ github.sha }}
+          path: android-plugin/app/build/outputs/apk/trace/release/MobileGL-plugin-trace-release-${{ github.sha }}.apk
+          archive: false
+          if-no-files-found: error
+
+  trace-cases:
+    name: trace case matrix
+    runs-on: ubuntu-latest
+    needs: build
+    outputs:
+      android: ${{ steps.trace-cases.outputs.android }}
+      names: ${{ steps.trace-cases.outputs.names }}
+    steps:
+      - name: Checkout repo
+        uses: actions/checkout@v6
+
+      - name: Load trace cases
+        id: trace-cases
+        run: |
+          echo "android=$(python3 tools/trace_replay/trace_cases.py --ci --format github-apk)" >> "$GITHUB_OUTPUT"
+          echo "names=$(python3 tools/trace_replay/trace_cases.py --ci --format names)" >> "$GITHUB_OUTPUT"
+
+  trace-fixtures:
+    name: trace fixture (${{ matrix.case }})
+    runs-on: ubuntu-latest
+    needs: trace-cases
+    strategy:
+      fail-fast: false
+      max-parallel: 4
+      matrix:
+        case: ${{ fromJSON(needs.trace-cases.outputs.names) }}
+    steps:
+      - name: Checkout repo
+        uses: actions/checkout@v6
+
+      - name: Fetch trace fixture
+        run: bash .github/scripts/fetch-trace-fixture-lfs.sh '${{ matrix.case }}'
+
+      - name: Stage trace fixture
+        run: |
+          safe_case="$(printf '%s' '${{ matrix.case }}' | sed 's/[^A-Za-z0-9._-]/_/g')"
+          stage_dir="trace-fixtures/${safe_case}"
+          mkdir -p "${stage_dir}"
+          python3 tools/trace_replay/trace_cases.py --format fixture-files --case '${{ matrix.case }}' |
+            while IFS= read -r file; do
+              cp "${file}" "${stage_dir}/"
+            done
+
+      - name: Upload trace fixture
+        uses: actions/upload-artifact@v7
+        with:
+          name: MobileGL-trace-fixture-${{ matrix.case }}
+          path: trace-fixtures/**
+          if-no-files-found: error
+
+  android-avd:
+    name: android avd image
+    runs-on: ubuntu-latest
+    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
+
+      - name: Setup Android SDK
+        uses: android-actions/setup-android@v4
+        with:
+          accept-android-sdk-licenses: false
+
+      - name: Accept Android SDK licenses
+        run: yes | sdkmanager --licenses >/dev/null
+
+      - name: Restore Android AVD cache
+        id: android-avd-cache
+        uses: actions/cache@v5
+        with:
+          path: |
+            ${{ env.ANDROID_AVD_HOME }}
+            ${{ 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'
+        run: |
+          sh android-plugin/run-avd-ci.sh create \
+            --api-level 35 \
+            --target google_apis \
+            --arch x86_64 \
+            --profile pixel_6 \
+            --avd-name "${AVD_NAME}"
+
+  retrace:
+    name: retrace (${{ matrix.backend.name }}, ${{ matrix.case.name }})
+    runs-on: ubuntu-latest
+    needs:
+      - build
+      - android-avd
+      - trace-cases
+      - trace-fixtures
+    if: ${{ always() && needs.build.result == 'success' && needs.android-avd.result == 'success' && needs.trace-cases.result == 'success' }}
+    timeout-minutes: 75
+    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
+      matrix:
+        backend:
+          - name: DirectGLES
+            gpu: software
+          - name: DirectVulkan
+            gpu: lavapipe
+        case: ${{ fromJSON(needs.trace-cases.outputs.android) }}
+    steps:
+      - name: Set Swap Space
+        uses: pierotofy/set-swap-space@v1.0
+        with:
+          swap-size-gb: 8
+
+      - name: Checkout repo
+        uses: actions/checkout@v6
+
+      - name: Download trace fixture
+        uses: actions/download-artifact@v8
+        with:
+          name: MobileGL-trace-fixture-${{ matrix.case.name }}
+          path: trace-fixture-download
+
+      - name: Install trace fixture
+        run: |
+          mkdir -p tools/trace_replay/fixtures
+          find trace-fixture-download -type f -exec cp {} tools/trace_replay/fixtures/ \;
+
+      - name: Set artifact metadata
+        run: |
+          echo "date_today=$(date +'%Y-%m-%d')" >> "$GITHUB_ENV"
+          echo "EMULATOR_LOG=${RUNNER_TEMP}/mobilegl-emulator.log" >> "$GITHUB_ENV"
+          echo "EMULATOR_PID_FILE=${RUNNER_TEMP}/mobilegl-emulator.pid" >> "$GITHUB_ENV"
+
+      - name: Setup Android SDK
+        uses: android-actions/setup-android@v4
+        with:
+          accept-android-sdk-licenses: false
+
+      - name: Accept Android SDK licenses
+        run: yes | sdkmanager --licenses >/dev/null
+
+      - name: Restore Android AVD cache
+        id: android-avd-cache
+        uses: actions/cache/restore@v5
+        with:
+          path: |
+            ${{ env.ANDROID_AVD_HOME }}
+            ${{ 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
+        with:
+          name: MobileGL-plugin-trace-release-${{ github.sha }}.apk
+          path: android-retrace-apks
+
+      - name: Enable KVM
+        run: |
+          echo 'KERNEL=="kvm", GROUP="kvm", MODE="0666", OPTIONS+="static_node=kvm"' | sudo tee /etc/udev/rules.d/99-kvm4all.rules
+          sudo udevadm control --reload-rules
+          sudo udevadm trigger --name-match=kvm
+
+      - name: Create AVD
+        if: steps.android-avd-cache.outputs.cache-hit != 'true'
+        run: |
+          sh android-plugin/run-avd-ci.sh create \
+            --api-level 35 \
+            --target google_apis \
+            --arch x86_64 \
+            --profile pixel_6 \
+            --avd-name "${AVD_NAME}"
+
+      - name: Launch Emulator
+        run: |
+          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
+
+      - name: Retrace and validate
+        env:
+          MOBILEGL_USE_ANGLE: ${{ matrix.backend.name == 'DirectGLES' && '1' || '0' }}
+          MOBILEGL_TRACE_ANGLE_VARIANT: ${{ matrix.case.name == 'minecraft-1.21.4-fabric-iris-bliss-in-world' && '90a62123d794' || 'ec889e6ea831' }}
+          MOBILEGL_MAGMA_R11G11B10F_FALLBACK: ${{ matrix.backend.name == 'DirectVulkan' && '1' || '0' }}
+        run: |
+          apk_file="android-retrace-apks/MobileGL-plugin-trace-release-${GITHUB_SHA}.apk"
+          test -f "${apk_file}"
+          extra_retrace_args=()
+          # Bliss needs the newer signed ANGLE variant plus sampler mipmap
+          # min-filter downgrading on ANGLE llvmpipe.
+          if [ "${{ matrix.backend.name }}" = "DirectGLES" ] && [ "${{ matrix.case.name }}" = "minecraft-1.21.4-fabric-iris-bliss-in-world" ]; then
+            extra_retrace_args+=(--avoid-angle-llvmpipe-sampler-mipmap-min-filter)
+          fi
+          if [ "${{ matrix.case.coherent_as_flush || false }}" = "true" ]; then
+            extra_retrace_args+=(--coherent-as-flush)
+          fi
+
+          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 "${retrace_status}"
+          fi
+
+      - name: Collect retrace summary inputs
+        if: always()
+        run: |
+          safe_case="$(printf '%s' '${{ matrix.case.name }}' | sed 's/[^A-Za-z0-9._-]/_/g')"
+          result_dir="android-retrace-result/${safe_case}-${{ matrix.backend.name }}"
+          mkdir -p "${result_dir}"
+          if [ -s "${{ matrix.case.golden }}" ]; then
+            cp "${{ matrix.case.golden }}" "${result_dir}/${safe_case}-${{ matrix.backend.name }}-golden.png"
+          fi
+          if [ -n "${{ matrix.case.alternate_golden || '' }}" ] && [ -s "${{ matrix.case.alternate_golden || '' }}" ]; then
+            cp "${{ matrix.case.alternate_golden || '' }}" "${result_dir}/${safe_case}-${{ matrix.backend.name }}-alternate-golden.png"
+          fi
+
+      - name: Collect emulator diagnostics
+        if: always()
+        run: |
+          mkdir -p android-retrace-result/diagnostics
+          adb devices -l > android-retrace-result/diagnostics/adb-devices.txt || true
+          timeout 30 adb logcat -d -t 1000 > android-retrace-result/diagnostics/logcat.txt || true
+          if [ -f "${EMULATOR_LOG}" ]; then
+            cp "${EMULATOR_LOG}" android-retrace-result/diagnostics/emulator.log
+          fi
+
+      - name: Stop Emulator
+        if: always()
+        run: |
+          sh android-plugin/run-avd-ci.sh stop \
+            --avd-name "${AVD_NAME}" \
+            --emulator-log "${EMULATOR_LOG}" \
+            --pid-file "${EMULATOR_PID_FILE}"
+
+      - name: Upload Android retrace result
+        if: always()
+        uses: actions/upload-artifact@v7
+        with:
+          name: MobileGL-android-retrace-result-${{ env.date_today }}-${{ github.sha }}-${{ matrix.backend.name }}-${{ matrix.case.name }}
+          path: android-retrace-result/**
+          if-no-files-found: warn
+
+  retrace-summary:
+    name: retrace summary
+    runs-on: ubuntu-latest
+    needs: retrace
+    if: always()
+
+    steps:
+      - name: Checkout repo
+        uses: actions/checkout@v6
+
+      - name: Set artifact metadata
+        run: |
+          echo "date_today=$(date +'%Y-%m-%d')" >> "$GITHUB_ENV"
+
+      - name: Set up Node.js
+        uses: actions/setup-node@v7
+        with:
+          node-version: '22'
+
+      - name: Download Android retrace results
+        uses: actions/download-artifact@v8
+        with:
+          pattern: MobileGL-android-retrace-result-*
+          path: retrace-artifacts
+
+      - name: Render retrace summary
+        run: |
+          node tools/trace_replay/render_retrace_summary.mjs \
+            --input retrace-artifacts \
+            --output-dir android-retrace-summary \
+            --title "MobileGL Android retrace overview" \
+            --group-label "Android Emulator" \
+            --html mobilegl-android-retrace-overview.html
+
+      - name: Upload Android retrace summary
+        uses: actions/upload-artifact@v7
+        with:
+          path: android-retrace-summary/mobilegl-android-retrace-overview.html
+          archive: false
+          if-no-files-found: error
+
+  remove-artifact-clutter:
+    name: remove artifact clutter
+    runs-on: ubuntu-latest
+    needs: retrace-summary
+    if: always()
+    permissions:
+      actions: write
+    steps:
+      - name: Delete intermediate Android retrace artifacts
+        env:
+          GH_TOKEN: ${{ github.token }}
+        run: |
+          declare -A failed_cases=()
+          while IFS= read -r job_name; do
+            case_name="${job_name#retrace (*, }"
+            case_name="${case_name%)}"
+            failed_cases["${case_name}"]=1
+          done < <(
+            gh api --paginate "repos/${GITHUB_REPOSITORY}/actions/runs/${GITHUB_RUN_ID}/jobs?per_page=100" \
+              --jq '.jobs[] | select(.name | startswith("retrace (")) | select(.conclusion == "failure" or .conclusion == "cancelled" or .conclusion == "timed_out" or .conclusion == "action_required") | .name'
+          )
+
+          if ((${#failed_cases[@]})); then
+            echo "Retaining fixtures for failed retrace case(s):"
+            printf '  %s\n' "${!failed_cases[@]}"
+          else
+            echo "All retrace jobs succeeded; no fixtures need to be retained."
+          fi
+
+          deleted=0
+          retained=0
+          while IFS=$'\t' read -r artifact_id artifact_name; do
+            if [[ "${artifact_name}" == MobileGL-trace-fixture-* ]]; then
+              case_name="${artifact_name#MobileGL-trace-fixture-}"
+              if [[ -v "failed_cases[${case_name}]" ]]; then
+                echo "Retaining ${artifact_name} (${artifact_id}) for failed retrace."
+                ((retained += 1))
+                continue
+              fi
+            fi
+
+            echo "Deleting ${artifact_name} (${artifact_id})"
+            gh api --method DELETE "repos/${GITHUB_REPOSITORY}/actions/artifacts/${artifact_id}"
+            ((deleted += 1))
+          done < <(
+            gh api --paginate "repos/${GITHUB_REPOSITORY}/actions/runs/${GITHUB_RUN_ID}/artifacts?per_page=100" \
+              --jq '.artifacts[] | select(.name | startswith("MobileGL-trace-fixture-") or startswith("MobileGL-android-retrace-result-") or startswith("trace-fixture-") or startswith("retrace-result-")) | [.id, .name] | @tsv'
+          )
+
+          echo "Deleted ${deleted} intermediate Android artifact(s); retained ${retained} failed-retrace fixture(s)."

.github/workflows/benchmark.yml

@@ -1,64 +0,0 @@
-name: Benchmark
-
-on:
-  push:
-    branches: 
-      - dev
-      - Feat/Backend-Direct-GLES
-      - Feat/Backend-Direct-Vulkan
-
-jobs:
-  benchmark:
-    runs-on: ubuntu-latest
-    env:
-      # BENCH_ROOT: ${{github.workspace}}/MobileGL/MG_Benchmark
-      BENCH_ROOT: ${{github.workspace}}
-
-    steps:
-      - name: Set Swap Space
-        uses: pierotofy/set-swap-space@master
-        with:
-          swap-size-gb: 32
-
-      - name: Checkout repo
-        uses: actions/checkout@v4
-        with:
-          submodules: true
-
-      - name: Get CMake
-        uses: lukka/get-cmake@latest
-
-      - name: Prepare Vulkan SDK
-        uses: humbletim/setup-vulkan-sdk@v1.2.1
-        with:
-          vulkan-query-version: 1.4.304.1
-          vulkan-components: Vulkan-Headers, Vulkan-Loader
-          vulkan-use-cache: true
-
-      - name: Update glslang external sources
-        working-directory: ${{env.BENCH_ROOT}}/3rdparty/glslang
-        run: python update_glslang_sources.py
-
-      - name: Install clang-20
-        run: |
-          sudo apt-get update
-          sudo apt-get install -y clang-20 clang++-20 lld-20 libc++-20-dev libc++abi-20-dev libvulkan-dev
-
-      - name: Show installed toolchain
-        run: |
-          clang-20 --version
-          clang++-20 --version
-          ld.lld-20 --version || ld.lld --version || true
-          dpkg -l 'libc++*' || true
-
-      - name: Configure CMake
-        working-directory: ${{env.BENCH_ROOT}}
-        run: cmake -S . -B build-bench -G Ninja -DCMAKE_BUILD_TYPE=Release -DCMAKE_C_COMPILER=clang-20 -DCMAKE_CXX_COMPILER=clang++-20 -DBENCHMARK_DOWNLOAD_DEPENDENCIES=ON -DBENCHMARK_ENABLE_TESTING=OFF -DMOBILEGL_BUILD_TEST=OFF -DMOBILEGL_BUILD_BENCHMARK=ON -DCMAKE_POLICY_VERSION_MINIMUM=3.5
-
-      - name: Build
-        working-directory: ${{env.BENCH_ROOT}}/build-bench
-        run: cmake --build .
-
-      - name: Benchmark
-        working-directory: ${{env.BENCH_ROOT}}/build-bench/MobileGL/MG_Benchmark
-        run: ctest -V -C Release

.github/workflows/plugin-apk.yml

@@ -1,80 +0,0 @@
-name: MobileGL Plugin APK
-
-on:
-  push:
-    branches:
-      - dev
-      - Feat/Backend-Direct-GLES
-      - Feat/Backend-Direct-Vulkan
-  workflow_dispatch:
-
-jobs:
-  build:
-    runs-on: ubuntu-latest
-
-    steps:
-      - name: Checkout repo
-        uses: actions/checkout@v4
-        with:
-          submodules: recursive
-
-      - name: Set artifact metadata
-        run: |
-          echo "date_today=$(date +'%Y-%m-%d')" >> "$GITHUB_ENV"
-          echo "short_sha=${GITHUB_SHA::7}" >> "$GITHUB_ENV"
-
-      - name: Set up JDK
-        uses: actions/setup-java@v4
-        with:
-          distribution: zulu
-          java-version: '17'
-
-      - name: Setup Gradle
-        uses: gradle/actions/setup-gradle@v4
-        with:
-          gradle-version: 8.10.2
-
-      - name: Setup Android SDK
-        uses: android-actions/setup-android@v3
-
-      - name: Install Android NDK
-        run: |
-          sdkmanager "ndk;27.3.13750724"
-          echo "ndk.dir=$ANDROID_HOME/ndk/27.3.13750724" >> android-plugin/local.properties
-
-      - name: Update glslang external sources
-        working-directory: 3rdparty/glslang
-        run: python update_glslang_sources.py
-
-      - name: Build plugin APK
-        run: gradle --no-daemon -p android-plugin :app:assembleRelease
-        env:
-          SIGNING_STORE_PASSWORD: ${{ secrets.SIGNING_STORE_PASSWORD }}
-          SIGNING_KEY_ALIAS: ${{ secrets.SIGNING_KEY_ALIAS }}
-          SIGNING_KEY_PASSWORD: ${{ secrets.SIGNING_KEY_PASSWORD }}
-
-      - name: Verify signed APK
-        run: |
-          APKSIGNER="$(find "$ANDROID_HOME/build-tools" -name apksigner -type f | sort -V | tail -n 1)"
-          mapfile -t APKS < <(find android-plugin/app/build/outputs/apk -type f -path '*/release/*.apk' | sort)
-          if [ "${#APKS[@]}" -eq 0 ]; then
-            echo "::error::No release APKs found under android-plugin/app/build/outputs/apk"
-            find android-plugin/app/build/outputs/apk -type f -print || true
-            exit 1
-          fi
-
-          for APK in "${APKS[@]}"; do
-            if [[ "$APK" == *-unsigned.apk ]]; then
-              echo "::error::Unsigned release APK produced: $APK"
-              exit 1
-            fi
-            "$APKSIGNER" verify --verbose "$APK"
-          done
-
-      - name: Upload plugin APK
-        uses: actions/upload-artifact@v4
-        with:
-          name: MobileGL-plugin-${{ env.date_today }}-${{ env.short_sha }}
-          path: |
-            android-plugin/app/build/outputs/apk/release/*.apk
-            android-plugin/app/build/outputs/apk/**/release/*.apk

.github/workflows/test.yml

@@ -6,27 +6,41 @@ on:
       - dev
       - Feat/Backend-Direct-GLES
       - Feat/Backend-Direct-Vulkan
+  workflow_dispatch:
 
 jobs:
-  test:
+  build-linux:
     runs-on: ubuntu-latest
     env:
-      # TEST_ROOT: ${{github.workspace}}/MobileGL/MG_Test
-      TEST_ROOT: ${{github.workspace}}
+      BUILD_DIR: build-linux
+      CCACHE_BASEDIR: ${{ github.workspace }}
+      CCACHE_COMPRESS: "true"
+      CCACHE_DIR: ${{ github.workspace }}/.ccache
+      CCACHE_MAXSIZE: 4G
+      CCACHE_NOHASHDIR: "true"
 
     steps:
       - name: Set Swap Space
-        uses: pierotofy/set-swap-space@master
+        uses: pierotofy/set-swap-space@v1.0
         with:
           swap-size-gb: 32
 
       - name: Checkout repo
-        uses: actions/checkout@v4
+        uses: actions/checkout@v6
         with:
-          submodules: true
+          submodules: recursive
 
       - name: Get CMake
-        uses: lukka/get-cmake@latest
+        uses: lukka/get-cmake@v4.3.3
+
+      - name: Restore ccache
+        uses: actions/cache@v5
+        with:
+          path: .ccache
+          key: ${{ runner.os }}-test-${{ github.job }}-ccache-${{ github.ref_name }}-${{ github.run_id }}
+          restore-keys: |
+            ${{ runner.os }}-test-${{ github.job }}-ccache-${{ github.ref_name }}-
+            ${{ runner.os }}-test-${{ github.job }}-ccache-
 
       - name: Prepare Vulkan SDK
         uses: humbletim/setup-vulkan-sdk@v1.2.1
@@ -36,39 +50,511 @@ jobs:
           vulkan-use-cache: true
 
       - name: Update glslang external sources
-        working-directory: ${{env.TEST_ROOT}}/3rdparty/glslang
+        working-directory: 3rdparty/glslang
         run: python update_glslang_sources.py
 
-      - name: Install clang-20
+      - name: Install build dependencies
         run: |
           sudo apt-get update
-          sudo apt-get install -y clang-20 clang++-20 lld-20 libc++-20-dev libc++abi-20-dev libvulkan-dev
+          sudo apt-get install -y ccache clang-20 clang++-20 lld-20 libc++-20-dev libc++abi-20-dev libvulkan-dev libegl1-mesa-dev libgles2-mesa-dev libgl1-mesa-dri mesa-vulkan-drivers ninja-build
 
       - name: Show installed toolchain
         run: |
+          ccache --version
           clang-20 --version
           clang++-20 --version
           ld.lld-20 --version || ld.lld --version || true
-          dpkg -l 'libc++*' || true
-          
+          dpkg -l 'libc++*' 'libegl*' 'libgles*' 'mesa*' 'vulkan*' || true
+
       - name: Configure CMake
-        working-directory: ${{env.TEST_ROOT}}
         run: |
-          if [ "${{ secrets.ACTIONS_STEP_DEBUG }}" == "true" ]; then
-            cmake -S . -B build-test -G Ninja -DCMAKE_C_COMPILER=clang-20 -DCMAKE_CXX_COMPILER=clang++-20 -DCMAKE_BUILD_TYPE=Debug -DMOBILEGL_BUILD_TEST=ON -DMOBILEGL_BUILD_BENCHMARK=OFF -DCMAKE_POLICY_VERSION_MINIMUM=3.5
+          if [ "${{ secrets.ACTIONS_STEP_DEBUG }}" = "true" ]; then
+            BUILD_TYPE=Debug
           else
-            cmake -S . -B build-test -G Ninja -DCMAKE_C_COMPILER=clang-20 -DCMAKE_CXX_COMPILER=clang++-20 -DCMAKE_BUILD_TYPE=Release -DMOBILEGL_BUILD_TEST=ON -DMOBILEGL_BUILD_BENCHMARK=OFF -DCMAKE_POLICY_VERSION_MINIMUM=3.5
+            BUILD_TYPE=Release
           fi
-          
+
+          cmake -S . -B "${BUILD_DIR}" -G Ninja \
+            -DCMAKE_C_COMPILER=clang-20 \
+            -DCMAKE_CXX_COMPILER=clang++-20 \
+            -DCMAKE_C_COMPILER_LAUNCHER=ccache \
+            -DCMAKE_CXX_COMPILER_LAUNCHER=ccache \
+            -DCMAKE_BUILD_TYPE="${BUILD_TYPE}" \
+            -DMOBILEGL_LOG_ACTIVE_LEVEL=MOBILEGL_LOG_LEVEL_INFO \
+            -DMOBILEGL_BUILD_TEST=ON \
+            -DMOBILEGL_BUILD_BENCHMARK=ON \
+            -DMOBILEGL_BUILD_TRACE_REPLAY=OFF \
+            -DBENCHMARK_DOWNLOAD_DEPENDENCIES=ON \
+            -DBENCHMARK_ENABLE_TESTING=OFF \
+            -DCMAKE_POLICY_VERSION_MINIMUM=3.5
+
       - name: Build
-        working-directory: ${{env.TEST_ROOT}}/build-test
-        run: cmake --build .
+        run: cmake --build "${BUILD_DIR}" --parallel "$(nproc)"
+
+      - name: Show ccache stats
+        if: always()
+        run: ccache --show-stats
+
+      - name: Package Linux runtime
+        run: |
+          mkdir -p ci-artifacts
+          mapfile -t SHARED_LIBS < <(find "${BUILD_DIR}" -type f \( -name '*.so' -o -name '*.so.*' \) -print | sort)
+          tar \
+            --exclude='*/CMakeFiles' \
+            --exclude='*.o' \
+            --exclude='*.a' \
+            --exclude='*.ninja*' \
+            --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[@]}"
+
+      - name: Upload Linux runtime
+        uses: actions/upload-artifact@v7
+        with:
+          name: mobilegl-linux-runtime
+          path: ci-artifacts/mobilegl-linux-runtime.tgz
+          if-no-files-found: error
+
+  test:
+    runs-on: ubuntu-latest
+    needs: build-linux
+
+    steps:
+      - name: Checkout repo
+        uses: actions/checkout@v6
+
+      - name: Get CMake
+        uses: lukka/get-cmake@v4.3.3
+
+      - name: Install runtime dependencies
+        run: |
+          sudo apt-get update
+          sudo apt-get install -y libvulkan1 libegl1 libgles2 libgl1-mesa-dri mesa-vulkan-drivers
+
+      - name: Download Linux runtime
+        uses: actions/download-artifact@v8
+        with:
+          name: mobilegl-linux-runtime
+          path: .
+
+      - name: Unpack Linux runtime
+        run: tar -xzf mobilegl-linux-runtime.tgz
+
+      - name: Normalize CTest command paths
+        run: |
+          python - <<'PY'
+          from pathlib import Path
+          import re
+
+          for path in Path('build-linux').rglob('CTestTestfile.cmake'):
+              text = path.read_text()
+              text = re.sub(r'"[^"]*/cmake-[^"]*/bin/cmake"', '"cmake"', text)
+              path.write_text(text)
+          PY
 
       - name: Test
-        working-directory: ${{env.TEST_ROOT}}/build-test/MobileGL/MG_Test
+        working-directory: build-linux
         run: |
-          if [ "${{ secrets.ACTIONS_STEP_DEBUG }}" == "true" ]; then
-            ctest -V
+          if [ "${{ secrets.ACTIONS_STEP_DEBUG }}" = "true" ]; then
+            ctest -V -L unit --no-tests=error
           else
-            ctest
+            ctest --output-on-failure -L unit --no-tests=error
           fi
+
+  benchmark:
+    runs-on: ubuntu-latest
+    needs: build-linux
+
+    steps:
+      - name: Checkout repo
+        uses: actions/checkout@v6
+
+      - name: Get CMake
+        uses: lukka/get-cmake@v4.3.3
+
+      - name: Install runtime dependencies
+        run: |
+          sudo apt-get update
+          sudo apt-get install -y libvulkan1 libegl1 libgles2 libgl1-mesa-dri mesa-vulkan-drivers
+
+      - name: Download Linux runtime
+        uses: actions/download-artifact@v8
+        with:
+          name: mobilegl-linux-runtime
+          path: .
+
+      - name: Unpack Linux runtime
+        run: tar -xzf mobilegl-linux-runtime.tgz
+
+      - name: Normalize CTest command paths
+        run: |
+          python - <<'PY'
+          from pathlib import Path
+          import re
+
+          for path in Path('build-linux').rglob('CTestTestfile.cmake'):
+              text = path.read_text()
+              text = re.sub(r'"[^"]*/cmake-[^"]*/bin/cmake"', '"cmake"', text)
+              path.write_text(text)
+          PY
+
+      - name: Benchmark
+        working-directory: build-linux
+        run: ctest -V -C Release -L benchmark --no-tests=error
+
+  build-retrace:
+    runs-on: ubuntu-latest
+    needs:
+      - build-linux
+      - test
+      - benchmark
+    env:
+      BUILD_DIR: build-retrace
+      CCACHE_BASEDIR: ${{ github.workspace }}
+      CCACHE_COMPRESS: "true"
+      CCACHE_DIR: ${{ github.workspace }}/.ccache
+      CCACHE_MAXSIZE: 4G
+      CCACHE_NOHASHDIR: "true"
+      MOBILEGL_LIBRARY: ${{ github.workspace }}/build-linux/libMobileGL.so
+
+    steps:
+      - name: Set Swap Space
+        uses: pierotofy/set-swap-space@v1.0
+        with:
+          swap-size-gb: 32
+
+      - name: Checkout repo
+        uses: actions/checkout@v6
+        with:
+          submodules: recursive
+
+      - name: Get CMake
+        uses: lukka/get-cmake@v4.3.3
+
+      - name: Restore ccache
+        uses: actions/cache@v5
+        with:
+          path: .ccache
+          key: ${{ runner.os }}-test-${{ github.job }}-ccache-${{ github.ref_name }}-${{ github.run_id }}
+          restore-keys: |
+            ${{ runner.os }}-test-${{ github.job }}-ccache-${{ github.ref_name }}-
+            ${{ runner.os }}-test-${{ github.job }}-ccache-
+
+      - name: Prepare Vulkan SDK
+        uses: humbletim/setup-vulkan-sdk@v1.2.1
+        with:
+          vulkan-query-version: 1.4.304.1
+          vulkan-components: Vulkan-Headers, Vulkan-Loader
+          vulkan-use-cache: true
+
+      - name: Update glslang external sources
+        working-directory: 3rdparty/glslang
+        run: python update_glslang_sources.py
+
+      - name: Install dependencies
+        run: |
+          sudo apt-get update
+          sudo apt-get install -y ccache clang-20 clang++-20 lld-20 libc++-20-dev libc++abi-20-dev libvulkan-dev libegl1-mesa-dev libgles2-mesa-dev libgl1-mesa-dri mesa-vulkan-drivers ninja-build
+
+      - name: Show installed toolchain
+        run: |
+          ccache --version
+          clang-20 --version
+          clang++-20 --version
+          ld.lld-20 --version || ld.lld --version || true
+          dpkg -l 'libc++*' 'libegl*' 'libgles*' 'mesa*' 'vulkan*' || true
+
+      - name: Download Linux runtime
+        uses: actions/download-artifact@v8
+        with:
+          name: mobilegl-linux-runtime
+          path: .
+
+      - name: Unpack Linux runtime
+        run: |
+          tar -xzf mobilegl-linux-runtime.tgz
+          test -f "${MOBILEGL_LIBRARY}"
+
+      - name: Configure CMake
+        run: |
+          if [ "${{ secrets.ACTIONS_STEP_DEBUG }}" = "true" ]; then
+            BUILD_TYPE=Debug
+          else
+            BUILD_TYPE=Release
+          fi
+
+          cmake -S . -B "${BUILD_DIR}" -G Ninja \
+            -DCMAKE_C_COMPILER=clang-20 \
+            -DCMAKE_CXX_COMPILER=clang++-20 \
+            -DCMAKE_C_COMPILER_LAUNCHER=ccache \
+            -DCMAKE_CXX_COMPILER_LAUNCHER=ccache \
+            -DCMAKE_BUILD_TYPE="${BUILD_TYPE}" \
+            -DMOBILEGL_LOG_ACTIVE_LEVEL=MOBILEGL_LOG_LEVEL_INFO \
+            -DMOBILEGL_BUILD_TEST=OFF \
+            -DMOBILEGL_BUILD_BENCHMARK=OFF \
+            -DMOBILEGL_BUILD_TRACE_REPLAY=ON \
+            -DMOBILEGL_TRACE_REPLAY_MOBILEGL_LIBRARY="${MOBILEGL_LIBRARY}" \
+            -DCMAKE_POLICY_VERSION_MINIMUM=3.5
+
+      - name: Build trace replay
+        run: cmake --build "${BUILD_DIR}" --target mobilegl_trace_replay --parallel "$(nproc)"
+
+      - name: Show ccache stats
+        if: always()
+        run: ccache --show-stats
+
+      - name: Normalize CTest command paths
+        run: |
+          python - <<'PY'
+          from pathlib import Path
+          import re
+
+          for path in Path('build-retrace').rglob('CTestTestfile.cmake'):
+              text = path.read_text()
+              text = re.sub(r'"[^"]*/cmake-[^"]*/bin/cmake"', '"cmake"', text)
+              path.write_text(text)
+          PY
+
+      - name: Package trace replay
+        run: |
+          mkdir -p ci-artifacts
+          tar -czf ci-artifacts/mobilegl-trace-replay.tgz \
+            build-retrace/tools/trace_replay/mobilegl_trace_replay \
+            build-retrace/tools/trace_replay/CTestTestfile.cmake
+
+      - name: Upload trace replay
+        uses: actions/upload-artifact@v7
+        with:
+          name: mobilegl-trace-replay
+          path: ci-artifacts/mobilegl-trace-replay.tgz
+          if-no-files-found: error
+
+  trace-cases:
+    name: trace case matrix
+    runs-on: ubuntu-latest
+    needs:
+      - test
+      - benchmark
+    outputs:
+      names: ${{ steps.trace-cases.outputs.names }}
+    steps:
+      - name: Checkout repo
+        uses: actions/checkout@v6
+
+      - name: Load trace cases
+        id: trace-cases
+        run: echo "names=$(python3 tools/trace_replay/trace_cases.py --ci --format names)" >> "$GITHUB_OUTPUT"
+
+  trace-fixtures:
+    name: trace fixture (${{ matrix.case }})
+    runs-on: ubuntu-latest
+    needs: trace-cases
+    strategy:
+      fail-fast: false
+      max-parallel: 4
+      matrix:
+        case: ${{ fromJSON(needs.trace-cases.outputs.names) }}
+    steps:
+      - name: Checkout repo
+        uses: actions/checkout@v6
+
+      - name: Fetch trace fixture
+        run: bash .github/scripts/fetch-trace-fixture-lfs.sh '${{ matrix.case }}'
+
+      - name: Stage trace fixture
+        run: |
+          safe_case="$(printf '%s' '${{ matrix.case }}' | sed 's/[^A-Za-z0-9._-]/_/g')"
+          stage_dir="trace-fixtures/${safe_case}"
+          mkdir -p "${stage_dir}"
+          python3 tools/trace_replay/trace_cases.py --format fixture-files --case '${{ matrix.case }}' |
+            while IFS= read -r file; do
+              cp "${file}" "${stage_dir}/"
+            done
+
+      - name: Upload trace fixture
+        uses: actions/upload-artifact@v7
+        with:
+          name: trace-fixture-${{ matrix.case }}
+          path: trace-fixtures/**
+          if-no-files-found: error
+
+  retrace:
+    name: retrace (${{ matrix.backend }}, ${{ matrix.case }})
+    runs-on: ubuntu-latest
+    needs:
+      - build-linux
+      - build-retrace
+      - trace-cases
+      - trace-fixtures
+    if: ${{ always() && needs.build-linux.result == 'success' && needs.build-retrace.result == 'success' && needs.trace-cases.result == 'success' }}
+    strategy:
+      fail-fast: false
+      max-parallel: 4
+      matrix:
+        backend:
+          - DirectGLES
+          - DirectVulkan
+        case: ${{ fromJSON(needs.trace-cases.outputs.names) }}
+
+    steps:
+      - name: Set Swap Space
+        uses: pierotofy/set-swap-space@v1.0
+        with:
+          swap-size-gb: 16
+
+      - name: Checkout repo
+        uses: actions/checkout@v6
+
+      - name: Download trace fixture
+        uses: actions/download-artifact@v8
+        with:
+          name: trace-fixture-${{ matrix.case }}
+          path: trace-fixture-download
+
+      - name: Install trace fixture
+        run: |
+          mkdir -p tools/trace_replay/fixtures
+          find trace-fixture-download -type f -exec cp {} tools/trace_replay/fixtures/ \;
+
+      - name: Get CMake
+        uses: lukka/get-cmake@v4.3.3
+
+      - name: Install runtime dependencies
+        run: |
+          sudo apt-get update
+          sudo apt-get install -y libvulkan1 libegl1-mesa-dev libgles2-mesa-dev libgl1-mesa-dri mesa-vulkan-drivers
+          test -e /usr/lib/x86_64-linux-gnu/libEGL.so
+          test -e /usr/lib/x86_64-linux-gnu/libGLESv2.so
+
+      - name: Download Linux runtime
+        uses: actions/download-artifact@v8
+        with:
+          name: mobilegl-linux-runtime
+          path: .
+
+      - name: Download trace replay
+        uses: actions/download-artifact@v8
+        with:
+          name: mobilegl-trace-replay
+          path: .
+
+      - name: Unpack retrace runtime
+        run: |
+          tar -xzf mobilegl-linux-runtime.tgz
+          tar -xzf mobilegl-trace-replay.tgz
+          test -f build-linux/libMobileGL.so
+          test -f build-retrace/tools/trace_replay/mobilegl_trace_replay
+
+      - name: Retrace and validate
+        working-directory: build-retrace/tools/trace_replay
+        run: |
+          if [ '${{ matrix.backend }}' = 'DirectVulkan' ]; then
+            export MOBILEGL_MAGMA_R11G11B10F_FALLBACK=1
+          fi
+          ctest -V --no-tests=error -R '^MobileGLTraceReplay\.${{ matrix.case }}\.${{ matrix.backend }}$'
+
+      - name: Upload actual image
+        if: always()
+        uses: actions/upload-artifact@v7
+        with:
+          name: retrace-result-${{ matrix.backend }}-${{ matrix.case }}
+          path: |
+            build-retrace/tools/trace_replay/${{ matrix.case }}/actual-images/**
+            build-retrace/tools/trace_replay/${{ matrix.case }}/${{ matrix.backend }}/output/**
+          if-no-files-found: warn
+
+  retrace-summary:
+    name: retrace summary
+    runs-on: ubuntu-latest
+    needs: retrace
+    if: ${{ always() && needs.retrace.result != 'skipped' }}
+
+    steps:
+      - name: Checkout repo
+        uses: actions/checkout@v6
+
+      - name: Set artifact metadata
+        run: |
+          echo "date_today=$(date +'%Y-%m-%d')" >> "$GITHUB_ENV"
+
+      - name: Set up Node.js
+        uses: actions/setup-node@v7
+        with:
+          node-version: '22'
+
+      - name: Download retrace results
+        uses: actions/download-artifact@v8
+        with:
+          pattern: retrace-result-*
+          path: retrace-artifacts
+
+      - name: Render retrace summary
+        run: |
+          node tools/trace_replay/render_retrace_summary.mjs \
+            --input retrace-artifacts \
+            --output-dir retrace-summary \
+            --title "MobileGL Linux retrace overview" \
+            --group-label "Linux" \
+            --html mobilegl-linux-retrace-overview.html
+
+      - name: Upload retrace summary
+        uses: actions/upload-artifact@v7
+        with:
+          path: retrace-summary/mobilegl-linux-retrace-overview.html
+          archive: false
+          if-no-files-found: error
+
+  remove-artifact-clutter:
+    name: remove artifact clutter
+    runs-on: ubuntu-latest
+    needs: retrace-summary
+    if: always()
+    permissions:
+      actions: write
+    steps:
+      - name: Delete intermediate Linux retrace artifacts
+        env:
+          GH_TOKEN: ${{ github.token }}
+        run: |
+          declare -A failed_cases=()
+          while IFS= read -r job_name; do
+            case_name="${job_name#retrace (*, }"
+            case_name="${case_name%)}"
+            failed_cases["${case_name}"]=1
+          done < <(
+            gh api --paginate "repos/${GITHUB_REPOSITORY}/actions/runs/${GITHUB_RUN_ID}/jobs?per_page=100" \
+              --jq '.jobs[] | select(.name | startswith("retrace (")) | select(.conclusion == "failure" or .conclusion == "cancelled" or .conclusion == "timed_out" or .conclusion == "action_required") | .name'
+          )
+
+          if ((${#failed_cases[@]})); then
+            echo "Retaining fixtures for failed retrace case(s):"
+            printf '  %s\n' "${!failed_cases[@]}"
+          else
+            echo "All retrace jobs succeeded; no fixtures need to be retained."
+          fi
+
+          deleted=0
+          retained=0
+          while IFS=$'\t' read -r artifact_id artifact_name; do
+            if [[ "${artifact_name}" == trace-fixture-* ]]; then
+              case_name="${artifact_name#trace-fixture-}"
+              if [[ -v "failed_cases[${case_name}]" ]]; then
+                echo "Retaining ${artifact_name} (${artifact_id}) for failed retrace."
+                ((retained += 1))
+                continue
+              fi
+            fi
+
+            echo "Deleting ${artifact_name} (${artifact_id})"
+            gh api --method DELETE "repos/${GITHUB_REPOSITORY}/actions/artifacts/${artifact_id}"
+            ((deleted += 1))
+          done < <(
+            gh api --paginate "repos/${GITHUB_REPOSITORY}/actions/runs/${GITHUB_RUN_ID}/artifacts?per_page=100" \
+              --jq '.artifacts[] | select(.name | startswith("trace-fixture-") or startswith("retrace-result-")) | [.id, .name] | @tsv'
+          )
+
+          echo "Deleted ${deleted} intermediate Linux artifact(s); retained ${retained} failed-retrace fixture(s)."

.gitignore

@@ -22,3 +22,6 @@ MobileGL/MG*/cmake-build*
 /android-plugin/.gradle
 /android-plugin/build
 /android-plugin/app/build
+/android-plugin/app/src/trace/jniLibs
+/android-plugin/local.properties
+tools/trace_replay/work/

.gitmodules

@@ -28,3 +28,6 @@
 [submodule "3rdparty/SPIRV-Reflect"]
 	path = 3rdparty/SPIRV-Reflect
 	url = https://github.com/KhronosGroup/SPIRV-Reflect.git
+[submodule "3rdparty/apitrace"]
+	path = 3rdparty/apitrace
+	url = https://github.com/MobileGL-Dev/apitrace.git

CMakeLists.txt

@@ -6,6 +6,11 @@ option(MOBILEGL_BUILD_TEST        "Build MobileGL tests"
 option(MOBILEGL_BUILD_BENCHMARK   "Build MobileGL benchmarks"                        ON )
 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)
+option(MOBILEGL_TRACE_ANGLE_VARIANTS "Enable signed trace-APK ANGLE variant loading" OFF)
+option(MOBILEGL_IOS               "Build MobileGL for iOS instead of macOS when APPLE is set" OFF)
+set(MOBILEGL_LOG_ACTIVE_LEVEL "MOBILEGL_LOG_LEVEL_INFO" CACHE STRING "MobileGL active log level macro")
+set(MOBILEGL_VULKAN_LIBRARY "" CACHE FILEPATH "Vulkan loader/MoltenVK library to link for iOS builds")
 
 if (ANDROID)
     set(MOBILEGL_BUILD_TEST       OFF CACHE BOOL "Build MobileGL tests"      FORCE)
@@ -181,10 +186,17 @@ set(SOURCE_FILES
     MobileGL/MG_Util/ShaderTranspiler/glslang/TMglGlslIoResolver.cpp
     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/DecomposeWorkgroupVec3Pass.cpp
+    MobileGL/MG_Util/ShaderTranspiler/SpirvPasses/LowerDrawParametersPass.cpp
+    MobileGL/MG_Util/ShaderTranspiler/SpirvPasses/RebaseInstanceIndexPass.cpp
+    MobileGL/MG_Util/ShaderTranspiler/SpirvPasses/StripUboMemberRelaxedPrecisionPass.cpp
 
     MobileGL/MG_Util/BackendLoaders/OpenGL/Loader.cpp
     MobileGL/MG_Util/BackendLoaders/Vulkan/Loader.cpp
 
+    MobileGL/MG_Util/SelfTest/DriverPost.cpp
+
     MobileGL/MG_Util/Texture/PixelStoreProcessor.cpp
     MobileGL/MG_Util/Texture/TextureFormatProcessor.cpp
 
@@ -212,6 +224,7 @@ set(SOURCE_FILES
     MobileGL/MG_Impl/GLImpl/Exporting/Definitions.cpp
     MobileGL/MG_Impl/GLImpl/Getter/GL_Getter.cpp
     MobileGL/MG_Impl/GLImpl/Sync/GL_Sync.cpp
+    MobileGL/MG_Impl/GLImpl/Query/GL_Query.cpp
 
     MobileGL/MG_Impl/Init.cpp
     MobileGL/MG_Impl/GetProcAddress.cpp
@@ -239,6 +252,7 @@ set(SOURCE_FILES
     MobileGL/MG_Backend/DirectVulkan/Renderer/VertexInputStateFactory.cpp
     MobileGL/MG_Backend/DirectVulkan/Renderer/VkBufferObject.cpp
     MobileGL/MG_Backend/DirectVulkan/Renderer/VkTextureManager.cpp
+    MobileGL/MG_Backend/DirectVulkan/Renderer/VkTimerQueryManager.cpp
     MobileGL/MG_Backend/DirectVulkan/Renderer/VkSamplerManager.cpp
     MobileGL/MG_Backend/DirectVulkan/Renderer/VkClearManager.cpp
     MobileGL/MG_Backend/DirectVulkan/Renderer/VkRenderPassManager.cpp
@@ -271,6 +285,21 @@ set(SOURCE_FILES
     MobileGL/MG_State/GLState/RenderbufferState/RenderbufferState.cpp
 )
 
+if (APPLE AND NOT MOBILEGL_IOS)
+    list(APPEND SOURCE_FILES
+        MobileGL/MG_Impl/CGLImpl/CGLImpl.cpp
+        MobileGL/MG_Impl/CGLImpl/Exporting/Definitions.cpp
+        MobileGL/MG_Impl/DyldInterpose/DyldInterpose.cpp
+        MobileGL/MG_Impl/NSOpenGLImpl/NSOpenGLImpl.cpp
+    )
+endif()
+
+if (ANDROID)
+    list(APPEND SOURCE_FILES
+        MobileGL/MG_Util/SelfTest/DriverPostJni.cpp
+    )
+endif()
+
 set(MOBILEGL_LINK_LIBRARIES
         glslang::glslang
         spirv-cross-c
@@ -329,8 +358,22 @@ target_link_libraries(${CMAKE_PROJECT_NAME}
 target_compile_definitions(${CMAKE_PROJECT_NAME}
         PUBLIC
         ${MOBILEGL_COMPILE_DEF}
+        MOBILEGL_LOG_ACTIVE_LEVEL=${MOBILEGL_LOG_ACTIVE_LEVEL}
+        $<$<BOOL:${MOBILEGL_TRACE_ANGLE_VARIANTS}>:MOBILEGL_TRACE_ANGLE_VARIANTS=1>
 )
 
+if(UNIX AND NOT APPLE AND NOT ANDROID)
+    foreach(MOBILEGL_LOADER_ALIAS
+            libEGL.so libEGL.so.1)
+        add_custom_command(TARGET ${CMAKE_PROJECT_NAME} POST_BUILD
+            COMMAND ${CMAKE_COMMAND} -E create_symlink
+                    "$<TARGET_FILE_NAME:${CMAKE_PROJECT_NAME}>"
+                    "$<TARGET_FILE_DIR:${CMAKE_PROJECT_NAME}>/${MOBILEGL_LOADER_ALIAS}"
+            COMMENT "Creating ${MOBILEGL_LOADER_ALIAS} alias for Linux GL/EGL loaders"
+        )
+    endforeach()
+endif()
+
 if(NOT ANDROID)
     add_library(${CMAKE_PROJECT_NAME}_s STATIC 
         ${SOURCE_FILES}
@@ -362,6 +405,7 @@ if(NOT ANDROID)
     target_compile_definitions(${CMAKE_PROJECT_NAME}_s
             PUBLIC
             ${MOBILEGL_COMPILE_DEF}
+            MOBILEGL_LOG_ACTIVE_LEVEL=${MOBILEGL_LOG_ACTIVE_LEVEL}
     )
 endif()
 
@@ -380,7 +424,48 @@ if (ANDROID)
     )
 endif()
 
-if (NOT ANDROID)
+if (APPLE AND NOT MOBILEGL_IOS)
+    target_link_libraries(${CMAKE_PROJECT_NAME} PUBLIC
+        "-framework Cocoa"
+        "-framework QuartzCore"
+        "-framework Foundation"
+        "-framework OpenGL"
+        objc)
+    if(TARGET ${CMAKE_PROJECT_NAME}_s)
+        target_link_libraries(${CMAKE_PROJECT_NAME}_s PUBLIC
+            "-framework Cocoa"
+            "-framework QuartzCore"
+            "-framework Foundation"
+            "-framework OpenGL"
+            objc)
+    endif()
+endif()
+
+if (APPLE AND MOBILEGL_IOS)
+    target_compile_definitions(${CMAKE_PROJECT_NAME} PUBLIC MOBILEGL_IOS=1 _LIBCPP_DISABLE_AVAILABILITY)
+    target_link_libraries(${CMAKE_PROJECT_NAME} PUBLIC
+        "-framework CoreGraphics"
+        "-framework Foundation"
+        "-framework QuartzCore"
+        objc)
+    if (MOBILEGL_VULKAN_LIBRARY)
+        target_link_libraries(${CMAKE_PROJECT_NAME} PUBLIC "${MOBILEGL_VULKAN_LIBRARY}")
+    endif()
+
+    if(TARGET ${CMAKE_PROJECT_NAME}_s)
+        target_compile_definitions(${CMAKE_PROJECT_NAME}_s PUBLIC MOBILEGL_IOS=1 _LIBCPP_DISABLE_AVAILABILITY)
+        target_link_libraries(${CMAKE_PROJECT_NAME}_s PUBLIC
+            "-framework CoreGraphics"
+            "-framework Foundation"
+            "-framework QuartzCore"
+            objc)
+        if (MOBILEGL_VULKAN_LIBRARY)
+            target_link_libraries(${CMAKE_PROJECT_NAME}_s PUBLIC "${MOBILEGL_VULKAN_LIBRARY}")
+        endif()
+    endif()
+endif()
+
+if (NOT ANDROID AND NOT MOBILEGL_IOS)
     find_package(Vulkan)
     if (Vulkan_FOUND)
         target_link_libraries(${CMAKE_PROJECT_NAME} PUBLIC Vulkan::Vulkan Vulkan::Headers)
@@ -388,6 +473,17 @@ if (NOT ANDROID)
         target_include_directories(${CMAKE_PROJECT_NAME} PUBLIC ${Vulkan_INCLUDE_DIR})
         target_include_directories(${CMAKE_PROJECT_NAME}_s PUBLIC ${Vulkan_INCLUDE_DIR})
     endif ()
+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)
@@ -396,4 +492,8 @@ if (NOT ANDROID)
     if (MOBILEGL_BUILD_BENCHMARK)
         add_subdirectory(MobileGL/MG_Benchmark)
     endif()
+
+    if (MOBILEGL_BUILD_TRACE_REPLAY)
+        add_subdirectory(tools/trace_replay)
+    endif()
 endif()

MobileGL/Config.h

@@ -14,9 +14,59 @@ 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, 6, 0, "-dev", VersionType::Development};
+    inline const Version CoreVersion = {26, 7, 0, "-dev", VersionType::Development};
     inline const VersionStringFormatAttrib DefaultVersionStringFormatAttrib = {2, 2, 0, true, true};
     inline const Uint64 CacheVersion = 0;
 
     extern BackendType ActiveBackendType;
+
+    // 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"
+    // (case-insensitive).
+    //
+    // Env variables intentionally NOT mirrored here (kept as live std::getenv at their
+    // call sites):
+    //   - 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).
+    struct FeaturesTable {
+        // MOBILEGL_DISABLE_TIMERQUERY: do not advertise or use GPU timer queries.
+        Bool DisableTimerQuery = false;
+        // MOBILEGL_USE_ANGLE: load ANGLE EGL/GLES libraries.
+        Bool UseAngle = false;
+#if defined(MOBILEGL_TRACE_ANGLE_VARIANTS)
+        // MOBILEGL_TRACE_ANGLE_VARIANT: signed trace-APK ANGLE build short hash.
+        String TraceAngleVariant;
+#endif
+        // MOBILEGL_DISABLE_SUBGROUP: force-disable Vulkan shader subgroup support.
+        Bool DisableSubgroup = false;
+        // MOBILEGL_MAGMA_R11G11B10F_FALLBACK: use fallback format for R11G11B10F on Vulkan.
+        Bool MagmaR11G11B10FFallback = false;
+        // MOBILEGL_MAGMA_FRAMESINFLIGHT: requested Magma frames in flight, defaulting to 3.
+        Uint32 MagmaFramesInFlight = 3;
+        // MOBILEGL_AVOID_SAMPLER_MIPMAP_MIN_FILTER: avoid mipmap min filters in samplers,
+        // resolves certain rendering bugs on ANGLE + llvmpipe.
+        Bool AvoidSamplerMipmapMinFilter = false;
+        // MOBILEGL_COHERENT_AS_FLUSH: app-compat for engines (e.g. Flywheel) that write
+        // GPU-read data through persistent GL_MAP_FLUSH_EXPLICIT_BIT maps they never
+        // flush. Persistent FLUSH_EXPLICIT map requests are rewritten to coherent
+        // semantics: writes reach the backend without glFlushMappedBufferRange, and
+        // flush calls on rewritten maps become error-free no-ops. Non-persistent maps
+        // keep spec FLUSH_EXPLICIT behavior.
+        Bool CoherentAsFlush = false;
+        // MOBILEGL_TRACE_SKIP_AUTODESTROY: skip teardown in the ELF destructor (Init.cpp).
+        Bool TraceSkipAutodestroy = false;
+        // MOBILEGL_DISABLE_UBO_RING: force the DirectGLES global-UBO upload back to the
+        // 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;
+    };
+    extern FeaturesTable Features;
 } // namespace MobileGL::MG_Config

MobileGL/ConfigLoader.cpp

@@ -8,10 +8,19 @@
 
 #include "Config.h"
 
+#include <cerrno>
+#include <cstdlib>
+
 #ifndef _WIN32
 extern char** environ;
 #endif
 
+namespace MobileGL::MG_Config {
+    // Zero/default-initialized at static-init time (all fields have constexpr-friendly
+    // defaults), so it is safe to read even if MG_ConfigLoader::Init has not run yet.
+    FeaturesTable Features;
+} // namespace MobileGL::MG_Config
+
 namespace MobileGL::MG_ConfigLoader {
     static UniquePtr<UnorderedMap<String, String>> acceptedEnvVariablesMap;
 
@@ -60,6 +69,62 @@ namespace MobileGL::MG_ConfigLoader {
         }
     }
 
+    // Unified truthy rule for boolean feature env variables: set, non-empty, not "0",
+    // and not "false" (case-insensitive).
+    static Bool IsTruthyValue(const String& value) {
+        if (value.empty() || value == "0") {
+            return false;
+        }
+        String lowered = value;
+        std::transform(lowered.begin(), lowered.end(), lowered.begin(),
+                       [](unsigned char c) { return static_cast<char>(std::tolower(c)); });
+        return lowered != "false";
+    }
+
+    inline Bool QueryEnvFlag(const String& key) {
+        auto it = acceptedEnvVariablesMap->find(key);
+        return it != acceptedEnvVariablesMap->end() && IsTruthyValue(it->second);
+    }
+
+    inline Uint32 QueryEnvUint32(const String& key, Uint32 defaultValue, Uint32 minValue, Uint32 maxValue) {
+        auto it = acceptedEnvVariablesMap->find(key);
+        if (it == acceptedEnvVariablesMap->end()) {
+            return defaultValue;
+        }
+
+        const String& value = it->second;
+        char* parseEnd = nullptr;
+        errno = 0;
+        const unsigned long parsedValue = std::strtoul(value.c_str(), &parseEnd, 10);
+        if (parseEnd == value.c_str() || *parseEnd != '\0' || errno == ERANGE || parsedValue < minValue ||
+            parsedValue > maxValue) {
+            MGLOG_W("Config: Ignoring invalid env variable %s='%s'; expected an integer in range [%u, %u], "
+                    "using default %u",
+                    key.c_str(), value.c_str(), minValue, maxValue, defaultValue);
+            return defaultValue;
+        }
+
+        return static_cast<Uint32>(parsedValue);
+    }
+
+    inline void InitFeatures() {
+        auto& features = MG_Config::Features;
+        features.DisableTimerQuery = QueryEnvFlag("MOBILEGL_DISABLE_TIMERQUERY");
+        features.UseAngle = QueryEnvFlag("MOBILEGL_USE_ANGLE");
+#if defined(MOBILEGL_TRACE_ANGLE_VARIANTS)
+        QueryEnvVariable("MOBILEGL_TRACE_ANGLE_VARIANT", features.TraceAngleVariant, "");
+#endif
+        features.DisableSubgroup = QueryEnvFlag("MOBILEGL_DISABLE_SUBGROUP");
+        features.MagmaR11G11B10FFallback = QueryEnvFlag("MOBILEGL_MAGMA_R11G11B10F_FALLBACK");
+        features.MagmaFramesInFlight = QueryEnvUint32("MOBILEGL_MAGMA_FRAMESINFLIGHT", 3, 1, 64);
+        features.AvoidSamplerMipmapMinFilter =
+            QueryEnvFlag("MOBILEGL_AVOID_SAMPLER_MIPMAP_MIN_FILTER");
+        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");
+    }
+
     inline void InitBackendType() {
         String backendTypeStr;
         QueryEnvVariable("MOBILEGL_BACKEND_TYPE", backendTypeStr, "DirectGLES");
@@ -81,6 +146,7 @@ namespace MobileGL::MG_ConfigLoader {
         InitializeAcceptedEnvVariables();
 
         InitBackendType();
+        InitFeatures();
 
         // Destroy the map since we won't need it anymore
         acceptedEnvVariablesMap.reset();

MobileGL/Defines.h

@@ -32,10 +32,12 @@
 #define MOBILEGL_GLX_API MOBILEGL_API
 #define MOBILEGL_GL_API MOBILEGL_API
 #define MOBILEGL_EGL_API MOBILEGL_API
+#define MOBILEGL_CGL_API MOBILEGL_API
+#define MOBILEGL_NSOPENGL_API MOBILEGL_API
 
 // ====================== MobileGL configurations ======================= //
 #ifndef MOBILEGL_LOG_ACTIVE_LEVEL
-#define MOBILEGL_LOG_ACTIVE_LEVEL MOBILEGL_LOG_LEVEL_DEBUG
+#define MOBILEGL_LOG_ACTIVE_LEVEL MOBILEGL_LOG_LEVEL_INFO
 #endif
 
 #define MOBILEGL_LOG_ENABLE_CONSOLE 0

MobileGL/Init.cpp

@@ -15,7 +15,39 @@
 #include <MG_Impl/GLImpl/Framebuffer/GL_Framebuffer.h>
 
 namespace MobileGL {
+    namespace {
+        Bool g_isInitialized = false;
+
+        void DestroyImpl(Bool logLifecycle) {
+            if (!g_isInitialized) {
+                return;
+            }
+
+            if (logLifecycle) {
+                MGLOG_I("MobileGL closing...");
+            }
+            glslang::FinalizeProcess();
+            MG_Backend::pActiveBackendObject.reset();
+            MG_State::pGLContext.reset();
+            MG_State::pEGLContext.reset();
+            MG_Impl::GLImpl::TextureImpl::pProxyTextureManager.reset();
+            MG_Impl::GLImpl::FramebufferImpl::pDefaultFramebufferInfo.reset();
+            MG_Backend::gBackendFunctionsTable = {};
+            g_isInitialized = false;
+            if (logLifecycle) {
+                MG_Util::Debug::Close();
+            }
+
+            // TODO: add and use Destroy functions for other subsystems
+        }
+    }
+
     void Initialize() {
+        if (g_isInitialized) {
+            MGLOG_D("MobileGL already initialized; skipping duplicate Initialize()");
+            return;
+        }
+
         MG_Util::Debug::InitFile();
         MGLOG_I("Initializing MobileGL...");
         MG_ConfigLoader::Init();
@@ -28,19 +60,12 @@ namespace MobileGL {
         MGLOG_D("MG_Impl initialized");
         glslang::InitializeProcess();
         MGLOG_D("glslang initialized");
+        g_isInitialized = true;
         MGLOG_I("MobileGL initialized");
     }
 
     void Destroy() {
-        MGLOG_I("MobileGL closing...");
-        glslang::FinalizeProcess();
-        MG_State::pGLContext.reset();
-        MG_State::pEGLContext.reset();
-        MG_Impl::GLImpl::TextureImpl::pProxyTextureManager.reset();
-        MG_Impl::GLImpl::FramebufferImpl::pDefaultFramebufferInfo.reset();
-        MG_Util::Debug::Close();
-
-        // TODO: add and use Destroy functions for other subsystems
+        DestroyImpl(true);
     }
 
 #if defined(__linux__) || defined(__APPLE__)
@@ -49,7 +74,15 @@ namespace MobileGL {
     }
 
     __attribute__((destructor)) static void AutoDestroy() {
-        Destroy();
+        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
 

MobileGL/MG_Backend/BackendObject.cpp

@@ -7,18 +7,164 @@
 // End of Source File Header
 
 #include "BackendObject.h"
+#include "MG_Util/Converters/MGToStr/TextureEnumConverter.h"
+#include <algorithm>
+#include <cstring>
+#include <iomanip>
+#include <sstream>
 
 namespace MobileGL::MG_Backend {
     namespace {
         Bool IsReleaseCurrentRequest(EGLDisplay dpy, EGLSurface draw, EGLSurface read, EGLContext ctx) {
-            return dpy == EGL_NO_DISPLAY && draw == EGL_NO_SURFACE && read == EGL_NO_SURFACE && ctx == EGL_NO_CONTEXT;
+            (void)dpy;
+            return draw == EGL_NO_SURFACE && read == EGL_NO_SURFACE && ctx == EGL_NO_CONTEXT;
         }
 
         std::thread::id CurrentThreadKey() {
             return std::this_thread::get_id();
         }
+
+        const char* GetFormatCapabilitySupportString(const FormatCapabilityCache& cache,
+                                                     SizeT targetIndex,
+                                                     SizeT formatIndex,
+                                                     FormatCapability capability) {
+            if (HasFormatCapability(cache.FullCaps[targetIndex][formatIndex], capability)) return "Full";
+            if (HasFormatCapability(cache.CaveatCaps[targetIndex][formatIndex], capability)) return "Caveat";
+            return "None";
+        }
+
+        SizeT GetPrintedFormatNameWidth() {
+            SizeT width = 0;
+            for (SizeT formatIndex = 0; formatIndex < kFormatCapabilityFormatCount; ++formatIndex) {
+                const auto format = static_cast<TextureInternalFormat>(formatIndex);
+                width = std::max(width, MG_Util::ConvertTextureInternalFormatToString(format).size());
+            }
+            return width;
+        }
+
+        SizeT GetCapabilityColumnWidth(FormatCapability capability) {
+            SizeT width = std::strlen(GetFormatCapabilityName(capability));
+            width = std::max<SizeT>(width, std::strlen("Caveat"));
+            return width;
+        }
+
+        String BuildFormatCapabilityHeader(SizeT formatNameWidth) {
+            std::ostringstream line;
+            line << std::left << std::setw(static_cast<Int>(formatNameWidth)) << "";
+            for (FormatCapability capability : kReportedFormatCapabilities) {
+                line << " | " << std::left << std::setw(static_cast<Int>(GetCapabilityColumnWidth(capability)))
+                     << GetFormatCapabilityName(capability);
+            }
+            return line.str();
+        }
+
+        String BuildFormatCapabilityRow(const FormatCapabilityCache& cache,
+                                        SizeT targetIndex,
+                                        SizeT formatIndex,
+                                        SizeT formatNameWidth) {
+            const auto format = static_cast<TextureInternalFormat>(formatIndex);
+            std::ostringstream line;
+            line << std::left << std::setw(static_cast<Int>(formatNameWidth))
+                 << MG_Util::ConvertTextureInternalFormatToString(format);
+            for (FormatCapability capability : kReportedFormatCapabilities) {
+                line << " | " << std::left << std::setw(static_cast<Int>(GetCapabilityColumnWidth(capability)))
+                     << GetFormatCapabilitySupportString(cache, targetIndex, formatIndex, capability);
+            }
+            return line.str();
+        }
     } // namespace
 
+    void FormatCapabilityCache::Clear() {
+        for (auto& row : FullCaps) {
+            row.fill(FormatCapabilityFlags{});
+        }
+        for (auto& row : CaveatCaps) {
+            row.fill(FormatCapabilityFlags{});
+        }
+        for (auto& row : SampleCounts) {
+            for (auto& counts : row) {
+                counts.clear();
+            }
+        }
+    }
+
+    Bool HasFormatCapability(FormatCapabilityFlags caps, FormatCapability capability) {
+        return static_cast<Bool>(caps & capability);
+    }
+
+    SizeT GetFormatCapabilityTargetIndex(TextureTarget target) {
+        if (target == TextureTarget::Unknown || static_cast<Int>(target) < 0 ||
+            static_cast<SizeT>(target) >= kFormatCapabilityTextureTargetCount) {
+            return kFormatCapabilityTargetCount;
+        }
+        return static_cast<SizeT>(target);
+    }
+
+    SizeT GetRenderbufferFormatCapabilityTargetIndex() {
+        return kFormatCapabilityRenderbufferTargetIndex;
+    }
+
+    const char* GetFormatCapabilityName(FormatCapability capability) {
+        switch (capability) {
+        case FormatCapability::Creatable:
+            return "Creatable";
+        case FormatCapability::Sampled:
+            return "Sampled";
+        case FormatCapability::LinearFilter:
+            return "LinearFilter";
+        case FormatCapability::GenerateMipmap:
+            return "GenerateMipmap";
+        case FormatCapability::TextureGather:
+            return "TextureGather";
+        case FormatCapability::TextureShadow:
+            return "TextureShadow";
+        case FormatCapability::FramebufferRenderable:
+            return "FramebufferRenderable";
+        case FormatCapability::FramebufferLayered:
+            return "FramebufferLayered";
+        case FormatCapability::MultisampleTexture:
+            return "MultisampleTexture";
+        case FormatCapability::MultisampleRenderbuffer:
+            return "MultisampleRenderbuffer";
+        case FormatCapability::ColorAttachment:
+            return "ColorAttachment";
+        case FormatCapability::DepthAttachment:
+            return "DepthAttachment";
+        case FormatCapability::StencilAttachment:
+            return "StencilAttachment";
+        case FormatCapability::TextureBuffer:
+            return "TextureBuffer";
+        }
+        return "Unknown";
+    }
+
+    String GetFormatCapabilityTargetName(SizeT targetIndex) {
+        if (targetIndex == kFormatCapabilityRenderbufferTargetIndex) {
+            return "Renderbuffer";
+        }
+        if (targetIndex >= kFormatCapabilityTextureTargetCount) {
+            return "Unknown";
+        }
+        return MG_Util::ConvertTextureTargetToString(static_cast<TextureTarget>(targetIndex));
+    }
+
+    void PrintFormatCapabilities(const FormatCapabilityCache& cache) {
+        const SizeT formatNameWidth = GetPrintedFormatNameWidth();
+
+        MGLOG_D("Backend format capabilities:");
+        for (SizeT targetIndex = 0; targetIndex < kFormatCapabilityTargetCount; ++targetIndex) {
+            MGLOG_D("");
+            const String targetName = GetFormatCapabilityTargetName(targetIndex);
+            MGLOG_D("- %s", targetName.c_str());
+            const String header = BuildFormatCapabilityHeader(formatNameWidth);
+            MGLOG_D("%s", header.c_str());
+            for (SizeT formatIndex = 0; formatIndex < kFormatCapabilityFormatCount; ++formatIndex) {
+                const String row = BuildFormatCapabilityRow(cache, targetIndex, formatIndex, formatNameWidth);
+                MGLOG_D("%s", row.c_str());
+            }
+        }
+    }
+
     Bool BackendObject::InitializeEGLDisplay(EGLDisplay dpy, EGLint* major, EGLint* minor) {
         const std::lock_guard<std::recursive_mutex> lock(m_eglStateMutex);
         if (dpy == EGL_NO_DISPLAY) {
@@ -42,57 +188,116 @@ namespace MobileGL::MG_Backend {
         return true;
     }
 
-    Bool BackendObject::CreateEGLWindowSurface(const WindowHandle& handle) {
+    Bool BackendObject::CreateEGLWindowSurface(EGLSurface surface, const WindowHandle& handle) {
         const std::lock_guard<std::recursive_mutex> lock(m_eglStateMutex);
-        if (!m_eglDisplayInitialized) {
-            MGLOG_E("CreateEGLWindowSurface failed: EGL display is not initialized");
+        return RegisterEGLWindowSurface(surface, handle) && ActivateEGLSurface(surface);
+    }
+
+    Bool BackendObject::ResizeEGLWindowSurface(EGLSurface surface, Uint32 width, Uint32 height) {
+        const std::lock_guard<std::recursive_mutex> lock(m_eglStateMutex);
+        auto surfaceIt = m_eglSurfaces.find(surface);
+        if (surfaceIt == m_eglSurfaces.end() || surfaceIt->second.Kind != SurfaceKind::Window) {
+            MGLOG_E("ResizeEGLWindowSurface failed: no window surface is initialized");
             return false;
         }
-        if (handle.Backend == WindowBackend::Unknown || !handle.Handle) {
-            MGLOG_E("CreateEGLWindowSurface failed: invalid native window handle");
-            return false;
+        surfaceIt->second.Window.Width = width;
+        surfaceIt->second.Window.Height = height;
+        if (m_eglSurface == surface) {
+            m_windowHandle.Width = width;
+            m_windowHandle.Height = height;
         }
-
-        if (m_eglSurfaceInitialized && m_eglSurfaceKind == SurfaceKind::Window &&
-            m_windowHandle.Backend == handle.Backend && m_windowHandle.Handle == handle.Handle) {
-            return true;
-        }
-
-        SetWindowHandle(handle);
-        if (!InitWindowSurface()) {
-            MGLOG_E("CreateEGLWindowSurface failed: backend InitWindowSurface failed");
-            return false;
-        }
-
-        m_eglSurfaceInitialized = true;
-        m_eglSurfaceKind = SurfaceKind::Window;
-        m_eglCurrentThreads.clear();
-        m_backendCapabilitiesInitialized = false;
         return true;
     }
 
-    Bool BackendObject::CreateEGLPbufferSurface(EGLint width, EGLint height) {
+    Bool BackendObject::CreateEGLPbufferSurface(EGLSurface surface, EGLint width, EGLint height) {
+        const std::lock_guard<std::recursive_mutex> lock(m_eglStateMutex);
+        return RegisterEGLPbufferSurface(surface, width, height) && ActivateEGLSurface(surface);
+    }
+
+    Bool BackendObject::RegisterEGLWindowSurface(EGLSurface surface, const WindowHandle& handle) {
         const std::lock_guard<std::recursive_mutex> lock(m_eglStateMutex);
         if (!m_eglDisplayInitialized) {
-            MGLOG_E("CreateEGLPbufferSurface failed: EGL display is not initialized");
+            MGLOG_E("RegisterEGLWindowSurface failed: EGL display is not initialized");
+            return false;
+        }
+        if (surface == EGL_NO_SURFACE) {
+            MGLOG_E("RegisterEGLWindowSurface failed: invalid EGLSurface");
+            return false;
+        }
+        if (handle.Backend == WindowBackend::Unknown || !handle.Handle) {
+            MGLOG_E("RegisterEGLWindowSurface failed: invalid native window handle");
+            return false;
+        }
+
+        auto& state = m_eglSurfaces[surface];
+        state = EGLSurfaceState{
+            .Kind = SurfaceKind::Window,
+            .Window = handle,
+            .Width = static_cast<EGLint>(std::max<Uint32>(handle.Width, 1)),
+            .Height = static_cast<EGLint>(std::max<Uint32>(handle.Height, 1)),
+        };
+        return true;
+    }
+
+    Bool BackendObject::RegisterEGLPbufferSurface(EGLSurface surface, EGLint width, EGLint height) {
+        const std::lock_guard<std::recursive_mutex> lock(m_eglStateMutex);
+        if (!m_eglDisplayInitialized) {
+            MGLOG_E("RegisterEGLPbufferSurface failed: EGL display is not initialized");
+            return false;
+        }
+        if (surface == EGL_NO_SURFACE) {
+            MGLOG_E("RegisterEGLPbufferSurface failed: invalid EGLSurface");
             return false;
         }
         if (width <= 0 || height <= 0) {
-            MGLOG_E("CreateEGLPbufferSurface failed: invalid size %dx%d", width, height);
+            MGLOG_E("RegisterEGLPbufferSurface failed: invalid size %dx%d", width, height);
             return false;
         }
 
-        if (m_eglSurfaceInitialized && m_eglSurfaceKind == SurfaceKind::Pbuffer) {
+        m_eglSurfaces[surface] = EGLSurfaceState{
+            .Kind = SurfaceKind::Pbuffer,
+            .Width = width,
+            .Height = height,
+        };
+        return true;
+    }
+
+    const BackendObject::EGLSurfaceState* BackendObject::GetRegisteredEGLSurface(EGLSurface surface) const {
+        const std::lock_guard<std::recursive_mutex> lock(m_eglStateMutex);
+        auto surfaceIt = m_eglSurfaces.find(surface);
+        return surfaceIt == m_eglSurfaces.end() ? nullptr : &surfaceIt->second;
+    }
+
+    Bool BackendObject::ActivateEGLSurface(EGLSurface surface) {
+        const std::lock_guard<std::recursive_mutex> lock(m_eglStateMutex);
+        const auto* surfaceState = GetRegisteredEGLSurface(surface);
+        if (!surfaceState) {
+            MGLOG_E("ActivateEGLSurface failed: EGL surface is not registered");
+            return false;
+        }
+        if (m_eglSurfaceInitialized && m_eglSurface == surface) {
             return true;
         }
 
-        if (!InitPbufferSurface(width, height)) {
-            MGLOG_E("CreateEGLPbufferSurface failed: backend InitPbufferSurface failed");
+        if (surfaceState->Kind == SurfaceKind::Window) {
+            SetWindowHandle(surfaceState->Window);
+            if (!InitWindowSurface()) {
+                MGLOG_E("ActivateEGLSurface failed: backend InitWindowSurface failed");
+                return false;
+            }
+        } else if (surfaceState->Kind == SurfaceKind::Pbuffer) {
+            if (!InitPbufferSurface(surfaceState->Width, surfaceState->Height)) {
+                MGLOG_E("ActivateEGLSurface failed: backend InitPbufferSurface failed");
+                return false;
+            }
+        } else {
+            MGLOG_E("ActivateEGLSurface failed: unsupported surface kind");
             return false;
         }
 
+        m_eglSurface = surface;
         m_eglSurfaceInitialized = true;
-        m_eglSurfaceKind = SurfaceKind::Pbuffer;
+        m_eglSurfaceKind = surfaceState->Kind;
         m_eglCurrentThreads.clear();
         m_backendCapabilitiesInitialized = false;
         return true;
@@ -102,7 +307,7 @@ namespace MobileGL::MG_Backend {
         const std::lock_guard<std::recursive_mutex> lock(m_eglStateMutex);
         const auto threadKey = CurrentThreadKey();
         if (IsReleaseCurrentRequest(dpy, draw, read, ctx)) {
-            m_eglCurrentThreads.erase(threadKey);
+            ReleaseEGLCurrentThread(threadKey);
             return true;
         }
 
@@ -111,7 +316,21 @@ namespace MobileGL::MG_Backend {
             return false;
         }
         if (!m_eglSurfaceInitialized) {
-            MGLOG_E("MakeEGLCurrent failed: EGL surface is not initialized");
+            if (draw != read || !ActivateEGLSurface(draw)) {
+                MGLOG_E("MakeEGLCurrent failed: EGL surface is not initialized");
+                return false;
+            }
+        }
+        if (!GetRegisteredEGLSurface(draw) || !GetRegisteredEGLSurface(read)) {
+            MGLOG_E("MakeEGLCurrent failed: EGL surface is not registered");
+            return false;
+        }
+        if (draw != read) {
+            MGLOG_E("MakeEGLCurrent failed: separate draw/read surfaces are not supported");
+            return false;
+        }
+        if (draw != m_eglSurface && !ActivateEGLSurface(draw)) {
+            MGLOG_E("MakeEGLCurrent failed: EGL surface is not backed by this backend");
             return false;
         }
         if (draw == EGL_NO_SURFACE || read == EGL_NO_SURFACE || ctx == EGL_NO_CONTEXT) {
@@ -127,7 +346,13 @@ namespace MobileGL::MG_Backend {
             m_backendCapabilitiesInitialized = true;
         }
 
-        m_eglCurrentThreads[threadKey] = true;
+        ReleaseEGLCurrentThread(threadKey);
+        m_eglCurrentThreads[threadKey] = EGLCurrentState{
+            .Display = dpy,
+            .DrawSurface = draw,
+            .ReadSurface = read,
+            .Context = ctx,
+        };
         return true;
     }
 
@@ -136,6 +361,8 @@ namespace MobileGL::MG_Backend {
         m_eglSurfaceInitialized = false;
         m_backendCapabilitiesInitialized = false;
         m_eglSurfaceKind = SurfaceKind::None;
+        m_eglSurface = EGL_NO_SURFACE;
+        m_windowHandle = {};
         m_eglCurrentThreads.clear();
     }
 
@@ -145,11 +372,17 @@ namespace MobileGL::MG_Backend {
             MGLOG_E("SwapEGLBuffers failed: EGL display mismatch or not initialized");
             return false;
         }
-        if (m_eglCurrentThreads.find(CurrentThreadKey()) == m_eglCurrentThreads.end()) {
+        const auto currentIt = m_eglCurrentThreads.find(CurrentThreadKey());
+        if (currentIt == m_eglCurrentThreads.end()) {
             MGLOG_E("SwapEGLBuffers failed: no current context attached");
             return false;
         }
-        if (!m_eglSurfaceInitialized || draw == EGL_NO_SURFACE) {
+        if (currentIt->second.Display != dpy || currentIt->second.DrawSurface != draw ||
+            currentIt->second.Context == EGL_NO_CONTEXT) {
+            MGLOG_E("SwapEGLBuffers failed: draw surface is not current on this thread");
+            return false;
+        }
+        if (!m_eglSurfaceInitialized || draw == EGL_NO_SURFACE || draw != m_eglSurface) {
             MGLOG_E("SwapEGLBuffers failed: invalid draw surface");
             return false;
         }
@@ -164,12 +397,77 @@ namespace MobileGL::MG_Backend {
         return true;
     }
 
+    void BackendObject::SetEGLSwapInterval(Int interval) {
+        const auto& backendFunctions = GetBackendFunctions();
+        if (backendFunctions.SetSwapInterval) {
+            backendFunctions.SetSwapInterval(interval);
+        }
+    }
+
+    Bool BackendObject::IsEGLSurfaceCurrent(EGLSurface surface) const {
+        if (surface == EGL_NO_SURFACE) {
+            return false;
+        }
+        for (const auto& current : m_eglCurrentThreads) {
+            if (current.second.DrawSurface == surface || current.second.ReadSurface == surface) {
+                return true;
+            }
+        }
+        return false;
+    }
+
+    void BackendObject::DestroyPendingEGLSurfaceIfUnused(EGLSurface surface) {
+        auto surfaceIt = m_eglSurfaces.find(surface);
+        if (surfaceIt == m_eglSurfaces.end() || !surfaceIt->second.DestroyPending ||
+            IsEGLSurfaceCurrent(surface)) {
+            return;
+        }
+
+        m_eglSurfaces.erase(surfaceIt);
+        if (m_eglSurface == surface) {
+            OnEGLSurfaceReleased(surface);
+            ResetEGLRuntimeState();
+        }
+    }
+
+    void BackendObject::ReleaseEGLCurrentThread(const std::thread::id& threadKey) {
+        auto currentIt = m_eglCurrentThreads.find(threadKey);
+        if (currentIt == m_eglCurrentThreads.end()) {
+            return;
+        }
+
+        const EGLSurface drawSurface = currentIt->second.DrawSurface;
+        const EGLSurface readSurface = currentIt->second.ReadSurface;
+        m_eglCurrentThreads.erase(currentIt);
+        DestroyPendingEGLSurfaceIfUnused(drawSurface);
+        DestroyPendingEGLSurfaceIfUnused(readSurface);
+    }
+
+    void BackendObject::ReleaseEGLSurface(EGLSurface surface) {
+        const std::lock_guard<std::recursive_mutex> lock(m_eglStateMutex);
+        auto surfaceIt = m_eglSurfaces.find(surface);
+        if (surfaceIt == m_eglSurfaces.end()) {
+            return;
+        }
+
+        if (IsEGLSurfaceCurrent(surface)) {
+            surfaceIt->second.DestroyPending = true;
+            return;
+        }
+
+        m_eglSurfaces.erase(surfaceIt);
+        if (m_eglSurface == surface) {
+            OnEGLSurfaceReleased(surface);
+            ResetEGLRuntimeState();
+        }
+    }
+
     void BackendObject::ReleaseEGLResources() {
         const std::lock_guard<std::recursive_mutex> lock(m_eglStateMutex);
         ResetEGLRuntimeState();
+        m_eglSurfaces.clear();
         m_eglDisplay = EGL_NO_DISPLAY;
         m_eglDisplayInitialized = false;
-        m_windowHandle = {};
     }
 
     void BackendObject::SetWindowHandle(const WindowHandle& handle) {
@@ -177,9 +475,21 @@ namespace MobileGL::MG_Backend {
         m_windowHandle = handle;
     }
 
+    const FormatCapabilityCache& BackendObject::GetFormatCapabilities() const {
+        return m_formatCapabilities;
+    }
+
+    FormatCapabilityCache& BackendObject::MutableFormatCapabilities() {
+        return m_formatCapabilities;
+    }
+
     Bool BackendObject::InitPbufferSurface(EGLint width, EGLint height) {
         (void)width;
         (void)height;
         return false;
     }
+
+    void BackendObject::OnEGLSurfaceReleased(EGLSurface surface) {
+        (void)surface;
+    }
 } // namespace MobileGL::MG_Backend

MobileGL/MG_Backend/BackendObject.h

@@ -24,11 +24,88 @@ namespace MobileGL {
     };
 
     namespace MG_Backend {
+        enum class FormatCapability : Uint64 {
+            Creatable = 1ull << 0,
+
+            Sampled = 1ull << 1,
+            LinearFilter = 1ull << 2,
+            GenerateMipmap = 1ull << 3,
+            TextureGather = 1ull << 4,
+            TextureShadow = 1ull << 5,
+
+            FramebufferRenderable = 1ull << 6,
+            FramebufferLayered = 1ull << 7,
+            MultisampleTexture = 1ull << 8,
+            MultisampleRenderbuffer = 1ull << 9,
+
+            ColorAttachment = 1ull << 10,
+            DepthAttachment = 1ull << 11,
+            StencilAttachment = 1ull << 12,
+
+            TextureBuffer = 1ull << 13
+        };
+
+        using FormatCapabilityFlags = Flags<FormatCapability>;
+
+        inline constexpr Array<FormatCapability, 14> kReportedFormatCapabilities = {
+            FormatCapability::Creatable,
+            FormatCapability::Sampled,
+            FormatCapability::LinearFilter,
+            FormatCapability::GenerateMipmap,
+            FormatCapability::TextureGather,
+            FormatCapability::TextureShadow,
+            FormatCapability::FramebufferRenderable,
+            FormatCapability::FramebufferLayered,
+            FormatCapability::MultisampleTexture,
+            FormatCapability::MultisampleRenderbuffer,
+            FormatCapability::ColorAttachment,
+            FormatCapability::DepthAttachment,
+            FormatCapability::StencilAttachment,
+            FormatCapability::TextureBuffer,
+        };
+
+        inline constexpr SizeT kFormatCapabilityTextureTargetCount =
+            static_cast<SizeT>(TextureTarget::TextureTargetCount);
+        inline constexpr SizeT kFormatCapabilityRenderbufferTargetIndex = kFormatCapabilityTextureTargetCount;
+        inline constexpr SizeT kFormatCapabilityTargetCount = kFormatCapabilityTextureTargetCount + 1;
+        inline constexpr SizeT kFormatCapabilityFormatCount =
+            static_cast<SizeT>(TextureInternalFormat::TextureInternalFormatCount);
+
+        using FormatCapabilityTable =
+            Array<Array<FormatCapabilityFlags, kFormatCapabilityFormatCount>, kFormatCapabilityTargetCount>;
+        using FormatSampleCountTable =
+            Array<Array<Vector<Int>, kFormatCapabilityFormatCount>, kFormatCapabilityTargetCount>;
+
+        struct FormatCapabilityCache {
+            FormatCapabilityTable FullCaps{};
+            FormatCapabilityTable CaveatCaps{};
+            FormatSampleCountTable SampleCounts{};
+
+            void Clear();
+        };
+
+        Bool HasFormatCapability(FormatCapabilityFlags caps, FormatCapability capability);
+        SizeT GetFormatCapabilityTargetIndex(TextureTarget target);
+        SizeT GetRenderbufferFormatCapabilityTargetIndex();
+        const char* GetFormatCapabilityName(FormatCapability capability);
+        String GetFormatCapabilityTargetName(SizeT targetIndex);
+        void PrintFormatCapabilities(const FormatCapabilityCache& cache);
+
+        // Opaque backend fence-sync handle, created by GLFunctionsTable::FenceSync
+        // and released by GLFunctionsTable::DeleteSync.
+        using BackendSyncHandle = void*;
+
+        // Opaque backend timer-query handle, created by
+        // GLFunctionsTable::BeginTimeElapsedQuery / QueryCounterTimestamp and
+        // released by GLFunctionsTable::DeleteBackendQuery.
+        using BackendQueryHandle = void*;
+
         struct GLFunctionsTable {
             void (*DrawArrays)(GLenum mode, GLint first, GLsizei count);
             void (*DrawElements)(GLenum mode, GLsizei count, GLenum type, const void* indices);
             void (*DrawElementsBaseVertex)(GLenum mode, GLsizei count, GLenum type, const void* indices,
                                            GLint basevertex);
+            void (*MultiDrawArrays)(GLenum mode, const GLint* first, const GLsizei* count, GLsizei drawcount);
             void (*MultiDrawElements)(GLenum mode, const GLsizei* count, GLenum type, const GLvoid* const* indices,
                                       GLsizei drawcount);
             void (*MultiDrawElementsBaseVertex)(GLenum mode, const GLsizei* count, GLenum type,
@@ -79,6 +156,11 @@ namespace MobileGL {
                                    GLsizei height, GLint border);
             void (*CopyTexSubImage2D)(GLenum target, GLint level, GLint xoffset, GLint yoffset, GLint x, GLint y,
                                       GLsizei width, GLsizei height);
+            void (*CopyImageSubData)(const SharedPtr<MG_State::GLState::ITextureObject>& srcTexture,
+                                     GLenum srcTarget, GLint srcLevel, GLint srcX, GLint srcY, GLint srcZ,
+                                     const SharedPtr<MG_State::GLState::ITextureObject>& dstTexture,
+                                     GLenum dstTarget, GLint dstLevel, GLint dstX, GLint dstY, GLint dstZ,
+                                     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);
@@ -104,14 +186,106 @@ namespace MobileGL {
             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);
+            // 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
+            // fence right now (e.g. the calling thread does not own the backend
+            // context); the frontend treats such a sync as always signaled.
+            BackendSyncHandle (*FenceSync)();
+            GLenum (*ClientWaitSync)(BackendSyncHandle sync, GLbitfield flags, GLuint64 timeout);
+            void (*WaitSync)(BackendSyncHandle sync, GLbitfield flags, GLuint64 timeout);
+            void (*DeleteSync)(BackendSyncHandle sync);
+            Bool (*GetSyncStatus)(BackendSyncHandle sync); // true = signaled
+            // GL timer-query objects (GL_ARB_timer_query). All entries are
+            // optional (may be null); the frontend then falls back to zero
+            // results and reports GL_QUERY_COUNTER_BITS == 0.
+            // BeginTimeElapsedQuery / QueryCounterTimestamp may themselves
+            // return null when the backend cannot create a query right now;
+            // the frontend treats such a query as immediately available with
+            // a zero result.
+            // Dynamic support check: true only when the live backend can
+            // actually time at the moment of the call (extension / entry
+            // points / timestamp valid bits are known then, not at table
+            // init). Gates the advertised GL_QUERY_COUNTER_BITS.
+            Bool (*IsTimerQuerySupported)();
+            BackendQueryHandle (*BeginTimeElapsedQuery)();            // starts a TIME_ELAPSED span
+            void (*EndTimeElapsedQuery)(BackendQueryHandle query);    // ends the span
+            BackendQueryHandle (*QueryCounterTimestamp)();            // glQueryCounter(GL_TIMESTAMP) one-shot
+            Bool (*IsQueryResultAvailable)(BackendQueryHandle query); // non-blocking
+            // Returns true when a final value was produced (*outNanoseconds
+            // written; the frontend may cache it and release the handle).
+            // Returns false when the result could not be obtained YET - e.g.
+            // a Vulkan wait that refuses to block on a not-yet-submitted
+            // frame serial - in which case the frontend must keep the handle
+            // and leave the query readable later.
+            Bool (*GetQueryResult64)(BackendQueryHandle query, Bool wait, Uint64* outNanoseconds);
+            void (*DeleteBackendQuery)(BackendQueryHandle query);
+            Int64 (*GetGpuTimestampNs)(); // glGetInteger64v(GL_TIMESTAMP); 0 if unsupported
         };
         struct GlobalBackendFunctionsTable {
             GLFunctionsTable GL;
             void (*Present)();
+            // Optional: applies the app-requested eglSwapInterval to the native
+            // presentation path (null = backend keeps its own pacing policy).
+            void (*SetSwapInterval)(Int interval);
         };
 
         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;
+            Float SmoothLineWidthRangeMax = 1.0f;
+            Float SmoothLineWidthGranularity = 1.0f;
+            Float PointSizeRangeMin = 1.0f;
+            Float PointSizeRangeMax = 1.0f;
+            Float PointSizeGranularity = 1.0f;
+            Int Max3DTextureSize = 16384;
+            Int MaxArrayTextureLayers = 2048;
+            Int MaxCubeMapTextureSize = 16384;
+            Int MaxFramebufferWidth = 16384;
+            Int MaxFramebufferHeight = 16384;
+            Int MaxFramebufferLayers = 2048;
+            Int MaxRenderbufferSize = 16384;
+            Int MaxTextureSize = 16384;
+            Int MaxColorTextureSamples = 1;
+            Int MaxDepthTextureSamples = 1;
+            Int MaxFramebufferSamples = 1;
+            Int MaxIntegerSamples = 1;
+            Int MaxSamples = 1;
+            Int MaxSampleMaskWords = 1;
+            Int MaxTextureImageUnits = 32;
+            Int MaxVertexTextureImageUnits = 32;
+            Int MaxComputeTextureImageUnits = 32;
+            Int MaxCombinedTextureImageUnits = 192;
+            Int MaxVertexAttribs = 16;
+            Int MaxComputeShaderStorageBlocks = 8;
+            Int MaxCombinedShaderStorageBlocks = 32;
+            Int MaxComputeUniformBlocks = 12;
+            Int MaxComputeWorkGroupInvocations = 128;
+            Int MaxShaderStorageBufferBindings = 8;
+            Int MaxTextureBufferSize = 65536;
+            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;
+            Int MaxClipDistances = 8;
+            Int MaxViewports = 16;
+            Int MaxViewportWidth = 16384;
+            Int MaxViewportHeight = 16384;
+            Float ViewportBoundsRangeMin = 0.0f;
+            Float ViewportBoundsRangeMax = 0.0f;
+            Int ViewportSubpixelBits = 0;
+            Bool SupportsWideLines = false;
             SizeT MaxShaderStorageBlockSize = 128 * 1024 * 1024;
             Uint32 SubgroupSize = 0;
             Uint32 SubgroupSupportedStages = 0;
@@ -122,7 +296,8 @@ namespace MobileGL {
         enum class WindowBackend {
             Android,
             X11,
-            // TODO: X11, Wayland, Windows, macOS, etc.
+            MetalLayer,
+            // TODO: Wayland, Windows, etc.
             WindowBackendCount,
             Unknown = -1
         };
@@ -130,6 +305,8 @@ namespace MobileGL {
         struct WindowHandle {
             WindowBackend Backend = WindowBackend::Unknown;
             void* Handle = nullptr;
+            Uint32 Width = 0;
+            Uint32 Height = 0;
         };
 
         class BackendObject {
@@ -141,10 +318,15 @@ namespace MobileGL {
             virtual Bool InitWindowSurface() = 0;
 
             virtual Bool InitializeEGLDisplay(EGLDisplay dpy, EGLint* major, EGLint* minor);
-            virtual Bool CreateEGLWindowSurface(const WindowHandle& handle);
-            virtual Bool CreateEGLPbufferSurface(EGLint width, EGLint height);
+            virtual Bool CreateEGLWindowSurface(EGLSurface surface, const WindowHandle& handle);
+            virtual Bool ResizeEGLWindowSurface(EGLSurface surface, Uint32 width, Uint32 height);
+            virtual Bool CreateEGLPbufferSurface(EGLSurface surface, EGLint width, EGLint height);
             virtual Bool MakeEGLCurrent(EGLDisplay dpy, EGLSurface draw, EGLSurface read, EGLContext ctx);
             virtual Bool SwapEGLBuffers(EGLDisplay dpy, EGLSurface draw);
+            // Forwards the app-requested eglSwapInterval to the backend's native
+            // presentation path (no-op for backends without a SetSwapInterval hook).
+            virtual void SetEGLSwapInterval(Int interval);
+            virtual void ReleaseEGLSurface(EGLSurface surface);
             virtual void ReleaseEGLResources();
 
             void SetWindowHandle(const WindowHandle& handle);
@@ -153,6 +335,7 @@ namespace MobileGL {
             virtual String GetBackendAPIVersionString() const = 0;
             virtual const GlobalBackendFunctionsTable& GetBackendFunctions() const = 0;
             virtual const DynamicBackendParameters& GetDynamicParameters() const = 0;
+            const FormatCapabilityCache& GetFormatCapabilities() const;
             virtual BackendType GetBackendType() const = 0;
 
         protected:
@@ -162,17 +345,46 @@ namespace MobileGL {
                 Pbuffer
             };
 
+            struct EGLCurrentState {
+                EGLDisplay Display = EGL_NO_DISPLAY;
+                EGLSurface DrawSurface = EGL_NO_SURFACE;
+                EGLSurface ReadSurface = EGL_NO_SURFACE;
+                EGLContext Context = EGL_NO_CONTEXT;
+            };
+
+            struct EGLSurfaceState {
+                SurfaceKind Kind = SurfaceKind::None;
+                Bool DestroyPending = false;
+                WindowHandle Window;
+                EGLint Width = 1;
+                EGLint Height = 1;
+            };
+
             void ResetEGLRuntimeState();
+            Bool RegisterEGLWindowSurface(EGLSurface surface, const WindowHandle& handle);
+            Bool RegisterEGLPbufferSurface(EGLSurface surface, EGLint width, EGLint height);
+            const EGLSurfaceState* GetRegisteredEGLSurface(EGLSurface surface) const;
+            Bool ActivateEGLSurface(EGLSurface surface);
             virtual Bool InitPbufferSurface(EGLint width, EGLint height);
+            virtual void OnEGLSurfaceReleased(EGLSurface surface);
+            FormatCapabilityCache& MutableFormatCapabilities();
 
             mutable std::recursive_mutex m_eglStateMutex;
+            FormatCapabilityCache m_formatCapabilities;
             WindowHandle m_windowHandle;
             EGLDisplay m_eglDisplay = EGL_NO_DISPLAY;
+            EGLSurface m_eglSurface = EGL_NO_SURFACE;
             Bool m_eglDisplayInitialized = false;
             Bool m_eglSurfaceInitialized = false;
             Bool m_backendCapabilitiesInitialized = false;
             SurfaceKind m_eglSurfaceKind = SurfaceKind::None;
-            UnorderedMap<std::thread::id, Bool> m_eglCurrentThreads;
+            UnorderedMap<std::thread::id, EGLCurrentState> m_eglCurrentThreads;
+            UnorderedMap<EGLSurface, EGLSurfaceState> m_eglSurfaces;
+
+        private:
+            Bool IsEGLSurfaceCurrent(EGLSurface surface) const;
+            void DestroyPendingEGLSurfaceIfUnused(EGLSurface surface);
+            void ReleaseEGLCurrentThread(const std::thread::id& threadKey);
         };
     } // namespace MG_Backend
 } // namespace MobileGL

MobileGL/MG_Backend/DirectGLES/BackendObject_DirectGLES.h

@@ -12,6 +12,12 @@
 #include <MG_Util/BackendLoaders/OpenGL/Loader.h>
 
 namespace MobileGL::MG_Backend::DirectGLES {
+    // Populates the same format-capability cache used by backend startup. The caller
+    // must keep the supplied GLES context current for the duration of this call.
+    void PopulateFormatCapabilities(const MG_External::GLESFunctionsTable& gl,
+                                    const MG_External::GLESCapabilities& capabilities,
+                                    FormatCapabilityCache& cache);
+
     class BackendObject_DirectGLES : public BackendObject {
     public:
         ~BackendObject_DirectGLES() override;
@@ -20,9 +26,11 @@ namespace MobileGL::MG_Backend::DirectGLES {
         Bool InitCapabilities() override;
         Bool InitWindowSurface() override;
         Bool InitializeEGLDisplay(EGLDisplay dpy, EGLint* major, EGLint* minor) override;
-        Bool CreateEGLWindowSurface(const WindowHandle& handle) override;
+        Bool CreateEGLWindowSurface(EGLSurface surface, const WindowHandle& handle) override;
+        Bool CreateEGLPbufferSurface(EGLSurface surface, EGLint width, EGLint height) override;
         Bool MakeEGLCurrent(EGLDisplay dpy, EGLSurface draw, EGLSurface read, EGLContext ctx) override;
         Bool SwapEGLBuffers(EGLDisplay dpy, EGLSurface draw) override;
+        void ReleaseEGLSurface(EGLSurface surface) override;
         void ReleaseEGLResources() override;
 
         const RendererInfo& GetRendererInfo() const override;
@@ -33,10 +41,12 @@ 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();
         Bool InitPbufferSurface(EGLint width, EGLint height) override;
+        void OnEGLSurfaceReleased(EGLSurface surface) override;
 
         Bool m_initialized = false;
         MG_External::EGLFunctionsTable m_EGLFunctions;
@@ -44,4 +54,25 @@ namespace MobileGL::MG_Backend::DirectGLES {
         MG_External::GLESCapabilities m_GLESCapabilities;
         DynamicBackendParameters m_dynamicParameters;
     };
+
+    // Single-source-of-truth helpers shared with the driver POST
+    // (MG_Util/SelfTest/DriverPost.cpp), so the identity strings and extension list
+    // MobileGL reports to applications on this backend cannot drift from what the
+    // POST screen shows.
+
+    // Static identity of the Espryt renderer (renderer/backend names, target GL/GLSL
+    // versions, ExtraVendor). The Extensions vector inside is live backend state that
+    // is reconciled after capability init; callers that need the advertised list for
+    // a known capability set must use BuildAdvertisedExtensions instead.
+    const RendererInfo& GetRendererIdentity();
+
+    // The full OpenGL extension list Espryt advertises (glGetString(GL_EXTENSIONS))
+    // 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
+    // inside the application-visible GL_RENDERER string).
+    String FormatBackendAPIVersionString(const String& glesRendererString, Int glesMajor, Int glesMinor);
 } // namespace MobileGL::MG_Backend::DirectGLES

MobileGL/MG_Backend/DirectGLES/DirectGLES.h

@@ -8,6 +8,7 @@
 
 #pragma once
 #include <Includes.h>
+#include <MG_Backend/BackendObject.h>
 #include <MG_State/GLState/FramebufferState/FramebufferObject.h>
 #include <MG_State/GLState/TextureState/TextureState.h>
 #include <MG_State/GLState/SamplerState/SamplerObject.h>
@@ -18,6 +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);
@@ -26,6 +31,7 @@ namespace MobileGL::MG_Backend::DirectGLES {
     void DrawElements(GLenum mode, GLsizei count, GLenum type, const void* indices);
     void DrawArrays(GLenum mode, GLint first, GLsizei count);
     void DrawElementsBaseVertex(GLenum mode, GLsizei count, GLenum type, const GLvoid* indices, GLint basevertex);
+    void MultiDrawArrays(GLenum mode, const GLint* first, const GLsizei* count, GLsizei drawcount);
     void MultiDrawElements(GLenum mode, const GLsizei* count, GLenum type, const GLvoid* const* indices,
                            GLsizei drawcount);
     void MultiDrawElementsBaseVertex(GLenum mode, const GLsizei* count, GLenum type, const GLvoid* const* indices,
@@ -64,6 +70,11 @@ namespace MobileGL::MG_Backend::DirectGLES {
                         GLsizei height, GLint border);
     void CopyTexSubImage2D(GLenum target, GLint level, GLint xoffset, GLint yoffset, GLint x, GLint y, GLsizei width,
                            GLsizei height);
+    void CopyImageSubData(const SharedPtr<MG_State::GLState::ITextureObject>& srcTexture,
+                          GLenum srcTarget, GLint srcLevel, GLint srcX, GLint srcY, GLint srcZ,
+                          const SharedPtr<MG_State::GLState::ITextureObject>& dstTexture,
+                          GLenum dstTarget, GLint dstLevel, GLint dstX, GLint dstY, GLint dstZ,
+                          GLsizei srcWidth, GLsizei srcHeight, GLsizei srcDepth);
     void GenerateMipmap(GLenum target);
     const GLubyte* GetString(GLenum name);
     void ReadPixels(GLint x, GLint y, GLsizei width, GLsizei height, GLenum format, GLenum type, void* pixels);
@@ -88,7 +99,56 @@ namespace MobileGL::MG_Backend::DirectGLES {
     void ShaderStorageBlockBinding(GLuint program, GLuint storageBlockIndex, GLuint storageBlockBinding);
     Bool InitWindowSurface(NativeWindowType window);
     Bool InitPbufferSurface(EGLint width, EGLint height);
+    Bool MakeCurrent();
+    Bool ReleaseCurrent();
+    // True when the backend ES context is current on the calling thread, i.e.
+    // immediate buffer ops may issue GL calls right now.
+    Bool IsBackendContextCurrentOnThisThread();
+    // GL fence sync objects, backed by native ES fences. FenceSync returns null
+    // (the frontend then falls back to an always-signaled sync) when the calling
+    // thread does not own the ES context. Waits/queries degrade to "signaled" in
+    // the same situation, and handles created under a since-destroyed ES context
+    // are always treated as signaled.
+    BackendSyncHandle FenceSync();
+    GLenum ClientWaitSync(BackendSyncHandle sync, GLbitfield flags, GLuint64 timeout);
+    void WaitSync(BackendSyncHandle sync, GLbitfield flags, GLuint64 timeout);
+    void DeleteSync(BackendSyncHandle sync);
+    Bool GetSyncStatus(BackendSyncHandle sync);
+    // True when GL_EXT_disjoint_timer_query and every entry point the timer
+    // hooks below need are present. Also gates the E_GL_ARB_timer_query
+    // advertisement in BackendObject_DirectGLES::InitCapabilities, and is
+    // registered as the GLFunctionsTable::IsTimerQuerySupported hook: a pure
+    // capability read needs no current ES context, and it stays false until
+    // the ES capabilities have been filled in.
+    Bool AreTimerQueriesSupported();
+    // GL timer-query objects, backed by GL_EXT_disjoint_timer_query. The
+    // creators return null (the frontend then falls back to an immediately
+    // available zero result) when the calling thread does not own the ES
+    // context or the extension/entry points are missing, and handles created
+    // under a since-destroyed ES context are always treated as complete with
+    // a zero result (mirrors the fence-sync handles above).
+    BackendQueryHandle BeginTimeElapsedQuery();
+    void EndTimeElapsedQuery(BackendQueryHandle query);
+    BackendQueryHandle QueryCounterTimestamp();
+    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
+    // and release the handle). Returns false only when the calling thread
+    // does not own the ES context, so the value is genuinely unobtainable
+    // right now; the handle stays alive and readable later.
+    Bool GetQueryResult64(BackendQueryHandle query, Bool wait, Uint64* outNanoseconds);
+    void DeleteBackendQuery(BackendQueryHandle query);
+    Int64 GetGpuTimestampNs();
     void Present();
+    // Frame-completion watermarks for the buffer-storage pool: CurrentFrameSerial()
+    // is bumped once per Present(); CompletedFrameSerial() is the newest frame whose
+    // GPU work has provably finished (advanced by polling a one-fence-per-frame ring).
+    // A buffer retired during frame N is safe to recycle once CompletedFrameSerial() >= N.
+    Uint64 CurrentFrameSerial();
+    Uint64 CompletedFrameSerial();
+    // Applies (or defers until the window surface exists) the app-requested
+    // eglSwapInterval on the native EGL surface.
+    void SetSwapInterval(Int interval);
     void SetEGLFuncsTable(const MG_External::EGLFunctionsTable& eglFuncs);
     void SetGLESFuncsTable(const MG_External::GLESFunctionsTable& glesFuncs);
     void SetGLESCapabilities(const MG_External::GLESCapabilities& capabilities);

MobileGL/MG_Backend/DirectGLES/Managers.h

@@ -8,14 +8,18 @@
 
 #pragma once
 #include <Includes.h>
+#include <atomic>
+#include <mutex>
 #include "DirectGLES.h"
 #include "MG_State/GLState/SamplerState/SamplerObject.h"
 #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);
 
     template <typename StateObject, typename BackendObject>
     class StateBackendObjectRegistry {
@@ -52,6 +56,8 @@ namespace MobileGL::MG_Backend::DirectGLES {
             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(); }
 
@@ -113,26 +119,114 @@ namespace MobileGL::MG_Backend::DirectGLES {
 
     namespace BufferImpl {
         const GLenum TempBufferTarget = GL_ARRAY_BUFFER;
-        class BackendBufferObject {
+
+        // 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.
+        class GLESBufferResource : public MG_State::GLState::BackendBufferResource {
         public:
-            BackendBufferObject();
-            void SyncToBackend(const SharedPtr<MG_State::GLState::BufferObject>& stateBufferObject);
-            Uint GetBackendBufferId() const { return m_backendBufferId; }
-            void Bind(GLenum target = TempBufferTarget);
+            ~GLESBufferResource() override = default;
 
-        private:
-            void SyncToBackend_glBufferData(const SharedPtr<MG_State::GLState::BufferObject>& stateBufferObject);
-            void SyncToBackend_glBufferSubData(const SharedPtr<MG_State::GLState::BufferObject>& stateBufferObject);
-            void SyncToBackend_glMapBufferRange(const SharedPtr<MG_State::GLState::BufferObject>& stateBufferObject,
-                                                Bool invalidate = true, Bool unsynchronized = true);
-
-            Uint m_backendBufferId = 0;
-            SizeT m_prevBufferSize = 0;
-            Bool m_isInitialized = false;
+            Uint id = 0;
+            SizeT storageSize = 0;
+            Bool storageInitialized = false;
+            // ES context generation this resource's id belongs to; ids from a
+            // destroyed context are invalid and must not be deleted or reused.
+            Uint contextGeneration = 0;
+            // Frontend change serial the backend storage reflects. When immediate
+            // ops cannot run (ops unregistered, no current context), this lags and
+            // EnsureBufferResource falls back to a full re-upload. Atomic: read on
+            // the context-owning thread while ops on other threads may update it.
+            std::atomic<Uint64> syncedChangeSerial{0};
+            // Ops that arrived while no ES context was current on the calling thread
+            // (or before storage existed); replayed by EnsureBufferResource. The ES
+            // context migrates between app threads, so deferring ops can race with
+            // the owning thread replaying them: guard both fields with pendingMutex.
+            Bool pendingRespecify = false;
+            VecRange1D pendingRanges;
+            std::mutex pendingMutex;
+            // 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
+            // sync is a no-op and no per-draw glBufferSubData is issued. Cleared on ES
+            // context loss.
+            Bool persistentMapped = false;
+            void* persistentPtr = nullptr;
         };
 
-        extern BackendBufferObject* g_boundVertexBufferObject;
-        extern StateBackendObjectRegistry<MG_State::GLState::BufferObject, BackendBufferObject> g_backendBufferObjects;
+        // Registered as the frontend's BufferBackendOps at backend init and on
+        // every MakeCurrent (the ES context can be destroyed and recreated, e.g.
+        // by the trace replayer's probe context).
+        void RegisterBufferBackendOps();
+        void UnregisterBufferBackendOps();
+        // The ES context died: unregister ops, invalidate all outstanding GL ids
+        // (they belonged to the dead context) and drop deferred deletes.
+        void OnBackendContextDestroyed();
+
+        // Get-or-create the backend resource and bring its storage up to date
+        // (creates the GL buffer, replays pending ops, pushes persistent-mapped
+        // ranges). Requires the ES context to be current. Returns nullptr only
+        // for null input.
+        GLESBufferResource* EnsureBufferResource(const SharedPtr<MG_State::GLState::BufferObject>& bufferObject);
+        // Existing resource or nullptr; performs no GL calls.
+        GLESBufferResource* GetBufferResource(MG_State::GLState::BufferObject* bufferObject);
+
+        // Deletes GL buffers whose owning frontend objects died (possibly on a
+        // thread without a current ES context). Called from draw-time sync.
+        void ProcessDeferredBufferReleases();
+
+        // glBindBuffer with a redundant-bind cache for GL_ARRAY_BUFFER.
+        void BindBufferId(GLenum target, Uint id);
+        void InvalidateArrayBufferBindingCache();
+        // 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/
+        // sampler caches already do. Invalidated on MakeCurrent (context may reset).
+        void BindBufferBaseCached(GLenum glTarget, Uint index, Uint id);
+        void BindBufferRangeCached(GLenum glTarget, Uint index, Uint id, GLintptr offset, GLsizeiptr size);
+        void InvalidateIndexedBufferBindingCache();
+        // Buffer-storage pool maintenance. TrimBufferPool evicts over-budget entries
+        // (called once per frame from Present); ClearBufferPool drops all pooled ids
+        // without glDeleteBuffers (called when the ES context is going away).
+        void TrimBufferPool();
+        void ClearBufferPool();
+
+        // --- Global-UBO ring ------------------------------------------------------
+        // One persistently+coherently mapped buffer (EXT_buffer_storage) shared by
+        // every program's lowered default-uniform block. Each content change is
+        // bump-allocated into a fresh slot and bound with glBindBufferRange, so the
+        // CPU never rewrites bytes the GPU may still be reading — the per-draw
+        // glBufferSubData into one static UBO forced Adreno to resolve that
+        // write-after-read hazard on every uniform-dirtying draw (MC dirties
+        // uniforms every draw). Reclamation rides the Present() frame-fence
+        // watermark; no ring bytes are recycled before their frame's GPU work
+        // completed.
+        //
+        // A program's cached slot, reusable within one frame while the frontend UBO
+        // content version is unchanged. Cross-frame reuse is intentionally not
+        // attempted: later same-frame allocations may recycle bytes of completed
+        // frames, so re-referencing them would need per-bind pinning — rewriting
+        // GetUBOSize() bytes once per program per frame is far cheaper.
+        struct UboRingAllocation {
+            Uint32 contentVersion = ~0u; // frontend UBO content version held at `offset`
+            Uint32 ringGeneration = 0;   // ring identity the slot lives in (0 = never valid)
+            Uint64 frameSerial = ~Uint64{0}; // frame the slot was written in
+            SizeT offset = 0;
+        };
+        // False when the feature is disabled, EXT_buffer_storage / fences are
+        // missing, the ES context is not current, or ring creation already failed
+        // under this context (callers then take the legacy glBufferSubData path).
+        Bool UboRingAvailable();
+        // Bump-allocate `size` bytes aligned to GL_UNIFORM_BUFFER_OFFSET_ALIGNMENT.
+        // Grows the ring (new GL store, generation bump) when the in-flight span
+        // would be overrun. Returns false when storage (re)creation fails.
+        Bool UboRingAllocate(SizeT size, SizeT& outOffset);
+        void* UboRingMappedPtr();
+        Uint UboRingBufferId();
+        Uint32 UboRingGeneration();
+        // Present()-time upkeep: records the frame's high-water mark for reclamation
+        // and deletes grown-away ring stores once the GPU is done with them.
+        void UboRingOnPresent();
     } // namespace BufferImpl
 
     namespace VertexArrayImpl {
@@ -161,11 +255,53 @@ namespace MobileGL::MG_Backend::DirectGLES {
 
     namespace TextureImpl {
         inline Bool IsSupportedTextureTarget(TextureTarget target) {
-            if (target == TextureTarget::Texture1D || target == TextureTarget::TextureRectangle ||
-                target == TextureTarget::Texture2DMultisampleArray || target == TextureTarget::Texture1DArray ||
-                target == TextureTarget::Texture2DMultisample || target == TextureTarget::Texture2DArray)
-                return false;
-            return true;
+            // Rectangle textures need non-normalized sampling ES cannot express; everything else is
+            // either native or emulated (1D -> 2D with height 1, 1D array -> 2D array, see
+            // MapToBackendTextureTarget). SPIRV-Cross already emits the matching ESSL samplers and
+            // coordinate padding for 1D/1D-array shaders.
+            return target != TextureTarget::TextureRectangle;
+        }
+
+        // ES has no 1D targets: 1D textures are stored as 2D (height 1) and 1D arrays as 2D arrays
+        // (height 1, layers in depth). Must match SPIRV-Cross's ES 1D-as-2D shader emulation.
+        inline TextureTarget MapToBackendTextureTarget(TextureTarget target) {
+            switch (target) {
+            case TextureTarget::Texture1D:
+                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:
+                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;
         }
 
         inline Bool SupportsWrapR(TextureTarget target) {
@@ -179,11 +315,14 @@ namespace MobileGL::MG_Backend::DirectGLES {
             SizeT depth = 0;
             SizeT mipmapLevels = 0;
             Uint bufferExternalIndex = 0;
+            Int samples = 0;
+            Bool fixedSampleLocations = true;
 
             bool operator==(const StateTextureBasicInfo& other) const {
                 return internalFormat == other.internalFormat && width == other.width && height == other.height &&
                        depth == other.depth && mipmapLevels == other.mipmapLevels &&
-                       bufferExternalIndex == other.bufferExternalIndex;
+                       bufferExternalIndex == other.bufferExternalIndex && samples == other.samples &&
+                       fixedSampleLocations == other.fixedSampleLocations;
             }
 
             bool operator!=(const StateTextureBasicInfo& other) const { return !(*this == other); }
@@ -196,12 +335,17 @@ namespace MobileGL::MG_Backend::DirectGLES {
             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);
+            void RequireImageBindableStorage();
             void Bind(GLenum target, Uint unit = TempTextureUnit);
             Uint GetBackendTextureId() const;
 
         private:
+            void RecreateBackendTexture();
+
             Uint m_backendTextureId = 0;
             Bool m_isInitialized = false;
+            Bool m_imageBindableStorageRequired = false;
+            Bool m_backendStorageImmutable = false;
             StateTextureBasicInfo m_prevTextureInfo;
             SamplerParameters m_cacheSamplerParameters;
             UintVec2 m_cacheLodRange = {0, 1000};
@@ -216,6 +360,9 @@ namespace MobileGL::MG_Backend::DirectGLES {
         void UnbindTexture(Uint unit, GLenum target);
         extern StateBackendObjectRegistry<MG_State::GLState::ITextureObject, BackendTextureObject>
             g_backendTextureObjects;
+        SharedPtr<BackendTextureObject>& SyncTextureObjectToBackend(
+            const SharedPtr<MG_State::GLState::ITextureObject>& textureObject,
+            Bool imageBindableStorageRequired = false);
         extern Array<Array<BackendTextureObject*, (SizeT)TextureTarget::TextureTargetCount>,
                      MG_State::GLState::TextureState::MAX_TEXTURE_IMAGE_UNITS>
             g_boundTexturesCache;
@@ -261,26 +408,109 @@ namespace MobileGL::MG_Backend::DirectGLES {
         extern StateBackendObjectRegistry<MG_State::GLState::FramebufferObject, BackendFramebufferObject>
             g_backendFramebufferObjects;
         extern Array<Uint16, SizeT(FramebufferTarget::FramebufferTargetCount)> g_fboBindVersions;
+        // 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;
+        extern Array<MG_State::GLState::FramebufferObject*, SizeT(FramebufferTarget::FramebufferTargetCount)>
+            g_fboSyncedObjects;
     } // namespace FramebufferImpl
 
+    // 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.
+    inline Bool IsImageUniformType(GLenum type) {
+        switch (type) {
+        case 0x904D: /*GL_IMAGE_2D*/
+        case 0x904E: /*GL_IMAGE_3D*/
+        case 0x9050: /*GL_IMAGE_CUBE*/
+        case 0x9051: /*GL_IMAGE_BUFFER*/
+        case 0x9053: /*GL_IMAGE_2D_ARRAY*/
+        case 0x9058: /*GL_INT_IMAGE_2D*/
+        case 0x9059: /*GL_INT_IMAGE_3D*/
+        case 0x905B: /*GL_INT_IMAGE_CUBE*/
+        case 0x905C: /*GL_INT_IMAGE_BUFFER*/
+        case 0x905E: /*GL_INT_IMAGE_2D_ARRAY*/
+        case 0x9063: /*GL_UNSIGNED_INT_IMAGE_2D*/
+        case 0x9064: /*GL_UNSIGNED_INT_IMAGE_3D*/
+        case 0x9066: /*GL_UNSIGNED_INT_IMAGE_CUBE*/
+        case 0x9067: /*GL_UNSIGNED_INT_IMAGE_BUFFER*/
+        case 0x9069: /*GL_UNSIGNED_INT_IMAGE_2D_ARRAY*/
+            return true;
+        default:
+            return false;
+        }
+    }
+
     namespace PrgramImpl {
         class BackendProgramObjectImpl {
         public:
+            // Per-link cache of a sampler-style uniform's backend location: built once in
+            // SyncToBackend so draws stop issuing glGetUniformLocation string queries.
+            // lastAssignedUnit mirrors the program-state value set through glUniform1i
+            // (program state persists across binds, so caching per program is exact).
+            struct SamplerUniformBinding {
+                Uint frontendLocation = 0;
+                Int backendLocation = -1;
+                GLenum uniformType = 0;
+                Int lastAssignedUnit = -1;
+            };
+
             BackendProgramObjectImpl();
             ~BackendProgramObjectImpl();
             void SyncToBackend(const SharedPtr<MG_State::GLState::ProgramObject>& stateProgramObject);
             void Use() const;
             void SetBaseInstance(Uint32 baseInstance) const;
+            void SetBaseInstanceWordIndex(Int32 wordIndex) const;
+            void SetDrawID(Uint32 drawId) const;
+            Int GetIndirectParamsBinding() const { return m_indirectParamsBinding; }
             Uint GetBackendProgramId() const { return m_backendProgramId; }
             Uint GetBackendGlobalUBOId() const { return m_backendGlobalUBOId; }
+            Uint32 GetSnormFallbackClampOutputMask() const { return m_snormFallbackClampOutputMask; }
+            Uint32 GetUnormFallbackClampOutputMask() const { return m_unormFallbackClampOutputMask; }
+
+            Bool HasGlobalUboBlock() const { return m_globalUboBackendBlockIndex >= 0; }
+            const Vector<Int>& GetUniformBlockBackendIndices() const { return m_uniformBlockBackendIndices; }
+            Vector<SamplerUniformBinding>& GetSamplerUniformBindings() { return m_samplerUniformBindings; }
+            Uint32 GetLastUploadedGlobalUboVersion() const { return m_lastUploadedGlobalUboVersion; }
+            void SetLastUploadedGlobalUboVersion(Uint32 version) { m_lastUploadedGlobalUboVersion = version; }
+            // Backend-reported GL_UNIFORM_BLOCK_DATA_SIZE of the global block; ring
+            // bindings must span at least this much (may exceed the frontend's
+            // reflected size when the transpiled block pads differently).
+            Int GetGlobalUboBackendBlockSize() const { return m_globalUboBackendBlockSize; }
+            BufferImpl::UboRingAllocation& GetGlobalUboRingAllocation() { return m_globalUboRingAllocation; }
+            // 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; }
 
         private:
+            void CacheResourceLocations(const SharedPtr<MG_State::GLState::ProgramObject>& stateProgramObject);
+
             Uint m_backendProgramId = 0;
             Uint m_backendGlobalUBOId = 0;
             Int m_baseInstanceUniformLocation = -1;
+            Int m_drawIdUniformLocation = -1;
+            Int m_baseInstanceWordIndexUniformLocation = -1;
+            Int m_indirectParamsBinding = -1;
+            Uint32 m_snormFallbackClampOutputMask = 0;
+            Uint32 m_unormFallbackClampOutputMask = 0;
             Bool m_isInitialized = false;
+
+            Int m_globalUboBackendBlockIndex = -1;
+            Int m_globalUboBackendBlockSize = 0;
+            Vector<Int> m_uniformBlockBackendIndices; // frontend block index -> backend index (-1 = absent)
+            Vector<SamplerUniformBinding> m_samplerUniformBindings;
+            Uint32 m_lastUploadedGlobalUboVersion = ~0u;
+            BufferImpl::UboRingAllocation m_globalUboRingAllocation;
+            Uint32 m_syncedLinkVersion = ~0u;
         };
 
+        extern Uint32 g_snormFallbackClampOutputMask;
+        extern Uint32 g_unormFallbackClampOutputMask;
+        // 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;
     } // namespace PrgramImpl
@@ -322,6 +552,7 @@ namespace MobileGL::MG_Backend::DirectGLES {
             TextureInternalFormat m_cacheInternalFormat = TextureInternalFormat::Unknown;
             Int m_cacheWidth = 0;
             Int m_cacheHeight = 0;
+            Int m_cacheSamples = 0;
         };
 
         extern StateBackendObjectRegistry<MG_State::GLState::RenderbufferObject, BackendRenderbufferObject>

MobileGL/MG_Backend/DirectGLES/Utils.cpp

@@ -9,6 +9,7 @@
 #include "DirectGLES.h"
 #include "Utils.h"
 #include "Managers.h"
+#include "MG_Backend/BackendObjects.h"
 #include "MG_Util/Converters/GLToMG/FramebufferEnumConverter.h"
 #include "MG_Util/Texture/TextureFormatProcessor.h"
 
@@ -17,19 +18,135 @@
 #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>
 
 namespace MobileGL::MG_Backend::DirectGLES {
+    namespace {
+        Flags<PixelFormatNormalizeOptionBit> GetForcedPixelFormatNormalizeOptions() {
+            Flags<PixelFormatNormalizeOptionBit> options;
+            if (g_GLESCapabilities.IsAngleRenderer) {
+                options |= PixelFormatNormalizeOptionBit::NoRgb16;
+                options |= PixelFormatNormalizeOptionBit::NoSnorm16;
+                options |= PixelFormatNormalizeOptionBit::NoSnorm8;
+            }
+            return options;
+        }
+
+        Flags<PixelFormatNormalizeOptionBit> GetDriverPixelFormatNormalizeOptions() {
+            Flags<PixelFormatNormalizeOptionBit> options = PixelFormatNormalizeOptionBit::NoDepthComponent32;
+            options |= PixelFormatNormalizeOptionBit::NoRGBA8Snorm;
+            options |= PixelFormatNormalizeOptionBit::NoRGB16Snorm;
+            if (!g_GLESCapabilities.SupportsNorm16Texture) {
+                options |= PixelFormatNormalizeOptionBit::NoNorm16;
+            }
+            return options;
+        }
+
+        Flags<PixelFormatNormalizeOptionBit> GetRuntimeFallbackNormalizeOptions(GLenum requestedInternalFormat) {
+            using namespace MG_Util::TextureFormatProcessor;
+            const Flags<PixelFormatNormalizeOptionBit> forcedOptions =
+                GetApplicablePixelFormatNormalizeOptions(requestedInternalFormat, GetForcedPixelFormatNormalizeOptions());
+            if (forcedOptions) {
+                return forcedOptions;
+            }
+            return GetApplicablePixelFormatNormalizeOptions(requestedInternalFormat,
+                                                            GetDriverPixelFormatNormalizeOptions());
+        }
+
+        Bool HasCachedFormatCapability(TextureInternalFormat internalFormat,
+                                       SizeT targetIndex,
+                                       Bool caveat,
+                                       FormatCapability capability) {
+            if (!pActiveBackendObject || targetIndex >= kFormatCapabilityTargetCount) {
+                return false;
+            }
+            const SizeT formatIndex = static_cast<SizeT>(internalFormat);
+            if (formatIndex >= kFormatCapabilityFormatCount) {
+                return false;
+            }
+
+            const FormatCapabilityCache& cache = pActiveBackendObject->GetFormatCapabilities();
+            const FormatCapabilityFlags caps =
+                caveat ? cache.CaveatCaps[targetIndex][formatIndex] : cache.FullCaps[targetIndex][formatIndex];
+            return HasFormatCapability(caps, capability);
+        }
+
+        Bool HasAnyCachedFormatCapability(TextureInternalFormat internalFormat,
+                                          Bool caveat,
+                                          FormatCapability capability) {
+            for (SizeT targetIndex = 0; targetIndex < kFormatCapabilityTargetCount; ++targetIndex) {
+                if (HasCachedFormatCapability(internalFormat, targetIndex, caveat, capability)) {
+                    return true;
+                }
+            }
+            return false;
+        }
+
+        Bool ShouldUseCaveatFormat(TextureInternalFormat internalFormat, SizeT targetIndex) {
+            if (targetIndex < kFormatCapabilityTargetCount) {
+                const Bool fullCreatable =
+                    HasCachedFormatCapability(internalFormat, targetIndex, false, FormatCapability::Creatable);
+                const Bool caveatCreatable =
+                    HasCachedFormatCapability(internalFormat, targetIndex, true, FormatCapability::Creatable);
+                const Bool fullRenderable =
+                    HasCachedFormatCapability(internalFormat, targetIndex, false, FormatCapability::FramebufferRenderable);
+                const Bool caveatRenderable =
+                    HasCachedFormatCapability(internalFormat, targetIndex, true, FormatCapability::FramebufferRenderable);
+                return (!fullCreatable && caveatCreatable) || (!fullRenderable && caveatRenderable);
+            }
+
+            if (HasAnyCachedFormatCapability(internalFormat, false, FormatCapability::Creatable)) {
+                return false;
+            }
+            return HasAnyCachedFormatCapability(internalFormat, true, FormatCapability::Creatable);
+        }
+
+        void GenerateFormatInfo(TextureInternalFormat internalFormat,
+                                SizeT targetIndex,
+                                GLenum* outInternalFormat,
+                                GLenum* outFormat,
+                                GLenum* outType) {
+            using namespace MobileGL::MG_Util::TextureFormatProcessor;
+            const GLenum requestedInternalFormat = MG_Util::ConvertTextureInternalFormatToGLEnum(internalFormat);
+            Flags<PixelFormatNormalizeOptionBit> options;
+            if (!pActiveBackendObject || ShouldUseCaveatFormat(internalFormat, targetIndex)) {
+                options = GetRuntimeFallbackNormalizeOptions(requestedInternalFormat);
+            }
+            NormalizePixelFormat(requestedInternalFormat, options, outInternalFormat, outFormat, outType);
+        }
+    } // namespace
+
     namespace TextureImpl {
         void GenerateTextureFormatInfo(TextureInternalFormat internalFormat, GLenum* outInternalFormat,
-                                       GLenum* outFormat, GLenum* outType) {
+                                       GLenum* outFormat, GLenum* outType, TextureTarget target) {
 #ifdef TRACY_ENABLE
             ZoneScopedC(TRACY_ZONECOLOR_BACKEND);
 #endif
-            using namespace MobileGL::MG_Util::TextureFormatProcessor;
-            auto options = (g_GLESCapabilities.SupportsNorm16Texture) ? PixelFormatNormalizeOptionBit::None
-                                                                      : PixelFormatNormalizeOptionBit::NoNorm16;
-            NormalizePixelFormat(MG_Util::ConvertTextureInternalFormatToGLEnum(internalFormat), options,
-                                 outInternalFormat, outFormat, outType);
+            const SizeT targetIndex =
+                target == TextureTarget::Unknown ? kFormatCapabilityTargetCount : GetFormatCapabilityTargetIndex(target);
+            GenerateFormatInfo(internalFormat, targetIndex, outInternalFormat, outFormat, outType);
+        }
+
+        void GenerateRenderbufferFormatInfo(TextureInternalFormat internalFormat, GLenum* outInternalFormat,
+                                            GLenum* outFormat, GLenum* outType) {
+#ifdef TRACY_ENABLE
+            ZoneScopedC(TRACY_ZONECOLOR_BACKEND);
+#endif
+            GenerateFormatInfo(internalFormat, GetRenderbufferFormatCapabilityTargetIndex(), outInternalFormat,
+                               outFormat, outType);
+        }
+
+        Bool ShouldUseCaveatTextureFormat(TextureInternalFormat internalFormat, TextureTarget target) {
+            const SizeT targetIndex =
+                target == TextureTarget::Unknown ? kFormatCapabilityTargetCount : GetFormatCapabilityTargetIndex(target);
+            return ShouldUseCaveatFormat(internalFormat, targetIndex);
+        }
+
+        Bool ShouldUseCaveatRenderbufferFormat(TextureInternalFormat internalFormat) {
+            return ShouldUseCaveatFormat(internalFormat, GetRenderbufferFormatCapabilityTargetIndex());
         }
     } // namespace TextureImpl
     namespace PrgramImpl {
@@ -101,6 +218,64 @@ namespace MobileGL::MG_Backend::DirectGLES {
             return result;
         }
 
+        String ClampNormFallbackOutputs(String glslCode, GLenum shaderType, Uint32 snormOutputMask,
+                                        Uint32 unormOutputMask) {
+#ifdef TRACY_ENABLE
+            ZoneScopedC(TRACY_ZONECOLOR_BACKEND);
+#endif
+            const Uint32 outputMask = snormOutputMask | unormOutputMask;
+            if (shaderType != GL_FRAGMENT_SHADER || outputMask == 0) {
+                return glslCode;
+            }
+
+            const std::regex outputPattern(
+                R"(layout\s*\(\s*location\s*=\s*([0-9]+)\s*\)\s*out\s+(?:(?:lowp|mediump|highp)\s+)?vec4\s+([A-Za-z_][A-Za-z0-9_]*)\s*;)");
+            std::sregex_iterator outputIt(glslCode.begin(), glslCode.end(), outputPattern);
+            std::sregex_iterator outputEnd;
+            struct OutputClamp {
+                String Name;
+                Bool Signed;
+            };
+            Vector<OutputClamp> outputClamps;
+            for (; outputIt != outputEnd; ++outputIt) {
+                const Uint location = static_cast<Uint>(std::stoul((*outputIt)[1].str()));
+                if (location < 32 && (outputMask & (1u << location))) {
+                    outputClamps.push_back({(*outputIt)[2].str(), static_cast<Bool>(snormOutputMask & (1u << location))});
+                }
+            }
+            if (outputClamps.empty()) {
+                return glslCode;
+            }
+
+            const std::regex mainPattern(R"(void\s+main\s*\([^)]*\)\s*\{)");
+            std::smatch mainMatch;
+            if (!std::regex_search(glslCode, mainMatch, mainPattern)) {
+                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) {
+                        String clampLine;
+                        for (const OutputClamp& outputClamp : outputClamps) {
+                            const String minValue = outputClamp.Signed ? "-1.0" : "0.0";
+                            clampLine += "\n    " + outputClamp.Name + " = clamp(" + outputClamp.Name +
+                                         ", vec4(" + minValue + "), vec4(1.0));";
+                        }
+                        clampLine += "\n";
+                        glslCode.insert(pos, clampLine);
+                        return glslCode;
+                    }
+                }
+            }
+            return glslCode;
+        }
+
         String ForceFlatIntegerVaryings(const String& glslCode, GLenum shaderType) {
 #ifdef TRACY_ENABLE
             ZoneScopedC(TRACY_ZONECOLOR_BACKEND);
@@ -136,10 +311,35 @@ namespace MobileGL::MG_Backend::DirectGLES {
 #ifdef TRACY_ENABLE
             ZoneScopedC(TRACY_ZONECOLOR_BACKEND);
 #endif
+            // Sampler and uniform-block bindings are re-established at draw time through the
+            // API, so their layout qualifiers are stripped (they may exceed ES limits). SSBO
+            // blocks and image uniforms are different: ES has no glShaderStorageBlockBinding,
+            // and image units cannot be set with glUniform1i, so for those declarations the
+            // binding qualifier is the only binding mechanism and must be preserved.
             static std::regex bindingRegex(R"(layout\s*\(\s*binding\s*=\s*\d+\s*\)\s*)");
-            String result = std::regex_replace(glslCode, bindingRegex, "");
             static std::regex bindingRegex2(R"(layout\s*\(\s*binding\s*=\s*\d+\s*,)");
-            result = std::regex_replace(result, bindingRegex2, "layout(");
+            static std::regex keepBindingRegex(R"(\b(buffer|[iu]?image[A-Za-z0-9]*)\b)");
+
+            String result;
+            result.reserve(glslCode.size());
+            SizeT lineStart = 0;
+            while (lineStart <= glslCode.size()) {
+                SizeT lineEnd = glslCode.find('\n', lineStart);
+                const Bool lastLine = lineEnd == String::npos;
+                String line = glslCode.substr(lineStart, lastLine ? String::npos : lineEnd - lineStart);
+
+                if (!std::regex_search(line, keepBindingRegex)) {
+                    line = std::regex_replace(line, bindingRegex, "");
+                    line = std::regex_replace(line, bindingRegex2, "layout(");
+                }
+
+                result += line;
+                if (lastLine) {
+                    break;
+                }
+                result += '\n';
+                lineStart = lineEnd + 1;
+            }
             return result;
         }
     } // namespace PrgramImpl
@@ -149,7 +349,7 @@ namespace MobileGL::MG_Backend::DirectGLES {
 #ifdef TRACY_ENABLE
             ZoneScopedC(TRACY_ZONECOLOR_BACKEND);
 #endif
-            while (GLenum err = g_GLESFuncs.glGetError() != GL_NO_ERROR) {
+            for (GLenum err = g_GLESFuncs.glGetError(); err != GL_NO_ERROR; err = g_GLESFuncs.glGetError()) {
                 MGLOG_E("-> GLES Error: %s", MG_Util::ConvertGLEnumToString(err).c_str());
             }
         }
@@ -252,4 +452,317 @@ 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;
+                            }
+                        }
+                    }
+                }
+            }
+        }
+    } // namespace ReadbackImpl
 } // namespace MobileGL::MG_Backend::DirectGLES

MobileGL/MG_Backend/DirectGLES/Utils.h

@@ -35,14 +35,66 @@ namespace MobileGL::MG_Backend::DirectGLES {
 
     namespace TextureImpl {
         void GenerateTextureFormatInfo(TextureInternalFormat internalFormat, GLenum* outInternalFormat,
-                                       GLenum* outFormat, GLenum* outType);
+                                       GLenum* outFormat, GLenum* outType,
+                                       TextureTarget target = TextureTarget::Unknown);
+        void GenerateRenderbufferFormatInfo(TextureInternalFormat internalFormat, GLenum* outInternalFormat,
+                                            GLenum* outFormat, GLenum* outType);
+        Bool ShouldUseCaveatTextureFormat(TextureInternalFormat internalFormat, TextureTarget target);
+        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);
+    } // 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);
         String RemoveLayoutBinding(const String& glslCode);
     } // namespace PrgramImpl

MobileGL/MG_Backend/DirectVulkan/BackendObject_DirectVulkan.cpp

@@ -9,36 +9,319 @@
 #include "BackendObject_DirectVulkan.h"
 #include "MG_Backend/BackendObject.h"
 #include "DirectVulkan.h"
+#include "MG_State/GLState/FramebufferState/FramebufferObject.h"
+#include "MG_State/GLState/TextureState/TextureState.h"
+#include "MG_Util/Classifiers/TextureEnumClassifier.h"
+#include "MG_Util/Converters/MGToGL/TextureEnumConverter.h"
+#include "MG_Util/Converters/MGToStr/TextureEnumConverter.h"
+#include "MG_Util/Converters/MGToVk/TextureEnumConverter.h"
+#include "MG_Util/Texture/TextureFormatProcessor.h"
+
+#include <Config.h>
+#include <cstdlib>
+#include <cstring>
 
 namespace MobileGL::MG_Backend::DirectVulkan {
     namespace {
+        Bool IsR11G11B10FFallbackEnabled() {
+            return MG_Config::Features.MagmaR11G11B10FFallback;
+        }
+
         Bool IsReleaseCurrentRequest(EGLDisplay dpy, EGLSurface draw, EGLSurface read, EGLContext ctx) {
-            return dpy == EGL_NO_DISPLAY && draw == EGL_NO_SURFACE && read == EGL_NO_SURFACE && ctx == EGL_NO_CONTEXT;
+            (void)dpy;
+            return draw == EGL_NO_SURFACE && read == EGL_NO_SURFACE && ctx == EGL_NO_CONTEXT;
+        }
+
+        Bool IsFormatIndexValid(TextureInternalFormat format) {
+            return format != TextureInternalFormat::Unknown && static_cast<Int>(format) >= 0 &&
+                   static_cast<SizeT>(format) < kFormatCapabilityFormatCount;
+        }
+
+        Bool IsLayeredTarget(TextureTarget target) {
+            return target == TextureTarget::Texture3D || target == TextureTarget::Texture1DArray ||
+                   target == TextureTarget::Texture2DArray || target == TextureTarget::TextureCubeMap ||
+                   target == TextureTarget::TextureCubeMapArray ||
+                   target == TextureTarget::Texture2DMultisampleArray;
+        }
+
+        Bool IsMultisampleTarget(TextureTarget target) {
+            return target == TextureTarget::Texture2DMultisample ||
+                   target == TextureTarget::Texture2DMultisampleArray;
+        }
+
+        Bool IsTextureBufferTarget(TextureTarget target) {
+            return target == TextureTarget::TextureBuffer;
+        }
+
+        Bool IsIntegerInternalFormat(TextureInternalFormat format) {
+            const GLenum glFormat = MG_Util::ConvertTextureInternalFormatToGLEnum(format);
+            GLenum normalizedInternalFormat = glFormat;
+            GLenum imageFormat = GL_RGBA;
+            GLenum imageType = GL_UNSIGNED_BYTE;
+            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;
+        }
+
+        FormatCapabilityFlags GetAttachmentCaps(TextureInternalFormat format) {
+            FormatCapabilityFlags caps = FormatCapability::FramebufferRenderable;
+            const Bool isDepth = MG_Util::IsDepthFormatInternalFormat(format);
+            const Bool isStencil = MG_Util::IsStencilFormatInternalFormat(format);
+            if (!isDepth && !isStencil) {
+                caps |= FormatCapability::ColorAttachment;
+            }
+            if (isDepth) {
+                caps |= FormatCapability::DepthAttachment;
+            }
+            if (isStencil) {
+                caps |= FormatCapability::StencilAttachment;
+            }
+            return caps;
+        }
+
+        FormatCapabilityFlags BuildVulkanCaps(TextureInternalFormat logicalFormat,
+                                              TextureTarget target,
+                                              VkFormatFeatureFlags features) {
+            FormatCapabilityFlags caps;
+            const Bool isDepth = MG_Util::IsDepthFormatInternalFormat(logicalFormat);
+            const Bool isStencil = MG_Util::IsStencilFormatInternalFormat(logicalFormat);
+            const Bool isInteger = IsIntegerInternalFormat(logicalFormat);
+
+            if (IsTextureBufferTarget(target)) {
+                if ((features & VK_FORMAT_FEATURE_UNIFORM_TEXEL_BUFFER_BIT) != 0) {
+                    caps |= FormatCapability::Creatable;
+                    caps |= FormatCapability::Sampled;
+                    caps |= FormatCapability::TextureBuffer;
+                }
+                return caps;
+            }
+
+            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 renderable = (isDepth || isStencil) ? depthStencilRenderable : colorRenderable;
+
+            if (sampled || renderable) {
+                caps |= FormatCapability::Creatable;
+            }
+            if (sampled) {
+                caps |= FormatCapability::Sampled;
+                if (linearFilter && !isInteger && !isStencil) {
+                    caps |= FormatCapability::LinearFilter;
+                }
+                if (!isStencil && (features & VK_FORMAT_FEATURE_BLIT_SRC_BIT) != 0 &&
+                    (features & VK_FORMAT_FEATURE_BLIT_DST_BIT) != 0) {
+                    caps |= FormatCapability::GenerateMipmap;
+                }
+                if (!isInteger && !isDepth && !isStencil) {
+                    caps |= FormatCapability::TextureGather;
+                }
+                if (isDepth && !isStencil) {
+                    caps |= FormatCapability::TextureShadow;
+                }
+            }
+            if (renderable) {
+                caps |= GetAttachmentCaps(logicalFormat);
+                if (IsLayeredTarget(target)) {
+                    caps |= FormatCapability::FramebufferLayered;
+                }
+            }
+            if (IsMultisampleTarget(target)) {
+                caps |= FormatCapability::MultisampleTexture;
+            }
+            return caps;
+        }
+
+        Optional<TextureInternalFormat> ResolveVulkanFallbackLogicalFormat(TextureInternalFormat format) {
+            switch (format) {
+            case TextureInternalFormat::RGB:
+            case TextureInternalFormat::RGB8:
+                return TextureInternalFormat::RGBA8;
+            case TextureInternalFormat::SRGB8:
+                return TextureInternalFormat::SRGB8Alpha8;
+            case TextureInternalFormat::RGB8Snorm:
+                return TextureInternalFormat::RGBA8Snorm;
+            case TextureInternalFormat::RGB16:
+                return TextureInternalFormat::RGBA16;
+            case TextureInternalFormat::RGB16Snorm:
+                return TextureInternalFormat::RGBA16Snorm;
+            case TextureInternalFormat::RGB16F:
+                return TextureInternalFormat::RGBA16F;
+            case TextureInternalFormat::R11FG11FB10F:
+                if (IsR11G11B10FFallbackEnabled()) {
+                    return TextureInternalFormat::RGBA16F;
+                }
+                return Nullopt;
+            case TextureInternalFormat::RGB32F:
+                return TextureInternalFormat::RGBA32F;
+            case TextureInternalFormat::RGB8I:
+                return TextureInternalFormat::RGBA8I;
+            case TextureInternalFormat::RGB8UI:
+                return TextureInternalFormat::RGBA8UI;
+            case TextureInternalFormat::RGB16I:
+                return TextureInternalFormat::RGBA16I;
+            case TextureInternalFormat::RGB16UI:
+                return TextureInternalFormat::RGBA16UI;
+            case TextureInternalFormat::RGB32I:
+                return TextureInternalFormat::RGBA32I;
+            case TextureInternalFormat::RGB32UI:
+                return TextureInternalFormat::RGBA32UI;
+            default:
+                return Nullopt;
+            }
+        }
+
+        Optional<VkFormat> ResolveVulkanFallbackFormat(TextureInternalFormat format) {
+            const Optional<TextureInternalFormat> fallbackLogicalFormat = ResolveVulkanFallbackLogicalFormat(format);
+            if (!fallbackLogicalFormat) {
+                return Nullopt;
+            }
+            return MG_Util::ConvertTextureInternalFormatToVkEnum(*fallbackLogicalFormat);
+        }
+
+        Bool HasNewCaveatFormatCaps(FormatCapabilityFlags nativeCaps, FormatCapabilityFlags fallbackCaps) {
+            for (FormatCapability capability : kReportedFormatCapabilities) {
+                if (HasFormatCapability(fallbackCaps, capability) &&
+                    !HasFormatCapability(nativeCaps, capability)) {
+                    return true;
+                }
+            }
+            return false;
+        }
+
+        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());
+        }
+
+        Vector<Int> BuildSampleCounts(Int maxSamples) {
+            Vector<Int> counts;
+            for (Int samples = std::max(maxSamples, 1); samples > 1; samples >>= 1) {
+                counts.push_back(samples);
+            }
+            counts.push_back(1);
+            return counts;
+        }
+
+        void PopulateFormatCapabilitiesImpl(VkPhysicalDevice physicalDevice,
+                                            PFN_vkGetPhysicalDeviceFormatProperties getFormatProperties,
+                                            const MG_External::VulkanCapabilities& capabilities,
+                                            FormatCapabilityCache& cache) {
+            cache.Clear();
+            if (physicalDevice == VK_NULL_HANDLE || getFormatProperties == nullptr) {
+                return;
+            }
+
+            for (SizeT formatIndex = 0; formatIndex < kFormatCapabilityFormatCount; ++formatIndex) {
+                const auto logicalFormat = static_cast<TextureInternalFormat>(formatIndex);
+                if (!IsFormatIndexValid(logicalFormat)) {
+                    continue;
+                }
+
+                VkFormat nativeFormat = MG_Util::ConvertTextureInternalFormatToVkEnum(logicalFormat);
+                const Optional<TextureInternalFormat> fallbackLogicalFormat =
+                    ResolveVulkanFallbackLogicalFormat(logicalFormat);
+                VkFormat fallbackFormat = ResolveVulkanFallbackFormat(logicalFormat).value_or(VK_FORMAT_UNDEFINED);
+
+                VkFormatProperties nativeProperties{};
+                if (nativeFormat != VK_FORMAT_UNDEFINED) {
+                    getFormatProperties(physicalDevice, nativeFormat, &nativeProperties);
+                }
+
+                VkFormatProperties fallbackProperties{};
+                if (fallbackFormat != VK_FORMAT_UNDEFINED && fallbackFormat != nativeFormat) {
+                    getFormatProperties(physicalDevice, fallbackFormat, &fallbackProperties);
+                }
+
+                for (SizeT targetIndex = 0; targetIndex < kFormatCapabilityTextureTargetCount; ++targetIndex) {
+                    const auto target = static_cast<TextureTarget>(targetIndex);
+                    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;
+                    FormatCapabilityFlags fallbackCaps = BuildVulkanCaps(logicalFormat, target, fallbackFeatures);
+                    if (fallbackFormat != VK_FORMAT_UNDEFINED && fallbackFormat != nativeFormat) {
+                        cache.CaveatCaps[targetIndex][formatIndex] |= fallbackCaps;
+                        if (fallbackLogicalFormat && HasNewCaveatFormatCaps(nativeCaps, fallbackCaps)) {
+                            LogVulkanFormatCaveat(logicalFormat, targetIndex, *fallbackLogicalFormat);
+                        }
+                    }
+
+                    if (HasFormatCapability(nativeCaps | fallbackCaps, FormatCapability::MultisampleTexture)) {
+                        const Bool isDepth = MG_Util::IsDepthFormatInternalFormat(logicalFormat);
+                        const Bool isStencil = MG_Util::IsStencilFormatInternalFormat(logicalFormat);
+                        const Bool isInteger = IsIntegerInternalFormat(logicalFormat);
+                        Int maxSamples = capabilities.MaxColorTextureSamples;
+                        if (isDepth || isStencil) {
+                            maxSamples = capabilities.MaxDepthTextureSamples;
+                        } else if (isInteger) {
+                            maxSamples = capabilities.MaxIntegerSamples;
+                        }
+                        cache.SampleCounts[targetIndex][formatIndex] = BuildSampleCounts(maxSamples);
+                    }
+                }
+
+                const SizeT renderbufferTargetIndex = GetRenderbufferFormatCapabilityTargetIndex();
+                FormatCapabilityFlags renderbufferCaps =
+                    BuildVulkanCaps(logicalFormat, TextureTarget::Texture2D, nativeProperties.optimalTilingFeatures);
+                renderbufferCaps &= FormatCapability::Creatable;
+                if ((nativeProperties.optimalTilingFeatures &
+                     (VK_FORMAT_FEATURE_COLOR_ATTACHMENT_BIT | VK_FORMAT_FEATURE_DEPTH_STENCIL_ATTACHMENT_BIT)) != 0) {
+                    renderbufferCaps |= GetAttachmentCaps(logicalFormat);
+                    renderbufferCaps |= FormatCapability::MultisampleRenderbuffer;
+                }
+                cache.FullCaps[renderbufferTargetIndex][formatIndex] |= renderbufferCaps;
+
+                if (fallbackFormat != VK_FORMAT_UNDEFINED && fallbackFormat != nativeFormat) {
+                    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)) !=
+                        0) {
+                        fallbackRenderbufferCaps |= GetAttachmentCaps(logicalFormat);
+                        fallbackRenderbufferCaps |= FormatCapability::MultisampleRenderbuffer;
+                    }
+                    cache.CaveatCaps[renderbufferTargetIndex][formatIndex] |= fallbackRenderbufferCaps;
+                    if (fallbackLogicalFormat &&
+                        HasNewCaveatFormatCaps(renderbufferCaps, fallbackRenderbufferCaps)) {
+                        LogVulkanFormatCaveat(logicalFormat, renderbufferTargetIndex, *fallbackLogicalFormat);
+                    }
+                }
+
+                const FormatCapabilityFlags rbCaps = cache.FullCaps[renderbufferTargetIndex][formatIndex] |
+                                                     cache.CaveatCaps[renderbufferTargetIndex][formatIndex];
+                if (HasFormatCapability(rbCaps, FormatCapability::MultisampleRenderbuffer)) {
+                    cache.SampleCounts[renderbufferTargetIndex][formatIndex] =
+                        BuildSampleCounts(capabilities.MaxFramebufferSamples);
+                }
+            }
         }
     } // namespace
 
+    void PopulateFormatCapabilities(VkPhysicalDevice physicalDevice,
+                                    PFN_vkGetPhysicalDeviceFormatProperties getFormatProperties,
+                                    const MG_External::VulkanCapabilities& capabilities,
+                                    FormatCapabilityCache& cache) {
+        PopulateFormatCapabilitiesImpl(physicalDevice, getFormatProperties, capabilities, cache);
+    }
+
     BackendObject_DirectVulkan::~BackendObject_DirectVulkan() = default;
 
-    BackendObject_DirectVulkan::BackendObject_DirectVulkan():
-        m_rendererInfo{
-            .RendererName = "Magma",
-            .BackendName = "Direct (Vulkan)",
-            .ExtraVendor = Nullopt,
-            .RendererGLInfo =
-                {
-                    .TargetGLVersion = {3, 3, 0},
-                    .TargetGLSLVersion = {4, 6, 0},
-                    .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_direct_state_access,
-                                   E_GL_ARB_shader_draw_parameters, E_GL_ARB_gpu_shader_int64},
-                    .IsCompatibilityProfile = false
-                },
-            .StaticBackendCapability = {.AllowVSOnlyPrograms = false}} {}
+    BackendObject_DirectVulkan::BackendObject_DirectVulkan(): m_rendererInfo{GetRendererIdentity()} {}
 
     Bool BackendObject_DirectVulkan::InitWindowSurface() {
         if (!m_windowHandle.Handle) {
@@ -48,12 +331,28 @@ namespace MobileGL::MG_Backend::DirectVulkan {
 
         auto nativeWindow = reinterpret_cast<NativeWindowType>(m_windowHandle.Handle);
 
+        // Any renderer instance this assignment replaces is destroyed here;
+        // fence/timer-query handles stamped with the old generation go stale.
+        BumpRendererGeneration();
         pVulkanRenderer = MakeUnique<MG_Backend::DirectVulkan::VulkanRenderer>(nativeWindow);
         MOBILEGL_ASSERT(pVulkanRenderer != nullptr, "InitWindowSurface: VulkanRenderer creation failed");
         pVulkanRenderer->Initialize();
         return true;
     }
 
+    Bool BackendObject_DirectVulkan::InitPbufferSurface(EGLint width, EGLint height) {
+        VulkanRendererConfig config;
+        config.SurfaceWidth = static_cast<Uint32>(std::max<EGLint>(width, 1));
+        config.SurfaceHeight = static_cast<Uint32>(std::max<EGLint>(height, 1));
+        // Any renderer instance this assignment replaces is destroyed here;
+        // fence/timer-query handles stamped with the old generation go stale.
+        BumpRendererGeneration();
+        pVulkanRenderer = MakeUnique<MG_Backend::DirectVulkan::VulkanRenderer>(NativeWindowType{}, config);
+        MOBILEGL_ASSERT(pVulkanRenderer != nullptr, "InitPbufferSurface: VulkanRenderer creation failed");
+        pVulkanRenderer->Initialize();
+        return true;
+    }
+
     void BackendObject_DirectVulkan::Initialize() {
         m_initialized = true;
     }
@@ -76,6 +375,9 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         }
         UpdateDynamicBackendParameters();
         UpdateAdvertisedExtensions();
+        PopulateFormatCapabilities(physicalDevice.handle, vkGetPhysicalDeviceFormatProperties, m_vulkanCaps,
+                                   MutableFormatCapabilities());
+        PrintFormatCapabilities(GetFormatCapabilities());
         return true;
     }
 
@@ -87,40 +389,48 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         return BackendObject::InitializeEGLDisplay(dpy, major, minor);
     }
 
-    Bool BackendObject_DirectVulkan::CreateEGLWindowSurface(const WindowHandle& handle) {
+    Bool BackendObject_DirectVulkan::CreateEGLWindowSurface(EGLSurface surface, const WindowHandle& handle) {
         const std::lock_guard<std::recursive_mutex> lock(m_eglStateMutex);
         if (!m_initialized) {
             MGLOG_E("DirectVulkan backend not initialized");
             return false;
         }
-        if (!handle.Handle || (handle.Backend != WindowBackend::Android && handle.Backend != WindowBackend::X11)) {
-            MGLOG_E("DirectVulkan backend only supports Android and X11 native windows");
+        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");
             return false;
         }
 
-        const Bool sameHandle = m_eglSurfaceInitialized && m_eglSurfaceKind == SurfaceKind::Window &&
-                                m_windowHandle.Backend == handle.Backend && m_windowHandle.Handle == handle.Handle;
-        if (sameHandle) {
-            return true;
-        }
+        return RegisterEGLWindowSurface(surface, handle);
+    }
 
-        if (m_eglSurfaceInitialized || pVulkanRenderer) {
-            pVulkanRenderer.reset();
-            ResetEGLRuntimeState();
+    Bool BackendObject_DirectVulkan::ResizeEGLWindowSurface(EGLSurface surface, Uint32 width, Uint32 height) {
+        const std::lock_guard<std::recursive_mutex> lock(m_eglStateMutex);
+        if (!m_initialized) {
+            MGLOG_E("DirectVulkan backend not initialized");
+            return false;
         }
+        if (!BackendObject::ResizeEGLWindowSurface(surface, width, height)) {
+            return false;
+        }
+        if (pVulkanRenderer && m_eglSurface == surface) {
+            pVulkanRenderer->RequestSwapchainResize(width, height);
+        }
+        return true;
+    }
 
-        return BackendObject::CreateEGLWindowSurface(handle);
+    Bool BackendObject_DirectVulkan::CreateEGLPbufferSurface(EGLSurface surface, EGLint width, EGLint height) {
+        const std::lock_guard<std::recursive_mutex> lock(m_eglStateMutex);
+        if (!m_initialized) {
+            MGLOG_E("DirectVulkan backend not initialized");
+            return false;
+        }
+        return RegisterEGLPbufferSurface(surface, width, height);
     }
 
     Bool BackendObject_DirectVulkan::MakeEGLCurrent(EGLDisplay dpy, EGLSurface draw, EGLSurface read, EGLContext ctx) {
         const std::lock_guard<std::recursive_mutex> lock(m_eglStateMutex);
-        if (IsReleaseCurrentRequest(dpy, draw, read, ctx)) {
-            return BackendObject::MakeEGLCurrent(dpy, draw, read, ctx);
-        }
-        if (!pVulkanRenderer) {
-            MGLOG_E("DirectVulkan renderer is not initialized");
-            return false;
-        }
         return BackendObject::MakeEGLCurrent(dpy, draw, read, ctx);
     }
 
@@ -133,12 +443,28 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         return BackendObject::SwapEGLBuffers(dpy, draw);
     }
 
+    void BackendObject_DirectVulkan::ReleaseEGLSurface(EGLSurface surface) {
+        const std::lock_guard<std::recursive_mutex> lock(m_eglStateMutex);
+        BackendObject::ReleaseEGLSurface(surface);
+    }
+
     void BackendObject_DirectVulkan::ReleaseEGLResources() {
         const std::lock_guard<std::recursive_mutex> lock(m_eglStateMutex);
+        // Outstanding fence/timer-query handles now refer to a dead renderer;
+        // treat them as signaled/available with zero results from here on.
+        BumpRendererGeneration();
         pVulkanRenderer.reset();
         BackendObject::ReleaseEGLResources();
     }
 
+    void BackendObject_DirectVulkan::OnEGLSurfaceReleased(EGLSurface surface) {
+        (void)surface;
+        // Outstanding fence/timer-query handles now refer to a dead renderer;
+        // treat them as signaled/available with zero results from here on.
+        BumpRendererGeneration();
+        pVulkanRenderer.reset();
+    }
+
     const RendererInfo& BackendObject_DirectVulkan::GetRendererInfo() const {
         return m_rendererInfo;
     }
@@ -147,11 +473,65 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         if (!m_initialized) {
             return "<uninitialized DirectVulkan backend>";
         }
+        return FormatBackendAPIVersionString(m_vulkanCaps.DeviceName, m_vulkanCaps.VulkanAPIVersion.toString(),
+                                             m_vulkanCaps.DriverVersionString);
+    }
+
+    const RendererInfo& GetRendererIdentity() {
+        static const RendererInfo rendererInfo = {
+            .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, false),
+                    .IsCompatibilityProfile = false
+                },
+            .StaticBackendCapability = {.AllowVSOnlyPrograms = false}};
+        return rendererInfo;
+    }
+
+    Vector<GLExtension> BuildAdvertisedExtensions(Bool shaderSubgroupSupported, Bool timerQueriesSupported,
+                                                  Bool anisotropicFilteringSupported) {
+        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_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};
+        if (shaderSubgroupSupported && !MG_Config::Features.DisableSubgroup) {
+            extensions.push_back(E_GL_KHR_shader_subgroup);
+        }
+        // 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;
+    }
+
+    String FormatBackendAPIVersionString(const String& deviceName, const String& vulkanApiVersionString,
+                                         const String& driverVersionString) {
         // Format:
         // <GPU Name>, Vulkan <Vulkan Version>, Driver <Driver Version>
-        String str = m_vulkanCaps.DeviceName + ", Vulkan " + m_vulkanCaps.VulkanAPIVersion.toString() + ", Driver " +
-                     m_vulkanCaps.DriverVersionString;
-        return str;
+        return deviceName + ", Vulkan " + vulkanApiVersionString + ", Driver " + driverVersionString;
     }
 
     BackendType BackendObject_DirectVulkan::GetBackendType() const {
@@ -166,6 +546,7 @@ namespace MobileGL::MG_Backend::DirectVulkan {
             funcsTable.GL.DrawArrays = DrawArrays;
             funcsTable.GL.DrawElements = DrawElements;
             funcsTable.GL.DrawElementsBaseVertex = DrawElementsBaseVertex;
+            funcsTable.GL.MultiDrawArrays = MultiDrawArrays;
             funcsTable.GL.MultiDrawElements = MultiDrawElements;
             funcsTable.GL.MultiDrawElementsBaseVertex = MultiDrawElementsBaseVertex;
             funcsTable.GL.MultiDrawElementsIndirect = MultiDrawElementsIndirect;
@@ -193,6 +574,7 @@ namespace MobileGL::MG_Backend::DirectVulkan {
             funcsTable.GL.BlitNamedFramebuffer = BlitNamedFramebuffer;
             funcsTable.GL.CopyTexImage2D = CopyTexImage2D;
             funcsTable.GL.CopyTexSubImage2D = CopyTexSubImage2D;
+            funcsTable.GL.CopyImageSubData = CopyImageSubData;
             funcsTable.GL.GenerateMipmap = GenerateMipmap;
             funcsTable.GL.ReadPixels = ReadPixels;
             funcsTable.GL.GetTexImage = GetTexImage;
@@ -212,6 +594,25 @@ namespace MobileGL::MG_Backend::DirectVulkan {
             funcsTable.GL.GetProgramResourceLocation = GetProgramResourceLocation;
             funcsTable.GL.GetProgramResourceLocationIndex = GetProgramResourceLocationIndex;
             funcsTable.GL.ShaderStorageBlockBinding = ShaderStorageBlockBinding;
+            funcsTable.GL.FenceSync = FenceSync;
+            funcsTable.GL.ClientWaitSync = ClientWaitSync;
+            funcsTable.GL.WaitSync = WaitSync;
+            funcsTable.GL.DeleteSync = DeleteSync;
+            funcsTable.GL.GetSyncStatus = GetSyncStatus;
+            // Optional timer-query group: left null (the frontend then falls
+            // back) when disabled via MOBILEGL_DISABLE_TIMERQUERY. The hooks
+            // themselves additionally degrade to null handles when the device
+            // lacks timestamp support.
+            if (!MG_Config::Features.DisableTimerQuery) {
+                funcsTable.GL.IsTimerQuerySupported = IsTimerQuerySupported;
+                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;
+            }
             funcsTableInitialized = true;
         }
         return funcsTable;
@@ -226,16 +627,19 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         m_vulkanCaps = capabilities;
         UpdateDynamicBackendParameters();
         UpdateAdvertisedExtensions();
+        MutableFormatCapabilities().Clear();
     }
 
     void BackendObject_DirectVulkan::UpdateAdvertisedExtensions() {
-        auto& extensions = m_rendererInfo.RendererGLInfo.Extensions;
-        extensions.erase(std::remove(extensions.begin(), extensions.end(), E_GL_KHR_shader_subgroup),
-                         extensions.end());
-
-        if (m_vulkanCaps.SupportsShaderSubgroup) {
-            extensions.push_back(E_GL_KHR_shader_subgroup);
-        }
+        // GL_ARB_timer_query gates MC's F3 GPU% (LWJGL checks the extension
+        // string). InitCapabilities runs after InitWindowSurface has created
+        // and initialized the renderer, so the advertisement can be gated on
+        // real device timestamp support. ApplyVulkanCapabilitiesForTesting may
+        // 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(),
+            pVulkanRenderer && pVulkanRenderer->IsSamplerAnisotropySupported());
     }
 
     void BackendObject_DirectVulkan::UpdateDynamicBackendParameters() {
@@ -283,6 +687,95 @@ namespace MobileGL::MG_Backend::DirectVulkan {
 
         static constexpr SizeT kMaxAdvertisedShaderStorageBlockSize = 512ull * 1024ull * 1024ull;
         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;
+        m_dynamicParameters.PointSizeRangeMin = m_vulkanCaps.PointSizeRangeMin;
+        m_dynamicParameters.PointSizeRangeMax = m_vulkanCaps.PointSizeRangeMax;
+        m_dynamicParameters.PointSizeGranularity = m_vulkanCaps.PointSizeGranularity;
+        m_dynamicParameters.Max3DTextureSize = m_vulkanCaps.Max3DTextureSize;
+        m_dynamicParameters.MaxArrayTextureLayers = m_vulkanCaps.MaxArrayTextureLayers;
+        m_dynamicParameters.MaxCubeMapTextureSize = m_vulkanCaps.MaxCubeMapTextureSize;
+        m_dynamicParameters.MaxFramebufferWidth = m_vulkanCaps.MaxFramebufferWidth;
+        m_dynamicParameters.MaxFramebufferHeight = m_vulkanCaps.MaxFramebufferHeight;
+        m_dynamicParameters.MaxFramebufferLayers = m_vulkanCaps.MaxFramebufferLayers;
+        m_dynamicParameters.MaxRenderbufferSize = m_vulkanCaps.MaxRenderbufferSize;
+        m_dynamicParameters.MaxTextureSize = m_vulkanCaps.MaxTextureSize;
+        m_dynamicParameters.MaxColorTextureSamples = m_vulkanCaps.MaxColorTextureSamples;
+        m_dynamicParameters.MaxDepthTextureSamples = m_vulkanCaps.MaxDepthTextureSamples;
+        m_dynamicParameters.MaxFramebufferSamples = m_vulkanCaps.MaxFramebufferSamples;
+        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);
+        // 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
+        // an array bound: Minecraft's Blaze3D GlStateManager.TEXTURES[] holds 128 entries and Iris
+        // iterates [0, GL_MAX_TEXTURE_IMAGE_UNITS) over it (CompositeRenderer.renderAll), so any value
+        // > 128 throws ArrayIndexOutOfBoundsException. Match desktop drivers (32) for the per-stage
+        // 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.MaxVertexTextureImageUnits =
+            std::min(m_vulkanCaps.MaxVertexTextureImageUnits, maxPerStageTextureUnits);
+        m_dynamicParameters.MaxComputeTextureImageUnits =
+            std::min(m_vulkanCaps.MaxComputeTextureImageUnits, maxPerStageTextureUnits);
+        m_dynamicParameters.MaxCombinedTextureImageUnits =
+            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.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.MaxUniformBufferBindings = m_vulkanCaps.MaxUniformBufferBindings;
+        m_dynamicParameters.MaxUniformBlockSize = m_vulkanCaps.MaxUniformBlockSize;
+        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;
+        m_dynamicParameters.MaxViewports = m_vulkanCaps.MaxViewports;
+        m_dynamicParameters.MaxViewportWidth = m_vulkanCaps.MaxViewportWidth;
+        m_dynamicParameters.MaxViewportHeight = m_vulkanCaps.MaxViewportHeight;
+        m_dynamicParameters.ViewportBoundsRangeMin = m_vulkanCaps.ViewportBoundsRangeMin;
+        m_dynamicParameters.ViewportBoundsRangeMax = m_vulkanCaps.ViewportBoundsRangeMax;
+        m_dynamicParameters.ViewportSubpixelBits = m_vulkanCaps.ViewportSubpixelBits;
+        m_dynamicParameters.SupportsWideLines = m_vulkanCaps.SupportsWideLines;
         m_dynamicParameters.MaxShaderStorageBlockSize =
             std::min(m_vulkanCaps.MaxShaderStorageBlockSize, kMaxAdvertisedShaderStorageBlockSize);
         if (m_vulkanCaps.SupportsShaderSubgroup) {

MobileGL/MG_Backend/DirectVulkan/BackendObject_DirectVulkan.h

@@ -12,6 +12,14 @@
 #include <MG_Util/BackendLoaders/Vulkan/Loader.h>
 
 namespace MobileGL::MG_Backend::DirectVulkan {
+    // Populates the same format-capability cache used by backend startup. Passing the
+    // instance-resolved function keeps standalone callers independent of global loader
+    // initialization; the physical device must remain valid for the duration of the call.
+    void PopulateFormatCapabilities(VkPhysicalDevice physicalDevice,
+                                    PFN_vkGetPhysicalDeviceFormatProperties getFormatProperties,
+                                    const MG_External::VulkanCapabilities& capabilities,
+                                    FormatCapabilityCache& cache);
+
     class BackendObject_DirectVulkan : public BackendObject {
     public:
         BackendObject_DirectVulkan();
@@ -21,9 +29,12 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         Bool InitWindowSurface() override;
         Bool InitCapabilities() override;
         Bool InitializeEGLDisplay(EGLDisplay dpy, EGLint* major, EGLint* minor) override;
-        Bool CreateEGLWindowSurface(const WindowHandle& handle) override;
+        Bool CreateEGLWindowSurface(EGLSurface surface, const WindowHandle& handle) override;
+        Bool ResizeEGLWindowSurface(EGLSurface surface, Uint32 width, Uint32 height) override;
+        Bool CreateEGLPbufferSurface(EGLSurface surface, EGLint width, EGLint height) override;
         Bool MakeEGLCurrent(EGLDisplay dpy, EGLSurface draw, EGLSurface read, EGLContext ctx) override;
         Bool SwapEGLBuffers(EGLDisplay dpy, EGLSurface draw) override;
+        void ReleaseEGLSurface(EGLSurface surface) override;
         void ReleaseEGLResources() override;
 
         const RendererInfo& GetRendererInfo() const override;
@@ -34,6 +45,8 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         void ApplyVulkanCapabilitiesForTesting(const MG_External::VulkanCapabilities& capabilities);
 
     private:
+        Bool InitPbufferSurface(EGLint width, EGLint height) override;
+        void OnEGLSurfaceReleased(EGLSurface surface) override;
         void UpdateAdvertisedExtensions();
         void UpdateDynamicBackendParameters();
 
@@ -42,4 +55,30 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         MG_External::VulkanCapabilities m_vulkanCaps;
         RendererInfo m_rendererInfo;
     };
+
+    // Single-source-of-truth helpers shared with the driver POST
+    // (MG_Util/SelfTest/DriverPost.cpp), so the identity strings and extension list
+    // MobileGL reports to applications on this backend cannot drift from what the
+    // POST screen shows.
+
+    // Static identity of the Magma renderer (renderer/backend names, target GL/GLSL
+    // versions, ExtraVendor) with the baseline extension advertisement (no shader
+    // subgroup, no timer queries). A live backend copies this in its constructor and
+    // reconciles the Extensions in UpdateAdvertisedExtensions once real capabilities
+    // exist; callers that need the advertised list for a known capability set must
+    // use BuildAdvertisedExtensions instead.
+    const RendererInfo& GetRendererIdentity();
+
+    // The full OpenGL extension list Magma advertises (glGetString(GL_EXTENSIONS)) for
+    // 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,
+                                                  Bool anisotropicFilteringSupported);
+
+    // Format: <GPU Name>, Vulkan <Vulkan Version>, Driver <Driver Version> — the exact
+    // string an initialized backend returns from GetBackendAPIVersionString (and that
+    // ends up inside the application-visible GL_RENDERER string).
+    String FormatBackendAPIVersionString(const String& deviceName, const String& vulkanApiVersionString,
+                                         const String& driverVersionString);
 } // namespace MobileGL::MG_Backend::DirectVulkan

MobileGL/MG_Backend/DirectVulkan/DirectVulkan.h

@@ -8,11 +8,21 @@
 
 #pragma once
 #include <Includes.h>
+#include <MG_Backend/BackendObject.h>
 #include "Renderer/VulkanRenderer.h"
 
 namespace MobileGL::MG_Backend::DirectVulkan {
     extern UniquePtr<VulkanRenderer> pVulkanRenderer;
 
+    // Generation of the live VulkanRenderer instance, mirroring DirectGLES's
+    // g_syncContextGeneration. BackendObject_DirectVulkan bumps it wherever
+    // pVulkanRenderer is reset or recreated; fence and timer-query handles
+    // stamped with an older generation are stale and resolve as signaled /
+    // available with zero results instead of dereferencing the destroyed
+    // renderer's frame serials and query-pool slots.
+    Uint64 GetRendererGeneration();
+    void BumpRendererGeneration();
+
     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);
@@ -25,6 +35,7 @@ namespace MobileGL::MG_Backend::DirectVulkan {
     void DrawElements(GLenum mode, GLsizei count, GLenum type, const void* indices);
     void DrawArrays(GLenum mode, GLint first, GLsizei count);
     void DrawElementsBaseVertex(GLenum mode, GLsizei count, GLenum type, const GLvoid* indices, GLint basevertex);
+    void MultiDrawArrays(GLenum mode, const GLint* first, const GLsizei* count, GLsizei drawcount);
     void MultiDrawElements(GLenum mode, const GLsizei* count, GLenum type, const GLvoid* const* indices,
                            GLsizei drawcount);
     void MultiDrawElementsBaseVertex(GLenum mode, const GLsizei* count, GLenum type, const GLvoid* const* indices,
@@ -61,6 +72,11 @@ namespace MobileGL::MG_Backend::DirectVulkan {
                         GLsizei height, GLint border);
     void CopyTexSubImage2D(GLenum target, GLint level, GLint xoffset, GLint yoffset, GLint x, GLint y, GLsizei width,
                            GLsizei height);
+    void CopyImageSubData(const SharedPtr<MG_State::GLState::ITextureObject>& srcTexture,
+                          GLenum srcTarget, GLint srcLevel, GLint srcX, GLint srcY, GLint srcZ,
+                          const SharedPtr<MG_State::GLState::ITextureObject>& dstTexture,
+                          GLenum dstTarget, GLint dstLevel, GLint dstX, GLint dstY, GLint dstZ,
+                          GLsizei srcWidth, GLsizei srcHeight, GLsizei srcDepth);
     void GenerateMipmap(GLenum target);
     void DispatchCompute(GLuint numGroupsX, GLuint numGroupsY, GLuint numGroupsZ);
     void DispatchComputeIndirect(GLintptr indirect);
@@ -84,5 +100,35 @@ namespace MobileGL::MG_Backend::DirectVulkan {
     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, GLsizei bufSize, GLvoid* pixels);
+    // GL fence sync objects, mapped onto the renderer's frame-serial busy
+    // tracking: a fence captures the frame serial current at creation and is
+    // signaled once every command recorded under that serial has completed on
+    // the GPU.
+    BackendSyncHandle FenceSync();
+    GLenum ClientWaitSync(BackendSyncHandle sync, GLbitfield flags, GLuint64 timeout);
+    void WaitSync(BackendSyncHandle sync, GLbitfield flags, GLuint64 timeout);
+    void DeleteSync(BackendSyncHandle sync);
+    Bool GetSyncStatus(BackendSyncHandle sync);
+    // GPU timer queries (GL_TIME_ELAPSED spans and GL_TIMESTAMP one-shots),
+    // backed by per-frame VkQueryPool timestamp slots. All hooks degrade
+    // gracefully: null handles when the renderer is absent, the device lacks
+    // timestamp support, or the frame's pool is exhausted.
+    // Dynamic support check (GLFunctionsTable::IsTimerQuerySupported): true
+    // only while a live renderer exists whose device can actually time.
+    Bool IsTimerQuerySupported();
+    BackendQueryHandle BeginTimeElapsedQuery();
+    void EndTimeElapsedQuery(BackendQueryHandle query);
+    BackendQueryHandle QueryCounterTimestamp();
+    Bool IsQueryResultAvailable(BackendQueryHandle query);
+    // Returns true when a final value was produced (outNanoseconds set; the
+    // frontend may cache it and release the handle), false when the result
+    // cannot be obtained yet (e.g. a wait refused because the records' frame
+    // serial is the current unsubmitted frame) - the handle then stays
+    // readable later.
+    Bool GetQueryResult64(BackendQueryHandle query, Bool wait, Uint64* outNanoseconds);
+    void DeleteBackendQuery(BackendQueryHandle query);
+    // Always 0: Vulkan cannot synchronously sample the GPU clock (timestamps
+    // only exist as vkCmdWriteTimestamp results); the frontend falls back.
+    Int64 GetGpuTimestampNs();
     void Present();
 } // namespace MobileGL::MG_Backend::DirectVulkan

MobileGL/MG_Backend/DirectVulkan/Renderer/FrameContext.cpp

@@ -13,6 +13,8 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         Destroy(device, commandPool);
         m_frames.assign(frameCount, {});
         currentFrameIndex = 0;
+        m_device = device;
+        m_commandPool = commandPool;
 
         Vector<VkCommandBuffer> commandBuffers(frameCount, VK_NULL_HANDLE);
         VkCommandBufferAllocateInfo allocInfo{};
@@ -55,10 +57,15 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         }
         DestroySwapchainSemaphores(device);
         if (device != VK_NULL_HANDLE && commandPool != VK_NULL_HANDLE && !m_frames.empty()) {
+            for (auto& frame : m_frames) {
+                FreeRetiredCommandBuffers(frame);
+            }
             vkFreeCommandBuffers(device, commandPool, frameCount, commandBuffers.data());
         }
         m_frames.clear();
         currentFrameIndex = 0;
+        m_device = VK_NULL_HANDLE;
+        m_commandPool = VK_NULL_HANDLE;
     }
 
     FrameContext::FrameData& FrameContext::GetCurrent() {
@@ -97,6 +104,9 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         VK_VERIFY(vkBeginCommandBuffer(frame.commandBuffer, &beginInfo), "BeginCommandRecording, vkBeginCommandBuffer");
 
         frame.isCommandRecording = true;
+        if (m_recordingObserver != nullptr) {
+            m_recordingObserver->OnFrameCommandRecordingBegan(frame.commandBuffer);
+        }
         return frame.commandBuffer;
     }
 
@@ -188,18 +198,18 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         return packet;
     }
 
-    FrameContext::PresentInfoPacket FrameContext::GetPresentInfo(VkSwapchainKHR swapchain, const Uint32& imageIndex) const {
+    FrameContext::PresentInfoPacket FrameContext::GetPresentInfo(VkSwapchainKHR swapchain, Uint32 imageIndex) const {
         AssertValidSwapchainImageIndex(imageIndex);
         PresentInfoPacket packet{};
         packet.waitSemaphore = m_swapchainImageRenderFinishedSemaphores[imageIndex];
         packet.swapchain = swapchain;
-        packet.imageIndex = &imageIndex;
+        packet.imageIndex = imageIndex;
 
         packet.presentInfo.waitSemaphoreCount = 1;
         packet.presentInfo.pWaitSemaphores = &packet.waitSemaphore;
         packet.presentInfo.swapchainCount = 1;
         packet.presentInfo.pSwapchains = &packet.swapchain;
-        packet.presentInfo.pImageIndices = packet.imageIndex;
+        packet.presentInfo.pImageIndices = &packet.imageIndex;
         packet.presentInfo.pResults = nullptr;
         return packet;
     }
@@ -211,15 +221,18 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         if (result != VK_SUCCESS) {
             return result;
         }
+        // The slot's fence has been waited: every command buffer this slot
+        // submitted (including mid-frame flushes) has finished executing.
+        FreeRetiredCommandBuffers(frame);
 
-        result = vkResetFences(device, 1, &frame.imageInFlightFence);
+        result = vkAcquireNextImageKHR(device, swapchain, timeout, frame.imageAvailableSemaphore, acquireFence,
+                                       &outImageIndex);
         if (result != VK_SUCCESS) {
             return result;
         }
 
         frame.imageAvailableSemaphoreConsumed = false;
-        return vkAcquireNextImageKHR(device, swapchain, timeout, frame.imageAvailableSemaphore, acquireFence,
-                                     &outImageIndex);
+        return vkResetFences(device, 1, &frame.imageInFlightFence);
     }
 
     Uint32 FrameContext::GetCurrentFrameIndex() const {
@@ -230,6 +243,43 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         return static_cast<Uint32>(m_frames.size());
     }
 
+    void FrameContext::SetRecordingObserver(IRecordingObserver* observer) {
+        m_recordingObserver = observer;
+    }
+
+    VkResult FrameContext::RetireCurrentCommandBuffer() {
+        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");
+
+        VkCommandBufferAllocateInfo allocInfo{};
+        allocInfo.sType = VK_STRUCTURE_TYPE_COMMAND_BUFFER_ALLOCATE_INFO;
+        allocInfo.commandPool = m_commandPool;
+        allocInfo.level = VK_COMMAND_BUFFER_LEVEL_PRIMARY;
+        allocInfo.commandBufferCount = 1;
+        VkCommandBuffer replacement = VK_NULL_HANDLE;
+        const VkResult result = vkAllocateCommandBuffers(m_device, &allocInfo, &replacement);
+        if (result != VK_SUCCESS) {
+            return result;
+        }
+        frame.retiredCommandBuffers.push_back(frame.commandBuffer);
+        frame.commandBuffer = replacement;
+        return VK_SUCCESS;
+    }
+
+    void FrameContext::FreeRetiredCommandBuffers(FrameData& frame) {
+        if (frame.retiredCommandBuffers.empty()) {
+            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());
+        }
+        frame.retiredCommandBuffers.clear();
+    }
+
     void FrameContext::AssertValidFrameIndex(Uint32 frameIndex) const {
         MOBILEGL_ASSERT(frameIndex < m_frames.size(), "FrameContext index out of range");
     }

MobileGL/MG_Backend/DirectVulkan/Renderer/FrameContext.h

@@ -14,6 +14,17 @@
 namespace MobileGL::MG_Backend::DirectVulkan {
     class FrameContext {
     public:
+        // Notified immediately after a frame command buffer begins recording
+        // (before any render pass has been begun); every BeginCommandRecording
+        // caller funnels through this single seam. Implemented by the renderer
+        // to prepare per-frame timer-query pools (vkCmdResetQueryPool must be
+        // recorded outside a render pass).
+        class IRecordingObserver {
+        public:
+            virtual ~IRecordingObserver() = default;
+            virtual void OnFrameCommandRecordingBegan(VkCommandBuffer commandBuffer) = 0;
+        };
+
         struct SubmitInfoPacket {
             VkPipelineStageFlags waitDstStageMask = VK_PIPELINE_STAGE_TOP_OF_PIPE_BIT;
             VkSemaphore waitSemaphore = VK_NULL_HANDLE;
@@ -25,7 +36,7 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         struct PresentInfoPacket {
             VkSemaphore waitSemaphore = VK_NULL_HANDLE;
             VkSwapchainKHR swapchain = VK_NULL_HANDLE;
-            const Uint32* imageIndex = nullptr;
+            Uint32 imageIndex = 0;
             VkPresentInfoKHR presentInfo{VK_STRUCTURE_TYPE_PRESENT_INFO_KHR};
         };
 
@@ -36,6 +47,13 @@ namespace MobileGL::MG_Backend::DirectVulkan {
             Bool isCommandRecording = false;
             Bool hasCommandBufferRecorded = 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;
+            // Submit-tracker index of this slot's most recent queue submission
+            // (written by the renderer at submit time).
+            Uint64 lastSubmitIndex = 0;
         };
 
         VkResult Initialize(VkDevice device, VkCommandPool commandPool, Uint32 frameCount);
@@ -54,13 +72,22 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         Bool TransitionToPresent(VkImage image, VkImageLayout oldLayout,
                                  VkImageLayout presentLayout = VK_IMAGE_LAYOUT_PRESENT_SRC_KHR);
         SubmitInfoPacket GetSubmitInfo(Bool shouldSubmitCommandBuffer, Uint32 swapchainImageIndex) const;
-        PresentInfoPacket GetPresentInfo(VkSwapchainKHR swapchain, const Uint32& imageIndex) const;
+        PresentInfoPacket GetPresentInfo(VkSwapchainKHR swapchain, Uint32 imageIndex) const;
         VkResult WaitAndAcquireNextImage(VkDevice device, VkSwapchainKHR swapchain, Uint32& outImageIndex,
                                          Uint64 timeout = UINT64_MAX, VkFence acquireFence = VK_NULL_HANDLE);
 
+        // 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();
+
         Uint32 GetCurrentFrameIndex() const;
         Uint32 GetFrameCount() const;
 
+        // Observer may be null (no notifications). Not owned.
+        void SetRecordingObserver(IRecordingObserver* observer);
+
     private:
         void AssertValidFrameIndex(Uint32 frameIndex) const;
         void AssertValidSwapchainImageIndex(Uint32 imageIndex) const;
@@ -69,9 +96,14 @@ namespace MobileGL::MG_Backend::DirectVulkan {
                                            const VkSemaphoreCreateInfo& semaphoreInfo,
                                            const VkFenceCreateInfo& fenceInfo);
         void DestroySyncObjectsForFrame(VkDevice device, Uint32 frameIndex);
+        void FreeRetiredCommandBuffers(FrameData& frame);
 
         Vector<FrameData> m_frames;
         Vector<VkSemaphore> m_swapchainImageRenderFinishedSemaphores;
         Uint32 currentFrameIndex = 0;
+        IRecordingObserver* m_recordingObserver = nullptr;
+        // Stored at Initialize for retired-command-buffer management.
+        VkDevice m_device = VK_NULL_HANDLE;
+        VkCommandPool m_commandPool = VK_NULL_HANDLE;
     };
 } // namespace MobileGL::MG_Backend::DirectVulkan

MobileGL/MG_Backend/DirectVulkan/Renderer/PipelineFactory.cpp

@@ -9,10 +9,100 @@
 #include "PipelineFactory.h"
 
 namespace MobileGL::MG_Backend::DirectVulkan {
+    static const char* PrimitiveTopologyToString(VkPrimitiveTopology topology) {
+        switch (topology) {
+        ENUM_STR_CASE(VK_PRIMITIVE_TOPOLOGY_POINT_LIST)
+        ENUM_STR_CASE(VK_PRIMITIVE_TOPOLOGY_LINE_LIST)
+        ENUM_STR_CASE(VK_PRIMITIVE_TOPOLOGY_LINE_STRIP)
+        ENUM_STR_CASE(VK_PRIMITIVE_TOPOLOGY_TRIANGLE_LIST)
+        ENUM_STR_CASE(VK_PRIMITIVE_TOPOLOGY_TRIANGLE_STRIP)
+        ENUM_STR_CASE(VK_PRIMITIVE_TOPOLOGY_TRIANGLE_FAN)
+        ENUM_STR_CASE(VK_PRIMITIVE_TOPOLOGY_LINE_LIST_WITH_ADJACENCY)
+        ENUM_STR_CASE(VK_PRIMITIVE_TOPOLOGY_LINE_STRIP_WITH_ADJACENCY)
+        ENUM_STR_CASE(VK_PRIMITIVE_TOPOLOGY_TRIANGLE_LIST_WITH_ADJACENCY)
+        ENUM_STR_CASE(VK_PRIMITIVE_TOPOLOGY_TRIANGLE_STRIP_WITH_ADJACENCY)
+        ENUM_STR_CASE(VK_PRIMITIVE_TOPOLOGY_PATCH_LIST)
+        default:
+            return "VK_PRIMITIVE_TOPOLOGY_UNKNOWN";
+        }
+    }
+
+    static const char* SampleCountToString(VkSampleCountFlagBits sampleCount) {
+        switch (sampleCount) {
+        ENUM_STR_CASE(VK_SAMPLE_COUNT_1_BIT)
+        ENUM_STR_CASE(VK_SAMPLE_COUNT_2_BIT)
+        ENUM_STR_CASE(VK_SAMPLE_COUNT_4_BIT)
+        ENUM_STR_CASE(VK_SAMPLE_COUNT_8_BIT)
+        ENUM_STR_CASE(VK_SAMPLE_COUNT_16_BIT)
+        ENUM_STR_CASE(VK_SAMPLE_COUNT_32_BIT)
+        ENUM_STR_CASE(VK_SAMPLE_COUNT_64_BIT)
+        default:
+            return "VK_SAMPLE_COUNT_UNKNOWN";
+        }
+    }
+
+    static const char* CullModeToString(VkCullModeFlags cullMode) {
+        switch (cullMode) {
+        case VK_CULL_MODE_NONE:
+            return "VK_CULL_MODE_NONE";
+        case VK_CULL_MODE_FRONT_BIT:
+            return "VK_CULL_MODE_FRONT_BIT";
+        case VK_CULL_MODE_BACK_BIT:
+            return "VK_CULL_MODE_BACK_BIT";
+        case VK_CULL_MODE_FRONT_AND_BACK:
+            return "VK_CULL_MODE_FRONT_AND_BACK";
+        default:
+            return "VK_CULL_MODE_UNKNOWN";
+        }
+    }
+
+    static const char* CompareOpToString(VkCompareOp compareOp) {
+        switch (compareOp) {
+        ENUM_STR_CASE(VK_COMPARE_OP_NEVER)
+        ENUM_STR_CASE(VK_COMPARE_OP_LESS)
+        ENUM_STR_CASE(VK_COMPARE_OP_EQUAL)
+        ENUM_STR_CASE(VK_COMPARE_OP_LESS_OR_EQUAL)
+        ENUM_STR_CASE(VK_COMPARE_OP_GREATER)
+        ENUM_STR_CASE(VK_COMPARE_OP_NOT_EQUAL)
+        ENUM_STR_CASE(VK_COMPARE_OP_GREATER_OR_EQUAL)
+        ENUM_STR_CASE(VK_COMPARE_OP_ALWAYS)
+        default:
+            return "VK_COMPARE_OP_UNKNOWN";
+        }
+    }
+
+    static const char* LogicOpToString(VkLogicOp logicOp) {
+        switch (logicOp) {
+        ENUM_STR_CASE(VK_LOGIC_OP_CLEAR)
+        ENUM_STR_CASE(VK_LOGIC_OP_AND)
+        ENUM_STR_CASE(VK_LOGIC_OP_AND_REVERSE)
+        ENUM_STR_CASE(VK_LOGIC_OP_COPY)
+        ENUM_STR_CASE(VK_LOGIC_OP_AND_INVERTED)
+        ENUM_STR_CASE(VK_LOGIC_OP_NO_OP)
+        ENUM_STR_CASE(VK_LOGIC_OP_XOR)
+        ENUM_STR_CASE(VK_LOGIC_OP_OR)
+        ENUM_STR_CASE(VK_LOGIC_OP_NOR)
+        ENUM_STR_CASE(VK_LOGIC_OP_EQUIVALENT)
+        ENUM_STR_CASE(VK_LOGIC_OP_INVERT)
+        ENUM_STR_CASE(VK_LOGIC_OP_OR_REVERSE)
+        ENUM_STR_CASE(VK_LOGIC_OP_COPY_INVERTED)
+        ENUM_STR_CASE(VK_LOGIC_OP_OR_INVERTED)
+        ENUM_STR_CASE(VK_LOGIC_OP_NAND)
+        ENUM_STR_CASE(VK_LOGIC_OP_SET)
+        default:
+            return "VK_LOGIC_OP_UNKNOWN";
+        }
+    }
+
     PipelineFactory::PipelineFactory(VkDevice device, const VulkanRendererConfig& config):
         m_device(device), m_config(config) {
         MOBILEGL_ASSERT(m_device != VK_NULL_HANDLE, "PipelineFactory: device is null");
 
+        if (m_config.DisablePipelineCache) {
+            MGLOG_I("DirectVulkan: pipeline cache disabled");
+            return;
+        }
+
         VkPipelineCacheCreateInfo pipelineCacheInfo{VK_STRUCTURE_TYPE_PIPELINE_CACHE_CREATE_INFO};
         VK_VERIFY(vkCreatePipelineCache(m_device, &pipelineCacheInfo, nullptr, &m_pipelineCache),
                   "vkCreatePipelineCache");
@@ -33,13 +123,35 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         XXHASH_VERIFY(XXH64_update(m_hashState, &payload.pipelineLayout, sizeof(payload.pipelineLayout)));
         XXHASH_VERIFY(XXH64_update(m_hashState, &payload.renderPass, sizeof(payload.renderPass)));
         XXHASH_VERIFY(XXH64_update(m_hashState, &payload.colorAttachmentCount, sizeof(payload.colorAttachmentCount)));
+        XXHASH_VERIFY(XXH64_update(m_hashState, &payload.rasterizationSamples, sizeof(payload.rasterizationSamples)));
         XXHASH_VERIFY(XXH64_update(m_hashState, &payload.subpass, sizeof(payload.subpass)));
         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.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.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)));
+        XXHASH_VERIFY(
+            XXH64_update(m_hashState, &payload.rasterizerDiscardEnable, sizeof(payload.rasterizerDiscardEnable)));
+        XXHASH_VERIFY(XXH64_update(m_hashState, &payload.logicOpEnable, sizeof(payload.logicOpEnable)));
+        XXHASH_VERIFY(XXH64_update(m_hashState, &payload.stencilTestEnable, sizeof(payload.stencilTestEnable)));
         XXHASH_VERIFY(XXH64_update(m_hashState, &payload.depthCompareOp, sizeof(payload.depthCompareOp)));
+        XXHASH_VERIFY(XXH64_update(m_hashState, &payload.logicOp, sizeof(payload.logicOp)));
+        XXHASH_VERIFY(XXH64_update(m_hashState, &payload.frontStencilFailOp, sizeof(payload.frontStencilFailOp)));
+        XXHASH_VERIFY(XXH64_update(m_hashState, &payload.frontStencilPassOp, sizeof(payload.frontStencilPassOp)));
+        XXHASH_VERIFY(
+            XXH64_update(m_hashState, &payload.frontStencilDepthFailOp, sizeof(payload.frontStencilDepthFailOp)));
+        XXHASH_VERIFY(
+            XXH64_update(m_hashState, &payload.frontStencilCompareOp, sizeof(payload.frontStencilCompareOp)));
+        XXHASH_VERIFY(XXH64_update(m_hashState, &payload.backStencilFailOp, sizeof(payload.backStencilFailOp)));
+        XXHASH_VERIFY(XXH64_update(m_hashState, &payload.backStencilPassOp, sizeof(payload.backStencilPassOp)));
+        XXHASH_VERIFY(
+            XXH64_update(m_hashState, &payload.backStencilDepthFailOp, sizeof(payload.backStencilDepthFailOp)));
+        XXHASH_VERIFY(
+            XXH64_update(m_hashState, &payload.backStencilCompareOp, sizeof(payload.backStencilCompareOp)));
         if (payload.colorAttachmentCount > 0) {
             XXHASH_VERIFY(XXH64_update(
                 m_hashState,
@@ -86,7 +198,13 @@ namespace MobileGL::MG_Backend::DirectVulkan {
 
         static constexpr VkDynamicState kDynamicStates[] = {
             VK_DYNAMIC_STATE_VIEWPORT,
-            VK_DYNAMIC_STATE_SCISSOR
+            VK_DYNAMIC_STATE_SCISSOR,
+            VK_DYNAMIC_STATE_BLEND_CONSTANTS,
+            VK_DYNAMIC_STATE_DEPTH_BIAS,
+            VK_DYNAMIC_STATE_LINE_WIDTH,
+            VK_DYNAMIC_STATE_STENCIL_COMPARE_MASK,
+            VK_DYNAMIC_STATE_STENCIL_WRITE_MASK,
+            VK_DYNAMIC_STATE_STENCIL_REFERENCE
         };
 
         VkPipelineDynamicStateCreateInfo dynamicState{};
@@ -96,32 +214,53 @@ namespace MobileGL::MG_Backend::DirectVulkan {
 
         VkPipelineInputAssemblyStateCreateInfo ia{VK_STRUCTURE_TYPE_PIPELINE_INPUT_ASSEMBLY_STATE_CREATE_INFO};
         ia.topology = payload.topology;
+        ia.primitiveRestartEnable = payload.primitiveRestartEnable ? VK_TRUE : VK_FALSE;
 
         VkPipelineViewportStateCreateInfo vpci{VK_STRUCTURE_TYPE_PIPELINE_VIEWPORT_STATE_CREATE_INFO};
         vpci.viewportCount = 1;
         vpci.scissorCount = 1;
 
         VkPipelineRasterizationStateCreateInfo raster{VK_STRUCTURE_TYPE_PIPELINE_RASTERIZATION_STATE_CREATE_INFO};
-        raster.polygonMode = VK_POLYGON_MODE_FILL;
+        raster.polygonMode = payload.polygonMode;
         raster.cullMode = payload.cullMode;
         raster.frontFace = payload.frontFace;
+        raster.depthBiasEnable = payload.depthBiasEnable ? VK_TRUE : VK_FALSE;
+        raster.rasterizerDiscardEnable = payload.rasterizerDiscardEnable ? VK_TRUE : VK_FALSE;
         raster.lineWidth = 1.0f;
 
         VkPipelineMultisampleStateCreateInfo ms{VK_STRUCTURE_TYPE_PIPELINE_MULTISAMPLE_STATE_CREATE_INFO};
-        ms.rasterizationSamples = VK_SAMPLE_COUNT_1_BIT;
+        ms.rasterizationSamples = payload.rasterizationSamples;
 
         VkPipelineDepthStencilStateCreateInfo depthStencil{VK_STRUCTURE_TYPE_PIPELINE_DEPTH_STENCIL_STATE_CREATE_INFO};
         depthStencil.depthTestEnable = payload.depthTestEnable ? VK_TRUE : VK_FALSE;
         depthStencil.depthWriteEnable = payload.depthWriteEnable ? VK_TRUE : VK_FALSE;
         depthStencil.depthCompareOp = payload.depthCompareOp;
         depthStencil.depthBoundsTestEnable = VK_FALSE;
-        depthStencil.stencilTestEnable = VK_FALSE;
+        depthStencil.stencilTestEnable = payload.stencilTestEnable ? VK_TRUE : VK_FALSE;
+        if (payload.stencilTestEnable) {
+            depthStencil.front.failOp = payload.frontStencilFailOp;
+            depthStencil.front.passOp = payload.frontStencilPassOp;
+            depthStencil.front.depthFailOp = payload.frontStencilDepthFailOp;
+            depthStencil.front.compareOp = payload.frontStencilCompareOp;
+            depthStencil.front.compareMask = 0xffffffffu;
+            depthStencil.front.writeMask = 0xffffffffu;
+            depthStencil.front.reference = 0;
+            depthStencil.back.failOp = payload.backStencilFailOp;
+            depthStencil.back.passOp = payload.backStencilPassOp;
+            depthStencil.back.depthFailOp = payload.backStencilDepthFailOp;
+            depthStencil.back.compareOp = payload.backStencilCompareOp;
+            depthStencil.back.compareMask = 0xffffffffu;
+            depthStencil.back.writeMask = 0xffffffffu;
+            depthStencil.back.reference = 0;
+        }
 
         Vector<VkPipelineColorBlendAttachmentState> colorAttachments(payload.colorAttachmentCount);
         for (Uint32 i = 0; i < payload.colorAttachmentCount; ++i) {
             colorAttachments[i] = payload.colorBlendAttachments[i];
         }
         VkPipelineColorBlendStateCreateInfo blend{VK_STRUCTURE_TYPE_PIPELINE_COLOR_BLEND_STATE_CREATE_INFO};
+        blend.logicOpEnable = payload.logicOpEnable ? VK_TRUE : VK_FALSE;
+        blend.logicOp = payload.logicOp;
         blend.attachmentCount = payload.colorAttachmentCount;
         blend.pAttachments = colorAttachments.empty() ? nullptr : colorAttachments.data();
 
@@ -141,8 +280,52 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         gpi.subpass = payload.subpass;
 
         VkPipeline pipeline = VK_NULL_HANDLE;
-        VK_VERIFY(vkCreateGraphicsPipelines(m_device, m_pipelineCache, 1, &gpi, nullptr, &pipeline),
-                  "vkCreateGraphicsPipelines");
+        const VkResult result = vkCreateGraphicsPipelines(m_device, m_pipelineCache, 1, &gpi, nullptr, &pipeline);
+        if (result != VK_SUCCESS) {
+            MGLOG_F("PipelineFactory::CreatePipeline failed: result=%s (%d) programHash=0x%llx vertexInputHash=0x%llx stageCount=%u topology=%s(%d) colorAttachmentCount=%u samples=%s(%d) subpass=%u",
+                    VkResultToString(result),
+                    result,
+                    static_cast<unsigned long long>(payload.programHash),
+                    static_cast<unsigned long long>(payload.vertexInputHash),
+                    gpi.stageCount,
+                    PrimitiveTopologyToString(payload.topology),
+                    payload.topology,
+                    payload.colorAttachmentCount,
+                    SampleCountToString(payload.rasterizationSamples),
+                    payload.rasterizationSamples,
+                    payload.subpass);
+            MGLOG_F("PipelineFactory::CreatePipeline state: cullMode=%s(0x%x) frontFace=%d depthTest=%d depthWrite=%d depthCompare=%s(%d) depthBias=%d rasterizerDiscard=%d stencilTest=%d logicOpEnable=%d logicOp=%s(%d)",
+                    CullModeToString(payload.cullMode),
+                    static_cast<Uint32>(payload.cullMode),
+                    payload.frontFace,
+                    payload.depthTestEnable ? 1 : 0,
+                    payload.depthWriteEnable ? 1 : 0,
+                    CompareOpToString(payload.depthCompareOp),
+                    payload.depthCompareOp,
+                    payload.depthBiasEnable ? 1 : 0,
+                    payload.rasterizerDiscardEnable ? 1 : 0,
+                    payload.stencilTestEnable ? 1 : 0,
+                    payload.logicOpEnable ? 1 : 0,
+                    LogicOpToString(payload.logicOp),
+                    payload.logicOp);
+            MGLOG_F("PipelineFactory::CreatePipeline vertex input: bindingCount=%u attributeCount=%u",
+                    payload.vertexInputState->vertexBindingDescriptionCount,
+                    payload.vertexInputState->vertexAttributeDescriptionCount);
+            for (Uint32 i = 0; i < payload.colorAttachmentCount; ++i) {
+                const auto& attachment = payload.colorBlendAttachments[i];
+                MGLOG_F("PipelineFactory::CreatePipeline colorAttachment[%u]: blend=%d colorWriteMask=0x%x srcColor=%d dstColor=%d colorOp=%d srcAlpha=%d dstAlpha=%d alphaOp=%d",
+                        i,
+                        attachment.blendEnable == VK_TRUE ? 1 : 0,
+                        static_cast<Uint32>(attachment.colorWriteMask),
+                        attachment.srcColorBlendFactor,
+                        attachment.dstColorBlendFactor,
+                        attachment.colorBlendOp,
+                        attachment.srcAlphaBlendFactor,
+                        attachment.dstAlphaBlendFactor,
+                        attachment.alphaBlendOp);
+            }
+        }
+        VK_VERIFY(result, "vkCreateGraphicsPipelines");
         return pipeline;
     }
 } // namespace MobileGL::MG_Backend::DirectVulkan

MobileGL/MG_Backend/DirectVulkan/Renderer/PipelineFactory.h

@@ -26,13 +26,29 @@ namespace MobileGL::MG_Backend::DirectVulkan {
             VkPipelineLayout pipelineLayout = VK_NULL_HANDLE;
             VkRenderPass renderPass = VK_NULL_HANDLE;
             Uint32 colorAttachmentCount = 1;
+            VkSampleCountFlagBits rasterizationSamples = VK_SAMPLE_COUNT_1_BIT;
             Uint32 subpass = 0;
             VkPrimitiveTopology topology = VK_PRIMITIVE_TOPOLOGY_TRIANGLE_LIST;
+            Bool primitiveRestartEnable = false;
+            VkPolygonMode polygonMode = VK_POLYGON_MODE_FILL;
             VkCullModeFlags cullMode = VK_CULL_MODE_BACK_BIT;
             VkFrontFace frontFace = VK_FRONT_FACE_CLOCKWISE;
             Bool depthTestEnable = false;
             Bool depthWriteEnable = false;
+            Bool depthBiasEnable = false;
+            Bool rasterizerDiscardEnable = false;
+            Bool logicOpEnable = false;
+            Bool stencilTestEnable = false;
             VkCompareOp depthCompareOp = VK_COMPARE_OP_ALWAYS;
+            VkLogicOp logicOp = VK_LOGIC_OP_COPY;
+            VkStencilOp frontStencilFailOp = VK_STENCIL_OP_KEEP;
+            VkStencilOp frontStencilPassOp = VK_STENCIL_OP_KEEP;
+            VkStencilOp frontStencilDepthFailOp = VK_STENCIL_OP_KEEP;
+            VkCompareOp frontStencilCompareOp = VK_COMPARE_OP_ALWAYS;
+            VkStencilOp backStencilFailOp = VK_STENCIL_OP_KEEP;
+            VkStencilOp backStencilPassOp = VK_STENCIL_OP_KEEP;
+            VkStencilOp backStencilDepthFailOp = VK_STENCIL_OP_KEEP;
+            VkCompareOp backStencilCompareOp = VK_COMPARE_OP_ALWAYS;
             Array<VkPipelineColorBlendAttachmentState, kMaxColorAttachments> colorBlendAttachments{};
             const Vector<VkPipelineShaderStageCreateInfo>* stages = nullptr;
             const VkPipelineVertexInputStateCreateInfo* vertexInputState = nullptr;

MobileGL/MG_Backend/DirectVulkan/Renderer/ProgramFactory.cpp

@@ -9,6 +9,7 @@
 #include "ProgramFactory.h"
 
 #include "MG_Backend/DirectVulkan/DirectVulkanResourceState.h"
+#include "MG_Util/ShaderTranspiler/ShaderCompiler.h"
 #include "MG_Util/ShaderTranspiler/SpvcSession.h"
 #include "MG_Util/ShaderTranspiler/Types.h"
 #include <cstring>
@@ -311,6 +312,34 @@ namespace MobileGL::MG_Backend::DirectVulkan {
             return targetEnv;
         }
 
+        // Cheap raw-word scan for an `OpDecorate <id> BuiltIn InstanceIndex` decoration. Used
+        // only to decide whether to warn when shaderDrawParameters is unavailable; a false
+        // negative merely suppresses a diagnostic.
+        Bool SpirvDeclaresInstanceIndexBuiltin(const Vector<Uint>& spirv) {
+            constexpr Uint32 kSpirvMagicNumber = 0x07230203u;
+            constexpr SizeT kHeaderWordCount = 5;
+            if (spirv.size() <= kHeaderWordCount || spirv[0] != kSpirvMagicNumber) {
+                return false;
+            }
+
+            SizeT wordIndex = kHeaderWordCount;
+            while (wordIndex < spirv.size()) {
+                const Uint32 firstWord = spirv[wordIndex];
+                const Uint32 wordCount = firstWord >> 16;
+                const auto opcode = static_cast<spv::Op>(firstWord & 0xffffu);
+                if (wordCount == 0 || wordIndex + wordCount > spirv.size()) {
+                    break;
+                }
+                if (opcode == spv::Op::OpDecorate && wordCount >= 4 &&
+                    static_cast<spv::Decoration>(spirv[wordIndex + 2]) == spv::Decoration::BuiltIn &&
+                    static_cast<spv::BuiltIn>(spirv[wordIndex + 3]) == spv::BuiltIn::InstanceIndex) {
+                    return true;
+                }
+                wordIndex += wordCount;
+            }
+            return false;
+        }
+
         Bool IsInterfaceVariableStaticallyUsed(const Vector<Uint>& spirv, Uint32 spirvId) {
             if (spirv.empty() || spirvId == 0) {
                 return false;
@@ -1168,6 +1197,25 @@ namespace MobileGL::MG_Backend::DirectVulkan {
                 return TextureTarget::Unknown;
             }
         }
+
+        Bool IsFloatStorageImageUniformType(GLenum uniformType) {
+            switch (uniformType) {
+            case GL_IMAGE_1D:
+            case GL_IMAGE_2D:
+            case GL_IMAGE_3D:
+            case GL_IMAGE_2D_RECT:
+            case GL_IMAGE_CUBE:
+            case GL_IMAGE_BUFFER:
+            case GL_IMAGE_1D_ARRAY:
+            case GL_IMAGE_2D_ARRAY:
+            case GL_IMAGE_CUBE_MAP_ARRAY:
+            case GL_IMAGE_2D_MULTISAMPLE:
+            case GL_IMAGE_2D_MULTISAMPLE_ARRAY:
+                return true;
+            default:
+                return false;
+            }
+        }
     } // namespace
 
     VkShaderStageFlagBits ProgramFactory::ToVkStage(ShaderStage stage) {
@@ -1189,6 +1237,105 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         }
     }
 
+    VkFormat ProgramFactory::ConvertSpirvImageFormatToVkFormat(SpvImageFormat format) {
+        switch (format) {
+        case SpvImageFormatUnknown: return VK_FORMAT_UNDEFINED;
+        case SpvImageFormatRgba32f: return VK_FORMAT_R32G32B32A32_SFLOAT;
+        case SpvImageFormatRgba16f: return VK_FORMAT_R16G16B16A16_SFLOAT;
+        case SpvImageFormatR32f: return VK_FORMAT_R32_SFLOAT;
+        case SpvImageFormatRgba8: return VK_FORMAT_R8G8B8A8_UNORM;
+        case SpvImageFormatRgba8Snorm: return VK_FORMAT_R8G8B8A8_SNORM;
+        case SpvImageFormatRg32f: return VK_FORMAT_R32G32_SFLOAT;
+        case SpvImageFormatRg16f: return VK_FORMAT_R16G16_SFLOAT;
+        case SpvImageFormatR11fG11fB10f: return VK_FORMAT_B10G11R11_UFLOAT_PACK32;
+        case SpvImageFormatR16f: return VK_FORMAT_R16_SFLOAT;
+        case SpvImageFormatRgba16: return VK_FORMAT_R16G16B16A16_UNORM;
+        case SpvImageFormatRgb10A2: return VK_FORMAT_A2R10G10B10_UNORM_PACK32;
+        case SpvImageFormatRg16: return VK_FORMAT_R16G16_UNORM;
+        case SpvImageFormatRg8: return VK_FORMAT_R8G8_UNORM;
+        case SpvImageFormatR16: return VK_FORMAT_R16_UNORM;
+        case SpvImageFormatR8: return VK_FORMAT_R8_UNORM;
+        case SpvImageFormatRgba16Snorm: return VK_FORMAT_R16G16B16A16_SNORM;
+        case SpvImageFormatRg16Snorm: return VK_FORMAT_R16G16_SNORM;
+        case SpvImageFormatRg8Snorm: return VK_FORMAT_R8G8_SNORM;
+        case SpvImageFormatR16Snorm: return VK_FORMAT_R16_SNORM;
+        case SpvImageFormatR8Snorm: return VK_FORMAT_R8_SNORM;
+        case SpvImageFormatRgba32i: return VK_FORMAT_R32G32B32A32_SINT;
+        case SpvImageFormatRgba16i: return VK_FORMAT_R16G16B16A16_SINT;
+        case SpvImageFormatRgba8i: return VK_FORMAT_R8G8B8A8_SINT;
+        case SpvImageFormatR32i: return VK_FORMAT_R32_SINT;
+        case SpvImageFormatRg32i: return VK_FORMAT_R32G32_SINT;
+        case SpvImageFormatRg16i: return VK_FORMAT_R16G16_SINT;
+        case SpvImageFormatRg8i: return VK_FORMAT_R8G8_SINT;
+        case SpvImageFormatR16i: return VK_FORMAT_R16_SINT;
+        case SpvImageFormatR8i: return VK_FORMAT_R8_SINT;
+        case SpvImageFormatRgba32ui: return VK_FORMAT_R32G32B32A32_UINT;
+        case SpvImageFormatRgba16ui: return VK_FORMAT_R16G16B16A16_UINT;
+        case SpvImageFormatRgba8ui: return VK_FORMAT_R8G8B8A8_UINT;
+        case SpvImageFormatR32ui: return VK_FORMAT_R32_UINT;
+        case SpvImageFormatRgb10a2ui: return VK_FORMAT_A2R10G10B10_UINT_PACK32;
+        case SpvImageFormatRg32ui: return VK_FORMAT_R32G32_UINT;
+        case SpvImageFormatRg16ui: return VK_FORMAT_R16G16_UINT;
+        case SpvImageFormatRg8ui: return VK_FORMAT_R8G8_UINT;
+        case SpvImageFormatR16ui: return VK_FORMAT_R16_UINT;
+        case SpvImageFormatR8ui: return VK_FORMAT_R8_UINT;
+        case SpvImageFormatR64ui: return VK_FORMAT_R64_UINT;
+        case SpvImageFormatR64i: return VK_FORMAT_R64_SINT;
+        case SpvImageFormatMax: return VK_FORMAT_UNDEFINED;
+        }
+        return VK_FORMAT_UNDEFINED;
+    }
+
+    SamplerNumericDomain ProgramFactory::UniformTypeToSamplerNumericDomain(GLenum glType) {
+        switch (glType) {
+        case GL_INT_SAMPLER_1D:
+        case GL_INT_SAMPLER_2D:
+        case GL_INT_SAMPLER_3D:
+        case GL_INT_SAMPLER_CUBE:
+        case GL_INT_SAMPLER_2D_RECT:
+        case GL_INT_SAMPLER_1D_ARRAY:
+        case GL_INT_SAMPLER_2D_ARRAY:
+        case GL_INT_SAMPLER_BUFFER:
+        case GL_INT_SAMPLER_2D_MULTISAMPLE:
+        case GL_INT_SAMPLER_2D_MULTISAMPLE_ARRAY:
+        case GL_INT_SAMPLER_CUBE_MAP_ARRAY:
+            return SamplerNumericDomain::SignedInteger;
+        case GL_UNSIGNED_INT_SAMPLER_1D:
+        case GL_UNSIGNED_INT_SAMPLER_2D:
+        case GL_UNSIGNED_INT_SAMPLER_3D:
+        case GL_UNSIGNED_INT_SAMPLER_CUBE:
+        case GL_UNSIGNED_INT_SAMPLER_2D_RECT:
+        case GL_UNSIGNED_INT_SAMPLER_1D_ARRAY:
+        case GL_UNSIGNED_INT_SAMPLER_2D_ARRAY:
+        case GL_UNSIGNED_INT_SAMPLER_BUFFER:
+        case GL_UNSIGNED_INT_SAMPLER_2D_MULTISAMPLE:
+        case GL_UNSIGNED_INT_SAMPLER_2D_MULTISAMPLE_ARRAY:
+        case GL_UNSIGNED_INT_SAMPLER_CUBE_MAP_ARRAY:
+            return SamplerNumericDomain::UnsignedInteger;
+        case GL_SAMPLER_1D:
+        case GL_SAMPLER_2D:
+        case GL_SAMPLER_3D:
+        case GL_SAMPLER_CUBE:
+        case GL_SAMPLER_2D_RECT:
+        case GL_SAMPLER_1D_ARRAY:
+        case GL_SAMPLER_2D_ARRAY:
+        case GL_SAMPLER_BUFFER:
+        case GL_SAMPLER_2D_MULTISAMPLE:
+        case GL_SAMPLER_2D_MULTISAMPLE_ARRAY:
+        case GL_SAMPLER_CUBE_MAP_ARRAY:
+        case GL_SAMPLER_1D_SHADOW:
+        case GL_SAMPLER_2D_SHADOW:
+        case GL_SAMPLER_CUBE_SHADOW:
+        case GL_SAMPLER_2D_RECT_SHADOW:
+        case GL_SAMPLER_1D_ARRAY_SHADOW:
+        case GL_SAMPLER_2D_ARRAY_SHADOW:
+        case GL_SAMPLER_CUBE_MAP_ARRAY_SHADOW:
+            return SamplerNumericDomain::Float;
+        default:
+            return SamplerNumericDomain::Unknown;
+        }
+    }
+
     ProgramFactory::HashType ProgramFactory::ComputeHash(const MG_State::GLState::ProgramObject& program,
                                                          CompileOptionFlags flags) const {
         XXHASH_VERIFY(XXH64_reset(m_hashState, m_config.CacheVersion));
@@ -1436,6 +1583,9 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         entry.samplerNameByBinding.assign(m_maxBindings, String());
         entry.samplerUniformLocationByBinding.assign(m_maxBindings, -1);
         entry.samplerTextureTargetByBinding.assign(m_maxBindings, TextureTarget::Texture2D);
+        entry.samplerNumericDomainByBinding.assign(m_maxBindings, SamplerNumericDomain::Unknown);
+        entry.storageImageFormatByBinding.assign(m_maxBindings, VK_FORMAT_UNDEFINED);
+        entry.storageImageUsesBindingFormatByBinding.assign(m_maxBindings, false);
         entry.storageBlockNameByBinding.assign(m_maxBindings, String());
         entry.storageBlockIndexByBinding.assign(m_maxBindings, -1);
         entry.globalUboBinding = -1;
@@ -1563,10 +1713,54 @@ namespace MobileGL::MG_Backend::DirectVulkan {
                     continue;
                 }
 
-                const TextureTarget target = UniformTypeToTextureTarget(program.GetUniformType(static_cast<Uint>(location)));
+                const GLenum uniformType = program.GetUniformType(static_cast<Uint>(location));
+
+                if (descriptorKind == DescriptorBindingKind::StorageImage) {
+                    const VkFormat reflectedFormat =
+                        ConvertSpirvImageFormatToVkFormat(sampler->image.image_format);
+                    VkFormat& existingFormat = entry.storageImageFormatByBinding[binding];
+                    MOBILEGL_ASSERT(existingFormat == VK_FORMAT_UNDEFINED ||
+                                        reflectedFormat == VK_FORMAT_UNDEFINED ||
+                                        existingFormat == reflectedFormat,
+                                    "ProgramFactory::ReflectLayout: storage image binding %u ('%s') has "
+                                    "conflicting reflected formats (%d vs %d)",
+                                    binding, uniformName.c_str(), static_cast<Int>(existingFormat),
+                                    static_cast<Int>(reflectedFormat));
+                    if (existingFormat == VK_FORMAT_UNDEFINED) {
+                        existingFormat = reflectedFormat;
+                    }
+                    if (m_unformattedFloatStorageImagesEnabled &&
+                        existingFormat == VK_FORMAT_UNDEFINED &&
+                        IsFloatStorageImageUniformType(uniformType)) {
+                        entry.storageImageUsesBindingFormatByBinding[binding] = true;
+                    } else if (reflectedFormat != VK_FORMAT_UNDEFINED) {
+                        // A typed declaration in any stage wins for the entire binding. This is
+                        // required when another stage reaches the same image through an atomic
+                        // path and therefore could not be made formatless.
+                        entry.storageImageUsesBindingFormatByBinding[binding] = false;
+                    }
+                }
+
+                const TextureTarget target = UniformTypeToTextureTarget(uniformType);
                 MOBILEGL_ASSERT(target != TextureTarget::Unknown,
                                 "ProgramFactory::ReflectLayout: failed to resolve texture target for '%s'",
                                 uniformName.c_str());
+                if (descriptorKind == DescriptorBindingKind::CombinedImageSampler) {
+                    const SamplerNumericDomain numericDomain = UniformTypeToSamplerNumericDomain(uniformType);
+                    MOBILEGL_ASSERT(numericDomain != SamplerNumericDomain::Unknown,
+                                    "ProgramFactory::ReflectLayout: failed to resolve sampler numeric domain "
+                                    "for '%s' (uniformType=0x%x)",
+                                    uniformName.c_str(), uniformType);
+                    MOBILEGL_ASSERT(entry.samplerNumericDomainByBinding[binding] ==
+                                            SamplerNumericDomain::Unknown ||
+                                        entry.samplerNumericDomainByBinding[binding] == numericDomain,
+                                    "ProgramFactory::ReflectLayout: sampler binding %u ('%s') has conflicting "
+                                    "numeric domains (%d vs %d)",
+                                    binding, uniformName.c_str(),
+                                    static_cast<Int>(entry.samplerNumericDomainByBinding[binding]),
+                                    static_cast<Int>(numericDomain));
+                    entry.samplerNumericDomainByBinding[binding] = numericDomain;
+                }
                 MOBILEGL_ASSERT(entry.samplerUniformLocationByBinding[binding] < 0 || location < 0 ||
                                     entry.samplerUniformLocationByBinding[binding] == location,
                                 "ProgramFactory::ReflectLayout: texture binding %u maps to conflicting uniform locations (%d vs %d)",
@@ -1637,7 +1831,13 @@ namespace MobileGL::MG_Backend::DirectVulkan {
 
     const ProgramFactory::VkProgramObject& ProgramFactory::GetOrCreateProgram(
         const MG_State::GLState::ProgramObject& program, CompileOptionFlags flags) {
-        const HashType hash = ComputeHash(program, flags);
+        // Hashing the full SPIR-V of every stage is far too expensive to repeat per draw;
+        // reuse the program's memoized hash while its backend state version is unchanged.
+        HashType hash = 0;
+        if (!program.GetBackendHashMemo(flags.GetRaw(), hash)) {
+            hash = ComputeHash(program, flags);
+            program.SetBackendHashMemo(flags.GetRaw(), hash);
+        }
         auto it = m_cache.find(hash);
         if (it != m_cache.end()) {
             return it->second;
@@ -1661,6 +1861,48 @@ namespace MobileGL::MG_Backend::DirectVulkan {
             } else {
                 moduleSpirvs[i] = spv;
             }
+
+            // glslang's relaxed-Vulkan mode aliases GL's zero-based gl_InstanceID to Vulkan's
+            // gl_InstanceIndex, which wrongly includes the draw's baseInstance. Rebase vertex-stage
+            // loads to (InstanceIndex - BaseInstance) so shaders observe GL semantics. Reflection
+            // below runs on the rebased words so the added BaseInstance builtin stays consistent.
+            if (shaders[i] && shaders[i]->GetShaderStage() == ShaderStage::Vertex) {
+                if (m_shaderDrawParametersEnabled) {
+                    Vector<Uint> rebasedSpirv;
+                    if (MG_Util::ShaderTranspiler::ShaderCompiler::RebaseInstanceIndexForVulkan(moduleSpirvs[i],
+                                                                                               rebasedSpirv)) {
+                        moduleSpirvs[i] = std::move(rebasedSpirv);
+                    } else {
+                        MGLOG_E("ProgramFactory: failed to rebase gl_InstanceID for program %u; "
+                                "instanced draws with a non-zero baseInstance may render incorrectly",
+                                program.GetExternalIndex());
+                    }
+                } else if (SpirvDeclaresInstanceIndexBuiltin(moduleSpirvs[i])) {
+                    static Bool s_warnedInstanceIndexUnsupported = false;
+                    if (!s_warnedInstanceIndexUnsupported) {
+                        s_warnedInstanceIndexUnsupported = true;
+                        MGLOG_W("ProgramFactory: shaderDrawParameters is unavailable; gl_InstanceID cannot be "
+                                "rebased and instanced draws with a non-zero baseInstance may render incorrectly");
+                    }
+                }
+            }
+
+            // When Vulkan can legally access storage images without a statically declared
+            // format, let GL's glBindImageTexture format select the runtime image view. This
+            // provides desktop-driver-compatible behavior for packs such as iterationRP, whose
+            // float image qualifier can disagree with the bound render-target format. Integer
+            // storage images remain formatted so r32ui/r32i bit-reinterpretation paths keep the
+            // exact descriptor format required by their shader operations.
+            if (m_unformattedFloatStorageImagesEnabled) {
+                Vector<Uint> unformattedSpirv;
+                if (MG_Util::ShaderTranspiler::ShaderCompiler::UseUnformattedFloatStorageImagesForVulkan(
+                        moduleSpirvs[i], unformattedSpirv)) {
+                    moduleSpirvs[i] = std::move(unformattedSpirv);
+                } else {
+                    MGLOG_E("ProgramFactory: failed to make float storage images unformatted for program %u",
+                            program.GetExternalIndex());
+                }
+            }
         }
 
         const Bool remapOk = RemapDescriptorBindingsForVulkan(moduleSpirvs, m_maxBindings, moduleSpirvs);

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 {
@@ -54,6 +62,9 @@ namespace MobileGL::MG_Backend::DirectVulkan {
             Vector<String> samplerNameByBinding;
             Vector<Int> samplerUniformLocationByBinding;
             Vector<TextureTarget> samplerTextureTargetByBinding;
+            Vector<SamplerNumericDomain> samplerNumericDomainByBinding;
+            Vector<VkFormat> storageImageFormatByBinding;
+            Vector<Bool> storageImageUsesBindingFormatByBinding;
             Vector<String> storageBlockNameByBinding;
             Vector<Int> storageBlockIndexByBinding;
             Int globalUboBinding = -1;
@@ -82,6 +93,10 @@ namespace MobileGL::MG_Backend::DirectVulkan {
                 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);
                 globalUboBinding = other.globalUboBinding;
@@ -118,6 +133,10 @@ namespace MobileGL::MG_Backend::DirectVulkan {
                 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);
                 globalUboBinding = other.globalUboBinding;
@@ -166,8 +185,12 @@ namespace MobileGL::MG_Backend::DirectVulkan {
             }
         };
 
-        explicit ProgramFactory(VkDevice device, const VulkanRendererConfig& config, Uint32 maxBindings = 16)
-            : m_device(device), m_config(config), m_maxBindings(maxBindings) {
+        explicit ProgramFactory(VkDevice device, const VulkanRendererConfig& config, Uint32 maxBindings = 16,
+                                Bool shaderDrawParametersEnabled = false,
+                                Bool unformattedFloatStorageImagesEnabled = false)
+            : m_device(device), m_maxBindings(maxBindings), m_config(config),
+              m_shaderDrawParametersEnabled(shaderDrawParametersEnabled),
+              m_unformattedFloatStorageImagesEnabled(unformattedFloatStorageImagesEnabled) {
             VkProgramObject::s_device = device;
         }
         ~ProgramFactory() = default;
@@ -178,6 +201,8 @@ namespace MobileGL::MG_Backend::DirectVulkan {
             const MG_State::GLState::ProgramObject& program, CompileOptionFlags flags);
 
         static VkShaderStageFlagBits ToVkStage(ShaderStage stage);
+        static VkFormat ConvertSpirvImageFormatToVkFormat(SpvImageFormat format);
+        static SamplerNumericDomain UniformTypeToSamplerNumericDomain(GLenum glType);
 
     private:
         struct ProgramLookupCache {
@@ -201,6 +226,12 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         Uint32 m_maxBindings = 0;
         UnorderedMap<HashType, VkProgramObject> m_cache;
         const VulkanRendererConfig& m_config;
+        // 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;
         static inline XXH64_state_t* m_hashState = XXH64_createState();
     };

MobileGL/MG_Backend/DirectVulkan/Renderer/SwapchainObject.cpp

@@ -31,8 +31,19 @@ static const char* string_VkColorSpaceKHR(VkColorSpaceKHR) {
     return "VkColorSpaceKHR(unknown)";
 }
 
-static const char* string_VkPresentModeKHR(VkPresentModeKHR) {
-    return "VkPresentModeKHR(unknown)";
+static const char* string_VkPresentModeKHR(VkPresentModeKHR presentMode) {
+    switch (presentMode) {
+    case VK_PRESENT_MODE_IMMEDIATE_KHR:
+        return "VK_PRESENT_MODE_IMMEDIATE_KHR";
+    case VK_PRESENT_MODE_MAILBOX_KHR:
+        return "VK_PRESENT_MODE_MAILBOX_KHR";
+    case VK_PRESENT_MODE_FIFO_KHR:
+        return "VK_PRESENT_MODE_FIFO_KHR";
+    case VK_PRESENT_MODE_FIFO_RELAXED_KHR:
+        return "VK_PRESENT_MODE_FIFO_RELAXED_KHR";
+    default:
+        return "VkPresentModeKHR(unknown)";
+    }
 }
 
 static const char* string_VkSurfaceTransformFlagBitsKHR(VkSurfaceTransformFlagBitsKHR) {
@@ -105,7 +116,15 @@ namespace MobileGL::MG_Backend::DirectVulkan {
     VkSurfaceFormatKHR SwapchainObject::ChooseSwapchainSurfaceFormat(
         const Vector<VkSurfaceFormatKHR>& availableFormats) {
         for (const auto& availableFormat : availableFormats) {
-            if (availableFormat.format == VK_FORMAT_B8G8R8A8_SRGB &&
+            if ((availableFormat.format == VK_FORMAT_B8G8R8A8_UNORM ||
+                 availableFormat.format == VK_FORMAT_R8G8B8A8_UNORM) &&
+                availableFormat.colorSpace == VK_COLOR_SPACE_SRGB_NONLINEAR_KHR) {
+                return availableFormat;
+            }
+        }
+        for (const auto& availableFormat : availableFormats) {
+            if ((availableFormat.format == VK_FORMAT_B8G8R8A8_SRGB ||
+                 availableFormat.format == VK_FORMAT_R8G8B8A8_SRGB) &&
                 availableFormat.colorSpace == VK_COLOR_SPACE_SRGB_NONLINEAR_KHR) {
                 return availableFormat;
             }
@@ -130,7 +149,8 @@ namespace MobileGL::MG_Backend::DirectVulkan {
     }
 
     void SwapchainObject::Create(VkDevice device, VkPhysicalDevice physicalDevice, VkSurfaceKHR surface,
-                                 Uint32 graphicsQueueFamily, Uint32 presentQueueFamily, Uint32 minImageCountHint) {
+                                 Uint32 graphicsQueueFamily, Uint32 presentQueueFamily, Uint32 minImageCountHint,
+                                 VkExtent2D desiredExtent) {
         const auto swapchainCapabilities = GetSwapchainCapabilities(physicalDevice, surface);
         MOBILEGL_ASSERT(swapchainCapabilities.IsComplete(),
                         "SwapchainObject::Create failed: incomplete swapchain capabilities");
@@ -153,7 +173,10 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         MGLOG_I("Picked present mode: %s", string_VkPresentModeKHR(presentMode));
 
         const auto& swapchainCaps = swapchainCapabilities.capabilities;
-        const auto targetImageCount = std::max<Uint32>(minImageCountHint, swapchainCaps.minImageCount);
+        Uint32 targetImageCount = std::max<Uint32>(minImageCountHint, swapchainCaps.minImageCount);
+        if (swapchainCaps.maxImageCount != 0) {
+            targetImageCount = std::min(targetImageCount, swapchainCaps.maxImageCount);
+        }
         MGLOG_I("Set minImageCount = %u", targetImageCount);
         MGLOG_I("Swapchain currentTransform = %s",
                 string_VkSurfaceTransformFlagBitsKHR(swapchainCaps.currentTransform));
@@ -164,6 +187,15 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         createInfo.imageFormat = pickedSurfaceFormat.format;
         createInfo.imageColorSpace = pickedSurfaceFormat.colorSpace;
         createInfo.imageExtent = swapchainCaps.currentExtent;
+        if (createInfo.imageExtent.width == UINT32_MAX || createInfo.imageExtent.height == UINT32_MAX) {
+            createInfo.imageExtent.width = std::clamp(desiredExtent.width,
+                                                      swapchainCaps.minImageExtent.width,
+                                                      swapchainCaps.maxImageExtent.width);
+            createInfo.imageExtent.height = std::clamp(desiredExtent.height,
+                                                       swapchainCaps.minImageExtent.height,
+                                                       swapchainCaps.maxImageExtent.height);
+        }
+        const VkExtent2D defaultFramebufferExtent = createInfo.imageExtent;
         if (swapchainCaps.currentTransform == VK_SURFACE_TRANSFORM_ROTATE_90_BIT_KHR ||
             swapchainCaps.currentTransform == VK_SURFACE_TRANSFORM_ROTATE_270_BIT_KHR) {
             std::swap(createInfo.imageExtent.width, createInfo.imageExtent.height);
@@ -234,11 +266,17 @@ namespace MobileGL::MG_Backend::DirectVulkan {
 
         // Properly initialize Default FBO here
         auto& defaultFBOInfo = MG_Impl::GLImpl::FramebufferImpl::pDefaultFramebufferInfo;
+        const Int extentWidth = static_cast<Int>(defaultFramebufferExtent.width);
+        const Int extentHeight = static_cast<Int>(defaultFramebufferExtent.height);
+        const SizeT defaultAttachmentByteSize =
+            static_cast<SizeT>(defaultFramebufferExtent.width) *
+            static_cast<SizeT>(defaultFramebufferExtent.height) * 4;
+
         auto* colorTex = static_cast<MG_State::GLState::TextureObject2D*>(defaultFBOInfo->colorAttachment.get());
         colorTex->AllocateStorage(
             TextureUploadTarget::Texture2D, 0, {
-                {(Int)createInfo.imageExtent.width, (Int)createInfo.imageExtent.height, 1},
-                createInfo.imageExtent.width * (Int)createInfo.imageExtent.height * 4}); // TODO: 4 is format size
+                {extentWidth, extentHeight, 1},
+                defaultAttachmentByteSize}); // TODO: 4 is format size
         TextureInternalFormat depthFormat = TextureInternalFormat::Depth24Stencil8;
         switch (m_depthStencilFormat) {
             case VK_FORMAT_D24_UNORM_S8_UINT:
@@ -257,8 +295,32 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         auto* depthTex = static_cast<MG_State::GLState::TextureObject2D*>(defaultFBOInfo->depthAttachment.get());
         depthTex->SetInternalFormat(depthFormat);
         depthTex->AllocateStorage(TextureUploadTarget::Texture2D, 0, {
-            {(Int)createInfo.imageExtent.width, (Int)createInfo.imageExtent.height, 1},
-                        createInfo.imageExtent.width * createInfo.imageExtent.width * 4}); // TODO: 4 is format size
+            {extentWidth, extentHeight, 1},
+            defaultAttachmentByteSize}); // TODO: 4 is format size
+
+        // The default FBO's stencil attachment must track the swapchain extent:
+        // FramebufferObject::CheckCompleteness requires every valid attachment
+        // to share the same dimensions, and Init.cpp leaves a 512x512 placeholder.
+        // Without this the retrace-layer glReadPixels snapshot fails with
+        // GL_INVALID_FRAMEBUFFER_OPERATION on DirectVulkan.
+        TextureInternalFormat stencilFormat = TextureInternalFormat::Depth24Stencil8;
+        switch (m_depthStencilFormat) {
+            case VK_FORMAT_D32_SFLOAT_S8_UINT:
+                stencilFormat = TextureInternalFormat::Depth32FStencil8;
+                break;
+            case VK_FORMAT_D24_UNORM_S8_UINT:
+                stencilFormat = TextureInternalFormat::Depth24Stencil8;
+                break;
+            default:
+                // No stencil plane; mirror the depth format for consistency.
+                stencilFormat = depthFormat;
+                break;
+        }
+        auto* stencilTex = static_cast<MG_State::GLState::TextureObject2D*>(defaultFBOInfo->stencilAttachment.get());
+        stencilTex->SetInternalFormat(stencilFormat);
+        stencilTex->AllocateStorage(TextureUploadTarget::Texture2D, 0, {
+            {extentWidth, extentHeight, 1},
+            defaultAttachmentByteSize}); // TODO: 4 is format size
 
     }
 

MobileGL/MG_Backend/DirectVulkan/Renderer/SwapchainObject.h

@@ -29,7 +29,7 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         static VkPresentModeKHR ChooseSwapchainPresentMode(const Vector<VkPresentModeKHR>& availablePresentModes);
 
         void Create(VkDevice device, VkPhysicalDevice physicalDevice, VkSurfaceKHR surface, Uint32 graphicsQueueFamily,
-                    Uint32 presentQueueFamily, Uint32 minImageCountHint);
+                    Uint32 presentQueueFamily, Uint32 minImageCountHint, VkExtent2D desiredExtent);
         void Shutdown(VkDevice device);
 
         VkSwapchainKHR GetHandle() const { return m_swapchain; }

MobileGL/MG_Backend/DirectVulkan/Renderer/UniformManager.cpp

@@ -13,9 +13,11 @@
 #include "MG_State/GLState/ProgramState/ProgramObject.h"
 #include "MG_State/GLState/TextureState/TextureObject2D.h"
 #include "MG_State/GLState/TextureState/TextureObjectBuffer.h"
+#include "MG_Util/Converters/GLToMG/TextureEnumConverter.h"
 #include "MG_Util/Converters/MGToStr/FramebufferEnumConverter.h"
 #include "MG_Util/Converters/MGToVk/TextureEnumConverter.h"
 #include "MG_Util/Metrics/TextureMetrics.h"
+#include <Config.h>
 #include <cstdio>
 #include <cstdlib>
 #include <cstring>
@@ -77,12 +79,14 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         return uniformUnit >= 0 ? uniformUnit : 0;
     }
 
-    static Bool ShouldDumpDescriptorStats() {
-        static const Bool enabled = [] {
-            const char* value = std::getenv("MOBILEGL_DESCRIPTOR_STATS");
-            return value != nullptr && value[0] != '\0' && std::strcmp(value, "0") != 0;
-        }();
-        return enabled;
+    VkFormat UniformManager::ResolveStorageImageViewFormat(VkFormat reflectedFormat, GLenum bindingFormat,
+                                                           VkFormat resourceFormat, Bool useBindingFormat) {
+        if (useBindingFormat) {
+            const TextureInternalFormat bindingInternalFormat =
+                MG_Util::ConvertGLEnumToTextureInternalFormat(bindingFormat);
+            return MG_Util::ConvertTextureInternalFormatToVkEnum(bindingInternalFormat);
+        }
+        return reflectedFormat != VK_FORMAT_UNDEFINED ? reflectedFormat : resourceFormat;
     }
 
     Bool UniformManager::Initialize(VkDevice device, VkBufferManager* bufferManager,
@@ -110,6 +114,7 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         m_minDynamicOffsetAlignment = std::max<VkDeviceSize>(1, minUniformBufferOffsetAlignment);
         m_frameCount = frameCount;
         m_maxBindings = maxBindings;
+        m_samplerResolveMemo.assign(m_maxBindings, SamplerResolveMemo{});
         m_setsPerFrame = setsPerFrame;
         m_peakDescriptorSetsObserved = 0;
         m_textureManager = textureManager;
@@ -196,6 +201,14 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         for (auto& cacheEntryPair : frame.descriptorSetCacheByLayout) {
             cacheEntryPair.second.cursor = 0;
         }
+        // The frame's descriptor sets are recycled above, so last frame's reuse target
+        // is gone: start the per-draw descriptor-reuse cache fresh this frame.
+        m_hasLastDescriptor = false;
+        // Re-fingerprint the bound sampler set fresh this frame so any GL object address
+        // reuse cannot outlive a single frame (see SamplerResolveMemo).
+        for (auto& memo : m_samplerResolveMemo) {
+            memo.valid = false;
+        }
     }
 
     Bool UniformManager::ResolveSamplerDescriptor(VkCommandBuffer commandBuffer,
@@ -206,21 +219,20 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         MOBILEGL_ASSERT(m_samplerManager != nullptr, "ResolveSamplerDescriptor: sampler manager is null");
         MOBILEGL_ASSERT(binding < programObj.samplerNameByBinding.size(),
                         "ResolveSamplerDescriptor: sampler binding %u name lookup out of range", binding);
-        SharedPtr<MG_State::GLState::ITextureObject> texture;
-        const Bool resolvedTexture = ResolveSamplerTexture(program, programObj, binding, texture);
-        if (!resolvedTexture) {
-            MGLOG_E("ResolveSamplerDescriptor: failed to resolve sampler texture for binding %u ('%s')", binding,
-                programObj.samplerNameByBinding[binding].c_str());
-            return false;
-        }
+        // Raw-pointer resolve to skip the SharedPtr atomic refcount churn: the bound texture stays
+        // alive through the draw via GL binding state. Only the fallback path needs a SharedPtr to
+        // keep the fallback texture alive for the rest of this call.
+        MG_State::GLState::ITextureObject* texture = ResolveSamplerTextureRaw(program, programObj, binding);
 
         const Int location = programObj.samplerUniformLocationByBinding[binding];
         const Int unit = ResolveSamplerUnitIndex(program, location, binding);
         auto& textureUnit = MG_State::pGLContext->GetTextureUnitObject(unit);
-        const auto samplerOverride = textureUnit.GetSamplerObject();
+        const auto& samplerOverride = textureUnit.GetSamplerObject();
         const auto preferredTarget = programObj.samplerTextureTargetByBinding[binding];
+        SharedPtr<MG_State::GLState::ITextureObject> fallbackHolder;
         if (texture == nullptr) {
-            texture = GetFallbackTexture(preferredTarget);
+            fallbackHolder = GetFallbackTexture(preferredTarget);
+            texture = fallbackHolder.get();
             MOBILEGL_ASSERT(texture != nullptr,
                             "ResolveSamplerDescriptor: no fallback texture available for binding=%u location=%d unit=%d target=%d",
                             binding, location, unit, static_cast<Int>(preferredTarget));
@@ -275,26 +287,74 @@ namespace MobileGL::MG_Backend::DirectVulkan {
                             "ResolveSamplerDescriptor: invalid sampled image layout=%d for textureId=%d, binding=%u",
                             static_cast<Int>(resource->layout), texture->GetExternalIndex(), binding);
         }
+
+        MOBILEGL_ASSERT(binding < programObj.samplerNumericDomainByBinding.size(),
+                        "ResolveSamplerDescriptor: sampler numeric-domain binding %u out of range", binding);
+        const SamplerNumericDomain numericDomain = programObj.samplerNumericDomainByBinding[binding];
+        // Vulkan forbids linear filtering and anisotropy for integer sampled-image formats.
+        // Some desktop GL shader packs deliberately bit-read a mutable float texture through a
+        // usampler and still leave the texture's ordinary linear parameters in place; texelFetch
+        // ignores filtering, so a nearest VkSampler preserves the operation while keeping the
+        // descriptor valid.
+        const Bool forceNearestFiltering = numericDomain == SamplerNumericDomain::SignedInteger ||
+                                           numericDomain == SamplerNumericDomain::UnsignedInteger;
+        const VkFormat sampledViewFormat =
+            VkTextureManager::ResolveSampledImageViewFormat(resource->format, numericDomain);
+        if (sampledViewFormat == VK_FORMAT_UNDEFINED) {
+            MGLOG_E("ResolveSamplerDescriptor: no compatible sampled view for binding=%u ('%s') "
+                    "textureId=%d imageFormat=%d numericDomain=%d",
+                    binding, programObj.samplerNameByBinding[binding].c_str(), texture->GetExternalIndex(),
+                    static_cast<Int>(resource->format), static_cast<Int>(numericDomain));
+            return false;
+        }
+        const VkImageView sampledImageView =
+            m_textureManager->GetOrCreateSampledImageView(*texture, sampledViewFormat);
+        if (sampledImageView == VK_NULL_HANDLE) {
+            MGLOG_E("ResolveSamplerDescriptor: failed to resolve sampled view for binding=%u ('%s') "
+                    "textureId=%d imageFormat=%d viewFormat=%d numericDomain=%d",
+                    binding, programObj.samplerNameByBinding[binding].c_str(), texture->GetExternalIndex(),
+                    static_cast<Int>(resource->format), static_cast<Int>(sampledViewFormat),
+                    static_cast<Int>(numericDomain));
+            return false;
+        }
+        // Skip GetOrCreateSampler's per-draw key hash + map lookup when this binding's
+        // sampler object and texture (both by lifetime id + version) are unchanged from the
+        // last draw that resolved it: the resulting sampler key, and therefore the VkSampler
+        // handle, are guaranteed identical. Lifetime ids are never reused, so a freed-and-
+        // reallocated sampler/texture at the same address gets a fresh id and misses instead
+        // of false-hitting. Cached handles live until Shutdown, so the memo can never hand
+        // back a destroyed sampler.
+        VkSampler resolvedSampler = VK_NULL_HANDLE;
+        if (binding < m_samplerResolveMemo.size()) {
+            auto& memo = m_samplerResolveMemo[binding];
+            const Uint64 samplerLifetimeId = samplerToUse->GetLifetimeId();
+            const Uint16 samplerVersion = samplerToUse->GetVersion();
+            const Uint64 textureLifetimeId = texture->GetLifetimeId();
+            const Uint16 textureParamsVersion = texture->GetTextureParamsVersion();
+            if (memo.valid && memo.samplerLifetimeId == samplerLifetimeId && memo.samplerVersion == samplerVersion &&
+                memo.textureLifetimeId == textureLifetimeId && memo.textureParamsVersion == textureParamsVersion &&
+                memo.forceNearestFiltering == forceNearestFiltering) {
+                resolvedSampler = memo.sampler;
+            } else {
+                resolvedSampler =
+                    m_samplerManager->GetOrCreateSampler(*samplerToUse, *texture, forceNearestFiltering);
+                memo.samplerLifetimeId = samplerLifetimeId;
+                memo.samplerVersion = samplerVersion;
+                memo.textureLifetimeId = textureLifetimeId;
+                memo.textureParamsVersion = textureParamsVersion;
+                memo.forceNearestFiltering = forceNearestFiltering;
+                memo.sampler = resolvedSampler;
+                memo.valid = true;
+            }
+        } else {
+            resolvedSampler =
+                m_samplerManager->GetOrCreateSampler(*samplerToUse, *texture, forceNearestFiltering);
+        }
         outImageInfo = {
-            .sampler = m_samplerManager->GetOrCreateSampler(*samplerToUse, *texture),
-            .imageView = resource->sampledView != VK_NULL_HANDLE ? resource->sampledView : resource->fullView,
+            .sampler = resolvedSampler,
+            .imageView = sampledImageView,
             .imageLayout = resource->layout,
         };
-        if (ShouldDumpDescriptorStats()) {
-            std::fprintf(stderr,
-                         "MOBILEGL_DESCRIPTOR_STATS program=%u binding=%u name=%s location=%d unit=%d "
-                         "texture=%u target=%d sampler=%p imageView=%p layout=%d\n",
-                         program.GetExternalIndex(),
-                         binding,
-                         programObj.samplerNameByBinding[binding].c_str(),
-                         location,
-                         unit,
-                         texture->GetExternalIndex(),
-                         static_cast<Int>(texture->GetTarget()),
-                         reinterpret_cast<void*>(outImageInfo.sampler),
-                         reinterpret_cast<void*>(outImageInfo.imageView),
-                         static_cast<Int>(outImageInfo.imageLayout));
-        }
         return outImageInfo.sampler != VK_NULL_HANDLE;
     }
 
@@ -345,10 +405,43 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         auto& textureUnit = MG_State::pGLContext->GetTextureUnitObject(unit);
         const TextureTarget preferredTarget = programObj.samplerTextureTargetByBinding[binding];
         outTexture = textureUnit.GetBindingSlot(preferredTarget).GetBoundObject();
+        // The slot always holds at least the target's default texture (name 0). While that
+        // default has no image it is unsampleable; report it as "unbound" so callers keep
+        // taking their fallback paths instead of trying to sync a storage-less texture.
+        if (MG_State::GLState::IsUndefinedDefaultTexture(outTexture.get())) {
+            outTexture.reset();
+        }
 
         return true;
     }
 
+    MG_State::GLState::ITextureObject* UniformManager::ResolveSamplerTextureRaw(
+        const MG_State::GLState::ProgramObject& program, const ProgramFactory::VkProgramObject& programObj,
+        Uint32 binding) {
+        MOBILEGL_ASSERT(MG_State::pGLContext != nullptr, "ResolveSamplerTextureRaw: GL context is null");
+        MOBILEGL_ASSERT(binding < programObj.samplerUniformLocationByBinding.size(),
+                        "ResolveSamplerTextureRaw: sampler location binding %u out of range", binding);
+        MOBILEGL_ASSERT(binding < programObj.samplerTextureTargetByBinding.size(),
+                        "ResolveSamplerTextureRaw: sampler target binding %u out of range", binding);
+
+        const Int location = programObj.samplerUniformLocationByBinding[binding];
+        const Int unit = ResolveSamplerUnitIndex(program, location, binding);
+
+        auto& textureUnit = MG_State::pGLContext->GetTextureUnitObject(unit);
+        const TextureTarget preferredTarget = programObj.samplerTextureTargetByBinding[binding];
+        // GetBoundObject() returns the SharedPtr by const ref; .get() reads the pointer without
+        // touching the refcount (no atomic inc/dec per binding per draw).
+        MG_State::GLState::ITextureObject* texture =
+            textureUnit.GetBindingSlot(preferredTarget).GetBoundObject().get();
+        // The slot always holds at least the target's default texture (name 0). While that
+        // default has no image it is unsampleable; report it as "unbound" so the caller
+        // substitutes its fallback texture exactly like it did for the old null slot.
+        if (MG_State::GLState::IsUndefinedDefaultTexture(texture)) {
+            return nullptr;
+        }
+        return texture;
+    }
+
     Bool UniformManager::ResolveTexelBufferDescriptor(const MG_State::GLState::ProgramObject& program,
                                                       const ProgramFactory::VkProgramObject& programObj,
                                                       Uint32 binding, Uint32 frameIndex,
@@ -374,7 +467,7 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         }
 
         auto* textureBuffer = static_cast<MG_State::GLState::TextureObjectBuffer*>(texture.get());
-        const auto bufferObject = textureBuffer->GetBufferBindingSlot().GetBoundObject();
+        const auto& bufferObject = textureBuffer->GetBufferBindingSlot().GetBoundObject();
         if (bufferObject == nullptr) {
             MGLOG_E("ResolveTexelBufferDescriptor: texture buffer binding %u ('%s') has no GL buffer bound",
                     binding, programObj.samplerNameByBinding[binding].c_str());
@@ -382,7 +475,7 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         }
 
         BufferSlice slice{};
-        if (!m_bufferManager->SyncResidentBuffer(BufferKind::TextureBuffer, bufferObject, slice) || !slice.IsValid()) {
+        if (!m_bufferManager->AcquireResidentSlice(BufferKind::TextureBuffer, bufferObject, slice) || !slice.IsValid()) {
             MGLOG_E("ResolveTexelBufferDescriptor: failed to sync GL buffer %u for texture buffer %u",
                     bufferObject->GetExternalIndex(), texture->GetExternalIndex());
             return false;
@@ -449,7 +542,7 @@ namespace MobileGL::MG_Backend::DirectVulkan {
                         frontendBinding, programObj.storageBlockNameByBinding[binding].c_str());
 
         auto& bindingPoint = MG_State::pGLContext->GetBufferBindingPoint(BufferTarget::ShaderStorage, frontendBinding);
-        const auto bufferObject = bindingPoint.GetBoundObject();
+        const auto& bufferObject = bindingPoint.GetBoundObject();
         if (bufferObject == nullptr) {
             MGLOG_E("ResolveStorageBufferDescriptor: no SSBO bound at frontend binding %u for block '%s'",
                     frontendBinding, programObj.storageBlockNameByBinding[binding].c_str());
@@ -457,7 +550,7 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         }
 
         BufferSlice slice{};
-        if (!m_bufferManager->SyncResidentBuffer(BufferKind::ShaderStorage, bufferObject, slice) || !slice.IsValid()) {
+        if (!m_bufferManager->AcquireResidentSlice(BufferKind::ShaderStorage, bufferObject, slice) || !slice.IsValid()) {
             MGLOG_E("ResolveStorageBufferDescriptor: failed to sync GL buffer %u for block '%s'",
                     bufferObject->GetExternalIndex(), programObj.storageBlockNameByBinding[binding].c_str());
             return false;
@@ -524,9 +617,32 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         }
 
         const Uint32 mipLevel = static_cast<Uint32>(std::max<GLint>(0, imageBinding.Level));
-        VkImageView view = m_textureManager->GetOrCreateViewAtMipLevel(*imageBinding.Texture, mipLevel);
+        MOBILEGL_ASSERT(binding < programObj.storageImageFormatByBinding.size(),
+                        "ResolveStorageImageDescriptor: storage image format binding %u out of range", binding);
+        MOBILEGL_ASSERT(binding < programObj.storageImageUsesBindingFormatByBinding.size(),
+                        "ResolveStorageImageDescriptor: storage image format policy binding %u out of range",
+                        binding);
+        const VkFormat reflectedFormat = programObj.storageImageFormatByBinding[binding];
+        const Bool useBindingFormat = programObj.storageImageUsesBindingFormatByBinding[binding];
+        const VkFormat viewFormat = ResolveStorageImageViewFormat(
+            reflectedFormat, imageBinding.Format, resource->format, useBindingFormat);
+        if (viewFormat == VK_FORMAT_UNDEFINED) {
+            MGLOG_E("ResolveStorageImageDescriptor: unsupported glBindImageTexture format=0x%x "
+                    "for binding=%u imageUnit=%d textureId=%d bindingPolicy=%s",
+                    imageBinding.Format, binding, imageUnit, imageBinding.Texture->GetExternalIndex(),
+                    useBindingFormat ? "true" : "false");
+            return false;
+        }
+        const VkImageView view = m_textureManager->GetOrCreateStorageImageView(
+            *imageBinding.Texture, mipLevel, viewFormat, imageBinding.Layered != GL_FALSE, imageBinding.Layer);
         if (view == VK_NULL_HANDLE) {
-            view = resource->fullView;
+            MGLOG_E("ResolveStorageImageDescriptor: failed to resolve storage view textureId=%d mip=%u "
+                    "bindingFormat=0x%x imageFormat=%d reflectedFormat=%d selectedFormat=%d bindingPolicy=%s",
+                    imageBinding.Texture->GetExternalIndex(), mipLevel, imageBinding.Format,
+                    static_cast<Int>(resource->format), static_cast<Int>(reflectedFormat),
+                    static_cast<Int>(viewFormat),
+                    useBindingFormat ? "true" : "false");
+            return false;
         }
         outImageInfo.sampler = VK_NULL_HANDLE;
         outImageInfo.imageView = view;
@@ -563,14 +679,66 @@ namespace MobileGL::MG_Backend::DirectVulkan {
                 continue;
             }
 
-            SharedPtr<MG_State::GLState::ITextureObject> texture;
-            if (!ResolveSamplerTexture(program, programObj, binding, texture) || !texture) {
-                continue;
+            MG_State::GLState::ITextureObject* texture = ResolveSamplerTextureRaw(program, programObj, binding);
+            if (!texture) {
+                // ResolveSamplerDescriptor will substitute the fallback texture for this binding;
+                // include it in the sampled set so the pre-render-pass sync/transition pass covers
+                // its first use instead of leaving that work to happen inside an active pass.
+                const TextureTarget preferredTarget = programObj.samplerTextureTargetByBinding[binding];
+                if (preferredTarget != TextureTarget::Texture2D &&
+                    preferredTarget != TextureTarget::TextureRectangle) {
+                    continue;
+                }
+                texture = GetFallbackTexture(preferredTarget).get();
             }
 
-            auto found = std::find(outTextures.begin(), outTextures.end(), texture.get());
+            auto found = std::find(outTextures.begin(), outTextures.end(), texture);
             if (found == outTextures.end()) {
-                outTextures.push_back(texture.get());
+                outTextures.push_back(texture);
+            }
+        }
+        return true;
+    }
+
+    Bool UniformManager::CollectStorageImageTextures(
+        const MG_State::GLState::ProgramObject& program,
+        const ProgramFactory::VkProgramObject& programObj,
+        Vector<MG_State::GLState::ITextureObject*>& outTextures) const {
+        outTextures.clear();
+        MOBILEGL_ASSERT(MG_State::pGLContext != nullptr,
+                        "CollectStorageImageTextures: GL context is null");
+
+        const Uint32 bindingCount =
+            std::min<Uint32>(m_maxBindings, static_cast<Uint32>(programObj.bindingKinds.size()));
+        for (Uint32 binding = 0; binding < bindingCount; ++binding) {
+            if (programObj.bindingKinds[binding] != ProgramFactory::DescriptorBindingKind::StorageImage) {
+                continue;
+            }
+            if (binding >= programObj.samplerUniformLocationByBinding.size()) {
+                MGLOG_E("CollectStorageImageTextures: binding %u has no uniform-location mapping", binding);
+                return false;
+            }
+
+            const Int location = programObj.samplerUniformLocationByBinding[binding];
+            if (location < 0) {
+                MGLOG_E("CollectStorageImageTextures: binding %u has no image uniform location", binding);
+                return false;
+            }
+            const Int imageUnit = program.GetUniformSamplerOrImageUnitIndex(static_cast<Uint>(location));
+            if (imageUnit < 0 || imageUnit >= MG_State::GLState::TextureState::MAX_TEXTURE_IMAGE_UNITS) {
+                MGLOG_E("CollectStorageImageTextures: image unit %d is invalid for binding %u",
+                        imageUnit, binding);
+                return false;
+            }
+
+            auto* texture = MG_State::pGLContext->GetImageTextureBinding(imageUnit).Texture.get();
+            if (texture == nullptr) {
+                MGLOG_E("CollectStorageImageTextures: image unit %d is unbound for binding %u",
+                        imageUnit, binding);
+                return false;
+            }
+            if (std::find(outTextures.begin(), outTextures.end(), texture) == outTextures.end()) {
+                outTextures.push_back(texture);
             }
         }
         return true;
@@ -578,9 +746,9 @@ namespace MobileGL::MG_Backend::DirectVulkan {
 
     Bool UniformManager::ResolveUniformBufferPayload(const MG_State::GLState::ProgramObject& program,
                                                      const ProgramFactory::VkProgramObject& programObj, Uint32 binding,
-                                                     const void*& outData, VkDeviceSize& outSize) const {
-        outData = nullptr;
-        outSize = 0;
+                                                     UboBindResult& out) const {
+        const void* outData = nullptr;
+        VkDeviceSize outSize = 0;
 
         MOBILEGL_ASSERT(MG_State::pGLContext != nullptr, "ResolveUniformBufferPayload: GL context is null");
         MOBILEGL_ASSERT(binding < programObj.bindingKinds.size(),
@@ -596,6 +764,9 @@ namespace MobileGL::MG_Backend::DirectVulkan {
                 outData = emptyGlobalUbo.data();
                 outSize = static_cast<VkDeviceSize>(emptyGlobalUbo.size());
             }
+            // The global UBO is CPU uniform data, not an app buffer -> always UploadTransient.
+            out.payload = outData;
+            out.payloadSize = outSize;
             return outData != nullptr && outSize > 0;
         }
 
@@ -618,14 +789,13 @@ namespace MobileGL::MG_Backend::DirectVulkan {
                         frontendBinding, program.GetUniformBlockName(static_cast<Uint32>(blockIndex)).c_str());
 
         auto& bindingPoint = MG_State::pGLContext->GetBufferBindingPoint(BufferTarget::Uniform, frontendBinding);
-        const auto bufferObject = bindingPoint.GetBoundObject();
+        const auto& bufferObject = bindingPoint.GetBoundObject();
         MOBILEGL_ASSERT(bufferObject != nullptr,
                         "ResolveUniformBufferPayload: no UBO bound at frontend binding %u for block '%s'",
                         frontendBinding, program.GetUniformBlockName(static_cast<Uint32>(blockIndex)).c_str());
-        bufferObject->MarkPersistentMappedRangeDirty();
+        bufferObject->SyncPersistentMappedRange();
 
-        const auto bufferData = bufferObject->GetDataReadOnly();
-        MOBILEGL_ASSERT(bufferData != nullptr && !bufferData->empty(),
+        MOBILEGL_ASSERT(bufferObject->MappedData() != nullptr && bufferObject->GetSize() != 0,
                         "ResolveUniformBufferPayload: bound UBO data is empty for block '%s'",
                         program.GetUniformBlockName(static_cast<Uint32>(blockIndex)).c_str());
 
@@ -652,13 +822,34 @@ namespace MobileGL::MG_Backend::DirectVulkan {
                         program.GetUniformBlockName(static_cast<Uint32>(blockIndex)).c_str());
 
         const VkDeviceSize available = rangeEnd - rangeStart;
-        MOBILEGL_ASSERT(available >= blockSize,
-                        "ResolveUniformBufferPayload: bound range %zu is smaller than UBO size %zu for block '%s'",
-                        static_cast<SizeT>(available), static_cast<SizeT>(blockSize),
-                        program.GetUniformBlockName(static_cast<Uint32>(blockIndex)).c_str());
-
-        outData = bufferData->data() + static_cast<SizeT>(rangeStart);
         outSize = blockSize;
+        outData = bufferObject->MappedData() + static_cast<SizeT>(rangeStart);
+        if (available < blockSize) {
+            static thread_local Vector<Uint8> paddedUbo;
+            paddedUbo.assign(static_cast<SizeT>(blockSize), 0);
+            Memcpy(paddedUbo.data(), outData, static_cast<SizeT>(available));
+            outData = paddedUbo.data();
+        }
+        out.payload = outData;
+        out.payloadSize = outSize;
+
+        // Zero-copy direct bind: for a persistent-mapped coherent app buffer whose full reflected
+        // block fits within the aligned bound range, point the descriptor straight at the app's
+        // resident VkBuffer (the same buffer the GLES backend binds) with the block range as the
+        // dynamic offset - no per-draw copy into a transient ring. Any gate failing keeps the
+        // UploadTransient payload above. AcquireResidentSlice does the persistent busy-tracking and
+        // (for the persistent case) hits a zero-work fast path returning the whole-buffer slice.
+        if (bufferObject->IsBackendPersistentMapped() && available >= blockSize &&
+            (rangeStart % m_minDynamicOffsetAlignment) == 0) {
+            BufferSlice slice{};
+            if (m_bufferManager->AcquireResidentSlice(BufferKind::Uniform, bufferObject, slice) &&
+                slice.IsValid() && slice.offset == 0 && slice.size >= rangeStart + blockSize) {
+                out.directBindable = true;
+                out.buffer = slice.buffer;
+                out.range = blockSize;
+                out.dynamicOffset = rangeStart;
+            }
+        }
         return true;
     }
 
@@ -809,24 +1000,26 @@ namespace MobileGL::MG_Backend::DirectVulkan {
             frame.activeDescriptorPoolIndex = 0;
         }
 
+        // The descriptor set is chosen AFTER the writes are built (below), so a draw
+        // whose resolved descriptor content matches the previous draw can reuse that
+        // set and skip both AcquireDescriptorSet and vkUpdateDescriptorSets.
         VkDescriptorSet descriptorSet = VK_NULL_HANDLE;
-        VkResult allocResult = AcquireDescriptorSet(frameIndex, programObj, descriptorSet);
-        if (allocResult != VK_SUCCESS || descriptorSet == VK_NULL_HANDLE) {
-            MGLOG_E("UniformDescriptorBinder::BindProgramUniformBuffers failed: descriptor set acquire returned %d",
-                    allocResult);
-            return false;
-        }
 
         MOBILEGL_ASSERT(m_textureManager != nullptr, "BindProgramUniformBuffers: texture manager is null");
         MOBILEGL_ASSERT(m_samplerManager != nullptr, "BindProgramUniformBuffers: sampler manager is null");
         MOBILEGL_ASSERT(m_bufferManager != nullptr, "BindProgramUniformBuffers: buffer manager is null");
 
-        Vector<VkWriteDescriptorSet> writes;
+        auto& writes = m_writesScratch;
+        auto& bufferInfos = m_bufferInfosScratch;
+        auto& imageInfos = m_imageInfosScratch;
+        auto& texelBufferViews = m_texelBufferViewsScratch;
+        auto& dynamicOffsets = m_dynamicOffsetsScratch;
+        writes.clear();
+        bufferInfos.clear();
+        imageInfos.clear();
+        texelBufferViews.clear();
+        dynamicOffsets.clear();
         writes.reserve(m_maxBindings);
-        Vector<VkDescriptorBufferInfo> bufferInfos;
-        Vector<VkDescriptorImageInfo> imageInfos;
-        Vector<VkBufferView> texelBufferViews;
-        Vector<Uint32> dynamicOffsets;
         bufferInfos.reserve(m_maxBindings);
         imageInfos.reserve(m_maxBindings);
         texelBufferViews.reserve(m_maxBindings);
@@ -848,31 +1041,40 @@ namespace MobileGL::MG_Backend::DirectVulkan {
             write.descriptorCount = 1;
 
             if (kind == ProgramFactory::DescriptorBindingKind::UniformBufferDynamic) {
-                const void* payload = nullptr;
-                VkDeviceSize payloadSize = 0;
-                const Bool hasPayload = ResolveUniformBufferPayload(program, programObj, binding, payload, payloadSize);
-                MOBILEGL_ASSERT(hasPayload && payload != nullptr && payloadSize > 0,
+                UboBindResult ubo{};
+                const Bool hasPayload = ResolveUniformBufferPayload(program, programObj, binding, ubo);
+                MOBILEGL_ASSERT(hasPayload && ubo.payload != nullptr && ubo.payloadSize > 0,
                                 "UniformDescriptorBinder::BindProgramUniformBuffers failed: missing UBO payload on binding %u",
                                 binding);
 
-                BufferSlice slice{};
-                if (!m_bufferManager->UploadTransient(BufferKind::Uniform, frameIndex, payload, payloadSize,
-                                                     m_minDynamicOffsetAlignment, slice)) {
-                    MOBILEGL_ASSERT(false, "UniformDescriptorBinder::BindProgramUniformBuffers failed: UBO upload failed on binding %u",
-                            binding);
-                    return false;
-                }
-
                 VkDescriptorBufferInfo bufferInfo{};
-                bufferInfo.buffer = slice.buffer;
+                // Keep offset 0 (sub-range selected via the dynamic offset) so the hashed bufferInfo
+                // is stable across draws and the descriptor-set reuse cache keeps hitting.
                 bufferInfo.offset = 0;
-                bufferInfo.range = payloadSize;
+                Uint32 dynOffset;
+                if (ubo.directBindable) {
+                    // Zero-copy: bind the app's resident VkBuffer directly, no per-draw memcpy.
+                    bufferInfo.buffer = ubo.buffer;
+                    bufferInfo.range = ubo.range;
+                    dynOffset = static_cast<Uint32>(ubo.dynamicOffset);
+                } else {
+                    BufferSlice slice{};
+                    if (!m_bufferManager->UploadTransient(BufferKind::Uniform, frameIndex, ubo.payload,
+                                                          ubo.payloadSize, m_minDynamicOffsetAlignment, slice)) {
+                        MOBILEGL_ASSERT(false, "UniformDescriptorBinder::BindProgramUniformBuffers failed: UBO upload failed on binding %u",
+                                binding);
+                        return false;
+                    }
+                    bufferInfo.buffer = slice.buffer;
+                    bufferInfo.range = ubo.payloadSize;
+                    dynOffset = static_cast<Uint32>(slice.offset);
+                }
                 bufferInfos.push_back(bufferInfo);
 
                 write.descriptorType = VK_DESCRIPTOR_TYPE_UNIFORM_BUFFER_DYNAMIC;
                 write.pBufferInfo = &bufferInfos.back();
                 writes.push_back(write);
-                dynamicOffsets.push_back(static_cast<Uint32>(slice.offset));
+                dynamicOffsets.push_back(dynOffset);
             } else if (kind == ProgramFactory::DescriptorBindingKind::UniformTexelBuffer) {
                 VkBufferView bufferView = VK_NULL_HANDLE;
                 if (!ResolveTexelBufferDescriptor(program, programObj, binding, frameIndex, bufferView) ||
@@ -942,8 +1144,62 @@ namespace MobileGL::MG_Backend::DirectVulkan {
             }
         }
 
-        if (!writes.empty()) {
-            vkUpdateDescriptorSets(m_device, static_cast<Uint32>(writes.size()), writes.data(), 0, nullptr);
+        // Reuse the previous draw's descriptor set when the resolved content is
+        // byte-identical (only the bind-time dynamic offsets differ). The signature
+        // covers the descriptor-set layout + every write's binding/type/count + the
+        // pointed-to buffer/image/texel-buffer infos (all value-initialized, so no
+        // padding noise). Correctness: bindings are re-resolved every draw, so the
+        // signature always reflects the current state and reuse happens only on an
+        // exact match; the reused set is never re-acquired within a frame (the acquire
+        // cursor only advances), so its written contents survive; the layout is part of
+        // the signature so reuse never crosses programs. Sampler overrides (blits)
+        // bypass and invalidate the cache.
+        const Bool cacheable = (samplerBindingOverride == nullptr);
+        Uint64 signature = 0xcbf29ce484222325ULL;
+        {
+            const auto mix64 = [&signature](Uint64 word) {
+                signature = (signature ^ word) * 0x100000001b3ULL;
+            };
+            // The hashed descriptor payloads (VkDescriptorBufferInfo=24B,
+            // VkDescriptorImageInfo=24B, VkBufferView=8B) are all 8-byte-multiple sized
+            // and value-initialized (padding is zero), so hashing 64-bit words at a time
+            // is exact and ~8x cheaper than byte-wise - the signature is recomputed every
+            // draw, so its own cost has to stay small.
+            const auto mixWords = [&mix64](const void* data, SizeT byteSize) {
+                const auto* words = static_cast<const Uint64*>(data);
+                for (SizeT i = 0; i < byteSize / sizeof(Uint64); ++i) {
+                    mix64(words[i]);
+                }
+            };
+            mixWords(&programObj.descriptorSetLayout, sizeof(programObj.descriptorSetLayout));
+            for (const auto& write : writes) {
+                mix64((static_cast<Uint64>(write.dstBinding) << 40) ^
+                      (static_cast<Uint64>(write.descriptorType) << 8) ^
+                      static_cast<Uint64>(write.descriptorCount));
+            }
+            mixWords(bufferInfos.data(), bufferInfos.size() * sizeof(VkDescriptorBufferInfo));
+            mixWords(imageInfos.data(), imageInfos.size() * sizeof(VkDescriptorImageInfo));
+            mixWords(texelBufferViews.data(), texelBufferViews.size() * sizeof(VkBufferView));
+        }
+
+        if (cacheable && m_hasLastDescriptor && signature == m_lastDescriptorSignature) {
+            descriptorSet = m_lastBoundDescriptorSet;
+        } else {
+            VkResult allocResult = AcquireDescriptorSet(frameIndex, programObj, descriptorSet);
+            if (allocResult != VK_SUCCESS || descriptorSet == VK_NULL_HANDLE) {
+                MGLOG_E("UniformDescriptorBinder::BindProgramUniformBuffers failed: descriptor set acquire returned %d",
+                        allocResult);
+                return false;
+            }
+            for (auto& write : writes) {
+                write.dstSet = descriptorSet;
+            }
+            if (!writes.empty()) {
+                vkUpdateDescriptorSets(m_device, static_cast<Uint32>(writes.size()), writes.data(), 0, nullptr);
+            }
+            m_lastBoundDescriptorSet = descriptorSet;
+            m_lastDescriptorSignature = signature;
+            m_hasLastDescriptor = cacheable;
         }
 
         vkCmdBindDescriptorSets(commandBuffer, bindPoint, programObj.pipelineLayout, 0, 1,

MobileGL/MG_Backend/DirectVulkan/Renderer/UniformManager.h

@@ -42,6 +42,9 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         Bool CollectSampledTextures(const MG_State::GLState::ProgramObject& program,
                                     const ProgramFactory::VkProgramObject& programObj,
                                     Vector<MG_State::GLState::ITextureObject*>& outTextures);
+        Bool CollectStorageImageTextures(const MG_State::GLState::ProgramObject& program,
+                                         const ProgramFactory::VkProgramObject& programObj,
+                                         Vector<MG_State::GLState::ITextureObject*>& outTextures) const;
         Bool BindProgramUniformBuffers(VkCommandBuffer commandBuffer,
                                        const MG_State::GLState::ProgramObject& program,
                                        const ProgramFactory::VkProgramObject& programObj,
@@ -49,6 +52,12 @@ namespace MobileGL::MG_Backend::DirectVulkan {
                                        VkPipelineBindPoint bindPoint = VK_PIPELINE_BIND_POINT_GRAPHICS,
                                        const SamplerBindingOverride* samplerBindingOverride = nullptr);
 
+        // 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);
+
     private:
         struct DescriptorPoolBucket {
             VkDescriptorPool handle = VK_NULL_HANDLE;
@@ -73,6 +82,12 @@ 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);
+        // 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.
+        static MG_State::GLState::ITextureObject* ResolveSamplerTextureRaw(
+            const MG_State::GLState::ProgramObject& program,
+            const ProgramFactory::VkProgramObject& programObj, Uint32 binding);
         SharedPtr<MG_State::GLState::ITextureObject> GetFallbackTexture(TextureTarget target) const;
         Bool ResolveSamplerDescriptor(VkCommandBuffer commandBuffer, const MG_State::GLState::ProgramObject& program,
                                       const ProgramFactory::VkProgramObject& programObj, Uint32 binding,
@@ -89,9 +104,19 @@ namespace MobileGL::MG_Backend::DirectVulkan {
                                            const MG_State::GLState::ProgramObject& program,
                                            const ProgramFactory::VkProgramObject& programObj, Uint32 binding,
                                            VkDescriptorImageInfo& outImageInfo) const;
+        // Result of resolving a UBO binding: either a zero-copy direct bind to the app's resident
+        // VkBuffer (the GLES backend's approach - no per-draw copy) or the CPU payload to upload.
+        struct UboBindResult {
+            Bool directBindable = false;
+            VkBuffer buffer = VK_NULL_HANDLE;
+            VkDeviceSize range = 0;         // reflected block size; constant across draws (hashed)
+            VkDeviceSize dynamicOffset = 0; // block range start; moves per draw (NOT hashed)
+            const void* payload = nullptr;  // fallback UploadTransient path
+            VkDeviceSize payloadSize = 0;
+        };
         Bool ResolveUniformBufferPayload(const MG_State::GLState::ProgramObject& program,
                                          const ProgramFactory::VkProgramObject& programObj, Uint32 binding,
-                                         const void*& outData, VkDeviceSize& outSize) const;
+                                         UboBindResult& out) const;
         Bool CreateDescriptorPool(Uint32 maxSets, VkDescriptorPool& outPool) const;
         Bool GrowFrameDescriptorPool(FrameResources& frame, Uint32 frameIndex);
         VkResult AllocateDescriptorSetsFromActivePool(
@@ -113,6 +138,45 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         VkTextureManager* m_textureManager = nullptr;
         VkSamplerManager* m_samplerManager = nullptr;
         mutable SharedPtr<MG_State::GLState::ITextureObject> m_fallbackTexture2D;
+
+        // Per-draw scratch buffers for BindProgramUniformBuffers: reused (clear keeps
+        // capacity) so the descriptor-write path stops allocating on every draw.
+        Vector<VkWriteDescriptorSet> m_writesScratch;
+        Vector<VkDescriptorBufferInfo> m_bufferInfosScratch;
+        Vector<VkDescriptorImageInfo> m_imageInfosScratch;
+        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;
+
+        // 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
+        // sampler objects with identical state still resolve to one VkSampler. This memo only
+        // skips recomputing that hash. Across a draw batch the bound sampler set is stable, so a
+        // binding whose sampler (lifetime id + version, bumped on every setter) and texture
+        // (lifetime id + params version, bumped on the format/border-color setters that feed the
+        // key) are unchanged recycles the VkSampler it resolved last draw; a param change bumps
+        // a version and forces a re-resolve. Both objects are keyed by a never-reused monotonic
+        // lifetime id, so a freed-and-reallocated sampler or texture at the same heap address
+        // always gets a fresh id and misses (a raw pointer would false-hit that ABA) - so a
+        // stale guess can only miss and fall through to the hash, never resolve wrong. Still
+        // reset each frame alongside the descriptor-set cache. Indexed by binding.
+        struct SamplerResolveMemo {
+            Uint64 samplerLifetimeId = 0;
+            Uint64 textureLifetimeId = 0;
+            VkSampler sampler = VK_NULL_HANDLE;
+            Uint16 samplerVersion = 0;
+            Uint16 textureParamsVersion = 0;
+            Bool forceNearestFiltering = false;
+            Bool valid = false;
+        };
+        mutable Vector<SamplerResolveMemo> m_samplerResolveMemo;
     };
 } // namespace MobileGL::MG_Backend::DirectVulkan
-

MobileGL/MG_Backend/DirectVulkan/Renderer/VertexInputStateFactory.cpp

@@ -29,6 +29,7 @@ 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.IsBgra, sizeof(attr.IsBgra)));
             XXHASH_VERIFY(XXH64_update(m_hashState, &attr.Divisor, sizeof(attr.Divisor)));
 
             const SizeT bufferKey = reinterpret_cast<SizeT>(attr.Buffer.get());
@@ -38,10 +39,19 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         return XXH64_digest(m_hashState);
     }
 
+    VertexInputStateFactory::HashType VertexInputStateFactory::GetOrComputeHash(
+        const MG_State::GLState::VertexArrayObject& vao) const {
+        HashType hash = 0;
+        if (!vao.GetBackendHashMemo(hash)) {
+            hash = ComputeHash(vao);
+            vao.SetBackendHashMemo(hash);
+        }
+        return hash;
+    }
+
     const VertexInputStateFactory::BackendVertexInputState& VertexInputStateFactory::GetOrCreateVertexInputState(
         const MG_State::GLState::VertexArrayObject& vao) {
-        const HashType hash = ComputeHash(vao);
-        return GetOrCreateVertexInputState(vao, hash);
+        return GetOrCreateVertexInputState(vao, GetOrComputeHash(vao));
     }
 
     const VertexInputStateFactory::BackendVertexInputState& VertexInputStateFactory::GetOrCreateVertexInputState(
@@ -56,6 +66,8 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         Vector<SizeT> bindingBaseOffsets;
         Vector<Uint32> bindingAttributeLocations;
         Vector<Bool> bindingUsesClientMemory;
+        Vector<VertexStreamConversion> bindingConversions;
+        Uint32 unsupportedAttribMask = 0;
 
         for (Uint32 location = 0; location < MG_State::GLState::VertexArrayObject::MAX_VERTEX_ATTRIBS; ++location) {
             const auto& attr = vao.GetAttribute(location);
@@ -63,23 +75,74 @@ namespace MobileGL::MG_Backend::DirectVulkan {
                 continue;
             }
 
-            const auto vkFormat = ToVkVertexFormat(attr.Type, attr.Size, attr.Normalized, attr.IsInteger);
-            if (vkFormat == VK_FORMAT_UNDEFINED) {
-                MGLOG_D("Skipping unsupported vertex attribute layout (location=%u, type=%s, size=%d)",
+            const VkFormat sourceVkFormat =
+                ToVkVertexFormat(attr.Type, attr.Size, attr.Normalized, attr.IsInteger, attr.IsBgra);
+            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);
+                unsupportedAttribMask |= (1u << location);
                 continue;
             }
 
-            const SizeT componentSize = GetComponentSize(attr.Type);
-            if (componentSize == 0) {
-                MGLOG_D("Skipping vertex attribute with unknown component size (location=%u, type=%s)",
+            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 "
+                        "enabled but cannot be sized",
                         location, MG_Util::ConvertDataTypeToString(attr.Type).c_str());
+                unsupportedAttribMask |= (1u << location);
                 continue;
             }
 
-            const Uint32 stride = attr.Stride > 0
-                                      ? static_cast<Uint32>(attr.Stride)
-                                      : static_cast<Uint32>(componentSize * static_cast<SizeT>(attr.Size));
+            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);
+            if (conversion == VertexStreamConversion::None && requiredAlignment > 1 &&
+                ((sourceStride % requiredAlignment) != 0 || (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;
 
@@ -89,6 +152,7 @@ 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);
         }
@@ -103,14 +167,40 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         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();
         return entry;
     }
 
-    VkFormat VertexInputStateFactory::ToVkVertexFormat(DataType type, Int size, Bool normalized, Bool isInteger) {
+    VkFormat VertexInputStateFactory::ToVkVertexFormat(DataType type, Int size, Bool normalized, Bool isInteger,
+                                                       Bool isBgra) {
+        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
+            // components back into R,G,B,A order for the shader.
+            switch (type) {
+            case DataType::Uint8:
+                return VK_FORMAT_B8G8R8A8_UNORM;
+            case DataType::Uint2101010Rev:
+                return VK_FORMAT_A2R10G10B10_UNORM_PACK32;
+            case DataType::Int2101010Rev:
+                return VK_FORMAT_A2R10G10B10_SNORM_PACK32;
+            default:
+                return VK_FORMAT_UNDEFINED;
+            }
+        }
         switch (type) {
+        case DataType::Uint2101010Rev:
+            // Packed 2_10_10_10 travels the float-normalizing path only; size is always 4. SNORM/UNORM
+            // normalize, SSCALED/USCALED cast the packed field to float.
+            if (isInteger || size != 4) return VK_FORMAT_UNDEFINED;
+            return normalized ? VK_FORMAT_A2B10G10R10_UNORM_PACK32 : VK_FORMAT_A2B10G10R10_USCALED_PACK32;
+        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::Float32:
             switch (size) {
             case 1: return VK_FORMAT_R32_SFLOAT;
@@ -119,6 +209,17 @@ namespace MobileGL::MG_Backend::DirectVulkan {
             case 4: return VK_FORMAT_R32G32B32A32_SFLOAT;
             default: return VK_FORMAT_UNDEFINED;
             }
+        case DataType::Float16:
+            // GL_HALF_FLOAT is a floating-point array type: it is never an integer attribute, and
+            // GL_TRUE for `normalized` is ignored for float types rather than selecting a *NORM format.
+            if (isInteger) return VK_FORMAT_UNDEFINED;
+            switch (size) {
+            case 1: return VK_FORMAT_R16_SFLOAT;
+            case 2: return VK_FORMAT_R16G16_SFLOAT;
+            case 3: return VK_FORMAT_R16G16B16_SFLOAT;
+            case 4: return VK_FORMAT_R16G16B16A16_SFLOAT;
+            default: return VK_FORMAT_UNDEFINED;
+            }
         case DataType::Int32:
             if (!isInteger || normalized) return VK_FORMAT_UNDEFINED;
             switch (size) {
@@ -222,4 +323,57 @@ namespace MobileGL::MG_Backend::DirectVulkan {
             return 0;
         }
     }
+
+    SizeT VertexInputStateFactory::GetAttributeByteSize(DataType type, Int size, Bool isBgra) {
+        // The packed 2_10_10_10 types are a single 32-bit word for all 4 components; GL_BGRA is always
+        // 4 components (GL_UNSIGNED_BYTE x4 = 4 bytes, or a packed word = 4 bytes) -- both are 4 bytes.
+        if (type == DataType::Int2101010Rev || type == DataType::Uint2101010Rev || isBgra) {
+            return 4;
+        }
+        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

@@ -19,6 +19,12 @@ namespace MobileGL::MG_Backend::DirectVulkan {
     public:
         using HashType = Uint64;
 
+        enum class VertexStreamConversion : Uint8 {
+            None = 0,
+            Repack,
+            ScaledIntegerToFloat32,
+        };
+
         struct BackendVertexInputState {
             HashType hash = 0;
             Vector<VkVertexInputBindingDescription> bindings;
@@ -27,26 +33,42 @@ namespace MobileGL::MG_Backend::DirectVulkan {
             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;
             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;
 
         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.
+        HashType GetOrComputeHash(const MG_State::GLState::VertexArrayObject& vao) const;
         const BackendVertexInputState& GetOrCreateVertexInputState(
             const MG_State::GLState::VertexArrayObject& vao, HashType hash);
         const BackendVertexInputState& GetOrCreateVertexInputState(const MG_State::GLState::VertexArrayObject& vao);
         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
+        // an unknown/unsupported type.
+        static SizeT GetAttributeByteSize(DataType type, Int size, Bool isBgra);
 
     private:
-        static VkFormat ToVkVertexFormat(DataType type, Int size, Bool normalized, Bool isInteger);
+        static VkFormat ToVkVertexFormat(DataType type, Int size, Bool normalized, Bool isInteger, Bool isBgra = false);
+        static Bool IsScaledIntegerVertexFormat(VkFormat format);
+        static VkFormat ToFloat32VertexFormat(Int componentCount);
+        Bool SupportsVertexBufferFormat(VkFormat format) const;
 
         const VulkanRendererConfig& m_config;
+        VkPhysicalDevice m_physicalDevice = VK_NULL_HANDLE;
         UnorderedMap<HashType, BackendVertexInputState> m_cache;
         static inline XXH64_state_t* m_hashState = XXH64_createState();
     };

MobileGL/MG_Backend/DirectVulkan/Renderer/VkBufferManager.cpp

@@ -10,9 +10,73 @@
 
 namespace MobileGL::MG_Backend::DirectVulkan {
     namespace {
-        constexpr Uint32 kResidentBufferGCInterval = 60;
         constexpr VmaAllocationCreateFlags kResidentBufferAllocationFlags =
             VMA_ALLOCATION_CREATE_HOST_ACCESS_SEQUENTIAL_WRITE_BIT;
+        constexpr SizeT kLiveResourcePruneThreshold = 256;
+
+        // A zero-copy persistent buffer is created once and never recreated (the app holds
+        // its mapped pointer), and may be bound to any role, so it carries every usage.
+        // TRANSFER_DST is added by CreateResidentStorage.
+        constexpr VkBufferUsageFlags kPersistentBackedUsage =
+            VK_BUFFER_USAGE_VERTEX_BUFFER_BIT | VK_BUFFER_USAGE_INDEX_BUFFER_BIT |
+            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;
+        // 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 =
+            VK_MEMORY_PROPERTY_HOST_VISIBLE_BIT | VK_MEMORY_PROPERTY_HOST_COHERENT_BIT;
+
+        using MG_State::GLState::BackendBufferResource;
+        using MG_State::GLState::BufferBackendOps;
+        using MG_State::GLState::BufferObject;
+
+        // The manager owned by the active VulkanRenderer; immediate ops route here.
+        VkBufferManager* g_activeBufferManager = nullptr;
+
+        void Ops_Respecify(BufferObject& bufferObject) {
+            if (g_activeBufferManager) {
+                g_activeBufferManager->OnRespecify(bufferObject);
+            }
+        }
+
+        void Ops_SubData(BufferObject& bufferObject, SizeT offset, SizeT size) {
+            if (g_activeBufferManager) {
+                g_activeBufferManager->OnSubData(bufferObject, offset, size);
+            }
+        }
+
+        void Ops_FlushMappedRange(BufferObject& bufferObject, Range1D range,
+                                  Flags<BufferMappingAccessBit> appAccess) {
+            if (g_activeBufferManager) {
+                g_activeBufferManager->OnFlushMappedRange(bufferObject, range, appAccess);
+            }
+        }
+
+        void* Ops_AcquirePersistentMap(BufferObject& bufferObject) {
+            if (g_activeBufferManager) {
+                return g_activeBufferManager->AcquirePersistentMap(bufferObject);
+            }
+            return nullptr;
+        }
+
+        void Ops_OnDestroy(SharedPtr<BackendBufferResource>&& resource) {
+            if (g_activeBufferManager) {
+                g_activeBufferManager->OnResourceDestroyed(std::move(resource));
+            }
+            // No active manager: the device/allocator is gone or going away and
+            // Shutdown() already destroyed the storage; dropping the handle here
+            // must not touch Vulkan. VkBufferResource's dtor destroys via VMA only
+            // when the allocation is still valid, which Shutdown() cleared.
+        }
+
+        const BufferBackendOps g_vulkanBufferBackendOps = {
+            .Respecify = Ops_Respecify,
+            .SubData = Ops_SubData,
+            .FlushMappedRange = Ops_FlushMappedRange,
+            .OnDestroy = Ops_OnDestroy,
+            .AcquirePersistentMap = Ops_AcquirePersistentMap,
+        };
     } // namespace
 
     Bool VkBufferManager::Initialize(const VkBufferManagerInitInfo& initInfo) {
@@ -22,40 +86,93 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         MOBILEGL_ASSERT(initInfo.frameCount > 0, "VkBufferManager::Initialize requires non-zero frame count");
 
         m_initInfo = initInfo;
-        m_deferredResidentReleases.resize(initInfo.frameCount);
+        m_deferredBufferReleases.resize(initInfo.frameCount);
+        m_deferredResourceReleases.resize(initInfo.frameCount);
         m_currentFrameIndex = 0;
-        return InitializeTransientArenas();
+        m_frameSerial = 1;
+        m_completedSerialFloor = 0;
+        if (!InitializeTransientArenas()) {
+            return false;
+        }
+        g_activeBufferManager = this;
+        MG_State::GLState::SetBufferBackendOps(&g_vulkanBufferBackendOps);
+        return true;
     }
 
     void VkBufferManager::Shutdown() {
+        if (g_activeBufferManager == this) {
+            g_activeBufferManager = nullptr;
+            if (MG_State::GLState::GetBufferBackendOps() == &g_vulkanBufferBackendOps) {
+                MG_State::GLState::SetBufferBackendOps(nullptr);
+            }
+        }
         m_transientUploadArena.Shutdown();
-        DestroyResidentBuffers();
-        DestroyDeferredResidentReleases();
+        DestroyAllDeferredReleases();
+        ReleaseAllLiveResources();
+        m_copyProvider = nullptr;
         m_initInfo = {};
         m_currentFrameIndex = 0;
-        m_residentGcTick = 0;
+        m_frameSerial = 1;
+        m_completedSerialFloor = 0;
     }
 
     Bool VkBufferManager::RecreateTransientArenas(Uint32 frameCount) {
-        MOBILEGL_ASSERT(m_initInfo.allocator != nullptr, "VkBufferManager::RecreateTransientArenas requires initialized manager");
+        MOBILEGL_ASSERT(m_initInfo.allocator != nullptr,
+                        "VkBufferManager::RecreateTransientArenas requires initialized manager");
         MOBILEGL_ASSERT(frameCount > 0, "VkBufferManager::RecreateTransientArenas requires non-zero frame count");
 
+        // Callers guarantee the device is idle around arena recreation.
+        NotifyDeviceIdle();
         m_transientUploadArena.Shutdown();
         m_initInfo.frameCount = frameCount;
-        DestroyDeferredResidentReleases();
-        m_deferredResidentReleases.resize(frameCount);
+        DestroyAllDeferredReleases();
+        m_deferredBufferReleases.resize(frameCount);
+        m_deferredResourceReleases.resize(frameCount);
         m_currentFrameIndex = 0;
         return InitializeTransientArenas();
     }
 
     void VkBufferManager::BeginFrame(Uint32 frameIndex) {
-        MOBILEGL_ASSERT(frameIndex < m_deferredResidentReleases.size(),
+        MOBILEGL_ASSERT(frameIndex < m_deferredBufferReleases.size(),
                         "VkBufferManager::BeginFrame frame index out of range");
         m_currentFrameIndex = frameIndex;
-        CollectDeferredResidentReleases(frameIndex);
+        ++m_frameSerial;
+        CollectDeferredReleases(frameIndex);
         m_transientUploadArena.BeginFrame(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
+        // remains busy.
+        if (m_frameSerial > 0) {
+            m_completedSerialFloor = m_frameSerial - 1;
+        }
+    }
+
+    void VkBufferManager::NotifyFrameSerialComplete(Uint64 serial) {
+        // The current serial's work is still being recorded; a completion
+        // report for it (or beyond) can only come from a stale caller.
+        if (serial >= m_frameSerial) {
+            return;
+        }
+        m_completedSerialFloor = std::max(m_completedSerialFloor, serial);
+    }
+
+    void VkBufferManager::SetCopyCommandProvider(IBufferCopyCommandProvider* provider) {
+        m_copyProvider = provider;
+    }
+
+    Uint64 VkBufferManager::GetCompletedSerial() const {
+        const Uint64 frameCount = m_initInfo.frameCount > 0 ? m_initInfo.frameCount : 1;
+        const Uint64 completed = m_frameSerial > frameCount ? m_frameSerial - frameCount : 0;
+        return std::max(completed, m_completedSerialFloor);
+    }
+
+    Bool VkBufferManager::IsResourceBusy(const VkBufferResource& resource) const {
+        return resource.lastUseSerial > GetCompletedSerial();
+    }
+
     Bool VkBufferManager::UploadTransient(BufferKind kind, Uint32 frameIndex, const void* data,
                                           VkDeviceSize size, VkDeviceSize alignment, BufferSlice& outSlice) {
         (void)kind;
@@ -67,7 +184,8 @@ namespace MobileGL::MG_Backend::DirectVulkan {
             .allocator = m_initInfo.allocator,
             .frameCount = m_initInfo.frameCount,
             .usage = VK_BUFFER_USAGE_VERTEX_BUFFER_BIT | VK_BUFFER_USAGE_INDEX_BUFFER_BIT |
-                     VK_BUFFER_USAGE_UNIFORM_BUFFER_BIT | VK_BUFFER_USAGE_INDIRECT_BUFFER_BIT,
+                     VK_BUFFER_USAGE_UNIFORM_BUFFER_BIT | VK_BUFFER_USAGE_INDIRECT_BUFFER_BIT |
+                     VK_BUFFER_USAGE_TRANSFER_SRC_BIT,
             .memoryUsage = m_initInfo.transientMemoryUsage,
             .allocationFlags = m_initInfo.transientAllocationFlags,
             .minBufferSize = m_initInfo.minUploadBytes,
@@ -75,116 +193,394 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         });
     }
 
-    Bool VkBufferManager::SyncResidentBuffer(BufferKind kind,
-                                             const SharedPtr<MG_State::GLState::BufferObject>& bufferObject,
-                                             BufferSlice& outSlice) {
-        const VkBufferUsageFlags requiredUsage = GetVkBufferUsage(kind);
-        MOBILEGL_ASSERT(requiredUsage != 0,
-                        "VkBufferManager::SyncResidentBuffer unsupported resident buffer kind");
-        MOBILEGL_ASSERT(bufferObject != nullptr, "VkBufferManager::SyncResidentBuffer requires valid buffer object");
-        CollectResidentGarbageIfNeeded();
+    VkBufferResource* VkBufferManager::ResourceOf(MG_State::GLState::BufferObject& bufferObject) {
+        return static_cast<VkBufferResource*>(bufferObject.GetBackendResource().get());
+    }
 
-        const auto* bufferData = bufferObject->GetDataReadOnly().get();
-        MOBILEGL_ASSERT(bufferData != nullptr, "VkBufferManager::SyncResidentBuffer requires frontend buffer data");
-        bufferObject->MarkPersistentMappedRangeDirty();
+    VkBufferResource* VkBufferManager::GetOrCreateResource(
+        const SharedPtr<MG_State::GLState::BufferObject>& bufferObject) {
+        // 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 static_cast<VkBufferResource*>(existing.get());
+        }
+        auto resource = MakeShared<VkBufferResource>();
+        VkBufferResource* raw = resource.get();
+        bufferObject->SetBackendResource(resource);
+        TrackLiveResource(resource);
+        return raw;
+    }
 
-        const VkDeviceSize bufferSize = static_cast<VkDeviceSize>(bufferObject->GetSize());
-        if (bufferSize == 0) {
-            MGLOG_E("VkBufferManager::SyncResidentBuffer failed: buffer size is zero");
+    void VkBufferManager::TrackLiveResource(const SharedPtr<VkBufferResource>& resource) {
+        if (m_liveResources.size() >= kLiveResourcePruneThreshold) {
+            std::erase_if(m_liveResources, [](const WeakPtr<VkBufferResource>& weak) { return weak.expired(); });
+        }
+        m_liveResources.push_back(resource);
+    }
+
+    void VkBufferManager::ReleaseAllLiveResources() {
+        for (auto& weak : m_liveResources) {
+            if (auto resource = weak.lock()) {
+                resource->buffer.Destroy();
+                resource->storageSize = 0;
+                resource->usageFlags = 0;
+                resource->lastUseSerial = 0;
+                resource->pendingFullUpload = true;
+                resource->transientSlice = {};
+                resource->transientFrameSerial = 0;
+            }
+        }
+        m_liveResources.clear();
+    }
+
+    Bool VkBufferManager::CreateResidentStorage(VkBufferResource& resource, VkDeviceSize size,
+                                                VkBufferUsageFlags usage, VkMemoryPropertyFlags requiredFlags) {
+        // Staged range copies write resident storage with vkCmdCopyBuffer.
+        usage |= VK_BUFFER_USAGE_TRANSFER_DST_BIT;
+        const Bool created = resource.buffer.Create({
+            .allocator = m_initInfo.allocator,
+            .size = size,
+            .usage = usage,
+            .memoryUsage = VMA_MEMORY_USAGE_AUTO,
+            .allocationFlags = kResidentBufferAllocationFlags,
+            .requiredFlags = requiredFlags,
+        });
+        if (!created || resource.buffer.Map() == nullptr) {
+            MGLOG_E("VkBufferManager::CreateResidentStorage failed (size=%llu)",
+                    static_cast<unsigned long long>(size));
+            resource.buffer.Destroy();
+            resource.storageSize = 0;
+            resource.usageFlags = 0;
             return false;
         }
-
-        auto& entry = m_residentBuffers[bufferObject.get()];
-        entry.aliveRef = bufferObject;
-
-        const auto changeBits = bufferObject->GetChangeBits();
-        const Bool needsRecreate = !entry.buffer.IsValid() || entry.size != bufferSize ||
-                                   ((entry.usage & requiredUsage) != requiredUsage) ||
-                                   (changeBits & BufferChangeBits::PreferReallocationBit);
-        if (needsRecreate) {
-            const VkBufferUsageFlags recreatedUsage = entry.usage | requiredUsage;
-            DeferResidentRelease(std::move(entry.buffer));
-            const Bool created = entry.buffer.Create({
-                .allocator = m_initInfo.allocator,
-                .size = bufferSize,
-                .usage = recreatedUsage,
-                .memoryUsage = VMA_MEMORY_USAGE_AUTO,
-                .allocationFlags = kResidentBufferAllocationFlags,
-            });
-            if (!created || entry.buffer.Map() == nullptr) {
-                MGLOG_E("VkBufferManager::SyncResidentBuffer failed: unable to create resident buffer");
-                entry.buffer.Destroy();
-                entry.size = 0;
-                entry.usage = 0;
-                return false;
-            }
-            if (!entry.buffer.Upload(bufferData->data(), bufferSize, 0)) {
-                MGLOG_E("VkBufferManager::SyncResidentBuffer failed: initial upload failed");
-                entry.buffer.Destroy();
-                entry.size = 0;
-                entry.usage = 0;
-                return false;
-            }
-            entry.size = bufferSize;
-            entry.usage = recreatedUsage;
-            bufferObject->ClearDirty();
-            outSlice = entry.buffer.GetSlice(0, bufferSize);
-            return true;
-        }
-
-        if (changeBits & BufferChangeBits::DirtyBit) {
-            const auto& dirtyRanges = bufferObject->GetDirtyRanges();
-            for (const auto& range : dirtyRanges) {
-                const VkDeviceSize rangeOffset = static_cast<VkDeviceSize>(range.start);
-                const VkDeviceSize rangeSize = static_cast<VkDeviceSize>(range.end - range.start);
-                if (rangeSize == 0) {
-                    continue;
-                }
-                if (!entry.buffer.Upload(bufferData->data() + range.start, rangeSize, rangeOffset)) {
-                    MGLOG_E("VkBufferManager::SyncResidentBuffer failed: dirty range upload failed");
-                    return false;
-                }
-            }
-            bufferObject->ClearDirty();
-        }
-
-        outSlice = entry.buffer.GetSlice(0, bufferSize);
+        resource.storageSize = size;
+        resource.usageFlags = usage;
         return true;
     }
 
-    void VkBufferManager::DowngradeResidentBufferToTransient(const SharedPtr<MG_State::GLState::BufferObject>& bufferObject) {
-        if (bufferObject == nullptr) {
-            return;
+    Bool VkBufferManager::SwapStorageAndUploadAll(VkBufferResource& resource,
+                                                  MG_State::GLState::BufferObject& bufferObject) {
+        const VkDeviceSize size = static_cast<VkDeviceSize>(bufferObject.GetSize());
+        const VkBufferUsageFlags usage = resource.usageFlags;
+        DeferRelease(std::move(resource.buffer));
+        if (!CreateResidentStorage(resource, size, usage)) {
+            resource.pendingFullUpload = true;
+            return false;
         }
-
-        auto it = m_residentBuffers.find(bufferObject.get());
-        if (it == m_residentBuffers.end()) {
-            return;
+        if (!resource.buffer.Upload(bufferObject.MappedData(), size, 0)) {
+            MGLOG_E("VkBufferManager::SwapStorageAndUploadAll: upload failed");
+            resource.pendingFullUpload = true;
+            return false;
         }
-
-        DeferResidentRelease(std::move(it->second.buffer));
-        m_residentBuffers.erase(it);
+        resource.pendingFullUpload = false;
+        return true;
     }
 
-    void VkBufferManager::DeferResidentRelease(VkBufferObject&& buffer) {
+    Bool VkBufferManager::StagedRangeCopy(VkBufferResource& resource, MG_State::GLState::BufferObject& bufferObject,
+                                          SizeT offset, SizeT size) {
+        if (!m_copyProvider) {
+            return false;
+        }
+        BufferSlice staging{};
+        if (!m_transientUploadArena.Upload(m_currentFrameIndex, bufferObject.MappedData() + offset,
+                                           static_cast<VkDeviceSize>(size), 16, staging)) {
+            return false;
+        }
+        VkCommandBuffer commandBuffer = m_copyProvider->AcquireBufferCopyCommandBuffer();
+        if (commandBuffer == VK_NULL_HANDLE) {
+            return false;
+        }
+
+        // Order the copy after every prior read/write of this buffer, both from
+        // in-flight frames (submission order) and from commands already recorded
+        // in this frame's command buffer.
+        VkMemoryBarrier beforeBarrier{VK_STRUCTURE_TYPE_MEMORY_BARRIER};
+        beforeBarrier.srcAccessMask = VK_ACCESS_MEMORY_READ_BIT | VK_ACCESS_MEMORY_WRITE_BIT;
+        beforeBarrier.dstAccessMask = VK_ACCESS_TRANSFER_WRITE_BIT;
+        vkCmdPipelineBarrier(commandBuffer, VK_PIPELINE_STAGE_ALL_COMMANDS_BIT, VK_PIPELINE_STAGE_TRANSFER_BIT, 0, 1,
+                             &beforeBarrier, 0, nullptr, 0, nullptr);
+
+        VkBufferCopy region{};
+        region.srcOffset = staging.offset;
+        region.dstOffset = static_cast<VkDeviceSize>(offset);
+        region.size = static_cast<VkDeviceSize>(size);
+        vkCmdCopyBuffer(commandBuffer, staging.buffer, resource.buffer.GetHandle(), 1, &region);
+
+        VkMemoryBarrier afterBarrier{VK_STRUCTURE_TYPE_MEMORY_BARRIER};
+        afterBarrier.srcAccessMask = VK_ACCESS_TRANSFER_WRITE_BIT;
+        afterBarrier.dstAccessMask = VK_ACCESS_MEMORY_READ_BIT | VK_ACCESS_MEMORY_WRITE_BIT;
+        vkCmdPipelineBarrier(commandBuffer, VK_PIPELINE_STAGE_TRANSFER_BIT, VK_PIPELINE_STAGE_ALL_COMMANDS_BIT, 0, 1,
+                             &afterBarrier, 0, nullptr, 0, nullptr);
+
+        resource.lastUseSerial = m_frameSerial;
+        return true;
+    }
+
+    void VkBufferManager::OnRespecify(MG_State::GLState::BufferObject& bufferObject) {
+        auto* resource = ResourceOf(bufferObject);
+        if (!resource) {
+            return; // lazy: AcquireResidentSlice performs a full upload on creation
+        }
+        // Any cached streaming slice refers to the previous contents.
+        resource->transientFrameSerial = 0;
+        if (!resource->buffer.IsValid()) {
+            return; // streaming-only resource: shadow + serial are enough
+        }
+
+        const VkDeviceSize size = static_cast<VkDeviceSize>(bufferObject.GetSize());
+        if (size == 0) {
+            DeferRelease(std::move(resource->buffer));
+            resource->storageSize = 0;
+            resource->pendingFullUpload = false;
+            return;
+        }
+
+        if (size != resource->storageSize || IsResourceBusy(*resource)) {
+            // Conditional orphan: only swap the storage when the old one is
+            // still referenced by the GPU (or no longer fits).
+            SwapStorageAndUploadAll(*resource, bufferObject);
+            return;
+        }
+
+        if (!resource->buffer.Upload(bufferObject.MappedData(), size, 0)) {
+            MGLOG_E("VkBufferManager::OnRespecify: in-place upload failed");
+            resource->pendingFullUpload = true;
+        }
+    }
+
+    void VkBufferManager::OnSubData(MG_State::GLState::BufferObject& bufferObject, SizeT offset, SizeT size) {
+        auto* resource = ResourceOf(bufferObject);
+        if (!resource) {
+            return;
+        }
+        resource->transientFrameSerial = 0;
+        if (!resource->buffer.IsValid() || resource->pendingFullUpload) {
+            return;
+        }
+        if (static_cast<VkDeviceSize>(bufferObject.GetSize()) != resource->storageSize) {
+            resource->pendingFullUpload = true;
+            return;
+        }
+
+        if (!IsResourceBusy(*resource)) {
+            if (!resource->buffer.Upload(bufferObject.MappedData() + offset,
+                                         static_cast<VkDeviceSize>(size), static_cast<VkDeviceSize>(offset))) {
+                MGLOG_E("VkBufferManager::OnSubData: host upload failed");
+                resource->pendingFullUpload = true;
+            }
+            return;
+        }
+
+        // Busy partial write: stage + GPU copy preserves GL ordering within the
+        // frame and leaves bytes outside the range (possibly GPU-written, e.g.
+        // SSBO) intact. Fall back to a storage swap if staging is unavailable.
+        if (!StagedRangeCopy(*resource, bufferObject, offset, size)) {
+            SwapStorageAndUploadAll(*resource, bufferObject);
+        }
+    }
+
+    void VkBufferManager::OnFlushMappedRange(MG_State::GLState::BufferObject& bufferObject, Range1D range,
+                                             Flags<BufferMappingAccessBit> appAccess) {
+        auto* resource = ResourceOf(bufferObject);
+        if (!resource) {
+            return;
+        }
+        resource->transientFrameSerial = 0;
+        if (!resource->buffer.IsValid() || resource->pendingFullUpload) {
+            return;
+        }
+        if (static_cast<VkDeviceSize>(bufferObject.GetSize()) != resource->storageSize) {
+            resource->pendingFullUpload = true;
+            return;
+        }
+
+        const SizeT offset = range.start;
+        const SizeT size = range.end - range.start;
+        // GL_MAP_UNSYNCHRONIZED_BIT: the app guarantees it does not overwrite
+        // data the GPU is still reading; honour it with a direct host write.
+        if ((appAccess & BufferMappingAccessBit::Unsynchronized) || !IsResourceBusy(*resource)) {
+            if (!resource->buffer.Upload(bufferObject.MappedData() + offset,
+                                         static_cast<VkDeviceSize>(size), static_cast<VkDeviceSize>(offset))) {
+                MGLOG_E("VkBufferManager::OnFlushMappedRange: host upload failed");
+                resource->pendingFullUpload = true;
+            }
+            return;
+        }
+
+        if (!StagedRangeCopy(*resource, bufferObject, offset, size)) {
+            SwapStorageAndUploadAll(*resource, bufferObject);
+        }
+    }
+
+    void VkBufferManager::OnResourceDestroyed(SharedPtr<MG_State::GLState::BackendBufferResource>&& resource) {
+        if (!resource) {
+            return;
+        }
+        auto vkResource = std::static_pointer_cast<VkBufferResource>(std::move(resource));
+        if (!vkResource->buffer.IsValid()) {
+            return;
+        }
+        if (m_deferredResourceReleases.empty()) {
+            vkResource->buffer.Destroy();
+            return;
+        }
+        MOBILEGL_ASSERT(m_currentFrameIndex < m_deferredResourceReleases.size(),
+                        "VkBufferManager::OnResourceDestroyed current frame index out of range");
+        // Keep the whole resource alive until this frame slot's fence has been
+        // waited, then the storage is destroyed with it.
+        m_deferredResourceReleases[m_currentFrameIndex].push_back(std::move(vkResource));
+    }
+
+    void* VkBufferManager::AcquirePersistentMap(MG_State::GLState::BufferObject& bufferObject) {
+        const VkDeviceSize size = static_cast<VkDeviceSize>(bufferObject.GetSize());
+        if (size == 0) {
+            return nullptr;
+        }
+
+        auto resource = std::static_pointer_cast<VkBufferResource>(bufferObject.GetBackendResource());
+        if (!resource) {
+            resource = MakeShared<VkBufferResource>();
+            bufferObject.SetBackendResource(resource);
+            TrackLiveResource(resource);
+        }
+
+        // Idempotent: an already-backed buffer returns the same mapped base.
+        if (resource->persistentMapped && resource->buffer.IsValid() && resource->storageSize == size) {
+            return resource->buffer.GetMappedData();
+        }
+
+        // One-time creation of HOST_VISIBLE + HOST_COHERENT, persistently mapped storage
+        // carrying every usage (never recreated, so the app's pointer never dangles). Seed
+        // 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)) {
+            resource->persistentMapped = false;
+            resource->storageSize = 0;
+            resource->usageFlags = 0;
+            return nullptr;
+        }
+        const Uint8* seed = bufferObject.MappedData();
+        if (seed != nullptr) {
+            resource->buffer.Upload(seed, size, 0);
+        }
+        resource->persistentMapped = true;
+        resource->pendingFullUpload = false;
+        resource->storageSize = size;
+        resource->lastUseSerial = 0;
+        return resource->buffer.GetMappedData();
+    }
+
+    Bool VkBufferManager::AcquireResidentSlice(BufferKind kind,
+                                               const SharedPtr<MG_State::GLState::BufferObject>& bufferObject,
+                                               BufferSlice& outSlice) {
+        const VkBufferUsageFlags requiredUsage = GetVkBufferUsage(kind);
+        MOBILEGL_ASSERT(requiredUsage != 0, "VkBufferManager::AcquireResidentSlice unsupported buffer kind");
+        MOBILEGL_ASSERT(bufferObject != nullptr, "VkBufferManager::AcquireResidentSlice requires valid buffer object");
+
+        auto resource = GetOrCreateResource(bufferObject);
+        bufferObject->SyncPersistentMappedRange();
+
+        const VkDeviceSize size = static_cast<VkDeviceSize>(bufferObject->GetSize());
+        if (size == 0) {
+            MGLOG_E("VkBufferManager::AcquireResidentSlice failed: buffer size is zero");
+            return false;
+        }
+
+        // Zero-copy persistent buffers already hold the app's live coherent writes in
+        // host-visible storage carrying every usage; bind directly, no re-upload/staging.
+        if (resource->persistentMapped && resource->buffer.IsValid() && resource->storageSize == size) {
+            resource->lastUseSerial = m_frameSerial;
+            outSlice = resource->buffer.GetSlice(0, size);
+            return outSlice.IsValid();
+        }
+
+        const Bool needsRecreate = !resource->buffer.IsValid() || resource->storageSize != size ||
+                                   ((resource->usageFlags & requiredUsage) != requiredUsage) ||
+                                   resource->pendingFullUpload;
+        if (needsRecreate) {
+            const VkBufferUsageFlags usage = resource->usageFlags | requiredUsage;
+            DeferRelease(std::move(resource->buffer));
+            if (!CreateResidentStorage(*resource, size, usage)) {
+                return false;
+            }
+            if (!resource->buffer.Upload(bufferObject->MappedData(), size, 0)) {
+                MGLOG_E("VkBufferManager::AcquireResidentSlice failed: initial upload failed");
+                resource->buffer.Destroy();
+                resource->storageSize = 0;
+                resource->usageFlags = 0;
+                return false;
+            }
+            resource->pendingFullUpload = false;
+        }
+
+        resource->lastUseSerial = m_frameSerial;
+        outSlice = resource->buffer.GetSlice(0, size);
+        return true;
+    }
+
+    Bool VkBufferManager::AcquireStreamedSlice(BufferKind kind,
+                                               const SharedPtr<MG_State::GLState::BufferObject>& bufferObject,
+                                               BufferSlice& outSlice) {
+        (void)kind;
+        MOBILEGL_ASSERT(bufferObject != nullptr, "VkBufferManager::AcquireStreamedSlice requires valid buffer object");
+
+        auto resource = GetOrCreateResource(bufferObject);
+        bufferObject->SyncPersistentMappedRange();
+
+        const VkDeviceSize size = static_cast<VkDeviceSize>(bufferObject->GetSize());
+        if (size == 0) {
+            MGLOG_E("VkBufferManager::AcquireStreamedSlice failed: buffer size is zero");
+            return false;
+        }
+
+        const Uint64 changeSerial = bufferObject->GetChangeSerial();
+        if (resource->transientFrameSerial == m_frameSerial && resource->transientChangeSerial == changeSerial &&
+            resource->transientSize == size && resource->transientSlice.IsValid()) {
+            outSlice = resource->transientSlice;
+            return true;
+        }
+
+        if (!m_transientUploadArena.Upload(m_currentFrameIndex, bufferObject->MappedData(), size, 16,
+                                           outSlice)) {
+            return false;
+        }
+        resource->transientSlice = outSlice;
+        resource->transientFrameSerial = m_frameSerial;
+        resource->transientChangeSerial = changeSerial;
+        resource->transientSize = size;
+
+        // Streaming path is authoritative now; release resident storage so we do
+        // not keep a second, stale copy alive (downgrade).
+        if (resource->buffer.IsValid()) {
+            DeferRelease(std::move(resource->buffer));
+            resource->storageSize = 0;
+        }
+        return true;
+    }
+
+    void VkBufferManager::DeferRelease(VkBufferObject&& buffer) {
         if (!buffer.IsValid()) {
             return;
         }
 
-        if (m_deferredResidentReleases.empty()) {
+        if (m_deferredBufferReleases.empty()) {
             buffer.Destroy();
             return;
         }
 
-        MOBILEGL_ASSERT(m_currentFrameIndex < m_deferredResidentReleases.size(),
-                        "VkBufferManager::DeferResidentRelease current frame index out of range");
-        m_deferredResidentReleases[m_currentFrameIndex].push_back(std::move(buffer));
+        MOBILEGL_ASSERT(m_currentFrameIndex < m_deferredBufferReleases.size(),
+                        "VkBufferManager::DeferRelease current frame index out of range");
+        m_deferredBufferReleases[m_currentFrameIndex].push_back(std::move(buffer));
     }
 
-    void VkBufferManager::CollectDeferredResidentReleases(Uint32 frameIndex) {
-        MOBILEGL_ASSERT(frameIndex < m_deferredResidentReleases.size(),
-                        "VkBufferManager::CollectDeferredResidentReleases frame index out of range");
-        m_deferredResidentReleases[frameIndex].clear();
+    void VkBufferManager::CollectDeferredReleases(Uint32 frameIndex) {
+        MOBILEGL_ASSERT(frameIndex < m_deferredBufferReleases.size(),
+                        "VkBufferManager::CollectDeferredReleases frame index out of range");
+        m_deferredBufferReleases[frameIndex].clear();
+        m_deferredResourceReleases[frameIndex].clear();
     }
 
     VkBufferUsageFlags VkBufferManager::GetVkBufferUsage(BufferKind kind) {
@@ -209,46 +605,20 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         }
     }
 
-    void VkBufferManager::CollectResidentGarbageIfNeeded() {
-        ++m_residentGcTick;
-        if (m_residentGcTick < kResidentBufferGCInterval) {
-            return;
-        }
-        CollectResidentGarbageNow();
-        m_residentGcTick = 0;
-    }
-
-    void VkBufferManager::CollectResidentGarbageNow() {
-        Vector<MG_State::GLState::BufferObject*> staleBuffers;
-        staleBuffers.reserve(m_residentBuffers.size());
-
-        for (const auto& [rawBuffer, entry] : m_residentBuffers) {
-            if (entry.aliveRef.expired()) {
-                staleBuffers.push_back(rawBuffer);
+    void VkBufferManager::DestroyAllDeferredReleases() {
+        for (auto& releases : m_deferredBufferReleases) {
+            for (auto& buffer : releases) {
+                buffer.Destroy();
             }
+            releases.clear();
         }
-
-        for (const auto* rawBuffer : staleBuffers) {
-            auto it = m_residentBuffers.find(const_cast<MG_State::GLState::BufferObject*>(rawBuffer));
-            if (it == m_residentBuffers.end()) {
-                continue;
+        m_deferredBufferReleases.clear();
+        for (auto& releases : m_deferredResourceReleases) {
+            for (auto& resource : releases) {
+                resource->buffer.Destroy();
             }
-            DeferResidentRelease(std::move(it->second.buffer));
-            m_residentBuffers.erase(it);
+            releases.clear();
         }
-    }
-
-    void VkBufferManager::DestroyDeferredResidentReleases() {
-        for (auto& deferredReleases : m_deferredResidentReleases) {
-            deferredReleases.clear();
-        }
-        m_deferredResidentReleases.clear();
-    }
-
-    void VkBufferManager::DestroyResidentBuffers() {
-        for (auto& [_, entry] : m_residentBuffers) {
-            entry.buffer.Destroy();
-        }
-        m_residentBuffers.clear();
+        m_deferredResourceReleases.clear();
     }
 } // namespace MobileGL::MG_Backend::DirectVulkan

MobileGL/MG_Backend/DirectVulkan/Renderer/VkBufferManager.h

@@ -33,6 +33,42 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         Bool transientPersistentMapping = false;
     };
 
+    // The DirectVulkan storage behind one frontend buffer (pipe_resource analogue).
+    // Owned (refcounted) by the frontend BufferObject; the manager holds only weak
+    // references (for shutdown) plus strong references on deferred-release lists.
+    class VkBufferResource : public MG_State::GLState::BackendBufferResource {
+    public:
+        ~VkBufferResource() override = default;
+
+        // Resident storage (may be invalid for streaming-only buffers).
+        VkBufferObject buffer;
+        VkDeviceSize storageSize = 0;
+        VkBufferUsageFlags usageFlags = 0;
+        // Frame serial of the last GPU reference; drives busy tracking.
+        Uint64 lastUseSerial = 0;
+        // Set when an immediate op could not be applied; forces a full re-upload
+        // on the next AcquireResidentSlice.
+        Bool pendingFullUpload = false;
+        // Backs a zero-copy coherent persistent map (PipeResource GPU residency): the
+        // buffer is HOST_VISIBLE+COHERENT, persistently mapped, carries every usage and is
+        // never orphaned or recreated. Draw-time acquire binds it directly, no re-upload.
+        Bool persistentMapped = false;
+
+        // Cached transient (streaming) slice for the current frame.
+        BufferSlice transientSlice{};
+        Uint64 transientFrameSerial = 0;
+        Uint64 transientChangeSerial = 0;
+        VkDeviceSize transientSize = 0;
+    };
+
+    // Supplies a command buffer that is recording and outside any render pass,
+    // for staged buffer-range copies. Implemented by VulkanRenderer.
+    class IBufferCopyCommandProvider {
+    public:
+        virtual ~IBufferCopyCommandProvider() = default;
+        virtual VkCommandBuffer AcquireBufferCopyCommandBuffer() = 0;
+    };
+
     class VkBufferManager {
     public:
         Bool Initialize(const VkBufferManagerInitInfo& initInfo);
@@ -41,35 +77,77 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         // Recreate all per-frame transient arenas
         Bool RecreateTransientArenas(Uint32 frameCount);
         void BeginFrame(Uint32 frameIndex);
+        // All previously submitted GPU work has completed (vkDeviceWaitIdle).
+        void NotifyDeviceIdle();
+        // A frame slot's submission fence has been waited: every serial up to
+        // and including `serial` is complete. Raises the completed floor so
+        // GetCompletedSerial reflects real fence progress instead of only the
+        // frameSerial-minus-frameCount inference.
+        void NotifyFrameSerialComplete(Uint64 serial);
+        void SetCopyCommandProvider(IBufferCopyCommandProvider* provider);
 
         Bool UploadTransient(BufferKind kind, Uint32 frameIndex, const void* data, VkDeviceSize size,
                              VkDeviceSize alignment, BufferSlice& outSlice);
-        Bool SyncResidentBuffer(BufferKind kind, const SharedPtr<MG_State::GLState::BufferObject>& bufferObject,
-                                BufferSlice& outSlice);
-        void DowngradeResidentBufferToTransient(const SharedPtr<MG_State::GLState::BufferObject>& bufferObject);
+
+        // Draw-time acquire for resident (device-storage) buffers: ensures the
+        // resource exists and is fully uploaded, marks it used this frame.
+        Bool AcquireResidentSlice(BufferKind kind, const SharedPtr<MG_State::GLState::BufferObject>& bufferObject,
+                                  BufferSlice& outSlice);
+        // Draw-time acquire for streamed buffers: uploads the whole shadow into
+        // the per-frame arena (cached by change serial), releasing any resident
+        // storage the buffer may still own.
+        Bool AcquireStreamedSlice(BufferKind kind, const SharedPtr<MG_State::GLState::BufferObject>& bufferObject,
+                                  BufferSlice& outSlice);
+
+        // Zero-copy persistent map (PipeResource GPU residency): create (once) a
+        // HOST_VISIBLE+COHERENT, persistently mapped resident buffer carrying every usage,
+        // seed it from the shadow, and return its mapped base for the app to write into
+        // directly. Idempotent. Returns nullptr on failure (frontend keeps its shadow).
+        void* AcquirePersistentMap(MG_State::GLState::BufferObject& bufferObject);
+
+        // Immediate ops, dispatched from the frontend BufferBackendOps table.
+        void OnRespecify(MG_State::GLState::BufferObject& bufferObject);
+        void OnSubData(MG_State::GLState::BufferObject& bufferObject, SizeT offset, SizeT size);
+        void OnFlushMappedRange(MG_State::GLState::BufferObject& bufferObject, Range1D range,
+                                Flags<BufferMappingAccessBit> appAccess);
+        void OnResourceDestroyed(SharedPtr<MG_State::GLState::BackendBufferResource>&& resource);
+
+        Uint64 GetFrameSerial() const { return m_frameSerial; }
+        // 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.
+        Uint64 GetCompletedSerial() const;
+        // Busy = potentially referenced by GPU work that has not been fenced yet
+        // (including commands recorded for the current, unsubmitted frame).
+        Bool IsResourceBusy(const VkBufferResource& resource) const;
 
     private:
-        struct ResidentBufferEntry {
-            WeakPtr<MG_State::GLState::BufferObject> aliveRef;
-            VkBufferObject buffer;
-            VkDeviceSize size = 0;
-            VkBufferUsageFlags usage = 0;
-        };
-
         Bool InitializeTransientArenas();
         static VkBufferUsageFlags GetVkBufferUsage(BufferKind kind);
-        void DeferResidentRelease(VkBufferObject&& buffer);
-        void CollectDeferredResidentReleases(Uint32 frameIndex);
-        void CollectResidentGarbageIfNeeded();
-        void CollectResidentGarbageNow();
-        void DestroyDeferredResidentReleases();
-        void DestroyResidentBuffers();
+        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);
+        // Swap storage (conditional orphan) and refill it from the shadow copy.
+        Bool SwapStorageAndUploadAll(VkBufferResource& resource, MG_State::GLState::BufferObject& bufferObject);
+        // Record a staging-slice copy into the resident storage, ordered against
+        // in-flight and already-recorded GPU work.
+        Bool StagedRangeCopy(VkBufferResource& resource, MG_State::GLState::BufferObject& bufferObject,
+                             SizeT offset, SizeT size);
+        void DeferRelease(VkBufferObject&& buffer);
+        void CollectDeferredReleases(Uint32 frameIndex);
+        void DestroyAllDeferredReleases();
+        void TrackLiveResource(const SharedPtr<VkBufferResource>& resource);
+        void ReleaseAllLiveResources();
 
         VkBufferManagerInitInfo m_initInfo{};
         BufferArena m_transientUploadArena;
-        UnorderedMap<MG_State::GLState::BufferObject*, ResidentBufferEntry> m_residentBuffers;
-        Vector<Vector<VkBufferObject>> m_deferredResidentReleases;
+        IBufferCopyCommandProvider* m_copyProvider = nullptr;
+        Vector<Vector<VkBufferObject>> m_deferredBufferReleases;
+        Vector<Vector<SharedPtr<VkBufferResource>>> m_deferredResourceReleases;
+        Vector<WeakPtr<VkBufferResource>> m_liveResources;
         Uint32 m_currentFrameIndex = 0;
-        Uint32 m_residentGcTick = 0;
+        Uint64 m_frameSerial = 1;
+        Uint64 m_completedSerialFloor = 0;
     };
 } // namespace MobileGL::MG_Backend::DirectVulkan

MobileGL/MG_Backend/DirectVulkan/Renderer/VkBufferObject.cpp

@@ -49,11 +49,13 @@ namespace MobileGL::MG_Backend::DirectVulkan {
     }
 
     Bool VkBufferObject::Create(const VkBufferObjectDesc& desc) {
-        return Create(desc.allocator, desc.size, desc.usage, desc.memoryUsage, desc.allocationFlags);
+        return Create(desc.allocator, desc.size, desc.usage, desc.memoryUsage, desc.allocationFlags,
+                      desc.requiredFlags);
     }
 
     Bool VkBufferObject::Create(VmaAllocator allocator, VkDeviceSize size, VkBufferUsageFlags usage,
-                                VmaMemoryUsage memoryUsage, VmaAllocationCreateFlags allocationFlags) {
+                                VmaMemoryUsage memoryUsage, VmaAllocationCreateFlags allocationFlags,
+                                VkMemoryPropertyFlags requiredFlags) {
         MOBILEGL_ASSERT(allocator != nullptr, "VkBufferObject::Create requires valid VMA allocator");
         MOBILEGL_ASSERT(size > 0, "VkBufferObject::Create requires non-zero size");
 
@@ -69,6 +71,7 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         VmaAllocationCreateInfo allocationInfo{};
         allocationInfo.usage = memoryUsage;
         allocationInfo.flags = allocationFlags;
+        allocationInfo.requiredFlags = requiredFlags;
 
         const VkResult result =
             vmaCreateBuffer(m_allocator, &bufferInfo, &allocationInfo, &m_buffer, &m_allocation, nullptr);
@@ -154,6 +157,25 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         return true;
     }
 
+    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");
+
+        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;
+    }
+
     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/MG_Backend/DirectVulkan/Renderer/VkBufferObject.h

@@ -20,6 +20,9 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         VkBufferUsageFlags usage = 0;
         VmaMemoryUsage memoryUsage = VMA_MEMORY_USAGE_AUTO;
         VmaAllocationCreateFlags allocationFlags = 0;
+        // Memory property bits the allocation MUST satisfy (e.g. HOST_VISIBLE|HOST_COHERENT
+        // for a persistently-mapped buffer the app writes into without explicit flushes).
+        VkMemoryPropertyFlags requiredFlags = 0;
     };
 
     class VkBufferObject {
@@ -34,12 +37,14 @@ namespace MobileGL::MG_Backend::DirectVulkan {
 
         Bool Create(const VkBufferObjectDesc& desc);
         Bool Create(VmaAllocator allocator, VkDeviceSize size, VkBufferUsageFlags usage,
-                    VmaMemoryUsage memoryUsage, VmaAllocationCreateFlags allocationFlags = 0);
+                    VmaMemoryUsage memoryUsage, VmaAllocationCreateFlags allocationFlags = 0,
+                    VkMemoryPropertyFlags requiredFlags = 0);
         void Destroy();
 
         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; }

MobileGL/MG_Backend/DirectVulkan/Renderer/VkClearManager.cpp

@@ -12,7 +12,43 @@
 #include "MG_Util/Converters/MGToStr/TextureEnumConverter.h"
 
 namespace MobileGL::MG_Backend::DirectVulkan {
-    static SharedPtr<MG_State::GLState::ITextureObject> GetClearableAttachmentTexture(
+    static Bool IsCubeMapFaceUploadTarget(TextureUploadTarget target) {
+        return target >= TextureUploadTarget::CubeMapPositiveX &&
+               target <= TextureUploadTarget::CubeMapNegativeZ;
+    }
+
+    static Bool PendingClearMatchesTextureIdentity(const PendingClearKey& key, const TextureIdentity& identity) {
+        return key.texture == identity.texture && key.textureLifetimeId == identity.lifetimeId;
+    }
+
+    static Uint32 ResolveAttachmentBaseArrayLayer(TextureUploadTarget target) {
+        if (!IsCubeMapFaceUploadTarget(target)) {
+            return 0;
+        }
+        return static_cast<Uint32>(target) - static_cast<Uint32>(TextureUploadTarget::CubeMapPositiveX);
+    }
+
+    static Uint32 ResolveAttachmentBaseArrayLayer(
+        const MG_State::GLState::FramebufferAttachmentObject& attachment) {
+        if (attachment.IsLayered()) {
+            return 0;
+        }
+        const TextureUploadTarget uploadTarget = attachment.GetTextureUploadTarget();
+        if (!IsCubeMapFaceUploadTarget(uploadTarget)) {
+            return static_cast<Uint32>(std::max(attachment.GetTextureLayer(), 0));
+        }
+        return ResolveAttachmentBaseArrayLayer(uploadTarget);
+    }
+
+    static Uint32 ResolveAttachmentLayerCount(
+        const MG_State::GLState::FramebufferAttachmentObject& attachment) {
+        if (attachment.IsLayered()) {
+            return static_cast<Uint32>(std::max(attachment.GetSize().z(), 1));
+        }
+        return 1u;
+    }
+
+    static const MG_State::GLState::FramebufferAttachmentObject* GetClearableAttachment(
         const MG_State::GLState::FramebufferObject& drawFbo, FramebufferAttachmentType attachmentType) {
         if (attachmentType == FramebufferAttachmentType::None) {
             return nullptr;
@@ -23,7 +59,30 @@ namespace MobileGL::MG_Backend::DirectVulkan {
             return nullptr;
         }
 
-        return attachment.GetTexture();
+        return &attachment;
+    }
+
+    PendingClearKey VkClearManager::MakePendingClearKey(MG_State::GLState::ITextureObject* texture, Uint32 mipLevel,
+                                                        Uint32 baseArrayLayer, Uint32 layerCount) {
+        return PendingClearKey {
+            .texture = texture,
+            .textureLifetimeId = texture ? texture->GetLifetimeId() : 0,
+            .mipLevel = mipLevel,
+            .baseArrayLayer = baseArrayLayer,
+            .layerCount = layerCount,
+        };
+    }
+
+    PendingClearKey VkClearManager::MakePendingClearKey(
+        const MG_State::GLState::FramebufferAttachmentObject& attachment) {
+        MOBILEGL_ASSERT(attachment.IsTexture() && !attachment.IsRenderbuffer(),
+                        "MakePendingClearKey requires a texture framebuffer attachment");
+        auto* texture = attachment.GetTexture().get();
+        MOBILEGL_ASSERT(texture != nullptr, "MakePendingClearKey: texture attachment resolved to null");
+        const Uint32 mipLevel = static_cast<Uint32>(std::max(attachment.GetTextureLevel(), 0));
+        const Uint32 baseArrayLayer = ResolveAttachmentBaseArrayLayer(attachment);
+        const Uint32 layerCount = ResolveAttachmentLayerCount(attachment);
+        return MakePendingClearKey(texture, mipLevel, baseArrayLayer, layerCount);
     }
 
     Bool VkClearManager::Initialize() {
@@ -31,7 +90,74 @@ namespace MobileGL::MG_Backend::DirectVulkan {
     }
 
     void VkClearManager::Shutdown() {
+        const std::lock_guard<std::mutex> lock(m_mutex);
+        m_pendingClears.clear();
+        m_aliveObjects.clear();
+    }
 
+    TextureIdentity VkClearManager::MakeTextureIdentity(MG_State::GLState::ITextureObject* texture) {
+        return TextureIdentity {
+            .texture = texture,
+            .lifetimeId = texture ? texture->GetLifetimeId() : 0,
+        };
+    }
+
+    void VkClearManager::MergeClearPayload(ClearAttachmentPayload& dst, const ClearAttachmentPayload& src) {
+        dst.mask |= src.mask;
+        if ((src.mask & GL_COLOR_BUFFER_BIT) != 0) {
+            dst.color = src.color;
+        }
+        if ((src.mask & GL_DEPTH_BUFFER_BIT) != 0) {
+            dst.depth = src.depth;
+        }
+        if ((src.mask & GL_STENCIL_BUFFER_BIT) != 0) {
+            dst.stencil = src.stencil;
+        }
+    }
+
+    void VkClearManager::ErasePendingClearsForTextureLocked(const TextureIdentity& identity) {
+        Vector<PendingClearKey> keysToErase;
+        keysToErase.reserve(m_pendingClears.size());
+        for (auto it = m_pendingClears.begin(); it != m_pendingClears.end(); ++it) {
+            if (PendingClearMatchesTextureIdentity(it->first, identity)) {
+                keysToErase.emplace_back(it->first);
+            }
+        }
+        for (const auto& key : keysToErase) {
+            m_pendingClears.erase(key);
+        }
+        m_aliveObjects.erase(identity);
+    }
+
+    Bool VkClearManager::LockTextureIdentityLocked(const TextureIdentity& identity,
+                                                   SharedPtr<MG_State::GLState::ITextureObject>& outTexture) {
+        outTexture.reset();
+        if (identity.texture == nullptr) {
+            return false;
+        }
+
+        auto aliveIt = m_aliveObjects.find(identity);
+        if (aliveIt == m_aliveObjects.end()) {
+            ErasePendingClearsForTextureLocked(identity);
+            return false;
+        }
+
+        outTexture = aliveIt->second.lock();
+        if (!outTexture || outTexture.get() != identity.texture || outTexture->GetLifetimeId() != identity.lifetimeId) {
+            ErasePendingClearsForTextureLocked(identity);
+            outTexture.reset();
+            return false;
+        }
+
+        return true;
+    }
+
+    Bool VkClearManager::LockTextureLocked(const PendingClearKey& key,
+                                           SharedPtr<MG_State::GLState::ITextureObject>& outTexture) {
+        return LockTextureIdentityLocked(TextureIdentity{
+            .texture = key.texture,
+            .lifetimeId = key.textureLifetimeId,
+        }, outTexture);
     }
 
     void VkClearManager::QueueClear(GLbitfield mask, const ClearFramebufferPayload& clearPayload,
@@ -40,88 +166,143 @@ namespace MobileGL::MG_Backend::DirectVulkan {
             auto& drawbufs = drawFbo.GetDrawBuffers();
             // This should automatically work on default & offscreen FBO
             for (auto drawbuf: drawbufs) {
-                auto texture = GetClearableAttachmentTexture(drawFbo, drawbuf);
-                if (!texture) {
+                const auto* attachment = GetClearableAttachment(drawFbo, drawbuf);
+                if (!attachment) {
                     continue;
                 }
 
                 QueueClear({
                     .mask = GL_COLOR_BUFFER_BIT,
                     .color = clearPayload.color
-                }, texture);
+                }, *attachment);
 
                 MGLOG_D("%s: %s (texture %d) - color = (%.2f, %.2f, %.2f, %.2f)", __func__,
                     MG_Util::ConvertFramebufferAttachmentTypeToString(drawbuf).c_str(),
-                    texture->GetExternalIndex(),
+                    attachment->GetTexture()->GetExternalIndex(),
                     clearPayload.color[0], clearPayload.color[1], clearPayload.color[2], clearPayload.color[3]);
             }
         }
 
         if (mask & GL_DEPTH_BUFFER_BIT) {
-            auto texture = GetClearableAttachmentTexture(drawFbo, FramebufferAttachmentType::Depth);
-            if (texture) {
+            const auto* attachment = GetClearableAttachment(drawFbo, FramebufferAttachmentType::Depth);
+            if (attachment) {
                 QueueClear({
                     .mask = GL_DEPTH_BUFFER_BIT,
                     .depth = clearPayload.depth,
-                }, texture);
+                }, *attachment);
 
                 MGLOG_D("%s: Depth (texture %d) - depth = (%.2f)", __func__,
-                    texture->GetExternalIndex(), clearPayload.depth);
+                    attachment->GetTexture()->GetExternalIndex(), clearPayload.depth);
             }
         }
 
         if (mask & GL_STENCIL_BUFFER_BIT) {
-            auto texture = GetClearableAttachmentTexture(drawFbo, FramebufferAttachmentType::Stencil);
-            if (texture) {
+            const auto* attachment = GetClearableAttachment(drawFbo, FramebufferAttachmentType::Stencil);
+            if (attachment) {
                 QueueClear({
                     .mask = GL_STENCIL_BUFFER_BIT,
                     .stencil = clearPayload.stencil,
-                }, texture);
+                }, *attachment);
 
                 MGLOG_D("%s: Stencil (texture %d) - stencil = (%u)", __func__,
-                    texture->GetExternalIndex(), clearPayload.stencil);
+                    attachment->GetTexture()->GetExternalIndex(), clearPayload.stencil);
             }
         }
     }
 
     void VkClearManager::QueueClear(const ClearAttachmentPayload& clearPayload,
                                     const SharedPtr<MG_State::GLState::ITextureObject>& texture) {
-        if (clearPayload.mask == 0) {
+        if (clearPayload.mask == 0 || !texture) {
             return;
         }
-        WeakPtr<MG_State::GLState::ITextureObject> weakTexturePtr = texture;
-        if (weakTexturePtr.expired())
+
+        const PendingClearKey key = MakePendingClearKey(texture.get());
+        const std::lock_guard<std::mutex> lock(m_mutex);
+        m_aliveObjects[MakeTextureIdentity(texture.get())] = texture;
+        auto& pending = m_pendingClears[key];
+        MergeClearPayload(pending, clearPayload);
+    }
+
+    void VkClearManager::QueueClear(const ClearAttachmentPayload& clearPayload,
+                                    const MG_State::GLState::FramebufferAttachmentObject& attachment) {
+        if (clearPayload.mask == 0 || !attachment.IsTexture() || attachment.IsRenderbuffer()) {
             return;
-        auto* pTexture = weakTexturePtr.lock().get();
-        m_aliveObjects[pTexture] = weakTexturePtr;
-        auto& pending = m_pendingClears[pTexture];
-        pending.mask |= clearPayload.mask;
-        if (clearPayload.mask & GL_COLOR_BUFFER_BIT) {
-            pending.color = clearPayload.color;
         }
-        if (clearPayload.mask & GL_DEPTH_BUFFER_BIT) {
-            pending.depth = clearPayload.depth;
-        }
-        if (clearPayload.mask & GL_STENCIL_BUFFER_BIT) {
-            pending.stencil = clearPayload.stencil;
+        const auto texture = attachment.GetTexture();
+        if (!texture) {
+            return;
         }
+
+        const PendingClearKey key = MakePendingClearKey(attachment);
+        const std::lock_guard<std::mutex> lock(m_mutex);
+        m_aliveObjects[MakeTextureIdentity(texture.get())] = texture;
+        auto& pending = m_pendingClears[key];
+        MergeClearPayload(pending, clearPayload);
     }
 
     Bool VkClearManager::HasPendingClear(MG_State::GLState::ITextureObject* texture) {
-        return m_pendingClears.find(texture) != m_pendingClears.end();
-    }
-
-    Bool VkClearManager::GetPendingClear(MG_State::GLState::ITextureObject* texture, ClearAttachmentPayload& outPayload) {
-        if (m_aliveObjects.find(texture) == m_aliveObjects.end() ||
-            m_pendingClears.find(texture) == m_pendingClears.end()) {
-            MGLOG_D("%s: Failed getting pending clear for texture %d", __func__, texture->GetExternalIndex());
+        if (texture == nullptr) {
             return false;
         }
 
-        outPayload = m_pendingClears[texture];
-        MGLOG_D("%s: Got pending clear for texture %d (%s), mask=0x%x clear value: color = (%.2f, %.2f, %.2f, %.2f), depth = (%.2f), stencil = (%u)", __func__,
-            texture->GetExternalIndex(),
-            MG_Util::ConvertTextureInternalFormatToString(texture->GetFormat()).c_str(),
+        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) {
+            if (it->first.texture == texture && it->first.textureLifetimeId == lifetimeId) {
+                SharedPtr<MG_State::GLState::ITextureObject> liveTexture;
+                return LockTextureLocked(it->first, liveTexture);
+            }
+        }
+        return false;
+    }
+
+    Bool VkClearManager::HasPendingClear(const PendingClearKey& key) {
+        if (key.texture == nullptr) {
+            return false;
+        }
+
+        const std::lock_guard<std::mutex> lock(m_mutex);
+        if (m_pendingClears.find(key) == m_pendingClears.end()) {
+            return false;
+        }
+
+        SharedPtr<MG_State::GLState::ITextureObject> liveTexture;
+        return LockTextureLocked(key, liveTexture);
+    }
+
+    Bool VkClearManager::HasPendingClear(const MG_State::GLState::FramebufferAttachmentObject& attachment) {
+        if (!attachment.IsTexture() || attachment.IsRenderbuffer() || !attachment.GetTexture()) {
+            return false;
+        }
+        return HasPendingClear(MakePendingClearKey(attachment));
+    }
+
+    Bool VkClearManager::GetPendingClear(const PendingClearKey& key, ClearAttachmentPayload& outPayload) {
+        SharedPtr<MG_State::GLState::ITextureObject> liveTexture;
+        return GetPendingClear(key, outPayload, liveTexture);
+    }
+
+    Bool VkClearManager::GetPendingClear(const PendingClearKey& key, ClearAttachmentPayload& outPayload,
+                                         SharedPtr<MG_State::GLState::ITextureObject>& outTexture) {
+        if (key.texture == nullptr) {
+            return false;
+        }
+
+        const std::lock_guard<std::mutex> lock(m_mutex);
+        if (!LockTextureLocked(key, outTexture)) {
+            return false;
+        }
+        auto it = m_pendingClears.find(key);
+        if (it == m_pendingClears.end()) {
+            outTexture.reset();
+            return false;
+        }
+
+        outPayload = it->second;
+        MGLOG_D("%s: Got pending clear for texture@%p lifetime=%llu, mip=%u layer=%u count=%u mask=0x%x clear value: color = (%.2f, %.2f, %.2f, %.2f), depth = (%.2f), stencil = (%u)", __func__,
+            static_cast<void*>(key.texture),
+            static_cast<unsigned long long>(key.textureLifetimeId),
+            key.mipLevel, key.baseArrayLayer, key.layerCount,
             static_cast<Uint32>(outPayload.mask),
             outPayload.color[0], outPayload.color[1], outPayload.color[2], outPayload.color[3],
             outPayload.depth,
@@ -129,27 +310,93 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         return true;
     }
 
+    Bool VkClearManager::GetPendingClear(const MG_State::GLState::FramebufferAttachmentObject& attachment,
+                                         ClearAttachmentPayload& outPayload) {
+        if (!attachment.IsTexture() || attachment.IsRenderbuffer() || !attachment.GetTexture()) {
+            MGLOG_D("%s: Failed getting pending clear for non-texture framebuffer attachment", __func__);
+            return false;
+        }
+        return GetPendingClear(MakePendingClearKey(attachment), outPayload);
+    }
+
+    Bool VkClearManager::GetPendingClears(MG_State::GLState::ITextureObject* texture,
+                                          Vector<PendingClearEntry>& outEntries) {
+        outEntries.clear();
+        if (texture == nullptr) {
+            return false;
+        }
+
+        const Uint64 lifetimeId = texture->GetLifetimeId();
+        const std::lock_guard<std::mutex> lock(m_mutex);
+        SharedPtr<MG_State::GLState::ITextureObject> liveTexture;
+        if (!LockTextureIdentityLocked(MakeTextureIdentity(texture), liveTexture)) {
+            return false;
+        }
+        for (auto it = m_pendingClears.begin(); it != m_pendingClears.end(); ++it) {
+            if (it->first.texture == texture && it->first.textureLifetimeId == lifetimeId) {
+                outEntries.emplace_back(PendingClearEntry{.key = it->first, .payload = it->second});
+            }
+        }
+        return !outEntries.empty();
+    }
+
     void VkClearManager::PopPendingClear(MG_State::GLState::ITextureObject* texture) {
-        MGLOG_D("%s: Pop pending clear for texture %d", __func__, texture->GetExternalIndex());
-        m_aliveObjects.erase(texture);
-        m_pendingClears.erase(texture);
+        if (texture == nullptr) {
+            return;
+        }
+
+        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);
+        ErasePendingClearsForTextureLocked(identity);
+    }
+
+    void VkClearManager::PopPendingClear(const PendingClearKey& key) {
+        if (key.texture == nullptr) {
+            return;
+        }
+
+        {
+            const std::lock_guard<std::mutex> lock(m_mutex);
+            auto it = m_pendingClears.find(key);
+            if (it != m_pendingClears.end()) {
+                m_pendingClears.erase(it);
+            }
+        }
+
+        MGLOG_D("%s: Pop pending clear for texture@%p lifetime=%llu mip=%u layer=%u count=%u", __func__,
+                static_cast<void*>(key.texture), static_cast<unsigned long long>(key.textureLifetimeId),
+                key.mipLevel, key.baseArrayLayer, key.layerCount);
+    }
+
+    void VkClearManager::PopPendingClear(const MG_State::GLState::FramebufferAttachmentObject& attachment) {
+        if (!attachment.IsTexture() || attachment.IsRenderbuffer() || !attachment.GetTexture()) {
+            return;
+        }
+        PopPendingClear(MakePendingClearKey(attachment));
     }
 
     SizeT VkClearManager::CollectGarbage() {
+        const std::lock_guard<std::mutex> lock(m_mutex);
         m_gcCounter++;
         if (m_gcCounter != 0) {
             return 0;
         }
 
-        SizeT count = 0;
-        for (auto it = m_aliveObjects.begin(); it != m_aliveObjects.end();) {
-            auto current = it++;
-            if (current->second.expired()) {
-                m_pendingClears.erase(current->first);
-                m_aliveObjects.erase(current);
-                ++count;
+        Vector<TextureIdentity> expiredTextures;
+        expiredTextures.reserve(m_aliveObjects.size());
+        for (auto it = m_aliveObjects.begin(); it != m_aliveObjects.end(); ++it) {
+            if (it->second.expired()) {
+                expiredTextures.emplace_back(it->first);
             }
         }
-        return count;
+        if (expiredTextures.empty()) {
+            return 0;
+        }
+
+        for (const auto& identity : expiredTextures) {
+            ErasePendingClearsForTextureLocked(identity);
+        }
+        return expiredTextures.size();
     }
 } // namespace MobileGL::MG_Backend::DirectVulkan

MobileGL/MG_Backend/DirectVulkan/Renderer/VkClearManager.h

@@ -14,6 +14,7 @@
 #include "MG_Util/Math/VectorTypes.h"
 
 #include <Includes.h>
+#include <unordered_map>
 
 namespace MobileGL::MG_Backend::DirectVulkan {
     struct ClearFramebufferPayload {
@@ -29,8 +30,64 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         Uint32 stencil = 0;
     };
 
+    struct PendingClearKey {
+        MG_State::GLState::ITextureObject* texture = nullptr;
+        Uint64 textureLifetimeId = 0;
+        Uint32 mipLevel = 0;
+        Uint32 baseArrayLayer = 0;
+        Uint32 layerCount = 1;
+
+        Bool operator==(const PendingClearKey& other) const {
+            return texture == other.texture && textureLifetimeId == other.textureLifetimeId &&
+                   mipLevel == other.mipLevel &&
+                   baseArrayLayer == other.baseArrayLayer && layerCount == other.layerCount;
+        }
+    };
+
+    struct TextureIdentity {
+        MG_State::GLState::ITextureObject* texture = nullptr;
+        Uint64 lifetimeId = 0;
+
+        Bool operator==(const TextureIdentity& other) const {
+            return texture == other.texture && lifetimeId == other.lifetimeId;
+        }
+    };
+
+    struct PendingClearEntry {
+        PendingClearKey key{};
+        ClearAttachmentPayload payload{};
+    };
+
+    struct PendingClearKeyHash {
+        SizeT operator()(const PendingClearKey& key) const {
+            const SizeT textureHash = std::hash<MG_State::GLState::ITextureObject*>{}(key.texture);
+            const SizeT textureLifetimeHash = std::hash<Uint64>{}(key.textureLifetimeId);
+            const SizeT mipHash = std::hash<Uint32>{}(key.mipLevel);
+            const SizeT layerHash = std::hash<Uint32>{}(key.baseArrayLayer);
+            const SizeT layerCountHash = std::hash<Uint32>{}(key.layerCount);
+            SizeT hash = textureHash;
+            hash ^= textureLifetimeHash + 0x9e3779b9u + (hash << 6) + (hash >> 2);
+            hash ^= mipHash + 0x9e3779b9u + (hash << 6) + (hash >> 2);
+            hash ^= layerHash + 0x9e3779b9u + (hash << 6) + (hash >> 2);
+            hash ^= layerCountHash + 0x9e3779b9u + (hash << 6) + (hash >> 2);
+            return hash;
+        }
+    };
+
+    struct TextureIdentityHash {
+        SizeT operator()(const TextureIdentity& key) const {
+            SizeT hash = std::hash<MG_State::GLState::ITextureObject*>{}(key.texture);
+            hash ^= std::hash<Uint64>{}(key.lifetimeId) + 0x9e3779b9u + (hash << 6) + (hash >> 2);
+            return hash;
+        }
+    };
+
     class VkClearManager {
     public:
+        static PendingClearKey MakePendingClearKey(const MG_State::GLState::FramebufferAttachmentObject& attachment);
+        static PendingClearKey MakePendingClearKey(MG_State::GLState::ITextureObject* texture, Uint32 mipLevel = 0,
+                                                   Uint32 baseArrayLayer = 0, Uint32 layerCount = 1);
+
         Bool Initialize();
         void Shutdown();
 
@@ -38,13 +95,33 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         void QueueClear(
             const ClearAttachmentPayload& clearPayload,
             const SharedPtr<MG_State::GLState::ITextureObject>& texture);
+        void QueueClear(const ClearAttachmentPayload& clearPayload,
+                        const MG_State::GLState::FramebufferAttachmentObject& attachment);
         Bool HasPendingClear(MG_State::GLState::ITextureObject* texture);
-        Bool GetPendingClear(MG_State::GLState::ITextureObject* texture, ClearAttachmentPayload& outPayload);
+        Bool HasPendingClear(const PendingClearKey& key);
+        Bool HasPendingClear(const MG_State::GLState::FramebufferAttachmentObject& attachment);
+        Bool GetPendingClear(const PendingClearKey& key, ClearAttachmentPayload& outPayload);
+        Bool GetPendingClear(const PendingClearKey& key, ClearAttachmentPayload& outPayload,
+                             SharedPtr<MG_State::GLState::ITextureObject>& outTexture);
+        Bool GetPendingClear(const MG_State::GLState::FramebufferAttachmentObject& attachment,
+                             ClearAttachmentPayload& outPayload);
+        Bool GetPendingClears(MG_State::GLState::ITextureObject* texture, Vector<PendingClearEntry>& outEntries);
         void PopPendingClear(MG_State::GLState::ITextureObject* texture);
+        void PopPendingClear(const PendingClearKey& key);
+        void PopPendingClear(const MG_State::GLState::FramebufferAttachmentObject& attachment);
         SizeT CollectGarbage();
     private:
+        static TextureIdentity MakeTextureIdentity(MG_State::GLState::ITextureObject* texture);
+        static void MergeClearPayload(ClearAttachmentPayload& dst, const ClearAttachmentPayload& src);
+        void ErasePendingClearsForTextureLocked(const TextureIdentity& identity);
+        Bool LockTextureIdentityLocked(const TextureIdentity& identity,
+                                      SharedPtr<MG_State::GLState::ITextureObject>& outTexture);
+        Bool LockTextureLocked(const PendingClearKey& key,
+                               SharedPtr<MG_State::GLState::ITextureObject>& outTexture);
+
         Uint8 m_gcCounter = 0;
-        UnorderedMap<MG_State::GLState::ITextureObject*, ClearAttachmentPayload> m_pendingClears;
-        UnorderedMap<MG_State::GLState::ITextureObject*, WeakPtr<MG_State::GLState::ITextureObject>> m_aliveObjects;
+        mutable std::mutex m_mutex;
+        std::unordered_map<PendingClearKey, ClearAttachmentPayload, PendingClearKeyHash> m_pendingClears;
+        std::unordered_map<TextureIdentity, WeakPtr<MG_State::GLState::ITextureObject>, TextureIdentityHash> m_aliveObjects;
     };
 } // namespace MobileGL::MG_Backend::DirectVulkan

MobileGL/MG_Backend/DirectVulkan/Renderer/VkRenderPassManager.h

@@ -16,22 +16,33 @@
 #include "MG_State/GLState/FramebufferState/FramebufferObject.h"
 
 #include <Includes.h>
+#include <vk_mem_alloc.h>
 
 namespace MobileGL::MG_Backend::DirectVulkan {
     enum class TrackedAttachmentTarget : Uint8 {
         Texture,
+        Renderbuffer,
         SwapchainColor,
         SwapchainDepthStencil
     };
 
     struct PendingClearAttachmentInfo {
+        // Index into the render pass attachment descriptions (VkRenderPassBeginInfo::pClearValues space).
         Uint32 attachmentIndex = 0;
-        MG_State::GLState::ITextureObject* texture = nullptr;
+        // 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;
+        ClearAttachmentPayload inlinePayload{};
     };
 
     struct TrackedAttachmentLayoutInfo {
         TrackedAttachmentTarget target = TrackedAttachmentTarget::Texture;
-        MG_State::GLState::ITextureObject* texture = nullptr;
+        WeakPtr<MG_State::GLState::ITextureObject> texture;
+        WeakPtr<MG_State::GLState::RenderbufferObject> renderbuffer;
         Uint32 textureMipLevel = 0;
         Uint32 swapchainImageIndex = 0;
         VkImageLayout finalLayout = VK_IMAGE_LAYOUT_UNDEFINED;
@@ -45,6 +56,8 @@ namespace MobileGL::MG_Backend::DirectVulkan {
 
     DepthStencilAttachmentLoadInfo ResolveDepthStencilAttachmentLoadInfo(
         VkImageLayout trackedLayout, Bool clearDepth, Bool clearStencil);
+    IntVec2 ResolveRenderPassFramebufferExtent(Bool isDefaultFbo, const TextureSize& attachmentExtent,
+                                               VkExtent2D swapchainExtent);
 
     struct RenderPassEntry {
         static inline VkDevice s_device;
@@ -58,8 +71,12 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         Uint32 attachmentCount = 0;
         Uint32 colorAttachmentCount = 0;
         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;
@@ -73,8 +90,10 @@ namespace MobileGL::MG_Backend::DirectVulkan {
             std::swap(attachmentCount, that.attachmentCount);
             std::swap(colorAttachmentCount, that.colorAttachmentCount);
             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,
@@ -86,7 +105,8 @@ namespace MobileGL::MG_Backend::DirectVulkan {
             Uint32 attachmentCount,
             Uint32 colorAttachmentCount,
             Bool hasDepthStencilAttachment,
-            IntVec2 extent, int subpass):
+            VkSampleCountFlagBits sampleCount,
+            IntVec2 extent, Uint32 layers):
             hash(hash),
             renderPass(renderpass),
             framebuffer(framebuffer),
@@ -96,8 +116,9 @@ namespace MobileGL::MG_Backend::DirectVulkan {
             attachmentCount(attachmentCount),
             colorAttachmentCount(colorAttachmentCount),
             hasDepthStencilAttachment(hasDepthStencilAttachment),
+            sampleCount(sampleCount),
             extent(extent),
-            subpass(subpass)
+            layers(layers)
         {}
 
         ~RenderPassEntry() {
@@ -137,8 +158,8 @@ namespace MobileGL::MG_Backend::DirectVulkan {
     public:
         using HashType = Uint64;
         VkRenderPassManager(VkDevice device,
-            const VulkanRendererConfig& config, VkClearManager& clearManager, VkTextureManager& textureManager,
-            SwapchainObject& swapchainObject);
+            VkPhysicalDevice physicalDevice, VmaAllocator allocator, const VulkanRendererConfig& config,
+            VkClearManager& clearManager, VkTextureManager& textureManager, SwapchainObject& swapchainObject);
         ~VkRenderPassManager();
 
         Bool Initialize();
@@ -147,23 +168,87 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         HashType ComputeHash(
             const MG_State::GLState::FramebufferObject& fbo,
             Uint32 swapchainImageIndex,
-            Bool includePendingClear = true) const;
+            Bool includePendingClear = true);
         RenderPassEntry& GetOrCreateRenderPass(const MG_State::GLState::FramebufferObject& fbo, Uint32 swapchainImageIndex);
+        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();
     private:
         VkDevice m_device = VK_NULL_HANDLE;
+        VkPhysicalDevice m_physicalDevice = VK_NULL_HANDLE;
+        VmaAllocator m_allocator = nullptr;
         const VulkanRendererConfig& m_config;
         VkClearManager& m_clearManager;
         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;
+
+        // 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;
+
+        // 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 /
+        // version change, swapchain rotation, any attachment image recreation (the two epochs),
+        // or a pending clear. Portable to Vulkan 1.1 (no dynamic_rendering / imageless FB needed).
+        Bool m_rpFastValid = false;
+        const MG_State::GLState::FramebufferObject* m_rpFastFbo = nullptr;
+        Uint16 m_rpFastFboVersion = 0;
+        Uint32 m_rpFastSwapchainIndex = 0;
+        Uint64 m_rpFastTexEpoch = 0;
+        Uint64 m_rpFastRbEpoch = 0;
+        Uint64 m_rpFastRenderPassHash = 0;
+
+        struct RenderbufferResource {
+            WeakPtr<MG_State::GLState::RenderbufferObject> renderbuffer;
+            VkImage image = VK_NULL_HANDLE;
+            VmaAllocation allocation = nullptr;
+            VkImageView view = VK_NULL_HANDLE;
+            VkImageLayout layout = VK_IMAGE_LAYOUT_UNDEFINED;
+            VkFormat format = VK_FORMAT_UNDEFINED;
+            VkImageAspectFlags aspect = VK_IMAGE_ASPECT_NONE;
+            VkExtent2D extent = {0, 0};
+            VkSampleCountFlagBits sampleCount = VK_SAMPLE_COUNT_1_BIT;
+            TextureInternalFormat internalFormat = TextureInternalFormat::Unknown;
+            Int samples = 0;
+
+            void Destroy(VkDevice device, VmaAllocator allocator);
+        };
+
+        struct PendingRenderbufferClear {
+            WeakPtr<MG_State::GLState::RenderbufferObject> renderbuffer;
+            ClearAttachmentPayload payload{};
+        };
+
+        UnorderedMap<MG_State::GLState::RenderbufferObject*, RenderbufferResource> m_renderbufferResources;
+        UnorderedMap<MG_State::GLState::RenderbufferObject*, PendingRenderbufferClear> m_pendingRenderbufferClears;
+
+        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();
+
         static inline XXH64_state_t* m_hashState = XXH64_createState();
         static inline ActiveRenderPassInfo s_activeRenderPass{};
         static inline Bool s_hasActiveRenderPass = false;
         static inline VkClearManager* s_clearManager = nullptr;
         static inline VkTextureManager* s_textureManager = nullptr;
         static inline SwapchainObject* s_swapchainObject = nullptr;
+        static inline VkRenderPassManager* s_renderPassManager = nullptr;
     };
 } // namespace MobileGL::MG_Backend::DirectVulkan

MobileGL/MG_Backend/DirectVulkan/Renderer/VkSamplerManager.cpp

@@ -58,11 +58,26 @@ 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) {
@@ -77,10 +92,13 @@ namespace MobileGL::MG_Backend::DirectVulkan {
     }
 
     Uint64 VkSamplerManager::BuildSamplerKey(const MG_State::GLState::SamplerObject& sampler,
-                                             const MG_State::GLState::ITextureObject& texture) const {
+                                             const MG_State::GLState::ITextureObject& texture,
+                                             Bool forceNearestFiltering) 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)));
+
         const auto minFilter = sampler.GetMinFilter();
         XXHASH_VERIFY(XXH64_update(m_hashState, &minFilter, sizeof(minFilter)));
         const auto magFilter = sampler.GetMagFilter();
@@ -99,6 +117,11 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         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);
@@ -109,8 +132,9 @@ 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) {
+        const Uint64 key = BuildSamplerKey(sampler, texture, forceNearestFiltering);
         auto it = m_samplers.find(key);
         if (it != m_samplers.end()) {
             return it->second.handle;
@@ -118,15 +142,19 @@ namespace MobileGL::MG_Backend::DirectVulkan {
 
         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 ? 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);

MobileGL/MG_Backend/DirectVulkan/Renderer/VkSamplerManager.h

@@ -24,13 +24,18 @@ 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();
 
     VkSampler GetOrCreateSampler(const MG_State::GLState::SamplerObject& sampler,
-                                 const MG_State::GLState::ITextureObject& texture);
+                                 const MG_State::GLState::ITextureObject& texture,
+                                 Bool forceNearestFiltering = false);
 
 private:
     struct SamplerCacheEntry {
@@ -40,7 +45,8 @@ private:
     };
 
     Uint64 BuildSamplerKey(const MG_State::GLState::SamplerObject& sampler,
-                           const MG_State::GLState::ITextureObject& texture) const;
+                           const MG_State::GLState::ITextureObject& texture,
+                           Bool forceNearestFiltering) const;
     static VkFilter ToVkFilter(SamplerFilterMode mode);
     static VkSamplerMipmapMode ToVkMipmapMode(SamplerMipmapMode mode);
     static VkSamplerAddressMode ToVkAddressMode(SamplerWrapMode mode);
@@ -49,9 +55,17 @@ private:
                                                  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;
     static inline XXH64_state_t* m_hashState = XXH64_createState();
 };

MobileGL/MG_Backend/DirectVulkan/Renderer/VkTextureManager.h

@@ -12,14 +12,39 @@
 #include <Includes.h>
 #include <MG_State/GLState/TextureState/TextureObject.h>
 #include <vk_mem_alloc.h>
+#include <unordered_map>
 
 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; }
+
+    struct TextureIdentity {
+        MG_State::GLState::ITextureObject* texture = nullptr;
+        Uint64 lifetimeId = 0;
+
+        Bool operator==(const TextureIdentity& other) const {
+            return texture == other.texture && lifetimeId == other.lifetimeId;
+        }
+    };
+
+    struct TextureIdentityHash {
+        SizeT operator()(const TextureIdentity& key) const {
+            SizeT hash = std::hash<MG_State::GLState::ITextureObject*>{}(key.texture);
+            hash ^= std::hash<Uint64>{}(key.lifetimeId) + 0x9e3779b9u + (hash << 6) + (hash >> 2);
+            return hash;
+        }
+    };
+
     struct InitInfo {
         VkDevice device = VK_NULL_HANDLE;
         VkPhysicalDevice physicalDevice = VK_NULL_HANDLE;
@@ -30,12 +55,95 @@ public:
     };
 
     struct TextureResource {
+        struct AttachmentViewKey {
+            Uint32 mipLevel = 0;
+            Uint32 baseArrayLayer = 0;
+            Uint32 layerCount = 1;
+            VkImageViewType viewType = VK_IMAGE_VIEW_TYPE_2D;
+
+            Bool operator==(const AttachmentViewKey& other) const {
+                return mipLevel == other.mipLevel &&
+                       baseArrayLayer == other.baseArrayLayer &&
+                       layerCount == other.layerCount &&
+                       viewType == other.viewType;
+            }
+        };
+
+        struct AttachmentViewKeyHash {
+            SizeT operator()(const AttachmentViewKey& 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);
+                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;
+            }
+        };
+
         VkImage image = VK_NULL_HANDLE;
         VmaAllocation allocation = nullptr;
         VkImageView fullView = VK_NULL_HANDLE;
         VkImageView sampledView = VK_NULL_HANDLE;
         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;
@@ -46,7 +154,16 @@ public:
         VkFormat format = VK_FORMAT_UNDEFINED;
         VkImageAspectFlags aspect = VK_IMAGE_ASPECT_NONE;
         VkImageViewType viewType = VK_IMAGE_VIEW_TYPE_2D;
+        VkSampleCountFlagBits sampleCount = VK_SAMPLE_COUNT_1_BIT;
+        VkImageCreateFlags imageCreateFlags = 0;
         Uint16 syncedTextureParamsVersion = 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;
+        // Snapshot of the defined mip-level count at the last sync. Folded into the early-out key
+        // as defense-in-depth: any path that grows the level set (which resizes the sampled view)
+        // busts the skip even if it failed to bump the content version.
+        Uint32 syncedMipLevelCount = 0;
 
         TextureResource() = default;
         TextureResource(const TextureResource&) = delete;
@@ -57,6 +174,9 @@ public:
             std::swap(this->sampledView, that.sampledView);
             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);
@@ -67,7 +187,11 @@ public:
             std::swap(this->format, that.format);
             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->syncedTextureParamsVersion, that.syncedTextureParamsVersion);
+            std::swap(this->syncedContentVersion, that.syncedContentVersion);
+            std::swap(this->syncedMipLevelCount, that.syncedMipLevelCount);
         }
 
         void Reset() {
@@ -87,6 +211,21 @@ public:
                     vkDestroyImageView(s_device, sampledView, nullptr);
                 }
             }
+            for (const auto& [_, attachmentView] : attachmentViews) {
+                if (attachmentView != VK_NULL_HANDLE) {
+                    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);
             }
@@ -94,6 +233,9 @@ public:
             sampledView = VK_NULL_HANDLE;
             perMipViews.clear();
             perMipSampledViews.clear();
+            attachmentViews.clear();
+            alternateSampledViews.clear();
+            storageImageViews.clear();
             image = VK_NULL_HANDLE;
             allocation = nullptr;
             layout = VK_IMAGE_LAYOUT_UNDEFINED;
@@ -106,7 +248,11 @@ public:
             format = VK_FORMAT_UNDEFINED;
             aspect = VK_IMAGE_ASPECT_NONE;
             viewType = VK_IMAGE_VIEW_TYPE_2D;
+            sampleCount = VK_SAMPLE_COUNT_1_BIT;
+            imageCreateFlags = 0;
             syncedTextureParamsVersion = 0;
+            syncedContentVersion = 0;
+            syncedMipLevelCount = 0;
         }
 
         ~TextureResource() {
@@ -124,7 +270,13 @@ public:
     TextureResource* SyncTextureAndGetDescriptor(
         MG_State::GLState::ITextureObject& texture);
     VkImageView GetOrCreateViewAtMipLevel(MG_State::GLState::ITextureObject& texture, Uint32 mipLevel);
+    VkImageView GetOrCreateAttachmentViewAtMipLevel(MG_State::GLState::ITextureObject& texture, Uint32 mipLevel,
+                                                    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,
@@ -134,6 +286,9 @@ public:
     Bool TransitionTextureForStorageImage(VkCommandBuffer commandBuffer, MG_State::GLState::ITextureObject& texture);
 
     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,
@@ -143,7 +298,33 @@ public:
                                Uint32 layerCount = 1);
 
     SizeT CollectGarbage();
+
+    // Per-draw sync memo. Within a single SetupDraw the same sampled texture is
+    // resolved ~3x (SetupDraw's layout-probe loop, its post-transition loop, and
+    // again inside ResolveSamplerDescriptor). No GL texture mutation can happen
+    // mid-SetupDraw, and layout is tracked on the TextureResource independently of
+    // SyncTexture, so after the first successful sync of a texture in a draw the
+    // heavy SyncTexture work (mip-completeness/resource/view resync + dirty scan)
+    // is pure redundancy. BeginDrawSyncScope opens a window in which repeat
+    // SyncTextureAndGetDescriptor calls short-circuit to the already-synced
+    // resource; EndDrawSyncScope closes it. Use the RAII DrawSyncScope guard.
+    void BeginDrawSyncScope();
+    void EndDrawSyncScope();
+
+    // RAII guard that opens/closes a per-draw sync memo window (see above).
+    class DrawSyncScope {
+    public:
+        explicit DrawSyncScope(VkTextureManager& manager) : m_manager(manager) { m_manager.BeginDrawSyncScope(); }
+        ~DrawSyncScope() { m_manager.EndDrawSyncScope(); }
+        DrawSyncScope(const DrawSyncScope&) = delete;
+        DrawSyncScope& operator=(const DrawSyncScope&) = delete;
+    private:
+        VkTextureManager& m_manager;
+    };
+
 private:
+    // Bumped in SyncTextureResource right after vmaCreateImage(texture). See GetTextureImageEpoch().
+    Uint64 m_textureImageEpoch = 1;
 
     Bool SyncTexture(MG_State::GLState::ITextureObject &texture,
                      TextureResource &outResource);
@@ -154,8 +335,10 @@ private:
     Bool SyncTextureViews(const MG_State::GLState::ITextureObject& texture, TextureResource& resource);
     VkImageView CreateImageView(VkImage image, VkFormat format, VkImageAspectFlags aspect,
                                 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);
@@ -172,6 +355,9 @@ private:
     void DeferViewRelease(VkImageView view);
     void CollectDeferredReleases(Uint32 frameIndex);
     void DestroyDeferredReleases();
+    static TextureIdentity MakeTextureIdentity(MG_State::GLState::ITextureObject* texture);
+    void EraseTrackedTexture(const TextureIdentity& identity);
+    void PruneStaleTextureAliases(MG_State::GLState::ITextureObject* texture);
 
     VkDevice m_device = VK_NULL_HANDLE;
     VkPhysicalDevice m_physicalDevice = VK_NULL_HANDLE;
@@ -181,8 +367,20 @@ private:
     Uint32 m_currentFrameIndex = 0;
 
     Uint8 m_gcCounter = 0;
-    UnorderedMap<MG_State::GLState::ITextureObject*, WeakPtr<MG_State::GLState::ITextureObject>> m_aliveObjects;
-    UnorderedMap<MG_State::GLState::ITextureObject*, TextureResource> m_textureResources;
+    // Active only between BeginDrawSyncScope/EndDrawSyncScope; identities of
+    // textures already fully synced in the current draw (small N -> flat scan).
+    Bool m_drawSyncScopeActive = false;
+    // Per-draw sync memo: the identity plus the resolved resource pointer. The pointer is stable
+    // across rehash in the node-based m_textureResources and stays valid for the draw (a texture
+    // synced this draw is alive and is not erased mid-draw), so a repeat sync of the same texture
+    // returns the resource without re-hashing the identity into m_textureResources.
+    struct DrawSyncedTexture {
+        TextureIdentity identity;
+        TextureResource* resource = nullptr;
+    };
+    Vector<DrawSyncedTexture> m_drawSyncedThisDraw;
+    std::unordered_map<TextureIdentity, WeakPtr<MG_State::GLState::ITextureObject>, TextureIdentityHash> m_aliveObjects;
+    std::unordered_map<TextureIdentity, TextureResource, TextureIdentityHash> m_textureResources;
     Vector<Vector<TextureResource>> m_deferredReleases;
     Vector<Vector<VkImageView>> m_deferredViewReleases;
 };

MobileGL/MG_Backend/DirectVulkan/Renderer/VkTimerQueryManager.cpp

@@ -0,0 +1,179 @@
+// MobileGL - MobileGL/MG_Backend/DirectVulkan/Renderer/VkTimerQueryManager.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 "VkTimerQueryManager.h"
+
+namespace MobileGL::MG_Backend::DirectVulkan {
+    Bool VkTimerQueryManager::Initialize(const InitInfo& initInfo) {
+        Shutdown();
+
+        MOBILEGL_ASSERT(initInfo.device != VK_NULL_HANDLE, "VkTimerQueryManager::Initialize requires valid VkDevice");
+        MOBILEGL_ASSERT(initInfo.frameCount > 0, "VkTimerQueryManager::Initialize requires non-zero frame count");
+        if (initInfo.timestampValidBits == 0 || initInfo.timestampPeriodNs <= 0.0f || initInfo.slotsPerPool == 0) {
+            MGLOG_W("VkTimerQueryManager: timestamps unsupported (validBits=%u, period=%f, slots=%u)",
+                    initInfo.timestampValidBits, initInfo.timestampPeriodNs, initInfo.slotsPerPool);
+            return false;
+        }
+
+        m_device = initInfo.device;
+        m_timestampPeriodNs = initInfo.timestampPeriodNs;
+        m_validBitsMask = initInfo.timestampValidBits >= 64
+                              ? ~0ull
+                              : ((1ull << initInfo.timestampValidBits) - 1ull);
+        m_slotsPerPool = initInfo.slotsPerPool;
+        m_pools.resize(initInfo.frameCount);
+
+        VkQueryPoolCreateInfo poolInfo{};
+        poolInfo.sType = VK_STRUCTURE_TYPE_QUERY_POOL_CREATE_INFO;
+        poolInfo.queryType = VK_QUERY_TYPE_TIMESTAMP;
+        poolInfo.queryCount = m_slotsPerPool;
+        for (auto& poolState : m_pools) {
+            const VkResult result = vkCreateQueryPool(m_device, &poolInfo, nullptr, &poolState.pool);
+            if (result != VK_SUCCESS) {
+                MGLOG_E("VkTimerQueryManager: vkCreateQueryPool failed with %s", VkResultToString(result));
+                Shutdown();
+                return false;
+            }
+        }
+        return true;
+    }
+
+    void VkTimerQueryManager::Shutdown() {
+        if (m_device != VK_NULL_HANDLE) {
+            for (auto& poolState : m_pools) {
+                if (poolState.pool != VK_NULL_HANDLE) {
+                    vkDestroyQueryPool(m_device, poolState.pool, nullptr);
+                }
+            }
+        }
+        // Records the frontend still holds simply stay unharvested; their
+        // results read back as 0.
+        m_pools.clear();
+        m_device = VK_NULL_HANDLE;
+        m_timestampPeriodNs = 0.0f;
+        m_validBitsMask = 0;
+        m_slotsPerPool = 0;
+    }
+
+    void VkTimerQueryManager::OnFrameCommandRecordingBegan(VkCommandBuffer commandBuffer, Uint32 frameIndex,
+                                                           Uint64 frameSerial) {
+        MOBILEGL_ASSERT(frameIndex < m_pools.size(), "VkTimerQueryManager frame index out of range");
+        auto& poolState = m_pools[frameIndex];
+        if (poolState.preparedFrameSerial == frameSerial) {
+            // Recording re-began within the same frame (mid-frame readback
+            // submit or the Present layout transition); the pool was already
+            // harvested and reset for this cycle, and resetting again would
+            // clobber timestamps written earlier in the frame.
+            return;
+        }
+
+        // Harvest what the pool's previous cycle left behind. The frame slot's
+        // fence was waited before re-recording, so every executed query is
+        // already available and the reads return immediately.
+        DrainPoolPending(poolState);
+
+        vkCmdResetQueryPool(commandBuffer, poolState.pool, 0, m_slotsPerPool);
+        poolState.cursor = 0;
+        poolState.exhaustionWarned = false;
+        poolState.preparedFrameSerial = frameSerial;
+    }
+
+    SharedPtr<VkTimerQueryManager::TimestampRecord> VkTimerQueryManager::WriteTimestamp(VkCommandBuffer commandBuffer,
+                                                                                        Uint32 frameIndex,
+                                                                                        Uint64 frameSerial) {
+        MOBILEGL_ASSERT(frameIndex < m_pools.size(), "VkTimerQueryManager frame index out of range");
+        auto& poolState = m_pools[frameIndex];
+        if (poolState.cursor >= m_slotsPerPool) {
+            if (!poolState.exhaustionWarned) {
+                MGLOG_W("VkTimerQueryManager: frame %u timestamp pool exhausted (%u slots); further timer queries "
+                        "this frame fall back to the frontend path",
+                        frameIndex, m_slotsPerPool);
+                poolState.exhaustionWarned = true;
+            }
+            return nullptr;
+        }
+
+        auto record = MakeShared<TimestampRecord>();
+        record->poolIndex = frameIndex;
+        record->slot = poolState.cursor++;
+        record->frameSerial = frameSerial;
+        vkCmdWriteTimestamp(commandBuffer, VK_PIPELINE_STAGE_BOTTOM_OF_PIPE_BIT, poolState.pool, record->slot);
+        poolState.pendingRecords.push_back(record);
+        return record;
+    }
+
+    Bool VkTimerQueryManager::TryHarvest(TimestampRecord& record) {
+        if (record.harvested) {
+            return true;
+        }
+        if (m_device == VK_NULL_HANDLE || record.poolIndex >= m_pools.size()) {
+            return false;
+        }
+
+        Uint64 resultWithAvailability[2] = {0, 0};
+        const VkResult result = vkGetQueryPoolResults(
+            m_device, m_pools[record.poolIndex].pool, record.slot, 1, sizeof(resultWithAvailability),
+            resultWithAvailability, sizeof(Uint64), VK_QUERY_RESULT_64_BIT | VK_QUERY_RESULT_WITH_AVAILABILITY_BIT);
+        if (result != VK_SUCCESS && result != VK_NOT_READY) {
+            MGLOG_E("VkTimerQueryManager: vkGetQueryPoolResults failed with %s", VkResultToString(result));
+            return false;
+        }
+        if (resultWithAvailability[1] == 0) {
+            return false;
+        }
+        record.rawTicks = resultWithAvailability[0];
+        record.harvested = true;
+        return true;
+    }
+
+    void VkTimerQueryManager::InvalidatePendingRecords() {
+        for (auto& poolState : m_pools) {
+            DrainPoolPending(poolState);
+            // Force a harvest-free reset cycle the next time this pool's frame
+            // begins recording.
+            poolState.preparedFrameSerial = 0;
+        }
+    }
+
+    void VkTimerQueryManager::DrainPoolPending(PoolState& poolState) {
+        for (auto& record : poolState.pendingRecords) {
+            if (record->harvested) {
+                continue;
+            }
+            if (!TryHarvest(*record)) {
+                // The commands carrying this timestamp never executed (they
+                // were dropped, e.g. by a swapchain recreation mid-frame).
+                // Mark the record resolved-as-invalid so waits on it cannot
+                // hang; its result reads back as 0.
+                record->harvested = true;
+                record->valid = false;
+            }
+        }
+        poolState.pendingRecords.clear();
+    }
+
+    Uint64 VkTimerQueryManager::MaskToValidBits(Uint64 ticks) const {
+        return ticks & m_validBitsMask;
+    }
+
+    Uint64 VkTimerQueryManager::ElapsedNs(const TimestampRecord& begin, const TimestampRecord& end) const {
+        if (!begin.valid || !end.valid) {
+            return 0;
+        }
+        const Uint64 deltaTicks = MaskToValidBits(end.rawTicks - begin.rawTicks);
+        return static_cast<Uint64>(static_cast<double>(deltaTicks) * static_cast<double>(m_timestampPeriodNs));
+    }
+
+    Uint64 VkTimerQueryManager::TimestampNs(const TimestampRecord& record) const {
+        if (!record.valid) {
+            return 0;
+        }
+        return static_cast<Uint64>(static_cast<double>(MaskToValidBits(record.rawTicks)) *
+                                   static_cast<double>(m_timestampPeriodNs));
+    }
+} // namespace MobileGL::MG_Backend::DirectVulkan

MobileGL/MG_Backend/DirectVulkan/Renderer/VkTimerQueryManager.h

@@ -0,0 +1,111 @@
+// MobileGL - MobileGL/MG_Backend/DirectVulkan/Renderer/VkTimerQueryManager.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 "../VkIncludes.h"
+#include <Includes.h>
+
+namespace MobileGL::MG_Backend::DirectVulkan {
+    // GPU timestamp storage backing the GL timer-query frontend (GL_TIME_ELAPSED
+    // spans and GL_TIMESTAMP one-shots): one VkQueryPool of timestamp slots per
+    // frame in flight.
+    //
+    // Per-frame lifecycle: right after a frame slot's command buffer begins
+    // recording (and before any render pass, since vkCmdResetQueryPool must be
+    // recorded outside one), OnFrameCommandRecordingBegan harvests every
+    // not-yet-read slot of the pool about to be reused (the slot's frame fence
+    // was waited before re-recording, so the results are already available),
+    // records a reset of the whole pool, and rewinds the allocation cursor.
+    class VkTimerQueryManager {
+    public:
+        // One vkCmdWriteTimestamp landing spot. Shared (via SharedPtr) between
+        // the frontend-held query object and the owning pool's pending list, so
+        // deleting a query while its result is still in flight never leaves the
+        // pool with a dangling record.
+        struct TimestampRecord {
+            Uint32 poolIndex = 0;
+            Uint32 slot = 0;
+            // VkBufferManager frame serial current when the timestamp was
+            // recorded; result availability is bounded by its completion.
+            Uint64 frameSerial = 0;
+            Bool harvested = false;
+            // Cleared when the recorded commands were dropped before they could
+            // execute (swapchain recreation abandons the in-progress command
+            // buffer); the result then reads back as 0.
+            Bool valid = true;
+            Uint64 rawTicks = 0;
+        };
+
+        struct InitInfo {
+            VkDevice device = VK_NULL_HANDLE;
+            Uint32 frameCount = 0;
+            Uint32 timestampValidBits = 0;
+            Float timestampPeriodNs = 0.0f; // nanoseconds per timestamp tick
+            Uint32 slotsPerPool = 128;
+        };
+
+        Bool Initialize(const InitInfo& initInfo);
+        // The caller guarantees the device is idle (same contract as the other
+        // DirectVulkan managers' Shutdown paths).
+        void Shutdown();
+
+        // The per-frame hook described in the class comment. Re-begins within
+        // the same frame serial (mid-frame readback submits, the Present layout
+        // transition) are skipped so already-written slots survive.
+        void OnFrameCommandRecordingBegan(VkCommandBuffer commandBuffer, Uint32 frameIndex, Uint64 frameSerial);
+
+        // Allocates a slot from the frame's pool and records a bottom-of-pipe
+        // vkCmdWriteTimestamp (valid both inside and outside a render pass).
+        // Returns null on pool exhaustion, with one warning per pool cycle; the
+        // frontend falls back gracefully on a null handle.
+        SharedPtr<TimestampRecord> WriteTimestamp(VkCommandBuffer commandBuffer, Uint32 frameIndex,
+                                                  Uint64 frameSerial);
+
+        // Non-blocking single-slot read (WITH_AVAILABILITY, no WAIT). Returns
+        // true once the record holds its raw ticks. Callers gate this on the
+        // record's frame serial being complete.
+        Bool TryHarvest(TimestampRecord& record);
+
+        // Reads every pending result that is available (the caller guarantees
+        // the device is idle) and marks the rest invalid. Called when recorded
+        // but unsubmitted commands are dropped (swapchain recreation), which
+        // would otherwise leave slots that never become available. Each pool is
+        // reset lazily on its next OnFrameCommandRecordingBegan.
+        void InvalidatePendingRecords();
+
+        // end - begin using unsigned wrap arithmetic masked to the queue's
+        // timestampValidBits, converted to nanoseconds. 0 if either record was
+        // invalidated.
+        Uint64 ElapsedNs(const TimestampRecord& begin, const TimestampRecord& end) const;
+        // Raw GPU timestamp converted to nanoseconds. 0 if invalidated.
+        Uint64 TimestampNs(const TimestampRecord& record) const;
+
+    private:
+        struct PoolState {
+            VkQueryPool pool = VK_NULL_HANDLE;
+            Uint32 cursor = 0;
+            // Frame serial the pool was last harvested + reset for; guards
+            // against double resets when recording re-begins mid-frame.
+            Uint64 preparedFrameSerial = 0;
+            Bool exhaustionWarned = false;
+            Vector<SharedPtr<TimestampRecord>> pendingRecords;
+        };
+
+        Uint64 MaskToValidBits(Uint64 ticks) const;
+        // Harvest (or invalidate, when the result never became available)
+        // every pending record of a pool and clear its pending list.
+        void DrainPoolPending(PoolState& pool);
+
+        VkDevice m_device = VK_NULL_HANDLE;
+        Float m_timestampPeriodNs = 0.0f;
+        Uint64 m_validBitsMask = 0;
+        Uint32 m_slotsPerPool = 0;
+        Vector<PoolState> m_pools;
+    };
+} // namespace MobileGL::MG_Backend::DirectVulkan

MobileGL/MG_Backend/DirectVulkan/Renderer/VulkanRenderer.h

@@ -20,6 +20,7 @@
 #include "VkRenderPassManager.h"
 #include "VkSamplerManager.h"
 #include "VkTextureManager.h"
+#include "VkTimerQueryManager.h"
 #include "MG_Util/Math/VectorTypes.h"
 #include <Includes.h>
 #include <vk_mem_alloc.h>
@@ -86,6 +87,12 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         DrawIndexedCmdParam* pParams = nullptr;
     };
 
+    struct MultiDrawCmd {
+        GLenum mode = GL_TRIANGLES;
+        Uint32 drawCount = 0;
+        DrawCmdParam* pParams = nullptr;
+    };
+
     struct QueueFamilyIndices {
         Int32 graphicsFamily = -1;
         Int32 presentFamily = -1;
@@ -101,7 +108,7 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         }
     };
 
-    class VulkanRenderer {
+    class VulkanRenderer : public IBufferCopyCommandProvider, public FrameContext::IRecordingObserver {
     public:
         VulkanRenderer(NativeWindowType window, const VulkanRendererConfig& cfg = {});
         ~VulkanRenderer();
@@ -109,12 +116,29 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         void Initialize();
         void Shutdown();
 
+        // IBufferCopyCommandProvider: recording command buffer, outside any
+        // render pass, for immediate staged buffer copies.
+        VkCommandBuffer AcquireBufferCopyCommandBuffer() override;
+
+        // FrameContext::IRecordingObserver: prepares the frame's timer-query
+        // pool (harvest + reset) right after the frame command buffer begins
+        // recording, before any render pass.
+        void OnFrameCommandRecordingBegan(VkCommandBuffer commandBuffer) override;
+
         Bool SetupDraw(FrameContext::FrameData& frame, GLenum mode, Flags<DrawSetupAspect> aspects,
                        const DrawCmdParam& drawParams,
                        const IndexBufferView* pIndexBufferView = nullptr);
         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);
@@ -134,8 +158,18 @@ namespace MobileGL::MG_Backend::DirectVulkan {
                                   GLbitfield mask, GLenum filter);
         void CopyTexSubImage2D(GLenum target, GLint level, GLint xoffset, GLint yoffset,
                        GLint x, GLint y, GLsizei width, GLsizei height);
+        void CopyImageSubData(const SharedPtr<MG_State::GLState::ITextureObject>& srcTexture,
+                              GLenum srcTarget, GLint srcLevel, GLint srcX, GLint srcY, GLint srcZ,
+                              const SharedPtr<MG_State::GLState::ITextureObject>& dstTexture,
+                              GLenum dstTarget, GLint dstLevel, GLint dstX, GLint dstY, GLint dstZ,
+                              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);
+        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,
@@ -146,7 +180,11 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         static VkMemoryBarrier BuildMemoryBarrierForGlBarriers(GLbitfield barriers);
         void DrawArrays(const DrawCmd& payload);
         void DrawElements(const DrawIndexedCmd& payload);
+        void MultiDrawArrays(const MultiDrawCmd& payload);
         void MultiDrawElements(const MultiDrawIndexedCmd& payloads);
+        void MultiDrawElementsIndirect(GLenum mode, GLenum type, const void* indirect, GLsizei drawcount,
+                                       GLsizei stride);
+        void MultiDrawArraysIndirect(GLenum mode, const void* indirect, GLsizei drawcount, GLsizei stride);
         void MultiDrawElementsIndirectCount(GLenum mode, GLenum type, const void* indirect, GLintptr drawcount,
                                             GLsizei maxdrawcount, GLsizei stride);
         void Present();
@@ -155,6 +193,64 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         VkInstance GetInstance() const;
         Bool IsDrawIndirectCountExtensionEnabled() const;
 
+        // GL fence support, expressed in queue-submission indices backed by
+        // real VkFences. A GL fence captures GetSyncPointSubmitIndex() at
+        // creation: the index of the submission that will carry the commands
+        // recorded so far (m_submitCounter + 1 while work is pending, or
+        // m_submitCounter when nothing has been recorded since the last
+        // submit). It is signaled once that submission's fence is observed
+        // signaled - unlike the frame-serial heuristic, this makes fences
+        // signal as soon as the GPU actually finishes, which MC 1.21.5's
+        // fence-paced ring buffers rely on to recycle their space.
+        Uint64 GetSyncPointSubmitIndex() const;
+        // Non-blocking: polls outstanding submission fences and reports
+        // whether every submission up to `submitIndex` has completed.
+        Bool IsSubmitIndexComplete(Uint64 submitIndex);
+        // Submits the commands recorded so far without waiting (GL flush).
+        // Recording restarts lazily on a fresh command buffer; the submitted
+        // one is retired until the frame slot's fence is next waited. Returns
+        // true when a submission was made.
+        Bool FlushPendingCommands();
+        // Flush gated on usefulness: only flushes when `submitIndex` is still
+        // unsubmitted, so poll loops on already-submitted fences do not split
+        // the frame's render pass (a full tile load/store on TBDR GPUs).
+        Bool FlushForSyncPoint(Uint64 submitIndex);
+        // Blocking wait for a submission index with a nanosecond timeout.
+        // When the index is still unsubmitted and flushIfPending is set, the
+        // pending commands are flushed first so the wait can make progress.
+        Bool WaitForSubmitIndex(Uint64 submitIndex, Uint64 timeoutNs, Bool flushIfPending);
+
+        // Frame-serial completion, still used by the timer-query paths (their
+        // records are bucketed per frame slot).
+        Bool IsFrameSerialComplete(Uint64 serial) const;
+        // Blocking wait for a submitted serial. Returns false when the serial
+        // cannot complete without further submissions (it belongs to the
+        // current, not-yet-presented frame) or when the wait failed.
+        Bool WaitForFrameSerial(Uint64 serial, Uint64 timeoutNs);
+
+        // GPU timer queries, backing the GL_TIME_ELAPSED / GL_TIMESTAMP
+        // 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.
+        SharedPtr<VkTimerQueryManager::TimestampRecord> WriteTimerQueryTimestamp();
+        // Non-blocking: true once the record's raw ticks are on the CPU
+        // (harvests the slot once its frame serial has completed).
+        Bool IsTimerQueryResultReady(VkTimerQueryManager::TimestampRecord& record);
+        // Blocking wait, mirroring ClientWaitSync's caveat: a record written
+        // this frame cannot complete until Present submits the commands, so
+        // this returns false (result reads as 0) instead of deadlocking.
+        Bool WaitForTimerQueryResult(VkTimerQueryManager::TimestampRecord& record);
+        Uint64 GetTimerQueryElapsedNs(const VkTimerQueryManager::TimestampRecord& begin,
+                                      const VkTimerQueryManager::TimestampRecord& end) const;
+        Uint64 GetTimerQueryTimestampNs(const VkTimerQueryManager::TimestampRecord& record) const;
+
+        void RequestSwapchainResize(Uint32 width, Uint32 height);
         void RecreateSwapchain();
 
     private:
@@ -195,12 +291,64 @@ 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
+        // order. Present/readback submissions reference the frame slot's
+        // fence (not pool-owned); mid-frame flushes use pooled fences that are
+        // recycled once their submission is observed complete.
+        // Not thread-safe: like the rest of the renderer, the tracker relies
+        // on GL calls being serialized (launchers migrate the context across
+        // threads, but calls never run concurrently), so sync-object polls
+        // may mutate it without locking.
+        struct SubmitRecord {
+            Uint64 submitIndex = 0;
+            // Buffer-manager frame serial the submission was made under; its
+            // completion raises the completed-serial floor (timer queries and
+            // buffer busy-tracking live in frame-serial space).
+            Uint64 frameSerial = 0;
+            VkFence fence = VK_NULL_HANDLE;
+            Bool pooledFence = false;
+        };
+        // Registers a submission that vkQueueSubmit just made with `fence`.
+        // Invariant: every graphics-queue submission that outlives its call
+        // site must be registered so GL fences observe it. Exempt are the
+        // texture-upload/preserve submits in VkTextureManager, which
+        // vkWaitForFences inline before returning.
+        void RegisterSubmit(VkFence fence, Bool pooledFence);
+        // Builds the submit packet for the frame's pending command buffer
+        // (consuming the acquire semaphore on the slot's first submission),
+        // submits it with `fence`, and registers the submission. On failure
+        // the frame state is left untouched. Shared by the mid-frame flush
+        // and the readback path so the semaphore-consumption invariant lives
+        // in one place.
+        Bool SubmitPendingCommandBuffer(FrameContext::FrameData& frame, VkFence fence, Bool pooledFence);
+        // Polls in-flight submission fences (prefix order) and advances the
+        // completed counter past every fence observed signaled.
+        void RefreshCompletedSubmits();
+        // All submissions up to `submitIndex` are known complete (their fence
+        // was waited or the device was idled); drops their records and
+        // recycles pooled fences.
+        void OnSubmitsCompletedUpTo(Uint64 submitIndex);
+        VkFence AcquirePooledSubmitFence();
+        void DestroySubmitFencePool();
+        Bool HasPendingRecordedWork() const;
+
+        Vector<SubmitRecord> m_inFlightSubmits;
+        Vector<VkFence> m_freeSubmitFences;
+        Uint64 m_submitCounter = 0;
+        Uint64 m_completedSubmitCounter = 0;
 
         NativeWindowType m_window = 0;
         void* m_platformDisplay = nullptr;
         void* m_platformLibrary = nullptr;
         void* m_platformCloseDisplay = nullptr;
         VulkanRendererConfig m_config;
+        Bool m_swapchainResizeRequested = false;
 
         // Vulkan objects
         Bool m_validationLayersEnabled = false;
@@ -217,6 +365,27 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         VkQueue m_presentQueue = VK_NULL_HANDLE;
         Bool m_drawIndirectCountExtensionEnabled = false;
         Bool m_indexTypeUint8ExtensionEnabled = false;
+        Bool m_logicOpFeatureEnabled = false;
+        Bool m_multiDrawIndirectFeatureEnabled = 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.
+        Bool m_fillModeNonSolidFeatureEnabled = false;
+        Bool m_independentBlendFeatureEnabled = false;
+        // dualSrcBlend gates GL_SRC1_* blend factors (glBindFragDataLocationIndexed dual-source blend);
+        // primitiveTopologyListRestart gates primitive restart on *list* topologies (strip/fan restart
+        // 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;
+        // Cached at device creation from the graphics queue family properties
+        // and device limits; drives timer-query support.
+        Uint32 m_timestampValidBits = 0;
+        Float m_timestampPeriodNs = 0.0f;
+        Bool m_timerQuerySupported = false;
         using PFNDrawIndexedIndirectCountFunc = void(VKAPI_PTR*)(VkCommandBuffer commandBuffer, VkBuffer buffer,
                                                                  VkDeviceSize offset, VkBuffer countBuffer,
                                                                  VkDeviceSize countBufferOffset, Uint32 maxDrawCount,
@@ -225,20 +394,24 @@ namespace MobileGL::MG_Backend::DirectVulkan {
 
         VkCommandPool m_commandPool = VK_NULL_HANDLE;
 
-        struct TransientBufferSliceCacheEntry {
-            BufferSlice slice;
-            Uint64 changeSerial = 0;
-            SizeT size = 0;
-        };
-
         VkBufferManager m_bufferManager;
-        UnorderedMap<const MG_State::GLState::BufferObject*, TransientBufferSliceCacheEntry>
-            m_transientVertexIndexBufferSlicesThisFrame;
 
         Uint m_imageIndexAcquired = 0;
         FrameContext m_frameContext;
 
         UniquePtr<PipelineFactory> m_pipelineFactory;
+        // Single-slot "last pipeline" memo: skip the per-draw GetOrCreatePipeline work (state
+        // 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;
         UnorderedMap<ProgramFactory::HashType, VkPipeline> m_computePipelines;
         UniquePtr<ProgramFactory> m_programFactory;
         UniquePtr<UniformManager> m_uniformManager;
@@ -247,10 +420,77 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         UniquePtr<VkRenderPassManager> m_renderPassManager;
         UniquePtr<VkTextureManager> m_textureManager;
         UniquePtr<VkSamplerManager> m_samplerManager;
+        UniquePtr<VkTimerQueryManager> m_timerQueryManager;
         BlitResources m_blitResources;
         DepthMipmapResources m_depthMipmapResources;
         Vector<DeferredDepthMipmapCleanup> m_deferredDepthMipmapCleanup;
 
+        // Skip the per-draw CollectSampledTextures walk (~5% of the render thread) when the sampled
+        // texture SET is provably unchanged from the previous draw: same program (lifetime id +
+        // backend-state version, which covers sampler-uniform reassignment / relink) and transform
+        // flags, and no texture bind/unbind/delete since (GetTextureBindGeneration). On a hit,
+        // m_sampledTexturesScratch still holds the previous draw's list and steps 2-4 (feedback /
+        // layout probe / transition) re-run on it, so layout correctness is unaffected - only the GL
+        // walk is skipped. The program lifetime id (never reused, unlike the GL name) and the
+        // monotonic bind generation make the key ABA-proof; the per-command-buffer reset is a cheap
+        // belt-and-suspenders.
+        Bool m_lastSampledSetValid = false;
+        Uint64 m_lastSampledSetProgramLifetimeId = 0;
+        Uint32 m_lastSampledSetProgramVersion = 0;
+        ProgramFactory::CompileOptionFlags m_lastSampledSetTransformFlags = {};
+        Uint64 m_lastSampledSetBindGeneration = 0;
+
+        // 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;
+        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;
+            }
+        };
+
+        UnorderedMap<ConvertedVertexStreamKey, BufferSlice, ConvertedVertexStreamKeyHash>
+            m_convertedVertexStreams;
+
         void CreateInstance();
         VkResult SetupDebugMessenger();
         VkResult DestroyDebugMessenger();
@@ -272,9 +512,14 @@ namespace MobileGL::MG_Backend::DirectVulkan {
             const RenderPassEntry& renderPassEntry);
         VkPipeline GetOrCreateComputePipeline(const ProgramFactory::VkProgramObject& programObj);
         void DestroyComputePipelines();
+        Bool PrepareStorageImageTextures(
+            VkCommandBuffer commandBuffer,
+            const MG_State::GLState::ProgramObject& program,
+            const ProgramFactory::VkProgramObject& programObj);
 
         Bool UploadAndBindVertexBuffers(VkCommandBuffer commandBuffer, const MG_State::GLState::VertexArrayObject& vao,
-                                        const DrawCmdParam& drawParams);
+                                        const ProgramFactory::VkProgramObject& programObj,
+                                        const DrawCmdParam& drawParams, Bool indexedDraw);
         Bool UploadAndBindIndexBuffer(FrameContext::FrameData& frame,
                                      const MG_State::GLState::VertexArrayObject& vao,
                                       const IndexBufferView* pIndexBufferView = nullptr);

MobileGL/MG_Backend/DirectVulkan/VkIncludes.h

@@ -10,16 +10,61 @@
 
 #include "VulkanRendererConfig.h"
 
+#define ENUM_STR_CASE(c) case c: return #c;
+
+namespace MobileGL::MG_Backend::DirectVulkan {
+    inline const char* VkResultToString(VkResult result) {
+        switch (result) {
+        ENUM_STR_CASE(VK_SUCCESS)
+        ENUM_STR_CASE(VK_NOT_READY)
+        ENUM_STR_CASE(VK_TIMEOUT)
+        ENUM_STR_CASE(VK_EVENT_SET)
+        ENUM_STR_CASE(VK_EVENT_RESET)
+        ENUM_STR_CASE(VK_INCOMPLETE)
+        ENUM_STR_CASE(VK_ERROR_OUT_OF_HOST_MEMORY)
+        ENUM_STR_CASE(VK_ERROR_OUT_OF_DEVICE_MEMORY)
+        ENUM_STR_CASE(VK_ERROR_INITIALIZATION_FAILED)
+        ENUM_STR_CASE(VK_ERROR_DEVICE_LOST)
+        ENUM_STR_CASE(VK_ERROR_MEMORY_MAP_FAILED)
+        ENUM_STR_CASE(VK_ERROR_LAYER_NOT_PRESENT)
+        ENUM_STR_CASE(VK_ERROR_EXTENSION_NOT_PRESENT)
+        ENUM_STR_CASE(VK_ERROR_FEATURE_NOT_PRESENT)
+        ENUM_STR_CASE(VK_ERROR_INCOMPATIBLE_DRIVER)
+        ENUM_STR_CASE(VK_ERROR_TOO_MANY_OBJECTS)
+        ENUM_STR_CASE(VK_ERROR_FORMAT_NOT_SUPPORTED)
+        ENUM_STR_CASE(VK_ERROR_FRAGMENTED_POOL)
+        ENUM_STR_CASE(VK_ERROR_UNKNOWN)
+        ENUM_STR_CASE(VK_ERROR_OUT_OF_POOL_MEMORY)
+        ENUM_STR_CASE(VK_ERROR_INVALID_EXTERNAL_HANDLE)
+        ENUM_STR_CASE(VK_ERROR_FRAGMENTATION)
+        ENUM_STR_CASE(VK_ERROR_INVALID_OPAQUE_CAPTURE_ADDRESS)
+        ENUM_STR_CASE(VK_PIPELINE_COMPILE_REQUIRED)
+        ENUM_STR_CASE(VK_ERROR_SURFACE_LOST_KHR)
+        ENUM_STR_CASE(VK_ERROR_NATIVE_WINDOW_IN_USE_KHR)
+        ENUM_STR_CASE(VK_SUBOPTIMAL_KHR)
+        ENUM_STR_CASE(VK_ERROR_OUT_OF_DATE_KHR)
+        ENUM_STR_CASE(VK_ERROR_INCOMPATIBLE_DISPLAY_KHR)
+        ENUM_STR_CASE(VK_ERROR_VALIDATION_FAILED_EXT)
+        ENUM_STR_CASE(VK_ERROR_INVALID_SHADER_NV)
+        default:
+            return "VK_RESULT_UNKNOWN";
+        }
+    }
+} // namespace MobileGL::MG_Backend::DirectVulkan
+
 #define VK_VERIFY(expr, ...)                                                                                           \
     do {                                                                                                               \
         VkResult _vk_verify_result = (expr);                                                                           \
-        MOBILEGL_ASSERT(_vk_verify_result == VK_SUCCESS, "Vulkan error %d at %s:%d" __VA_OPT__(" - ") __VA_ARGS__, _vk_verify_result, __FILE__, __LINE__);  \
+        if (_vk_verify_result != VK_SUCCESS) {                                                                         \
+            MGLOG_F("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" __VA_OPT__(" - ") __VA_ARGS__, MobileGL::MG_Backend::DirectVulkan::VkResultToString(_vk_verify_result), _vk_verify_result, __FILE__, __LINE__);  \
     } while (0)
 
-#define ENUM_STR_CASE(c) case c: return #c;
-
 #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__);  \
-    } while (0)
+    } while (0)

MobileGL/MG_Backend/DirectVulkan/VulkanRendererConfig.h

@@ -11,10 +11,18 @@
 
 namespace MobileGL::MG_Backend::DirectVulkan {
     struct VulkanRendererConfig {
-        Uint32 MaxFramesInFlight = 2;
+        // Fallback CPU pipeline depth used when the MOBILEGL_MAGMA_FRAMESINFLIGHT env var is
+        // unset/invalid. A deeper pipeline lets the CPU run further ahead of the GPU, hiding
+        // per-frame GPU-completion latency. Whatever value is chosen (env or this fallback) is
+        // only a request: VulkanRenderer::Initialize clamps it down to the surface's maxImageCount
+        // (and never below 2), since not every driver allows that many swapchain images.
+        Uint32 MaxFramesInFlight = 3;
         String AppName = "MobileGL-VulkanRenderer";
         MobileGL::Version Version = MG_Config::CoreVersion;
         Uint64 CacheVersion = MG_Config::CacheVersion;
+        Uint32 SurfaceWidth = 1;
+        Uint32 SurfaceHeight = 1;
+        Bool DisablePipelineCache = false;
 #if MOBILEGL_LOG_ACTIVE_LEVEL <= MOBILEGL_LOG_LEVEL_DEBUG
         Bool EnableValidationLayers = true;
 #else

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 +38,7 @@ 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)

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

@@ -0,0 +1,700 @@
+// MobileGL - MobileGL/MG_Impl/CGLImpl/CGLImpl.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 "CGLImpl.h"
+
+#if defined(__APPLE__)
+#include "../EGLImpl/EGLImpl.h"
+
+namespace MobileGL::MG_Impl::CGLImpl {
+    namespace {
+        struct PixelFormatObject {
+            Uint32 RetainCount = 1;
+            Bool DoubleBuffer = true;
+            GLint ColorSize = 24;
+            GLint AlphaSize = 8;
+            GLint DepthSize = 24;
+            GLint StencilSize = 8;
+            GLint SampleBuffers = 0;
+            GLint Samples = 0;
+            GLint Profile = kCGLOGLPVersion_3_2_Core;
+            GLint RendererId = 0x4d474c;
+        };
+
+        struct ContextObject {
+            Uint32 RetainCount = 1;
+            CGLPixelFormatObj PixelFormat = nullptr;
+            CGLContextObj Share = nullptr;
+            EGLDisplay Display = EGL_NO_DISPLAY;
+            EGLConfig Config = nullptr;
+            EGLContext Context = EGL_NO_CONTEXT;
+            EGLSurface Surface = EGL_NO_SURFACE;
+            void* NSObject = nullptr;
+            void* View = nullptr;
+            void* MetalLayer = nullptr;
+            GLint SwapInterval = 1;
+            GLint VirtualScreen = 0;
+            GLint SurfaceBackingSize[2] = {0, 0};
+            Bool HasDrawable = false;
+            Bool Locked = false;
+        };
+
+        std::recursive_mutex& RegistryMutex() {
+            static auto* mutex = new std::recursive_mutex();
+            return *mutex;
+        }
+
+        Uint64& NextPixelFormatHandle() {
+            static auto* handle = new Uint64(1);
+            return *handle;
+        }
+
+        Uint64& NextContextHandle() {
+            static auto* handle = new Uint64(1);
+            return *handle;
+        }
+
+        UnorderedMap<CGLPixelFormatObj, PixelFormatObject>& PixelFormats() {
+            static auto* formats = new UnorderedMap<CGLPixelFormatObj, PixelFormatObject>();
+            return *formats;
+        }
+
+        UnorderedMap<CGLContextObj, ContextObject>& Contexts() {
+            static auto* contexts = new UnorderedMap<CGLContextObj, ContextObject>();
+            return *contexts;
+        }
+
+        UnorderedMap<std::thread::id, CGLContextObj>& CurrentContexts() {
+            static auto* contexts = new UnorderedMap<std::thread::id, CGLContextObj>();
+            return *contexts;
+        }
+
+        CGLPixelFormatObj EncodePixelFormat(Uint64 handle) {
+            return reinterpret_cast<CGLPixelFormatObj>(static_cast<SizeT>(handle));
+        }
+
+        CGLContextObj EncodeContext(Uint64 handle) {
+            return reinterpret_cast<CGLContextObj>(static_cast<SizeT>(handle));
+        }
+
+        std::thread::id CurrentThreadKey() {
+            return std::this_thread::get_id();
+        }
+
+        Bool AttributeHasValue(CGLPixelFormatAttribute attrib) {
+            switch (attrib) {
+            case kCGLPFAColorSize:
+            case kCGLPFAAlphaSize:
+            case kCGLPFADepthSize:
+            case kCGLPFAStencilSize:
+            case kCGLPFASampleBuffers:
+            case kCGLPFASamples:
+            case kCGLPFARendererID:
+            case kCGLPFADisplayMask:
+            case kCGLPFAOpenGLProfile:
+                return true;
+            default:
+                return false;
+            }
+        }
+
+        void ApplyPixelFormatAttribute(PixelFormatObject& pixelFormat,
+                                       CGLPixelFormatAttribute attrib,
+                                       GLint value) {
+            switch (attrib) {
+            case kCGLPFADoubleBuffer:
+                pixelFormat.DoubleBuffer = true;
+                break;
+            case kCGLPFAColorSize:
+                pixelFormat.ColorSize = value;
+                break;
+            case kCGLPFAAlphaSize:
+                pixelFormat.AlphaSize = value;
+                break;
+            case kCGLPFADepthSize:
+                pixelFormat.DepthSize = value;
+                break;
+            case kCGLPFAStencilSize:
+                pixelFormat.StencilSize = value;
+                break;
+            case kCGLPFASampleBuffers:
+                pixelFormat.SampleBuffers = value;
+                break;
+            case kCGLPFASamples:
+                pixelFormat.Samples = value;
+                break;
+            case kCGLPFAOpenGLProfile:
+                pixelFormat.Profile = value;
+                break;
+            case kCGLPFARendererID:
+                pixelFormat.RendererId = value;
+                break;
+            default:
+                break;
+            }
+        }
+
+        Bool InitEGLContext(ContextObject& object, CGLPixelFormatObj pix, CGLContextObj share) {
+            auto* pixelFormat = [&]() -> PixelFormatObject* {
+                auto& pixelFormats = PixelFormats();
+                auto it = pixelFormats.find(pix);
+                return it == pixelFormats.end() ? nullptr : &it->second;
+            }();
+            if (!pixelFormat) {
+                return false;
+            }
+
+            EGLDisplay display = EGLImpl::GetDisplay(EGL_DEFAULT_DISPLAY);
+            if (display == EGL_NO_DISPLAY) {
+                return false;
+            }
+            if (!EGLImpl::Initialize(display, nullptr, nullptr)) {
+                return false;
+            }
+            EGLImpl::BindAPI(EGL_OPENGL_API);
+
+            const EGLint attribs[] = {
+                EGL_RED_SIZE, 8,
+                EGL_GREEN_SIZE, 8,
+                EGL_BLUE_SIZE, 8,
+                EGL_ALPHA_SIZE, std::max(pixelFormat->AlphaSize, 0),
+                EGL_DEPTH_SIZE, std::max(pixelFormat->DepthSize, 0),
+                EGL_STENCIL_SIZE, std::max(pixelFormat->StencilSize, 0),
+                EGL_SURFACE_TYPE, EGL_WINDOW_BIT | EGL_PBUFFER_BIT,
+                EGL_RENDERABLE_TYPE, EGL_OPENGL_BIT,
+                EGL_NONE,
+            };
+
+            EGLConfig config = nullptr;
+            EGLint count = 0;
+            if (!EGLImpl::ChooseConfig(display, attribs, &config, 1, &count) || count <= 0) {
+                return false;
+            }
+
+            EGLContext shareContext = EGL_NO_CONTEXT;
+            if (share != nullptr) {
+                auto& contexts = Contexts();
+                auto shareIt = contexts.find(share);
+                if (shareIt == contexts.end()) {
+                    return false;
+                }
+                shareContext = shareIt->second.Context;
+            }
+
+            const EGLint contextAttribs[] = {
+                EGL_CONTEXT_MAJOR_VERSION, 3,
+                EGL_CONTEXT_MINOR_VERSION, 3,
+                EGL_NONE,
+            };
+            EGLContext eglContext = EGLImpl::CreateContext(display, config, shareContext, contextAttribs);
+            if (eglContext == EGL_NO_CONTEXT) {
+                return false;
+            }
+
+            object.Display = display;
+            object.Config = config;
+            object.Context = eglContext;
+            object.PixelFormat = pix;
+            object.Share = share;
+            return true;
+        }
+
+        ContextObject* TryGetContext(CGLContextObj ctx) {
+            auto& contexts = Contexts();
+            auto it = contexts.find(ctx);
+            return it == contexts.end() ? nullptr : &it->second;
+        }
+
+        const ContextObject* TryGetContext(CGLContextObj ctx, const std::lock_guard<std::recursive_mutex>&) {
+            auto& contexts = Contexts();
+            auto it = contexts.find(ctx);
+            return it == contexts.end() ? nullptr : &it->second;
+        }
+
+        PixelFormatObject* TryGetPixelFormat(CGLPixelFormatObj pix) {
+            auto& pixelFormats = PixelFormats();
+            auto it = pixelFormats.find(pix);
+            return it == pixelFormats.end() ? nullptr : &it->second;
+        }
+
+        CGLError MakeCurrentLocked(CGLContextObj ctx, ContextObject& object) {
+            CurrentContexts()[CurrentThreadKey()] = ctx;
+            if (!object.HasDrawable || object.Surface == EGL_NO_SURFACE) {
+                return kCGLNoError;
+            }
+            if (!EGLImpl::MakeCurrent(object.Display, object.Surface, object.Surface, object.Context)) {
+                return kCGLBadState;
+            }
+            return kCGLNoError;
+        }
+
+        CGLError RecreateSurfaceLocked(CGLContextObj ctx, ContextObject& object) {
+            if (!object.MetalLayer) {
+                return kCGLBadDrawable;
+            }
+            if (object.Surface != EGL_NO_SURFACE) {
+                EGLImpl::DestroySurface(object.Display, object.Surface);
+                object.Surface = EGL_NO_SURFACE;
+            }
+            const EGLAttrib attribs[] = {
+                EGL_WIDTH, std::max<GLint>(object.SurfaceBackingSize[0], 1),
+                EGL_HEIGHT, std::max<GLint>(object.SurfaceBackingSize[1], 1),
+                EGL_NONE,
+            };
+            EGLSurface surface = EGLImpl::CreatePlatformWindowSurface(object.Display, object.Config,
+                                                                      object.MetalLayer, attribs);
+            if (surface == EGL_NO_SURFACE) {
+                object.HasDrawable = false;
+                return kCGLBadDrawable;
+            }
+            object.Surface = surface;
+            object.HasDrawable = true;
+            return GetCurrentContext() == ctx ? MakeCurrentLocked(ctx, object) : kCGLNoError;
+        }
+
+        CGLError ResizeSurfaceLocked(ContextObject& object) {
+            if (object.Surface == EGL_NO_SURFACE) {
+                return kCGLBadDrawable;
+            }
+            return EGLImpl::ResizePlatformWindowSurface(
+                       object.Display, object.Surface,
+                       std::max<GLint>(object.SurfaceBackingSize[0], 1),
+                       std::max<GLint>(object.SurfaceBackingSize[1], 1))
+                       ? kCGLNoError
+                       : kCGLBadDrawable;
+        }
+    } // namespace
+
+    CGLError ChoosePixelFormat(const CGLPixelFormatAttribute* attribs, CGLPixelFormatObj* pix, GLint* npix) {
+        const std::lock_guard<std::recursive_mutex> lock(RegistryMutex());
+        if (!pix || !npix) {
+            return kCGLBadAddress;
+        }
+
+        PixelFormatObject object;
+        if (attribs) {
+            for (SizeT i = 0; attribs[i] != static_cast<CGLPixelFormatAttribute>(0); ++i) {
+                const auto attrib = attribs[i];
+                GLint value = 1;
+                if (AttributeHasValue(attrib)) {
+                    value = static_cast<GLint>(attribs[++i]);
+                }
+                ApplyPixelFormatAttribute(object, attrib, value);
+            }
+        }
+
+        const auto handle = EncodePixelFormat(NextPixelFormatHandle()++);
+        PixelFormats()[handle] = object;
+        *pix = handle;
+        *npix = 1;
+        return kCGLNoError;
+    }
+
+    CGLError DestroyPixelFormat(CGLPixelFormatObj pix) {
+        ReleasePixelFormat(pix);
+        return kCGLNoError;
+    }
+
+    CGLError DescribePixelFormat(CGLPixelFormatObj pix, GLint pixNum, CGLPixelFormatAttribute attrib, GLint* value) {
+        const std::lock_guard<std::recursive_mutex> lock(RegistryMutex());
+        if (!value) {
+            return kCGLBadAddress;
+        }
+        if (pixNum != 0 && pixNum != 1) {
+            return kCGLBadValue;
+        }
+        auto* pixelFormat = TryGetPixelFormat(pix);
+        if (!pixelFormat) {
+            return kCGLBadPixelFormat;
+        }
+
+        switch (attrib) {
+        case kCGLPFADoubleBuffer:
+            *value = pixelFormat->DoubleBuffer ? 1 : 0;
+            return kCGLNoError;
+        case kCGLPFAAccelerated:
+        case kCGLPFAAcceleratedCompute:
+        case kCGLPFASupportsAutomaticGraphicsSwitching:
+            *value = 1;
+            return kCGLNoError;
+        case kCGLPFAColorSize:
+            *value = pixelFormat->ColorSize;
+            return kCGLNoError;
+        case kCGLPFAAlphaSize:
+            *value = pixelFormat->AlphaSize;
+            return kCGLNoError;
+        case kCGLPFADepthSize:
+            *value = pixelFormat->DepthSize;
+            return kCGLNoError;
+        case kCGLPFAStencilSize:
+            *value = pixelFormat->StencilSize;
+            return kCGLNoError;
+        case kCGLPFASampleBuffers:
+            *value = pixelFormat->SampleBuffers;
+            return kCGLNoError;
+        case kCGLPFASamples:
+            *value = pixelFormat->Samples;
+            return kCGLNoError;
+        case kCGLPFARendererID:
+            *value = pixelFormat->RendererId;
+            return kCGLNoError;
+        case kCGLPFAOpenGLProfile:
+            *value = pixelFormat->Profile;
+            return kCGLNoError;
+        case kCGLPFAVirtualScreenCount:
+            *value = 1;
+            return kCGLNoError;
+        default:
+            *value = 0;
+            return kCGLNoError;
+        }
+    }
+
+    void ReleasePixelFormat(CGLPixelFormatObj pix) {
+        const std::lock_guard<std::recursive_mutex> lock(RegistryMutex());
+        auto* pixelFormat = TryGetPixelFormat(pix);
+        if (!pixelFormat) {
+            return;
+        }
+        if (pixelFormat->RetainCount > 1) {
+            --pixelFormat->RetainCount;
+            return;
+        }
+        PixelFormats().erase(pix);
+    }
+
+    CGLPixelFormatObj RetainPixelFormat(CGLPixelFormatObj pix) {
+        const std::lock_guard<std::recursive_mutex> lock(RegistryMutex());
+        auto* pixelFormat = TryGetPixelFormat(pix);
+        if (pixelFormat) {
+            ++pixelFormat->RetainCount;
+        }
+        return pix;
+    }
+
+    GLuint GetPixelFormatRetainCount(CGLPixelFormatObj pix) {
+        const std::lock_guard<std::recursive_mutex> lock(RegistryMutex());
+        auto* pixelFormat = TryGetPixelFormat(pix);
+        return pixelFormat ? pixelFormat->RetainCount : 0;
+    }
+
+    CGLError CreateContext(CGLPixelFormatObj pix, CGLContextObj share, CGLContextObj* ctx) {
+        const std::lock_guard<std::recursive_mutex> lock(RegistryMutex());
+        if (!ctx) {
+            return kCGLBadAddress;
+        }
+        if (!TryGetPixelFormat(pix)) {
+            return kCGLBadPixelFormat;
+        }
+        if (share && !TryGetContext(share)) {
+            return kCGLBadMatch;
+        }
+
+        ContextObject object;
+        if (!InitEGLContext(object, pix, share)) {
+            return kCGLBadAlloc;
+        }
+        RetainPixelFormat(pix);
+        const auto handle = EncodeContext(NextContextHandle()++);
+        Contexts()[handle] = object;
+        *ctx = handle;
+        return kCGLNoError;
+    }
+
+    CGLError DestroyContext(CGLContextObj ctx) {
+        ReleaseContext(ctx);
+        return kCGLNoError;
+    }
+
+    CGLContextObj RetainContext(CGLContextObj ctx) {
+        const std::lock_guard<std::recursive_mutex> lock(RegistryMutex());
+        auto* object = TryGetContext(ctx);
+        if (object) {
+            ++object->RetainCount;
+        }
+        return ctx;
+    }
+
+    void ReleaseContext(CGLContextObj ctx) {
+        const std::lock_guard<std::recursive_mutex> lock(RegistryMutex());
+        auto* object = TryGetContext(ctx);
+        if (!object) {
+            return;
+        }
+        if (object->RetainCount > 1) {
+            --object->RetainCount;
+            return;
+        }
+        if (object->Surface != EGL_NO_SURFACE) {
+            EGLImpl::DestroySurface(object->Display, object->Surface);
+        }
+        if (object->Context != EGL_NO_CONTEXT) {
+            EGLImpl::DestroyContext(object->Display, object->Context);
+        }
+        ReleasePixelFormat(object->PixelFormat);
+        auto& currentContexts = CurrentContexts();
+        for (auto it = currentContexts.begin(); it != currentContexts.end();) {
+            if (it->second == ctx) {
+                it = currentContexts.erase(it);
+            } else {
+                ++it;
+            }
+        }
+        Contexts().erase(ctx);
+    }
+
+    GLuint GetContextRetainCount(CGLContextObj ctx) {
+        const std::lock_guard<std::recursive_mutex> lock(RegistryMutex());
+        auto* object = TryGetContext(ctx);
+        return object ? object->RetainCount : 0;
+    }
+
+    CGLPixelFormatObj GetPixelFormat(CGLContextObj ctx) {
+        const std::lock_guard<std::recursive_mutex> lock(RegistryMutex());
+        auto* object = TryGetContext(ctx);
+        return object ? object->PixelFormat : nullptr;
+    }
+
+    CGLError SetCurrentContext(CGLContextObj ctx) {
+        const std::lock_guard<std::recursive_mutex> lock(RegistryMutex());
+        if (!ctx) {
+            CurrentContexts().erase(CurrentThreadKey());
+            EGLImpl::MakeCurrent(EGL_NO_DISPLAY, EGL_NO_SURFACE, EGL_NO_SURFACE, EGL_NO_CONTEXT);
+            return kCGLNoError;
+        }
+        auto* object = TryGetContext(ctx);
+        if (!object) {
+            return kCGLBadContext;
+        }
+        return MakeCurrentLocked(ctx, *object);
+    }
+
+    CGLContextObj GetCurrentContext() {
+        const std::lock_guard<std::recursive_mutex> lock(RegistryMutex());
+        auto& currentContexts = CurrentContexts();
+        auto it = currentContexts.find(CurrentThreadKey());
+        return it == currentContexts.end() ? nullptr : it->second;
+    }
+
+    CGLError SetParameter(CGLContextObj ctx, CGLContextParameter pname, const GLint* params) {
+        const std::lock_guard<std::recursive_mutex> lock(RegistryMutex());
+        auto* object = TryGetContext(ctx);
+        if (!object) {
+            return kCGLBadContext;
+        }
+        if (!params && pname != kCGLCPReclaimResources) {
+            return kCGLBadAddress;
+        }
+        switch (pname) {
+        case kCGLCPSwapInterval:
+            object->SwapInterval = params[0];
+            EGLImpl::SwapInterval(object->Display, object->SwapInterval);
+            return kCGLNoError;
+        case kCGLCPSurfaceBackingSize:
+        {
+            const GLint width = std::max<GLint>(params[0], 1);
+            const GLint height = std::max<GLint>(params[1], 1);
+            if (object->SurfaceBackingSize[0] == width && object->SurfaceBackingSize[1] == height) {
+                return kCGLNoError;
+            }
+            object->SurfaceBackingSize[0] = width;
+            object->SurfaceBackingSize[1] = height;
+            if (object->MetalLayer && object->Surface != EGL_NO_SURFACE) {
+                return ResizeSurfaceLocked(*object);
+            }
+            return kCGLNoError;
+        }
+        case kCGLCPSurfaceOpacity:
+        case kCGLCPSurfaceOrder:
+        case kCGLCPMPSwapsInFlight:
+        case kCGLCPReclaimResources:
+            return kCGLNoError;
+        default:
+            return kCGLNoError;
+        }
+    }
+
+    CGLError GetParameter(CGLContextObj ctx, CGLContextParameter pname, GLint* params) {
+        const std::lock_guard<std::recursive_mutex> lock(RegistryMutex());
+        auto* object = TryGetContext(ctx);
+        if (!object) {
+            return kCGLBadContext;
+        }
+        if (!params) {
+            return kCGLBadAddress;
+        }
+        switch (pname) {
+        case kCGLCPSwapInterval:
+            params[0] = object->SwapInterval;
+            return kCGLNoError;
+        case kCGLCPSurfaceBackingSize:
+            params[0] = object->SurfaceBackingSize[0];
+            params[1] = object->SurfaceBackingSize[1];
+            return kCGLNoError;
+        case kCGLCPCurrentRendererID:
+            params[0] = 0x4d474c;
+            return kCGLNoError;
+        case kCGLCPGPUVertexProcessing:
+        case kCGLCPGPUFragmentProcessing:
+        case kCGLCPHasDrawable:
+            params[0] = object->HasDrawable ? 1 : 0;
+            return kCGLNoError;
+        case kCGLCPMPSwapsInFlight:
+            params[0] = 1;
+            return kCGLNoError;
+        default:
+            params[0] = 0;
+            return kCGLNoError;
+        }
+    }
+
+    CGLError UpdateContext(CGLContextObj ctx) {
+        const std::lock_guard<std::recursive_mutex> lock(RegistryMutex());
+        return TryGetContext(ctx) ? kCGLNoError : kCGLBadContext;
+    }
+
+    CGLError ClearDrawable(CGLContextObj ctx) {
+        const std::lock_guard<std::recursive_mutex> lock(RegistryMutex());
+        auto* object = TryGetContext(ctx);
+        if (!object) {
+            return kCGLBadContext;
+        }
+        if (object->Surface != EGL_NO_SURFACE) {
+            EGLImpl::DestroySurface(object->Display, object->Surface);
+        }
+        object->Surface = EGL_NO_SURFACE;
+        object->View = nullptr;
+        object->MetalLayer = nullptr;
+        object->HasDrawable = false;
+        return kCGLNoError;
+    }
+
+    CGLError FlushDrawable(CGLContextObj ctx) {
+        const std::lock_guard<std::recursive_mutex> lock(RegistryMutex());
+        auto* object = TryGetContext(ctx);
+        if (!object) {
+            return kCGLBadContext;
+        }
+        if (!object->HasDrawable || object->Surface == EGL_NO_SURFACE) {
+            return kCGLBadDrawable;
+        }
+        const auto currentError = MakeCurrentLocked(ctx, *object);
+        if (currentError != kCGLNoError) {
+            return currentError;
+        }
+        return EGLImpl::SwapBuffers(object->Display, object->Surface) ? kCGLNoError : kCGLBadDrawable;
+    }
+
+    CGLError LockContext(CGLContextObj ctx) {
+        const std::lock_guard<std::recursive_mutex> lock(RegistryMutex());
+        auto* object = TryGetContext(ctx);
+        if (!object) {
+            return kCGLBadContext;
+        }
+        object->Locked = true;
+        return kCGLNoError;
+    }
+
+    CGLError UnlockContext(CGLContextObj ctx) {
+        const std::lock_guard<std::recursive_mutex> lock(RegistryMutex());
+        auto* object = TryGetContext(ctx);
+        if (!object) {
+            return kCGLBadContext;
+        }
+        object->Locked = false;
+        return kCGLNoError;
+    }
+
+    void GetVersion(GLint* majorvers, GLint* minorvers) {
+        if (majorvers) {
+            *majorvers = 1;
+        }
+        if (minorvers) {
+            *minorvers = 0;
+        }
+    }
+
+    const char* ErrorString(CGLError error) {
+        switch (error) {
+        case kCGLNoError:
+            return "no error";
+        case kCGLBadAttribute:
+            return "invalid pixel format attribute";
+        case kCGLBadPixelFormat:
+            return "invalid pixel format";
+        case kCGLBadContext:
+            return "invalid context";
+        case kCGLBadDrawable:
+            return "invalid drawable";
+        case kCGLBadState:
+            return "invalid context state";
+        case kCGLBadValue:
+            return "invalid numerical value";
+        case kCGLBadMatch:
+            return "invalid share context";
+        case kCGLBadAddress:
+            return "invalid pointer";
+        case kCGLBadAlloc:
+            return "invalid memory allocation";
+        default:
+            return "unknown CGL error";
+        }
+    }
+
+    CGLError AttachDrawable(CGLContextObj ctx, void* nsView, void* metalLayer, GLint width, GLint height) {
+        const std::lock_guard<std::recursive_mutex> lock(RegistryMutex());
+        auto* object = TryGetContext(ctx);
+        if (!object) {
+            return kCGLBadContext;
+        }
+        if (!metalLayer) {
+            return kCGLBadDrawable;
+        }
+        width = std::max<GLint>(width, 1);
+        height = std::max<GLint>(height, 1);
+        const Bool sameSize = object->SurfaceBackingSize[0] == width && object->SurfaceBackingSize[1] == height;
+        object->SurfaceBackingSize[0] = width;
+        object->SurfaceBackingSize[1] = height;
+        if (object->Surface != EGL_NO_SURFACE && object->MetalLayer == metalLayer && sameSize) {
+            object->View = nsView;
+            object->HasDrawable = true;
+            return kCGLNoError;
+        }
+        if (object->Surface != EGL_NO_SURFACE && object->MetalLayer == metalLayer) {
+            object->View = nsView;
+            object->HasDrawable = true;
+            return ResizeSurfaceLocked(*object);
+        }
+        if (object->Surface != EGL_NO_SURFACE) {
+            EGLImpl::DestroySurface(object->Display, object->Surface);
+            object->Surface = EGL_NO_SURFACE;
+        }
+        object->View = nsView;
+        object->MetalLayer = metalLayer;
+        const auto recreateError = RecreateSurfaceLocked(ctx, *object);
+        if (recreateError != kCGLNoError) {
+            return recreateError;
+        }
+        return kCGLNoError;
+    }
+
+    void* GetContextNSObject(CGLContextObj ctx) {
+        const std::lock_guard<std::recursive_mutex> lock(RegistryMutex());
+        auto* object = TryGetContext(ctx);
+        return object ? object->NSObject : nullptr;
+    }
+
+    void SetContextNSObject(CGLContextObj ctx, void* nsObject) {
+        const std::lock_guard<std::recursive_mutex> lock(RegistryMutex());
+        auto* object = TryGetContext(ctx);
+        if (object) {
+            object->NSObject = nsObject;
+        }
+    }
+} // namespace MobileGL::MG_Impl::CGLImpl
+#endif

MobileGL/MG_Impl/CGLImpl/CGLImpl.h

@@ -0,0 +1,49 @@
+// MobileGL - MobileGL/MG_Impl/CGLImpl/CGLImpl.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>
+
+#if defined(__APPLE__)
+#ifndef GL_SILENCE_DEPRECATION
+#define GL_SILENCE_DEPRECATION
+#endif
+#include <OpenGL/OpenGL.h>
+
+namespace MobileGL::MG_Impl::CGLImpl {
+    CGLError ChoosePixelFormat(const CGLPixelFormatAttribute* attribs, CGLPixelFormatObj* pix, GLint* npix);
+    CGLError DestroyPixelFormat(CGLPixelFormatObj pix);
+    CGLError DescribePixelFormat(CGLPixelFormatObj pix, GLint pixNum, CGLPixelFormatAttribute attrib, GLint* value);
+    void ReleasePixelFormat(CGLPixelFormatObj pix);
+    CGLPixelFormatObj RetainPixelFormat(CGLPixelFormatObj pix);
+    GLuint GetPixelFormatRetainCount(CGLPixelFormatObj pix);
+
+    CGLError CreateContext(CGLPixelFormatObj pix, CGLContextObj share, CGLContextObj* ctx);
+    CGLError DestroyContext(CGLContextObj ctx);
+    CGLContextObj RetainContext(CGLContextObj ctx);
+    void ReleaseContext(CGLContextObj ctx);
+    GLuint GetContextRetainCount(CGLContextObj ctx);
+    CGLPixelFormatObj GetPixelFormat(CGLContextObj ctx);
+
+    CGLError SetCurrentContext(CGLContextObj ctx);
+    CGLContextObj GetCurrentContext();
+    CGLError SetParameter(CGLContextObj ctx, CGLContextParameter pname, const GLint* params);
+    CGLError GetParameter(CGLContextObj ctx, CGLContextParameter pname, GLint* params);
+    CGLError UpdateContext(CGLContextObj ctx);
+    CGLError ClearDrawable(CGLContextObj ctx);
+    CGLError FlushDrawable(CGLContextObj ctx);
+    CGLError LockContext(CGLContextObj ctx);
+    CGLError UnlockContext(CGLContextObj ctx);
+    void GetVersion(GLint* majorvers, GLint* minorvers);
+    const char* ErrorString(CGLError error);
+
+    CGLError AttachDrawable(CGLContextObj ctx, void* nsView, void* metalLayer, GLint width, GLint height);
+    void* GetContextNSObject(CGLContextObj ctx);
+    void SetContextNSObject(CGLContextObj ctx, void* nsObject);
+}
+#endif

MobileGL/MG_Impl/CGLImpl/Exporting/Definitions.cpp

@@ -0,0 +1,110 @@
+// MobileGL - MobileGL/MG_Impl/CGLImpl/Exporting/Definitions.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 "../CGLImpl.h"
+
+#if defined(__APPLE__)
+
+MOBILEGL_CGL_API CGLError CGLChoosePixelFormat(const CGLPixelFormatAttribute* attribs,
+                                               CGLPixelFormatObj* pix,
+                                               GLint* npix) {
+    return MobileGL::MG_Impl::CGLImpl::ChoosePixelFormat(attribs, pix, npix);
+}
+
+MOBILEGL_CGL_API CGLError CGLDestroyPixelFormat(CGLPixelFormatObj pix) {
+    return MobileGL::MG_Impl::CGLImpl::DestroyPixelFormat(pix);
+}
+
+MOBILEGL_CGL_API CGLError CGLDescribePixelFormat(CGLPixelFormatObj pix,
+                                                 GLint pix_num,
+                                                 CGLPixelFormatAttribute attrib,
+                                                 GLint* value) {
+    return MobileGL::MG_Impl::CGLImpl::DescribePixelFormat(pix, pix_num, attrib, value);
+}
+
+MOBILEGL_CGL_API void CGLReleasePixelFormat(CGLPixelFormatObj pix) {
+    MobileGL::MG_Impl::CGLImpl::ReleasePixelFormat(pix);
+}
+
+MOBILEGL_CGL_API CGLPixelFormatObj CGLRetainPixelFormat(CGLPixelFormatObj pix) {
+    return MobileGL::MG_Impl::CGLImpl::RetainPixelFormat(pix);
+}
+
+MOBILEGL_CGL_API GLuint CGLGetPixelFormatRetainCount(CGLPixelFormatObj pix) {
+    return MobileGL::MG_Impl::CGLImpl::GetPixelFormatRetainCount(pix);
+}
+
+MOBILEGL_CGL_API CGLError CGLCreateContext(CGLPixelFormatObj pix, CGLContextObj share, CGLContextObj* ctx) {
+    return MobileGL::MG_Impl::CGLImpl::CreateContext(pix, share, ctx);
+}
+
+MOBILEGL_CGL_API CGLError CGLDestroyContext(CGLContextObj ctx) {
+    return MobileGL::MG_Impl::CGLImpl::DestroyContext(ctx);
+}
+
+MOBILEGL_CGL_API CGLContextObj CGLRetainContext(CGLContextObj ctx) {
+    return MobileGL::MG_Impl::CGLImpl::RetainContext(ctx);
+}
+
+MOBILEGL_CGL_API void CGLReleaseContext(CGLContextObj ctx) {
+    MobileGL::MG_Impl::CGLImpl::ReleaseContext(ctx);
+}
+
+MOBILEGL_CGL_API GLuint CGLGetContextRetainCount(CGLContextObj ctx) {
+    return MobileGL::MG_Impl::CGLImpl::GetContextRetainCount(ctx);
+}
+
+MOBILEGL_CGL_API CGLPixelFormatObj CGLGetPixelFormat(CGLContextObj ctx) {
+    return MobileGL::MG_Impl::CGLImpl::GetPixelFormat(ctx);
+}
+
+MOBILEGL_CGL_API CGLError CGLSetCurrentContext(CGLContextObj ctx) {
+    return MobileGL::MG_Impl::CGLImpl::SetCurrentContext(ctx);
+}
+
+MOBILEGL_CGL_API CGLContextObj CGLGetCurrentContext(void) {
+    return MobileGL::MG_Impl::CGLImpl::GetCurrentContext();
+}
+
+MOBILEGL_CGL_API CGLError CGLSetParameter(CGLContextObj ctx, CGLContextParameter pname, const GLint* params) {
+    return MobileGL::MG_Impl::CGLImpl::SetParameter(ctx, pname, params);
+}
+
+MOBILEGL_CGL_API CGLError CGLGetParameter(CGLContextObj ctx, CGLContextParameter pname, GLint* params) {
+    return MobileGL::MG_Impl::CGLImpl::GetParameter(ctx, pname, params);
+}
+
+MOBILEGL_CGL_API CGLError CGLUpdateContext(CGLContextObj ctx) {
+    return MobileGL::MG_Impl::CGLImpl::UpdateContext(ctx);
+}
+
+MOBILEGL_CGL_API CGLError CGLClearDrawable(CGLContextObj ctx) {
+    return MobileGL::MG_Impl::CGLImpl::ClearDrawable(ctx);
+}
+
+MOBILEGL_CGL_API CGLError CGLFlushDrawable(CGLContextObj ctx) {
+    return MobileGL::MG_Impl::CGLImpl::FlushDrawable(ctx);
+}
+
+MOBILEGL_CGL_API CGLError CGLLockContext(CGLContextObj ctx) {
+    return MobileGL::MG_Impl::CGLImpl::LockContext(ctx);
+}
+
+MOBILEGL_CGL_API CGLError CGLUnlockContext(CGLContextObj ctx) {
+    return MobileGL::MG_Impl::CGLImpl::UnlockContext(ctx);
+}
+
+MOBILEGL_CGL_API void CGLGetVersion(GLint* majorvers, GLint* minorvers) {
+    MobileGL::MG_Impl::CGLImpl::GetVersion(majorvers, minorvers);
+}
+
+MOBILEGL_CGL_API const char* CGLErrorString(CGLError error) {
+    return MobileGL::MG_Impl::CGLImpl::ErrorString(error);
+}
+
+#endif

MobileGL/MG_Impl/DyldInterpose/DyldInterpose.cpp

@@ -0,0 +1,56 @@
+// MobileGL - MobileGL/MG_Impl/DyldInterpose/DyldInterpose.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 <Includes.h>
+
+#if defined(__APPLE__)
+
+#include "MG_Impl/GetProcAddress.h"
+
+#include <dlfcn.h>
+
+namespace {
+    struct DyldInterposeEntry {
+        const void* Replacement;
+        const void* Replacee;
+    };
+
+    bool IsGLProcName(const char* name) {
+        if (name == nullptr) {
+            return false;
+        }
+
+        if (strncmp(name, "CGL", 3) == 0) {
+            return true;
+        }
+
+        if (strncmp(name, "gl", 2) != 0) {
+            return false;
+        }
+
+        // Avoid stealing glfw*/glib*/glX*/global application symbols.
+        return name[2] >= 'A' && name[2] <= 'Z' && name[2] != 'X';
+    }
+
+    void* MobileGLDlsym(void* handle, const char* symbol) {
+        if (IsGLProcName(symbol)) {
+            if (void* proc = MobileGL::MG_Impl::GetProcAddress(symbol)) {
+                return proc;
+            }
+        }
+
+        return dlsym(handle, symbol);
+    }
+
+    __attribute__((used)) static const DyldInterposeEntry kMobileGLDyldInterpose[]
+        __attribute__((section("__DATA,__interpose"))) = {
+            {reinterpret_cast<const void*>(MobileGLDlsym), reinterpret_cast<const void*>(dlsym)},
+        };
+} // namespace
+
+#endif

MobileGL/MG_Impl/EGLImpl/EGLImpl.cpp

@@ -10,6 +10,8 @@
 #include "../GetProcAddress.h"
 #include <MG_Backend/BackendObjects.h>
 #include <MG_State/EGLState/Core.h>
+#include <mutex>
+#include <sstream>
 #include <type_traits>
 
 namespace MobileGL::MG_Impl::EGLImpl {
@@ -31,9 +33,22 @@ namespace MobileGL::MG_Impl::EGLImpl {
             return backendObject;
         }
 
+        std::recursive_mutex& EGLOperationMutex() {
+            static std::recursive_mutex mutex;
+            return mutex;
+        }
+
+        String CurrentThreadIdString() {
+            std::ostringstream stream;
+            stream << std::this_thread::get_id();
+            return stream.str();
+        }
+
         MG_Backend::WindowBackend DetectWindowBackend() {
 #if defined(ANDROID) || defined(__ANDROID__)
             return MG_Backend::WindowBackend::Android;
+#elif defined(__APPLE__)
+            return MG_Backend::WindowBackend::MetalLayer;
 #elif defined(__linux__)
             return MG_Backend::WindowBackend::X11;
 #else
@@ -53,6 +68,18 @@ namespace MobileGL::MG_Impl::EGLImpl {
             return defaultValue;
         }
 
+        EGLint GetAttribValueAttrib(const EGLAttrib* attribList, EGLint attrib, EGLint defaultValue) {
+            if (!attribList) {
+                return defaultValue;
+            }
+            for (SizeT i = 0; attribList[i] != EGL_NONE; i += 2) {
+                if (attribList[i] == attrib) {
+                    return static_cast<EGLint>(attribList[i + 1]);
+                }
+            }
+            return defaultValue;
+        }
+
         template <typename NativeType>
         Bool IsNullNativeHandle(NativeType nativeHandle) {
             if constexpr (std::is_pointer_v<NativeType>) {
@@ -91,25 +118,35 @@ namespace MobileGL::MG_Impl::EGLImpl {
             return EGL_NO_SURFACE;
         }
 
-        auto* backendObject = GetBackendObject(state);
-        if (!backendObject) {
-            MGLOG_E("activeBackendObject not initialized!");
-            return EGL_NO_SURFACE;
-        }
-
         const MG_Backend::WindowHandle windowHandle = {
             .Backend = DetectWindowBackend(),
             .Handle = ToVoidHandle(window),
+            .Width = static_cast<Uint32>(std::max<EGLint>(GetAttribValue(attrib_list, EGL_WIDTH, 0), 0)),
+            .Height = static_cast<Uint32>(std::max<EGLint>(GetAttribValue(attrib_list, EGL_HEIGHT, 0), 0)),
         };
-        if (!backendObject->CreateEGLWindowSurface(windowHandle)) {
+
+        EGLSurface surface = state->CreateWindowSurface(dpy, config, window, attrib_list);
+        if (surface == EGL_NO_SURFACE) {
+            return EGL_NO_SURFACE;
+        }
+
+        auto* backendObject = GetBackendObject(state);
+        if (!backendObject) {
+            MGLOG_E("activeBackendObject not initialized!");
+            state->DestroySurface(dpy, surface);
+            return EGL_NO_SURFACE;
+        }
+        if (!backendObject->CreateEGLWindowSurface(surface, windowHandle)) {
+            state->DestroySurface(dpy, surface);
             state->SetError(EGL_BAD_NATIVE_WINDOW);
             return EGL_NO_SURFACE;
         }
 
-        return state->CreateWindowSurface(dpy, config, window, attrib_list);
+        return surface;
     }
 
     EGLBoolean SwapBuffers(EGLDisplay dpy, EGLSurface draw) {
+        const std::lock_guard<std::recursive_mutex> operationLock(EGLOperationMutex());
         auto* state = GetState();
         if (!state) {
             return EGL_FALSE;
@@ -125,6 +162,7 @@ namespace MobileGL::MG_Impl::EGLImpl {
             return EGL_FALSE;
         }
         if (!backendObject->SwapEGLBuffers(dpy, draw)) {
+            MGLOG_E("eglSwapBuffers failed on thread=%s dpy=%p draw=%p", CurrentThreadIdString().c_str(), dpy, draw);
             state->SetError(EGL_BAD_SURFACE);
             return EGL_FALSE;
         }
@@ -186,6 +224,7 @@ namespace MobileGL::MG_Impl::EGLImpl {
     }
 
     EGLBoolean MakeCurrent(EGLDisplay dpy, EGLSurface draw, EGLSurface read, EGLContext ctx) {
+        const std::lock_guard<std::recursive_mutex> operationLock(EGLOperationMutex());
         auto* state = GetState();
         if (!state) {
             return EGL_FALSE;
@@ -195,17 +234,30 @@ namespace MobileGL::MG_Impl::EGLImpl {
         const auto oldDraw = state->GetCurrentSurface(EGL_DRAW);
         const auto oldRead = state->GetCurrentSurface(EGL_READ);
         const auto oldContext = state->GetCurrentContext();
+        const String threadId = CurrentThreadIdString();
+
+        MGLOG_D("eglMakeCurrent begin thread=%s dpy=%p draw=%p read=%p ctx=%p oldDpy=%p oldDraw=%p oldRead=%p oldCtx=%p",
+                threadId.c_str(), dpy, draw, read, ctx, oldDisplay, oldDraw, oldRead, oldContext);
 
         if (!state->MakeCurrent(dpy, draw, read, ctx)) {
+            const EGLint error = state->ConsumeError();
+            MGLOG_D("eglMakeCurrent rejected by EGLState thread=%s error=0x%04x", threadId.c_str(), error);
+            state->SetError(error);
             return EGL_FALSE;
         }
 
         const Bool releaseCurrentRequest =
-            dpy == EGL_NO_DISPLAY && draw == EGL_NO_SURFACE && read == EGL_NO_SURFACE && ctx == EGL_NO_CONTEXT;
+            draw == EGL_NO_SURFACE && read == EGL_NO_SURFACE && ctx == EGL_NO_CONTEXT;
         if (releaseCurrentRequest) {
             if (auto* backendObject = MG_Backend::pActiveBackendObject.get()) {
-                (void)backendObject->MakeEGLCurrent(dpy, draw, read, ctx);
+                if (!backendObject->MakeEGLCurrent(dpy, draw, read, ctx)) {
+                    MGLOG_E("eglMakeCurrent release failed in backend thread=%s", threadId.c_str());
+                    state->MakeCurrent(oldDisplay, oldDraw, oldRead, oldContext);
+                    state->SetError(EGL_BAD_ACCESS);
+                    return EGL_FALSE;
+                }
             }
+            MGLOG_D("eglMakeCurrent release succeeded thread=%s", threadId.c_str());
             return EGL_TRUE;
         }
 
@@ -216,10 +268,14 @@ namespace MobileGL::MG_Impl::EGLImpl {
             return EGL_FALSE;
         }
         if (!backendObject->MakeEGLCurrent(dpy, draw, read, ctx)) {
+            MGLOG_E("eglMakeCurrent backend attach failed thread=%s dpy=%p draw=%p read=%p ctx=%p", threadId.c_str(),
+                    dpy, draw, read, ctx);
             state->SetError(EGL_BAD_ACCESS);
             state->MakeCurrent(oldDisplay, oldDraw, oldRead, oldContext);
             return EGL_FALSE;
         }
+        MGLOG_D("eglMakeCurrent attach succeeded thread=%s dpy=%p draw=%p read=%p ctx=%p", threadId.c_str(), dpy, draw,
+                read, ctx);
         return EGL_TRUE;
     }
 
@@ -232,11 +288,18 @@ namespace MobileGL::MG_Impl::EGLImpl {
     }
 
     EGLBoolean DestroySurface(EGLDisplay dpy, EGLSurface surface) {
+        const std::lock_guard<std::recursive_mutex> operationLock(EGLOperationMutex());
         auto* state = GetState();
         if (!state) {
             return EGL_FALSE;
         }
-        return state->DestroySurface(dpy, surface) ? EGL_TRUE : EGL_FALSE;
+        if (!state->DestroySurface(dpy, surface)) {
+            return EGL_FALSE;
+        }
+        if (auto* backendObject = MG_Backend::pActiveBackendObject.get()) {
+            backendObject->ReleaseEGLSurface(surface);
+        }
+        return EGL_TRUE;
     }
 
     EGLBoolean Terminate(EGLDisplay dpy) {
@@ -258,6 +321,9 @@ namespace MobileGL::MG_Impl::EGLImpl {
         if (!state) {
             return EGL_FALSE;
         }
+        if (auto* backendObject = MG_Backend::pActiveBackendObject.get()) {
+            (void)backendObject->MakeEGLCurrent(EGL_NO_DISPLAY, EGL_NO_SURFACE, EGL_NO_SURFACE, EGL_NO_CONTEXT);
+        }
         state->ReleaseThread();
         return EGL_TRUE;
     }
@@ -330,7 +396,14 @@ namespace MobileGL::MG_Impl::EGLImpl {
         case EGL_CLIENT_APIS:
             return "OpenGL OpenGL_ES";
         case EGL_EXTENSIONS:
-            return "";
+            if (display == EGL_NO_DISPLAY) {
+                return "EGL_EXT_client_extensions "
+                       "EGL_EXT_platform_base "
+                       "EGL_KHR_platform_base "
+                       "EGL_MESA_platform_surfaceless";
+            }
+            return "EGL_KHR_create_context "
+                   "EGL_MESA_platform_surfaceless";
         default:
             state->SetError(EGL_BAD_PARAMETER);
             return nullptr;
@@ -342,7 +415,17 @@ namespace MobileGL::MG_Impl::EGLImpl {
         if (!state) {
             return EGL_FALSE;
         }
-        return state->SwapInterval(dpy, interval) ? EGL_TRUE : EGL_FALSE;
+        if (!state->SwapInterval(dpy, interval)) {
+            return EGL_FALSE;
+        }
+        // Forward the request to the backend's native presentation path; without this
+        // the app's vsync setting only ever reaches MobileGL's shadow state and the
+        // native surface stays at the driver default (interval 1 = always vsynced).
+        auto* backendObject = GetBackendObject(state);
+        if (backendObject) {
+            backendObject->SetEGLSwapInterval(static_cast<Int>(interval));
+        }
+        return EGL_TRUE;
     }
 
     EGLSurface CreatePbufferSurface(EGLDisplay dpy, EGLConfig config, const EGLint* attrib_list) {
@@ -361,7 +444,7 @@ namespace MobileGL::MG_Impl::EGLImpl {
         if (!backendObject) {
             return EGL_NO_SURFACE;
         }
-        if (!backendObject->CreateEGLPbufferSurface(width, height)) {
+        if (!backendObject->CreateEGLPbufferSurface(surface, width, height)) {
             state->DestroySurface(dpy, surface);
             state->SetError(EGL_BAD_ALLOC);
             return EGL_NO_SURFACE;
@@ -584,22 +667,53 @@ namespace MobileGL::MG_Impl::EGLImpl {
             return EGL_NO_SURFACE;
         }
 
-        auto* backendObject = GetBackendObject(state);
-        if (!backendObject) {
-            MGLOG_E("activeBackendObject not initialized!");
-            return EGL_NO_SURFACE;
-        }
-
         const MG_Backend::WindowHandle windowHandle = {
             .Backend = DetectWindowBackend(),
             .Handle = native_window,
+            .Width = static_cast<Uint32>(std::max<EGLint>(GetAttribValueAttrib(attrib_list, EGL_WIDTH, 0), 0)),
+            .Height = static_cast<Uint32>(std::max<EGLint>(GetAttribValueAttrib(attrib_list, EGL_HEIGHT, 0), 0)),
         };
-        if (!backendObject->CreateEGLWindowSurface(windowHandle)) {
+
+        EGLSurface surface = state->CreatePlatformWindowSurface(dpy, config, native_window, attrib_list);
+        if (surface == EGL_NO_SURFACE) {
+            return EGL_NO_SURFACE;
+        }
+
+        auto* backendObject = GetBackendObject(state);
+        if (!backendObject) {
+            MGLOG_E("activeBackendObject not initialized!");
+            state->DestroySurface(dpy, surface);
+            return EGL_NO_SURFACE;
+        }
+        if (!backendObject->CreateEGLWindowSurface(surface, windowHandle)) {
+            state->DestroySurface(dpy, surface);
             state->SetError(EGL_BAD_NATIVE_WINDOW);
             return EGL_NO_SURFACE;
         }
 
-        return state->CreatePlatformWindowSurface(dpy, config, native_window, attrib_list);
+        return surface;
+    }
+
+    EGLBoolean ResizePlatformWindowSurface(EGLDisplay dpy, EGLSurface surface, EGLint width, EGLint height) {
+        auto* state = GetState();
+        if (!state) {
+            return EGL_FALSE;
+        }
+        if (!state->ResizeSurface(dpy, surface, width, height)) {
+            return EGL_FALSE;
+        }
+        auto* backendObject = GetBackendObject(state);
+        if (!backendObject) {
+            MGLOG_E("activeBackendObject not initialized!");
+            return EGL_FALSE;
+        }
+        width = std::max<EGLint>(width, 1);
+        height = std::max<EGLint>(height, 1);
+        if (!backendObject->ResizeEGLWindowSurface(surface, static_cast<Uint32>(width), static_cast<Uint32>(height))) {
+            state->SetError(EGL_BAD_NATIVE_WINDOW);
+            return EGL_FALSE;
+        }
+        return EGL_TRUE;
     }
 
     EGLSurface CreatePlatformPixmapSurface(EGLDisplay dpy, EGLConfig config, void* native_pixmap,

MobileGL/MG_Impl/EGLImpl/EGLImpl.h

@@ -57,6 +57,7 @@ namespace MobileGL::MG_Impl::EGLImpl {
     EGLDisplay GetPlatformDisplay(EGLenum platform, void* native_display, const EGLAttrib* attrib_list);
     EGLSurface CreatePlatformWindowSurface(EGLDisplay dpy, EGLConfig config, void* native_window,
                                            const EGLAttrib* attrib_list);
+    EGLBoolean ResizePlatformWindowSurface(EGLDisplay dpy, EGLSurface surface, EGLint width, EGLint height);
     EGLSurface CreatePlatformPixmapSurface(EGLDisplay dpy, EGLConfig config, void* native_pixmap,
                                            const EGLAttrib* attrib_list);
     EGLBoolean WaitSync(EGLDisplay dpy, EGLSync sync, EGLint flags);

MobileGL/MG_Impl/EGLImpl/Exporting/Definitions.cpp

@@ -235,6 +235,14 @@ MOBILEGL_EGL_API EGLDisplay eglGetPlatformDisplay(EGLenum platform, void* native
     return MobileGL::MG_Impl::EGLImpl::GetPlatformDisplay(platform, native_display, attrib_list);
 }
 
+MOBILEGL_EGL_API EGLDisplay eglGetPlatformDisplayEXT(EGLenum platform, void* native_display,
+                                                     const EGLint* attrib_list) {
+    MGLOG_D("eglGetPlatformDisplayEXT(platform=%u, native_display=%p, attrib_list=%p)", platform, native_display,
+            attrib_list);
+    return MobileGL::MG_Impl::EGLImpl::GetPlatformDisplay(
+        platform, native_display, reinterpret_cast<const EGLAttrib*>(attrib_list));
+}
+
 MOBILEGL_EGL_API EGLSurface eglCreatePlatformWindowSurface(EGLDisplay dpy, EGLConfig config, void* native_window,
                                                            const EGLAttrib* attrib_list) {
     MGLOG_D("eglCreatePlatformWindowSurface(dpy=%p, config=%p, native_window=%p, attrib_list=%p)", dpy, config,

MobileGL/MG_Impl/GLImpl/Buffer/GL_Buffer.cpp

@@ -8,6 +8,7 @@
 
 #include "GL_Buffer.h"
 #include "Validators.h"
+#include <Config.h>
 #include <MG_State/GLState/Core.h>
 #include <MG_State/GLState/ErrorState/Error.h>
 #include <MG_Util/Converters/GLToStr/GLEnumConverter.h>
@@ -208,6 +209,26 @@ namespace MobileGL::MG_Impl::GLImpl {
             return bufferObject;
         }
 
+        // MOBILEGL_COHERENT_AS_FLUSH: rewrite a validated persistent FLUSH_EXPLICIT mapping
+        // request to coherent semantics: the map becomes coherent-persistent (eligible for
+        // the zero-copy backend map, otherwise synced wholesale at draw time), so its writes
+        // reach the GPU without glFlushMappedBufferRange; flush calls on rewritten maps are
+        // tolerated as no-ops by the FlushMappedBufferRange entry points. Non-persistent
+        // maps keep spec FLUSH_EXPLICIT behavior on purpose: the GPU cannot read them while
+        // mapped, so they gain nothing from the rewrite, and honoring only the app's flushed
+        // subranges avoids clobbering GPU-written bytes elsewhere in the mapped range.
+        // Runs after validation so the app's original access combination is what gets
+        // validated (Coherent is injected without requiring GL_MAP_COHERENT_BIT storage).
+        Flags<BufferMappingAccessBit> ApplyCoherentAsFlush(Flags<BufferMappingAccessBit> accessBits) {
+            if (!MG_Config::Features.CoherentAsFlush) return accessBits;
+            if (!(accessBits & BufferMappingAccessBit::FlushExplicit)) return accessBits;
+            if (!(accessBits & BufferMappingAccessBit::Persistent)) return accessBits;
+            accessBits = Flags<BufferMappingAccessBit>(
+                accessBits.GetRaw() & ~static_cast<Uint>(BufferMappingAccessBit::FlushExplicit));
+            accessBits |= BufferMappingAccessBit::Coherent;
+            return accessBits;
+        }
+
         Bool ValidateStorageFlags(GLbitfield flags, BufferOp op) {
             constexpr GLbitfield validFlags = GL_MAP_READ_BIT | GL_MAP_WRITE_BIT | GL_MAP_PERSISTENT_BIT |
                                               GL_MAP_COHERENT_BIT | GL_DYNAMIC_STORAGE_BIT | GL_CLIENT_STORAGE_BIT;
@@ -420,7 +441,10 @@ 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);
         }
     }
@@ -465,6 +489,15 @@ namespace MobileGL::MG_Impl::GLImpl {
 
         auto mappingAccess = bufferObject->GetMappingAccess();
         if (!(mappingAccess & BufferMappingAccessBit::FlushExplicit)) {
+            // MOBILEGL_COHERENT_AS_FLUSH strips FLUSH_EXPLICIT from persistent maps at map
+            // time (leaving Persistent|Coherent), so honor the app's flush on such a map as
+            // a no-op: its writes reach the backend without explicit flushes. Other maps
+            // keep the spec error.
+            if (MG_Config::Features.CoherentAsFlush &&
+                (mappingAccess & BufferMappingAccessBit::Persistent) &&
+                (mappingAccess & BufferMappingAccessBit::Coherent)) {
+                return;
+            }
             MG_State::pGLContext->RecordError(
                 ErrorCode::InvalidOperation,
                 MakeUnique<GenericErrorInfo>(
@@ -605,7 +638,7 @@ namespace MobileGL::MG_Impl::GLImpl {
         }
 
         void* result = bufferObject->AcquireMemoryRange(
-            {static_cast<SizeT>(offset), static_cast<SizeT>(offset + length)}, accessBits);
+            {static_cast<SizeT>(offset), static_cast<SizeT>(offset + length)}, ApplyCoherentAsFlush(accessBits));
         if (!result) {
             MG_State::pGLContext->RecordError(
                 ErrorCode::OutOfMemory,
@@ -799,6 +832,55 @@ namespace MobileGL::MG_Impl::GLImpl {
         bufferObject->UploadSubData({(void*)data, (SizeT)size}, offset);
     }
 
+    void GetBufferSubData_State(GLenum target, GLintptr offset, GLsizeiptr size, void* data) {
+        MGLOG_D("%s: target = %s, offset = %d, size = %d, data = %p", __func__,
+                MG_Util::ConvertGLEnumToString(target).c_str(), offset, size, data);
+        if (!data) {
+            // Match BufferSubData_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", "GetBufferSubData_State",
+                                                                           "Offset and size must be non-negative."));
+            return;
+        }
+
+        BufferTarget bufferTarget = MG_Util::ConvertGLEnumToBufferTarget(target);
+        if (!BufferImpl::ValidateBufferTarget(bufferTarget)) return;
+        auto& bindingSlot = GetBufferBindingSlot(bufferTarget);
+
+        auto& bufferObject = bindingSlot.GetBoundObject();
+        if (!bufferObject) {
+            MG_State::pGLContext->RecordError(
+                ErrorCode::InvalidOperation,
+                MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", "GetBufferSubData_State",
+                                             "Buffer target is bound to no buffer object."));
+            return;
+        }
+
+        SizeT bufferSize = bufferObject->GetSize();
+        if (static_cast<SizeT>(offset) + static_cast<SizeT>(size) > bufferSize) {
+            MG_State::pGLContext->RecordError(
+                ErrorCode::InvalidValue,
+                MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", "GetBufferSubData_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", "GetBufferSubData_State",
+                                             "Cannot read from a buffer object mapped without GL_MAP_PERSISTENT_BIT."));
+            return;
+        }
+
+        bufferObject->DownloadSubData(data, static_cast<SizeT>(offset), static_cast<SizeT>(size));
+    }
+
     void BufferData_State(GLenum target, GLsizeiptr size, const void* data, GLenum usage) {
         MGLOG_D("%s: %s, size = %d, data = %p, usage = %s", __func__, MG_Util::ConvertGLEnumToString(target).c_str(),
                 size, data, MG_Util::ConvertGLEnumToString(usage).c_str());
@@ -834,10 +916,7 @@ namespace MobileGL::MG_Impl::GLImpl {
         }
 
         bufferObject->SetUsage(bufferUsage);
-        bufferObject->Resize(size);
-        if (data) {
-            bufferObject->UploadData({(void*)data, (SizeT)size}, 0);
-        }
+        bufferObject->Respecify(size, data);
     }
 
     void BufferStorage_State(GLenum target, GLsizeiptr size, const void* data, GLbitfield flags) {
@@ -928,10 +1007,7 @@ namespace MobileGL::MG_Impl::GLImpl {
         }
 
         bufferObject->SetUsage(bufferUsage);
-        bufferObject->Resize(size);
-        if (data) {
-            bufferObject->UploadData({(void*)data, (SizeT)size}, 0);
-        }
+        bufferObject->Respecify(size, data);
     }
 
     void NamedBufferSubData_State(GLuint buffer, GLintptr offset, GLsizeiptr size, const void* data) {
@@ -1154,7 +1230,7 @@ namespace MobileGL::MG_Impl::GLImpl {
         }
 
         return bufferObject->AcquireMemoryRange({static_cast<SizeT>(offset), static_cast<SizeT>(offset + length)},
-                                                accessBits);
+                                                ApplyCoherentAsFlush(accessBits));
     }
 
     GLboolean UnmapNamedBuffer_State(GLuint buffer) {
@@ -1196,7 +1272,15 @@ namespace MobileGL::MG_Impl::GLImpl {
                                              "Offset and length exceed mapped range."));
             return;
         }
-        if (!(bufferObject->GetMappingAccess() & BufferMappingAccessBit::FlushExplicit)) {
+        const auto namedMappingAccess = bufferObject->GetMappingAccess();
+        if (!(namedMappingAccess & BufferMappingAccessBit::FlushExplicit)) {
+            // See FlushMappedBufferRange_State: rewritten coherent-as-flush persistent maps
+            // tolerate app flushes as no-ops.
+            if (MG_Config::Features.CoherentAsFlush &&
+                (namedMappingAccess & BufferMappingAccessBit::Persistent) &&
+                (namedMappingAccess & BufferMappingAccessBit::Coherent)) {
+                return;
+            }
             MG_State::pGLContext->RecordError(
                 ErrorCode::InvalidOperation,
                 MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", "FlushMappedNamedBufferRange_State",
@@ -1266,23 +1350,32 @@ namespace MobileGL::MG_Impl::GLImpl {
                 MG_Util::ConvertGLEnumToString(target).c_str(), pointIndex, buffer);
         BufferTarget bufferTarget = MG_Util::ConvertGLEnumToBufferTarget(target);
         if (!BufferImpl::ValidateBufferBindingPointTarget(bufferTarget)) return;
+        if (!BufferImpl::ValidateBufferBindingPointIndex(bufferTarget, pointIndex)) return;
+        MG_State::pGLContext->TouchBufferBindingPoint(bufferTarget, pointIndex);
 
         auto& point = MG_State::pGLContext->GetBufferBindingPoint(bufferTarget, pointIndex);
+        SharedPtr<MG_State::GLState::BufferObject> bufferObject;
         if (buffer == 0) {
             point.Bind(nullptr);
             point.SetRange(Range1D(0, 0));
             return;
         }
 
+        if (!BufferImpl::ValidateBufferName(buffer, true)) return;
+
         Bool doesBufferObjectCreated = MG_State::pGLContext->ValidateBufferObject(buffer);
         if (!doesBufferObjectCreated) {
             MG_State::pGLContext->CreateBufferObject(buffer);
         }
-        auto& bufferObject = MG_State::pGLContext->GetBufferObject(buffer);
+        bufferObject = MG_State::pGLContext->GetBufferObject(buffer);
 
         point.Bind(bufferObject);
-        point.SetRange(Range1D(0, bufferObject->GetSize()));
-        MGLOG_D("%s: set range (0, %d)", __func__, bufferObject->GetSize());
+        if (bufferObject) {
+            point.SetRange(Range1D(0, bufferObject->GetSize()), false);
+            MGLOG_D("%s: set range (0, %d)", __func__, bufferObject->GetSize());
+        } else {
+            point.ClearRange();
+        }
     }
 
     void BindBufferRange_State(GLenum target, GLuint index, GLuint buffer, GLintptr offset, GLsizeiptr size) {
@@ -1290,22 +1383,31 @@ namespace MobileGL::MG_Impl::GLImpl {
                 MG_Util::ConvertGLEnumToString(target).c_str(), index, buffer, offset, size);
         BufferTarget bufferTarget = MG_Util::ConvertGLEnumToBufferTarget(target);
         if (!BufferImpl::ValidateBufferBindingPointTarget(bufferTarget)) return;
+        if (!BufferImpl::ValidateBufferBindingPointIndex(bufferTarget, index)) return;
+        MG_State::pGLContext->TouchBufferBindingPoint(bufferTarget, index);
 
         auto& point = MG_State::pGLContext->GetBufferBindingPoint(bufferTarget, index);
+        SharedPtr<MG_State::GLState::BufferObject> bufferObject;
         if (buffer == 0) {
             point.Bind(nullptr);
             point.SetRange(Range1D(0, 0));
             return;
         }
 
+        if (!BufferImpl::ValidateBufferName(buffer, true)) return;
+
         Bool doesBufferObjectCreated = MG_State::pGLContext->ValidateBufferObject(buffer);
         if (!doesBufferObjectCreated) {
             MG_State::pGLContext->CreateBufferObject(buffer);
         }
-        auto& bufferObject = MG_State::pGLContext->GetBufferObject(buffer);
+        bufferObject = MG_State::pGLContext->GetBufferObject(buffer);
 
         point.Bind(bufferObject);
-        point.SetRange(Range1D(offset, offset + size));
+        if (bufferObject) {
+            point.SetRange(Range1D(offset, offset + size));
+        } else {
+            point.ClearRange();
+        }
     }
 
     /* @INSERTION_POINT:FUNCTION_IMPLEMENTATION@ */
@@ -1313,14 +1415,12 @@ namespace MobileGL::MG_Impl::GLImpl {
         GetBufferParameteriv_State(target, pname, params);
     }
 
-    void GetBufferParameteri64v(GLenum target, GLenum pname, GLint64* params) {
-        GetBufferParameteri64v_State(target, pname, params);
-    }
-
     void GetBufferPointerv(GLenum target, GLenum pname, void** params) {
         GetBufferPointerv_State(target, pname, params);
     }
-
+    void GetBufferParameteri64v(GLenum target, GLenum pname, GLint64* params) {
+        GetBufferParameteri64v_State(target, pname, params);
+    }
     GLboolean IsBuffer(GLuint buffer) {
         return IsBuffer_State(buffer);
     }
@@ -1417,6 +1517,10 @@ namespace MobileGL::MG_Impl::GLImpl {
         BufferSubData_State(target, offset, size, data);
     }
 
+    void GetBufferSubData(GLenum target, GLintptr offset, GLsizeiptr size, void* data) {
+        GetBufferSubData_State(target, offset, size, data);
+    }
+
     void BufferData(GLenum target, GLsizeiptr size, const void* data, GLenum usage) {
         BufferData_State(target, size, data, usage);
     }
@@ -1436,4 +1540,23 @@ namespace MobileGL::MG_Impl::GLImpl {
     void BindBufferRange(GLenum target, GLuint index, GLuint buffer, GLintptr offset, GLsizeiptr size) {
         BindBufferRange_State(target, index, buffer, offset, size);
     }
+
+    // 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).
+    void BindBuffersBase(GLenum target, GLuint first, GLsizei count, const GLuint* buffers) {
+        for (GLsizei i = 0; i < count; ++i) {
+            BindBufferBase_State(target, first + i, buffers ? buffers[i] : 0);
+        }
+    }
+
+    void BindBuffersRange(GLenum target, GLuint first, GLsizei count, const GLuint* buffers, const GLintptr* offsets,
+                          const GLsizeiptr* sizes) {
+        for (GLsizei i = 0; i < count; ++i) {
+            if (!buffers || buffers[i] == 0) {
+                BindBufferBase_State(target, first + i, 0);
+            } else {
+                BindBufferRange_State(target, first + i, buffers[i], offsets ? offsets[i] : 0, sizes ? sizes[i] : 0);
+            }
+        }
+    }
 } // namespace MobileGL::MG_Impl::GLImpl

MobileGL/MG_Impl/GLImpl/Buffer/GL_Buffer.h

@@ -40,10 +40,14 @@ namespace MobileGL::MG_Impl::GLImpl {
     void CopyBufferSubData(GLenum readTarget, GLenum writeTarget, GLintptr readOffset, GLintptr writeOffset,
                            GLsizeiptr size);
     void BufferSubData(GLenum target, GLintptr offset, GLsizeiptr size, const void* data);
+    void GetBufferSubData(GLenum target, 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);
     void BindBufferBase(GLenum target, GLuint index, GLuint buffer);
     void BindBufferRange(GLenum target, GLuint index, GLuint buffer, GLintptr offset, GLsizeiptr size);
+    void BindBuffersBase(GLenum target, GLuint first, GLsizei count, const GLuint* buffers);
+    void BindBuffersRange(GLenum target, GLuint first, GLsizei count, const GLuint* buffers, const GLintptr* offsets,
+                          const GLsizeiptr* sizes);
 
 } // namespace MobileGL::MG_Impl::GLImpl

MobileGL/MG_Impl/GLImpl/Buffer/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>
@@ -52,6 +53,26 @@ 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)));
+        }
+
+        if (index < pointCount) {
+            return true;
+        }
+
+        MG_State::pGLContext->RecordError(
+            ErrorCode::InvalidValue,
+            MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl/BufferImpl", "ValidateBufferBindingPointIndex",
+                                         std::format("Binding point index {} is out of range for target {}.", index,
+                                                     MG_Util::ConvertBufferTargetToString(target))));
+        return false;
+    }
+
     Bool ValidateBufferName(Uint index, Bool allowZero) {
         if (index == 0) {
             if (allowZero) return true;

MobileGL/MG_Impl/GLImpl/Buffer/Validators.h

@@ -16,4 +16,5 @@ namespace MobileGL::MG_Impl::GLImpl::BufferImpl {
     Bool ValidateBufferUsage(BufferUsage usage);
     Bool ValidateBufferMappingAccess(Flags<BufferMappingAccessBit> accessBits);
     Bool ValidateBufferBindingPointTarget(BufferTarget target);
+    Bool ValidateBufferBindingPointIndex(BufferTarget target, Uint index);
 } // namespace MobileGL::MG_Impl::GLImpl::BufferImpl

MobileGL/MG_Impl/GLImpl/Drawing/GL_Drawing.cpp

@@ -9,9 +9,75 @@
 #include "GL_Drawing.h"
 #include <Config.h>
 #include <MG_State/GLState/Core.h>
+#include <MG_State/EGLState/Core.h>
 #include <MG_Backend/BackendObjects.h>
 
 namespace MobileGL::MG_Impl::GLImpl {
+    static Bool ValidateCurrentProgramForExecution(const char* functionName) {
+        const auto& currentProgram = MG_State::pGLContext->GetCurrentProgram();
+        if (!currentProgram) {
+            MG_State::pGLContext->RecordError(
+                ErrorCode::InvalidOperation,
+                MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", functionName, "There is no current program object."));
+            return false;
+        }
+
+        if (!currentProgram->GetLinkStatus()) {
+            MG_State::pGLContext->RecordError(
+                ErrorCode::InvalidOperation,
+                MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", functionName,
+                                             "The current program object is not linked."));
+            return false;
+        }
+
+        return true;
+    }
+
+    static Bool ValidateCurrentProgramForCompute(const char* functionName) {
+        if (!ValidateCurrentProgramForExecution(functionName)) return false;
+
+        const auto& currentProgram = MG_State::pGLContext->GetCurrentProgram();
+        if (currentProgram->GetShaderIndexByStage(ShaderStage::Compute) < 0) {
+            MG_State::pGLContext->RecordError(
+                ErrorCode::InvalidOperation,
+                MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", functionName,
+                                             "The current program object has no compute shader stage."));
+            return false;
+        }
+
+        return true;
+    }
+
+    static Bool ValidatePrimitiveModeForBackend(const char* functionName, GLenum mode) {
+        const auto& activeBackendObject = MG_Backend::pActiveBackendObject;
+        if (!activeBackendObject) {
+            MG_State::pGLContext->RecordError(
+                ErrorCode::InvalidOperation,
+                MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", functionName, "No active backend object."));
+            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 (vao && vao->GetExternalIndex() == 0 && !MG_State::IsRelaxedSemanticsActive()) {
+            MG_State::pGLContext->RecordError(
+                ErrorCode::InvalidOperation,
+                MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", functionName,
+                                             "Default vertex array object cannot be used for drawing in core profile."));
+            return false;
+        }
+
+        return true;
+    }
+
     void Clear_Backend(GLbitfield mask) {
 #ifdef TRACY_ENABLE
         ZoneScopedC(TRACY_ZONECOLOR_BACKEND);
@@ -50,6 +116,13 @@ namespace MobileGL::MG_Impl::GLImpl {
         MG_Backend::gBackendFunctionsTable.GL.DrawArrays(mode, first, count);
     }
 
+    void MultiDrawArrays_Backend(GLenum mode, const GLint* first, const GLsizei* count, GLsizei drawcount) {
+#ifdef TRACY_ENABLE
+        ZoneScopedC(TRACY_ZONECOLOR_BACKEND);
+#endif
+        MG_Backend::gBackendFunctionsTable.GL.MultiDrawArrays(mode, first, count, drawcount);
+    }
+
     void DrawElementsBaseVertex_Backend(GLenum mode, GLsizei count, GLenum type, const void* indices,
                                         GLint basevertex) {
 #ifdef TRACY_ENABLE
@@ -182,6 +255,7 @@ namespace MobileGL::MG_Impl::GLImpl {
                 MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", __func__, "Backend does not support compute dispatch."));
             return;
         }
+        if (!ValidateCurrentProgramForCompute(__func__)) return;
         dispatchCompute(numGroupsX, numGroupsY, numGroupsZ);
     }
 
@@ -194,6 +268,7 @@ namespace MobileGL::MG_Impl::GLImpl {
                                              "Backend does not support indirect compute dispatch."));
             return;
         }
+        if (!ValidateCurrentProgramForCompute(__func__)) return;
         dispatchComputeIndirect(indirect);
     }
 
@@ -221,10 +296,14 @@ namespace MobileGL::MG_Impl::GLImpl {
     }
 
     void MultiDrawElementsIndirect(GLenum mode, GLenum type, const void* indirect, GLsizei drawcount, GLsizei stride) {
+        if (!ValidateCurrentProgramForExecution(__func__)) return;
+        if (!ValidatePrimitiveModeForBackend(__func__, mode)) return;
         MultiDrawElementsIndirect_Backend(mode, type, indirect, drawcount, stride);
     }
 
     void MultiDrawArraysIndirect(GLenum mode, const void* indirect, GLsizei drawcount, GLsizei stride) {
+        if (!ValidateCurrentProgramForExecution(__func__)) return;
+        if (!ValidatePrimitiveModeForBackend(__func__, mode)) return;
         MultiDrawArraysIndirect_Backend(mode, indirect, drawcount, stride);
     }
 
@@ -256,65 +335,105 @@ namespace MobileGL::MG_Impl::GLImpl {
 
     void DrawRangeElementsBaseVertex(GLenum mode, GLuint start, GLuint end, GLsizei count, GLenum type,
                                      const void* indices, GLint basevertex) {
+        if (!ValidateCurrentProgramForExecution(__func__)) return;
+        if (!ValidatePrimitiveModeForBackend(__func__, mode)) return;
         DrawRangeElementsBaseVertex_Backend(mode, start, end, count, type, indices, basevertex);
     }
 
     void DrawRangeElements(GLenum mode, GLuint start, GLuint end, GLsizei count, GLenum type, const void* indices) {
+        if (!ValidateCurrentProgramForExecution(__func__)) return;
+        if (!ValidatePrimitiveModeForBackend(__func__, mode)) return;
         DrawRangeElements_Backend(mode, start, end, count, type, indices);
     }
 
     void DrawElementsInstancedBaseVertexBaseInstance(GLenum mode, GLsizei count, GLenum type, const void* indices,
                                                      GLsizei instancecount, GLint basevertex, GLuint baseinstance) {
+        if (!ValidateCurrentProgramForExecution(__func__)) return;
+        if (!ValidatePrimitiveModeForBackend(__func__, mode)) return;
         DrawElementsInstancedBaseVertexBaseInstance_Backend(mode, count, type, indices, instancecount, basevertex,
                                                             baseinstance);
     }
 
     void DrawElementsInstancedBaseVertex(GLenum mode, GLsizei count, GLenum type, const void* indices,
                                          GLsizei instancecount, GLint basevertex) {
+        if (!ValidateCurrentProgramForExecution(__func__)) return;
+        if (!ValidatePrimitiveModeForBackend(__func__, mode)) return;
         DrawElementsInstancedBaseVertex_Backend(mode, count, type, indices, instancecount, basevertex);
     }
 
     void DrawElementsInstancedBaseInstance(GLenum mode, GLsizei count, GLenum type, const void* indices,
                                            GLsizei instancecount, GLuint baseinstance) {
+        if (!ValidateCurrentProgramForExecution(__func__)) return;
+        if (!ValidatePrimitiveModeForBackend(__func__, mode)) return;
         DrawElementsInstancedBaseInstance_Backend(mode, count, type, indices, instancecount, baseinstance);
     }
 
     void DrawElementsInstanced(GLenum mode, GLsizei count, GLenum type, const void* indices, GLsizei instancecount) {
+        if (!ValidateCurrentProgramForExecution(__func__)) return;
+        if (!ValidatePrimitiveModeForBackend(__func__, mode)) return;
         DrawElementsInstanced_Backend(mode, count, type, indices, instancecount);
     }
 
     void DrawElementsIndirect(GLenum mode, GLenum type, const void* indirect) {
+        if (!ValidateCurrentProgramForExecution(__func__)) return;
+        if (!ValidatePrimitiveModeForBackend(__func__, mode)) return;
         DrawElementsIndirect_Backend(mode, type, indirect);
     }
 
     void DrawArraysInstancedBaseInstance(GLenum mode, GLint first, GLsizei count, GLsizei instancecount,
                                          GLuint baseinstance) {
+        if (!ValidateCurrentProgramForExecution(__func__)) return;
+        if (!ValidatePrimitiveModeForBackend(__func__, mode)) return;
         DrawArraysInstancedBaseInstance_Backend(mode, first, count, instancecount, baseinstance);
     }
 
     void DrawArraysInstanced(GLenum mode, GLint first, GLsizei count, GLsizei instancecount) {
+        if (!ValidateCurrentProgramForExecution(__func__)) return;
+        if (!ValidatePrimitiveModeForBackend(__func__, mode)) return;
         DrawArraysInstanced_Backend(mode, first, count, instancecount);
     }
 
     void DrawArraysIndirect(GLenum mode, const void* indirect) {
+        if (!ValidateCurrentProgramForExecution(__func__)) return;
+        if (!ValidatePrimitiveModeForBackend(__func__, mode)) 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;
         DrawElementsBaseVertex_Backend(mode, count, type, indices, basevertex);
     }
 
     void DrawArrays(GLenum mode, GLint first, GLsizei count) {
+        if (!ValidateCurrentProgramForExecution(__func__)) return;
+        if (!ValidatePrimitiveModeForBackend(__func__, mode)) return;
         DrawArrays_Backend(mode, first, count);
     }
 
+    void MultiDrawArrays(GLenum mode, const GLint* first, const GLsizei* count, GLsizei drawcount) {
+        if (!ValidateCurrentProgramForExecution(__func__)) return;
+        if (!ValidatePrimitiveModeForBackend(__func__, mode)) return;
+        if (drawcount < 0) {
+            MG_State::pGLContext->RecordError(
+                ErrorCode::InvalidValue,
+                MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", __func__, "drawcount must be non-negative."));
+            return;
+        }
+        MultiDrawArrays_Backend(mode, first, count, drawcount);
+    }
+
     void MultiDrawElements(GLenum mode, const GLsizei* count, GLenum type, const void* const* indices,
                            GLsizei drawcount) {
+        if (!ValidateCurrentProgramForExecution(__func__)) return;
+        if (!ValidatePrimitiveModeForBackend(__func__, mode)) return;
         MultiDrawElements_Backend(mode, count, type, indices, drawcount);
     }
 
     void MultiDrawElementsBaseVertex(GLenum mode, const GLsizei* count, GLenum type, const void* const* indices,
                                      GLsizei drawcount, const GLint* basevertex) {
+        if (!ValidateCurrentProgramForExecution(__func__)) return;
+        if (!ValidatePrimitiveModeForBackend(__func__, mode)) return;
         MultiDrawElementsBaseVertex_Backend(mode, count, type, indices, drawcount, basevertex);
     }
 
@@ -323,6 +442,8 @@ 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;
         DrawElements_Backend(mode, count, type, indices);
     }
 

MobileGL/MG_Impl/GLImpl/Drawing/GL_Drawing.h

@@ -38,6 +38,7 @@ namespace MobileGL::MG_Impl::GLImpl {
     void DrawArraysIndirect(GLenum mode, const void* indirect);
     void DrawElementsBaseVertex(GLenum mode, GLsizei count, GLenum type, const void* indices, GLint basevertex);
     void DrawArrays(GLenum mode, GLint first, GLsizei count);
+    void MultiDrawArrays(GLenum mode, const GLint* first, const GLsizei* count, GLsizei drawcount);
     void MultiDrawElements(GLenum mode, const GLsizei* count, GLenum type, const void* const* indices,
                            GLsizei drawcount);
     void MultiDrawElementsBaseVertex(GLenum mode, const GLsizei* count, GLenum type, const void* const* indices,

MobileGL/MG_Impl/GLImpl/Exporting/Definitions.cpp

@@ -11,12 +11,15 @@
 #include "../Getter/GL_Getter.h"
 #include "../Sampler/GL_Sampler.h"
 #include "../Sync/GL_Sync.h"
+#include "../Query/GL_Query.h"
 #include "../Texture/GL_Texture.h"
 #include "../Drawing/GL_Drawing.h"
 #include "../Program/GL_Program.h"
 #include "../RenderState/GL_RenderState.h"
 #include "../Framebuffer/GL_Framebuffer.h"
 #include "../VertexArray/GL_VertexArray.h"
+#include "../Sync/GL_Sync.h"
+#include <MG_State/GLState/Core.h>
 
 #define DECLARE_GL_FUNCTION_STUB_HEAD(type, name, ...) MOBILEGL_GL_API type gl##name(__VA_ARGS__) {
 
@@ -76,7 +79,7 @@ DECLARE_GL_FUNCTION_HEAD(void, BufferSubData, GLenum target, GLintptr offset, GL
 DECLARE_GL_FUNCTION_HEAD(GLenum, CheckFramebufferStatus, GLenum target) DECLARE_GL_FUNCTION_END(GLenum, CheckFramebufferStatus, target)
 DECLARE_GL_FUNCTION_HEAD(void, Clear, GLbitfield mask) DECLARE_GL_FUNCTION_END_NO_RETURN(void, Clear, mask)
 DECLARE_GL_FUNCTION_HEAD(void, ClearColor, GLfloat red, GLfloat green, GLfloat blue, GLfloat alpha) DECLARE_GL_FUNCTION_END_NO_RETURN(void, ClearColor, red, green, blue, alpha)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, ClearDepthf, GLfloat d) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, ClearDepthf, d)
+DECLARE_GL_FUNCTION_HEAD(void, ClearDepthf, GLfloat d) DECLARE_GL_FUNCTION_END_NO_RETURN(void, ClearDepth, static_cast<GLclampd>(d))
 DECLARE_GL_FUNCTION_HEAD(void, ClearStencil, GLint s) DECLARE_GL_FUNCTION_END_NO_RETURN(void, ClearStencil, s)
 DECLARE_GL_FUNCTION_HEAD(void, ColorMask, GLboolean red, GLboolean green, GLboolean blue, GLboolean alpha) DECLARE_GL_FUNCTION_END_NO_RETURN(void, ColorMask, red, green, blue, alpha)
 DECLARE_GL_FUNCTION_HEAD(void, CompileShader, GLuint shader) DECLARE_GL_FUNCTION_END_NO_RETURN(void, CompileShader, shader)
@@ -95,7 +98,7 @@ DECLARE_GL_FUNCTION_HEAD(void, DeleteShader, GLuint shader) DECLARE_GL_FUNCTION_
 DECLARE_GL_FUNCTION_HEAD(void, DeleteTextures, GLsizei n, const GLuint* textures) DECLARE_GL_FUNCTION_END_NO_RETURN(void, DeleteTextures, n, textures)
 DECLARE_GL_FUNCTION_HEAD(void, DepthFunc, GLenum func) DECLARE_GL_FUNCTION_END_NO_RETURN(void, DepthFunc, func)
 DECLARE_GL_FUNCTION_HEAD(void, DepthMask, GLboolean flag) DECLARE_GL_FUNCTION_END_NO_RETURN(void, DepthMask, flag)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, DepthRangef, GLfloat n, GLfloat f) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, DepthRangef, n, f)
+DECLARE_GL_FUNCTION_HEAD(void, DepthRangef, GLfloat n, GLfloat f) DECLARE_GL_FUNCTION_END_NO_RETURN(void, DepthRange, static_cast<GLclampd>(n), static_cast<GLclampd>(f))
 DECLARE_GL_FUNCTION_HEAD(void, DetachShader, GLuint program, GLuint shader) DECLARE_GL_FUNCTION_END_NO_RETURN(void, DetachShader, program, shader)
 DECLARE_GL_FUNCTION_HEAD(void, Disable, GLenum cap) DECLARE_GL_FUNCTION_END_NO_RETURN(void, Disable, cap)
 DECLARE_GL_FUNCTION_HEAD(void, DisableVertexAttribArray, GLuint index) DECLARE_GL_FUNCTION_END_NO_RETURN(void, DisableVertexAttribArray, index)
@@ -117,10 +120,10 @@ DECLARE_GL_FUNCTION_HEAD(void, GetActiveAttrib, GLuint program, GLuint index, GL
 DECLARE_GL_FUNCTION_HEAD(void, GetActiveUniform, GLuint program, GLuint index, GLsizei bufSize, GLsizei* length, GLint* size, GLenum* type, GLchar* name) DECLARE_GL_FUNCTION_END_NO_RETURN(void, GetActiveUniform, program, index, bufSize, length, size, type, name)
 DECLARE_GL_FUNCTION_HEAD(void, GetAttachedShaders, GLuint program, GLsizei maxCount, GLsizei* count, GLuint* shaders) DECLARE_GL_FUNCTION_END_NO_RETURN(void, GetAttachedShaders, program, maxCount, count, shaders)
 DECLARE_GL_FUNCTION_HEAD(GLint, GetAttribLocation, GLuint program, const GLchar* name) DECLARE_GL_FUNCTION_END(GLint, GetAttribLocation, program, name)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, GetBooleanv, GLenum pname, GLboolean* data) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, GetBooleanv, pname, data)
+DECLARE_GL_FUNCTION_HEAD(void, GetBooleanv, GLenum pname, GLboolean* data) DECLARE_GL_FUNCTION_END_NO_RETURN(void, GetBooleanv, pname, data)
 DECLARE_GL_FUNCTION_HEAD(void, GetBufferParameteriv, GLenum target, GLenum pname, GLint* params) DECLARE_GL_FUNCTION_END_NO_RETURN(void, GetBufferParameteriv, target, pname, params)
 DECLARE_GL_FUNCTION_HEAD(GLenum, GetError) DECLARE_GL_FUNCTION_END(GLenum, GetError)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, GetFloatv, GLenum pname, GLfloat* data) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, GetFloatv, pname, data)
+DECLARE_GL_FUNCTION_HEAD(void, GetFloatv, GLenum pname, GLfloat* data) DECLARE_GL_FUNCTION_END_NO_RETURN(void, GetFloatv, pname, data)
 DECLARE_GL_FUNCTION_HEAD(void, GetFramebufferAttachmentParameteriv, GLenum target, GLenum attachment, GLenum pname, GLint* params) DECLARE_GL_FUNCTION_END_NO_RETURN(void, GetFramebufferAttachmentParameteriv, target, attachment, pname, params)
 DECLARE_GL_FUNCTION_HEAD(void, GetIntegerv, GLenum pname, GLint* data) DECLARE_GL_FUNCTION_END_NO_RETURN(void, GetIntegerv, pname, data)
 DECLARE_GL_FUNCTION_HEAD(void, GetProgramiv, GLuint program, GLenum pname, GLint* params) DECLARE_GL_FUNCTION_END_NO_RETURN(void, GetProgramiv, program, pname, params)
@@ -135,9 +138,9 @@ DECLARE_GL_FUNCTION_HEAD(void, GetTexParameteriv, GLenum target, GLenum pname, G
 DECLARE_GL_FUNCTION_HEAD(void, GetUniformfv, GLuint program, GLint location, GLfloat* params) DECLARE_GL_FUNCTION_END_NO_RETURN(void, GetUniformfv, program, location, params)
 DECLARE_GL_FUNCTION_HEAD(void, GetUniformiv, GLuint program, GLint location, GLint* params) DECLARE_GL_FUNCTION_END_NO_RETURN(void, GetUniformiv, program, location, params)
 DECLARE_GL_FUNCTION_HEAD(GLint, GetUniformLocation, GLuint program, const GLchar* name) DECLARE_GL_FUNCTION_END(GLint, GetUniformLocation, program, name)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, GetVertexAttribfv, GLuint index, GLenum pname, GLfloat* params) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, GetVertexAttribfv, index, pname, params)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, GetVertexAttribiv, GLuint index, GLenum pname, GLint* params) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, GetVertexAttribiv, index, pname, params)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, GetVertexAttribPointerv, GLuint index, GLenum pname, void** pointer) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, GetVertexAttribPointerv, index, pname, pointer)
+DECLARE_GL_FUNCTION_HEAD(void, GetVertexAttribfv, GLuint index, GLenum pname, GLfloat* params) DECLARE_GL_FUNCTION_END_NO_RETURN(void, GetVertexAttribfv, index, pname, params)
+DECLARE_GL_FUNCTION_HEAD(void, GetVertexAttribiv, GLuint index, GLenum pname, GLint* params) DECLARE_GL_FUNCTION_END_NO_RETURN(void, GetVertexAttribiv, index, pname, params)
+DECLARE_GL_FUNCTION_HEAD(void, GetVertexAttribPointerv, GLuint index, GLenum pname, void** pointer) DECLARE_GL_FUNCTION_END_NO_RETURN(void, GetVertexAttribPointerv, index, pname, pointer)
 DECLARE_GL_FUNCTION_HEAD(void, Hint, GLenum target, GLenum mode) DECLARE_GL_FUNCTION_END_NO_RETURN(void, Hint, target, mode)
 DECLARE_GL_FUNCTION_HEAD(GLboolean, IsBuffer, GLuint buffer) DECLARE_GL_FUNCTION_END(GLboolean, IsBuffer, buffer)
 DECLARE_GL_FUNCTION_HEAD(GLboolean, IsEnabled, GLenum cap) DECLARE_GL_FUNCTION_END(GLboolean, IsEnabled, cap)
@@ -190,14 +193,14 @@ DECLARE_GL_FUNCTION_HEAD(void, UniformMatrix3fv, GLint location, GLsizei count,
 DECLARE_GL_FUNCTION_HEAD(void, UniformMatrix4fv, GLint location, GLsizei count, GLboolean transpose, const GLfloat* value) DECLARE_GL_FUNCTION_END_NO_RETURN(void, UniformMatrix4fv, location, count, transpose, value)
 DECLARE_GL_FUNCTION_HEAD(void, UseProgram, GLuint program) DECLARE_GL_FUNCTION_END_NO_RETURN(void, UseProgram, program)
 DECLARE_GL_FUNCTION_HEAD(void, ValidateProgram, GLuint program) DECLARE_GL_FUNCTION_END_NO_RETURN(void, ValidateProgram, program)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, VertexAttrib1f, GLuint index, GLfloat x) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, VertexAttrib1f, index, x)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, VertexAttrib1fv, GLuint index, const GLfloat* v) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, VertexAttrib1fv, index, v)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, VertexAttrib2f, GLuint index, GLfloat x, GLfloat y) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, VertexAttrib2f, index, x, y)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, VertexAttrib2fv, GLuint index, const GLfloat* v) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, VertexAttrib2fv, index, v)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, VertexAttrib3f, GLuint index, GLfloat x, GLfloat y, GLfloat z) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, VertexAttrib3f, index, x, y, z)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, VertexAttrib3fv, GLuint index, const GLfloat* v) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, VertexAttrib3fv, index, v)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, VertexAttrib4f, GLuint index, GLfloat x, GLfloat y, GLfloat z, GLfloat w) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, VertexAttrib4f, index, x, y, z, w)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, VertexAttrib4fv, GLuint index, const GLfloat* v) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, VertexAttrib4fv, index, v)
+DECLARE_GL_FUNCTION_HEAD(void, VertexAttrib1f, GLuint index, GLfloat x) DECLARE_GL_FUNCTION_END_NO_RETURN(void, VertexAttrib1f, index, x)
+DECLARE_GL_FUNCTION_HEAD(void, VertexAttrib1fv, GLuint index, const GLfloat* v) DECLARE_GL_FUNCTION_END_NO_RETURN(void, VertexAttrib1fv, index, v)
+DECLARE_GL_FUNCTION_HEAD(void, VertexAttrib2f, GLuint index, GLfloat x, GLfloat y) DECLARE_GL_FUNCTION_END_NO_RETURN(void, VertexAttrib2f, index, x, y)
+DECLARE_GL_FUNCTION_HEAD(void, VertexAttrib2fv, GLuint index, const GLfloat* v) DECLARE_GL_FUNCTION_END_NO_RETURN(void, VertexAttrib2fv, index, v)
+DECLARE_GL_FUNCTION_HEAD(void, VertexAttrib3f, GLuint index, GLfloat x, GLfloat y, GLfloat z) DECLARE_GL_FUNCTION_END_NO_RETURN(void, VertexAttrib3f, index, x, y, z)
+DECLARE_GL_FUNCTION_HEAD(void, VertexAttrib3fv, GLuint index, const GLfloat* v) DECLARE_GL_FUNCTION_END_NO_RETURN(void, VertexAttrib3fv, index, v)
+DECLARE_GL_FUNCTION_HEAD(void, VertexAttrib4f, GLuint index, GLfloat x, GLfloat y, GLfloat z, GLfloat w) DECLARE_GL_FUNCTION_END_NO_RETURN(void, VertexAttrib4f, index, x, y, z, w)
+DECLARE_GL_FUNCTION_HEAD(void, VertexAttrib4fv, GLuint index, const GLfloat* v) DECLARE_GL_FUNCTION_END_NO_RETURN(void, VertexAttrib4fv, index, v)
 DECLARE_GL_FUNCTION_HEAD(void, VertexAttribPointer, GLuint index, GLint size, GLenum type, GLboolean normalized, GLsizei stride, const void* pointer) DECLARE_GL_FUNCTION_END_NO_RETURN(void, VertexAttribPointer, index, size, type, normalized, stride, pointer)
 DECLARE_GL_FUNCTION_HEAD(void, Viewport, GLint x, GLint y, GLsizei width, GLsizei height) DECLARE_GL_FUNCTION_END_NO_RETURN(void, Viewport, x, y, width, height)
 DECLARE_GL_FUNCTION_HEAD(void, ReadBuffer, GLenum src) DECLARE_GL_FUNCTION_END_NO_RETURN(void, ReadBuffer, src)
@@ -207,22 +210,22 @@ DECLARE_GL_FUNCTION_HEAD(void, TexSubImage3D, GLenum target, GLint level, GLint
 DECLARE_GL_FUNCTION_HEAD(void, CopyTexSubImage3D, GLenum target, GLint level, GLint xoffset, GLint yoffset, GLint zoffset, GLint x, GLint y, GLsizei width, GLsizei height) DECLARE_GL_FUNCTION_END_NO_RETURN(void, CopyTexSubImage3D, target, level, xoffset, yoffset, zoffset, x, y, width, height)
 DECLARE_GL_FUNCTION_HEAD(void, CompressedTexImage3D, GLenum target, GLint level, GLenum internalformat, GLsizei width, GLsizei height, GLsizei depth, GLint border, GLsizei imageSize, const void* data) DECLARE_GL_FUNCTION_END_NO_RETURN(void, CompressedTexImage3D, target, level, internalformat, width, height, depth, border, imageSize, data)
 DECLARE_GL_FUNCTION_HEAD(void, CompressedTexSubImage3D, GLenum target, GLint level, GLint xoffset, GLint yoffset, GLint zoffset, GLsizei width, GLsizei height, GLsizei depth, GLenum format, GLsizei imageSize, const void* data) DECLARE_GL_FUNCTION_END_NO_RETURN(void, CompressedTexSubImage3D, target, level, xoffset, yoffset, zoffset, width, height, depth, format, imageSize, data)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, GenQueries, GLsizei n, GLuint* ids) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, GenQueries, n, ids)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, DeleteQueries, GLsizei n, const GLuint* ids) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, DeleteQueries, n, ids)
-DECLARE_GL_FUNCTION_STUB_HEAD(GLboolean, IsQuery, GLuint id) DECLARE_GL_FUNCTION_STUB_END(GLboolean, IsQuery, id)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, BeginQuery, GLenum target, GLuint id) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, BeginQuery, target, id)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, EndQuery, GLenum target) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, EndQuery, target)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, GetQueryiv, GLenum target, GLenum pname, GLint* params) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, GetQueryiv, target, pname, params)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, GetQueryObjectuiv, GLuint id, GLenum pname, GLuint* params) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, GetQueryObjectuiv, id, pname, params)
+DECLARE_GL_FUNCTION_HEAD(void, GenQueries, GLsizei n, GLuint* ids) DECLARE_GL_FUNCTION_END_NO_RETURN(void, GenQueries, n, ids)
+DECLARE_GL_FUNCTION_HEAD(void, DeleteQueries, GLsizei n, const GLuint* ids) DECLARE_GL_FUNCTION_END_NO_RETURN(void, DeleteQueries, n, ids)
+DECLARE_GL_FUNCTION_HEAD(GLboolean, IsQuery, GLuint id) DECLARE_GL_FUNCTION_END(GLboolean, IsQuery, id)
+DECLARE_GL_FUNCTION_HEAD(void, BeginQuery, GLenum target, GLuint id) DECLARE_GL_FUNCTION_END_NO_RETURN(void, BeginQuery, target, id)
+DECLARE_GL_FUNCTION_HEAD(void, EndQuery, GLenum target) DECLARE_GL_FUNCTION_END_NO_RETURN(void, EndQuery, target)
+DECLARE_GL_FUNCTION_HEAD(void, GetQueryiv, GLenum target, GLenum pname, GLint* params) DECLARE_GL_FUNCTION_END_NO_RETURN(void, GetQueryiv, target, pname, params)
+DECLARE_GL_FUNCTION_HEAD(void, GetQueryObjectuiv, GLuint id, GLenum pname, GLuint* params) DECLARE_GL_FUNCTION_END_NO_RETURN(void, GetQueryObjectuiv, id, pname, params)
 DECLARE_GL_FUNCTION_HEAD(GLboolean, UnmapBuffer, GLenum target) DECLARE_GL_FUNCTION_END(GLboolean, UnmapBuffer, target)
 DECLARE_GL_FUNCTION_HEAD(void, GetBufferPointerv, GLenum target, GLenum pname, void** params) DECLARE_GL_FUNCTION_END_NO_RETURN(void, GetBufferPointerv, target, pname, params)
 DECLARE_GL_FUNCTION_HEAD(void, DrawBuffers, GLsizei n, const GLenum* bufs) DECLARE_GL_FUNCTION_END_NO_RETURN(void, DrawBuffers, n, bufs)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, UniformMatrix2x3fv, GLint location, GLsizei count, GLboolean transpose, const GLfloat* value) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, UniformMatrix2x3fv, location, count, transpose, value)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, UniformMatrix3x2fv, GLint location, GLsizei count, GLboolean transpose, const GLfloat* value) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, UniformMatrix3x2fv, location, count, transpose, value)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, UniformMatrix2x4fv, GLint location, GLsizei count, GLboolean transpose, const GLfloat* value) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, UniformMatrix2x4fv, location, count, transpose, value)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, UniformMatrix4x2fv, GLint location, GLsizei count, GLboolean transpose, const GLfloat* value) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, UniformMatrix4x2fv, location, count, transpose, value)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, UniformMatrix3x4fv, GLint location, GLsizei count, GLboolean transpose, const GLfloat* value) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, UniformMatrix3x4fv, location, count, transpose, value)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, UniformMatrix4x3fv, GLint location, GLsizei count, GLboolean transpose, const GLfloat* value) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, UniformMatrix4x3fv, location, count, transpose, value)
+DECLARE_GL_FUNCTION_HEAD(void, UniformMatrix2x3fv, GLint location, GLsizei count, GLboolean transpose, const GLfloat* value) DECLARE_GL_FUNCTION_END_NO_RETURN(void, UniformMatrix2x3fv, location, count, transpose, value)
+DECLARE_GL_FUNCTION_HEAD(void, UniformMatrix3x2fv, GLint location, GLsizei count, GLboolean transpose, const GLfloat* value) DECLARE_GL_FUNCTION_END_NO_RETURN(void, UniformMatrix3x2fv, location, count, transpose, value)
+DECLARE_GL_FUNCTION_HEAD(void, UniformMatrix2x4fv, GLint location, GLsizei count, GLboolean transpose, const GLfloat* value) DECLARE_GL_FUNCTION_END_NO_RETURN(void, UniformMatrix2x4fv, location, count, transpose, value)
+DECLARE_GL_FUNCTION_HEAD(void, UniformMatrix4x2fv, GLint location, GLsizei count, GLboolean transpose, const GLfloat* value) DECLARE_GL_FUNCTION_END_NO_RETURN(void, UniformMatrix4x2fv, location, count, transpose, value)
+DECLARE_GL_FUNCTION_HEAD(void, UniformMatrix3x4fv, GLint location, GLsizei count, GLboolean transpose, const GLfloat* value) DECLARE_GL_FUNCTION_END_NO_RETURN(void, UniformMatrix3x4fv, location, count, transpose, value)
+DECLARE_GL_FUNCTION_HEAD(void, UniformMatrix4x3fv, GLint location, GLsizei count, GLboolean transpose, const GLfloat* value) DECLARE_GL_FUNCTION_END_NO_RETURN(void, UniformMatrix4x3fv, location, count, transpose, value)
 DECLARE_GL_FUNCTION_HEAD(void, BlitFramebuffer, 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, BlitFramebuffer, srcX0, srcY0, srcX1, srcY1, dstX0, dstY0, dstX1, dstY1, mask, filter)
 //DECLARE_GL_FUNCTION_HEAD(void, BlitFramebuffer, 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, BlitFramebuffer, srcX0,srcY0,srcX1,srcY1,dstX0,dstY0,dstX1,dstY1,mask,filter)
 DECLARE_GL_FUNCTION_HEAD(void, RenderbufferStorageMultisample, GLenum target, GLsizei samples, GLenum internalformat, GLsizei width, GLsizei height) DECLARE_GL_FUNCTION_END_NO_RETURN(void, RenderbufferStorageMultisample, target, samples, internalformat, width, height)
@@ -240,29 +243,29 @@ DECLARE_GL_FUNCTION_HEAD(void, BindBufferBase, GLenum target, GLuint index, GLui
 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, 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_STUB_HEAD(void, GetVertexAttribIiv, GLuint index, GLenum pname, GLint* params) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, GetVertexAttribIiv, index, pname, params)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, GetVertexAttribIuiv, GLuint index, GLenum pname, GLuint* params) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, GetVertexAttribIuiv, index, pname, params)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, VertexAttribI4i, GLuint index, GLint x, GLint y, GLint z, GLint w) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, VertexAttribI4i, index, x, y, z, w)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, VertexAttribI4ui, GLuint index, GLuint x, GLuint y, GLuint z, GLuint w) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, VertexAttribI4ui, index, x, y, z, w)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, VertexAttribI4iv, GLuint index, const GLint* v) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, VertexAttribI4iv, index, v)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, VertexAttribI4uiv, GLuint index, const GLuint* v) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, VertexAttribI4uiv, index, v)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, GetUniformuiv, GLuint program, GLint location, GLuint* params) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, GetUniformuiv, program, location, params)
+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)
+DECLARE_GL_FUNCTION_HEAD(void, VertexAttribI4i, GLuint index, GLint x, GLint y, GLint z, GLint w) DECLARE_GL_FUNCTION_END_NO_RETURN(void, VertexAttribI4i, index, x, y, z, w)
+DECLARE_GL_FUNCTION_HEAD(void, VertexAttribI4ui, GLuint index, GLuint x, GLuint y, GLuint z, GLuint w) DECLARE_GL_FUNCTION_END_NO_RETURN(void, VertexAttribI4ui, index, x, y, z, w)
+DECLARE_GL_FUNCTION_HEAD(void, VertexAttribI4iv, GLuint index, const GLint* v) DECLARE_GL_FUNCTION_END_NO_RETURN(void, VertexAttribI4iv, index, v)
+DECLARE_GL_FUNCTION_HEAD(void, VertexAttribI4uiv, GLuint index, const GLuint* v) DECLARE_GL_FUNCTION_END_NO_RETURN(void, VertexAttribI4uiv, index, v)
+DECLARE_GL_FUNCTION_HEAD(void, GetUniformuiv, GLuint program, GLint location, GLuint* params) DECLARE_GL_FUNCTION_END_NO_RETURN(void, GetUniformuiv, program, location, params)
 DECLARE_GL_FUNCTION_HEAD(GLint, GetFragDataLocation, GLuint program, const GLchar* name) DECLARE_GL_FUNCTION_END(GLint, GetFragDataLocation, program, name)
 DECLARE_GL_FUNCTION_HEAD(void, Uniform1ui, GLint location, GLuint v0) DECLARE_GL_FUNCTION_END_NO_RETURN(void, Uniform1ui, location, v0)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, Uniform2ui, GLint location, GLuint v0, GLuint v1) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, Uniform2ui, location, v0, v1)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, Uniform3ui, GLint location, GLuint v0, GLuint v1, GLuint v2) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, Uniform3ui, location, v0, v1, v2)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, Uniform4ui, GLint location, GLuint v0, GLuint v1, GLuint v2, GLuint v3) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, Uniform4ui, location, v0, v1, v2, v3)
+DECLARE_GL_FUNCTION_HEAD(void, Uniform2ui, GLint location, GLuint v0, GLuint v1) DECLARE_GL_FUNCTION_END_NO_RETURN(void, Uniform2ui, location, v0, v1)
+DECLARE_GL_FUNCTION_HEAD(void, Uniform3ui, GLint location, GLuint v0, GLuint v1, GLuint v2) DECLARE_GL_FUNCTION_END_NO_RETURN(void, Uniform3ui, location, v0, v1, v2)
+DECLARE_GL_FUNCTION_HEAD(void, Uniform4ui, GLint location, GLuint v0, GLuint v1, GLuint v2, GLuint v3) DECLARE_GL_FUNCTION_END_NO_RETURN(void, Uniform4ui, location, v0, v1, v2, v3)
 DECLARE_GL_FUNCTION_HEAD(void, Uniform1uiv, GLint location, GLsizei count, const GLuint* value) DECLARE_GL_FUNCTION_END_NO_RETURN(void, Uniform1uiv, location, count, value)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, Uniform2uiv, GLint location, GLsizei count, const GLuint* value) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, Uniform2uiv, location, count, value)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, Uniform3uiv, GLint location, GLsizei count, const GLuint* value) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, Uniform3uiv, location, count, value)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, Uniform4uiv, GLint location, GLsizei count, const GLuint* value) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, Uniform4uiv, location, count, value)
+DECLARE_GL_FUNCTION_HEAD(void, Uniform2uiv, GLint location, GLsizei count, const GLuint* value) DECLARE_GL_FUNCTION_END_NO_RETURN(void, Uniform2uiv, location, count, value)
+DECLARE_GL_FUNCTION_HEAD(void, Uniform3uiv, GLint location, GLsizei count, const GLuint* value) DECLARE_GL_FUNCTION_END_NO_RETURN(void, Uniform3uiv, location, count, value)
+DECLARE_GL_FUNCTION_HEAD(void, Uniform4uiv, GLint location, GLsizei count, const GLuint* value) DECLARE_GL_FUNCTION_END_NO_RETURN(void, Uniform4uiv, location, count, value)
 DECLARE_GL_FUNCTION_HEAD(void, ClearBufferiv, GLenum buffer, GLint drawbuffer, const GLint* value) DECLARE_GL_FUNCTION_END_NO_RETURN(void, ClearBufferiv, buffer, drawbuffer, value)
 DECLARE_GL_FUNCTION_HEAD(void, ClearBufferuiv, GLenum buffer, GLint drawbuffer, const GLuint* value) DECLARE_GL_FUNCTION_END_NO_RETURN(void, ClearBufferuiv, buffer, drawbuffer, value)
 DECLARE_GL_FUNCTION_HEAD(void, ClearBufferfv, GLenum buffer, GLint drawbuffer, const GLfloat* value) DECLARE_GL_FUNCTION_END_NO_RETURN(void, ClearBufferfv, buffer, drawbuffer, value)
 DECLARE_GL_FUNCTION_HEAD(void, ClearBufferfi, GLenum buffer, GLint drawbuffer, GLfloat depth, GLint stencil) DECLARE_GL_FUNCTION_END_NO_RETURN(void, ClearBufferfi, buffer, drawbuffer, depth, stencil)
 DECLARE_GL_FUNCTION_HEAD(void, CopyBufferSubData, GLenum readTarget, GLenum writeTarget, GLintptr readOffset, GLintptr writeOffset, GLsizeiptr size) DECLARE_GL_FUNCTION_END_NO_RETURN(void, CopyBufferSubData, readTarget, writeTarget, readOffset, writeOffset, size)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, GetUniformIndices, GLuint program, GLsizei uniformCount, const GLchar* const* uniformNames, GLuint* uniformIndices) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, GetUniformIndices, program, uniformCount, uniformNames, uniformIndices)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, GetActiveUniformsiv, GLuint program, GLsizei uniformCount, const GLuint* uniformIndices, GLenum pname, GLint* params) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, GetActiveUniformsiv, program, uniformCount, uniformIndices, pname, params)
+DECLARE_GL_FUNCTION_HEAD(void, GetUniformIndices, GLuint program, GLsizei uniformCount, const GLchar* const* uniformNames, GLuint* uniformIndices) DECLARE_GL_FUNCTION_END_NO_RETURN(void, GetUniformIndices, program, uniformCount, uniformNames, uniformIndices)
+DECLARE_GL_FUNCTION_HEAD(void, GetActiveUniformsiv, GLuint program, GLsizei uniformCount, const GLuint* uniformIndices, GLenum pname, GLint* params) DECLARE_GL_FUNCTION_END_NO_RETURN(void, GetActiveUniformsiv, program, uniformCount, uniformIndices, pname, params)
 DECLARE_GL_FUNCTION_HEAD(GLuint, GetUniformBlockIndex, GLuint program, const GLchar* uniformBlockName) DECLARE_GL_FUNCTION_END(GLuint, GetUniformBlockIndex, program, uniformBlockName)
 DECLARE_GL_FUNCTION_HEAD(void, GetActiveUniformBlockiv, GLuint program, GLuint uniformBlockIndex, GLenum pname, GLint* params) DECLARE_GL_FUNCTION_END_NO_RETURN(void, GetActiveUniformBlockiv, program, uniformBlockIndex, pname, params)
 DECLARE_GL_FUNCTION_HEAD(void, GetActiveUniformBlockName, GLuint program, GLuint uniformBlockIndex, GLsizei bufSize, GLsizei* length, GLchar* uniformBlockName) DECLARE_GL_FUNCTION_END_NO_RETURN(void, GetActiveUniformBlockName, program, uniformBlockIndex, bufSize, length, uniformBlockName)
@@ -300,9 +303,9 @@ DECLARE_GL_FUNCTION_STUB_HEAD(void, ProgramBinary, GLuint program, GLenum binary
 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_STUB_HEAD(void, TexStorage2D, GLenum target, GLsizei levels, GLenum internalformat, GLsizei width, GLsizei height) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, TexStorage2D, target, levels, internalformat, width, height)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, TexStorage3D, GLenum target, GLsizei levels, GLenum internalformat, GLsizei width, GLsizei height, GLsizei depth) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, TexStorage3D, target, levels, internalformat, width, height, depth)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, GetInternalformativ, GLenum target, GLenum internalformat, GLenum pname, GLsizei bufSize, GLint* params) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, GetInternalformativ, target, internalformat, pname, bufSize, params)
+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)
 DECLARE_GL_FUNCTION_HEAD(void, DispatchCompute, GLuint num_groups_x, GLuint num_groups_y, GLuint num_groups_z) DECLARE_GL_FUNCTION_END_NO_RETURN(void, DispatchCompute, num_groups_x, num_groups_y, num_groups_z)
 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)
@@ -349,38 +352,52 @@ DECLARE_GL_FUNCTION_HEAD(void, ProgramUniform4fv, GLuint program, GLint location
 DECLARE_GL_FUNCTION_HEAD(void, ProgramUniformMatrix2fv, GLuint program, GLint location, GLsizei count, GLboolean transpose, const GLfloat* value) DECLARE_GL_FUNCTION_END_NO_RETURN(void, ProgramUniformMatrix2fv, program, location, count, transpose, value)
 DECLARE_GL_FUNCTION_HEAD(void, ProgramUniformMatrix3fv, GLuint program, GLint location, GLsizei count, GLboolean transpose, const GLfloat* value) DECLARE_GL_FUNCTION_END_NO_RETURN(void, ProgramUniformMatrix3fv, program, location, count, transpose, value)
 DECLARE_GL_FUNCTION_HEAD(void, ProgramUniformMatrix4fv, GLuint program, GLint location, GLsizei count, GLboolean transpose, const GLfloat* value) DECLARE_GL_FUNCTION_END_NO_RETURN(void, ProgramUniformMatrix4fv, program, location, count, transpose, value)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, ProgramUniformMatrix2x3fv, GLuint program, GLint location, GLsizei count, GLboolean transpose, const GLfloat* value) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, ProgramUniformMatrix2x3fv, program, location, count, transpose, value)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, ProgramUniformMatrix3x2fv, GLuint program, GLint location, GLsizei count, GLboolean transpose, const GLfloat* value) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, ProgramUniformMatrix3x2fv, program, location, count, transpose, value)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, ProgramUniformMatrix2x4fv, GLuint program, GLint location, GLsizei count, GLboolean transpose, const GLfloat* value) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, ProgramUniformMatrix2x4fv, program, location, count, transpose, value)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, ProgramUniformMatrix4x2fv, GLuint program, GLint location, GLsizei count, GLboolean transpose, const GLfloat* value) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, ProgramUniformMatrix4x2fv, program, location, count, transpose, value)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, ProgramUniformMatrix3x4fv, GLuint program, GLint location, GLsizei count, GLboolean transpose, const GLfloat* value) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, ProgramUniformMatrix3x4fv, program, location, count, transpose, value)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, ProgramUniformMatrix4x3fv, GLuint program, GLint location, GLsizei count, GLboolean transpose, const GLfloat* value) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, ProgramUniformMatrix4x3fv, program, location, count, transpose, value)
+DECLARE_GL_FUNCTION_HEAD(void, ProgramUniformMatrix2x3fv, GLuint program, GLint location, GLsizei count, GLboolean transpose, const GLfloat* value) DECLARE_GL_FUNCTION_END_NO_RETURN(void, ProgramUniformMatrix2x3fv, program, location, count, transpose, value)
+DECLARE_GL_FUNCTION_HEAD(void, ProgramUniformMatrix3x2fv, GLuint program, GLint location, GLsizei count, GLboolean transpose, const GLfloat* value) DECLARE_GL_FUNCTION_END_NO_RETURN(void, ProgramUniformMatrix3x2fv, program, location, count, transpose, value)
+DECLARE_GL_FUNCTION_HEAD(void, ProgramUniformMatrix2x4fv, GLuint program, GLint location, GLsizei count, GLboolean transpose, const GLfloat* value) DECLARE_GL_FUNCTION_END_NO_RETURN(void, ProgramUniformMatrix2x4fv, program, location, count, transpose, value)
+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, 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_STUB_HEAD(void, GetBooleani_v, GLenum target, GLuint index, GLboolean* data) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, GetBooleani_v, target, index, data)
+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)
 DECLARE_GL_FUNCTION_HEAD(void, MemoryBarrierByRegion, GLbitfield barriers) DECLARE_GL_FUNCTION_END_NO_RETURN(void, MemoryBarrierByRegion, barriers)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, TexStorage2DMultisample, GLenum target, GLsizei samples, GLenum internalformat, GLsizei width, GLsizei height, GLboolean fixedsamplelocations) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, TexStorage2DMultisample, target, samples, internalformat, width, height, fixedsamplelocations)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, GetMultisamplefv, GLenum pname, GLuint index, GLfloat* val) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, GetMultisamplefv, pname, index, val)
+DECLARE_GL_FUNCTION_HEAD(void, TexStorage2DMultisample, GLenum target, GLsizei samples, GLenum internalformat, GLsizei width, GLsizei height, GLboolean fixedsamplelocations) DECLARE_GL_FUNCTION_END_NO_RETURN(void, TexStorage2DMultisample, target, samples, internalformat, width, height, fixedsamplelocations)
+DECLARE_GL_FUNCTION_HEAD(void, GetMultisamplefv, GLenum pname, GLuint index, GLfloat* val) DECLARE_GL_FUNCTION_END_NO_RETURN(void, GetMultisamplefv, pname, index, val)
 DECLARE_GL_FUNCTION_HEAD(void, SampleMaski, GLuint maskNumber, GLbitfield mask) DECLARE_GL_FUNCTION_END_NO_RETURN(void, SampleMaski, maskNumber, mask)
 DECLARE_GL_FUNCTION_HEAD(void, GetTexLevelParameteriv, GLenum target, GLint level, GLenum pname, GLint* params) DECLARE_GL_FUNCTION_END_NO_RETURN(void, GetTexLevelParameteriv, target, level, pname, params)
 DECLARE_GL_FUNCTION_HEAD(void, GetTexLevelParameterfv, GLenum target, GLint level, GLenum pname, GLfloat* params) DECLARE_GL_FUNCTION_END_NO_RETURN(void, GetTexLevelParameterfv, target, level, pname, params)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, BindVertexBuffer, GLuint bindingindex, GLuint buffer, GLintptr offset, GLsizei stride) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, BindVertexBuffer, bindingindex, buffer, offset, stride)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, VertexAttribFormat, GLuint attribindex, GLint size, GLenum type, GLboolean normalized, GLuint relativeoffset) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, VertexAttribFormat, attribindex, size, type, normalized, relativeoffset)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, VertexAttribIFormat, GLuint attribindex, GLint size, GLenum type, GLuint relativeoffset) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, VertexAttribIFormat, attribindex, size, type, relativeoffset)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, VertexAttribBinding, GLuint attribindex, GLuint bindingindex) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, VertexAttribBinding, attribindex, bindingindex)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, VertexBindingDivisor, GLuint bindingindex, GLuint divisor) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, VertexBindingDivisor, bindingindex, divisor)
+DECLARE_GL_FUNCTION_HEAD(void, BindVertexBuffer, GLuint bindingindex, GLuint buffer, GLintptr offset, GLsizei stride) DECLARE_GL_FUNCTION_END_NO_RETURN(void, BindVertexBuffer, bindingindex, buffer, offset, stride)
+DECLARE_GL_FUNCTION_HEAD(void, VertexAttribFormat, GLuint attribindex, GLint size, GLenum type, GLboolean normalized, GLuint relativeoffset) DECLARE_GL_FUNCTION_END_NO_RETURN(void, VertexAttribFormat, attribindex, size, type, normalized, relativeoffset)
+DECLARE_GL_FUNCTION_HEAD(void, VertexAttribIFormat, GLuint attribindex, GLint size, GLenum type, GLuint relativeoffset) DECLARE_GL_FUNCTION_END_NO_RETURN(void, VertexAttribIFormat, attribindex, size, type, relativeoffset)
+DECLARE_GL_FUNCTION_HEAD(void, VertexAttribBinding, GLuint attribindex, GLuint bindingindex) DECLARE_GL_FUNCTION_END_NO_RETURN(void, VertexAttribBinding, attribindex, bindingindex)
+DECLARE_GL_FUNCTION_HEAD(void, VertexBindingDivisor, GLuint bindingindex, GLuint divisor) DECLARE_GL_FUNCTION_END_NO_RETURN(void, VertexBindingDivisor, bindingindex, divisor)
 DECLARE_GL_FUNCTION_STUB_HEAD(void, BlendBarrier) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, BlendBarrier)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, CopyImageSubData, GLuint srcName, GLenum srcTarget, GLint srcLevel, GLint srcX, GLint srcY, GLint srcZ, GLuint dstName, GLenum dstTarget, GLint dstLevel, GLint dstX, GLint dstY, GLint dstZ, GLsizei srcWidth, GLsizei srcHeight, GLsizei srcDepth) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, CopyImageSubData, srcName, srcTarget, srcLevel, srcX, srcY, srcZ, dstName, dstTarget, dstLevel, dstX, dstY, dstZ, srcWidth, srcHeight, srcDepth)
+DECLARE_GL_FUNCTION_HEAD(void, CopyImageSubData, GLuint srcName, GLenum srcTarget, GLint srcLevel, GLint srcX, GLint srcY, GLint srcZ, GLuint dstName, GLenum dstTarget, GLint dstLevel, GLint dstX, GLint dstY, GLint dstZ, GLsizei srcWidth, GLsizei srcHeight, GLsizei srcDepth) DECLARE_GL_FUNCTION_END_NO_RETURN(void, CopyImageSubData, srcName, srcTarget, srcLevel, srcX, srcY, srcZ, dstName, dstTarget, dstLevel, dstX, dstY, dstZ, srcWidth, srcHeight, srcDepth)
 DECLARE_GL_FUNCTION_STUB_HEAD(void, DebugMessageControl, GLenum source, GLenum type, GLenum severity, GLsizei count, const GLuint* ids, GLboolean enabled) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, DebugMessageControl, source, type, severity, count, ids, enabled)
 DECLARE_GL_FUNCTION_STUB_HEAD(void, DebugMessageInsert, GLenum source, GLenum type, GLuint id, GLenum severity, GLsizei length, const GLchar* buf) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, DebugMessageInsert, source, type, id, severity, length, buf)
 DECLARE_GL_FUNCTION_STUB_HEAD(void, DebugMessageCallback, GLDEBUGPROC callback, const void* userParam) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, DebugMessageCallback, callback, userParam)
 DECLARE_GL_FUNCTION_STUB_HEAD(GLuint, GetDebugMessageLog, GLuint count, GLsizei bufSize, GLenum* sources, GLenum* types, GLuint* ids, GLenum* severities, GLsizei* lengths, GLchar* messageLog) DECLARE_GL_FUNCTION_STUB_END(GLuint, GetDebugMessageLog, count, bufSize, sources, types, ids, severities, lengths, messageLog)
 DECLARE_GL_FUNCTION_STUB_HEAD(void, PushDebugGroup, GLenum source, GLuint id, GLsizei length, const GLchar* message) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, PushDebugGroup, source, id, length, message)
 DECLARE_GL_FUNCTION_STUB_HEAD(void, PopDebugGroup) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, PopDebugGroup)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, ObjectLabel, GLenum identifier, GLuint name, GLsizei length, const GLchar* label) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, ObjectLabel, identifier, name, length, label)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, GetObjectLabel, GLenum identifier, GLuint name, GLsizei bufSize, GLsizei* length, GLchar* label) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, GetObjectLabel, identifier, name, bufSize, length, label)
+MOBILEGL_GL_API void glObjectLabel(GLenum identifier, GLuint name, GLsizei length, const GLchar* label) {
+    (void)identifier;
+    (void)name;
+    (void)length;
+    (void)label;
+}
+MOBILEGL_GL_API void glGetObjectLabel(GLenum identifier, GLuint name, GLsizei bufSize, GLsizei* length, GLchar* label) {
+    (void)identifier;
+    (void)name;
+    if (length) {
+        *length = 0;
+    }
+    if (label && bufSize > 0) {
+        label[0] = '\0';
+    }
+}
 DECLARE_GL_FUNCTION_STUB_HEAD(void, ObjectPtrLabel, const void* ptr, GLsizei length, const GLchar* label) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, ObjectPtrLabel, ptr, length, label)
 DECLARE_GL_FUNCTION_STUB_HEAD(void, GetObjectPtrLabel, const void* ptr, GLsizei bufSize, GLsizei* length, GLchar* label) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, GetObjectPtrLabel, ptr, bufSize, length, label)
 DECLARE_GL_FUNCTION_STUB_HEAD(void, GetPointerv, GLenum pname, void** params) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, GetPointerv, pname, params)
@@ -394,7 +411,7 @@ DECLARE_GL_FUNCTION_HEAD(void, BlendFunci, GLuint buf, GLenum src, GLenum dst) D
 DECLARE_GL_FUNCTION_HEAD(void, BlendFunciARB, GLuint buf, GLenum src, GLenum dst) DECLARE_GL_FUNCTION_END_NO_RETURN(void, BlendFunci, buf, src, dst)
 DECLARE_GL_FUNCTION_HEAD(void, BlendFuncSeparatei, GLuint buf, GLenum srcRGB, GLenum dstRGB, GLenum srcAlpha, GLenum dstAlpha) DECLARE_GL_FUNCTION_END_NO_RETURN(void, BlendFuncSeparatei, buf, srcRGB, dstRGB, srcAlpha, dstAlpha)
 DECLARE_GL_FUNCTION_HEAD(void, BlendFuncSeparateiARB, GLuint buf, GLenum srcRGB, GLenum dstRGB, GLenum srcAlpha, GLenum dstAlpha) DECLARE_GL_FUNCTION_END_NO_RETURN(void, BlendFuncSeparatei, buf, srcRGB, dstRGB, srcAlpha, dstAlpha)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, ColorMaski, GLuint index, GLboolean r, GLboolean g, GLboolean b, GLboolean a) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, ColorMaski, index, r, g, b, a)
+DECLARE_GL_FUNCTION_HEAD(void, ColorMaski, GLuint index, GLboolean r, GLboolean g, GLboolean b, GLboolean a) DECLARE_GL_FUNCTION_END_NO_RETURN(void, ColorMaski, index, r, g, b, a)
 DECLARE_GL_FUNCTION_HEAD(GLboolean, IsEnabledi, GLenum target, GLuint index) DECLARE_GL_FUNCTION_END(GLboolean, IsEnabledi, target, index)
 DECLARE_GL_FUNCTION_HEAD(void, DrawElementsBaseVertex, GLenum mode, GLsizei count, GLenum type, const void* indices, GLint basevertex) DECLARE_GL_FUNCTION_END_NO_RETURN(void, DrawElementsBaseVertex, mode, count, type, indices, basevertex)
 DECLARE_GL_FUNCTION_HEAD(void, DrawRangeElementsBaseVertex, GLenum mode, GLuint start, GLuint end, GLsizei count, GLenum type, const void* indices, GLint basevertex) DECLARE_GL_FUNCTION_END_NO_RETURN(void, DrawRangeElementsBaseVertex, mode, start, end, count, type, indices, basevertex)
@@ -418,7 +435,7 @@ DECLARE_GL_FUNCTION_HEAD(void, GetSamplerParameterIiv, GLuint sampler, GLenum pn
 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_STUB_HEAD(void, TexStorage3DMultisample, GLenum target, GLsizei samples, GLenum internalformat, GLsizei width, GLsizei height, GLsizei depth, GLboolean fixedsamplelocations) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, TexStorage3DMultisample, target, samples, internalformat, width, height, depth, fixedsamplelocations)
+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)
 DECLARE_GL_FUNCTION_STUB_HEAD(void, IndexMask, GLuint mask) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, IndexMask, mask)
@@ -436,7 +453,7 @@ DECLARE_GL_FUNCTION_STUB_HEAD(void, GetClipPlane, GLenum plane, GLdouble* equati
 DECLARE_GL_FUNCTION_HEAD(void, DrawBuffer, GLenum mode) DECLARE_GL_FUNCTION_END_NO_RETURN(void, DrawBuffer, mode)
 DECLARE_GL_FUNCTION_STUB_HEAD(void, EnableClientState, GLenum cap) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, EnableClientState, cap)
 DECLARE_GL_FUNCTION_STUB_HEAD(void, DisableClientState, GLenum cap) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, DisableClientState, cap)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, GetDoublev, GLenum pname, GLdouble* params) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, GetDoublev, pname, params)
+DECLARE_GL_FUNCTION_HEAD(void, GetDoublev, GLenum pname, GLdouble* params) DECLARE_GL_FUNCTION_END_NO_RETURN(void, GetDoublev, pname, params)
 DECLARE_GL_FUNCTION_STUB_HEAD(void, PushAttrib, GLbitfield mask) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, PushAttrib, mask)
 DECLARE_GL_FUNCTION_STUB_HEAD(void, PopAttrib) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, PopAttrib)
 DECLARE_GL_FUNCTION_STUB_HEAD(void, PushClientAttrib, GLbitfield mask) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, PushClientAttrib, mask)
@@ -638,7 +655,7 @@ DECLARE_GL_FUNCTION_STUB_HEAD(void, GetMaterialfv, GLenum face, GLenum pname, GL
 DECLARE_GL_FUNCTION_STUB_HEAD(void, GetMaterialiv, GLenum face, GLenum pname, GLint* params) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, GetMaterialiv, face, pname, params)
 DECLARE_GL_FUNCTION_STUB_HEAD(void, ColorMaterial, GLenum face, GLenum mode) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, ColorMaterial, face, mode)
 DECLARE_GL_FUNCTION_STUB_HEAD(void, PixelZoom, GLfloat xfactor, GLfloat yfactor) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, PixelZoom, xfactor, yfactor)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, PixelStoref, GLenum pname, GLfloat param) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, PixelStoref, pname, param)
+DECLARE_GL_FUNCTION_HEAD(void, PixelStoref, GLenum pname, GLfloat param) DECLARE_GL_FUNCTION_END_NO_RETURN(void, PixelStoref, pname, param)
 DECLARE_GL_FUNCTION_STUB_HEAD(void, PixelTransferf, GLenum pname, GLfloat param) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, PixelTransferf, pname, param)
 DECLARE_GL_FUNCTION_STUB_HEAD(void, PixelTransferi, GLenum pname, GLint param) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, PixelTransferi, pname, param)
 DECLARE_GL_FUNCTION_STUB_HEAD(void, PixelMapfv, GLenum map, GLsizei mapsize, const GLfloat* values) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, PixelMapfv, map, mapsize, values)
@@ -709,22 +726,22 @@ DECLARE_GL_FUNCTION_STUB_HEAD(void, PopName) DECLARE_GL_FUNCTION_STUB_END_NO_RET
 DECLARE_GL_FUNCTION_HEAD(void, ClampColor, GLenum target, GLenum clamp) DECLARE_GL_FUNCTION_END_NO_RETURN(void, ClampColor, target, clamp)
 DECLARE_GL_FUNCTION_STUB_HEAD(void, BeginConditionalRender, GLuint id, GLenum mode) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, BeginConditionalRender, id, mode)
 DECLARE_GL_FUNCTION_STUB_HEAD(void, EndConditionalRender, void) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, EndConditionalRender)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, VertexAttribI1i, GLuint index, GLint x) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, VertexAttribI1i, index, x)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, VertexAttribI2i, GLuint index, GLint x, GLint y) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, VertexAttribI2i, index, x, y)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, VertexAttribI3i, GLuint index, GLint x, GLint y, GLint z) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, VertexAttribI3i, index, x, y, z)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, VertexAttribI1ui, GLuint index, GLuint x) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, VertexAttribI1ui, index, x)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, VertexAttribI2ui, GLuint index, GLuint x, GLuint y) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, VertexAttribI2ui, index, x, y)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, VertexAttribI3ui, GLuint index, GLuint x, GLuint y, GLuint z) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, VertexAttribI3ui, index, x, y, z)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, VertexAttribI1iv, GLuint index, const GLint* v) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, VertexAttribI1iv, index, v)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, VertexAttribI2iv, GLuint index, const GLint* v) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, VertexAttribI2iv, index, v)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, VertexAttribI3iv, GLuint index, const GLint* v) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, VertexAttribI3iv, index, v)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, VertexAttribI1uiv, GLuint index, const GLuint* v) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, VertexAttribI1uiv, index, v)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, VertexAttribI2uiv, GLuint index, const GLuint* v) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, VertexAttribI2uiv, index, v)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, VertexAttribI3uiv, GLuint index, const GLuint* v) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, VertexAttribI3uiv, index, v)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, VertexAttribI4bv, GLuint index, const GLbyte* v) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, VertexAttribI4bv, index, v)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, VertexAttribI4sv, GLuint index, const GLshort* v) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, VertexAttribI4sv, index, v)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, VertexAttribI4ubv, GLuint index, const GLubyte* v) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, VertexAttribI4ubv, index, v)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, VertexAttribI4usv, GLuint index, const GLushort* v) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, VertexAttribI4usv, index, v)
+DECLARE_GL_FUNCTION_HEAD(void, VertexAttribI1i, GLuint index, GLint x) DECLARE_GL_FUNCTION_END_NO_RETURN(void, VertexAttribI1i, index, x)
+DECLARE_GL_FUNCTION_HEAD(void, VertexAttribI2i, GLuint index, GLint x, GLint y) DECLARE_GL_FUNCTION_END_NO_RETURN(void, VertexAttribI2i, index, x, y)
+DECLARE_GL_FUNCTION_HEAD(void, VertexAttribI3i, GLuint index, GLint x, GLint y, GLint z) DECLARE_GL_FUNCTION_END_NO_RETURN(void, VertexAttribI3i, index, x, y, z)
+DECLARE_GL_FUNCTION_HEAD(void, VertexAttribI1ui, GLuint index, GLuint x) DECLARE_GL_FUNCTION_END_NO_RETURN(void, VertexAttribI1ui, index, x)
+DECLARE_GL_FUNCTION_HEAD(void, VertexAttribI2ui, GLuint index, GLuint x, GLuint y) DECLARE_GL_FUNCTION_END_NO_RETURN(void, VertexAttribI2ui, index, x, y)
+DECLARE_GL_FUNCTION_HEAD(void, VertexAttribI3ui, GLuint index, GLuint x, GLuint y, GLuint z) DECLARE_GL_FUNCTION_END_NO_RETURN(void, VertexAttribI3ui, index, x, y, z)
+DECLARE_GL_FUNCTION_HEAD(void, VertexAttribI1iv, GLuint index, const GLint* v) DECLARE_GL_FUNCTION_END_NO_RETURN(void, VertexAttribI1iv, index, v)
+DECLARE_GL_FUNCTION_HEAD(void, VertexAttribI2iv, GLuint index, const GLint* v) DECLARE_GL_FUNCTION_END_NO_RETURN(void, VertexAttribI2iv, index, v)
+DECLARE_GL_FUNCTION_HEAD(void, VertexAttribI3iv, GLuint index, const GLint* v) DECLARE_GL_FUNCTION_END_NO_RETURN(void, VertexAttribI3iv, index, v)
+DECLARE_GL_FUNCTION_HEAD(void, VertexAttribI1uiv, GLuint index, const GLuint* v) DECLARE_GL_FUNCTION_END_NO_RETURN(void, VertexAttribI1uiv, index, v)
+DECLARE_GL_FUNCTION_HEAD(void, VertexAttribI2uiv, GLuint index, const GLuint* v) DECLARE_GL_FUNCTION_END_NO_RETURN(void, VertexAttribI2uiv, index, v)
+DECLARE_GL_FUNCTION_HEAD(void, VertexAttribI3uiv, GLuint index, const GLuint* v) DECLARE_GL_FUNCTION_END_NO_RETURN(void, VertexAttribI3uiv, index, v)
+DECLARE_GL_FUNCTION_HEAD(void, VertexAttribI4bv, GLuint index, const GLbyte* v) DECLARE_GL_FUNCTION_END_NO_RETURN(void, VertexAttribI4bv, index, v)
+DECLARE_GL_FUNCTION_HEAD(void, VertexAttribI4sv, GLuint index, const GLshort* v) DECLARE_GL_FUNCTION_END_NO_RETURN(void, VertexAttribI4sv, index, v)
+DECLARE_GL_FUNCTION_HEAD(void, VertexAttribI4ubv, GLuint index, const GLubyte* v) DECLARE_GL_FUNCTION_END_NO_RETURN(void, VertexAttribI4ubv, index, v)
+DECLARE_GL_FUNCTION_HEAD(void, VertexAttribI4usv, GLuint index, const GLushort* v) DECLARE_GL_FUNCTION_END_NO_RETURN(void, VertexAttribI4usv, index, v)
 DECLARE_GL_FUNCTION_HEAD(void, BindFragDataLocation, GLuint program, GLuint color, const GLchar* name) DECLARE_GL_FUNCTION_END_NO_RETURN(void, BindFragDataLocation, program, color, name)
 DECLARE_GL_FUNCTION_HEAD(void, FramebufferTexture1D, GLenum target, GLenum attachment, GLenum textarget, GLuint texture, GLint level) DECLARE_GL_FUNCTION_END_NO_RETURN(void, FramebufferTexture1D, target, attachment, textarget, texture, level)
 DECLARE_GL_FUNCTION_HEAD(void, FramebufferTexture3D, GLenum target, GLenum attachment, GLenum textarget, GLuint texture, GLint level, GLint zoffset) DECLARE_GL_FUNCTION_END_NO_RETURN(void, FramebufferTexture3D, target, attachment, textarget, texture, level, zoffset)
@@ -768,12 +785,12 @@ DECLARE_GL_FUNCTION_STUB_HEAD(void, LoadTransposeMatrixf, const GLfloat* m) DECL
 DECLARE_GL_FUNCTION_STUB_HEAD(void, LoadTransposeMatrixd, const GLdouble* m) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, LoadTransposeMatrixd, m)
 DECLARE_GL_FUNCTION_STUB_HEAD(void, MultTransposeMatrixf, const GLfloat* m) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, MultTransposeMatrixf, m)
 DECLARE_GL_FUNCTION_STUB_HEAD(void, MultTransposeMatrixd, const GLdouble* m) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, MultTransposeMatrixd, m)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, MultiDrawArrays, GLenum mode, const GLint* first, const GLsizei* count, GLsizei drawcount) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, MultiDrawArrays, mode, first, count, drawcount)
+DECLARE_GL_FUNCTION_HEAD(void, MultiDrawArrays, GLenum mode, const GLint* first, const GLsizei* count, GLsizei drawcount) DECLARE_GL_FUNCTION_END_NO_RETURN(void, MultiDrawArrays, mode, first, count, drawcount)
 DECLARE_GL_FUNCTION_HEAD(void, MultiDrawElements, GLenum mode, const GLsizei* count, GLenum type, const void* const* indices, GLsizei drawcount) DECLARE_GL_FUNCTION_END_NO_RETURN(void, MultiDrawElements, mode, count, type, indices, drawcount)
 DECLARE_GL_FUNCTION_HEAD(void, PointParameterf, GLenum pname, GLfloat param) DECLARE_GL_FUNCTION_END_NO_RETURN(void, PointParameterf, pname, param)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, PointParameterfv, GLenum pname, const GLfloat* params) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, PointParameterfv, pname, params)
+DECLARE_GL_FUNCTION_HEAD(void, PointParameterfv, GLenum pname, const GLfloat* params) DECLARE_GL_FUNCTION_END_NO_RETURN(void, PointParameterfv, pname, params)
 DECLARE_GL_FUNCTION_HEAD(void, PointParameteri, GLenum pname, GLint param) DECLARE_GL_FUNCTION_END_NO_RETURN(void, PointParameteri, pname, param)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, PointParameteriv, GLenum pname, const GLint* params) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, PointParameteriv, pname, params)
+DECLARE_GL_FUNCTION_HEAD(void, PointParameteriv, GLenum pname, const GLint* params) DECLARE_GL_FUNCTION_END_NO_RETURN(void, PointParameteriv, pname, params)
 DECLARE_GL_FUNCTION_STUB_HEAD(void, FogCoordf, GLfloat coord) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, FogCoordf, coord)
 DECLARE_GL_FUNCTION_STUB_HEAD(void, FogCoordfv, const GLfloat* coord) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, FogCoordfv, coord)
 DECLARE_GL_FUNCTION_STUB_HEAD(void, FogCoordd, GLdouble coord) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, FogCoordd, coord)
@@ -812,56 +829,56 @@ DECLARE_GL_FUNCTION_STUB_HEAD(void, WindowPos3i, GLint x, GLint y, GLint z) DECL
 DECLARE_GL_FUNCTION_STUB_HEAD(void, WindowPos3iv, const GLint* v) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, WindowPos3iv, v)
 DECLARE_GL_FUNCTION_STUB_HEAD(void, WindowPos3s, GLshort x, GLshort y, GLshort z) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, WindowPos3s, x, y, z)
 DECLARE_GL_FUNCTION_STUB_HEAD(void, WindowPos3sv, const GLshort* v) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, WindowPos3sv, v)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, GetQueryObjectiv, GLuint id, GLenum pname, GLint* params) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, GetQueryObjectiv, id, pname, params)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, GetBufferSubData, GLenum target, GLintptr offset, GLsizeiptr size, void* data) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, GetBufferSubData, target, offset, size, data)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, GetVertexAttribdv, GLuint index, GLenum pname, GLdouble* params) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, GetVertexAttribdv, index, pname, params)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, VertexAttrib1d, GLuint index, GLdouble x) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, VertexAttrib1d, index, x)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, VertexAttrib1dv, GLuint index, const GLdouble* v) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, VertexAttrib1dv, index, v)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, VertexAttrib1s, GLuint index, GLshort x) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, VertexAttrib1s, index, x)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, VertexAttrib1sv, GLuint index, const GLshort* v) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, VertexAttrib1sv, index, v)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, VertexAttrib2d, GLuint index, GLdouble x, GLdouble y) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, VertexAttrib2d, index, x, y)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, VertexAttrib2dv, GLuint index, const GLdouble* v) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, VertexAttrib2dv, index, v)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, VertexAttrib2s, GLuint index, GLshort x, GLshort y) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, VertexAttrib2s, index, x, y)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, VertexAttrib2sv, GLuint index, const GLshort* v) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, VertexAttrib2sv, index, v)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, VertexAttrib3d, GLuint index, GLdouble x, GLdouble y, GLdouble z) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, VertexAttrib3d, index, x, y, z)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, VertexAttrib3dv, GLuint index, const GLdouble* v) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, VertexAttrib3dv, index, v)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, VertexAttrib3s, GLuint index, GLshort x, GLshort y, GLshort z) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, VertexAttrib3s, index, x, y, z)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, VertexAttrib3sv, GLuint index, const GLshort* v) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, VertexAttrib3sv, index, v)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, VertexAttrib4Nbv, GLuint index, const GLbyte* v) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, VertexAttrib4Nbv, index, v)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, VertexAttrib4Niv, GLuint index, const GLint* v) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, VertexAttrib4Niv, index, v)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, VertexAttrib4Nsv, GLuint index, const GLshort* v) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, VertexAttrib4Nsv, index, v)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, VertexAttrib4Nub, GLuint index, GLubyte x, GLubyte y, GLubyte z, GLubyte w) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, VertexAttrib4Nub, index, x, y, z, w)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, VertexAttrib4Nubv, GLuint index, const GLubyte* v) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, VertexAttrib4Nubv, index, v)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, VertexAttrib4Nuiv, GLuint index, const GLuint* v) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, VertexAttrib4Nuiv, index, v)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, VertexAttrib4Nusv, GLuint index, const GLushort* v) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, VertexAttrib4Nusv, index, v)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, VertexAttrib4bv, GLuint index, const GLbyte* v) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, VertexAttrib4bv, index, v)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, VertexAttrib4d, GLuint index, GLdouble x, GLdouble y, GLdouble z, GLdouble w) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, VertexAttrib4d, index, x, y, z, w)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, VertexAttrib4dv, GLuint index, const GLdouble* v) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, VertexAttrib4dv, index, v)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, VertexAttrib4iv, GLuint index, const GLint* v) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, VertexAttrib4iv, index, v)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, VertexAttrib4s, GLuint index, GLshort x, GLshort y, GLshort z, GLshort w) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, VertexAttrib4s, index, x, y, z, w)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, VertexAttrib4sv, GLuint index, const GLshort* v) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, VertexAttrib4sv, index, v)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, VertexAttrib4ubv, GLuint index, const GLubyte* v) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, VertexAttrib4ubv, index, v)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, VertexAttrib4uiv, GLuint index, const GLuint* v) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, VertexAttrib4uiv, index, v)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, VertexAttrib4usv, GLuint index, const GLushort* v) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, VertexAttrib4usv, index, v)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, PrimitiveRestartIndex, GLuint index) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, PrimitiveRestartIndex, index)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, GetActiveUniformName, GLuint program, GLuint uniformIndex, GLsizei bufSize, GLsizei* length, GLchar* uniformName) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, GetActiveUniformName, program, uniformIndex, bufSize, length, uniformName)
+DECLARE_GL_FUNCTION_HEAD(void, GetQueryObjectiv, GLuint id, GLenum pname, GLint* params) DECLARE_GL_FUNCTION_END_NO_RETURN(void, GetQueryObjectiv, id, pname, params)
+DECLARE_GL_FUNCTION_HEAD(void, GetBufferSubData, GLenum target, GLintptr offset, GLsizeiptr size, void* data) DECLARE_GL_FUNCTION_END_NO_RETURN(void, GetBufferSubData, target, offset, size, data)
+DECLARE_GL_FUNCTION_HEAD(void, GetVertexAttribdv, GLuint index, GLenum pname, GLdouble* params) DECLARE_GL_FUNCTION_END_NO_RETURN(void, GetVertexAttribdv, index, pname, params)
+DECLARE_GL_FUNCTION_HEAD(void, VertexAttrib1d, GLuint index, GLdouble x) DECLARE_GL_FUNCTION_END_NO_RETURN(void, VertexAttrib1d, index, x)
+DECLARE_GL_FUNCTION_HEAD(void, VertexAttrib1dv, GLuint index, const GLdouble* v) DECLARE_GL_FUNCTION_END_NO_RETURN(void, VertexAttrib1dv, index, v)
+DECLARE_GL_FUNCTION_HEAD(void, VertexAttrib1s, GLuint index, GLshort x) DECLARE_GL_FUNCTION_END_NO_RETURN(void, VertexAttrib1s, index, x)
+DECLARE_GL_FUNCTION_HEAD(void, VertexAttrib1sv, GLuint index, const GLshort* v) DECLARE_GL_FUNCTION_END_NO_RETURN(void, VertexAttrib1sv, index, v)
+DECLARE_GL_FUNCTION_HEAD(void, VertexAttrib2d, GLuint index, GLdouble x, GLdouble y) DECLARE_GL_FUNCTION_END_NO_RETURN(void, VertexAttrib2d, index, x, y)
+DECLARE_GL_FUNCTION_HEAD(void, VertexAttrib2dv, GLuint index, const GLdouble* v) DECLARE_GL_FUNCTION_END_NO_RETURN(void, VertexAttrib2dv, index, v)
+DECLARE_GL_FUNCTION_HEAD(void, VertexAttrib2s, GLuint index, GLshort x, GLshort y) DECLARE_GL_FUNCTION_END_NO_RETURN(void, VertexAttrib2s, index, x, y)
+DECLARE_GL_FUNCTION_HEAD(void, VertexAttrib2sv, GLuint index, const GLshort* v) DECLARE_GL_FUNCTION_END_NO_RETURN(void, VertexAttrib2sv, index, v)
+DECLARE_GL_FUNCTION_HEAD(void, VertexAttrib3d, GLuint index, GLdouble x, GLdouble y, GLdouble z) DECLARE_GL_FUNCTION_END_NO_RETURN(void, VertexAttrib3d, index, x, y, z)
+DECLARE_GL_FUNCTION_HEAD(void, VertexAttrib3dv, GLuint index, const GLdouble* v) DECLARE_GL_FUNCTION_END_NO_RETURN(void, VertexAttrib3dv, index, v)
+DECLARE_GL_FUNCTION_HEAD(void, VertexAttrib3s, GLuint index, GLshort x, GLshort y, GLshort z) DECLARE_GL_FUNCTION_END_NO_RETURN(void, VertexAttrib3s, index, x, y, z)
+DECLARE_GL_FUNCTION_HEAD(void, VertexAttrib3sv, GLuint index, const GLshort* v) DECLARE_GL_FUNCTION_END_NO_RETURN(void, VertexAttrib3sv, index, v)
+DECLARE_GL_FUNCTION_HEAD(void, VertexAttrib4Nbv, GLuint index, const GLbyte* v) DECLARE_GL_FUNCTION_END_NO_RETURN(void, VertexAttrib4Nbv, index, v)
+DECLARE_GL_FUNCTION_HEAD(void, VertexAttrib4Niv, GLuint index, const GLint* v) DECLARE_GL_FUNCTION_END_NO_RETURN(void, VertexAttrib4Niv, index, v)
+DECLARE_GL_FUNCTION_HEAD(void, VertexAttrib4Nsv, GLuint index, const GLshort* v) DECLARE_GL_FUNCTION_END_NO_RETURN(void, VertexAttrib4Nsv, index, v)
+DECLARE_GL_FUNCTION_HEAD(void, VertexAttrib4Nub, GLuint index, GLubyte x, GLubyte y, GLubyte z, GLubyte w) DECLARE_GL_FUNCTION_END_NO_RETURN(void, VertexAttrib4Nub, index, x, y, z, w)
+DECLARE_GL_FUNCTION_HEAD(void, VertexAttrib4Nubv, GLuint index, const GLubyte* v) DECLARE_GL_FUNCTION_END_NO_RETURN(void, VertexAttrib4Nubv, index, v)
+DECLARE_GL_FUNCTION_HEAD(void, VertexAttrib4Nuiv, GLuint index, const GLuint* v) DECLARE_GL_FUNCTION_END_NO_RETURN(void, VertexAttrib4Nuiv, index, v)
+DECLARE_GL_FUNCTION_HEAD(void, VertexAttrib4Nusv, GLuint index, const GLushort* v) DECLARE_GL_FUNCTION_END_NO_RETURN(void, VertexAttrib4Nusv, index, v)
+DECLARE_GL_FUNCTION_HEAD(void, VertexAttrib4bv, GLuint index, const GLbyte* v) DECLARE_GL_FUNCTION_END_NO_RETURN(void, VertexAttrib4bv, index, v)
+DECLARE_GL_FUNCTION_HEAD(void, VertexAttrib4d, GLuint index, GLdouble x, GLdouble y, GLdouble z, GLdouble w) DECLARE_GL_FUNCTION_END_NO_RETURN(void, VertexAttrib4d, index, x, y, z, w)
+DECLARE_GL_FUNCTION_HEAD(void, VertexAttrib4dv, GLuint index, const GLdouble* v) DECLARE_GL_FUNCTION_END_NO_RETURN(void, VertexAttrib4dv, index, v)
+DECLARE_GL_FUNCTION_HEAD(void, VertexAttrib4iv, GLuint index, const GLint* v) DECLARE_GL_FUNCTION_END_NO_RETURN(void, VertexAttrib4iv, index, v)
+DECLARE_GL_FUNCTION_HEAD(void, VertexAttrib4s, GLuint index, GLshort x, GLshort y, GLshort z, GLshort w) DECLARE_GL_FUNCTION_END_NO_RETURN(void, VertexAttrib4s, index, x, y, z, w)
+DECLARE_GL_FUNCTION_HEAD(void, VertexAttrib4sv, GLuint index, const GLshort* v) DECLARE_GL_FUNCTION_END_NO_RETURN(void, VertexAttrib4sv, index, v)
+DECLARE_GL_FUNCTION_HEAD(void, VertexAttrib4ubv, GLuint index, const GLubyte* v) DECLARE_GL_FUNCTION_END_NO_RETURN(void, VertexAttrib4ubv, index, v)
+DECLARE_GL_FUNCTION_HEAD(void, VertexAttrib4uiv, GLuint index, const GLuint* v) DECLARE_GL_FUNCTION_END_NO_RETURN(void, VertexAttrib4uiv, index, v)
+DECLARE_GL_FUNCTION_HEAD(void, VertexAttrib4usv, GLuint index, const GLushort* v) DECLARE_GL_FUNCTION_END_NO_RETURN(void, VertexAttrib4usv, index, v)
+DECLARE_GL_FUNCTION_HEAD(void, PrimitiveRestartIndex, GLuint index) DECLARE_GL_FUNCTION_END_NO_RETURN(void, PrimitiveRestartIndex, index)
+DECLARE_GL_FUNCTION_HEAD(void, GetActiveUniformName, GLuint program, GLuint uniformIndex, GLsizei bufSize, GLsizei* length, GLchar* uniformName) DECLARE_GL_FUNCTION_END_NO_RETURN(void, GetActiveUniformName, program, uniformIndex, bufSize, length, uniformName)
 DECLARE_GL_FUNCTION_HEAD(void, MultiDrawElementsBaseVertex, GLenum mode, const GLsizei* count, GLenum type, const void* const* indices, GLsizei drawcount, const GLint* basevertex) DECLARE_GL_FUNCTION_END_NO_RETURN(void, MultiDrawElementsBaseVertex, mode, count, type, indices, drawcount, basevertex)
 DECLARE_GL_FUNCTION_HEAD(void, ProvokingVertex, GLenum mode) DECLARE_GL_FUNCTION_END_NO_RETURN(void, ProvokingVertex, mode)
 DECLARE_GL_FUNCTION_HEAD(void, TexImage2DMultisample, GLenum target, GLsizei samples, GLenum internalformat, GLsizei width, GLsizei height, GLboolean fixedsamplelocations) DECLARE_GL_FUNCTION_END_NO_RETURN(void, TexImage2DMultisample, target, samples, internalformat, width, height, fixedsamplelocations)
 DECLARE_GL_FUNCTION_HEAD(void, TexImage3DMultisample, GLenum target, GLsizei samples, GLenum internalformat, GLsizei width, GLsizei height, GLsizei depth, GLboolean fixedsamplelocations) DECLARE_GL_FUNCTION_END_NO_RETURN(void, TexImage3DMultisample, target, samples, internalformat, width, height, depth, fixedsamplelocations)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, BindFragDataLocationIndexed, GLuint program, GLuint colorNumber, GLuint index, const GLchar* name) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, BindFragDataLocationIndexed, program, colorNumber, index, name)
-DECLARE_GL_FUNCTION_STUB_HEAD(GLint, GetFragDataIndex, GLuint program, const GLchar* name) DECLARE_GL_FUNCTION_STUB_END(GLint, GetFragDataIndex, program, name)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, QueryCounter, GLuint id, GLenum target) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, QueryCounter, id, target)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, GetQueryObjecti64v, GLuint id, GLenum pname, GLint64* params) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, GetQueryObjecti64v, id, pname, params)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, GetQueryObjectui64v, GLuint id, GLenum pname, GLuint64* params) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, GetQueryObjectui64v, id, pname, params)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, VertexAttribP1ui, GLuint index, GLenum type, GLboolean normalized, GLuint value) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, VertexAttribP1ui, index, type, normalized, value)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, VertexAttribP1uiv, GLuint index, GLenum type, GLboolean normalized, const GLuint* value) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, VertexAttribP1uiv, index, type, normalized, value)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, VertexAttribP2ui, GLuint index, GLenum type, GLboolean normalized, GLuint value) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, VertexAttribP2ui, index, type, normalized, value)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, VertexAttribP2uiv, GLuint index, GLenum type, GLboolean normalized, const GLuint* value) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, VertexAttribP2uiv, index, type, normalized, value)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, VertexAttribP3ui, GLuint index, GLenum type, GLboolean normalized, GLuint value) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, VertexAttribP3ui, index, type, normalized, value)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, VertexAttribP3uiv, GLuint index, GLenum type, GLboolean normalized, const GLuint* value) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, VertexAttribP3uiv, index, type, normalized, value)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, VertexAttribP4ui, GLuint index, GLenum type, GLboolean normalized, GLuint value) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, VertexAttribP4ui, index, type, normalized, value)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, VertexAttribP4uiv, GLuint index, GLenum type, GLboolean normalized, const GLuint* value) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, VertexAttribP4uiv, index, type, normalized, value)
+DECLARE_GL_FUNCTION_HEAD(void, BindFragDataLocationIndexed, GLuint program, GLuint colorNumber, GLuint index, const GLchar* name) DECLARE_GL_FUNCTION_END_NO_RETURN(void, BindFragDataLocationIndexed, program, colorNumber, index, name)
+DECLARE_GL_FUNCTION_HEAD(GLint, GetFragDataIndex, GLuint program, const GLchar* name) DECLARE_GL_FUNCTION_END(GLint, GetFragDataIndex, program, name)
+DECLARE_GL_FUNCTION_HEAD(void, QueryCounter, GLuint id, GLenum target) DECLARE_GL_FUNCTION_END_NO_RETURN(void, QueryCounter, id, target)
+DECLARE_GL_FUNCTION_HEAD(void, GetQueryObjecti64v, GLuint id, GLenum pname, GLint64* params) DECLARE_GL_FUNCTION_END_NO_RETURN(void, GetQueryObjecti64v, id, pname, params)
+DECLARE_GL_FUNCTION_HEAD(void, GetQueryObjectui64v, GLuint id, GLenum pname, GLuint64* params) DECLARE_GL_FUNCTION_END_NO_RETURN(void, GetQueryObjectui64v, id, pname, params)
+DECLARE_GL_FUNCTION_HEAD(void, VertexAttribP1ui, GLuint index, GLenum type, GLboolean normalized, GLuint value) DECLARE_GL_FUNCTION_END_NO_RETURN(void, VertexAttribP1ui, index, type, normalized, value)
+DECLARE_GL_FUNCTION_HEAD(void, VertexAttribP1uiv, GLuint index, GLenum type, GLboolean normalized, const GLuint* value) DECLARE_GL_FUNCTION_END_NO_RETURN(void, VertexAttribP1uiv, index, type, normalized, value)
+DECLARE_GL_FUNCTION_HEAD(void, VertexAttribP2ui, GLuint index, GLenum type, GLboolean normalized, GLuint value) DECLARE_GL_FUNCTION_END_NO_RETURN(void, VertexAttribP2ui, index, type, normalized, value)
+DECLARE_GL_FUNCTION_HEAD(void, VertexAttribP2uiv, GLuint index, GLenum type, GLboolean normalized, const GLuint* value) DECLARE_GL_FUNCTION_END_NO_RETURN(void, VertexAttribP2uiv, index, type, normalized, value)
+DECLARE_GL_FUNCTION_HEAD(void, VertexAttribP3ui, GLuint index, GLenum type, GLboolean normalized, GLuint value) DECLARE_GL_FUNCTION_END_NO_RETURN(void, VertexAttribP3ui, index, type, normalized, value)
+DECLARE_GL_FUNCTION_HEAD(void, VertexAttribP3uiv, GLuint index, GLenum type, GLboolean normalized, const GLuint* value) DECLARE_GL_FUNCTION_END_NO_RETURN(void, VertexAttribP3uiv, index, type, normalized, value)
+DECLARE_GL_FUNCTION_HEAD(void, VertexAttribP4ui, GLuint index, GLenum type, GLboolean normalized, GLuint value) DECLARE_GL_FUNCTION_END_NO_RETURN(void, VertexAttribP4ui, index, type, normalized, value)
+DECLARE_GL_FUNCTION_HEAD(void, VertexAttribP4uiv, GLuint index, GLenum type, GLboolean normalized, const GLuint* value) DECLARE_GL_FUNCTION_END_NO_RETURN(void, VertexAttribP4uiv, index, type, normalized, value)
 DECLARE_GL_FUNCTION_STUB_HEAD(void, VertexP2ui, GLenum type, GLuint value) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, VertexP2ui, type, value)
 DECLARE_GL_FUNCTION_STUB_HEAD(void, VertexP2uiv, GLenum type, const GLuint* value) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, VertexP2uiv, type, value)
 DECLARE_GL_FUNCTION_STUB_HEAD(void, VertexP3ui, GLenum type, GLuint value) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, VertexP3ui, type, value)
@@ -981,14 +998,14 @@ DECLARE_GL_FUNCTION_HEAD(void, ShaderStorageBlockBinding, GLuint program, GLuint
 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, 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_STUB_HEAD(void, BindBuffersBase, GLenum target, GLuint first, GLsizei count, const GLuint* buffers) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, BindBuffersBase, target, first, count, buffers)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, BindBuffersRange, GLenum target, GLuint first, GLsizei count, const GLuint* buffers, const GLintptr* offsets, const GLsizeiptr* sizes) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, BindBuffersRange, target, first, count, buffers, offsets, sizes)
+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)
 DECLARE_GL_FUNCTION_HEAD(void, BindSamplers, GLuint first, GLsizei count, const GLuint* samplers) DECLARE_GL_FUNCTION_END_NO_RETURN(void, BindSamplers, first, count, samplers)
 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_STUB_HEAD(void, BindVertexBuffers, GLuint first, GLsizei count, const GLuint* buffers, const GLintptr* offsets, const GLsizei* strides) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, BindVertexBuffers, first, count, buffers, offsets, strides)
+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)
@@ -1013,7 +1030,7 @@ DECLARE_GL_FUNCTION_HEAD(void, CreateFramebuffers, GLsizei n, GLuint* framebuffe
 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, NamedFramebufferTexture, GLuint framebuffer, GLenum attachment, GLuint texture, GLint level) DECLARE_GL_FUNCTION_END_NO_RETURN(void, NamedFramebufferTexture, framebuffer, attachment, texture, level)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, NamedFramebufferTextureLayer, GLuint framebuffer, GLenum attachment, GLuint texture, GLint level, GLint layer) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, NamedFramebufferTextureLayer, framebuffer, attachment, texture, level, layer)
+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)
@@ -1029,52 +1046,52 @@ DECLARE_GL_FUNCTION_STUB_HEAD(void, GetNamedFramebufferParameteriv, GLuint frame
 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_STUB_HEAD(void, NamedRenderbufferStorageMultisample, GLuint renderbuffer, GLsizei samples, GLenum internalformat, GLsizei width, GLsizei height) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, NamedRenderbufferStorageMultisample, renderbuffer, samples, 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_STUB_HEAD(void, TextureStorage1D, GLuint texture, GLsizei levels, GLenum internalformat, GLsizei width) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, TextureStorage1D, texture, levels, internalformat, width)
+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_STUB_HEAD(void, TextureStorage3D, GLuint texture, GLsizei levels, GLenum internalformat, GLsizei width, GLsizei height, GLsizei depth) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, TextureStorage3D, texture, levels, internalformat, width, height, depth)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, TextureStorage2DMultisample, GLuint texture, GLsizei samples, GLenum internalformat, GLsizei width, GLsizei height, GLboolean fixedsamplelocations) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, TextureStorage2DMultisample, texture, samples, internalformat, width, height, fixedsamplelocations)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, TextureStorage3DMultisample, GLuint texture, GLsizei samples, GLenum internalformat, GLsizei width, GLsizei height, GLsizei depth, GLboolean fixedsamplelocations) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, TextureStorage3DMultisample, texture, samples, internalformat, width, height, depth, fixedsamplelocations)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, TextureSubImage1D, GLuint texture, GLint level, GLint xoffset, GLsizei width, GLenum format, GLenum type, const void* pixels) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, TextureSubImage1D, texture, level, xoffset, width, format, type, pixels)
+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)
+DECLARE_GL_FUNCTION_HEAD(void, TextureStorage2DMultisample, GLuint texture, GLsizei samples, GLenum internalformat, GLsizei width, GLsizei height, GLboolean fixedsamplelocations) DECLARE_GL_FUNCTION_END_NO_RETURN(void, TextureStorage2DMultisample, texture, samples, internalformat, width, height, fixedsamplelocations)
+DECLARE_GL_FUNCTION_HEAD(void, TextureStorage3DMultisample, GLuint texture, GLsizei samples, GLenum internalformat, GLsizei width, GLsizei height, GLsizei depth, GLboolean fixedsamplelocations) DECLARE_GL_FUNCTION_END_NO_RETURN(void, TextureStorage3DMultisample, texture, samples, internalformat, width, height, depth, fixedsamplelocations)
+DECLARE_GL_FUNCTION_HEAD(void, TextureSubImage1D, GLuint texture, GLint level, GLint xoffset, GLsizei width, GLenum format, GLenum type, const void* pixels) DECLARE_GL_FUNCTION_END_NO_RETURN(void, TextureSubImage1D, texture, level, xoffset, width, format, type, pixels)
 DECLARE_GL_FUNCTION_HEAD(void, TextureSubImage2D, GLuint texture, GLint level, GLint xoffset, GLint yoffset, GLsizei width, GLsizei height, GLenum format, GLenum type, const void* pixels) DECLARE_GL_FUNCTION_END_NO_RETURN(void, TextureSubImage2D, texture, level, xoffset, yoffset, width, height, format, type, pixels)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, TextureSubImage3D, GLuint texture, GLint level, GLint xoffset, GLint yoffset, GLint zoffset, GLsizei width, GLsizei height, GLsizei depth, GLenum format, GLenum type, const void* pixels) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, TextureSubImage3D, texture, level, xoffset, yoffset, zoffset, width, height, depth, format, type, pixels)
+DECLARE_GL_FUNCTION_HEAD(void, TextureSubImage3D, GLuint texture, GLint level, GLint xoffset, GLint yoffset, GLint zoffset, GLsizei width, GLsizei height, GLsizei depth, GLenum format, GLenum type, const void* pixels) DECLARE_GL_FUNCTION_END_NO_RETURN(void, TextureSubImage3D, texture, level, xoffset, yoffset, zoffset, width, height, depth, format, type, pixels)
 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_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_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, TextureParameterf, GLuint texture, GLenum pname, GLfloat param) DECLARE_GL_FUNCTION_END_NO_RETURN(void, TextureParameterf, texture, pname, param)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, TextureParameterfv, GLuint texture, GLenum pname, const GLfloat* param) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, TextureParameterfv, 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)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, TextureParameterIiv, GLuint texture, GLenum pname, const GLint* params) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, TextureParameterIiv, texture, pname, params)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, TextureParameterIuiv, GLuint texture, GLenum pname, const GLuint* params) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, TextureParameterIuiv, texture, pname, params)
+DECLARE_GL_FUNCTION_HEAD(void, TextureParameterIiv, GLuint texture, GLenum pname, const GLint* params) DECLARE_GL_FUNCTION_END_NO_RETURN(void, TextureParameterIiv, texture, pname, params)
+DECLARE_GL_FUNCTION_HEAD(void, TextureParameterIuiv, GLuint texture, GLenum pname, const GLuint* params) DECLARE_GL_FUNCTION_END_NO_RETURN(void, TextureParameterIuiv, texture, pname, params)
 DECLARE_GL_FUNCTION_HEAD(void, TextureParameteriv, GLuint texture, GLenum pname, const GLint* param) DECLARE_GL_FUNCTION_END_NO_RETURN(void, TextureParameteriv, texture, pname, param)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, GenerateTextureMipmap, GLuint texture) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, GenerateTextureMipmap, texture)
+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_STUB_HEAD(void, GetTextureLevelParameterfv, GLuint texture, GLint level, GLenum pname, GLfloat* params) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, GetTextureLevelParameterfv, texture, level, pname, params)
+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_STUB_HEAD(void, GetTextureParameterfv, GLuint texture, GLenum pname, GLfloat* params) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, GetTextureParameterfv, texture, pname, params)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, GetTextureParameterIiv, GLuint texture, GLenum pname, GLint* params) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, GetTextureParameterIiv, texture, pname, params)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, GetTextureParameterIuiv, GLuint texture, GLenum pname, GLuint* params) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, GetTextureParameterIuiv, texture, 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)
+DECLARE_GL_FUNCTION_HEAD(void, GetTextureParameterIiv, GLuint texture, GLenum pname, GLint* params) DECLARE_GL_FUNCTION_END_NO_RETURN(void, GetTextureParameterIiv, texture, pname, params)
+DECLARE_GL_FUNCTION_HEAD(void, GetTextureParameterIuiv, GLuint texture, GLenum pname, GLuint* params) DECLARE_GL_FUNCTION_END_NO_RETURN(void, GetTextureParameterIuiv, texture, pname, params)
 DECLARE_GL_FUNCTION_HEAD(void, GetTextureParameteriv, GLuint texture, GLenum pname, GLint* params) DECLARE_GL_FUNCTION_END_NO_RETURN(void, GetTextureParameteriv, texture, pname, params)
 DECLARE_GL_FUNCTION_HEAD(void, CreateVertexArrays, GLsizei n, GLuint* arrays) DECLARE_GL_FUNCTION_END_NO_RETURN(void, CreateVertexArrays, n, arrays)
 DECLARE_GL_FUNCTION_HEAD(void, DisableVertexArrayAttrib, GLuint vaobj, GLuint index) DECLARE_GL_FUNCTION_END_NO_RETURN(void, DisableVertexArrayAttrib, vaobj, index)
 DECLARE_GL_FUNCTION_HEAD(void, EnableVertexArrayAttrib, GLuint vaobj, GLuint index) DECLARE_GL_FUNCTION_END_NO_RETURN(void, EnableVertexArrayAttrib, vaobj, index)
 DECLARE_GL_FUNCTION_HEAD(void, VertexArrayElementBuffer, GLuint vaobj, GLuint buffer) DECLARE_GL_FUNCTION_END_NO_RETURN(void, VertexArrayElementBuffer, vaobj, buffer)
 DECLARE_GL_FUNCTION_HEAD(void, VertexArrayVertexBuffer, GLuint vaobj, GLuint bindingindex, GLuint buffer, GLintptr offset, GLsizei stride) DECLARE_GL_FUNCTION_END_NO_RETURN(void, VertexArrayVertexBuffer, vaobj, bindingindex, buffer, offset, stride)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, VertexArrayVertexBuffers, GLuint vaobj, GLuint first, GLsizei count, const GLuint* buffers, const GLintptr* offsets, const GLsizei* strides) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, VertexArrayVertexBuffers, vaobj, first, count, buffers, offsets, strides)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, VertexArrayAttribBinding, GLuint vaobj, GLuint attribindex, GLuint bindingindex) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, VertexArrayAttribBinding, vaobj, attribindex, bindingindex)
+DECLARE_GL_FUNCTION_HEAD(void, VertexArrayVertexBuffers, GLuint vaobj, GLuint first, GLsizei count, const GLuint* buffers, const GLintptr* offsets, const GLsizei* strides) DECLARE_GL_FUNCTION_END_NO_RETURN(void, VertexArrayVertexBuffers, vaobj, first, count, buffers, offsets, strides)
+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_STUB_HEAD(void, VertexArrayBindingDivisor, GLuint vaobj, GLuint bindingindex, GLuint divisor) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, VertexArrayBindingDivisor, vaobj, bindingindex, divisor)
+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)
@@ -1490,9 +1507,9 @@ DECLARE_GL_FUNCTION_STUB_HEAD(void, Vertex3xvOES, const GLfixed* coords) DECLARE
 DECLARE_GL_FUNCTION_STUB_HEAD(void, Vertex4xOES, GLfixed x, GLfixed y, GLfixed z) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, Vertex4xOES, x, y, z)
 DECLARE_GL_FUNCTION_STUB_HEAD(void, Vertex4xvOES, const GLfixed* coords) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, Vertex4xvOES, coords)
 DECLARE_GL_FUNCTION_STUB_HEAD(GLbitfield, QueryMatrixxOES, GLfixed* mantissa, GLint* exponent) DECLARE_GL_FUNCTION_STUB_END(GLbitfield, QueryMatrixxOES, mantissa, exponent)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, ClearDepthfOES, GLclampf depth) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, ClearDepthfOES, depth)
+DECLARE_GL_FUNCTION_HEAD(void, ClearDepthfOES, GLclampf depth) DECLARE_GL_FUNCTION_END_NO_RETURN(void, ClearDepth, static_cast<GLclampd>(depth))
 DECLARE_GL_FUNCTION_STUB_HEAD(void, ClipPlanefOES, GLenum plane, const GLfloat* equation) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, ClipPlanefOES, plane, equation)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, DepthRangefOES, GLclampf n, GLclampf f) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, DepthRangefOES, n, f)
+DECLARE_GL_FUNCTION_HEAD(void, DepthRangefOES, GLclampf n, GLclampf f) DECLARE_GL_FUNCTION_END_NO_RETURN(void, DepthRange, static_cast<GLclampd>(n), static_cast<GLclampd>(f))
 DECLARE_GL_FUNCTION_STUB_HEAD(void, FrustumfOES, GLfloat l, GLfloat r, GLfloat b, GLfloat t, GLfloat n, GLfloat f) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, FrustumfOES, l, r, b, t, n, f)
 DECLARE_GL_FUNCTION_STUB_HEAD(void, GetClipPlanefOES, GLenum plane, GLfloat* equation) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, GetClipPlanefOES, plane, equation)
 DECLARE_GL_FUNCTION_STUB_HEAD(void, OrthofOES, GLfloat l, GLfloat r, GLfloat b, GLfloat t, GLfloat n, GLfloat f) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, OrthofOES, l, r, b, t, n, f)
@@ -1760,25 +1777,25 @@ DECLARE_GL_FUNCTION_STUB_HEAD(void, MatrixPopEXT, GLenum mode) DECLARE_GL_FUNCTI
 DECLARE_GL_FUNCTION_STUB_HEAD(void, MatrixPushEXT, GLenum mode) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, MatrixPushEXT, mode)
 DECLARE_GL_FUNCTION_STUB_HEAD(void, ClientAttribDefaultEXT, GLbitfield mask) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, ClientAttribDefaultEXT, mask)
 DECLARE_GL_FUNCTION_STUB_HEAD(void, PushClientAttribDefaultEXT, GLbitfield mask) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, PushClientAttribDefaultEXT, mask)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, TextureParameterfEXT, GLuint texture, GLenum target, GLenum pname, GLfloat param) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, TextureParameterfEXT, texture, target, pname, param)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, TextureParameterfvEXT, GLuint texture, GLenum target, GLenum pname, const GLfloat* params) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, TextureParameterfvEXT, texture, target, pname, params)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, TextureParameteriEXT, GLuint texture, GLenum target, GLenum pname, GLint param) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, TextureParameteriEXT, texture, target, pname, param)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, TextureParameterivEXT, GLuint texture, GLenum target, GLenum pname, const GLint* params) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, TextureParameterivEXT, texture, target, pname, params)
+DECLARE_GL_FUNCTION_HEAD(void, TextureParameterfEXT, GLuint texture, GLenum target, GLenum pname, GLfloat param) DECLARE_GL_FUNCTION_END_NO_RETURN(void, TextureParameterf, texture, pname, param)
+DECLARE_GL_FUNCTION_HEAD(void, TextureParameterfvEXT, GLuint texture, GLenum target, GLenum pname, const GLfloat* params) DECLARE_GL_FUNCTION_END_NO_RETURN(void, TextureParameterfv, texture, pname, params)
+DECLARE_GL_FUNCTION_HEAD(void, TextureParameteriEXT, GLuint texture, GLenum target, GLenum pname, GLint param) DECLARE_GL_FUNCTION_END_NO_RETURN(void, TextureParameteri, texture, pname, param)
+DECLARE_GL_FUNCTION_HEAD(void, TextureParameterivEXT, GLuint texture, GLenum target, GLenum pname, const GLint* params) DECLARE_GL_FUNCTION_END_NO_RETURN(void, TextureParameteriv, texture, pname, params)
 DECLARE_GL_FUNCTION_STUB_HEAD(void, TextureImage1DEXT, GLuint texture, GLenum target, GLint level, GLint internalformat, GLsizei width, GLint border, GLenum format, GLenum type, const void* pixels) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, TextureImage1DEXT, texture, target, level, internalformat, width, border, format, type, pixels)
 DECLARE_GL_FUNCTION_STUB_HEAD(void, TextureImage2DEXT, GLuint texture, GLenum target, GLint level, GLint internalformat, GLsizei width, GLsizei height, GLint border, GLenum format, GLenum type, const void* pixels) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, TextureImage2DEXT, texture, target, level, internalformat, width, height, border, format, type, pixels)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, TextureSubImage1DEXT, GLuint texture, GLenum target, GLint level, GLint xoffset, GLsizei width, GLenum format, GLenum type, const void* pixels) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, TextureSubImage1DEXT, texture, target, level, xoffset, width, format, type, pixels)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, TextureSubImage2DEXT, GLuint texture, GLenum target, GLint level, GLint xoffset, GLint yoffset, GLsizei width, GLsizei height, GLenum format, GLenum type, const void* pixels) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, TextureSubImage2DEXT, texture, target, level, xoffset, yoffset, width, height, format, type, pixels)
+DECLARE_GL_FUNCTION_HEAD(void, TextureSubImage1DEXT, GLuint texture, GLenum target, GLint level, GLint xoffset, GLsizei width, GLenum format, GLenum type, const void* pixels) DECLARE_GL_FUNCTION_END_NO_RETURN(void, TextureSubImage1D, texture, level, xoffset, width, format, type, pixels)
+DECLARE_GL_FUNCTION_HEAD(void, TextureSubImage2DEXT, GLuint texture, GLenum target, GLint level, GLint xoffset, GLint yoffset, GLsizei width, GLsizei height, GLenum format, GLenum type, const void* pixels) DECLARE_GL_FUNCTION_END_NO_RETURN(void, TextureSubImage2D, texture, level, xoffset, yoffset, width, height, format, type, pixels)
 DECLARE_GL_FUNCTION_STUB_HEAD(void, CopyTextureImage1DEXT, GLuint texture, GLenum target, GLint level, GLenum internalformat, GLint x, GLint y, GLsizei width, GLint border) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, CopyTextureImage1DEXT, texture, target, level, internalformat, x, y, width, border)
 DECLARE_GL_FUNCTION_STUB_HEAD(void, CopyTextureImage2DEXT, GLuint texture, GLenum target, GLint level, GLenum internalformat, GLint x, GLint y, GLsizei width, GLsizei height, GLint border) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, CopyTextureImage2DEXT, texture, target, level, internalformat, x, y, width, height, border)
 DECLARE_GL_FUNCTION_STUB_HEAD(void, CopyTextureSubImage1DEXT, GLuint texture, GLenum target, GLint level, GLint xoffset, GLint x, GLint y, GLsizei width) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, CopyTextureSubImage1DEXT, texture, target, level, xoffset, x, y, width)
 DECLARE_GL_FUNCTION_STUB_HEAD(void, CopyTextureSubImage2DEXT, GLuint texture, GLenum target, GLint level, GLint xoffset, GLint yoffset, GLint x, GLint y, GLsizei width, GLsizei height) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, CopyTextureSubImage2DEXT, texture, target, level, xoffset, yoffset, x, y, width, height)
 DECLARE_GL_FUNCTION_STUB_HEAD(void, GetTextureImageEXT, GLuint texture, GLenum target, GLint level, GLenum format, GLenum type, void* pixels) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, GetTextureImageEXT, texture, target, level, format, type, pixels)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, GetTextureParameterfvEXT, GLuint texture, GLenum target, GLenum pname, GLfloat* params) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, GetTextureParameterfvEXT, texture, target, pname, params)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, GetTextureParameterivEXT, GLuint texture, GLenum target, GLenum pname, GLint* params) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, GetTextureParameterivEXT, texture, target, pname, params)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, GetTextureLevelParameterfvEXT, GLuint texture, GLenum target, GLint level, GLenum pname, GLfloat* params) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, GetTextureLevelParameterfvEXT, texture, target, level, pname, params)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, GetTextureLevelParameterivEXT, GLuint texture, GLenum target, GLint level, GLenum pname, GLint* params) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, GetTextureLevelParameterivEXT, texture, target, level, pname, params)
+DECLARE_GL_FUNCTION_HEAD(void, GetTextureParameterfvEXT, GLuint texture, GLenum target, GLenum pname, GLfloat* params) DECLARE_GL_FUNCTION_END_NO_RETURN(void, GetTextureParameterfv, texture, pname, params)
+DECLARE_GL_FUNCTION_HEAD(void, GetTextureParameterivEXT, GLuint texture, GLenum target, GLenum pname, GLint* params) DECLARE_GL_FUNCTION_END_NO_RETURN(void, GetTextureParameteriv, texture, pname, params)
+DECLARE_GL_FUNCTION_HEAD(void, GetTextureLevelParameterfvEXT, GLuint texture, GLenum target, GLint level, GLenum pname, GLfloat* params) DECLARE_GL_FUNCTION_END_NO_RETURN(void, GetTextureLevelParameterfv, texture, level, pname, params)
+DECLARE_GL_FUNCTION_HEAD(void, GetTextureLevelParameterivEXT, GLuint texture, GLenum target, GLint level, GLenum pname, GLint* params) DECLARE_GL_FUNCTION_END_NO_RETURN(void, GetTextureLevelParameteriv, texture, level, pname, params)
 DECLARE_GL_FUNCTION_STUB_HEAD(void, TextureImage3DEXT, GLuint texture, GLenum target, GLint level, GLint internalformat, GLsizei width, GLsizei height, GLsizei depth, GLint border, GLenum format, GLenum type, const void* pixels) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, TextureImage3DEXT, texture, target, level, internalformat, width, height, depth, border, format, type, pixels)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, TextureSubImage3DEXT, GLuint texture, GLenum target, GLint level, GLint xoffset, GLint yoffset, GLint zoffset, GLsizei width, GLsizei height, GLsizei depth, GLenum format, GLenum type, const void* pixels) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, TextureSubImage3DEXT, texture, target, level, xoffset, yoffset, zoffset, width, height, depth, format, type, pixels)
+DECLARE_GL_FUNCTION_HEAD(void, TextureSubImage3DEXT, GLuint texture, GLenum target, GLint level, GLint xoffset, GLint yoffset, GLint zoffset, GLsizei width, GLsizei height, GLsizei depth, GLenum format, GLenum type, const void* pixels) DECLARE_GL_FUNCTION_END_NO_RETURN(void, TextureSubImage3D, texture, level, xoffset, yoffset, zoffset, width, height, depth, format, type, pixels)
 DECLARE_GL_FUNCTION_STUB_HEAD(void, CopyTextureSubImage3DEXT, GLuint texture, GLenum target, GLint level, GLint xoffset, GLint yoffset, GLint zoffset, GLint x, GLint y, GLsizei width, GLsizei height) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, CopyTextureSubImage3DEXT, texture, target, level, xoffset, yoffset, zoffset, x, y, width, height)
 DECLARE_GL_FUNCTION_STUB_HEAD(void, BindMultiTextureEXT, GLenum texunit, GLenum target, GLuint texture) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, BindMultiTextureEXT, texunit, target, texture)
 DECLARE_GL_FUNCTION_STUB_HEAD(void, MultiTexCoordPointerEXT, GLenum texunit, GLint size, GLenum type, GLsizei stride, const void* pointer) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, MultiTexCoordPointerEXT, texunit, size, type, stride, pointer)
@@ -1853,10 +1870,10 @@ DECLARE_GL_FUNCTION_HEAD(void, GetNamedBufferPointervEXT, GLuint buffer, GLenum
 DECLARE_GL_FUNCTION_STUB_HEAD(void, GetNamedBufferSubDataEXT, GLuint buffer, GLintptr offset, GLsizeiptr size, void* data) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, GetNamedBufferSubDataEXT, buffer, offset, size, data)
 DECLARE_GL_FUNCTION_STUB_HEAD(void, TextureBufferEXT, GLuint texture, GLenum target, GLenum internalformat, GLuint buffer) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, TextureBufferEXT, texture, target, internalformat, buffer)
 DECLARE_GL_FUNCTION_STUB_HEAD(void, MultiTexBufferEXT, GLenum texunit, GLenum target, GLenum internalformat, GLuint buffer) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, MultiTexBufferEXT, texunit, target, internalformat, buffer)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, TextureParameterIivEXT, GLuint texture, GLenum target, GLenum pname, const GLint* params) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, TextureParameterIivEXT, texture, target, pname, params)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, TextureParameterIuivEXT, GLuint texture, GLenum target, GLenum pname, const GLuint* params) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, TextureParameterIuivEXT, texture, target, pname, params)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, GetTextureParameterIivEXT, GLuint texture, GLenum target, GLenum pname, GLint* params) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, GetTextureParameterIivEXT, texture, target, pname, params)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, GetTextureParameterIuivEXT, GLuint texture, GLenum target, GLenum pname, GLuint* params) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, GetTextureParameterIuivEXT, texture, target, pname, params)
+DECLARE_GL_FUNCTION_HEAD(void, TextureParameterIivEXT, GLuint texture, GLenum target, GLenum pname, const GLint* params) DECLARE_GL_FUNCTION_END_NO_RETURN(void, TextureParameterIiv, texture, pname, params)
+DECLARE_GL_FUNCTION_HEAD(void, TextureParameterIuivEXT, GLuint texture, GLenum target, GLenum pname, const GLuint* params) DECLARE_GL_FUNCTION_END_NO_RETURN(void, TextureParameterIuiv, texture, pname, params)
+DECLARE_GL_FUNCTION_HEAD(void, GetTextureParameterIivEXT, GLuint texture, GLenum target, GLenum pname, GLint* params) DECLARE_GL_FUNCTION_END_NO_RETURN(void, GetTextureParameterIiv, texture, pname, params)
+DECLARE_GL_FUNCTION_HEAD(void, GetTextureParameterIuivEXT, GLuint texture, GLenum target, GLenum pname, GLuint* params) DECLARE_GL_FUNCTION_END_NO_RETURN(void, GetTextureParameterIuiv, texture, pname, params)
 DECLARE_GL_FUNCTION_STUB_HEAD(void, MultiTexParameterIivEXT, GLenum texunit, GLenum target, GLenum pname, const GLint* params) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, MultiTexParameterIivEXT, texunit, target, pname, params)
 DECLARE_GL_FUNCTION_STUB_HEAD(void, MultiTexParameterIuivEXT, GLenum texunit, GLenum target, GLenum pname, const GLuint* params) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, MultiTexParameterIuivEXT, texunit, target, pname, params)
 DECLARE_GL_FUNCTION_STUB_HEAD(void, GetMultiTexParameterIivEXT, GLenum texunit, GLenum target, GLenum pname, GLint* params) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, GetMultiTexParameterIivEXT, texunit, target, pname, params)
@@ -1886,22 +1903,22 @@ DECLARE_GL_FUNCTION_STUB_HEAD(void, GetNamedProgramivEXT, GLuint program, GLenum
 DECLARE_GL_FUNCTION_STUB_HEAD(void, GetNamedProgramStringEXT, GLuint program, GLenum target, GLenum pname, void* string) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, GetNamedProgramStringEXT, program, target, pname, string)
 DECLARE_GL_FUNCTION_HEAD(void, NamedRenderbufferStorageEXT, 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, GetNamedRenderbufferParameterivEXT, GLuint renderbuffer, GLenum pname, GLint* params) DECLARE_GL_FUNCTION_END_NO_RETURN(void, GetNamedRenderbufferParameteriv, renderbuffer, pname, params)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, NamedRenderbufferStorageMultisampleEXT, GLuint renderbuffer, GLsizei samples, GLenum internalformat, GLsizei width, GLsizei height) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, NamedRenderbufferStorageMultisampleEXT, renderbuffer, samples, internalformat, width, height)
+DECLARE_GL_FUNCTION_HEAD(void, NamedRenderbufferStorageMultisampleEXT, 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_STUB_HEAD(void, NamedRenderbufferStorageMultisampleCoverageEXT, GLuint renderbuffer, GLsizei coverageSamples, GLsizei colorSamples, GLenum internalformat, GLsizei width, GLsizei height) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, NamedRenderbufferStorageMultisampleCoverageEXT, renderbuffer, coverageSamples, colorSamples, internalformat, width, height)
-DECLARE_GL_FUNCTION_STUB_HEAD(GLenum, CheckNamedFramebufferStatusEXT, GLuint framebuffer, GLenum target) DECLARE_GL_FUNCTION_STUB_END(GLenum, CheckNamedFramebufferStatusEXT, framebuffer, target)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, NamedFramebufferTexture1DEXT, GLuint framebuffer, GLenum attachment, GLenum textarget, GLuint texture, GLint level) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, NamedFramebufferTexture1DEXT, framebuffer, attachment, textarget, texture, level)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, NamedFramebufferTexture2DEXT, GLuint framebuffer, GLenum attachment, GLenum textarget, GLuint texture, GLint level) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, NamedFramebufferTexture2DEXT, framebuffer, attachment, textarget, texture, level)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, NamedFramebufferTexture3DEXT, GLuint framebuffer, GLenum attachment, GLenum textarget, GLuint texture, GLint level, GLint zoffset) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, NamedFramebufferTexture3DEXT, framebuffer, attachment, textarget, texture, level, zoffset)
+DECLARE_GL_FUNCTION_HEAD(GLenum, CheckNamedFramebufferStatusEXT, GLuint framebuffer, GLenum target) DECLARE_GL_FUNCTION_END(GLenum, CheckNamedFramebufferStatus, framebuffer, target)
+DECLARE_GL_FUNCTION_HEAD(void, NamedFramebufferTexture1DEXT, GLuint framebuffer, GLenum attachment, GLenum textarget, GLuint texture, GLint level) DECLARE_GL_FUNCTION_END_NO_RETURN(void, NamedFramebufferTexture1D, framebuffer, attachment, textarget, texture, level)
+DECLARE_GL_FUNCTION_HEAD(void, NamedFramebufferTexture2DEXT, GLuint framebuffer, GLenum attachment, GLenum textarget, GLuint texture, GLint level) DECLARE_GL_FUNCTION_END_NO_RETURN(void, NamedFramebufferTexture2D, framebuffer, attachment, textarget, texture, level)
+DECLARE_GL_FUNCTION_HEAD(void, NamedFramebufferTexture3DEXT, GLuint framebuffer, GLenum attachment, GLenum textarget, GLuint texture, GLint level, GLint zoffset) DECLARE_GL_FUNCTION_END_NO_RETURN(void, NamedFramebufferTexture3D, framebuffer, attachment, textarget, texture, level, zoffset)
 DECLARE_GL_FUNCTION_HEAD(void, NamedFramebufferRenderbufferEXT, 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, GetNamedFramebufferAttachmentParameterivEXT, GLuint framebuffer, GLenum attachment, GLenum pname, GLint* params) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, GetNamedFramebufferAttachmentParameterivEXT, framebuffer, attachment, pname, params)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, GenerateTextureMipmapEXT, GLuint texture, GLenum target) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, GenerateTextureMipmapEXT, texture, target)
+DECLARE_GL_FUNCTION_HEAD(void, GenerateTextureMipmapEXT, GLuint texture, GLenum target) DECLARE_GL_FUNCTION_END_NO_RETURN(void, GenerateTextureMipmap, texture)
 DECLARE_GL_FUNCTION_STUB_HEAD(void, GenerateMultiTexMipmapEXT, GLenum texunit, GLenum target) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, GenerateMultiTexMipmapEXT, texunit, target)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, FramebufferDrawBufferEXT, GLuint framebuffer, GLenum mode) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, FramebufferDrawBufferEXT, framebuffer, mode)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, FramebufferDrawBuffersEXT, GLuint framebuffer, GLsizei n, const GLenum* bufs) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, FramebufferDrawBuffersEXT, framebuffer, n, bufs)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, FramebufferReadBufferEXT, GLuint framebuffer, GLenum mode) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, FramebufferReadBufferEXT, framebuffer, mode)
+DECLARE_GL_FUNCTION_HEAD(void, FramebufferDrawBufferEXT, GLuint framebuffer, GLenum mode) DECLARE_GL_FUNCTION_END_NO_RETURN(void, NamedFramebufferDrawBuffer, framebuffer, mode)
+DECLARE_GL_FUNCTION_HEAD(void, FramebufferDrawBuffersEXT, GLuint framebuffer, GLsizei n, const GLenum* bufs) DECLARE_GL_FUNCTION_END_NO_RETURN(void, NamedFramebufferDrawBuffers, framebuffer, n, bufs)
+DECLARE_GL_FUNCTION_HEAD(void, FramebufferReadBufferEXT, GLuint framebuffer, GLenum mode) DECLARE_GL_FUNCTION_END_NO_RETURN(void, NamedFramebufferReadBuffer, framebuffer, mode)
 DECLARE_GL_FUNCTION_STUB_HEAD(void, NamedCopyBufferSubDataEXT, GLuint readBuffer, GLuint writeBuffer, GLintptr readOffset, GLintptr writeOffset, GLsizeiptr size) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, NamedCopyBufferSubDataEXT, readBuffer, writeBuffer, readOffset, writeOffset, size)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, NamedFramebufferTextureEXT, GLuint framebuffer, GLenum attachment, GLuint texture, GLint level) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, NamedFramebufferTextureEXT, framebuffer, attachment, texture, level)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, NamedFramebufferTextureLayerEXT, GLuint framebuffer, GLenum attachment, GLuint texture, GLint level, GLint layer) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, NamedFramebufferTextureLayerEXT, framebuffer, attachment, texture, level, layer)
+DECLARE_GL_FUNCTION_HEAD(void, NamedFramebufferTextureEXT, 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, NamedFramebufferTextureLayerEXT, 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_STUB_HEAD(void, NamedFramebufferTextureFaceEXT, GLuint framebuffer, GLenum attachment, GLuint texture, GLint level, GLenum face) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, NamedFramebufferTextureFaceEXT, framebuffer, attachment, texture, level, face)
 DECLARE_GL_FUNCTION_STUB_HEAD(void, TextureRenderbufferEXT, GLuint texture, GLenum target, GLuint renderbuffer) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, TextureRenderbufferEXT, texture, target, renderbuffer)
 DECLARE_GL_FUNCTION_STUB_HEAD(void, MultiTexRenderbufferEXT, GLenum texunit, GLenum target, GLuint renderbuffer) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, MultiTexRenderbufferEXT, texunit, target, renderbuffer)
@@ -1948,11 +1965,11 @@ DECLARE_GL_FUNCTION_STUB_HEAD(void, ProgramUniformMatrix3x4dvEXT, GLuint program
 DECLARE_GL_FUNCTION_STUB_HEAD(void, ProgramUniformMatrix4x2dvEXT, GLuint program, GLint location, GLsizei count, GLboolean transpose, const GLdouble* value) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, ProgramUniformMatrix4x2dvEXT, program, location, count, transpose, value)
 DECLARE_GL_FUNCTION_STUB_HEAD(void, ProgramUniformMatrix4x3dvEXT, GLuint program, GLint location, GLsizei count, GLboolean transpose, const GLdouble* value) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, ProgramUniformMatrix4x3dvEXT, program, location, count, transpose, value)
 DECLARE_GL_FUNCTION_STUB_HEAD(void, TextureBufferRangeEXT, GLuint texture, GLenum target, GLenum internalformat, GLuint buffer, GLintptr offset, GLsizeiptr size) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, TextureBufferRangeEXT, texture, target, internalformat, buffer, offset, size)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, TextureStorage1DEXT, GLuint texture, GLenum target, GLsizei levels, GLenum internalformat, GLsizei width) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, TextureStorage1DEXT, texture, target, levels, internalformat, width)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, TextureStorage2DEXT, GLuint texture, GLenum target, GLsizei levels, GLenum internalformat, GLsizei width, GLsizei height) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, TextureStorage2DEXT, texture, target, levels, internalformat, width, height)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, TextureStorage3DEXT, GLuint texture, GLenum target, GLsizei levels, GLenum internalformat, GLsizei width, GLsizei height, GLsizei depth) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, TextureStorage3DEXT, texture, target, levels, internalformat, width, height, depth)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, TextureStorage2DMultisampleEXT, GLuint texture, GLenum target, GLsizei samples, GLenum internalformat, GLsizei width, GLsizei height, GLboolean fixedsamplelocations) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, TextureStorage2DMultisampleEXT, texture, target, samples, internalformat, width, height, fixedsamplelocations)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, TextureStorage3DMultisampleEXT, GLuint texture, GLenum target, GLsizei samples, GLenum internalformat, GLsizei width, GLsizei height, GLsizei depth, GLboolean fixedsamplelocations) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, TextureStorage3DMultisampleEXT, texture, target, samples, internalformat, width, height, depth, fixedsamplelocations)
+DECLARE_GL_FUNCTION_HEAD(void, TextureStorage1DEXT, GLuint texture, GLenum target, GLsizei levels, GLenum internalformat, GLsizei width) DECLARE_GL_FUNCTION_END_NO_RETURN(void, TextureStorage1D, texture, levels, internalformat, width)
+DECLARE_GL_FUNCTION_HEAD(void, TextureStorage2DEXT, GLuint texture, GLenum target, 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, TextureStorage3DEXT, GLuint texture, GLenum target, GLsizei levels, GLenum internalformat, GLsizei width, GLsizei height, GLsizei depth) DECLARE_GL_FUNCTION_END_NO_RETURN(void, TextureStorage3D, texture, levels, internalformat, width, height, depth)
+DECLARE_GL_FUNCTION_HEAD(void, TextureStorage2DMultisampleEXT, GLuint texture, GLenum target, GLsizei samples, GLenum internalformat, GLsizei width, GLsizei height, GLboolean fixedsamplelocations) DECLARE_GL_FUNCTION_END_NO_RETURN(void, TextureStorage2DMultisample, texture, samples, internalformat, width, height, fixedsamplelocations)
+DECLARE_GL_FUNCTION_HEAD(void, TextureStorage3DMultisampleEXT, GLuint texture, GLenum target, GLsizei samples, GLenum internalformat, GLsizei width, GLsizei height, GLsizei depth, GLboolean fixedsamplelocations) DECLARE_GL_FUNCTION_END_NO_RETURN(void, TextureStorage3DMultisample, texture, samples, internalformat, width, height, depth, fixedsamplelocations)
 DECLARE_GL_FUNCTION_STUB_HEAD(void, VertexArrayBindVertexBufferEXT, GLuint vaobj, GLuint bindingindex, GLuint buffer, GLintptr offset, GLsizei stride) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, VertexArrayBindVertexBufferEXT, vaobj, bindingindex, buffer, offset, stride)
 DECLARE_GL_FUNCTION_STUB_HEAD(void, VertexArrayVertexAttribFormatEXT, GLuint vaobj, GLuint attribindex, GLint size, GLenum type, GLboolean normalized, GLuint relativeoffset) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, VertexArrayVertexAttribFormatEXT, vaobj, attribindex, size, type, normalized, relativeoffset)
 DECLARE_GL_FUNCTION_STUB_HEAD(void, VertexArrayVertexAttribIFormatEXT, GLuint vaobj, GLuint attribindex, GLint size, GLenum type, GLuint relativeoffset) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, VertexArrayVertexAttribIFormatEXT, vaobj, attribindex, size, type, relativeoffset)
@@ -2086,9 +2103,9 @@ DECLARE_GL_FUNCTION_STUB_HEAD(void, ClearColorIuiEXT, GLuint red, GLuint green,
 DECLARE_GL_FUNCTION_STUB_HEAD(GLboolean, AreTexturesResidentEXT, GLsizei n, const GLuint* textures, GLboolean* residences) DECLARE_GL_FUNCTION_STUB_END(GLboolean, AreTexturesResidentEXT, n, textures, residences)
 DECLARE_GL_FUNCTION_STUB_HEAD(void, PrioritizeTexturesEXT, GLsizei n, const GLuint* textures, const GLclampf* priorities) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, PrioritizeTexturesEXT, n, textures, priorities)
 DECLARE_GL_FUNCTION_STUB_HEAD(void, TextureNormalEXT, GLenum mode) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, TextureNormalEXT, mode)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, TexStorage1DEXT, GLenum target, GLsizei levels, GLenum internalformat, GLsizei width) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, TexStorage1DEXT, target, levels, internalformat, width)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, GetQueryObjecti64vEXT, GLuint id, GLenum pname, GLint64* params) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, GetQueryObjecti64vEXT, id, pname, params)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, GetQueryObjectui64vEXT, GLuint id, GLenum pname, GLuint64* params) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, GetQueryObjectui64vEXT, id, pname, params)
+DECLARE_GL_FUNCTION_HEAD(void, TexStorage1DEXT, GLenum target, GLsizei levels, GLenum internalformat, GLsizei width) DECLARE_GL_FUNCTION_END_NO_RETURN(void, TexStorage1D, target, levels, internalformat, width)
+DECLARE_GL_FUNCTION_HEAD(void, GetQueryObjecti64vEXT, GLuint id, GLenum pname, GLint64* params) DECLARE_GL_FUNCTION_END_NO_RETURN(void, GetQueryObjecti64v, id, pname, params)
+DECLARE_GL_FUNCTION_HEAD(void, GetQueryObjectui64vEXT, GLuint id, GLenum pname, GLuint64* params) DECLARE_GL_FUNCTION_END_NO_RETURN(void, GetQueryObjectui64v, id, pname, params)
 DECLARE_GL_FUNCTION_STUB_HEAD(void, BindBufferOffsetEXT, GLenum target, GLuint index, GLuint buffer, GLintptr offset) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, BindBufferOffsetEXT, target, index, buffer, offset)
 DECLARE_GL_FUNCTION_STUB_HEAD(void, ArrayElementEXT, GLint i) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, ArrayElementEXT, i)
 DECLARE_GL_FUNCTION_STUB_HEAD(void, ColorPointerEXT, GLint size, GLenum type, GLsizei stride, GLsizei count, const void* pointer) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, ColorPointerEXT, size, type, stride, count, pointer)
@@ -2297,7 +2314,7 @@ DECLARE_GL_FUNCTION_STUB_HEAD(void, GetMapParameterfvNV, GLenum target, GLenum p
 DECLARE_GL_FUNCTION_STUB_HEAD(void, GetMapAttribParameterivNV, GLenum target, GLuint index, GLenum pname, GLint* params) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, GetMapAttribParameterivNV, target, index, pname, params)
 DECLARE_GL_FUNCTION_STUB_HEAD(void, GetMapAttribParameterfvNV, GLenum target, GLuint index, GLenum pname, GLfloat* params) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, GetMapAttribParameterfvNV, target, index, pname, params)
 DECLARE_GL_FUNCTION_STUB_HEAD(void, EvalMapsNV, GLenum target, GLenum mode) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, EvalMapsNV, target, mode)
-DECLARE_GL_FUNCTION_STUB_HEAD(void, GetMultisamplefvNV, GLenum pname, GLuint index, GLfloat* val) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, GetMultisamplefvNV, pname, index, val)
+DECLARE_GL_FUNCTION_HEAD(void, GetMultisamplefvNV, GLenum pname, GLuint index, GLfloat* val) DECLARE_GL_FUNCTION_END_NO_RETURN(void, GetMultisamplefv, pname, index, val)
 DECLARE_GL_FUNCTION_STUB_HEAD(void, SampleMaskIndexedNV, GLuint index, GLbitfield mask) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, SampleMaskIndexedNV, index, mask)
 DECLARE_GL_FUNCTION_STUB_HEAD(void, TexRenderbufferNV, GLenum target, GLuint renderbuffer) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, TexRenderbufferNV, target, renderbuffer)
 DECLARE_GL_FUNCTION_STUB_HEAD(void, DeleteFencesNV, GLsizei n, const GLuint* fences) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, DeleteFencesNV, n, fences)

MobileGL/MG_Impl/GLImpl/Framebuffer/GL_Framebuffer.h

@@ -26,6 +26,8 @@ namespace MobileGL::MG_Impl::GLImpl {
     void GenRenderbuffers(GLsizei n, GLuint* renderbuffers);
     void CreateRenderbuffers(GLsizei n, GLuint* renderbuffers);
     void NamedRenderbufferStorage(GLuint renderbuffer, GLenum internalformat, GLsizei width, GLsizei height);
+    void NamedRenderbufferStorageMultisample(GLuint renderbuffer, GLsizei samples, GLenum internalformat,
+                                             GLsizei width, GLsizei height);
     void GetNamedRenderbufferParameteriv(GLuint renderbuffer, GLenum pname, GLint* params);
     void FramebufferRenderbuffer(GLenum target, GLenum attachment, GLenum renderbuffertarget, GLuint renderbuffer);
     void NamedFramebufferRenderbuffer(GLuint framebuffer, GLenum attachment, GLenum renderbuffertarget,
@@ -44,6 +46,11 @@ namespace MobileGL::MG_Impl::GLImpl {
     void FramebufferTexture1D(GLenum target, GLenum attachment, GLenum textarget, GLuint texture, GLint level);
     void FramebufferTexture(GLenum target, GLenum attachment, GLuint texture, GLint level);
     void NamedFramebufferTexture(GLuint framebuffer, GLenum attachment, GLuint texture, GLint level);
+    void NamedFramebufferTexture1D(GLuint framebuffer, GLenum attachment, GLenum textarget, GLuint texture, GLint level);
+    void NamedFramebufferTexture2D(GLuint framebuffer, GLenum attachment, GLenum textarget, GLuint texture, GLint level);
+    void NamedFramebufferTexture3D(GLuint framebuffer, GLenum attachment, GLenum textarget, GLuint texture, GLint level,
+                                   GLint zoffset);
+    void NamedFramebufferTextureLayer(GLuint framebuffer, GLenum attachment, GLuint texture, GLint level, GLint layer);
     void NamedFramebufferDrawBuffer(GLuint framebuffer, GLenum buf);
     void NamedFramebufferDrawBuffers(GLuint framebuffer, GLsizei n, const GLenum* bufs);
     void NamedFramebufferReadBuffer(GLuint framebuffer, GLenum src);

MobileGL/MG_Impl/GLImpl/Framebuffer/Validators.cpp

@@ -76,7 +76,13 @@ 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",

MobileGL/MG_Impl/GLImpl/Getter/GL_Getter.h

@@ -13,8 +13,11 @@ namespace MobileGL::MG_Impl::GLImpl {
     /* @INSERTION_POINT:FUNCTION_DECLARATION@ */
     const GLubyte* GetString(GLenum name);
     const GLubyte* GetStringi(GLenum name, GLuint index);
+    void GetBooleanv(GLenum pname, GLboolean* params);
+    void GetFloatv(GLenum pname, GLfloat* params);
+    void GetDoublev(GLenum pname, GLdouble* params);
     void GetIntegerv(GLenum pname, GLint* params);
-    void GetInteger64v(GLenum pname, GLint64* data);
+    void GetInteger64v(GLenum pname, GLint64* params);
     void GetIntegeri_v(GLenum target, GLuint index, GLint* data);
     void GetInteger64i_v(GLenum target, GLuint index, GLint64* data);
     GLenum GetError();

MobileGL/MG_Impl/GLImpl/Program/GL_Program.h

@@ -22,6 +22,12 @@ namespace MobileGL::MG_Impl::GLImpl {
                          GLchar* name);
     void GetActiveUniform(GLuint program, GLuint index, GLsizei bufSize, GLsizei* length, GLint* size, GLenum* type,
                           GLchar* name);
+    void GetActiveUniformName(GLuint program, GLuint uniformIndex, GLsizei bufSize, GLsizei* length,
+                              GLchar* uniformName);
+    void GetUniformIndices(GLuint program, GLsizei uniformCount, const GLchar* const* uniformNames,
+                           GLuint* uniformIndices);
+    void GetActiveUniformsiv(GLuint program, GLsizei uniformCount, const GLuint* uniformIndices, GLenum pname,
+                             GLint* params);
     void GetAttachedShaders(GLuint program, GLsizei maxCount, GLsizei* count, GLuint* shaders);
     GLint GetAttribLocation(GLuint program, const GLchar* name);
     void GetProgramiv(GLuint program, GLenum pname, GLint* params);
@@ -32,6 +38,7 @@ namespace MobileGL::MG_Impl::GLImpl {
     GLint GetUniformLocation(GLuint program, const GLchar* name);
     void GetUniformfv(GLuint program, GLint location, GLfloat* params);
     void GetUniformiv(GLuint program, GLint location, GLint* params);
+    void GetUniformuiv(GLuint program, GLint location, GLuint* params);
     GLboolean IsProgram(GLuint program);
     GLboolean IsShader(GLuint shader);
     void LinkProgram(GLuint program);
@@ -46,6 +53,9 @@ namespace MobileGL::MG_Impl::GLImpl {
     void Uniform3i(GLint location, GLint v0, GLint v1, GLint v2);
     void Uniform4i(GLint location, GLint v0, GLint v1, GLint v2, GLint v3);
     void Uniform1ui(GLint location, GLuint v0);
+    void Uniform2ui(GLint location, GLuint v0, GLuint v1);
+    void Uniform3ui(GLint location, GLuint v0, GLuint v1, GLuint v2);
+    void Uniform4ui(GLint location, GLuint v0, GLuint v1, GLuint v2, GLuint v3);
     void Uniform1fv(GLint location, GLsizei count, const GLfloat* value);
     void Uniform2fv(GLint location, GLsizei count, const GLfloat* value);
     void Uniform3fv(GLint location, GLsizei count, const GLfloat* value);
@@ -55,6 +65,9 @@ namespace MobileGL::MG_Impl::GLImpl {
     void Uniform3iv(GLint location, GLsizei count, const GLint* value);
     void Uniform4iv(GLint location, GLsizei count, const GLint* value);
     void Uniform1uiv(GLint location, GLsizei count, const GLuint* value);
+    void Uniform2uiv(GLint location, GLsizei count, const GLuint* value);
+    void Uniform3uiv(GLint location, GLsizei count, const GLuint* value);
+    void Uniform4uiv(GLint location, GLsizei count, const GLuint* value);
     void UniformMatrix2fv(GLint location, GLsizei count, GLboolean transpose, const GLfloat* value);
     void UniformMatrix3fv(GLint location, GLsizei count, GLboolean transpose, const GLfloat* value);
     void UniformMatrix4fv(GLint location, GLsizei count, GLboolean transpose, const GLfloat* value);
@@ -88,13 +101,33 @@ namespace MobileGL::MG_Impl::GLImpl {
                                  const GLfloat* value);
     void ProgramUniformMatrix4fv(GLuint program, GLint location, GLsizei count, GLboolean transpose,
                                  const GLfloat* value);
+    void UniformMatrix2x3fv(GLint location, GLsizei count, GLboolean transpose, const GLfloat* value);
+    void UniformMatrix3x2fv(GLint location, GLsizei count, GLboolean transpose, const GLfloat* value);
+    void UniformMatrix2x4fv(GLint location, GLsizei count, GLboolean transpose, const GLfloat* value);
+    void UniformMatrix4x2fv(GLint location, GLsizei count, GLboolean transpose, const GLfloat* value);
+    void UniformMatrix3x4fv(GLint location, GLsizei count, GLboolean transpose, const GLfloat* value);
+    void UniformMatrix4x3fv(GLint location, GLsizei count, GLboolean transpose, const GLfloat* value);
+    void ProgramUniformMatrix2x3fv(GLuint program, GLint location, GLsizei count, GLboolean transpose,
+                                   const GLfloat* value);
+    void ProgramUniformMatrix3x2fv(GLuint program, GLint location, GLsizei count, GLboolean transpose,
+                                   const GLfloat* value);
+    void ProgramUniformMatrix2x4fv(GLuint program, GLint location, GLsizei count, GLboolean transpose,
+                                   const GLfloat* value);
+    void ProgramUniformMatrix4x2fv(GLuint program, GLint location, GLsizei count, GLboolean transpose,
+                                   const GLfloat* value);
+    void ProgramUniformMatrix3x4fv(GLuint program, GLint location, GLsizei count, GLboolean transpose,
+                                   const GLfloat* value);
+    void ProgramUniformMatrix4x3fv(GLuint program, GLint location, GLsizei count, GLboolean transpose,
+                                   const GLfloat* value);
     GLuint GetUniformBlockIndex(GLuint program, const GLchar* uniformBlockName);
     void UniformBlockBinding(GLuint program, GLuint uniformBlockIndex, GLuint uniformBlockBinding);
     void GetActiveUniformBlockiv(GLuint program, GLuint uniformBlockIndex, GLenum pname, GLint* params);
     void GetActiveUniformBlockName(GLuint program, GLuint uniformBlockIndex, GLsizei bufSize, GLsizei* length,
                                    GLchar* uniformBlockName);
     void BindFragDataLocation(GLuint program, GLuint colorNumber, const char* name);
+    void BindFragDataLocationIndexed(GLuint program, GLuint colorNumber, GLuint index, const char* name);
     GLint GetFragDataLocation(GLuint program, const char* name);
+    GLint GetFragDataIndex(GLuint program, const char* name);
     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,

MobileGL/MG_Impl/GLImpl/Query/GL_Query.cpp

@@ -0,0 +1,362 @@
+// MobileGL - MobileGL/MG_Impl/GLImpl/Query/GL_Query.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_Query.h"
+#include <Config.h>
+#include <MG_Backend/BackendObjects.h>
+#include <MG_State/GLState/Core.h>
+#include <MG_State/GLState/ErrorState/ErrorInfo.h>
+
+namespace MobileGL::MG_Impl::GLImpl {
+    namespace {
+        // Frontend query object (GL_ARB_timer_query): wraps an optional backend
+        // timer-query handle. A null backend handle (backend has no timer-query
+        // support, timer queries are disabled by config, or the backend could
+        // not create a query at call time) keeps a graceful fallback: the query
+        // result is immediately available and reads as zero.
+        struct QueryObject {
+            GLuint id = 0;
+            GLenum target = 0; // 0 = gen'd but never used with BeginQuery/QueryCounter
+            MG_Backend::BackendQueryHandle backendHandle = nullptr;
+            Bool active = false;
+            Bool ended = false;
+            Bool resultCached = false;
+            Uint64 cachedResult = 0;
+        };
+
+        // Query calls may arrive from any thread (launchers migrate the context
+        // across JVM threads), so the live-object registry is mutex-guarded,
+        // like the sync-object registry in GL_Sync.cpp. Entries left at process
+        // shutdown are simply dropped; their backend handles die with the
+        // backend.
+        std::mutex g_queryObjectsMutex;
+        UnorderedMap<GLuint, QueryObject*> g_liveQueryObjects;
+        // Monotonically increasing id allocator; ids are valid query objects
+        // immediately after GenQueries.
+        GLuint g_nextQueryId = 1;
+        // Id of the query currently active on GL_TIME_ELAPSED (0 = none).
+        GLuint g_activeTimeElapsedQueryId = 0;
+
+        Bool TimerQueryDisabled() {
+            return MG_Config::Features.DisableTimerQuery;
+        }
+
+        void RecordQueryError(ErrorCode code, const char* function, const char* message) {
+            MG_State::pGLContext->RecordError(code,
+                                              MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", function, message));
+        }
+
+        // Callers must hold g_queryObjectsMutex.
+        QueryObject* FindQueryObjectLocked(GLuint id) {
+            const auto it = g_liveQueryObjects.find(id);
+            return it != g_liveQueryObjects.end() ? it->second : nullptr;
+        }
+
+        // Callers must hold g_queryObjectsMutex. Releases the backend handle
+        // (if any) and clears any cached result, so the object can be reused.
+        void ResetQueryObjectLocked(QueryObject* queryObject) {
+            if (queryObject->backendHandle) {
+                if (const auto deleteBackendQuery = MG_Backend::gBackendFunctionsTable.GL.DeleteBackendQuery) {
+                    deleteBackendQuery(queryObject->backendHandle);
+                }
+                queryObject->backendHandle = nullptr;
+            }
+            queryObject->active = false;
+            queryObject->ended = false;
+            queryObject->resultCached = false;
+            queryObject->cachedResult = 0;
+        }
+
+        // Callers must hold g_queryObjectsMutex.
+        void EndTimeElapsedQueryLocked(QueryObject* queryObject) {
+            const auto endTimeElapsedQuery = MG_Backend::gBackendFunctionsTable.GL.EndTimeElapsedQuery;
+            if (endTimeElapsedQuery && queryObject->backendHandle) {
+                endTimeElapsedQuery(queryObject->backendHandle);
+            }
+            queryObject->active = false;
+            queryObject->ended = true;
+            g_activeTimeElapsedQueryId = 0;
+        }
+
+        // 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) {
+            const std::lock_guard<std::mutex> lock(g_queryObjectsMutex);
+            auto* queryObject = FindQueryObjectLocked(id);
+            if (!queryObject) {
+                RecordQueryError(ErrorCode::InvalidOperation, function, "Query object does not exist.");
+                return false;
+            }
+            if (queryObject->active) {
+                RecordQueryError(ErrorCode::InvalidOperation, function, "Query object is still active.");
+                return false;
+            }
+
+            switch (pname) {
+            case GL_QUERY_RESULT_AVAILABLE: {
+                if (queryObject->resultCached || !queryObject->backendHandle) {
+                    outValue = 1;
+                    return true;
+                }
+                const auto isQueryResultAvailable = MG_Backend::gBackendFunctionsTable.GL.IsQueryResultAvailable;
+                outValue = (!isQueryResultAvailable || isQueryResultAvailable(queryObject->backendHandle)) ? 1 : 0;
+                return true;
+            }
+            case GL_QUERY_RESULT: {
+                if (queryObject->resultCached) {
+                    outValue = queryObject->cachedResult;
+                    return true;
+                }
+                Uint64 result = 0;
+                if (queryObject->backendHandle) {
+                    const auto getQueryResult64 = MG_Backend::gBackendFunctionsTable.GL.GetQueryResult64;
+                    if (getQueryResult64 &&
+                        !getQueryResult64(queryObject->backendHandle, /*wait=*/true, &result)) {
+                        // The backend could not produce the result YET (e.g. a
+                        // Vulkan wait refusing to block on a not-yet-submitted
+                        // frame serial). Per the documented no-stall tradeoff
+                        // this call reads 0, but the value is NOT cached and
+                        // the backend handle is kept, so a later AVAILABLE
+                        // poll / RESULT read still produces the real value.
+                        outValue = 0;
+                        return true;
+                    }
+                    // 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.
+                    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;
+            }
+            default:
+                RecordQueryError(ErrorCode::InvalidEnum, function, "Unsupported query object parameter.");
+                return false;
+            }
+        }
+    } // namespace
+
+    void GenQueries(GLsizei n, GLuint* ids) {
+        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;
+            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.");
+            return;
+        }
+        if (!ids) {
+            return;
+        }
+        const std::lock_guard<std::mutex> lock(g_queryObjectsMutex);
+        for (GLsizei i = 0; i < n; ++i) {
+            const auto it = g_liveQueryObjects.find(ids[i]);
+            if (it == g_liveQueryObjects.end()) {
+                continue; // unknown ids are silently ignored
+            }
+            QueryObject* queryObject = it->second;
+            if (queryObject->active) {
+                EndTimeElapsedQueryLocked(queryObject); // implicitly end before deletion
+            }
+            if (queryObject->backendHandle) {
+                if (const auto deleteBackendQuery = MG_Backend::gBackendFunctionsTable.GL.DeleteBackendQuery) {
+                    deleteBackendQuery(queryObject->backendHandle);
+                }
+                queryObject->backendHandle = nullptr;
+            }
+            g_liveQueryObjects.erase(it);
+            delete queryObject;
+        }
+    }
+
+    GLboolean IsQuery(GLuint id) {
+        if (id == 0) {
+            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;
+    }
+
+    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.
+            RecordQueryError(ErrorCode::InvalidEnum, __FUNCTION__, "Query target is not supported.");
+            return;
+        }
+        if (id == 0) {
+            RecordQueryError(ErrorCode::InvalidOperation, __FUNCTION__, "Query id 0 cannot be used.");
+            return;
+        }
+        const std::lock_guard<std::mutex> lock(g_queryObjectsMutex);
+        auto* queryObject = FindQueryObjectLocked(id);
+        if (!queryObject) {
+            RecordQueryError(ErrorCode::InvalidOperation, __FUNCTION__, "Query object does not exist.");
+            return;
+        }
+        if (g_activeTimeElapsedQueryId != 0) {
+            RecordQueryError(ErrorCode::InvalidOperation, __FUNCTION__,
+                             "A query is already active on GL_TIME_ELAPSED.");
+            return;
+        }
+        if (queryObject->active) {
+            RecordQueryError(ErrorCode::InvalidOperation, __FUNCTION__, "Query object is already active.");
+            return;
+        }
+        if (queryObject->target != 0 && queryObject->target != target) {
+            RecordQueryError(ErrorCode::InvalidOperation, __FUNCTION__,
+                             "Query object was already used with a different target.");
+            return;
+        }
+
+        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;
+    }
+
+    void EndQuery(GLenum target) {
+        if (target != GL_TIME_ELAPSED) {
+            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.");
+            return;
+        }
+        auto* queryObject = FindQueryObjectLocked(g_activeTimeElapsedQueryId);
+        if (!queryObject) {
+            g_activeTimeElapsedQueryId = 0; // should not happen; keep state consistent
+            return;
+        }
+        EndTimeElapsedQueryLocked(queryObject);
+    }
+
+    void QueryCounter(GLuint id, GLenum target) {
+        if (target != GL_TIMESTAMP) {
+            RecordQueryError(ErrorCode::InvalidEnum, __FUNCTION__, "QueryCounter target must be GL_TIMESTAMP.");
+            return;
+        }
+        if (id == 0) {
+            RecordQueryError(ErrorCode::InvalidOperation, __FUNCTION__, "Query id 0 cannot be used.");
+            return;
+        }
+        const std::lock_guard<std::mutex> lock(g_queryObjectsMutex);
+        auto* queryObject = FindQueryObjectLocked(id);
+        if (!queryObject) {
+            RecordQueryError(ErrorCode::InvalidOperation, __FUNCTION__, "Query object does not exist.");
+            return;
+        }
+        if (queryObject->active) {
+            RecordQueryError(ErrorCode::InvalidOperation, __FUNCTION__, "Query object is currently active.");
+            return;
+        }
+        if (queryObject->target != 0 && queryObject->target != target) {
+            RecordQueryError(ErrorCode::InvalidOperation, __FUNCTION__,
+                             "Query object was already used with a different target.");
+            return;
+        }
+
+        ResetQueryObjectLocked(queryObject); // discard any previous result
+        queryObject->target = target;
+        const auto queryCounterTimestamp = MG_Backend::gBackendFunctionsTable.GL.QueryCounterTimestamp;
+        queryObject->backendHandle =
+            (!TimerQueryDisabled() && queryCounterTimestamp) ? queryCounterTimestamp() : nullptr;
+        queryObject->ended = true;
+    }
+
+    void GetQueryiv(GLenum target, GLenum pname, GLint* params) {
+        if (!params) {
+            return;
+        }
+        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;
+            return;
+        }
+        case GL_QUERY_COUNTER_BITS: {
+            // 64 bits are advertised only while the live backend can actually
+            // 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.
+            const Bool timerTarget = target == GL_TIME_ELAPSED || target == GL_TIMESTAMP;
+            const auto isTimerQuerySupported = MG_Backend::gBackendFunctionsTable.GL.IsTimerQuerySupported;
+            const Bool supported =
+                timerTarget && !TimerQueryDisabled() && isTimerQuerySupported && isTimerQuerySupported();
+            *params = supported ? 64 : 0;
+            return;
+        }
+        default:
+            RecordQueryError(ErrorCode::InvalidEnum, __FUNCTION__, "Unsupported query parameter.");
+            return;
+        }
+    }
+
+    void GetQueryObjectiv(GLuint id, GLenum pname, GLint* params) {
+        Uint64 value = 0;
+        if (!GetQueryObjectValue(id, pname, __FUNCTION__, value) || !params) {
+            return;
+        }
+        constexpr Uint64 kMaxInt = static_cast<Uint64>(INT_MAX);
+        *params = value > kMaxInt ? INT_MAX : static_cast<GLint>(value);
+    }
+
+    void GetQueryObjectuiv(GLuint id, GLenum pname, GLuint* params) {
+        Uint64 value = 0;
+        if (!GetQueryObjectValue(id, pname, __FUNCTION__, value) || !params) {
+            return;
+        }
+        *params = static_cast<GLuint>(value & 0xFFFFFFFFull);
+    }
+
+    void GetQueryObjecti64v(GLuint id, GLenum pname, GLint64* params) {
+        Uint64 value = 0;
+        if (!GetQueryObjectValue(id, pname, __FUNCTION__, value) || !params) {
+            return;
+        }
+        *params = static_cast<GLint64>(value);
+    }
+
+    void GetQueryObjectui64v(GLuint id, GLenum pname, GLuint64* params) {
+        Uint64 value = 0;
+        if (!GetQueryObjectValue(id, pname, __FUNCTION__, value) || !params) {
+            return;
+        }
+        *params = static_cast<GLuint64>(value);
+    }
+} // namespace MobileGL::MG_Impl::GLImpl

MobileGL/MG_Impl/GLImpl/Query/GL_Query.h

@@ -0,0 +1,24 @@
+// MobileGL - MobileGL/MG_Impl/GLImpl/Query/GL_Query.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 GenQueries(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 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 QueryCounter(GLuint id, GLenum target);
+} // namespace MobileGL::MG_Impl::GLImpl

MobileGL/MG_Impl/GLImpl/RenderState/GL_RenderState.cpp

@@ -7,6 +7,7 @@
 // End of Source File Header
 
 #include "GL_RenderState.h"
+#include <cmath>
 #include <MG_State/GLState/Core.h>
 #include <MG_Util/Converters/GLToStr/GLEnumConverter.h>
 #include <MG_Util/Converters/GLToMG/RenderStateEnumConverter.h>
@@ -14,6 +15,32 @@
 #include <MG_Util/Converters/MGToStr/RenderStateEnumConverter.h>
 
 namespace MobileGL::MG_Impl::GLImpl {
+    static Float ClampUnitFloat(GLfloat value) {
+        return std::clamp(static_cast<Float>(value), 0.0f, 1.0f);
+    }
+
+    static Bool ValidateIndexedBlendCapability(GLenum target, GLuint index, const char* functionName) {
+        if (target != GL_BLEND) {
+            MG_State::pGLContext->RecordError(
+                ErrorCode::InvalidEnum,
+                MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", functionName,
+                                             "Only GL_BLEND is supported for indexed capability state."));
+            return false;
+        }
+
+        if (index >= MG_State::GLState::FramebufferObject::MAX_DRAW_BUFFERS) {
+            MG_State::pGLContext->RecordError(
+                ErrorCode::InvalidValue,
+                MakeUnique<GenericErrorInfo>(
+                    "MG_Impl/GLImpl", functionName,
+                    "Buffer index " + std::to_string(index) + " is out of range. Max supported is " +
+                        std::to_string(MG_State::GLState::FramebufferObject::MAX_DRAW_BUFFERS - 1) + "."));
+            return false;
+        }
+
+        return true;
+    }
+
     static Bool TryConvertBlendEquation(GLenum mode, const char* functionName,
                                         ::MobileGL::BlendEquation& outEquation) {
         outEquation = MG_Util::ConvertGLEnumToBlendEquation(mode);
@@ -27,6 +54,43 @@ namespace MobileGL::MG_Impl::GLImpl {
         return false;
     }
 
+    static Bool TryDecodeStencilFace(GLenum face, const char* functionName, Bool& applyFront, Bool& applyBack) {
+        switch (face) {
+        case GL_FRONT:
+            applyFront = true;
+            applyBack = false;
+            return true;
+        case GL_BACK:
+            applyFront = false;
+            applyBack = true;
+            return true;
+        case GL_FRONT_AND_BACK:
+            applyFront = true;
+            applyBack = true;
+            return true;
+        default:
+            MG_State::pGLContext->RecordError(
+                ErrorCode::InvalidEnum,
+                MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", functionName,
+                                             "Stencil face enum " + MG_Util::ConvertGLEnumToString(face) +
+                                                 " is not supported."));
+            return false;
+        }
+    }
+
+    static Bool TryConvertStencilOperation(GLenum value, const char* functionName, const char* paramName,
+                                           StencilOperation& outOperation) {
+        outOperation = MG_Util::ConvertGLEnumToStencilOperation(value);
+        if (outOperation != StencilOperation::Unknown) return true;
+
+        MG_State::pGLContext->RecordError(
+            ErrorCode::InvalidEnum,
+            MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", functionName,
+                                         String(paramName) + " enum " + MG_Util::ConvertGLEnumToString(value) +
+                                             " is not supported."));
+        return false;
+    }
+
     void Viewport_State(GLint x, GLint y, GLsizei width, GLsizei height) {
         if (width < 0 || height < 0) {
             MG_State::pGLContext->RecordError(ErrorCode::InvalidValue,
@@ -39,27 +103,74 @@ namespace MobileGL::MG_Impl::GLImpl {
     }
 
     void StencilOpSeparate_State(GLenum face, GLenum sfail, GLenum dpfail, GLenum dppass) {
-        // TODO: implement
+        Bool applyFront = false;
+        Bool applyBack = false;
+        if (!TryDecodeStencilFace(face, "StencilOpSeparate_State", applyFront, applyBack)) return;
+
+        StencilOperation failOp = StencilOperation::Unknown;
+        StencilOperation depthFailOp = StencilOperation::Unknown;
+        StencilOperation depthPassOp = StencilOperation::Unknown;
+        if (!TryConvertStencilOperation(sfail, "StencilOpSeparate_State", "sfail", failOp) ||
+            !TryConvertStencilOperation(dpfail, "StencilOpSeparate_State", "dpfail", depthFailOp) ||
+            !TryConvertStencilOperation(dppass, "StencilOpSeparate_State", "dppass", depthPassOp)) {
+            return;
+        }
+
+        if (applyFront) {
+            MG_State::pGLContext->SetStencilOp(StencilFace::Front, failOp, depthFailOp, depthPassOp);
+        }
+        if (applyBack) {
+            MG_State::pGLContext->SetStencilOp(StencilFace::Back, failOp, depthFailOp, depthPassOp);
+        }
     }
 
     void StencilOp_State(GLenum fail, GLenum zfail, GLenum zpass) {
-        // TODO: implement
+        StencilOpSeparate_State(GL_FRONT_AND_BACK, fail, zfail, zpass);
     }
 
     void StencilMaskSeparate_State(GLenum face, GLuint mask) {
-        // TODO: implement
+        Bool applyFront = false;
+        Bool applyBack = false;
+        if (!TryDecodeStencilFace(face, "StencilMaskSeparate_State", applyFront, applyBack)) return;
+
+        if (applyFront) {
+            MG_State::pGLContext->SetStencilMask(StencilFace::Front, mask);
+        }
+        if (applyBack) {
+            MG_State::pGLContext->SetStencilMask(StencilFace::Back, mask);
+        }
     }
 
     void StencilMask_State(GLuint mask) {
-        // TODO: implement
+        StencilMaskSeparate_State(GL_FRONT_AND_BACK, mask);
     }
 
     void StencilFuncSeparate_State(GLenum face, GLenum func, GLint ref, GLuint mask) {
-        // TODO: implement
+        Bool applyFront = false;
+        Bool applyBack = false;
+        if (!TryDecodeStencilFace(face, "StencilFuncSeparate_State", applyFront, applyBack)) return;
+
+        DepthTestFunc depthFunc = MG_Util::ConvertGLEnumToDepthTestFunc(func);
+        if (depthFunc == DepthTestFunc::Unknown) {
+            MG_State::pGLContext->RecordError(
+                ErrorCode::InvalidEnum,
+                MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", "StencilFuncSeparate_State",
+                                             "Stencil func enum " + MG_Util::ConvertGLEnumToString(func) +
+                                                 " is not supported."));
+            return;
+        }
+
+        const Int clampedRef = std::max(ref, 0);
+        if (applyFront) {
+            MG_State::pGLContext->SetStencilFunc(StencilFace::Front, depthFunc, clampedRef, mask);
+        }
+        if (applyBack) {
+            MG_State::pGLContext->SetStencilFunc(StencilFace::Back, depthFunc, clampedRef, mask);
+        }
     }
 
     void StencilFunc_State(GLenum func, GLint ref, GLuint mask) {
-        // TODO: implement
+        StencilFuncSeparate_State(GL_FRONT_AND_BACK, func, ref, mask);
     }
 
     void Scissor_State(GLint x, GLint y, GLsizei width, GLsizei height) {
@@ -74,27 +185,111 @@ namespace MobileGL::MG_Impl::GLImpl {
     }
 
     void SampleCoverage_State(GLfloat value, GLboolean invert) {
-        // TODO: implement
+        MG_State::pGLContext->SetSampleCoverage(std::clamp(static_cast<Float>(value), 0.0f, 1.0f), invert == GL_TRUE);
     }
 
     void PolygonOffset_State(GLfloat factor, GLfloat units) {
-        // TODO: implement
+        MG_State::pGLContext->SetPolygonOffset(static_cast<Float>(factor), static_cast<Float>(units));
     }
 
     void PolygonMode_State(GLenum face, GLenum mode) {
-        // TODO: implement
+        // GL 3.3 core: separate front/back polygon modes were removed in 3.1, so the only legal
+        // face is GL_FRONT_AND_BACK. GL_FRONT / GL_BACK must be rejected (some desktop drivers
+        // leniently accept them, but that is non-conformant). Both errors are GL_INVALID_ENUM and
+        // leave state untouched.
+        if (face != GL_FRONT_AND_BACK) {
+            MG_State::pGLContext->RecordError(
+                ErrorCode::InvalidEnum,
+                MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", __func__,
+                                             "glPolygonMode face must be GL_FRONT_AND_BACK in the core profile; got " +
+                                                 MG_Util::ConvertGLEnumToString(face) + "."));
+            return;
+        }
+        if (mode != GL_POINT && mode != GL_LINE && mode != GL_FILL) {
+            MG_State::pGLContext->RecordError(
+                ErrorCode::InvalidEnum,
+                MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", __func__,
+                                             "glPolygonMode mode must be GL_POINT, GL_LINE, or GL_FILL; got " +
+                                                 MG_Util::ConvertGLEnumToString(mode) + "."));
+            return;
+        }
+        // Core sets both faces together; keep two slots so GL_POLYGON_MODE round-trips its two values.
+        MG_State::pGLContext->SetPolygonMode(mode, mode);
     }
 
     void PointSize_State(GLfloat size) {
-        // TODO: implement
+        if (size <= 0.0f) {
+            MG_State::pGLContext->RecordError(
+                ErrorCode::InvalidValue,
+                MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", "PointSize_State",
+                                             "Point size must be greater than zero."));
+            return;
+        }
+
+        MG_State::pGLContext->SetPointSize(static_cast<Float>(size));
     }
 
-    void PointParameterf_State(GLenum pname, GLfloat param) {
-        // TODO: implement
+    // Single funnel for all four glPointParameter forms. The two GL 3.3 core pnames both carry one
+    // component, so the *v forms pass params[0], and the integer forms widen to float. The
+    // GL_POINT_SPRITE_COORD_ORIGIN value is an enum passed as a float (36001.0/36002.0 are exact).
+    void PointParameter_State(GLenum pname, GLfloat value) {
+        switch (pname) {
+        case GL_POINT_FADE_THRESHOLD_SIZE:
+            if (value < 0.0f) {
+                MG_State::pGLContext->RecordError(
+                    ErrorCode::InvalidValue,
+                    MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", __func__,
+                                                 "GL_POINT_FADE_THRESHOLD_SIZE must be non-negative."));
+                return;
+            }
+            MG_State::pGLContext->SetPointFadeThresholdSize(value);
+            return;
+        case GL_POINT_SPRITE_COORD_ORIGIN: {
+            const GLenum origin = static_cast<GLenum>(std::lround(value));
+            if (origin != GL_LOWER_LEFT && origin != GL_UPPER_LEFT) {
+                MG_State::pGLContext->RecordError(
+                    ErrorCode::InvalidEnum,
+                    MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", __func__,
+                                                 "GL_POINT_SPRITE_COORD_ORIGIN must be GL_LOWER_LEFT or "
+                                                 "GL_UPPER_LEFT."));
+                return;
+            }
+            MG_State::pGLContext->SetPointSpriteCoordOrigin(origin);
+            return;
+        }
+        default:
+            MG_State::pGLContext->RecordError(
+                ErrorCode::InvalidEnum,
+                MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", __func__,
+                                             "Unsupported point parameter pname: " + std::to_string(pname)));
+            return;
+        }
     }
 
+    void PointParameterf_State(GLenum pname, GLfloat param) { PointParameter_State(pname, param); }
+
     void PointParameteri_State(GLenum pname, GLint param) {
-        // TODO: implement
+        PointParameter_State(pname, static_cast<GLfloat>(param));
+    }
+
+    void PointParameterfv_State(GLenum pname, const GLfloat* params) {
+        if (!params) {
+            MG_State::pGLContext->RecordError(
+                ErrorCode::InvalidValue,
+                MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", __func__, "params pointer cannot be null."));
+            return;
+        }
+        PointParameter_State(pname, params[0]);
+    }
+
+    void PointParameteriv_State(GLenum pname, const GLint* params) {
+        if (!params) {
+            MG_State::pGLContext->RecordError(
+                ErrorCode::InvalidValue,
+                MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", __func__, "params pointer cannot be null."));
+            return;
+        }
+        PointParameter_State(pname, static_cast<GLfloat>(params[0]));
     }
 
     void PixelStorei_State(GLenum pname, GLint param) {
@@ -114,14 +309,36 @@ namespace MobileGL::MG_Impl::GLImpl {
     }
 
     void LogicOp_State(GLenum opcode) {
-        // TODO: implement
+        LogicOperation logicOp = MG_Util::ConvertGLEnumToLogicOperation(opcode);
+        if (logicOp == LogicOperation::Unknown) {
+            MG_State::pGLContext->RecordError(
+                ErrorCode::InvalidEnum,
+                MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", "LogicOp_State",
+                                             "Logic op enum " + MG_Util::ConvertGLEnumToString(opcode) +
+                                                 " is not supported."));
+            return;
+        }
+
+        MG_State::pGLContext->SetLogicOp(logicOp);
     }
 
     void LineWidth_State(GLfloat width) {
-        // TODO: implement
+        if (width <= 0.0f) {
+            MG_State::pGLContext->RecordError(
+                ErrorCode::InvalidValue,
+                MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", "LineWidth_State",
+                                             "Line width must be greater than zero."));
+            return;
+        }
+
+        MG_State::pGLContext->SetLineWidth(static_cast<Float>(width));
     }
 
     GLboolean IsEnabledi_State(GLenum target, GLuint index) {
+        if (!ValidateIndexedBlendCapability(target, index, "IsEnabledi_State")) {
+            return GL_FALSE;
+        }
+
         CapabilityInput capInput = MG_Util::ConvertGLEnumToCapabilityInput(target);
         if (capInput == CapabilityInput::Unknown) {
             MG_State::pGLContext->RecordError(
@@ -135,6 +352,37 @@ namespace MobileGL::MG_Impl::GLImpl {
         return MG_State::pGLContext->IsCapabilityEnabledIndexed(capInput, index) ? GL_TRUE : GL_FALSE;
     }
 
+    void GetBooleani_v_State(GLenum target, GLuint index, GLboolean* data) {
+        if (!data) {
+            MG_State::pGLContext->RecordError(
+                ErrorCode::InvalidValue,
+                MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", "GetBooleani_v_State",
+                                             "data pointer cannot be null."));
+            return;
+        }
+
+        if (target == GL_COLOR_WRITEMASK) {
+            // Indexed per-draw-buffer color writemask writes 4 booleans (R,G,B,A) for draw buffer
+            // `index`. The non-indexed glGetBooleanv(GL_COLOR_WRITEMASK) reports draw buffer 0.
+            if (index >= MG_State::GLState::FramebufferObject::MAX_DRAW_BUFFERS) {
+                MG_State::pGLContext->RecordError(
+                    ErrorCode::InvalidValue,
+                    MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", "GetBooleani_v_State",
+                                                 "Color writemask draw buffer index " + std::to_string(index) +
+                                                     " is out of range."));
+                return;
+            }
+            const BoolVec4 mask = MG_State::pGLContext->GetColorMaskIndexed(index);
+            data[0] = mask.x() ? GL_TRUE : GL_FALSE;
+            data[1] = mask.y() ? GL_TRUE : GL_FALSE;
+            data[2] = mask.z() ? GL_TRUE : GL_FALSE;
+            data[3] = mask.w() ? GL_TRUE : GL_FALSE;
+            return;
+        }
+
+        *data = IsEnabledi_State(target, index);
+    }
+
     GLboolean IsEnabled_State(GLenum cap) {
         CapabilityInput capInput = MG_Util::ConvertGLEnumToCapabilityInput(cap);
         if (capInput == CapabilityInput::Unknown) {
@@ -150,7 +398,27 @@ namespace MobileGL::MG_Impl::GLImpl {
     }
 
     void Hint_State(GLenum target, GLenum mode) {
-        // TODO: implement
+        switch (target) {
+        case GL_LINE_SMOOTH_HINT:
+        case GL_POLYGON_SMOOTH_HINT:
+        case GL_TEXTURE_COMPRESSION_HINT:
+        case GL_FRAGMENT_SHADER_DERIVATIVE_HINT:
+            break;
+        default:
+            MG_State::pGLContext->RecordError(
+                ErrorCode::InvalidEnum,
+                MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", __func__,
+                                             "Unsupported hint target: " + std::to_string(target)));
+            return;
+        }
+        if (mode != GL_FASTEST && mode != GL_NICEST && mode != GL_DONT_CARE) {
+            MG_State::pGLContext->RecordError(
+                ErrorCode::InvalidEnum,
+                MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", __func__,
+                                             "Hint mode must be GL_FASTEST, GL_NICEST or GL_DONT_CARE."));
+            return;
+        }
+        MG_State::pGLContext->SetHint(target, mode);
     }
 
     void FrontFace_State(GLenum mode) {
@@ -184,6 +452,16 @@ namespace MobileGL::MG_Impl::GLImpl {
     }
 
     void Enable_State(GLenum cap) {
+        switch (cap) {
+        case GL_TEXTURE_1D:
+        case GL_TEXTURE_2D:
+        case GL_TEXTURE_3D:
+        case GL_TEXTURE_CUBE_MAP:
+            return;
+        default:
+            break;
+        }
+
         CapabilityInput capInput = MG_Util::ConvertGLEnumToCapabilityInput(cap);
         if (capInput == CapabilityInput::Unknown) {
             MG_State::pGLContext->RecordError(
@@ -198,6 +476,16 @@ namespace MobileGL::MG_Impl::GLImpl {
     }
 
     void Disable_State(GLenum cap) {
+        switch (cap) {
+        case GL_TEXTURE_1D:
+        case GL_TEXTURE_2D:
+        case GL_TEXTURE_3D:
+        case GL_TEXTURE_CUBE_MAP:
+            return;
+        default:
+            break;
+        }
+
         CapabilityInput capInput = MG_Util::ConvertGLEnumToCapabilityInput(cap);
         if (capInput == CapabilityInput::Unknown) {
             MG_State::pGLContext->RecordError(
@@ -212,7 +500,8 @@ namespace MobileGL::MG_Impl::GLImpl {
     }
 
     void DepthRange_State(GLclampd near_val, GLclampd far_val) {
-        // TODO: implement
+        MG_State::pGLContext->SetDepthRange(
+            FloatVec2(ClampUnitFloat(static_cast<GLfloat>(near_val)), ClampUnitFloat(static_cast<GLfloat>(far_val))));
     }
 
     void DepthMask_State(GLboolean flag) {
@@ -249,12 +538,59 @@ namespace MobileGL::MG_Impl::GLImpl {
     }
 
     void ColorMask_State(GLboolean red, GLboolean green, GLboolean blue, GLboolean alpha) {
+        // glColorMask broadcasts to every draw buffer. GLboolean coercion: any nonzero value enables
+        // the component; only exactly GL_FALSE disables it.
         MG_State::pGLContext->SetColorMask(
-            BoolVec4(red == GL_TRUE, green == GL_TRUE, blue == GL_TRUE, alpha == GL_TRUE));
+            BoolVec4(red != GL_FALSE, green != GL_FALSE, blue != GL_FALSE, alpha != GL_FALSE));
+    }
+
+    void ColorMaski_State(GLuint buf, GLboolean red, GLboolean green, GLboolean blue, GLboolean alpha) {
+        // Indexed color writemask for the single draw buffer `buf`. buf is a GLuint index, never an
+        // enum, so the only error is GL_INVALID_VALUE when it is out of range (mirrors the indexed
+        // blend entry points, which bound against MAX_DRAW_BUFFERS).
+        if (buf >= MG_State::GLState::FramebufferObject::MAX_DRAW_BUFFERS) {
+            MG_State::pGLContext->RecordError(
+                ErrorCode::InvalidValue,
+                MakeUnique<GenericErrorInfo>(
+                    "MG_Impl/GLImpl", __func__,
+                    "glColorMaski buffer index " + std::to_string(buf) + " is out of range. Max supported is " +
+                        std::to_string(MG_State::GLState::FramebufferObject::MAX_DRAW_BUFFERS - 1) + "."));
+            return;
+        }
+        MG_State::pGLContext->SetColorMaskIndexed(
+            buf, BoolVec4(red != GL_FALSE, green != GL_FALSE, blue != GL_FALSE, alpha != GL_FALSE));
+    }
+
+    void PrimitiveRestartIndex_State(GLuint index) {
+        // glPrimitiveRestartIndex accepts any GLuint and generates no error.
+        MG_State::pGLContext->SetPrimitiveRestartIndex(index);
     }
 
     void ClampColor_State(GLenum target, GLenum clamp) {
-        // TODO: implement
+        // GL 3.3 core: the only legal target is GL_CLAMP_READ_COLOR. The compatibility-only
+        // GL_CLAMP_VERTEX_COLOR / GL_CLAMP_FRAGMENT_COLOR were removed from the core profile and
+        // must be rejected.
+        if (target != GL_CLAMP_READ_COLOR) {
+            MG_State::pGLContext->RecordError(
+                ErrorCode::InvalidEnum,
+                MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", __func__,
+                                             "glClampColor target must be GL_CLAMP_READ_COLOR in the core profile; "
+                                             "got " +
+                                                 MG_Util::ConvertGLEnumToString(target) + "."));
+            return;
+        }
+        // clamp must be one of GL_TRUE, GL_FALSE, or GL_FIXED_ONLY. NOTE: the Khronos man page's
+        // Errors section wrongly omits GL_FIXED_ONLY, but the spec lists it as legal AND it is the
+        // default value, so it must be accepted here.
+        if (clamp != GL_TRUE && clamp != GL_FALSE && clamp != GL_FIXED_ONLY) {
+            MG_State::pGLContext->RecordError(
+                ErrorCode::InvalidEnum,
+                MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", __func__,
+                                             "glClampColor clamp must be GL_TRUE, GL_FALSE, or GL_FIXED_ONLY; got " +
+                                                 MG_Util::ConvertGLEnumToString(clamp) + "."));
+            return;
+        }
+        MG_State::pGLContext->SetClampReadColor(clamp);
     }
 
     void BlendFuncSeparate_State(GLenum sfactorRGB, GLenum dfactorRGB, GLenum sfactorAlpha, GLenum dfactorAlpha) {
@@ -304,7 +640,8 @@ namespace MobileGL::MG_Impl::GLImpl {
     }
 
     void BlendColor_State(GLfloat red, GLfloat green, GLfloat blue, GLfloat alpha) {
-        // TODO: implement
+        MG_State::pGLContext->SetBlendColor(
+            FloatVec4(ClampUnitFloat(red), ClampUnitFloat(green), ClampUnitFloat(blue), ClampUnitFloat(alpha)));
     }
 
     void ClearStencil_State(GLint s) {
@@ -312,7 +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) {
@@ -374,6 +713,10 @@ namespace MobileGL::MG_Impl::GLImpl {
     }
 
     void Disablei_State(GLenum target, GLuint index) {
+        if (!ValidateIndexedBlendCapability(target, index, "Disablei_State")) {
+            return;
+        }
+
         auto capInput = MG_Util::ConvertGLEnumToCapabilityInput(target);
         if (capInput == CapabilityInput::Unknown) {
             MG_State::pGLContext->RecordError(
@@ -388,6 +731,10 @@ namespace MobileGL::MG_Impl::GLImpl {
     }
 
     void Enablei_State(GLenum target, GLuint index) {
+        if (!ValidateIndexedBlendCapability(target, index, "Enablei_State")) {
+            return;
+        }
+
         auto capInput = MG_Util::ConvertGLEnumToCapabilityInput(target);
         if (capInput == CapabilityInput::Unknown) {
             MG_State::pGLContext->RecordError(
@@ -418,6 +765,10 @@ namespace MobileGL::MG_Impl::GLImpl {
         BlendFuncSeparatei_State(buf, srcRGB, dstRGB, srcAlpha, dstAlpha);
     }
 
+    void GetBooleani_v(GLenum target, GLuint index, GLboolean* data) {
+        GetBooleani_v_State(target, index, data);
+    }
+
     void Disablei(GLenum target, GLuint index) {
         Disablei_State(target, index);
     }
@@ -486,10 +837,36 @@ namespace MobileGL::MG_Impl::GLImpl {
         PointParameteri_State(pname, param);
     }
 
+    void PointParameterfv(GLenum pname, const GLfloat* params) {
+        PointParameterfv_State(pname, params);
+    }
+
+    void PointParameteriv(GLenum pname, const GLint* params) {
+        PointParameteriv_State(pname, params);
+    }
+
     void PixelStorei(GLenum pname, GLint param) {
         PixelStorei_State(pname, param);
     }
 
+    void PixelStoref(GLenum pname, GLfloat param) {
+        // Boolean pixel-store pnames convert by a zero-test (0.4 -> TRUE); integer pnames round to
+        // nearest. Branch before converting so a fractional value cannot round a true flag to false.
+        GLint intParam;
+        switch (pname) {
+        case GL_PACK_SWAP_BYTES:
+        case GL_UNPACK_SWAP_BYTES:
+        case GL_PACK_LSB_FIRST:
+        case GL_UNPACK_LSB_FIRST:
+            intParam = (param != 0.0f) ? 1 : 0;
+            break;
+        default:
+            intParam = static_cast<GLint>(std::lround(param));
+            break;
+        }
+        PixelStorei_State(pname, intParam);
+    }
+
     void LogicOp(GLenum opcode) {
         LogicOp_State(opcode);
     }
@@ -546,10 +923,18 @@ namespace MobileGL::MG_Impl::GLImpl {
         ColorMask_State(red, green, blue, alpha);
     }
 
+    void ColorMaski(GLuint index, GLboolean red, GLboolean green, GLboolean blue, GLboolean alpha) {
+        ColorMaski_State(index, red, green, blue, alpha);
+    }
+
     void ClampColor(GLenum target, GLenum clamp) {
         ClampColor_State(target, clamp);
     }
 
+    void PrimitiveRestartIndex(GLuint index) {
+        PrimitiveRestartIndex_State(index);
+    }
+
     void BlendFuncSeparate(GLenum sfactorRGB, GLenum dfactorRGB, GLenum sfactorAlpha, GLenum dfactorAlpha) {
         BlendFuncSeparate_State(sfactorRGB, dfactorRGB, sfactorAlpha, dfactorAlpha);
     }

MobileGL/MG_Impl/GLImpl/RenderState/GL_RenderState.h

@@ -15,6 +15,7 @@ namespace MobileGL::MG_Impl::GLImpl {
     void BlendEquationSeparatei(GLuint buf, GLenum modeRGB, GLenum modeAlpha);
     void BlendFunci(GLuint buf, GLenum src, GLenum dst);
     void BlendFuncSeparatei(GLuint buf, GLenum srcRGB, GLenum dstRGB, GLenum srcAlpha, GLenum dstAlpha);
+    void GetBooleani_v(GLenum target, GLuint index, GLboolean* data);
     void Disablei(GLenum target, GLuint index);
     void Enablei(GLenum target, GLuint index);
     void BlendFunc(GLenum sfactor, GLenum dfactor);
@@ -32,7 +33,10 @@ namespace MobileGL::MG_Impl::GLImpl {
     void PointSize(GLfloat size);
     void PointParameterf(GLenum pname, GLfloat param);
     void PointParameteri(GLenum pname, GLint param);
+    void PointParameterfv(GLenum pname, const GLfloat* params);
+    void PointParameteriv(GLenum pname, const GLint* params);
     void PixelStorei(GLenum pname, GLint param);
+    void PixelStoref(GLenum pname, GLfloat param);
     void LogicOp(GLenum opcode);
     void LineWidth(GLfloat width);
     GLboolean IsEnabledi(GLenum target, GLuint index);
@@ -47,7 +51,9 @@ namespace MobileGL::MG_Impl::GLImpl {
     void DepthFunc(GLenum func);
     void CullFace(GLenum mode);
     void ColorMask(GLboolean red, GLboolean green, GLboolean blue, GLboolean alpha);
+    void ColorMaski(GLuint index, GLboolean red, GLboolean green, GLboolean blue, GLboolean alpha);
     void ClampColor(GLenum target, GLenum clamp);
+    void PrimitiveRestartIndex(GLuint index);
     void BlendFuncSeparate(GLenum sfactorRGB, GLenum dfactorRGB, GLenum sfactorAlpha, GLenum dfactorAlpha);
     void BlendEquation(GLenum mode);
     void BlendEquationSeparate(GLenum modeRGB, GLenum modeAlpha);

MobileGL/MG_Impl/GLImpl/Sampler/GL_Sampler.cpp

@@ -13,7 +13,45 @@
 #include <MG_Util/Converters/MGToGL/TextureEnumConverter.h>
 
 namespace MobileGL::MG_Impl::GLImpl {
-    void SetSamplerParam_State(GLuint sampler, GLenum pname, const void* param, bool isFloat, bool isInteger) {
+    namespace {
+        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) {
+            case GL_TEXTURE_MIN_LOD:
+            case GL_TEXTURE_MAX_LOD:
+            case GL_TEXTURE_LOD_BIAS:
+                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;
+            }
+
+            if (isFloat) {
+                return SamplerImpl::ValidateSamplerFloatParam(pname, *(const GLfloat*)param);
+            }
+            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 isUnsignedInteger) {
+        if (param == nullptr) return;
         if (!SamplerImpl::ValidateSamplerName(sampler)) return;
 
         Bool doesSamplerObjectCreated = MG_State::pGLContext->ValidateSamplerObject(sampler);
@@ -23,6 +61,7 @@ namespace MobileGL::MG_Impl::GLImpl {
         }
         auto& samplerObj = MG_State::pGLContext->GetSamplerObject(sampler);
         if (!SamplerImpl::ValidateSamplerObject(sampler)) return;
+        if (!ValidateSamplerParameterValue(pname, param, isFloat, isUnsignedInteger)) return;
 
         using namespace MG_Util;
         switch (pname) {
@@ -51,6 +90,9 @@ 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;
@@ -64,7 +106,9 @@ 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;
 
         Bool doesSamplerObjectCreated = MG_State::pGLContext->ValidateSamplerObject(sampler);
@@ -103,6 +147,15 @@ 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;
@@ -176,10 +229,20 @@ namespace MobileGL::MG_Impl::GLImpl {
         }
 
         auto& textureUnit = MG_State::pGLContext->GetTextureUnitObject((Int)unit);
+        MG_State::pGLContext->NoteTextureUnitTouched((Int)unit);
         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);
@@ -213,7 +276,7 @@ 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) {
@@ -241,7 +304,7 @@ 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

@@ -99,6 +99,16 @@ 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 +135,16 @@ 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

@@ -7,115 +7,123 @@
 // End of Source File Header
 
 #include "GL_Sync.h"
-
-#include <MG_State/GLState/Core.h>
-#include <MG_State/GLState/ErrorState/Error.h>
+#include <MG_Backend/BackendObjects.h>
 
 namespace MobileGL::MG_Impl::GLImpl {
     namespace {
+        // Frontend sync object: wraps an optional backend fence handle. A null
+        // backend handle (backend has no fence support, or could not create a
+        // fence at call time) keeps the legacy always-signaled behavior.
         struct SyncObject {
-            GLenum Condition = GL_SYNC_GPU_COMMANDS_COMPLETE;
-            GLbitfield Flags = 0;
+            MG_Backend::BackendSyncHandle backendHandle = nullptr;
+            GLenum condition = GL_SYNC_GPU_COMMANDS_COMPLETE;
+            GLbitfield flags = 0;
         };
 
-        UnorderedMap<GLsync, UniquePtr<SyncObject>> g_syncObjects;
+        // Sync calls may arrive from any thread (launchers migrate the context
+        // across JVM threads), so the live-object registry is mutex-guarded.
+        // Entries left at process shutdown are simply dropped; their backend
+        // handles die with the backend.
+        std::mutex g_syncObjectsMutex;
+        UnorderedMap<GLsync, SyncObject*> g_liveSyncObjects;
 
-        void RecordSyncError(const char* funcName, ErrorCode code, String message) {
-            MG_State::pGLContext->RecordError(code,
-                                              MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", funcName, Move(message)));
-        }
-
-        SyncObject* GetSyncObject(GLsync sync, const char* funcName) {
-            auto it = g_syncObjects.find(sync);
-            if (sync == nullptr || it == g_syncObjects.end()) {
-                RecordSyncError(funcName, ErrorCode::InvalidValue, "Sync object is not valid.");
-                return nullptr;
-            }
-            return it->second.get();
+        SyncObject* FindSyncObject(GLsync sync) {
+            const std::lock_guard<std::mutex> lock(g_syncObjectsMutex);
+            const auto it = g_liveSyncObjects.find(sync);
+            return it != g_liveSyncObjects.end() ? it->second : nullptr;
         }
     } // namespace
 
     GLsync FenceSync(GLenum condition, GLbitfield flags) {
-        if (condition != GL_SYNC_GPU_COMMANDS_COMPLETE) {
-            RecordSyncError("FenceSync", ErrorCode::InvalidEnum, "Condition must be GL_SYNC_GPU_COMMANDS_COMPLETE.");
-            return nullptr;
+        auto* syncObject = new SyncObject;
+        syncObject->condition = condition;
+        syncObject->flags = flags;
+        if (const auto backendFenceSync = MG_Backend::gBackendFunctionsTable.GL.FenceSync) {
+            syncObject->backendHandle = backendFenceSync();
         }
-        if (flags != 0) {
-            RecordSyncError("FenceSync", ErrorCode::InvalidValue, "Flags must be zero.");
-            return nullptr;
-        }
-
-        auto syncObject = MakeUnique<SyncObject>();
-        syncObject->Condition = condition;
-        syncObject->Flags = flags;
-        GLsync handle = reinterpret_cast<GLsync>(syncObject.get());
-        g_syncObjects[handle] = Move(syncObject);
+        const GLsync handle = reinterpret_cast<GLsync>(syncObject);
+        const std::lock_guard<std::mutex> lock(g_syncObjectsMutex);
+        g_liveSyncObjects[handle] = syncObject;
         return handle;
     }
 
     GLboolean IsSync(GLsync sync) {
-        return g_syncObjects.find(sync) != g_syncObjects.end() ? GL_TRUE : GL_FALSE;
+        return FindSyncObject(sync) != nullptr ? GL_TRUE : GL_FALSE;
     }
 
     GLenum ClientWaitSync(GLsync sync, GLbitfield flags, GLuint64 timeout) {
-        (void)timeout;
-        if ((flags & ~GL_SYNC_FLUSH_COMMANDS_BIT) != 0) {
-            RecordSyncError("ClientWaitSync", ErrorCode::InvalidValue,
-                            "Flags can only contain GL_SYNC_FLUSH_COMMANDS_BIT.");
+        const auto* syncObject = FindSyncObject(sync);
+        if (!syncObject) {
             return GL_WAIT_FAILED;
         }
-        if (!GetSyncObject(sync, "ClientWaitSync")) return GL_WAIT_FAILED;
-        return GL_ALREADY_SIGNALED;
+        const auto backendClientWaitSync = MG_Backend::gBackendFunctionsTable.GL.ClientWaitSync;
+        if (!backendClientWaitSync || !syncObject->backendHandle) {
+            return GL_ALREADY_SIGNALED; // legacy always-signaled fallback
+        }
+        return backendClientWaitSync(syncObject->backendHandle, flags, timeout);
     }
 
     void WaitSync(GLsync sync, GLbitfield flags, GLuint64 timeout) {
-        if (flags != 0) {
-            RecordSyncError("WaitSync", ErrorCode::InvalidValue, "Flags must be zero.");
+        const auto* syncObject = FindSyncObject(sync);
+        if (!syncObject) {
             return;
         }
-        if (timeout != GL_TIMEOUT_IGNORED) {
-            RecordSyncError("WaitSync", ErrorCode::InvalidValue, "Timeout must be GL_TIMEOUT_IGNORED.");
-            return;
+        const auto backendWaitSync = MG_Backend::gBackendFunctionsTable.GL.WaitSync;
+        if (backendWaitSync && syncObject->backendHandle) {
+            backendWaitSync(syncObject->backendHandle, flags, timeout);
         }
-        (void)GetSyncObject(sync, "WaitSync");
     }
 
     void DeleteSync(GLsync sync) {
-        if (sync == nullptr) return;
-        auto it = g_syncObjects.find(sync);
-        if (it == g_syncObjects.end()) {
-            RecordSyncError("DeleteSync", ErrorCode::InvalidValue, "Sync object is not valid.");
-            return;
+        if (sync == nullptr) {
+            return; // glDeleteSync(0) is silently ignored
         }
-        g_syncObjects.erase(it);
+        SyncObject* syncObject = nullptr;
+        {
+            const std::lock_guard<std::mutex> lock(g_syncObjectsMutex);
+            const auto it = g_liveSyncObjects.find(sync);
+            if (it == g_liveSyncObjects.end()) {
+                return;
+            }
+            syncObject = it->second;
+            g_liveSyncObjects.erase(it);
+        }
+        const auto backendDeleteSync = MG_Backend::gBackendFunctionsTable.GL.DeleteSync;
+        if (backendDeleteSync && syncObject->backendHandle) {
+            backendDeleteSync(syncObject->backendHandle);
+        }
+        delete syncObject;
     }
 
     void GetSynciv(GLsync sync, GLenum pname, GLsizei bufSize, GLsizei* length, GLint* values) {
-        if (bufSize < 0) {
-            RecordSyncError("GetSynciv", ErrorCode::InvalidValue, "bufSize must be non-negative.");
+        const auto* syncObject = FindSyncObject(sync);
+        if (!syncObject) {
+            if (length) {
+                *length = 0;
+            }
             return;
         }
 
-        auto* syncObject = GetSyncObject(sync, "GetSynciv");
-        if (!syncObject) return;
-
         GLint value = 0;
         switch (pname) {
         case GL_OBJECT_TYPE:
             value = GL_SYNC_FENCE;
             break;
-        case GL_SYNC_STATUS:
-            value = GL_SIGNALED;
+        case GL_SYNC_STATUS: {
+            const auto backendGetSyncStatus = MG_Backend::gBackendFunctionsTable.GL.GetSyncStatus;
+            const Bool signaled = !backendGetSyncStatus || !syncObject->backendHandle ||
+                                  backendGetSyncStatus(syncObject->backendHandle);
+            value = signaled ? GL_SIGNALED : GL_UNSIGNALED;
             break;
+        }
         case GL_SYNC_CONDITION:
-            value = static_cast<GLint>(syncObject->Condition);
+            value = static_cast<GLint>(syncObject->condition);
             break;
         case GL_SYNC_FLAGS:
-            value = static_cast<GLint>(syncObject->Flags);
+            value = static_cast<GLint>(syncObject->flags);
             break;
         default:
-            RecordSyncError("GetSynciv", ErrorCode::InvalidEnum, std::format("Invalid pname enum: 0x{:X}", pname));
-            return;
+            break;
         }
 
         if (length) {

MobileGL/MG_Impl/GLImpl/Texture/GL_Texture.h

@@ -11,23 +11,53 @@
 
 namespace MobileGL::MG_Impl::GLImpl {
     /* @INSERTION_POINT:FUNCTION_DECLARATION@ */
+    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);
     void GetTexImage(GLenum target, GLint level, GLenum format, GLenum type, GLvoid* pixels);
     void CreateTextures(GLenum target, GLsizei n, GLuint* textures);
+    void TextureStorage1D(GLuint texture, GLsizei levels, GLenum internalformat, GLsizei width);
     void TextureStorage2D(GLuint texture, GLsizei levels, GLenum internalformat, GLsizei width, GLsizei height);
+    void TextureStorage3D(GLuint texture, GLsizei levels, GLenum internalformat, GLsizei width, GLsizei height,
+                          GLsizei depth);
+    void TextureStorage2DMultisample(GLuint texture, GLsizei samples, GLenum internalformat, GLsizei width,
+                                     GLsizei height, GLboolean fixedsamplelocations);
+    void TextureStorage3DMultisample(GLuint texture, GLsizei samples, GLenum internalformat, GLsizei width,
+                                     GLsizei height, GLsizei depth, GLboolean fixedsamplelocations);
+    void TextureSubImage1D(GLuint texture, GLint level, GLint xoffset, GLsizei width, GLenum format, GLenum type,
+                           const void* pixels);
     void TextureSubImage2D(GLuint texture, GLint level, GLint xoffset, GLint yoffset, GLsizei width, GLsizei height,
                            GLenum format, GLenum type, const void* pixels);
+    void TextureSubImage3D(GLuint texture, GLint level, GLint xoffset, GLint yoffset, GLint zoffset, GLsizei width,
+                           GLsizei height, GLsizei depth, GLenum format, GLenum type, const void* pixels);
     void TextureParameterf(GLuint texture, GLenum pname, GLfloat param);
+    void TextureParameterfv(GLuint texture, GLenum pname, const GLfloat* params);
     void TextureParameteri(GLuint texture, GLenum pname, GLint param);
+    void TextureParameterIiv(GLuint texture, GLenum pname, const GLint* params);
+    void TextureParameterIuiv(GLuint texture, GLenum pname, const GLuint* params);
     void TextureParameteriv(GLuint texture, GLenum pname, const GLint* params);
+    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 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);
+    void GetTextureParameterIiv(GLuint texture, GLenum pname, GLint* params);
+    void GetTextureParameterIuiv(GLuint texture, GLenum pname, GLuint* params);
     void GetTextureParameteriv(GLuint texture, GLenum pname, GLint* params);
+    void GetTextureLevelParameterfv(GLuint texture, GLint level, GLenum pname, GLfloat* params);
     void GetTextureLevelParameteriv(GLuint texture, GLint level, GLenum pname, GLint* params);
+    void TexStorage1D(GLenum target, GLsizei levels, GLenum internalformat, GLsizei width);
+    void TexStorage2D(GLenum target, GLsizei levels, GLenum internalformat, GLsizei width, GLsizei height);
+    void TexStorage3D(GLenum target, GLsizei levels, GLenum internalformat, GLsizei width, GLsizei height,
+                      GLsizei depth);
+    void TexStorage2DMultisample(GLenum target, GLsizei samples, GLenum internalformat, GLsizei width,
+                                 GLsizei height, GLboolean fixedsamplelocations);
+    void TexStorage3DMultisample(GLenum target, GLsizei samples, GLenum internalformat, GLsizei width,
+                                 GLsizei height, GLsizei depth, GLboolean fixedsamplelocations);
     void TexSubImage3D(GLenum target, GLint level, GLint xoffset, GLint yoffset, GLint zoffset, GLsizei width,
                        GLsizei height, GLsizei depth, GLenum format, GLenum type, const void* pixels);
     void TexSubImage2D(GLenum target, GLint level, GLint xoffset, GLint yoffset, GLsizei width, GLsizei height,
@@ -59,6 +89,8 @@ namespace MobileGL::MG_Impl::GLImpl {
     void GetTexParameterfv(GLenum target, GLenum pname, GLfloat* params);
     void GetTexLevelParameteriv(GLenum target, GLint level, GLenum pname, GLint* params);
     void GetTexLevelParameterfv(GLenum target, GLint level, GLenum pname, GLfloat* params);
+    void GetMultisamplefv(GLenum pname, GLuint index, GLfloat* val);
+    void GetInternalformativ(GLenum target, GLenum internalformat, GLenum pname, GLsizei bufSize, GLint* params);
     void GetCompressedTexImage(GLenum target, GLint level, void* img);
     void GenTextures(GLsizei n, GLuint* textures);
     void DeleteTextures(GLsizei n, const GLuint* textures);
@@ -66,11 +98,16 @@ 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 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);
     void CopyTexImage1D(GLenum target, GLint level, GLenum internalformat, GLint x, GLint y, GLsizei width,
                         GLint border);
+    void CopyImageSubData(GLuint srcName, GLenum srcTarget, GLint srcLevel, GLint srcX, GLint srcY, GLint srcZ,
+                          GLuint dstName, GLenum dstTarget, GLint dstLevel, GLint dstX, GLint dstY, GLint dstZ,
+                          GLsizei srcWidth, GLsizei srcHeight, GLsizei srcDepth);
     void CompressedTexSubImage3D(GLenum target, GLint level, GLint xoffset, GLint yoffset, GLint zoffset, GLsizei width,
                                  GLsizei height, GLsizei depth, GLenum format, GLsizei imageSize, const void* data);
     void CompressedTexSubImage2D(GLenum target, GLint level, GLint xoffset, GLint yoffset, GLsizei width,

MobileGL/MG_Impl/GLImpl/Texture/ProxyTexture.cpp

@@ -7,7 +7,11 @@
 // End of Source File Header
 
 #include "ProxyTexture.h"
+#include <MG_State/GLState/TextureState/TextureObject1D.h>
 #include <MG_State/GLState/TextureState/TextureObject2D.h>
+#include <MG_State/GLState/TextureState/TextureObject2DCube.h>
+#include <MG_State/GLState/TextureState/TextureObject3D.h>
+#include <MG_State/GLState/TextureState/TextureObjectStubs.h>
 
 namespace MobileGL::MG_Impl::GLImpl::TextureImpl {
     UniquePtr<ProxyTextureManager> pProxyTextureManager;
@@ -37,7 +41,39 @@ namespace MobileGL::MG_Impl::GLImpl::TextureImpl {
             m_proxyTexturesMap.erase(it);
         }
         auto& obj = m_proxyTexturesMap[target];
-        obj = MakeShared<MG_State::GLState::TextureObject2D>(0);
+        switch (target) {
+        case TextureUploadTarget::ProxyTexture1D:
+        case TextureUploadTarget::ProxyTexture1DArray:
+            obj = MakeShared<MG_State::GLState::TextureObject1D>(0);
+            break;
+        case TextureUploadTarget::ProxyTexture2D:
+            obj = MakeShared<MG_State::GLState::TextureObject2D>(0);
+            break;
+        case TextureUploadTarget::ProxyTexture3D:
+            obj = MakeShared<MG_State::GLState::TextureObject3D>(0);
+            break;
+        case TextureUploadTarget::ProxyCubeMap:
+            obj = MakeShared<MG_State::GLState::TextureObject2DCube>(0);
+            break;
+        case TextureUploadTarget::ProxyTextureRectangle:
+            obj = MakeShared<MG_State::GLState::TextureObjectRectangle>(0);
+            break;
+        case TextureUploadTarget::ProxyTexture2DArray:
+            obj = MakeShared<MG_State::GLState::TextureObject2DArray>(0);
+            break;
+        case TextureUploadTarget::ProxyCubeMapArray:
+            obj = MakeShared<MG_State::GLState::TextureObjectCubeMapArray>(0);
+            break;
+        case TextureUploadTarget::ProxyTexture2DMultisample:
+            obj = MakeShared<MG_State::GLState::TextureObject2DMultisample>(0);
+            break;
+        case TextureUploadTarget::ProxyTexture2DMultisampleArray:
+            obj = MakeShared<MG_State::GLState::TextureObject2DMultisampleArray>(0);
+            break;
+        default:
+            obj = MakeShared<MG_State::GLState::TextureObject2D>(0);
+            break;
+        }
         return obj;
     }
 

MobileGL/MG_Impl/GLImpl/Texture/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>
@@ -83,8 +84,20 @@ namespace MobileGL::MG_Impl::GLImpl::TextureImpl {
             return false;
         }
 
-        // TODO: GL_INVALID_VALUE may be generated if level is greater than log2(max), where max is the returned
-        // value of GL_MAX_TEXTURE_SIZE.
+        Int maxTextureSize = MG_Backend::DynamicBackendParameters{}.MaxTextureSize;
+        if (MG_Backend::pActiveBackendObject) {
+            maxTextureSize = MG_Backend::pActiveBackendObject->GetDynamicParameters().MaxTextureSize;
+        }
+        Int maxLevel = 0;
+        for (Int size = std::max(maxTextureSize, 1); size > 1; size >>= 1) {
+            ++maxLevel;
+        }
+        if (level > maxLevel) {
+            MG_State::pGLContext->RecordError(
+                ErrorCode::InvalidValue, MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", "ValidateTextureLevelNumber",
+                                                                      "Texture level exceeds GL_MAX_TEXTURE_SIZE"));
+            return false;
+        }
 
         return true;
     }
@@ -129,7 +142,7 @@ namespace MobileGL::MG_Impl::GLImpl::TextureImpl {
         return true;
     }
 
-    Bool ValidateTextureSizeRange(SizeT width, SizeT height, SizeT depth) {
+    Bool ValidateTextureSizeRange(Int width, Int height, Int depth) {
         if (width < 0 || height < 0 || depth < 0) {
             MG_State::pGLContext->RecordError(
                 ErrorCode::InvalidValue, MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", "ValidateTextureSizeRange",
@@ -162,61 +175,153 @@ namespace MobileGL::MG_Impl::GLImpl::TextureImpl {
         return true;
     }
 
-    Bool ValidateTextureInternalFormatCompatibleWithInput(TextureInputFormat format,
-                                                          TextureInternalFormat internalFormat,
-                                                          TexturePixelDataType type) {
-        if (type == TexturePixelDataType::UnsignedByte332 || type == TexturePixelDataType::UnsignedByte233Rev ||
-            type == TexturePixelDataType::UnsignedShort565 || type == TexturePixelDataType::UnsignedShort565Rev ||
-            type == TexturePixelDataType::UnsignedInt101111Rev) {
-            if (format != TextureInputFormat::RGB) {
-                MG_State::pGLContext->RecordError(
-                    ErrorCode::InvalidOperation,
-                    MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", "ValidateTextureInternalFormatCompatibleWithInput",
-                                                 "Invalid format for the given type"));
+    Bool IsIntegerColorInputFormat(TextureInputFormat format) {
+        return format == TextureInputFormat::RInteger || format == TextureInputFormat::RGInteger ||
+               format == TextureInputFormat::RGBInteger || format == TextureInputFormat::BGRInteger ||
+               format == TextureInputFormat::RGBAInteger || format == TextureInputFormat::BGRAInteger ||
+               format == TextureInputFormat::GreenInteger || format == TextureInputFormat::BlueInteger ||
+               format == TextureInputFormat::AlphaInteger;
+    }
+
+    Bool IsIntegerColorInternalFormat(TextureInternalFormat internalFormat) {
+        switch (internalFormat) {
+            case TextureInternalFormat::R8I:
+            case TextureInternalFormat::R8UI:
+            case TextureInternalFormat::R16I:
+            case TextureInternalFormat::R16UI:
+            case TextureInternalFormat::R32I:
+            case TextureInternalFormat::R32UI:
+            case TextureInternalFormat::RG8I:
+            case TextureInternalFormat::RG8UI:
+            case TextureInternalFormat::RG16I:
+            case TextureInternalFormat::RG16UI:
+            case TextureInternalFormat::RG32I:
+            case TextureInternalFormat::RG32UI:
+            case TextureInternalFormat::RGB8I:
+            case TextureInternalFormat::RGB8UI:
+            case TextureInternalFormat::RGB16I:
+            case TextureInternalFormat::RGB16UI:
+            case TextureInternalFormat::RGB32I:
+            case TextureInternalFormat::RGB32UI:
+            case TextureInternalFormat::RGBA8I:
+            case TextureInternalFormat::RGBA8UI:
+            case TextureInternalFormat::RGBA16I:
+            case TextureInternalFormat::RGBA16UI:
+            case TextureInternalFormat::RGBA32I:
+            case TextureInternalFormat::RGBA32UI:
+            case TextureInternalFormat::RGB10A2UI:
+                return true;
+            default:
                 return false;
+        }
+    }
+
+    static Bool IsDepthLikeInternalFormat(TextureInternalFormat internalFormat) {
+        switch (internalFormat) {
+            case TextureInternalFormat::DepthComponent:
+            case TextureInternalFormat::DepthComponent16:
+            case TextureInternalFormat::DepthComponent24:
+            case TextureInternalFormat::DepthComponent32: // not core, kept for Minecraft 1.21.5+
+            case TextureInternalFormat::DepthComponent32F:
+            case TextureInternalFormat::Depth24Stencil8:
+            case TextureInternalFormat::Depth32FStencil8:
+            case TextureInternalFormat::DepthStencil:
+                return true;
+            default:
+                return false;
+        }
+    }
+
+    static Bool IsDepthLikeInputFormat(TextureInputFormat format) {
+        return format == TextureInputFormat::DepthComponent || format == TextureInputFormat::DepthStencil ||
+               format == TextureInputFormat::StencilIndex;
+    }
+
+    // Client-memory format<->type pairing rules shared by pixel uploads (TexImage*) and readbacks
+    // (ReadPixels, GetTexImage). Mirrors the desktop-GL validity matrix used by GL CTS packed_pixels
+    // (glcPackedPixelsTests isFormatValid): packed types constrain the formats they may pair with, and
+    // integer formats reject floating-point types; violations raise GL_INVALID_OPERATION.
+    Bool ValidateClientFormatTypePairing(TextureInputFormat format, TexturePixelDataType type) {
+        const auto recordInvalidOperation = [](const char* message) {
+            MG_State::pGLContext->RecordError(
+                ErrorCode::InvalidOperation,
+                MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", "ValidateClientFormatTypePairing", message));
+            return false;
+        };
+
+        if (type == TexturePixelDataType::UnsignedByte332 || type == TexturePixelDataType::UnsignedByte233Rev ||
+            type == TexturePixelDataType::UnsignedShort565 || type == TexturePixelDataType::UnsignedShort565Rev) {
+            if (format != TextureInputFormat::RGB && format != TextureInputFormat::RGBInteger) {
+                return recordInvalidOperation("Packed RGB type requires RGB or RGB_INTEGER format");
+            }
+        }
+
+        if (type == TexturePixelDataType::UnsignedInt101111Rev || type == TexturePixelDataType::UnsignedInt5999Rev) {
+            if (format != TextureInputFormat::RGB) {
+                return recordInvalidOperation("Packed float RGB type requires RGB format");
             }
         }
 
         if (type == TexturePixelDataType::UnsignedShort4444 || type == TexturePixelDataType::UnsignedShort4444Rev ||
             type == TexturePixelDataType::UnsignedShort5551 || type == TexturePixelDataType::UnsignedShort1555Rev ||
             type == TexturePixelDataType::UnsignedInt8888 || type == TexturePixelDataType::UnsignedInt8888Rev ||
-            type == TexturePixelDataType::UnsignedInt1010102 || type == TexturePixelDataType::UnsignedInt2101010Rev ||
-            type == TexturePixelDataType::UnsignedInt5999Rev) {
-            if (format != TextureInputFormat::RGBA && format != TextureInputFormat::BGRA) {
-                MG_State::pGLContext->RecordError(
-                    ErrorCode::InvalidOperation,
-                    MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", "ValidateTextureInternalFormatCompatibleWithInput",
-                                                 "Invalid format for the given type"));
-                return false;
+            type == TexturePixelDataType::UnsignedInt1010102 || type == TexturePixelDataType::UnsignedInt2101010Rev) {
+            if (format != TextureInputFormat::RGBA && format != TextureInputFormat::BGRA &&
+                format != TextureInputFormat::RGBAInteger && format != TextureInputFormat::BGRAInteger) {
+                return recordInvalidOperation("Packed RGBA type requires RGBA/BGRA (integer) format");
             }
         }
 
-        if (internalFormat == TextureInternalFormat::DepthComponent ||
-            internalFormat == TextureInternalFormat::DepthComponent16 ||
-            internalFormat == TextureInternalFormat::DepthComponent24 ||
-            internalFormat == TextureInternalFormat::DepthComponent32F) {
-            if (format != TextureInputFormat::DepthComponent) {
-                MG_State::pGLContext->RecordError(
-                    ErrorCode::InvalidOperation,
-                    MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", "ValidateTextureInternalFormatCompatibleWithInput",
-                                                 "Invalid format for depth component internal format"));
-                return false;
+        if (type == TexturePixelDataType::UnsignedInt248 || type == TexturePixelDataType::Float32UnsignedInt248Rev) {
+            if (format != TextureInputFormat::DepthStencil) {
+                return recordInvalidOperation("Packed depth-stencil type requires DEPTH_STENCIL format");
             }
         }
 
-        if (format == TextureInputFormat::DepthComponent &&
-            (internalFormat != TextureInternalFormat::DepthComponent &&
-             internalFormat != TextureInternalFormat::DepthComponent16 &&
-             internalFormat != TextureInternalFormat::DepthComponent24 &&
-             internalFormat != TextureInternalFormat::DepthComponent32F &&
-             internalFormat != TextureInternalFormat::DepthComponent32 // workaround for Minecraft 1.21.5+
-             )) {
+        if (format == TextureInputFormat::DepthStencil && type != TexturePixelDataType::UnsignedInt248 &&
+            type != TexturePixelDataType::Float32UnsignedInt248Rev) {
+            return recordInvalidOperation("DEPTH_STENCIL format requires a packed depth-stencil type");
+        }
+
+        if (IsIntegerColorInputFormat(format) &&
+            (type == TexturePixelDataType::Float || type == TexturePixelDataType::HalfFloat)) {
+            return recordInvalidOperation("Integer format cannot be used with a floating-point type");
+        }
+
+        return true;
+    }
+
+    // Mirrors the desktop-GL validity matrix used by GL CTS packed_pixels (glcPackedPixelsTests
+    // isFormatValid, INPUT_TEXIMAGE): packed-type/format pairing, depth-vs-color mismatch, and
+    // integer-ness matching all raise GL_INVALID_OPERATION instead of reaching the upload path.
+    Bool ValidateTextureInternalFormatCompatibleWithInput(TextureInputFormat format,
+                                                          TextureInternalFormat internalFormat,
+                                                          TexturePixelDataType type) {
+        const auto recordInvalidOperation = [](const char* message) {
             MG_State::pGLContext->RecordError(
                 ErrorCode::InvalidOperation,
                 MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", "ValidateTextureInternalFormatCompatibleWithInput",
-                                             "Invalid internal format for depth component format"));
+                                             message));
+            return false;
+        };
+
+        if (!ValidateClientFormatTypePairing(format, type)) {
             return false;
         }
+
+        // TexImage in core 3.3 has no stencil-only upload path (that arrived with GL 4.4).
+        if (format == TextureInputFormat::StencilIndex) {
+            return recordInvalidOperation("STENCIL_INDEX is not a valid texture upload format");
+        }
+
+        if (IsDepthLikeInputFormat(format) != IsDepthLikeInternalFormat(internalFormat)) {
+            return recordInvalidOperation("Depth/stencil-ness of format and internal format must match");
+        }
+
+        if (IsIntegerColorInputFormat(format) != IsIntegerColorInternalFormat(internalFormat)) {
+            return recordInvalidOperation("Integer-ness of format and internal format must match");
+        }
+
         return true;
     }
 
@@ -230,6 +335,18 @@ namespace MobileGL::MG_Impl::GLImpl::TextureImpl {
                 return false;
             }
         }
+        if (target == TextureUploadTarget::Texture2DMultisample ||
+            target == TextureUploadTarget::ProxyTexture2DMultisample ||
+            target == TextureUploadTarget::Texture2DMultisampleArray ||
+            target == TextureUploadTarget::ProxyTexture2DMultisampleArray) {
+            if (level != 0) {
+                MG_State::pGLContext->RecordError(
+                    ErrorCode::InvalidValue,
+                    MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", "ValidateTextureLevelWithUploadTarget",
+                                                 "Level must be zero for multisample textures"));
+                return false;
+            }
+        }
         return true;
     }
 
@@ -243,6 +360,19 @@ namespace MobileGL::MG_Impl::GLImpl::TextureImpl {
         return true;
     }
 
+    Bool ValidateTextureNotDefault(const SharedPtr<MG_State::GLState::ITextureObject>& textureObject,
+                                   const char* caller) {
+        if (textureObject && textureObject->GetExternalIndex() == 0) {
+            MG_State::pGLContext->RecordError(
+                ErrorCode::InvalidOperation,
+                MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", caller,
+                                             "This operation is not allowed on the default texture (zero is "
+                                             "bound to the target)."));
+            return false;
+        }
+        return true;
+    }
+
     Bool ValidateTextureTargetUniformity(SharedPtr<MG_State::GLState::ITextureObject> textureObject,
                                          TextureTarget target) {
         if (!textureObject) return true; // should be created later

MobileGL/MG_Impl/GLImpl/Texture/Validators.h

@@ -20,14 +20,22 @@ namespace MobileGL::MG_Impl::GLImpl::TextureImpl {
     Bool ValidateTexturePixelDataType(TexturePixelDataType texturePixelDataType);
     Bool ValidateTextureLevelNumber(Int level);
     Bool ValidateTextureSizeWithTextureUploadTarget(TextureUploadTarget target, GLsizei width, GLsizei height);
-    Bool ValidateTextureSizeRange(SizeT width, SizeT height, SizeT depth);
+    Bool ValidateTextureSizeRange(Int width, Int height, Int depth);
     Bool ValidateTextureInternalFormat(TextureInternalFormat format);
     Bool ValidateTextureBorderNumber(Int border);
+    Bool IsIntegerColorInputFormat(TextureInputFormat format);
+    Bool IsIntegerColorInternalFormat(TextureInternalFormat internalFormat);
+    Bool ValidateClientFormatTypePairing(TextureInputFormat format, TexturePixelDataType type);
     Bool ValidateTextureInternalFormatCompatibleWithInput(TextureInputFormat format,
                                                           TextureInternalFormat internalFormat,
                                                           TexturePixelDataType type);
     Bool ValidateTextureLevelWithUploadTarget(TextureUploadTarget target, Int level);
     Bool ValidateTextureObject(SharedPtr<MG_State::GLState::ITextureObject> textureObject);
+    // Rejects the per-target default texture objects (name 0) with GL_INVALID_OPERATION for entry
+    // points that require a GenTextures-created texture, e.g. TexStorage* ("An INVALID_OPERATION
+    // error is generated if zero is bound to target", ARB_texture_storage).
+    Bool ValidateTextureNotDefault(const SharedPtr<MG_State::GLState::ITextureObject>& textureObject,
+                                   const char* caller);
     Bool ValidateTextureTargetUniformity(SharedPtr<MG_State::GLState::ITextureObject> textureObject,
                                          TextureTarget target);
     Bool ValidateTextureSubImageOffsets(SharedPtr<MG_State::GLState::ITextureObject> textureObject, Int xoffset,

MobileGL/MG_Impl/GLImpl/VertexArray/GL_VertexArray.cpp

@@ -12,8 +12,147 @@
 #include <MG_State/GLState/Core.h>
 #include <MG_State/GLState/ErrorState/Error.h>
 #include <MG_Util/Converters/GLToMG/DataTypeConverter.h>
+#include <MG_Util/Converters/GLToStr/GLEnumConverter.h>
+#include <MG_Util/Converters/MGToGL/DataTypeConverter.h>
 
 namespace MobileGL::MG_Impl::GLImpl {
+    namespace {
+        // GL 3.3 Core signed normalized fixed-point -> float (spec §2.1.2 Eq 2.2):
+        //   f = (2c + 1) / (2^b - 1)
+        // This maps the FULL signed range [-2^(b-1), 2^(b-1)-1] onto exactly [-1, 1] (so -128 -> -1.0
+        // and 127 -> +1.0 with no clamp), and consequently cannot represent 0 exactly (0 -> 1/(2^b-1)).
+        // NOTE: GL 4.2 later switched signed normalization to f = max(c/(2^(b-1)-1), -1); do NOT use that
+        // form here -- it is not GL 3.3 Core. Unsigned normalization (f = c/(2^b-1)) is unchanged.
+        // The bit width fixes the arithmetic type: 8/16-bit stay exact in int/float, but the 32-bit forms
+        // must use double because 2*INT_MAX overflows int32 and neither 2^32-1 nor 2^31-1 is float-exact.
+        constexpr GLfloat NormalizeSignedByte(GLbyte c) {   // b = 8,  divisor 2^8 - 1  = 255
+            return (2 * static_cast<int>(c) + 1) / 255.0f;
+        }
+        constexpr GLfloat NormalizeSignedShort(GLshort c) { // b = 16, divisor 2^16 - 1 = 65535
+            return (2 * static_cast<int>(c) + 1) / 65535.0f;
+        }
+        constexpr GLfloat NormalizeSignedInt(GLint c) {     // b = 32, divisor 2^32 - 1 (double!)
+            return static_cast<GLfloat>((2.0 * static_cast<double>(c) + 1.0) / 4294967295.0);
+        }
+        constexpr GLfloat NormalizeUnsignedShort(GLushort c) { // b = 16
+            return static_cast<GLfloat>(c) / 65535.0f;
+        }
+        constexpr GLfloat NormalizeUnsignedInt(GLuint c) {     // b = 32 (double!)
+            return static_cast<GLfloat>(static_cast<double>(c) / 4294967295.0);
+        }
+        // (b = 8 unsigned normalization is VertexAttrib4Nub's  x * (1/255).)
+
+        // Sign-extend a `bits`-wide two's-complement field held in the low bits of `field`.
+        constexpr GLint SignExtendField(GLuint field, int bits) {
+            const GLuint signBit = 1u << (bits - 1);
+            return (field & signBit) ? static_cast<GLint>(field | (~0u << bits)) : static_cast<GLint>(field);
+        }
+
+        // Decode one GL_INT_/GL_UNSIGNED_INT_2_10_10_10_REV packed word into four float components.
+        // The _REV layout packs x in bits [0..9], y in [10..19], z in [20..29], w in [30..31]; x/y/z
+        // are 10-bit fields and w is a 2-bit field. Signed fields are two's-complement, and normalized
+        // conversion uses the GL 3.3 (2c+1)/(2^b-1) form (matching NormalizeSigned* above), NOT the
+        // GL 4.2 clamp form.
+        Array<GLfloat, 4> DecodePacked2101010(GLuint value, bool signedType, bool normalized) {
+            const GLuint fx = value & 0x3FFu;
+            const GLuint fy = (value >> 10) & 0x3FFu;
+            const GLuint fz = (value >> 20) & 0x3FFu;
+            const GLuint fw = (value >> 30) & 0x3u;
+            if (signedType) {
+                const GLint sx = SignExtendField(fx, 10);
+                const GLint sy = SignExtendField(fy, 10);
+                const GLint sz = SignExtendField(fz, 10);
+                const GLint sw = SignExtendField(fw, 2);
+                if (normalized) {
+                    return {(2 * sx + 1) / 1023.0f, (2 * sy + 1) / 1023.0f, (2 * sz + 1) / 1023.0f,
+                            (2 * sw + 1) / 3.0f};
+                }
+                return {static_cast<GLfloat>(sx), static_cast<GLfloat>(sy), static_cast<GLfloat>(sz),
+                        static_cast<GLfloat>(sw)};
+            }
+            if (normalized) {
+                return {fx / 1023.0f, fy / 1023.0f, fz / 1023.0f, fw / 3.0f};
+            }
+            return {static_cast<GLfloat>(fx), static_cast<GLfloat>(fy), static_cast<GLfloat>(fz),
+                    static_cast<GLfloat>(fw)};
+        }
+
+        static bool ValidateCurrentVertexAttribIndex(GLuint index, const char* funcName) {
+            // GL 3.3 core 2.7: VertexAttrib* sets the current value of ANY generic attribute,
+            // including index 0 - only an out-of-range index is an error (INVALID_VALUE).
+            // "Attribute 0 is immutable" was legacy immediate-mode lore; rejecting it broke GL
+            // CTS's per-case state reset, which writes vertexAttrib4f(0, 0,0,0,1) after every case.
+            static_cast<void>(funcName);
+            return VertexArrayImpl::ValidateVertexAttributeIndex(index);
+        }
+
+        static bool TryGetVertexAttribute(GLuint index, const MG_State::GLState::VertexAttribute** outAttr) {
+            if (!VertexArrayImpl::ValidateVertexAttributeIndex(index)) return false;
+
+            auto& vao = MG_State::pGLContext->GetBoundVertexArray();
+            if (!vao) {
+                MG_State::pGLContext->RecordError(
+                    ErrorCode::InvalidOperation,
+                    MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", __func__, "No vertex array object is bound."));
+                return false;
+            }
+
+            *outAttr = &vao->GetAttribute(index);
+            return true;
+        }
+
+        static bool IsCurrentVertexAttribQuery(GLenum pname) {
+            return pname == GL_CURRENT_VERTEX_ATTRIB;
+        }
+
+        static bool ValidateVertexBindingIndex(GLuint bindingindex, const char* funcName) {
+            // Bound by the same dynamic limit as attribute indices: the default attribute -> binding
+            // mapping is the identity, so a binding point the backend cannot address as an attribute
+            // would resolve into an attribute the backend must then reject on every draw. Real drivers
+            // likewise report MAX_VERTEX_ATTRIB_BINDINGS == MAX_VERTEX_ATTRIBS.
+            if (bindingindex >= VertexArrayImpl::GetMaxVertexAttribs()) {
+                MG_State::pGLContext->RecordError(
+                    ErrorCode::InvalidValue,
+                    MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", funcName,
+                                                 "bindingindex exceeds GL_MAX_VERTEX_ATTRIB_BINDINGS."));
+                return false;
+            }
+            return true;
+        }
+
+        static SharedPtr<MG_State::GLState::VertexArrayObject> GetBoundVertexArrayOrError(const char* funcName) {
+            auto& vao = MG_State::pGLContext->GetBoundVertexArray();
+            if (!vao) {
+                MG_State::pGLContext->RecordError(
+                    ErrorCode::InvalidOperation,
+                    MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", funcName, "No vertex array object is bound."));
+            }
+            return vao;
+        }
+
+        static bool ValidateVertexAttribPname(GLenum pname) {
+            switch (pname) {
+            case GL_VERTEX_ATTRIB_ARRAY_ENABLED:
+            case GL_VERTEX_ATTRIB_ARRAY_SIZE:
+            case GL_VERTEX_ATTRIB_ARRAY_STRIDE:
+            case GL_VERTEX_ATTRIB_ARRAY_TYPE:
+            case GL_VERTEX_ATTRIB_ARRAY_NORMALIZED:
+            case GL_CURRENT_VERTEX_ATTRIB:
+            case GL_VERTEX_ATTRIB_ARRAY_BUFFER_BINDING:
+            case GL_VERTEX_ATTRIB_ARRAY_INTEGER:
+            case GL_VERTEX_ATTRIB_ARRAY_DIVISOR:
+            case GL_VERTEX_ATTRIB_ARRAY_POINTER:
+                return true;
+            default:
+                MG_State::pGLContext->RecordError(
+                    ErrorCode::InvalidEnum,
+                    MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", __func__,
+                                                 "Unsupported vertex attrib pname: " + std::to_string(pname)));
+                return false;
+            }
+        }
+    } // namespace
+
     SharedPtr<MG_State::GLState::VertexArrayObject> GetNamedVertexArrayObject_State(GLuint vaobj,
                                                                                    const char* caller) {
         if (!VertexArrayImpl::ValidateVertexArrayName(vaobj)) return nullptr;
@@ -66,12 +205,12 @@ namespace MobileGL::MG_Impl::GLImpl {
         vao->EnableAttribute(index);
     }
 
-    // TODO: implement GL_BGRA support
     void VertexAttribIPointer_State(GLuint index, GLint size, GLenum type, GLsizei stride, const void* pointer) {
         if (!VertexArrayImpl::ValidateVertexAttributeIndex(index)) return;
 
         DataType dataType = MG_Util::ConvertGLEnumToDataType(type);
-        if (!VertexArrayImpl::ValidateVertexAttribPointerParams(index, size, dataType, stride)) return;
+        // Integer path: never normalized, never BGRA/packed (the validator rejects those).
+        if (!VertexArrayImpl::ValidateVertexAttribFormat(index, size, dataType, false, stride, true)) return;
 
         auto& vao = MG_State::pGLContext->GetBoundVertexArray();
         if (!vao) {
@@ -86,17 +225,17 @@ namespace MobileGL::MG_Impl::GLImpl {
 
         auto offset = reinterpret_cast<SizeT>(pointer);
 
-        vao->SetAttributeFormat(index, size, dataType, false, stride, offset, true);
+        vao->SetAttributeFormat(index, size, dataType, false, stride, offset, true, false);
         vao->BindAttributeBuffer(index, vbo);
     }
 
-    // TODO: implement GL_BGRA support
     void VertexAttribPointer_State(GLuint index, GLint size, GLenum type, GLboolean normalized, GLsizei stride,
                                    const void* pointer) {
         if (!VertexArrayImpl::ValidateVertexAttributeIndex(index)) return;
 
         DataType dataType = MG_Util::ConvertGLEnumToDataType(type);
-        if (!VertexArrayImpl::ValidateVertexAttribPointerParams(index, size, dataType, stride)) return;
+        if (!VertexArrayImpl::ValidateVertexAttribFormat(index, size, dataType, normalized == GL_TRUE, stride, false))
+            return;
 
         auto& vao = MG_State::pGLContext->GetBoundVertexArray();
         if (!vao) {
@@ -111,7 +250,11 @@ namespace MobileGL::MG_Impl::GLImpl {
 
         SizeT offset = reinterpret_cast<SizeT>(pointer);
 
-        vao->SetAttributeFormat(index, size, dataType, normalized, stride, offset, false);
+        // GL_BGRA is a 4-component reversed-order format; store 4 components and mark it BGRA so the
+        // backend can pick the reversed VkFormat / pass GL_BGRA through to a GLES driver.
+        const bool isBgra = (size == static_cast<GLint>(GL_BGRA));
+        const int effectiveSize = isBgra ? 4 : size;
+        vao->SetAttributeFormat(index, effectiveSize, dataType, normalized, stride, offset, false, isBgra);
         vao->BindAttributeBuffer(index, vbo);
     }
 
@@ -142,7 +285,9 @@ namespace MobileGL::MG_Impl::GLImpl {
             GLuint vao = arrays[i];
             if (vao == 0) continue;
 
-            if (!VertexArrayImpl::ValidateVertexArrayName(vao)) continue;
+            // GL 3.3 core 2.10: unknown names are silently ignored on delete; the shared bind-path
+            // validator would record INVALID_OPERATION instead.
+            if (!MG_State::pGLContext->ValidateVertexArrayName(vao)) continue;
 
             if (MG_State::pGLContext->GetBoundVertexArray() &&
                 MG_State::pGLContext->GetBoundVertexArray() == MG_State::pGLContext->GetVertexArrayObject(vao)) {
@@ -204,51 +349,83 @@ namespace MobileGL::MG_Impl::GLImpl {
         vao->GetIndexBufferBindingSlot().Bind(bufferObject);
     }
 
+    static void VertexBufferBinding_State(const SharedPtr<MG_State::GLState::VertexArrayObject>& vao,
+                                          GLuint bindingindex, GLuint buffer, GLintptr offset, GLsizei stride,
+                                          const char* caller) {
+        if (!ValidateVertexBindingIndex(bindingindex, caller)) return;
+        if (offset < 0 || stride < 0) {
+            MG_State::pGLContext->RecordError(
+                ErrorCode::InvalidValue,
+                MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", caller, "offset and stride must be non-negative."));
+            return;
+        }
+        auto bufferObject = GetVertexArrayBufferObject_State(buffer, caller);
+        if (buffer != 0 && !bufferObject) return;
+
+        vao->SetBindingBuffer(bindingindex, bufferObject, static_cast<SizeT>(offset), stride);
+    }
+
     void VertexArrayVertexBuffer_State(GLuint vaobj, GLuint bindingindex, GLuint buffer, GLintptr offset,
                                        GLsizei stride) {
         auto vao = GetNamedVertexArrayObject_State(vaobj, "VertexArrayVertexBuffer_State");
         if (!vao) return;
-        if (!VertexArrayImpl::ValidateVertexAttributeIndex(bindingindex)) return;
-        if (offset < 0 || stride < 0) {
-            MG_State::pGLContext->RecordError(
-                ErrorCode::InvalidValue,
-                MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", "VertexArrayVertexBuffer_State",
-                                             "offset and stride must be non-negative."));
-            return;
-        }
-        auto bufferObject = GetVertexArrayBufferObject_State(buffer, "VertexArrayVertexBuffer_State");
-        if (buffer != 0 && !bufferObject) return;
+        VertexBufferBinding_State(vao, bindingindex, buffer, offset, stride, "VertexArrayVertexBuffer_State");
+    }
 
-        const auto& attr = vao->GetAttribute(bindingindex);
-        vao->SetAttributeFormat(bindingindex, attr.Size, attr.Type, attr.Normalized, stride, static_cast<SizeT>(offset),
-                                attr.IsInteger);
-        vao->BindAttributeBuffer(bindingindex, bufferObject);
+    void VertexArrayVertexBuffers_State(GLuint vaobj, GLuint first, GLsizei count, const GLuint* buffers,
+                                        const GLintptr* offsets, const GLsizei* strides) {
+        auto vao = GetNamedVertexArrayObject_State(vaobj, "VertexArrayVertexBuffers_State");
+        if (!vao) return;
+        for (GLsizei i = 0; i < count; ++i) {
+            if (!buffers) {
+                VertexBufferBinding_State(vao, first + i, 0, 0, 16, "VertexArrayVertexBuffers_State");
+            } else {
+                VertexBufferBinding_State(vao, first + i, buffers[i], offsets ? offsets[i] : 0,
+                                          strides ? strides[i] : 16, "VertexArrayVertexBuffers_State");
+            }
+        }
+    }
+
+    static void VertexAttribFormatSeparate_State(const SharedPtr<MG_State::GLState::VertexArrayObject>& vao,
+                                                 GLuint attribindex, GLint size, GLenum type, GLboolean normalized,
+                                                 GLuint relativeoffset, Bool isInteger, const char* caller) {
+        if (!VertexArrayImpl::ValidateVertexAttributeIndex(attribindex)) return;
+
+        DataType dataType = MG_Util::ConvertGLEnumToDataType(type);
+        if (!VertexArrayImpl::ValidateVertexAttribPointerParams(attribindex, size, dataType, 0)) return;
+
+        vao->SetAttributeFormatSeparate(attribindex, size, dataType, normalized, isInteger, relativeoffset);
     }
 
     void VertexArrayAttribFormat_State(GLuint vaobj, GLuint attribindex, GLint size, GLenum type,
                                        GLboolean normalized, GLuint relativeoffset) {
         auto vao = GetNamedVertexArrayObject_State(vaobj, "VertexArrayAttribFormat_State");
         if (!vao) return;
-        if (!VertexArrayImpl::ValidateVertexAttributeIndex(attribindex)) return;
-
-        DataType dataType = MG_Util::ConvertGLEnumToDataType(type);
-        const auto& attr = vao->GetAttribute(attribindex);
-        if (!VertexArrayImpl::ValidateVertexAttribPointerParams(attribindex, size, dataType, attr.Stride)) return;
-
-        vao->SetAttributeFormat(attribindex, size, dataType, normalized, attr.Stride, relativeoffset, false);
+        VertexAttribFormatSeparate_State(vao, attribindex, size, type, normalized, relativeoffset, false,
+                                         "VertexArrayAttribFormat_State");
     }
 
     void VertexArrayAttribIFormat_State(GLuint vaobj, GLuint attribindex, GLint size, GLenum type,
                                         GLuint relativeoffset) {
         auto vao = GetNamedVertexArrayObject_State(vaobj, "VertexArrayAttribIFormat_State");
         if (!vao) return;
+        VertexAttribFormatSeparate_State(vao, attribindex, size, type, GL_FALSE, relativeoffset, true,
+                                         "VertexArrayAttribIFormat_State");
+    }
+
+    void VertexArrayAttribBinding_State(GLuint vaobj, GLuint attribindex, GLuint bindingindex) {
+        auto vao = GetNamedVertexArrayObject_State(vaobj, "VertexArrayAttribBinding_State");
+        if (!vao) return;
         if (!VertexArrayImpl::ValidateVertexAttributeIndex(attribindex)) return;
+        if (!ValidateVertexBindingIndex(bindingindex, "VertexArrayAttribBinding_State")) return;
+        vao->SetAttributeBinding(attribindex, bindingindex);
+    }
 
-        DataType dataType = MG_Util::ConvertGLEnumToDataType(type);
-        const auto& attr = vao->GetAttribute(attribindex);
-        if (!VertexArrayImpl::ValidateVertexAttribPointerParams(attribindex, size, dataType, attr.Stride)) return;
-
-        vao->SetAttributeFormat(attribindex, size, dataType, false, attr.Stride, relativeoffset, true);
+    void VertexArrayBindingDivisor_State(GLuint vaobj, GLuint bindingindex, GLuint divisor) {
+        auto vao = GetNamedVertexArrayObject_State(vaobj, "VertexArrayBindingDivisor_State");
+        if (!vao) return;
+        if (!ValidateVertexBindingIndex(bindingindex, "VertexArrayBindingDivisor_State")) return;
+        vao->SetBindingDivisor(bindingindex, divisor);
     }
 
     GLboolean IsVertexArray_State(GLuint array) {
@@ -271,6 +448,582 @@ namespace MobileGL::MG_Impl::GLImpl {
     }
 
     /* @INSERTION_POINT:FUNCTION_IMPLEMENTATION@ */
+    void VertexAttrib1f(GLuint index, GLfloat x) {
+        if (!ValidateCurrentVertexAttribIndex(index, __func__)) return;
+        MG_State::pGLContext->SetCurrentVertexAttributeFloat(index, {x, 0.0f, 0.0f, 1.0f});
+    }
+
+    void VertexAttrib1fv(GLuint index, const GLfloat* v) {
+        if (!v) {
+            MG_State::pGLContext->RecordError(
+                ErrorCode::InvalidValue,
+                MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", __func__, "value pointer cannot be null."));
+            return;
+        }
+        VertexAttrib1f(index, v[0]);
+    }
+
+    void VertexAttrib2f(GLuint index, GLfloat x, GLfloat y) {
+        if (!ValidateCurrentVertexAttribIndex(index, __func__)) return;
+        MG_State::pGLContext->SetCurrentVertexAttributeFloat(index, {x, y, 0.0f, 1.0f});
+    }
+
+    void VertexAttrib2fv(GLuint index, const GLfloat* v) {
+        if (!v) {
+            MG_State::pGLContext->RecordError(
+                ErrorCode::InvalidValue,
+                MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", __func__, "value pointer cannot be null."));
+            return;
+        }
+        VertexAttrib2f(index, v[0], v[1]);
+    }
+
+    void VertexAttrib3f(GLuint index, GLfloat x, GLfloat y, GLfloat z) {
+        if (!ValidateCurrentVertexAttribIndex(index, __func__)) return;
+        MG_State::pGLContext->SetCurrentVertexAttributeFloat(index, {x, y, z, 1.0f});
+    }
+
+    void VertexAttrib3fv(GLuint index, const GLfloat* v) {
+        if (!v) {
+            MG_State::pGLContext->RecordError(
+                ErrorCode::InvalidValue,
+                MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", __func__, "value pointer cannot be null."));
+            return;
+        }
+        VertexAttrib3f(index, v[0], v[1], v[2]);
+    }
+
+    void VertexAttrib4f(GLuint index, GLfloat x, GLfloat y, GLfloat z, GLfloat w) {
+        if (!ValidateCurrentVertexAttribIndex(index, __func__)) return;
+        MG_State::pGLContext->SetCurrentVertexAttributeFloat(index, {x, y, z, w});
+    }
+
+    void VertexAttrib4fv(GLuint index, const GLfloat* v) {
+        if (!v) {
+            MG_State::pGLContext->RecordError(
+                ErrorCode::InvalidValue,
+                MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", __func__, "value pointer cannot be null."));
+            return;
+        }
+        VertexAttrib4f(index, v[0], v[1], v[2], v[3]);
+    }
+
+    void VertexAttribI4i(GLuint index, GLint x, GLint y, GLint z, GLint w) {
+        if (!ValidateCurrentVertexAttribIndex(index, __func__)) return;
+        MG_State::pGLContext->SetCurrentVertexAttributeInt(index, {x, y, z, w});
+    }
+
+    void VertexAttribI4ui(GLuint index, GLuint x, GLuint y, GLuint z, GLuint w) {
+        if (!ValidateCurrentVertexAttribIndex(index, __func__)) return;
+        MG_State::pGLContext->SetCurrentVertexAttributeUint(index, {x, y, z, w});
+    }
+
+    void VertexAttribI4iv(GLuint index, const GLint* v) {
+        if (!v) {
+            MG_State::pGLContext->RecordError(
+                ErrorCode::InvalidValue,
+                MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", __func__, "value pointer cannot be null."));
+            return;
+        }
+        VertexAttribI4i(index, v[0], v[1], v[2], v[3]);
+    }
+
+    void VertexAttribI4uiv(GLuint index, const GLuint* v) {
+        if (!v) {
+            MG_State::pGLContext->RecordError(
+                ErrorCode::InvalidValue,
+                MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", __func__, "value pointer cannot be null."));
+            return;
+        }
+        VertexAttribI4ui(index, v[0], v[1], v[2], v[3]);
+    }
+
+    // Shared body for glVertexAttribP{1,2,3,4}ui(v). These set the CURRENT generic vertex attribute
+    // value (they are the packed members of the immediate VertexAttrib* family, not the array-format
+    // path), so they take the float current-value funnel. The single packed word is always fully
+    // decoded, but only the first `componentCount` components are written; the rest keep the generic
+    // attribute defaults (0, 0, 0, 1). type must be one of the two 2_10_10_10_REV packed enums.
+    static void VertexAttribP_Common(GLuint index, GLenum type, GLboolean normalized, GLuint value,
+                                     int componentCount, const char* funcName) {
+        if (!ValidateCurrentVertexAttribIndex(index, funcName)) return;
+
+        bool signedType;
+        if (type == GL_INT_2_10_10_10_REV) {
+            signedType = true;
+        } else if (type == GL_UNSIGNED_INT_2_10_10_10_REV) {
+            signedType = false;
+        } else {
+            MG_State::pGLContext->RecordError(
+                ErrorCode::InvalidEnum,
+                MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", funcName,
+                                             "glVertexAttribP*ui type must be GL_INT_2_10_10_10_REV or "
+                                             "GL_UNSIGNED_INT_2_10_10_10_REV; got " +
+                                                 MG_Util::ConvertGLEnumToString(type) + "."));
+            return;
+        }
+
+        const Array<GLfloat, 4> decoded = DecodePacked2101010(value, signedType, normalized == GL_TRUE);
+        Array<GLfloat, 4> out = {0.0f, 0.0f, 0.0f, 1.0f};
+        for (int i = 0; i < componentCount; ++i) out[i] = decoded[i];
+        MG_State::pGLContext->SetCurrentVertexAttributeFloat(index, out);
+    }
+
+    void VertexAttribP1ui(GLuint index, GLenum type, GLboolean normalized, GLuint value) {
+        VertexAttribP_Common(index, type, normalized, value, 1, __func__);
+    }
+    void VertexAttribP2ui(GLuint index, GLenum type, GLboolean normalized, GLuint value) {
+        VertexAttribP_Common(index, type, normalized, value, 2, __func__);
+    }
+    void VertexAttribP3ui(GLuint index, GLenum type, GLboolean normalized, GLuint value) {
+        VertexAttribP_Common(index, type, normalized, value, 3, __func__);
+    }
+    void VertexAttribP4ui(GLuint index, GLenum type, GLboolean normalized, GLuint value) {
+        VertexAttribP_Common(index, type, normalized, value, 4, __func__);
+    }
+
+    // The *uiv forms dereference a pointer to a SINGLE packed GLuint (never an array of N words).
+    void VertexAttribP1uiv(GLuint index, GLenum type, GLboolean normalized, const GLuint* value) {
+        if (!value) {
+            MG_State::pGLContext->RecordError(
+                ErrorCode::InvalidValue,
+                MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", __func__, "value pointer cannot be null."));
+            return;
+        }
+        VertexAttribP_Common(index, type, normalized, value[0], 1, __func__);
+    }
+    void VertexAttribP2uiv(GLuint index, GLenum type, GLboolean normalized, const GLuint* value) {
+        if (!value) {
+            MG_State::pGLContext->RecordError(
+                ErrorCode::InvalidValue,
+                MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", __func__, "value pointer cannot be null."));
+            return;
+        }
+        VertexAttribP_Common(index, type, normalized, value[0], 2, __func__);
+    }
+    void VertexAttribP3uiv(GLuint index, GLenum type, GLboolean normalized, const GLuint* value) {
+        if (!value) {
+            MG_State::pGLContext->RecordError(
+                ErrorCode::InvalidValue,
+                MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", __func__, "value pointer cannot be null."));
+            return;
+        }
+        VertexAttribP_Common(index, type, normalized, value[0], 3, __func__);
+    }
+    void VertexAttribP4uiv(GLuint index, GLenum type, GLboolean normalized, const GLuint* value) {
+        if (!value) {
+            MG_State::pGLContext->RecordError(
+                ErrorCode::InvalidValue,
+                MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", __func__, "value pointer cannot be null."));
+            return;
+        }
+        VertexAttribP_Common(index, type, normalized, value[0], 4, __func__);
+    }
+
+    void VertexAttrib4Nub(GLuint index, GLubyte x, GLubyte y, GLubyte z, GLubyte w) {
+        constexpr float kInv255 = 1.0f / 255.0f;
+        VertexAttrib4f(index, x * kInv255, y * kInv255, z * kInv255, w * kInv255);
+    }
+
+    void VertexAttrib4Nubv(GLuint index, const GLubyte* v) {
+        if (!v) {
+            MG_State::pGLContext->RecordError(
+                ErrorCode::InvalidValue,
+                MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", __func__, "value pointer cannot be null."));
+            return;
+        }
+        VertexAttrib4Nub(index, v[0], v[1], v[2], v[3]);
+    }
+
+    void VertexAttrib4ubv(GLuint index, const GLubyte* v) {
+        if (!v) {
+            MG_State::pGLContext->RecordError(
+                ErrorCode::InvalidValue,
+                MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", __func__, "value pointer cannot be null."));
+            return;
+        }
+        VertexAttrib4f(index, static_cast<GLfloat>(v[0]), static_cast<GLfloat>(v[1]), static_cast<GLfloat>(v[2]),
+                       static_cast<GLfloat>(v[3]));
+    }
+
+    // ---- Stubbed glVertexAttrib* current-value setters, funnelled into the primitives above -------
+    // These add ONLY a null-pointer guard: index validation (incl. the index-0 rejection) is inherited
+    // from VertexAttrib4f / VertexAttribI4i / VertexAttribI4ui via ValidateCurrentVertexAttribIndex, so
+    // the funnels must not re-validate it. Component fill matches the primitives: unspecified middle
+    // components are 0, unspecified w is 1 (integer 1 for the I* forms).
+#define MG_ATTRIB_NULL_GUARD(ptr)                                                                                      \
+    if (!(ptr)) {                                                                                                      \
+        MG_State::pGLContext->RecordError(                                                                            \
+            ErrorCode::InvalidValue,                                                                                   \
+            MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", __func__, "value pointer cannot be null."));               \
+        return;                                                                                                        \
+    }
+
+    // Family A -- GLdouble, value-preserving narrowing to float.
+    void VertexAttrib1d(GLuint index, GLdouble x) { VertexAttrib4f(index, static_cast<GLfloat>(x), 0.0f, 0.0f, 1.0f); }
+    void VertexAttrib2d(GLuint index, GLdouble x, GLdouble y) {
+        VertexAttrib4f(index, static_cast<GLfloat>(x), static_cast<GLfloat>(y), 0.0f, 1.0f);
+    }
+    void VertexAttrib3d(GLuint index, GLdouble x, GLdouble y, GLdouble z) {
+        VertexAttrib4f(index, static_cast<GLfloat>(x), static_cast<GLfloat>(y), static_cast<GLfloat>(z), 1.0f);
+    }
+    void VertexAttrib4d(GLuint index, GLdouble x, GLdouble y, GLdouble z, GLdouble w) {
+        VertexAttrib4f(index, static_cast<GLfloat>(x), static_cast<GLfloat>(y), static_cast<GLfloat>(z),
+                       static_cast<GLfloat>(w));
+    }
+    void VertexAttrib1dv(GLuint index, const GLdouble* v) { MG_ATTRIB_NULL_GUARD(v) VertexAttrib1d(index, v[0]); }
+    void VertexAttrib2dv(GLuint index, const GLdouble* v) { MG_ATTRIB_NULL_GUARD(v) VertexAttrib2d(index, v[0], v[1]); }
+    void VertexAttrib3dv(GLuint index, const GLdouble* v) {
+        MG_ATTRIB_NULL_GUARD(v) VertexAttrib3d(index, v[0], v[1], v[2]);
+    }
+    void VertexAttrib4dv(GLuint index, const GLdouble* v) {
+        MG_ATTRIB_NULL_GUARD(v) VertexAttrib4d(index, v[0], v[1], v[2], v[3]);
+    }
+
+    // Family A -- GLshort, value-preserving (sign kept), NOT normalized.
+    void VertexAttrib1s(GLuint index, GLshort x) { VertexAttrib4f(index, static_cast<GLfloat>(x), 0.0f, 0.0f, 1.0f); }
+    void VertexAttrib2s(GLuint index, GLshort x, GLshort y) {
+        VertexAttrib4f(index, static_cast<GLfloat>(x), static_cast<GLfloat>(y), 0.0f, 1.0f);
+    }
+    void VertexAttrib3s(GLuint index, GLshort x, GLshort y, GLshort z) {
+        VertexAttrib4f(index, static_cast<GLfloat>(x), static_cast<GLfloat>(y), static_cast<GLfloat>(z), 1.0f);
+    }
+    void VertexAttrib4s(GLuint index, GLshort x, GLshort y, GLshort z, GLshort w) {
+        VertexAttrib4f(index, static_cast<GLfloat>(x), static_cast<GLfloat>(y), static_cast<GLfloat>(z),
+                       static_cast<GLfloat>(w));
+    }
+    void VertexAttrib1sv(GLuint index, const GLshort* v) { MG_ATTRIB_NULL_GUARD(v) VertexAttrib1s(index, v[0]); }
+    void VertexAttrib2sv(GLuint index, const GLshort* v) { MG_ATTRIB_NULL_GUARD(v) VertexAttrib2s(index, v[0], v[1]); }
+    void VertexAttrib3sv(GLuint index, const GLshort* v) {
+        MG_ATTRIB_NULL_GUARD(v) VertexAttrib3s(index, v[0], v[1], v[2]);
+    }
+    void VertexAttrib4sv(GLuint index, const GLshort* v) {
+        MG_ATTRIB_NULL_GUARD(v) VertexAttrib4s(index, v[0], v[1], v[2], v[3]);
+    }
+
+    // Family A -- 4-component *v with no scalar sibling, value-preserving. NOT the normalized 4N* forms.
+    void VertexAttrib4bv(GLuint index, const GLbyte* v) {
+        MG_ATTRIB_NULL_GUARD(v)
+        VertexAttrib4f(index, static_cast<GLfloat>(v[0]), static_cast<GLfloat>(v[1]), static_cast<GLfloat>(v[2]),
+                       static_cast<GLfloat>(v[3]));
+    }
+    void VertexAttrib4iv(GLuint index, const GLint* v) {
+        MG_ATTRIB_NULL_GUARD(v)
+        VertexAttrib4f(index, static_cast<GLfloat>(v[0]), static_cast<GLfloat>(v[1]), static_cast<GLfloat>(v[2]),
+                       static_cast<GLfloat>(v[3]));
+    }
+    void VertexAttrib4uiv(GLuint index, const GLuint* v) {
+        MG_ATTRIB_NULL_GUARD(v)
+        VertexAttrib4f(index, static_cast<GLfloat>(v[0]), static_cast<GLfloat>(v[1]), static_cast<GLfloat>(v[2]),
+                       static_cast<GLfloat>(v[3]));
+    }
+    void VertexAttrib4usv(GLuint index, const GLushort* v) {
+        MG_ATTRIB_NULL_GUARD(v)
+        VertexAttrib4f(index, static_cast<GLfloat>(v[0]), static_cast<GLfloat>(v[1]), static_cast<GLfloat>(v[2]),
+                       static_cast<GLfloat>(v[3]));
+    }
+
+    // Family B -- normalized 4N* forms (GL 3.3 Core Eq 2.1/2.2 via the Normalize* helpers).
+    void VertexAttrib4Nbv(GLuint index, const GLbyte* v) {
+        MG_ATTRIB_NULL_GUARD(v)
+        VertexAttrib4f(index, NormalizeSignedByte(v[0]), NormalizeSignedByte(v[1]), NormalizeSignedByte(v[2]),
+                       NormalizeSignedByte(v[3]));
+    }
+    void VertexAttrib4Nsv(GLuint index, const GLshort* v) {
+        MG_ATTRIB_NULL_GUARD(v)
+        VertexAttrib4f(index, NormalizeSignedShort(v[0]), NormalizeSignedShort(v[1]), NormalizeSignedShort(v[2]),
+                       NormalizeSignedShort(v[3]));
+    }
+    void VertexAttrib4Niv(GLuint index, const GLint* v) {
+        MG_ATTRIB_NULL_GUARD(v)
+        VertexAttrib4f(index, NormalizeSignedInt(v[0]), NormalizeSignedInt(v[1]), NormalizeSignedInt(v[2]),
+                       NormalizeSignedInt(v[3]));
+    }
+    void VertexAttrib4Nusv(GLuint index, const GLushort* v) {
+        MG_ATTRIB_NULL_GUARD(v)
+        VertexAttrib4f(index, NormalizeUnsignedShort(v[0]), NormalizeUnsignedShort(v[1]),
+                       NormalizeUnsignedShort(v[2]), NormalizeUnsignedShort(v[3]));
+    }
+    void VertexAttrib4Nuiv(GLuint index, const GLuint* v) {
+        MG_ATTRIB_NULL_GUARD(v)
+        VertexAttrib4f(index, NormalizeUnsignedInt(v[0]), NormalizeUnsignedInt(v[1]), NormalizeUnsignedInt(v[2]),
+                       NormalizeUnsignedInt(v[3]));
+    }
+
+    // Family C -- pure integer forms. Signed -> VertexAttribI4i (sign-extend), unsigned ->
+    // VertexAttribI4ui (zero-extend). w defaults to the integer 1 / 1u. Never touches the float view.
+    void VertexAttribI1i(GLuint index, GLint x) { VertexAttribI4i(index, x, 0, 0, 1); }
+    void VertexAttribI2i(GLuint index, GLint x, GLint y) { VertexAttribI4i(index, x, y, 0, 1); }
+    void VertexAttribI3i(GLuint index, GLint x, GLint y, GLint z) { VertexAttribI4i(index, x, y, z, 1); }
+    void VertexAttribI1ui(GLuint index, GLuint x) { VertexAttribI4ui(index, x, 0u, 0u, 1u); }
+    void VertexAttribI2ui(GLuint index, GLuint x, GLuint y) { VertexAttribI4ui(index, x, y, 0u, 1u); }
+    void VertexAttribI3ui(GLuint index, GLuint x, GLuint y, GLuint z) { VertexAttribI4ui(index, x, y, z, 1u); }
+    void VertexAttribI1iv(GLuint index, const GLint* v) { MG_ATTRIB_NULL_GUARD(v) VertexAttribI1i(index, v[0]); }
+    void VertexAttribI2iv(GLuint index, const GLint* v) { MG_ATTRIB_NULL_GUARD(v) VertexAttribI2i(index, v[0], v[1]); }
+    void VertexAttribI3iv(GLuint index, const GLint* v) {
+        MG_ATTRIB_NULL_GUARD(v) VertexAttribI3i(index, v[0], v[1], v[2]);
+    }
+    void VertexAttribI1uiv(GLuint index, const GLuint* v) { MG_ATTRIB_NULL_GUARD(v) VertexAttribI1ui(index, v[0]); }
+    void VertexAttribI2uiv(GLuint index, const GLuint* v) {
+        MG_ATTRIB_NULL_GUARD(v) VertexAttribI2ui(index, v[0], v[1]);
+    }
+    void VertexAttribI3uiv(GLuint index, const GLuint* v) {
+        MG_ATTRIB_NULL_GUARD(v) VertexAttribI3ui(index, v[0], v[1], v[2]);
+    }
+    void VertexAttribI4bv(GLuint index, const GLbyte* v) {
+        MG_ATTRIB_NULL_GUARD(v)
+        VertexAttribI4i(index, static_cast<GLint>(v[0]), static_cast<GLint>(v[1]), static_cast<GLint>(v[2]),
+                        static_cast<GLint>(v[3]));
+    }
+    void VertexAttribI4sv(GLuint index, const GLshort* v) {
+        MG_ATTRIB_NULL_GUARD(v)
+        VertexAttribI4i(index, static_cast<GLint>(v[0]), static_cast<GLint>(v[1]), static_cast<GLint>(v[2]),
+                        static_cast<GLint>(v[3]));
+    }
+    void VertexAttribI4ubv(GLuint index, const GLubyte* v) {
+        MG_ATTRIB_NULL_GUARD(v)
+        VertexAttribI4ui(index, static_cast<GLuint>(v[0]), static_cast<GLuint>(v[1]), static_cast<GLuint>(v[2]),
+                         static_cast<GLuint>(v[3]));
+    }
+    void VertexAttribI4usv(GLuint index, const GLushort* v) {
+        MG_ATTRIB_NULL_GUARD(v)
+        VertexAttribI4ui(index, static_cast<GLuint>(v[0]), static_cast<GLuint>(v[1]), static_cast<GLuint>(v[2]),
+                         static_cast<GLuint>(v[3]));
+    }
+#undef MG_ATTRIB_NULL_GUARD
+
+    void GetVertexAttribfv(GLuint index, GLenum pname, GLfloat* params) {
+        if (!params) {
+            MG_State::pGLContext->RecordError(
+                ErrorCode::InvalidValue,
+                MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", __func__, "params pointer cannot be null."));
+            return;
+        }
+        // GL_CURRENT_VERTEX_ATTRIB is context state and returns before TryGetVertexAttribute, so the
+        // index bound has to be enforced up front or an out-of-range index reads past the array.
+        if (!VertexArrayImpl::ValidateVertexAttributeIndex(index)) return;
+        if (!ValidateVertexAttribPname(pname)) return;
+
+        if (IsCurrentVertexAttribQuery(pname)) {
+            const auto& current = MG_State::pGLContext->GetCurrentVertexAttribute(index);
+            params[0] = current.floatValue[0];
+            params[1] = current.floatValue[1];
+            params[2] = current.floatValue[2];
+            params[3] = current.floatValue[3];
+            return;
+        }
+
+        const MG_State::GLState::VertexAttribute* attr = nullptr;
+        if (!TryGetVertexAttribute(index, &attr)) return;
+
+        switch (pname) {
+        case GL_VERTEX_ATTRIB_ARRAY_ENABLED:
+            params[0] = attr->Enabled ? 1.0f : 0.0f;
+            return;
+        case GL_VERTEX_ATTRIB_ARRAY_SIZE:
+            params[0] = static_cast<GLfloat>(attr->Size);
+            return;
+        case GL_VERTEX_ATTRIB_ARRAY_STRIDE:
+            params[0] = static_cast<GLfloat>(attr->Stride);
+            return;
+        case GL_VERTEX_ATTRIB_ARRAY_TYPE:
+            params[0] = static_cast<GLfloat>(MG_Util::ConvertDataTypeToGLEnum(attr->Type));
+            return;
+        case GL_VERTEX_ATTRIB_ARRAY_NORMALIZED:
+            params[0] = attr->Normalized ? 1.0f : 0.0f;
+            return;
+        case GL_VERTEX_ATTRIB_ARRAY_BUFFER_BINDING:
+            params[0] = attr->Buffer ? static_cast<GLfloat>(attr->Buffer->GetExternalIndex()) : 0.0f;
+            return;
+        case GL_VERTEX_ATTRIB_ARRAY_INTEGER:
+            params[0] = attr->IsInteger ? 1.0f : 0.0f;
+            return;
+        case GL_VERTEX_ATTRIB_ARRAY_DIVISOR:
+            params[0] = static_cast<GLfloat>(attr->Divisor);
+            return;
+        default:
+            MG_State::pGLContext->RecordError(
+                ErrorCode::InvalidEnum,
+                MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", __func__,
+                                             "Unsupported float vertex attrib pname: " + std::to_string(pname)));
+            return;
+        }
+    }
+
+    // The double query mirrors GetVertexAttribfv exactly (it is the other float-domain getter): the
+    // current value is read from the float view, and float -> double widening is lossless.
+    void GetVertexAttribdv(GLuint index, GLenum pname, GLdouble* params) {
+        if (!params) {
+            MG_State::pGLContext->RecordError(
+                ErrorCode::InvalidValue,
+                MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", __func__, "params pointer cannot be null."));
+            return;
+        }
+        // GL_CURRENT_VERTEX_ATTRIB is context state and returns before TryGetVertexAttribute, so the
+        // index bound has to be enforced up front or an out-of-range index reads past the array.
+        if (!VertexArrayImpl::ValidateVertexAttributeIndex(index)) return;
+        if (!ValidateVertexAttribPname(pname)) return;
+
+        if (IsCurrentVertexAttribQuery(pname)) {
+            const auto& current = MG_State::pGLContext->GetCurrentVertexAttribute(index);
+            params[0] = static_cast<GLdouble>(current.floatValue[0]);
+            params[1] = static_cast<GLdouble>(current.floatValue[1]);
+            params[2] = static_cast<GLdouble>(current.floatValue[2]);
+            params[3] = static_cast<GLdouble>(current.floatValue[3]);
+            return;
+        }
+
+        const MG_State::GLState::VertexAttribute* attr = nullptr;
+        if (!TryGetVertexAttribute(index, &attr)) return;
+
+        switch (pname) {
+        case GL_VERTEX_ATTRIB_ARRAY_ENABLED:
+            params[0] = attr->Enabled ? 1.0 : 0.0;
+            return;
+        case GL_VERTEX_ATTRIB_ARRAY_SIZE:
+            params[0] = static_cast<GLdouble>(attr->Size);
+            return;
+        case GL_VERTEX_ATTRIB_ARRAY_STRIDE:
+            params[0] = static_cast<GLdouble>(attr->Stride);
+            return;
+        case GL_VERTEX_ATTRIB_ARRAY_TYPE:
+            params[0] = static_cast<GLdouble>(MG_Util::ConvertDataTypeToGLEnum(attr->Type));
+            return;
+        case GL_VERTEX_ATTRIB_ARRAY_NORMALIZED:
+            params[0] = attr->Normalized ? 1.0 : 0.0;
+            return;
+        case GL_VERTEX_ATTRIB_ARRAY_BUFFER_BINDING:
+            params[0] = attr->Buffer ? static_cast<GLdouble>(attr->Buffer->GetExternalIndex()) : 0.0;
+            return;
+        case GL_VERTEX_ATTRIB_ARRAY_INTEGER:
+            params[0] = attr->IsInteger ? 1.0 : 0.0;
+            return;
+        case GL_VERTEX_ATTRIB_ARRAY_DIVISOR:
+            params[0] = static_cast<GLdouble>(attr->Divisor);
+            return;
+        default:
+            MG_State::pGLContext->RecordError(
+                ErrorCode::InvalidEnum,
+                MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", __func__,
+                                             "Unsupported double vertex attrib pname: " + std::to_string(pname)));
+            return;
+        }
+    }
+
+    void GetVertexAttribiv(GLuint index, GLenum pname, GLint* params) {
+        if (!params) {
+            MG_State::pGLContext->RecordError(
+                ErrorCode::InvalidValue,
+                MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", __func__, "params pointer cannot be null."));
+            return;
+        }
+        if (!VertexArrayImpl::ValidateVertexAttributeIndex(index)) return;
+        if (!ValidateVertexAttribPname(pname)) return;
+
+        if (IsCurrentVertexAttribQuery(pname)) {
+            const auto& current = MG_State::pGLContext->GetCurrentVertexAttribute(index);
+            params[0] = current.intValue[0];
+            params[1] = current.intValue[1];
+            params[2] = current.intValue[2];
+            params[3] = current.intValue[3];
+            return;
+        }
+
+        const MG_State::GLState::VertexAttribute* attr = nullptr;
+        if (!TryGetVertexAttribute(index, &attr)) return;
+
+        switch (pname) {
+        case GL_VERTEX_ATTRIB_ARRAY_ENABLED:
+            params[0] = attr->Enabled ? GL_TRUE : GL_FALSE;
+            return;
+        case GL_VERTEX_ATTRIB_ARRAY_SIZE:
+            params[0] = attr->Size;
+            return;
+        case GL_VERTEX_ATTRIB_ARRAY_STRIDE:
+            params[0] = attr->Stride;
+            return;
+        case GL_VERTEX_ATTRIB_ARRAY_TYPE:
+            params[0] = static_cast<GLint>(MG_Util::ConvertDataTypeToGLEnum(attr->Type));
+            return;
+        case GL_VERTEX_ATTRIB_ARRAY_NORMALIZED:
+            params[0] = attr->Normalized ? GL_TRUE : GL_FALSE;
+            return;
+        case GL_VERTEX_ATTRIB_ARRAY_BUFFER_BINDING:
+            params[0] = attr->Buffer ? static_cast<GLint>(attr->Buffer->GetExternalIndex()) : 0;
+            return;
+        case GL_VERTEX_ATTRIB_ARRAY_INTEGER:
+            params[0] = attr->IsInteger ? GL_TRUE : GL_FALSE;
+            return;
+        case GL_VERTEX_ATTRIB_ARRAY_DIVISOR:
+            params[0] = static_cast<GLint>(attr->Divisor);
+            return;
+        default:
+            MG_State::pGLContext->RecordError(
+                ErrorCode::InvalidEnum,
+                MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", __func__,
+                                             "Unsupported integer vertex attrib pname: " + std::to_string(pname)));
+            return;
+        }
+    }
+
+    void GetVertexAttribPointerv(GLuint index, GLenum pname, void** pointer) {
+        if (!pointer) {
+            MG_State::pGLContext->RecordError(
+                ErrorCode::InvalidValue,
+                MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", __func__, "pointer cannot be null."));
+            return;
+        }
+        if (!VertexArrayImpl::ValidateVertexAttributeIndex(index)) return;
+        if (pname != GL_VERTEX_ATTRIB_ARRAY_POINTER) {
+            MG_State::pGLContext->RecordError(
+                ErrorCode::InvalidEnum,
+                MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", __func__,
+                                             "pname must be GL_VERTEX_ATTRIB_ARRAY_POINTER."));
+            return;
+        }
+
+        auto& vao = MG_State::pGLContext->GetBoundVertexArray();
+        if (!vao) {
+            MG_State::pGLContext->RecordError(
+                ErrorCode::InvalidOperation,
+                MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", __func__, "No vertex array object is bound."));
+            return;
+        }
+
+        const auto& attr = vao->GetAttribute(index);
+        *pointer = reinterpret_cast<void*>(attr.Offset);
+    }
+
+    void GetVertexAttribIiv(GLuint index, GLenum pname, GLint* params) {
+        GetVertexAttribiv(index, pname, params);
+    }
+
+    void GetVertexAttribIuiv(GLuint index, GLenum pname, GLuint* params) {
+        if (!params) {
+            MG_State::pGLContext->RecordError(
+                ErrorCode::InvalidValue,
+                MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", __func__, "params pointer cannot be null."));
+            return;
+        }
+        if (!VertexArrayImpl::ValidateVertexAttributeIndex(index)) return;
+        if (!ValidateVertexAttribPname(pname)) return;
+
+        if (IsCurrentVertexAttribQuery(pname)) {
+            const auto& current = MG_State::pGLContext->GetCurrentVertexAttribute(index);
+            params[0] = current.uintValue[0];
+            params[1] = current.uintValue[1];
+            params[2] = current.uintValue[2];
+            params[3] = current.uintValue[3];
+            return;
+        }
+
+        GLint signedParams[4] = {};
+        GetVertexAttribiv(index, pname, signedParams);
+        params[0] = static_cast<GLuint>(signedParams[0]);
+        params[1] = static_cast<GLuint>(signedParams[1]);
+        params[2] = static_cast<GLuint>(signedParams[2]);
+        params[3] = static_cast<GLuint>(signedParams[3]);
+    }
+
     void CreateVertexArrays(GLsizei n, GLuint* arrays) {
         CreateVertexArrays_State(n, arrays);
     }
@@ -300,6 +1053,68 @@ namespace MobileGL::MG_Impl::GLImpl {
         VertexArrayAttribIFormat_State(vaobj, attribindex, size, type, relativeoffset);
     }
 
+    void VertexArrayAttribBinding(GLuint vaobj, GLuint attribindex, GLuint bindingindex) {
+        VertexArrayAttribBinding_State(vaobj, attribindex, bindingindex);
+    }
+
+    void VertexArrayBindingDivisor(GLuint vaobj, GLuint bindingindex, GLuint divisor) {
+        VertexArrayBindingDivisor_State(vaobj, bindingindex, divisor);
+    }
+
+    void VertexArrayVertexBuffers(GLuint vaobj, GLuint first, GLsizei count, const GLuint* buffers,
+                                  const GLintptr* offsets, const GLsizei* strides) {
+        VertexArrayVertexBuffers_State(vaobj, first, count, buffers, offsets, strides);
+    }
+
+    void BindVertexBuffer(GLuint bindingindex, GLuint buffer, GLintptr offset, GLsizei stride) {
+        auto vao = GetBoundVertexArrayOrError("BindVertexBuffer");
+        if (!vao) return;
+        VertexBufferBinding_State(vao, bindingindex, buffer, offset, stride, "BindVertexBuffer");
+    }
+
+    void BindVertexBuffers(GLuint first, GLsizei count, const GLuint* buffers, const GLintptr* offsets,
+                           const GLsizei* strides) {
+        auto vao = GetBoundVertexArrayOrError("BindVertexBuffers");
+        if (!vao) return;
+        for (GLsizei i = 0; i < count; ++i) {
+            if (!buffers) {
+                VertexBufferBinding_State(vao, first + i, 0, 0, 16, "BindVertexBuffers");
+            } else {
+                VertexBufferBinding_State(vao, first + i, buffers[i], offsets ? offsets[i] : 0,
+                                          strides ? strides[i] : 16, "BindVertexBuffers");
+            }
+        }
+    }
+
+    void VertexAttribFormat(GLuint attribindex, GLint size, GLenum type, GLboolean normalized, GLuint relativeoffset) {
+        auto vao = GetBoundVertexArrayOrError("VertexAttribFormat");
+        if (!vao) return;
+        VertexAttribFormatSeparate_State(vao, attribindex, size, type, normalized, relativeoffset, false,
+                                         "VertexAttribFormat");
+    }
+
+    void VertexAttribIFormat(GLuint attribindex, GLint size, GLenum type, GLuint relativeoffset) {
+        auto vao = GetBoundVertexArrayOrError("VertexAttribIFormat");
+        if (!vao) return;
+        VertexAttribFormatSeparate_State(vao, attribindex, size, type, GL_FALSE, relativeoffset, true,
+                                         "VertexAttribIFormat");
+    }
+
+    void VertexAttribBinding(GLuint attribindex, GLuint bindingindex) {
+        auto vao = GetBoundVertexArrayOrError("VertexAttribBinding");
+        if (!vao) return;
+        if (!VertexArrayImpl::ValidateVertexAttributeIndex(attribindex)) return;
+        if (!ValidateVertexBindingIndex(bindingindex, "VertexAttribBinding")) return;
+        vao->SetAttributeBinding(attribindex, bindingindex);
+    }
+
+    void VertexBindingDivisor(GLuint bindingindex, GLuint divisor) {
+        auto vao = GetBoundVertexArrayOrError("VertexBindingDivisor");
+        if (!vao) return;
+        if (!ValidateVertexBindingIndex(bindingindex, "VertexBindingDivisor")) return;
+        vao->SetBindingDivisor(bindingindex, divisor);
+    }
+
     void VertexAttribDivisor(GLuint index, GLuint divisor) {
         VertexAttribDivisor_State(index, divisor);
     }

MobileGL/MG_Impl/GLImpl/VertexArray/GL_VertexArray.h

@@ -11,6 +11,82 @@
 
 namespace MobileGL::MG_Impl::GLImpl {
     /* @INSERTION_POINT:FUNCTION_DECLARATION@ */
+    void VertexAttrib1f(GLuint index, GLfloat x);
+    void VertexAttrib1fv(GLuint index, const GLfloat* v);
+    void VertexAttrib2f(GLuint index, GLfloat x, GLfloat y);
+    void VertexAttrib2fv(GLuint index, const GLfloat* v);
+    void VertexAttrib3f(GLuint index, GLfloat x, GLfloat y, GLfloat z);
+    void VertexAttrib3fv(GLuint index, const GLfloat* v);
+    void VertexAttrib4f(GLuint index, GLfloat x, GLfloat y, GLfloat z, GLfloat w);
+    void VertexAttrib4fv(GLuint index, const GLfloat* v);
+    void VertexAttribI4i(GLuint index, GLint x, GLint y, GLint z, GLint w);
+    void VertexAttribI4ui(GLuint index, GLuint x, GLuint y, GLuint z, GLuint w);
+    void VertexAttribI4iv(GLuint index, const GLint* v);
+    void VertexAttribI4uiv(GLuint index, const GLuint* v);
+    // Packed current-value setters (GL_INT_/GL_UNSIGNED_INT_2_10_10_10_REV). Decode one packed word
+    // into the first 1/2/3/4 components of the generic attribute's float current value.
+    void VertexAttribP1ui(GLuint index, GLenum type, GLboolean normalized, GLuint value);
+    void VertexAttribP2ui(GLuint index, GLenum type, GLboolean normalized, GLuint value);
+    void VertexAttribP3ui(GLuint index, GLenum type, GLboolean normalized, GLuint value);
+    void VertexAttribP4ui(GLuint index, GLenum type, GLboolean normalized, GLuint value);
+    void VertexAttribP1uiv(GLuint index, GLenum type, GLboolean normalized, const GLuint* value);
+    void VertexAttribP2uiv(GLuint index, GLenum type, GLboolean normalized, const GLuint* value);
+    void VertexAttribP3uiv(GLuint index, GLenum type, GLboolean normalized, const GLuint* value);
+    void VertexAttribP4uiv(GLuint index, GLenum type, GLboolean normalized, const GLuint* value);
+    void VertexAttrib4Nub(GLuint index, GLubyte x, GLubyte y, GLubyte z, GLubyte w);
+    void VertexAttrib4Nubv(GLuint index, const GLubyte* v);
+    void VertexAttrib4ubv(GLuint index, const GLubyte* v);
+    // Float-domain current-value setters that funnel into VertexAttrib4f. The d/s/bv/iv/uiv/usv
+    // forms are value-preserving (only the 4N* forms normalize per GL 3.3 Core Eq 2.1/2.2).
+    void VertexAttrib1d(GLuint index, GLdouble x);
+    void VertexAttrib2d(GLuint index, GLdouble x, GLdouble y);
+    void VertexAttrib3d(GLuint index, GLdouble x, GLdouble y, GLdouble z);
+    void VertexAttrib4d(GLuint index, GLdouble x, GLdouble y, GLdouble z, GLdouble w);
+    void VertexAttrib1dv(GLuint index, const GLdouble* v);
+    void VertexAttrib2dv(GLuint index, const GLdouble* v);
+    void VertexAttrib3dv(GLuint index, const GLdouble* v);
+    void VertexAttrib4dv(GLuint index, const GLdouble* v);
+    void VertexAttrib1s(GLuint index, GLshort x);
+    void VertexAttrib2s(GLuint index, GLshort x, GLshort y);
+    void VertexAttrib3s(GLuint index, GLshort x, GLshort y, GLshort z);
+    void VertexAttrib4s(GLuint index, GLshort x, GLshort y, GLshort z, GLshort w);
+    void VertexAttrib1sv(GLuint index, const GLshort* v);
+    void VertexAttrib2sv(GLuint index, const GLshort* v);
+    void VertexAttrib3sv(GLuint index, const GLshort* v);
+    void VertexAttrib4sv(GLuint index, const GLshort* v);
+    void VertexAttrib4bv(GLuint index, const GLbyte* v);
+    void VertexAttrib4iv(GLuint index, const GLint* v);
+    void VertexAttrib4uiv(GLuint index, const GLuint* v);
+    void VertexAttrib4usv(GLuint index, const GLushort* v);
+    void VertexAttrib4Nbv(GLuint index, const GLbyte* v);
+    void VertexAttrib4Nsv(GLuint index, const GLshort* v);
+    void VertexAttrib4Niv(GLuint index, const GLint* v);
+    void VertexAttrib4Nusv(GLuint index, const GLushort* v);
+    void VertexAttrib4Nuiv(GLuint index, const GLuint* v);
+    // Pure-integer current-value setters that funnel into VertexAttribI4i / VertexAttribI4ui and
+    // write the integer view, never the float one.
+    void VertexAttribI1i(GLuint index, GLint x);
+    void VertexAttribI2i(GLuint index, GLint x, GLint y);
+    void VertexAttribI3i(GLuint index, GLint x, GLint y, GLint z);
+    void VertexAttribI1ui(GLuint index, GLuint x);
+    void VertexAttribI2ui(GLuint index, GLuint x, GLuint y);
+    void VertexAttribI3ui(GLuint index, GLuint x, GLuint y, GLuint z);
+    void VertexAttribI1iv(GLuint index, const GLint* v);
+    void VertexAttribI2iv(GLuint index, const GLint* v);
+    void VertexAttribI3iv(GLuint index, const GLint* v);
+    void VertexAttribI1uiv(GLuint index, const GLuint* v);
+    void VertexAttribI2uiv(GLuint index, const GLuint* v);
+    void VertexAttribI3uiv(GLuint index, const GLuint* v);
+    void VertexAttribI4bv(GLuint index, const GLbyte* v);
+    void VertexAttribI4sv(GLuint index, const GLshort* v);
+    void VertexAttribI4ubv(GLuint index, const GLubyte* v);
+    void VertexAttribI4usv(GLuint index, const GLushort* v);
+    void GetVertexAttribfv(GLuint index, GLenum pname, GLfloat* params);
+    void GetVertexAttribdv(GLuint index, GLenum pname, GLdouble* params);
+    void GetVertexAttribiv(GLuint index, GLenum pname, GLint* params);
+    void GetVertexAttribPointerv(GLuint index, GLenum pname, void** pointer);
+    void GetVertexAttribIiv(GLuint index, GLenum pname, GLint* params);
+    void GetVertexAttribIuiv(GLuint index, GLenum pname, GLuint* params);
     void CreateVertexArrays(GLsizei n, GLuint* arrays);
     void DisableVertexArrayAttrib(GLuint vaobj, GLuint index);
     void EnableVertexArrayAttrib(GLuint vaobj, GLuint index);
@@ -19,6 +95,17 @@ namespace MobileGL::MG_Impl::GLImpl {
     void VertexArrayAttribFormat(GLuint vaobj, GLuint attribindex, GLint size, GLenum type, GLboolean normalized,
                                  GLuint relativeoffset);
     void VertexArrayAttribIFormat(GLuint vaobj, GLuint attribindex, GLint size, GLenum type, GLuint relativeoffset);
+    void VertexArrayAttribBinding(GLuint vaobj, GLuint attribindex, GLuint bindingindex);
+    void VertexArrayBindingDivisor(GLuint vaobj, GLuint bindingindex, GLuint divisor);
+    void VertexArrayVertexBuffers(GLuint vaobj, GLuint first, GLsizei count, const GLuint* buffers,
+                                  const GLintptr* offsets, const GLsizei* strides);
+    void BindVertexBuffer(GLuint bindingindex, GLuint buffer, GLintptr offset, GLsizei stride);
+    void BindVertexBuffers(GLuint first, GLsizei count, const GLuint* buffers, const GLintptr* offsets,
+                           const GLsizei* strides);
+    void VertexAttribFormat(GLuint attribindex, GLint size, GLenum type, GLboolean normalized, GLuint relativeoffset);
+    void VertexAttribIFormat(GLuint attribindex, GLint size, GLenum type, GLuint relativeoffset);
+    void VertexAttribBinding(GLuint attribindex, GLuint bindingindex);
+    void VertexBindingDivisor(GLuint bindingindex, GLuint divisor);
     void VertexAttribDivisor(GLuint index, GLuint divisor);
     GLboolean IsVertexArray(GLuint array);
     void DisableVertexAttribArray(GLuint index);

MobileGL/MG_Impl/GLImpl/VertexArray/Validators.cpp

@@ -7,12 +7,22 @@
 // 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/MGToGL/DataTypeConverter.h>
 #include <MG_Util/Converters/MGToStr/DataTypeConverter.h>
 
 namespace MobileGL::MG_Impl::GLImpl::VertexArrayImpl {
+    Uint GetMaxVertexAttribs() {
+        constexpr Uint capacity = static_cast<Uint>(MG_State::GLState::VertexArrayObject::MAX_VERTEX_ATTRIBS);
+        if (!MG_Backend::pActiveBackendObject) return capacity;
+
+        const Int backendLimit = MG_Backend::pActiveBackendObject->GetDynamicParameters().MaxVertexAttribs;
+        if (backendLimit <= 0) return capacity;
+        return std::min(static_cast<Uint>(backendLimit), capacity);
+    }
+
     Bool ValidateVertexArrayName(Uint index) {
         Bool isValid = MG_State::pGLContext->ValidateVertexArrayName(index);
         if (!isValid) {
@@ -37,13 +47,13 @@ namespace MobileGL::MG_Impl::GLImpl::VertexArrayImpl {
     }
 
     Bool ValidateVertexAttributeIndex(Uint index) {
-        if (index >= MG_State::GLState::VertexArrayObject::MAX_VERTEX_ATTRIBS) {
+        const Uint maxVertexAttribs = GetMaxVertexAttribs();
+        if (index >= maxVertexAttribs) {
             MG_State::pGLContext->RecordError(
                 ErrorCode::InvalidValue,
                 MakeUnique<GenericErrorInfo>(
                     "MG_Impl/GLImpl", "ValidateVertexAttributeIndex",
-                    std::format("Attribute index {} exceeds maximum of {}.", index,
-                                MG_State::GLState::VertexArrayObject::MAX_VERTEX_ATTRIBS - 1)));
+                    std::format("Attribute index {} exceeds maximum of {}.", index, maxVertexAttribs - 1)));
             return false;
         }
         return true;
@@ -79,4 +89,85 @@ namespace MobileGL::MG_Impl::GLImpl::VertexArrayImpl {
 
         return true;
     }
+
+    Bool ValidateVertexAttribFormat(Uint index, GLint sizeRaw, DataType type, Bool normalized, Int stride,
+                                    Bool integerPath) {
+        constexpr const char* fn = "ValidateVertexAttribFormat";
+        if (type == DataType::Unknown) {
+            MG_State::pGLContext->RecordError(
+                ErrorCode::InvalidEnum,
+                MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", fn,
+                                             std::format("Invalid type for attribute {}.", index)));
+            return false;
+        }
+
+        const bool isPacked = (type == DataType::Int2101010Rev || type == DataType::Uint2101010Rev);
+        // The packed 2_10_10_10 types are float-normalizing only; glVertexAttribIPointer never accepts them.
+        if (integerPath && isPacked) {
+            MG_State::pGLContext->RecordError(
+                ErrorCode::InvalidEnum,
+                MakeUnique<GenericErrorInfo>(
+                    "MG_Impl/GLImpl", fn,
+                    std::format("glVertexAttribIPointer does not accept packed 2_10_10_10 types (attribute {}).",
+                                index)));
+            return false;
+        }
+
+        if (sizeRaw == static_cast<GLint>(GL_BGRA)) {
+            // GL_BGRA is a float-path-only size: it needs GL_UNSIGNED_BYTE or a 2_10_10_10 type and
+            // normalized == GL_TRUE. On the integer path it is simply an out-of-range size.
+            if (integerPath) {
+                MG_State::pGLContext->RecordError(
+                    ErrorCode::InvalidValue,
+                    MakeUnique<GenericErrorInfo>(
+                        "MG_Impl/GLImpl", fn,
+                        std::format("GL_BGRA size is not valid for glVertexAttribIPointer (attribute {}).", index)));
+                return false;
+            }
+            if (!(type == DataType::Uint8 || isPacked)) {
+                MG_State::pGLContext->RecordError(
+                    ErrorCode::InvalidOperation,
+                    MakeUnique<GenericErrorInfo>(
+                        "MG_Impl/GLImpl", fn,
+                        std::format("GL_BGRA size requires GL_UNSIGNED_BYTE or a 2_10_10_10 type (attribute {}).",
+                                    index)));
+                return false;
+            }
+            if (!normalized) {
+                MG_State::pGLContext->RecordError(
+                    ErrorCode::InvalidOperation,
+                    MakeUnique<GenericErrorInfo>(
+                        "MG_Impl/GLImpl", fn,
+                        std::format("GL_BGRA size requires normalized == GL_TRUE (attribute {}).", index)));
+                return false;
+            }
+        } else {
+            // Size-range (INVALID_VALUE) takes precedence over the packed-size-must-be-4 rule.
+            if (sizeRaw < 1 || sizeRaw > 4) {
+                MG_State::pGLContext->RecordError(
+                    ErrorCode::InvalidValue,
+                    MakeUnique<GenericErrorInfo>(
+                        "MG_Impl/GLImpl", fn,
+                        std::format("Invalid size {} for attribute {}. Must be 1-4 or GL_BGRA.", sizeRaw, index)));
+                return false;
+            }
+            if (isPacked && sizeRaw != 4) {
+                MG_State::pGLContext->RecordError(
+                    ErrorCode::InvalidOperation,
+                    MakeUnique<GenericErrorInfo>(
+                        "MG_Impl/GLImpl", fn,
+                        std::format("A 2_10_10_10 type requires size 4 or GL_BGRA (attribute {}).", index)));
+                return false;
+            }
+        }
+
+        if (stride < 0) {
+            MG_State::pGLContext->RecordError(
+                ErrorCode::InvalidValue,
+                MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", fn,
+                                             std::format("Negative stride {} for attribute {}.", stride, index)));
+            return false;
+        }
+        return true;
+    }
 } // namespace MobileGL::MG_Impl::GLImpl::VertexArrayImpl

MobileGL/MG_Impl/GLImpl/VertexArray/Validators.h

@@ -11,8 +11,17 @@
 #include <MG_State/GLState/VertexArrayState/VertexArrayObject.h>
 
 namespace MobileGL::MG_Impl::GLImpl::VertexArrayImpl {
+    // The GL-visible GL_MAX_VERTEX_ATTRIBS: min(active backend limit, VertexArrayObject storage
+    // capacity). Falls back to the capacity when no backend is active (unit tests).
+    Uint GetMaxVertexAttribs();
+
     Bool ValidateVertexArrayName(Uint index);
     Bool ValidateVertexArrayObject(Uint index);
     Bool ValidateVertexAttributeIndex(Uint index);
     Bool ValidateVertexAttribPointerParams(Uint index, SizeT size, DataType type, Int stride);
+    // Full glVertexAttribPointer / glVertexAttribIPointer format validation, including the packed
+    // 2_10_10_10 types and GL_BGRA size. sizeRaw is the untranslated GL size (possibly GL_BGRA);
+    // integerPath selects the glVertexAttribIPointer rules.
+    Bool ValidateVertexAttribFormat(Uint index, GLint sizeRaw, DataType type, Bool normalized, Int stride,
+                                    Bool integerPath);
 } // namespace MobileGL::MG_Impl::GLImpl::VertexArrayImpl

MobileGL/MG_Impl/GetProcAddress.cpp

@@ -7,6 +7,15 @@
 // End of Source File Header
 
 #include "GetProcAddress.h"
+#if defined(__APPLE__) && !defined(MOBILEGL_IOS)
+#ifndef GL_SILENCE_DEPRECATION
+#define GL_SILENCE_DEPRECATION
+#endif
+#include <OpenGL/OpenGL.h>
+#endif
+
+extern "C" EGLDisplay eglGetPlatformDisplayEXT(EGLenum platform, void* native_display, const EGLint* attrib_list);
+
 #define GETPROC(name, var)                                                                                             \
     if (strcmp(#name, var) == 0) {                                                                                     \
         return (void*)name;                                                                                            \
@@ -56,10 +65,37 @@ namespace MobileGL::MG_Impl {
         GETPROC(eglCreateImage, name);
         GETPROC(eglDestroyImage, name);
         GETPROC(eglGetPlatformDisplay, name);
+        GETPROC(eglGetPlatformDisplayEXT, name);
         GETPROC(eglCreatePlatformWindowSurface, name);
         GETPROC(eglCreatePlatformPixmapSurface, name);
         GETPROC(eglWaitSync, name);
 
+#if defined(__APPLE__) && !defined(MOBILEGL_IOS)
+        GETPROC(CGLChoosePixelFormat, name);
+        GETPROC(CGLDestroyPixelFormat, name);
+        GETPROC(CGLDescribePixelFormat, name);
+        GETPROC(CGLReleasePixelFormat, name);
+        GETPROC(CGLRetainPixelFormat, name);
+        GETPROC(CGLGetPixelFormatRetainCount, name);
+        GETPROC(CGLCreateContext, name);
+        GETPROC(CGLDestroyContext, name);
+        GETPROC(CGLRetainContext, name);
+        GETPROC(CGLReleaseContext, name);
+        GETPROC(CGLGetContextRetainCount, name);
+        GETPROC(CGLGetPixelFormat, name);
+        GETPROC(CGLSetCurrentContext, name);
+        GETPROC(CGLGetCurrentContext, name);
+        GETPROC(CGLSetParameter, name);
+        GETPROC(CGLGetParameter, name);
+        GETPROC(CGLUpdateContext, name);
+        GETPROC(CGLClearDrawable, name);
+        GETPROC(CGLFlushDrawable, name);
+        GETPROC(CGLLockContext, name);
+        GETPROC(CGLUnlockContext, name);
+        GETPROC(CGLGetVersion, name);
+        GETPROC(CGLErrorString, name);
+#endif
+
         GETPROC(glCullFace, name);
         GETPROC(glFrontFace, name);
         GETPROC(glHint, name);