[Perf] (MG_Backend/DirectVulkanTMP): Optimize buffer uploads with staging ring + batched copies.

.clang-tidy

@@ -14,6 +14,7 @@ bugprone-forwarding-reference-overload,
 bugprone-inaccurate-erase,
 bugprone-incorrect-roundings,
 bugprone-integer-division,
+bugprone-lambda-function-name,
 bugprone-macro-parentheses,
 bugprone-macro-repeated-side-effects,
 bugprone-misplaced-operator-in-strlen-in-alloc,
@@ -62,6 +63,7 @@ cert-str34-c,
 cppcoreguidelines-interfaces-global-init,
 cppcoreguidelines-narrowing-conversions,
 cppcoreguidelines-pro-type-member-init,
+cppcoreguidelines-pro-type-static-cast-downcast,
 cppcoreguidelines-slicing,
 google-default-arguments,
 google-runtime-operator,

.gitattributes

@@ -1,4 +0,0 @@
-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

@@ -1,199 +0,0 @@
-#!/usr/bin/env bash
-set -euo pipefail
-
-script_dir="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
-# shellcheck source=trace-fixture-lib.sh
-. "${script_dir}/trace-fixture-lib.sh"
-
-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="${PYTHON:-python3}"
-# Fixture mirrors, tried in order before falling back to Git LFS. Override the
-# whole list with MOBILEGL_TRACE_FIXTURE_MIRROR_BASES (whitespace separated);
-# MOBILEGL_TRACE_FIXTURE_MIRROR_BASE still works and is tried first.
-default_mirror_bases=(
-  "https://git.hit.moe/swung0x48/MobileGL/media/branch/dev/tools/trace_replay/fixtures"
-  "https://repo.miawa.cn/mgl/tools/trace_replay/fixtures"
-)
-if [ -n "${MOBILEGL_TRACE_FIXTURE_MIRROR_BASES:-}" ]; then
-  read -r -a mirror_bases <<< "${MOBILEGL_TRACE_FIXTURE_MIRROR_BASES}"
-else
-  mirror_bases=("${default_mirror_bases[@]}")
-fi
-if [ -n "${MOBILEGL_TRACE_FIXTURE_MIRROR_BASE:-}" ]; then
-  mirror_bases=("${MOBILEGL_TRACE_FIXTURE_MIRROR_BASE}" "${mirror_bases[@]}")
-fi
-# Optional bearer token for mirrors that require authentication (private Gitea).
-mirror_token="${MOBILEGL_TRACE_FIXTURE_MIRROR_TOKEN:-}"
-download_attempts="${MOBILEGL_TRACE_FIXTURE_DOWNLOAD_ATTEMPTS:-5}"
-retry_delay="${MOBILEGL_TRACE_FIXTURE_RETRY_DELAY:-2}"
-
-if ! command -v "${python_bin}" >/dev/null 2>&1 && command -v python >/dev/null 2>&1; then
-  python_bin=python
-fi
-
-if ! [[ "${download_attempts}" =~ ^[1-9][0-9]*$ ]]; then
-  echo "MOBILEGL_TRACE_FIXTURE_DOWNLOAD_ATTEMPTS must be a positive integer: ${download_attempts}" >&2
-  exit 2
-fi
-if ! [[ "${retry_delay}" =~ ^[0-9]+$ ]]; then
-  echo "MOBILEGL_TRACE_FIXTURE_RETRY_DELAY must be a non-negative integer: ${retry_delay}" >&2
-  exit 2
-fi
-
-fixture_list="$("${python_bin}" tools/trace_replay/trace_cases.py \
-  --format fixture-files \
-  --case "${case_name}" \
-  --fixture-root "${fixture_dir}")"
-# Strip CR so the script also works when python emits CRLF (Git Bash on Windows).
-mapfile -t files < <(printf '%s\n' "${fixture_list}" | tr -d '\r')
-
-include="$(IFS=,; echo "${files[*]}")"
-if [ "${case_name}" = "OpenRA" ]; then
-  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
-
-fetch_file_from_mirror() {
-  local file="$1"
-  local url="$2"
-  local metadata
-  local expected_oid
-  local expected_size
-  local tmp_file="${file}.tmp"
-  local attempt
-  local partial_size
-  local curl_status
-  local curl_auth
-
-  metadata="$(get_lfs_metadata "${file}")" || return 1
-  read -r expected_oid expected_size <<< "${metadata}"
-
-  if [ -f "${tmp_file}" ]; then
-    partial_size="$(wc -c < "${tmp_file}" | tr -d '[:space:]')"
-    if [ "${partial_size}" -gt "${expected_size}" ]; then
-      echo "Discarding oversized partial fixture ${tmp_file}: ${partial_size} > ${expected_size}" >&2
-      rm -f "${tmp_file}"
-    elif [ "${partial_size}" = "${expected_size}" ]; then
-      if verify_fixture_file "${tmp_file}" "${file}" "${expected_oid}" "${expected_size}"; then
-        mv "${tmp_file}" "${file}"
-        return 0
-      fi
-      rm -f "${tmp_file}"
-    fi
-  fi
-
-  for ((attempt = 1; attempt <= download_attempts; attempt++)); do
-    partial_size=0
-    if [ -f "${tmp_file}" ]; then
-      partial_size="$(wc -c < "${tmp_file}" | tr -d '[:space:]')"
-    fi
-
-    if [ "${partial_size}" -gt 0 ]; then
-      echo "Resuming mirror download for ${file} at byte ${partial_size} (attempt ${attempt}/${download_attempts})"
-    else
-      echo "Starting mirror download for ${file} (attempt ${attempt}/${download_attempts})"
-    fi
-
-    curl_auth=()
-    if [ -n "${mirror_token}" ]; then
-      curl_auth=(--header "Authorization: token ${mirror_token}")
-    fi
-    if curl -L --fail --show-error --continue-at - "${curl_auth[@]}" --output "${tmp_file}" "${url}"; then
-      if verify_fixture_file "${tmp_file}" "${file}" "${expected_oid}" "${expected_size}"; then
-        mv "${tmp_file}" "${file}"
-        return 0
-      fi
-      echo "Mirror download failed integrity verification; retrying from the beginning: ${file}" >&2
-      rm -f "${tmp_file}"
-    else
-      curl_status=$?
-      partial_size=0
-      if [ -f "${tmp_file}" ]; then
-        partial_size="$(wc -c < "${tmp_file}" | tr -d '[:space:]')"
-      fi
-
-      if [ "${partial_size}" = "${expected_size}" ]; then
-        if verify_fixture_file "${tmp_file}" "${file}" "${expected_oid}" "${expected_size}"; then
-          mv "${tmp_file}" "${file}"
-          return 0
-        fi
-        rm -f "${tmp_file}"
-        partial_size=0
-      elif [ "${partial_size}" -gt "${expected_size}" ]; then
-        echo "Discarding oversized partial fixture ${tmp_file}: ${partial_size} > ${expected_size}" >&2
-        rm -f "${tmp_file}"
-        partial_size=0
-      elif [ "${curl_status}" -eq 33 ]; then
-        echo "Mirror refused the resume request; retrying from the beginning: ${file}" >&2
-        rm -f "${tmp_file}"
-        partial_size=0
-      fi
-
-      echo "Mirror download attempt ${attempt}/${download_attempts} failed with curl exit ${curl_status}; retained ${partial_size} bytes for resume: ${file}" >&2
-    fi
-
-    if [ "${attempt}" -lt "${download_attempts}" ]; then
-      sleep "${retry_delay}"
-    fi
-  done
-
-  rm -f "${tmp_file}"
-  return 1
-}
-
-# Files no mirror could serve, even after retrying every mirror. Only these fall
-# back to Git LFS, so a mirror that served the rest of the case still spares
-# GitHub the bandwidth for those files.
-mirror_failures=()
-
-fetch_from_mirror() {
-  mkdir -p "${fixture_dir}"
-  for file in "${files[@]}"; do
-    local name
-    local url
-    local base
-    local fetched=0
-    name="$(basename "${file}")"
-    for base in "${mirror_bases[@]}"; do
-      url="${base%/}/${name}"
-      echo "Fetching trace fixture from mirror: ${url}"
-      if fetch_file_from_mirror "${file}" "${url}"; then
-        fetched=1
-        break
-      fi
-      echo "Mirror did not serve ${name}; trying the next mirror" >&2
-    done
-    if [ "${fetched}" -ne 1 ]; then
-      mirror_failures+=("${file}")
-    fi
-  done
-  [ "${#mirror_failures[@]}" -eq 0 ]
-}
-
-if fetch_from_mirror; then
-  echo "Fetched trace fixture files for ${case_name} from mirror: ${include}"
-else
-  fallback_include="$(IFS=,; echo "${mirror_failures[*]}")"
-  echo "All mirrors failed for ${#mirror_failures[@]} of ${#files[@]} file(s) of ${case_name}; falling back to Git LFS: ${fallback_include}"
-  git lfs install --local
-  git lfs pull --include="${fallback_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/trace-fixture-cache.sh

@@ -1,117 +0,0 @@
-#!/usr/bin/env bash
-# Cache-side helper for trace fixtures.
-#
-#   key <case> [fixture-dir]     derive the actions/cache key and path list
-#   verify <case> [fixture-dir]  check restored fixtures against their pointers
-#   reset <case> [fixture-dir]   drop restored fixtures, leaving the pointers
-#
-# The cache key is content-addressed on the Git LFS pointer oids tracked at
-# HEAD, which are readable from a plain checkout without smudging. Fixture
-# content therefore maps 1:1 onto a key: unchanged content hits, changed
-# content is a new key and thus a miss, and the download path handles it. The
-# key deliberately carries no restore-keys prefix in the workflow - a fixture
-# that does not match the pointer exactly must never be restored.
-set -euo pipefail
-
-script_dir="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
-# shellcheck source=trace-fixture-lib.sh
-. "${script_dir}/trace-fixture-lib.sh"
-
-# Bump when the key derivation changes in a way that must invalidate old
-# entries; the content digest alone would not notice a format change.
-key_schema="v1"
-
-if [ "$#" -lt 2 ] || [ "$#" -gt 3 ]; then
-  echo "usage: $0 <key|verify|reset> <trace-case> [fixture-dir]" >&2
-  exit 2
-fi
-
-command_name="$1"
-case_name="$2"
-fixture_dir="${3:-tools/trace_replay/fixtures}"
-python_bin="${PYTHON:-python3}"
-
-if ! command -v "${python_bin}" >/dev/null 2>&1 && command -v python >/dev/null 2>&1; then
-  python_bin=python
-fi
-
-mapfile -t files < <(trace_fixture_files "${case_name}" "${fixture_dir}" "${python_bin}")
-if [ "${#files[@]}" -eq 0 ]; then
-  echo "no fixture files declared for trace case: ${case_name}" >&2
-  exit 1
-fi
-
-# Writes "name=value" to $GITHUB_OUTPUT when running under Actions, and to
-# stdout otherwise so the script stays runnable (and testable) off-CI.
-emit_output() {
-  local name="$1"
-  local value="$2"
-  if [ -n "${GITHUB_OUTPUT:-}" ]; then
-    if [[ "${value}" == *$'\n'* ]]; then
-      local delimiter="ghadelim_$(date +%s%N)_$$"
-      {
-        printf '%s<<%s\n' "${name}" "${delimiter}"
-        printf '%s\n' "${value}"
-        printf '%s\n' "${delimiter}"
-      } >> "${GITHUB_OUTPUT}"
-    else
-      printf '%s=%s\n' "${name}" "${value}" >> "${GITHUB_OUTPUT}"
-    fi
-  fi
-  printf '%s=%s\n' "${name}" "${value}"
-}
-
-sanitize_case() {
-  printf '%s' "$1" | sed 's/[^A-Za-z0-9._-]/_/g'
-}
-
-case "${command_name}" in
-  key)
-    manifest=""
-    for file in "${files[@]}"; do
-      # A case whose fixtures are committed directly rather than through Git LFS
-      # (OpenRA) has no pointer oid to key on, and nothing to download either.
-      # Report it as uncacheable so the workflow skips the cache entirely.
-      if ! metadata="$(get_lfs_metadata "${file}" 2>/dev/null)"; then
-        echo "trace case ${case_name} is not stored in Git LFS; skipping fixture cache" >&2
-        emit_output "cacheable" "false"
-        emit_output "key" ""
-        exit 0
-      fi
-      read -r expected_oid expected_size <<< "${metadata}"
-      manifest+="$(basename "${file}") ${expected_oid} ${expected_size}"$'\n'
-    done
-
-    digest="$(printf '%s' "${manifest}" | sha256sum | awk '{ print substr($1, 1, 16) }')"
-    safe_case="$(sanitize_case "${case_name}")"
-
-    emit_output "cacheable" "true"
-    emit_output "key" "trace-fixture-${key_schema}-${safe_case}-${digest}"
-    emit_output "paths" "$(printf '%s\n' "${files[@]}")"
-    ;;
-
-  verify)
-    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
-    echo "Verified ${#files[@]} fixture file(s) for ${case_name} against the tracked Git LFS pointers."
-    ;;
-
-  reset)
-    # Put the working tree back to the pointer files a fresh checkout would
-    # have, so that a rejected cache entry falls through to exactly the same
-    # download path a cache miss takes.
-    for file in "${files[@]}"; do
-      rm -f "${file}" "${file}.tmp"
-    done
-    git checkout -- "${files[@]}"
-    echo "Reset ${#files[@]} fixture file(s) for ${case_name} to their tracked Git LFS pointers."
-    ;;
-
-  *)
-    echo "unknown command: ${command_name}" >&2
-    exit 2
-    ;;
-esac

.github/scripts/trace-fixture-lib.sh

@@ -1,73 +0,0 @@
-#!/usr/bin/env bash
-# Shared helpers for trace-fixture handling: reading the in-tree Git LFS pointer
-# metadata and verifying a fixture file against it. Sourced by
-# fetch-trace-fixture-lfs.sh (verify after download) and by
-# trace-fixture-cache.sh (cache key derivation and verify after cache restore),
-# so both paths agree on what a valid fixture is.
-
-# Reads the Git LFS pointer tracked at HEAD for a fixture path and prints
-# "<oid> <size>". Fails if the tracked blob is not a well-formed LFS pointer.
-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}"
-}
-
-# Checks an on-disk fixture against the size and SHA-256 from its LFS pointer.
-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
-}
-
-# Prints the fixture file paths of a trace case, one per line. Strips CR so the
-# result is usable when python emits CRLF (Git Bash on Windows).
-trace_fixture_files() {
-  local case_name="$1"
-  local fixture_dir="$2"
-  local python_bin="${3:-python3}"
-
-  "${python_bin}" tools/trace_replay/trace_cases.py \
-    --format fixture-files \
-    --case "${case_name}" \
-    --fixture-root "${fixture_dir}" | tr -d '\r'
-}

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

@@ -1,75 +0,0 @@
-#!/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

@@ -1,660 +0,0 @@
-name: MobileGL APK
-
-on:
-  push:
-    branches:
-      - dev
-      - Feat/Backend-Direct-GLES
-      - Feat/Backend-Direct-Vulkan
-  workflow_dispatch:
-
-jobs:
-  build:
-    runs-on: ubuntu-latest
-    permissions:
-      actions: write
-      contents: read
-    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/restore@v5
-        with:
-          path: .ccache
-          key: ${{ runner.os }}-apk-${{ github.job }}-ccache-v1
-          restore-keys: |
-            ${{ runner.os }}-apk-${{ 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
-
-      # Rewrite one rolling entry per job on the default branch. The upload stays
-      # cumulative - it carries every object restored at the top of this run plus
-      # the few TUs that actually changed - but Actions cache keys are immutable,
-      # so the superseded blob has to be released before the same key can be
-      # re-uploaded. Running after the build means a failed build leaves the
-      # existing entry untouched. The other trigger branches restore this entry
-      # rather than each writing a ~4 GB one of their own.
-      - name: Release superseded ccache entry
-        if: github.ref_name == github.event.repository.default_branch
-        env:
-          GH_TOKEN: ${{ github.token }}
-          CACHE_KEY: ${{ runner.os }}-apk-${{ github.job }}-ccache-v1
-        run: gh cache delete "${CACHE_KEY}" || true
-
-      - name: Save ccache
-        if: github.ref_name == github.event.repository.default_branch
-        continue-on-error: true
-        uses: actions/cache/save@v5
-        with:
-          path: .ccache
-          key: ${{ runner.os }}-apk-${{ github.job }}-ccache-v1
-
-      - 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-matrix)" >> "$GITHUB_OUTPUT"
-          echo "names=$(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: ${{ fromJSON(needs.trace-cases.outputs.names) }}
-    steps:
-      - name: Checkout repo
-        uses: actions/checkout@v6
-
-      - name: Derive trace fixture cache key
-        id: fixture-key
-        run: bash .github/scripts/trace-fixture-cache.sh key '${{ matrix.case }}'
-
-      - name: Restore trace fixture cache
-        id: fixture-cache
-        if: steps.fixture-key.outputs.cacheable == 'true'
-        uses: actions/cache/restore@v5
-        with:
-          path: ${{ steps.fixture-key.outputs.paths }}
-          key: ${{ steps.fixture-key.outputs.key }}
-
-      - name: Verify restored trace fixture
-        id: fixture-verify
-        if: steps.fixture-cache.outputs.cache-hit == 'true'
-        run: |
-          if bash .github/scripts/trace-fixture-cache.sh verify '${{ matrix.case }}'; then
-            echo "ok=true" >> "$GITHUB_OUTPUT"
-          else
-            echo "ok=false" >> "$GITHUB_OUTPUT"
-            echo "::warning::Cached fixture for ${{ matrix.case }} failed verification; falling back to the download path"
-            bash .github/scripts/trace-fixture-cache.sh reset '${{ matrix.case }}'
-          fi
-
-      - name: Fetch trace fixture
-        if: steps.fixture-verify.outputs.ok != 'true'
-        run: bash .github/scripts/fetch-trace-fixture-lfs.sh '${{ matrix.case }}'
-
-      - name: Save trace fixture cache
-        if: steps.fixture-key.outputs.cacheable == 'true' && steps.fixture-cache.outputs.cache-hit != 'true'
-        uses: actions/cache/save@v5
-        with:
-          path: ${{ steps.fixture-key.outputs.paths }}
-          key: ${{ steps.fixture-key.outputs.key }}
-
-      - name: Stage trace fixture
-        run: |
-          safe_case="$(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: ${{ fromJSON(needs.trace-cases.outputs.android) }}
-    steps:
-      - name: Set Swap Space
-        uses: pierotofy/set-swap-space@v1.0
-        with:
-          swap-size-gb: 8
-
-      - name: Checkout repo
-        uses: actions/checkout@v6
-
-      - name: Download trace fixture
-        uses: actions/download-artifact@v8
-        with:
-          name: MobileGL-trace-fixture-${{ 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' }}
-          MOBILEGL_FIX_ITERATIONRP_SUBGROUP_SCRATCH: ${{ matrix.backend.name == 'DirectVulkan' && matrix.case.name == 'minecraft-1.21.4-fabric-iris-iterationrp-in-world' && '1' || '0' }}
-          MOBILEGL_DERIVE_NUM_SUBGROUPS: ${{ matrix.backend.name == 'DirectVulkan' && matrix.case.name == 'minecraft-1.21.4-fabric-iris-iterationrp-in-world' && '1' || '0' }}
-          MOBILEGL_ITERATIONRP_FIX_BARRIER: ${{ matrix.backend.name == 'DirectVulkan' && matrix.case.name == 'minecraft-1.21.4-fabric-iris-iterationrp-in-world' && '1' || '0' }}
-        run: |
-          apk_file="android-retrace-apks/MobileGL-plugin-trace-release-${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.backend.name }}" = "DirectGLES" ] && [ "${{ matrix.case.avoid_angle_llvmpipe_explicit_lod_bias || false }}" = "true" ]; then
-            extra_retrace_args+=(--avoid-angle-llvmpipe-explicit-lod-bias)
-          fi
-          if [ "${{ 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."
-            # Surface-lost is retried rather than failed, so it would otherwise
-            # be invisible. Report it per job - a healthy run prints nothing and
-            # a rate spike shows up as a row per affected case.
-            reason_file="android-retrace-result/infrastructure-failure-reason.txt"
-            surface_lost_retries=0
-            if [ -f "${reason_file}" ]; then
-              surface_lost_retries="$(grep -c 'angle-surface-lost' "${reason_file}" || true)"
-            fi
-            if [ "${surface_lost_retries}" -gt 0 ]; then
-              echo "surface-lost retries: ${surface_lost_retries} (${{ matrix.backend.name }}, ${{ matrix.case.name }})" \
-                >> "${GITHUB_STEP_SUMMARY}"
-            fi
-            # The restart truncates EMULATOR_LOG, and the attempt that lost the
-            # emulator is the one worth reading - the retry usually only shows
-            # the wreckage. Keep the first attempt's log before it is clobbered.
-            if [ -f "${EMULATOR_LOG}" ]; then
-              cp "${EMULATOR_LOG}" "${EMULATOR_LOG}.first-attempt" || true
-            fi
-            sh android-plugin/run-avd-ci.sh stop \
-              --avd-name "${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
-          if [ -f "${EMULATOR_LOG}.first-attempt" ]; then
-            cp "${EMULATOR_LOG}.first-attempt" android-retrace-result/diagnostics/emulator-first-attempt.log
-          fi
-          # A vanished emulator looks identical whether the host OOM killer took
-          # qemu or the renderer faulted. These two say which.
-          free -h > android-retrace-result/diagnostics/host-memory.txt 2>&1 || true
-          sudo dmesg -T 2>/dev/null | tail -300 > android-retrace-result/diagnostics/host-dmesg.txt || true
-
-      - 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 ((${#failed_cases[@]})); then
-            echo "Retaining fixtures and results for failed retrace case(s):"
-            printf '  %s\n' "${!failed_cases[@]}"
-          else
-            echo "All retrace jobs succeeded; nothing needs to be retained."
-          fi
-
-          deleted=0
-          retained=0
-          while IFS=$'\t' read -r artifact_id artifact_name; do
-            keep=0
-            if [[ "${artifact_name}" == MobileGL-trace-fixture-* ]]; then
-              case_name="${artifact_name#MobileGL-trace-fixture-}"
-              if [[ -v "failed_cases[${case_name}]" ]]; then
-                keep=1
-              fi
-            elif [[ "${artifact_name}" == MobileGL-android-retrace-result-* ]]; then
-              # The result artifact carries mobilegl.log, retrace.log, logcat,
-              # the emulator log and the actual/diff images - the only record of
-              # why a retrace failed. Its name ends in -<backend>-<case>, so a
-              # suffix match on the case name keeps both backends' results for a
-              # case that failed on either of them, which is what a comparison
-              # needs. The match is anchored at the end, so a case name that is a
-              # prefix of a longer one does not retain the longer one's results.
-              for case_name in "${!failed_cases[@]}"; do
-                if [[ "${artifact_name}" == *-"${case_name}" ]]; then
-                  keep=1
-                  break
-                fi
-              done
-            fi
-
-            if ((keep)); then
-              echo "Retaining ${artifact_name} (${artifact_id}) for failed retrace."
-              ((retained += 1))
-              continue
-            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

@@ -0,0 +1,57 @@
+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: 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/test.yml

@@ -1,4 +1,4 @@
-name: Test
+name: Test
 
 on:
   push:
@@ -6,765 +6,62 @@ on:
       - dev
       - Feat/Backend-Direct-GLES
       - Feat/Backend-Direct-Vulkan
-  workflow_dispatch:
 
 jobs:
-  build-linux:
-    runs-on: ubuntu-latest
-    permissions:
-      actions: write
-      contents: read
-    env:
-      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@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/restore@v5
-        with:
-          path: .ccache
-          key: ${{ runner.os }}-test-${{ github.job }}-ccache-v1
-          restore-keys: |
-            ${{ runner.os }}-test-${{ 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 build 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: 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="${BUILD_TYPE}" \
-            -DMOBILEGL_LOG_ACTIVE_LEVEL=MOBILEGL_LOG_LEVEL_INFO \
-            -DMOBILEGL_BUILD_TEST=ON \
-            -DMOBILEGL_BUILD_BENCHMARK=ON \
-            -DMOBILEGL_BUILD_INTEGRATION_TEST=ON \
-            -DMOBILEGL_ITEST_VK_ICD=/usr/share/vulkan/icd.d/lvp_icd.json \
-            -DMOBILEGL_BUILD_TRACE_REPLAY=OFF \
-            -DBENCHMARK_DOWNLOAD_DEPENDENCIES=ON \
-            -DBENCHMARK_ENABLE_TESTING=OFF \
-            -DCMAKE_POLICY_VERSION_MINIMUM=3.5
-
-      - name: Build
-        run: cmake --build "${BUILD_DIR}" --parallel "$(nproc)"
-
-      - name: Show ccache stats
-        if: always()
-        run: ccache --show-stats
-
-      # Rewrite one rolling entry per job on the default branch. The upload stays
-      # cumulative - it carries every object restored at the top of this run plus
-      # the few TUs that actually changed - but Actions cache keys are immutable,
-      # so the superseded blob has to be released before the same key can be
-      # re-uploaded. Running after the build means a failed build leaves the
-      # existing entry untouched. The other trigger branches restore this entry
-      # rather than each writing one of their own.
-      - name: Release superseded ccache entry
-        if: github.ref_name == github.event.repository.default_branch
-        env:
-          GH_TOKEN: ${{ github.token }}
-          CACHE_KEY: ${{ runner.os }}-test-${{ github.job }}-ccache-v1
-        run: gh cache delete "${CACHE_KEY}" || true
-
-      - name: Save ccache
-        if: github.ref_name == github.event.repository.default_branch
-        continue-on-error: true
-        uses: actions/cache/save@v5
-        with:
-          path: .ccache
-          key: ${{ runner.os }}-test-${{ github.job }}-ccache-v1
-
-      - 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" \
-            "${BUILD_DIR}/MobileGL/MG_Benchmark" \
-            "${BUILD_DIR}/MobileGL/MG_IntegrationTest" \
-            "${SHARED_LIBS[@]}"
-
-      - name: Upload Linux runtime
-        uses: actions/upload-artifact@v7
-        with:
-          name: mobilegl-linux-runtime
-          path: ci-artifacts/mobilegl-linux-runtime.tgz
-          if-no-files-found: error
-
   test:
     runs-on: ubuntu-latest
-    needs: build-linux
-
-    steps:
-      - name: Checkout repo
-        uses: actions/checkout@v6
-
-      - name: Get CMake
-        uses: lukka/get-cmake@v4.3.3
-
-      - name: Install runtime dependencies
-        run: |
-          sudo apt-get update
-          sudo apt-get install -y libvulkan1 libegl1 libgles2 libgl1-mesa-dri mesa-vulkan-drivers
-
-      - name: Download Linux runtime
-        uses: actions/download-artifact@v8
-        with:
-          name: mobilegl-linux-runtime
-          path: .
-
-      - name: Unpack Linux runtime
-        run: tar -xzf mobilegl-linux-runtime.tgz
-
-      - name: Normalize CTest command paths
-        run: |
-          python - <<'PY'
-          from pathlib import Path
-          import re
-
-          for path in Path('build-linux').rglob('CTestTestfile.cmake'):
-              text = path.read_text()
-              text = re.sub(r'"[^"]*/cmake-[^"]*/bin/cmake"', '"cmake"', text)
-              path.write_text(text)
-          PY
-
-      - name: Test
-        working-directory: build-linux
-        run: |
-          ulimit -c unlimited
-          sudo sysctl -w kernel.core_pattern='/tmp/core.%e.%p'
-          if [ "${{ secrets.ACTIONS_STEP_DEBUG }}" = "true" ]; then
-            ctest -V -L unit --no-tests=error
-          else
-            ctest --output-on-failure -L unit --no-tests=error
-          fi
-
-      - name: Upload core dumps
-        if: failure()
-        uses: actions/upload-artifact@v7
-        with:
-          name: unit-core-dumps
-          path: /tmp/core.*
-          if-no-files-found: ignore
-
-  integration:
-    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
-        # Same set as the benchmark job, for the same reason: the scenarios bring
-        # up real headless EGL (llvmpipe) and Vulkan (lavapipe) contexts, and
-        # libegl-mesa0 - the EGL vendor library behind glvnd's libegl1 dispatch -
-        # only arrives as a Recommends.
-        run: |
-          sudo apt-get update
-          sudo apt-get install -y libvulkan1 libegl1 libegl-mesa0 libgles2 libgl1-mesa-dri mesa-vulkan-drivers
-
-      - name: Download Linux runtime
-        uses: actions/download-artifact@v8
-        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: Integration scenarios
-        working-directory: build-linux
-        # REQUIRE_GPU makes a driverless runner FAIL instead of skipping every
-        # scenario - an all-skip run is otherwise indistinguishable from a pass,
-        # which is how a five-month-old draw-dropping bug survived unseen until
-        # this lane existed.
-        #
-        # The lavapipe ICD pin lives in the build-linux configure
-        # (-DMOBILEGL_ITEST_VK_ICD), NOT here: the configure bakes it into each
-        # test's ctest ENVIRONMENT property, and a property entry OVERRIDES the
-        # job environment - a VK_ICD_FILENAMES exported here would be silently
-        # ignored while looking like it works. This lane runs on lavapipe
-        # deterministically, not on whichever of the eight Mesa ICDs a GPU-less
-        # runner enumerates first.
-        #
-        # Cores are armed so that any crash - the harness pre-flight child's
-        # included - leaves /tmp/core.*, which the failure-only step below ships
-        # as an artifact. Analyzing a downloaded core against the runtime
-        # artifact's binary in an ubuntu-24.04 userspace reproduces the exact
-        # crash stack without burning a CI round on an in-workflow debugger.
-        env:
-          MOBILEGL_ITEST_REQUIRE_GPU: "1"
-          MOBILEGL_FIX_ITERATIONRP_SUBGROUP_SCRATCH: "1"
-          MOBILEGL_DERIVE_NUM_SUBGROUPS: "1"
-          MOBILEGL_ITERATIONRP_FIX_BARRIER: "1"
-        run: |
-          ulimit -c unlimited
-          sudo sysctl -w kernel.core_pattern='/tmp/core.%e.%p'
-          if [ "${{ secrets.ACTIONS_STEP_DEBUG }}" = "true" ]; then
-            ctest -V -L integration-gpu --no-tests=error
-          else
-            ctest --output-on-failure -L integration-gpu --no-tests=error
-          fi
-
-      - name: Upload core dumps
-        if: failure()
-        uses: actions/upload-artifact@v7
-        with:
-          name: integration-core-dumps
-          path: /tmp/core.*
-          if-no-files-found: ignore
-
-  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
-        # libegl-mesa0 is the EGL vendor library itself: DriverBench brings up a
-        # real GL context, and libegl1 is only glvnd's dispatch. It normally
-        # arrives as a Recommends of libegl1, which is too quiet a dependency for
-        # the one job that needs a working driver.
-        run: |
-          sudo apt-get update
-          sudo apt-get install -y libvulkan1 libegl1 libegl-mesa0 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: |
-          ulimit -c unlimited
-          sudo sysctl -w kernel.core_pattern='/tmp/core.%e.%p'
-          ctest -V -C Release -L benchmark --no-tests=error
-
-      - name: Upload core dumps
-        if: failure()
-        uses: actions/upload-artifact@v7
-        with:
-          name: benchmark-core-dumps
-          path: /tmp/core.*
-          if-no-files-found: ignore
-
-  build-retrace:
-    runs-on: ubuntu-latest
-    needs:
-      - build-linux
-      - test
-      - benchmark
-      - integration
-    permissions:
-      actions: write
-      contents: read
     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
+      # TEST_ROOT: ${{github.workspace}}/MobileGL/MG_Test
+      TEST_ROOT: ${{github.workspace}}
 
     steps:
       - name: Set Swap Space
-        uses: pierotofy/set-swap-space@v1.0
+        uses: pierotofy/set-swap-space@master
         with:
           swap-size-gb: 32
 
       - name: Checkout repo
-        uses: actions/checkout@v6
+        uses: actions/checkout@v4
         with:
-          submodules: recursive
+          submodules: true
 
       - name: Get CMake
-        uses: lukka/get-cmake@v4.3.3
-
-      - name: Restore ccache
-        uses: actions/cache/restore@v5
-        with:
-          path: .ccache
-          key: ${{ runner.os }}-test-${{ github.job }}-ccache-v1
-          restore-keys: |
-            ${{ runner.os }}-test-${{ 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
+        uses: lukka/get-cmake@latest
 
       - name: Update glslang external sources
-        working-directory: 3rdparty/glslang
+        working-directory: ${{env.TEST_ROOT}}/3rdparty/glslang
         run: python update_glslang_sources.py
 
-      - name: Install dependencies
+      - name: Install clang-20
         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
+          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: |
-          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}"
-
+          dpkg -l 'libc++*' || true
+          
       - name: Configure CMake
+        working-directory: ${{env.TEST_ROOT}}
         run: |
-          if [ "${{ secrets.ACTIONS_STEP_DEBUG }}" = "true" ]; then
-            BUILD_TYPE=Debug
+          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
           else
-            BUILD_TYPE=Release
+            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
           fi
+          
+      - name: Build
+        working-directory: ${{env.TEST_ROOT}}/build-test
+        run: cmake --build .
 
-          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: Release superseded ccache entry
-        if: github.ref_name == github.event.repository.default_branch
-        env:
-          GH_TOKEN: ${{ github.token }}
-          CACHE_KEY: ${{ runner.os }}-test-${{ github.job }}-ccache-v1
-        run: gh cache delete "${CACHE_KEY}" || true
-
-      - name: Save ccache
-        if: github.ref_name == github.event.repository.default_branch
-        continue-on-error: true
-        uses: actions/cache/save@v5
-        with:
-          path: .ccache
-          key: ${{ runner.os }}-test-${{ github.job }}-ccache-v1
-
-      - name: Normalize CTest command paths
+      - name: Test
+        working-directory: ${{env.TEST_ROOT}}/build-test/MobileGL/MG_Test
         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
-      - integration
-    outputs:
-      matrix: ${{ steps.trace-cases.outputs.matrix }}
-      names: ${{ steps.trace-cases.outputs.names }}
-    steps:
-      - name: Checkout repo
-        uses: actions/checkout@v6
-
-      - name: Load trace cases
-        id: trace-cases
-        run: |
-          echo "matrix=$(python3 tools/trace_replay/trace_cases.py --ci --format github-test-matrix)" >> "$GITHUB_OUTPUT"
-          echo "names=$(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: ${{ fromJSON(needs.trace-cases.outputs.names) }}
-    steps:
-      - name: Checkout repo
-        uses: actions/checkout@v6
-
-      - name: Derive trace fixture cache key
-        id: fixture-key
-        run: bash .github/scripts/trace-fixture-cache.sh key '${{ matrix.case }}'
-
-      - name: Restore trace fixture cache
-        id: fixture-cache
-        if: steps.fixture-key.outputs.cacheable == 'true'
-        uses: actions/cache/restore@v5
-        with:
-          path: ${{ steps.fixture-key.outputs.paths }}
-          key: ${{ steps.fixture-key.outputs.key }}
-
-      - name: Verify restored trace fixture
-        id: fixture-verify
-        if: steps.fixture-cache.outputs.cache-hit == 'true'
-        run: |
-          if bash .github/scripts/trace-fixture-cache.sh verify '${{ matrix.case }}'; then
-            echo "ok=true" >> "$GITHUB_OUTPUT"
+          if [ "${{ secrets.ACTIONS_STEP_DEBUG }}" == "true" ]; then
+            ctest -V
           else
-            echo "ok=false" >> "$GITHUB_OUTPUT"
-            echo "::warning::Cached fixture for ${{ matrix.case }} failed verification; falling back to the download path"
-            bash .github/scripts/trace-fixture-cache.sh reset '${{ matrix.case }}'
+            ctest
           fi
-
-      - name: Fetch trace fixture
-        if: steps.fixture-verify.outputs.ok != 'true'
-        run: bash .github/scripts/fetch-trace-fixture-lfs.sh '${{ matrix.case }}'
-
-      - name: Save trace fixture cache
-        if: steps.fixture-key.outputs.cacheable == 'true' && steps.fixture-cache.outputs.cache-hit != 'true'
-        uses: actions/cache/save@v5
-        with:
-          path: ${{ steps.fixture-key.outputs.paths }}
-          key: ${{ steps.fixture-key.outputs.key }}
-
-      - name: Stage trace fixture
-        run: |
-          safe_case="$(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: ${{ fromJSON(needs.trace-cases.outputs.matrix) }}
-
-    steps:
-      - name: Set Swap Space
-        uses: pierotofy/set-swap-space@v1.0
-        with:
-          swap-size-gb: 16
-
-      - name: Checkout repo
-        uses: actions/checkout@v6
-
-      - name: Download trace fixture
-        uses: actions/download-artifact@v8
-        with:
-          name: trace-fixture-${{ 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: |
-          ulimit -c unlimited
-          sudo sysctl -w kernel.core_pattern='/tmp/core.%e.%p'
-          if [ '${{ matrix.backend }}' = 'DirectVulkan' ]; then
-            export MOBILEGL_MAGMA_R11G11B10F_FALLBACK=1
-          fi
-          if [ '${{ matrix.backend }}' = 'DirectVulkan' ] \
-             && [ '${{ matrix.case }}' = 'minecraft-1.21.4-fabric-iris-iterationrp-in-world' ]; then
-            export MOBILEGL_FIX_ITERATIONRP_SUBGROUP_SCRATCH=1
-            export MOBILEGL_DERIVE_NUM_SUBGROUPS=1
-            export MOBILEGL_ITERATIONRP_FIX_BARRIER=1
-          fi
-          # The blended depth-write quirk auto-enables only on Qualcomm, which no CI
-          # runner has, so force it on for the OIT case it exists to fix. ForceOn
-          # bypasses only the vendor gate, so this exercises the real strip on
-          # lavapipe. The Android AVD lane deliberately leaves it off, keeping the
-          # unstripped path covered for the same trace.
-          if [ '${{ matrix.backend }}' = 'DirectVulkan' ] \
-             && [ '${{ matrix.case }}' = 'improved-transparency-minecraft-26.3' ]; then
-            export MOBILEGL_MAGMA_DISABLE_BLENDED_DEPTH_WRITE=1
-          fi
-          ctest -V --no-tests=error -R '^MobileGLTraceReplay\.${{ matrix.case }}\.${{ matrix.backend }}$'
-
-      - name: Upload core dumps
-        if: failure()
-        uses: actions/upload-artifact@v7
-        with:
-          name: retrace-core-dumps-${{ matrix.backend }}-${{ matrix.case }}
-          path: /tmp/core.*
-          if-no-files-found: ignore
-
-      - 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

@@ -14,17 +14,4 @@ MobileGLCodeManager
 .vscode
 .clangd
 MobileGL/MG_Test/build
-/build_*
-/cmake-build*
-.idea
-MobileGL/MG*/build*
-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/
-__pycache__/
-*.py[cod]
-/.gradle
+/build_*

.gitmodules

@@ -7,30 +7,12 @@
 [submodule "3rdparty/SPIRV-Cross"]
 	path = 3rdparty/SPIRV-Cross
 	url = https://github.com/KhronosGroup/SPIRV-Cross.git
+[submodule "include/FastSTL"]
+	path = include/FastSTL
+	url = https://github.com/MobileGL-Dev/FastSTL.git
 [submodule "3rdparty/tracy"]
 	path = 3rdparty/tracy
 	url = https://github.com/wolfpld/tracy.git
 [submodule "3rdparty/xxHash"]
 	path = 3rdparty/xxHash
 	url = https://github.com/Cyan4973/xxHash.git
-[submodule "3rdparty/VulkanMemoryAllocator"]
-	path = 3rdparty/VulkanMemoryAllocator
-	url = https://github.com/GPUOpen-LibrariesAndSDKs/VulkanMemoryAllocator.git
-[submodule "3rdparty/Vulkan-Utility-Libraries"]
-	path = 3rdparty/Vulkan-Utility-Libraries
-	url = https://github.com/KhronosGroup/Vulkan-Utility-Libraries.git
-[submodule "3rdparty/Vulkan-Headers"]
-	path = 3rdparty/Vulkan-Headers
-	url = https://github.com/KhronosGroup/Vulkan-Headers.git
-[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
-[submodule "3rdparty/asio"]
-	path = 3rdparty/asio
-	url = https://github.com/chriskohlhoff/asio.git
-[submodule "include/ska"]
-	path = include/ska
-	url = https://github.com/MobileGL-Dev/flat_hash_map.git

CMakeLists.txt

@@ -4,102 +4,15 @@ project("MobileGL")
 
 option(MOBILEGL_BUILD_TEST        "Build MobileGL tests"                             ON )
 option(MOBILEGL_BUILD_BENCHMARK   "Build MobileGL benchmarks"                        ON )
-# Headless end-to-end GPU scenarios (MobileGL/MG_IntegrationTest). They need a
-# real GPU/ICD to do anything, so they are off by default for CI; every scenario
-# skips cleanly where there is none. Registered under the `integration-gpu`
-# ctest label so a run can select or exclude them.
-option(MOBILEGL_BUILD_INTEGRATION_TEST "Build MobileGL headless GPU integration tests" OFF)
 option(MOBILEGL_FORCE_RELEASE_OPT "Enable Release optimization flags in Debug build" ON )
 option(MOBILEGL_ENABLE_TRACY      "Enable tracy for profiling"                       OFF)
-option(MOBILEGL_BUILD_TRACE_REPLAY "Build desktop apitrace replay runner"            OFF)
-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)
     set(MOBILEGL_BUILD_BENCHMARK  OFF CACHE BOOL "Build MobileGL benchmarks" FORCE)
-
-    # ------- Android API level policy: minimum 26, decided here and only here -------
-    # MobileGL ships against API 26: the codebase must not use any API introduced
-    # after 26. That usage constraint is enforced where it is real - the shipping
-    # gradle build compiles at minSdk 26, where a newer API is simply undeclared
-    # and fails to compile. Configuring at a HIGHER level is therefore allowed
-    # (nothing in the tree may rely on it), but a LOWER level would change the
-    # libc contract underneath the shipped library and is refused.
-    #
-    # This has to live at configure time because the level cannot be corrected
-    # from a source header. A `#define __ANDROID_API__ 26` in a common header
-    # only rewrites the macro for the bionic headers that happen to be included
-    # after it; any libc++ header pulled in earlier has already latched its
-    # feature macros at the real configure-time level. libc++ and bionic then
-    # disagree about which symbols exist - libc++ calls e.g.
-    # pthread_cond_clockwait while bionic, re-read at the lowered level, has
-    # hidden its declaration. MobileGL/Defines.h carried exactly that pin from
-    # the first commit until it was removed; this guard is what replaces it.
-    #
-    # Read the level back from the compiler target triple first. Its trailing
-    # number (aarch64-none-linux-android26) is precisely what clang turns into
-    # __ANDROID_API__, so it cannot disagree with the compile itself, and it is
-    # already past every NDK normalisation step - codename aliases, "latest",
-    # and per-ABI minimum pull-ups. ANDROID_PLATFORM_LEVEL is the fallback for
-    # generators/languages where the triple variable is not populated.
-    #
-    # Note CMAKE_SYSTEM_VERSION is deliberately NOT consulted: it holds the API
-    # level only under the NDK's newer toolchain path, and is a meaningless 1
-    # when ANDROID_USE_LEGACY_TOOLCHAIN_FILE is on (which is what AGP has been
-    # defaulting to). Reading it would fail every legacy-mode build.
-    set(MOBILEGL_ANDROID_API_LEVEL 26)
-
-    set(_mobilegl_android_api "")
-    foreach (_mobilegl_api_triple "${CMAKE_CXX_COMPILER_TARGET}"
-                                  "${CMAKE_C_COMPILER_TARGET}")
-        if (NOT _mobilegl_android_api AND
-            _mobilegl_api_triple MATCHES "-android([0-9]+)$")
-            set(_mobilegl_android_api "${CMAKE_MATCH_1}")
-        endif()
-    endforeach()
-
-    foreach (_mobilegl_api_var ANDROID_PLATFORM_LEVEL ANDROID_NATIVE_API_LEVEL
-                               ANDROID_PLATFORM)
-        if (NOT _mobilegl_android_api AND ${_mobilegl_api_var})
-            string(REGEX REPLACE "^android-" ""
-                   _mobilegl_android_api "${${_mobilegl_api_var}}")
-        endif()
-    endforeach()
-
-    if (NOT _mobilegl_android_api MATCHES "^[0-9]+$")
-        message(FATAL_ERROR
-            "MobileGL: could not determine the Android API level (got "
-            "\"${_mobilegl_android_api}\"). Configure with the NDK toolchain "
-            "file and -DANDROID_PLATFORM=android-${MOBILEGL_ANDROID_API_LEVEL}.")
-    elseif (_mobilegl_android_api LESS MOBILEGL_ANDROID_API_LEVEL)
-        message(FATAL_ERROR
-            "MobileGL requires at least Android API ${MOBILEGL_ANDROID_API_LEVEL}, "
-            "but this build resolved to API ${_mobilegl_android_api}.\n"
-            "Configure with -DANDROID_PLATFORM=android-${MOBILEGL_ANDROID_API_LEVEL} "
-            "(gradle builds get this from minSdk ${MOBILEGL_ANDROID_API_LEVEL}, so "
-            "check that minSdk instead of adding an override).")
-    elseif (_mobilegl_android_api GREATER MOBILEGL_ANDROID_API_LEVEL)
-        message(STATUS
-            "MobileGL: configuring at Android API ${_mobilegl_android_api} "
-            "(> shipping minimum ${MOBILEGL_ANDROID_API_LEVEL}). Allowed, but the "
-            "tree must not use post-${MOBILEGL_ANDROID_API_LEVEL} APIs - the "
-            "minSdk-${MOBILEGL_ANDROID_API_LEVEL} gradle build is the enforcing "
-            "compile.")
-    endif()
-
-    message(STATUS "MobileGL: Android API level ${_mobilegl_android_api}")
-
-    unset(_mobilegl_android_api)
-    unset(_mobilegl_api_var)
-    unset(_mobilegl_api_triple)
 endif()
 
-option(MOBILEGL_ENABLE_LTO "Build with ThinLTO/IPO" OFF)
-
-if ((NOT CMAKE_BUILD_TYPE STREQUAL "Debug" OR MOBILEGL_FORCE_RELEASE_OPT) AND MOBILEGL_ENABLE_LTO)
+if (NOT CMAKE_BUILD_TYPE STREQUAL "Debug" OR MOBILEGL_FORCE_RELEASE_OPT)
     # Check if ThinLTO or LTO is suppported
     include(CheckIPOSupported)
     include(CheckCCompilerFlag)
@@ -182,7 +95,6 @@ set(ENABLE_SPVREMAPPER         OFF CACHE BOOL "Enable SPVRemapper" FORCE)
 set(ENABLE_OPT                 ON  CACHE BOOL "Enable SPIRV-Tools opt usage in glslang" FORCE)
 set(BUILD_EXTERNAL             ON  CACHE BOOL "Build external deps in External/" FORCE)
 set(ENABLE_GLSLANG_INSTALL     OFF CACHE BOOL "Install glslang targets" FORCE)
-set(SPIRV_SKIP_EXECUTABLES     ON  CACHE BOOL "Skip building SPIRV-Tools executables" FORCE)
 
 set(SPIRV_CROSS_C_API          ON  CACHE BOOL "Enable C API" FORCE)
 set(SPIRV_CROSS_ENABLE_GLSL    ON  CACHE BOOL "Enable GLSL backend" FORCE)
@@ -192,20 +104,9 @@ set(SPIRV_CROSS_ENABLE_CPP     OFF CACHE BOOL "Disable C++ API target" FORCE)
 set(SPIRV_CROSS_CLI            OFF CACHE BOOL "Disable CLI binary" FORCE)
 set(SPIRV_CROSS_STATIC         ON  CACHE BOOL "Prefer static libs" FORCE)
 
-set(SPIRV_REFLECT_EXECUTABLE     OFF CACHE BOOL "Build spirv-reflect executable" FORCE)
-set(SPIRV_REFLECT_STATIC_LIB     ON  CACHE BOOL "Build a SPIRV-Reflect static library" FORCE)
-set(SPIRV_REFLECT_BUILD_TESTS    OFF CACHE BOOL "Build the SPIRV-Reflect test suite" FORCE)
-set(SPIRV_REFLECT_ENABLE_ASSERTS OFF CACHE BOOL  "Enable asserts for debugging" FORCE)
-set(SPIRV_REFLECT_ENABLE_ASAN    OFF CACHE BOOL "Use address sanitization" FORCE)
-set(SPIRV_REFLECT_INSTALL        OFF CACHE BOOL "Whether to install" FORCE)
-
 # add_subdirectory(3rdparty/DiligentCore)
 add_subdirectory(3rdparty/glslang)
 add_subdirectory(3rdparty/SPIRV-Cross)
-add_subdirectory(3rdparty/VulkanMemoryAllocator)
-add_subdirectory(3rdparty/Vulkan-Headers)
-add_subdirectory(3rdparty/Vulkan-Utility-Libraries)
-add_subdirectory(3rdparty/SPIRV-Reflect)
 
 set(XXHASH_BUILD_XXHSUM OFF)
 option(BUILD_SHARED_LIBS OFF)
@@ -226,13 +127,9 @@ endif ()
 set(SOURCE_FILES
     MobileGL/Init.cpp
     MobileGL/GlobalObjects.cpp
-    MobileGL/ConfigLoader.cpp
 
     MobileGL/MG_Util/Debug/Log.cpp
 
-    MobileGL/MG_Util/Async/JobNode.cpp
-    MobileGL/MG_Util/Async/ShaderCompilePool.cpp
-
     MobileGL/MG_Util/Math/VectorTypes.cpp
     MobileGL/MG_Util/Metrics/TextureMetrics.cpp
 
@@ -261,64 +158,22 @@ set(SOURCE_FILES
     MobileGL/MG_Util/Converters/GLToMG/RenderStateEnumConverter.cpp
     MobileGL/MG_Util/Converters/GLToMG/ProgramEnumConverter.cpp
     MobileGL/MG_Util/Converters/MGToMG/TextureEnumConverter.cpp
-    MobileGL/MG_Util/Converters/MGToVk/RenderStateEnumConverter.cpp
-    MobileGL/MG_Util/Converters/MGToVk/TextureEnumConverter.cpp
 
     MobileGL/MG_Util/Classifiers/TextureEnumClassifier.cpp
 
-    MobileGL/MG_Util/ShaderTranspiler/CompileEnv.cpp
     MobileGL/MG_Util/ShaderTranspiler/ShaderCompiler.cpp
     MobileGL/MG_Util/ShaderTranspiler/SpvcSession.cpp
     MobileGL/MG_Util/ShaderTranspiler/ShaderSourceProcessor.cpp
-    MobileGL/MG_Util/ShaderTranspiler/TranslationCache.cpp
     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/RenameBuiltinShadowingFunctionsPass.cpp
-    MobileGL/MG_Util/ShaderTranspiler/SpirvPasses/DecomposeWorkgroupVec3Pass.cpp
-    MobileGL/MG_Util/ShaderTranspiler/SpirvPasses/DecoratePositionInvariantPass.cpp
-    MobileGL/MG_Util/ShaderTranspiler/SpirvPasses/DemoteFloat64Pass.cpp
-    MobileGL/MG_Util/ShaderTranspiler/SpirvPasses/FlattenFloat64StorageBlockPass.cpp
-    MobileGL/MG_Util/ShaderTranspiler/SpirvPasses/LowerDrawParametersPass.cpp
-    MobileGL/MG_Util/ShaderTranspiler/SpirvPasses/LowerViewportIndexPass.cpp
-    MobileGL/MG_Util/ShaderTranspiler/SpirvPasses/PackDoubleVertexInputsPass.cpp
-    MobileGL/MG_Util/ShaderTranspiler/SpirvPasses/FlattenXfbInterfaceBlocksPass.cpp
-    MobileGL/MG_Util/ShaderTranspiler/SpirvPasses/UniquifyIoBlockNamesPass.cpp
-    MobileGL/MG_Util/ShaderTranspiler/SpirvPasses/SplitArrayVertexInputsPass.cpp
-    MobileGL/MG_Util/ShaderTranspiler/SpirvPasses/RebaseInstanceIndexPass.cpp
-    MobileGL/MG_Util/ShaderTranspiler/SpirvPasses/ZeroBaseVertexPass.cpp
-    MobileGL/MG_Util/ShaderTranspiler/SpirvPasses/DeriveNumSubgroupsPass.cpp
-    MobileGL/MG_Util/ShaderTranspiler/SpirvPasses/FixIterationRPBarrierPass.cpp
-    MobileGL/MG_Util/ShaderTranspiler/SpirvPasses/FixIterationRPSubgroupScratchPass.cpp
-    MobileGL/MG_Util/ShaderTranspiler/SpirvPasses/EmulateSubgroupsPass.cpp
-    MobileGL/MG_Util/ShaderTranspiler/SpirvPasses/NormalizeRectCoordinatesPass.cpp
-    MobileGL/MG_Util/ShaderTranspiler/SpirvPasses/Lower1DArrayImagesPass.cpp
-    MobileGL/MG_Util/ShaderTranspiler/SpirvPasses/Lower1DSampledImagesPass.cpp
-    MobileGL/MG_Util/ShaderTranspiler/SpirvPasses/BakeImageFormatsPass.cpp
-    MobileGL/MG_Util/ShaderTranspiler/SpirvPasses/WidenImageFormatsPass.cpp
-    MobileGL/MG_Util/ShaderTranspiler/SpirvPasses/ClampMultisampleFetchPass.cpp
-    MobileGL/MG_Util/ShaderTranspiler/SpirvPasses/PrivateToEntryLocalPass.cpp
-    MobileGL/MG_Util/ShaderTranspiler/SpirvPasses/StripUniformLocationsPass.cpp
-    MobileGL/MG_Util/ShaderTranspiler/SpirvPasses/StripUboMemberRelaxedPrecisionPass.cpp
-    MobileGL/MG_Util/ShaderTranspiler/SpirvPasses/StripNoPerspectivePass.cpp
-    MobileGL/MG_Util/ShaderTranspiler/SpirvPasses/EmulateNoPerspectivePass.cpp
-    MobileGL/MG_Util/ShaderTranspiler/SpirvPasses/LegalizeFragmentOutputIndexPass.cpp
-    MobileGL/MG_Util/ShaderTranspiler/SpirvPasses/LegalizeResourceArrayIndexPass.cpp
-    MobileGL/MG_Util/ShaderTranspiler/SpirvPasses/FlattenAtomicCounterBlockPass.cpp
 
     MobileGL/MG_Util/BackendLoaders/OpenGL/Loader.cpp
     MobileGL/MG_Util/BackendLoaders/Vulkan/Loader.cpp
 
-    MobileGL/MG_Util/SelfTest/DriverBugProbes.cpp
-    MobileGL/MG_Util/SelfTest/DriverPost.cpp
-    MobileGL/MG_Util/SelfTest/DriverPostIterationRPWitness.cpp
-
     MobileGL/MG_Util/Texture/PixelStoreProcessor.cpp
     MobileGL/MG_Util/Texture/TextureFormatProcessor.cpp
 
     MobileGL/MG_Impl/GLXImpl/Exporting/Definitions.cpp
-    MobileGL/MG_Impl/GLXImpl/GLXImpl.cpp
     MobileGL/MG_Impl/GLXImpl/LookUp/LookUp.cpp
 
     MobileGL/MG_Impl/EGLImpl/Exporting/Definitions.cpp
@@ -332,8 +187,6 @@ set(SOURCE_FILES
     MobileGL/MG_Impl/GLImpl/Framebuffer/Validators.cpp
     MobileGL/MG_Impl/GLImpl/Framebuffer/GL_Framebuffer.cpp
     MobileGL/MG_Impl/GLImpl/Program/GL_Program.cpp
-    MobileGL/MG_Impl/GLImpl/Program/ProgramInterface.cpp
-    MobileGL/MG_Impl/GLImpl/Program/GL_ProgramPipeline.cpp
     MobileGL/MG_Impl/GLImpl/Texture/GL_Texture.cpp
     MobileGL/MG_Impl/GLImpl/Texture/Validators.cpp
     MobileGL/MG_Impl/GLImpl/Texture/ProxyTexture.cpp
@@ -344,7 +197,6 @@ 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
@@ -356,30 +208,17 @@ set(SOURCE_FILES
     MobileGL/MG_Backend/DirectGLES/BackendObject_DirectGLES.cpp
     MobileGL/MG_Backend/DirectGLES/Utils.cpp
     MobileGL/MG_Backend/DirectGLES/Managers.cpp
-    MobileGL/MG_Backend/DirectGLES/MultiDraw.cpp
 
-    MobileGL/MG_Backend/DirectVulkan/DirectVulkan.cpp
-    MobileGL/MG_Backend/DirectVulkan/BackendObject_DirectVulkan.cpp
-    MobileGL/MG_Backend/DirectVulkan/VmaImpl.cpp
-    MobileGL/MG_Backend/DirectVulkan/Renderer/VulkanRenderer.cpp
-    MobileGL/MG_Backend/DirectVulkan/Renderer/SwapchainObject.cpp
-    MobileGL/MG_Backend/DirectVulkan/Renderer/FrameContext.cpp
-    MobileGL/MG_Backend/DirectVulkan/Renderer/PipelineFactory.cpp
-    MobileGL/MG_Backend/DirectVulkan/Renderer/ProgramFactory.cpp
-        MobileGL/MG_Backend/DirectVulkan/Renderer/UniformManager.cpp
-    MobileGL/MG_Backend/DirectVulkan/Renderer/BufferArena.cpp
-    MobileGL/MG_Backend/DirectVulkan/Renderer/VkBufferManager.cpp
-    MobileGL/MG_Backend/DirectVulkan/Renderer/VertexInputStateBuilder.cpp
-    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
+    MobileGL/MG_Backend/DirectVulkanTMP/DirectVulkanTMP.cpp
+    MobileGL/MG_Backend/DirectVulkanTMP/TmpImpl.cpp
+    MobileGL/MG_Backend/DirectVulkanTMP/BackendObject_DirectVulkanTMP.cpp
+    MobileGL/MG_Backend/DirectVulkanTMP/Renderer/VulkanContext.cpp
+    MobileGL/MG_Backend/DirectVulkanTMP/Renderer/SwapchainManager.cpp
+    MobileGL/MG_Backend/DirectVulkanTMP/Renderer/PipelineManager.cpp
+    MobileGL/MG_Backend/DirectVulkanTMP/Renderer/FrameContext.cpp
+    MobileGL/MG_Backend/DirectVulkanTMP/Managers/ProgramManager.cpp
 
     MobileGL/MG_State/GLState/Core.cpp
-    MobileGL/MG_State/EGLState/Core.cpp
     MobileGL/MG_State/GLState/ErrorState/Error.cpp
     MobileGL/MG_State/GLState/BufferState/BufferState.cpp
     MobileGL/MG_State/GLState/BufferState/BufferObject.cpp
@@ -395,13 +234,7 @@ set(SOURCE_FILES
     MobileGL/MG_State/GLState/TextureState/TextureUnit.cpp
     MobileGL/MG_State/GLState/TextureState/TextureState.cpp
     MobileGL/MG_State/GLState/ProgramState/ProgramObject.cpp
-    MobileGL/MG_State/GLState/ProgramState/ProgramLinkTask.cpp
-    MobileGL/MG_State/GLState/ProgramState/ProgramTranslationCache.cpp
-    MobileGL/MG_State/GLState/ProgramState/ProgramSpirvTask.cpp
-    MobileGL/MG_State/GLState/ProgramState/ShaderCompileTask.cpp
     MobileGL/MG_State/GLState/ProgramState/ShaderObject.cpp
-    MobileGL/MG_State/GLState/ProgramState/ShaderPreprocessCache.cpp
-    MobileGL/MG_State/GLState/ProgramState/ShaderCompileAdoptionMap.cpp
     MobileGL/MG_State/GLState/ProgramState/ProgramState.cpp
     MobileGL/MG_State/GLState/RenderState/RenderState.cpp
     MobileGL/MG_State/GLState/FramebufferState/FramebufferObject.cpp
@@ -412,58 +245,14 @@ 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
-        MobileGL/MG_Util/SelfTest/DriverBenchJni.cpp
-    )
-endif()
-
-if (WIN32)
-    list(APPEND SOURCE_FILES
-        MobileGL/MG_Impl/WGLImpl/WGLImpl.cpp
-        MobileGL/MG_Impl/WGLImpl/Exporting/Definitions.cpp
-    )
-endif()
-
-# The shader-compile pool runs standalone Asio on real threads. This host's glibc (>= 2.34)
-# merged pthread into libc, so it links without asking, but the NDK and musl are not
-# guaranteed to be as forgiving - ask for it explicitly rather than rely on the accident.
-find_package(Threads REQUIRED)
-
 set(MOBILEGL_LINK_LIBRARIES
         glslang::glslang
         spirv-cross-c
         SPIRV-Tools-opt
         SPIRV-Tools
         xxHash::xxhash
-        GPUOpen::VulkanMemoryAllocator
-        Vulkan::UtilityHeaders
-        spirv-reflect-static
-        Threads::Threads
 )
 
-set(MOBILEGL_COMPILE_DEF
-        -DVMA_STATIC_VULKAN_FUNCTIONS=0
-        -DVMA_DYNAMIC_VULKAN_FUNCTIONS=1
-        -DVMA_VULKAN_VERSION=1001000
-        # Header-only Asio, no Boost, no deprecated interfaces. Set on the definition list
-        # rather than per-target so the shared library and the _s static target agree.
-        -DASIO_STANDALONE
-        -DASIO_NO_DEPRECATED
-)
-
-message(STATUS "MOBILEGL_COMPILE_DEF=${MOBILEGL_COMPILE_DEF}")
-
 set(MOBILEGL_INCLUDE_DIR
         ${CMAKE_SOURCE_DIR}/include
         ${CMAKE_SOURCE_DIR}/MobileGL
@@ -471,24 +260,12 @@ set(MOBILEGL_INCLUDE_DIR
         ${spirv-tools_SOURCE_DIR}/include
         ${spirv-tools_BINARY_DIR}
         ${SPIRV-Headers_SOURCE_DIR}/include
-        # Header-only submodule: no add_subdirectory, no link target. Only
-        # MG_Util/Async/ShaderCompilePool.cpp includes it, and it stays behind that file's
-        # pimpl so no consumer target needs this path.
-        ${CMAKE_SOURCE_DIR}/3rdparty/asio/include
 )
 
-add_library(${CMAKE_PROJECT_NAME} SHARED
+add_library(${CMAKE_PROJECT_NAME} SHARED 
     ${SOURCE_FILES}
 )
 
-if (WIN32)
-    # The wgl* entry points are exported via .def (see the comment in wgl.def);
-    # only the shared library links it.
-    target_sources(${CMAKE_PROJECT_NAME} PRIVATE
-        MobileGL/MG_Impl/WGLImpl/Exporting/wgl.def
-    )
-endif()
-
 if (CMAKE_BUILD_TYPE STREQUAL "Debug")
     set_target_properties(${CMAKE_PROJECT_NAME} PROPERTIES
         C_VISIBILITY_PRESET default
@@ -508,41 +285,10 @@ target_include_directories(${CMAKE_PROJECT_NAME} PUBLIC
 )
 
 target_link_libraries(${CMAKE_PROJECT_NAME}
-    PUBLIC
+    PRIVATE
     ${MOBILEGL_LINK_LIBRARIES}
 )
 
-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(WIN32)
-    # Drop-in for the classic GL loader path: a copy named opengl32.dll placed
-    # next to a host executable is what LoadLibrary("opengl32.dll") and gdi32's
-    # pixel-format forwarding will resolve.
-    add_custom_command(TARGET ${CMAKE_PROJECT_NAME} POST_BUILD
-        COMMAND ${CMAKE_COMMAND} -E copy_if_different
-                "$<TARGET_FILE:${CMAKE_PROJECT_NAME}>"
-                "$<TARGET_FILE_DIR:${CMAKE_PROJECT_NAME}>/opengl32.dll"
-        COMMENT "Creating opengl32.dll drop-in copy"
-    )
-endif()
-
 if(NOT ANDROID)
     add_library(${CMAKE_PROJECT_NAME}_s STATIC 
         ${SOURCE_FILES}
@@ -567,15 +313,9 @@ if(NOT ANDROID)
     )
 
     target_link_libraries(${CMAKE_PROJECT_NAME}_s
-        PUBLIC
+        PRIVATE
         ${MOBILEGL_LINK_LIBRARIES}
     )
-
-    target_compile_definitions(${CMAKE_PROJECT_NAME}_s
-            PUBLIC
-            ${MOBILEGL_COMPILE_DEF}
-            MOBILEGL_LOG_ACTIVE_LEVEL=${MOBILEGL_LOG_ACTIVE_LEVEL}
-    )
 endif()
 
 if (TRACY_ENABLE)
@@ -593,62 +333,7 @@ if (ANDROID)
     )
 endif()
 
-if (APPLE AND NOT MOBILEGL_IOS)
-    # MobileGL statically embeds glslang, SPIRV-Tools, and SPIRV-Cross. When
-    # this dylib is injected with DYLD_INSERT_LIBRARIES, exporting those C++
-    # symbols interposes incompatible copies embedded by host libraries such
-    # as shaderc. Keep only the public GL/EGL/CGL loader surface globally
-    # visible; GetProcAddress can still return pointers to hidden internals.
-    set(MOBILEGL_MACOS_EXPORTED_SYMBOLS
-        "${CMAKE_CURRENT_SOURCE_DIR}/MobileGL/MG_Impl/DyldInterpose/ExportedSymbols.txt")
-    target_link_options(${CMAKE_PROJECT_NAME} PRIVATE
-        "LINKER:-exported_symbols_list,${MOBILEGL_MACOS_EXPORTED_SYMBOLS}")
-    set_property(TARGET ${CMAKE_PROJECT_NAME} APPEND PROPERTY
-        LINK_DEPENDS "${MOBILEGL_MACOS_EXPORTED_SYMBOLS}")
-
-    target_link_libraries(${CMAKE_PROJECT_NAME} PUBLIC
-        "-framework Cocoa"
-        "-framework CoreVideo"
-        "-framework QuartzCore"
-        "-framework Foundation"
-        "-framework OpenGL"
-        objc)
-    if(TARGET ${CMAKE_PROJECT_NAME}_s)
-        target_link_libraries(${CMAKE_PROJECT_NAME}_s PUBLIC
-            "-framework Cocoa"
-            "-framework CoreVideo"
-            "-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 "${MOBILEGL_VULKAN_LIBRARY}")
-        endif()
-    endif()
-endif()
-
-if (NOT ANDROID AND NOT MOBILEGL_IOS)
+if (NOT ANDROID)
     find_package(Vulkan)
     if (Vulkan_FOUND)
         target_link_libraries(${CMAKE_PROJECT_NAME} PUBLIC Vulkan::Vulkan Vulkan::Headers)
@@ -656,40 +341,12 @@ if (NOT ANDROID AND NOT MOBILEGL_IOS)
         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)
     endif()
 
-    # After MG_Test so googletest is already available when the unit tests are
-    # built; the module fetches its own copy when they are not.
-    if (MOBILEGL_BUILD_INTEGRATION_TEST)
-        add_subdirectory(MobileGL/MG_IntegrationTest)
-    endif()
-
     if (MOBILEGL_BUILD_BENCHMARK)
         add_subdirectory(MobileGL/MG_Benchmark)
     endif()
-
-    if (MOBILEGL_BUILD_TRACE_REPLAY)
-        add_subdirectory(tools/trace_replay)
-    endif()
-endif()
-
-# The integration binary is also useful as a standalone adb-shell executable.
-# Android cannot use the desktop-only MobileGL_s target, so its CMake module
-# links libMobileGL.so and creates an AImageReader-backed window instead.
-if (ANDROID AND MOBILEGL_BUILD_INTEGRATION_TEST)
-    add_subdirectory(MobileGL/MG_IntegrationTest)
 endif()

MobileGL/Config.h

@@ -14,217 +14,8 @@ 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, 8, 0, "-dev", VersionType::Development};
+    inline const Version CoreVersion = {26, 2, 0, "-dev", VersionType::Development};
     inline const VersionStringFormatAttrib DefaultVersionStringFormatAttrib = {2, 2, 0, true, true};
-    inline const Uint64 CacheVersion = 0;
 
     extern BackendType ActiveBackendType;
-
-    // Tri-state override for device-specific quirks: Auto lets the detected device decide,
-    // ForceOn/ForceOff bypass the detection in either direction. ForceOn only bypasses the
-    // device gate - each quirk keeps its structural safety checks.
-    enum class QuirkOverride : Uint8 {
-        Auto = 0,
-        ForceOn,
-        ForceOff,
-    };
-
-    // Preferred DirectVulkan dispatch tier for the glMultiDraw* families. A preference,
-    // never a demand: the renderer clamps it to what the device supports at device
-    // creation, falling down the chain ext -> indirect -> unroll with one log line.
-    enum class MultiDrawMode : Uint8 {
-        Auto = 0, // unset: best supported tier
-        Ext,      // VK_EXT_multi_draw: one vkCmdDrawMultiEXT / vkCmdDrawMultiIndexedEXT
-        Indirect, // multiDrawIndirect feature: one vkCmdDraw*Indirect over a transient command array
-        Unroll,   // one vkCmdDraw* per sub-draw
-    };
-
-    // Preferred DirectGLES emulation tier for glMultiDrawElements(BaseVertex). GLES has no
-    // such entry point in core, so every tier below is an emulation; they differ only in
-    // which driver capability they lean on and how many driver calls a batch costs. Like
-    // the Magma knob this is a preference, clamped at resolution time to what the ES
-    // driver actually supports, with one log line when it falls back.
-    enum class GLESMultiDrawMode : Uint8 {
-        Auto = 0,      // unset: best supported tier
-        Ext,           // one glMultiDrawElementsBaseVertexEXT
-        MultiIndirect, // one glMultiDrawElementsIndirectEXT over a scratch command buffer
-        Indirect,      // one glDrawElementsIndirect per sub-draw over that same buffer
-        BaseVertex,    // one glDrawElementsBaseVertex per sub-draw
-        DrawElements,  // baseVertex folded into a scratch index buffer on the CPU, then plain
-                       // glDrawElements per sub-draw (for drivers with no base-vertex draw at all)
-        Compute,       // a compute shader flattens every sub-draw into one rebased index buffer,
-                       // drawn by a single glDrawElements
-    };
-
-    // Feature toggles parsed once from environment variables in MG_ConfigLoader::Init()
-    // (ConfigLoader.cpp), before the accepted-env map is destroyed. All Bool fields share
-    // one truthy rule: the variable is set, non-empty, not "0", and not "false"
-    // (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_ENABLE_SPIRV_VALIDATION: validate generated and transformed SPIR-V.
-        // Disabled by default because validation is a diagnostics-only cost.
-        Bool EnableSpirvValidation = 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,
-        // including the opt-in emulated compute path below.
-        Bool DisableSubgroup = false;
-        // MOBILEGL_MAGMA_EMULATE_SUBGROUP: implement GL_KHR_shader_subgroup's compute
-        // stage on a 32-lane VIRTUAL subgroup lowered to workgroup-shared memory
-        // (ShaderTranspiler::EmulateSubgroupsPass). Strictly a last resort: it only ever
-        // engages when this flag is set AND the device has no native subgroup support at
-        // all - a device with real subgroup operations always uses them natively,
-        // whatever their width (the known iterationRP defect is patched by
-        // FixIterationRPSubgroupScratch below instead). Off by default.
-        Bool MagmaEmulateSubgroup = false;
-        // MOBILEGL_FIX_ITERATIONRP_SUBGROUP_SCRATCH: patch iterationRP's own bug - the
-        // pack declares `shared vec2 prefixSumCache[32]` for a 512-invocation exposure
-        // reduction and indexes it by gl_SubgroupID, so any device with sub-16-lane
-        // subgroups (8-lane lavapipe -> 64 subgroups) writes shared memory out of
-        // bounds. The pass grows that one array to what the device's topology needs and
-        // touches nothing else; it only rewrites modules positively matching the pack's
-        // reduction fingerprint (ShaderTranspiler::FixIterationRPSubgroupScratchPass),
-        // so every other shader passes through byte-identical - as does iterationRP
-        // itself on >= 16-lane devices. Auto is ON; ForceOff replays the pack's bug
-        // verbatim.
-        QuirkOverride FixIterationRPSubgroupScratch = QuirkOverride::Auto;
-        // MOBILEGL_ITERATIONRP_FIX_BARRIER: repair Program 203's missing workgroup
-        // rendezvous between its two reductions over prefixSumCache. Off by default and
-        // fingerprint-gated by FixIterationRPBarrierPass when enabled.
-        Bool IterationRPFixBarrier = false;
-        // MOBILEGL_DERIVE_NUM_SUBGROUPS: replace compute gl_NumSubgroups loads with
-        // ceil(workgroup invocations / gl_SubgroupSize) on the NATIVE subgroup path
-        // (ShaderTranspiler::DeriveNumSubgroupsPass). Auto is ON: GL requires
-        // gl_SubgroupID < gl_NumSubgroups, Adreno's builtin reports 1 while the same
-        // dispatch emits IDs 0..7, and the derived value is the one Vulkan guarantees
-        // whenever the pipeline can request REQUIRE_FULL_SUBGROUPS (which the renderer
-        // does whenever local_size_x is a multiple of the native width). ForceOff returns
-        // to the raw driver builtin.
-        QuirkOverride DeriveNumSubgroups = QuirkOverride::Auto;
-        // MOBILEGL_ADVERTISE_FP64: add GL_ARB_gpu_shader_fp64 to the advertised extension
-        // string. `double` in a shader always WORKS - it is narrowed to 32 bits before any
-        // module reaches a backend (ShaderTranspiler::DemoteFloat64Pass) - but the extension
-        // promises 64-bit precision, and that is the one thing the narrowing cannot deliver.
-        // Off by default so an application that checks the string before using doubles keeps
-        // its float path; on for measuring what the conformance suite makes of the demoted
-        // precision. See the DemoteFloat64Pass header and the "fp64" POST row.
-        Bool AdvertiseFp64 = 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_AVOID_EXPLICIT_LOD_BIAS: leave an already-explicit LOD argument alone when
-        // emulating GL_TEXTURE_LOD_BIAS, instead of adding the bias uniform to it. Injecting
-        // the uniform turns a compile-time-constant LOD into a runtime expression, which
-        // sends ANGLE + llvmpipe down a mip-selection path that dereferences a NULL
-        // descriptor and kills the process. Deviates from spec (Vulkan adds the bias to
-        // OpImageSampleExplicitLod), so it is an avoidance for that stack only.
-        Bool AvoidExplicitLodBias = 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_ESPRYT_FORCE_DS_READBACK_EMULATION: make DirectGLES skip the native ES
-        // depth/stencil reads and always go through the shader-sampling emulation. Core GL
-        // ES has no depth or stencil readback, but some drivers accept it anyway (Mesa does,
-        // Adreno does not), which means the emulation is dead code on exactly the stack the
-        // headless suite runs on. This forces it live so the scenarios and the CTS can
-        // exercise the path, and gives the device an A/B lever over the same choice.
-        Bool EsprytForceDepthStencilReadbackEmulation = false;
-        // MOBILEGL_RELAXED_SEMANTICS: relax strict core-profile rules (e.g. VAO-0 draws,
-        // texture-name reuse after delete) even on contexts that explicitly requested a core
-        // profile. Without it, relaxed semantics still apply to every context that did not
-        // explicitly request a core profile via EGL_CONTEXT_OPENGL_PROFILE_MASK / a >=3.1
-        // version request.
-        Bool RelaxedSemantics = false;
-        // MOBILEGL_MAGMA_DISABLE_BLENDED_DEPTH_WRITE: overrides the DirectVulkan quirk that
-        // strips depth writes from accumulation-blended pipelines (MIN/MAX or additive
-        // ONE+ONE - the multi-pass depth-equality signature) on drivers without
-        // cross-pipeline vertex position invariance. Sorted-transparency "over" blends,
-        // gl_FragDepth writers, and fully color-masked attachments are exempt (see
-        // PipelineFactory::ShouldSuppressDepthWrite). Auto detects Qualcomm.
-        QuirkOverride MagmaDisableBlendedDepthWriteQuirk = QuirkOverride::Auto;
-        // MOBILEGL_DISABLE_ROBUST_BUFFER_ACCESS: leave the Vulkan robustBufferAccess device
-        // feature off. It is enabled by default to match GL's defined out-of-range fetch
-        // behavior; this escape hatch exists to measure or dodge its GPU cost on a device.
-        Bool DisableRobustBufferAccess = false;
-        // MOBILEGL_MAGMA_MULTIDRAW_MODE: preferred DirectVulkan multi-draw dispatch tier
-        // ("ext" | "indirect" | "unroll", see MultiDrawMode). Clamped to device support;
-        // unset picks the best supported tier.
-        MultiDrawMode MagmaMultiDrawMode = MultiDrawMode::Auto;
-        // MOBILEGL_ESPRYT_MULTIDRAW_MODE: preferred DirectGLES glMultiDrawElements emulation
-        // tier ("ext" | "multiindirect" | "indirect" | "basevertex" | "drawelements" |
-        // "compute", see GLESMultiDrawMode). Clamped to driver support; unset picks the best
-        // supported tier, which never includes "compute" - see the note on its resolution.
-        GLESMultiDrawMode EsprytMultiDrawMode = GLESMultiDrawMode::Auto;
-        // MOBILEGL_ASYNC_SHADER_COMPILE: overrides asynchronous shader compilation. Unset
-        // keeps the built-in default (MG_Util::Async::kAsyncShaderCompileDefault); falsy
-        // forces every glCompileShader/glLinkProgram to run synchronously on the calling
-        // thread AND withdraws GL_KHR_parallel_shader_compile, so the single switch reverts
-        // both the threading and the application-visible behaviour change.
-        QuirkOverride AsyncShaderCompile = QuirkOverride::Auto;
-        // MOBILEGL_ASYNC_SHADER_COMPILE_THREADS: shader-compile worker count. 0 (unset) means
-        // auto, which is min(4, big cores); an explicit value is honoured as given.
-        Uint32 AsyncShaderCompileThreads = 0;
-        // MOBILEGL_ASYNC_OPTIMISTIC_SHADER_STATUS: while a compile job is still in flight,
-        // glGetShaderiv(GL_COMPILE_STATUS) answers GL_TRUE and the shader info log reads
-        // empty, WITHOUT joining the job (latched per compile - see
-        // ShaderObject::TakeOptimisticCompileAnswer). A deliberate, bounded spec violation:
-        // a real failure still fails the program link with the compile log quoted. It
-        // exists for applications that compile hundreds of shaders serially and read the
-        // status right after each glCompileShader - Iris's shader-pack load - where those
-        // per-shader joins are what serializes the batch on its main path (Iris's gbuffer
-        // phase issues no program-level query between programs; program-level LINK_STATUS
-        // and the program info log still join truthfully, so paths that check each link
-        // immediately stay serial by their own construction). Off by default; never
-        // advertise it.
-        QuirkOverride AsyncOptimisticShaderStatus = QuirkOverride::Auto;
-        // MOBILEGL_SHADER_CACHE: the three-level, in-memory shader translation memo
-        // (MG_Util/ShaderTranspiler/TranslationCache.h). The levels follow the GL
-        // entry points - L1c memoizes one glCompileShader's PARSE VERDICT, L1 a
-        // linked program's whole front end, L2 DirectGLES's emitted ESSL. Auto is
-        // ON; ForceOff turns ALL THREE off and makes every translation run from
-        // scratch. The escape hatch exists because a wrong cache hit is a silently
-        // miscompiled shader: if a device ever renders differently with the cache
-        // on, one run with this falsy says so.
-        QuirkOverride ShaderTranslationCache = QuirkOverride::Auto;
-        // MOBILEGL_FORCE_VIEWPORT_ARRAY_EMULATION: DirectGLES' gl_ViewportIndex routing
-        // emulation - the builtin becomes a flat varying, the fragment stage gets a
-        // per-pass gate, and a routed draw is REPLAYED once per distinct viewport state
-        // with the real glViewport/glScissor/glDepthRangef set for it. Auto is ON, and
-        // it is ON even where the driver advertises GL_OES_viewport_array, because that
-        // extension only ever gave the SHADER a compilable name: MobileGL has never
-        // programmed a driver's INDEXED viewport state (SyncRenderState pushes index 0
-        // and nothing else), so on an extension-capable driver every index rasterized as
-        // index 0 exactly as it did without one. ForceOff returns to that behaviour -
-        // the pre-emulation path, extension passthrough where it exists and
-        // LowerViewportIndexPass' demote-to-a-plain-global where it does not - and is
-        // the negative control the emulation is measured against.
-        QuirkOverride ViewportArrayEmulation = QuirkOverride::Auto;
-    };
-    extern FeaturesTable Features;
 } // namespace MobileGL::MG_Config

MobileGL/ConfigLoader.cpp

@@ -1,228 +0,0 @@
-// MobileGL - MobileGL/ConfigLoader.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 "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;
-
-    static Bool IsAcceptedPrefix(const String& key) {
-        return (key.compare(0, 6, "LIBGL_") == 0 || key.compare(0, 9, "MOBILEGL_") == 0);
-    }
-
-    inline void InitializeAcceptedEnvVariables() {
-        if (!acceptedEnvVariablesMap) {
-            acceptedEnvVariablesMap = MakeUnique<UnorderedMap<String, String>>();
-        } else {
-            acceptedEnvVariablesMap->clear();
-        }
-
-        char** envPtr = nullptr;
-
-#ifdef _WIN32
-        envPtr = _environ;
-#else // POSIX
-        envPtr = ::environ;
-#endif
-
-        if (envPtr == nullptr) return;
-
-        for (char** env = envPtr; *env != nullptr; ++env) {
-            String entry(*env);
-            SizeT pos = entry.find('=');
-            if (pos != String::npos) {
-                String key = entry.substr(0, pos);
-                String value = entry.substr(pos + 1);
-
-                if (IsAcceptedPrefix(key)) {
-                    (*acceptedEnvVariablesMap)[key] = value;
-                    MGLOG_D("Config: Accepted env variable: %s=%s", key.c_str(), value.c_str());
-                }
-            }
-        }
-    }
-
-    inline void QueryEnvVariable(const String& key, String& outValue, const String& defaultValue) {
-        auto it = acceptedEnvVariablesMap->find(key);
-        if (it != acceptedEnvVariablesMap->end()) {
-            outValue = it->second;
-        } else {
-            outValue = defaultValue;
-        }
-    }
-
-    // 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);
-    }
-
-    // Quirk overrides are tri-state: an unset variable keeps device auto-detection, a truthy
-    // value forces the quirk on, anything else set ("0", "false", "") forces it off.
-    inline MG_Config::QuirkOverride QueryEnvQuirkOverride(const String& key) {
-        auto it = acceptedEnvVariablesMap->find(key);
-        if (it == acceptedEnvVariablesMap->end()) {
-            return MG_Config::QuirkOverride::Auto;
-        }
-        return IsTruthyValue(it->second) ? MG_Config::QuirkOverride::ForceOn
-                                         : MG_Config::QuirkOverride::ForceOff;
-    }
-
-    // Multi-draw mode is a named-value preference: unset keeps Auto (best supported tier),
-    // a recognized name selects that tier as the ceiling, anything else warns and keeps Auto.
-    inline MG_Config::MultiDrawMode QueryEnvMultiDrawMode(const String& key) {
-        auto it = acceptedEnvVariablesMap->find(key);
-        if (it == acceptedEnvVariablesMap->end()) {
-            return MG_Config::MultiDrawMode::Auto;
-        }
-        String lowered = it->second;
-        std::transform(lowered.begin(), lowered.end(), lowered.begin(),
-                       [](unsigned char c) { return static_cast<char>(std::tolower(c)); });
-        if (lowered == "ext") return MG_Config::MultiDrawMode::Ext;
-        if (lowered == "indirect") return MG_Config::MultiDrawMode::Indirect;
-        if (lowered == "unroll") return MG_Config::MultiDrawMode::Unroll;
-        if (lowered.empty() || lowered == "auto") return MG_Config::MultiDrawMode::Auto;
-        MGLOG_W("Config: Ignoring invalid env variable %s='%s'; expected ext|indirect|unroll|auto, using auto",
-                key.c_str(), it->second.c_str());
-        return MG_Config::MultiDrawMode::Auto;
-    }
-
-    // Same contract as QueryEnvMultiDrawMode, over the DirectGLES tier names.
-    inline MG_Config::GLESMultiDrawMode QueryEnvGLESMultiDrawMode(const String& key) {
-        auto it = acceptedEnvVariablesMap->find(key);
-        if (it == acceptedEnvVariablesMap->end()) {
-            return MG_Config::GLESMultiDrawMode::Auto;
-        }
-        String lowered = it->second;
-        std::transform(lowered.begin(), lowered.end(), lowered.begin(),
-                       [](unsigned char c) { return static_cast<char>(std::tolower(c)); });
-        if (lowered == "ext") return MG_Config::GLESMultiDrawMode::Ext;
-        if (lowered == "multiindirect") return MG_Config::GLESMultiDrawMode::MultiIndirect;
-        if (lowered == "indirect") return MG_Config::GLESMultiDrawMode::Indirect;
-        if (lowered == "basevertex") return MG_Config::GLESMultiDrawMode::BaseVertex;
-        if (lowered == "drawelements") return MG_Config::GLESMultiDrawMode::DrawElements;
-        if (lowered == "compute") return MG_Config::GLESMultiDrawMode::Compute;
-        if (lowered.empty() || lowered == "auto") return MG_Config::GLESMultiDrawMode::Auto;
-        MGLOG_W("Config: Ignoring invalid env variable %s='%s'; expected "
-                "ext|multiindirect|indirect|basevertex|drawelements|compute|auto, using auto",
-                key.c_str(), it->second.c_str());
-        return MG_Config::GLESMultiDrawMode::Auto;
-    }
-
-    inline Uint32 QueryEnvUint32(const String& key, Uint32 defaultValue, Uint32 minValue, Uint32 maxValue) {
-        auto it = acceptedEnvVariablesMap->find(key);
-        if (it == acceptedEnvVariablesMap->end()) {
-            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.EnableSpirvValidation = QueryEnvFlag("MOBILEGL_ENABLE_SPIRV_VALIDATION");
-        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.MagmaEmulateSubgroup = QueryEnvFlag("MOBILEGL_MAGMA_EMULATE_SUBGROUP");
-        features.FixIterationRPSubgroupScratch =
-            QueryEnvQuirkOverride("MOBILEGL_FIX_ITERATIONRP_SUBGROUP_SCRATCH");
-        features.IterationRPFixBarrier = QueryEnvFlag("MOBILEGL_ITERATIONRP_FIX_BARRIER");
-        features.DeriveNumSubgroups = QueryEnvQuirkOverride("MOBILEGL_DERIVE_NUM_SUBGROUPS");
-        features.AdvertiseFp64 = QueryEnvFlag("MOBILEGL_ADVERTISE_FP64");
-        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.AvoidExplicitLodBias = QueryEnvFlag("MOBILEGL_AVOID_EXPLICIT_LOD_BIAS");
-        features.CoherentAsFlush = QueryEnvFlag("MOBILEGL_COHERENT_AS_FLUSH");
-        features.TraceSkipAutodestroy = QueryEnvFlag("MOBILEGL_TRACE_SKIP_AUTODESTROY");
-        features.DisableUboRing = QueryEnvFlag("MOBILEGL_DISABLE_UBO_RING");
-        features.EsprytForceDepthStencilReadbackEmulation =
-            QueryEnvFlag("MOBILEGL_ESPRYT_FORCE_DS_READBACK_EMULATION");
-        features.RelaxedSemantics = QueryEnvFlag("MOBILEGL_RELAXED_SEMANTICS");
-        features.MagmaDisableBlendedDepthWriteQuirk =
-            QueryEnvQuirkOverride("MOBILEGL_MAGMA_DISABLE_BLENDED_DEPTH_WRITE");
-        features.DisableRobustBufferAccess = QueryEnvFlag("MOBILEGL_DISABLE_ROBUST_BUFFER_ACCESS");
-        features.MagmaMultiDrawMode = QueryEnvMultiDrawMode("MOBILEGL_MAGMA_MULTIDRAW_MODE");
-        features.EsprytMultiDrawMode = QueryEnvGLESMultiDrawMode("MOBILEGL_ESPRYT_MULTIDRAW_MODE");
-        features.AsyncShaderCompile = QueryEnvQuirkOverride("MOBILEGL_ASYNC_SHADER_COMPILE");
-        features.AsyncShaderCompileThreads = QueryEnvUint32("MOBILEGL_ASYNC_SHADER_COMPILE_THREADS", 0, 0, 64);
-        features.AsyncOptimisticShaderStatus =
-            QueryEnvQuirkOverride("MOBILEGL_ASYNC_OPTIMISTIC_SHADER_STATUS");
-        features.ShaderTranslationCache = QueryEnvQuirkOverride("MOBILEGL_SHADER_CACHE");
-        features.ViewportArrayEmulation =
-            QueryEnvQuirkOverride("MOBILEGL_FORCE_VIEWPORT_ARRAY_EMULATION");
-    }
-
-    inline void InitBackendType() {
-        String backendTypeStr;
-        QueryEnvVariable("MOBILEGL_BACKEND_TYPE", backendTypeStr, "DirectGLES");
-#define ENTRY(backendType)                                                                                             \
-    if (backendTypeStr == #backendType) {                                                                              \
-        MG_Config::ActiveBackendType = BackendType::backendType;                                                       \
-        MGLOG_I("Config: Active backend type set to " #backendType);                                                   \
-        return;                                                                                                        \
-    }
-        ENTRY(DirectGLES)
-        ENTRY(DirectVulkan)
-        ENTRY(Unknown)
-        MG_Config::ActiveBackendType = BackendType::Unknown;
-#undef ENTRY
-    }
-
-    void Init() {
-        MGLOG_D("Loading configuration from environment variables...");
-        InitializeAcceptedEnvVariables();
-
-        InitBackendType();
-        InitFeatures();
-
-        // Destroy the map since we won't need it anymore
-        acceptedEnvVariablesMap.reset();
-    }
-} // namespace MobileGL::MG_ConfigLoader

MobileGL/Defines.h

@@ -9,20 +9,10 @@
 #pragma once
 
 // ============== Platform-specific definitions and macros ============== //
-// No __ANDROID_API__ pin here on purpose. The effective API level is owned by
-// the build system (gradle minSdk 26 -> -DANDROID_PLATFORM=android-26, enforced
-// by the configure-time guard in CMakeLists.txt), not by a macro.
-//
-// History: this used to `#define __ANDROID_API__ 26` to *raise* the level back
-// when the build configured something lower, so that pthread_getname_np (which
-// bionic guards with __INTRODUCED_IN(26)) would be declared. Once a later
-// change added an `#undef` in front of it, the same line started *lowering* the
-// level whenever the build configured higher than 26 - and that is an
-// include-order split-brain, not a compatibility knob: a TU that includes any
-// libc++ header before Includes.h latches libc++'s feature macros at the
-// configure-time level, and only the bionic headers pulled in afterwards see
-// the lowered value. The two halves then disagree (e.g. libc++ believes
-// pthread_cond_clockwait exists while bionic has since hidden its declaration).
+#ifdef __ANDROID__
+#undef __ANDROID_API__
+#define __ANDROID_API__ 26 // force Android API level to 26 for compatibility
+#endif
 
 #ifdef _WIN32
 #ifndef NOMINMAX
@@ -42,31 +32,9 @@
 #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
-#define MOBILEGL_WGL_API MOBILEGL_API
 
 // ====================== MobileGL configurations ======================= //
-// The numeric log levels live here, not only in Log.h: MOBILEGL_ASSERT below compares
-// MOBILEGL_LOG_ACTIVE_LEVEL against MOBILEGL_LOG_LEVEL_DEBUG, and in a translation unit
-// that includes Defines.h without Log.h both tokens would silently evaluate to 0 in the
-// preprocessor conditional - enabling the assert in exactly the INFO-level builds it is
-// documented to be compiled out of. Log.h redefines them identically, which is legal.
-//
-// Severity order, ascending: DEBUG < INFO < WARN < ERROR < FATAL. MOBILEGL_LOG_ACTIVE_LEVEL
-// names the lowest severity compiled in, so the production default INFO keeps I/W/E/F and
-// drops only D. Any edit here must be mirrored in Log.h.
-#ifndef MOBILEGL_LOG_LEVEL_DEBUG
-#define MOBILEGL_LOG_LEVEL_DEBUG 0
-#define MOBILEGL_LOG_LEVEL_INFO 1
-#define MOBILEGL_LOG_LEVEL_WARN 2
-#define MOBILEGL_LOG_LEVEL_ERROR 3
-#define MOBILEGL_LOG_LEVEL_FATAL 4
-#endif
-
-#ifndef MOBILEGL_LOG_ACTIVE_LEVEL
 #define MOBILEGL_LOG_ACTIVE_LEVEL MOBILEGL_LOG_LEVEL_INFO
-#endif
 
 #define MOBILEGL_LOG_ENABLE_CONSOLE 0
 #define MOBILEGL_LOG_ENABLE_FILE 1
@@ -95,21 +63,11 @@
 #endif
 
 // =============================== Utils ================================ //
-// Asserts are live in exactly the builds where MGLOG_D is live, i.e. DEBUG builds only;
-// an INFO build (the production default) compiles them out. DEBUG is the lowest severity
-// in the ordering above, so "ACTIVE <= DEBUG" is true only for ACTIVE == DEBUG - the same
-// gate MGLOG_D uses in Log.h. That equivalence is what makes this gate survive the
-// 2026-08-13 renumbering unchanged; the contract is and stays
-// "INFO builds: asserts OFF; DEBUG builds: asserts ON".
-#if MOBILEGL_LOG_ACTIVE_LEVEL <= MOBILEGL_LOG_LEVEL_DEBUG
-    #define MOBILEGL_ASSERT(condition, ...)                                                                                \
-        do {                                                                                                               \
-            if (!(condition)) {                                                                                            \
-                MGLOG_F("Assertion failed" __VA_OPT__(": ") __VA_ARGS__);                                                  \
-                MGLOG_F("  at %s:%d (%s)", __FILE__, __LINE__, __func__);                                                  \
-                TRAP;                                                                                                      \
-            }                                                                                                              \
-        } while (0)
-#else
-    #define MOBILEGL_ASSERT(condition, ...)
-#endif
+#define MOBILEGL_ASSERT(condition, ...)                                                                                \
+    do {                                                                                                               \
+        if (!(condition)) {                                                                                            \
+            MGLOG_F("Assertion failed" __VA_OPT__(": ") __VA_ARGS__);                                                  \
+            MGLOG_F("  at %s:%d (%s)", __FILE__, __LINE__, __func__);                                                  \
+            TRAP;                                                                                                      \
+        }                                                                                                              \
+    } while (0)

MobileGL/GlobalObjects.cpp

@@ -10,17 +10,11 @@
 
 namespace MobileGL {
     namespace MG_Config {
-        BackendType ActiveBackendType;
+        BackendType ActiveBackendType = BackendType::DirectVulkanTMP;
     } // namespace MG_Config
 
     namespace MG_Backend {
-        // Leak-at-exit storage: the UniquePtr itself lives on the heap and is
-        // never destroyed by the runtime, so process exit runs no backend
-        // destructors (static destruction order across TUs is undefined).
-        // Deterministic teardown happens inside the EGL lifecycle instead:
-        // the last eglTerminate calls MobileGL::Destroy(), which .reset()s
-        // these singletons while the process is still healthy.
-        UniquePtr<BackendObject>& pActiveBackendObject = *new UniquePtr<BackendObject>();
+        UniquePtr<BackendObject> pActiveBackendObject;
         GlobalBackendFunctionsTable gBackendFunctionsTable;
     } // namespace MG_Backend
 } // namespace MobileGL

MobileGL/Includes.h

@@ -32,14 +32,13 @@
 #include <thread>
 #include <vector>
 #include <cassert>
-#include <climits>
-#include <cstdlib>
 #include <cstdarg>
 #include <cstring>
 #include <numeric>
 #include <expected>
 #include <iostream>
 #include <optional>
+#include <xxhash.h>
 #include <algorithm>
 #include <stdexcept>
 #include <functional>
@@ -49,11 +48,8 @@
 #include <stacktrace>
 #endif
 
-// Include ska::flat_hash_map
-#include <ska/flat_hash_map.hpp>
-
-// Include xxHash
-#include <xxhash.h>
+// Include FastSTL
+#include <FastSTL/UnorderedMap.h>
 
 // Include spirv_cross
 #include <spirv_cross/spirv_cross_c.h>
@@ -64,9 +60,7 @@
 #endif
 #include <EGL/egl.h>
 #define GL_GLEXT_PROTOTYPES
-#ifndef NO_GL_H
 #include "GL/gl.h"
-#endif
 #include <GL/glcorearb.h>
 #undef GL_GLEXT_PROTOTYPES
 
@@ -98,44 +92,13 @@
 #endif
 
 #ifdef __ANDROID__
+#define VK_USE_PLATFORM_ANDROID_KHR
 #include <unistd.h>
 #include <pthread.h>
 #include <android/log.h>
 #include <android/native_window.h>
 #endif
-
-#ifdef __ANDROID__
-#define VK_USE_PLATFORM_ANDROID_KHR
-#elif _WIN32
-#define VK_USE_PLATFORM_WIN32_KHR
-#elif defined(__APPLE__)
-#define VK_USE_PLATFORM_METAL_EXT
-#elif defined(__linux__)
-#define VK_USE_PLATFORM_XLIB_KHR
-typedef struct _XDisplay Display;
-typedef unsigned long XID;
-typedef XID Window;
-typedef unsigned long VisualID;
-#else
-#warning "VK_USE_PLATFORM_*_KHR not defined for this platform!"
-#endif
-#if defined(VK_USE_PLATFORM_XLIB_KHR)
-#pragma push_macro("Bool")
-#pragma push_macro("None")
-#pragma push_macro("Always")
-#pragma push_macro("Status")
-#pragma push_macro("LSBFirst")
-#pragma push_macro("DestroyAll")
-#endif
 #include <vulkan/vulkan.h>
-#if defined(VK_USE_PLATFORM_XLIB_KHR)
-#pragma pop_macro("DestroyAll")
-#pragma pop_macro("LSBFirst")
-#pragma pop_macro("Status")
-#pragma pop_macro("Always")
-#pragma pop_macro("None")
-#pragma pop_macro("Bool")
-#endif
 
 #ifdef TRACY_ENABLE
 #include <tracy/Tracy.hpp>

MobileGL/Init.cpp

@@ -8,156 +8,60 @@
 
 #include "Init.h"
 #include "Config.h"
+#include <MG_Impl/Init.h>
 #include <MG_Backend/BackendObjects.h>
-#include <MG_Backend/DirectVulkan/DirectVulkan.h>
 #include <MG_State/GLState/Core.h>
-#include <MG_State/EGLState/Core.h>
 #include <MG_Impl/GLImpl/Texture/ProxyTexture.h>
 #include <MG_Impl/GLImpl/Framebuffer/GL_Framebuffer.h>
-#include <MG_Impl/GLImpl/Sync/GL_Sync.h>
-#include <MG_Impl/GLImpl/Query/GL_Query.h>
-#include <MG_Util/Async/ShaderCompilePool.h>
-#include <MG_Util/ShaderTranspiler/ShaderCompiler.h>
-#include <MG_State/GLState/ProgramState/ProgramTranslationCache.h>
-#include <MG_Util/ShaderTranspiler/TranslationCache.h>
-
-#include <atomic>
-#include <mutex>
 
 namespace MobileGL {
-    namespace {
-        std::atomic<Bool> g_isInitialized = false;
-        thread_local Bool tl_initializing = false;
-
-        std::mutex& InitMutex() {
-            static std::mutex mutex;
-            return mutex;
-        }
-
-        void DestroyImpl(Bool logLifecycle) {
-            if (!g_isInitialized) {
-                return;
-            }
-
-            if (logLifecycle) {
-                MGLOG_I("MobileGL closing...");
-            }
-            // First, before anything else is torn down. In-flight compile/link jobs own
-            // their own inputs and are safe against everything below EXCEPT glslang's
-            // process globals and the TShader/TProgram objects hanging off pGLContext,
-            // both of which this function is about to destroy. This is the one
-            // cancellation path in the whole design that waits.
-            MG_Util::Async::ShaderCompilePool::Get().StopAndDrain();
-            // GL syncs die with their contexts, and every context is gone by the
-            // time full teardown runs: drain the live-sync registry while the
-            // backend function table can still release the backend handles (and
-            // before a re-initialized library could pair them with the wrong
-            // backend's DeleteSync).
-            MG_Impl::GLImpl::DestroyAllSyncObjects();
-            // Queries die with their contexts for the same reason, and their registry
-            // is the same shape of process-global map: drain it here too, while the
-            // function table can still pair each backend handle with the backend that
-            // minted it.
-            MG_Impl::GLImpl::DestroyAllQueryObjects();
-            MG_Backend::pActiveBackendObject.reset();
-            MG_State::pGLContext.reset();
-            MG_State::pEGLContext.reset();
-            MG_Impl::GLImpl::TextureImpl::pProxyTextureManager.reset();
-            MG_Impl::GLImpl::FramebufferImpl::pDefaultFramebufferInfo.reset();
-            // Must run AFTER pGLContext.reset(). FinalizeProcess -> ShFinalize deletes
-            // glslang's process-wide pool allocator and every cached built-in symbol table,
-            // while the TShader/TProgram objects owned by the shader and program objects
-            // still reference levels adopted from those tables. Finalizing first left live
-            // glslang objects pointing at freed memory for the rest of the teardown.
-            glslang::FinalizeProcess();
-            // Immediately after, and never apart from it: FinalizeProcess just deleted the
-            // built-in symbol tables the prewarm latch stands for, so leaving it set would
-            // make the next Initialize() skip a prewarm it genuinely needs.
-            MG_Util::ShaderTranspiler::ShaderCompiler::ResetPrewarmLatch();
-            // The two-level translation memo. Nothing in it references a glslang object -
-            // both levels hold plain bytes - so this is RSS hygiene rather than a lifetime
-            // requirement, and it is safe either side of FinalizeProcess. Stats first: an
-            // fordebug build gets one line per level saying how the run went.
-            MG_Util::ShaderTranspiler::LogShaderTranslationCacheStats();
-            MG_Util::ShaderTranspiler::ClearShaderTranslationCaches();
-            MG_State::GLState::LogProgramTranslationCacheStats();
-            MG_State::GLState::ClearProgramTranslationCache();
-            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;
-        }
-
+    void MG_Initialize() {
         MG_Util::Debug::InitFile();
         MGLOG_I("Initializing MobileGL...");
-        MG_ConfigLoader::Init();
-        MGLOG_I("Config loaded");
         MG_State::Init();
-        MGLOG_D("MG_State initialized");
+        MGLOG_D("MobileGL State initialized");
         MG_Backend::Init();
-        MGLOG_D("MG_Backend initialized");
+        MGLOG_D("MobileGL Backend initialized");
         MG_Impl::Init();
-        MGLOG_D("MG_Impl initialized");
+        MGLOG_D("MobileGL Implementation initialized");
         glslang::InitializeProcess();
-        // On the GL thread, before any worker can exist. glslang builds its built-in symbol
-        // tables lazily under a process-wide lock held for the whole build, so without this
-        // the first concurrent compiles of a shaderpack all serialize behind the very first
-        // parse and asynchronous compilation looks like it is doing nothing.
-        //
-        // Gated on the flag, because the problem it solves only exists when there are
-        // workers: with compilation synchronous, nothing ever contends for that lock and the
-        // three throwaway parses buy nothing - they just add to every eglInitialize. Read the
-        // flag here rather than inside PrewarmBuiltins so ShaderCompiler keeps no dependency
-        // on the async subsystem (ProgramUtilTest compiles that file without it).
-        if (MG_Util::Async::AsyncShaderCompileEnabled()) {
-            MG_Util::ShaderTranspiler::ShaderCompiler::PrewarmBuiltins();
-        }
         MGLOG_D("glslang initialized");
-        g_isInitialized = true;
         MGLOG_I("MobileGL initialized");
     }
 
-    void EnsureInitialized() {
-        if (g_isInitialized.load(std::memory_order_acquire)) {
-            return;
-        }
-        // Re-entrant call while this thread is already inside Initialize()
-        // (e.g. an init step routing back through a public entry point).
-        if (tl_initializing) {
-            return;
-        }
-        const std::lock_guard<std::mutex> lock(InitMutex());
-        if (g_isInitialized.load(std::memory_order_acquire)) {
-            return;
-        }
-        tl_initializing = true;
-        Initialize();
-        tl_initializing = false;
+    void MG_Destroy() {
+        MGLOG_I("MobileGL closing...");
+        glslang::FinalizeProcess();
+        delete MG_State::pGLContext;
+        delete MG_Impl::GLImpl::TextureImpl::pProxyTextureManager;
+        delete MG_Impl::GLImpl::FramebufferImpl::pDefaultFramebufferInfo;
+        MG_Util::Debug::Close();
+
+        // TODO: add and use Destroy functions for other subsystems
     }
 
-    void Destroy() {
-        DestroyImpl(true);
+#if defined(__linux__) || defined(__APPLE__)
+    __attribute__((constructor)) static void AutoInit() {
+        MG_Initialize();
     }
 
-    // MobileGL's lifecycle is owned entirely by the host-API layers
-    // (EGL/WGL/CGL): initialization happens lazily on the first entry point
-    // via EnsureInitialized(), and full teardown happens deterministically
-    // when the last EGL display is terminated with nothing current (EGLImpl
-    // calls Destroy()). There is intentionally no backend-initializing static
-    // constructor, no static destructor, and no DllMain: the global singletons
-    // use leak-at-exit storage (see GlobalObjects.cpp), so a process that exits
-    // without eglTerminate simply leaks them to the OS instead of running
-    // backend destructors during static teardown. macOS has a lightweight
-    // dyld constructor that installs NSOpenGL dispatch hooks only; full backend
-    // initialization still enters here from the first hooked CGL context.
+    __attribute__((destructor)) static void AutoDestroy() {
+        MG_Destroy();
+    }
+#endif
+
+#ifdef _WIN32
+    BOOL WINAPI DllMain(HMODULE hModule, DWORD ul_reason_for_call, LPVOID lpReserved) {
+        switch (ul_reason_for_call) {
+        case DLL_PROCESS_ATTACH:
+            MG_Initialize();
+            break;
+
+        case DLL_PROCESS_DETACH:
+            MG_Destroy();
+            break;
+        }
+        return TRUE;
+    }
+#endif
 } // namespace MobileGL

MobileGL/Init.h

@@ -10,29 +10,6 @@
 #include "Includes.h"
 
 namespace MobileGL {
-    void Initialize();
-    // Thread-safe, idempotent, and re-entrant wrapper around Initialize().
-    // Host layers (EGL/WGL/CGL entry points) call this lazily on first use so
-    // full backend initialization never depends on ELF/DLL static constructors,
-    // and so a fresh init can follow a full Destroy() (e.g. after the last
-    // eglTerminate). The macOS dyld bootstrap installs only lightweight
-    // NSOpenGL method hooks.
-    void EnsureInitialized();
-    void Destroy();
-
-    namespace MG_Util::Debug {
-        void InitFile();
-    } // namespace MG_Util::Debug
-
-    namespace MG_ConfigLoader {
-        void Init();
-    } // namespace MG_ConfigLoader
-
-    namespace MG_Backend {
-        void Init();
-    } // namespace MG_Backend
-
-    namespace MG_Impl {
-        void Init();
-    } // namespace MG_Impl
-} // namespace MobileGL
+    void MG_Initialize();
+    void MG_Destroy();
+} // namespace MobileGL

MobileGL/MG_Backend/BackendObject.cpp

@@ -7,489 +7,9 @@
 // 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) {
-            (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) {
-            MGLOG_E("InitializeEGLDisplay failed: invalid EGLDisplay");
-            return false;
-        }
-
-        if (m_eglDisplayInitialized && m_eglDisplay != dpy) {
-            MGLOG_E("InitializeEGLDisplay failed: backend already bound to a different EGLDisplay");
-            return false;
-        }
-
-        m_eglDisplay = dpy;
-        m_eglDisplayInitialized = true;
-        if (major) {
-            *major = 1;
-        }
-        if (minor) {
-            *minor = 5;
-        }
-        return true;
-    }
-
-    Bool BackendObject::CreateEGLWindowSurface(EGLSurface surface, const WindowHandle& handle) {
-        const std::lock_guard<std::recursive_mutex> lock(m_eglStateMutex);
-        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;
-        }
-        surfaceIt->second.Window.Width = width;
-        surfaceIt->second.Window.Height = height;
-        if (m_eglSurface == surface) {
-            m_windowHandle.Width = width;
-            m_windowHandle.Height = height;
-        }
-        return true;
-    }
-
-    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("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("RegisterEGLPbufferSurface failed: invalid size %dx%d", width, height);
-            return false;
-        }
-
-        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 (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 = surfaceState->Kind;
-        m_eglCurrentThreads.clear();
-        m_backendCapabilitiesInitialized = false;
-        return true;
-    }
-
-    Bool BackendObject::MakeEGLCurrent(EGLDisplay dpy, EGLSurface draw, EGLSurface read, EGLContext ctx) {
-        const std::lock_guard<std::recursive_mutex> lock(m_eglStateMutex);
-        const auto threadKey = CurrentThreadKey();
-        if (IsReleaseCurrentRequest(dpy, draw, read, ctx)) {
-            ReleaseEGLCurrentThread(threadKey);
-            return true;
-        }
-
-        if (!m_eglDisplayInitialized || m_eglDisplay != dpy) {
-            MGLOG_E("MakeEGLCurrent failed: EGL display mismatch or not initialized");
-            return false;
-        }
-        if (!m_eglSurfaceInitialized) {
-            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) {
-            MGLOG_E("MakeEGLCurrent failed: draw/read/context is invalid");
-            return false;
-        }
-
-        if (!m_backendCapabilitiesInitialized) {
-            if (!InitCapabilities()) {
-                MGLOG_E("MakeEGLCurrent failed: InitCapabilities failed");
-                return false;
-            }
-            m_backendCapabilitiesInitialized = true;
-        }
-
-        ReleaseEGLCurrentThread(threadKey);
-        m_eglCurrentThreads[threadKey] = EGLCurrentState{
-            .Display = dpy,
-            .DrawSurface = draw,
-            .ReadSurface = read,
-            .Context = ctx,
-        };
-        return true;
-    }
-
-    void BackendObject::ResetEGLRuntimeState() {
-        const std::lock_guard<std::recursive_mutex> lock(m_eglStateMutex);
-        m_eglSurfaceInitialized = false;
-        m_backendCapabilitiesInitialized = false;
-        m_eglSurfaceKind = SurfaceKind::None;
-        m_eglSurface = EGL_NO_SURFACE;
-        m_windowHandle = {};
-        m_eglCurrentThreads.clear();
-    }
-
-    Bool BackendObject::SwapEGLBuffers(EGLDisplay dpy, EGLSurface draw) {
-        const std::lock_guard<std::recursive_mutex> lock(m_eglStateMutex);
-        if (!m_eglDisplayInitialized || m_eglDisplay != dpy) {
-            MGLOG_E("SwapEGLBuffers failed: EGL display mismatch or not initialized");
-            return false;
-        }
-        const auto currentIt = m_eglCurrentThreads.find(CurrentThreadKey());
-        if (currentIt == m_eglCurrentThreads.end()) {
-            MGLOG_E("SwapEGLBuffers failed: no current context attached");
-            return false;
-        }
-        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;
-        }
-
-        const auto& backendFunctions = GetBackendFunctions();
-        if (!backendFunctions.Present) {
-            MGLOG_E("SwapEGLBuffers failed: backend Present function is null");
-            return false;
-        }
-
-        backendFunctions.Present();
-        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;
-    }
-
     void BackendObject::SetWindowHandle(const WindowHandle& handle) {
-        const std::lock_guard<std::recursive_mutex> lock(m_eglStateMutex);
         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

@@ -8,118 +8,21 @@
 
 #pragma once
 #include <Includes.h>
-#include "MG_State/GLState/TextureState/TextureEnum.h"
 
 namespace MobileGL {
-    namespace MG_State::GLState {
-        class FramebufferObject;
-        class ITextureObject;
-        class RenderbufferObject;
-    }
-
     enum class BackendType {
         DirectGLES,
-        DirectVulkan,
+        DirectVulkanTMP,
         BackendTypeCount,
         Unknown = -1
     };
 
     namespace MG_Backend {
-        // One endpoint of a glCopyImageSubData. GL 4.6 core 18.3.2 accepts GL_RENDERBUFFER
-        // alongside the ten whole-image texture targets, and a renderbuffer name lives in a
-        // namespace of its own - so an endpoint is a sum type, not an ITextureObject. At most
-        // one of the two pointers is set; neither is set when the name named nothing, which is
-        // the INVALID_VALUE the frontend validator reports.
-        struct CopyImageEndpoint {
-            SharedPtr<MG_State::GLState::ITextureObject> Texture;
-            SharedPtr<MG_State::GLState::RenderbufferObject> Renderbuffer;
-
-            Bool IsRenderbuffer() const { return Renderbuffer != nullptr; }
-            Bool Exists() const { return Texture != nullptr || Renderbuffer != nullptr; }
-        };
-
-        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,
@@ -128,10 +31,6 @@ namespace MobileGL {
             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 (*MultiDrawArraysIndirectCount)(GLenum mode, const void* indirect, GLintptr drawcount,
-                                                 GLsizei maxdrawcount, GLsizei stride);
             void (*DrawRangeElementsBaseVertex)(GLenum mode, GLuint start, GLuint end, GLsizei count, GLenum type,
                                                 const void* indices, GLint basevertex);
             void (*DrawRangeElements)(GLenum mode, GLuint start, GLuint end, GLsizei count, GLenum type,
@@ -155,341 +54,29 @@ namespace MobileGL {
             void (*ClearBufferfv)(GLenum buffer, GLint drawbuffer, const GLfloat* value);
             void (*ClearBufferuiv)(GLenum buffer, GLint drawbuffer, const GLuint* value);
             void (*ClearBufferiv)(GLenum buffer, GLint drawbuffer, const GLint* value);
-            void (*ClearNamedFramebufferfv)(const SharedPtr<MG_State::GLState::FramebufferObject>& framebuffer,
-                                            GLenum buffer, GLint drawbuffer, const GLfloat* value);
-            void (*ClearNamedFramebufferfi)(const SharedPtr<MG_State::GLState::FramebufferObject>& framebuffer,
-                                            GLenum buffer, GLint drawbuffer, GLfloat depth, GLint stencil);
-            void (*ClearNamedFramebufferiv)(const SharedPtr<MG_State::GLState::FramebufferObject>& framebuffer,
-                                            GLenum buffer, GLint drawbuffer, const GLint* value);
-            void (*ClearNamedFramebufferuiv)(const SharedPtr<MG_State::GLState::FramebufferObject>& framebuffer,
-                                             GLenum buffer, GLint drawbuffer, const GLuint* value);
             void (*BlitFramebuffer)(GLint srcX0, GLint srcY0, GLint srcX1, GLint srcY1, GLint dstX0, GLint dstY0,
                                     GLint dstX1, GLint dstY1, GLbitfield mask, GLenum filter);
-            void (*BlitNamedFramebuffer)(const SharedPtr<MG_State::GLState::FramebufferObject>& readFramebuffer,
-                                         const SharedPtr<MG_State::GLState::FramebufferObject>& drawFramebuffer,
-                                         GLint srcX0, GLint srcY0, GLint srcX1, GLint srcY1,
-                                         GLint dstX0, GLint dstY0, GLint dstX1, GLint dstY1,
-                                         GLbitfield mask, GLenum filter);
             void (*CopyTexImage2D)(GLenum target, GLint level, GLenum internalformat, GLint x, GLint y, GLsizei width,
                                    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 CopyImageEndpoint& src,
-                                     GLenum srcTarget, GLint srcLevel, GLint srcX, GLint srcY, GLint srcZ,
-                                     const CopyImageEndpoint& dst,
-                                     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);
             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);
-            void (*DispatchCompute)(GLuint numGroupsX, GLuint numGroupsY, GLuint numGroupsZ);
-            void (*DispatchComputeIndirect)(GLintptr indirect);
-            void (*MemoryBarrier)(GLbitfield barriers);
-            void (*MemoryBarrierByRegion)(GLbitfield barriers);
-            void (*BindImageTexture)(GLuint unit, GLuint texture, GLint level, GLboolean layered, GLint layer,
-                                     GLenum access, GLenum format);
-            void (*GetIntegeri_v)(GLenum target, GLuint index, GLint* data);
-            void (*GetInteger64i_v)(GLenum target, GLuint index, GLint64* data);
-            void (*GetProgramiv)(GLuint program, GLenum pname, GLint* params);
-            // The GL program interface (glGetProgramInterfaceiv / glGetProgramResource*) is NOT
-            // a backend query: it describes the program the application wrote, in the
-            // application's namespace, which neither backend program is in. It is answered
-            // entirely by MG_Impl/GLImpl/Program/ProgramInterface from the frontend reflection.
-            // Takes the block's GL NAME, not glShaderStorageBlockBinding's index. The index
-            // the application passes is the frontend interface-query enumeration's, and no
-            // backend shares that index space: DirectVulkan enumerates SPIR-V descriptor
-            // bindings and DirectGLES asks a real driver about SPIRV-Cross-generated ESSL.
-            // The name is the one coordinate all three agree on, so the frontend resolves the
-            // index against its own enumeration and each backend maps the name to its own.
-            void (*ShaderStorageBlockBinding)(GLuint program, const GLchar* storageBlockName,
-                                              GLuint storageBlockBinding);
-            // GL fence sync objects. All entries are optional (may be null); the
-            // frontend then falls back to always-signaled sync semantics.
-            // FenceSync may itself return null when the backend cannot create a
-            // 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);
-            // GL_SAMPLES_PASSED occlusion queries (optional; null = unsupported,
-            // the frontend then rejects the target). Results/deletion flow through
-            // GetQueryResult64 / DeleteBackendQuery like timer queries.
-            BackendQueryHandle (*BeginOcclusionQuery)();
-            void (*EndOcclusionQuery)(BackendQueryHandle query);
-            // Transform feedback primitive queries backed by real GPU query pools
-            // (optional; null = frontend falls back to CPU accounting).
-            BackendQueryHandle (*BeginXfbPrimitivesQuery)(Bool generated);
-            void (*EndXfbPrimitivesQuery)(BackendQueryHandle query);
-            // Whether GL_TRANSFORM_FEEDBACK_PRIMITIVES_WRITTEN should be answered from the
-            // frontend's own accounting wherever that accounting is exact - a capture with no
-            // geometry stage - instead of from the query above. Set by DirectGLES, whose result
-            // is whatever the ES driver's PRIMITIVES_WRITTEN counter says: Adreno reports twice
-            // the written count for a vertex-only capture that follows a large render pass,
-            // where the desktop-exact answer is the one the frontend already computed. Defaults
-            // to false, so a backend that never sets it keeps using its GPU result.
-            Bool PrefersCpuXfbPrimitiveAccounting = false;
-            // Transform feedback capture spans, for backends whose own GL/ES driver
-            // performs the capture (DirectGLES). Both optional; null means the backend
-            // drives capture from its draw recording instead (DirectVulkan). End is
-            // called while the frontend capture state is still active, so the backend
-            // can still see the capture program and buffer bindings.
-            // GL_PATCH_VERTICES; ES 3.2 spells it the same way.
-            void (*PatchParameteri)(GLenum pname, GLint value);
-            void (*BeginTransformFeedback)(GLenum primitiveMode);
-            void (*EndTransformFeedback)();
-            // ARB_transform_feedback2. A backend that leaves these null keeps the single
-            // implicit capture span the frontend has always modelled; the frontend state
-            // (paused flag, per-object bindings) is tracked either way.
-            void (*PauseTransformFeedback)();
-            void (*ResumeTransformFeedback)();
-            void (*BindTransformFeedback)(GLuint name);
-            void (*DeleteTransformFeedback)(GLuint name);
-            Int64 (*GetGpuTimestampNs)(); // glGetInteger64v(GL_TIMESTAMP); 0 if unsupported
         };
         struct GlobalBackendFunctionsTable {
             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);
-        };
-
-        // Coarse GPU vendor identity for gating device-specific quirks. Detected from the
-        // Vulkan physical-device vendorID or the GLES GL_VENDOR/GL_RENDERER strings; stays
-        // Unknown when detection is inconclusive, in which case auto-gated quirks stay off.
-        enum class GpuVendorKind : Uint8 {
-            Unknown = 0,
-            Qualcomm,
-            Arm,
-            Nvidia,
-            Amd,
-            Intel,
-            ImgTec,
-            // Software rasterizers (llvmpipe/lavapipe, SwiftShader).
-            Software,
         };
 
         struct DynamicBackendParameters {
             SizeT UniformBufferOffsetAlignment = 256;
-            // GL_MAX_TEXTURE_MAX_ANISOTROPY_EXT. 1.0 means the backend cannot filter anisotropically,
-            // which is also why the extension is not advertised in that case.
-            Float MaxTextureMaxAnisotropy = 1.0f;
-            Float AliasedLineWidthRangeMin = 1.0f;
-            Float AliasedLineWidthRangeMax = 1.0f;
-            Float SmoothLineWidthRangeMin = 1.0f;
-            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;
-            // Tessellation limits; defaults are the GL 4.0 core minimums.
-            Int MaxPatchVertices = 32;
-            Int MaxTessGenLevel = 64;
-            // GL_MIN/MAX_PROGRAM_TEXTURE_GATHER_OFFSET. Defaults are the GL 4.0 core
-            // minimums, which every ES 3.1 driver also guarantees.
-            Int MinProgramTextureGatherOffset = -8;
-            Int MaxProgramTextureGatherOffset = 7;
-            Int MaxTextureImageUnits = 32;
-            Int MaxVertexTextureImageUnits = 32;
-            Int MaxComputeTextureImageUnits = 32;
-            Int MaxCombinedTextureImageUnits = 192;
-            Int MaxVertexAttribs = 16;
-            Int MaxComputeShaderStorageBlocks = 8;
-            Int MaxCombinedShaderStorageBlocks = 32;
-            // Per-stage GL_MAX_*_SHADER_STORAGE_BLOCKS. Zero is a legal answer for the four
-            // non-compute, non-fragment stages and these defaults are the spec minimums, not
-            // placeholders: GL 4.6 table 23.64 and ES 3.2 table 21.44 both set the minimum for
-            // vertex, tessellation control, tessellation evaluation and geometry at 0, and only
-            // fragment (8 in GL, 4 in ES) and compute are guaranteed to have any. Every real ARM
-            // GLES driver takes that allowance - a Mali-G925 reports 0 for all four - so a
-            // backend that cannot honour a graphics-stage storage block MUST report 0 here
-            // rather than a hopeful number. Advertising a non-zero count the driver will refuse
-            // does not make the block work; it only moves the failure from an honest
-            // "unsupported" at query time to a backend link error the frontend never surfaces,
-            // after which every draw with that program silently renders nothing.
-            Int MaxVertexShaderStorageBlocks = 0;
-            Int MaxTessControlShaderStorageBlocks = 0;
-            Int MaxTessEvaluationShaderStorageBlocks = 0;
-            Int MaxGeometryShaderStorageBlocks = 0;
-            Int MaxFragmentShaderStorageBlocks = 8;
-            Int MaxComputeUniformBlocks = 12;
-            Int MaxComputeWorkGroupInvocations = 128;
-            Int MaxShaderStorageBufferBindings = 8;
-            Int MaxTextureBufferSize = 65536;
-            // GL_TEXTURE_BUFFER_OFFSET_ALIGNMENT; 1 means the offset is unconstrained.
-            Int TextureBufferOffsetAlignment = 1;
-            Int MaxUniformBufferBindings = 24;
-            Int MaxUniformBlockSize = 16384;
-            Int MaxImageUnits = 8;
-            Int MaxCombinedImageUniforms = 8;
-            Int MaxVertexImageUniforms = 0;
-            Int MaxGeometryImageUniforms = 0;
-            Int MaxFragmentImageUniforms = 8;
-            Int MaxComputeImageUniforms = 8;
-            Int MaxDrawBuffers = 8;
-            Int MaxColorAttachments = 8;
-            // GL_MAX_CLIP_DISTANCES. Zero is a legal answer here, not a placeholder, and a
-            // backend that cannot host a clip distance MUST report it: advertising eight the
-            // backend will refuse does not make gl_ClipDistance work, it only moves the failure
-            // from an honest "unsupported" at query time to a backend shader-compile error the
-            // frontend never surfaces, after which every draw with that program silently renders
-            // nothing. DirectGLES fills it from GL_EXT_clip_cull_distance, DirectVulkan from the
-            // shaderClipDistance device feature. The DEFAULT stays at the GL 4.3 core minimum
-            // because it describes the no-backend case (standalone shader compiles, unit tests),
-            // where there is no device to be honest about and BuildTBuiltInResource still has to
-            // hand glslang a workable gl_MaxClipDistances.
-            Int MaxClipDistances = 8;
-            Int MaxViewports = 16;
-            // GL_LAYER_PROVOKING_VERTEX / GL_VIEWPORT_INDEX_PROVOKING_VERTEX: which vertex of a
-            // primitive supplies gl_Layer and gl_ViewportIndex. GL 4.6 table 23.65 makes
-            // GL_UNDEFINED_VERTEX a legal answer for both, and it is the honest default - naming
-            // a convention is a statement about behaviour, so a backend that does not pin one
-            // must not claim it does. DirectGLES fills the layer one from the ES 3.2 query and
-            // the viewport one from GL_OES_viewport_array, and leaves UNDEFINED where the
-            // capability is absent: without the viewport array extension only viewport 0 is ever
-            // rasterized, so no convention selects anything. DirectVulkan keeps UNDEFINED for
-            // both - which vertex provokes is decided per pipeline by
-            // VulkanRenderer::SelectProvokingVertexMode out of VK_EXT_provoking_vertex,
-            // provokingVertexModePerPipeline and the topology, so no single convention is true
-            // of the backend.
-            GLenum LayerProvokingVertex = GL_UNDEFINED_VERTEX;
-            GLenum ViewportIndexProvokingVertex = GL_UNDEFINED_VERTEX;
-            Int MaxViewportWidth = 16384;
-            Int MaxViewportHeight = 16384;
-            Float ViewportBoundsRangeMin = 0.0f;
-            Float ViewportBoundsRangeMax = 0.0f;
-            Int ViewportSubpixelBits = 0;
-            // GL 4.x fragment-interpolation offset limits. These defaults are the
-            // core minimums and are replaced by live GLES/Vulkan device limits.
-            Float MinFragmentInterpolationOffset = -0.5f;
-            // For four fractional bits the greatest required legal offset is
-            // 0.5 - 2^-4 = 0.4375 (GL 4.6 table 23.70).
-            Float MaxFragmentInterpolationOffset = 0.4375f;
-            Int FragmentInterpolationOffsetBits = 4;
-            Bool SupportsWideLines = false;
-            // Whether a framebuffer whose depth and stencil attachments are distinct
-            // images can be rendered to. GL only requires support when both refer to the
-            // same image and lets an implementation answer GL_FRAMEBUFFER_UNSUPPORTED
-            // otherwise, which is what DirectVulkan (one combined attachment) and the
-            // real ES drivers behind DirectGLES both do. Defaults to true so a backend
-            // that never sets it keeps the permissive behaviour.
-            Bool SupportsDistinctDepthStencilAttachments = true;
-            // Whether attaching a single layer of a 3D or array texture to a framebuffer actually
-            // renders to that layer. DirectGLES hands the layer straight to
-            // glFramebufferTextureLayer, so it does; DirectVulkan maps a GL layer onto a Vulkan
-            // array layer with no notion of a 3D depth slice, so it does not yet. Defaults to false
-            // so a backend that never sets it gets the conservative answer.
-            // Which layered texture targets this backend can attach ONE layer of to a framebuffer
-            // and then really clear, render and read back that layer. Bit (1u << TextureTarget) is
-            // set for each supported target. Deliberately per target rather than one flag: the three
-            // ways a GL layer maps onto Vulkan are independent capabilities. A 2D or 2D multisample
-            // array layer IS a VkImage array layer and needs nothing extra; a 3D texture's layer is
-            // a z slice, which needs a 2D-array-compatible image and a per-slice clear that
-            // vkCmdClearColorImage cannot express; a cube map array needs an image shape and the
-            // imageCubeArray feature before it can be attached at any layer at all. Defaults to 0 so
-            // a backend that never sets it gets the conservative answer.
-            Uint32 PerLayerFramebufferAttachmentTargets = 0;
-
-            static constexpr Uint32 PerLayerFramebufferAttachmentBit(TextureTarget target) {
-                return (static_cast<Int>(target) >= 0 &&
-                        static_cast<Int>(target) < static_cast<Int>(TextureTarget::TextureTargetCount))
-                           ? (1u << static_cast<Uint32>(target))
-                           : 0u;
-            }
-
-            Bool SupportsPerLayerFramebufferAttachment(TextureTarget target) const {
-                const Uint32 bit = PerLayerFramebufferAttachmentBit(target);
-                return bit != 0 && (PerLayerFramebufferAttachmentTargets & bit) != 0;
-            }
-            // Whether this backend can CONSUME a shader module that still declares 64-bit floats,
-            // i.e. whether `double` survives the transpile instead of being narrowed to `float`
-            // (ShaderTranspiler::DemoteFloat64Pass). Detected, never assumed:
-            //   * DirectVulkan sets it from VkPhysicalDeviceFeatures::shaderFloat64, the feature
-            //     VUID-VkShaderModuleCreateInfo-pCode-08740 requires before a module declaring
-            //     OpCapability Float64 may be created at all. lavapipe has it; Adreno and Mali
-            //     both report VK_FALSE, so no real mobile device does.
-            //   * DirectGLES can NEVER have it. GLSL ES has no 64-bit float type in any version
-            //     or extension, so SPIRV-Cross cannot emit one ("FP64 not supported in ES
-            //     profile") and the demotion there is mathematically mandatory, always.
-            // Defaults to false so a backend that never sets it - and the no-backend case, which
-            // is what standalone shader compiles and the unit tests run under - keeps the
-            // demotion, which is the behaviour that works everywhere.
-            Bool SupportsShaderFloat64 = false;
-            // Whether glVertexAttribLFormat / glVertexArrayAttribLFormat can be honoured, i.e.
-            // whether a 64-bit vertex attribute can actually reach a shader unconverted. Detected,
-            // never assumed: DirectVulkan needs VkPhysicalDeviceFeatures::shaderFloat64 (the
-            // attribute travels as its 32-bit word pair, so no VK_FORMAT_R64* is required, but the
-            // bitcast result is Float64); DirectGLES can never have it, ESSL having no fp64 type at
-            // all. Defaults to false so a backend that never sets it gets the conservative answer.
-            //
-            // INDEPENDENT of SupportsShaderFloat64, and it has to be: this flag decides a VkFormat
-            // from the VAO ATTRIBUTE alone, which does not know what type the shader declared, and
-            // glVertexAttribFormat(GL_DOUBLE) feeding a plain `in vec4` is both legal and common
-            // (KHR-GL43.vertex_attrib_binding.basic-input-case4/5, advanced-bindingUpdate). A
-            // backend with native fp64 that still cannot FETCH 64 bits keeps this false and relies
-            // on the per-MODULE rule in ShaderCompiler::SanitizeAndOptimizeBinary instead: a vertex
-            // module that declares a 64-bit float INPUT is demoted whole, so the two shader-side
-            // halves (PackDoubleVertexInputsPass and VertexInputStateFactory::ToVkVertexFormat)
-            // still see one consistent world.
-            Bool SupportsFloat64VertexAttributes = false;
-            SizeT MaxShaderStorageBlockSize = 128 * 1024 * 1024;
-            Uint32 SubgroupSize = 0;
-            Uint32 SubgroupSupportedStages = 0;
-            Uint32 SubgroupSupportedFeatures = 0;
-            Bool SubgroupQuadOperationsInAllStages = false;
-            GpuVendorKind GpuVendor = GpuVendorKind::Unknown;
         };
 
         enum class WindowBackend {
             Android,
-            X11,
-            MetalLayer,
-            Win32, // Handle is an HWND
-            // TODO: Wayland, etc.
+            // TODO: X11, Wayland, Windows, macOS, etc.
             WindowBackendCount,
             Unknown = -1
         };
@@ -497,8 +84,6 @@ namespace MobileGL {
         struct WindowHandle {
             WindowBackend Backend = WindowBackend::Unknown;
             void* Handle = nullptr;
-            Uint32 Width = 0;
-            Uint32 Height = 0;
         };
 
         class BackendObject {
@@ -506,20 +91,8 @@ namespace MobileGL {
             virtual ~BackendObject() = default;
 
             virtual void Initialize() = 0;
-            virtual Bool InitCapabilities() = 0;
-            virtual Bool InitWindowSurface() = 0;
-
-            virtual Bool InitializeEGLDisplay(EGLDisplay dpy, EGLint* major, EGLint* minor);
-            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();
+            virtual void InitCapabilities() = 0;
+            virtual void InitWindowSurface() = 0;
 
             void SetWindowHandle(const WindowHandle& handle);
 
@@ -527,56 +100,10 @@ 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:
-            enum class SurfaceKind {
-                None,
-                Window,
-                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, 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/BackendObjects.h

@@ -10,9 +10,11 @@
 #include <Includes.h>
 #include "BackendObject.h"
 #include "DirectGLES/BackendObject_DirectGLES.h"
-#include "DirectVulkan/BackendObject_DirectVulkan.h"
+#include "DirectVulkanTMP/BackendObject_DirectVulkanTMP.h"
 
 namespace MobileGL::MG_Backend {
-    extern UniquePtr<BackendObject>& pActiveBackendObject;
+    extern UniquePtr<BackendObject> pActiveBackendObject;
     extern GlobalBackendFunctionsTable gBackendFunctionsTable;
+
+    void Init();
 } // namespace MobileGL::MG_Backend

MobileGL/MG_Backend/DirectGLES/BackendObject_DirectGLES.h

@@ -12,36 +12,13 @@
 #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);
-
-    // Clamps a requested sample count down to what the ES driver can really deliver for this
-    // format on this format-capability target: the probed per-format list when there is one, the
-    // driver's per-class GL_MAX_*_SAMPLES otherwise. The frontend deliberately validates against
-    // the count MobileGL advertises instead (GL_Getter's GetAdvertisedMaxSamples), which on a
-    // driver reporting GL_MAX_INTEGER_SAMPLES 1 is higher than the driver accepts, so every ES
-    // allocation call has to come through here. The shadow state keeps the requested count, so
-    // GL_TEXTURE_SAMPLES and framebuffer completeness still answer what the application asked for.
-    Int ClampSamplesToBackendSupport(SizeT targetIndex, TextureInternalFormat logicalFormat, GLenum imageFormat,
-                                     Int samples);
-
     class BackendObject_DirectGLES : public BackendObject {
     public:
         ~BackendObject_DirectGLES() override;
 
         void Initialize() override;
-        Bool InitCapabilities() override;
-        Bool InitWindowSurface() override;
-        Bool InitializeEGLDisplay(EGLDisplay dpy, EGLint* major, EGLint* minor) 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;
+        void InitCapabilities() override;
+        void InitWindowSurface() override;
 
         const RendererInfo& GetRendererInfo() const override;
         String GetBackendAPIVersionString() const override;
@@ -51,12 +28,9 @@ 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;
@@ -64,28 +38,4 @@ 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 / native indirect draws /
-    // non-zero indirect baseInstance semantics are (or are not) usable.
-    // The MOBILEGL_DISABLE_TIMERQUERY escape hatch is applied inside.
-    Vector<GLExtension> BuildAdvertisedExtensions(Bool timerQueriesSupported, Bool anisotropicFilteringSupported,
-                                                  Bool drawIndirectSupported,
-                                                  Bool nonZeroIndirectBaseInstanceSupported);
-
-    // 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

@@ -8,8 +8,6 @@
 
 #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>
 #include <MG_Util/BackendLoaders/OpenGL/Loader.h>
@@ -19,10 +17,6 @@
     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);
@@ -31,17 +25,12 @@ 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,
                                      GLsizei drawcount, const GLint* basevertex);
     void MultiDrawElementsIndirect(GLenum mode, GLenum type, const void* indirect, GLsizei drawcount, GLsizei stride);
-    void MultiDrawElementsIndirectCount(GLenum mode, GLenum type, const void* indirect, GLintptr drawcount,
-                                        GLsizei maxdrawcount, GLsizei stride);
     void MultiDrawArraysIndirect(GLenum mode, const void* indirect, GLsizei drawcount, GLsizei stride);
-    void MultiDrawArraysIndirectCount(GLenum mode, const void* indirect, GLintptr drawcount, GLsizei maxdrawcount,
-                                      GLsizei stride);
     void DrawRangeElementsBaseVertex(GLenum mode, GLuint start, GLuint end, GLsizei count, GLenum type,
                                      const void* indices, GLint basevertex);
     void DrawRangeElements(GLenum mode, GLuint start, GLuint end, GLsizei count, GLenum type, const void* indices);
@@ -57,177 +46,23 @@ namespace MobileGL::MG_Backend::DirectGLES {
                                          GLuint baseinstance);
     void DrawArraysInstanced(GLenum mode, GLint first, GLsizei count, GLsizei instancecount);
     void DrawArraysIndirect(GLenum mode, const void* indirect);
-    void ClearNamedFramebufferfv(const SharedPtr<MG_State::GLState::FramebufferObject>& framebuffer,
-                                 GLenum buffer, GLint drawbuffer, const GLfloat* value);
-    void ClearNamedFramebufferfi(const SharedPtr<MG_State::GLState::FramebufferObject>& framebuffer,
-                                 GLenum buffer, GLint drawbuffer, GLfloat depth, GLint stencil);
-    void ClearNamedFramebufferiv(const SharedPtr<MG_State::GLState::FramebufferObject>& framebuffer,
-                                 GLenum buffer, GLint drawbuffer, const GLint* value);
-    void ClearNamedFramebufferuiv(const SharedPtr<MG_State::GLState::FramebufferObject>& framebuffer,
-                                  GLenum buffer, GLint drawbuffer, const GLuint* value);
     void BlitFramebuffer(GLint srcX0, GLint srcY0, GLint srcX1, GLint srcY1, GLint dstX0, GLint dstY0, GLint dstX1,
                          GLint dstY1, GLbitfield mask, GLenum filter);
-    void BlitNamedFramebuffer(const SharedPtr<MG_State::GLState::FramebufferObject>& readFramebuffer,
-                              const SharedPtr<MG_State::GLState::FramebufferObject>& drawFramebuffer,
-                              GLint srcX0, GLint srcY0, GLint srcX1, GLint srcY1,
-                              GLint dstX0, GLint dstY0, GLint dstX1, GLint dstY1,
-                              GLbitfield mask, GLenum filter);
     void CopyTexImage2D(GLenum target, GLint level, GLenum internalformat, GLint x, GLint y, GLsizei width,
                         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 CopyImageEndpoint& src,
-                          GLenum srcTarget, GLint srcLevel, GLint srcX, GLint srcY, GLint srcZ,
-                          const CopyImageEndpoint& dst,
-                          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);
     void GetTexImage(GLenum target, GLint level, GLenum format, GLenum type, GLvoid* pixels);
-    void DispatchCompute(GLuint numGroupsX, GLuint numGroupsY, GLuint numGroupsZ);
-    void DispatchComputeIndirect(GLintptr indirect);
-    void MemoryBarrier(GLbitfield barriers);
-    void MemoryBarrierByRegion(GLbitfield barriers);
-    void BindImageTexture(GLuint unit, GLuint texture, GLint level, GLboolean layered, GLint layer, GLenum access,
-                          GLenum format);
-    void GetIntegeri_v(GLenum target, GLuint index, GLint* data);
-    void GetInteger64i_v(GLenum target, GLuint index, GLint64* data);
-    void GetProgramiv(GLuint program, GLenum pname, GLint* params);
-    void ShaderStorageBlockBinding(GLuint program, const GLchar* storageBlockName, 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();
-    // True when the host ES driver can back a GL_TEXTURE_BUFFER at all - ES 3.2 core, or
-    // EXT/OES_texture_buffer, with glTexBuffer resolved. Desktop GL has had buffer textures as
-    // core since 3.1, so the frontend advertises them unconditionally and an app may call
-    // glTexBuffer whenever it likes; this is the only thing standing between that call and a
-    // null entry point. False also means every shader declaring a samplerBuffer is
-    // uncompilable on this driver, which the program build reports by name.
-    Bool AreBufferTexturesSupported();
-    // Human-readable name of the buffer-texture tier for diagnostics and the driver POST:
-    // "core (ES 3.2)", "GL_EXT_texture_buffer", "GL_OES_texture_buffer" or "unsupported".
-    const char* GetBufferTextureTierName();
-    // glTexBuffer / glTexBufferRange through whichever spelling this driver's buffer-texture
-    // support actually ships: the unsuffixed names are ES 3.2 core, while an EXT/OES driver
-    // exports glTexBuffer{,Range}EXT / OES. Callers must have checked
-    // AreBufferTexturesSupported() first. CallTexBufferRange reports whether it could honour
-    // the range - no tier is required to expose the range form, and the whole-buffer form is
-    // the documented fallback.
-    void CallTexBuffer(GLenum target, GLenum internalFormat, GLuint buffer);
-    Bool CallTexBufferRange(GLenum target, GLenum internalFormat, GLuint buffer, GLintptr offset, GLsizeiptr size);
-    // 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();
-    // GL_ANY_SAMPLES_PASSED(_CONSERVATIVE) occlusion queries: core ES3, independent of
-    // GL_EXT_disjoint_timer_query and of MOBILEGL_DISABLE_TIMERQUERY. Results/deletion
-    // flow through GetQueryResult64/DeleteBackendQuery like the timer queries above.
-    BackendQueryHandle BeginOcclusionQuery();
-    void EndOcclusionQuery(BackendQueryHandle query);
-    // GL_TRANSFORM_FEEDBACK_PRIMITIVES_WRITTEN / GL_PRIMITIVES_GENERATED, also core ES
-    // (GL_PRIMITIVES_GENERATED from ES 3.2 on). Null when the target is unavailable, in
-    // which case the frontend falls back to counting primitives from the draw calls.
-    BackendQueryHandle BeginXfbPrimitivesQuery(Bool generated);
-    void EndXfbPrimitivesQuery(BackendQueryHandle query);
-    Bool IsQueryResultAvailable(BackendQueryHandle query);
-    // Returns true when a final value landed in *outNanoseconds (a zero for
-    // null or stale-generation handles IS final: the frontend may cache it
-    // 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();
-    // Block (up to timeoutNs) until the given frame serial provably retired on the
-    // GPU, using the per-frame fence ring. False when no usable fence covers the
-    // serial (fence-less context, foreign thread, or the slot was recycled);
-    // completion state is untouched in that case.
-    Bool WaitForFrameSerialCompleted(Uint64 serial, Uint64 timeoutNs);
-    // Applies (or defers until the window surface exists) the app-requested
-    // eglSwapInterval on the native EGL surface.
-    void SetSwapInterval(Int interval);
     void SetEGLFuncsTable(const MG_External::EGLFunctionsTable& eglFuncs);
     void SetGLESFuncsTable(const MG_External::GLESFunctionsTable& glesFuncs);
     void SetGLESCapabilities(const MG_External::GLESCapabilities& capabilities);
     void DestroyEGLContext();
 
-    // Transform feedback capture spans, performed by the real ES driver. The
-    // capture set is declared on the backend program at link time; the driver-side
-    // begin is deferred to the first draw of the span (ES needs the capturing
-    // program current and the capture buffers bound), and the end also mirrors the
-    // captured bytes back into the frontend buffer shadows.
-    void PatchParameteri(GLenum pname, GLint value);
-
-    namespace XfbImpl {
-        Bool AreTransformFeedbacksSupported();
-        // True while a capture span is open on the current transform feedback object
-        // (frontend Begin seen and not paused), whether or not the deferred driver-side
-        // Begin has been issued yet. Draw paths that would restructure the primitive
-        // stream, or that need to dispatch compute mid-draw, decline while it is set.
-        Bool IsCaptureSpanOpen();
-        void BeginTransformFeedback(GLenum primitiveMode);
-        void EndTransformFeedback();
-        void PauseTransformFeedback();
-        void ResumeTransformFeedback();
-        void BindTransformFeedback(GLuint name);
-        void DeleteTransformFeedback(GLuint name);
-        void OnBackendContextDestroyed();
-    } // namespace XfbImpl
-
-    namespace RenderStateImpl {
-        // Pushes the frontend's render-state block to the ES driver, diffed against what was
-        // last pushed.
-        //
-        // `forColorClear` names the CALLER, and the only thing it changes is the colour write
-        // mask handed to the driver. A draw into a colour attachment the backend widened from
-        // three channels to four gets that buffer's alpha channel masked OFF, so nothing can
-        // move the stored alpha away from the 1.0 the application's three-channel format
-        // implies (see FramebufferImpl::g_alphaWidenedDrawBufferMask). A CLEAR is how that 1.0
-        // gets there in the first place, so it must be allowed to write alpha - hence the flag
-        // rather than an unconditional doctoring. It is part of the sync memo, so a clear
-        // followed by a draw re-pushes the mask instead of early-outing on an unchanged
-        // frontend version.
-        //
-        // The application's own colour mask is never modified: glGet(GL_COLOR_WRITEMASK)
-        // answers from the frontend state, which this function only reads.
-        void SyncRenderState(Bool forColorClear = false);
-        void InvalidateSyncedRenderState();
-    } // namespace RenderStateImpl
-
     extern MG_External::EGLFunctionsTable g_EGLFuncs;
     extern MG_External::GLESFunctionsTable g_GLESFuncs;
     extern MG_External::GLESCapabilities g_GLESCapabilities;

MobileGL/MG_Backend/DirectGLES/MultiDraw.cpp

@@ -1,938 +0,0 @@
-// MobileGL - MobileGL/MG_Backend/DirectGLES/MultiDraw.cpp
-// Copyright (c) 2025-2026 MobileGL-Dev
-// Licensed under the GNU Lesser General Public License v3.0:
-//   https://www.gnu.org/licenses/gpl-3.0.txt
-//   https://www.gnu.org/licenses/lgpl-3.0.txt
-// SPDX-License-Identifier: LGPL-3.0-only
-// End of Source File Header
-
-#include "MultiDraw.h"
-#include "Managers.h"
-#include <MG_State/GLState/Core.h>
-#include <cstring>
-#include <limits>
-
-namespace MobileGL::MG_Backend::DirectGLES::MultiDrawImpl {
-    using MG_Config::GLESMultiDrawMode;
-
-    namespace {
-        // ---------------------------------------------------------------------------
-        // Batch shape
-        // ---------------------------------------------------------------------------
-
-        SizeT IndexTypeSize(GLenum type) {
-            switch (type) {
-            case GL_UNSIGNED_BYTE: return 1;
-            case GL_UNSIGNED_SHORT: return 2;
-            case GL_UNSIGNED_INT: return 4;
-            default: return 0;
-            }
-        }
-
-        // The all-ones value of an index type, which is what GL restarts on once
-        // primitive restart is in play. CheckPrimitiveRestartSupported has already
-        // rejected the arbitrary-index form of GL_PRIMITIVE_RESTART, so an enabled
-        // restart always restarts here and nowhere else.
-        Uint32 RestartSentinelFor(GLenum type) {
-            switch (type) {
-            case GL_UNSIGNED_BYTE: return 0xFFu;
-            case GL_UNSIGNED_SHORT: return 0xFFFFu;
-            default: return 0xFFFFFFFFu;
-            }
-        }
-
-        Bool RestartActive() {
-            return MG_State::pGLContext->IsCapabilityEnabled(CapabilityInput::PrimitiveRestart) ||
-                   MG_State::pGLContext->IsCapabilityEnabled(CapabilityInput::PrimitiveRestartFixedIndex);
-        }
-
-        // Vertices per primitive for the modes whose sub-draws may be concatenated into a
-        // single draw without changing the primitive stream. Zero for strip/loop/fan modes
-        // (concatenation would weld one sub-draw's last primitive to the next sub-draw's
-        // first) and for GL_PATCHES, whose primitive size is dynamic tessellation state.
-        Uint32 ConcatenablePrimitiveSize(GLenum mode) {
-            switch (mode) {
-            case GL_POINTS: return 1;
-            case GL_LINES: return 2;
-            case GL_TRIANGLES: return 3;
-            case GL_LINES_ADJACENCY: return 4;
-            case GL_TRIANGLES_ADJACENCY: return 6;
-            default: return 0;
-            }
-        }
-
-        // Beyond this an emulated batch would ask for a scratch allocation measured in
-        // hundreds of megabytes (and the scratch ring never shrinks again); decline and let
-        // a per-sub-draw tier handle it instead of trying and failing inside the driver.
-        constexpr SizeT kMaxFlattenedIndices = SizeT{1} << 24;
-
-        // The flattening dispatch is one invocation per output index. ES 3.1 only
-        // guarantees 65535 work groups per dimension, and exceeding it makes
-        // glDispatchCompute an INVALID_VALUE no-op - which would leave the draw reading an
-        // uninitialised index buffer rather than failing visibly. Cap the tier there
-        // instead of querying: 4.19M indices is far past any real multi-draw batch, and
-        // beyond it the per-sub-draw tiers are the better answer anyway.
-        constexpr SizeT kComputeWorkGroupSize = 64;
-        constexpr SizeT kMaxComputeWorkGroups = 65535;
-        constexpr SizeT kMaxComputeFlattenedIndices = kMaxComputeWorkGroups * kComputeWorkGroupSize;
-
-        Uint BoundDrawIndirectBufferId() {
-            const auto& indirect =
-                MG_State::pGLContext->GetBufferBindingSlot(BufferTarget::DrawIndirect).GetBoundObject();
-            if (!indirect) return 0;
-            const auto* resource = BufferImpl::EnsureBufferResource(indirect);
-            return resource ? resource->id : 0;
-        }
-
-        const SharedPtr<MG_State::GLState::BufferObject>& BoundIndexBuffer() {
-            static const SharedPtr<MG_State::GLState::BufferObject> none;
-            const auto& vao = MG_State::pGLContext->GetBoundVertexArray();
-            if (!vao) return none;
-            return vao->GetIndexBufferBindingSlot().GetBoundObject();
-        }
-
-        // The GL name PrepareForDraw left on GL_ELEMENT_ARRAY_BUFFER, i.e. what a tier
-        // that swaps in a scratch index buffer has to put back. Restoring the exact name
-        // matters beyond tidiness: the VAO twin memoises that it already synced this
-        // index binding and will not re-issue it on the next draw.
-        Uint BoundIndexBufferId() {
-            const auto& ibo = BoundIndexBuffer();
-            if (!ibo) return 0;
-            const auto* resource = BufferImpl::EnsureBufferResource(ibo);
-            return resource ? resource->id : 0;
-        }
-
-        // ---------------------------------------------------------------------------
-        // Scratch GL objects
-        //
-        // All of them belong to the ES context and are abandoned (not deleted) when it
-        // dies, exactly like XfbImpl's scatter buffer: the names are the dead context's
-        // to reclaim, and deleting them would target whatever the successor context
-        // handed out for the same name.
-        // ---------------------------------------------------------------------------
-
-        struct ScratchBuffer {
-            Uint id = 0;
-            SizeT capacity = 0;
-            SizeT cursor = 0; // ring buffers only: next free byte
-        };
-
-        ScratchBuffer g_indirectCommands; // synthesized DrawElementsIndirectCommand array
-        ScratchBuffer g_rebasedIndices;   // CPU-rebased index stream
-        ScratchBuffer g_drawInfo;         // compute tier: per-sub-draw descriptors
-        ScratchBuffer g_flattenedIndices; // compute tier: flattened index stream
-
-        Uint g_computeProgram = 0;
-        Bool g_computeProgramFailed = false;
-        GLint g_uElementSize = -1;
-        GLint g_uDrawCount = -1;
-        GLint g_uTotalIndices = -1;
-
-        // Reused staging, so a steady stream of batches allocates nothing.
-        Vector<DrawElementsIndirectCommand> g_commandStaging;
-        Vector<Uint32> g_indexStaging;
-        Vector<Uint32> g_drawInfoStaging;
-        Vector<GLint> g_zeroBaseVertices;
-
-        // Everything below stages through GL_ARRAY_BUFFER, the manager-wide staging target
-        // (BufferImpl::TempBufferTarget); binding it disturbs no VAO state.
-        Bool EnsureScratchName(ScratchBuffer& buffer) {
-            if (buffer.id != 0) return true;
-            GLuint id = 0;
-            g_GLESFuncs.glGenBuffers(1, &id);
-            if (id == 0) return false;
-            buffer.id = id;
-            buffer.capacity = 0;
-            buffer.cursor = 0;
-            return true;
-        }
-
-        // Whole-buffer upload, for the two buffers that are read from offset 0 because they
-        // are bound as storage blocks. Respecifies rather than sub-updates: glBufferData
-        // orphans the previous store, so the upload never waits on a dispatch still reading
-        // the old contents out of the same name.
-        Bool UploadScratch(ScratchBuffer& buffer, SizeT bytes, const void* data) {
-            if (bytes == 0) return true;
-            if (!EnsureScratchName(buffer)) return false;
-            BufferImpl::BindBufferId(BufferImpl::TempBufferTarget, buffer.id);
-            // Grow in powers of two so a batch that creeps up in size stops respecifying.
-            SizeT capacity = buffer.capacity == 0 ? bytes : buffer.capacity;
-            while (capacity < bytes) capacity *= 2;
-            g_GLESFuncs.glBufferData(BufferImpl::TempBufferTarget, static_cast<GLsizeiptr>(capacity), nullptr,
-                                     GL_STREAM_DRAW);
-            buffer.capacity = capacity;
-            buffer.cursor = 0;
-            if (data) {
-                g_GLESFuncs.glBufferSubData(BufferImpl::TempBufferTarget, 0, static_cast<GLsizeiptr>(bytes), data);
-            }
-            return true;
-        }
-
-        // Ring upload, for the buffers whose consumers can address a byte offset (indirect
-        // commands and rewritten index streams). Respecifying per batch is what an
-        // orphan-every-time scheme costs, and on a desktop-class driver that allocation
-        // dominated the tiers that use these buffers - a multi-draw of 32 sub-draws stages
-        // 640 bytes and paid for a fresh store to hold them. Bump-allocating instead means
-        // one respecify per wrap; every byte between two wraps is written exactly once, so
-        // nothing in flight is overwritten, and the wrap itself orphans.
-        constexpr SizeT kRingAlignment = 16; // >= 4, so both command and uint32-index offsets stay legal
-        constexpr SizeT kMinRingBytes = 1u << 16;
-
-        Bool UploadScratchRing(ScratchBuffer& buffer, SizeT bytes, const void* data, SizeT& outOffset) {
-            outOffset = 0;
-            if (bytes == 0) return true;
-            if (!EnsureScratchName(buffer)) return false;
-            BufferImpl::BindBufferId(BufferImpl::TempBufferTarget, buffer.id);
-
-            const SizeT aligned = (bytes + kRingAlignment - 1) & ~(kRingAlignment - 1);
-            if (buffer.capacity < aligned) {
-                SizeT capacity = buffer.capacity == 0 ? kMinRingBytes : buffer.capacity;
-                while (capacity < aligned) capacity *= 2;
-                g_GLESFuncs.glBufferData(BufferImpl::TempBufferTarget, static_cast<GLsizeiptr>(capacity), nullptr,
-                                         GL_STREAM_DRAW);
-                buffer.capacity = capacity;
-                buffer.cursor = 0;
-            } else if (buffer.cursor + aligned > buffer.capacity) {
-                g_GLESFuncs.glBufferData(BufferImpl::TempBufferTarget, static_cast<GLsizeiptr>(buffer.capacity),
-                                         nullptr, GL_STREAM_DRAW);
-                buffer.cursor = 0;
-            }
-
-            outOffset = buffer.cursor;
-            if (data) {
-                g_GLESFuncs.glBufferSubData(BufferImpl::TempBufferTarget, static_cast<GLintptr>(outOffset),
-                                            static_cast<GLsizeiptr>(bytes), data);
-            }
-            buffer.cursor += aligned;
-            return true;
-        }
-
-        // ---------------------------------------------------------------------------
-        // Tier resolution
-        // ---------------------------------------------------------------------------
-
-        // Best-first, and measured rather than assumed. MobileGlues orders its own Auto
-        // multiindirect -> indirect -> basevertex; on both ES drivers available here that
-        // is backwards, because staging a command buffer per batch costs more than the
-        // driver entries it saves. mc_sodium_multidraw (132 batches x 32 sub-draws),
-        // ns/op, median of three:
-        //
-        //                    NVIDIA ES 3.2   Mesa llvmpipe ES 3.2
-        //   ext                  n/a               19300
-        //   basevertex           2500              25200
-        //   multiindirect        5700              27600
-        //   drawelements         5600              28700
-        //   indirect             5800              31000
-        //
-        // Ring-allocating the command staging (instead of respecifying per batch) was
-        // tried first and moved the indirect tiers by less than noise, so the cost is the
-        // indirect draw path itself, not the upload. Only "ext" - a real multi-draw entry
-        // point rather than an indirect one - actually beats replaying the sub-draws.
-        //
-        // The compute tier is deliberately absent from the ladder: it rewrites the
-        // primitive stream rather than replaying it, and it measured slowest of all here,
-        // so it stays opt-in behind the env knob (the same call MobileGlues makes - its
-        // Auto never selects Compute either).
-        constexpr GLESMultiDrawMode kAutoLadder[] = {
-            GLESMultiDrawMode::Ext,      GLESMultiDrawMode::BaseVertex,   GLESMultiDrawMode::MultiIndirect,
-            GLESMultiDrawMode::Indirect, GLESMultiDrawMode::DrawElements,
-        };
-
-        Bool SupportsTier(GLESMultiDrawMode tier) {
-            return IsTierSupported(g_GLESCapabilities, g_GLESFuncs, tier);
-        }
-
-        GLESMultiDrawMode g_resolvedTier = GLESMultiDrawMode::Auto;
-        Bool g_tierResolved = false;
-        String g_tierResolution;
-
-        void ResolveTierOnce() {
-            if (g_tierResolved) return;
-            g_tierResolved = true;
-            g_resolvedTier =
-                ResolveTier(g_GLESCapabilities, g_GLESFuncs, MG_Config::Features.EsprytMultiDrawMode,
-                            &g_tierResolution);
-            MGLOG_D("DirectGLES multi-draw: %s", g_tierResolution.c_str());
-        }
-
-        // Which tiers have already announced themselves, one bit per GLESMultiDrawMode.
-        // The resolution line above says which tier was CHOSEN; this says which one a
-        // batch actually went through, and the two differ whenever a batch's shape
-        // demotes it. Worth a line each: a multi-draw path that resolves to a tier and
-        // then quietly runs a different one is exactly how "the batch drew nothing"
-        // hides.
-        Uint32 g_announcedTiers = 0;
-
-        void NoteTierExecuted(GLESMultiDrawMode tier) {
-            const Uint32 bit = 1u << static_cast<Uint32>(tier);
-            if (g_announcedTiers & bit) return;
-            g_announcedTiers |= bit;
-            MGLOG_D("DirectGLES multi-draw: first batch executed via tier \"%s\"", TierName(tier));
-        }
-
-        // The tier this particular batch can actually take. A tier is demoted here when
-        // the batch's own shape - not the driver - rules it out; the compute tier keeps
-        // its remaining feasibility checks inside its implementation, where the data it
-        // has to walk is already in hand.
-        GLESMultiDrawMode ResolveTierForBatch(Bool programReadsDrawID, Bool perSubDrawBaseVertex,
-                                              Bool hasIndexBuffer) {
-            ResolveTierOnce();
-            GLESMultiDrawMode tier = g_resolvedTier;
-
-            // Batched tiers issue one driver entry for the whole batch, so the emulated
-            // gl_DrawID uniform can only hold one value across every sub-draw. A program
-            // that reads gl_DrawID gets an unrolled tier, which feeds each sub-draw its
-            // own index (the spec's value); nothing else observes the difference. The
-            // emulated gl_BaseVertex is one uniform for the same reason, so a batch whose
-            // sub-draws carry their own base vertices unrolls too - even the Ext tier,
-            // which hands the driver the whole basevertex array, can only leave ONE value
-            // in the uniform the shader reads.
-            const Bool batched = tier == GLESMultiDrawMode::Ext || tier == GLESMultiDrawMode::MultiIndirect ||
-                                 tier == GLESMultiDrawMode::Compute;
-            if (batched && (programReadsDrawID || perSubDrawBaseVertex)) {
-                tier = SupportsTier(GLESMultiDrawMode::BaseVertex) ? GLESMultiDrawMode::BaseVertex
-                                                                   : GLESMultiDrawMode::DrawElements;
-            }
-
-            // The indirect tiers describe each sub-draw as an element offset into the
-            // bound element array buffer. A client-memory index array has no such buffer,
-            // and indirect draws are not defined without one.
-            if (!hasIndexBuffer &&
-                (tier == GLESMultiDrawMode::MultiIndirect || tier == GLESMultiDrawMode::Indirect)) {
-                tier = SupportsTier(GLESMultiDrawMode::BaseVertex) ? GLESMultiDrawMode::BaseVertex
-                                                                   : GLESMultiDrawMode::DrawElements;
-            }
-            return tier;
-        }
-
-        // ---------------------------------------------------------------------------
-        // Index rewriting, shared by the two tiers that fold base vertices into indices
-        // ---------------------------------------------------------------------------
-
-        // Both of those tiers emit GL_UNSIGNED_INT regardless of the source type. Keeping
-        // the source width would be wrong, not merely tight: GL adds baseVertex to the
-        // index at full precision, so a GL_UNSIGNED_SHORT index plus a base vertex past
-        // 65535 addresses a vertex the source type cannot spell. Widening also gives the
-        // rewritten stream a restart sentinel (0xFFFFFFFF) that survives the rebase.
-        void RebaseIndices(const Uint8* source, SizeT sourceIndexCount, SizeT indexSize, Int32 baseVertex,
-                           Bool restartActive, Uint32 restartSentinel, Uint32* out) {
-            const Uint32 baseVertexBits = static_cast<Uint32>(baseVertex);
-            for (SizeT i = 0; i < sourceIndexCount; ++i) {
-                Uint32 value = 0;
-                switch (indexSize) {
-                case 1: value = source[i]; break;
-                case 2: {
-                    Uint16 narrow = 0;
-                    std::memcpy(&narrow, source + i * 2, sizeof(narrow));
-                    value = narrow;
-                    break;
-                }
-                default: std::memcpy(&value, source + i * 4, sizeof(value)); break;
-                }
-                // Unsigned wraparound is the defined behaviour for a negative base vertex.
-                out[i] = (restartActive && value == restartSentinel) ? 0xFFFFFFFFu : value + baseVertexBits;
-            }
-        }
-
-        // CPU-readable bytes of one sub-draw's indices, from the frontend shadow of the
-        // bound index buffer or straight from the client array. Null when the sub-draw
-        // would read outside the buffer.
-        const Uint8* ResolveSubDrawIndices(const SharedPtr<MG_State::GLState::BufferObject>& indexBuffer,
-                                           const Uint8* indexBufferBytes, SizeT indexBufferSize, const void* indices,
-                                           SizeT indexCount, SizeT indexSize) {
-            if (!indexBuffer) {
-                return static_cast<const Uint8*>(indices);
-            }
-            if (!indexBufferBytes) return nullptr;
-            const SizeT byteOffset = reinterpret_cast<SizeT>(indices);
-            const SizeT byteEnd = byteOffset + indexCount * indexSize;
-            if (byteEnd > indexBufferSize || byteEnd < byteOffset) return nullptr;
-            return indexBufferBytes + byteOffset;
-        }
-
-        // ---------------------------------------------------------------------------
-        // Tier: Ext - one glMultiDrawElementsBaseVertexEXT
-        // ---------------------------------------------------------------------------
-
-        Bool RunExt(GLenum mode, const GLsizei* count, GLenum type, const GLvoid* const* indices, GLsizei drawcount,
-                    const GLint* basevertex) {
-            if (!SupportsTier(GLESMultiDrawMode::Ext)) return false;
-            const GLint* baseVertices = basevertex;
-            if (!baseVertices) {
-                // glMultiDrawElements: every base vertex is 0, but the entry point still
-                // wants an array. One permanently-zero vector serves every such batch.
-                if (g_zeroBaseVertices.size() < static_cast<SizeT>(drawcount)) {
-                    g_zeroBaseVertices.resize(static_cast<SizeT>(drawcount), 0);
-                }
-                baseVertices = g_zeroBaseVertices.data();
-            }
-            g_GLESFuncs.glMultiDrawElementsBaseVertexEXT(mode, count, type, indices, drawcount, baseVertices);
-            NoteTierExecuted(GLESMultiDrawMode::Ext);
-            return true;
-        }
-
-        // ---------------------------------------------------------------------------
-        // Tiers: MultiIndirect / Indirect - synthesized indirect commands
-        // ---------------------------------------------------------------------------
-
-        Bool RunIndirect(GLenum mode, const GLsizei* count, GLenum type, const GLvoid* const* indices,
-                         GLsizei drawcount, const GLint* basevertex, Bool batched, Bool feedDrawID,
-                         Bool feedBaseVertex) {
-            if (!SupportsTier(batched ? GLESMultiDrawMode::MultiIndirect : GLESMultiDrawMode::Indirect)) return false;
-            const SizeT indexSize = IndexTypeSize(type);
-            if (indexSize == 0) return false;
-            // Indirect commands address indices as an element offset into the bound element
-            // array buffer, and an indirect draw is not defined without one.
-            const auto& indexBuffer = BoundIndexBuffer();
-            if (!indexBuffer) return false;
-
-            g_commandStaging.resize(static_cast<SizeT>(drawcount));
-            for (GLsizei i = 0; i < drawcount; ++i) {
-                const SizeT byteOffset = reinterpret_cast<SizeT>(indices[i]);
-                // firstIndex counts elements, so an offset that is not a whole number of
-                // them cannot be expressed as a command at all.
-                if (byteOffset % indexSize != 0) return false;
-                auto& command = g_commandStaging[static_cast<SizeT>(i)];
-                command.count = count[i] > 0 ? static_cast<Uint32>(count[i]) : 0u;
-                command.instanceCount = 1;
-                command.firstIndex = static_cast<Uint32>(byteOffset / indexSize);
-                command.baseVertex = basevertex ? basevertex[i] : 0;
-                command.baseInstance = 0;
-            }
-
-            const SizeT commandBytes = g_commandStaging.size() * sizeof(DrawElementsIndirectCommand);
-            SizeT commandBase = 0;
-            if (!UploadScratchRing(g_indirectCommands, commandBytes, g_commandStaging.data(), commandBase)) {
-                return false;
-            }
-
-            // Every synthesized command carries baseInstance 0. Say so through the direct
-            // path, which also clears the indirect-params word index a preceding real
-            // indirect draw may have left pointing into its own command buffer.
-            SetCurrentBaseInstance(0);
-
-            const Uint previousIndirectBinding = BoundDrawIndirectBufferId();
-            BufferImpl::BindBufferId(GL_DRAW_INDIRECT_BUFFER, g_indirectCommands.id);
-            if (batched) {
-                ForEachViewportRoutingPass([&] {
-                    g_GLESFuncs.glMultiDrawElementsIndirectEXT(mode, type, reinterpret_cast<const void*>(commandBase),
-                                                               drawcount, 0);
-                });
-            } else {
-                for (GLsizei i = 0; i < drawcount; ++i) {
-                    if (feedDrawID) SetCurrentDrawID(static_cast<Uint32>(i));
-                    if (feedBaseVertex) SetCurrentBaseVertex(basevertex ? basevertex[i] : 0);
-                    const SizeT commandOffset = commandBase + static_cast<SizeT>(i) * sizeof(DrawElementsIndirectCommand);
-                    ForEachViewportRoutingPass([&] {
-                        g_GLESFuncs.glDrawElementsIndirect(mode, type, reinterpret_cast<const void*>(commandOffset));
-                    });
-                }
-                if (feedDrawID) SetCurrentDrawID(0);
-                if (feedBaseVertex) SetCurrentBaseVertex(0);
-            }
-            BufferImpl::BindBufferId(GL_DRAW_INDIRECT_BUFFER, previousIndirectBinding);
-            NoteTierExecuted(batched ? GLESMultiDrawMode::MultiIndirect : GLESMultiDrawMode::Indirect);
-            return true;
-        }
-
-        // ---------------------------------------------------------------------------
-        // Tier: BaseVertex - the per-sub-draw replay
-        // ---------------------------------------------------------------------------
-
-        Bool RunBaseVertexLoop(GLenum mode, const GLsizei* count, GLenum type, const GLvoid* const* indices,
-                               GLsizei drawcount, const GLint* basevertex, Bool feedDrawID, Bool feedBaseVertex) {
-            if (!SupportsTier(GLESMultiDrawMode::BaseVertex)) return false;
-            for (GLsizei i = 0; i < drawcount; ++i) {
-                if (count[i] <= 0) continue;
-                if (feedDrawID) SetCurrentDrawID(static_cast<Uint32>(i));
-                if (feedBaseVertex) SetCurrentBaseVertex(basevertex ? basevertex[i] : 0);
-                ForEachViewportRoutingPass([&] {
-                    g_GLESFuncs.glDrawElementsBaseVertex(mode, count[i], type, indices[i],
-                                                         basevertex ? basevertex[i] : 0);
-                });
-            }
-            if (feedDrawID) SetCurrentDrawID(0);
-            if (feedBaseVertex) SetCurrentBaseVertex(0);
-            NoteTierExecuted(GLESMultiDrawMode::BaseVertex);
-            return true;
-        }
-
-        // ---------------------------------------------------------------------------
-        // Tier: DrawElements - base vertices folded into a scratch index stream
-        // ---------------------------------------------------------------------------
-
-        Bool RunRebasedDrawElements(GLenum mode, const GLsizei* count, GLenum type, const GLvoid* const* indices,
-                                    GLsizei drawcount, const GLint* basevertex, Bool feedDrawID,
-                                    Bool feedBaseVertex) {
-            const SizeT indexSize = IndexTypeSize(type);
-            if (indexSize == 0) return false;
-
-            SizeT total = 0;
-            for (GLsizei i = 0; i < drawcount; ++i) {
-                if (count[i] > 0) total += static_cast<SizeT>(count[i]);
-            }
-            if (total == 0) return true;
-            if (total > kMaxFlattenedIndices) return false;
-
-            const auto& indexBuffer = BoundIndexBuffer();
-            const Uint8* indexBufferBytes = nullptr;
-            SizeT indexBufferSize = 0;
-            if (indexBuffer) {
-                // The shadow is the source of truth for CPU reads, but a persistent map or
-                // a shader write may have moved past it since the last sync.
-                indexBuffer->SyncPersistentMappedRange();
-                indexBuffer->SyncGpuWrites();
-                indexBufferBytes = indexBuffer->MappedData();
-                indexBufferSize = indexBuffer->GetSize();
-            }
-
-            const Bool restartActive = RestartActive();
-            const Uint32 restartSentinel = RestartSentinelFor(type);
-            g_indexStaging.resize(total);
-            SizeT cursor = 0;
-            for (GLsizei i = 0; i < drawcount; ++i) {
-                if (count[i] <= 0) continue;
-                const SizeT subDrawCount = static_cast<SizeT>(count[i]);
-                const Uint8* source = ResolveSubDrawIndices(indexBuffer, indexBufferBytes, indexBufferSize, indices[i],
-                                                            subDrawCount, indexSize);
-                if (!source) {
-                    MGLOG_E_ONCE("DirectGLES multi-draw (drawelements tier): sub-draw %d reads outside the bound index "
-                            "buffer; skipping the batch",
-                            i);
-                    return false;
-                }
-                RebaseIndices(source, subDrawCount, indexSize, basevertex ? basevertex[i] : 0, restartActive,
-                              restartSentinel, g_indexStaging.data() + cursor);
-                cursor += subDrawCount;
-            }
-
-            SizeT indexBase = 0;
-            if (!UploadScratchRing(g_rebasedIndices, total * sizeof(Uint32), g_indexStaging.data(), indexBase)) {
-                return false;
-            }
-
-            const Uint previousIndexBinding = BoundIndexBufferId();
-            BufferImpl::BindBufferId(GL_ELEMENT_ARRAY_BUFFER, g_rebasedIndices.id);
-            cursor = 0;
-            for (GLsizei i = 0; i < drawcount; ++i) {
-                if (count[i] <= 0) continue;
-                if (feedDrawID) SetCurrentDrawID(static_cast<Uint32>(i));
-                // The base vertex is folded into the rewritten index stream here, so the
-                // driver sees none - but gl_BaseVertex still has to report the value the
-                // application passed for this sub-draw.
-                if (feedBaseVertex) SetCurrentBaseVertex(basevertex ? basevertex[i] : 0);
-                ForEachViewportRoutingPass([&] {
-                    g_GLESFuncs.glDrawElements(mode, count[i], GL_UNSIGNED_INT,
-                                               reinterpret_cast<const void*>(indexBase + cursor * sizeof(Uint32)));
-                });
-                cursor += static_cast<SizeT>(count[i]);
-            }
-            if (feedDrawID) SetCurrentDrawID(0);
-            if (feedBaseVertex) SetCurrentBaseVertex(0);
-            BufferImpl::BindBufferId(GL_ELEMENT_ARRAY_BUFFER, previousIndexBinding);
-            NoteTierExecuted(GLESMultiDrawMode::DrawElements);
-            return true;
-        }
-
-        // ---------------------------------------------------------------------------
-        // Tier: Compute - the whole batch flattened into one rebased index stream
-        // ---------------------------------------------------------------------------
-
-        // One index per invocation. The sub-draw an output slot belongs to is found by
-        // binary search over the inclusive prefix sums of the sub-draw counts, which is
-        // why the descriptors are sorted by construction. Sub-draws with a zero count
-        // repeat the previous prefix sum and are therefore skipped by the search.
-        //
-        // Three storage blocks, not the five the shape suggests: ES 3.1 only guarantees
-        // four per compute stage, so the per-sub-draw descriptors share one buffer.
-        constexpr const char* kFlattenComputeSource = R"(#version 310 es
-layout(local_size_x = 64) in;
-
-uniform uint uElementSize;
-uniform uint uDrawCount;
-uniform uint uTotalIndices;
-
-layout(std430, binding = 0) readonly buffer SourceIndices { uint sourceWords[]; };
-layout(std430, binding = 1) readonly buffer DrawInfo { uint drawInfo[]; };
-layout(std430, binding = 2) writeonly buffer FlatIndices { uint flatIndices[]; };
-
-uint ReadSourceIndex(uint element) {
-    if (uElementSize == 4u) {
-        return sourceWords[element];
-    }
-    if (uElementSize == 2u) {
-        uint word = sourceWords[element >> 1u];
-        return (word >> ((element & 1u) * 16u)) & 0xFFFFu;
-    }
-    uint word = sourceWords[element >> 2u];
-    return (word >> ((element & 3u) * 8u)) & 0xFFu;
-}
-
-void main() {
-    uint outIndex = gl_GlobalInvocationID.x;
-    if (outIndex >= uTotalIndices) {
-        return;
-    }
-
-    uint low = 0u;
-    uint high = uDrawCount - 1u;
-    while (low < high) {
-        uint mid = low + (high - low) / 2u;
-        if (drawInfo[mid * 3u + 2u] > outIndex) {
-            high = mid;
-        } else {
-            low = mid + 1u;
-        }
-    }
-
-    uint localIndex = outIndex - (low == 0u ? 0u : drawInfo[(low - 1u) * 3u + 2u]);
-    // Unsigned wraparound is the defined behaviour for a negative base vertex. No
-    // restart sentinel handling: the tier declines outright while restart is enabled.
-    flatIndices[outIndex] = ReadSourceIndex(localIndex + drawInfo[low * 3u]) + drawInfo[low * 3u + 1u];
-}
-)";
-
-        struct FlattenedStream {
-            Uint bufferId = 0;
-            SizeT indexCount = 0;
-        };
-
-        Bool EnsureComputeProgram() {
-            if (g_computeProgram != 0) return true;
-            if (g_computeProgramFailed) return false;
-            g_computeProgramFailed = true; // cleared again only on a complete success
-
-            const GLuint shader = g_GLESFuncs.glCreateShader(GL_COMPUTE_SHADER);
-            if (shader == 0) {
-                MGLOG_E_ONCE("DirectGLES multi-draw (compute tier): glCreateShader(GL_COMPUTE_SHADER) failed");
-                return false;
-            }
-            const char* source = kFlattenComputeSource;
-            g_GLESFuncs.glShaderSource(shader, 1, &source, nullptr);
-            g_GLESFuncs.glCompileShader(shader);
-            GLint status = GL_FALSE;
-            g_GLESFuncs.glGetShaderiv(shader, GL_COMPILE_STATUS, &status);
-            if (status != GL_TRUE) {
-                char log[1024] = {};
-                g_GLESFuncs.glGetShaderInfoLog(shader, sizeof(log) - 1, nullptr, log);
-                MGLOG_E_ONCE("DirectGLES multi-draw (compute tier): index-flattening shader failed to compile: %s", log);
-                g_GLESFuncs.glDeleteShader(shader);
-                return false;
-            }
-
-            const GLuint program = g_GLESFuncs.glCreateProgram();
-            if (program == 0) {
-                MGLOG_E_ONCE("DirectGLES multi-draw (compute tier): glCreateProgram failed");
-                g_GLESFuncs.glDeleteShader(shader);
-                return false;
-            }
-            g_GLESFuncs.glAttachShader(program, shader);
-            g_GLESFuncs.glLinkProgram(program);
-            g_GLESFuncs.glDeleteShader(shader);
-            g_GLESFuncs.glGetProgramiv(program, GL_LINK_STATUS, &status);
-            if (status != GL_TRUE) {
-                char log[1024] = {};
-                g_GLESFuncs.glGetProgramInfoLog(program, sizeof(log) - 1, nullptr, log);
-                MGLOG_E_ONCE("DirectGLES multi-draw (compute tier): index-flattening program failed to link: %s", log);
-                g_GLESFuncs.glDeleteProgram(program);
-                return false;
-            }
-
-            g_computeProgram = program;
-            g_uElementSize = g_GLESFuncs.glGetUniformLocation(program, "uElementSize");
-            g_uDrawCount = g_GLESFuncs.glGetUniformLocation(program, "uDrawCount");
-            g_uTotalIndices = g_GLESFuncs.glGetUniformLocation(program, "uTotalIndices");
-            g_computeProgramFailed = false;
-            MGLOG_D("DirectGLES multi-draw: index-flattening compute program ready (id %u)", program);
-            return true;
-        }
-
-        // Builds the flattened stream, or leaves `out` empty when this batch's shape rules
-        // the tier out. Runs BEFORE PrepareForDraw - see the call site - so it may leave
-        // the compute program current and the first storage points unbound; the
-        // preparation that follows re-establishes both.
-        void FlattenWithCompute(GLenum mode, const GLsizei* count, GLenum type, const GLvoid* const* indices,
-                                GLsizei drawcount, const GLint* basevertex, FlattenedStream& out) {
-            if (!SupportsTier(GLESMultiDrawMode::Compute)) return;
-            const SizeT indexSize = IndexTypeSize(type);
-            if (indexSize == 0) return;
-
-            // Merging sub-draws into a single draw only reproduces the original primitive
-            // stream for list-shaped modes: a strip, loop or fan would gain primitives
-            // spanning the seam between two sub-draws.
-            const Uint32 primitiveSize = ConcatenablePrimitiveSize(mode);
-            if (primitiveSize == 0) return;
-
-            // Primitive restart defeats the whole-multiple-of-a-primitive argument below,
-            // even for a list mode. A restart ends the current primitive, so a sub-draw of
-            // six GL_TRIANGLES indices with a restart after the third emits ONE triangle
-            // and drops the two leftover vertices - and once concatenated those leftovers
-            // find a third vertex in the next sub-draw and become a triangle that GL never
-            // draws. Splicing separator sentinels into the flattened stream could fix it,
-            // at the cost of a per-sub-draw offset the prefix-sum layout does not carry;
-            // declining is the honest trade for a tier that is already opt-in.
-            if (RestartActive()) return;
-
-            // The shader reads the source indices as a storage buffer, so there has to be
-            // a real buffer to read - a client-memory index array has none.
-            const auto& indexBuffer = BoundIndexBuffer();
-            if (!indexBuffer) return;
-
-            // A dispatch inside an open capture span is not legal, and the span would also
-            // observe one merged draw rather than the batch it asked for.
-            if (XfbImpl::IsCaptureSpanOpen()) return;
-
-            auto* sourceResource = BufferImpl::EnsureBufferResource(indexBuffer);
-            if (!sourceResource || sourceResource->id == 0) return;
-            const SizeT sourceSize = indexBuffer->GetSize();
-            // std430 addresses the source as uint[]; a tail shorter than a word is not
-            // reachable, so a narrow index type needs a word-multiple buffer.
-            if (indexSize < 4 && (sourceSize % 4) != 0) return;
-
-            g_drawInfoStaging.resize(3 * static_cast<SizeT>(drawcount));
-            SizeT total = 0;
-            for (GLsizei i = 0; i < drawcount; ++i) {
-                const SizeT subDrawCount = count[i] > 0 ? static_cast<SizeT>(count[i]) : 0;
-                // GL drops a trailing partial primitive per sub-draw; concatenation would
-                // instead splice it onto the next sub-draw's first vertices.
-                if (subDrawCount % primitiveSize != 0) return;
-                const SizeT byteOffset = reinterpret_cast<SizeT>(indices[i]);
-                if (byteOffset % indexSize != 0) return;
-                if (subDrawCount != 0) {
-                    const SizeT byteEnd = byteOffset + subDrawCount * indexSize;
-                    if (byteEnd > sourceSize || byteEnd < byteOffset) return;
-                }
-                total += subDrawCount;
-                if (total > kMaxComputeFlattenedIndices) return;
-                const SizeT slot = 3 * static_cast<SizeT>(i);
-                g_drawInfoStaging[slot] = static_cast<Uint32>(byteOffset / indexSize);
-                g_drawInfoStaging[slot + 1] = static_cast<Uint32>(basevertex ? basevertex[i] : 0);
-                g_drawInfoStaging[slot + 2] = static_cast<Uint32>(total);
-            }
-            if (total == 0) return; // nothing to draw; the ordinary tiers no-op just as well
-
-            if (!EnsureComputeProgram()) return;
-            if (!UploadScratch(g_drawInfo, g_drawInfoStaging.size() * sizeof(Uint32), g_drawInfoStaging.data())) {
-                return;
-            }
-            if (!UploadScratch(g_flattenedIndices, total * sizeof(Uint32), nullptr)) return;
-
-            BufferImpl::BindBufferBaseCached(GL_SHADER_STORAGE_BUFFER, 0, sourceResource->id);
-            BufferImpl::BindBufferBaseCached(GL_SHADER_STORAGE_BUFFER, 1, g_drawInfo.id);
-            BufferImpl::BindBufferBaseCached(GL_SHADER_STORAGE_BUFFER, 2, g_flattenedIndices.id);
-
-            g_GLESFuncs.glUseProgram(g_computeProgram);
-            PrgramImpl::g_lastUsedBackendProgramId = g_computeProgram;
-            if (g_uElementSize >= 0) g_GLESFuncs.glUniform1ui(g_uElementSize, static_cast<GLuint>(indexSize));
-            if (g_uDrawCount >= 0) g_GLESFuncs.glUniform1ui(g_uDrawCount, static_cast<GLuint>(drawcount));
-            if (g_uTotalIndices >= 0) g_GLESFuncs.glUniform1ui(g_uTotalIndices, static_cast<GLuint>(total));
-
-            g_GLESFuncs.glDispatchCompute(
-                static_cast<GLuint>((total + kComputeWorkGroupSize - 1) / kComputeWorkGroupSize), 1, 1);
-            g_GLESFuncs.glMemoryBarrier(GL_SHADER_STORAGE_BARRIER_BIT | GL_ELEMENT_ARRAY_BARRIER_BIT);
-
-            // Hand the storage points back to their GL default. PrepareForDraw re-syncs
-            // only the points the app has actually touched, so leaving a scratch buffer on
-            // an untouched point would keep it visible to the next shader that declares one.
-            for (Uint point = 0; point < 3; ++point) {
-                BufferImpl::BindBufferBaseCached(GL_SHADER_STORAGE_BUFFER, point, 0);
-            }
-
-            NoteTierExecuted(GLESMultiDrawMode::Compute);
-            out.bufferId = g_flattenedIndices.id;
-            out.indexCount = total;
-        }
-    } // namespace
-
-    // -------------------------------------------------------------------------------
-    // Public surface
-    // -------------------------------------------------------------------------------
-
-    Bool IsTierSupported(const MG_External::GLESCapabilities& caps, const MG_External::GLESFunctionsTable& funcs,
-                         GLESMultiDrawMode tier) {
-        const Bool esAtLeast31 =
-            caps.GLESVersion.Major > 3 || (caps.GLESVersion.Major == 3 && caps.GLESVersion.Minor >= 1);
-        switch (tier) {
-        case GLESMultiDrawMode::Ext:
-            return caps.SupportsMultiDrawElementsBaseVertex;
-        case GLESMultiDrawMode::MultiIndirect:
-            return caps.SupportsMultiDrawIndirect && esAtLeast31 && funcs.glDrawElementsIndirect != nullptr;
-        case GLESMultiDrawMode::Indirect:
-            return esAtLeast31 && funcs.glDrawElementsIndirect != nullptr;
-        case GLESMultiDrawMode::BaseVertex:
-            return caps.SupportsDrawElementsBaseVertex;
-        case GLESMultiDrawMode::DrawElements:
-            // Plain glDrawElements over a rewritten index stream: ES 2 core, so this is
-            // the floor every other tier can fall back to.
-            return true;
-        case GLESMultiDrawMode::Compute:
-            // Three storage blocks, which is inside the four ES 3.1 guarantees per stage.
-            return caps.SupportsComputeShader && caps.MaxComputeShaderStorageBlocks >= 3 &&
-                   funcs.glBindBufferBase != nullptr;
-        case GLESMultiDrawMode::Auto:
-            break;
-        }
-        return false;
-    }
-
-    GLESMultiDrawMode ResolveTier(const MG_External::GLESCapabilities& caps,
-                                  const MG_External::GLESFunctionsTable& funcs, GLESMultiDrawMode requested,
-                                  String* explanation) {
-        const auto bestAuto = [&]() {
-            for (const GLESMultiDrawMode tier : kAutoLadder) {
-                if (IsTierSupported(caps, funcs, tier)) return tier;
-            }
-            return GLESMultiDrawMode::DrawElements;
-        };
-
-        GLESMultiDrawMode resolved = GLESMultiDrawMode::DrawElements;
-        String line;
-        if (requested == GLESMultiDrawMode::Auto) {
-            resolved = bestAuto();
-            line = String("auto -> ") + TierName(resolved);
-        } else if (IsTierSupported(caps, funcs, requested)) {
-            resolved = requested;
-            line = String("MOBILEGL_ESPRYT_MULTIDRAW_MODE=") + TierName(requested) + " -> " + TierName(resolved);
-        } else {
-            resolved = bestAuto();
-            line = String("MOBILEGL_ESPRYT_MULTIDRAW_MODE=") + TierName(requested) +
-                   " requested but unsupported by this driver -> " + TierName(resolved);
-        }
-
-        if (explanation) {
-            String supported;
-            for (const GLESMultiDrawMode tier : kAutoLadder) {
-                if (!IsTierSupported(caps, funcs, tier)) continue;
-                if (!supported.empty()) supported += ", ";
-                supported += TierName(tier);
-            }
-            if (IsTierSupported(caps, funcs, GLESMultiDrawMode::Compute)) {
-                supported += supported.empty() ? "compute (opt-in)" : ", compute (opt-in)";
-            }
-            *explanation = line + " (driver supports: " + supported + ")";
-        }
-        return resolved;
-    }
-
-    const char* TierName(GLESMultiDrawMode tier) {
-        switch (tier) {
-        case GLESMultiDrawMode::Auto: return "auto";
-        case GLESMultiDrawMode::Ext: return "ext";
-        case GLESMultiDrawMode::MultiIndirect: return "multiindirect";
-        case GLESMultiDrawMode::Indirect: return "indirect";
-        case GLESMultiDrawMode::BaseVertex: return "basevertex";
-        case GLESMultiDrawMode::DrawElements: return "drawelements";
-        case GLESMultiDrawMode::Compute: return "compute";
-        }
-        return "unknown";
-    }
-
-    GLESMultiDrawMode ResolvedTier() {
-        ResolveTierOnce();
-        return g_resolvedTier;
-    }
-
-    String DescribeTierResolution() {
-        ResolveTierOnce();
-        return g_tierResolution;
-    }
-
-    void OnBackendContextDestroyed() {
-        g_indirectCommands = {};
-        g_rebasedIndices = {};
-        g_drawInfo = {};
-        g_flattenedIndices = {};
-        g_computeProgram = 0;
-        g_computeProgramFailed = false;
-        g_uElementSize = -1;
-        g_uDrawCount = -1;
-        g_uTotalIndices = -1;
-    }
-
-    void DrawElementsBatch(GLenum mode, const GLsizei* count, GLenum type, const GLvoid* const* indices,
-                           GLsizei drawcount, const GLint* basevertex) {
-        if (drawcount <= 0 || !count || !indices) return;
-        // State-independent and possibly throwing, so it runs before any GL work.
-        CheckPrimitiveRestartSupported(type);
-
-        const Bool hasIndexBuffer = BoundIndexBuffer() != nullptr;
-
-        // The compute tier dispatches BEFORE the draw state is established: doing it
-        // afterwards would mean unpicking the program, SSBO and index bindings
-        // PrepareForDraw just made, and a dispatch inside an open transform feedback
-        // span is not legal at all. On success it hands back a flattened index stream.
-        // A batch whose sub-draws carry their own base vertices cannot be flattened either
-        // when the program reads gl_BaseVertex: one draw call leaves one uniform value.
-        // Asked conservatively because this decision precedes PrepareForDraw - see
-        // CurrentProgramMayNeedPerSubDrawBuiltins. Flattening is the irreversible half:
-        // once the batch is one draw the values are gone, whereas declining to flatten only
-        // costs the unrolled tier.
-        FlattenedStream flattened;
-        if (ResolvedTier() == GLESMultiDrawMode::Compute &&
-            !CurrentProgramMayNeedPerSubDrawBuiltins(basevertex != nullptr)) {
-            FlattenWithCompute(mode, count, type, indices, drawcount, basevertex, flattened);
-        }
-
-        PrepareForDraw(DrawSyncBit::IndexBuffer);
-
-        if (flattened.indexCount != 0) {
-            const Uint previousIndexBinding = BoundIndexBufferId();
-            BufferImpl::BindBufferId(GL_ELEMENT_ARRAY_BUFFER, flattened.bufferId);
-            ForEachViewportRoutingPass([&] {
-                g_GLESFuncs.glDrawElements(mode, static_cast<GLsizei>(flattened.indexCount), GL_UNSIGNED_INT, nullptr);
-            });
-            BufferImpl::BindBufferId(GL_ELEMENT_ARRAY_BUFFER, previousIndexBinding);
-            return;
-        }
-
-        // Now that PrepareForDraw has synced the program, both questions have real answers;
-        // the tier choice and the per-sub-draw feeds use those, not the guess above.
-        const Bool feedDrawID = CurrentProgramReadsDrawID();
-        const Bool feedBaseVertex = basevertex != nullptr && CurrentProgramReadsBaseVertex();
-        const GLESMultiDrawMode tier = ResolveTierForBatch(feedDrawID, feedBaseVertex, hasIndexBuffer);
-
-        Bool drawn = false;
-        switch (tier) {
-        case GLESMultiDrawMode::Ext:
-            drawn = RunExt(mode, count, type, indices, drawcount, basevertex);
-            break;
-        case GLESMultiDrawMode::MultiIndirect:
-            drawn = RunIndirect(mode, count, type, indices, drawcount, basevertex, /*batched=*/true, feedDrawID,
-                                feedBaseVertex);
-            break;
-        case GLESMultiDrawMode::Indirect:
-            drawn = RunIndirect(mode, count, type, indices, drawcount, basevertex, /*batched=*/false, feedDrawID,
-                                feedBaseVertex);
-            break;
-        case GLESMultiDrawMode::BaseVertex:
-            drawn = RunBaseVertexLoop(mode, count, type, indices, drawcount, basevertex, feedDrawID, feedBaseVertex);
-            break;
-        case GLESMultiDrawMode::DrawElements:
-            drawn = RunRebasedDrawElements(mode, count, type, indices, drawcount, basevertex, feedDrawID,
-                                           feedBaseVertex);
-            break;
-        case GLESMultiDrawMode::Compute:
-            // Its pre-pass ran above; reaching here means it declined this batch's shape.
-            break;
-        case GLESMultiDrawMode::Auto:
-            break; // resolution never yields Auto
-        }
-
-        // Every tier above may decline a batch whose shape it cannot express. The two
-        // below are the floor: a base-vertex replay where the driver has one, and the
-        // rewritten index stream where it does not. Both are safe for any batch these
-        // entry points can receive.
-        if (!drawn) {
-            drawn = RunBaseVertexLoop(mode, count, type, indices, drawcount, basevertex, feedDrawID, feedBaseVertex);
-        }
-        if (!drawn) {
-            drawn = RunRebasedDrawElements(mode, count, type, indices, drawcount, basevertex, feedDrawID,
-                                           feedBaseVertex);
-        }
-        if (!drawn) {
-            MGLOG_E_ONCE("DirectGLES multi-draw: no usable tier for a %d sub-draw batch (mode 0x%x, type 0x%x); "
-                    "the batch was dropped",
-                    drawcount, mode, type);
-        }
-    }
-} // namespace MobileGL::MG_Backend::DirectGLES::MultiDrawImpl

MobileGL/MG_Backend/DirectGLES/MultiDraw.h

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

MobileGL/MG_Backend/DirectGLES/Utils.h

@@ -9,22 +9,20 @@
 #pragma once
 #include <Includes.h>
 #include <MG_State/GLState/Core.h>
-#include <MG_Util/BackendLoaders/OpenGL/Loader.h>
-#include <MG_Util/Texture/TextureFormatProcessor.h>
 
 namespace MobileGL::MG_Backend::DirectGLES {
     namespace DebugImpl {
         class ErrorLopper {
         public:
-            static void Loop(const std::function<void(GLenum)>&);
-            static void Clear();
+            void Loop(std::function<void(GLenum)>);
+            void Clear();
             ErrorLopper();
             ~ErrorLopper();
         };
 
         class OpenGLScopeMarker {
         public:
-            explicit OpenGLScopeMarker(const String& scopeName);
+            explicit OpenGLScopeMarker(String scopeName);
             ~OpenGLScopeMarker();
         };
     } // namespace DebugImpl
@@ -36,477 +34,16 @@ namespace MobileGL::MG_Backend::DirectGLES {
     } // namespace VertexArrayImpl
 
     namespace TextureImpl {
-        // Whether images on this format-capability target can back a colour attachment, and so
-        // need a colour-renderable storage format even when the frontend asked for a
-        // three-channel one ES never renders to. Shared by the capability probe (which passes the
-        // capabilities it has just queried, before the globals are published) and by the
-        // allocation path (which reads the active backend's), so the format the cache was probed
-        // with is always the format the image is created with.
-        Bool TargetRequiresRenderableFormat(SizeT targetIndex);
-        Flags<PixelFormatNormalizeOptionBit> GetRenderTargetNormalizeOptions(
-            const MG_External::GLESCapabilities& capabilities, SizeT targetIndex);
-
         void GenerateTextureFormatInfo(TextureInternalFormat internalFormat, GLenum* outInternalFormat,
-                                       GLenum* outFormat, GLenum* outType,
-                                       TextureTarget target = TextureTarget::Unknown);
-        void GenerateRenderbufferFormatInfo(TextureInternalFormat internalFormat, GLenum* outInternalFormat,
-                                            GLenum* outFormat, GLenum* outType);
-        Bool ShouldUseCaveatTextureFormat(TextureInternalFormat internalFormat, TextureTarget target);
-
-        // True when the format the image is actually created with has an alpha channel the
-        // frontend format does not (the three-channel colour-renderable widening). GL reads such
-        // a channel back as 1.0, so any swizzle source of ALPHA has to be answered with ONE and
-        // any readback of the image has to overwrite the alpha the draw happened to leave there.
-        Bool BackendTextureFormatAddsAlpha(TextureInternalFormat internalFormat, TextureTarget target);
-        Bool BackendRenderbufferFormatAddsAlpha(TextureInternalFormat internalFormat);
-        Bool ShouldUseCaveatRenderbufferFormat(TextureInternalFormat internalFormat);
-
-        // The CHANNEL WIDENING an image-bindable texture's ES storage takes, so that a format
-        // GLSL ES cannot spell as an image is carried by one it can.
-        //
-        // GL has forty image formats, GLSL ES core has thirteen, and no test device advertises
-        // GL_NV_image_formats - so a shader declaring one of the other twenty-six has no legal
-        // ESSL at all and glBindImageTexture rejects the narrow format outright for most of them
-        // (GL_INVALID_VALUE for nineteen of twenty-six on Adreno, twenty-five on both Malis).
-        // Seventeen have a core format of the SAME per-channel width and component type,
-        // differing only in channel count, and in one of those the emulation is EXACT: GL already
-        // defines an imageLoad from a narrower format as (r, 0, 0, 1) and an imageStore as
-        // dropping the components the format does not have, so the carrier's surplus channels
-        // hold values GL has already named. WidenImageFormatsPass pins them in the shader; this
-        // is the storage half, and DirectGLES::TextureImpl::SyncImageTextureBinding the bind
-        // half. All three ask WidenedCoreEsslImageFormat, so they cannot pick different carriers.
-        //
-        // Reports nothing (InternalFormat == GL_UNKNOWN_MGL) for a format that is core already,
-        // for the nine with no exact carrier (r11f_g11f_b10f, rgb10_a2, rgb10_a2ui, rgba16, rg16,
-        // r16, rgba16_snorm, rg16_snorm, r16_snorm - those keep the honest "no GLSL ES spelling"
-        // diagnostic rather than a silent approximation), and on a driver that HAS
-        // GL_NV_image_formats, where the shader keeps the declared format and no widening may
-        // happen behind it.
-        //
-        // The widened triple REPLACES what GenerateTextureFormatInfo chose, including any
-        // renderability substitution: an image that cannot be image-bound is useless whatever its
-        // attachment behaviour, so the image constraint wins. In practice that only bites
-        // RG8_SNORM/R8_SNORM on a driver without EXT_render_snorm, where the storage stays
-        // signed-normalized instead of becoming the half float that fallback would have picked -
-        // so an image-bound texture in one of those two formats is no longer attachable, and
-        // glGetTexImage on it falls through to the CPU shadow, which a shader-side imageStore
-        // does not update. Accepted deliberately: before the widening, an image binding in either
-        // format was refused outright by every driver tested and the stage that declared it never
-        // compiled at all, so nothing that works today is being given up.
-        //
-        // KNOWN GAP, for the same "all three layers move together" reason: a widened texture that
-        // is ALSO an FBO colour attachment gains one to three writable channels, and a draw into
-        // it can leave values in channels GL says are 0 and 1. Sampling and imageLoad are covered
-        // (the swizzle composition in SyncTextureParamsToBackend and the shader-side mask), but a
-        // glReadPixels/glGetTexImage that asks for more channels than the frontend format has
-        // would see them. Closing it needs the per-draw-buffer colour mask the three-channel
-        // widening already carries (FramebufferImpl::g_alphaWidenedDrawBufferMask) generalized
-        // from "alpha" to a channel count, which is its own change.
-        // How the FRONTEND's CPU shadow for a widened format is laid out relative to the carrier's
-        // transfer, i.e. what the upload has to do to it. Almost every entry is `Components`: the
-        // shadow already holds SourceChannels components of exactly the carrier's own type, so
-        // padding it out to four is the whole conversion. The packed entries do not - their shadow
-        // is ONE 32-bit word per texel - and reading such a word as components of the carrier's
-        // type takes twelve or sixteen bytes out of four and shears the level.
-        enum class ImageWidenSourceEncoding : Uint8 {
-            Components = 0,
-            // r11f_g11f_b10f: GL_UNSIGNED_INT_10F_11F_11F_REV -> four GL_FLOATs of an rgba16f.
-            PackedFloat11f11f10f,
-            // rgb10_a2 and rgb10_a2ui: GL_UNSIGNED_INT_2_10_10_10_REV -> four GL_UNSIGNED_SHORT
-            // channel CODES of an rgba16ui. The same split serves both: the two formats differ
-            // only in what the codes MEAN, which is the shader's business and not the transfer's.
-            PackedInt2101010Rev,
-        };
-
-        struct ImageBindableStorageWidening {
-            GLenum InternalFormat = GL_UNKNOWN_MGL;
-            GLenum Format = GL_UNKNOWN_MGL;
-            GLenum Type = GL_UNKNOWN_MGL;
-            // Channels the FRONTEND format has, i.e. how many of the carrier's four the client
-            // data fills. The rest are uploaded as 0, and the fourth as the format's implied 1.
-            Uint SourceChannels = 0;
-            // Whether that implied 1 is the integer one or a saturated normalized field - the
-            // transfer type cannot tell the two apart (GL_UNSIGNED_BYTE serves both RG8 and
-            // RG8UI), so the carrier decides.
-            Bool IntegerData = false;
-            // What the upload has to do to the frontend shadow before it describes the level to
-            // the driver (PrepareImageWidenedUpload).
-            ImageWidenSourceEncoding SourceEncoding = ImageWidenSourceEncoding::Components;
-            // Non-zero when the carrier holds this format's channels as the INTEGER CODES of a
-            // NORMALIZED value - the seven 16-bit and 10-bit normalized formats, which core ESSL
-            // has no image format of any width for and which a float carrier would requantise.
-            // Each entry is the largest code that channel can hold, i.e. the denominator of GL 4.6
-            // 2.3.5; SignedNormalized picks which of the two conversions it is the denominator of.
-            //
-            // Two things depend on it, both because the ES storage no longer shares the frontend
-            // format's component class: the upload pads a missing alpha with ChannelMax[3] instead
-            // of the transfer type's own "one" (through a uint carrier the saturated field IS the
-            // one), and glGetTexImage divides the codes back out into the floats the application
-            // is still owed.
-            Uint ChannelMax[4] = {0u, 0u, 0u, 0u};
-            Bool SignedNormalized = false;
-
-            Bool CarriesNormalizedCodes() const { return ChannelMax[0] != 0u; }
-            explicit operator Bool() const { return InternalFormat != GL_UNKNOWN_MGL; }
-        };
-        ImageBindableStorageWidening GetImageBindableStorageWidening(TextureInternalFormat internalFormat);
-
-        // The single-channel core format an image-bindable BUFFER texture's view is SPLIT into, or
-        // GL_UNKNOWN_MGL for a format that needs no split (or has no core base).
-        //
-        // A buffer texture cannot be widened: its texels are the application's buffer object, at
-        // the size and layout the application gave it, and it is usually also a vertex, index or
-        // storage buffer whose bytes are not ours to restride. But an rg32f view of N texels and
-        // an r32f view of 2N texels describe exactly the SAME bytes, so the split changes only
-        // how the shader subscripts them - component j of texel i is texel 2i + j of the base
-        // view - which WidenImageFormatsPass rewrites every access to do. The same rule as the
-        // widening decides WHETHER: a driver that can spell rg32f for an imageBuffer needs
-        // nothing.
-        //
-        // KNOWN GAP, and the reason this is not applied to a texture that is merely sampled: a
-        // buffer texture that is BOTH image-bound and read through a samplerBuffer would have its
-        // sampled view split too, and the sampler side is not rewritten. Accepted for the same
-        // reason the storage widening's gaps are - on a driver where the split applies at all
-        // there is no legal ESSL for the image declaration, so such a program did not compile.
-        GLenum GetImageBindableBufferSplitFormat(TextureInternalFormat internalFormat);
+                                       GLenum* outFormat, GLenum* outType);
     } // namespace TextureImpl
 
     namespace FramebufferImpl {} // namespace FramebufferImpl
 
-    // Pure CPU helpers of the client-format readback conversion (ReadPixels/GetTexImage repack a wide
-    // RGBA(_INTEGER) read into the caller's (format, type) layout). Kept context-free so unit tests can
-    // exercise the exact packing the GL CTS packed_pixels oracle compares against.
-    namespace ReadbackImpl {
-        struct ReadbackChannelMapping {
-            Int sourceChannel[4]; // RGBA source channel feeding each destination component
-            Int channelCount;     // destination component count
-            Bool isInteger;
-        };
-        Bool GetReadbackChannelMapping(GLenum format, ReadbackChannelMapping& outMapping);
-
-        // Byte size of one destination component of `type`; packed types report the packed word size.
-        // 0 = type not supported by the conversion path.
-        SizeT GetReadbackComponentSize(GLenum type);
-
-        // Bit-field layout of a GL packed pixel type. width/shift are indexed in the client format's
-        // component order (matching ReadbackChannelMapping); shift is the LSB position of the field in
-        // the packed word: non-REV types pack the first component from the MSB, *_REV types from the
-        // LSB (GL 3.3 table 3.6; field positions mirror the GL CTS glcPackedPixelsTests pack_* oracle).
-        struct PackedReadbackLayout {
-            Int fieldCount;     // format components stored in the packed word
-            Int width[4];       // bit width of each component's field
-            Int shift[4];       // LSB bit position of each component's field
-            SizeT byteSize;     // packed word size in bytes (1, 2 or 4)
-            Bool isFloatPacked; // 10F_11F_11F_REV / 5_9_9_9_REV: fields hold unsigned small floats
-        };
-        Bool GetPackedReadbackLayout(GLenum type, PackedReadbackLayout& out);
-
-        // Unsigned small-float encoders (EXT_packed_float / EXT_texture_shared_exponent semantics).
-        Uint32 EncodeFloatToUnsignedF11(Float value);
-        Uint32 EncodeFloatToUnsignedF10(Float value);
-        Uint32 EncodeSharedExponentRGB9E5(const Float rgb[3]);
-
-        // Destination bytes per pixel for a (format mapping, type) readback pair; 0 when the pair is
-        // not convertible (unknown type, packed field count != format component count, floating-point
-        // or packed-float type with an integer format).
-        SizeT GetReadbackDstPixelSize(const ReadbackChannelMapping& mapping, GLenum type);
-
-        // Repacks one row of wide RGBA(_INTEGER) texels (4 components of wideType each) into the
-        // client's (format, type) layout. src holds width * 4 * GetReadbackComponentSize(wideType)
-        // bytes, dst receives width * GetReadbackDstPixelSize(mapping, type) bytes.
-        void ConvertWideReadbackRow(const Uint8* src, Uint8* dst, SizeT width, GLenum wideType,
-                                    const ReadbackChannelMapping& mapping, GLenum type);
-
-        // Stores wide RGBA(_INTEGER) rows into the client pointer or the bound PACK pixel buffer,
-        // honoring the client-side PACK pixel-store parameters (row length, alignment, skips,
-        // swap-bytes, and - when applyPackImageParams - image height/skip images). Shared by the
-        // DirectGLES and DirectVulkan readback conversion paths.
-        Bool StoreWideRowsToClient(const Uint8* wide, GLenum wideType, GLsizei width, GLsizei sliceHeight,
-                                   GLsizei sliceCount, const ReadbackChannelMapping& mapping, GLenum type,
-                                   void* pixels, Bool applyPackImageParams);
-
-        // Stores packed 32-bit source words verbatim, with the same destination addressing, PACK
-        // parameters and pixel-pack-buffer handling as StoreWideRowsToClient. For the sources whose
-        // storage word already IS the client word (MG_Util::IsRawPackedPixelTransfer): routing those
-        // through the wide float intermediate re-encodes them, and the RGB9_E5 encoder canonicalizes
-        // the shared exponent, so glGetTexImage would answer with different bits than were stored.
-        // `srcWords` holds sliceHeight * sliceCount tightly stacked rows of `width` 32-bit words.
-        // False when `type` is not a 4-byte packed type.
-        Bool StorePackedWordsToClient(const Uint8* srcWords, GLsizei width, GLsizei sliceHeight, GLsizei sliceCount,
-                                      GLenum type, void* pixels, Bool applyPackImageParams);
-    } // namespace ReadbackImpl
-
     namespace PrgramImpl {
         String ProcessOutColorLocations(const String& glslCode);
         String ForceSupporterOutput(const String& glslCode);
-        String ClampNormFallbackOutputs(String glslCode, GLenum shaderType, Uint32 snormOutputMask,
-                                        Uint32 unormOutputMask);
-        String ForceFlatIntegerVaryings(const String& glslCode, GLenum shaderType);
-        // Legacy GLSL's gl_FragColor is broadcast to every enabled draw buffer (GL 4.6
-        // 15.2.3), but ShaderSourceProcessor lowers it to the single output mg_FragColor,
-        // which only ever reaches draw buffer 0. Replicates it across `drawBufferCount`
-        // outputs and copies the value into them at the end of main. A no-op for
-        // drawBufferCount <= 1, i.e. for everything but a framebuffer that actually
-        // enables several draw buffers, so the ordinary single-target shader is untouched.
-        String BroadcastLegacyFragColor(String glslCode, GLenum shaderType, Uint drawBufferCount);
-        // SPIRV-Cross emits `#extension GL_EXT_texture_buffer : require` for every buffer-texture
-        // sampler when it targets ESSL below 320, and offers no way to ask for the OES spelling.
-        // On a driver that advertises only GL_OES_texture_buffer that directive is a compile
-        // error, so the name is retargeted in the emitted source. A no-op on every other tier:
-        // ES 3.2 needs no directive at all and an EXT driver already has the right one.
-        String RetargetTextureBufferExtension(String glslCode,
-                                              MG_External::GLESCapabilities::TextureBufferTier tier);
-        // Adds `#extension GL_NV_image_formats : require` when the shader carries an image
-        // format qualifier GLSL ES has no core spelling for. SPIRV-Cross prints the format and
-        // asks for nothing, so the request has to be made here. `needed` is the caller's answer,
-        // because only it knows which formats are in play AND whether the driver advertises the
-        // extension - requesting an unadvertised extension is itself a compile error, so this is
-        // never emitted speculatively. A no-op when not needed or already present.
-        String RequestExtendedImageFormats(String glslCode, Bool needed);
-        // Adds `#extension GL_OES_viewport_array : require` when the emitted ESSL names
-        // gl_ViewportIndex. SPIRV-Cross prints that identifier and asks for nothing (unlike
-        // gl_Layer, which it backs with GL_NV_viewport_array2 on ES) and ESSL has no core
-        // spelling for it at any version, so the request has to be made here or the stage does
-        // not compile - which loses the whole program, not just the multi-viewport routing.
-        // `needed` is the caller's answer for the same reason as above: only it knows whether the
-        // driver advertises the extension, and requesting an unadvertised one is itself a compile
-        // error, so this is never emitted speculatively. A no-op when not needed or already
-        // present.
-        String RequestViewportArrayExtension(String glslCode, Bool needed);
-        // Writes a format layout qualifier into the image declarations named in
-        // `esslFormatByUniformName` that still have none. The completion half of the image-format
-        // bake, and ONLY that: the SPIR-V pass (BakeImageFormatsPass) is what normally puts the
-        // format in, but SPIRV-Cross throws rather than printing the formats it calls
-        // desktop-only when it targets ESSL - r8ui among them, which is what the stencil half of
-        // KHR-GL4x.packed_depth_stencil.stencil_texturing binds - and a throw loses the whole
-        // stage. So those formats stay out of the module and are spelled here instead, on the
-        // emitted text, where nothing can refuse them.
-        //
-        // Declarations that already carry a format are left exactly as they are, whoever wrote
-        // it. Must run before RemoveLayoutBinding, which is where an image's layout qualifier
-        // stops being safe to edit by hand.
-        String BakeImageFormatQualifiers(String glslCode, const UnorderedMap<String, String>& esslFormatByUniformName);
         String RemoveLayoutBinding(const String& glslCode);
-        // Prefix of the per-element scalar declarations RemapImageArrayElementUnits splits an
-        // image array into; the suffix is the array's own name and the element's index.
-        constexpr const char* IMAGE_ARRAY_ELEMENT_PREFIX = "mg_imageElem_";
-        // One image ARRAY whose elements the application pointed at units that are not
-        // consecutive-from-element-zero.
-        struct ImageArrayUnitPlan {
-            String name;       // the array's name, exactly as the emitted ESSL declares it
-            Vector<Int> units; // the frontend image unit element k has to reach
-        };
-        // Desktop GL lets an application give each element of an image array an ARBITRARY unit
-        // (glUniform1i per element). ES has no such call at all - "ES image units come
-        // exclusively from the layout(binding=N) qualifier" - and one declaration carries one
-        // binding, so ESSL nails an array's elements to the CONSECUTIVE units N, N+1, N+2, ...
-        // MobileGL used to stamp element [0]'s unit as the binding and let the rest fall where
-        // they fell: KHR-GL4x.shader_image_load_store.advanced-sso-simple assigns 0,2,4,6 and
-        // 1,3,5,7, so its two programs actually addressed 0,1,2,3 and 1,2,3,4 - one layer got the
-        // wrong value and three were never written, with no GL error and no link log. The same
-        // defect for SAMPLER arrays was fixed API-side (SubscriptUniformNameForElement); an image
-        // array has no API side to fix, because ES makes glUniform1i on an image uniform an
-        // INVALID_OPERATION.
-        //
-        // Repaired by SPLITTING the array into one SCALAR image uniform per element, each with
-        // its own layout(binding = N), and rewriting `name[k]` to the scalar declared for
-        // element k. One declaration carries one binding, so one declaration per unit is the
-        // only spelling that reaches an arbitrary set of them.
-        //
-        // That rewrite needs every k in the emitted text to be a LITERAL, and it is:
-        // LegalizeResourceArrayIndexingForEssl has already folded or lowered every dynamic
-        // image-array subscript in the module, because ESSL forbids one outright ("image arrays
-        // indexed with non-constant expressions are forbidden in GLSL ES", Mesa 26.1.4 at
-        // ES 3.2, on a raw GLES probe with no MobileGL in the loop). The earlier shape here -
-        // widening the array to cover the whole span of units and routing each subscript through
-        // a `const highp int` offset table - was written before that pass covered images, and
-        // the table lookup was itself one of the non-constant expressions the same probe refuses.
-        // The split also costs exactly the image uniforms the application declared, where the
-        // widening cost the whole SPAN (seven for the four elements of
-        // KHR-GL42.shader_image_load_store.advanced-sso-simple), so there is no budget for it to
-        // fail to fit in.
-        //
-        // Declines - leaving the array exactly as it was, and naming it in `outDeclined` for the
-        // caller to report - when the emitted extent disagrees with the reflection, when the
-        // array is reached by anything other than a subscript, or when a subscript is not a
-        // literal element index. Silence was the whole defect here, so a decline must be audible.
-        //
-        // Must run AFTER RebindImageUniformsToFrontendUnits and BakeImageFormatQualifiers (both
-        // key on the GL uniform name and on a binding already being stamped) and BEFORE
-        // SplitReadWriteImageUniforms (so each element that is both read and written is split
-        // with its own binding already on it) and RemoveLayoutBinding (which is what preserves
-        // image bindings). Like them, it is downstream of the L2 shader-translation memo, so the
-        // per-program units it reads need no entry in BuildEsslTranslationKey.
-        String RemapImageArrayElementUnits(const String& glslCode, const Vector<ImageArrayUnitPlan>& plans,
-                                           Vector<String>* outDeclined = nullptr);
-        // The member list of a `gl_PerVertex { ... }` redeclaration in already-emitted ESSL -
-        // the text between the braces, verbatim - or nullopt when the shader does not redeclare
-        // the block in that direction. `input` selects the `in gl_PerVertex` form over the
-        // `out` one.
-        //
-        // Exists so BuildPassthroughTessControlEssl can MIRROR the stages it has to sit between
-        // rather than guess at them. Whether SPIRV-Cross redeclares the built-in block, and with
-        // which members, depends on what the application's shader touched; a synthesized stage
-        // that redeclares a different shape than its neighbours is an ES link error against a
-        // program that has no other problem.
-        std::optional<String> ExtractPerVertexBlockMembers(const String& essl, Bool input);
-        // The pass-through tessellation control stage GL 4.6 core 11.2.2 describes: "the input
-        // patch is passed through unmodified", the output patch has PATCH_VERTICES vertices, and
-        // the levels come from the PATCH_DEFAULT_OUTER_LEVEL / PATCH_DEFAULT_INNER_LEVEL state.
-        //
-        // Desktop GL makes the control stage OPTIONAL. OpenGL ES 3.2 does not: it has no
-        // PATCH_DEFAULT_*_LEVEL state at all (only glPatchParameteri, for PATCH_VERTICES) and
-        // rejects a program that has an evaluation stage without a control stage - with an EMPTY
-        // info log, verified on an Adreno 830 with no MobileGL in the process. MobileGL's own
-        // frontend link succeeds, so the program reports GL_LINK_STATUS = TRUE, program 0 is
-        // bound in its place, and every draw silently renders nothing.
-        //
-        // `inPerVertexMembers` / `outPerVertexMembers` are the member lists to redeclare gl_in
-        // and gl_out with - normally taken from the neighbouring stages' own emitted ESSL via
-        // ExtractPerVertexBlockMembers, and empty to leave the driver's built-in declaration
-        // alone, which is what matching a neighbour that did not redeclare requires.
-        //
-        // All four outer levels and both inner levels are written unconditionally: writing a
-        // level the evaluation stage's domain does not use is legal and ignored, and it saves
-        // this from having to know the domain. They are literal 1.0 because that is the GL
-        // default and glPatchParameterfv - their only setter - is a stub in this frontend
-        // (MG_Impl/GLImpl/Exporting/Definitions.cpp). Implementing that entry point means making
-        // the levels a parameter here AND part of what makes a built program stale, exactly as
-        // PATCH_VERTICES already is; the two must move together, so they are named together.
-        //
-        // The same stage, for the same reason, that DirectVulkan synthesizes in
-        // ProgramFactory::BuildPassthroughTessControlSource - Vulkan likewise requires both
-        // tessellation stages. Kept as two generators rather than one because the two targets
-        // disagree on everything but the algorithm: desktop GLSL 450 against ESSL, a fixed
-        // gl_PerVertex shape that Vulkan matches structurally against a mirrored one, and a
-        // VkShaderModule against a driver shader object.
-        String BuildPassthroughTessControlEssl(Uint esslVersion, Uint patchVertices,
-                                               const String& inPerVertexMembers,
-                                               const String& outPerVertexMembers);
-        // Prefix of the writeonly half a read+write image uniform is split into (see
-        // SplitReadWriteImageUniforms); the suffix is the image's own (already access-tagged) name.
-        constexpr const char* IMAGE_WRITE_ALIAS_PREFIX = "mg_imageWrite_";
-        // The three names SplitReadWriteImageUniforms renames a rewritten image declaration
-        // under, one per REPAIR it can apply. Which one a stage picks is decided by that stage's
-        // own accesses, so two stages that use an image the same way arrive at the SAME name and
-        // two that use it differently arrive at different ones - which is exactly the property
-        // the rename exists for, at no cost to the stages that agree. Exposed for the tests.
-        constexpr const char* IMAGE_READONLY_ALIAS_PREFIX = "mg_imageRo_";
-        constexpr const char* IMAGE_WRITEONLY_ALIAS_PREFIX = "mg_imageWo_";
-        constexpr const char* IMAGE_SPLIT_READ_ALIAS_PREFIX = "mg_imageRw_";
-        // ESSL refuses an image variable that carries a format qualifier other than r32f /
-        // r32i / r32ui unless it also carries `readonly` or `writeonly` (GLSL ES 3.10 4.9 /
-        // 3.20 4.10; glslang enforces it verbatim in ParseHelper.cpp's layoutObjectCheck).
-        // SPIRV-Cross emits NEITHER for an image the shader both reads and writes: it
-        // speculatively decorates every storage image NonWritable+NonReadable
-        // (fixup_image_load_store_access), then OpImageRead clears NonReadable and
-        // OpImageWrite clears NonWritable, and to_qualifiers_glsl only prints `readonly`
-        // from NonWritable and `writeonly` from NonReadable. Desktop GLSL is happy with the
-        // bare declaration, so the frontend raises no error and the illegal ESSL only shows
-        // up as a device compile failure - and then as a silently no-op draw.
-        //
-        // Restores a legal declaration, and RENAMES it after the repair it applied while doing so:
-        //  * loaded only            -> add `readonly`, rename under IMAGE_READONLY_ALIAS_PREFIX
-        //  * stored only            -> add `writeonly`, rename under IMAGE_WRITEONLY_ALIAS_PREFIX
-        //  * both                   -> emit TWO declarations on the same binding and of the
-        //                              same type, `coherent readonly
-        //                              <IMAGE_SPLIT_READ_ALIAS_PREFIX><name>` and `coherent
-        //                              writeonly <IMAGE_WRITE_ALIAS_PREFIX><that name>`, point
-        //                              every imageStore at the second one, and follow each of
-        //                              those stores with `memoryBarrierImage();`. Several image
-        //                              variables may share an image unit as long as they have
-        //                              the same type and format, which is exactly what the pair
-        //                              is.
-        //
-        // The rename is the other half of the repair and applies to all three cases. The qualifier
-        // chosen above is a decision about ONE STAGE's accesses, and GLSL requires a uniform
-        // declared in two stages to be declared identically - so a shader that stores an image from
-        // the vertex stage and loads it from the fragment stage came out of here `writeonly` in one
-        // and `readonly` in the other. Adreno merges the two same-named declarations and silently
-        // drops the vertex-stage STORES: no GL error, no link log, LINK_STATUS = 1, and the image
-        // still reads back its initial contents
-        // (KHR-GL4x.shader_image_load_store.advanced-memory-dependentInvocation; a raw-ES probe
-        // isolated the trigger to the same-name/mismatched-qualifier pair, and only when both
-        // carry `coherent`). Renaming leaves no cross-stage variable to merge.
-        //
-        // The name is keyed on the REPAIR, not on the stage, and that distinction is the whole
-        // point: two stages that use an image the same way emit byte-identical declarations, so
-        // letting them keep one shared name costs nothing and merging them is correct, while two
-        // stages that use it differently land on different prefixes and cannot be merged at all.
-        // A per-STAGE tag also satisfied the first requirement but violated the second: it made
-        // the SAME image a distinct uniform in every stage that named it, and Adreno allocates
-        // image LOCATIONS per distinct uniform. KHR-GL43.shading_language_420pack.
-        // binding_images_texture_type_* declares three read+write images in each of its five
-        // stages; merged that is 6 image uniforms, per-stage-tagged it is 30, and the Adreno 830
-        // linker answered "Error: Image Image location or component exceeds max allowed. Error:
-        // Linking failed." - which, the frontend having already published LINK_STATUS = TRUE from
-        // glslang's link, surfaced only as every draw silently doing nothing and the images
-        // reading back zero. Mali and Mesa link the same text, so nothing but a device gate
-        // catches this.
-        //
-        // A declaration SPIRV-Cross already tagged `readonly` or `writeonly` needs no qualifier
-        // repair, but it is NOT stage-independent: that tag is derived from the accesses of the
-        // stage being emitted, so an image stored in the vertex stage and loaded in the fragment
-        // stage arrives here as `coherent writeonly g_image` and `coherent readonly g_image` -
-        // one name, two spellings, which is exactly the pair Adreno merges. Those declarations
-        // are therefore renamed too, keyed on the qualifier they already carry (readonly ->
-        // IMAGE_READONLY_ALIAS_PREFIX, writeonly -> IMAGE_WRITEONLY_ALIAS_PREFIX) and with
-        // nothing but the identifier changed. Stages that agree still reach the same alias and
-        // stay merged, so this costs no shader an extra image uniform.
-        //
-        // The declarations this pass still leaves untouched keep their names: one carrying BOTH
-        // readonly and writeonly (a spelling no access analysis produces, so it came from the
-        // application and is identical everywhere), and one carrying NEITHER, which is legal only
-        // for the r32f/r32i/r32ui formats and is likewise spelled the same in every stage.
-        //
-        // The `coherent` on both halves of the pair is load-bearing, not decoration: GLSL only
-        // guarantees a write through one image variable is visible to a read through a DIFFERENT
-        // one when both are coherent, and the split is what makes a same-variable
-        // read-after-write cross-variable. The single-declaration repairs above do not get it -
-        // nothing aliases them.
-        //
-        // The barrier is the other half of the same problem, and coherent alone did not cover it:
-        // visibility is not ORDER. Within one invocation the ES compiler sees a write to one
-        // variable and a read of another it has no reason to believe alias, and is free to serve
-        // the read from before the write - which is what advanced-memory-order's store/load/
-        // compare loop measured on Adreno. memoryBarrierImage() orders exactly those two, is core
-        // GLSL ES 3.10 in every stage, and is not an execution barrier, so it is legal in
-        // non-uniform control flow. It costs something in a shader that stores to a read+write
-        // image in a loop, which is why it is confined to the split pair.
-        //
-        // Budget note: the split DOUBLES the image-uniform count of the stage it fires in, so
-        // a driver advertising a tight GL_MAX_{FRAGMENT,VERTEX,...}_IMAGE_UNIFORMS can turn a
-        // shader that used to compile into a link failure. ES only guarantees 4 fragment image
-        // uniforms, so a shader with more than half the limit in read+write images is the case
-        // to watch.
-        //
-        // Runs on the transpiled ESSL, so it must see the bindings the frontend units were
-        // already rewritten to and must run before those bindings are stripped - see the call
-        // site in Managers.cpp. Its output is a function of the emitted text alone - it needs no
-        // stage and no per-program state - so it adds nothing to BuildEsslTranslationKey either.
-        //
-        // `outSplitCount`, when given, receives the number of declarations that were actually
-        // doubled - i.e. exactly how many image uniforms this stage gained over what the
-        // application declared. Zero for every shader but a handful, and the only number the
-        // budget note above can be reported with.
-        String SplitReadWriteImageUniforms(const String& glslCode, Uint* outSplitCount = nullptr);
-        // Prefix of the per-sampler float uniform that carries GL_TEXTURE_LOD_BIAS into
-        // the shader (see EmulateTextureLodBias); the suffix is the sampler's own name.
-        constexpr const char* LOD_BIAS_UNIFORM_PREFIX = "mg_lodBias_";
-        // ES has no per-texture/sampler LOD bias at all (GL_TEXTURE_LOD_BIAS is desktop
-        // only; Vulkan spells it VkSamplerCreateInfo::mipLodBias), so it has to reach the
-        // shader as a uniform and be folded into every lookup's level of detail. Declares
-        // one `uniform highp float mg_lodBias_<sampler>;` per mip-capable sampler and adds
-        // it to the bias / explicit-LOD argument of every lookup that takes one. Draws push
-        // the bound texture's (or sampler object's) value into it; a shader whose samplers
-        // all have a zero bias is therefore unaffected. Returns the source unchanged when
-        // there is nothing to rewrite.
-        //
-        // avoidExplicitLodBias leaves lookups that already carry an explicit LOD untouched,
-        // so their constant level stays constant; only the implicit-LOD forms take the bias.
-        // Off by default and only ever set on ANGLE + llvmpipe, where injecting the uniform
-        // into a constant LOD crashes the driver (MOBILEGL_AVOID_EXPLICIT_LOD_BIAS).
-        String EmulateTextureLodBias(const String& glslCode, Bool avoidExplicitLodBias = false);
     } // namespace PrgramImpl
 
     namespace Utils {

MobileGL/MG_Backend/DirectVulkan/BackendObject_DirectVulkan.h

@@ -1,85 +0,0 @@
-// MobileGL - MobileGL/MG_Backend/DirectVulkan/BackendObject_DirectVulkan.h
-// Copyright (c) 2025-2026 MobileGL-Dev
-// Licensed under the GNU Lesser General Public License v3.0:
-//   https://www.gnu.org/licenses/gpl-3.0.txt
-//   https://www.gnu.org/licenses/lgpl-3.0.txt
-// SPDX-License-Identifier: LGPL-3.0-only
-// End of Source File Header
-
-#pragma once
-#include <Includes.h>
-#include "../BackendObject.h"
-#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();
-        ~BackendObject_DirectVulkan() override;
-
-        void Initialize() override;
-        Bool InitWindowSurface() override;
-        Bool InitCapabilities() override;
-        Bool InitializeEGLDisplay(EGLDisplay dpy, EGLint* major, EGLint* minor) 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;
-        String GetBackendAPIVersionString() const override;
-        const GlobalBackendFunctionsTable& GetBackendFunctions() const override;
-        const DynamicBackendParameters& GetDynamicParameters() const override;
-        BackendType GetBackendType() const override;
-        void ApplyVulkanCapabilitiesForTesting(const MG_External::VulkanCapabilities& capabilities);
-
-    private:
-        Bool InitPbufferSurface(EGLint width, EGLint height) override;
-        void OnEGLSurfaceReleased(EGLSurface surface) override;
-        void UpdateAdvertisedExtensions();
-        void UpdateDynamicBackendParameters();
-
-        Bool m_initialized = false;
-        DynamicBackendParameters m_dynamicParameters;
-        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 runtime-gated
-    // capabilities). 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,
-                                                  Bool nonZeroIndirectBaseInstanceSupported);
-
-    // 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

@@ -1,140 +0,0 @@
-// MobileGL - MobileGL/MG_Backend/DirectVulkan/DirectVulkan.h
-// Copyright (c) 2025-2026 MobileGL-Dev
-// Licensed under the GNU Lesser General Public License v3.0:
-//   https://www.gnu.org/licenses/gpl-3.0.txt
-//   https://www.gnu.org/licenses/lgpl-3.0.txt
-// SPDX-License-Identifier: LGPL-3.0-only
-// End of Source File Header
-
-#pragma once
-#include <Includes.h>
-#include <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();
-
-    // Drops every cached program-resource reflection entry (CPU-side strings/vectors
-    // only, no Vulkan handles). Called at EGL teardown next to the renderer reset;
-    // safe because GL calls are serialized in this codebase, and any still-live
-    // program rebuilds its entry from the retained generated SPIR-V on demand.
-    void ClearProgramResourceCaches();
-
-    void ClearBufferfi(GLenum buffer, GLint drawbuffer, GLfloat depth, GLint stencil);
-    void ClearBufferfv(GLenum buffer, GLint drawbuffer, const GLfloat* value);
-    void ClearBufferuiv(GLenum buffer, GLint drawbuffer, const GLuint* value);
-    void ClearBufferiv(GLenum buffer, GLint drawbuffer, const GLint* value);
-    void ClearNamedFramebufferfv(const SharedPtr<MG_State::GLState::FramebufferObject>& framebuffer, GLenum buffer,
-                                 GLint drawbuffer, const GLfloat* value);
-    void ClearNamedFramebufferiv(const SharedPtr<MG_State::GLState::FramebufferObject>& framebuffer, GLenum buffer,
-                                 GLint drawbuffer, const GLint* value);
-    void ClearNamedFramebufferuiv(const SharedPtr<MG_State::GLState::FramebufferObject>& framebuffer, GLenum buffer,
-                                  GLint drawbuffer, const GLuint* value);
-    void ClearNamedFramebufferfi(const SharedPtr<MG_State::GLState::FramebufferObject>& framebuffer, GLenum buffer,
-                                 GLint drawbuffer, GLfloat depth, GLint stencil);
-    void Clear(GLbitfield mask);
-    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,
-                                     GLsizei drawcount, const GLint* basevertex);
-    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 MultiDrawArraysIndirectCount(GLenum mode, const void* indirect, GLintptr drawcount,
-                                      GLsizei maxdrawcount, GLsizei stride);
-    void DrawRangeElementsBaseVertex(GLenum mode, GLuint start, GLuint end, GLsizei count, GLenum type,
-                                     const void* indices, GLint basevertex);
-    void DrawRangeElements(GLenum mode, GLuint start, GLuint end, GLsizei count, GLenum type, const void* indices);
-    void DrawElementsInstancedBaseVertexBaseInstance(GLenum mode, GLsizei count, GLenum type, const void* indices,
-                                                     GLsizei instancecount, GLint basevertex, GLuint baseinstance);
-    void DrawElementsInstancedBaseVertex(GLenum mode, GLsizei count, GLenum type, const void* indices,
-                                         GLsizei instancecount, GLint basevertex);
-    void DrawElementsInstancedBaseInstance(GLenum mode, GLsizei count, GLenum type, const void* indices,
-                                           GLsizei instancecount, GLuint baseinstance);
-    void DrawElementsInstanced(GLenum mode, GLsizei count, GLenum type, const void* indices, GLsizei instancecount);
-    void DrawElementsIndirect(GLenum mode, GLenum type, const void* indirect);
-    void DrawArraysInstancedBaseInstance(GLenum mode, GLint first, GLsizei count, GLsizei instancecount,
-                                         GLuint baseinstance);
-    void DrawArraysInstanced(GLenum mode, GLint first, GLsizei count, GLsizei instancecount);
-    void DrawArraysIndirect(GLenum mode, const void* indirect);
-    void BlitFramebuffer(GLint srcX0, GLint srcY0, GLint srcX1, GLint srcY1, GLint dstX0, GLint dstY0, GLint dstX1,
-                         GLint dstY1, GLbitfield mask, GLenum filter);
-    void BlitNamedFramebuffer(const SharedPtr<MG_State::GLState::FramebufferObject>& readFramebuffer,
-                              const SharedPtr<MG_State::GLState::FramebufferObject>& drawFramebuffer,
-                              GLint srcX0, GLint srcY0, GLint srcX1, GLint srcY1,
-                              GLint dstX0, GLint dstY0, GLint dstX1, GLint dstY1,
-                              GLbitfield mask, GLenum filter);
-    void CopyTexImage2D(GLenum target, GLint level, GLenum internalformat, GLint x, GLint y, GLsizei width,
-                        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 CopyImageEndpoint& src,
-                          GLenum srcTarget, GLint srcLevel, GLint srcX, GLint srcY, GLint srcZ,
-                          const CopyImageEndpoint& dst,
-                          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);
-    void MemoryBarrier(GLbitfield barriers);
-    void MemoryBarrierByRegion(GLbitfield barriers);
-    void BindImageTexture(GLuint unit, GLuint texture, GLint level, GLboolean layered, GLint layer, GLenum access,
-                          GLenum format);
-    void GetIntegeri_v(GLenum target, GLuint index, GLint* data);
-    void GetInteger64i_v(GLenum target, GLuint index, GLint64* data);
-    void GetProgramiv(GLuint program, GLenum pname, GLint* params);
-    void ShaderStorageBlockBinding(GLuint program, const GLchar* storageBlockName, GLuint storageBlockBinding);
-    void ReadPixels(GLint x, GLint y, GLsizei width, GLsizei height, GLenum format, GLenum type, void* pixels);
-    void GetTexImage(GLenum target, GLint level, GLenum format, GLenum type, GLvoid* pixels);
-    void GetTextureImage(const SharedPtr<MG_State::GLState::ITextureObject>& texture, TextureUploadTarget uploadTarget,
-                         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();
-    BackendQueryHandle BeginXfbPrimitivesQuery(Bool generated);
-    void EndXfbPrimitivesQuery(BackendQueryHandle query);
-    BackendQueryHandle BeginOcclusionQuery();
-    void EndOcclusionQuery(BackendQueryHandle query);
-    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/DirectVulkanResourceState.h

@@ -1,20 +0,0 @@
-// MobileGL - MobileGL/MG_Backend/DirectVulkan/DirectVulkanResourceState.h
-// Copyright (c) 2025-2026 MobileGL-Dev
-// Licensed under the GNU Lesser General Public License v3.0:
-//   https://www.gnu.org/licenses/gpl-3.0.txt
-//   https://www.gnu.org/licenses/lgpl-3.0.txt
-// SPDX-License-Identifier: LGPL-3.0-only
-// End of Source File Header
-
-#pragma once
-
-#include <Includes.h>
-
-namespace MobileGL::MG_State::GLState {
-    class ProgramObject;
-}
-
-namespace MobileGL::MG_Backend::DirectVulkan {
-    GLuint GetShaderStorageBlockIndex(const MG_State::GLState::ProgramObject& program, const String& name);
-    GLuint GetShaderStorageBlockBinding(const MG_State::GLState::ProgramObject& program, GLuint blockIndex);
-}

MobileGL/MG_Backend/DirectVulkan/Renderer/BufferArena.cpp

@@ -1,143 +0,0 @@
-// MobileGL - MobileGL/MG_Backend/DirectVulkan/Renderer/BufferArena.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 "BufferArena.h"
-
-namespace MobileGL::MG_Backend::DirectVulkan {
-    Bool BufferArena::Initialize(const BufferArenaDesc& desc) {
-        Shutdown();
-
-        MOBILEGL_ASSERT(desc.allocator != nullptr, "BufferArena::Initialize requires valid allocator");
-        MOBILEGL_ASSERT(desc.frameCount > 0, "BufferArena::Initialize requires non-zero frame count");
-        MOBILEGL_ASSERT(desc.usage != 0, "BufferArena::Initialize requires non-zero buffer usage");
-
-        m_desc = desc;
-        m_frames.clear();
-        m_frames.resize(desc.frameCount);
-        m_deferredReleases.resize(desc.frameCount);
-        return true;
-    }
-
-    void BufferArena::Shutdown() {
-        for (auto& frame : m_frames) {
-            frame.buffer.Destroy();
-            frame.writeCursor = 0;
-        }
-        m_frames.clear();
-        m_deferredReleases.clear();
-        m_desc = {};
-    }
-
-    void BufferArena::BeginFrame(Uint32 frameIndex) {
-        CollectDeferredReleases(frameIndex);
-        ResetFrame(frameIndex);
-    }
-
-    void BufferArena::ResetFrame(Uint32 frameIndex) {
-        AssertValidFrameIndex(frameIndex);
-        m_frames[frameIndex].writeCursor = 0;
-    }
-
-    void BufferArena::CollectDeferredReleases(Uint32 frameIndex) {
-        AssertValidFrameIndex(frameIndex);
-        m_deferredReleases[frameIndex].clear();
-    }
-
-    Bool BufferArena::Allocate(Uint32 frameIndex, VkDeviceSize size, VkDeviceSize alignment, BufferSlice& outSlice) {
-        AssertValidFrameIndex(frameIndex);
-        MOBILEGL_ASSERT(size > 0, "BufferArena::Allocate requires non-zero size");
-
-        auto& frame = m_frames[frameIndex];
-        const VkDeviceSize resolvedAlignment = alignment > 0 ? alignment : 1;
-        const VkDeviceSize offset = (frame.writeCursor + resolvedAlignment - 1) & ~(resolvedAlignment - 1);
-        const VkDeviceSize endOffset = offset + size;
-
-        if (!EnsureCapacity(frameIndex, endOffset)) {
-            return false;
-        }
-
-        frame.writeCursor = endOffset;
-        outSlice = frame.buffer.GetSlice(offset, size);
-        return outSlice.IsValid();
-    }
-
-    Bool BufferArena::Upload(Uint32 frameIndex, const void* data, VkDeviceSize size, VkDeviceSize alignment,
-                             BufferSlice& outSlice) {
-        MOBILEGL_ASSERT(data != nullptr || size == 0, "BufferArena::Upload data pointer is null");
-        if (!Allocate(frameIndex, size, alignment, outSlice)) {
-            return false;
-        }
-
-        if (outSlice.mapped != nullptr) {
-            Memcpy(outSlice.mapped, data, static_cast<SizeT>(size));
-            return true;
-        }
-
-        return m_frames[frameIndex].buffer.Upload(data, size, outSlice.offset);
-    }
-
-    VkDeviceSize BufferArena::GetWriteCursor(Uint32 frameIndex) const {
-        AssertValidFrameIndex(frameIndex);
-        return m_frames[frameIndex].writeCursor;
-    }
-
-    Uint32 BufferArena::GetFrameCount() const {
-        return static_cast<Uint32>(m_frames.size());
-    }
-
-    Bool BufferArena::EnsureCapacity(Uint32 frameIndex, VkDeviceSize requiredEndOffset) {
-        AssertValidFrameIndex(frameIndex);
-        auto& frame = m_frames[frameIndex];
-        auto& buffer = frame.buffer;
-
-        if (buffer.IsValid() && buffer.GetSize() >= requiredEndOffset) {
-            return true;
-        }
-
-        VkDeviceSize newCapacity = buffer.IsValid() ? buffer.GetSize() : 0;
-        if (newCapacity < m_desc.minBufferSize) {
-            newCapacity = m_desc.minBufferSize;
-        }
-        if (newCapacity == 0) {
-            newCapacity = requiredEndOffset;
-        }
-        while (newCapacity < requiredEndOffset) {
-            newCapacity *= 2;
-        }
-
-        if (buffer.IsValid()) {
-            // Outgrown, not dead: every BufferSlice handed out from this frame's arena so far
-            // still names it, and those slices stay in service until the frame slot is rewound
-            // (VkBufferResource::transientSlice, the converted-vertex-stream cache, the draw
-            // memos). The release therefore has to survive every mid-frame reclaim and land on
-            // the next ResetFrame of this slot - see VkBufferManager::CollectAllDeferredReleases.
-            m_deferredReleases[frameIndex].push_back(std::move(buffer));
-        }
-
-        VkBufferObjectDesc bufferDesc{};
-        bufferDesc.allocator = m_desc.allocator;
-        bufferDesc.size = newCapacity;
-        bufferDesc.usage = m_desc.usage;
-        bufferDesc.memoryUsage = m_desc.memoryUsage;
-        bufferDesc.allocationFlags = m_desc.allocationFlags;
-        if (!buffer.Create(bufferDesc)) {
-            return false;
-        }
-        if (m_desc.persistentlyMapped && buffer.Map() == nullptr) {
-            buffer.Destroy();
-            return false;
-        }
-
-        frame.writeCursor = 0;
-        return true;
-    }
-
-    void BufferArena::AssertValidFrameIndex(Uint32 frameIndex) const {
-        MOBILEGL_ASSERT(frameIndex < m_frames.size(), "BufferArena frame index out of range");
-    }
-} // namespace MobileGL::MG_Backend::DirectVulkan

MobileGL/MG_Backend/DirectVulkan/Renderer/BufferArena.h

@@ -1,56 +0,0 @@
-// MobileGL - MobileGL/MG_Backend/DirectVulkan/Renderer/BufferArena.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 "BufferSlice.h"
-#include "VkBufferObject.h"
-#include "../VkIncludes.h"
-#include <Includes.h>
-#include <vk_mem_alloc.h>
-
-namespace MobileGL::MG_Backend::DirectVulkan {
-    struct BufferArenaDesc {
-        VmaAllocator allocator = nullptr;
-        Uint32 frameCount = 0;
-        VkBufferUsageFlags usage = 0;
-        VmaMemoryUsage memoryUsage = VMA_MEMORY_USAGE_AUTO;
-        VmaAllocationCreateFlags allocationFlags = 0;
-        VkDeviceSize minBufferSize = 0;
-        Bool persistentlyMapped = false;
-    };
-
-    class BufferArena {
-    public:
-        Bool Initialize(const BufferArenaDesc& desc);
-        void Shutdown();
-
-        void BeginFrame(Uint32 frameIndex);
-        void ResetFrame(Uint32 frameIndex);
-        void CollectDeferredReleases(Uint32 frameIndex);
-
-        Bool Allocate(Uint32 frameIndex, VkDeviceSize size, VkDeviceSize alignment, BufferSlice& outSlice);
-        Bool Upload(Uint32 frameIndex, const void* data, VkDeviceSize size, VkDeviceSize alignment, BufferSlice& outSlice);
-
-        VkDeviceSize GetWriteCursor(Uint32 frameIndex) const;
-        Uint32 GetFrameCount() const;
-
-    private:
-        struct FrameResources {
-            VkBufferObject buffer;
-            VkDeviceSize writeCursor = 0;
-        };
-
-        Bool EnsureCapacity(Uint32 frameIndex, VkDeviceSize requiredEndOffset);
-        void AssertValidFrameIndex(Uint32 frameIndex) const;
-
-        BufferArenaDesc m_desc{};
-        Vector<FrameResources> m_frames;
-        Vector<Vector<VkBufferObject>> m_deferredReleases;
-    };
-} // namespace MobileGL::MG_Backend::DirectVulkan

MobileGL/MG_Backend/DirectVulkan/Renderer/BufferSlice.h

@@ -1,23 +0,0 @@
-// MobileGL - MobileGL/MG_Backend/DirectVulkan/Renderer/BufferSlice.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 {
-    struct BufferSlice {
-        VkBuffer buffer = VK_NULL_HANDLE;
-        VkDeviceSize offset = 0;
-        VkDeviceSize size = 0;
-        void* mapped = nullptr;
-
-        Bool IsValid() const { return buffer != VK_NULL_HANDLE; }
-    };
-} // namespace MobileGL::MG_Backend::DirectVulkan

MobileGL/MG_Backend/DirectVulkan/Renderer/FrameContext.cpp

@@ -1,454 +0,0 @@
-// MobileGL - MobileGL/MG_Backend/DirectVulkan/Renderer/FrameContext.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 "FrameContext.h"
-
-namespace MobileGL::MG_Backend::DirectVulkan {
-    VkResult FrameContext::Initialize(VkDevice device, VkCommandPool commandPool, Uint32 frameCount) {
-        Destroy(device, commandPool);
-        m_frames.assign(frameCount, {});
-        currentFrameIndex = 0;
-        m_device = device;
-        m_commandPool = commandPool;
-
-        Vector<VkCommandBuffer> commandBuffers(frameCount * 2, VK_NULL_HANDLE);
-        VkCommandBufferAllocateInfo allocInfo{};
-        allocInfo.sType = VK_STRUCTURE_TYPE_COMMAND_BUFFER_ALLOCATE_INFO;
-        allocInfo.commandPool = commandPool;
-        allocInfo.level = VK_COMMAND_BUFFER_LEVEL_PRIMARY;
-        allocInfo.commandBufferCount = frameCount * 2;
-        VkResult result = vkAllocateCommandBuffers(device, &allocInfo, commandBuffers.data());
-        if (result != VK_SUCCESS) {
-            return result;
-        }
-        for (Uint32 i = 0; i < frameCount; ++i) {
-            m_frames[i].commandBuffer = commandBuffers[i];
-            m_frames[i].preCommandBuffer = commandBuffers[frameCount + i];
-        }
-
-        VkSemaphoreCreateInfo semaphoreInfo{VK_STRUCTURE_TYPE_SEMAPHORE_CREATE_INFO};
-        VkFenceCreateInfo fenceInfo{VK_STRUCTURE_TYPE_FENCE_CREATE_INFO};
-        fenceInfo.flags = VK_FENCE_CREATE_SIGNALED_BIT;
-
-        for (Uint32 i = 0; i < frameCount; ++i) {
-            result = CreateSyncObjectsForFrame(device, i, semaphoreInfo, fenceInfo);
-            if (result != VK_SUCCESS) {
-                Destroy(device, commandPool);
-                return result;
-            }
-        }
-
-        return VK_SUCCESS;
-    }
-
-    void FrameContext::Destroy(VkDevice device, VkCommandPool commandPool) {
-        const Uint32 frameCount = static_cast<Uint32>(m_frames.size());
-        Vector<VkCommandBuffer> commandBuffers(frameCount * 2, VK_NULL_HANDLE);
-        for (Uint32 i = 0; i < frameCount; ++i) {
-            commandBuffers[i] = m_frames[i].commandBuffer;
-            commandBuffers[frameCount + i] = m_frames[i].preCommandBuffer;
-        }
-
-        for (Uint32 i = 0; i < frameCount; ++i) {
-            DestroySyncObjectsForFrame(device, i);
-        }
-        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 * 2, commandBuffers.data());
-        }
-        m_frames.clear();
-        currentFrameIndex = 0;
-        m_device = VK_NULL_HANDLE;
-        m_commandPool = VK_NULL_HANDLE;
-    }
-
-    FrameContext::FrameData& FrameContext::GetCurrent() {
-        MOBILEGL_ASSERT(!m_frames.empty(), "FrameContext is not initialized");
-        return m_frames[currentFrameIndex];
-    }
-
-    const FrameContext::FrameData& FrameContext::GetCurrent() const {
-        MOBILEGL_ASSERT(!m_frames.empty(), "FrameContext is not initialized");
-        return m_frames[currentFrameIndex];
-    }
-
-    Bool FrameContext::IsCommandRecording() const {
-        return GetCurrent().isCommandRecording;
-    }
-
-    void FrameContext::AdvanceToNext() {
-        MOBILEGL_ASSERT(!m_frames.empty(), "FrameContext is not initialized");
-        currentFrameIndex = (currentFrameIndex + 1) % static_cast<Uint32>(m_frames.size());
-        GetCurrent().isCommandRecording = false;
-        GetCurrent().hasCommandBufferRecorded = false;
-        GetCurrent().isPreCommandRecording = false;
-        GetCurrent().hasPreCommandBufferRecorded = false;
-    }
-
-    VkCommandBuffer& FrameContext::BeginCommandRecording(VkCommandBufferUsageFlags flags,
-                                                         const VkCommandBufferInheritanceInfo* pInheritanceInfo) {
-        auto& frame = GetCurrent();
-        MOBILEGL_ASSERT(!frame.isCommandRecording, "BeginCommandRecording called while command buffer is already recording");
-
-        frame.hasCommandBufferRecorded = false;
-        VK_VERIFY(vkResetCommandBuffer(frame.commandBuffer, 0), "BeginCommandRecording, vkResetCommandBuffer");
-
-        VkCommandBufferBeginInfo beginInfo{};
-        beginInfo.sType = VK_STRUCTURE_TYPE_COMMAND_BUFFER_BEGIN_INFO;
-        beginInfo.flags = flags;
-        beginInfo.pInheritanceInfo = pInheritanceInfo;
-        VK_VERIFY(vkBeginCommandBuffer(frame.commandBuffer, &beginInfo), "BeginCommandRecording, vkBeginCommandBuffer");
-
-        frame.isCommandRecording = true;
-        if (m_recordingObserver != nullptr) {
-            m_recordingObserver->OnFrameCommandRecordingBegan(frame.commandBuffer);
-        }
-        return frame.commandBuffer;
-    }
-
-    void FrameContext::EndCommandRecording() {
-        auto& frame = GetCurrent();
-        MOBILEGL_ASSERT(frame.isCommandRecording, "EndCommandRecording called without active command buffer recording");
-        VK_VERIFY(vkEndCommandBuffer(frame.commandBuffer), "EndCommandRecording, vkEndCommandBuffer");
-        frame.isCommandRecording = false;
-        frame.hasCommandBufferRecorded = true;
-    }
-
-    VkCommandBuffer FrameContext::BeginPreCommandRecording() {
-        auto& frame = GetCurrent();
-        if (frame.isPreCommandRecording) {
-            return frame.preCommandBuffer;
-        }
-        MOBILEGL_ASSERT(!frame.hasPreCommandBufferRecorded,
-                        "BeginPreCommandRecording: a recorded pre stream is still awaiting submission");
-        VK_VERIFY(vkResetCommandBuffer(frame.preCommandBuffer, 0), "BeginPreCommandRecording, vkResetCommandBuffer");
-        VkCommandBufferBeginInfo beginInfo{};
-        beginInfo.sType = VK_STRUCTURE_TYPE_COMMAND_BUFFER_BEGIN_INFO;
-        VK_VERIFY(vkBeginCommandBuffer(frame.preCommandBuffer, &beginInfo),
-                  "BeginPreCommandRecording, vkBeginCommandBuffer");
-        frame.isPreCommandRecording = true;
-        return frame.preCommandBuffer;
-    }
-
-    void FrameContext::EndPreCommandRecordingIfOpen() {
-        auto& frame = GetCurrent();
-        if (!frame.isPreCommandRecording) {
-            return;
-        }
-        VK_VERIFY(vkEndCommandBuffer(frame.preCommandBuffer), "EndPreCommandRecordingIfOpen, vkEndCommandBuffer");
-        frame.isPreCommandRecording = false;
-        frame.hasPreCommandBufferRecorded = true;
-    }
-
-    void FrameContext::AbandonPreCommandRecording() {
-        auto& frame = GetCurrent();
-        if (frame.isPreCommandRecording) {
-            VK_VERIFY(vkEndCommandBuffer(frame.preCommandBuffer), "AbandonPreCommandRecording, vkEndCommandBuffer");
-        }
-        frame.isPreCommandRecording = false;
-        frame.hasPreCommandBufferRecorded = false;
-    }
-
-    VkResult FrameContext::InitializeSwapchainSemaphores(VkDevice device, Uint32 swapchainImageCount) {
-        DestroySwapchainSemaphores(device);
-        if (swapchainImageCount == 0) {
-            return VK_SUCCESS;
-        }
-
-        m_swapchainImageRenderFinishedSemaphores.assign(swapchainImageCount, VK_NULL_HANDLE);
-        VkSemaphoreCreateInfo semaphoreInfo{VK_STRUCTURE_TYPE_SEMAPHORE_CREATE_INFO};
-        for (Uint32 imageIndex = 0; imageIndex < swapchainImageCount; ++imageIndex) {
-            VkResult result =
-                vkCreateSemaphore(device, &semaphoreInfo, nullptr, &m_swapchainImageRenderFinishedSemaphores[imageIndex]);
-            if (result != VK_SUCCESS) {
-                DestroySwapchainSemaphores(device);
-                return result;
-            }
-        }
-        return VK_SUCCESS;
-    }
-
-    void FrameContext::DestroySwapchainSemaphores(VkDevice device) {
-        if (device != VK_NULL_HANDLE) {
-            for (auto semaphore : m_swapchainImageRenderFinishedSemaphores) {
-                if (semaphore != VK_NULL_HANDLE) {
-                    vkDestroySemaphore(device, semaphore, nullptr);
-                }
-            }
-        }
-        m_swapchainImageRenderFinishedSemaphores.clear();
-    }
-
-    Bool FrameContext::TransitionToPresent(VkImage image, VkImageLayout oldLayout, VkImageLayout presentLayout) {
-        auto& frame = GetCurrent();
-        if (oldLayout == presentLayout || oldLayout == VK_IMAGE_LAYOUT_SHARED_PRESENT_KHR) {
-            return false;
-        }
-
-        // The barrier belongs in the frame's own recording. Bailing out because
-        // something was already recorded (the previous behaviour) dropped the
-        // transition entirely for every frame that never ran a default-framebuffer
-        // render pass - the only other thing that carries the image to
-        // PRESENT_SRC_KHR, via that pass's finalLayout - so the swapchain image was
-        // handed to the WSI still in the layout it was acquired in.
-        // A closed-but-unsubmitted buffer can only come from a submit that already
-        // failed (SubmitPendingCommandBuffer leaves the flag set on error), and
-        // appending to it is illegal while reopening would reset the frame's own
-        // commands away. The device is gone on that path anyway - stay silent-safe
-        // rather than trade a lost device for a barrier into a closed buffer.
-        if (frame.hasCommandBufferRecorded) {
-            MGLOG_E_ONCE("TransitionToPresent: command buffer already closed; skipping the present barrier");
-            return false;
-        }
-
-        // Reopening a recording here would vkResetCommandBuffer this frame's own
-        // commands away, so append to the open one and let the caller close it.
-        const Bool openedRecording = !frame.isCommandRecording;
-        VkCommandBuffer commandBuffer = openedRecording ? BeginCommandRecording() : frame.commandBuffer;
-
-        VkImageMemoryBarrier presentBarrier{};
-        presentBarrier.sType = VK_STRUCTURE_TYPE_IMAGE_MEMORY_BARRIER;
-        presentBarrier.srcAccessMask = 0;
-        presentBarrier.dstAccessMask = 0;
-        presentBarrier.oldLayout = oldLayout;
-        presentBarrier.newLayout = presentLayout;
-        presentBarrier.srcQueueFamilyIndex = VK_QUEUE_FAMILY_IGNORED;
-        presentBarrier.dstQueueFamilyIndex = VK_QUEUE_FAMILY_IGNORED;
-        presentBarrier.image = image;
-        presentBarrier.subresourceRange.aspectMask = VK_IMAGE_ASPECT_COLOR_BIT;
-        presentBarrier.subresourceRange.baseMipLevel = 0;
-        presentBarrier.subresourceRange.levelCount = 1;
-        presentBarrier.subresourceRange.baseArrayLayer = 0;
-        presentBarrier.subresourceRange.layerCount = 1;
-        vkCmdPipelineBarrier(commandBuffer, VK_PIPELINE_STAGE_TOP_OF_PIPE_BIT, VK_PIPELINE_STAGE_BOTTOM_OF_PIPE_BIT, 0, 0,
-                             nullptr, 0, nullptr, 1, &presentBarrier);
-
-        if (openedRecording) {
-            EndCommandRecording();
-        }
-        return true;
-    }
-
-    FrameContext::SubmitInfoPacket FrameContext::GetSubmitInfo(Bool shouldSubmitCommandBuffer,
-                                                               Uint32 swapchainImageIndex) const {
-        const auto& frame = GetCurrent();
-        MOBILEGL_ASSERT(!frame.isCommandRecording, "GetSubmitInfo called while command buffer recording is still active");
-        MOBILEGL_ASSERT(!frame.isPreCommandRecording,
-                        "GetSubmitInfo called while the pre-pass stream is still recording");
-        AssertValidSwapchainImageIndex(swapchainImageIndex);
-        SubmitInfoPacket packet{};
-        packet.waitSemaphore = frame.imageAvailableSemaphore;
-        packet.signalSemaphore = m_swapchainImageRenderFinishedSemaphores[swapchainImageIndex];
-
-        Uint32 commandBufferCount = 0;
-        // The pre-pass stream executes strictly before the frame's commands.
-        if (frame.hasPreCommandBufferRecorded) {
-            packet.commandBuffers[commandBufferCount++] = frame.preCommandBuffer;
-        }
-        if (shouldSubmitCommandBuffer) {
-            packet.commandBuffers[commandBufferCount++] = frame.commandBuffer;
-        }
-
-        packet.submitInfo.waitSemaphoreCount = frame.imageAvailableSemaphoreConsumed ? 0U : 1U;
-        packet.submitInfo.pWaitSemaphores = frame.imageAvailableSemaphoreConsumed ? nullptr : &packet.waitSemaphore;
-        packet.submitInfo.pWaitDstStageMask = frame.imageAvailableSemaphoreConsumed ? nullptr : &packet.waitDstStageMask;
-        packet.submitInfo.commandBufferCount = commandBufferCount;
-        packet.submitInfo.pCommandBuffers = commandBufferCount > 0 ? packet.commandBuffers : nullptr;
-        packet.submitInfo.signalSemaphoreCount = 1;
-        packet.submitInfo.pSignalSemaphores = &packet.signalSemaphore;
-        return packet;
-    }
-
-    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.presentInfo.waitSemaphoreCount = 1;
-        packet.presentInfo.pWaitSemaphores = &packet.waitSemaphore;
-        packet.presentInfo.swapchainCount = 1;
-        packet.presentInfo.pSwapchains = &packet.swapchain;
-        packet.presentInfo.pImageIndices = &packet.imageIndex;
-        packet.presentInfo.pResults = nullptr;
-        return packet;
-    }
-
-    VkResult FrameContext::WaitAndAcquireNextImage(VkDevice device, VkSwapchainKHR swapchain, Uint32& outImageIndex,
-                                                   Uint64 timeout, VkFence acquireFence) {
-        auto& frame = GetCurrent();
-        VkResult result = vkWaitForFences(device, 1, &frame.imageInFlightFence, VK_TRUE, timeout);
-        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 = vkAcquireNextImageKHR(device, swapchain, timeout, frame.imageAvailableSemaphore, acquireFence,
-                                       &outImageIndex);
-        // VK_SUBOPTIMAL_KHR is a success code: an image *was* acquired and
-        // imageAvailableSemaphore *will* be signaled. Bailing out on it skipped both
-        // the consumed-flag reset (leaving a stale "already consumed", so the next
-        // submit never waited on the pending signal) and the fence reset (leaving
-        // the slot's fence signaled for the next submit to reuse). Only a genuine
-        // failure - VK_ERROR_OUT_OF_DATE_KHR and friends, where nothing is acquired
-        // and nothing is signaled - skips the bookkeeping.
-        if (result != VK_SUCCESS && result != VK_SUBOPTIMAL_KHR) {
-            return result;
-        }
-
-        frame.imageAvailableSemaphoreConsumed = false;
-        const VkResult resetResult = vkResetFences(device, 1, &frame.imageInFlightFence);
-        // Hand the acquire's own code back so the caller can schedule a rebuild.
-        return resetResult == VK_SUCCESS ? result : resetResult;
-    }
-
-    Uint32 FrameContext::GetCurrentFrameIndex() const {
-        return currentFrameIndex;
-    }
-
-    Uint32 FrameContext::GetFrameCount() const {
-        return static_cast<Uint32>(m_frames.size());
-    }
-
-    void FrameContext::SetRecordingObserver(IRecordingObserver* observer) {
-        m_recordingObserver = observer;
-    }
-
-    VkResult FrameContext::RetireCurrentCommandBuffer(Bool retirePreCommandBuffer) {
-        MOBILEGL_ASSERT(m_device != VK_NULL_HANDLE && m_commandPool != VK_NULL_HANDLE,
-                        "RetireCurrentCommandBuffer requires an initialized FrameContext");
-        auto& frame = GetCurrent();
-        MOBILEGL_ASSERT(!frame.isCommandRecording,
-                        "RetireCurrentCommandBuffer called while the command buffer is still recording");
-        MOBILEGL_ASSERT(!frame.isPreCommandRecording,
-                        "RetireCurrentCommandBuffer called while the pre-pass stream is still recording");
-
-        VkCommandBufferAllocateInfo allocInfo{};
-        allocInfo.sType = VK_STRUCTURE_TYPE_COMMAND_BUFFER_ALLOCATE_INFO;
-        allocInfo.commandPool = m_commandPool;
-        allocInfo.level = VK_COMMAND_BUFFER_LEVEL_PRIMARY;
-        allocInfo.commandBufferCount = 1;
-        VkCommandBuffer replacement = VK_NULL_HANDLE;
-        VkResult result = vkAllocateCommandBuffers(m_device, &allocInfo, &replacement);
-        if (result != VK_SUCCESS) {
-            return result;
-        }
-        if (retirePreCommandBuffer) {
-            VkCommandBuffer preReplacement = VK_NULL_HANDLE;
-            result = vkAllocateCommandBuffers(m_device, &allocInfo, &preReplacement);
-            if (result != VK_SUCCESS) {
-                vkFreeCommandBuffers(m_device, m_commandPool, 1, &replacement);
-                return result;
-            }
-            frame.retiredCommandBuffers.push_back({frame.preCommandBuffer, frame.lastSubmitIndex});
-            frame.preCommandBuffer = preReplacement;
-        }
-        // lastSubmitIndex was just written by the renderer for the submission
-        // that carried this command buffer.
-        frame.retiredCommandBuffers.push_back({frame.commandBuffer, frame.lastSubmitIndex});
-        frame.commandBuffer = replacement;
-        return VK_SUCCESS;
-    }
-
-    void FrameContext::FreeRetiredCommandBuffers(FrameData& frame) {
-        if (frame.retiredCommandBuffers.empty()) {
-            return;
-        }
-        if (m_device != VK_NULL_HANDLE && m_commandPool != VK_NULL_HANDLE) {
-            for (const auto& retired : frame.retiredCommandBuffers) {
-                vkFreeCommandBuffers(m_device, m_commandPool, 1, &retired.commandBuffer);
-            }
-        }
-        frame.retiredCommandBuffers.clear();
-    }
-
-    void FrameContext::FreeRetiredCommandBuffersCompletedUpTo(Uint64 completedSubmitIndex) {
-        if (m_device == VK_NULL_HANDLE || m_commandPool == VK_NULL_HANDLE) {
-            return;
-        }
-        for (auto& frame : m_frames) {
-            // Retired buffers are appended in submit order, so the completed
-            // ones form a prefix.
-            SizeT completedCount = 0;
-            while (completedCount < frame.retiredCommandBuffers.size() &&
-                   frame.retiredCommandBuffers[completedCount].submitIndex <= completedSubmitIndex) {
-                vkFreeCommandBuffers(m_device, m_commandPool, 1,
-                                     &frame.retiredCommandBuffers[completedCount].commandBuffer);
-                ++completedCount;
-            }
-            if (completedCount > 0) {
-                frame.retiredCommandBuffers.erase(frame.retiredCommandBuffers.begin(),
-                                                  frame.retiredCommandBuffers.begin() + completedCount);
-            }
-        }
-    }
-
-    void FrameContext::FreeAllRetiredCommandBuffers() {
-        for (auto& frame : m_frames) {
-            FreeRetiredCommandBuffers(frame);
-        }
-    }
-
-    void FrameContext::AssertValidFrameIndex(Uint32 frameIndex) const {
-        MOBILEGL_ASSERT(frameIndex < m_frames.size(), "FrameContext index out of range");
-    }
-
-    void FrameContext::AssertValidSwapchainImageIndex(Uint32 imageIndex) const {
-        MOBILEGL_ASSERT(imageIndex < m_swapchainImageRenderFinishedSemaphores.size(),
-                        "FrameContext swapchain image index out of range");
-    }
-
-    VkResult FrameContext::CreateSyncObjectsForFrame(VkDevice device, Uint32 frameIndex,
-                                                     const VkSemaphoreCreateInfo& semaphoreInfo,
-                                                     const VkFenceCreateInfo& fenceInfo) {
-        AssertValidFrameIndex(frameIndex);
-        DestroySyncObjectsForFrame(device, frameIndex);
-
-        auto& frame = m_frames[frameIndex];
-        VkResult result =
-            vkCreateSemaphore(device, &semaphoreInfo, nullptr, &frame.imageAvailableSemaphore);
-        if (result != VK_SUCCESS) {
-            return result;
-        }
-
-        result = vkCreateFence(device, &fenceInfo, nullptr, &frame.imageInFlightFence);
-        if (result != VK_SUCCESS) {
-            vkDestroySemaphore(device, frame.imageAvailableSemaphore, nullptr);
-            frame.imageAvailableSemaphore = VK_NULL_HANDLE;
-            return result;
-        }
-
-        frame.hasCommandBufferRecorded = false;
-        frame.isCommandRecording = false;
-        frame.imageAvailableSemaphoreConsumed = false;
-        return VK_SUCCESS;
-    }
-
-    void FrameContext::DestroySyncObjectsForFrame(VkDevice device, Uint32 frameIndex) {
-        AssertValidFrameIndex(frameIndex);
-        auto& frame = m_frames[frameIndex];
-        if (device != VK_NULL_HANDLE && frame.imageInFlightFence != VK_NULL_HANDLE) {
-            vkDestroyFence(device, frame.imageInFlightFence, nullptr);
-        }
-        frame.imageInFlightFence = VK_NULL_HANDLE;
-
-        if (device != VK_NULL_HANDLE && frame.imageAvailableSemaphore != VK_NULL_HANDLE) {
-            vkDestroySemaphore(device, frame.imageAvailableSemaphore, nullptr);
-        }
-        frame.imageAvailableSemaphore = VK_NULL_HANDLE;
-        frame.isCommandRecording = false;
-        frame.hasCommandBufferRecorded = false;
-        frame.imageAvailableSemaphoreConsumed = false;
-    }
-} // namespace MobileGL::MG_Backend::DirectVulkan

MobileGL/MG_Backend/DirectVulkan/Renderer/FrameContext.h

@@ -1,147 +0,0 @@
-// MobileGL - MobileGL/MG_Backend/DirectVulkan/Renderer/FrameContext.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 {
-    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;
-            VkSemaphore signalSemaphore = VK_NULL_HANDLE;
-            // [0] = pre-pass command buffer (when recorded), then the frame
-            // command buffer; submitInfo.pCommandBuffers points here.
-            VkCommandBuffer commandBuffers[2] = {VK_NULL_HANDLE, VK_NULL_HANDLE};
-            VkSubmitInfo submitInfo{VK_STRUCTURE_TYPE_SUBMIT_INFO};
-        };
-
-        struct PresentInfoPacket {
-            VkSemaphore waitSemaphore = VK_NULL_HANDLE;
-            VkSwapchainKHR swapchain = VK_NULL_HANDLE;
-            Uint32 imageIndex = 0;
-            VkPresentInfoKHR presentInfo{VK_STRUCTURE_TYPE_PRESENT_INFO_KHR};
-        };
-
-        // A command buffer submitted mid-frame (FlushPendingCommands), tagged
-        // with the submit-tracker index it was submitted under so it can be
-        // freed as soon as that submission is observed complete - without
-        // waiting for the slot's fence to be waited again (present-less flush
-        // loops never wait it).
-        struct RetiredCommandBuffer {
-            VkCommandBuffer commandBuffer = VK_NULL_HANDLE;
-            Uint64 submitIndex = 0;
-        };
-
-        struct FrameData {
-            VkCommandBuffer commandBuffer = VK_NULL_HANDLE;
-            // Pre-pass work stream: out-of-pass commands (deferred clear
-            // materialization, sampled-layout transitions) for resources the
-            // frame's recording has not touched yet. Submitted immediately
-            // BEFORE commandBuffer in the same vkQueueSubmit, so recording
-            // into it never has to split the frame's active render pass.
-            VkCommandBuffer preCommandBuffer = VK_NULL_HANDLE;
-            VkSemaphore imageAvailableSemaphore = VK_NULL_HANDLE;
-            VkFence imageInFlightFence = VK_NULL_HANDLE;
-            Bool isCommandRecording = false;
-            Bool hasCommandBufferRecorded = false;
-            Bool isPreCommandRecording = false;
-            Bool hasPreCommandBufferRecorded = false;
-            Bool imageAvailableSemaphoreConsumed = false;
-            // Command buffers submitted mid-frame (FlushPendingCommands),
-            // appended in submit order; freed once their submission is known
-            // complete (fence wait or completion poll).
-            Vector<RetiredCommandBuffer> retiredCommandBuffers;
-            // Submit-tracker index of this slot's most recent queue submission
-            // (written by the renderer at submit time).
-            Uint64 lastSubmitIndex = 0;
-        };
-
-        VkResult Initialize(VkDevice device, VkCommandPool commandPool, Uint32 frameCount);
-        void Destroy(VkDevice device, VkCommandPool commandPool);
-
-        // Lifecycle functions
-        FrameData& GetCurrent();
-        const FrameData& GetCurrent() const;
-        Bool IsCommandRecording() const;
-        void AdvanceToNext();
-        VkCommandBuffer& BeginCommandRecording(VkCommandBufferUsageFlags flags = 0,
-                                               const VkCommandBufferInheritanceInfo* pInheritanceInfo = nullptr);
-        void EndCommandRecording();
-        // Lazily opens the pre-pass work stream (see FrameData::preCommandBuffer).
-        VkCommandBuffer BeginPreCommandRecording();
-        // Closes the pre stream if open, marking it for submission ahead of the
-        // frame command buffer. Safe to call when it never opened.
-        void EndPreCommandRecordingIfOpen();
-        // Drops an in-progress or recorded-but-unsubmitted pre stream (dropped
-        // frame recordings, swapchain recreation).
-        void AbandonPreCommandRecording();
-        VkResult InitializeSwapchainSemaphores(VkDevice device, Uint32 swapchainImageCount);
-        void DestroySwapchainSemaphores(VkDevice device);
-        Bool TransitionToPresent(VkImage image, VkImageLayout oldLayout,
-                                 VkImageLayout presentLayout = VK_IMAGE_LAYOUT_PRESENT_SRC_KHR);
-        SubmitInfoPacket GetSubmitInfo(Bool shouldSubmitCommandBuffer, Uint32 swapchainImageIndex) 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, or as soon
-        // as their submission is observed complete.
-        VkResult RetireCurrentCommandBuffer(Bool retirePreCommandBuffer = false);
-
-        // Frees every retired command buffer whose tagged submission index is
-        // known complete. Driven by the renderer's submit tracker on completion
-        // events (fence waits and non-blocking polls), so present-less flush
-        // loops reclaim their buffers without any extra wait.
-        void FreeRetiredCommandBuffersCompletedUpTo(Uint64 completedSubmitIndex);
-        // Frees every slot's retired command buffers. Only valid when the
-        // caller has proven every queue submission complete.
-        void FreeAllRetiredCommandBuffers();
-
-        Uint32 GetCurrentFrameIndex() const;
-        Uint32 GetFrameCount() const;
-
-        // Observer may be null (no notifications). Not owned.
-        void SetRecordingObserver(IRecordingObserver* observer);
-
-    private:
-        void AssertValidFrameIndex(Uint32 frameIndex) const;
-        void AssertValidSwapchainImageIndex(Uint32 imageIndex) const;
-
-        VkResult CreateSyncObjectsForFrame(VkDevice device, Uint32 frameIndex,
-                                           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

@@ -1,633 +0,0 @@
-// MobileGL - MobileGL/MG_Backend/DirectVulkan/Renderer/PipelineFactory.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 "PipelineFactory.h"
-
-#include <algorithm>
-
-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");
-    }
-
-    // Must be called once, before any pipeline is created: the flag is not part of the
-    // pipeline hash, so flipping it mid-life would serve cached pipelines built under the
-    // old value.
-    void PipelineFactory::SetSuppressBlendedDepthWrite(Bool enabled) {
-        s_suppressBlendedDepthWrite = enabled;
-    }
-
-    Bool PipelineFactory::ShouldSuppressBlendedDepthWriteForDevice(MG_Config::QuirkOverride quirkOverride,
-                                                                   Uint32 vendorId) {
-        static constexpr Uint32 kVendorIdQualcomm = 0x5143;
-        switch (quirkOverride) {
-        case MG_Config::QuirkOverride::ForceOn:
-            return true;
-        case MG_Config::QuirkOverride::ForceOff:
-            return false;
-        case MG_Config::QuirkOverride::Auto:
-        default:
-            return vendorId == kVendorIdQualcomm;
-        }
-    }
-
-    namespace {
-        // MIN/MAX extremum blending: the signature of a depth-bounds accumulation pass
-        // (MC 26.3 OIT writes vec4(-linD, linD, deviceZ, 0) under GL_MAX while writing
-        // depth for its equality chain). MIN/MAX ignore blend factors per the Vulkan spec.
-        //
-        // Deliberately the ONLY shape stripped. A quirk should touch as little unrelated
-        // content as possible, and a trace sweep of every fixture showed the wider
-        // alternatives all cost more than they fix:
-        //   - additive ONE+ONE with a depth write matched zero draws of the 26.3 chain
-        //     (its transmittance/accumulate passes disable depth writes themselves) - the
-        //     only real content it caught was harmless additive glow effects (Create);
-        //   - sorted-transparency "over" blends (SRC_ALPHA-style) are order-dependent,
-        //     drawn once per surface, and rely on their depth writes for occlusion;
-        //   - separate-alpha accumulation over an over-blending color channel has no
-        //     known pairing with a depth-equality chain (color channel only, see tests).
-        // If a future workload pairs another blend shape with an equality chain, widen
-        // this with that evidence in hand rather than pre-emptively.
-        Bool IsAccumulationBlend(const VkPipelineColorBlendAttachmentState& attachment) {
-            return attachment.colorBlendOp == VK_BLEND_OP_MIN ||
-                   attachment.colorBlendOp == VK_BLEND_OP_MAX;
-        }
-    } // namespace
-
-    Bool PipelineFactory::ShouldSuppressDepthWrite(const PipelineCreatePayload& payload) {
-        if (!payload.depthWriteEnable) {
-            return false;
-        }
-        // A shader that assigns gl_FragDepth supplies depth itself rather than taking the
-        // pipeline's interpolated Z, so a driver that varies the vertex position math
-        // between pipelines cannot desynchronize it. (A gl_FragDepth = gl_FragCoord.z
-        // passthrough is the exception that stays exposed; no known content pairs one with
-        // an equality chain, and 26.3's composite is a genuine computed-depth writer.)
-        if (payload.fragmentReplacesDepth) {
-            return false;
-        }
-        for (Uint32 i = 0; i < payload.colorAttachmentCount; ++i) {
-            const VkPipelineColorBlendAttachmentState& attachment = payload.colorBlendAttachments[i];
-            if (attachment.blendEnable != VK_TRUE) {
-                continue;
-            }
-            // All color writes masked: blending is moot (depth-prepass pattern that left
-            // GL_BLEND enabled); stripping the depth write would delete the whole prepass.
-            if (attachment.colorWriteMask == 0) {
-                continue;
-            }
-            // Any attachment qualifies, not just attachment 0: the 26.3 transmittance pass
-            // accumulates into a 2-target MRT and must stay stripped.
-            if (IsAccumulationBlend(attachment)) {
-                return true;
-            }
-        }
-        return false;
-    }
-
-    PipelineFactory::~PipelineFactory() {
-        DestroyAll();
-        if (m_pipelineCache != VK_NULL_HANDLE) {
-            vkDestroyPipelineCache(m_device, m_pipelineCache, nullptr);
-            m_pipelineCache = VK_NULL_HANDLE;
-        }
-    }
-
-    PipelineFactory::HashType PipelineFactory::ComputeHash(const PipelineCreatePayload& payload) const {
-        XXHASH_VERIFY(XXH64_reset(m_hashState, m_config.CacheVersion));
-        XXHASH_VERIFY(XXH64_update(m_hashState, &payload.programHash, sizeof(payload.programHash)));
-        XXHASH_VERIFY(XXH64_update(m_hashState, &payload.vertexInputHash, sizeof(payload.vertexInputHash)));
-        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.patchControlPoints, sizeof(payload.patchControlPoints)));
-        XXHASH_VERIFY(XXH64_update(m_hashState, &payload.viewportCount, sizeof(payload.viewportCount)));
-        XXHASH_VERIFY(XXH64_update(m_hashState, &payload.polygonMode, sizeof(payload.polygonMode)));
-        XXHASH_VERIFY(XXH64_update(m_hashState, &payload.cullMode, sizeof(payload.cullMode)));
-        XXHASH_VERIFY(XXH64_update(m_hashState, &payload.frontFace, sizeof(payload.frontFace)));
-        XXHASH_VERIFY(
-            XXH64_update(m_hashState, &payload.provokingVertexMode, sizeof(payload.provokingVertexMode)));
-        XXHASH_VERIFY(XXH64_update(m_hashState, &payload.depthTestEnable, sizeof(payload.depthTestEnable)));
-        XXHASH_VERIFY(XXH64_update(m_hashState, &payload.depthWriteEnable, sizeof(payload.depthWriteEnable)));
-        XXHASH_VERIFY(XXH64_update(m_hashState, &payload.depthBiasEnable, sizeof(payload.depthBiasEnable)));
-        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)));
-        XXHASH_VERIFY(
-            XXH64_update(m_hashState, &payload.fragmentReplacesDepth, sizeof(payload.fragmentReplacesDepth)));
-        if (payload.colorAttachmentCount > 0) {
-            XXHASH_VERIFY(XXH64_update(
-                m_hashState,
-                payload.colorBlendAttachments.data(),
-                sizeof(payload.colorBlendAttachments[0]) * payload.colorAttachmentCount));
-        }
-        return XXH64_digest(m_hashState);
-    }
-
-    VkPipeline PipelineFactory::GetOrCreatePipeline(const PipelineCreatePayload& payload) {
-        const HashType hash = ComputeHash(payload);
-        auto it = m_cache.find(hash);
-        if (it != m_cache.end()) {
-            it->second.lastUsedFrame = m_frameCounter;
-            return it->second.pipeline;
-        }
-
-        VkPipeline pipeline = CreatePipeline(payload);
-        // A failed creation must never be memoized. Caching VK_NULL_HANDLE served the null back for
-        // the rest of the process, so one transient driver rejection turned every later draw with
-        // the same state into a vkCmdBindPipeline(VK_NULL_HANDLE) - the SIGSEGV behind 9 of the 15
-        // CTS process deaths. Retrying costs one failed vkCreateGraphicsPipelines per draw, which
-        // is the correct price for a broken pipeline and is bounded by the draw itself being
-        // skipped.
-        if (pipeline == VK_NULL_HANDLE) {
-            // Unlatched, like the CreatePipeline report it accompanies: a pipeline MobileGL
-            // assembled and the driver refused is a broken invariant, not an expected failure,
-            // so it stays loud for as long as it is reachable. Raised from MGLOG_I once the
-            // Log.h ordering fix made MGLOG_E live in INFO builds.
-            MGLOG_E("PipelineFactory::GetOrCreatePipeline: creation failed for hash=0x%llx "
-                    "programHash=0x%llx; not caching the failure",
-                    static_cast<unsigned long long>(hash),
-                    static_cast<unsigned long long>(payload.programHash));
-            return VK_NULL_HANDLE;
-        }
-        m_cache.emplace(hash, PipelineCacheEntry{pipeline, payload.programHash, payload.renderPass,
-                                                 m_frameCounter});
-        return pipeline;
-    }
-
-    void PipelineFactory::DestroyAll() {
-        for (auto& pair : m_cache) {
-            if (pair.second.pipeline != VK_NULL_HANDLE) {
-                vkDestroyPipeline(m_device, pair.second.pipeline, nullptr);
-            }
-        }
-        m_cache.clear();
-    }
-
-    Uint32 PipelineFactory::OnFrameBoundary() {
-        ++m_frameCounter;
-
-        // Sweep cadence and retire age mirror VkRenderPassManager::OnPresent: an entry
-        // idle for more than kRetireAgeFrames frame boundaries cannot be referenced by
-        // any in-flight command buffer (frames-in-flight <= MOBILEGL_MAGMA_FRAMESINFLIGHT),
-        // so immediate vkDestroyPipeline is safe. The caller must drop its "last
-        // pipeline" memo when this returns non-zero: the memo can return a cached
-        // handle without touching this cache, so an evicted pipeline may still be
-        // memoized (present-less flush loops never reset the memo per frame).
-        constexpr Uint64 kSweepInterval = 256;
-        constexpr Uint64 kRetireAgeFrames = 1024;
-        if ((m_frameCounter % kSweepInterval) != 0) {
-            return 0;
-        }
-
-        Uint32 evicted = 0;
-        for (auto it = m_cache.begin(); it != m_cache.end();) {
-            if (m_frameCounter - it->second.lastUsedFrame > kRetireAgeFrames) {
-                if (it->second.pipeline != VK_NULL_HANDLE) {
-                    vkDestroyPipeline(m_device, it->second.pipeline, nullptr);
-                }
-                it = m_cache.erase(it);
-                ++evicted;
-            } else {
-                ++it;
-            }
-        }
-        if (evicted > 0) {
-            MGLOG_D("PipelineFactory::OnFrameBoundary: evicted %u idle pipelines (%zu remain)", evicted,
-                    m_cache.size());
-        }
-        return evicted;
-    }
-
-    Uint32 PipelineFactory::EvictByRenderPasses(const Vector<VkRenderPass>& renderPasses) {
-        if (renderPasses.empty() || m_cache.empty()) {
-            return 0;
-        }
-        // Sorted-batch membership test keeps a mass eviction (shader-pack switch,
-        // dimension exit) at one O(cache * log batch) scan instead of one full scan
-        // per dying pass.
-        Vector<VkRenderPass> sortedPasses = renderPasses;
-        std::sort(sortedPasses.begin(), sortedPasses.end());
-        Uint32 evicted = 0;
-        for (auto it = m_cache.begin(); it != m_cache.end();) {
-            if (std::binary_search(sortedPasses.begin(), sortedPasses.end(), it->second.renderPass)) {
-                if (it->second.pipeline != VK_NULL_HANDLE) {
-                    vkDestroyPipeline(m_device, it->second.pipeline, nullptr);
-                }
-                it = m_cache.erase(it);
-                ++evicted;
-            } else {
-                ++it;
-            }
-        }
-        if (evicted > 0) {
-            MGLOG_D("PipelineFactory::EvictByRenderPasses: evicted %u pipelines for %zu destroyed render passes",
-                    evicted, sortedPasses.size());
-        }
-        return evicted;
-    }
-
-    Uint32 PipelineFactory::EvictByProgramHash(HashType programHash) {
-        Uint32 evicted = 0;
-        for (auto it = m_cache.begin(); it != m_cache.end();) {
-            if (it->second.programHash == programHash) {
-                if (it->second.pipeline != VK_NULL_HANDLE) {
-                    vkDestroyPipeline(m_device, it->second.pipeline, nullptr);
-                }
-                it = m_cache.erase(it);
-                ++evicted;
-            } else {
-                ++it;
-            }
-        }
-        if (evicted > 0) {
-            MGLOG_D("PipelineFactory::EvictByProgramHash: evicted %u pipelines for program hash 0x%llx",
-                    evicted, static_cast<unsigned long long>(programHash));
-        }
-        return evicted;
-    }
-
-    VkPipeline PipelineFactory::CreatePipeline(const PipelineCreatePayload& payload) const {
-        MOBILEGL_ASSERT(payload.stages != nullptr && !payload.stages->empty(), "PipelineFactory: stages are empty");
-        MOBILEGL_ASSERT(payload.vertexInputState != nullptr, "PipelineFactory: vertexInputState is null");
-        MOBILEGL_ASSERT(payload.pipelineLayout != VK_NULL_HANDLE, "PipelineFactory: pipelineLayout is null");
-        MOBILEGL_ASSERT(payload.renderPass != VK_NULL_HANDLE, "PipelineFactory: renderPass is null");
-        MOBILEGL_ASSERT(payload.colorAttachmentCount <= PipelineCreatePayload::kMaxColorAttachments,
-                "PipelineFactory: colorAttachmentCount=%u is unexpectedly large",
-                payload.colorAttachmentCount);
-        MGLOG_D("PipelineFactory::CreatePipeline: programHash=0x%llx vertexInputHash=0x%llx colorAttachmentCount=%u subpass=%u",
-            static_cast<unsigned long long>(payload.programHash),
-            static_cast<unsigned long long>(payload.vertexInputHash),
-            payload.colorAttachmentCount,
-            payload.subpass);
-
-        static constexpr VkDynamicState kDynamicStates[] = {
-            VK_DYNAMIC_STATE_VIEWPORT,
-            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{};
-        dynamicState.sType = VK_STRUCTURE_TYPE_PIPELINE_DYNAMIC_STATE_CREATE_INFO;
-        dynamicState.dynamicStateCount = static_cast<uint32_t>(std::size(kDynamicStates));
-        dynamicState.pDynamicStates = kDynamicStates;
-
-        VkPipelineInputAssemblyStateCreateInfo ia{VK_STRUCTURE_TYPE_PIPELINE_INPUT_ASSEMBLY_STATE_CREATE_INFO};
-        ia.topology = payload.topology;
-        ia.primitiveRestartEnable = payload.primitiveRestartEnable ? VK_TRUE : VK_FALSE;
-
-        // Only a patch topology has a tessellation stage to configure; leaving the pointer null
-        // otherwise is what the spec expects.
-        VkPipelineTessellationStateCreateInfo tessellation{VK_STRUCTURE_TYPE_PIPELINE_TESSELLATION_STATE_CREATE_INFO};
-        tessellation.patchControlPoints = payload.patchControlPoints;
-
-        VkPipelineViewportStateCreateInfo vpci{VK_STRUCTURE_TYPE_PIPELINE_VIEWPORT_STATE_CREATE_INFO};
-        // Both counts move together: GL has one scissor rectangle per viewport, and Vulkan
-        // requires viewportCount == scissorCount whenever both are dynamic
-        // (VUID-VkPipelineViewportStateCreateInfo-scissorCount-04136). The caller has already
-        // clamped this to the device's multiViewport capability.
-        vpci.viewportCount = std::max<Uint32>(payload.viewportCount, 1u);
-        vpci.scissorCount = vpci.viewportCount;
-
-        VkPipelineRasterizationStateCreateInfo raster{VK_STRUCTURE_TYPE_PIPELINE_RASTERIZATION_STATE_CREATE_INFO};
-        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;
-        // Only chain the struct when the mode is not Vulkan's implicit default: a device without
-        // VK_EXT_provoking_vertex enabled must never see this pNext entry, and the renderer's
-        // selector already collapses to FIRST in exactly that case - so a device without the
-        // extension produces a byte-identical VkGraphicsPipelineCreateInfo to before.
-        VkPipelineRasterizationProvokingVertexStateCreateInfoEXT provokingVertexState{
-            VK_STRUCTURE_TYPE_PIPELINE_RASTERIZATION_PROVOKING_VERTEX_STATE_CREATE_INFO_EXT};
-        if (payload.provokingVertexMode != VK_PROVOKING_VERTEX_MODE_FIRST_VERTEX_EXT) {
-            provokingVertexState.provokingVertexMode = payload.provokingVertexMode;
-            provokingVertexState.pNext = raster.pNext;
-            raster.pNext = &provokingVertexState;
-        }
-
-        VkPipelineMultisampleStateCreateInfo ms{VK_STRUCTURE_TYPE_PIPELINE_MULTISAMPLE_STATE_CREATE_INFO};
-        ms.rasterizationSamples = payload.rasterizationSamples;
-
-        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 = 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];
-        }
-        // Suppress depth writes on accumulation-blended pipelines when the active driver
-        // cannot keep vertex positions invariant across the pipelines of a multi-pass
-        // depth-equality chain (see SetSuppressBlendedDepthWrite). The decision is narrowed
-        // in ShouldSuppressDepthWrite: sorted-transparency "over" blends (vanilla MC water),
-        // gl_FragDepth writers, and masked-out attachments keep their depth writes.
-        // This bakes the decision into the pipeline, which only works because depth write is
-        // static state here - adding VK_DYNAMIC_STATE_DEPTH_WRITE_ENABLE to kDynamicStates
-        // would let the record-time value override it and silently disable the quirk.
-        if (s_suppressBlendedDepthWrite && ShouldSuppressDepthWrite(payload)) {
-            depthStencil.depthWriteEnable = VK_FALSE;
-        }
-        VkPipelineColorBlendStateCreateInfo blend{VK_STRUCTURE_TYPE_PIPELINE_COLOR_BLEND_STATE_CREATE_INFO};
-        blend.logicOpEnable = payload.logicOpEnable ? VK_TRUE : VK_FALSE;
-        blend.logicOp = payload.logicOp;
-        blend.attachmentCount = payload.colorAttachmentCount;
-        blend.pAttachments = colorAttachments.empty() ? nullptr : colorAttachments.data();
-
-        // A GL program may have a tessellation EVALUATION stage and no CONTROL stage: GL 4.6 core
-        // 11.2.2 gives it a fixed-function pass-through instead. Vulkan has no such stage, and
-        // VUID-VkGraphicsPipelineCreateInfo-pStages-00730 requires both tessellation stages or
-        // neither - so the renderer synthesizes the pass-through GL describes and hands it in
-        // here (see ProgramFactory::GetOrCreatePassthroughTessControlStage).
-        //
-        // The refusal below is what keeps the half-tessellated shape away from the driver when
-        // there is no synthesized stage to add - because Mali does not reject it, it dereferences
-        // null INSIDE vkCreateGraphicsPipelines and takes the process down (SIGSEGV, fault addr
-        // 0x34, on Mali-G715/r54p2 and Mali-G925/r49p1 alike; Adreno and lavapipe merely render
-        // wrong). Returning VK_NULL_HANDLE routes this through the same path a driver rejection
-        // takes: the draw is skipped, nothing is memoised, and the process survives.
-        const Vector<VkPipelineShaderStageCreateInfo>* effectiveStages = payload.stages;
-        Vector<VkPipelineShaderStageCreateInfo> stagesWithPassthrough;
-        if (payload.passthroughTessControlStage.module != VK_NULL_HANDLE) {
-            stagesWithPassthrough = *payload.stages;
-            stagesWithPassthrough.push_back(payload.passthroughTessControlStage);
-            effectiveStages = &stagesWithPassthrough;
-        }
-        {
-            VkShaderStageFlags stagesPresent = 0;
-            for (const auto& stageInfo : *effectiveStages) {
-                stagesPresent |= stageInfo.stage;
-            }
-            const Bool hasTessControl = (stagesPresent & VK_SHADER_STAGE_TESSELLATION_CONTROL_BIT) != 0;
-            const Bool hasTessEval = (stagesPresent & VK_SHADER_STAGE_TESSELLATION_EVALUATION_BIT) != 0;
-            if (hasTessControl != hasTessEval) {
-                // Latched, and the latch is the point: a failed creation is deliberately never
-                // memoised (see GetOrCreatePipeline), so a program in this state re-enters here
-                // once per draw, every frame - and a refusal diagnostic that repeats per draw is
-                // noise, not a diagnostic. One line names the program; the draws it explains are
-                // all the same draw.
-                static Bool s_warnedHalfTessellatedPipeline = false;
-                if (!s_warnedHalfTessellatedPipeline) {
-                    s_warnedHalfTessellatedPipeline = true;
-                    MGLOG_E_ONCE("PipelineFactory::CreatePipeline: refusing a pipeline with %s tessellation stage and "
-                            "no %s stage (VUID-VkGraphicsPipelineCreateInfo-pStages-00730). programHash=0x%llx "
-                            "patchControlPoints=%u. Its draws are skipped; logged once.",
-                            hasTessEval ? "an evaluation" : "a control",
-                            hasTessEval ? "control" : "evaluation",
-                            static_cast<unsigned long long>(payload.programHash),
-                            payload.patchControlPoints);
-                }
-                return VK_NULL_HANDLE;
-            }
-        }
-
-        VkGraphicsPipelineCreateInfo gpi{VK_STRUCTURE_TYPE_GRAPHICS_PIPELINE_CREATE_INFO};
-        gpi.stageCount = static_cast<Uint32>(effectiveStages->size());
-        gpi.pStages = effectiveStages->data();
-        gpi.pVertexInputState = payload.vertexInputState;
-        gpi.pInputAssemblyState = &ia;
-        gpi.pTessellationState =
-            payload.topology == VK_PRIMITIVE_TOPOLOGY_PATCH_LIST ? &tessellation : nullptr;
-        gpi.pViewportState = &vpci;
-        gpi.pRasterizationState = &raster;
-        gpi.pMultisampleState = &ms;
-        gpi.pDepthStencilState = &depthStencil;
-        gpi.pColorBlendState = &blend;
-        gpi.pDynamicState = &dynamicState;
-        gpi.layout = payload.pipelineLayout;
-        gpi.renderPass = payload.renderPass;
-        gpi.subpass = payload.subpass;
-
-        VkPipeline pipeline = VK_NULL_HANDLE;
-        const VkResult result = vkCreateGraphicsPipelines(m_device, m_pipelineCache, 1, &gpi, nullptr, &pipeline);
-        // Loud, at MGLOG_F, and deliberately NOT latched. vkCreateGraphicsPipelines refusing a
-        // pipeline MobileGL assembled is a should-never-happen state, and the driver's own
-        // answer is VK_ERROR_UNKNOWN - no information at all - so this dump is the entire
-        // diagnosis. It is not an expected failure mode, so the one-shot rule that quiets W/E
-        // does not apply: while this is reachable it should keep saying so on every draw.
-        // GetOrCreatePipeline deliberately does not cache the failure, which is what makes that
-        // repetition happen; if the repetition ever needs to stop, fix the pipeline, not the log.
-        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);
-            // The driver's own answer is VK_ERROR_UNKNOWN, i.e. no information at all, so the only
-            // way to work out WHICH shader it choked on (the open sampler-array-in-struct
-            // investigation) is to name the modules. MGLOG_I, not _D: this is part of a
-            // should-never-happen report and must survive in the INFO-level builds that CTS
-            // actually runs against, alongside the MGLOG_F lines above.
-            if (payload.stageSpirvDigests) {
-                for (SizeT i = 0; i < payload.stageSpirvDigests->size(); ++i) {
-                    const auto& digest = (*payload.stageSpirvDigests)[i];
-                    MGLOG_I("PipelineFactory::CreatePipeline spirv[%zu]: stage=0x%x words=%u bytes=%zu "
-                            "hash=0x%llx",
-                            i, digest.stage, digest.wordCount,
-                            static_cast<SizeT>(digest.wordCount) * sizeof(Uint32),
-                            static_cast<unsigned long long>(digest.hash));
-                }
-            } else {
-                MGLOG_I("PipelineFactory::CreatePipeline: no SPIR-V digests attached to the payload");
-            }
-            if (payload.stages) {
-                for (SizeT i = 0; i < payload.stages->size(); ++i) {
-                    const auto& stage = (*payload.stages)[i];
-                    // VkShaderModule is a non-dispatchable handle: a pointer on 64-bit but a
-                    // plain uint64_t on 32-bit ABIs, where a cast to const void* is ill-formed
-                    // (broke the armeabi-v7a build). Print it as the 64-bit value it is.
-                    MGLOG_I("PipelineFactory::CreatePipeline stage[%zu]: stage=0x%x module=0x%llx entry=%s "
-                            "specialization=%d",
-                            i, static_cast<Uint32>(stage.stage),
-                            static_cast<unsigned long long>(reinterpret_cast<Uint64>(stage.module)),
-                            stage.pName ? stage.pName : "(null)", stage.pSpecializationInfo ? 1 : 0);
-                }
-            }
-            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

@@ -1,171 +0,0 @@
-// MobileGL - MobileGL/MG_Backend/DirectVulkan/Renderer/PipelineFactory.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 "Config.h"
-#include "../VkIncludes.h"
-#include "MG_State/GLState/FramebufferState/FramebufferObject.h"
-#include <Includes.h>
-
-namespace MobileGL::MG_Backend::DirectVulkan {
-    // Enough of a fingerprint to identify the exact module the driver rejected without keeping the
-    // SPIR-V alive for every program in the cache: a driver that answers VK_ERROR_UNKNOWN tells us
-    // nothing, so the log has to carry the shader's identity itself. Diagnostic only - never part
-    // of any pipeline or program hash.
-    struct ShaderStageSpirvDigest {
-        Uint32 stage = 0; // VkShaderStageFlagBits
-        Uint32 wordCount = 0;
-        Uint64 hash = 0;
-    };
-
-    class PipelineFactory {
-    public:
-        using HashType = Uint64;
-
-        struct PipelineCreatePayload {
-            static constexpr Uint32 kMaxColorAttachments = MG_State::GLState::FramebufferObject::MAX_DRAW_BUFFERS;
-
-            HashType programHash = 0;
-            HashType vertexInputHash = 0;
-            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;
-            // GL_PATCH_VERTICES; only read for a PATCH_LIST topology.
-            Uint32 patchControlPoints = 3;
-            // How many of ARB_viewport_array's viewports this pipeline rasterizes into. 1 for
-            // every program that never assigns gl_ViewportIndex, which is all of them outside the
-            // conformance suite - the wide shape costs a longer vkCmdSetViewport/Scissor per state
-            // change and can cost hardware fast paths, so it is opt-in per program. Baked into the
-            // pipeline (viewportCount is not dynamic without VK_EXT_extended_dynamic_state) and
-            // therefore hashed; the DYNAMIC viewport/scissor arrays the draw pushes must have
-            // exactly this many elements (VUID-vkCmdDraw-viewportCount-03417/-03418).
-            Uint32 viewportCount = 1;
-            VkPolygonMode polygonMode = VK_POLYGON_MODE_FILL;
-            VkCullModeFlags cullMode = VK_CULL_MODE_BACK_BIT;
-            VkFrontFace frontFace = VK_FRONT_FACE_CLOCKWISE;
-            // GL's provoking vertex, baked into the pipeline (VK_EXT_provoking_vertex). It selects
-            // which vertex a flat varying takes AND the vertex order transform feedback records for
-            // strips/fans, so it is part of the pipeline's identity, not dynamic state. Defaults to
-            // Vulkan's own convention, which is what a device without the extension gets.
-            VkProvokingVertexModeEXT provokingVertexMode = VK_PROVOKING_VERTEX_MODE_FIRST_VERTEX_EXT;
-            Bool depthTestEnable = false;
-            Bool depthWriteEnable = false;
-            Bool depthBiasEnable = false;
-            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;
-            // The fragment module writes gl_FragDepth (SPIR-V DepthReplacing); exempts the
-            // pipeline from the blended depth-write quirk (see ShouldSuppressDepthWrite).
-            Bool fragmentReplacesDepth = false;
-            Array<VkPipelineColorBlendAttachmentState, kMaxColorAttachments> colorBlendAttachments{};
-            const Vector<VkPipelineShaderStageCreateInfo>* stages = nullptr;
-            // The tessellation control stage this renderer synthesized for a program that has
-            // an evaluation stage and none of its own (GL 4.6 core 11.2.2 gives such a program a
-            // fixed-function pass-through; Vulkan has no such thing and
-            // VUID-VkGraphicsPipelineCreateInfo-pStages-00730 forbids the half-tessellated
-            // pipeline outright). Appended to `stages` at creation. A null module means the
-            // renderer could not build one, and CreatePipeline refuses the pipeline - the same
-            // refusal it applies when `stages` itself is half-tessellated.
-            //
-            // NOT hashed: it is a pure function of the program and of patchControlPoints, both
-            // of which ComputeHash already mixes in.
-            VkPipelineShaderStageCreateInfo passthroughTessControlStage{};
-            const VkPipelineVertexInputStateCreateInfo* vertexInputState = nullptr;
-            // Diagnostic only; may be null. Read solely from the pipeline-creation failure path.
-            const Vector<ShaderStageSpirvDigest>* stageSpirvDigests = nullptr;
-        };
-
-        explicit PipelineFactory(VkDevice device, const VulkanRendererConfig& config);
-        ~PipelineFactory();
-        PipelineFactory(const PipelineFactory&) = delete;
-
-        HashType ComputeHash(const PipelineCreatePayload& payload) const;
-        VkPipeline GetOrCreatePipeline(const PipelineCreatePayload& payload);
-        void DestroyAll();
-
-        // Frame boundary hook: ages the pipeline cache and destroys long-unused entries
-        // (their command buffers retired many frames ago), mirroring
-        // VkRenderPassManager::OnPresent's sweep. Returns the number of pipelines
-        // destroyed so the caller can drop any memoized VkPipeline handle.
-        Uint32 OnFrameBoundary();
-        // Destroys every cached pipeline hashed on one of `renderPasses`. Only safe
-        // when the caller guarantees GPU idleness for them - the render-pass manager
-        // calls this (via the renderer) for passes its own >1024-boundary-idle sweep
-        // just evicted, and a pipeline hashed on those handles is only ever bound by
-        // draws that also hit the render-pass entries. Also closes the handle-recycling
-        // hazard: a recycled VkRenderPass value must never serve a stale pipeline.
-        // Batched: one cache scan regardless of how many passes died in the sweep.
-        // Returns the number destroyed (callers invalidate memos when non-zero).
-        Uint32 EvictByRenderPasses(const Vector<VkRenderPass>& renderPasses);
-        // Destroys every cached pipeline built from the program with content hash
-        // `programHash`. Called from the ProgramFactory eviction path, which proves the
-        // same >1024-boundary idleness (the program's pipelines are only bound by draws
-        // that stamp its factory entry). Returns the number destroyed.
-        Uint32 EvictByProgramHash(HashType programHash);
-
-        // Driver quirk: suppress depth writes on accumulation-blended pipelines. Multi-pass
-        // depth-equality rendering (a blended prepass writes depth that later passes re-test
-        // with an equality-inclusive compare on the re-rasterized geometry) requires
-        // cross-pipeline position invariance that some mobile compilers do not provide, even
-        // with the SPIR-V Invariant decoration; whole primitives then drop out of the later
-        // passes. Only MIN/MAX extremum blends are stripped - the signature of such a
-        // chain's depth-bounds pass (MC 26.3 OIT), and per a fixture-wide trace sweep the
-        // only depth-writing shape the chain actually uses - so every other blend
-        // (sorted-transparency "over" like vanilla MC water, additive glows, ...) keeps
-        // its depth writes. Set at renderer initialization based on the active driver.
-        static void SetSuppressBlendedDepthWrite(Bool enabled);
-        static Bool IsSuppressBlendedDepthWriteEnabled() { return s_suppressBlendedDepthWrite; }
-        // Device gate for the quirk: ForceOn/ForceOff bypass detection, Auto enables it on
-        // the known-affected vendor (Qualcomm).
-        static Bool ShouldSuppressBlendedDepthWriteForDevice(MG_Config::QuirkOverride quirkOverride,
-                                                             Uint32 vendorId);
-        // Pure per-pipeline strip decision (exempts gl_FragDepth writers, masked-out and
-        // non-accumulation blends); combined with the device flag in CreatePipeline. Static
-        // and payload-only so tests can pin the contract without a VkDevice.
-        static Bool ShouldSuppressDepthWrite(const PipelineCreatePayload& payload);
-
-    private:
-        struct PipelineCacheEntry {
-            VkPipeline pipeline = VK_NULL_HANDLE;
-            // The hashed inputs the eviction paths key on: programHash ties the entry to
-            // its ProgramFactory entry, renderPass records the exact handle the hash
-            // folded in (the hash is one-way, so targeted eviction needs them verbatim).
-            HashType programHash = 0;
-            VkRenderPass renderPass = VK_NULL_HANDLE;
-            // Frame-boundary counter value of the last GetOrCreatePipeline hit; drives
-            // cache eviction (see OnFrameBoundary).
-            Uint64 lastUsedFrame = 0;
-        };
-
-        VkPipeline CreatePipeline(const PipelineCreatePayload& payload) const;
-
-        VkDevice m_device = VK_NULL_HANDLE;
-        const VulkanRendererConfig& m_config;
-        VkPipelineCache m_pipelineCache = VK_NULL_HANDLE;
-        UnorderedMap<HashType, PipelineCacheEntry> m_cache;
-        // Monotonic frame-boundary counter (bumped in OnFrameBoundary) for cache aging.
-        Uint64 m_frameCounter = 0;
-        static inline XXH64_state_t* m_hashState = XXH64_createState();
-        static inline Bool s_suppressBlendedDepthWrite = false;
-    };
-} // namespace MobileGL::MG_Backend::DirectVulkan

MobileGL/MG_Backend/DirectVulkan/Renderer/ProgramFactory.h

@@ -1,558 +0,0 @@
-// MobileGL - MobileGL/MG_Backend/DirectVulkan/Renderer/ProgramFactory.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 "PipelineFactory.h"
-#include "MG_State/GLState/ProgramState/ProgramObject.h"
-#include "MG_State/GLState/ProgramState/ShaderObject.h"
-#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 {
-            None = 0,
-            UniformBufferDynamic,
-            CombinedImageSampler,
-            UniformTexelBuffer,
-            StorageBuffer,
-            StorageImage,
-            // GLSL `imageBuffer` - a buffer texture reached through an IMAGE unit rather than a
-            // texture unit. Vulkan spells it VK_DESCRIPTOR_TYPE_STORAGE_TEXEL_BUFFER, which is a
-            // VkBufferView like UniformTexelBuffer and not a VkImageView like StorageImage: it is
-            // the one image uniform whose descriptor is a buffer. Appended, never inserted -
-            // DescriptorKeyHash mixes the enumerator's value.
-            StorageTexelBuffer
-        };
-
-        enum class CompileOptionBit : Uint {
-            None = 0,
-            PositionYFlip = 1 << 0,
-            PositionZRemap = 1 << 1,
-            SurfaceRotate90 = 1 << 2,
-            SurfaceRotate180 = 1 << 3,
-            SurfaceRotate270 = 1 << 4,
-            // Rewrites the fragment stage's implicit-LOD image samples to explicit LOD 0.
-            // Only ever set for a draw whose every sampler binding is clamped to a single mip
-            // level, which makes the two forms produce identical texels (the implicit lambda is
-            // clamped into [minLod, maxLod] = [0, 0] regardless of derivatives or bias).
-            ExplicitLod0Sampling = 1 << 5,
-            // Decorates the last vertex-processing stage's captured varyings with
-            // XfbBuffer/XfbStride/Offset (VK_EXT_transform_feedback). Set only for draws
-            // recorded while GL transform feedback is active, so plain draws keep the
-            // undecorated variant.
-            XfbCapture = 1 << 6,
-            // Rewrites the fragment stage's gl_FragCoord reads to GL's bottom-left window
-            // origin. Vulkan's gl_FragCoord.y IS the framebuffer row being written, and the
-            // default framebuffer's image is stored in display (top-left) order, so a shader
-            // that reads gl_FragCoord there sees `height - y_GL`. Set together with
-            // PositionYFlip (the two are the same fact about the same draws) except under a
-            // quarter turn, which this renderer does not convert rectangles for either.
-            FragCoordYFlip = 1 << 7,
-            // Replaces the vertex stage's gl_BaseVertex reads with zero. GL defines the builtin
-            // as zero for every drawing command that has no baseVertex parameter - all the
-            // DrawArrays forms - while Vulkan's BaseVertex reports firstVertex there. Set only
-            // for a non-indexed draw whose program actually reads the builtin, so nothing else
-            // acquires a second program/pipeline variant. See ZeroBaseVertexPass.
-            ZeroBaseVertex = 1 << 8,
-        };
-        using CompileOptionFlags = Flags<CompileOptionBit>;
-        using HashType = Uint64;
-
-        struct UpdateAfterBindLimits {
-            Bool enabled = false;
-            Uint32 maxPerStageSamplers = 0;
-            Uint32 maxPerStageUniformBuffers = 0;
-            Uint32 maxPerStageStorageBuffers = 0;
-            Uint32 maxPerStageSampledImages = 0;
-            Uint32 maxPerStageStorageImages = 0;
-            Uint32 maxPerStageResources = 0;
-            Uint32 maxSetSamplers = 0;
-            Uint32 maxSetUniformBuffers = 0;
-            Uint32 maxSetUniformBuffersDynamic = 0;
-            Uint32 maxSetStorageBuffers = 0;
-            Uint32 maxSetStorageBuffersDynamic = 0;
-            Uint32 maxSetSampledImages = 0;
-            Uint32 maxSetStorageImages = 0;
-        };
-
-        struct VkProgramObject {
-            static constexpr Uint32 kMaxVertexInputLocations = 32;
-
-            HashType hash = 0;
-            Vector<VkPipelineShaderStageCreateInfo> stages;
-            Vector<VkShaderModule> modules;
-            // Parallel to stages; identifies the exact module bytes handed to the driver when a
-            // pipeline creation fails. Sixteen bytes per stage instead of keeping the SPIR-V.
-            Vector<ShaderStageSpirvDigest> stageSpirvDigests;
-
-            // Layout data (previously in separate VkProgramLayout)
-            VkDescriptorSetLayout descriptorSetLayout = VK_NULL_HANDLE;
-            // True only when this layout passed every descriptor-indexing feature and
-            // update-after-bind limit gate at reflection time. It controls both the
-            // layout/binding flags and the pool class used by UniformManager.
-            Bool usesUpdateAfterBind = false;
-            VkPipelineLayout pipelineLayout = VK_NULL_HANDLE;
-            Vector<DescriptorBindingKind> bindingKinds;
-            // The bindings this program actually declares, ascending. bindingKinds is sized to the
-            // 256-binding cap while a real GL program uses 1-8, so the per-draw descriptor walk was
-            // scanning 256 slots to find a handful. MUST stay ascending: Vulkan consumes
-            // pDynamicOffsets in binding order and the writer pushes them in iteration order, so an
-            // unordered list would silently mis-pair dynamic offsets with their uniform blocks.
-            Vector<Uint32> activeBindings;
-            Vector<Uint32> dynamicBindings;
-            Vector<Int> uniformBlockIndexByBinding;
-            // Descriptor count per binding (1 except for a descriptor ARRAY - a UBO or storage
-            // block instance array, an image uniform array or a sampler uniform array - each of
-            // which occupies one binding with descriptorCount = N).
-            Vector<Uint16> bindingDescriptorCounts;
-            // Per-element GL uniform block indices for arrayed UBO bindings (count > 1);
-            // element 0 of a non-arrayed binding stays in uniformBlockIndexByBinding.
-            UnorderedMap<Uint32, Vector<Int>> arrayedUniformBlockIndicesByBinding;
-            Vector<String> samplerNameByBinding;
-            Vector<Int> samplerUniformLocationByBinding;
-            Vector<TextureTarget> samplerTextureTargetByBinding;
-            Vector<SamplerNumericDomain> samplerNumericDomainByBinding;
-            // Shared by StorageImage and StorageTexelBuffer bindings: a binding is one kind or
-            // the other, never both, and both need exactly the same thing - the format the
-            // shader declared, so the per-draw resolve can tell a typed declaration from a
-            // formatless one. Kept as one pair rather than two so the move operations below
-            // cannot drift out of sync with a field that only one kind populates.
-            Vector<VkFormat> storageImageFormatByBinding;
-            Vector<Bool> storageImageUsesBindingFormatByBinding;
-            Vector<String> storageBlockNameByBinding;
-            Vector<Int> storageBlockIndexByBinding;
-            // Set once during ReflectLayout so the per-draw path can skip the whole
-            // storage-image preparation for the overwhelming majority of programs.
-            Bool hasStorageImages = false;
-            // Something about this program's descriptors could not be resolved - an opaque
-            // uniform array whose elements have no addressable uniform locations (the
-            // multi-dimensional case), or a binding remap that failed outright. The binding
-            // STAYS DECLARED in the descriptor set layout; declining is done here, by refusing
-            // every draw, and BindProgramUniformBuffers returns false so the draw setup skips
-            // the draw exactly as it does for any other bind failure.
-            //
-            // Keeping the layout intact is the load-bearing half. Shrinking it instead - which
-            // is what the first cut of this did - leaves the shader reading a descriptor the
-            // layout never declared, and lavapipe segfaults on that inside PIPELINE CREATION,
-            // in a JIT worker thread, before any draw runs where a refusal could help. The
-            // reason was logged once at MGLOG_I when the descriptor was declined.
-            Bool declinedDescriptors = false;
-            Int globalUboBinding = -1;
-            Uint32 activeVertexInputLocationMask = 0;
-            Array<GLenum, kMaxVertexInputLocations> vertexInputTypes{};
-            Uint32 activeFragmentOutputLocationMask = 0;
-            Array<GLenum, kMaxVertexInputLocations> fragmentOutputTypes{};
-            ShaderStage rasterizationProducerStage = ShaderStage::Unknown;
-            Uint32 producerOutputComponentCount = 0;
-            Uint32 fragmentInputComponentCount = 0;
-            // The fragment module declares the DepthReplacing execution mode (writes
-            // gl_FragDepth); shader-computed depth is immune to the cross-pipeline
-            // position-invariance quirk (see PipelineFactory::ShouldSuppressDepthWrite).
-            Bool fragmentReplacesDepth = false;
-            // The vertex module declares the BaseVertex builtin. Selects the ZeroBaseVertex
-            // program variant for non-indexed draws, and is deliberately a property of the
-            // PROGRAM rather than of the variant: the zeroed variant leaves the variable
-            // declared, so both variants answer the same and the draw path can ask either.
-            Bool readsBaseVertexBuiltin = false;
-            // Some pre-rasterization stage assigns gl_ViewportIndex. Its pipeline declares
-            // viewportCount = the renderer's rasterizable viewport count instead of 1, and its
-            // draws push the whole viewport/scissor array; every other program keeps the
-            // single-viewport fast path untouched. Part of the program's identity (folded into
-            // the pipeline hash through programHash), so no memo can serve the wrong shape.
-            Bool writesViewportIndexBuiltin = false;
-            // This program has a tessellation EVALUATION stage and no tessellation CONTROL
-            // stage. GL allows that (4.6 core 11.2.2: with no control shader the input patch
-            // is passed through unmodified, the output patch size is PATCH_VERTICES, and the
-            // levels come from the PATCH_DEFAULT_*_LEVEL state); Vulkan does not - either both
-            // tessellation stages are present or neither
-            // (VUID-VkGraphicsPipelineCreateInfo-pStages-00730). So the draw path has to supply
-            // the pass-through stage GL describes; see GetOrCreatePassthroughTessControlStage.
-            Bool needsPassthroughTessControl = false;
-            // ...and the pass-through this renderer can synthesize carries gl_Position and
-            // nothing else, so it is only correct when the evaluation stage's inputs are
-            // built-ins. A user-defined varying would arrive at the evaluation stage
-            // UNWRITTEN once a control stage sits between it and the vertex stage, which is
-            // silently wrong pixels rather than a crash - so those programs are declined
-            // instead (PipelineFactory::CreatePipeline refuses the pipeline and the draw is
-            // skipped). See ReflectPassthroughTessControlNeed.
-            Bool passthroughTessControlEmulatable = false;
-            // Frame-boundary counter value of the last GetOrCreateProgram hit; drives
-            // cache eviction (see OnFrameBoundary). Mutable: the draw snapshot's memoised
-            // entry pointer re-stamps use through a const reference (StampProgramUse).
-            mutable Uint64 lastUsedFrame = 0;
-
-            static inline VkDevice s_device = VK_NULL_HANDLE;
-
-            VkProgramObject() = default;
-            VkProgramObject(const VkProgramObject&) = delete;
-            VkProgramObject& operator=(const VkProgramObject&) = delete;
-            VkProgramObject(VkProgramObject&& other) noexcept {
-                hash = other.hash;
-                stages = std::move(other.stages);
-                modules = std::move(other.modules);
-                // Must travel with `modules`: these digests name the SPIR-V those exact
-                // shader modules were built from, and the pipeline-failure diagnostics
-                // print the two together. Leaving it behind used to merely lose the
-                // digests on a rehash; now that the cache is a robin-hood table, insertion
-                // SWAPS two entries, and a field that no move touches stays behind in the
-                // slot - pairing one program's modules with another program's digests, so
-                // a pipeline failure would be reported against the wrong SPIR-V.
-                stageSpirvDigests = std::move(other.stageSpirvDigests);
-                descriptorSetLayout = other.descriptorSetLayout;
-                usesUpdateAfterBind = other.usesUpdateAfterBind;
-                pipelineLayout = other.pipelineLayout;
-                bindingKinds = std::move(other.bindingKinds);
-                activeBindings = std::move(other.activeBindings);
-                dynamicBindings = std::move(other.dynamicBindings);
-                uniformBlockIndexByBinding = std::move(other.uniformBlockIndexByBinding);
-                bindingDescriptorCounts = std::move(other.bindingDescriptorCounts);
-                arrayedUniformBlockIndicesByBinding = std::move(other.arrayedUniformBlockIndicesByBinding);
-                samplerNameByBinding = std::move(other.samplerNameByBinding);
-                samplerUniformLocationByBinding = std::move(other.samplerUniformLocationByBinding);
-                samplerTextureTargetByBinding = std::move(other.samplerTextureTargetByBinding);
-                samplerNumericDomainByBinding = std::move(other.samplerNumericDomainByBinding);
-                storageImageFormatByBinding = std::move(other.storageImageFormatByBinding);
-                storageImageUsesBindingFormatByBinding =
-                    std::move(other.storageImageUsesBindingFormatByBinding);
-                storageBlockNameByBinding = std::move(other.storageBlockNameByBinding);
-                storageBlockIndexByBinding = std::move(other.storageBlockIndexByBinding);
-                hasStorageImages = other.hasStorageImages;
-                declinedDescriptors = other.declinedDescriptors;
-                globalUboBinding = other.globalUboBinding;
-                activeVertexInputLocationMask = other.activeVertexInputLocationMask;
-                vertexInputTypes = other.vertexInputTypes;
-                activeFragmentOutputLocationMask = other.activeFragmentOutputLocationMask;
-                fragmentOutputTypes = other.fragmentOutputTypes;
-                rasterizationProducerStage = other.rasterizationProducerStage;
-                producerOutputComponentCount = other.producerOutputComponentCount;
-                fragmentInputComponentCount = other.fragmentInputComponentCount;
-                fragmentReplacesDepth = other.fragmentReplacesDepth;
-                readsBaseVertexBuiltin = other.readsBaseVertexBuiltin;
-                writesViewportIndexBuiltin = other.writesViewportIndexBuiltin;
-                needsPassthroughTessControl = other.needsPassthroughTessControl;
-                passthroughTessControlEmulatable = other.passthroughTessControlEmulatable;
-                lastUsedFrame = other.lastUsedFrame;
-                other.hash = 0;
-                other.descriptorSetLayout = VK_NULL_HANDLE;
-                other.usesUpdateAfterBind = false;
-                other.pipelineLayout = VK_NULL_HANDLE;
-                other.hasStorageImages = false;
-                other.declinedDescriptors = false;
-                other.globalUboBinding = -1;
-                other.activeVertexInputLocationMask = 0;
-                other.activeFragmentOutputLocationMask = 0;
-                other.rasterizationProducerStage = ShaderStage::Unknown;
-                other.producerOutputComponentCount = 0;
-                other.fragmentInputComponentCount = 0;
-                other.fragmentReplacesDepth = false;
-                other.readsBaseVertexBuiltin = false;
-                other.writesViewportIndexBuiltin = false;
-                other.needsPassthroughTessControl = false;
-                other.passthroughTessControlEmulatable = false;
-                other.lastUsedFrame = 0;
-            }
-            VkProgramObject& operator=(VkProgramObject&& other) noexcept {
-                if (this == &other) {
-                    return *this;
-                }
-                Destroy();
-                hash = other.hash;
-                stages = std::move(other.stages);
-                modules = std::move(other.modules);
-                stageSpirvDigests = std::move(other.stageSpirvDigests); // travels with `modules` - see the move ctor
-                descriptorSetLayout = other.descriptorSetLayout;
-                usesUpdateAfterBind = other.usesUpdateAfterBind;
-                pipelineLayout = other.pipelineLayout;
-                bindingKinds = std::move(other.bindingKinds);
-                activeBindings = std::move(other.activeBindings);
-                dynamicBindings = std::move(other.dynamicBindings);
-                uniformBlockIndexByBinding = std::move(other.uniformBlockIndexByBinding);
-                bindingDescriptorCounts = std::move(other.bindingDescriptorCounts);
-                arrayedUniformBlockIndicesByBinding = std::move(other.arrayedUniformBlockIndicesByBinding);
-                samplerNameByBinding = std::move(other.samplerNameByBinding);
-                samplerUniformLocationByBinding = std::move(other.samplerUniformLocationByBinding);
-                samplerTextureTargetByBinding = std::move(other.samplerTextureTargetByBinding);
-                samplerNumericDomainByBinding = std::move(other.samplerNumericDomainByBinding);
-                storageImageFormatByBinding = std::move(other.storageImageFormatByBinding);
-                storageImageUsesBindingFormatByBinding =
-                    std::move(other.storageImageUsesBindingFormatByBinding);
-                storageBlockNameByBinding = std::move(other.storageBlockNameByBinding);
-                storageBlockIndexByBinding = std::move(other.storageBlockIndexByBinding);
-                hasStorageImages = other.hasStorageImages;
-                declinedDescriptors = other.declinedDescriptors;
-                globalUboBinding = other.globalUboBinding;
-                activeVertexInputLocationMask = other.activeVertexInputLocationMask;
-                vertexInputTypes = other.vertexInputTypes;
-                activeFragmentOutputLocationMask = other.activeFragmentOutputLocationMask;
-                fragmentOutputTypes = other.fragmentOutputTypes;
-                rasterizationProducerStage = other.rasterizationProducerStage;
-                producerOutputComponentCount = other.producerOutputComponentCount;
-                fragmentInputComponentCount = other.fragmentInputComponentCount;
-                fragmentReplacesDepth = other.fragmentReplacesDepth;
-                readsBaseVertexBuiltin = other.readsBaseVertexBuiltin;
-                writesViewportIndexBuiltin = other.writesViewportIndexBuiltin;
-                needsPassthroughTessControl = other.needsPassthroughTessControl;
-                passthroughTessControlEmulatable = other.passthroughTessControlEmulatable;
-                lastUsedFrame = other.lastUsedFrame;
-                other.hash = 0;
-                other.descriptorSetLayout = VK_NULL_HANDLE;
-                other.usesUpdateAfterBind = false;
-                other.pipelineLayout = VK_NULL_HANDLE;
-                other.hasStorageImages = false;
-                other.declinedDescriptors = false;
-                other.globalUboBinding = -1;
-                other.activeVertexInputLocationMask = 0;
-                other.activeFragmentOutputLocationMask = 0;
-                other.rasterizationProducerStage = ShaderStage::Unknown;
-                other.producerOutputComponentCount = 0;
-                other.fragmentInputComponentCount = 0;
-                other.fragmentReplacesDepth = false;
-                other.readsBaseVertexBuiltin = false;
-                other.writesViewportIndexBuiltin = false;
-                other.needsPassthroughTessControl = false;
-                other.passthroughTessControlEmulatable = false;
-                other.lastUsedFrame = 0;
-                return *this;
-            }
-
-            ~VkProgramObject() {
-                Destroy();
-            }
-
-        private:
-            void Destroy() {
-                if (s_device != VK_NULL_HANDLE) {
-                    if (pipelineLayout != VK_NULL_HANDLE) {
-                        vkDestroyPipelineLayout(s_device, pipelineLayout, nullptr);
-                        pipelineLayout = VK_NULL_HANDLE;
-                    }
-                    if (descriptorSetLayout != VK_NULL_HANDLE) {
-                        vkDestroyDescriptorSetLayout(s_device, descriptorSetLayout, nullptr);
-                        descriptorSetLayout = VK_NULL_HANDLE;
-                    }
-                    for (auto module : modules) {
-                        if (module != VK_NULL_HANDLE) {
-                            vkDestroyShaderModule(s_device, module, nullptr);
-                        }
-                    }
-                }
-                modules.clear();
-                stages.clear();
-                stageSpirvDigests.clear(); // the modules they describe are gone
-            }
-        };
-
-        // Notified when the OnFrameBoundary sweep destroys an aged-out cache entry,
-        // carrying the entry's content hash and the VkDescriptorSetLayout it owned.
-        // Dependent caches (compute pipelines, PipelineFactory entries, UniformManager's
-        // per-layout descriptor sets) must purge in the same step: after vkDestroy the
-        // layout handle value may be recycled for an unrelated layout, and the program
-        // hash may be re-inserted by a later rebuild of the same content.
-        class IEvictionObserver {
-        public:
-            virtual ~IEvictionObserver() = default;
-            virtual void OnProgramEvicted(HashType programHash, VkDescriptorSetLayout descriptorSetLayout) = 0;
-        };
-
-        // How this factory's compute modules implement GL_KHR_shader_subgroup. Computed
-        // once at renderer initialization (SubgroupSupportPolicy.h + the device's
-        // subgroup properties) so lowering can never disagree with the advertised
-        // capabilities. Native subgroup operations always execute natively; the two
-        // repair passes patch modules AROUND them, and the emulation only replaces them
-        // on opted-in devices with no subgroup support at all.
-        struct SubgroupLoweringPolicy {
-            Bool emulateSubgroups = false;      // MOBILEGL_MAGMA_EMULATE_SUBGROUP, no-native-support devices
-            Bool fixIterationRPSubgroupScratch = false; // patch iterationRP's under-declared scratch
-            Bool fixIterationRPBarrier = false; // repair Program 203's shared-scratch race
-            Bool deriveNumSubgroups = false;    // repair the NumSubgroups builtin
-            Bool requireFullSubgroups = false;  // computeFullSubgroups enabled on the device
-            Uint32 nativeSubgroupSize = 0;
-            // Full-subgroup launches are bounded by this device limit; a dispatch whose
-            // workgroup needs more subgroups than this cannot request the flag.
-            Uint32 maxComputeWorkgroupSubgroups = 0;
-            // VkPhysicalDeviceLimits::maxComputeSharedMemorySize; bounds the scratch the
-            // emulation pass may add (0 falls back to the Vulkan minimum, 16384).
-            Uint32 maxComputeSharedMemoryBytes = 0;
-        };
-
-        explicit ProgramFactory(VkDevice device, const VulkanRendererConfig& config, Uint32 maxBindings,
-                                Bool shaderDrawParametersEnabled,
-                                Bool unformattedFloatStorageImagesEnabled,
-                                Bool enableSpirvValidation,
-                                UpdateAfterBindLimits updateAfterBindLimits,
-                                SubgroupLoweringPolicy subgroupPolicy)
-            : m_device(device), m_maxBindings(maxBindings), m_config(config),
-              m_shaderDrawParametersEnabled(shaderDrawParametersEnabled),
-              m_unformattedFloatStorageImagesEnabled(unformattedFloatStorageImagesEnabled),
-              m_enableSpirvValidation(enableSpirvValidation),
-              m_updateAfterBindLimits(updateAfterBindLimits),
-              m_subgroupPolicy(subgroupPolicy) {
-            VkProgramObject::s_device = device;
-        }
-        // Destroys the pass-through tessellation control modules. Runs while the device is
-        // still alive for the same reason ~VkProgramObject's does: this factory outlives
-        // nothing that owns the device.
-        ~ProgramFactory();
-        ProgramFactory(const ProgramFactory&) = delete;
-
-        HashType ComputeHash(const MG_State::GLState::ProgramObject& program, CompileOptionFlags flags) const;
-        const VkProgramObject& GetOrCreateProgram(
-            const MG_State::GLState::ProgramObject& program, CompileOptionFlags flags);
-
-        // The default framebuffer's current image height, baked as a literal into every
-        // FragCoordYFlip variant (there is no push-constant or specialization channel here, and
-        // adding one for a value that changes only on swapchain recreation would cost the draw
-        // path more than a recompile costs a resize). It is therefore part of those variants'
-        // identity: ComputeHash mixes it in when the bit is set, so a height change re-keys them
-        // and leaves every other program's hash untouched. Setting a NEW height also bumps the
-        // cache-structure epoch, because a caller holding a memoised VkProgramObject* would
-        // otherwise keep using a module compiled against the old height.
-        void SetDefaultFramebufferHeight(Uint32 height);
-        Uint32 GetDefaultFramebufferHeight() const { return m_defaultFramebufferHeight; }
-
-        // Bumped whenever m_cache's STRUCTURE changes (any insert or erase): the cache is
-        // an open-addressing map holding entries by value, so both moves existing entries.
-        // A caller that memoised a VkProgramObject* may keep dereferencing it only while
-        // this is unchanged; on a bump it must re-run GetOrCreateProgram.
-        Uint64 GetCacheStructureEpoch() const { return m_cacheStructureEpoch; }
-        // A memoised entry pointer bypasses GetOrCreateProgram, whose per-lookup stamp is
-        // what keeps an in-use entry out of OnFrameBoundary's idle sweep - so such a
-        // caller must re-stamp the entry itself, at least once per frame boundary.
-        void StampProgramUse(const VkProgramObject& entry) const { entry.lastUsedFrame = m_frameCounter; }
-
-        // Observer may be null (no notifications). Not owned.
-        void SetEvictionObserver(IEvictionObserver* observer) { m_evictionObserver = observer; }
-        // Frame boundary hook: ages the program cache and evicts long-unused entries
-        // (their command buffers retired many frames ago), mirroring
-        // VkRenderPassManager::OnPresent's sweep.
-        void OnFrameBoundary();
-
-        static VkShaderStageFlagBits ToVkStage(ShaderStage stage);
-        static VkFormat ConvertSpirvImageFormatToVkFormat(SpvImageFormat format);
-        static SamplerNumericDomain UniformTypeToSamplerNumericDomain(GLenum glType);
-        // True when any entry point declares the DepthReplacing execution mode, i.e. the
-        // shader assigns gl_FragDepth. Exposed so the blended depth-write quirk's exemption
-        // can be pinned by tests. A false negative loses the exemption, so such a shader is
-        // stripped conservatively and forfeits its depth write.
-        static Bool ReflectedFragmentReplacesDepth(const SpvReflectShaderModule& reflectModule);
-        // True when an entry point reads the InstanceIndex builtin. Only gates a diagnostic:
-        // without shaderDrawParameters such a shader cannot have gl_InstanceID rebased.
-        static Bool ReflectedReadsInstanceIndexBuiltin(const SpvReflectShaderModule& reflectModule);
-        // True when an entry point declares the BaseVertex builtin, i.e. when a non-indexed
-        // draw with this program has to take the ZeroBaseVertex variant.
-        static Bool ReflectedReadsBaseVertexBuiltin(const SpvReflectShaderModule& reflectModule);
-        // Shared by the two above: does any entry point list an input variable decorated with
-        // this builtin?
-        static Bool ReflectedDeclaresInputBuiltin(const SpvReflectShaderModule& reflectModule, SpvBuiltIn builtin);
-        // True when an entry point writes the ViewportIndex builtin (gl_ViewportIndex), i.e. when
-        // the program can route primitives to a viewport other than 0 and its pipeline therefore
-        // has to declare more than one. Asks about OUTPUT variables because that is the direction
-        // a pre-rasterization stage declares it in.
-        static Bool ReflectedWritesViewportIndexBuiltin(const SpvReflectShaderModule& reflectModule);
-        static Bool ReflectedDeclaresOutputBuiltin(const SpvReflectShaderModule& reflectModule, SpvBuiltIn builtin);
-
-        // The pass-through tessellation control stage GL 4.6 core 11.2.2 describes for a
-        // program that has an evaluation stage and no control stage, for an input patch of
-        // `patchVertices` control points. Returned BY VALUE (a stage description is a POD, and
-        // the cache below is a rehashing map, so a pointer into it would not survive the next
-        // distinct patch size). `.module == VK_NULL_HANDLE` means the stage could not be built:
-        // the caller then has no control stage to inject, and CreatePipeline refuses the
-        // pipeline rather than handing the driver a half-tessellated one.
-        //
-        // Keyed on the patch size because GL takes the output patch size from PATCH_VERTICES,
-        // which is draw state, not link state - the CTS case that motivated this links at the
-        // default 3 and draws at 4. The pipeline cache already re-keys on patchControlPoints,
-        // so the module a pipeline was built with is part of that pipeline's identity.
-        // Compiling is bounded by the number of distinct patch sizes a program draws with
-        // (MAX_PATCH_VERTICES = 32 in the worst case, one or two in practice) and only ever
-        // happens for the rare program that has no control stage at all.
-        VkPipelineShaderStageCreateInfo GetOrCreatePassthroughTessControlStage(Uint32 patchVertices);
-
-        // Source of the module above. Exposed for tests: the generated GLSL is the whole
-        // contract with the evaluation stage, so it is worth pinning independently of a device.
-        static String BuildPassthroughTessControlSource(Uint32 patchVertices);
-
-    private:
-        struct ProgramLookupCache {
-            const MG_State::GLState::ProgramObject* program = nullptr;
-            Uint32 backendStateVersion = 0;
-            CompileOptionFlags flags{};
-            HashType hash = 0;
-        };
-
-        static TextureTarget UniformTypeToTextureTarget(GLenum glType);
-        // `stages` is ALWAYS ProgramObject::GetLinkedShaderStages() - one entry per module of
-        // `spirv`, at the same index. Taking the stages rather than the shader objects is what
-        // keeps the program's live attach list, which is a longer and differently-indexed list
-        // the moment a glAttachShader lands after the link, from being passed here by mistake.
-        void ReflectVertexInputs(const Vector<ShaderStage>& stages,
-                     const Vector<Vector<Uint>>& spirv,
-                     VkProgramObject& entry) const;
-        void ReflectViewportIndexUsage(const Vector<ShaderStage>& stages,
-                                       const Vector<Vector<Uint>>& spirv,
-                                       VkProgramObject& entry) const;
-        void ReflectFragmentOutputs(const Vector<ShaderStage>& stages,
-                        const Vector<Vector<Uint>>& spirv,
-                        VkProgramObject& entry) const;
-        void ReflectLayout(const MG_State::GLState::ProgramObject& program, const Vector<Vector<Uint>>& spirv,
-                           VkProgramObject& entry) const;
-        // Fills needsPassthroughTessControl / passthroughTessControlEmulatable off the linked
-        // modules. Const and reflection-only: it decides nothing about the pipeline, it only
-        // records what the evaluation stage's input interface is made of.
-        void ReflectPassthroughTessControlNeed(const Vector<ShaderStage>& stages,
-                                               const Vector<Vector<Uint>>& spirv,
-                                               VkProgramObject& entry) const;
-
-        VkDevice m_device = VK_NULL_HANDLE;
-        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;
-        // Startup snapshot used only by internally synthesized shader modules, which do not
-        // originate from a ProgramLinkTask.
-        Bool m_enableSpirvValidation = false;
-        // Device feature and limit gate resolved before vkCreateDevice. Keeping it in
-        // the factory lets each reflected layout choose ordinary descriptors when its
-        // own counts would exceed the update-after-bind budget.
-        UpdateAfterBindLimits m_updateAfterBindLimits{};
-        SubgroupLoweringPolicy m_subgroupPolicy{};
-        // See SetDefaultFramebufferHeight. 0 means "not known yet"; the FragCoordYFlip bit is
-        // never set before the swapchain exists, so no variant can be compiled against it.
-        Uint32 m_defaultFramebufferHeight = 0;
-        mutable ProgramLookupCache m_lastLookup;
-        // Monotonic frame-boundary counter (bumped in OnFrameBoundary) for cache aging.
-        Uint64 m_frameCounter = 0;
-        // See GetCacheStructureEpoch(). Starts at 1 so a zero-initialized memo can never match.
-        Uint64 m_cacheStructureEpoch = 1;
-        IEvictionObserver* m_evictionObserver = nullptr;
-        // Pass-through tessellation control stages by input patch size. Never evicted: at most
-        // MAX_PATCH_VERTICES entries exist for the lifetime of the device, and every pipeline
-        // ever built from one keeps referencing its module. A failed build is cached as
-        // VK_NULL_HANDLE so a broken generator costs one compile, not one per draw.
-        UnorderedMap<Uint32, VkPipelineShaderStageCreateInfo> m_passthroughTessControlStages;
-        static inline XXH64_state_t* m_hashState = XXH64_createState();
-    };
-} // namespace MobileGL::MG_Backend::DirectVulkan

MobileGL/MG_Backend/DirectVulkan/Renderer/SwapchainObject.cpp

@@ -1,533 +0,0 @@
-// MobileGL - MobileGL/MG_Backend/DirectVulkan/Renderer/SwapchainObject.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 "SwapchainObject.h"
-
-#include "MG_Impl/GLImpl/Framebuffer/GL_Framebuffer.h"
-#include "MG_State/GLState/TextureState/TextureObject2D.h"
-
-#if defined(__has_include)
-#if __has_include(<vulkan/vk_enum_string_helper.h>)
-#include <vulkan/vk_enum_string_helper.h>
-#define MOBILEGL_HAS_VK_ENUM_STRING_HELPER 1
-#else
-#define MOBILEGL_HAS_VK_ENUM_STRING_HELPER 0
-#endif
-#else
-#define MOBILEGL_HAS_VK_ENUM_STRING_HELPER 0
-#endif
-
-#if !MOBILEGL_HAS_VK_ENUM_STRING_HELPER
-static const char* string_VkFormat(VkFormat) {
-    return "VkFormat(unknown)";
-}
-
-static const char* string_VkColorSpaceKHR(VkColorSpaceKHR) {
-    return "VkColorSpaceKHR(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) {
-    return "VkSurfaceTransformFlagBitsKHR(unknown)";
-}
-#endif
-
-namespace MobileGL::MG_Backend::DirectVulkan {
-    namespace {
-        Bool HasStencilComponent(VkFormat format) {
-            return format == VK_FORMAT_D24_UNORM_S8_UINT || format == VK_FORMAT_D32_SFLOAT_S8_UINT;
-        }
-
-        VkFormat FindSupportedDepthStencilFormat(VkPhysicalDevice physicalDevice) {
-            const VkFormat candidates[] = {VK_FORMAT_D24_UNORM_S8_UINT, VK_FORMAT_D32_SFLOAT_S8_UINT,
-                                           VK_FORMAT_D32_SFLOAT};
-            for (VkFormat format : candidates) {
-                VkFormatProperties props{};
-                vkGetPhysicalDeviceFormatProperties(physicalDevice, format, &props);
-                if ((props.optimalTilingFeatures & VK_FORMAT_FEATURE_DEPTH_STENCIL_ATTACHMENT_BIT) != 0) {
-                    return format;
-                }
-            }
-            return VK_FORMAT_UNDEFINED;
-        }
-
-        Uint32 FindMemoryType(VkPhysicalDevice physicalDevice, Uint32 typeFilter, VkMemoryPropertyFlags properties) {
-            VkPhysicalDeviceMemoryProperties memProperties{};
-            vkGetPhysicalDeviceMemoryProperties(physicalDevice, &memProperties);
-
-            for (Uint32 i = 0; i < memProperties.memoryTypeCount; i++) {
-                if ((typeFilter & (1 << i)) &&
-                    (memProperties.memoryTypes[i].propertyFlags & properties) == properties) {
-                    return i;
-                }
-            }
-
-            MOBILEGL_ASSERT(false, "Failed to find suitable memory type.");
-            return 0;
-        }
-    } // namespace
-
-    SwapchainObject::SwapchainCapabilities SwapchainObject::GetSwapchainCapabilities(VkPhysicalDevice physicalDevice,
-                                                                                      VkSurfaceKHR surface) {
-        SwapchainCapabilities swapchainCapabilities{};
-
-        VK_VERIFY(
-            vkGetPhysicalDeviceSurfaceCapabilitiesKHR(physicalDevice, surface, &swapchainCapabilities.capabilities));
-
-        Uint32 formatCount = 0;
-        VK_VERIFY(vkGetPhysicalDeviceSurfaceFormatsKHR(physicalDevice, surface, &formatCount, nullptr));
-        if (formatCount != 0) {
-            swapchainCapabilities.surfaceFormats.resize(formatCount);
-            VK_VERIFY(vkGetPhysicalDeviceSurfaceFormatsKHR(
-                physicalDevice, surface, &formatCount, swapchainCapabilities.surfaceFormats.data()));
-        }
-
-        Uint32 presentModeCount = 0;
-        VK_VERIFY(
-            vkGetPhysicalDeviceSurfacePresentModesKHR(physicalDevice, surface, &presentModeCount, nullptr));
-        if (presentModeCount != 0) {
-            swapchainCapabilities.presentModes.resize(presentModeCount);
-            VK_VERIFY(vkGetPhysicalDeviceSurfacePresentModesKHR(
-                physicalDevice, surface, &presentModeCount, swapchainCapabilities.presentModes.data()));
-        }
-
-        return swapchainCapabilities;
-    }
-
-    VkSurfaceFormatKHR SwapchainObject::ChooseSwapchainSurfaceFormat(
-        const Vector<VkSurfaceFormatKHR>& availableFormats) {
-        for (const auto& availableFormat : availableFormats) {
-            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;
-            }
-        }
-
-        // TODO: Properly rank other formats
-        return availableFormats[0];
-    }
-
-    VkPresentModeKHR SwapchainObject::ChooseSwapchainPresentMode(
-        const Vector<VkPresentModeKHR>& availablePresentModes) {
-        for (auto desiredPresentMode : s_desiredPresentModes) {
-            for (const auto& presentMode : availablePresentModes) {
-                if (presentMode == desiredPresentMode) {
-                    return presentMode;
-                }
-            }
-        }
-
-        // TODO: Properly rank other modes
-        return availablePresentModes[0];
-    }
-
-    void SwapchainObject::Create(VkDevice device, VkPhysicalDevice physicalDevice, VkSurfaceKHR surface,
-                                 Uint32 graphicsQueueFamily, Uint32 presentQueueFamily, Uint32 minImageCountHint,
-                                 VkExtent2D desiredExtent) {
-        const auto swapchainCapabilities = GetSwapchainCapabilities(physicalDevice, surface);
-        MOBILEGL_ASSERT(swapchainCapabilities.IsComplete(),
-                        "SwapchainObject::Create failed: incomplete swapchain capabilities");
-
-        MGLOG_I("Got %d surface formats:", swapchainCapabilities.surfaceFormats.size());
-        for (const auto& sf : swapchainCapabilities.surfaceFormats) {
-            MGLOG_D("    [%s, %s]", string_VkFormat(sf.format), string_VkColorSpaceKHR(sf.colorSpace));
-        }
-
-        const auto pickedSurfaceFormat = ChooseSwapchainSurfaceFormat(swapchainCapabilities.surfaceFormats);
-        MGLOG_I("Picked surface format: [%s, %s]", string_VkFormat(pickedSurfaceFormat.format),
-                string_VkColorSpaceKHR(pickedSurfaceFormat.colorSpace));
-
-        MGLOG_I("Got %d present modes:", swapchainCapabilities.presentModes.size());
-        for (const auto& pm : swapchainCapabilities.presentModes) {
-            MGLOG_D("    %s", string_VkPresentModeKHR(pm));
-        }
-
-        const auto presentMode = ChooseSwapchainPresentMode(swapchainCapabilities.presentModes);
-        MGLOG_I("Picked present mode: %s", string_VkPresentModeKHR(presentMode));
-
-        const auto& swapchainCaps = swapchainCapabilities.capabilities;
-        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));
-
-        VkSwapchainCreateInfoKHR createInfo{VK_STRUCTURE_TYPE_SWAPCHAIN_CREATE_INFO_KHR};
-        createInfo.surface = surface;
-        createInfo.minImageCount = targetImageCount;
-        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);
-        }
-
-        createInfo.imageArrayLayers = 1;
-        const VkImageUsageFlags requiredImageUsage =
-            VK_IMAGE_USAGE_COLOR_ATTACHMENT_BIT | VK_IMAGE_USAGE_TRANSFER_DST_BIT;
-        MOBILEGL_ASSERT((swapchainCaps.supportedUsageFlags & requiredImageUsage) == requiredImageUsage,
-                        "Swapchain does not support required usage flags (COLOR_ATTACHMENT | TRANSFER_DST). "
-                        "supportedUsageFlags=0x%x",
-                        static_cast<Uint32>(swapchainCaps.supportedUsageFlags));
-
-        VkImageUsageFlags imageUsage = requiredImageUsage;
-        if ((swapchainCaps.supportedUsageFlags & VK_IMAGE_USAGE_TRANSFER_SRC_BIT) != 0) {
-            imageUsage |= VK_IMAGE_USAGE_TRANSFER_SRC_BIT;
-        }
-        createInfo.imageUsage = imageUsage;
-        MGLOG_I("Swapchain imageUsage = 0x%x (supportedUsageFlags = 0x%x)", static_cast<Uint32>(createInfo.imageUsage),
-                static_cast<Uint32>(swapchainCaps.supportedUsageFlags));
-        Uint32 queueFamilyIndices[] = {graphicsQueueFamily, presentQueueFamily};
-        if (graphicsQueueFamily != presentQueueFamily) {
-            createInfo.imageSharingMode = VK_SHARING_MODE_CONCURRENT;
-            createInfo.queueFamilyIndexCount = 2;
-            createInfo.pQueueFamilyIndices = queueFamilyIndices;
-        } else {
-            createInfo.imageSharingMode = VK_SHARING_MODE_EXCLUSIVE;
-            createInfo.queueFamilyIndexCount = 0;
-            createInfo.pQueueFamilyIndices = nullptr;
-        }
-        createInfo.preTransform = swapchainCaps.currentTransform;
-        MGLOG_I("Set swapchain preTransform = %s", string_VkSurfaceTransformFlagBitsKHR(createInfo.preTransform));
-        const VkCompositeAlphaFlagBitsKHR compositeAlphaCandidates[] = {
-            VK_COMPOSITE_ALPHA_OPAQUE_BIT_KHR,
-            VK_COMPOSITE_ALPHA_PRE_MULTIPLIED_BIT_KHR,
-            VK_COMPOSITE_ALPHA_POST_MULTIPLIED_BIT_KHR,
-            VK_COMPOSITE_ALPHA_INHERIT_BIT_KHR
-        };
-        createInfo.compositeAlpha = VK_COMPOSITE_ALPHA_OPAQUE_BIT_KHR;
-        for (auto candidate : compositeAlphaCandidates) {
-            if ((swapchainCaps.supportedCompositeAlpha & candidate) != 0) {
-                createInfo.compositeAlpha = candidate;
-                break;
-            }
-        }
-        createInfo.presentMode = presentMode;
-        createInfo.clipped = VK_TRUE;
-        createInfo.oldSwapchain = VK_NULL_HANDLE;
-
-        m_surfaceFormat = {createInfo.imageFormat, createInfo.imageColorSpace};
-        m_extent = createInfo.imageExtent;
-        // The surface-space extent this swapchain was built from, i.e. before the
-        // quarter-turn swap above. Out-of-date checks must compare in THIS space: comparing a
-        // freshly queried currentExtent against the swapped m_extent flips axes every rotation
-        // and makes the comparison alternate forever.
-        m_surfaceExtent = defaultFramebufferExtent;
-        m_preTransform = createInfo.preTransform;
-
-        VK_VERIFY(vkCreateSwapchainKHR(device, &createInfo, nullptr, &m_swapchain));
-
-        Uint32 imageCount = 0;
-        VK_VERIFY(vkGetSwapchainImagesKHR(device, m_swapchain, &imageCount, nullptr));
-
-        m_images.resize(imageCount, VK_NULL_HANDLE);
-        VK_VERIFY(vkGetSwapchainImagesKHR(device, m_swapchain, &imageCount, m_images.data()));
-        m_imageLayouts.assign(imageCount, VK_IMAGE_LAYOUT_UNDEFINED);
-        // Fresh swapchain images hold garbage until a render pass stores into them.
-        m_imageContentDefined.assign(imageCount, false);
-        m_depthStencilContentDefined.assign(imageCount, false);
-
-        CreateImageViews(device);
-        CreateDepthStencilResources(device, physicalDevice);
-
-        MGLOG_I("Swapchain created, extent = %dx%d, swapchain imageCount = %d", m_extent.width, m_extent.height,
-                imageCount);
-
-        // 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, {
-                {extentWidth, extentHeight, 1},
-                defaultAttachmentByteSize}); // TODO: 4 is format size
-        TextureInternalFormat depthFormat = TextureInternalFormat::Depth24Stencil8;
-        switch (m_depthStencilFormat) {
-            case VK_FORMAT_D24_UNORM_S8_UINT:
-                depthFormat = TextureInternalFormat::Depth24Stencil8;
-                break;
-            case VK_FORMAT_D32_SFLOAT_S8_UINT:
-                depthFormat = TextureInternalFormat::Depth32FStencil8;
-                break;
-            case VK_FORMAT_D32_SFLOAT:
-                depthFormat = TextureInternalFormat::DepthComponent32F;
-                break;
-            default:
-                depthFormat = TextureInternalFormat::Depth24Stencil8;
-                break;
-        }
-        auto* depthTex = static_cast<MG_State::GLState::TextureObject2D*>(defaultFBOInfo->depthAttachment.get());
-        depthTex->SetInternalFormat(depthFormat);
-        depthTex->AllocateStorage(TextureUploadTarget::Texture2D, 0, {
-            {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
-
-    }
-
-    void SwapchainObject::CreateDepthStencilResources(VkDevice device, VkPhysicalDevice physicalDevice) {
-        DestroyDepthStencilResources(device);
-
-        const auto imageCount = static_cast<Uint32>(m_images.size());
-        if (imageCount == 0) {
-            return;
-        }
-
-        m_depthStencilFormat = FindSupportedDepthStencilFormat(physicalDevice);
-        MOBILEGL_ASSERT(m_depthStencilFormat != VK_FORMAT_UNDEFINED, "No supported depth/stencil format found.");
-
-        m_depthStencilImages.assign(imageCount, VK_NULL_HANDLE);
-        m_depthStencilImageMemories.assign(imageCount, VK_NULL_HANDLE);
-        m_depthStencilImageViews.assign(imageCount, VK_NULL_HANDLE);
-        m_depthStencilImageLayouts.assign(imageCount, VK_IMAGE_LAYOUT_UNDEFINED);
-
-        for (Uint32 i = 0; i < imageCount; ++i) {
-            VkImageCreateInfo imageInfo{};
-            imageInfo.sType = VK_STRUCTURE_TYPE_IMAGE_CREATE_INFO;
-            imageInfo.imageType = VK_IMAGE_TYPE_2D;
-            imageInfo.extent.width = m_extent.width;
-            imageInfo.extent.height = m_extent.height;
-            imageInfo.extent.depth = 1;
-            imageInfo.mipLevels = 1;
-            imageInfo.arrayLayers = 1;
-            imageInfo.format = m_depthStencilFormat;
-            imageInfo.tiling = VK_IMAGE_TILING_OPTIMAL;
-            imageInfo.initialLayout = VK_IMAGE_LAYOUT_UNDEFINED;
-            imageInfo.usage = VK_IMAGE_USAGE_DEPTH_STENCIL_ATTACHMENT_BIT | VK_IMAGE_USAGE_TRANSFER_SRC_BIT;
-            imageInfo.samples = VK_SAMPLE_COUNT_1_BIT;
-            imageInfo.sharingMode = VK_SHARING_MODE_EXCLUSIVE;
-            VK_VERIFY(vkCreateImage(device, &imageInfo, nullptr, &m_depthStencilImages[i]), "vkCreateImage(depth)");
-
-            VkMemoryRequirements memRequirements{};
-            vkGetImageMemoryRequirements(device, m_depthStencilImages[i], &memRequirements);
-
-            VkMemoryAllocateInfo allocInfo{};
-            allocInfo.sType = VK_STRUCTURE_TYPE_MEMORY_ALLOCATE_INFO;
-            allocInfo.allocationSize = memRequirements.size;
-            allocInfo.memoryTypeIndex =
-                FindMemoryType(physicalDevice, memRequirements.memoryTypeBits, VK_MEMORY_PROPERTY_DEVICE_LOCAL_BIT);
-            VK_VERIFY(vkAllocateMemory(device, &allocInfo, nullptr, &m_depthStencilImageMemories[i]),
-                      "vkAllocateMemory(depth)");
-            VK_VERIFY(vkBindImageMemory(device, m_depthStencilImages[i], m_depthStencilImageMemories[i], 0),
-                      "vkBindImageMemory(depth)");
-
-            VkImageViewCreateInfo viewInfo{};
-            viewInfo.sType = VK_STRUCTURE_TYPE_IMAGE_VIEW_CREATE_INFO;
-            viewInfo.image = m_depthStencilImages[i];
-            viewInfo.viewType = VK_IMAGE_VIEW_TYPE_2D;
-            viewInfo.format = m_depthStencilFormat;
-            viewInfo.subresourceRange.aspectMask = VK_IMAGE_ASPECT_DEPTH_BIT;
-            if (HasStencilComponent(m_depthStencilFormat)) {
-                viewInfo.subresourceRange.aspectMask |= VK_IMAGE_ASPECT_STENCIL_BIT;
-            }
-            viewInfo.subresourceRange.baseMipLevel = 0;
-            viewInfo.subresourceRange.levelCount = 1;
-            viewInfo.subresourceRange.baseArrayLayer = 0;
-            viewInfo.subresourceRange.layerCount = 1;
-            VK_VERIFY(vkCreateImageView(device, &viewInfo, nullptr, &m_depthStencilImageViews[i]),
-                      "vkCreateImageView(depth)");
-        }
-    }
-
-    void SwapchainObject::DestroyDepthStencilResources(VkDevice device) {
-        for (auto view : m_depthStencilImageViews) {
-            if (view != VK_NULL_HANDLE) {
-                vkDestroyImageView(device, view, nullptr);
-            }
-        }
-        m_depthStencilImageViews.clear();
-
-        for (auto image : m_depthStencilImages) {
-            if (image != VK_NULL_HANDLE) {
-                vkDestroyImage(device, image, nullptr);
-            }
-        }
-        m_depthStencilImages.clear();
-
-        for (auto memory : m_depthStencilImageMemories) {
-            if (memory != VK_NULL_HANDLE) {
-                vkFreeMemory(device, memory, nullptr);
-            }
-        }
-        m_depthStencilImageMemories.clear();
-        m_depthStencilImageLayouts.clear();
-        m_depthStencilFormat = VK_FORMAT_UNDEFINED;
-    }
-
-    void SwapchainObject::Shutdown(VkDevice device) {
-        DestroyDepthStencilResources(device);
-
-        for (auto imageView : m_imageViews) {
-            vkDestroyImageView(device, imageView, nullptr);
-        }
-        m_imageViews.clear();
-
-        if (m_swapchain != VK_NULL_HANDLE) {
-            vkDestroySwapchainKHR(device, m_swapchain, nullptr);
-            m_swapchain = VK_NULL_HANDLE;
-        }
-
-        m_images.clear();
-        m_imageLayouts.clear();
-        m_imageContentDefined.clear();
-        m_depthStencilContentDefined.clear();
-        m_preTransform = VK_SURFACE_TRANSFORM_IDENTITY_BIT_KHR;
-    }
-
-    Bool SwapchainObject::IsImageContentDefined(Uint32 index) const {
-        MOBILEGL_ASSERT(index < m_imageContentDefined.size(), "Swapchain image content index out of range");
-        return m_imageContentDefined[index];
-    }
-
-    void SwapchainObject::SetImageContentDefined(Uint32 index, Bool defined) {
-        MOBILEGL_ASSERT(index < m_imageContentDefined.size(), "Swapchain image content index out of range");
-        m_imageContentDefined[index] = defined;
-    }
-
-    Bool SwapchainObject::IsDepthStencilContentDefined(Uint32 index) const {
-        MOBILEGL_ASSERT(index < m_depthStencilContentDefined.size(),
-                        "Swapchain depth/stencil content index out of range");
-        return m_depthStencilContentDefined[index];
-    }
-
-    void SwapchainObject::SetDepthStencilContentDefined(Uint32 index, Bool defined) {
-        MOBILEGL_ASSERT(index < m_depthStencilContentDefined.size(),
-                        "Swapchain depth/stencil content index out of range");
-        m_depthStencilContentDefined[index] = defined;
-    }
-
-    void SwapchainObject::SetAllDepthStencilContentUndefined() {
-        for (SizeT i = 0; i < m_depthStencilContentDefined.size(); ++i) {
-            m_depthStencilContentDefined[i] = false;
-        }
-    }
-
-    VkImage SwapchainObject::GetImage(Uint32 index) const {
-        MOBILEGL_ASSERT(index < m_images.size(), "Swapchain image index out of range");
-        return m_images[index];
-    }
-
-    VkImageLayout SwapchainObject::GetImageLayout(Uint32 index) const {
-        MOBILEGL_ASSERT(index < m_imageLayouts.size(), "Swapchain image layout index out of range");
-        return m_imageLayouts[index];
-    }
-
-    void SwapchainObject::SetImageLayout(Uint32 index, VkImageLayout layout) {
-        MOBILEGL_ASSERT(index < m_imageLayouts.size(), "Swapchain image layout index out of range");
-        m_imageLayouts[index] = layout;
-    }
-
-    VkImage SwapchainObject::GetDepthStencilImage(Uint32 index) const {
-        MOBILEGL_ASSERT(index < m_depthStencilImages.size(), "Swapchain depth/stencil image index out of range");
-        return m_depthStencilImages[index];
-    }
-
-    VkImageView SwapchainObject::GetDepthStencilImageView(Uint32 index) const {
-        MOBILEGL_ASSERT(index < m_depthStencilImageViews.size(),
-                        "Swapchain depth/stencil image view index out of range");
-        return m_depthStencilImageViews[index];
-    }
-
-    VkImageLayout SwapchainObject::GetDepthStencilImageLayout(Uint32 index) const {
-        MOBILEGL_ASSERT(index < m_depthStencilImageLayouts.size(),
-                        "Swapchain depth/stencil image layout index out of range");
-        return m_depthStencilImageLayouts[index];
-    }
-
-    void SwapchainObject::SetDepthStencilImageLayout(Uint32 index, VkImageLayout layout) {
-        MOBILEGL_ASSERT(index < m_depthStencilImageLayouts.size(),
-                        "Swapchain depth/stencil image layout index out of range");
-        m_depthStencilImageLayouts[index] = layout;
-    }
-
-    void SwapchainObject::CreateImageViews(VkDevice device) {
-        m_imageViews.resize(m_images.size(), VK_NULL_HANDLE);
-        for (SizeT i = 0; i < m_imageViews.size(); i++) {
-            VkImageViewCreateInfo createInfo{};
-            createInfo.sType = VK_STRUCTURE_TYPE_IMAGE_VIEW_CREATE_INFO;
-            createInfo.image = m_images[i];
-            createInfo.viewType = VK_IMAGE_VIEW_TYPE_2D;
-            createInfo.format = m_surfaceFormat.format;
-            createInfo.components.r = VK_COMPONENT_SWIZZLE_IDENTITY;
-            createInfo.components.g = VK_COMPONENT_SWIZZLE_IDENTITY;
-            createInfo.components.b = VK_COMPONENT_SWIZZLE_IDENTITY;
-            createInfo.components.a = VK_COMPONENT_SWIZZLE_IDENTITY;
-            createInfo.subresourceRange.aspectMask = VK_IMAGE_ASPECT_COLOR_BIT;
-            createInfo.subresourceRange.baseMipLevel = 0;
-            createInfo.subresourceRange.levelCount = 1;
-            createInfo.subresourceRange.baseArrayLayer = 0;
-            createInfo.subresourceRange.layerCount = 1;
-            VK_VERIFY(vkCreateImageView(device, &createInfo, nullptr, &m_imageViews[i]));
-        }
-        MGLOG_I("Swapchain image views created");
-    }
-
-#undef VK_VERIFY
-} // namespace MobileGL::MG_Backend::DirectVulkan

MobileGL/MG_Backend/DirectVulkan/Renderer/SwapchainObject.h

@@ -1,98 +0,0 @@
-// MobileGL - MobileGL/MG_Backend/DirectVulkan/Renderer/SwapchainObject.h
-// Copyright (c) 2025-2026 MobileGL-Dev
-// Licensed under the GNU Lesser General Public License v3.0:
-//   https://www.gnu.org/licenses/gpl-3.0.txt
-//   https://www.gnu.org/licenses/lgpl-3.0.txt
-// SPDX-License-Identifier: LGPL-3.0-only
-// End of Source File Header
-
-#pragma once
-
-#include <Includes.h>
-#include "../VkIncludes.h"
-
-namespace MobileGL::MG_Backend::DirectVulkan {
-    class SwapchainObject {
-    public:
-        struct SwapchainCapabilities {
-            VkSurfaceCapabilitiesKHR capabilities;
-            Vector<VkSurfaceFormatKHR> surfaceFormats;
-            Vector<VkPresentModeKHR> presentModes;
-
-            Bool IsComplete() const {
-                return !surfaceFormats.empty() && !presentModes.empty();
-            }
-        };
-
-        static SwapchainCapabilities GetSwapchainCapabilities(VkPhysicalDevice physicalDevice, VkSurfaceKHR surface);
-        static VkSurfaceFormatKHR ChooseSwapchainSurfaceFormat(const Vector<VkSurfaceFormatKHR>& availableFormats);
-        static VkPresentModeKHR ChooseSwapchainPresentMode(const Vector<VkPresentModeKHR>& availablePresentModes);
-
-        void Create(VkDevice device, VkPhysicalDevice physicalDevice, VkSurfaceKHR surface, Uint32 graphicsQueueFamily,
-                    Uint32 presentQueueFamily, Uint32 minImageCountHint, VkExtent2D desiredExtent);
-        void Shutdown(VkDevice device);
-
-        VkSwapchainKHR GetHandle() const { return m_swapchain; }
-        const VkSurfaceFormatKHR& GetSurfaceFormat() const { return m_surfaceFormat; }
-        VkExtent2D GetExtent() const { return m_extent; }
-        // Surface-space extent (before the pre-rotation quarter-turn swap) this swapchain was
-        // created from - the value to compare a freshly queried currentExtent against.
-        VkExtent2D GetSurfaceExtent() const { return m_surfaceExtent; }
-        VkSurfaceTransformFlagBitsKHR GetPreTransform() const { return m_preTransform; }
-        const Vector<VkImage>& GetImages() const { return m_images; }
-        const Vector<VkImageView>& GetImageViews() const { return m_imageViews; }
-        VkFormat GetDepthStencilFormat() const { return m_depthStencilFormat; }
-        const Vector<VkImageView>& GetDepthStencilImageViews() const { return m_depthStencilImageViews; }
-        VkImage GetDepthStencilImage(Uint32 index) const;
-        VkImageView GetDepthStencilImageView(Uint32 index) const;
-        VkImageLayout GetDepthStencilImageLayout(Uint32 index) const;
-        void SetDepthStencilImageLayout(Uint32 index, VkImageLayout layout);
-        VkImage GetImage(Uint32 index) const;
-        VkImageLayout GetImageLayout(Uint32 index) const;
-        void SetImageLayout(Uint32 index, VkImageLayout layout);
-        SizeT GetImageCount() const { return m_images.size(); }
-
-        // EGL content-validity tracking for the default framebuffer. A color
-        // buffer's content is undefined once its image has been presented
-        // (EGL_BUFFER_DESTROYED swap behaviour, the implementation default),
-        // and every ancillary (depth/stencil) buffer's content is undefined
-        // after ANY swap regardless of swap behaviour (EGL 1.5 §3.10.1). The
-        // render-pass manager turns an undefined attachment's tile load into
-        // LOAD_OP_DONT_CARE. Flags start false (a fresh swapchain image holds
-        // garbage) and a render pass storing into an attachment sets it back
-        // to defined.
-        Bool IsImageContentDefined(Uint32 index) const;
-        void SetImageContentDefined(Uint32 index, Bool defined);
-        Bool IsDepthStencilContentDefined(Uint32 index) const;
-        void SetDepthStencilContentDefined(Uint32 index, Bool defined);
-        void SetAllDepthStencilContentUndefined();
-
-    private:
-        void CreateImageViews(VkDevice device);
-        void CreateDepthStencilResources(VkDevice device, VkPhysicalDevice physicalDevice);
-        void DestroyDepthStencilResources(VkDevice device);
-        static constexpr VkPresentModeKHR s_desiredPresentModes[] {
-            VK_PRESENT_MODE_MAILBOX_KHR,
-            VK_PRESENT_MODE_IMMEDIATE_KHR,
-            VK_PRESENT_MODE_FIFO_RELAXED_KHR,
-            VK_PRESENT_MODE_FIFO_KHR
-        };
-
-        VkSwapchainKHR m_swapchain = VK_NULL_HANDLE;
-        VkSurfaceFormatKHR m_surfaceFormat{};
-        VkExtent2D m_extent{};
-        VkExtent2D m_surfaceExtent{};
-        VkSurfaceTransformFlagBitsKHR m_preTransform = VK_SURFACE_TRANSFORM_IDENTITY_BIT_KHR;
-        Vector<VkImage> m_images;
-        Vector<VkImageView> m_imageViews;
-        Vector<VkImageLayout> m_imageLayouts;
-
-        VkFormat m_depthStencilFormat = VK_FORMAT_UNDEFINED;
-        Vector<VkImage> m_depthStencilImages;
-        Vector<VkDeviceMemory> m_depthStencilImageMemories;
-        Vector<VkImageView> m_depthStencilImageViews;
-        Vector<VkImageLayout> m_depthStencilImageLayouts;
-        Vector<Bool> m_imageContentDefined;
-        Vector<Bool> m_depthStencilContentDefined;
-    };
-} // namespace MobileGL::MG_Backend::DirectVulkan

MobileGL/MG_Backend/DirectVulkan/Renderer/UniformManager.h

@@ -1,415 +0,0 @@
-// MobileGL - MobileGL/MG_Backend/DirectVulkan/Renderer/UniformDescriptorBinder.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 "ProgramFactory.h"
-#include "VkBufferManager.h"
-#include "VkSamplerManager.h"
-#include "VkTextureManager.h"
-#include "../VkIncludes.h"
-#include <Includes.h>
-
-namespace MobileGL::MG_State::GLState {
-    class ITextureObject;
-    class ProgramObject;
-    class SamplerObject;
-}
-
-namespace MobileGL::MG_Backend::DirectVulkan {
-    class UniformManager {
-    public:
-        struct SamplerBindingOverride {
-            Uint32 binding = 0;
-            Uint32 element = 0;
-            MG_State::GLState::ITextureObject* texture = nullptr;
-            const MG_State::GLState::SamplerObject* sampler = nullptr;
-            VkImageView imageView = VK_NULL_HANDLE;
-            VkImageLayout imageLayout = VK_IMAGE_LAYOUT_UNDEFINED;
-            Bool forceNearestFiltering = false;
-        };
-
-        struct SamplerImageFeedbackBinding {
-            Uint32 samplerBinding = 0;
-            Uint32 samplerElement = 0;
-            MG_State::GLState::ITextureObject* texture = nullptr;
-            const MG_State::GLState::SamplerObject* sampler = nullptr;
-            SamplerNumericDomain numericDomain = SamplerNumericDomain::Unknown;
-        };
-
-        Bool Initialize(VkDevice device, VkBufferManager* bufferManager,
-                        ProgramFactory* programFactory,
-                        VkDeviceSize minUniformBufferOffsetAlignment, Uint32 frameCount,
-                        Uint32 maxBindings = 16, Uint32 setsPerFrame = 64,
-                        VkTextureManager* textureManager = nullptr, VkSamplerManager* samplerManager = nullptr);
-        void Shutdown();
-
-        void BeginFrame(Uint32 frameIndex);
-        // A command buffer (re)began recording: descriptor bindings recorded into
-        // the previous buffer do not carry over, so drop the bind-dedup shadow.
-        void OnCommandBufferBoundary() { m_lastBindValid = false; }
-        // A ProgramFactory eviction just destroyed this layout: purge every frame
-        // slot's cached descriptor sets for it, so a recycled handle value can never
-        // stale-hit sets written for the dead layout's bindings. The sets are
-        // vkFreeDescriptorSets'd back to their pools (created with
-        // FREE_DESCRIPTOR_SET_BIT) and the pool accounting is credited, so program
-        // churn recycles pool capacity instead of abandoning it. GPU-safe: the layout
-        // only dies after >1024 idle frame boundaries, so no in-flight command buffer
-        // references its sets. This is the only eviction path for the per-layout
-        // caches - a live layout's entry must never be purged (its sets would be
-        // unreachable pool slots), so there is deliberately no age-based sweep here.
-        void OnDescriptorSetLayoutDestroyed(VkDescriptorSetLayout descriptorSetLayout);
-        // One record per visited CombinedImageSampler DESCRIPTOR (post fallback substitution,
-        // in binding order, and within a binding in array-element order): the resolved texture
-        // and effective sampler, as never-reused lifetime ids so a freed-and-reallocated object
-        // at the same heap address can only MISS a comparison, never false-hit it (same ABA
-        // rule as SamplerResolveMemo). An arrayed binding contributes one record per element -
-        // element granularity is required, or swapping the textures of two elements of the same
-        // array would leave the record list identical and the fast path would keep a stale set.
-        struct SampledBindingRecord {
-            Uint64 textureLifetimeId = 0;
-            Uint64 samplerLifetimeId = 0;
-        };
-        Bool CollectSampledTextures(const MG_State::GLState::ProgramObject& program,
-                                    const ProgramFactory::VkProgramObject& programObj,
-                                    Vector<MG_State::GLState::ITextureObject*>& outTextures,
-                                    Vector<SampledBindingRecord>* outBindingRecords = nullptr);
-        // Shadow-compare for the SetupDraw fast path: re-runs the CollectSampledTextures
-        // walk and reports whether every visited binding still resolves to the recorded
-        // (texture, effective sampler) pair. A texture bind generation bump alone (e.g. a
-        // redundant glBindSampler, which always bumps it) does not prove the sampled set
-        // moved; this walk does, without rebuilding the set or falling off the fast path.
-        Bool SampledBindingsUnchanged(const MG_State::GLState::ProgramObject& program,
-                                      const ProgramFactory::VkProgramObject& programObj,
-                                      const Vector<SampledBindingRecord>& previousRecords) const;
-        Bool CollectStorageImageTextures(const MG_State::GLState::ProgramObject& program,
-                                         const ProgramFactory::VkProgramObject& programObj,
-                                         Vector<MG_State::GLState::ITextureObject*>& outTextures) const;
-        Bool CollectSamplerImageFeedback(
-            const MG_State::GLState::ProgramObject& program,
-            const ProgramFactory::VkProgramObject& programObj,
-            Vector<SamplerImageFeedbackBinding>& outBindings) const;
-        static Bool SamplerOverlapsWritableImageSubresource(Int samplerBaseLevel, Int samplerMaxLevel,
-                                                             GLint imageLevel, GLenum imageAccess);
-        // samplerDescriptorsUnchangedHint: the caller (SetupDraw fast path) proved that
-        // every input of every combined-image-sampler resolution is unchanged since the
-        // previous draw's resolve - same (texture, sampler) per binding, texture params
-        // sum, sampling-resolution generation (sampler params + texture shape), image
-        // epochs AND per-resource layout values - so the per-binding cached
-        // VkDescriptorImageInfo may be reused without re-running the resolve chain.
-        Bool BindProgramUniformBuffers(VkCommandBuffer commandBuffer,
-                                       const MG_State::GLState::ProgramObject& program,
-                                       const ProgramFactory::VkProgramObject& programObj,
-                                       Uint32 frameIndex,
-                                       VkPipelineBindPoint bindPoint = VK_PIPELINE_BIND_POINT_GRAPHICS,
-                                       const SamplerBindingOverride* samplerBindingOverride = nullptr,
-                                       Bool samplerDescriptorsUnchangedHint = false,
-                                       const Vector<SamplerBindingOverride>* samplerBindingOverrides = 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);
-
-        // True when the program reads at least one sampler and every one of them is bound to a
-        // texture whose GL level range is a single level. Such a sampler resolves to
-        // minLod = maxLod = 0 (see VkSamplerManager::GetOrCreateSampler), so an implicit-LOD sample
-        // and an explicit LOD 0 sample must read the same texel - which is what makes the
-        // ExplicitLod0Sampling SPIR-V rewrite safe to request. Deliberately conservative: it reads
-        // only GL state, so a texture that ends up single-level for another reason (one uploaded
-        // level under a wide level range) merely misses the rewrite.
-        static Bool ProgramSamplesOnlySingleLevelTextures(const MG_State::GLState::ProgramObject& program,
-                                                          const ProgramFactory::VkProgramObject& programObj);
-
-    private:
-        struct DescriptorPoolBucket {
-            VkDescriptorPool handle = VK_NULL_HANDLE;
-            Uint32 maxSets = 0;
-            Uint32 allocatedSets = 0;
-            Bool updateAfterBind = false;
-        };
-
-        // A cached descriptor set together with the pool it was allocated from, so a
-        // layout-destroyed purge can vkFreeDescriptorSets it back and credit the
-        // owning bucket's accounting.
-        struct CachedDescriptorSet {
-            VkDescriptorSet set = VK_NULL_HANDLE;
-            VkDescriptorPool pool = VK_NULL_HANDLE;
-        };
-
-        struct DescriptorSetCacheEntry {
-            Vector<CachedDescriptorSet> sets;
-            Uint32 cursor = 0;
-        };
-
-        struct FrameResources {
-            Vector<DescriptorPoolBucket> descriptorPools;
-            UnorderedMap<VkDescriptorSetLayout, DescriptorSetCacheEntry> descriptorSetCacheByLayout;
-            Vector<VkBufferView> texelBufferViews;
-            Uint32 activeDescriptorPoolIndex = 0;
-            Uint32 allocatedSetsThisFrame = 0;
-            Uint32 peakAllocatedSetsThisFrame = 0;
-        };
-
-        static Bool ResolveSamplerTexture(const MG_State::GLState::ProgramObject& program,
-                                   const ProgramFactory::VkProgramObject& programObj, Uint32 binding,
-                                   SharedPtr<MG_State::GLState::ITextureObject>& outTexture);
-        // Shared per-binding resolution for CollectSampledTextures and
-        // SampledBindingsUnchanged, so membership and comparison can never diverge:
-        // texture after the fallback substitution (may still be null when no fallback
-        // exists), effective sampler = unit override else the texture's own sampler.
-        // False = the binding is skipped (unbound with a non-2D fallback target).
-        // `element` indexes a sampler array inside the binding; see ResolveSamplerDescriptor.
-        Bool ResolveSampledBinding(const MG_State::GLState::ProgramObject& program,
-                                   const ProgramFactory::VkProgramObject& programObj, Uint32 binding, Uint32 element,
-                                   MG_State::GLState::ITextureObject*& outTexture,
-                                   const MG_State::GLState::SamplerObject*& outSampler) const;
-        // Raw-pointer variant for the per-draw sampled-texture walk (CollectSampledTextures):
-        // the bound texture stays alive through the draw via GL binding state, so callers that
-        // only need the pointer skip the SharedPtr copy's atomic refcount churn.
-        static MG_State::GLState::ITextureObject* ResolveSamplerTextureRaw(
-            const MG_State::GLState::ProgramObject& program,
-            const ProgramFactory::VkProgramObject& programObj, Uint32 binding, Uint32 element);
-        SharedPtr<MG_State::GLState::ITextureObject> GetFallbackTexture(TextureTarget target) const;
-        // `element` indexes a sampler ARRAY inside one binding; each element carries its own
-        // independently assigned GL texture unit, so it selects the texture, the sampler
-        // override and the fallback separately from its neighbours.
-        //
-        // trustUnchangedHint: reuse this binding's cached VkDescriptorImageInfo outright
-        // (see BindProgramUniformBuffers' samplerDescriptorsUnchangedHint for the proof
-        // obligations the caller carries). The cache is keyed by binding alone, so it is
-        // used ONLY for single-descriptor bindings - see m_samplerResolveMemo.
-        Bool ResolveSamplerDescriptor(VkCommandBuffer commandBuffer, const MG_State::GLState::ProgramObject& program,
-                                      const ProgramFactory::VkProgramObject& programObj, Uint32 binding,
-                                      Uint32 element, VkDescriptorImageInfo& outImageInfo,
-                                      Bool trustUnchangedHint = false) const;
-        Bool ResolveSamplerDescriptorOverride(const SamplerBindingOverride& samplerBindingOverride,
-                                              VkDescriptorImageInfo& outImageInfo) const;
-        Bool ResolveTexelBufferDescriptor(const MG_State::GLState::ProgramObject& program,
-                                          const ProgramFactory::VkProgramObject& programObj, Uint32 binding,
-                                          Uint32 frameIndex, VkBufferView& outBufferView);
-        // GLSL `imageBuffer`: the same VkBufferView descriptor as the sampled texel buffer above,
-        // but resolved from an IMAGE unit (glBindImageTexture) rather than a texture unit, and
-        // made GPU-resident-writable because the shader may store to it. No `element` parameter:
-        // an imageBuffer ARRAY is refused at program creation, so a binding is always one
-        // descriptor (see the array gate in RemapDescriptorBindingsForVulkan).
-        Bool ResolveStorageTexelBufferDescriptor(const MG_State::GLState::ProgramObject& program,
-                                                 const ProgramFactory::VkProgramObject& programObj, Uint32 binding,
-                                                 Uint32 frameIndex, VkBufferView& outBufferView);
-        // `element` indexes a block INSTANCE array's descriptors; it is 0 for every ordinary
-        // block. Each element resolves through its own GL storage block, and so its own GL
-        // binding point, buffer and glBindBufferRange window.
-        Bool ResolveStorageBufferDescriptor(const MG_State::GLState::ProgramObject& program,
-                                            const ProgramFactory::VkProgramObject& programObj, Uint32 binding,
-                                            Uint32 element, VkDescriptorBufferInfo& outBufferInfo) const;
-        // `element` indexes an image ARRAY inside one binding; each element carries its own
-        // independently assigned GL image unit.
-        Bool ResolveStorageImageDescriptor(VkCommandBuffer commandBuffer,
-                                           const MG_State::GLState::ProgramObject& program,
-                                           const ProgramFactory::VkProgramObject& programObj, Uint32 binding,
-                                           Uint32 element, 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,
-                                         Uint32 arrayElement, UboBindResult& out) const;
-        // Shared resolution of one dynamic-UBO binding element into the
-        // (buffer, range, dynamicOffset) triple the descriptor consumes: direct
-        // bind, global-slice reuse, or transient upload. Used by the full walk
-        // and by the dynamic-offset-only rebind (see FastRebindMemo).
-        Bool ResolveDynamicUboDescriptor(const MG_State::GLState::ProgramObject& program,
-                                         const ProgramFactory::VkProgramObject& programObj, Uint32 binding,
-                                         Uint32 arrayElement, Uint32 frameIndex, VkBuffer& outBuffer,
-                                         VkDeviceSize& outRange, Uint32& outDynamicOffset);
-        // The vkCmdBindDescriptorSets tail shared by the full walk and the
-        // dynamic-offset-only rebind: skips the driver call when this exact
-        // binding is already live on the command buffer (see the bind-dedup
-        // shadow below), otherwise binds and refreshes the shadow.
-        void BindDescriptorSetDeduped(VkCommandBuffer commandBuffer, VkPipelineBindPoint bindPoint,
-                                      VkPipelineLayout pipelineLayout, VkDescriptorSet descriptorSet,
-                                      const Vector<Uint32>& dynamicOffsets);
-        Bool CreateDescriptorPool(Uint32 maxSets, Bool updateAfterBind, VkDescriptorPool& outPool) const;
-        Bool GrowFrameDescriptorPool(FrameResources& frame, Uint32 frameIndex, Bool updateAfterBind);
-        VkResult AllocateDescriptorSetsFromActivePool(
-            Uint32 frameIndex, const ProgramFactory::VkProgramObject& programObj, VkDescriptorSet& outDescriptorSet);
-        VkResult AcquireDescriptorSet(Uint32 frameIndex,
-                                      const ProgramFactory::VkProgramObject& programObj,
-                                      VkDescriptorSet& outDescriptorSet);
-
-        VkDevice m_device = VK_NULL_HANDLE;
-        VkBufferManager* m_bufferManager = nullptr;
-        ProgramFactory* m_programFactory = nullptr;
-        Vector<FrameResources> m_frames;
-
-        VkDeviceSize m_minDynamicOffsetAlignment = 1;
-        Uint32 m_frameCount = 0;
-        Uint32 m_maxBindings = 0;
-        Uint32 m_setsPerFrame = 0;
-        Uint32 m_peakDescriptorSetsObserved = 0;
-        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 recent draws (see BindProgramUniformBuffers).
-        // When a draw's resolved descriptor content is byte-identical to one memoized
-        // earlier, reuse that VkDescriptorSet and skip AcquireDescriptorSet +
-        // vkUpdateDescriptorSets - only the bind-time dynamic offsets differ. Four
-        // entries with round-robin replacement rather than one: draws alternating
-        // between two programs (MC's chunk<->entity ping-pong) would thrash a single
-        // slot into a full re-allocate+write every draw. Reset each frame in BeginFrame
-        // because the frame's descriptor sets are recycled there.
-        struct DescriptorReuseEntry {
-            Uint64 signature = 0;
-            VkDescriptorSet set = VK_NULL_HANDLE;
-            Bool valid = false;
-        };
-        static constexpr Uint32 kDescriptorReuseMemoSize = 4;
-        DescriptorReuseEntry m_descriptorReuseMemo[kDescriptorReuseMemoSize];
-        Uint32 m_descriptorReuseMemoNext = 0;
-
-        // Dynamic-offset-only rebind (see BindProgramUniformBuffers): records the
-        // descriptor set selected by the last cacheable full walk of a program
-        // whose active bindings are exactly one dynamic UBO (single descriptor)
-        // plus combined-image samplers. When the next call proves every sampler
-        // descriptor input unchanged (samplerDescriptorsUnchangedHint) and the
-        // UBO re-resolves to the SAME VkBuffer+range - only the dynamic offset
-        // moved, the per-draw glUniform case - the walk collapses to: resolve one
-        // offset, rebind the recorded set with new pDynamicOffsets (Vulkan allows
-        // rebinding the same set with different dynamic offsets).
-        // Invalidation inventory: BeginFrame clears it (the frame's sets are
-        // recycled) and the frameIndex field guards cross-frame confusion on top;
-        // OnDescriptorSetLayoutDestroyed clears it (the set may be freed); a
-        // sampler-override walk clears it (mirrors m_descriptorReuseMemo); a
-        // program relink bumps the backend state version and thus programObj.hash
-        // so the key misses; the program lifetime id is never reused, so a
-        // deleted-and-recreated program misses; a texture/sampler/binding change
-        // drops the hint upstream; an arena wrap or growth resolves a different
-        // VkBuffer and misses. AcquireDescriptorSet's per-frame cursor only
-        // advances, so the recorded set is never re-written within its frame.
-        struct FastRebindMemo {
-            Bool valid = false;
-            Uint32 frameIndex = 0;
-            Uint64 programLifetimeId = 0;
-            ProgramFactory::HashType programHash = 0;
-            Uint32 uboBinding = 0;
-            VkBuffer uboBuffer = VK_NULL_HANDLE;
-            VkDeviceSize uboRange = 0;
-            VkDescriptorSet set = VK_NULL_HANDLE;
-        };
-        FastRebindMemo m_fastRebindMemo;
-
-        // vkCmdBindDescriptorSets dedup: consecutive draws with a static uniform
-        // block resolve to the same set AND the same dynamic offsets, so the
-        // driver call can be skipped outright. Command-buffer-scope state; reset
-        // via OnCommandBufferBoundary whenever a recording (re)begins. Keyed on
-        // layout+bind point, so a pipeline-layout switch always rebinds.
-        static constexpr Uint32 kMaxShadowedDynamicOffsets = 8;
-        Bool m_lastBindValid = false;
-        VkDescriptorSet m_lastBindSet = VK_NULL_HANDLE;
-        VkPipelineLayout m_lastBindLayout = VK_NULL_HANDLE;
-        VkPipelineBindPoint m_lastBindPoint = VK_PIPELINE_BIND_POINT_GRAPHICS;
-        Uint32 m_lastBindOffsetCount = 0;
-        Uint32 m_lastBindOffsets[kMaxShadowedDynamicOffsets] = {};
-
-        // Global-UBO transient-slice reuse: MC leaves the default uniform block
-        // untouched across long GUI/terrain runs, so the per-draw re-upload of
-        // the same bytes can reuse the slice uploaded earlier THIS frame (frame
-        // serial guards arena recycling; the content version guards writes).
-        struct GlobalUboSliceMemo {
-            Uint64 programLifetimeId = 0;
-            Uint64 frameSerial = 0;
-            Uint32 uboContentVersion = 0;
-            VkBuffer buffer = VK_NULL_HANDLE;
-            VkDeviceSize offset = 0;
-            VkDeviceSize range = 0;
-        };
-        static constexpr Uint32 kGlobalUboMemoSize = 4;
-        GlobalUboSliceMemo m_globalUboMemo[kGlobalUboMemoSize];
-        Uint32 m_globalUboMemoNext = 0;
-
-        // Per-binding fast path over VkSamplerManager's content-hashed sampler cache, which
-        // stays the source of truth: its key hashes all sampler+texture state, so two distinct
-        // 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, but the
-        // whole-descriptor entry is additionally keyed by program lifetime: Vulkan binding
-        // numbers are layout-local and unrelated programs routinely reuse binding 0/1.
-        struct SamplerResolveMemo {
-            Uint64 infoProgramLifetimeId = 0;
-            Uint64 samplerLifetimeId = 0;
-            Uint64 textureLifetimeId = 0;
-            VkSampler sampler = VK_NULL_HANDLE;
-            Uint32 viewLevelCount = 0;
-            Uint16 samplerVersion = 0;
-            Uint16 textureParamsVersion = 0;
-            Bool forceNearestFiltering = false;
-            Bool valid = false;
-            // ResolveSampledImageViewFormat is pure in (image format, numeric domain), but a
-            // domain mismatch walks a ~184-entry format table. Memo the resolution per binding
-            // so a reinterpreted sampler pays that scan once, not once per draw.
-            VkFormat viewFormatSource = VK_FORMAT_UNDEFINED;
-            SamplerNumericDomain viewFormatDomain = SamplerNumericDomain::Unknown;
-            VkFormat viewFormat = VK_FORMAT_UNDEFINED;
-            Bool viewFormatValid = false;
-            // Whole resolved descriptor from this binding's last full resolve. Reused
-            // ONLY under ResolveSamplerDescriptor's trustUnchangedHint, whose caller
-            // proves every resolve input unchanged; cleared with the per-frame reset
-            // (the cached VkSampler outlives a frame only via a fresh resolve, which
-            // also re-stamps it against VkSamplerManager's frame-boundary sweep).
-            //
-            // This one field is keyed by binding but describes ONE descriptor, so it is
-            // written and read only for single-descriptor bindings. A sampler ARRAY's
-            // elements share the binding and would overwrite each other here - the last
-            // element resolved would then be handed to element 0 on the next hinted draw.
-            // Every other field above is self-validating (each compares its full key
-            // before reuse, and the view-format entry is a pure function of format and
-            // numeric domain), so an arrayed binding may keep using those.
-            VkDescriptorImageInfo info{};
-            Bool infoValid = false;
-        };
-        mutable Vector<SamplerResolveMemo> m_samplerResolveMemo;
-        // Exclusive upper bound on the entries of m_samplerResolveMemo that any resolve
-        // has ever written. The vector is sized to the DEVICE binding cap (256 on desktop
-        // NVIDIA), but a program declares 1-8 bindings, so the per-frame reset below was
-        // memsetting ~22 KB of never-touched entries every frame - a measurable slice of
-        // the per-frame fixed cost on draw-light frames. Every site that can turn any of
-        // an entry's *Valid flags on raises this mark first, so entries at or above it are
-        // provably still in their constructed (all-invalid) state and clearing them is a
-        // no-op. Never lowered except by Initialize/Shutdown, which rebuild the vector.
-        mutable Uint32 m_samplerResolveMemoHighWater = 0;
-        void NoteSamplerResolveMemoTouched(Uint32 binding) const {
-            if (binding >= m_samplerResolveMemoHighWater) {
-                m_samplerResolveMemoHighWater = binding + 1;
-            }
-        }
-    };
-} // namespace MobileGL::MG_Backend::DirectVulkan

MobileGL/MG_Backend/DirectVulkan/Renderer/VertexInputStateBuilder.cpp

@@ -1,64 +0,0 @@
-// MobileGL - MobileGL/MG_Backend/DirectVulkan/Renderer/VertexInputStateBuilder.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 "VertexInputStateBuilder.h"
-
-namespace MobileGL::MG_Backend::DirectVulkan {
-    VertexInputStateBuilder::VertexInputStateBuilder() {
-        Reset();
-    }
-
-    void VertexInputStateBuilder::Reset() {
-        m_bindings.clear();
-        m_attributes.clear();
-
-        m_state = {};
-        m_state.sType = VK_STRUCTURE_TYPE_PIPELINE_VERTEX_INPUT_STATE_CREATE_INFO;
-        m_state.vertexBindingDescriptionCount = 0;
-        m_state.pVertexBindingDescriptions = nullptr;
-        m_state.vertexAttributeDescriptionCount = 0;
-        m_state.pVertexAttributeDescriptions = nullptr;
-    }
-
-    VertexInputStateBuilder& VertexInputStateBuilder::AddBinding(
-        Uint32 binding, Uint32 stride, VkVertexInputRate inputRate) {
-        VkVertexInputBindingDescription desc{};
-        desc.binding = binding;
-        desc.stride = stride;
-        desc.inputRate = inputRate;
-        m_bindings.push_back(desc);
-        return *this;
-    }
-
-    VertexInputStateBuilder& VertexInputStateBuilder::AddAttribute(
-        Uint32 location, Uint32 binding, VkFormat format, Uint32 offset) {
-        VkVertexInputAttributeDescription desc{};
-        desc.location = location;
-        desc.binding = binding;
-        desc.format = format;
-        desc.offset = offset;
-        m_attributes.push_back(desc);
-        return *this;
-    }
-
-    const VkPipelineVertexInputStateCreateInfo& VertexInputStateBuilder::Build() {
-        m_state.vertexBindingDescriptionCount = static_cast<Uint32>(m_bindings.size());
-        m_state.pVertexBindingDescriptions = m_bindings.empty() ? nullptr : m_bindings.data();
-        m_state.vertexAttributeDescriptionCount = static_cast<Uint32>(m_attributes.size());
-        m_state.pVertexAttributeDescriptions = m_attributes.empty() ? nullptr : m_attributes.data();
-        return m_state;
-    }
-
-    const Vector<VkVertexInputBindingDescription>& VertexInputStateBuilder::GetBindings() const {
-        return m_bindings;
-    }
-
-    const Vector<VkVertexInputAttributeDescription>& VertexInputStateBuilder::GetAttributes() const {
-        return m_attributes;
-    }
-} // namespace MobileGL::MG_Backend::DirectVulkan

MobileGL/MG_Backend/DirectVulkan/Renderer/VertexInputStateBuilder.h

@@ -1,31 +0,0 @@
-// MobileGL - MobileGL/MG_Backend/DirectVulkan/Renderer/VertexInputStateBuilder.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_Backend::DirectVulkan {
-    class VertexInputStateBuilder {
-    public:
-        VertexInputStateBuilder();
-
-        void Reset();
-        VertexInputStateBuilder& AddBinding(
-            Uint32 binding, Uint32 stride, VkVertexInputRate inputRate = VK_VERTEX_INPUT_RATE_VERTEX);
-        VertexInputStateBuilder& AddAttribute(Uint32 location, Uint32 binding, VkFormat format, Uint32 offset);
-
-        const VkPipelineVertexInputStateCreateInfo& Build();
-        const Vector<VkVertexInputBindingDescription>& GetBindings() const;
-        const Vector<VkVertexInputAttributeDescription>& GetAttributes() const;
-
-    private:
-        VkPipelineVertexInputStateCreateInfo m_state{};
-        Vector<VkVertexInputBindingDescription> m_bindings;
-        Vector<VkVertexInputAttributeDescription> m_attributes;
-    };
-} // namespace MobileGL::MG_Backend::DirectVulkan

MobileGL/MG_Backend/DirectVulkan/Renderer/VertexInputStateFactory.cpp

@@ -1,558 +0,0 @@
-// MobileGL - MobileGL/MG_Backend/DirectVulkan/Renderer/VertexInputStateFactory.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 "VertexInputStateFactory.h"
-#include "MG_Util/Converters/MGToStr/DataTypeConverter.h"
-#include <MG_Backend/BackendObjects.h>
-#include <utility>
-
-namespace MobileGL::MG_Backend::DirectVulkan {
-    VertexInputStateFactory::HashType VertexInputStateFactory::ComputeHash(
-        const MG_State::GLState::VertexArrayObject& vao) const {
-        XXHASH_VERIFY(XXH64_reset(m_hashState, m_config.CacheVersion));
-
-        for (Int i = 0; i < MG_State::GLState::VertexArrayObject::MAX_VERTEX_ATTRIBS; ++i) {
-            const auto& attr = vao.GetAttribute(i);
-
-            XXHASH_VERIFY(XXH64_update(m_hashState, &attr.Enabled, sizeof(attr.Enabled)));
-            if (!attr.Enabled) {
-                continue;
-            }
-
-            XXHASH_VERIFY(XXH64_update(m_hashState, &attr.Size, sizeof(attr.Size)));
-            XXHASH_VERIFY(XXH64_update(m_hashState, &attr.Type, sizeof(attr.Type)));
-            XXHASH_VERIFY(XXH64_update(m_hashState, &attr.Normalized, sizeof(attr.Normalized)));
-            XXHASH_VERIFY(XXH64_update(m_hashState, &attr.Stride, sizeof(attr.Stride)));
-            XXHASH_VERIFY(XXH64_update(m_hashState, &attr.Offset, sizeof(attr.Offset)));
-            XXHASH_VERIFY(XXH64_update(m_hashState, &attr.IsInteger, sizeof(attr.IsInteger)));
-            XXHASH_VERIFY(XXH64_update(m_hashState, &attr.IsLong, sizeof(attr.IsLong)));
-            XXHASH_VERIFY(XXH64_update(m_hashState, &attr.IsBgra, sizeof(attr.IsBgra)));
-            XXHASH_VERIFY(XXH64_update(m_hashState, &attr.Divisor, sizeof(attr.Divisor)));
-
-            // The bound buffer's IDENTITY is a component of the key, and it has to be the
-            // buffer's never-reused lifetime id - NOT its heap address, which this used to
-            // hash. An address is recycled by the allocator, so a deleted-and-recreated
-            // buffer reproduces it; combined with a byte-identical attribute layout that
-            // reproduces the WHOLE content hash, and the hash is what
-            // TryBindResolvedVertexBindings accepts as proof that a memoised binding still
-            // reads the buffer it was resolved from. It did not: a destroyed buffer's GPU
-            // slice was bound for its successor's draw, which is how a transform-feedback
-            // capture came back holding a dead VAO's vertex data (0,0,0,1 - the previous
-            // test's positions) instead of its own.
-            // Zero for client memory (no buffer), which is a distinct identity of its own.
-            const Uint64 bufferKey = attr.Buffer ? attr.Buffer->GetLifetimeId() : 0;
-            XXHASH_VERIFY(XXH64_update(m_hashState, &bufferKey, sizeof(bufferKey)));
-        }
-
-        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) {
-        // Per-draw fast path: the VAO carries a pointer to its resolved entry,
-        // valid while its config version and the cache's eviction epoch both
-        // match - no re-hash, no map lookup.
-        const void* memoState = nullptr;
-        Uint64 memoEpoch = 0;
-        if (vao.GetBackendStateMemo(memoState, memoEpoch) && memoEpoch == m_evictionEpoch) {
-            const auto* entry = static_cast<const BackendVertexInputState*>(memoState);
-            entry->lastUsedFrameBoundary = m_frameBoundaryCounter;
-            return *entry;
-        }
-        const BackendVertexInputState& entry = GetOrCreateVertexInputState(vao, GetOrComputeHash(vao));
-        vao.SetBackendStateMemo(&entry, m_evictionEpoch);
-        // Also mirror the layout identity and the two per-draw masks into the VAO's aux
-        // memo (pure VALUES derived from the VAO configuration, so config-version
-        // guarding alone is sound). The draw fast path reads them from the VAO object it
-        // already touched instead of chasing into this entry - see PackVertexInputAuxMemo.
-        vao.SetBackendAuxMemo(entry.layoutHash,
-                              PackVertexInputAuxMasks(entry.unsupportedAttribMask, entry.attributeLocationMask));
-        return entry;
-    }
-
-    const VertexInputStateFactory::BackendVertexInputState& VertexInputStateFactory::GetOrCreateVertexInputState(
-        const MG_State::GLState::VertexArrayObject& vao, HashType hash) {
-        auto it = m_cache.find(hash);
-        if (it != m_cache.end()) {
-            it->second->lastUsedFrameBoundary = m_frameBoundaryCounter;
-            return *it->second;
-        }
-
-        VertexInputStateBuilder builder;
-        Vector<SizeT> bindingBufferKeys;
-        Vector<SizeT> bindingBaseOffsets;
-        Vector<Uint32> bindingAttributeLocations;
-        Vector<Bool> bindingUsesClientMemory;
-        Vector<VertexStreamConversion> bindingConversions;
-        Vector<VkVertexInputBindingDivisorDescriptionEXT> bindingDivisors;
-        Uint32 unsupportedAttribMask = 0;
-
-        for (Uint32 location = 0; location < MG_State::GLState::VertexArrayObject::MAX_VERTEX_ATTRIBS; ++location) {
-            const auto& attr = vao.GetAttribute(location);
-            if (!attr.Enabled) {
-                continue;
-            }
-
-            VkFormat sourceVkFormat =
-                ToVkVertexFormat(attr.Type, attr.Size, attr.Normalized, attr.IsInteger, attr.IsBgra, attr.IsLong);
-            VertexStreamConversion conversion = VertexStreamConversion::None;
-            // Gated on the SAME flag ToVkVertexFormat gates its 64-bit path on, and that is
-            // load-bearing rather than belt-and-braces: the narrowing is only correct because the
-            // shader's `dvec` input is a `vec` by the time the pipeline is built, and what
-            // guarantees that is the flag being clear. It is clear on every backend today, and a
-            // program with a 64-bit float vertex input is demoted WHOLE for the same reason even
-            // where the device has native fp64 (ProgramSpirvTask::GenerateSpirv). With the flag
-            // set, a dvec3/dvec4 would be declined by ToVkVertexFormat AND left 64-bit in the
-            // module, so a float32 stream would be fed to a Float64 input.
-            const Bool narrowFloat64Arrays =
-                MG_Backend::pActiveBackendObject == nullptr ||
-                !MG_Backend::pActiveBackendObject->GetDynamicParameters().SupportsFloat64VertexAttributes;
-            if (sourceVkFormat == VK_FORMAT_UNDEFINED && attr.Type == DataType::Float64 && narrowFloat64Arrays) {
-                // No native 64-bit fetch here (see ToVkVertexFormat's Float64 case), but the
-                // source bytes are ordinary IEEE-754 doubles and DemoteFloat64Pass has already
-                // narrowed every dvec input to a vec, so the array is narrowed to match rather
-                // than dropped. Mirrors what DirectGLES does for the same state.
-                const VkFormat narrowedFormat = ToFloat32VertexFormat(attr.Size);
-                if (narrowedFormat != VK_FORMAT_UNDEFINED && SupportsVertexBufferFormat(narrowedFormat)) {
-                    sourceVkFormat = narrowedFormat;
-                    conversion = VertexStreamConversion::Float64ToFloat32;
-                    MGLOG_W_ONCE("Vertex attribute location=%u is a 64-bit (GL_DOUBLE) array; fetching it at "
-                            "float32 precision through format=%d (size=%d long=%s)",
-                            location, static_cast<Int>(narrowedFormat), attr.Size, attr.IsLong ? "true" : "false");
-                }
-            }
-            if (sourceVkFormat == VK_FORMAT_UNDEFINED) {
-                MGLOG_E_ONCE("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;
-            }
-
-            VkFormat vkFormat = sourceVkFormat;
-            if (conversion == VertexStreamConversion::None && !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_ONCE("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_ONCE("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_ONCE("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;
-            }
-
-            // Verbatim, zero included. The frontend already resolved a pointer call's
-            // "tightly packed" stride 0 into the element size (see VertexAttribute::Stride),
-            // so a zero here is the binding model's stride 0 - every vertex reads the same
-            // element - which is exactly what a zero VkVertexInputBindingDescription::stride
-            // means. Substituting the element size fetched a fresh element per vertex and ran
-            // off the end of the buffer (KHR-GL43.vertex_attrib_binding.basic-input-case7/8).
-            // Client-memory arrays cannot reach zero: they only exist on the pointer path.
-            const Uint32 sourceStride = static_cast<Uint32>(attr.Stride);
-            const Bool packedAttribute = attr.Type == DataType::Int2101010Rev ||
-                                         attr.Type == DataType::Uint2101010Rev;
-            const SizeT requiredAlignment = packedAttribute ? attribByteSize : GetComponentSize(attr.Type);
-            // For a client-memory array attr.Offset holds the raw client pointer, and the
-            // draw path re-uploads the data to a 16-aligned transient slice with attribute
-            // offset 0, so only the stride can violate Vulkan's fetch alignment there.
-            const Bool clientMemoryAttribute = attr.Buffer == nullptr;
-            if (conversion == VertexStreamConversion::None && requiredAlignment > 1 &&
-                ((sourceStride % requiredAlignment) != 0 ||
-                 (!clientMemoryAttribute && (attr.Offset % requiredAlignment) != 0))) {
-                // GL accepts arbitrary byte strides and offsets. Core Vulkan vertex fetches do not
-                // unless VK_EXT_legacy_vertex_attributes is available, so deinterleave this one
-                // attribute into a tightly packed transient stream without changing its format.
-                conversion = VertexStreamConversion::Repack;
-                MGLOG_W_ONCE("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;
-            // A converted stream is tightly packed, so its stride is the converted element
-            // size - unless the source stride is zero, which does not describe a packing at
-            // all but "never advance". That survives the conversion unchanged: the draw path
-            // converts exactly one element and every vertex reads it.
-            if (sourceStride != 0) {
-                if (conversion == VertexStreamConversion::Repack) {
-                    stride = static_cast<Uint32>(attribByteSize);
-                } else if (conversion == VertexStreamConversion::ScaledIntegerToFloat32 ||
-                           conversion == VertexStreamConversion::Float64ToFloat32) {
-                    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;
-
-            const SizeT bufferKey = reinterpret_cast<SizeT>(attr.Buffer.get());
-            const Uint32 binding = static_cast<Uint32>(bindingBufferKeys.size());
-            bindingBufferKeys.push_back(bufferKey);
-            bindingBaseOffsets.push_back(attr.Buffer ? attr.Offset : 0);
-            bindingAttributeLocations.push_back(location);
-            bindingUsesClientMemory.push_back(attr.Buffer == nullptr);
-            bindingConversions.push_back(conversion);
-            builder.AddBinding(binding, stride, inputRate);
-            builder.AddAttribute(location, binding, vkFormat, 0);
-            // Divisor 1 is what VK_VERTEX_INPUT_RATE_INSTANCE already means; only anything
-            // else needs the extension to say it.
-            if (inputRate == VK_VERTEX_INPUT_RATE_INSTANCE && attr.Divisor != 1) {
-                bindingDivisors.push_back({binding, static_cast<Uint32>(attr.Divisor)});
-            }
-        }
-
-        const auto& state = builder.Build();
-
-        auto& slot = m_cache[hash];
-        if (!slot) {
-            slot = MakeUnique<BackendVertexInputState>();
-        }
-        BackendVertexInputState& entry = *slot;
-        entry.hash = hash;
-        entry.lastUsedFrameBoundary = m_frameBoundaryCounter;
-        entry.bindingDivisors = Move(bindingDivisors);
-        entry.bindings = builder.GetBindings();
-        entry.attributes = builder.GetAttributes();
-        // See the layoutHash declaration: hash only the resolved layout, never
-        // buffer identities, so identical layouts across VAOs/buffers agree.
-        XXHASH_VERIFY(XXH64_reset(m_hashState, 0));
-        for (const auto& binding : entry.bindings) {
-            XXHASH_VERIFY(XXH64_update(m_hashState, &binding.binding, sizeof(binding.binding)));
-            XXHASH_VERIFY(XXH64_update(m_hashState, &binding.stride, sizeof(binding.stride)));
-            XXHASH_VERIFY(XXH64_update(m_hashState, &binding.inputRate, sizeof(binding.inputRate)));
-        }
-        for (const auto& attribute : entry.attributes) {
-            XXHASH_VERIFY(XXH64_update(m_hashState, &attribute.location, sizeof(attribute.location)));
-            XXHASH_VERIFY(XXH64_update(m_hashState, &attribute.binding, sizeof(attribute.binding)));
-            XXHASH_VERIFY(XXH64_update(m_hashState, &attribute.format, sizeof(attribute.format)));
-            XXHASH_VERIFY(XXH64_update(m_hashState, &attribute.offset, sizeof(attribute.offset)));
-        }
-        for (const auto& divisor : entry.bindingDivisors) {
-            XXHASH_VERIFY(XXH64_update(m_hashState, &divisor.binding, sizeof(divisor.binding)));
-            XXHASH_VERIFY(XXH64_update(m_hashState, &divisor.divisor, sizeof(divisor.divisor)));
-        }
-        XXHASH_VERIFY(XXH64_update(m_hashState, &unsupportedAttribMask, sizeof(unsupportedAttribMask)));
-        entry.layoutHash = XXH64_digest(m_hashState);
-        entry.attributeLocationMask = 0;
-        for (const auto& attribute : entry.attributes) {
-            if (attribute.location < 32u) {
-                entry.attributeLocationMask |= (1u << attribute.location);
-            }
-        }
-        entry.bindingBufferKeys = std::move(bindingBufferKeys);
-        entry.bindingBaseOffsets = std::move(bindingBaseOffsets);
-        entry.bindingAttributeLocations = std::move(bindingAttributeLocations);
-        entry.bindingUsesClientMemory = std::move(bindingUsesClientMemory);
-        entry.bindingConversions = std::move(bindingConversions);
-        entry.unsupportedAttribMask = unsupportedAttribMask;
-        entry.state = state;
-        entry.state.pVertexBindingDescriptions = entry.bindings.empty() ? nullptr : entry.bindings.data();
-        entry.state.pVertexAttributeDescriptions = entry.attributes.empty() ? nullptr : entry.attributes.data();
-        if (!entry.bindingDivisors.empty()) {
-            entry.divisorState.vertexBindingDivisorCount = static_cast<Uint32>(entry.bindingDivisors.size());
-            entry.divisorState.pVertexBindingDivisors = entry.bindingDivisors.data();
-            entry.state.pNext = &entry.divisorState;
-        } else {
-            entry.state.pNext = nullptr;
-        }
-        return entry;
-    }
-
-    void VertexInputStateFactory::OnFrameBoundary() {
-        ++m_frameBoundaryCounter;
-
-        // Sweep occasionally; evict entries whose last hit is far in the past.
-        // Erasure happens only here, never mid-frame: the draw path holds a
-        // reference into the current entry across its setup, and unordered_map
-        // erase would invalidate it. Entries are CPU-side only, so no GPU-idle
-        // proof is needed; an evicted entry that is used again is simply rebuilt
-        // from the VAO state (same hash, same content).
-        constexpr Uint64 kSweepInterval = 256;
-        constexpr Uint64 kRetireAgeBoundaries = 1024;
-        if ((m_frameBoundaryCounter % kSweepInterval) != 0) {
-            return;
-        }
-
-        for (auto it = m_cache.begin(); it != m_cache.end();) {
-            if (m_frameBoundaryCounter - it->second->lastUsedFrameBoundary > kRetireAgeBoundaries) {
-                it = m_cache.erase(it);
-                // Invalidate every VAO's state-pointer memo: the erased node's
-                // address may be reused by a future insert. Advance through the
-                // process-wide source so the value stays unique across factory
-                // instances (see the member comment).
-                m_evictionEpoch = ++s_evictionEpochSource;
-            } else {
-                ++it;
-            }
-        }
-    }
-
-    VkFormat VertexInputStateFactory::ToVkVertexFormat(DataType type, Int size, Bool normalized, Bool isInteger,
-                                                       Bool isBgra, Bool isLong) {
-        if (isBgra) {
-            // GL_BGRA: four reversed-order components, always normalized (enforced at validation), only
-            // legal with GL_UNSIGNED_BYTE or a 2_10_10_10 type. The reversed VkFormats put the
-            // 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::Float64:
-            // A 64-bit attribute is fetched as its 32-bit word pair and bitcast back to double in the
-            // shader (PackDoubleVertexInputsPass does the shader half). That is bit-exact and, unlike
-            // VK_FORMAT_R64*_SFLOAT, needs no format capability: lavapipe reports bufferFeatures = 0
-            // for every R64 float format, so a native 64-bit vertex fetch is simply unavailable there
-            // while shaderFloat64 is not. Both halves key off nothing but the attribute being long,
-            // so they always agree without extra plumbing.
-            //
-            // ... as long as the shader half still runs. It does not when the backend has declared
-            // no 64-bit vertex attribute support: DemoteFloat64Pass has already narrowed every
-            // `dvec` input to a `vec` by then, so PackDoubleVertexInputsPass finds nothing to pack
-            // and a UINT-formatted attribute would be fed to a float input - garbage with no
-            // diagnostic anywhere. Declining here hands the attribute to the caller's
-            // Float64ToFloat32 fallback instead, which narrows the source doubles to match the
-            // demoted `vec` input - the same thing DirectGLES does for the same state. The
-            // frontend RECORDS the format either way, so this gate is the only thing standing
-            // between a legal glVertexAttribLFormat and a mismatched pipeline.
-            if (MG_Backend::pActiveBackendObject == nullptr ||
-                !MG_Backend::pActiveBackendObject->GetDynamicParameters().SupportsFloat64VertexAttributes) {
-                return VK_FORMAT_UNDEFINED;
-            }
-            if (!isLong || isInteger || normalized) return VK_FORMAT_UNDEFINED;
-            switch (size) {
-            case 1: return VK_FORMAT_R32G32_UINT;
-            case 2: return VK_FORMAT_R32G32B32A32_UINT;
-            // A dvec3/dvec4 input is 6/8 uint32 components: no single VkFormat, and GL spreads it
-            // over two attribute locations, which the location-per-VAO-index model here does not
-            // express. Declined rather than fetched wrong.
-            default: return VK_FORMAT_UNDEFINED;
-            }
-        case DataType::Float32:
-            switch (size) {
-            case 1: return VK_FORMAT_R32_SFLOAT;
-            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;
-            }
-        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) {
-            case 1: return VK_FORMAT_R32_SINT;
-            case 2: return VK_FORMAT_R32G32_SINT;
-            case 3: return VK_FORMAT_R32G32B32_SINT;
-            case 4: return VK_FORMAT_R32G32B32A32_SINT;
-            default: return VK_FORMAT_UNDEFINED;
-            }
-        case DataType::Uint32:
-            if (!isInteger || normalized) return VK_FORMAT_UNDEFINED;
-            switch (size) {
-            case 1: return VK_FORMAT_R32_UINT;
-            case 2: return VK_FORMAT_R32G32_UINT;
-            case 3: return VK_FORMAT_R32G32B32_UINT;
-            case 4: return VK_FORMAT_R32G32B32A32_UINT;
-            default: return VK_FORMAT_UNDEFINED;
-            }
-        case DataType::Int16:
-            switch (size) {
-            case 1:
-                return isInteger ? VK_FORMAT_R16_SINT : (normalized ? VK_FORMAT_R16_SNORM : VK_FORMAT_R16_SSCALED);
-            case 2:
-                return isInteger ? VK_FORMAT_R16G16_SINT
-                                 : (normalized ? VK_FORMAT_R16G16_SNORM : VK_FORMAT_R16G16_SSCALED);
-            case 3:
-                return isInteger ? VK_FORMAT_R16G16B16_SINT
-                                 : (normalized ? VK_FORMAT_R16G16B16_SNORM : VK_FORMAT_R16G16B16_SSCALED);
-            case 4:
-                return isInteger ? VK_FORMAT_R16G16B16A16_SINT
-                                 : (normalized ? VK_FORMAT_R16G16B16A16_SNORM : VK_FORMAT_R16G16B16A16_SSCALED);
-            default: return VK_FORMAT_UNDEFINED;
-            }
-        case DataType::Uint16:
-            switch (size) {
-            case 1:
-                return isInteger ? VK_FORMAT_R16_UINT : (normalized ? VK_FORMAT_R16_UNORM : VK_FORMAT_R16_USCALED);
-            case 2:
-                return isInteger ? VK_FORMAT_R16G16_UINT
-                                 : (normalized ? VK_FORMAT_R16G16_UNORM : VK_FORMAT_R16G16_USCALED);
-            case 3:
-                return isInteger ? VK_FORMAT_R16G16B16_UINT
-                                 : (normalized ? VK_FORMAT_R16G16B16_UNORM : VK_FORMAT_R16G16B16_USCALED);
-            case 4:
-                return isInteger ? VK_FORMAT_R16G16B16A16_UINT
-                                 : (normalized ? VK_FORMAT_R16G16B16A16_UNORM : VK_FORMAT_R16G16B16A16_USCALED);
-            default: return VK_FORMAT_UNDEFINED;
-            }
-        case DataType::Int8:
-            switch (size) {
-            case 1:
-                return isInteger ? VK_FORMAT_R8_SINT : (normalized ? VK_FORMAT_R8_SNORM : VK_FORMAT_R8_SSCALED);
-            case 2:
-                return isInteger ? VK_FORMAT_R8G8_SINT
-                                 : (normalized ? VK_FORMAT_R8G8_SNORM : VK_FORMAT_R8G8_SSCALED);
-            case 3:
-                return isInteger ? VK_FORMAT_R8G8B8_SINT
-                                 : (normalized ? VK_FORMAT_R8G8B8_SNORM : VK_FORMAT_R8G8B8_SSCALED);
-            case 4:
-                return isInteger ? VK_FORMAT_R8G8B8A8_SINT
-                                 : (normalized ? VK_FORMAT_R8G8B8A8_SNORM : VK_FORMAT_R8G8B8A8_SSCALED);
-            default: return VK_FORMAT_UNDEFINED;
-            }
-        case DataType::Uint8:
-            switch (size) {
-            case 1:
-                return isInteger ? VK_FORMAT_R8_UINT : (normalized ? VK_FORMAT_R8_UNORM : VK_FORMAT_R8_USCALED);
-            case 2:
-                return isInteger ? VK_FORMAT_R8G8_UINT
-                                 : (normalized ? VK_FORMAT_R8G8_UNORM : VK_FORMAT_R8G8_USCALED);
-            case 3:
-                return isInteger ? VK_FORMAT_R8G8B8_UINT
-                                 : (normalized ? VK_FORMAT_R8G8B8_UNORM : VK_FORMAT_R8G8B8_USCALED);
-            case 4:
-                return isInteger ? VK_FORMAT_R8G8B8A8_UINT
-                                 : (normalized ? VK_FORMAT_R8G8B8A8_UNORM : VK_FORMAT_R8G8B8A8_USCALED);
-            default: return VK_FORMAT_UNDEFINED;
-            }
-        default:
-            return VK_FORMAT_UNDEFINED;
-        }
-    }
-
-    SizeT VertexInputStateFactory::GetComponentSize(DataType type) {
-        switch (type) {
-        case DataType::Int8:
-        case DataType::Uint8:
-            return 1;
-        case DataType::Int16:
-        case DataType::Uint16:
-        case DataType::Float16:
-            return 2;
-        case DataType::Int32:
-        case DataType::Uint32:
-        case DataType::Float32:
-        case DataType::Fixed32:
-            return 4;
-        case DataType::Float64:
-            return 8;
-        default:
-            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

@@ -1,144 +0,0 @@
-// MobileGL - MobileGL/MG_Backend/DirectVulkan/Renderer/VertexInputStateFactory.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 "Config.h"
-#include "VertexInputStateBuilder.h"
-#include "MG_State/GLState/VertexArrayState/VertexArrayObject.h"
-#include <Includes.h>
-#include "../VkIncludes.h"
-
-namespace MobileGL::MG_Backend::DirectVulkan {
-    class VertexInputStateFactory {
-    public:
-        using HashType = Uint64;
-
-        enum class VertexStreamConversion : Uint8 {
-            None = 0,
-            Repack,
-            ScaledIntegerToFloat32,
-            // GL_DOUBLE source data narrowed to a tightly packed float32 stream: the fetch half
-            // of the fp64 demotion the shader side already does unconditionally.
-            Float64ToFloat32,
-        };
-
-        struct BackendVertexInputState {
-            HashType hash = 0;
-            // Hash of the resolved Vulkan vertex layout only (bindings, attributes,
-            // unsupported mask) - NO buffer identities. `hash` mixes each bound
-            // buffer's never-reused LIFETIME ID, so per-chunk VBOs mint a fresh
-            // identity per buffer; keying pipelines on that minted one VkPipeline per
-            // chunk section for an identical layout, defeating pipeline reuse and the
-            // per-draw memo. Pipelines depend only on the layout, so they key on this
-            // instead.
-            HashType layoutHash = 0;
-            // Frame boundary of the last cache hit; entries idle past the
-            // OnFrameBoundary retirement age are evicted (CPU heap only).
-            // Mutable: the VAO's state-pointer memo fast path stamps it through
-            // a const entry reference.
-            mutable Uint64 lastUsedFrameBoundary = 0;
-            Vector<VkVertexInputBindingDescription> bindings;
-            Vector<VkVertexInputAttributeDescription> attributes;
-            Vector<SizeT> bindingBufferKeys;
-            Vector<SizeT> bindingBaseOffsets;
-            Vector<Uint32> bindingAttributeLocations;
-            Vector<Bool> bindingUsesClientMemory;
-            Vector<VertexStreamConversion> bindingConversions;
-            // Locations whose array is ENABLED but whose GL format has no VkFormat mapping. They are
-            // absent from `attributes`, so without this mask the draw path cannot tell them apart from
-            // a genuinely disabled array and would silently feed the shader the current attribute value.
-            Uint32 unsupportedAttribMask = 0;
-            // Bitmask of `attributes[i].location` - the draw path needs it up to
-            // three times per draw, so it is baked once at build time.
-            Uint32 attributeLocationMask = 0;
-            // Per-binding glVertexAttribDivisor values other than 1. Vulkan's instance input
-            // rate advances once per instance and nothing else, so anything else has to be
-            // stated through VK_EXT_vertex_attribute_divisor. Empty when every instanced
-            // binding uses divisor 1, which is what the plain input rate already means.
-            Vector<VkVertexInputBindingDivisorDescriptionEXT> bindingDivisors;
-            VkPipelineVertexInputDivisorStateCreateInfoEXT divisorState{
-                VK_STRUCTURE_TYPE_PIPELINE_VERTEX_INPUT_DIVISOR_STATE_CREATE_INFO_EXT
-            };
-            VkPipelineVertexInputStateCreateInfo state{
-                VK_STRUCTURE_TYPE_PIPELINE_VERTEX_INPUT_STATE_CREATE_INFO
-            };
-        };
-
-        VertexInputStateFactory(const VulkanRendererConfig& config, VkPhysicalDevice physicalDevice):
-            m_config(config), m_physicalDevice(physicalDevice) {}
-        ~VertexInputStateFactory() = default;
-        VertexInputStateFactory(const VertexInputStateFactory&) = delete;
-
-        // The VAO aux-memo payload GetOrCreateVertexInputState(vao) stamps: aux0 is the
-        // entry's layoutHash, aux1 packs (unsupportedAttribMask << 32) | attributeLocationMask.
-        // Readers that find the aux memo valid can use these without resolving the entry.
-        static Uint64 PackVertexInputAuxMasks(Uint32 unsupportedAttribMask, Uint32 attributeLocationMask) {
-            return (static_cast<Uint64>(unsupportedAttribMask) << 32) | attributeLocationMask;
-        }
-
-        HashType ComputeHash(const MG_State::GLState::VertexArrayObject& vao) const;
-        // Memoized ComputeHash: reuses the VAO's cached hash while its config version
-        // is unchanged. Use this on per-draw paths.
-        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);
-        // Frame boundary hook: ages the cache and evicts entries not hit for many
-        // frames. The key mixes each bound buffer's never-reused lifetime id, so
-        // buffer/VAO churn keeps minting fresh keys - and does so by construction,
-        // not by luck: a recreated buffer can no longer land back on its dead
-        // predecessor's key. Without eviction the map grows for the whole session.
-        // Entries hold no Vulkan handles (pipeline creation copies the descriptions)
-        // and the draw path's entry reference never spans a frame boundary, so
-        // eviction here needs no GPU-idle proof. Self-gated: one counter bump and
-        // compare except on sweep boundaries.
-        void OnFrameBoundary();
-        static SizeT GetComponentSize(DataType type);
-        // Tightly-packed byte size of one vertex element for this attribute: componentSize * size for
-        // normal types, and 4 (one packed word) for the 2_10_10_10 types and GL_BGRA. Returns 0 for
-        // 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, Bool isBgra = false,
-                                         Bool isLong = false);
-        static Bool IsScaledIntegerVertexFormat(VkFormat format);
-        static VkFormat ToFloat32VertexFormat(Int componentCount);
-        Bool SupportsVertexBufferFormat(VkFormat format) const;
-
-        const VulkanRendererConfig& m_config;
-        VkPhysicalDevice m_physicalDevice = VK_NULL_HANDLE;
-        // Values are heap-allocated: UnorderedMap is open-addressing, so INSERT
-        // invalidates references to stored values - and so does ERASE, which shifts
-        // the rest of the probe cluster into the hole and therefore moves entries
-        // other than the erased one. The draw path (and the VAOs' state-pointer
-        // memos) hold entry pointers across both; only the unique_ptr cell moves,
-        // never the pointee.
-        UnorderedMap<HashType, UniquePtr<BackendVertexInputState>> m_cache;
-        // Monotonic frame-boundary counter (bumped in OnFrameBoundary) for cache aging.
-        Uint64 m_frameBoundaryCounter = 0;
-        // Bumped whenever any cache entry is erased. VAOs memo a raw pointer to
-        // their heap-allocated entry (stable across map insert/rehash by
-        // construction); a memo is honored only while its recorded epoch
-        // matches, so an evicted entry can never be dereferenced through a
-        // stale memo.
-        //
-        // Drawn from a process-wide source, never a per-instance counter: the VAO
-        // memos outlive this factory (they live on pGLContext's VAOs, the renderer
-        // is destroyed and recreated on EGL surface release/re-create), so a fresh
-        // factory restarting at a dead factory's epoch value would honor its
-        // dangling entry pointers. The constructor takes a value strictly greater
-        // than anything a predecessor ever stamped, so a dead factory's memo can
-        // never compare equal here - the same never-reused idiom as the lifetime ids.
-        // Single-threaded like the rest of the factory (renderer-thread only).
-        static inline Uint64 s_evictionEpochSource = 0;
-        Uint64 m_evictionEpoch = ++s_evictionEpochSource;
-        static inline XXH64_state_t* m_hashState = XXH64_createState();
-    };
-} // namespace MobileGL::MG_Backend::DirectVulkan

MobileGL/MG_Backend/DirectVulkan/Renderer/VkBufferManager.cpp

@@ -1,753 +0,0 @@
-// MobileGL - MobileGL/MG_Backend/DirectVulkan/Renderer/VkBufferManager.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 "VkBufferManager.h"
-#include "../DirectVulkan.h"
-#include "VulkanRenderer.h"
-
-namespace MobileGL::MG_Backend::DirectVulkan {
-    namespace {
-        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 |
-            // "Every usage" has to mean every usage: a buffer texture reached through an IMAGE
-            // unit takes a VK_DESCRIPTOR_TYPE_STORAGE_TEXEL_BUFFER descriptor, and the write is
-            // invalid unless the buffer was created with this bit. Nothing asked for it until
-            // imageBuffer support existed, so the omission was invisible.
-            VK_BUFFER_USAGE_STORAGE_TEXEL_BUFFER_BIT | VK_BUFFER_USAGE_TRANSFER_SRC_BIT;
-        // Appended to kPersistentBackedUsage when VK_EXT_transform_feedback is enabled
-        // (see VkBufferManagerInitInfo::transformFeedbackUsageEnabled).
-        constexpr VkBufferUsageFlags kTransformFeedbackUsage =
-            VK_BUFFER_USAGE_TRANSFORM_FEEDBACK_BUFFER_BIT_EXT;
-        // The app writes into the persistent map with no explicit flush, so its memory must
-        // be host-coherent (Adreno host-visible memory is; requiring it keeps us portable).
-        constexpr VkMemoryPropertyFlags kPersistentBackedRequiredFlags =
-            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);
-            }
-        }
-
-        // The CPU is about to read a buffer a shader wrote. Its bytes live in coherent
-        // host-visible GPU storage (EnsureGpuResidentStorage adopts it when the buffer is
-        // bound as a shader storage buffer), so nothing needs copying - but coherence only
-        // says the writes are visible once they have happened, so the work has to retire
-        // first.
-        void Ops_ReadbackFromGpu(BufferObject& bufferObject) {
-            (void)bufferObject;
-            if (pVulkanRenderer) {
-                pVulkanRenderer->FinishPendingGpuWork();
-            }
-        }
-
-        void* Ops_AcquirePersistentMap(BufferObject& bufferObject) {
-            if (g_activeBufferManager) {
-                return g_activeBufferManager->AcquirePersistentMap(bufferObject);
-            }
-            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,
-            .ReadbackFromGpu = Ops_ReadbackFromGpu,
-        };
-    } // namespace
-
-    Bool VkBufferManager::Initialize(const VkBufferManagerInitInfo& initInfo) {
-        Shutdown();
-
-        MOBILEGL_ASSERT(initInfo.allocator != nullptr, "VkBufferManager::Initialize requires valid allocator");
-        MOBILEGL_ASSERT(initInfo.frameCount > 0, "VkBufferManager::Initialize requires non-zero frame count");
-
-        m_initInfo = initInfo;
-        m_deferredBufferReleases.resize(initInfo.frameCount);
-        m_deferredResourceReleases.resize(initInfo.frameCount);
-        m_currentFrameIndex = 0;
-        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();
-        DestroyAllDeferredReleases();
-        ReleaseAllLiveResources();
-        m_copyProvider = nullptr;
-        m_initInfo = {};
-        m_currentFrameIndex = 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(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;
-        DestroyAllDeferredReleases();
-        m_deferredBufferReleases.resize(frameCount);
-        m_deferredResourceReleases.resize(frameCount);
-        m_currentFrameIndex = 0;
-        return InitializeTransientArenas();
-    }
-
-    void VkBufferManager::BeginFrame(Uint32 frameIndex) {
-        MOBILEGL_ASSERT(frameIndex < m_deferredBufferReleases.size(),
-                        "VkBufferManager::BeginFrame frame index out of range");
-        m_currentFrameIndex = frameIndex;
-        ++m_frameSerial;
-        CollectDeferredReleases(frameIndex);
-        m_transientUploadArena.BeginFrame(frameIndex);
-    }
-
-    void VkBufferManager::CollectAllDeferredReleases() {
-        // Per-resource releases only. Every one of them was deferred behind a BumpSliceEpoch,
-        // so no memo can still name the handle, and the caller has proved the GPU is idle.
-        //
-        // The transient arena's releases are deliberately NOT collected here. A buffer lands
-        // there when the arena outgrows it mid-frame (BufferArena::EnsureCapacity), and at
-        // that moment every slice already handed out from this frame's arena still names it -
-        // VkBufferResource::transientSlice above all, which AcquireStreamedSlice keeps
-        // serving for the whole frame serial on the strength of transientFrameSerial alone.
-        // Nothing bumps the slice epoch for those other resources, so freeing the buffer
-        // here left the streamed memo handing a destroyed VkBuffer to vkCmdBindIndexBuffer
-        // (llvmpipe then faulted inside the draw; the Create/Flywheel indirect retrace died
-        // exactly this way). Mid-frame drains do not advance m_frameSerial, so they must not
-        // free arena storage either: the arena's own ResetFrame/BeginFrame is the point where
-        // the slot's slices stop being reachable, and that is where these releases land.
-        for (Uint32 frameIndex = 0; frameIndex < m_deferredBufferReleases.size(); ++frameIndex) {
-            CollectDeferredReleases(frameIndex);
-        }
-    }
-
-    void VkBufferManager::NotifyDeviceIdle() {
-        // Everything submitted so far has completed. Work recorded for the
-        // current frame has not been submitted yet, so the current serial
-        // 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;
-        return m_transientUploadArena.Upload(frameIndex, data, size, alignment, outSlice);
-    }
-
-    Bool VkBufferManager::InitializeTransientArenas() {
-        return m_transientUploadArena.Initialize({
-            .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_TRANSFER_SRC_BIT,
-            .memoryUsage = m_initInfo.transientMemoryUsage,
-            .allocationFlags = m_initInfo.transientAllocationFlags,
-            .minBufferSize = m_initInfo.minUploadBytes,
-            .persistentlyMapped = m_initInfo.transientPersistentMapping,
-        });
-    }
-
-    VkBufferResource* VkBufferManager::ResourceOf(MG_State::GLState::BufferObject& bufferObject) {
-        return static_cast<VkBufferResource*>(bufferObject.GetBackendResource().get());
-    }
-
-    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;
-    }
-
-    void VkBufferManager::TrackLiveResource(const SharedPtr<VkBufferResource>& resource) {
-        // Sweep on a doubling watermark rather than on every insert past the threshold. The old
-        // form walked the whole vector for each new buffer once the list passed 256, and when the
-        // buffers are all live the walk removes nothing and the list grows by one - so creating N
-        // live buffers cost ~N^2/2 expired() checks. Reclamation semantics are unchanged: the sweep
-        // still removes exactly the expired entries, just less often and with the same bound on how
-        // much dead weight can accumulate (at most as many entries as were live at the last sweep).
-        if (m_liveResources.size() >= std::max<SizeT>(kLiveResourcePruneThreshold, 2 * m_liveResourcesLastPruned)) {
-            std::erase_if(m_liveResources, [](const WeakPtr<VkBufferResource>& weak) { return weak.expired(); });
-            m_liveResourcesLastPruned = m_liveResources.size();
-        }
-        m_liveResources.push_back(resource);
-    }
-
-    void VkBufferManager::ReleaseAllLiveResources() {
-        for (auto& weak : m_liveResources) {
-            if (auto resource = weak.lock()) {
-                BumpSliceEpoch(*resource);
-                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) {
-        // The only place a resident VkBuffer handle is minted, so every resident slice
-        // change funnels through here (callers release the old handle first).
-        BumpSliceEpoch(resource);
-        // Staged range copies write resident storage with vkCmdCopyBuffer.
-        usage |= VK_BUFFER_USAGE_TRANSFER_DST_BIT;
-        const Bool created = resource.buffer.Create({
-            .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_ONCE("VkBufferManager::CreateResidentStorage failed (size=%llu)",
-                    static_cast<unsigned long long>(size));
-            resource.buffer.Destroy();
-            resource.storageSize = 0;
-            resource.usageFlags = 0;
-            return false;
-        }
-        resource.storageSize = size;
-        resource.usageFlags = usage;
-        return true;
-    }
-
-    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;
-        }
-        if (!resource.buffer.Upload(bufferObject.MappedData(), size, 0)) {
-            MGLOG_E_ONCE("VkBufferManager::SwapStorageAndUploadAll: upload failed");
-            resource.pendingFullUpload = true;
-            return false;
-        }
-        resource.pendingFullUpload = false;
-        return true;
-    }
-
-    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
-        }
-        // A respecify can change the size, the usage hint (so the resident/streamed
-        // route), and the contents at once; retire every memo before deciding what to
-        // do about the storage.
-        BumpSliceEpoch(*resource);
-        // Any cached streaming slice refers to the previous contents.
-        resource->transientFrameSerial = 0;
-        // Redefining the store hands any adopted mapping back to the CPU shadow
-        // (BufferObject::RedefineStorage), so a buffer that reaches here persistent-mapped
-        // is an ordinary resident one again: it needs the busy-tracking and conditional
-        // orphan below, and the next AcquirePersistentMap has to mint storage for the new
-        // store rather than hand back a mapping of the old one.
-        resource->persistentMapped = false;
-        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_ONCE("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;
-        }
-        // Drops the streaming memo below and may end in a storage swap or a deferred
-        // full re-upload, so no memoised slice survives this.
-        BumpSliceEpoch(*resource);
-        resource->transientFrameSerial = 0;
-        if (!resource->buffer.IsValid() || resource->pendingFullUpload) {
-            return;
-        }
-        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_ONCE("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;
-        }
-        BumpSliceEpoch(*resource);
-        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_ONCE("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);
-        }
-
-        // Bumped for the request, not just for the storage it may create. This is the
-        // one call the frontend makes when a buffer becomes persistently mapped for
-        // writing (BufferObject::AcquireMemoryRange), and a map the backend declines
-        // keeps mutating its shadow with no further API call - so it is what lets
-        // GetSliceEpochCounter stand for "no buffer needs a persistent-map range push".
-        BumpSliceEpoch(*resource);
-
-        // Idempotent: an already-backed buffer returns the same mapped base.
-        if (resource->persistentMapped && resource->buffer.IsValid() && resource->storageSize == size) {
-            return resource->buffer.GetMappedData();
-        }
-
-        // 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));
-        const VkBufferUsageFlags persistentUsage =
-            kPersistentBackedUsage |
-            (m_initInfo.transformFeedbackUsageEnabled ? kTransformFeedbackUsage : 0);
-        if (!CreateResidentStorage(*resource, size, persistentUsage, 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_ONCE("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_ONCE("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();
-
-        // A persistently mapped resource's storage IS the application's copy of the bytes -
-        // the frontend adopted it in place of the shadow and hands out pointers into it, and
-        // a shader can have written bytes the shadow never saw (a transform feedback
-        // capture). Streaming a second copy would feed this draw the stale shadow, and the
-        // downgrade below would release the storage the application still points at,
-        // breaking the "never recreated" promise AcquirePersistentMap makes.
-        if (resource->persistentMapped) {
-            return AcquireResidentSlice(kind, bufferObject, outSlice);
-        }
-
-        const VkDeviceSize size = static_cast<VkDeviceSize>(bufferObject->GetSize());
-        if (size == 0) {
-            MGLOG_E_ONCE("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;
-        }
-
-        // Idle-content promotion: see the field comments in VkBufferResource. The
-        // streak counts frame BOUNDARIES survived unchanged (the same-frame memo
-        // above swallows repeat draws), so a promotion needs the content stable
-        // for kStreamedPromotionStreak whole frames - one no-op frame does not
-        // trigger the resident round-trip, whose creation upload is itself a
-        // staged copy worth avoiding for content that is about to change again.
-        constexpr Uint32 kStreamedPromotionStreak = 2;
-        if (resource->promotedResident) {
-            if (resource->promotedChangeSerial == changeSerial &&
-                static_cast<VkDeviceSize>(bufferObject->GetSize()) == size) {
-                return AcquireResidentSlice(kind, bufferObject, outSlice);
-            }
-            resource->promotedResident = false;
-            resource->unchangedStreak = 0;
-        } else if (resource->transientChangeSerial == changeSerial && resource->transientSize == size &&
-                   resource->transientFrameSerial != 0) {
-            if (++resource->unchangedStreak >= kStreamedPromotionStreak) {
-                // Promotion moves the buffer off the arena and onto resident storage.
-                resource->promotedResident = true;
-                resource->promotedChangeSerial = changeSerial;
-                BumpSliceEpoch(*resource);
-                if (AcquireResidentSlice(kind, bufferObject, outSlice)) {
-                    return true;
-                }
-                resource->promotedResident = false; // resident creation failed: stream as before
-            }
-        } else {
-            resource->unchangedStreak = 0;
-        }
-
-        // A fresh arena allocation: a different slice than the last call handed back,
-        // and (below) the point where a promoted buffer's resident storage is released.
-        // The stable-promotion exit above returns before this, so a buffer the app has
-        // stopped touching keeps one slice for as long as it keeps its resident storage.
-        BumpSliceEpoch(*resource);
-        if (!m_transientUploadArena.Upload(m_currentFrameIndex, bufferObject->MappedData(), size, 16,
-                                           outSlice)) {
-            return false;
-        }
-        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_deferredBufferReleases.empty()) {
-            buffer.Destroy();
-            return;
-        }
-
-        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::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) {
-        switch (kind) {
-        case BufferKind::Vertex:
-        case BufferKind::Index:
-            // A GL buffer can be rebound between ARRAY_BUFFER and ELEMENT_ARRAY_BUFFER,
-            // and may even be used as both within the same draw setup. Keep resident
-            // vertex/index buffers compatible with both roles from the start so we
-            // never need to recreate a buffer after it has already been bound.
-            return VK_BUFFER_USAGE_VERTEX_BUFFER_BIT | VK_BUFFER_USAGE_INDEX_BUFFER_BIT;
-        case BufferKind::Uniform:
-            return VK_BUFFER_USAGE_UNIFORM_BUFFER_BIT;
-        case BufferKind::TextureBuffer:
-            // Both texel roles, for the same reason vertex/index carry both bits: one GL buffer
-            // texture can be read as a samplerBuffer and written as an imageBuffer, and which of
-            // the two it is only becomes known when a shader that uses it is bound - long after
-            // the resident buffer was created. A VkBufferView for a storage-texel descriptor is
-            // invalid unless the buffer was created with the storage bit, so a buffer that
-            // acquired only the uniform bit could never be given one.
-            return VK_BUFFER_USAGE_UNIFORM_TEXEL_BUFFER_BIT | VK_BUFFER_USAGE_STORAGE_TEXEL_BUFFER_BIT;
-        case BufferKind::ShaderStorage:
-            return VK_BUFFER_USAGE_STORAGE_BUFFER_BIT | VK_BUFFER_USAGE_INDIRECT_BUFFER_BIT;
-        case BufferKind::Indirect:
-            return VK_BUFFER_USAGE_INDIRECT_BUFFER_BIT | VK_BUFFER_USAGE_STORAGE_BUFFER_BIT;
-        default:
-            return 0;
-        }
-    }
-
-    void VkBufferManager::DestroyAllDeferredReleases() {
-        for (auto& releases : m_deferredBufferReleases) {
-            for (auto& buffer : releases) {
-                buffer.Destroy();
-            }
-            releases.clear();
-        }
-        m_deferredBufferReleases.clear();
-        for (auto& releases : m_deferredResourceReleases) {
-            for (auto& resource : releases) {
-                resource->buffer.Destroy();
-            }
-            releases.clear();
-        }
-        m_deferredResourceReleases.clear();
-    }
-} // namespace MobileGL::MG_Backend::DirectVulkan

MobileGL/MG_Backend/DirectVulkan/Renderer/VkBufferManager.h

@@ -1,197 +0,0 @@
-// MobileGL - MobileGL/MG_Backend/DirectVulkan/Renderer/VkBufferManager.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 "BufferArena.h"
-#include "MG_State/GLState/BufferState/BufferObject.h"
-#include "../VkIncludes.h"
-#include <Includes.h>
-#include <vk_mem_alloc.h>
-
-namespace MobileGL::MG_Backend::DirectVulkan {
-    enum class BufferKind : Uint8 {
-        Vertex,
-        Index,
-        Uniform,
-        TextureBuffer,
-        ShaderStorage,
-        Indirect,
-    };
-
-    struct VkBufferManagerInitInfo {
-        VmaAllocator allocator = nullptr;
-        Uint32 frameCount = 0;
-        VkDeviceSize minUploadBytes = 4 * 1024 * 1024;
-        VmaMemoryUsage transientMemoryUsage = VMA_MEMORY_USAGE_AUTO;
-        VmaAllocationCreateFlags transientAllocationFlags = VMA_ALLOCATION_CREATE_HOST_ACCESS_SEQUENTIAL_WRITE_BIT;
-        Bool transientPersistentMapping = false;
-        // VK_EXT_transform_feedback is enabled: persistent-map storage additionally
-        // carries the transform feedback usage so capture targets can bind directly.
-        Bool transformFeedbackUsageEnabled = false;
-    };
-
-    // The DirectVulkan storage behind one frontend buffer (pipe_resource analogue).
-    // 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;
-
-        // Bumped from a manager-wide counter every time anything that decides which
-        // BufferSlice an Acquire*Slice call hands back changes: storage created or
-        // released, a full re-upload becoming due, a promotion/demotion between
-        // resident and streamed storage, or a new per-frame arena slice. Callers that
-        // memoise a resolved slice compare this to prove the memo still describes the
-        // buffer. The counter is manager-wide (never per-resource) so a freshly
-        // created resource - including one that replaces a destroyed resource at the
-        // same address - can never reproduce a value some memo already holds. 0 means
-        // "no slice has ever been handed out", which no memo can match.
-        Uint64 sliceEpoch = 0;
-
-        // Cached transient (streaming) slice for the current frame.
-        BufferSlice transientSlice{};
-        Uint64 transientFrameSerial = 0;
-        Uint64 transientChangeSerial = 0;
-        VkDeviceSize transientSize = 0;
-
-        // Streaming re-copies the whole store into the per-frame arena on every
-        // frame, which is right for genuinely per-frame data but pure waste for a
-        // Dynamic-hinted buffer the app stopped touching. After the content
-        // survives kStreamedPromotionStreak frame boundaries unchanged it is
-        // promoted to resident storage (one final upload, then zero per-frame
-        // cost); the first content change demotes it back to streaming, and the
-        // streaming path's existing downgrade releases the resident store.
-        Uint32 unchangedStreak = 0;
-        Bool promotedResident = false;
-        Uint64 promotedChangeSerial = 0;
-    };
-
-    // Supplies a command buffer that is recording and outside any render pass,
-    // 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);
-        void Shutdown();
-
-        // Recreate all per-frame transient arenas
-        Bool RecreateTransientArenas(Uint32 frameCount);
-        void BeginFrame(Uint32 frameIndex);
-        // Drains every frame slot's deferred buffer/resource releases. Only valid when
-        // the caller has proven every queue submission complete; used by the present-less
-        // frame-boundary drain. Deliberately does NOT touch the transient arena's parked
-        // superseded blocks: those are still named by this frame's slices (see the
-        // definition), and only a frame rewind retires them.
-        void CollectAllDeferredReleases();
-        // All previously submitted GPU work has completed (vkDeviceWaitIdle).
-        void NotifyDeviceIdle();
-        // A frame slot's submission fence has been waited: every serial up to
-        // 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);
-
-        // 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 value handed to any VkBufferResource::sliceEpoch. Unchanged since a
-        // memo was taken means no buffer this manager owns changed which slice it hands
-        // back, and none was persistently mapped, in between - so a memo of resolved
-        // slices needs no per-buffer re-check. See AcquirePersistentMap for the mapping half.
-        Uint64 GetSliceEpochCounter() const { return m_sliceEpochCounter; }
-        // Highest frame serial whose GPU work is known complete; serials at or
-        // below it may be considered signaled. Drives IsResourceBusy and the
-        // backend GL fence objects.
-        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:
-        Bool InitializeTransientArenas();
-        static VkBufferUsageFlags GetVkBufferUsage(BufferKind kind);
-        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();
-        // See VkBufferResource::sliceEpoch.
-        void BumpSliceEpoch(VkBufferResource& resource) { resource.sliceEpoch = ++m_sliceEpochCounter; }
-
-        VkBufferManagerInitInfo m_initInfo{};
-        BufferArena m_transientUploadArena;
-        IBufferCopyCommandProvider* m_copyProvider = nullptr;
-        Vector<Vector<VkBufferObject>> m_deferredBufferReleases;
-        Vector<Vector<SharedPtr<VkBufferResource>>> m_deferredResourceReleases;
-        Vector<WeakPtr<VkBufferResource>> m_liveResources;
-    // Size m_liveResources had just after the last sweep; the next sweep waits for it to double.
-    SizeT m_liveResourcesLastPruned = 0;
-        Uint32 m_currentFrameIndex = 0;
-        Uint64 m_frameSerial = 1;
-        Uint64 m_completedSerialFloor = 0;
-        // Never reset (not even by Shutdown): a value handed to a resource must stay
-        // unique for the process, or a memo taken before a re-initialize could match
-        // a different resource's state after it.
-        Uint64 m_sliceEpochCounter = 0;
-    };
-} // namespace MobileGL::MG_Backend::DirectVulkan

MobileGL/MG_Backend/DirectVulkan/Renderer/VkBufferObject.cpp

@@ -1,179 +0,0 @@
-// MobileGL - MobileGL/MG_Backend/DirectVulkan/Renderer/VkBufferObject.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 "VkBufferObject.h"
-
-namespace MobileGL::MG_Backend::DirectVulkan {
-    VkBufferObject::VkBufferObject(VkBufferObject&& other) noexcept {
-        m_allocator = other.m_allocator;
-        m_buffer = other.m_buffer;
-        m_allocation = other.m_allocation;
-        m_mappedData = other.m_mappedData;
-        m_size = other.m_size;
-
-        other.m_allocator = nullptr;
-        other.m_buffer = VK_NULL_HANDLE;
-        other.m_allocation = nullptr;
-        other.m_mappedData = nullptr;
-        other.m_size = 0;
-    }
-
-    VkBufferObject& VkBufferObject::operator=(VkBufferObject&& other) noexcept {
-        if (this == &other) {
-            return *this;
-        }
-
-        Destroy();
-
-        m_allocator = other.m_allocator;
-        m_buffer = other.m_buffer;
-        m_allocation = other.m_allocation;
-        m_mappedData = other.m_mappedData;
-        m_size = other.m_size;
-
-        other.m_allocator = nullptr;
-        other.m_buffer = VK_NULL_HANDLE;
-        other.m_allocation = nullptr;
-        other.m_mappedData = nullptr;
-        other.m_size = 0;
-        return *this;
-    }
-
-    VkBufferObject::~VkBufferObject() {
-        Destroy();
-    }
-
-    Bool VkBufferObject::Create(const VkBufferObjectDesc& desc) {
-        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,
-                                VkMemoryPropertyFlags requiredFlags) {
-        MOBILEGL_ASSERT(allocator != nullptr, "VkBufferObject::Create requires valid VMA allocator");
-        MOBILEGL_ASSERT(size > 0, "VkBufferObject::Create requires non-zero size");
-
-        Destroy();
-        m_allocator = allocator;
-
-        VkBufferCreateInfo bufferInfo{};
-        bufferInfo.sType = VK_STRUCTURE_TYPE_BUFFER_CREATE_INFO;
-        bufferInfo.size = size;
-        bufferInfo.usage = usage;
-        bufferInfo.sharingMode = VK_SHARING_MODE_EXCLUSIVE;
-
-        VmaAllocationCreateInfo allocationInfo{};
-        allocationInfo.usage = memoryUsage;
-        allocationInfo.flags = allocationFlags;
-        allocationInfo.requiredFlags = requiredFlags;
-
-        const VkResult result =
-            vmaCreateBuffer(m_allocator, &bufferInfo, &allocationInfo, &m_buffer, &m_allocation, nullptr);
-        if (result != VK_SUCCESS) {
-            MGLOG_E_ONCE("VkBufferObject::Create failed: vmaCreateBuffer returned %d", result);
-            m_allocator = nullptr;
-            m_buffer = VK_NULL_HANDLE;
-            m_allocation = nullptr;
-            m_size = 0;
-            return false;
-        }
-
-        m_size = size;
-        return true;
-    }
-
-    void VkBufferObject::Destroy() {
-        Unmap();
-        if (m_allocator != nullptr && m_buffer != VK_NULL_HANDLE && m_allocation != nullptr) {
-            vmaDestroyBuffer(m_allocator, m_buffer, m_allocation);
-        }
-        m_buffer = VK_NULL_HANDLE;
-        m_allocation = nullptr;
-        m_allocator = nullptr;
-        m_size = 0;
-    }
-
-    void* VkBufferObject::Map() {
-        MOBILEGL_ASSERT(IsValid(), "VkBufferObject::Map called on invalid buffer");
-
-        if (m_mappedData != nullptr) {
-            return m_mappedData;
-        }
-
-        const VkResult mapResult = vmaMapMemory(m_allocator, m_allocation, &m_mappedData);
-        if (mapResult != VK_SUCCESS || m_mappedData == nullptr) {
-            MGLOG_E_ONCE("VkBufferObject::Map failed: vmaMapMemory returned %d", mapResult);
-            m_mappedData = nullptr;
-            return nullptr;
-        }
-
-        return m_mappedData;
-    }
-
-    void VkBufferObject::Unmap() {
-        if (!IsValid() || m_mappedData == nullptr) {
-            m_mappedData = nullptr;
-            return;
-        }
-
-        vmaUnmapMemory(m_allocator, m_allocation);
-        m_mappedData = nullptr;
-    }
-
-    Bool VkBufferObject::Upload(const void* data, VkDeviceSize size, VkDeviceSize offset) {
-        MOBILEGL_ASSERT(IsValid(), "VkBufferObject::Upload called on invalid buffer");
-        MOBILEGL_ASSERT(data != nullptr || size == 0, "VkBufferObject::Upload data pointer is null");
-        MOBILEGL_ASSERT(offset + size <= m_size, "VkBufferObject::Upload out of range");
-
-        if (size == 0) {
-            return true;
-        }
-
-        const Bool wasMapped = IsMapped();
-        void* mapped = wasMapped ? m_mappedData : Map();
-        if (mapped == nullptr) {
-            MGLOG_E_ONCE("VkBufferObject::Upload failed: unable to map buffer");
-            return false;
-        }
-
-        Memcpy(static_cast<Uint8*>(mapped) + offset, data, static_cast<SizeT>(size));
-        const VkResult flushResult = vmaFlushAllocation(m_allocator, m_allocation, offset, size);
-        if (flushResult != VK_SUCCESS) {
-            MGLOG_E_ONCE("VkBufferObject::Upload failed: vmaFlushAllocation returned %d", flushResult);
-            if (!wasMapped) {
-                Unmap();
-            }
-            return false;
-        }
-        if (!wasMapped) {
-            Unmap();
-        }
-        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_ONCE("VkBufferObject::Invalidate failed: vmaInvalidateAllocation returned %d", result);
-            return false;
-        }
-        return true;
-    }
-
-} // namespace MobileGL::MG_Backend::DirectVulkan

MobileGL/MG_Backend/DirectVulkan/Renderer/VkBufferObject.h

@@ -1,76 +0,0 @@
-// MobileGL - MobileGL/MG_Backend/DirectVulkan/Renderer/VkBufferObject.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 "BufferSlice.h"
-#include "../VkIncludes.h"
-#include <Includes.h>
-#include <vk_mem_alloc.h>
-
-namespace MobileGL::MG_Backend::DirectVulkan {
-    struct VkBufferObjectDesc {
-        VmaAllocator allocator = nullptr;
-        VkDeviceSize size = 0;
-        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 {
-    public:
-        VkBufferObject() = default;
-        ~VkBufferObject();
-
-        VkBufferObject(const VkBufferObject&) = delete;
-        VkBufferObject& operator=(const VkBufferObject&) = delete;
-        VkBufferObject(VkBufferObject&& other) noexcept;
-        VkBufferObject& operator=(VkBufferObject&& other) noexcept;
-
-        Bool Create(const VkBufferObjectDesc& desc);
-        Bool Create(VmaAllocator allocator, VkDeviceSize size, VkBufferUsageFlags usage,
-                    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; }
-        // Inline: runs on the per-draw acquire path (a resident buffer bind is a
-        // GetSlice per binding), where an out-of-line call was measurable.
-        BufferSlice GetSlice(VkDeviceSize offset = 0, VkDeviceSize size = VK_WHOLE_SIZE) const {
-            MOBILEGL_ASSERT(offset <= m_size, "VkBufferObject::GetSlice offset out of range");
-            const VkDeviceSize resolvedSize = (size == VK_WHOLE_SIZE) ? (m_size - offset) : size;
-            MOBILEGL_ASSERT(offset + resolvedSize <= m_size, "VkBufferObject::GetSlice range out of bounds");
-
-            BufferSlice slice{};
-            slice.buffer = m_buffer;
-            slice.offset = offset;
-            slice.size = resolvedSize;
-            slice.mapped = (m_mappedData != nullptr) ? static_cast<Uint8*>(m_mappedData) + offset : nullptr;
-            return slice;
-        }
-        void* GetMappedData() const { return m_mappedData; }
-        Bool IsMapped() const { return m_mappedData != nullptr; }
-        Bool IsValid() const { return m_allocator != nullptr && m_buffer != VK_NULL_HANDLE && m_allocation != nullptr; }
-
-    private:
-        VmaAllocator m_allocator = nullptr;
-        VkBuffer m_buffer = VK_NULL_HANDLE;
-        VmaAllocation m_allocation = nullptr;
-        void* m_mappedData = nullptr;
-        VkDeviceSize m_size = 0;
-    };
-} // namespace MobileGL::MG_Backend::DirectVulkan

MobileGL/MG_Backend/DirectVulkan/Renderer/VkClearManager.cpp

@@ -1,491 +0,0 @@
-// MobileGL - MobileGL/MG_Backend/DirectVulkan/Renderer/VkClearManager.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 "VkClearManager.h"
-
-#include "MG_State/GLState/Core.h"
-#include "MG_Util/Converters/MGToStr/FramebufferEnumConverter.h"
-#include "MG_Util/Converters/MGToStr/TextureEnumConverter.h"
-
-#include <algorithm>
-#include <cmath>
-
-namespace MobileGL::MG_Backend::DirectVulkan {
-    static Bool IsCubeMapFaceUploadTarget(TextureUploadTarget target) {
-        return target >= TextureUploadTarget::CubeMapPositiveX &&
-               target <= TextureUploadTarget::CubeMapNegativeZ;
-    }
-
-    VkClearColorValue MakeVkClearColorValue(const ClearAttachmentPayload& payload, Bool formatLacksAlpha) {
-        VkClearColorValue clearValue{};
-        switch (payload.colorEncoding) {
-        case ClearColorEncoding::Int:
-            clearValue.int32[0] = payload.colorInt.x();
-            clearValue.int32[1] = payload.colorInt.y();
-            clearValue.int32[2] = payload.colorInt.z();
-            clearValue.int32[3] = formatLacksAlpha ? 1 : payload.colorInt.w();
-            break;
-        case ClearColorEncoding::Uint:
-            clearValue.uint32[0] = payload.colorUint.x();
-            clearValue.uint32[1] = payload.colorUint.y();
-            clearValue.uint32[2] = payload.colorUint.z();
-            clearValue.uint32[3] = formatLacksAlpha ? 1u : payload.colorUint.w();
-            break;
-        case ClearColorEncoding::Float:
-            clearValue.float32[0] = payload.color.x();
-            clearValue.float32[1] = payload.color.y();
-            clearValue.float32[2] = payload.color.z();
-            clearValue.float32[3] = formatLacksAlpha ? 1.0f : payload.color.w();
-            break;
-        }
-        return clearValue;
-    }
-
-    void PreCompensateSrgbClearColor(ClearAttachmentPayload& payload, VkFormat destinationFormat) {
-        if (payload.colorEncoding != ClearColorEncoding::Float) return;
-        // With GL_FRAMEBUFFER_SRGB enabled GL performs the encoding itself, so the driver doing it
-        // is exactly right and there is nothing to undo.
-        if (MG_State::pGLContext->IsCapabilityEnabled(MobileGL::CapabilityInput::FramebufferSrgb)) return;
-        if (ResolveSrgbAttachmentWriteFormat(destinationFormat, false) == destinationFormat) return;
-
-        // sRGB -> linear (GL 4.6 core 8.24), applied to the colour channels only: alpha is stored
-        // linearly in an sRGB format and must pass through untouched.
-        const auto toLinear = [](Float encoded) {
-            const Float value = std::clamp(encoded, 0.0f, 1.0f);
-            return value <= 0.04045f ? value / 12.92f : std::pow((value + 0.055f) / 1.055f, 2.4f);
-        };
-        payload.color = FloatVec4(toLinear(payload.color.x()), toLinear(payload.color.y()),
-                                  toLinear(payload.color.z()), payload.color.w());
-    }
-
-    void ForceOpaqueClearAlpha(ClearAttachmentPayload& payload) {
-        switch (payload.colorEncoding) {
-        case ClearColorEncoding::Int:
-            payload.colorInt = IntVec4(payload.colorInt.x(), payload.colorInt.y(), payload.colorInt.z(), 1);
-            break;
-        case ClearColorEncoding::Uint:
-            payload.colorUint = UintVec4(payload.colorUint.x(), payload.colorUint.y(), payload.colorUint.z(), 1u);
-            break;
-        case ClearColorEncoding::Float:
-            payload.color = FloatVec4(payload.color.x(), payload.color.y(), payload.color.z(), 1.0f);
-            break;
-        }
-    }
-
-    static Bool PendingClearMatchesTextureIdentity(const PendingClearKey& key, const TextureIdentity& identity) {
-        return key.texture == identity.texture && key.textureLifetimeId == identity.lifetimeId;
-    }
-
-    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;
-        }
-
-        const auto& attachment = drawFbo.GetAttachment(attachmentType);
-        if (!attachment.IsTexture() || attachment.IsRenderbuffer()) {
-            return nullptr;
-        }
-
-        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() {
-        return true;
-    }
-
-    void VkClearManager::Shutdown() {
-        const std::lock_guard<std::mutex> lock(m_mutex);
-        m_pendingClears.clear();
-        m_aliveObjects.clear();
-        m_pendingCount.store(static_cast<Uint32>(m_pendingClears.size()), std::memory_order_relaxed);
-    }
-
-    TextureIdentity VkClearManager::MakeTextureIdentity(MG_State::GLState::ITextureObject* texture) {
-        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) {
-            // The whole colour story travels together (same rule as
-            // VkRenderPassManager::QueueRenderbufferClear): a glClearBufferiv/uiv
-            // payload carries its value in colorInt/colorUint and its branch selector
-            // in colorEncoding - dropping them here would leave the pending clear
-            // reading as an all-zero float one.
-            dst.color = src.color;
-            dst.colorEncoding = src.colorEncoding;
-            dst.colorInt = src.colorInt;
-            dst.colorUint = src.colorUint;
-        }
-        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);
-        m_pendingCount.store(static_cast<Uint32>(m_pendingClears.size()), std::memory_order_relaxed);
-    }
-
-    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,
-                                    const MG_State::GLState::FramebufferObject& drawFbo) {
-        if (mask & GL_COLOR_BUFFER_BIT) {
-            auto& drawbufs = drawFbo.GetDrawBuffers();
-            // This should automatically work on default & offscreen FBO
-            for (auto drawbuf: drawbufs) {
-                const auto* attachment = GetClearableAttachment(drawFbo, drawbuf);
-                if (!attachment) {
-                    continue;
-                }
-
-                QueueClear({
-                    .mask = GL_COLOR_BUFFER_BIT,
-                    .color = clearPayload.color
-                }, *attachment);
-
-                MGLOG_D("%s: %s (texture %d) - color = (%.2f, %.2f, %.2f, %.2f)", __func__,
-                    MG_Util::ConvertFramebufferAttachmentTypeToString(drawbuf).c_str(),
-                    attachment->GetTexture()->GetExternalIndex(),
-                    clearPayload.color[0], clearPayload.color[1], clearPayload.color[2], clearPayload.color[3]);
-            }
-        }
-
-        if (mask & GL_DEPTH_BUFFER_BIT) {
-            const auto* attachment = GetClearableAttachment(drawFbo, FramebufferAttachmentType::Depth);
-            if (attachment) {
-                QueueClear({
-                    .mask = GL_DEPTH_BUFFER_BIT,
-                    .depth = clearPayload.depth,
-                }, *attachment);
-
-                MGLOG_D("%s: Depth (texture %d) - depth = (%.2f)", __func__,
-                    attachment->GetTexture()->GetExternalIndex(), clearPayload.depth);
-            }
-        }
-
-        if (mask & GL_STENCIL_BUFFER_BIT) {
-            const auto* attachment = GetClearableAttachment(drawFbo, FramebufferAttachmentType::Stencil);
-            if (attachment) {
-                QueueClear({
-                    .mask = GL_STENCIL_BUFFER_BIT,
-                    .stencil = clearPayload.stencil,
-                }, *attachment);
-
-                MGLOG_D("%s: Stencil (texture %d) - stencil = (%u)", __func__,
-                    attachment->GetTexture()->GetExternalIndex(), clearPayload.stencil);
-            }
-        }
-    }
-
-    void VkClearManager::QueueClear(const ClearAttachmentPayload& clearPayload,
-                                    const SharedPtr<MG_State::GLState::ITextureObject>& texture) {
-        if (clearPayload.mask == 0 || !texture) {
-            return;
-        }
-
-        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);
-        m_pendingCount.store(static_cast<Uint32>(m_pendingClears.size()), std::memory_order_relaxed);
-    }
-
-    void VkClearManager::QueueClear(const ClearAttachmentPayload& clearPayload,
-                                    const MG_State::GLState::FramebufferAttachmentObject& attachment) {
-        if (clearPayload.mask == 0 || !attachment.IsTexture() || attachment.IsRenderbuffer()) {
-            return;
-        }
-        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);
-        m_pendingCount.store(static_cast<Uint32>(m_pendingClears.size()), std::memory_order_relaxed);
-    }
-
-    Bool VkClearManager::HasPendingClear(MG_State::GLState::ITextureObject* texture) {
-        if (texture == nullptr) {
-            return false;
-        }
-
-        if (m_pendingCount.load(std::memory_order_relaxed) == 0) {
-            return false;  // per-draw hot path: nothing pending anywhere
-        }
-
-        const Uint64 lifetimeId = texture->GetLifetimeId();
-        const std::lock_guard<std::mutex> lock(m_mutex);
-        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;
-        }
-        if (m_pendingCount.load(std::memory_order_relaxed) == 0) {
-            return false;  // per-draw hot path: nothing pending anywhere
-        }
-
-        const std::lock_guard<std::mutex> lock(m_mutex);
-        if (m_pendingClears.find(key) == m_pendingClears.end()) {
-            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;
-        }
-        if (m_pendingCount.load(std::memory_order_relaxed) == 0) {
-            return false;  // per-draw hot path: nothing pending anywhere
-        }
-
-        const std::lock_guard<std::mutex> lock(m_mutex);
-        if (!LockTextureLocked(key, outTexture)) {
-            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,
-            outPayload.stencil);
-        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;
-        }
-        if (m_pendingCount.load(std::memory_order_relaxed) == 0) {
-            return false;  // per-draw hot path: nothing pending anywhere
-        }
-
-        const Uint64 lifetimeId = texture->GetLifetimeId();
-        const std::lock_guard<std::mutex> lock(m_mutex);
-        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) {
-        if (texture == nullptr) {
-            return;
-        }
-
-        if (m_pendingCount.load(std::memory_order_relaxed) == 0) {
-            return;  // per-draw hot path: nothing pending anywhere
-        }
-        const TextureIdentity identity = MakeTextureIdentity(texture);
-        MGLOG_D("%s: Pop all pending clears for texture %d", __func__, texture->GetExternalIndex());
-        const std::lock_guard<std::mutex> lock(m_mutex);
-        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);
-            m_pendingCount.store(static_cast<Uint32>(m_pendingClears.size()), std::memory_order_relaxed);
-            }
-        }
-
-        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;
-        }
-
-        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);
-            }
-        }
-        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

@@ -1,168 +0,0 @@
-// MobileGL - MobileGL/MG_Backend/DirectVulkan/Renderer/VkClearManager.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 "../VulkanRendererConfig.h"
-#include "MG_State/GLState/FramebufferState/FramebufferObject.h"
-#include "MG_Util/Math/VectorTypes.h"
-
-#include <Includes.h>
-#include <atomic>
-#include <unordered_map>
-
-namespace MobileGL::MG_Backend::DirectVulkan {
-    struct ClearFramebufferPayload {
-        FloatVec4 color;
-        Float depth{};
-        Uint32 stencil{};
-    };
-
-    // A colour clear reaches us from one of glClear/ClearBufferfv, ClearBufferiv or
-    // ClearBufferuiv, and Vulkan reads VkClearColorValue's union according to the destination
-    // image's format rather than converting between the members - a float written where an
-    // integer format is expected is reinterpreted bit for bit, not rounded. Remember which entry
-    // point supplied the value so the member written when the clear is materialized matches.
-    enum class ClearColorEncoding : Uint8 { Float, Int, Uint };
-
-    struct ClearAttachmentPayload {
-        GLbitfield mask = 0;
-        FloatVec4 color = FloatVec4(0.0f, 0.0f, 0.0f, 0.0f);
-        ClearColorEncoding colorEncoding = ClearColorEncoding::Float;
-        IntVec4 colorInt = IntVec4(0, 0, 0, 0);
-        UintVec4 colorUint = UintVec4(0u, 0u, 0u, 0u);
-        Float depth = 1.0f;
-        Uint32 stencil = 0;
-    };
-
-    // Builds the clear value for `payload` in the union member its encoding calls for.
-    // `formatLacksAlpha` applies GL's rule that a format without an alpha channel reads as one,
-    // expressed in whichever type matches (GL 4.6 core 15.2.3).
-    VkClearColorValue MakeVkClearColorValue(const ClearAttachmentPayload& payload, Bool formatLacksAlpha);
-
-    // Applies that same rule in place, for the paths that have to bake it into the payload before
-    // the destination is known.
-    void ForceOpaqueClearAlpha(ClearAttachmentPayload& payload);
-
-    // vkCmdClearColorImage names the image, so the driver applies the destination format's transfer
-    // function to whatever value it is handed. Every other write path in this backend goes through
-    // the UNORM twin view while GL_FRAMEBUFFER_SRGB is off (ResolveSrgbAttachmentWriteFormat) and
-    // therefore stores the raw value GL asked for. Rewrites `payload` to the linear colour whose
-    // encoding is that raw value, so a direct image clear of an sRGB destination agrees with them.
-    // A no-op for every other format, for integer clear encodings, and when GL is doing the
-    // encoding itself.
-    void PreCompensateSrgbClearColor(ClearAttachmentPayload& payload, VkFormat destinationFormat);
-
-    struct PendingClearKey {
-        MG_State::GLState::ITextureObject* texture = nullptr;
-        Uint64 textureLifetimeId = 0;
-        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();
-
-        void QueueClear(GLbitfield mask, const ClearFramebufferPayload& clearPayload, const MG_State::GLState::FramebufferObject& drawFbo);
-        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 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;
-    public:
-        // Lock-free probe for the consecutive-draw fast path: any pending clear
-        // forces the full SetupDraw path (which materializes/consumes it).
-        Bool HasAnyPendingClears() const { return m_pendingCount.load(std::memory_order_relaxed) != 0; }
-
-    private:
-        mutable std::mutex m_mutex;
-        // Lock-free mirror of m_pendingClears.size(), maintained under m_mutex
-        // by every mutation. The per-draw probes (HasPendingClear/GetPending*)
-        // read it before taking the lock: during draw batches the pending set
-        // is almost always empty, so this turns several locked map probes per
-        // draw into one relaxed load.
-        std::atomic<Uint32> m_pendingCount{0};
-        std::unordered_map<PendingClearKey, ClearAttachmentPayload, PendingClearKeyHash> m_pendingClears;
-        std::unordered_map<TextureIdentity, WeakPtr<MG_State::GLState::ITextureObject>, TextureIdentityHash> m_aliveObjects;
-    };
-} // namespace MobileGL::MG_Backend::DirectVulkan

MobileGL/MG_Backend/DirectVulkan/Renderer/VkRenderPassManager.h

@@ -1,407 +0,0 @@
-// MobileGL - MobileGL/MG_Backend/DirectVulkan/Renderer/VkRenderPassManager.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 "SwapchainObject.h"
-#include "VkClearManager.h"
-#include "VkTextureManager.h"
-#include "../VkIncludes.h"
-#include "../VulkanRendererConfig.h"
-#include "MG_State/GLState/FramebufferState/FramebufferObject.h"
-
-#include <Includes.h>
-#include <unordered_map>
-#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;
-        // 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;
-        WeakPtr<MG_State::GLState::ITextureObject> texture;
-        // Identity-compare shortcut for the per-draw "does the active pass use
-        // this sampled texture" probe: comparing this against a LIVE texture's
-        // address needs no weak_ptr::lock (two refcount atomics per probe).
-        // May dangle once the texture dies - compare only, never dereference.
-        MG_State::GLState::ITextureObject* textureRaw = nullptr;
-        WeakPtr<MG_State::GLState::RenderbufferObject> renderbuffer;
-        Uint32 textureMipLevel = 0;
-        Uint32 swapchainImageIndex = 0;
-        VkImageLayout finalLayout = VK_IMAGE_LAYOUT_UNDEFINED;
-    };
-
-    struct DepthStencilAttachmentLoadInfo {
-        VkAttachmentLoadOp depthLoadOp = VK_ATTACHMENT_LOAD_OP_LOAD;
-        VkAttachmentLoadOp stencilLoadOp = VK_ATTACHMENT_LOAD_OP_LOAD;
-        VkImageLayout initialLayout = VK_IMAGE_LAYOUT_UNDEFINED;
-    };
-
-    DepthStencilAttachmentLoadInfo ResolveDepthStencilAttachmentLoadInfo(
-        VkImageLayout trackedLayout, Bool clearDepth, Bool clearStencil);
-    IntVec2 ResolveRenderPassFramebufferExtent(Bool isDefaultFbo, const TextureSize& attachmentExtent,
-                                               VkExtent2D swapchainExtent);
-
-    struct RenderPassEntry {
-        static inline VkDevice s_device;
-        static inline Vector<VkTextureManager::TextureResource*> s_textureResourcesScratch;
-        Uint64 hash = 0;
-        VkRenderPass renderPass = VK_NULL_HANDLE;
-        VkFramebuffer framebuffer = VK_NULL_HANDLE;
-        Uint64 compatibilityHash = 0;
-        Vector<PendingClearAttachmentInfo> pendingClearAttachments;
-        Vector<TrackedAttachmentLayoutInfo> trackedAttachmentLayouts;
-        Uint32 attachmentCount = 0;
-        Uint32 colorAttachmentCount = 0;
-        Bool hasDepthStencilAttachment = false;
-        VkSampleCountFlagBits sampleCount = VK_SAMPLE_COUNT_1_BIT;
-        IntVec2 extent = {0, 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;
-        RenderPassEntry(RenderPassEntry&& that) noexcept {
-            std::swap(hash, that.hash);
-            std::swap(renderPass, that.renderPass);
-            std::swap(framebuffer, that.framebuffer);
-            std::swap(compatibilityHash, that.compatibilityHash);
-            std::swap(pendingClearAttachments, that.pendingClearAttachments);
-            std::swap(trackedAttachmentLayouts, that.trackedAttachmentLayouts);
-            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(layers, that.layers);
-            std::swap(lastUsedFrame, that.lastUsedFrame);
-        }
-        // Move ASSIGNMENT, not just construction. The move constructor above and the
-        // destructor below each independently suppress the implicit one, which left the
-        // type move-constructible but not move-assignable - and therefore not swappable,
-        // which std::swap(pair&, pair&) requires. That was invisible while UnorderedMap
-        // only ever move-CONSTRUCTED an element into a fresh slot. ska::flat_hash_map
-        // probes robin-hood: inserting swaps the entry being placed against the one
-        // already sitting in the slot whenever it has travelled further from its desired
-        // position, so the mapped type has to be swappable or the table fails to
-        // instantiate at all.
-        //
-        // SWAP SEMANTICS, exactly like the move constructor: this does not release the
-        // destination's handles, it parks them in `that`, which destroys them when it
-        // dies. That is correct for the only caller - std::swap, whose temporary expires
-        // immediately - and it is what keeps the three-move sequence from destroying a
-        // live render pass. It is NOT correct for a hand-written `a = std::move(b)` where
-        // `a` held live handles and `b` outlives the statement: those handles would then
-        // survive until `b` dies. There is no such caller; add a destroy-then-steal
-        // assignment before writing one.
-        RenderPassEntry& operator=(RenderPassEntry&& that) noexcept {
-            if (this != &that) {
-                std::swap(hash, that.hash);
-                std::swap(renderPass, that.renderPass);
-                std::swap(framebuffer, that.framebuffer);
-                std::swap(compatibilityHash, that.compatibilityHash);
-                std::swap(pendingClearAttachments, that.pendingClearAttachments);
-                std::swap(trackedAttachmentLayouts, that.trackedAttachmentLayouts);
-                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(layers, that.layers);
-                std::swap(lastUsedFrame, that.lastUsedFrame);
-            }
-            return *this;
-        }
-        RenderPassEntry(
-            Uint64 hash,
-            VkRenderPass renderpass,
-            VkFramebuffer framebuffer,
-            Uint64 compatibilityHash,
-            const Vector<PendingClearAttachmentInfo>& pendingClearAttachments,
-            const Vector<TrackedAttachmentLayoutInfo>& trackedAttachmentLayouts,
-            Uint32 attachmentCount,
-            Uint32 colorAttachmentCount,
-            Bool hasDepthStencilAttachment,
-            VkSampleCountFlagBits sampleCount,
-            IntVec2 extent, Uint32 layers):
-            hash(hash),
-            renderPass(renderpass),
-            framebuffer(framebuffer),
-            compatibilityHash(compatibilityHash),
-            pendingClearAttachments(Move(pendingClearAttachments)),
-            trackedAttachmentLayouts(Move(trackedAttachmentLayouts)),
-            attachmentCount(attachmentCount),
-            colorAttachmentCount(colorAttachmentCount),
-            hasDepthStencilAttachment(hasDepthStencilAttachment),
-            sampleCount(sampleCount),
-            extent(extent),
-            layers(layers)
-        {}
-
-        ~RenderPassEntry() {
-            if (renderPass != VK_NULL_HANDLE) {
-                vkDestroyRenderPass(s_device, renderPass, nullptr);
-            }
-            if (framebuffer != VK_NULL_HANDLE) {
-                vkDestroyFramebuffer(s_device, framebuffer, nullptr);
-            }
-        }
-
-        Bool CompatibleWith(const RenderPassEntry& that) const {
-            return this->compatibilityHash == that.compatibilityHash;
-        }
-
-        Bool CompatibleWith(Uint64 compatibilityHash) const {
-            return this->compatibilityHash == compatibilityHash;
-        }
-    };
-
-    struct ActiveRenderPassInfo {
-        Uint64 hash = 0;
-        Uint64 compatibilityHash = 0;
-        Vector<TrackedAttachmentLayoutInfo> trackedAttachmentLayouts;
-        IntVec2 extent = {0, 0};
-
-        Bool CompatibleWith(const RenderPassEntry& that) const {
-            return compatibilityHash == that.compatibilityHash;
-        }
-
-        Bool CompatibleWith(Uint64 thatCompatibilityHash) const {
-            return compatibilityHash == thatCompatibilityHash;
-        }
-    };
-
-    class VkRenderPassManager {
-    public:
-        using HashType = Uint64;
-
-        // Notified once per OnPresent sweep with every aged-out entry's VkRenderPass
-        // value: pipelines are hashed on the raw handle, and once destroyed the value
-        // may be recycled for an incompatible pass, so dependent caches must purge
-        // everything keyed on them before any new pass can be created (the sweep and
-        // the notification run back-to-back with no creation in between; observers
-        // compare the values, never dereference them). Batched so a mass-idle cohort
-        // (shader-pack switch, dimension exit) costs the observer one pipeline-cache
-        // scan, not one per dying pass. The wholesale paths
-        // (Shutdown/RecreateSwapchain) do not notify - their callers already drop
-        // every pipeline outright.
-        class IEvictionObserver {
-        public:
-            virtual ~IEvictionObserver() = default;
-            virtual void OnRenderPassesDestroyed(const Vector<VkRenderPass>& renderPasses) = 0;
-        };
-
-        VkRenderPassManager(VkDevice device,
-            VkPhysicalDevice physicalDevice, VmaAllocator allocator, const VulkanRendererConfig& config,
-            VkClearManager& clearManager, VkTextureManager& textureManager, SwapchainObject& swapchainObject);
-        ~VkRenderPassManager();
-
-        // Observer may be null (no notifications). Not owned.
-        void SetEvictionObserver(IEvictionObserver* observer) { m_evictionObserver = observer; }
-
-        Bool Initialize();
-        void Shutdown();
-
-        HashType ComputeHash(
-            const MG_State::GLState::FramebufferObject& fbo,
-            Uint32 swapchainImageIndex,
-            Bool includePendingClear = true,
-            Bool includeDefaultFboDepthStencil = true);
-        // drawUsesDepthStencil: whether the operation about to run inside the pass
-        // reads or writes the depth/stencil buffer (depth test or stencil test
-        // enabled, or a depth/stencil clear). Only consulted for the DEFAULT
-        // framebuffer: EGL undefines its ancillary buffers at every swap, so a
-        // default-FBO pass whose draws provably never touch depth/stencil is
-        // created WITHOUT the depth attachment - on a tiler that skips the whole
-        // depth tile load AND store. The flavor only escalates: once a pass with
-        // depth is active, later depth-less draws keep using it, and a depth-using
-        // draw against a depth-less active pass resolves to a new (incompatible)
-        // entry, which the caller's compatibility check turns into a pass split;
-        // the new pass's depth loads DONT_CARE (content was undefined all along).
-        RenderPassEntry& GetOrCreateRenderPass(const MG_State::GLState::FramebufferObject& fbo,
-                                               Uint32 swapchainImageIndex,
-                                               Bool drawUsesDepthStencil = true);
-        void QueueRenderbufferClear(GLbitfield mask, const ClearFramebufferPayload& clearPayload,
-                                    const MG_State::GLState::FramebufferObject& drawFbo);
-        void QueueRenderbufferClear(const ClearAttachmentPayload& clearPayload,
-                                    const MG_State::GLState::FramebufferAttachmentObject& attachment);
-        void PopPendingRenderbufferClear(MG_State::GLState::RenderbufferObject* renderbuffer);
-        // Frame boundary hook: ages the render-pass cache and evicts long-unused
-        // entries (their command buffers retired many frames ago).
-        void OnPresent();
-        static Bool BeginRenderPass(VkCommandBuffer commandBuffer, RenderPassEntry& renderPassEntry);
-        static Bool EndRenderPass(VkCommandBuffer commandBuffer);
-        static ActiveRenderPassInfo* GetActiveRenderPass();
-    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;
-        IEvictionObserver* m_evictionObserver = nullptr;
-
-        // Bumped whenever a renderbuffer VkImage is (re)created; together with the texture
-        // manager's image epoch this invalidates the render-pass fast path on any attachment
-        // image recreation.
-        Uint64 m_renderbufferImageEpoch = 1;
-
-    public:
-        // Bumped whenever a renderbuffer backing is (re)created; consecutive-draw
-        // snapshots include it so an attachment respecify forces a re-resolve.
-        Uint64 GetRenderbufferImageEpoch() const { return m_renderbufferImageEpoch; }
-
-    private:
-
-        // Per-draw fast-path memo for GetOrCreateRenderPass (dirty-flag state tracking): when the
-        // framebuffer state is provably unchanged since the last resolution, the active render pass
-        // is reused WITHOUT recomputing the expensive per-draw hash. Invalidated by FBO switch /
-        // 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;
-        // The FBO's never-reused lifetime id joins the raw pointer + Uint16 version:
-        // a deleted FBO reallocated at the same address whose fresh setup performed
-        // the same number of version bumps would otherwise compare equal (both count
-        // from 0), serving the dead framebuffer's pass to the new object.
-        Uint64 m_rpFastFboLifetimeId = 0;
-        Uint16 m_rpFastFboVersion = 0;
-        Uint32 m_rpFastSwapchainIndex = 0;
-        Uint64 m_rpFastTexEpoch = 0;
-        Uint64 m_rpFastRbEpoch = 0;
-        Uint64 m_rpFastRenderPassHash = 0;
-        // Whether the memoized entry carries a depth/stencil attachment; a
-        // default-FBO resolution whose effective depth request differs must
-        // miss the memo (the depth-less/depth-full flavors hash differently).
-        Bool m_rpFastHadDepthStencil = false;
-
-    public:
-        struct RenderbufferResource {
-            // deadSinceFrame sentinel: the owning weak reference has not been observed
-            // expired. Dead resources age past every in-flight frame before Destroy
-            // (see CollectRenderbufferGarbage); the GPU may still reference the image
-            // for frames-in-flight frames after the GL object dies.
-            static constexpr Uint64 kNeverObservedDead = UINT64_MAX;
-
-            WeakPtr<MG_State::GLState::RenderbufferObject> renderbuffer;
-            VkImage image = VK_NULL_HANDLE;
-            VmaAllocation allocation = nullptr;
-            VkImageView view = VK_NULL_HANDLE;
-            // UNORM reinterpretation of an sRGB image, used as the attachment view while
-            // GL_FRAMEBUFFER_SRGB is disabled (raw writes). Null for non-sRGB formats.
-            VkImageView unormTwinView = VK_NULL_HANDLE;
-            VkImageLayout layout = VK_IMAGE_LAYOUT_UNDEFINED;
-            VkFormat format = VK_FORMAT_UNDEFINED;
-            VkImageAspectFlags aspect = VK_IMAGE_ASPECT_NONE;
-            VkExtent2D extent = {0, 0};
-            VkSampleCountFlagBits sampleCount = VK_SAMPLE_COUNT_1_BIT;
-            TextureInternalFormat internalFormat = TextureInternalFormat::Unknown;
-            Int samples = 0;
-            // m_frameCounter value at which the weak reference was first seen expired.
-            Uint64 deadSinceFrame = kNeverObservedDead;
-
-            void Destroy(VkDevice device, VmaAllocator allocator);
-        };
-
-        // Public so the renderer's blit/copy/readback bindings can source renderbuffer
-        // attachments the same way texture attachments go through the texture manager.
-        RenderbufferResource* GetOrCreateRenderbufferResource(
-            const SharedPtr<MG_State::GLState::RenderbufferObject>& renderbuffer);
-        Bool GetPendingRenderbufferClear(MG_State::GLState::RenderbufferObject* renderbuffer,
-                                         ClearAttachmentPayload& outPayload) const;
-
-    private:
-        struct PendingRenderbufferClear {
-            WeakPtr<MG_State::GLState::RenderbufferObject> renderbuffer;
-            ClearAttachmentPayload payload{};
-        };
-
-        // A superseded renderbuffer backing (glRenderbufferStorage respecify) parked
-        // until enough frame boundaries have passed that no in-flight command buffer
-        // can still reference it; destroyed in OnPresent (see RetireAgeFrames).
-        struct DeferredRenderbufferRelease {
-            VkImage image = VK_NULL_HANDLE;
-            VmaAllocation allocation = nullptr;
-            VkImageView view = VK_NULL_HANDLE;
-            VkImageView unormTwinView = VK_NULL_HANDLE;
-            Uint64 deferredAtFrame = 0;
-        };
-
-        // Node-based std::unordered_map, deliberately NOT the open-addressing UnorderedMap:
-        // callers cache a RenderbufferResource* - or a bare &resource->layout - and then make further
-        // calls that touch this map. BlitFramebuffer is the one that bit: it resolves the source and
-        // destination colour bindings (ResolveColorBlitBinding caches &rbResource->layout), then
-        // materializes the source's pending clear, which looks that same resource up again. Growing
-        // an open-addressed table relocates every element, so the cached pointer went on to name
-        // freed storage still holding the pre-clear VK_IMAGE_LAYOUT_UNDEFINED; BlitFramebuffer bailed
-        // out at "source image layout is undefined", silently dropping the blit -
-        // renderbuffers_storage_multisample read back zero instead of the clear colour on exactly the
-        // iterations that grew the table.
-        //
-        // Reordering the materialize ahead of the resolves - the fix ReadPixels got - does not cover
-        // this: the destination resolve still runs after the source pointer is taken. The depth blit,
-        // GetOrCreateRenderPass's depthRenderbufferResource and ReadDepthStencilPixels cache the same
-        // kind of pointer, so the invariant belongs in the container rather than in a per-call-site
-        // ordering rule. m_textureResources is node-based for the same reason.
-        //
-        // The case for keeping this node-based got STRONGER with ska::flat_hash_map, so do not read
-        // the paragraph above as merely historical: ska erases by shifting the rest of the probe
-        // cluster backwards into the hole, so erasing one renderbuffer relocates OTHER renderbuffers'
-        // entries - a cached pointer can now be invalidated by a key it has nothing to do with, which
-        // no call-site ordering rule can defend against. (What did change: ska's operator[] returns on
-        // a hit before it runs its grow check, so a plain lookup of a PRESENT key no longer relocates.
-        // That narrows the insert hazard; it does not touch the erase one.)
-        std::unordered_map<MG_State::GLState::RenderbufferObject*, RenderbufferResource> m_renderbufferResources;
-        UnorderedMap<MG_State::GLState::RenderbufferObject*, PendingRenderbufferClear> m_pendingRenderbufferClears;
-        Vector<DeferredRenderbufferRelease> m_deferredRenderbufferReleases;
-        // Supported sample counts per attachment format, so per-draw resource lookups
-        // do not repeat vkGetPhysicalDeviceImageFormatProperties.
-        UnorderedMap<VkFormat, VkSampleCountFlags> m_attachmentSampleCountsByFormat;
-
-        Bool HasPendingRenderbufferClear(
-            const MG_State::GLState::FramebufferAttachmentObject& attachment) const;
-        void CollectRenderbufferGarbage();
-        // Frame-boundary margin after which a resource last referenced by a retired
-        // GL object (or superseded backing) is provably past every in-flight frame.
-        Uint64 RetireAgeFrames() const;
-        void DeferRenderbufferBackingRelease(RenderbufferResource& resource);
-        void CollectDeferredRenderbufferReleases(Bool destroyAll);
-
-        static inline XXH64_state_t* m_hashState = XXH64_createState();
-        static inline ActiveRenderPassInfo s_activeRenderPass{};
-        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

@@ -1,319 +0,0 @@
-// MobileGL - MobileGL/MG_Backend/DirectVulkan/Renderer/VkSamplerManager.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 "VkSamplerManager.h"
-
-#include "MG_State/GLState/Core.h"
-
-#include <algorithm>
-#include <cmath>
-
-namespace MobileGL::MG_Backend::DirectVulkan {
-    namespace {
-        Bool UsesBorderColor(const MG_State::GLState::SamplerObject& sampler) {
-            return sampler.GetWrapS() == SamplerWrapMode::ClampToBorder ||
-                   sampler.GetWrapT() == SamplerWrapMode::ClampToBorder ||
-                   sampler.GetWrapR() == SamplerWrapMode::ClampToBorder;
-        }
-
-        Bool IsDepthTextureFormat(TextureInternalFormat format) {
-            switch (format) {
-            case TextureInternalFormat::DepthComponent:
-            case TextureInternalFormat::DepthComponent16:
-            case TextureInternalFormat::DepthComponent24:
-            case TextureInternalFormat::DepthComponent32:
-            case TextureInternalFormat::DepthComponent32F:
-            case TextureInternalFormat::Depth24Stencil8:
-            case TextureInternalFormat::Depth32FStencil8:
-            case TextureInternalFormat::DepthStencil:
-                return true;
-            default:
-                return false;
-            }
-        }
-
-        Bool NearlyEqual(Float lhs, Float rhs) {
-            return std::fabs(lhs - rhs) <= 1e-6f;
-        }
-
-        Float ResolveEffectiveMaxLod(const MG_State::GLState::SamplerObject& sampler) {
-            if (sampler.GetMipmapMode() == SamplerMipmapMode::None) {
-                return 0.0f;
-            }
-            return sampler.GetMaxLod();
-        }
-
-        Float ResolveEffectiveMinLod(const MG_State::GLState::SamplerObject& sampler, Float effectiveMaxLod) {
-            return std::min(sampler.GetMinLod(), effectiveMaxLod);
-        }
-
-        // A single-level view can only ever deliver the base level, but the LOD clamp must not be
-        // collapsed to exactly 0: both GL and Vulkan pick magFilter over minFilter from the
-        // *clamped* lambda, so maxLod = 0 would make every fragment magnify and quietly retire the
-        // min filter. 0.25 is the value VkSamplerCreateInfo's own note prescribes for emulating
-        // GL's non-mipmapped minification - large enough for lambda to stay positive, small enough
-        // that a NEAREST mip mode still rounds down to level 0. Clamped rather than assigned, so a
-        // texture whose GL_TEXTURE_MAX_LOD really is 0 keeps magnifying as GL says it must.
-        Float ResolveSingleLevelMaxLod(const MG_State::GLState::SamplerObject& sampler, Bool singleLevelView) {
-            const Float maxLod = ResolveEffectiveMaxLod(sampler);
-            return singleLevelView ? std::min(maxLod, 0.25f) : maxLod;
-        }
-    } // namespace
-
-    Bool VkSamplerManager::Initialize(const InitInfo& initInfo) {
-        Shutdown();
-
-        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) {
-                vkDestroySampler(m_device, sampler.handle, nullptr);
-            }
-            sampler.handle = VK_NULL_HANDLE;
-        }
-        m_samplers.clear();
-
-        m_device = VK_NULL_HANDLE;
-        m_config = nullptr;
-        m_frameBoundaryCounter = 0;
-    }
-
-    void VkSamplerManager::OnFrameBoundary() {
-        ++m_frameBoundaryCounter;
-
-        // Sweep occasionally; destroy samplers whose last use is far past every
-        // in-flight frame. Destroy and erase must stay atomic, or Shutdown would
-        // double-free the handle; an evicted key that recurs simply re-creates
-        // its sampler on the next miss.
-        constexpr Uint64 kSweepInterval = 256;
-        constexpr Uint64 kRetireAgeBoundaries = 1024;
-        if ((m_frameBoundaryCounter % kSweepInterval) != 0) {
-            return;
-        }
-
-        for (auto it = m_samplers.begin(); it != m_samplers.end();) {
-            auto& entry = it->second;
-            if (m_frameBoundaryCounter - entry.lastUsedFrameBoundary > kRetireAgeBoundaries) {
-                if (m_device != VK_NULL_HANDLE && entry.handle != VK_NULL_HANDLE) {
-                    vkDestroySampler(m_device, entry.handle, nullptr);
-                }
-                it = m_samplers.erase(it);
-            } else {
-                ++it;
-            }
-        }
-    }
-
-    Uint64 VkSamplerManager::BuildSamplerKey(const MG_State::GLState::SamplerObject& sampler,
-                                             const MG_State::GLState::ITextureObject& texture,
-                                             Bool forceNearestFiltering, Bool singleLevelView) const {
-        MOBILEGL_ASSERT(m_config != nullptr, "VkSamplerManager::BuildSamplerKey: m_config is null");
-        XXHASH_VERIFY(XXH64_reset(m_hashState, m_config->CacheVersion));
-
-        XXHASH_VERIFY(XXH64_update(m_hashState, &forceNearestFiltering, sizeof(forceNearestFiltering)));
-        XXHASH_VERIFY(XXH64_update(m_hashState, &singleLevelView, sizeof(singleLevelView)));
-
-        const auto minFilter = sampler.GetMinFilter();
-        XXHASH_VERIFY(XXH64_update(m_hashState, &minFilter, sizeof(minFilter)));
-        const auto magFilter = sampler.GetMagFilter();
-        XXHASH_VERIFY(XXH64_update(m_hashState, &magFilter, sizeof(magFilter)));
-        const auto mipmapMode = sampler.GetMipmapMode();
-        XXHASH_VERIFY(XXH64_update(m_hashState, &mipmapMode, sizeof(mipmapMode)));
-        const auto wrapS = sampler.GetWrapS();
-        XXHASH_VERIFY(XXH64_update(m_hashState, &wrapS, sizeof(wrapS)));
-        const auto wrapT = sampler.GetWrapT();
-        XXHASH_VERIFY(XXH64_update(m_hashState, &wrapT, sizeof(wrapT)));
-        const auto wrapR = sampler.GetWrapR();
-        XXHASH_VERIFY(XXH64_update(m_hashState, &wrapR, sizeof(wrapR)));
-        const auto maxLod = ResolveSingleLevelMaxLod(sampler, singleLevelView);
-        const auto minLod = ResolveEffectiveMinLod(sampler, maxLod);
-        XXHASH_VERIFY(XXH64_update(m_hashState, &minLod, sizeof(minLod)));
-        XXHASH_VERIFY(XXH64_update(m_hashState, &maxLod, sizeof(maxLod)));
-        const auto lodBias = sampler.GetLodBias();
-        XXHASH_VERIFY(XXH64_update(m_hashState, &lodBias, sizeof(lodBias)));
-        // The RESOLVED value, not the GL request: samplers that only differ in an anisotropy Vulkan
-        // will not apply (NEAREST filtering, or requests past the device limit) must still share one
-        // VkSampler, while two samplers that really do differ must not collide onto the first one's.
-        const auto maxAnisotropy = ResolveEffectiveMaxAnisotropy(sampler, forceNearestFiltering);
-        XXHASH_VERIFY(XXH64_update(m_hashState, &maxAnisotropy, sizeof(maxAnisotropy)));
-        const auto compareMode = sampler.GetCompareMode();
-        XXHASH_VERIFY(XXH64_update(m_hashState, &compareMode, sizeof(compareMode)));
-        const auto compareFunc = sampler.GetSamplerCompareFunc();
-        XXHASH_VERIFY(XXH64_update(m_hashState, &compareFunc, sizeof(compareFunc)));
-        const auto borderColor = ResolveVkBorderColor(sampler, texture);
-        XXHASH_VERIFY(XXH64_update(m_hashState, &borderColor, sizeof(borderColor)));
-        return XXH64_digest(m_hashState);
-    }
-
-    VkSampler VkSamplerManager::GetOrCreateSampler(const MG_State::GLState::SamplerObject& sampler,
-                                                   const MG_State::GLState::ITextureObject& texture,
-                                                   Bool forceNearestFiltering, Uint32 viewLevelCount) {
-        // A view that exposes a single mip level has no second level to blend with, so GL's
-        // *_MIPMAP_* minification filters degenerate to plain filtering on the base level -
-        // sampling is unchanged by pinning the Vulkan sampler to NEAREST mip mode at LOD 0.
-        // It is not cosmetic: MobileGL backs such a view with a fully allocated mip chain whose
-        // tail is never written, and a LINEAR mip mode lets the texture unit issue the level+1
-        // fetch anyway. On Adreno that fetch lands in uninitialized UBWC pages (or past the
-        // allocation for a genuinely single-level image) and faults the GPU - the same failure
-        // the default-framebuffer blit shader had to work around with an explicit-LOD sample.
-        const Bool singleLevelView = viewLevelCount == 1;
-        const Uint64 key = BuildSamplerKey(sampler, texture, forceNearestFiltering, singleLevelView);
-        auto it = m_samplers.find(key);
-        if (it != m_samplers.end()) {
-            it->second.lastUsedFrameBoundary = m_frameBoundaryCounter;
-            return it->second.handle;
-        }
-
-        VkSamplerCreateInfo samplerInfo{};
-        samplerInfo.sType = VK_STRUCTURE_TYPE_SAMPLER_CREATE_INFO;
-        samplerInfo.magFilter = forceNearestFiltering ? VK_FILTER_NEAREST : ToVkFilter(sampler.GetMagFilter());
-        samplerInfo.minFilter = forceNearestFiltering ? VK_FILTER_NEAREST : ToVkFilter(sampler.GetMinFilter());
-        samplerInfo.mipmapMode = (forceNearestFiltering || singleLevelView)
-                                     ? VK_SAMPLER_MIPMAP_MODE_NEAREST
-                                     : ToVkMipmapMode(sampler.GetMipmapMode());
-        samplerInfo.addressModeU = ToVkAddressMode(sampler.GetWrapS());
-        samplerInfo.addressModeV = ToVkAddressMode(sampler.GetWrapT());
-        samplerInfo.addressModeW = ToVkAddressMode(sampler.GetWrapR());
-        samplerInfo.mipLodBias = sampler.GetLodBias();
-        // 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(sampler.GetSamplerCompareFunc());
-        // Must match BuildSamplerKey's resolution exactly.
-        samplerInfo.maxLod = ResolveSingleLevelMaxLod(sampler, singleLevelView);
-        samplerInfo.minLod = ResolveEffectiveMinLod(sampler, samplerInfo.maxLod);
-        samplerInfo.borderColor = ResolveVkBorderColor(sampler, texture);
-        samplerInfo.unnormalizedCoordinates = VK_FALSE;
-
-        VkSampler vkSampler = VK_NULL_HANDLE;
-        VK_VERIFY(vkCreateSampler(m_device, &samplerInfo, nullptr, &vkSampler), "vkCreateSampler(texture)");
-
-        SamplerCacheEntry entry{};
-        entry.handle = vkSampler;
-        entry.externalIndex = sampler.GetExternalIndex();
-        entry.version = sampler.GetVersion();
-        entry.lastUsedFrameBoundary = m_frameBoundaryCounter;
-        m_samplers[key] = entry;
-        return vkSampler;
-    }
-
-    VkFilter VkSamplerManager::ToVkFilter(SamplerFilterMode mode) {
-        return mode == SamplerFilterMode::Nearest ? VK_FILTER_NEAREST : VK_FILTER_LINEAR;
-    }
-
-    VkSamplerMipmapMode VkSamplerManager::ToVkMipmapMode(SamplerMipmapMode mode) {
-        switch (mode) {
-        case SamplerMipmapMode::Nearest:
-            return VK_SAMPLER_MIPMAP_MODE_NEAREST;
-        case SamplerMipmapMode::Linear:
-            return VK_SAMPLER_MIPMAP_MODE_LINEAR;
-        case SamplerMipmapMode::None:
-        default:
-            return VK_SAMPLER_MIPMAP_MODE_NEAREST;
-        }
-    }
-
-    VkSamplerAddressMode VkSamplerManager::ToVkAddressMode(SamplerWrapMode mode) {
-        switch (mode) {
-        case SamplerWrapMode::ClampToEdge:
-            return VK_SAMPLER_ADDRESS_MODE_CLAMP_TO_EDGE;
-        case SamplerWrapMode::MirroredRepeat:
-            return VK_SAMPLER_ADDRESS_MODE_MIRRORED_REPEAT;
-        case SamplerWrapMode::Repeat:
-            return VK_SAMPLER_ADDRESS_MODE_REPEAT;
-        case SamplerWrapMode::ClampToBorder:
-            return VK_SAMPLER_ADDRESS_MODE_CLAMP_TO_BORDER;
-        case SamplerWrapMode::MirrorClampToEdge:
-            return VK_SAMPLER_ADDRESS_MODE_MIRROR_CLAMP_TO_EDGE;
-        default:
-            return VK_SAMPLER_ADDRESS_MODE_REPEAT;
-        }
-    }
-
-    VkCompareOp VkSamplerManager::ToVkCompareOp(SamplerCompareFunc func) {
-        switch (func) {
-        case SamplerCompareFunc::Never:
-            return VK_COMPARE_OP_NEVER;
-        case SamplerCompareFunc::Less:
-            return VK_COMPARE_OP_LESS;
-        case SamplerCompareFunc::Equal:
-            return VK_COMPARE_OP_EQUAL;
-        case SamplerCompareFunc::LessEqual:
-            return VK_COMPARE_OP_LESS_OR_EQUAL;
-        case SamplerCompareFunc::Greater:
-            return VK_COMPARE_OP_GREATER;
-        case SamplerCompareFunc::NotEqual:
-            return VK_COMPARE_OP_NOT_EQUAL;
-        case SamplerCompareFunc::GreaterEqual:
-            return VK_COMPARE_OP_GREATER_OR_EQUAL;
-        case SamplerCompareFunc::Always:
-        default:
-            return VK_COMPARE_OP_ALWAYS;
-        }
-    }
-
-    VkBorderColor VkSamplerManager::ResolveVkBorderColor(const MG_State::GLState::SamplerObject& sampler,
-                                                         const MG_State::GLState::ITextureObject& texture) {
-        if (!UsesBorderColor(sampler)) {
-            return VK_BORDER_COLOR_FLOAT_TRANSPARENT_BLACK;
-        }
-
-        // Border colour is sampler state: a bound sampler object supplies its own, and a texture
-        // with none reaches the very same value through the sampler object it owns.
-        const auto& borderColor = sampler.GetBorderColor();
-        const Bool isDepthTexture = IsDepthTextureFormat(texture.GetFormat());
-
-        if (isDepthTexture) {
-            if (NearlyEqual(borderColor.x(), 1.0f)) {
-                return VK_BORDER_COLOR_FLOAT_OPAQUE_WHITE;
-            }
-            if (NearlyEqual(borderColor.x(), 0.0f)) {
-                return VK_BORDER_COLOR_FLOAT_OPAQUE_BLACK;
-            }
-        }
-
-        const Bool rgbZero = NearlyEqual(borderColor.x(), 0.0f) && NearlyEqual(borderColor.y(), 0.0f) &&
-                             NearlyEqual(borderColor.z(), 0.0f);
-        if (rgbZero && NearlyEqual(borderColor.w(), 0.0f)) {
-            return VK_BORDER_COLOR_FLOAT_TRANSPARENT_BLACK;
-        }
-        if (rgbZero && NearlyEqual(borderColor.w(), 1.0f)) {
-            return VK_BORDER_COLOR_FLOAT_OPAQUE_BLACK;
-        }
-        if (NearlyEqual(borderColor.x(), 1.0f) && NearlyEqual(borderColor.y(), 1.0f) &&
-            NearlyEqual(borderColor.z(), 1.0f) && NearlyEqual(borderColor.w(), 1.0f)) {
-            return VK_BORDER_COLOR_FLOAT_OPAQUE_WHITE;
-        }
-
-        return VK_BORDER_COLOR_FLOAT_TRANSPARENT_BLACK;
-    }
-} // namespace MobileGL::MG_Backend::DirectVulkan

MobileGL/MG_Backend/DirectVulkan/Renderer/VkSamplerManager.h

@@ -1,90 +0,0 @@
-// MobileGL - MobileGL/MG_Backend/DirectVulkan/Renderer/VkSamplerManager.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 "../VulkanRendererConfig.h"
-#include <Includes.h>
-#include <MG_State/GLState/SamplerState/SamplerObject.h>
-
-namespace MobileGL::MG_State::GLState {
-class SamplerObject;
-class ITextureObject;
-}
-
-namespace MobileGL::MG_Backend::DirectVulkan {
-class VkSamplerManager {
-public:
-    struct InitInfo {
-        VkDevice device = VK_NULL_HANDLE;
-        const VulkanRendererConfig* config = nullptr;
-        // The samplerAnisotropy device feature was requested and granted at vkCreateDevice.
-        Bool samplerAnisotropySupported = false;
-        // VkPhysicalDeviceLimits::maxSamplerAnisotropy.
-        Float maxSamplerAnisotropy = 1.0f;
-    };
-
-    Bool Initialize(const InitInfo& initInfo);
-    void Shutdown();
-
-    // viewLevelCount is the mip-level count of the image view this sampler will be paired
-    // with; 0 means "unknown, do not narrow". See GetOrCreateSampler for why it matters.
-    VkSampler GetOrCreateSampler(const MG_State::GLState::SamplerObject& sampler,
-                                 const MG_State::GLState::ITextureObject& texture,
-                                 Bool forceNearestFiltering = false,
-                                 Uint32 viewLevelCount = 0);
-    // Frame boundary hook: ages the sampler cache and destroys samplers not used
-    // for many frames. The key hashes continuous float state (lodBias, LOD clamps,
-    // anisotropy), so an app animating those would otherwise mint an unbounded
-    // stream of never-destroyed VkSamplers and eventually exhaust the device's
-    // maxSamplerAllocationCount. A sampler idle for over a thousand frame
-    // boundaries cannot be referenced by any in-flight command buffer (frames in
-    // flight are single digits), and every descriptor set the GPU consumes is
-    // written that same frame with live handles (the per-binding resolve memo and
-    // descriptor-set reuse are both frame-reset), so destruction here needs no
-    // fence wait. Self-gated: one counter bump and compare except on sweep
-    // boundaries.
-    void OnFrameBoundary();
-
-private:
-    struct SamplerCacheEntry {
-        VkSampler handle = VK_NULL_HANDLE;
-        Uint externalIndex = 0;
-        Uint16 version = 0;
-        // Frame boundary of the last cache hit; entries idle past the
-        // OnFrameBoundary retirement age have their VkSampler destroyed.
-        Uint64 lastUsedFrameBoundary = 0;
-    };
-
-    Uint64 BuildSamplerKey(const MG_State::GLState::SamplerObject& sampler,
-                           const MG_State::GLState::ITextureObject& texture,
-                           Bool forceNearestFiltering, Bool singleLevelView) const;
-    static VkFilter ToVkFilter(SamplerFilterMode mode);
-    static VkSamplerMipmapMode ToVkMipmapMode(SamplerMipmapMode mode);
-    static VkSamplerAddressMode ToVkAddressMode(SamplerWrapMode mode);
-    static VkCompareOp ToVkCompareOp(SamplerCompareFunc func);
-    static VkBorderColor ResolveVkBorderColor(const MG_State::GLState::SamplerObject& sampler,
-                                              const MG_State::GLState::ITextureObject& texture);
-    // The anisotropy Vulkan will actually apply: 1.0 (i.e. disabled) unless the feature is on and
-    // the sampler filters linearly both ways, otherwise the GL request clamped to the device limit.
-    // GL happily carries GL_TEXTURE_MAX_ANISOTROPY on a NEAREST sampler (Blaze3D's blocks do exactly
-    // that) while Vulkan forbids anisotropyEnable there, so the GL value must never be forwarded raw.
-    Float ResolveEffectiveMaxAnisotropy(const MG_State::GLState::SamplerObject& sampler,
-                                        Bool forceNearestFiltering) const;
-
-    VkDevice m_device = VK_NULL_HANDLE;
-    const VulkanRendererConfig* m_config = nullptr;
-    Bool m_samplerAnisotropySupported = false;
-    Float m_maxSamplerAnisotropy = 1.0f;
-    UnorderedMap<Uint64, SamplerCacheEntry> m_samplers;
-    // Monotonic frame-boundary counter (bumped in OnFrameBoundary) for cache aging.
-    Uint64 m_frameBoundaryCounter = 0;
-    static inline XXH64_state_t* m_hashState = XXH64_createState();
-};
-} // namespace MobileGL::MG_Backend::DirectVulkan

MobileGL/MG_Backend/DirectVulkan/Renderer/VkTextureManager.h

@@ -1,635 +0,0 @@
-// MobileGL - MobileGL/MG_Backend/DirectVulkan/Renderer/VkTextureManager.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>
-#include <MG_State/GLState/TextureState/TextureObject.h>
-#include <vk_mem_alloc.h>
-#include <unordered_map>
-#include <unordered_set>
-
-namespace MobileGL::MG_State::GLState {
-class ITextureObject;
-}
-
-namespace MobileGL::MG_Backend::DirectVulkan {
-enum class SamplerNumericDomain : Uint8;
-
-// A GL 1D-ARRAY level keeps its LAYER COUNT in the state-side HEIGHT: that is what
-// glTexImage2D(GL_TEXTURE_1D_ARRAY, width, layers) means, and the frontend records the level
-// as {width, layers, 1} (see GL_Texture.cpp's AllocateStorage and the completeness walk in
-// TextureObject.cpp, which shrinks only x down the chain). Vulkan packs it the other way: a
-// 1D array is a VK_IMAGE_TYPE_1D image whose extent.height MUST be 1 and whose layers live in
-// arrayLayers - i.e. in the slot this backend reads out of z. So every place that turns a GL
-// level size into Vulkan image geometry has to move the count across first, and every GL-space
-// sub-box that rides along with it has to move its y the same way. DirectGLES performs the
-// identical remap onto the ES 2D array it maps 1D arrays to (GetBackendUploadSize).
-//
-// Applied to nothing else: a 2D array, a cube array and a 3D texture all already carry their
-// depth/layer count in z, which is where the Vulkan side expects it.
-inline IntVec3 ToVulkanLevelExtent(TextureTarget stateTarget, const IntVec3& glTexelSize) {
-    if (stateTarget == TextureTarget::Texture1DArray) {
-        return {glTexelSize.x(), 1, glTexelSize.y()};
-    }
-    return glTexelSize;
-}
-
-class VkTextureManager {
-public:
-    // Monotonic epoch bumped whenever a texture VkImage is (re)created. The render-pass
-    // manager keys its per-draw fast path on this so an attachment's image recreation
-    // invalidates the cached render pass (dirty-flag tracking; portable to Vulkan 1.1).
-    Uint64 GetTextureImageEpoch() const { return m_textureImageEpoch; }
-    // Bumped whenever any tracked texture resource is erased; cached
-    // TextureResource pointers are valid only while this is unchanged.
-    Uint64 GetResourceEraseEpoch() const { return m_resourceEraseEpoch; }
-
-    struct TextureIdentity {
-        MG_State::GLState::ITextureObject* texture = nullptr;
-        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;
-        VmaAllocator allocator = nullptr;
-        VkCommandPool commandPool = VK_NULL_HANDLE;
-        VkQueue graphicsQueue = VK_NULL_HANDLE;
-        Uint32 frameCount = 0;
-        // VK_KHR_image_format_list is enabled: MUTABLE_FORMAT images can name the exact set of
-        // formats they will be viewed as, which is what lets a tiler keep them compressed.
-        Bool imageFormatListSupported = false;
-        // Union of shader stages sampled-read barriers may name on this device; the renderer
-        // builds it from the enabled features because geometry/tessellation stage bits are
-        // invalid in a barrier when their feature is off.
-        VkPipelineStageFlags sampledReadStageMask = VK_PIPELINE_STAGE_VERTEX_SHADER_BIT |
-                                                    VK_PIPELINE_STAGE_FRAGMENT_SHADER_BIT |
-                                                    VK_PIPELINE_STAGE_COMPUTE_SHADER_BIT;
-        // Family of `graphicsQueue`; the manager creates its own command pool
-        // on it for the recycled upload-batch command buffers, so their parked
-        // allocations never sit in (and fragment) the renderer's shared pool
-        // that frame command buffers churn through every frame.
-        Uint32 graphicsQueueFamilyIndex = 0;
-    };
-
-    struct TextureResource {
-        struct AttachmentViewKey {
-            Uint32 mipLevel = 0;
-            Uint32 baseArrayLayer = 0;
-            Uint32 layerCount = 1;
-            VkImageViewType viewType = VK_IMAGE_VIEW_TYPE_2D;
-            // May differ from the image format: sRGB images attach through their UNORM
-            // twin while GL_FRAMEBUFFER_SRGB is disabled.
-            VkFormat viewFormat = VK_FORMAT_UNDEFINED;
-
-            Bool operator==(const AttachmentViewKey& other) const {
-                return mipLevel == other.mipLevel &&
-                       baseArrayLayer == other.baseArrayLayer &&
-                       layerCount == other.layerCount &&
-                       viewType == other.viewType &&
-                       viewFormat == other.viewFormat;
-            }
-        };
-
-        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);
-                hash ^= std::hash<Uint32>{}(static_cast<Uint32>(key.viewFormat)) +
-                        0x9e3779b9u + (hash << 6) + (hash >> 2);
-                return hash;
-            }
-        };
-
-        struct StorageImageViewKey {
-            Uint32 mipLevel = 0;
-            Uint32 baseArrayLayer = 0;
-            Uint32 layerCount = 1;
-            VkImageViewType viewType = VK_IMAGE_VIEW_TYPE_2D;
-            VkFormat format = VK_FORMAT_UNDEFINED;
-
-            Bool operator==(const StorageImageViewKey& other) const {
-                return mipLevel == other.mipLevel &&
-                       baseArrayLayer == other.baseArrayLayer &&
-                       layerCount == other.layerCount &&
-                       viewType == other.viewType &&
-                       format == other.format;
-            }
-        };
-
-        struct SampledImageViewKey {
-            Uint32 baseMipLevel = 0;
-            Uint32 levelCount = 1;
-            VkImageViewType viewType = VK_IMAGE_VIEW_TYPE_2D;
-            VkFormat format = VK_FORMAT_UNDEFINED;
-
-            Bool operator==(const SampledImageViewKey& other) const {
-                return baseMipLevel == other.baseMipLevel &&
-                       levelCount == other.levelCount &&
-                       viewType == other.viewType &&
-                       format == other.format;
-            }
-        };
-
-        struct SampledImageViewKeyHash {
-            SizeT operator()(const SampledImageViewKey& key) const {
-                SizeT hash = std::hash<Uint32>{}(key.baseMipLevel);
-                hash ^= std::hash<Uint32>{}(key.levelCount) + 0x9e3779b9u + (hash << 6) + (hash >> 2);
-                hash ^= std::hash<Uint32>{}(static_cast<Uint32>(key.viewType)) +
-                        0x9e3779b9u + (hash << 6) + (hash >> 2);
-                hash ^= std::hash<Uint32>{}(static_cast<Uint32>(key.format)) +
-                        0x9e3779b9u + (hash << 6) + (hash >> 2);
-                return hash;
-            }
-        };
-
-        struct StorageImageViewKeyHash {
-            SizeT operator()(const StorageImageViewKey& key) const {
-                SizeT hash = std::hash<Uint32>{}(key.mipLevel);
-                hash ^= std::hash<Uint32>{}(key.baseArrayLayer) + 0x9e3779b9u + (hash << 6) + (hash >> 2);
-                hash ^= std::hash<Uint32>{}(key.layerCount) + 0x9e3779b9u + (hash << 6) + (hash >> 2);
-                hash ^= std::hash<Uint32>{}(static_cast<Uint32>(key.viewType)) +
-                        0x9e3779b9u + (hash << 6) + (hash >> 2);
-                hash ^= std::hash<Uint32>{}(static_cast<Uint32>(key.format)) +
-                        0x9e3779b9u + (hash << 6) + (hash >> 2);
-                return hash;
-            }
-        };
-
-        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;
-        Uint32 arrayLayers = 1;
-        Uint32 mipLevels = 1;
-        Uint32 sampledBaseMipLevel = 0;
-        Uint32 sampledLevelCount = 1;
-        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;
-        // Usage the live image was created with. STORAGE is only requested for textures that
-        // have actually been bound to a GL image unit, because on Adreno a storage-capable
-        // image loses UBWC bandwidth compression; a later image binding upgrades the usage
-        // and recreates the image, so the resolved usage has to be part of the compatibility
-        // check that decides whether the existing image can be kept.
-        VkImageUsageFlags usageFlags = 0;
-        // True once this image was (re)resolved while the texture was already marked as an
-        // image-unit texture. Distinguishes "not upgraded yet" from "cannot be upgraded"
-        // (a format whose optimalTilingFeatures lack STORAGE_IMAGE never gains the bit), so
-        // NeedsStorageImagePreparation cannot ask for a recreate that will never happen.
-        Bool storageUsageResolved = false;
-        Uint16 syncedTextureParamsVersion = 0;
-        // Recording generation (VkTextureManager::GetRecordingGeneration) of the last
-        // command referencing this image that was recorded into the CURRENT frame
-        // command buffer. An image untouched by the open recording may have its
-        // out-of-pass work (deferred clears, sampled-layout transitions) recorded
-        // into the frame's PRE command buffer - which executes strictly before the
-        // frame's commands - instead of splitting the active render pass.
-        Uint64 lastRecordingGeneration = 0;
-        // Snapshot of ITextureObject::GetContentVersion() at the last successful sync;
-        // lets SyncTexture skip the whole re-check/re-upload when content is unchanged.
-        Uint64 syncedContentVersion = 0;
-        // 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;
-        // Snapshot of ITextureObject::GetShapeVersion() at the last successful sync. The content
-        // version alone does NOT cover a re-specification: glTexImage2D(..., nullptr) on an
-        // already-defined level changes its size or format and dirties no texel, so it moves the
-        // shape version and nothing else. Without this in the early-out key the image, its views
-        // and therefore imageSize() all keep answering with the texture's PREVIOUS shape.
-        Uint64 syncedShapeVersion = 0;
-
-        TextureResource() = default;
-        TextureResource(const TextureResource&) = delete;
-        TextureResource(TextureResource&& that) noexcept {
-            std::swap(this->image, that.image);
-            std::swap(this->allocation, that.allocation);
-            std::swap(this->fullView, that.fullView);
-            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);
-            std::swap(this->arrayLayers, that.arrayLayers);
-            std::swap(this->mipLevels, that.mipLevels);
-            std::swap(this->sampledBaseMipLevel, that.sampledBaseMipLevel);
-            std::swap(this->sampledLevelCount, that.sampledLevelCount);
-            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->usageFlags, that.usageFlags);
-            std::swap(this->storageUsageResolved, that.storageUsageResolved);
-            std::swap(this->syncedTextureParamsVersion, that.syncedTextureParamsVersion);
-            std::swap(this->lastRecordingGeneration, that.lastRecordingGeneration);
-            std::swap(this->syncedContentVersion, that.syncedContentVersion);
-            std::swap(this->syncedMipLevelCount, that.syncedMipLevelCount);
-            std::swap(this->syncedShapeVersion, that.syncedShapeVersion);
-        }
-
-        void Reset() {
-            if (fullView != VK_NULL_HANDLE) {
-                vkDestroyImageView(s_device, fullView, nullptr);
-            }
-            if (sampledView != VK_NULL_HANDLE) {
-                vkDestroyImageView(s_device, sampledView, nullptr);
-            }
-            for (const auto attachmentView : perMipViews) {
-                if (attachmentView != VK_NULL_HANDLE) {
-                    vkDestroyImageView(s_device, attachmentView, nullptr);
-                }
-            }
-            for (const auto sampledView : perMipSampledViews) {
-                if (sampledView != VK_NULL_HANDLE) {
-                    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);
-            }
-            fullView = VK_NULL_HANDLE;
-            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;
-            extent = {0, 0};
-            depth = 1;
-            arrayLayers = 1;
-            mipLevels = 1;
-            sampledBaseMipLevel = 0;
-            sampledLevelCount = 1;
-            format = VK_FORMAT_UNDEFINED;
-            aspect = VK_IMAGE_ASPECT_NONE;
-            viewType = VK_IMAGE_VIEW_TYPE_2D;
-            sampleCount = VK_SAMPLE_COUNT_1_BIT;
-            imageCreateFlags = 0;
-            usageFlags = 0;
-            storageUsageResolved = false;
-            syncedTextureParamsVersion = 0;
-            syncedContentVersion = 0;
-            syncedMipLevelCount = 0;
-            syncedShapeVersion = 0;
-        }
-
-        ~TextureResource() {
-            Reset();
-        }
-
-        static inline VkDevice s_device = VK_NULL_HANDLE;
-        static inline VmaAllocator s_allocator = VK_NULL_HANDLE;
-    };
-
-    struct SampledTextureSnapshot {
-        VkImageView imageView = VK_NULL_HANDLE;
-        VkImageLayout layout = VK_IMAGE_LAYOUT_UNDEFINED;
-    };
-
-    Bool Initialize(const InitInfo& initInfo);
-    void Shutdown();
-    void BeginFrame(Uint32 frameIndex);
-    // Submits the accumulated texture-upload batch (one command buffer, one
-    // vkQueueSubmit, one pooled fence) if any uploads are pending. MUST run
-    // before any other vkQueueSubmit on the shared graphics queue whose
-    // commands may consume an image the batch writes - the frame command
-    // buffer submit (mid-frame flush, readback, Present) and the
-    // preserve-on-recreate copy are the existing callers. No-op when the
-    // batch is empty.
-    void FlushPendingUploads();
-    // Drains every frame slot's deferred image/view releases. Only valid when
-    // the caller has proven every queue submission complete; used by the
-    // present-less frame-boundary drain.
-    void CollectAllDeferredReleases();
-
-    TextureResource* SyncTextureAndGetDescriptor(
-        MG_State::GLState::ITextureObject& texture);
-    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,
-                                                      Uint32 writtenMipLevel,
-                                                      VkImageLayout newLayout);
-    Bool TransitionTextureForSampling(VkCommandBuffer commandBuffer, MG_State::GLState::ITextureObject& texture);
-    Bool TransitionTextureForStorageImage(VkCommandBuffer commandBuffer, MG_State::GLState::ITextureObject& texture);
-    // Copies the complete sampler-visible mip range into a transient sampled image. The source is
-    // restored to its prior layout, so image-store descriptors continue to name the original image.
-    // The transient ownership is tied to the current frame slot and is safe through its submission.
-    Bool SnapshotTextureForSampling(VkCommandBuffer commandBuffer, MG_State::GLState::ITextureObject& texture,
-                                    SamplerNumericDomain numericDomain,
-                                    VkPipelineStageFlags consumerShaderStageMask,
-                                    SampledTextureSnapshot& outSnapshot);
-
-    // Recording-generation bookkeeping for the pre-pass command stream. The
-    // generation advances every time the frame command buffer (re)begins
-    // recording; a resource whose stamp does not match was not referenced by
-    // any command in the open recording, so its out-of-pass work may safely
-    // execute ahead of the whole recording (in the pre command buffer).
-    void AdvanceRecordingGeneration() { ++m_recordingGeneration; }
-    void StampResourceRecordingUse(TextureResource& resource) const {
-        resource.lastRecordingGeneration = m_recordingGeneration;
-    }
-    // Map-lookup variant for callers that only hold the GL texture object.
-    void StampTextureRecordingUse(MG_State::GLState::ITextureObject* texture);
-    Bool WasTouchedThisRecording(const TextureResource& resource) const {
-        return resource.lastRecordingGeneration == m_recordingGeneration;
-    }
-    // Records that this texture is bound to a GL image unit, so its image must carry
-    // VK_IMAGE_USAGE_STORAGE_BIT. Must be called before NeedsStorageImagePreparation, and
-    // therefore before the render pass is committed: an image that has to be upgraded is
-    // recreated, which is illegal inside a render pass. Sticky for the texture's lifetime -
-    // GL lets an image binding come and go, and re-creating the image every time it does
-    // would cost far more than the compression it wins back.
-    void MarkStorageImageTexture(MG_State::GLState::ITextureObject& texture);
-    // True when this texture is marked but its live image predates the mark, i.e. the next sync
-    // will recreate it with STORAGE usage and copy the old contents forward. Callers use this to
-    // submit their pending recording first, so that copy cannot read pre-flush content.
-    Bool NeedsStorageUsageUpgrade(MG_State::GLState::ITextureObject& texture) const;
-    // The same ordering question for the other recreate-and-preserve trigger: true when this
-    // texture's live image carries a shorter mip chain than a full one, so defining the missing
-    // levels recreates it and copies the old contents forward.
-    Bool NeedsMipChainGrowth(MG_State::GLState::ITextureObject& texture) const;
-    // Non-mutating probe for the per-draw storage-image fast path: true when preparing this
-    // texture as a storage image may need work that is illegal inside a render pass (resource
-    // creation, dirty-content upload, or a layout transition to GENERAL). Unknown state reports
-    // true - a false positive merely ends the render pass, a false negative would skip a barrier.
-    Bool NeedsStorageImagePreparation(MG_State::GLState::ITextureObject& texture) const;
-
-    // `depthStencilTextureMode` is the texture's GL_DEPTH_STENCIL_TEXTURE_MODE; it only decides
-    // anything for an image that carries both aspects. Defaulted so the call sites that have no
-    // texture in hand keep the depth-aspect answer they have always given.
-    static VkImageAspectFlags ResolveSampledImageViewAspectMask(VkImageAspectFlags imageAspect,
-                                                                GLenum depthStencilTextureMode = GL_DEPTH_COMPONENT);
-    static VkFormat ResolveSampledImageViewFormat(VkFormat imageFormat, SamplerNumericDomain numericDomain);
-    static Bool AreSampledImageViewFormatsCompatible(VkFormat imageFormat, VkFormat viewFormat);
-    static Bool AreStorageImageViewFormatsCompatible(VkFormat imageFormat, VkFormat viewFormat);
-
-    // Moves `image` to `newLayout` and writes the new layout back through `trackedLayout`.
-    //
-    // The barrier covers EVERY array layer of the image, and there is deliberately no layer
-    // parameter to say otherwise: layout here is tracked per IMAGE (one `TextureResource::layout`,
-    // or one caller-owned variable), so a barrier narrower than the image would leave the layers it
-    // skipped in the old layout while the tracker claims they moved. Every transfer against a
-    // framebuffer attachment above layer 0 - glReadPixels, glBlitFramebuffer, glCopyTexSubImage,
-    // glCopyImageSubData - then ran its copy on a layer no barrier had transitioned.
-    //
-    // The mip range IS a parameter, because mip levels really are transitioned piecewise (see
-    // UpdateTrackedImageLayoutAfterAttachmentWrite and the mipmap generation loops): those callers
-    // move the complement of the level they wrote so the whole image converges on one layout again.
-    // Nothing does, or can, do that per layer.
-    static Bool TransitionImageLayout(VkCommandBuffer commandBuffer, VkImage image, VkImageLayout& trackedLayout,
-                               VkImageLayout newLayout, VkPipelineStageFlags srcStageMask,
-                               VkPipelineStageFlags dstStageMask, VkAccessFlags srcAccessMask,
-                               VkAccessFlags dstAccessMask, VkImageAspectFlags aspectMask,
-                               Uint32 baseMipLevel = 0, Uint32 levelCount = 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;
-    // See AdvanceRecordingGeneration. Starts above every resource's default
-    // stamp of 0 so a fresh resource counts as untouched.
-    Uint64 m_recordingGeneration = 1;
-
-    Bool SyncTexture(MG_State::GLState::ITextureObject &texture,
-                     TextureResource &outResource);
-    Bool SyncTextureResource(const MG_State::GLState::ITextureObject &texture,
-                             TextureUploadTarget uploadTarget,
-                             const IntVec3 &texelSize, SizeT byteSize, Uint32 mipLevels,
-                             TextureResource &resource);
-    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,
-                                VkImageUsageFlags viewUsage = 0) const;
-    Bool UploadDirtyMipLevels(MG_State::GLState::TextureObjectMipmap &mipmapTexture,
-                      TextureUploadTarget uploadTarget,
-                      TextureResource &outResource);
-    static Bool CheckMipmapCompleteness(const MG_State::GLState::ITextureObject& texture,
-                                        TextureUploadTarget& outTarget,
-                                        IntVec3& outTexelSize,
-                                        SizeT& outByteSize,
-                                        Uint32& outMipLevelCount);
-    static Uint32 GetUploadMipLevelCount(const MG_State::GLState::TextureObjectMipmap& texture, TextureUploadTarget target);
-    static void ResolveViewMipRange(const MG_State::GLState::ITextureObject& texture, Uint32 mipLevels,
-                                    Uint32& outBaseMipLevel, Uint32& outLevelCount);
-    static VkImageAspectFlags GetAspectMaskForFormat(VkFormat format);
-    void DeferResourceRelease(TextureResource&& resource);
-    void DeferViewRelease(VkImageView view);
-    void CollectDeferredReleases(Uint32 frameIndex);
-    void DestroyDeferredReleases();
-    // Frees the fence/command buffer/staging buffer of every in-flight texture
-    // upload whose fence has signaled (submission order = completion order on
-    // the single queue, so the scan stops at the first still-pending entry).
-    // waitAll blocks on every entry - Shutdown's drain.
-    void ReclaimCompletedUploads(Bool waitAll = false);
-    static TextureIdentity MakeTextureIdentity(MG_State::GLState::ITextureObject* texture);
-    void EraseTrackedTexture(const TextureIdentity& identity);
-    void PruneStaleTextureAliases(MG_State::GLState::ITextureObject* texture);
-    SizeT PruneDeadTextures();
-
-    VkDevice m_device = VK_NULL_HANDLE;
-    VkPhysicalDevice m_physicalDevice = VK_NULL_HANDLE;
-    VmaAllocator m_allocator = nullptr;
-    VkCommandPool m_commandPool = VK_NULL_HANDLE;
-    // Dedicated pool for the recycled upload-batch command buffers (see
-    // InitInfo::graphicsQueueFamilyIndex).
-    VkCommandPool m_uploadCommandPool = VK_NULL_HANDLE;
-    VkQueue m_graphicsQueue = VK_NULL_HANDLE;
-    Bool m_imageFormatListSupported = false;
-    Uint32 m_currentFrameIndex = 0;
-
-    Uint8 m_gcCounter = 0;
-    // Frame-boundary GC gate: counts BeginFrame calls, not draws, so texture churn
-    // through non-draw paths (FBO clears, readbacks) still reaches the prune.
-    Uint32 m_gcFrameCounter = 0;
-    // Active only between BeginDrawSyncScope/EndDrawSyncScope; identities of
-    // textures already fully synced in the current draw (small N -> flat scan).
-    Bool m_drawSyncScopeActive = false;
-    // 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;
-    // Cross-draw sampled-texture memo: the same few textures (atlas, lightmap)
-    // are resolved on every draw, so cache their resource pointers and skip the
-    // alive/resource map lookups. Node-based std::unordered_map keeps the
-    // pointees stable across inserts; erases bump m_resourceEraseEpoch, which
-    // every memo entry must match. SyncTexture still runs on memo hits, so
-    // content/param freshness is unaffected. A dead-then-reused texture address
-    // cannot false-hit: the new object carries a new lifetime id.
-    struct SyncedTextureMemoEntry {
-        const MG_State::GLState::ITextureObject* texture = nullptr;
-        Uint64 lifetimeId = 0;
-        Uint64 eraseEpoch = 0;
-        TextureResource* resource = nullptr;
-    };
-    static constexpr Uint32 kSyncedTextureMemoSize = 8;
-    SyncedTextureMemoEntry m_syncedTextureMemo[kSyncedTextureMemoSize];
-    Uint32 m_syncedTextureMemoNext = 0;
-    Uint64 m_resourceEraseEpoch = 1;
-    // Formats whose mutable-image probe failed on this device; their images are created
-    // without MUTABLE_FORMAT_BIT so repeat syncs neither re-probe nor flag-mismatch.
-    std::unordered_set<VkFormat> m_mutableFormatUnsupported;
-    // Formats whose 3D images refused VK_IMAGE_CREATE_2D_ARRAY_COMPATIBLE_BIT. Per format+usage,
-    // exactly like the mutable-format verdict above, so it is answered at image creation and
-    // remembered rather than probed once globally.
-    std::unordered_set<VkFormat> m_2dArrayCompatibleUnsupported;
-    std::unordered_map<TextureIdentity, WeakPtr<MG_State::GLState::ITextureObject>, TextureIdentityHash> m_aliveObjects;
-    std::unordered_map<TextureIdentity, TextureResource, TextureIdentityHash> m_textureResources;
-    // Textures that have been bound to a GL image unit (see MarkStorageImageTexture).
-    std::unordered_set<TextureIdentity, TextureIdentityHash> m_storageImageTextures;
-    // Supported multisample counts per format, so repeat texture syncs do not
-    // re-query vkGetPhysicalDeviceImageFormatProperties.
-    std::unordered_map<VkFormat, VkSampleCountFlags> m_multisampleCountsByFormat;
-    Vector<Vector<TextureResource>> m_deferredReleases;
-    Vector<Vector<VkImageView>> m_deferredViewReleases;
-
-    // --- Batched upload machinery ---
-    // Uploads within a frame are recorded into ONE shared command buffer and
-    // submitted with ONE vkQueueSubmit at FlushPendingUploads (the renderer
-    // flushes before every frame-command-buffer submit). Staging memory comes
-    // from a pool of persistently-mapped, reusable blocks instead of a
-    // vmaCreateBuffer per upload.
-    struct UploadStagingBlock {
-        VkBuffer buffer = VK_NULL_HANDLE;
-        VmaAllocation allocation = nullptr;
-        Uint8* mapped = nullptr; // persistently mapped for the block's lifetime
-        VkDeviceSize capacity = 0;
-        VkDeviceSize cursor = 0; // bump cursor while the block backs the open batch
-    };
-    // Opens the batch command buffer lazily (allocates/reuses + begins recording).
-    VkCommandBuffer EnsureUploadBatchOpen();
-    // Bump-allocates `size` staging bytes for the open batch, growing onto a
-    // new/pooled block when the current one cannot fit. Returns the write
-    // pointer; outBuffer/outBaseOffset locate the space for copy commands.
-    Uint8* AcquireUploadStagingSpace(VkDeviceSize size, VkBuffer& outBuffer, VkDeviceSize& outBaseOffset);
-    void RecycleUploadStagingBlock(UploadStagingBlock&& block);
-    // Drops a recorded-but-unsubmitted batch on the floor. Shutdown only: the
-    // device is being torn down, so the lost texel data is unobservable.
-    void DiscardPendingUploadBatch();
-    void DestroyUploadPools();
-
-    Vector<UploadStagingBlock> m_freeUploadStagingBlocks;
-    VkDeviceSize m_freeUploadStagingBytes = 0;
-    Vector<VkCommandBuffer> m_freeUploadCommandBuffers;
-    Vector<VkFence> m_freeUploadFences;
-    Bool m_uploadBatchOpen = false;
-    VkCommandBuffer m_uploadBatchCommandBuffer = VK_NULL_HANDLE;
-    // Blocks whose staging bytes the open batch's copies reference (last =
-    // the block the bump cursor is currently allocating from).
-    Vector<UploadStagingBlock> m_uploadBatchBlocks;
-    // Images the open batch writes; consulted for the rare re-upload-after-
-    // draw flush and by DeferResourceRelease (an unsubmitted command buffer
-    // referencing a deferred-released image would escape every fence-based
-    // destruction proof, so the batch is flushed before the image is parked).
-    Vector<VkImage> m_uploadBatchImages;
-    VkDeviceSize m_uploadBatchStagingBytes = 0;
-
-    // Texture uploads are submitted out-of-band but NOT waited on (waiting
-    // behind the queue serialized the CPU against the previous frame's GPU
-    // work every time an animated atlas re-uploaded). Each flushed batch's
-    // transients are parked here and RECYCLED (fence reset to the fence pool,
-    // command buffer reset to the CB pool, staging blocks back to the block
-    // pool) once the batch fence signals.
-    struct PendingUploadReclaim {
-        VkFence fence = VK_NULL_HANDLE;
-        VkCommandBuffer commandBuffer = VK_NULL_HANDLE;
-        Vector<UploadStagingBlock> stagingBlocks;
-    };
-    Vector<PendingUploadReclaim> m_pendingUploadReclaims;
-};
-} // namespace MobileGL::MG_Backend::DirectVulkan

MobileGL/MG_Backend/DirectVulkan/Renderer/VkTimerQueryManager.cpp

@@ -1,179 +0,0 @@
-// 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_ONCE("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_ONCE("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_ONCE("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_ONCE("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

@@ -1,111 +0,0 @@
-// 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/SubgroupSupportPolicy.h

@@ -1,63 +0,0 @@
-// MobileGL - MobileGL/MG_Backend/DirectVulkan/SubgroupSupportPolicy.h
-// Copyright (c) 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 <Config.h>
-#include <Includes.h>
-
-namespace MobileGL::MG_Backend::DirectVulkan {
-    // The single decision point for how DirectVulkan implements GL_KHR_shader_subgroup,
-    // shared by capability advertisement (BackendObject) and module lowering
-    // (VulkanRenderer / ProgramFactory) so the two can never disagree.
-    //
-    // Native subgroups are the implementation whenever the device has them, whatever
-    // their width - subgroup operations execute on the hardware paths they were made
-    // for. Module-level repairs keep the GL contract intact around them:
-    //   - FixIterationRPSubgroupScratchPass patches the one known pack bug: iterationRP's
-    //     prefixSumCache[32], under-declared for sub-16-lane devices (8-lane lavapipe);
-    //   - FixIterationRPBarrierPass repairs Program 203's race between two reductions
-    //     reusing that scratch, when explicitly enabled;
-    //   - DeriveNumSubgroupsPass replaces the one builtin drivers get wrong
-    //     (gl_NumSubgroups) with the value the rest of the topology implies.
-    // The 32-lane shared-memory emulation (EmulateSubgroupsPass) is a LAST RESORT for
-    // devices with no subgroup support at all, and only when the user opts in with
-    // MOBILEGL_MAGMA_EMULATE_SUBGROUP=1; it never replaces available native operations.
-
-    inline constexpr Uint32 kEmulatedSubgroupSize = 32u;
-    inline constexpr Uint32 kEmulatedSubgroupStages = GL_COMPUTE_SHADER_BIT;
-    inline constexpr Uint32 kEmulatedSubgroupFeatures =
-        GL_SUBGROUP_FEATURE_BASIC_BIT_KHR | GL_SUBGROUP_FEATURE_VOTE_BIT_KHR |
-        GL_SUBGROUP_FEATURE_ARITHMETIC_BIT_KHR | GL_SUBGROUP_FEATURE_BALLOT_BIT_KHR |
-        GL_SUBGROUP_FEATURE_SHUFFLE_BIT_KHR | GL_SUBGROUP_FEATURE_SHUFFLE_RELATIVE_BIT_KHR |
-        GL_SUBGROUP_FEATURE_CLUSTERED_BIT_KHR | GL_SUBGROUP_FEATURE_QUAD_BIT_KHR;
-
-    inline Bool ShouldEmulateSubgroups(const Bool nativeSubgroupSupported) {
-        return MG_Config::Features.MagmaEmulateSubgroup && !nativeSubgroupSupported &&
-               !MG_Config::Features.DisableSubgroup;
-    }
-
-    inline Bool ShouldFixIterationRPSubgroupScratch() {
-        // Auto is ON: the patch is fingerprint-gated to iterationRP's reduction and
-        // grows one under-declared array; every other module passes through untouched.
-        return MG_Config::Features.FixIterationRPSubgroupScratch !=
-               MG_Config::QuirkOverride::ForceOff;
-    }
-
-    inline Bool ShouldFixIterationRPBarrier() {
-        return MG_Config::Features.IterationRPFixBarrier;
-    }
-
-    inline Bool ShouldDeriveNumSubgroups() {
-        // Auto is ON: gl_NumSubgroups must agree with the gl_SubgroupID range for the GL
-        // contract to hold, and the derived ceil() value is the one the renderer can pin
-        // with REQUIRE_FULL_SUBGROUPS - the driver builtin is the value with no
-        // cross-driver guarantee (Adreno returns 1 for an 8-subgroup dispatch).
-        return MG_Config::Features.DeriveNumSubgroups != MG_Config::QuirkOverride::ForceOff;
-    }
-} // namespace MobileGL::MG_Backend::DirectVulkan

MobileGL/MG_Backend/DirectVulkan/VkIncludes.h

@@ -1,111 +0,0 @@
-// MobileGL - MobileGL/MG_Backend/DirectVulkan/VkIncludes.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 "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
-
-namespace MobileGL::MG_Backend::DirectVulkan {
-    // GL renders into sRGB color attachments RAW while GL_FRAMEBUFFER_SRGB is disabled
-    // (the core-profile default); Vulkan sRGB attachments always encode on write. The
-    // attachment view (and render pass format) therefore drops to the UNORM twin
-    // whenever the capability is off. Sampled views keep the sRGB format (decode on
-    // sample is unconditional in GL).
-    inline VkFormat ResolveSrgbAttachmentWriteFormat(VkFormat format, bool framebufferSrgbEnabled) {
-        if (framebufferSrgbEnabled) return format;
-        switch (format) {
-        case VK_FORMAT_R8G8B8A8_SRGB:
-            return VK_FORMAT_R8G8B8A8_UNORM;
-        case VK_FORMAT_B8G8R8A8_SRGB:
-            return VK_FORMAT_B8G8R8A8_UNORM;
-        default:
-            return format;
-        }
-    }
-} // namespace MobileGL::MG_Backend::DirectVulkan
-
-// The context line (__VA_ARGS__ = its own format string + args) must be a SEPARATE log
-// call: appending its format to the base format while its arguments precede the base
-// arguments makes every conversion read the wrong slot (a %s pulling an int crashes).
-//
-// MGLOG_F and deliberately NOT latched. VK_VERIFY is the invariant-check macro: a Vulkan call
-// MobileGL believes it has already made legal came back non-success, which is a
-// should-never-happen state, not an expected failure mode a user hits. Those fast-fail loudly
-// and keep saying so - the log-quietness rules that latch W/E cover expected failures (driver
-// capability gaps, app misuse), not broken internal invariants. MOBILEGL_ASSERT below traps in
-// a DEBUG build; MGLOG_F is what makes the same condition visible in an INFO test run, where
-// the assert is compiled out by contract.
-//
-// A soft, recoverable failure must therefore NOT be routed through VK_VERIFY. Check the
-// VkResult directly and report it with MGLOG_E_ONCE - see VkTextureManager::SyncTextureResource,
-// where a driver legitimately refuses an image the format pre-check accepted.
-#define VK_VERIFY(expr, ...)                                                                                           \
-    do {                                                                                                               \
-        VkResult _vk_verify_result = (expr);                                                                           \
-        if (_vk_verify_result != VK_SUCCESS) {                                                                         \
-            __VA_OPT__(MGLOG_F(__VA_ARGS__);)                                                                          \
-            MGLOG_F("Vulkan error %s (%d) at %s:%d",                                                                   \
-                    MobileGL::MG_Backend::DirectVulkan::VkResultToString(_vk_verify_result),                          \
-                    _vk_verify_result, __FILE__, __LINE__);                                                            \
-        }                                                                                                              \
-        MOBILEGL_ASSERT(_vk_verify_result == VK_SUCCESS, "Vulkan error %s (%d) at %s:%d",                              \
-                        MobileGL::MG_Backend::DirectVulkan::VkResultToString(_vk_verify_result),                       \
-                        _vk_verify_result, __FILE__, __LINE__);                                                        \
-    } while (0)
-
-#define XXHASH_VERIFY(expr, ...)                                                                                       \
-    do {                                                                                                               \
-        XXH_errorcode _xxh_verify_result = (expr);                                                                     \
-        if (_xxh_verify_result != XXH_OK) {                                                                            \
-            __VA_OPT__(MGLOG_F(__VA_ARGS__);)                                                                          \
-        }                                                                                                              \
-        MOBILEGL_ASSERT(_xxh_verify_result == XXH_OK, "XXHash error %d at %s:%d", _xxh_verify_result, __FILE__,        \
-                        __LINE__);                                                                                     \
-    } while (0)

MobileGL/MG_Backend/DirectVulkan/VulkanRendererConfig.h

@@ -1,32 +0,0 @@
-// MobileGL - MobileGL/MG_Backend/DirectVulkan/Renderer/VulkanRendererConfig.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 "Config.h"
-
-namespace MobileGL::MG_Backend::DirectVulkan {
-    struct VulkanRendererConfig {
-        // 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
-        Bool EnableValidationLayers = false;
-#endif
-    };
-} // namespace MobileGL::MG_Backend::DirectVulkan

MobileGL/MG_Backend/DirectVulkanTMP/BackendObject_DirectVulkanTMP.cpp

@@ -0,0 +1,119 @@
+// MobileGL - MobileGL/MG_Backend/DirectVulkanTMP/BackendObject_DirectVulkanTMP.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 "BackendObject_DirectVulkanTMP.h"
+#include "MG_Backend/BackendObject.h"
+#include "DirectVulkanTMP.h"
+#include "TmpImpl.h"
+#include <MG_Util/BackendLoaders/OpenGL/Loader.h>
+
+namespace MobileGL::MG_Backend::DirectVulkanTMP {
+    BackendObject_DirectVulkanTMP::~BackendObject_DirectVulkanTMP() = default;
+
+    void BackendObject_DirectVulkanTMP::InitWindowSurface() {
+        auto nativeWindow = reinterpret_cast<NativeWindowType>(m_windowHandle.Handle);
+        if (!DirectVulkanTMP::InitWindowSurface(nativeWindow)) {
+            MGLOG_E("Failed to initialize window surface for DirectVulkanTMP backend");
+        }
+    }
+
+    void BackendObject_DirectVulkanTMP::Initialize() {
+        m_initialized = true;
+    }
+
+    void BackendObject_DirectVulkanTMP::InitCapabilities() {
+        if (!m_initialized) {
+            MGLOG_E("Cannot initialize capabilities before backend is initialized");
+            return;
+        }
+
+        MG_Util::BackendLoader::QueryVulkanCapabilities(m_vulkanCaps,
+                                                        DirectVulkanTMP::GetVulkanState().ctx->GetPhysicalDevice());
+        UpdateDynamicBackendParameters();
+    }
+
+    const RendererInfo& BackendObject_DirectVulkanTMP::GetRendererInfo() const {
+        static RendererInfo RendererInfo = {
+            .RendererName = "Magma-TMP",          // Renderer Name
+            .BackendName = "Direct (Vulkan) TMP", // Backend Name
+            .ExtraVendor = Nullopt,               // Extra vendor
+            .RendererGLInfo =
+                {
+                    .TargetGLVersion = {3, 3, 0},                      // Target OpenGL Version
+                    .TargetGLSLVersion = {4, 6, 0},                    // Target Shading Language Version
+                    .Extensions = {V_OpenGL30, V_OpenGL31, V_OpenGL32, // OpenGL Extensions
+                                   V_OpenGL33},
+                    .IsCompatibilityProfile = false // Is Compatibility Profile
+                },
+            .StaticBackendCapability = {.AllowVSOnlyPrograms = false} // Backend Capability
+        };
+        return RendererInfo;
+    }
+
+    String BackendObject_DirectVulkanTMP::GetBackendAPIVersionString() const {
+        if (!m_initialized) {
+            return "<uninitialized DirectVulkanTMP backend>";
+        }
+        // Format:
+        // <GPU Name>, Vulkan <Vulkan Version>, Driver <Driver Version>
+        // TODO
+        String str = m_vulkanCaps.DeviceName + ", Vulkan " + m_vulkanCaps.VulkanAPIVersion.toString() + ", Driver " +
+                     m_vulkanCaps.DriverVersionString;
+        return str;
+    }
+
+    BackendType BackendObject_DirectVulkanTMP::GetBackendType() const {
+        return BackendType::DirectVulkanTMP;
+    }
+
+    const GlobalBackendFunctionsTable& BackendObject_DirectVulkanTMP::GetBackendFunctions() const {
+        static GlobalBackendFunctionsTable funcsTable;
+        static Bool funcsTableInitialized = false;
+        if (!funcsTableInitialized) {
+            funcsTable.Present = DirectVulkanTMP::Present;
+            funcsTable.GL.DrawArrays = DrawArrays;
+            funcsTable.GL.DrawElements = DrawElements;
+            funcsTable.GL.DrawElementsBaseVertex = DrawElementsBaseVertex;
+            funcsTable.GL.MultiDrawElements = MultiDrawElements;
+            funcsTable.GL.MultiDrawElementsBaseVertex = MultiDrawElementsBaseVertex;
+            funcsTable.GL.MultiDrawElementsIndirect = MultiDrawElementsIndirect;
+            funcsTable.GL.MultiDrawArraysIndirect = MultiDrawArraysIndirect;
+            funcsTable.GL.DrawRangeElementsBaseVertex = DrawRangeElementsBaseVertex;
+            funcsTable.GL.DrawRangeElements = DrawRangeElements;
+            funcsTable.GL.DrawElementsInstancedBaseVertexBaseInstance = DrawElementsInstancedBaseVertexBaseInstance;
+            funcsTable.GL.DrawElementsInstancedBaseVertex = DrawElementsInstancedBaseVertex;
+            funcsTable.GL.DrawElementsInstancedBaseInstance = DrawElementsInstancedBaseInstance;
+            funcsTable.GL.DrawElementsInstanced = DrawElementsInstanced;
+            funcsTable.GL.DrawArraysInstancedBaseInstance = DrawArraysInstancedBaseInstance;
+            funcsTable.GL.DrawArraysInstanced = DrawArraysInstanced;
+            funcsTable.GL.DrawElementsIndirect = DrawElementsIndirect;
+            funcsTable.GL.DrawArraysIndirect = DrawArraysIndirect;
+            funcsTable.GL.Clear = Clear;
+            funcsTable.GL.ClearBufferfi = ClearBufferfi;
+            funcsTable.GL.ClearBufferfv = ClearBufferfv;
+            funcsTable.GL.ClearBufferuiv = ClearBufferuiv;
+            funcsTable.GL.ClearBufferiv = ClearBufferiv;
+            funcsTable.GL.BlitFramebuffer = BlitFramebuffer;
+            funcsTable.GL.CopyTexImage2D = CopyTexImage2D;
+            funcsTable.GL.CopyTexSubImage2D = CopyTexSubImage2D;
+            funcsTable.GL.GenerateMipmap = GenerateMipmap;
+            funcsTable.GL.ReadPixels = ReadPixels;
+            funcsTable.GL.GetTexImage = GetTexImage;
+            funcsTableInitialized = true;
+        }
+        return funcsTable;
+    }
+
+    const DynamicBackendParameters& BackendObject_DirectVulkanTMP::GetDynamicParameters() const {
+        return m_dynamicParameters;
+    }
+
+    void BackendObject_DirectVulkanTMP::UpdateDynamicBackendParameters() {
+        m_dynamicParameters.UniformBufferOffsetAlignment = m_vulkanCaps.UniformBufferOffsetAlignment;
+    }
+} // namespace MobileGL::MG_Backend::DirectVulkanTMP

MobileGL/MG_Backend/DirectVulkanTMP/BackendObject_DirectVulkanTMP.h

@@ -0,0 +1,36 @@
+// MobileGL - MobileGL/MG_Backend/DirectVulkanTMP/BackendObject_DirectVulkanTMP.h
+// Copyright (c) 2025-2026 MobileGL-Dev
+// Licensed under the GNU Lesser General Public License v3.0:
+//   https://www.gnu.org/licenses/gpl-3.0.txt
+//   https://www.gnu.org/licenses/lgpl-3.0.txt
+// SPDX-License-Identifier: LGPL-3.0-only
+// End of Source File Header
+
+#pragma once
+#include <Includes.h>
+#include "../BackendObject.h"
+#include <MG_Util/BackendLoaders/Vulkan/Loader.h>
+
+namespace MobileGL::MG_Backend::DirectVulkanTMP {
+    class BackendObject_DirectVulkanTMP : public BackendObject {
+    public:
+        ~BackendObject_DirectVulkanTMP() override;
+
+        void Initialize() override;
+        void InitWindowSurface() override;
+        void InitCapabilities() override;
+
+        const RendererInfo& GetRendererInfo() const override;
+        String GetBackendAPIVersionString() const override;
+        const GlobalBackendFunctionsTable& GetBackendFunctions() const override;
+        const DynamicBackendParameters& GetDynamicParameters() const override;
+        BackendType GetBackendType() const override;
+
+    private:
+        void UpdateDynamicBackendParameters();
+
+        Bool m_initialized = false;
+        DynamicBackendParameters m_dynamicParameters;
+        MG_External::VulkanCapabilities m_vulkanCaps;
+    };
+} // namespace MobileGL::MG_Backend::DirectVulkanTMP

MobileGL/MG_Backend/DirectVulkanTMP/DirectVulkanTMP.cpp

@@ -0,0 +1,74 @@
+// MobileGL - MobileGL/MG_Backend/DirectVulkanTMP/DirectVulkanTMP.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 "DirectVulkanTMP.h"
+#include "TmpImpl.h"
+
+namespace MobileGL::MG_Backend::DirectVulkanTMP {
+    void Clear(GLbitfield mask) {
+        MobileGL::MG_Backend::DirectVulkanTMP::TmpImpl::Clear(mask);
+    }
+
+    void DrawElements(GLenum mode, GLsizei count, GLenum type, const void* indices) {
+        MobileGL::MG_Backend::DirectVulkanTMP::TmpImpl::DrawElements(mode, count, type, indices);
+    }
+
+    void ClearBufferfi(GLenum buffer, GLint drawbuffer, GLfloat depth, GLint stencil) {}
+    void ClearBufferfv(GLenum buffer, GLint drawbuffer, const GLfloat* value) {}
+    void ClearBufferuiv(GLenum buffer, GLint drawbuffer, const GLuint* value) {}
+    void ClearBufferiv(GLenum buffer, GLint drawbuffer, const GLint* value) {}
+    void DrawArrays(GLenum mode, GLint first, GLsizei count) {}
+    void DrawElementsBaseVertex(GLenum mode, GLsizei count, GLenum type, const GLvoid* indices, GLint basevertex) {}
+    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,
+                                     GLsizei drawcount, const GLint* basevertex) {}
+    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 DrawRangeElementsBaseVertex(GLenum mode, GLuint start, GLuint end, GLsizei count, GLenum type,
+                                     const void* indices, GLint basevertex) {}
+    void DrawRangeElements(GLenum mode, GLuint start, GLuint end, GLsizei count, GLenum type, const void* indices) {}
+    void DrawElementsInstancedBaseVertexBaseInstance(GLenum mode, GLsizei count, GLenum type, const void* indices,
+                                                     GLsizei instancecount, GLint basevertex, GLuint baseinstance) {}
+    void DrawElementsInstancedBaseVertex(GLenum mode, GLsizei count, GLenum type, const void* indices,
+                                         GLsizei instancecount, GLint basevertex) {}
+    void DrawElementsInstancedBaseInstance(GLenum mode, GLsizei count, GLenum type, const void* indices,
+                                           GLsizei instancecount, GLuint baseinstance) {}
+    void DrawElementsInstanced(GLenum mode, GLsizei count, GLenum type, const void* indices, GLsizei instancecount) {}
+    void DrawElementsIndirect(GLenum mode, GLenum type, const void* indirect) {}
+    void DrawArraysInstancedBaseInstance(GLenum mode, GLint first, GLsizei count, GLsizei instancecount,
+                                         GLuint baseinstance) {}
+    void DrawArraysInstanced(GLenum mode, GLint first, GLsizei count, GLsizei instancecount) {}
+    void DrawArraysIndirect(GLenum mode, const void* indirect) {}
+    void BlitFramebuffer(GLint srcX0, GLint srcY0, GLint srcX1, GLint srcY1, GLint dstX0, GLint dstY0, GLint dstX1,
+                         GLint dstY1, GLbitfield mask, GLenum filter) {}
+    void CopyTexImage2D(GLenum target, GLint level, GLenum internalformat, GLint x, GLint y, GLsizei width,
+                        GLsizei height, GLint border) {}
+    void CopyTexSubImage2D(GLenum target, GLint level, GLint xoffset, GLint yoffset, GLint x, GLint y, GLsizei width,
+                           GLsizei height) {}
+    void GenerateMipmap(GLenum target) {}
+    void ReadPixels(GLint x, GLint y, GLsizei width, GLsizei height, GLenum format, GLenum type, void* pixels) {}
+    void GetTexImage(GLenum target, GLint level, GLenum format, GLenum type, GLvoid* pixels) {}
+
+    Bool InitWindowSurface(NativeWindowType window) {
+        if (!window) {
+            MGLOG_E("Cannot initialize Vulkan window surface: invalid window handle");
+            return false;
+        }
+        TmpImpl::InitVulkan(window);
+        return true;
+    }
+
+    void Present() {
+        TmpImpl::Present();
+    }
+
+    const TmpImpl::VulkanState& GetVulkanState() {
+        return TmpImpl::GetVulkanState();
+    }
+} // namespace MobileGL::MG_Backend::DirectVulkanTMP

MobileGL/MG_Backend/DirectVulkanTMP/DirectVulkanTMP.h

@@ -0,0 +1,58 @@
+// MobileGL - MobileGL/MG_Backend/DirectVulkanTMP/DirectVulkanTMP.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_Backend::DirectVulkanTMP {
+    namespace TmpImpl {
+        class VulkanState;
+    } // namespace TmpImpl
+
+    void ClearBufferfi(GLenum buffer, GLint drawbuffer, GLfloat depth, GLint stencil);
+    void ClearBufferfv(GLenum buffer, GLint drawbuffer, const GLfloat* value);
+    void ClearBufferuiv(GLenum buffer, GLint drawbuffer, const GLuint* value);
+    void ClearBufferiv(GLenum buffer, GLint drawbuffer, const GLint* value);
+    void Clear(GLbitfield mask);
+    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 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,
+                                     GLsizei drawcount, const GLint* basevertex);
+    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 DrawRangeElementsBaseVertex(GLenum mode, GLuint start, GLuint end, GLsizei count, GLenum type,
+                                     const void* indices, GLint basevertex);
+    void DrawRangeElements(GLenum mode, GLuint start, GLuint end, GLsizei count, GLenum type, const void* indices);
+    void DrawElementsInstancedBaseVertexBaseInstance(GLenum mode, GLsizei count, GLenum type, const void* indices,
+                                                     GLsizei instancecount, GLint basevertex, GLuint baseinstance);
+    void DrawElementsInstancedBaseVertex(GLenum mode, GLsizei count, GLenum type, const void* indices,
+                                         GLsizei instancecount, GLint basevertex);
+    void DrawElementsInstancedBaseInstance(GLenum mode, GLsizei count, GLenum type, const void* indices,
+                                           GLsizei instancecount, GLuint baseinstance);
+    void DrawElementsInstanced(GLenum mode, GLsizei count, GLenum type, const void* indices, GLsizei instancecount);
+    void DrawElementsIndirect(GLenum mode, GLenum type, const void* indirect);
+    void DrawArraysInstancedBaseInstance(GLenum mode, GLint first, GLsizei count, GLsizei instancecount,
+                                         GLuint baseinstance);
+    void DrawArraysInstanced(GLenum mode, GLint first, GLsizei count, GLsizei instancecount);
+    void DrawArraysIndirect(GLenum mode, const void* indirect);
+    void BlitFramebuffer(GLint srcX0, GLint srcY0, GLint srcX1, GLint srcY1, GLint dstX0, GLint dstY0, GLint dstX1,
+                         GLint dstY1, GLbitfield mask, GLenum filter);
+    void CopyTexImage2D(GLenum target, GLint level, GLenum internalformat, GLint x, GLint y, GLsizei width,
+                        GLsizei height, GLint border);
+    void CopyTexSubImage2D(GLenum target, GLint level, GLint xoffset, GLint yoffset, GLint x, GLint y, GLsizei width,
+                           GLsizei height);
+    void GenerateMipmap(GLenum target);
+    void ReadPixels(GLint x, GLint y, GLsizei width, GLsizei height, GLenum format, GLenum type, void* pixels);
+    void GetTexImage(GLenum target, GLint level, GLenum format, GLenum type, GLvoid* pixels);
+    Bool InitWindowSurface(NativeWindowType window);
+    void Present();
+    const TmpImpl::VulkanState& GetVulkanState();
+} // namespace MobileGL::MG_Backend::DirectVulkanTMP

MobileGL/MG_Backend/DirectVulkanTMP/Managers/ProgramManager.cpp

@@ -0,0 +1,447 @@
+// MobileGL - MobileGL/MG_Backend/DirectVulkanTMP/Managers/ProgramManager.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 "ProgramManager.h"
+
+#include "MG_Util/Debug/Log.h"
+#include "spirv-tools/libspirv.h"
+#include "spirv-tools/optimizer.hpp"
+#include "source/opt/constants.h"
+#include "source/opt/instruction.h"
+#include "source/opt/ir_builder.h"
+#include "source/opt/ir_context.h"
+#include "source/opt/module.h"
+#include "source/opt/pass.h"
+#include "source/opt/type_manager.h"
+
+#include <bit>
+
+namespace MobileGL::MG_Backend::DirectVulkanTMP::VkManager {
+    namespace {
+        using ProgramObject = MG_State::GLState::ProgramObject;
+        using ShaderObject = MG_State::GLState::ShaderObject;
+
+        struct PositionTargetInfo {
+            uint32_t variableId = 0;
+            uint32_t vectorTypeId = 0;
+            uint32_t floatTypeId = 0;
+            uint32_t vectorPtrTypeId = 0;
+            uint32_t memberIndex = 0;
+            bool isMember = false;
+        };
+
+        bool IsVec4Float32(spvtools::opt::IRContext* context, uint32_t typeId, uint32_t* outFloatTypeId) {
+            auto* vecInst = context->get_def_use_mgr()->GetDef(typeId);
+            if (!vecInst || vecInst->opcode() != spv::Op::OpTypeVector) return false;
+            if (vecInst->GetSingleWordInOperand(1) != 4) return false;
+
+            const uint32_t floatTypeId = vecInst->GetSingleWordInOperand(0);
+            auto* floatInst = context->get_def_use_mgr()->GetDef(floatTypeId);
+            if (!floatInst || floatInst->opcode() != spv::Op::OpTypeFloat) return false;
+            if (floatInst->GetSingleWordInOperand(0) != 32) return false;
+
+            if (outFloatTypeId) *outFloatTypeId = floatTypeId;
+            return true;
+        }
+
+        bool ResolveDirectPositionTarget(spvtools::opt::IRContext* context, uint32_t variableId,
+                                         PositionTargetInfo* outTarget) {
+            auto* varInst = context->get_def_use_mgr()->GetDef(variableId);
+            if (!varInst || varInst->opcode() != spv::Op::OpVariable) return false;
+            if (varInst->GetSingleWordInOperand(0) != static_cast<uint32_t>(spv::StorageClass::Output)) return false;
+
+            auto* ptrTypeInst = context->get_def_use_mgr()->GetDef(varInst->type_id());
+            if (!ptrTypeInst || ptrTypeInst->opcode() != spv::Op::OpTypePointer) return false;
+            if (ptrTypeInst->GetSingleWordInOperand(0) != static_cast<uint32_t>(spv::StorageClass::Output))
+                return false;
+
+            PositionTargetInfo target{};
+            target.variableId = variableId;
+            target.vectorTypeId = ptrTypeInst->GetSingleWordInOperand(1);
+            if (!IsVec4Float32(context, target.vectorTypeId, &target.floatTypeId)) return false;
+            target.vectorPtrTypeId = varInst->type_id();
+            target.isMember = false;
+
+            *outTarget = target;
+            return true;
+        }
+
+        uint32_t FindOutputVectorPointerTypeId(spvtools::opt::IRContext* context, uint32_t vectorTypeId) {
+            auto* vectorType = context->get_type_mgr()->GetType(vectorTypeId);
+            if (!vectorType) return 0;
+            spvtools::opt::analysis::Pointer ptrType(vectorType, spv::StorageClass::Output);
+            return context->get_type_mgr()->GetTypeInstruction(&ptrType);
+        }
+
+        bool ResolveMemberPositionTarget(spvtools::opt::IRContext* context, uint32_t structTypeId, uint32_t memberIndex,
+                                         PositionTargetInfo* outTarget) {
+            auto* structInst = context->get_def_use_mgr()->GetDef(structTypeId);
+            if (!structInst || structInst->opcode() != spv::Op::OpTypeStruct) return false;
+            if (memberIndex >= structInst->NumInOperands()) return false;
+
+            const uint32_t vectorTypeId = structInst->GetSingleWordInOperand(memberIndex);
+            uint32_t floatTypeId = 0;
+            if (!IsVec4Float32(context, vectorTypeId, &floatTypeId)) return false;
+
+            const uint32_t vectorPtrTypeId = FindOutputVectorPointerTypeId(context, vectorTypeId);
+            if (vectorPtrTypeId == 0) return false;
+
+            for (auto& inst : context->module()->types_values()) {
+                if (inst.opcode() != spv::Op::OpVariable) continue;
+                if (inst.GetSingleWordInOperand(0) != static_cast<uint32_t>(spv::StorageClass::Output)) continue;
+
+                auto* ptrTypeInst = context->get_def_use_mgr()->GetDef(inst.type_id());
+                if (!ptrTypeInst || ptrTypeInst->opcode() != spv::Op::OpTypePointer) continue;
+                if (ptrTypeInst->GetSingleWordInOperand(0) != static_cast<uint32_t>(spv::StorageClass::Output))
+                    continue;
+                if (ptrTypeInst->GetSingleWordInOperand(1) != structTypeId) continue;
+
+                PositionTargetInfo target{};
+                target.variableId = inst.result_id();
+                target.vectorTypeId = vectorTypeId;
+                target.floatTypeId = floatTypeId;
+                target.vectorPtrTypeId = vectorPtrTypeId;
+                target.memberIndex = memberIndex;
+                target.isMember = true;
+                *outTarget = target;
+                return true;
+            }
+
+            return false;
+        }
+
+        bool FindPositionTarget(spvtools::opt::IRContext* context, PositionTargetInfo* outTarget) {
+            Vector<Pair<uint32_t, uint32_t>> memberCandidates;
+            constexpr uint32_t kDecorationBuiltIn = static_cast<uint32_t>(spv::Decoration::BuiltIn);
+            constexpr uint32_t kBuiltInPosition = static_cast<uint32_t>(spv::BuiltIn::Position);
+
+            for (auto& inst : context->module()->annotations()) {
+                if (inst.opcode() == spv::Op::OpDecorate) {
+                    if (inst.NumInOperands() < 3) continue;
+                    if (inst.GetSingleWordInOperand(1) != kDecorationBuiltIn) continue;
+                    if (inst.GetSingleWordInOperand(2) != kBuiltInPosition) continue;
+                    if (ResolveDirectPositionTarget(context, inst.GetSingleWordInOperand(0), outTarget)) return true;
+                } else if (inst.opcode() == spv::Op::OpMemberDecorate) {
+                    if (inst.NumInOperands() < 4) continue;
+                    if (inst.GetSingleWordInOperand(2) != kDecorationBuiltIn) continue;
+                    if (inst.GetSingleWordInOperand(3) != kBuiltInPosition) continue;
+                    memberCandidates.emplace_back(inst.GetSingleWordInOperand(0), inst.GetSingleWordInOperand(1));
+                }
+            }
+
+            for (const auto& [structTypeId, memberIndex] : memberCandidates) {
+                if (ResolveMemberPositionTarget(context, structTypeId, memberIndex, outTarget)) return true;
+            }
+            return false;
+        }
+
+        bool InsertPositionFixup(spvtools::opt::IRContext* context, spvtools::opt::Instruction* insertBefore,
+                                 const PositionTargetInfo& target, uint32_t halfConstId, bool doYFlip, bool doZRemap) {
+            using namespace spvtools::opt;
+            InstructionBuilder builder(context, insertBefore,
+                                       IRContext::kAnalysisDefUse | IRContext::kAnalysisInstrToBlockMapping);
+
+            uint32_t positionPtrId = target.variableId;
+            if (target.isMember) {
+                const uint32_t memberIndexId = builder.GetUintConstantId(target.memberIndex);
+                if (memberIndexId == 0) return false;
+                auto* access = builder.AddAccessChain(target.vectorPtrTypeId, target.variableId, {memberIndexId});
+                if (!access) return false;
+                positionPtrId = access->result_id();
+            }
+
+            auto* position = builder.AddLoad(target.vectorTypeId, positionPtrId);
+            if (!position) return false;
+            auto* x = builder.AddCompositeExtract(target.floatTypeId, position->result_id(), {0});
+            auto* y = builder.AddCompositeExtract(target.floatTypeId, position->result_id(), {1});
+            auto* z = builder.AddCompositeExtract(target.floatTypeId, position->result_id(), {2});
+            auto* w = builder.AddCompositeExtract(target.floatTypeId, position->result_id(), {3});
+            if (!x || !y || !z || !w) return false;
+
+            if (!doYFlip && !doZRemap) return false;
+
+            uint32_t yValueId = y->result_id();
+            if (doYFlip) {
+                auto* negY = builder.AddUnaryOp(target.floatTypeId, spv::Op::OpFNegate, y->result_id());
+                if (!negY) return false;
+                yValueId = negY->result_id();
+            }
+
+            uint32_t zValueId = z->result_id();
+            if (doZRemap) {
+                auto* zPlusW = builder.AddBinaryOp(target.floatTypeId, spv::Op::OpFAdd, z->result_id(), w->result_id());
+                if (!zPlusW) return false;
+                auto* mappedZ =
+                    builder.AddBinaryOp(target.floatTypeId, spv::Op::OpFMul, zPlusW->result_id(), halfConstId);
+                if (!mappedZ) return false;
+                zValueId = mappedZ->result_id();
+            }
+
+            auto* fixedPosition = builder.AddCompositeConstruct(target.vectorTypeId,
+                                                                {x->result_id(), yValueId, zValueId, w->result_id()});
+            if (!fixedPosition) return false;
+
+            return builder.AddStore(positionPtrId, fixedPosition->result_id()) != nullptr;
+        }
+
+        class GlToVulkanPositionFixPass final : public spvtools::opt::Pass {
+        public:
+            const char* name() const override { return "gl-to-vulkan-position-fix"; }
+            explicit GlToVulkanPositionFixPass(ShaderTransformFlags transformFlags)
+                : m_transformFlags(transformFlags) {}
+
+            Status Process() override {
+                if (!m_transformFlags) return Status::SuccessWithoutChange;
+                PositionTargetInfo target{};
+                if (!FindPositionTarget(context(), &target)) return Status::SuccessWithoutChange;
+
+                auto* floatType = context()->get_type_mgr()->GetType(target.floatTypeId);
+                if (!floatType) return Status::SuccessWithoutChange;
+
+                const uint32_t halfBits = std::bit_cast<uint32_t>(0.5f);
+                const auto* halfConst = context()->get_constant_mgr()->GetConstant(floatType, {halfBits});
+                auto* halfInst = context()->get_constant_mgr()->GetDefiningInstruction(halfConst);
+                if (!halfInst) return Status::SuccessWithoutChange;
+                const uint32_t halfConstId = halfInst->result_id();
+
+                const bool doYFlip = (m_transformFlags & ShaderTransformBit::PositionYFlip);
+                const bool doZRemap = (m_transformFlags & ShaderTransformBit::PositionZRemap);
+
+                bool modified = false;
+                for (auto& entryPoint : get_module()->entry_points()) {
+                    if (entryPoint.opcode() != spv::Op::OpEntryPoint) continue;
+                    if (entryPoint.NumInOperands() < 2) continue;
+
+                    const auto model = static_cast<spv::ExecutionModel>(entryPoint.GetSingleWordInOperand(0));
+                    if (model != spv::ExecutionModel::Vertex && model != spv::ExecutionModel::TessellationEvaluation &&
+                        model != spv::ExecutionModel::Geometry) {
+                        continue;
+                    }
+
+                    auto* function = context()->GetFunction(entryPoint.GetSingleWordInOperand(1));
+                    if (!function) continue;
+
+                    for (auto& bb : *function) {
+                        for (auto instIter = bb.begin(); instIter != bb.end(); ++instIter) {
+                            auto* inst = &*instIter;
+                            const bool needsFixup =
+                                (model == spv::ExecutionModel::Geometry && inst->opcode() == spv::Op::OpEmitVertex) ||
+                                (model != spv::ExecutionModel::Geometry && inst->opcode() == spv::Op::OpReturn);
+                            if (!needsFixup) continue;
+
+                            modified |= InsertPositionFixup(context(), inst, target, halfConstId, doYFlip, doZRemap);
+                        }
+                    }
+                }
+
+                if (!modified) return Status::SuccessWithoutChange;
+                context()->InvalidateAnalysesExceptFor(spvtools::opt::IRContext::kAnalysisDefUse |
+                                                       spvtools::opt::IRContext::kAnalysisInstrToBlockMapping);
+                return Status::SuccessWithChange;
+            }
+
+        private:
+            ShaderTransformFlags m_transformFlags;
+        };
+
+        spvtools::Optimizer::PassToken CreateGlToVulkanPositionFixPass(ShaderTransformFlags transformFlags) {
+            return spvtools::Optimizer::PassToken(MakeUnique<GlToVulkanPositionFixPass>(transformFlags));
+        }
+
+        bool TransformSpirvForVulkanPositionFix(const Vector<Uint32>& input, Vector<Uint32>& output,
+                                                ShaderTransformFlags transformFlags) {
+            if (input.empty()) {
+                output.clear();
+                return true;
+            }
+
+            if (!transformFlags) {
+                output = input;
+                return true;
+            }
+
+            spvtools::Optimizer optimizer(SPV_ENV_VULKAN_1_3);
+            spvtools::OptimizerOptions options;
+            options.set_run_validator(false);
+            optimizer.RegisterPass(CreateGlToVulkanPositionFixPass(transformFlags));
+
+            const bool success = optimizer.Run(input.data(), input.size(), &output, options);
+            if (!success) {
+                MGLOG_E("Vulkan: failed to run GL->Vulkan position fix pass");
+                output = input;
+            }
+            return success;
+        }
+
+        ShaderStage PickClipFixupStage(const Vector<SharedPtr<ShaderObject>>& shaders) {
+            bool hasGeometry = false;
+            bool hasTessEval = false;
+            bool hasVertex = false;
+
+            for (const auto& shader : shaders) {
+                if (!shader) continue;
+                const auto stage = shader->GetShaderStage();
+                hasGeometry |= (stage == ShaderStage::Geometry);
+                hasTessEval |= (stage == ShaderStage::TessEval);
+                hasVertex |= (stage == ShaderStage::Vertex);
+            }
+
+            if (hasGeometry) return ShaderStage::Geometry;
+            if (hasTessEval) return ShaderStage::TessEval;
+            if (hasVertex) return ShaderStage::Vertex;
+            return ShaderStage::Unknown;
+        }
+    } // namespace
+
+    ProgramManager::~ProgramManager() {
+        for (auto& [_, stages] : m_cache) {
+            DestroyStages(stages);
+        }
+        m_cache.clear();
+    }
+
+    ProgramManager::HashType ProgramManager::ComputeSourceSpvHash(MG_State::GLState::ProgramObject* program) const {
+        if (!program) return 0;
+        XXH64_state_t* state = XXH64_createState();
+        XXH64_reset(state, 0xC0FFEEu);
+        auto& spirvs = program->GetGeneratedSpirv();
+        for (const auto& spv : spirvs) {
+            if (spv.empty()) continue;
+            XXH64_update(state, spv.data(), spv.size() * sizeof(Uint));
+        }
+        HashType hash = XXH64_digest(state);
+        XXH64_freeState(state);
+        return hash;
+    }
+
+    ProgramManager::HashType ProgramManager::ComputeSpvHash(const Vector<Vector<Uint32>>& spirvs) const {
+        XXH64_state_t* state = XXH64_createState();
+        XXH64_reset(state, 0xC0FFEEu);
+        for (const auto& spv : spirvs) {
+            if (spv.empty()) continue;
+            XXH64_update(state, spv.data(), spv.size() * sizeof(Uint32));
+        }
+        HashType hash = XXH64_digest(state);
+        XXH64_freeState(state);
+        return hash;
+    }
+
+    void ProgramManager::BuildPipelineSpirvModules(MG_State::GLState::ProgramObject* program,
+                                                   Vector<Vector<Uint32>>& outSpirvs,
+                                                   ShaderTransformFlags transformFlags) const {
+        outSpirvs.clear();
+        if (!program) return;
+
+        auto& spirvs = program->GetGeneratedSpirv();
+        auto& shaders = program->GetAttachedShaders();
+        const ShaderStage fixupStage = PickClipFixupStage(shaders);
+
+        outSpirvs.reserve(spirvs.size());
+        for (SizeT i = 0; i < spirvs.size(); ++i) {
+            Vector<Uint32> module = spirvs[i];
+
+            ShaderStage stage = ShaderStage::Unknown;
+            if (i < shaders.size() && shaders[i]) stage = shaders[i]->GetShaderStage();
+
+            if (!module.empty() && fixupStage != ShaderStage::Unknown && stage == fixupStage) {
+                Vector<Uint32> transformed;
+                TransformSpirvForVulkanPositionFix(module, transformed, transformFlags);
+                module = Move(transformed);
+            }
+            outSpirvs.push_back(Move(module));
+        }
+    }
+
+    ProgramManager::HashType ProgramManager::ComputeSpvHash(MG_State::GLState::ProgramObject* program,
+                                                            ShaderTransformFlags transformFlags) const {
+        Vector<Vector<Uint32>> spirvs;
+        BuildPipelineSpirvModules(program, spirvs, transformFlags);
+        return ComputeSpvHash(spirvs);
+    }
+
+    ProgramManager::HashType ProgramManager::ComputeProgramHash(MG_State::GLState::ProgramObject* program,
+                                                                ShaderTransformFlags transformFlags) const {
+        if (!program) return 0;
+        const HashType sourceHash = ComputeSourceSpvHash(program);
+        auto it = m_cache.find(program);
+        if (it != m_cache.end() && it->second.sourceHash == sourceHash) return it->second.hash;
+        return ComputeSpvHash(program, transformFlags);
+    }
+
+    VkShaderStageFlagBits ProgramManager::ToVkStage(ShaderStage stage) const {
+        switch (stage) {
+        case ShaderStage::Vertex:
+            return VK_SHADER_STAGE_VERTEX_BIT;
+        case ShaderStage::Fragment:
+            return VK_SHADER_STAGE_FRAGMENT_BIT;
+        case ShaderStage::Geometry:
+            return VK_SHADER_STAGE_GEOMETRY_BIT;
+        case ShaderStage::TessControl:
+            return VK_SHADER_STAGE_TESSELLATION_CONTROL_BIT;
+        case ShaderStage::TessEval:
+            return VK_SHADER_STAGE_TESSELLATION_EVALUATION_BIT;
+        case ShaderStage::Compute:
+            return VK_SHADER_STAGE_COMPUTE_BIT;
+        default:
+            return VK_SHADER_STAGE_ALL_GRAPHICS;
+        }
+    }
+
+    void ProgramManager::DestroyStages(ProgramStages& stages) {
+        for (auto module : stages.modules) {
+            if (module != VK_NULL_HANDLE) {
+                vkDestroyShaderModule(m_ctx.GetDevice(), module, nullptr);
+            }
+        }
+        stages.modules.clear();
+        stages.stages.clear();
+        stages.sourceHash = 0;
+        stages.hash = 0;
+    }
+
+    Vector<VkPipelineShaderStageCreateInfo>& ProgramManager::CreatePipelineShaderStages(
+        MG_State::GLState::ProgramObject* program, ShaderTransformFlags transformFlags) {
+        auto& entry = m_cache[program];
+        HashType sourceHash = ComputeSourceSpvHash(program);
+        if (!entry.stages.empty() && entry.sourceHash == sourceHash) return entry.stages;
+
+        DestroyStages(entry);
+        entry.sourceHash = sourceHash;
+
+        if (!program) return entry.stages;
+
+        Vector<Vector<Uint32>> spirvs;
+        BuildPipelineSpirvModules(program, spirvs, transformFlags);
+        entry.hash = ComputeSpvHash(spirvs);
+        auto& shaders = program->GetAttachedShaders();
+
+        for (SizeT i = 0; i < spirvs.size(); ++i) {
+            auto& spv = spirvs[i];
+            if (spv.empty()) continue;
+
+            VkShaderModuleCreateInfo smci{VK_STRUCTURE_TYPE_SHADER_MODULE_CREATE_INFO};
+            smci.codeSize = spv.size() * sizeof(Uint);
+            smci.pCode = spv.data();
+
+            VkShaderModule module = VK_NULL_HANDLE;
+            VK_VERIFY(vkCreateShaderModule(m_ctx.GetDevice(), &smci, nullptr, &module), "vkCreateShaderModule");
+
+            VkPipelineShaderStageCreateInfo stage{VK_STRUCTURE_TYPE_PIPELINE_SHADER_STAGE_CREATE_INFO};
+            ShaderStage shaderStage = ShaderStage::Unknown;
+            if (i < shaders.size() && shaders[i]) shaderStage = shaders[i]->GetShaderStage();
+            stage.stage = ToVkStage(shaderStage);
+            stage.module = module;
+            stage.pName = "main";
+
+            entry.modules.push_back(module);
+            entry.stages.push_back(stage);
+        }
+
+        return entry.stages;
+    }
+} // namespace MobileGL::MG_Backend::DirectVulkanTMP::VkManager

MobileGL/MG_Backend/DirectVulkanTMP/Managers/ProgramManager.h

@@ -0,0 +1,58 @@
+// MobileGL - MobileGL/MG_Backend/DirectVulkanTMP/Managers/ProgramManager.h
+// Copyright (c) 2025-2026 MobileGL-Dev
+// Licensed under the GNU Lesser General Public License v3.0:
+//   https://www.gnu.org/licenses/gpl-3.0.txt
+//   https://www.gnu.org/licenses/lgpl-3.0.txt
+// SPDX-License-Identifier: LGPL-3.0-only
+// End of Source File Header
+
+#pragma once
+#include <Includes.h>
+#include "../Renderer/VulkanContext.h"
+#include "../Renderer/VkCommon.h"
+#include "MG_State/GLState/ProgramState/ProgramObject.h"
+
+namespace MobileGL::MG_Backend::DirectVulkanTMP::VkManager {
+    enum class ShaderTransformBit : Uint {
+        None = 0,
+        PositionYFlip = 1 << 0,
+        PositionZRemap = 1 << 1,
+    };
+    using ShaderTransformFlags = Flags<ShaderTransformBit>;
+
+    class ProgramManager {
+    public:
+        using HashType = Uint64;
+
+        explicit ProgramManager(VulkanContext& ctx) : m_ctx(ctx) {}
+        ~ProgramManager();
+
+        ProgramManager(const ProgramManager&) = delete;
+        ProgramManager& operator=(const ProgramManager&) = delete;
+
+        Vector<VkPipelineShaderStageCreateInfo>& CreatePipelineShaderStages(
+            MG_State::GLState::ProgramObject* program,
+            ShaderTransformFlags transformFlags = ShaderTransformBit::PositionZRemap);
+        HashType ComputeProgramHash(MG_State::GLState::ProgramObject* program,
+                                    ShaderTransformFlags transformFlags = ShaderTransformBit::PositionZRemap) const;
+
+    private:
+        struct ProgramStages {
+            HashType sourceHash = 0;
+            HashType hash = 0;
+            Vector<VkPipelineShaderStageCreateInfo> stages;
+            Vector<VkShaderModule> modules;
+        };
+
+        void DestroyStages(ProgramStages& stages);
+        HashType ComputeSourceSpvHash(MG_State::GLState::ProgramObject* program) const;
+        HashType ComputeSpvHash(MG_State::GLState::ProgramObject* program, ShaderTransformFlags transformFlags) const;
+        HashType ComputeSpvHash(const Vector<Vector<Uint32>>& spirvs) const;
+        void BuildPipelineSpirvModules(MG_State::GLState::ProgramObject* program, Vector<Vector<Uint32>>& outSpirvs,
+                                       ShaderTransformFlags transformFlags) const;
+        VkShaderStageFlagBits ToVkStage(ShaderStage stage) const;
+
+        VulkanContext& m_ctx;
+        UnorderedMap<const MG_State::GLState::ProgramObject*, ProgramStages> m_cache;
+    };
+} // namespace MobileGL::MG_Backend::DirectVulkanTMP::VkManager

MobileGL/MG_Backend/DirectVulkanTMP/Renderer/FrameContext.cpp

@@ -0,0 +1,49 @@
+// MobileGL - MobileGL/MG_Backend/DirectVulkanTMP/Renderer/FrameContext.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 "FrameContext.h"
+
+namespace MobileGL::MG_Backend::DirectVulkanTMP::VkManager {
+    void FrameContext::Initialize(VulkanContext& ctx, VkCommandPool pool) {
+        CommandPool = pool;
+        VkCommandBufferAllocateInfo abci{VK_STRUCTURE_TYPE_COMMAND_BUFFER_ALLOCATE_INFO};
+        abci.commandPool = pool;
+        abci.level = VK_COMMAND_BUFFER_LEVEL_PRIMARY;
+        abci.commandBufferCount = 1;
+        VK_VERIFY(vkAllocateCommandBuffers(ctx.GetDevice(), &abci, &CommandBuffer), "vkAllocateCommandBuffers");
+
+        VkSemaphoreCreateInfo sci{VK_STRUCTURE_TYPE_SEMAPHORE_CREATE_INFO};
+        VK_VERIFY(vkCreateSemaphore(ctx.GetDevice(), &sci, nullptr, &ImageAvailable), "vkCreateSemaphore");
+        VK_VERIFY(vkCreateSemaphore(ctx.GetDevice(), &sci, nullptr, &RenderFinished), "vkCreateSemaphore");
+
+        VkFenceCreateInfo fci{VK_STRUCTURE_TYPE_FENCE_CREATE_INFO};
+        fci.flags = VK_FENCE_CREATE_SIGNALED_BIT;
+        VK_VERIFY(vkCreateFence(ctx.GetDevice(), &fci, nullptr, &InFlightFence), "vkCreateFence");
+    }
+
+    void FrameContext::Cleanup(VulkanContext& ctx) {
+        auto device = ctx.GetDevice();
+        if (InFlightFence != VK_NULL_HANDLE) {
+            vkDestroyFence(device, InFlightFence, nullptr);
+            InFlightFence = VK_NULL_HANDLE;
+        }
+        if (ImageAvailable != VK_NULL_HANDLE) {
+            vkDestroySemaphore(device, ImageAvailable, nullptr);
+            ImageAvailable = VK_NULL_HANDLE;
+        }
+        if (RenderFinished != VK_NULL_HANDLE) {
+            vkDestroySemaphore(device, RenderFinished, nullptr);
+            RenderFinished = VK_NULL_HANDLE;
+        }
+        if (CommandBuffer != VK_NULL_HANDLE) {
+            vkFreeCommandBuffers(device, CommandPool, 1, &CommandBuffer);
+            CommandBuffer = VK_NULL_HANDLE;
+        }
+        CommandPool = VK_NULL_HANDLE;
+    }
+} // namespace MobileGL::MG_Backend::DirectVulkanTMP::VkManager

MobileGL/MG_Backend/DirectVulkanTMP/Renderer/FrameContext.h

@@ -0,0 +1,42 @@
+// MobileGL - MobileGL/MG_Backend/DirectVulkanTMP/Renderer/FrameContext.h
+// Copyright (c) 2025-2026 MobileGL-Dev
+// Licensed under the GNU Lesser General Public License v3.0:
+//   https://www.gnu.org/licenses/gpl-3.0.txt
+//   https://www.gnu.org/licenses/lgpl-3.0.txt
+// SPDX-License-Identifier: LGPL-3.0-only
+// End of Source File Header
+
+#pragma once
+#include <Includes.h>
+#include "VulkanContext.h"
+#include "VkCommon.h"
+
+namespace MobileGL::MG_Backend::DirectVulkanTMP {
+    struct TrashBuffer {
+        VkBuffer buffer = VK_NULL_HANDLE;
+        VkDeviceMemory memory = VK_NULL_HANDLE;
+        Bool mapped = false;
+    };
+    struct TrashImage {
+        VkImage image = VK_NULL_HANDLE;
+        VkDeviceMemory memory = VK_NULL_HANDLE;
+        VkImageView view = VK_NULL_HANDLE;
+        Vector<VkImageView> mipViews;
+    };
+    namespace VkManager {
+        struct FrameContext {
+            VkCommandBuffer CommandBuffer = VK_NULL_HANDLE;
+            VkSemaphore ImageAvailable = VK_NULL_HANDLE;
+            VkSemaphore RenderFinished = VK_NULL_HANDLE;
+            VkFence InFlightFence = VK_NULL_HANDLE;
+            Uint32 CurrentImageIndex = 0;
+            VkCommandPool CommandPool = VK_NULL_HANDLE;
+            Vector<TrashBuffer> TrashBuffers;
+            Vector<TrashImage> TrashImages;
+            // VkCommandPool CommandPool = VK_NULL_HANDLE;
+
+            void Initialize(VulkanContext& ctx, VkCommandPool pool);
+            void Cleanup(VulkanContext& ctx);
+        };
+    } // namespace VkManager
+} // namespace MobileGL::MG_Backend::DirectVulkanTMP

MobileGL/MG_Backend/DirectVulkanTMP/Renderer/PipelineManager.cpp

@@ -1,4 +1,4 @@
-// MobileGL - MobileGL/MG_Impl/NSOpenGLImpl/NSOpenGLImpl.h
+// MobileGL - MobileGL/MG_Backend/DirectVulkanTMP/Renderer/PipelineManager.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
@@ -6,9 +6,6 @@
 // SPDX-License-Identifier: LGPL-3.0-only
 // End of Source File Header
 
-#pragma once
 #include <Includes.h>
 
-namespace MobileGL::MG_Impl::NSOpenGLImpl {
-    void InstallHooks();
-}
+namespace MobileGL::MG_Backend::DirectVulkanTMP::VkManager {}

MobileGL/MG_Backend/DirectVulkanTMP/Renderer/SwapchainManager.cpp

@@ -0,0 +1,166 @@
+// MobileGL - MobileGL/MG_Backend/DirectVulkanTMP/Renderer/SwapchainManager.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 "SwapchainManager.h"
+
+namespace MobileGL::MG_Backend::DirectVulkanTMP::VkManager {
+    namespace {
+        VkSurfaceFormatKHR ChooseSurfaceFormat(const Vector<VkSurfaceFormatKHR>& formats) {
+            for (const auto& f : formats) {
+                if ((f.format == VK_FORMAT_R8G8B8A8_UNORM || f.format == VK_FORMAT_B8G8R8A8_UNORM) &&
+                    f.colorSpace == VK_COLOR_SPACE_SRGB_NONLINEAR_KHR) {
+                    return f;
+                }
+            }
+            return formats.empty() ? VkSurfaceFormatKHR{VK_FORMAT_B8G8R8A8_UNORM, VK_COLOR_SPACE_SRGB_NONLINEAR_KHR}
+                                   : formats[0];
+        }
+
+        VkPresentModeKHR ChoosePresentMode(const Vector<VkPresentModeKHR>& modes) {
+            for (const auto& m : modes) {
+                if (m == VK_PRESENT_MODE_MAILBOX_KHR) return m;
+            }
+            return VK_PRESENT_MODE_FIFO_KHR;
+        }
+
+        VkExtent2D ChooseExtent(const VkSurfaceCapabilitiesKHR& caps, ANativeWindow* window) {
+            if (caps.currentExtent.width != UINT32_MAX) return caps.currentExtent;
+            // try to get frontend viewport size
+            VkExtent2D extent{640, 480};
+#ifdef VK_USE_PLATFORM_ANDROID_KHR
+            if (window) {
+                extent.width = static_cast<Uint32>(ANativeWindow_getWidth(window));
+                extent.height = static_cast<Uint32>(ANativeWindow_getHeight(window));
+            }
+#else
+            (void)window;
+#endif
+            extent.width = std::max(caps.minImageExtent.width, std::min(caps.maxImageExtent.width, extent.width));
+            extent.height = std::max(caps.minImageExtent.height, std::min(caps.maxImageExtent.height, extent.height));
+            return extent;
+        }
+    } // namespace
+
+    SwapchainManager::~SwapchainManager() {
+        DestroySwapchain();
+    }
+
+    void SwapchainManager::Initialize() {
+        CreateSwapchain(VK_NULL_HANDLE);
+    }
+
+    void SwapchainManager::Recreate() {
+        DestroySwapchain();
+        CreateSwapchain(VK_NULL_HANDLE);
+    }
+
+    void SwapchainManager::SetFramebuffers(Vector<VkFramebuffer>&& framebuffers) {
+        m_framebuffers = Move(framebuffers);
+    }
+
+    void SwapchainManager::DestroySwapchain() {
+        auto device = m_ctx.GetDevice();
+        if (device == VK_NULL_HANDLE) return;
+        for (auto fb : m_framebuffers) {
+            if (fb != VK_NULL_HANDLE) vkDestroyFramebuffer(device, fb, nullptr);
+        }
+        m_framebuffers.clear();
+
+        for (auto view : m_imageViews) {
+            if (view != VK_NULL_HANDLE) vkDestroyImageView(device, view, nullptr);
+        }
+        m_imageViews.clear();
+        m_images.clear();
+        m_imagesInFlight.clear();
+
+        if (m_swapchain != VK_NULL_HANDLE) {
+            vkDestroySwapchainKHR(device, m_swapchain, nullptr);
+            m_swapchain = VK_NULL_HANDLE;
+        }
+        m_format = VK_FORMAT_UNDEFINED;
+        m_extent = {0, 0};
+    }
+
+    void SwapchainManager::CreateSwapchain(VkSwapchainKHR oldSwapchain) {
+        VkSurfaceCapabilitiesKHR caps{};
+        VK_VERIFY(vkGetPhysicalDeviceSurfaceCapabilitiesKHR(m_ctx.GetPhysicalDevice(), m_ctx.GetSurface(), &caps),
+                  "vkGetPhysicalDeviceSurfaceCapabilitiesKHR");
+
+        Uint32 fmtCount = 0;
+        vkGetPhysicalDeviceSurfaceFormatsKHR(m_ctx.GetPhysicalDevice(), m_ctx.GetSurface(), &fmtCount, nullptr);
+        Vector<VkSurfaceFormatKHR> formats(fmtCount);
+        if (fmtCount > 0) {
+            vkGetPhysicalDeviceSurfaceFormatsKHR(m_ctx.GetPhysicalDevice(), m_ctx.GetSurface(), &fmtCount,
+                                                 formats.data());
+        }
+
+        Uint32 modeCount = 0;
+        vkGetPhysicalDeviceSurfacePresentModesKHR(m_ctx.GetPhysicalDevice(), m_ctx.GetSurface(), &modeCount, nullptr);
+        Vector<VkPresentModeKHR> modes(modeCount);
+        if (modeCount > 0) {
+            vkGetPhysicalDeviceSurfacePresentModesKHR(m_ctx.GetPhysicalDevice(), m_ctx.GetSurface(), &modeCount,
+                                                      modes.data());
+        }
+
+        VkSurfaceFormatKHR surfaceFormat = ChooseSurfaceFormat(formats);
+        VkPresentModeKHR presentMode = ChoosePresentMode(modes);
+        VkExtent2D extent;
+        if (m_viewportSize.x() == 0 || m_viewportSize.y() == 0) {
+            extent = ChooseExtent(caps, m_ctx.GetWindow());
+        } else {
+            extent = {m_viewportSize.x(), m_viewportSize.y()};
+        }
+
+        Uint32 imageCount = caps.minImageCount + 1;
+        if (caps.maxImageCount > 0 && imageCount > caps.maxImageCount) imageCount = caps.maxImageCount;
+
+        VkSwapchainCreateInfoKHR sci{VK_STRUCTURE_TYPE_SWAPCHAIN_CREATE_INFO_KHR};
+        sci.surface = m_ctx.GetSurface();
+        sci.minImageCount = imageCount;
+        sci.imageFormat = surfaceFormat.format;
+        sci.imageColorSpace = surfaceFormat.colorSpace;
+        sci.imageExtent = extent;
+        sci.imageArrayLayers = 1;
+        sci.imageUsage =
+            VK_IMAGE_USAGE_COLOR_ATTACHMENT_BIT | VK_IMAGE_USAGE_TRANSFER_DST_BIT | VK_IMAGE_USAGE_TRANSFER_SRC_BIT;
+        sci.imageSharingMode = VK_SHARING_MODE_EXCLUSIVE;
+        sci.preTransform = caps.currentTransform;
+        sci.compositeAlpha = VK_COMPOSITE_ALPHA_OPAQUE_BIT_KHR;
+        sci.presentMode = presentMode;
+        sci.clipped = VK_TRUE;
+        sci.oldSwapchain = oldSwapchain;
+
+        VK_VERIFY(vkCreateSwapchainKHR(m_ctx.GetDevice(), &sci, nullptr, &m_swapchain), "vkCreateSwapchainKHR");
+
+        Uint32 actualCount = 0;
+        vkGetSwapchainImagesKHR(m_ctx.GetDevice(), m_swapchain, &actualCount, nullptr);
+        m_images.resize(actualCount);
+        vkGetSwapchainImagesKHR(m_ctx.GetDevice(), m_swapchain, &actualCount, m_images.data());
+
+        m_imageViews.clear();
+        m_imageViews.reserve(actualCount);
+        for (auto image : m_images) {
+            VkImageViewCreateInfo ivci{VK_STRUCTURE_TYPE_IMAGE_VIEW_CREATE_INFO};
+            ivci.image = image;
+            ivci.viewType = VK_IMAGE_VIEW_TYPE_2D;
+            ivci.format = surfaceFormat.format;
+            ivci.subresourceRange.aspectMask = VK_IMAGE_ASPECT_COLOR_BIT;
+            ivci.subresourceRange.baseMipLevel = 0;
+            ivci.subresourceRange.levelCount = 1;
+            ivci.subresourceRange.baseArrayLayer = 0;
+            ivci.subresourceRange.layerCount = 1;
+            VkImageView view = VK_NULL_HANDLE;
+            VK_VERIFY(vkCreateImageView(m_ctx.GetDevice(), &ivci, nullptr, &view), "vkCreateImageView swapchain");
+            m_imageViews.push_back(view);
+        }
+
+        m_imagesInFlight.assign(actualCount, VK_NULL_HANDLE);
+        m_format = surfaceFormat.format;
+        m_extent = extent;
+    }
+} // namespace MobileGL::MG_Backend::DirectVulkanTMP::VkManager

MobileGL/MG_Backend/DirectVulkanTMP/Renderer/SwapchainManager.h

@@ -0,0 +1,52 @@
+// MobileGL - MobileGL/MG_Backend/DirectVulkanTMP/Renderer/SwapchainManager.h
+// Copyright (c) 2025-2026 MobileGL-Dev
+// Licensed under the GNU Lesser General Public License v3.0:
+//   https://www.gnu.org/licenses/gpl-3.0.txt
+//   https://www.gnu.org/licenses/lgpl-3.0.txt
+// SPDX-License-Identifier: LGPL-3.0-only
+// End of Source File Header
+
+#pragma once
+#include <Includes.h>
+#include "MG_Util/Math/VectorTypes.h"
+#include "VulkanContext.h"
+#include "VkCommon.h"
+
+namespace MobileGL::MG_Backend::DirectVulkanTMP::VkManager {
+    class SwapchainManager {
+    public:
+        explicit SwapchainManager(VulkanContext& ctx) : m_ctx(ctx) {}
+        ~SwapchainManager();
+
+        SwapchainManager(const SwapchainManager&) = delete;
+        SwapchainManager& operator=(const SwapchainManager&) = delete;
+
+        void Initialize();
+        void Recreate();
+        void SetViewportSize(const UintVec2& size) { m_viewportSize = size; }
+
+        VkSwapchainKHR GetSwapchain() const { return m_swapchain; }
+        VkFormat GetFormat() const { return m_format; }
+        VkExtent2D GetExtent() const { return m_extent; }
+        const Vector<VkImage>& GetImages() const { return m_images; }
+        const Vector<VkImageView>& GetImageViews() const { return m_imageViews; }
+        const Vector<VkFramebuffer>& GetFramebuffers() const { return m_framebuffers; }
+        void SetFramebuffers(Vector<VkFramebuffer>&& framebuffers);
+        Vector<VkFence>& GetImagesInFlight() { return m_imagesInFlight; }
+        const UintVec2& GetViewportSize() const { return m_viewportSize; }
+
+    private:
+        void CreateSwapchain(VkSwapchainKHR oldSwapchain);
+        void DestroySwapchain();
+
+        VulkanContext& m_ctx;
+        VkSwapchainKHR m_swapchain = VK_NULL_HANDLE;
+        VkFormat m_format = VK_FORMAT_UNDEFINED;
+        VkExtent2D m_extent{0, 0};
+        Vector<VkImage> m_images;
+        Vector<VkImageView> m_imageViews;
+        Vector<VkFramebuffer> m_framebuffers;
+        Vector<VkFence> m_imagesInFlight;
+        UintVec2 m_viewportSize{0, 0};
+    };
+} // namespace MobileGL::MG_Backend::DirectVulkanTMP::VkManager

MobileGL/MG_Backend/DirectVulkanTMP/Renderer/VkCommon.h

@@ -0,0 +1,22 @@
+// MobileGL - MobileGL/MG_Backend/DirectVulkanTMP/Renderer/VkCommon.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_Backend::DirectVulkanTMP::VkManager {
+    inline void VkCheck(VkResult result, const char* msg) {
+        if (result == VK_SUCCESS || result == VK_SUBOPTIMAL_KHR) return;
+        MGLOG_E("Vulkan error %d at %s", static_cast<Int>(result), msg ? msg : "(unknown)");
+        throw RuntimeError(msg ? msg : "Vulkan error");
+    }
+} // namespace MobileGL::MG_Backend::DirectVulkanTMP::VkManager
+
+#ifndef VK_VERIFY
+#define VK_VERIFY(res, msg) ::MobileGL::MG_Backend::DirectVulkanTMP::VkManager::VkCheck((res), (msg))
+#endif

MobileGL/MG_Backend/DirectVulkanTMP/Renderer/VulkanContext.cpp

@@ -0,0 +1,191 @@
+// MobileGL - MobileGL/MG_Backend/DirectVulkanTMP/Renderer/VulkanContext.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 "VulkanContext.h"
+
+namespace MobileGL::MG_Backend::DirectVulkanTMP::VkManager {
+    namespace {
+        Bool CheckDeviceExtensionSupport(VkPhysicalDevice device, const Vector<const char*>& required) {
+            Uint32 count = 0;
+            vkEnumerateDeviceExtensionProperties(device, nullptr, &count, nullptr);
+            Vector<VkExtensionProperties> props(count);
+            if (count > 0) vkEnumerateDeviceExtensionProperties(device, nullptr, &count, props.data());
+
+            for (auto* ext : required) {
+                Bool found = false;
+                for (const auto& p : props) {
+                    if (std::strcmp(p.extensionName, ext) == 0) {
+                        found = true;
+                        break;
+                    }
+                }
+                if (!found) return false;
+            }
+            return true;
+        }
+
+        Bool FindGraphicsQueueFamily(VkPhysicalDevice device, VkSurfaceKHR surface, Uint32& outFamily) {
+            Uint32 count = 0;
+            vkGetPhysicalDeviceQueueFamilyProperties(device, &count, nullptr);
+            if (count == 0) return false;
+            Vector<VkQueueFamilyProperties> props(count);
+            vkGetPhysicalDeviceQueueFamilyProperties(device, &count, props.data());
+
+            for (Uint32 i = 0; i < count; ++i) {
+                if (!(props[i].queueFlags & VK_QUEUE_GRAPHICS_BIT)) continue;
+                if (surface != VK_NULL_HANDLE) {
+                    VkBool32 presentSupport = VK_FALSE;
+                    vkGetPhysicalDeviceSurfaceSupportKHR(device, i, surface, &presentSupport);
+                    if (!presentSupport) continue;
+                }
+                outFamily = i;
+                return true;
+            }
+            return false;
+        }
+
+        Bool SupportsDynamicRendering(VkPhysicalDevice device) {
+            VkPhysicalDeviceVulkan13Features vk13{VK_STRUCTURE_TYPE_PHYSICAL_DEVICE_VULKAN_1_3_FEATURES};
+            VkPhysicalDeviceFeatures2 features2{VK_STRUCTURE_TYPE_PHYSICAL_DEVICE_FEATURES_2};
+            features2.pNext = &vk13;
+            vkGetPhysicalDeviceFeatures2(device, &features2);
+            return vk13.dynamicRendering == VK_TRUE;
+        }
+
+        Bool SupportsTimelineSemaphore(VkPhysicalDevice device) {
+            VkPhysicalDeviceVulkan12Features vk12{VK_STRUCTURE_TYPE_PHYSICAL_DEVICE_VULKAN_1_2_FEATURES};
+            VkPhysicalDeviceFeatures2 features2{VK_STRUCTURE_TYPE_PHYSICAL_DEVICE_FEATURES_2};
+            features2.pNext = &vk12;
+            vkGetPhysicalDeviceFeatures2(device, &features2);
+            return vk12.timelineSemaphore == VK_TRUE;
+        }
+    } // namespace
+
+    VulkanContext::~VulkanContext() {
+        Cleanup();
+    }
+
+    void VulkanContext::Initialize(ANativeWindow* window, const char* appName) {
+        if (m_instance != VK_NULL_HANDLE) return;
+        m_window = window;
+        CreateInstance(appName ? appName : "MobileGL-Vulkan");
+        CreateSurface(window);
+        PickPhysicalDevice();
+        CreateDevice();
+    }
+
+    void VulkanContext::Cleanup() {
+        if (m_device != VK_NULL_HANDLE) {
+            vkDeviceWaitIdle(m_device);
+            vkDestroyDevice(m_device, nullptr);
+            m_device = VK_NULL_HANDLE;
+        }
+        if (m_surface != VK_NULL_HANDLE) {
+            vkDestroySurfaceKHR(m_instance, m_surface, nullptr);
+            m_surface = VK_NULL_HANDLE;
+        }
+        if (m_instance != VK_NULL_HANDLE) {
+            vkDestroyInstance(m_instance, nullptr);
+            m_instance = VK_NULL_HANDLE;
+        }
+        m_physicalDevice = VK_NULL_HANDLE;
+        m_graphicsQueue = VK_NULL_HANDLE;
+        m_graphicsQueueFamily = ~0u;
+        m_window = nullptr;
+    }
+
+    void VulkanContext::CreateInstance(const char* appName) {
+        VkApplicationInfo app{VK_STRUCTURE_TYPE_APPLICATION_INFO};
+        app.pApplicationName = appName;
+        app.applicationVersion = VK_MAKE_VERSION(1, 3, 0);
+        app.pEngineName = "MobileGL";
+        app.engineVersion = VK_MAKE_VERSION(1, 3, 0);
+        app.apiVersion = VK_API_VERSION_1_3;
+
+        Vector<const char*> extensions;
+        extensions.push_back(VK_KHR_SURFACE_EXTENSION_NAME);
+#ifdef VK_USE_PLATFORM_ANDROID_KHR
+        extensions.push_back(VK_KHR_ANDROID_SURFACE_EXTENSION_NAME);
+#endif
+
+        VkInstanceCreateInfo ici{VK_STRUCTURE_TYPE_INSTANCE_CREATE_INFO};
+        ici.pApplicationInfo = &app;
+        ici.enabledExtensionCount = static_cast<Uint32>(extensions.size());
+        ici.ppEnabledExtensionNames = extensions.data();
+
+        VK_VERIFY(vkCreateInstance(&ici, nullptr, &m_instance), "vkCreateInstance");
+    }
+
+    void VulkanContext::CreateSurface(ANativeWindow* window) {
+        if (!window) return;
+#ifdef VK_USE_PLATFORM_ANDROID_KHR
+        VkAndroidSurfaceCreateInfoKHR sci{VK_STRUCTURE_TYPE_ANDROID_SURFACE_CREATE_INFO_KHR};
+        sci.window = window;
+        VK_VERIFY(vkCreateAndroidSurfaceKHR(m_instance, &sci, nullptr, &m_surface), "vkCreateAndroidSurfaceKHR");
+#else
+        (void)window;
+#endif
+    }
+
+    void VulkanContext::PickPhysicalDevice() {
+        Uint32 count = 0;
+        VK_VERIFY(vkEnumeratePhysicalDevices(m_instance, &count, nullptr), "vkEnumeratePhysicalDevices");
+        if (count == 0) throw RuntimeError("No Vulkan physical devices found");
+
+        Vector<VkPhysicalDevice> devices(count);
+        VK_VERIFY(vkEnumeratePhysicalDevices(m_instance, &count, devices.data()), "vkEnumeratePhysicalDevices list");
+
+        Vector<const char*> requiredExts = {VK_KHR_SWAPCHAIN_EXTENSION_NAME};
+
+        for (auto device : devices) {
+            Uint32 family = ~0u;
+            if (!FindGraphicsQueueFamily(device, m_surface, family)) continue;
+            if (!CheckDeviceExtensionSupport(device, requiredExts)) continue;
+            if (!SupportsDynamicRendering(device)) continue;
+
+            m_physicalDevice = device;
+            m_graphicsQueueFamily = family;
+            break;
+        }
+
+        if (m_physicalDevice == VK_NULL_HANDLE) {
+            throw RuntimeError("No suitable Vulkan physical device found");
+        }
+    }
+
+    void VulkanContext::CreateDevice() {
+        float priority = 1.0f;
+        VkDeviceQueueCreateInfo qci{VK_STRUCTURE_TYPE_DEVICE_QUEUE_CREATE_INFO};
+        qci.queueFamilyIndex = m_graphicsQueueFamily;
+        qci.queueCount = 1;
+        qci.pQueuePriorities = &priority;
+
+        Vector<const char*> deviceExtensions = {VK_KHR_SWAPCHAIN_EXTENSION_NAME};
+
+        VkPhysicalDeviceFeatures features{};
+        VkPhysicalDeviceVulkan13Features vk13{VK_STRUCTURE_TYPE_PHYSICAL_DEVICE_VULKAN_1_3_FEATURES};
+        vk13.dynamicRendering = VK_TRUE;
+        VkPhysicalDeviceVulkan12Features vk12{VK_STRUCTURE_TYPE_PHYSICAL_DEVICE_VULKAN_1_2_FEATURES};
+        vk12.timelineSemaphore = SupportsTimelineSemaphore(m_physicalDevice) ? VK_TRUE : VK_FALSE;
+        VkPhysicalDeviceFeatures2 features2{VK_STRUCTURE_TYPE_PHYSICAL_DEVICE_FEATURES_2};
+        features2.features = features;
+        vk13.pNext = &vk12;
+        features2.pNext = &vk13;
+
+        VkDeviceCreateInfo dci{VK_STRUCTURE_TYPE_DEVICE_CREATE_INFO};
+        dci.pNext = &features2;
+        dci.queueCreateInfoCount = 1;
+        dci.pQueueCreateInfos = &qci;
+        dci.enabledExtensionCount = static_cast<Uint32>(deviceExtensions.size());
+        dci.ppEnabledExtensionNames = deviceExtensions.data();
+        dci.pEnabledFeatures = nullptr;
+
+        VK_VERIFY(vkCreateDevice(m_physicalDevice, &dci, nullptr, &m_device), "vkCreateDevice");
+        vkGetDeviceQueue(m_device, m_graphicsQueueFamily, 0, &m_graphicsQueue);
+    }
+} // namespace MobileGL::MG_Backend::DirectVulkanTMP::VkManager

MobileGL/MG_Backend/DirectVulkanTMP/Renderer/VulkanContext.h

@@ -0,0 +1,47 @@
+// MobileGL - MobileGL/MG_Backend/DirectVulkanTMP/Renderer/VulkanContext.h
+// Copyright (c) 2025-2026 MobileGL-Dev
+// Licensed under the GNU Lesser General Public License v3.0:
+//   https://www.gnu.org/licenses/gpl-3.0.txt
+//   https://www.gnu.org/licenses/lgpl-3.0.txt
+// SPDX-License-Identifier: LGPL-3.0-only
+// End of Source File Header
+
+#pragma once
+#include <Includes.h>
+#include "VkCommon.h"
+
+namespace MobileGL::MG_Backend::DirectVulkanTMP::VkManager {
+    class VulkanContext {
+    public:
+        VulkanContext() = default;
+        ~VulkanContext();
+
+        VulkanContext(const VulkanContext&) = delete;
+        VulkanContext& operator=(const VulkanContext&) = delete;
+
+        void Initialize(ANativeWindow* window, const char* appName);
+        void Cleanup();
+
+        VkInstance GetInstance() const { return m_instance; }
+        VkPhysicalDevice GetPhysicalDevice() const { return m_physicalDevice; }
+        VkDevice GetDevice() const { return m_device; }
+        VkQueue GetGraphicsQueue() const { return m_graphicsQueue; }
+        Uint32 GetGraphicsQueueFamily() const { return m_graphicsQueueFamily; }
+        VkSurfaceKHR GetSurface() const { return m_surface; }
+        ANativeWindow* GetWindow() const { return m_window; }
+
+    private:
+        void CreateInstance(const char* appName);
+        void CreateSurface(ANativeWindow* window);
+        void PickPhysicalDevice();
+        void CreateDevice();
+
+        VkInstance m_instance = VK_NULL_HANDLE;
+        VkPhysicalDevice m_physicalDevice = VK_NULL_HANDLE;
+        VkDevice m_device = VK_NULL_HANDLE;
+        VkQueue m_graphicsQueue = VK_NULL_HANDLE;
+        VkSurfaceKHR m_surface = VK_NULL_HANDLE;
+        Uint32 m_graphicsQueueFamily = ~0u;
+        ANativeWindow* m_window = nullptr;
+    };
+} // namespace MobileGL::MG_Backend::DirectVulkanTMP::VkManager

MobileGL/MG_Backend/DirectVulkanTMP/TmpImpl.h

@@ -0,0 +1,308 @@
+// MobileGL - MobileGL/MG_Backend/DirectVulkanTMP/TmpImpl.h
+// Copyright (c) 2025-2026 MobileGL-Dev
+// Licensed under the GNU Lesser General Public License v3.0:
+//   https://www.gnu.org/licenses/gpl-3.0.txt
+//   https://www.gnu.org/licenses/lgpl-3.0.txt
+// SPDX-License-Identifier: LGPL-3.0-only
+// End of Source File Header
+
+#pragma once
+#include <Includes.h>
+#include "Renderer/VkCommon.h"
+#include "Renderer/VulkanContext.h"
+#include "Renderer/SwapchainManager.h"
+#include "Renderer/FrameContext.h"
+#include "Managers/ProgramManager.h"
+#include <MG_State/GLState/Core.h>
+
+namespace MobileGL::MG_Backend::DirectVulkanTMP::TmpImpl {
+    namespace DV = MobileGL::MG_Backend::DirectVulkanTMP::VkManager;
+    using BufferObject = MobileGL::MG_State::GLState::BufferObject;
+    using ProgramObject = MobileGL::MG_State::GLState::ProgramObject;
+    using VertexArrayObject = MobileGL::MG_State::GLState::VertexArrayObject;
+    using FramebufferObject = MobileGL::MG_State::GLState::FramebufferObject;
+    using FramebufferAttachmentObject = MobileGL::MG_State::GLState::FramebufferAttachmentObject;
+    using ITextureObject = MobileGL::MG_State::GLState::ITextureObject;
+    using RenderbufferObject = MobileGL::MG_State::GLState::RenderbufferObject;
+    using SamplerObject = MobileGL::MG_State::GLState::SamplerObject;
+    using TextureObjectMipmap = MobileGL::MG_State::GLState::TextureObjectMipmap;
+    using TrashImage = MobileGL::MG_Backend::DirectVulkanTMP::TrashImage;
+
+    struct BufferResource {
+        VkBuffer buffer = VK_NULL_HANDLE;
+        VkDeviceMemory memory = VK_NULL_HANDLE;
+        VkDeviceSize size = 0;
+        VkDeviceSize offset = 0;
+        VkBufferUsageFlags usage = 0;
+        VkMemoryPropertyFlags props = 0;
+        void* mapped = nullptr;
+        Bool fromRing = false;
+        Uint32 lastUsedFrame = ~0u;
+    };
+
+    struct BufferResourceSet {
+        Vector<BufferResource> perFrame;
+    };
+
+    struct PendingBufferCopyBatch {
+        VkBuffer src = VK_NULL_HANDLE;
+        VkBuffer dst = VK_NULL_HANDLE;
+        Vector<VkBufferCopy> regions;
+    };
+
+    struct StagingRing {
+        BufferResource buffer;
+        VkDeviceSize capacity = 0;
+        VkDeviceSize head = 0;
+    };
+
+    struct TextureResource {
+        VkImage image = VK_NULL_HANDLE;
+        VkDeviceMemory memory = VK_NULL_HANDLE;
+        VkImageView view = VK_NULL_HANDLE;
+        UnorderedMap<Uint32, VkImageView> mipViews;
+        VkFormat format = VK_FORMAT_UNDEFINED;
+        VkExtent3D extent{0, 0, 1};
+        VkImageLayout layout = VK_IMAGE_LAYOUT_UNDEFINED;
+        Uint32 mipLevels = 1;
+        Uint16 paramsVersion = 0;
+        bool valid = false;
+    };
+
+    struct RenderbufferResource {
+        VkImage image = VK_NULL_HANDLE;
+        VkDeviceMemory memory = VK_NULL_HANDLE;
+        VkImageView view = VK_NULL_HANDLE;
+        VkFormat format = VK_FORMAT_UNDEFINED;
+        VkExtent2D extent{0, 0};
+        VkImageLayout layout = VK_IMAGE_LAYOUT_UNDEFINED;
+        bool valid = false;
+    };
+
+    struct SamplerResource {
+        VkSampler sampler = VK_NULL_HANDLE;
+        Uint16 version = 0;
+        SamplerParameters params{};
+    };
+
+    struct PendingClearInfo {
+        GLbitfield mask = 0;
+        FloatVec4 clearColor = {0.0f, 0.0f, 0.0f, 1.0f};
+        Float clearDepth = 1.0f;
+    };
+
+    struct UniformBindingInfo {
+        String name;
+        Uint32 binding = 0;
+        Uint32 set = 0;
+        Uint32 blockIndex = 0xFFFFFFFFu;
+        VkShaderStageFlags stages = 0;
+    };
+
+    struct SamplerBindingInfo {
+        String name;
+        Uint32 binding = 0;
+        Uint32 set = 0;
+        VkShaderStageFlags stages = 0;
+    };
+
+    struct ProgramResource {
+        ProgramObject* program = nullptr;
+        Uint64 spvHash = 0;
+        DV::ProgramManager::HashType programHash = 0;
+        Vector<VkPipelineShaderStageCreateInfo>* shaderStages = nullptr;
+
+        VkDescriptorSetLayout setLayout = VK_NULL_HANDLE;
+        VkPipelineLayout pipelineLayout = VK_NULL_HANDLE;
+
+        struct UboPool {
+            Vector<BufferResource> buffers;
+            Uint32 cursor = 0;
+        };
+        Vector<UboPool> uboPools;
+        SizeT uboSize = 0;
+        Int32 uboBinding = -1;
+        Uint32 uniformDescriptorCount = 0;
+        Uint32 samplerDescriptorCount = 0;
+
+        Vector<UniformBindingInfo> uniformBindings;
+        Vector<SamplerBindingInfo> samplerBindings;
+        UnorderedMap<String, Uint32> samplerBindingByName;
+
+        UnorderedMap<Uint64, VkPipeline> pipelines;
+    };
+
+    struct DescriptorPoolConfig {
+        Uint32 maxSets = 0;
+        Uint32 uniformCount = 0;
+        Uint32 samplerCount = 0;
+    };
+
+    struct FrameDescriptorPools {
+        Vector<VkDescriptorPool> pools;
+        DescriptorPoolConfig config;
+        Uint32 activePool = 0;
+    };
+
+    struct VertexAttribKey {
+        Uint8 enabled = 0;
+        Uint8 size = 0;
+        Uint8 type = 0;
+        Uint8 normalized = 0;
+        Uint8 isInteger = 0;
+        Uint8 divisor = 0;
+        Uint16 pad = 0;
+        Uint32 stride = 0;
+        Uint64 offset = 0;
+    };
+
+    struct AttachmentInfo {
+        FramebufferAttachmentType type = FramebufferAttachmentType::None;
+        VkImageView view = VK_NULL_HANDLE;
+        VkFormat format = VK_FORMAT_UNDEFINED;
+        VkImageAspectFlags aspect = 0;
+        VkImageLayout finalLayout = VK_IMAGE_LAYOUT_UNDEFINED;
+        ITextureObject* texture = nullptr;
+        RenderbufferObject* renderbuffer = nullptr;
+    };
+
+    struct BackendFramebufferObject {
+        VkExtent2D extent{0, 0};
+        Uint32 colorAttachmentCount = 0;
+        Bool hasDepth = false;
+        VkFormat depthFormat = VK_FORMAT_UNDEFINED;
+        VkFormat depthAttachmentFormat = VK_FORMAT_UNDEFINED;
+        VkFormat stencilAttachmentFormat = VK_FORMAT_UNDEFINED;
+        Uint64 renderingCompatHash = 0;
+
+        Vector<AttachmentInfo> attachments;
+        Vector<VkFormat> colorAttachmentFormats;
+        Array<Int32, static_cast<SizeT>(FramebufferAttachmentType::FramebufferAttachmentTypeCount)> attachmentIndex =
+            {};
+
+        FramebufferObject::FramebufferAttachmentVersionArray syncedAttachmentVersions = {0};
+        FramebufferObject::FramebufferAttachmentArray frontendDrawBuffers = {FramebufferAttachmentType::None};
+        Array<Int32, FramebufferObject::MAX_DRAW_BUFFERS> drawBufferAttachmentIndices = {};
+        FramebufferAttachmentType frontendReadBuffer = FramebufferAttachmentType::Color0;
+        Uint64 configHash = 0;
+        Uint16 objectVersion = 0;
+
+        Bool IsValid() const { return !attachments.empty() && extent.width > 0 && extent.height > 0; }
+    };
+
+    struct VulkanState {
+        UniquePtr<DV::VulkanContext> ctx;
+        UniquePtr<DV::SwapchainManager> swapchain;
+        UniquePtr<DV::ProgramManager> programMgr;
+        VkCommandPool commandPool = VK_NULL_HANDLE;
+        Vector<UniquePtr<DV::FrameContext>> frames;
+        Vector<FrameDescriptorPools> frameDescriptorPools;
+        Vector<BufferResource> stagingPool;
+        Vector<Vector<BufferResource>> stagingPending;
+        Uint32 currentFrame = 0;
+        Uint32 maxFramesInFlight = 2;
+        Bool initialized = false;
+        UintVec2 viewportSize{0, 0};
+
+        VkImage depthImage = VK_NULL_HANDLE;
+        VkDeviceMemory depthMemory = VK_NULL_HANDLE;
+        VkImageView depthView = VK_NULL_HANDLE;
+        VkFormat depthFormat = VK_FORMAT_UNDEFINED;
+        Uint64 defaultRenderingCompatHash = 0;
+
+        BufferResource nullUbo;
+
+        TextureResource defaultTexture;
+        SamplerResource defaultSampler;
+
+        UnorderedMap<const BufferObject*, BufferResourceSet> buffers;
+        UnorderedMap<const ITextureObject*, TextureResource> textures;
+        UnorderedMap<const RenderbufferObject*, RenderbufferResource> renderbuffers;
+        UnorderedMap<const SamplerObject*, SamplerResource> samplers;
+        UnorderedMap<const ProgramObject*, ProgramResource> programs;
+        UnorderedMap<SharedPtr<MG_State::GLState::FramebufferObject>, SharedPtr<BackendFramebufferObject>> framebuffers;
+        Vector<PendingBufferCopyBatch> pendingBufferCopies;
+        Vector<StagingRing> stagingRings;
+
+        VkExtent2D activeExtent{0, 0};
+        Vector<VkImageView> activeColorViews;
+        Vector<VkImageLayout> activeColorLayouts;
+        Vector<VkFormat> activeColorFormats;
+        Vector<Int32> activeColorAttachmentIndices;
+        VkImageView activeDepthView = VK_NULL_HANDLE;
+        VkImageLayout activeDepthLayout = VK_IMAGE_LAYOUT_UNDEFINED;
+        VkImageView activeStencilView = VK_NULL_HANDLE;
+        VkImageLayout activeStencilLayout = VK_IMAGE_LAYOUT_UNDEFINED;
+        Uint32 activeSwapchainImageIndex = ~0u;
+        Uint32 activeColorAttachmentCount = 1;
+        Bool activeHasDepth = false;
+        VkFormat activeDepthFormat = VK_FORMAT_UNDEFINED;
+        VkFormat activeDepthAttachmentFormat = VK_FORMAT_UNDEFINED;
+        VkFormat activeStencilAttachmentFormat = VK_FORMAT_UNDEFINED;
+        Uint64 activeRenderingCompatHash = 0;
+        Uint64 activeRenderingConfigHash = 0;
+        SharedPtr<MG_State::GLState::FramebufferObject> activeStateFBO = nullptr;
+        SharedPtr<BackendFramebufferObject> activeBackendFBO = nullptr;
+        Bool activeIsDefault = true;
+        Bool activeDefaultColorWrites = true;
+
+        Uint64 recordingRenderingConfigHash = 0;
+        Bool cmdBufferBegun = false;
+
+        Bool recording = false;
+        Bool frameSubmitted = false;
+        FloatVec4 clearColor = {0.0f, 0.0f, 0.0f, 1.0f};
+        Float clearDepth = 1.0f;
+
+        UnorderedMap<SharedPtr<FramebufferObject>, PendingClearInfo> pendingClears;
+
+        Vector<VkImageLayout> swapchainImageLayouts;
+
+        PFN_vkCmdBeginRendering pfnCmdBeginRendering = nullptr;
+        PFN_vkCmdEndRendering pfnCmdEndRendering = nullptr;
+        PFN_vkWaitSemaphores pfnWaitSemaphores = nullptr;
+        VkSemaphore timelineSemaphore = VK_NULL_HANDLE;
+        Uint64 timelineValue = 0;
+    };
+
+    void Present();
+    void FrameBegin();
+    void InitVulkan(ANativeWindow* window);
+    const VulkanState& GetVulkanState();
+    void ClearBufferfi(GLenum buffer, GLint drawbuffer, GLfloat depth, GLint stencil);
+    void ClearBufferfv(GLenum buffer, GLint drawbuffer, const GLfloat* value);
+    void ClearBufferuiv(GLenum buffer, GLint drawbuffer, const GLuint* value);
+    void ClearBufferiv(GLenum buffer, GLint drawbuffer, const GLint* value);
+    void Clear(GLbitfield mask);
+    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 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,
+                                     GLsizei drawcount, const GLint* basevertex);
+    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 DrawRangeElementsBaseVertex(GLenum mode, GLuint start, GLuint end, GLsizei count, GLenum type,
+                                     const void* indices, GLint basevertex);
+    void DrawRangeElements(GLenum mode, GLuint start, GLuint end, GLsizei count, GLenum type, const void* indices);
+    void DrawElementsInstancedBaseVertexBaseInstance(GLenum mode, GLsizei count, GLenum type, const void* indices,
+                                                     GLsizei instancecount, GLint basevertex, GLuint baseinstance);
+    void DrawElementsInstancedBaseVertex(GLenum mode, GLsizei count, GLenum type, const void* indices,
+                                         GLsizei instancecount, GLint basevertex);
+    void DrawElementsInstancedBaseInstance(GLenum mode, GLsizei count, GLenum type, const void* indices,
+                                           GLsizei instancecount, GLuint baseinstance);
+    void DrawElementsInstanced(GLenum mode, GLsizei count, GLenum type, const void* indices, GLsizei instancecount);
+    void DrawElementsIndirect(GLenum mode, GLenum type, const void* indirect);
+    void DrawArraysInstancedBaseInstance(GLenum mode, GLint first, GLsizei count, GLsizei instancecount,
+                                         GLuint baseinstance);
+    void DrawArraysInstanced(GLenum mode, GLint first, GLsizei count, GLsizei instancecount);
+    void DrawArraysIndirect(GLenum mode, const void* indirect);
+    void BlitFramebuffer(GLint srcX0, GLint srcY0, GLint srcX1, GLint srcY1, GLint dstX0, GLint dstY0, GLint dstX1,
+                         GLint dstY1, GLbitfield mask, GLenum filter);
+    void CopyTexImage2D(GLenum target, GLint level, GLenum internalformat, GLint x, GLint y, GLsizei width,
+                        GLsizei height, GLint border);
+    void CopyTexSubImage2D(GLenum target, GLint level, GLint xoffset, GLint yoffset, GLint x, GLint y, GLsizei width,
+                           GLsizei height);
+    void GenerateMipmap(GLenum target);
+} // namespace MobileGL::MG_Backend::DirectVulkanTMP::TmpImpl

MobileGL/MG_Backend/Init.cpp

@@ -52,8 +52,8 @@ namespace MobileGL::MG_Backend {
         case BackendType::DirectGLES:
             pActiveBackendObject = MakeUnique<DirectGLES::BackendObject_DirectGLES>();
             break;
-        case BackendType::DirectVulkan:
-            pActiveBackendObject = MakeUnique<DirectVulkan::BackendObject_DirectVulkan>();
+        case BackendType::DirectVulkanTMP:
+            pActiveBackendObject = MakeUnique<DirectVulkanTMP::BackendObject_DirectVulkanTMP>();
             break;
         case BackendType::Unknown:
         default:

MobileGL/MG_Benchmark/Buffer/BufferBench.cpp

@@ -61,7 +61,7 @@ static void BM_CreateBufferObjectsAndBindBuffer(benchmark::State& state) {
 BENCHMARK(BM_CreateBufferObjectsAndBindBuffer)->Unit(benchmark::kMillisecond)->UseRealTime();
 
 static void BM_DeleteBufferObjects(benchmark::State& state) {
-    Initialize();
+    MG_Initialize();
     std::vector<GLuint> buffers(BUFFER_COUNT);
 
     for (auto _ : state) {
@@ -179,7 +179,7 @@ static void BM_UpdateDataPartially(benchmark::State& state) {
 BENCHMARK(BM_UpdateDataPartially)->Unit(benchmark::kMillisecond)->UseRealTime();
 
 int main(int argc, char** argv) {
-    Initialize();
+    MG_Initialize();
     benchmark ::MaybeReenterWithoutASLR(argc, argv);
     char arg0_default[] = "benchmark";
     char* args_default = reinterpret_cast<char*>(arg0_default);

MobileGL/MG_Benchmark/Buffer/CMakeLists.txt

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