Try to handle non-transient attatchment supporting GPUs

.clang-format

@@ -57,7 +57,7 @@ SpaceBeforeInheritanceColon: true
 SpaceBeforeParens: ControlStatements
 SpaceBeforeRangeBasedForLoopColon: false
 SpaceInEmptyParentheses: false
-SpacesBeforeTrailingComments: 1
+SpacesBeforeTrailingComments: 0
 SpacesInAngles: false
 SpacesInCStyleCastParentheses: false
 SpacesInContainerLiterals: false

.github/workflows/mac-continuous.yml

@@ -26,4 +26,4 @@ jobs:
           path: out/filament-release-darwin.tgz
       - name: Check public headers
         run: |
-          test/check-headers/test.sh out/release/filament/include
+          build/common/check-headers.sh out/release/filament/include

.github/workflows/presubmit.yml

@@ -131,7 +131,7 @@ jobs:
       - name: Prerequisites
         id: prereqs
         run: |
-          bash build/common/get-mesa.sh
+          bash test/utils/get_mesa.sh
           pip install tifffile numpy
       - name: Run Test
         run: bash test/renderdiff/test.sh
@@ -153,8 +153,8 @@ jobs:
       - name: Run test
         run: ./out/cmake-debug/libs/filamat/test_filamat --gtest_filter=MaterialCompiler.Wgsl*
 
-  test-code-correctness:
-    name: test-code-correctness
+  code-correctness:
+    name: code-correctness
     runs-on: 'macos-14-xlarge'
     steps:
       - uses: actions/checkout@v4.1.6

.github/workflows/release.yml

@@ -163,9 +163,6 @@ jobs:
           mv out/filamat-android-release.aar out/filamat-${TAG}-android.aar
           mv out/gltfio-android-release.aar out/gltfio-${TAG}-android.aar
           mv out/filament-utils-android-release.aar out/filament-utils-${TAG}-android.aar
-          cd out/android-release/filament
-          tar -czf ../../filament-${TAG}-android-native.tgz .
-          cd ../../..
       - name: Sign sample-gltf-viewer
         run: |
           echo "${APK_KEYSTORE_BASE64}" > filament.jks.base64
@@ -187,7 +184,7 @@ jobs:
           script: |
             const upload = require('./build/common/upload-release-assets');
             const { TAG } = process.env;
-            const globber = await glob.create(['out/*.aar', 'out/*.apk', 'out/*.tgz'].join('\n'));
+            const globber = await glob.create(['out/*.aar', 'out/*.apk'].join('\n'));
             await upload({ github, context }, await globber.glob(), TAG);
 
   build-ios:

BUILDING.md

@@ -97,10 +97,6 @@ Make sure you've installed the following dependencies:
 - `libxcomposite-dev` (`libXcomposite-devel` on Fedora)
 - `libxxf86vm-dev` (`libXxf86vm-devel` on Fedora)
 
-```shell
-sudo apt install clang-14 libglu1-mesa-dev libc++-14-dev libc++abi-14-dev ninja-build libxi-dev libxcomposite-dev libxxf86vm-dev -y
-```
-
 After dependencies have been installed, we highly recommend using the [easy build](#easy-build)
 script.
 

CMakeLists.txt

@@ -49,10 +49,6 @@ option(FILAMENT_SUPPORTS_OSMESA "Enable OSMesa (headless GL context) for Filamen
 
 option(FILAMENT_ENABLE_FGVIEWER "Enable the frame graph viewer" OFF)
 
-# This is to disable GTAO for the short-term while we investigate a way to better manage size increases.
-# On the regular filament build (where size is of less concern), we enable GTAO by default.
-option(FILAMENT_DISABLE_GTAO "Disable GTAO" OFF)
-
 set(FILAMENT_NDK_VERSION "" CACHE STRING
     "Android NDK version or version prefix to be used when building for Android."
 )

README.md

@@ -31,7 +31,7 @@ repositories {
 }
 
 dependencies {
-    implementation 'com.google.android.filament:filament-android:1.60.1'
+    implementation 'com.google.android.filament:filament-android:1.59.5'
 }
 ```
 
@@ -51,7 +51,7 @@ Here are all the libraries available in the group `com.google.android.filament`:
 iOS projects can use CocoaPods to install the latest release:
 
 ```shell
-pod 'Filament', '~> 1.60.1'
+pod 'Filament', '~> 1.59.5'
 ```
 
 ## Documentation

RELEASE_NOTES.md

@@ -7,21 +7,10 @@ A new header is inserted each time a *tag* is created.
 Instead, if you are authoring a PR for the main branch, add your release note to
 [NEW_RELEASE_NOTES.md](./NEW_RELEASE_NOTES.md).
 
-## v1.61.0
-
-- materials: sampler now export their type in the material binary [⚠️ **New Material Version**]
-- samples/texturedquad.cpp now has CLI to select backend api
-- samples/hellopbr.cpp CLI now allows for selecting webgpu
-
-## v1.60.1
-
-
 ## v1.60.0
 
 - materials: remove dependence on per-view descset layout from filamat. [⚠️ **New Material Version**]
-- matc non-functional change: Update GLSL postprocessor to
-  isolate calls to SPVRemap from calls to SPIRV-Cross.
-
+- `ColorGrading::Builder::toneMapper` now takes a `shared_ptr<ToneMapper>`
 
 ## v1.59.5
 

android/filament-android/src/main/cpp/ColorGrading.cpp

@@ -18,6 +18,7 @@
 
 #include <filament/ColorGrading.h>
 #include <filament/ToneMapper.h>
+#include <memory>
 
 #include <math/vec3.h>
 #include <math/vec4.h>
@@ -67,8 +68,9 @@ extern "C" JNIEXPORT void JNICALL
 Java_com_google_android_filament_ColorGrading_nBuilderToneMapper(JNIEnv*, jclass,
         jlong nativeBuilder, jlong toneMapper_) {
     ColorGrading::Builder* builder = (ColorGrading::Builder*) nativeBuilder;
-    const ToneMapper* toneMapper = (const ToneMapper*) toneMapper_;
-    builder->toneMapper(toneMapper);
+    ToneMapper* toneMapper = reinterpret_cast<ToneMapper*>(toneMapper_);
+    std::shared_ptr<ToneMapper> toneMapperCopy(toneMapper->clone());
+    builder->toneMapper(toneMapperCopy);
 }
 
 #pragma clang diagnostic push

android/filament-android/src/main/java/com/google/android/filament/ColorGrading.java

@@ -214,9 +214,9 @@ public class ColorGrading {
          *
          * The default tone mapping operator is {@link ToneMapper.ACESLegacy}.
          *
-         * The specified tone mapper must have a lifecycle that exceeds the lifetime of
-         * this builder. Since the build(Engine&) method is synchronous, it is safe to
-         * delete the tone mapper object after that finishes executing.
+         * The copy of the specified tone mapper is set to this builder. It is safe to delete
+         * the original tone mapper object while the copied one is held by the built ColorGrading
+         * object.
          *
          * @param toneMapper The tone mapping operator to apply to the HDR color buffer
          *

android/filament-android/src/main/java/com/google/android/filament/View.java

@@ -1801,22 +1801,6 @@ public class View {
      * @see setAmbientOcclusionOptions()
      */
     public static class AmbientOcclusionOptions {
-        public enum AmbientOcclusionType {
-            /**
-             * use Scalable Ambient Occlusion
-             */
-            SAO,
-            /**
-             * use Ground Truth-Based Ambient Occlusion
-             */
-            GTAO,
-        }
-
-        /**
-         * Type of ambient occlusion algorithm.
-         */
-        @NonNull
-        public AmbientOcclusionOptions.AmbientOcclusionType aoType = AmbientOcclusionOptions.AmbientOcclusionType.SAO;
         /**
          * Ambient Occlusion radius in meters, between 0 and ~10.
          */
@@ -1826,8 +1810,7 @@ public class View {
          */
         public float power = 1.0f;
         /**
-         * Self-occlusion bias in meters. Use to avoid self-occlusion.
-         * Between 0 and a few mm. No effect when aoType set to GTAO
+         * Self-occlusion bias in meters. Use to avoid self-occlusion. Between 0 and a few mm.
          */
         public float bias = 0.0005f;
         /**
@@ -1843,12 +1826,12 @@ public class View {
          */
         public float bilateralThreshold = 0.05f;
         /**
-         * affects # of samples used for AO and params for filtering
+         * affects # of samples used for AO.
          */
         @NonNull
         public QualityLevel quality = QualityLevel.LOW;
         /**
-         * affects AO smoothness. Recommend setting to HIGH when aoType set to GTAO.
+         * affects AO smoothness
          */
         @NonNull
         public QualityLevel lowPassFilter = QualityLevel.MEDIUM;
@@ -1866,7 +1849,7 @@ public class View {
          */
         public boolean bentNormals = false;
         /**
-         * min angle in radian to consider. No effect when aoType set to GTAO.
+         * min angle in radian to consider
          */
         public float minHorizonAngleRad = 0.0f;
         /**
@@ -1921,19 +1904,6 @@ public class View {
          */
         public boolean ssctEnabled = false;
 
-        /**
-         * Ground Truth-base Ambient Occlusion (GTAO) options
-         */
-        public int gtaoSampleSliceCount = 4;
-        /**
-         * Ground Truth-base Ambient Occlusion (GTAO) options
-         */
-        public int gtaoSampleStepsPerSlice = 3;
-        /**
-         * Ground Truth-base Ambient Occlusion (GTAO) options
-         */
-        public float gtaoThicknessHeuristic = 0.004f;
-
     }
 
     /**

android/gradle.properties

@@ -1,5 +1,5 @@
 GROUP=com.google.android.filament
-VERSION_NAME=1.60.1
+VERSION_NAME=1.59.5
 
 POM_DESCRIPTION=Real-time physically based rendering engine for Android.
 

build.sh

@@ -151,7 +151,7 @@ function print_fgviewer_help {
 }
 
 # Unless explicitly specified, NDK version will be selected as highest available version within same major release chain
-FILAMENT_NDK_VERSION=${FILAMENT_NDK_VERSION:-$(cat `dirname $0`/build/common/versions | grep GITHUB_NDK_VERSION | sed s/GITHUB_NDK_VERSION=//g | cut -f 1 -d ".")}
+FILAMENT_NDK_VERSION=${FILAMENT_NDK_VERSION:-$(cat `dirname $0`/build/common/versions | grep GITHUB_NDK_VERSION | cut -f 1 -d ".")}
 
 # Requirements
 CMAKE_MAJOR=3
@@ -463,6 +463,16 @@ function ensure_android_build {
         echo "Error: Android NDK side-by-side version ${FILAMENT_NDK_VERSION} or compatible must be installed, exiting"
         exit 1
     fi
+
+    local cmake_version=$(cmake --version)
+    if [[ "${cmake_version}" =~ ([0-9]+)\.([0-9]+)\.[0-9]+ ]]; then
+        if [[ "${BASH_REMATCH[1]}" -lt "${CMAKE_MAJOR}" ]] || \
+           [[ "${BASH_REMATCH[2]}" -lt "${CMAKE_MINOR}" ]]; then
+            echo "Error: cmake version ${CMAKE_MAJOR}.${CMAKE_MINOR}+ is required," \
+                 "${BASH_REMATCH[1]}.${BASH_REMATCH[2]} installed, exiting"
+            exit 1
+        fi
+    fi
 }
 
 function build_android {

docs_src/markdeep/Materials.md.html

@@ -1023,12 +1023,8 @@ samplerCubemap         | Cubemap texture
 [Table [materialParamsTypes]: Material parameter types]
 
 Samplers
-:     Sampler types can specify additional options:
-
-      - `format`: either `int` or `float` (defaults to `float`).
-      - `stages`: array of strings containing the list of shader stages this
-        sampler can be accessed from. Each entry must be either `vertex` or
-        `fragment` (defaults to both).
+:     Sampler types can also specify a `format` which can be either `int` or `float` (defaults to
+      `float`).
 
 Arrays
 :     A parameter can define an array of values by appending `[size]` after the type name, where

docs_src/src/SUMMARY.md

@@ -19,7 +19,6 @@
     - [Vulkan](./notes/vulkan_debugging.md)
     - [SPIR-V](./notes/spirv_debugging.md)
     - [Running with ASAN and UBSAN](./notes/asan_ubsan.md)
-    - [Using Instruments on macOS](./notes/instruments.md)
   - [Libraries](./notes/libs.md)
     - [bluegl](./dup/bluegl.md)
     - [bluevk](./dup/bluevk.md)

docs_src/src/notes/instruments.md

@@ -1,36 +0,0 @@
-# Using Instruments on macOS
-
-When running a binary under Instruments on macOS, you may run into the following issue when
-launching or attaching to an executable:
-
-```
-Failed to gain authorization
-Recovery Suggestion: Target binary needs to be debuggable and signed with 'get-task-allow'
-```
-
-This is a security precaution; the solution is to code sign the binary with the
-`com.apple.security.get-task-allow` entitlement.
-
-1. Create an `entitlements.plist` file with the following contents:
-
-```
-<?xml version="1.0" encoding="UTF-8"?>
-<!DOCTYPE plist PUBLIC "-//Apple//DTD PLIST 1.0//EN" "http://www.apple.com/DTDs/PropertyList-1.0.dtd">
-<plist version="1.0">
-<dict>
-    <key>com.apple.security.get-task-allow</key>
-    <true/>
-</dict>
-</plist>
-```
-
-2. Run the following command:
-
-```
-codesign -s - --entitlements entitlements.plist <binary>
-```
-
-Replace `<binary>` with the name of the binary, for example: `out/cmake-debug/samples/gltf_viewer`.
-
-Afterwards, you should be able to successfully launch and attach to the executable using
-Instruments.

filament/CMakeLists.txt

@@ -265,13 +265,6 @@ set(MATERIAL_SRCS
         src/materials/vsmMipmap.mat
 )
 
-if (NOT FILAMENT_DISABLE_GTAO)
-    list(APPEND MATERIAL_SRCS
-        src/materials/ssao/gtao.mat
-        src/materials/ssao/gtaoBentNormals.mat
-    )
-endif()
-
 set(MATERIAL_FL0_SRCS
         src/materials/defaultMaterial.mat
         src/materials/skybox.mat
@@ -321,14 +314,12 @@ if (FILAMENT_FORCE_PROFILING_MODE)
     add_definitions(-DFILAMENT_FORCE_PROFILING_MODE)
 endif()
 
-if (FILAMENT_DISABLE_GTAO)
-    add_definitions(-DFILAMENT_DISABLE_GTAO)
-endif()
-
 # ==================================================================================================
 # Definitions
 # ==================================================================================================
 
+# "2" corresponds to SYSTRACE_TAG_FILEMENT (See: utils/Systrace.h)
+add_definitions(-DSYSTRACE_TAG=2)
 add_definitions(-DFILAMENT_DFG_LUT_SIZE=${DFG_LUT_SIZE})
 add_definitions(
     -DFILAMENT_PER_RENDER_PASS_ARENA_SIZE_IN_MB=${FILAMENT_PER_RENDER_PASS_ARENA_SIZE_IN_MB}
@@ -472,30 +463,6 @@ add_custom_command(
         APPEND
 )
 
-if (NOT FILAMENT_DISABLE_GTAO)
-    add_custom_command(
-            OUTPUT "${MATERIAL_DIR}/gtao.filamat"
-            DEPENDS src/materials/ssao/ssaoUtils.fs
-            DEPENDS src/materials/ssao/ssct.fs
-            DEPENDS src/materials/utils/depthUtils.fs
-            DEPENDS src/materials/utils/geometry.fs
-            DEPENDS src/materials/ssao/gtaoImpl.fs
-            DEPENDS src/materials/ssao/ssctImpl.fs
-            APPEND
-    )
-
-    add_custom_command(
-            OUTPUT "${MATERIAL_DIR}/gtaoBentNormals.filamat"
-            DEPENDS src/materials/ssao/ssaoUtils.fs
-            DEPENDS src/materials/ssao/ssct.fs
-            DEPENDS src/materials/utils/depthUtils.fs
-            DEPENDS src/materials/utils/geometry.fs
-            DEPENDS src/materials/ssao/gtaoImpl.fs
-            DEPENDS src/materials/ssao/ssctImpl.fs
-            APPEND
-    )
-endif()
-
 add_custom_command(
         OUTPUT "${MATERIAL_DIR}/bilateralBlur.filamat"
         DEPENDS src/materials/ssao/ssaoUtils.fs

filament/backend/CMakeLists.txt

@@ -261,7 +261,6 @@ if (FILAMENT_SUPPORTS_WEBGPU)
             src/webgpu/WebGPUHandles.h
             src/webgpu/WebGPUPipelineCreation.cpp
             src/webgpu/WebGPUPipelineCreation.h
-            src/webgpu/WebGPUStrings.h
             src/webgpu/WebGPUSwapChain.cpp
             src/webgpu/WebGPUSwapChain.h
             src/webgpu/WGPUProgram.cpp
@@ -291,6 +290,12 @@ if (ANDROID)
     list(APPEND SRCS src/BackendUtilsAndroid.cpp)
 endif()
 
+# ==================================================================================================
+# Definitions
+# ==================================================================================================
+# "2" corresponds to SYSTRACE_TAG_FILEMENT (See: utils/Systrace.h)
+add_definitions(-DSYSTRACE_TAG=2 )
+
 # ==================================================================================================
 # Includes & target definition
 # ==================================================================================================

filament/backend/include/backend/BufferDescriptor.h

@@ -20,15 +20,10 @@
 #define TNT_FILAMENT_BACKEND_BUFFERDESCRIPTOR_H
 
 #include <utils/compiler.h>
-
-#include <utility>
+#include <utils/ostream.h>
 
 #include <stddef.h>
 
-namespace utils::io {
-class ostream;
-} // namespace utils::io
-
 namespace filament::backend {
 
 class CallbackHandler;
@@ -94,8 +89,8 @@ public:
      * @param callback  A callback used to release the CPU buffer from this BufferDescriptor
      * @param user      An opaque user pointer passed to the callback function when it's called
      */
-    BufferDescriptor(void const* buffer, size_t const size,
-            Callback const callback = nullptr, void* user = nullptr) noexcept
+    BufferDescriptor(void const* buffer, size_t size,
+            Callback callback = nullptr, void* user = nullptr) noexcept
                 : buffer(const_cast<void*>(buffer)), size(size), mCallback(callback), mUser(user) {
     }
 
@@ -103,12 +98,11 @@ public:
      * Creates a BufferDescriptor that references a CPU memory-buffer
      * @param buffer    Memory address of the CPU buffer to reference
      * @param size      Size of the CPU buffer in bytes
-     * @param handler   A custom handler for the callback
      * @param callback  A callback used to release the CPU buffer from this BufferDescriptor
      * @param user      An opaque user pointer passed to the callback function when it's called
      */
-    BufferDescriptor(void const* buffer, size_t const size,
-            CallbackHandler* handler, Callback const callback, void* user = nullptr) noexcept
+    BufferDescriptor(void const* buffer, size_t size,
+            CallbackHandler* handler, Callback callback, void* user = nullptr) noexcept
                 : buffer(const_cast<void*>(buffer)), size(size),
                 mCallback(callback), mUser(user), mHandler(handler) {
     }
@@ -122,9 +116,8 @@ public:
      *
      * @param buffer    Memory address of the CPU buffer to reference
      * @param size      Size of the CPU buffer in bytes
-     * @param data      A pointer to the data
      * @param handler   Handler to use to dispatch the callback, or nullptr for the default handler
-     * @return          A new BufferDescriptor
+     * @return          a new BufferDescriptor
      */
     template<typename T, void(T::*method)(void const*, size_t)>
     static BufferDescriptor make(void const* buffer, size_t size, T* data,
@@ -171,7 +164,7 @@ public:
      * @param callback  The new callback function
      * @param user      An opaque user pointer passed to the callbeck function when it's called
      */
-    void setCallback(Callback const callback, void* user = nullptr) noexcept {
+    void setCallback(Callback callback, void* user = nullptr) noexcept {
         this->mCallback = callback;
         this->mUser = user;
         this->mHandler = nullptr;
@@ -183,7 +176,7 @@ public:
      * @param callback  The new callback function
      * @param user      An opaque user pointer passed to the callbeck function when it's called
      */
-    void setCallback(CallbackHandler* handler, Callback const callback, void* user = nullptr) noexcept {
+    void setCallback(CallbackHandler* handler, Callback callback, void* user = nullptr) noexcept {
         mCallback = callback;
         mUser = user;
         mHandler = handler;

filament/backend/include/backend/DescriptorSetOffsetArray.h

@@ -19,6 +19,8 @@
 
 #include <backend/DriverApiForward.h>
 
+#include <utils/ostream.h>
+
 #include <initializer_list>
 #include <memory>
 
@@ -26,10 +28,6 @@
 #include <stdint.h>
 
 
-namespace utils::io {
-class ostream;
-} // namespace utils::io
-
 namespace filament::backend {
 
 void* allocateFromCommandStream(DriverApi& driver, size_t size, size_t alignment) noexcept;

filament/backend/include/backend/DriverEnums.h

@@ -25,26 +25,22 @@
 #include <backend/PresentCallable.h>
 
 #include <utils/BitmaskEnum.h>
-#include <utils/CString.h>
 #include <utils/FixedCapacityVector.h>
 #include <utils/Invocable.h>
-#include <utils/StaticString.h>
+#include <utils/compiler.h>
 #include <utils/debug.h>
+#include <utils/ostream.h>
+#include <utils/StaticString.h>
 
 #include <math/vec4.h>
 
 #include <array>
 #include <type_traits>
 #include <variant>
-#include <string_view>
 
 #include <stddef.h>
 #include <stdint.h>
 
-namespace utils::io {
-class ostream;
-} // namespace utils::io
-
 /**
  * Types and enums used by filament's driver.
  *
@@ -163,7 +159,7 @@ enum class TimerQueryResult : int8_t {
     AVAILABLE = 1,  // result is available
 };
 
-constexpr std::string_view to_string(Backend const backend) noexcept {
+static constexpr const char* backendToString(Backend backend) {
     switch (backend) {
         case Backend::NOOP:
             return "Noop";
@@ -175,10 +171,9 @@ constexpr std::string_view to_string(Backend const backend) noexcept {
             return "Metal";
         case Backend::WEBGPU:
             return "WebGPU";
-        case Backend::DEFAULT:
-            return "Default";
+        default:
+            return "Unknown";
     }
-    return "Unknown";
 }
 
 /**
@@ -195,7 +190,7 @@ enum class ShaderLanguage {
     WGSL = 5,
 };
 
-constexpr const char* shaderLanguageToString(ShaderLanguage shaderLanguage) noexcept {
+static constexpr const char* shaderLanguageToString(ShaderLanguage shaderLanguage) {
     switch (shaderLanguage) {
         case ShaderLanguage::ESSL1:
             return "ESSL 1.0";
@@ -210,7 +205,6 @@ constexpr const char* shaderLanguageToString(ShaderLanguage shaderLanguage) noex
         case ShaderLanguage::WGSL:
             return "WGSL";
     }
-    return "UNKNOWN";
 }
 
 enum class ShaderStage : uint8_t {
@@ -228,7 +222,7 @@ enum class ShaderStageFlags : uint8_t {
     ALL_SHADER_STAGE_FLAGS = VERTEX | FRAGMENT | COMPUTE
 };
 
-constexpr bool hasShaderType(ShaderStageFlags flags, ShaderStage type) noexcept {
+static inline constexpr bool hasShaderType(ShaderStageFlags flags, ShaderStage type) noexcept {
     switch (type) {
         case ShaderStage::VERTEX:
             return bool(uint8_t(flags) & uint8_t(ShaderStageFlags::VERTEX));
@@ -239,239 +233,14 @@ constexpr bool hasShaderType(ShaderStageFlags flags, ShaderStage type) noexcept
     }
 }
 
-enum class TextureType : uint8_t {
-    FLOAT,
-    INT,
-    UINT,
-    DEPTH,
-    STENCIL,
-    DEPTH_STENCIL
+enum class DescriptorType : uint8_t {
+    UNIFORM_BUFFER,
+    SHADER_STORAGE_BUFFER,
+    SAMPLER,
+    INPUT_ATTACHMENT,
+    SAMPLER_EXTERNAL
 };
 
-constexpr std::string_view to_string(TextureType type) noexcept {
-    switch (type) {
-        case TextureType::FLOAT:            return "FLOAT";
-        case TextureType::INT:              return "INT";
-        case TextureType::UINT:             return "UINT";
-        case TextureType::DEPTH:            return "DEPTH";
-        case TextureType::STENCIL:          return "STENCIL";
-        case TextureType::DEPTH_STENCIL:    return "DEPTH_STENCIL";
-    }
-    return "UNKNOWN";
-}
-
- enum class DescriptorType : uint8_t {
-     SAMPLER_2D_FLOAT,
-     SAMPLER_2D_INT,
-     SAMPLER_2D_UINT,
-     SAMPLER_2D_DEPTH,
-
-     SAMPLER_2D_ARRAY_FLOAT,
-     SAMPLER_2D_ARRAY_INT,
-     SAMPLER_2D_ARRAY_UINT,
-     SAMPLER_2D_ARRAY_DEPTH,
-
-     SAMPLER_CUBE_FLOAT,
-     SAMPLER_CUBE_INT,
-     SAMPLER_CUBE_UINT,
-     SAMPLER_CUBE_DEPTH,
-
-     SAMPLER_CUBE_ARRAY_FLOAT,
-     SAMPLER_CUBE_ARRAY_INT,
-     SAMPLER_CUBE_ARRAY_UINT,
-     SAMPLER_CUBE_ARRAY_DEPTH,
-
-     SAMPLER_3D_FLOAT,
-     SAMPLER_3D_INT,
-     SAMPLER_3D_UINT,
-
-     SAMPLER_2D_MS_FLOAT,
-     SAMPLER_2D_MS_INT,
-     SAMPLER_2D_MS_UINT,
-
-     SAMPLER_2D_MS_ARRAY_FLOAT,
-     SAMPLER_2D_MS_ARRAY_INT,
-     SAMPLER_2D_MS_ARRAY_UINT,
-
-     SAMPLER_EXTERNAL,
-     UNIFORM_BUFFER,
-     SHADER_STORAGE_BUFFER,
-     INPUT_ATTACHMENT,
- };
-
-constexpr bool isDepthDescriptor(DescriptorType const type) noexcept {
-    switch (type) {
-        case DescriptorType::SAMPLER_2D_DEPTH:
-        case DescriptorType::SAMPLER_2D_ARRAY_DEPTH:
-        case DescriptorType::SAMPLER_CUBE_DEPTH:
-        case DescriptorType::SAMPLER_CUBE_ARRAY_DEPTH:
-            return true;
-        default: ;
-    }
-    return false;
-}
-
-constexpr bool isFloatDescriptor(DescriptorType const type) noexcept {
-    switch (type) {
-        case DescriptorType::SAMPLER_2D_FLOAT:
-        case DescriptorType::SAMPLER_2D_ARRAY_FLOAT:
-        case DescriptorType::SAMPLER_CUBE_FLOAT:
-        case DescriptorType::SAMPLER_CUBE_ARRAY_FLOAT:
-        case DescriptorType::SAMPLER_3D_FLOAT:
-        case DescriptorType::SAMPLER_2D_MS_FLOAT:
-        case DescriptorType::SAMPLER_2D_MS_ARRAY_FLOAT:
-            return true;
-        default: ;
-    }
-    return false;
-}
-
-constexpr bool isIntDescriptor(DescriptorType const type) noexcept {
-    switch (type) {
-        case DescriptorType::SAMPLER_2D_INT:
-        case DescriptorType::SAMPLER_2D_ARRAY_INT:
-        case DescriptorType::SAMPLER_CUBE_INT:
-        case DescriptorType::SAMPLER_CUBE_ARRAY_INT:
-        case DescriptorType::SAMPLER_3D_INT:
-        case DescriptorType::SAMPLER_2D_MS_INT:
-        case DescriptorType::SAMPLER_2D_MS_ARRAY_INT:
-            return true;
-        default: ;
-    }
-    return false;
-}
-
-constexpr bool isUnsignedIntDescriptor(DescriptorType const type) noexcept {
-    switch (type) {
-        case DescriptorType::SAMPLER_2D_UINT:
-        case DescriptorType::SAMPLER_2D_ARRAY_UINT:
-        case DescriptorType::SAMPLER_CUBE_UINT:
-        case DescriptorType::SAMPLER_CUBE_ARRAY_UINT:
-        case DescriptorType::SAMPLER_3D_UINT:
-        case DescriptorType::SAMPLER_2D_MS_UINT:
-        case DescriptorType::SAMPLER_2D_MS_ARRAY_UINT:
-            return true;
-        default: ;
-    }
-    return false;
-}
-
-constexpr bool is3dTypeDescriptor(DescriptorType const type) noexcept {
-    switch (type) {
-        case DescriptorType::SAMPLER_3D_FLOAT:
-        case DescriptorType::SAMPLER_3D_INT:
-        case DescriptorType::SAMPLER_3D_UINT:
-            return true;
-        default: ;
-    }
-    return false;
-}
-
-constexpr bool is2dTypeDescriptor(DescriptorType const type) noexcept {
-    switch (type) {
-        case DescriptorType::SAMPLER_2D_FLOAT:
-        case DescriptorType::SAMPLER_2D_INT:
-        case DescriptorType::SAMPLER_2D_UINT:
-        case DescriptorType::SAMPLER_2D_DEPTH:
-        case DescriptorType::SAMPLER_2D_MS_FLOAT:
-        case DescriptorType::SAMPLER_2D_MS_INT:
-        case DescriptorType::SAMPLER_2D_MS_UINT:
-            return true;
-        default: ;
-    }
-    return false;
-}
-
-constexpr bool is2dArrayTypeDescriptor(DescriptorType const type) noexcept {
-    switch (type) {
-        case DescriptorType::SAMPLER_2D_ARRAY_FLOAT:
-        case DescriptorType::SAMPLER_2D_ARRAY_INT:
-        case DescriptorType::SAMPLER_2D_ARRAY_UINT:
-        case DescriptorType::SAMPLER_2D_ARRAY_DEPTH:
-        case DescriptorType::SAMPLER_2D_MS_ARRAY_FLOAT:
-        case DescriptorType::SAMPLER_2D_MS_ARRAY_INT:
-        case DescriptorType::SAMPLER_2D_MS_ARRAY_UINT:
-            return true;
-        default: ;
-    }
-    return false;
-}
-
-constexpr bool isCubeTypeDescriptor(DescriptorType const type) noexcept {
-    switch (type) {
-        case DescriptorType::SAMPLER_CUBE_FLOAT:
-        case DescriptorType::SAMPLER_CUBE_INT:
-        case DescriptorType::SAMPLER_CUBE_UINT:
-        case DescriptorType::SAMPLER_CUBE_DEPTH:
-            return true;
-        default: ;
-    }
-    return false;
-}
-
-constexpr bool isCubeArrayTypeDescriptor(DescriptorType const type) noexcept {
-    switch (type) {
-        case DescriptorType::SAMPLER_CUBE_ARRAY_FLOAT:
-        case DescriptorType::SAMPLER_CUBE_ARRAY_INT:
-        case DescriptorType::SAMPLER_CUBE_ARRAY_UINT:
-        case DescriptorType::SAMPLER_CUBE_ARRAY_DEPTH:
-            return true;
-        default: ;
-    }
-    return false;
-}
-
-constexpr bool isMultiSampledTypeDescriptor(DescriptorType const type) noexcept {
-    switch (type) {
-        case DescriptorType::SAMPLER_2D_MS_FLOAT:
-        case DescriptorType::SAMPLER_2D_MS_INT:
-        case DescriptorType::SAMPLER_2D_MS_UINT:
-        case DescriptorType::SAMPLER_2D_MS_ARRAY_FLOAT:
-        case DescriptorType::SAMPLER_2D_MS_ARRAY_INT:
-        case DescriptorType::SAMPLER_2D_MS_ARRAY_UINT:
-            return true;
-        default: ;
-    }
-    return false;
-}
-
-constexpr std::string_view to_string(DescriptorType type) noexcept {
-    #define DESCRIPTOR_TYPE_CASE(TYPE)  case DescriptorType::TYPE: return #TYPE;
-    switch (type) {
-        DESCRIPTOR_TYPE_CASE(SAMPLER_2D_FLOAT)
-        DESCRIPTOR_TYPE_CASE(SAMPLER_2D_INT)
-        DESCRIPTOR_TYPE_CASE(SAMPLER_2D_UINT)
-        DESCRIPTOR_TYPE_CASE(SAMPLER_2D_DEPTH)
-        DESCRIPTOR_TYPE_CASE(SAMPLER_2D_ARRAY_FLOAT)
-        DESCRIPTOR_TYPE_CASE(SAMPLER_2D_ARRAY_INT)
-        DESCRIPTOR_TYPE_CASE(SAMPLER_2D_ARRAY_UINT)
-        DESCRIPTOR_TYPE_CASE(SAMPLER_2D_ARRAY_DEPTH)
-        DESCRIPTOR_TYPE_CASE(SAMPLER_CUBE_FLOAT)
-        DESCRIPTOR_TYPE_CASE(SAMPLER_CUBE_INT)
-        DESCRIPTOR_TYPE_CASE(SAMPLER_CUBE_UINT)
-        DESCRIPTOR_TYPE_CASE(SAMPLER_CUBE_DEPTH)
-        DESCRIPTOR_TYPE_CASE(SAMPLER_CUBE_ARRAY_FLOAT)
-        DESCRIPTOR_TYPE_CASE(SAMPLER_CUBE_ARRAY_INT)
-        DESCRIPTOR_TYPE_CASE(SAMPLER_CUBE_ARRAY_UINT)
-        DESCRIPTOR_TYPE_CASE(SAMPLER_CUBE_ARRAY_DEPTH)
-        DESCRIPTOR_TYPE_CASE(SAMPLER_3D_FLOAT)
-        DESCRIPTOR_TYPE_CASE(SAMPLER_3D_INT)
-        DESCRIPTOR_TYPE_CASE(SAMPLER_3D_UINT)
-        DESCRIPTOR_TYPE_CASE(SAMPLER_2D_MS_FLOAT)
-        DESCRIPTOR_TYPE_CASE(SAMPLER_2D_MS_INT)
-        DESCRIPTOR_TYPE_CASE(SAMPLER_2D_MS_UINT)
-        DESCRIPTOR_TYPE_CASE(SAMPLER_2D_MS_ARRAY_FLOAT)
-        DESCRIPTOR_TYPE_CASE(SAMPLER_2D_MS_ARRAY_INT)
-        DESCRIPTOR_TYPE_CASE(SAMPLER_2D_MS_ARRAY_UINT)
-        DESCRIPTOR_TYPE_CASE(SAMPLER_EXTERNAL)
-        DESCRIPTOR_TYPE_CASE(UNIFORM_BUFFER)
-        DESCRIPTOR_TYPE_CASE(SHADER_STORAGE_BUFFER)
-        DESCRIPTOR_TYPE_CASE(INPUT_ATTACHMENT)
-    }
-    return "UNKNOWN";
-    #undef DESCRIPTOR_TYPE_CASE
-}
-
 enum class DescriptorFlags : uint8_t {
     NONE = 0x00,
     DYNAMIC_OFFSET = 0x01
@@ -482,13 +251,6 @@ using descriptor_set_t = uint8_t;
 using descriptor_binding_t = uint8_t;
 
 struct DescriptorSetLayoutBinding {
-    static bool isSampler(DescriptorType type) noexcept {
-        return int(type) <= int(DescriptorType::SAMPLER_EXTERNAL);
-    }
-    static bool isBuffer(DescriptorType type) noexcept {
-        return type == DescriptorType::UNIFORM_BUFFER ||
-               type == DescriptorType::SHADER_STORAGE_BUFFER;
-    }
     DescriptorType type;
     ShaderStageFlags stageFlags;
     descriptor_binding_t binding;
@@ -499,7 +261,7 @@ struct DescriptorSetLayoutBinding {
     //  no uninitialized padding bytes.
     //    uint8_t externalSamplerDataIndex = EXTERNAL_SAMPLER_DATA_INDEX_UNUSED;
 
-    friend bool operator==(DescriptorSetLayoutBinding const& lhs,
+    friend inline bool operator==(DescriptorSetLayoutBinding const& lhs,
             DescriptorSetLayoutBinding const& rhs) noexcept {
         return lhs.type == rhs.type &&
                lhs.flags == rhs.flags &&
@@ -532,7 +294,7 @@ enum class TargetBufferFlags : uint32_t {
     ALL = COLOR_ALL | DEPTH | STENCIL       //!< Color, depth and stencil buffer selected.
 };
 
-constexpr TargetBufferFlags getTargetBufferFlagsAt(size_t index) noexcept {
+inline constexpr TargetBufferFlags getTargetBufferFlagsAt(size_t index) noexcept {
     if (index == 0u) return TargetBufferFlags::COLOR0;
     if (index == 1u) return TargetBufferFlags::COLOR1;
     if (index == 2u) return TargetBufferFlags::COLOR2;
@@ -689,24 +451,6 @@ enum class SamplerType : uint8_t {
     SAMPLER_CUBEMAP_ARRAY,  //!< Cube map array texture (feature level 2)
 };
 
-constexpr std::string_view to_string(SamplerType const type) noexcept {
-    switch (type) {
-        case SamplerType::SAMPLER_2D:
-            return "SAMPLER_2D";
-        case SamplerType::SAMPLER_2D_ARRAY:
-            return "SAMPLER_2D_ARRAY";
-        case SamplerType::SAMPLER_CUBEMAP:
-            return "SAMPLER_CUBEMAP";
-        case SamplerType::SAMPLER_EXTERNAL:
-            return "SAMPLER_EXTERNAL";
-        case SamplerType::SAMPLER_3D:
-            return "SAMPLER_3D";
-        case SamplerType::SAMPLER_CUBEMAP_ARRAY:
-            return "SAMPLER_CUBEMAP_ARRAY";
-    }
-    return "Unknown";
-}
-
 //! Subpass type
 enum class SubpassType : uint8_t {
     SUBPASS_INPUT
@@ -720,20 +464,6 @@ enum class SamplerFormat : uint8_t {
     SHADOW = 3      //!< shadow sampler (PCF)
 };
 
-constexpr std::string_view to_string(SamplerFormat const format) noexcept {
-    switch (format) {
-        case SamplerFormat::INT:
-            return "INT";
-        case SamplerFormat::UINT:
-            return "UINT";
-        case SamplerFormat::FLOAT:
-            return "FLOAT";
-        case SamplerFormat::SHADOW:
-            return "SHADOW";
-    }
-    return "Unknown";
-}
-
 /**
  * Supported element types
  */
@@ -773,15 +503,6 @@ enum class BufferObjectBinding : uint8_t {
     SHADER_STORAGE
 };
 
-constexpr std::string_view to_string(BufferObjectBinding type) noexcept {
-    switch (type) {
-        case BufferObjectBinding::VERTEX:           return "VERTEX";
-        case BufferObjectBinding::UNIFORM:          return "UNIFORM";
-        case BufferObjectBinding::SHADER_STORAGE:   return "SHADER_STORAGE";
-    }
-    return "UNKNOWN";
-}
-
 //! Face culling Mode
 enum class CullingMode : uint8_t {
     NONE,               //!< No culling, front and back faces are visible
@@ -1043,8 +764,6 @@ enum class TextureFormat : uint16_t {
     SRGB_ALPHA_BPTC_UNORM,  // BC7 sRGB
 };
 
-TextureType getTextureType(TextureFormat format) noexcept;
-
 //! Bitmask describing the intended Texture Usage
 enum class TextureUsage : uint16_t {
     NONE                = 0x0000,
@@ -1072,7 +791,7 @@ enum class TextureSwizzle : uint8_t {
 };
 
 //! returns whether this format a depth format
-constexpr bool isDepthFormat(TextureFormat format) noexcept {
+static constexpr bool isDepthFormat(TextureFormat format) noexcept {
     switch (format) {
         case TextureFormat::DEPTH32F:
         case TextureFormat::DEPTH24:
@@ -1085,7 +804,7 @@ constexpr bool isDepthFormat(TextureFormat format) noexcept {
     }
 }
 
-constexpr bool isStencilFormat(TextureFormat format) noexcept {
+static constexpr bool isStencilFormat(TextureFormat format) noexcept {
     switch (format) {
         case TextureFormat::STENCIL8:
         case TextureFormat::DEPTH24_STENCIL8:
@@ -1096,7 +815,7 @@ constexpr bool isStencilFormat(TextureFormat format) noexcept {
     }
 }
 
-constexpr bool isColorFormat(TextureFormat format) noexcept {
+inline constexpr bool isColorFormat(TextureFormat format) noexcept {
     switch (format) {
         // Standard color formats
         case TextureFormat::R8:
@@ -1123,7 +842,7 @@ constexpr bool isColorFormat(TextureFormat format) noexcept {
     return false;
 }
 
-constexpr bool isUnsignedIntFormat(TextureFormat format) {
+static constexpr bool isUnsignedIntFormat(TextureFormat format) {
     switch (format) {
         case TextureFormat::R8UI:
         case TextureFormat::R16UI:
@@ -1144,7 +863,7 @@ constexpr bool isUnsignedIntFormat(TextureFormat format) {
     }
 }
 
-constexpr bool isSignedIntFormat(TextureFormat format) {
+static constexpr bool isSignedIntFormat(TextureFormat format) {
     switch (format) {
         case TextureFormat::R8I:
         case TextureFormat::R16I:
@@ -1166,35 +885,35 @@ constexpr bool isSignedIntFormat(TextureFormat format) {
 }
 
 //! returns whether this format is a compressed format
-constexpr bool isCompressedFormat(TextureFormat format) noexcept {
+static constexpr bool isCompressedFormat(TextureFormat format) noexcept {
     return format >= TextureFormat::EAC_R11;
 }
 
 //! returns whether this format is an ETC2 compressed format
-constexpr bool isETC2Compression(TextureFormat format) noexcept {
+static constexpr bool isETC2Compression(TextureFormat format) noexcept {
     return format >= TextureFormat::EAC_R11 && format <= TextureFormat::ETC2_EAC_SRGBA8;
 }
 
 //! returns whether this format is an S3TC compressed format
-constexpr bool isS3TCCompression(TextureFormat format) noexcept {
+static constexpr bool isS3TCCompression(TextureFormat format) noexcept {
     return format >= TextureFormat::DXT1_RGB && format <= TextureFormat::DXT5_SRGBA;
 }
 
-constexpr bool isS3TCSRGBCompression(TextureFormat format) noexcept {
+static constexpr bool isS3TCSRGBCompression(TextureFormat format) noexcept {
     return format >= TextureFormat::DXT1_SRGB && format <= TextureFormat::DXT5_SRGBA;
 }
 
 //! returns whether this format is an RGTC compressed format
-constexpr bool isRGTCCompression(TextureFormat format) noexcept {
+static constexpr bool isRGTCCompression(TextureFormat format) noexcept {
     return format >= TextureFormat::RED_RGTC1 && format <= TextureFormat::SIGNED_RED_GREEN_RGTC2;
 }
 
 //! returns whether this format is an BPTC compressed format
-constexpr bool isBPTCCompression(TextureFormat format) noexcept {
+static constexpr bool isBPTCCompression(TextureFormat format) noexcept {
     return format >= TextureFormat::RGB_BPTC_SIGNED_FLOAT && format <= TextureFormat::SRGB_ALPHA_BPTC_UNORM;
 }
 
-constexpr bool isASTCCompression(TextureFormat format) noexcept {
+static constexpr bool isASTCCompression(TextureFormat format) noexcept {
     return format >= TextureFormat::RGBA_ASTC_4x4 && format <= TextureFormat::SRGB8_ALPHA8_ASTC_12x12;
 }
 
@@ -1315,23 +1034,19 @@ struct SamplerParams {             // NOLINT
             assert_invariant(lhs.padding2 == 0);
             auto* pLhs = reinterpret_cast<uint32_t const*>(reinterpret_cast<char const*>(&lhs));
             auto* pRhs = reinterpret_cast<uint32_t const*>(reinterpret_cast<char const*>(&rhs));
-            return *pLhs < *pRhs;
+            return *pLhs == *pRhs;
         }
     };
 
-    bool isFiltered() const noexcept {
-        return filterMag != SamplerMagFilter::NEAREST || filterMin != SamplerMinFilter::NEAREST;
-    }
-
 private:
-    friend bool operator == (SamplerParams lhs, SamplerParams rhs) noexcept {
-        return EqualTo{}(lhs, rhs);
+    friend inline bool operator == (SamplerParams lhs, SamplerParams rhs) noexcept {
+        return SamplerParams::EqualTo{}(lhs, rhs);
     }
-    friend bool operator != (SamplerParams lhs, SamplerParams rhs) noexcept {
-        return  !EqualTo{}(lhs, rhs);
+    friend inline bool operator != (SamplerParams lhs, SamplerParams rhs) noexcept {
+        return  !SamplerParams::EqualTo{}(lhs, rhs);
     }
-    friend bool operator < (SamplerParams lhs, SamplerParams rhs) noexcept {
-        return LessThan{}(lhs, rhs);
+    friend inline bool operator < (SamplerParams lhs, SamplerParams rhs) noexcept {
+        return SamplerParams::LessThan{}(lhs, rhs);
     }
 };
 
@@ -1381,15 +1096,15 @@ struct SamplerYcbcrConversion {// NOLINT
     };
 
 private:
-    friend bool operator == (SamplerYcbcrConversion lhs, SamplerYcbcrConversion rhs)
+    friend inline bool operator == (SamplerYcbcrConversion lhs, SamplerYcbcrConversion rhs)
             noexcept {
         return SamplerYcbcrConversion::EqualTo{}(lhs, rhs);
     }
-    friend bool operator != (SamplerYcbcrConversion lhs, SamplerYcbcrConversion rhs)
+    friend inline bool operator != (SamplerYcbcrConversion lhs, SamplerYcbcrConversion rhs)
             noexcept {
         return  !SamplerYcbcrConversion::EqualTo{}(lhs, rhs);
     }
-    friend bool operator < (SamplerYcbcrConversion lhs, SamplerYcbcrConversion rhs)
+    friend inline bool operator < (SamplerYcbcrConversion lhs, SamplerYcbcrConversion rhs)
             noexcept {
         return SamplerYcbcrConversion::LessThan{}(lhs, rhs);
     }

filament/backend/include/backend/Handle.h

@@ -17,6 +17,9 @@
 #ifndef TNT_FILAMENT_BACKEND_HANDLE_H
 #define TNT_FILAMENT_BACKEND_HANDLE_H
 
+#if !defined(NDEBUG)
+#include <utils/ostream.h>
+#endif
 #include <utils/debug.h>
 
 #include <type_traits> // FIXME: STL headers are not allowed in public headers
@@ -24,10 +27,6 @@
 
 #include <stdint.h>
 
-namespace utils::io {
-class ostream;
-} // namespace utils::io
-
 namespace filament::backend {
 
 struct HwBufferObject;

filament/backend/include/backend/PipelineState.h

@@ -20,14 +20,12 @@
 #include <backend/DriverEnums.h>
 #include <backend/Handle.h>
 
+#include <utils/ostream.h>
+
 #include <array>
 
 #include <stdint.h>
 
-namespace utils::io {
-class ostream;
-} // namespace utils::io
-
 namespace filament::backend {
 
 //! \privatesection

filament/backend/include/backend/PixelBufferDescriptor.h

@@ -24,14 +24,11 @@
 
 #include <utils/compiler.h>
 #include <utils/debug.h>
+#include <utils/ostream.h>
 
 #include <stddef.h>
 #include <stdint.h>
 
-namespace utils::io {
-class ostream;
-} // namespace utils::io
-
 namespace filament::backend {
 
 /**
@@ -204,15 +201,23 @@ public:
                 }, new T(std::forward<T>(functor))
         };
     }
+
+    // --------------------------------------------------------------------------------------------
+
     /**
-     * Computes the size in bytes for a pixel of given dimensions and format
+     * Computes the size in bytes needed to fit an image of given dimensions and format
      *
      * @param format    Format of the image pixels
      * @param type      Type of the image pixels
-     * @return The size of the specified pixel in bytes
+     * @param stride    Stride of a row in pixels
+     * @param height    Height of the image in rows
+     * @param alignment Alignment in bytes of pixel rows
+     * @return The buffer size needed to fit this image in bytes
      */
+    static constexpr size_t computeDataSize(PixelDataFormat format, PixelDataType type,
+            size_t stride, size_t height, size_t alignment) noexcept {
+        assert_invariant(alignment);
 
-    static constexpr size_t computePixelSize(PixelDataFormat format, PixelDataType type) noexcept {
         if (type == PixelDataType::COMPRESSED) {
             return 0;
         }
@@ -234,7 +239,7 @@ public:
             case PixelDataFormat::RGB_INTEGER:
                 n = 3;
                 break;
-            case PixelDataFormat::UNUSED:// shouldn't happen (used to be rgbm)
+            case PixelDataFormat::UNUSED: // shouldn't happen (used to be rgbm)
             case PixelDataFormat::RGBA:
             case PixelDataFormat::RGBA_INTEGER:
                 n = 4;
@@ -243,7 +248,7 @@ public:
 
         size_t bpp = n;
         switch (type) {
-            case PixelDataType::COMPRESSED:// Impossible -- to squash the IDE warnings
+            case PixelDataType::COMPRESSED: // Impossible -- to squash the IDE warnings
             case PixelDataType::UBYTE:
             case PixelDataType::BYTE:
                 // nothing to do
@@ -274,35 +279,16 @@ public:
                 bpp = 2;
                 break;
         }
-        return bpp;
-    }
 
-    // --------------------------------------------------------------------------------------------
-
-    /**
-     * Computes the size in bytes needed to fit an image of given dimensions and format
-     *
-     * @param format    Format of the image pixels
-     * @param type      Type of the image pixels
-     * @param stride    Stride of a row in pixels
-     * @param height    Height of the image in rows
-     * @param alignment Alignment in bytes of pixel rows
-     * @return The buffer size needed to fit this image in bytes
-     */
-    static constexpr size_t computeDataSize(PixelDataFormat format, PixelDataType type,
-            size_t stride, size_t height, size_t alignment) noexcept {
-        assert_invariant(alignment);
-
-        size_t bpp = computePixelSize(format, type);
         size_t const bpr = bpp * stride;
         size_t const bprAligned = (bpr + (alignment - 1)) & (~alignment + 1);
         return bprAligned * height;
     }
 
     //! left coordinate in pixels
-    uint32_t left = 0;
+    uint32_t left   = 0;
     //! top coordinate in pixels
-    uint32_t top = 0;
+    uint32_t top    = 0;
     union {
         struct {
             //! stride in pixels

filament/backend/include/backend/Program.h

@@ -20,10 +20,12 @@
 #include <utils/CString.h>
 #include <utils/FixedCapacityVector.h>
 #include <utils/Invocable.h>
+#include <utils/ostream.h>
 
 #include <backend/DriverEnums.h>
 
 #include <array>
+#include <unordered_map>
 #include <tuple>
 #include <utility>
 #include <variant>
@@ -31,10 +33,6 @@
 #include <stddef.h>
 #include <stdint.h>
 
-namespace utils::io {
-class ostream;
-} // namespace utils::io
-
 namespace filament::backend {
 
 class Program {

filament/backend/include/backend/TargetBufferInfo.h

@@ -19,26 +19,22 @@
 
 #include <backend/Handle.h>
 
-#include <utility>
+#include <utils/ostream.h>
 
 #include <stddef.h>
 #include <stdint.h>
 
-namespace utils::io {
-class ostream;
-} // namespace utils::io
-
 namespace filament::backend {
 
 //! \privatesection
 
 struct TargetBufferInfo {
     // note: the parameters of this constructor are not in the order of this structure's fields
-    TargetBufferInfo(Handle<HwTexture> handle, uint8_t const level, uint16_t const layer) noexcept
-            : handle(std::move(handle)), level(level), layer(layer) {
+    TargetBufferInfo(Handle<HwTexture> handle, uint8_t level, uint16_t layer) noexcept
+            : handle(handle), level(level), layer(layer) {
     }
 
-    TargetBufferInfo(Handle<HwTexture> handle, uint8_t const level) noexcept
+    TargetBufferInfo(Handle<HwTexture> handle, uint8_t level) noexcept
             : handle(handle), level(level) {
     }
 
@@ -74,11 +70,11 @@ private:
     TargetBufferInfo mInfos[MAX_SUPPORTED_RENDER_TARGET_COUNT];
 
 public:
-    TargetBufferInfo const& operator[](size_t const i) const noexcept {
+    TargetBufferInfo const& operator[](size_t i) const noexcept {
         return mInfos[i];
     }
 
-    TargetBufferInfo& operator[](size_t const i) noexcept {
+    TargetBufferInfo& operator[](size_t i) noexcept {
         return mInfos[i];
     }
 

filament/backend/include/backend/platforms/OpenGLPlatform.h

@@ -199,7 +199,7 @@ public:
      */
     virtual bool makeCurrent(ContextType type,
             SwapChain* UTILS_NONNULL drawSwapChain,
-            SwapChain* UTILS_NONNULL readSwapChain) = 0;
+            SwapChain* UTILS_NONNULL readSwapChain) noexcept = 0;
 
     /**
      * Called by the driver to make the OpenGL context active on the calling thread and bind
@@ -219,7 +219,7 @@ public:
             SwapChain* UTILS_NONNULL drawSwapChain,
             SwapChain* UTILS_NONNULL readSwapChain,
             utils::Invocable<void()> preContextChange,
-            utils::Invocable<void(size_t index)> postContextChange);
+            utils::Invocable<void(size_t index)> postContextChange) noexcept;
 
     /**
      * Called by the backend just before calling commit()

filament/backend/include/backend/platforms/PlatformCocoaGL.h

@@ -58,7 +58,7 @@ protected:
     SwapChain* createSwapChain(void* nativewindow, uint64_t flags) noexcept override;
     SwapChain* createSwapChain(uint32_t width, uint32_t height, uint64_t flags) noexcept override;
     void destroySwapChain(SwapChain* swapChain) noexcept override;
-    bool makeCurrent(ContextType type, SwapChain* drawSwapChain, SwapChain* readSwapChain) override;
+    bool makeCurrent(ContextType type, SwapChain* drawSwapChain, SwapChain* readSwapChain) noexcept override;
     void commit(SwapChain* swapChain) noexcept override;
     ExternalTexture* createExternalImageTexture() noexcept override;
     void destroyExternalImageTexture(ExternalTexture* texture) noexcept override;

filament/backend/include/backend/platforms/PlatformCocoaTouchGL.h

@@ -55,7 +55,7 @@ public:
     SwapChain* createSwapChain(void* nativewindow, uint64_t flags) noexcept override;
     SwapChain* createSwapChain(uint32_t width, uint32_t height, uint64_t flags) noexcept override;
     void destroySwapChain(SwapChain* swapChain) noexcept override;
-    bool makeCurrent(ContextType type, SwapChain* drawSwapChain, SwapChain* readSwapChain) override;
+    bool makeCurrent(ContextType type, SwapChain* drawSwapChain, SwapChain* readSwapChain) noexcept override;
     void commit(SwapChain* swapChain) noexcept override;
 
     ExternalTexture* createExternalImageTexture() noexcept override;

filament/backend/include/backend/platforms/PlatformEGL.h

@@ -109,11 +109,11 @@ protected:
 
     bool makeCurrent(ContextType type,
             SwapChain* drawSwapChain,
-            SwapChain* readSwapChain) override;
+            SwapChain* readSwapChain) noexcept override;
 
     void makeCurrent(SwapChain* drawSwapChain, SwapChain* readSwapChain,
             utils::Invocable<void()> preContextChange,
-            utils::Invocable<void(size_t index)> postContextChange) override;
+            utils::Invocable<void(size_t index)> postContextChange) noexcept override;
 
     void commit(SwapChain* swapChain) noexcept override;
 
@@ -148,12 +148,12 @@ protected:
     EGLContext getContextForType(ContextType type) const noexcept;
 
     // makes the draw and read surface current without changing the current context
-    EGLBoolean makeCurrent(EGLSurface drawSurface, EGLSurface readSurface) {
+    EGLBoolean makeCurrent(EGLSurface drawSurface, EGLSurface readSurface) noexcept {
         return egl.makeCurrent(drawSurface, readSurface);
     }
 
     // makes context current and set draw and read surfaces to EGL_NO_SURFACE
-    EGLBoolean makeCurrent(EGLContext context) {
+    EGLBoolean makeCurrent(EGLContext context) noexcept {
         return egl.makeCurrent(context, mEGLDummySurface, mEGLDummySurface);
     }
 
@@ -211,9 +211,9 @@ private:
     public:
         explicit EGL(EGLDisplay& dpy) : mEGLDisplay(dpy) {}
         EGLBoolean makeCurrent(EGLContext context,
-                EGLSurface drawSurface, EGLSurface readSurface);
+                EGLSurface drawSurface, EGLSurface readSurface) noexcept;
 
-        EGLBoolean makeCurrent(EGLSurface drawSurface, EGLSurface readSurface) {
+        EGLBoolean makeCurrent(EGLSurface drawSurface, EGLSurface readSurface) noexcept {
             return makeCurrent(mCurrentContext, drawSurface, readSurface);
         }
     } egl{ mEGLDisplay };

filament/backend/include/backend/platforms/PlatformEGLAndroid.h

@@ -127,7 +127,7 @@ protected:
 protected:
     bool makeCurrent(ContextType type,
             SwapChain* drawSwapChain,
-            SwapChain* readSwapChain) override;
+            SwapChain* readSwapChain) noexcept override;
 
 private:
     struct InitializeJvmForPerformanceManagerIfNeeded {

filament/backend/include/backend/platforms/PlatformGLX.h

@@ -51,7 +51,7 @@ protected:
     SwapChain* createSwapChain(void* nativewindow, uint64_t flags) noexcept override;
     SwapChain* createSwapChain(uint32_t width, uint32_t height, uint64_t flags) noexcept override;
     void destroySwapChain(SwapChain* swapChain) noexcept override;
-    bool makeCurrent(ContextType type, SwapChain* drawSwapChain, SwapChain* readSwapChain) override;
+    bool makeCurrent(ContextType type, SwapChain* drawSwapChain, SwapChain* readSwapChain) noexcept override;
     void commit(SwapChain* swapChain) noexcept override;
 
 private:

filament/backend/include/backend/platforms/PlatformMetal.h

@@ -39,40 +39,18 @@ public:
     Driver* createDriver(void* sharedContext, const Platform::DriverConfig& driverConfig) noexcept override;
     int getOSVersion() const noexcept override { return 0; }
 
-    /**
-     * Optionally initializes the Metal platform by acquiring resources necessary for rendering.
-     *
-     * This method attempts to acquire a Metal device and command queue, returning true if both are
-     * successfully obtained, or false otherwise. Typically, these objects are acquired when
-     * the Metal backend is initialized. This method allows clients to check for their availability
-     * earlier.
-     *
-     * Calling initialize() is optional and safe to do so multiple times. After initialize() returns
-     * true, subsequent calls will continue to return true but have no effect.
-     *
-     * initialize() must be called from the main thread.
-     *
-     * @returns true if the device and command queue have been successfully obtained; false
-     * otherwise.
-     */
-    bool initialize() noexcept;
-
     /**
      * Obtain the preferred Metal device object for the backend to use.
      *
      * On desktop platforms, there may be multiple GPUs suitable for rendering, and this method is
      * free to decide which one to use. On mobile systems with a single GPU, implementations should
      * simply return the result of MTLCreateSystemDefaultDevice();
-     *
-     * createDevice is called by the Metal backend from the backend thread.
      */
     virtual void createDevice(MetalDevice& outDevice) noexcept;
 
     /**
      * Create a command submission queue on the Metal device object.
      *
-     * createCommandQueue is called by the Metal backend from the backend thread.
-     *
      * @param device The device which was returned from createDevice()
      */
     virtual void createCommandQueue(
@@ -82,8 +60,6 @@ public:
      * Obtain a MTLCommandBuffer enqueued on this Platform's MTLCommandQueue. The command buffer is
      * guaranteed to execute before all subsequent command buffers created either by Filament, or
      * further calls to this method.
-     *
-     * createAndEnqueueCommandBuffer must be called from the main thread.
      */
     void createAndEnqueueCommandBuffer(MetalCommandBuffer& outCommandBuffer) noexcept;
 
@@ -92,8 +68,6 @@ public:
      *
      * Each frame rendered requires a CAMetalDrawable texture, which is presented on-screen at the
      * completion of each frame. These are limited and provided round-robin style by the system.
-     *
-     * setDrawableFailureBehavior must be called from the main thread.
      */
     enum class DrawableFailureBehavior : uint8_t {
         /**

filament/backend/include/backend/platforms/PlatformOSMesa.h

@@ -56,7 +56,7 @@ protected:
     SwapChain* createSwapChain(uint32_t width, uint32_t height, uint64_t flags) noexcept override;
     void destroySwapChain(SwapChain* swapChain) noexcept override;
     bool makeCurrent(ContextType type, SwapChain* drawSwapChain,
-            SwapChain* readSwapChain) override;
+            SwapChain* readSwapChain) noexcept override;
     void commit(SwapChain* swapChain) noexcept override;
 
 private:

filament/backend/include/backend/platforms/PlatformWGL.h

@@ -53,7 +53,7 @@ protected:
     SwapChain* createSwapChain(void* nativewindow, uint64_t flags) noexcept override;
     SwapChain* createSwapChain(uint32_t width, uint32_t height, uint64_t flags) noexcept override;
     void destroySwapChain(SwapChain* swapChain) noexcept override;
-    bool makeCurrent(ContextType type, SwapChain* drawSwapChain, SwapChain* readSwapChain) override;
+    bool makeCurrent(ContextType type, SwapChain* drawSwapChain, SwapChain* readSwapChain) noexcept override;
     void commit(SwapChain* swapChain) noexcept override;
 
 protected:

filament/backend/include/backend/platforms/PlatformWebGL.h

@@ -46,7 +46,7 @@ protected:
     SwapChain* createSwapChain(void* nativewindow, uint64_t flags) noexcept override;
     SwapChain* createSwapChain(uint32_t width, uint32_t height, uint64_t flags) noexcept override;
     void destroySwapChain(SwapChain* swapChain) noexcept override;
-    bool makeCurrent(ContextType type, SwapChain* drawSwapChain, SwapChain* readSwapChain) override;
+    bool makeCurrent(ContextType type, SwapChain* drawSwapChain, SwapChain* readSwapChain) noexcept override;
     void commit(SwapChain* swapChain) noexcept override;
 };
 

filament/backend/include/backend/platforms/VulkanPlatform.h

@@ -27,11 +27,8 @@
 #include <utils/Hash.h>
 #include <utils/PrivateImplementation.h>
 
-#include <cstddef>
-#include <functional>
 #include <tuple>
 #include <unordered_set>
-#include <string>
 
 #include <stddef.h>
 #include <stdint.h>

filament/backend/include/backend/platforms/WebGPUPlatform.h

@@ -22,7 +22,6 @@
 #include <webgpu/webgpu_cpp.h>
 
 #include <cstdint>
-#include <vector>
 
 namespace filament::backend {
 
@@ -57,10 +56,6 @@ protected:
             const Platform::DriverConfig& driverConfig) noexcept override;
 
 private:
-    // returns adapter request option variations applicable for the particular
-    // platform
-    [[nodiscard]] static std::vector<wgpu::RequestAdapterOptions> getAdapterOptions();
-
     // we may consider having the driver own this in the future
     wgpu::Instance mInstance;
 };

filament/backend/include/private/backend/CircularBuffer.h

@@ -72,7 +72,7 @@ public:
     Range getBuffer() noexcept;
 
 private:
-    void* alloc(size_t size);
+    void* alloc(size_t size) noexcept;
     void dealloc() noexcept;
 
     // pointer to the beginning of the circular buffer (constant)

filament/backend/include/private/backend/CommandBufferQueue.h

@@ -76,7 +76,7 @@ public:
 
     // all commands buffers (Slices) written to this point are returned by waitForCommand(). This
     // call blocks until the CircularBuffer has at least mRequiredSize bytes available.
-    void flush();
+    void flush() noexcept;
 
     // returns from waitForCommands() immediately.
     void requestExit();

filament/backend/include/private/backend/HandleAllocator.h

@@ -222,56 +222,6 @@ public:
         return static_cast<Dp>(p);
     }
 
-    template<typename Dp, typename B>
-    inline std::enable_if_t<
-            std::is_pointer_v<Dp> && std::is_base_of_v<B, std::remove_pointer_t<Dp>>, int16_t>
-    handle_set_value(Handle<B>& handle, uint8_t v) {
-        assert_invariant(handle);
-        auto [p, tag] = handleToPointer(handle.getId());
-
-        if (isPoolHandle(handle.getId())) {
-            // check for pool handle use-after-free
-            if (UTILS_UNLIKELY(!mUseAfterFreeCheckDisabled)) {
-                auto const pNode = static_cast<typename Allocator::Node*>(p);
-                pNode[-1].test_value = v;
-                return 1;
-            }
-            return 0;
-        } else {
-            // check for heap handle use-after-free
-            if (UTILS_UNLIKELY(!mUseAfterFreeCheckDisabled)) {
-                return -1;
-            }
-            return -2;
-        }
-    }
-
-    template<typename Dp, typename B>
-    inline std::enable_if_t<
-            std::is_pointer_v<Dp> && std::is_base_of_v<B, std::remove_pointer_t<Dp>>, int16_t>
-    handle_get_value(Handle<B>& handle) {
-        assert_invariant(handle);
-        auto [p, tag] = handleToPointer(handle.getId());
-
-        if (isPoolHandle(handle.getId())) {
-            // check for pool handle use-after-free
-            if (UTILS_UNLIKELY(!mUseAfterFreeCheckDisabled)) {
-                auto const pNode = static_cast<typename Allocator::Node*>(p);
-                uint8_t age = pNode[-1].age;
-                uint8_t test_value = pNode[-1].test_value;
-                int16_t ret = (int16_t) ((age << 8) | test_value);
-                return ret;
-            }
-            return 0;
-        } else {
-            // check for heap handle use-after-free
-            if (UTILS_UNLIKELY(!mUseAfterFreeCheckDisabled)) {
-                return -1;
-            }
-            return -2;
-        }
-    }
-
     utils::CString getHandleTag(HandleBase::HandleId key) const noexcept;
 
     template<typename B>
@@ -326,10 +276,7 @@ private:
     class Allocator {
         friend class HandleAllocator;
         static constexpr size_t MIN_ALIGNMENT = alignof(std::max_align_t);
-        struct Node {
-            uint8_t age;
-            uint8_t test_value = 0xff;
-        };
+        struct Node { uint8_t age; };
         // Note: using the `extra` parameter of PoolAllocator<>, even with a 1-byte structure,
         // generally increases all pool allocations by 8-bytes because of alignment restrictions.
         template<size_t SIZE>

filament/backend/include/private/backend/VirtualMachineEnv.h

@@ -27,13 +27,13 @@ namespace filament {
 class VirtualMachineEnv {
 public:
     // must be called before VirtualMachineEnv::get() from a thread that is attached to the JavaVM
-    static jint JNI_OnLoad(JavaVM* vm);
+    static jint JNI_OnLoad(JavaVM* vm) noexcept;
 
     // must be called on backend thread
     static VirtualMachineEnv& get() noexcept;
 
     // can be called from any thread that already has a JniEnv
-    static JNIEnv* getThreadEnvironment();
+    static JNIEnv* getThreadEnvironment() noexcept;
 
     // must be called from the backend thread
     JNIEnv* getEnvironment() noexcept {
@@ -49,7 +49,7 @@ public:
 private:
     explicit VirtualMachineEnv(JavaVM* vm) noexcept;
     ~VirtualMachineEnv() noexcept;
-    JNIEnv* getEnvironmentSlow();
+    JNIEnv* getEnvironmentSlow() noexcept;
 
     static utils::Mutex sLock;
     static JavaVM* sVirtualMachine;

filament/backend/src/BackendUtils.cpp

@@ -18,8 +18,6 @@
 
 #include "DataReshaper.h"
 
-#include <backend/DriverEnums.h>
-
 #include <utils/CString.h>
 
 #include <string_view>
@@ -225,143 +223,6 @@ size_t getFormatSize(TextureFormat format) noexcept {
     }
 }
 
-TextureType getTextureType(TextureFormat const format) noexcept {
-    switch (format) {
-        case TextureFormat::UNUSED:
-            // should not happen
-            return TextureType::FLOAT;
-
-        case TextureFormat::R8:
-        case TextureFormat::R16F:
-        case TextureFormat::RG8:
-        case TextureFormat::RGB565:
-        case TextureFormat::RGB5_A1:
-        case TextureFormat::RGBA4:
-        case TextureFormat::R32F:
-        case TextureFormat::RGB8:
-        case TextureFormat::SRGB8:
-        case TextureFormat::RG16F:
-        case TextureFormat::R11F_G11F_B10F:
-        case TextureFormat::RGB9_E5:
-        case TextureFormat::RGBA8:
-        case TextureFormat::SRGB8_A8:
-        case TextureFormat::RGB10_A2:
-        case TextureFormat::RGB16F:
-        case TextureFormat::RG32F:
-        case TextureFormat::RGBA16F:
-        case TextureFormat::RGB32F:
-        case TextureFormat::RGBA32F:
-            return TextureType::FLOAT;
-
-        case TextureFormat::R8_SNORM:
-        case TextureFormat::RG8_SNORM:
-        case TextureFormat::RGB8_SNORM:
-        case TextureFormat::RGBA8_SNORM:
-            // SNORM are treated as float
-            return TextureType::FLOAT;
-
-        case TextureFormat::R8UI:
-        case TextureFormat::R16UI:
-        case TextureFormat::RG8UI:
-        case TextureFormat::RGB8UI:
-        case TextureFormat::R32UI:
-        case TextureFormat::RG16UI:
-        case TextureFormat::RGBA8UI:
-        case TextureFormat::RGB16UI:
-        case TextureFormat::RG32UI:
-        case TextureFormat::RGBA16UI:
-        case TextureFormat::RGB32UI:
-        case TextureFormat::RGBA32UI:
-            return TextureType::UINT;
-
-        case TextureFormat::R8I:
-        case TextureFormat::R16I:
-        case TextureFormat::RG8I:
-        case TextureFormat::RGB8I:
-        case TextureFormat::R32I:
-        case TextureFormat::RG16I:
-        case TextureFormat::RGBA8I:
-        case TextureFormat::RGB16I:
-        case TextureFormat::RG32I:
-        case TextureFormat::RGBA16I:
-        case TextureFormat::RGB32I:
-        case TextureFormat::RGBA32I:
-            return TextureType::INT;
-
-        case TextureFormat::DEPTH16:
-        case TextureFormat::DEPTH24:
-        case TextureFormat::DEPTH32F:
-            return TextureType::DEPTH;
-
-        case TextureFormat::STENCIL8:
-            return TextureType::STENCIL;
-
-        case TextureFormat::DEPTH24_STENCIL8:
-        case TextureFormat::DEPTH32F_STENCIL8:
-            return TextureType::DEPTH_STENCIL;
-
-        // Compressed formats ---------------------------------------------------------------------
-
-        case TextureFormat::EAC_RG11:
-        case TextureFormat::EAC_RG11_SIGNED:
-        case TextureFormat::ETC2_EAC_RGBA8:
-        case TextureFormat::ETC2_EAC_SRGBA8:
-        case TextureFormat::EAC_R11:
-        case TextureFormat::EAC_R11_SIGNED:
-        case TextureFormat::ETC2_RGB8:
-        case TextureFormat::ETC2_SRGB8:
-        case TextureFormat::ETC2_RGB8_A1:
-        case TextureFormat::ETC2_SRGB8_A1:
-        case TextureFormat::DXT1_RGB:
-        case TextureFormat::DXT1_RGBA:
-        case TextureFormat::DXT1_SRGB:
-        case TextureFormat::DXT1_SRGBA:
-        case TextureFormat::DXT3_RGBA:
-        case TextureFormat::DXT3_SRGBA:
-        case TextureFormat::DXT5_RGBA:
-        case TextureFormat::DXT5_SRGBA:
-        case TextureFormat::RED_RGTC1:
-        case TextureFormat::SIGNED_RED_RGTC1:
-        case TextureFormat::RED_GREEN_RGTC2:
-        case TextureFormat::SIGNED_RED_GREEN_RGTC2:
-        case TextureFormat::RGB_BPTC_SIGNED_FLOAT:
-        case TextureFormat::RGB_BPTC_UNSIGNED_FLOAT:
-        case TextureFormat::RGBA_BPTC_UNORM:
-        case TextureFormat::SRGB_ALPHA_BPTC_UNORM:
-        case TextureFormat::RGBA_ASTC_4x4:
-        case TextureFormat::RGBA_ASTC_5x4:
-        case TextureFormat::RGBA_ASTC_5x5:
-        case TextureFormat::RGBA_ASTC_6x5:
-        case TextureFormat::RGBA_ASTC_6x6:
-        case TextureFormat::RGBA_ASTC_8x5:
-        case TextureFormat::RGBA_ASTC_8x6:
-        case TextureFormat::RGBA_ASTC_8x8:
-        case TextureFormat::RGBA_ASTC_10x5:
-        case TextureFormat::RGBA_ASTC_10x6:
-        case TextureFormat::RGBA_ASTC_10x8:
-        case TextureFormat::RGBA_ASTC_10x10:
-        case TextureFormat::RGBA_ASTC_12x10:
-        case TextureFormat::RGBA_ASTC_12x12:
-        case TextureFormat::SRGB8_ALPHA8_ASTC_4x4:
-        case TextureFormat::SRGB8_ALPHA8_ASTC_5x4:
-        case TextureFormat::SRGB8_ALPHA8_ASTC_5x5:
-        case TextureFormat::SRGB8_ALPHA8_ASTC_6x5:
-        case TextureFormat::SRGB8_ALPHA8_ASTC_6x6:
-        case TextureFormat::SRGB8_ALPHA8_ASTC_8x5:
-        case TextureFormat::SRGB8_ALPHA8_ASTC_8x6:
-        case TextureFormat::SRGB8_ALPHA8_ASTC_8x8:
-        case TextureFormat::SRGB8_ALPHA8_ASTC_10x5:
-        case TextureFormat::SRGB8_ALPHA8_ASTC_10x6:
-        case TextureFormat::SRGB8_ALPHA8_ASTC_10x8:
-        case TextureFormat::SRGB8_ALPHA8_ASTC_10x10:
-        case TextureFormat::SRGB8_ALPHA8_ASTC_12x10:
-        case TextureFormat::SRGB8_ALPHA8_ASTC_12x12:
-            return TextureType::FLOAT;
-    }
-
-    return TextureType::FLOAT;
-}
-
 size_t getFormatComponentCount(TextureFormat format) noexcept {
     switch (format) {
         case TextureFormat::R8:

filament/backend/src/CircularBuffer.cpp

@@ -65,7 +65,7 @@ CircularBuffer::~CircularBuffer() noexcept {
 // to each others and a special case in circularize()
 
 UTILS_NOINLINE
-void* CircularBuffer::alloc(size_t size) {
+void* CircularBuffer::alloc(size_t size) noexcept {
 #if HAS_MMAP
     void* data = nullptr;
     void* vaddr = MAP_FAILED;

filament/backend/src/CommandBufferQueue.cpp

@@ -18,13 +18,12 @@
 #include "private/backend/CircularBuffer.h"
 #include "private/backend/CommandStream.h"
 
-#include <private/utils/Tracing.h>
-
 #include <utils/compiler.h>
 #include <utils/Log.h>
 #include <utils/Mutex.h>
 #include <utils/ostream.h>
 #include <utils/Panic.h>
+#include <utils/Systrace.h>
 #include <utils/debug.h>
 
 #include <algorithm>
@@ -53,18 +52,18 @@ CommandBufferQueue::~CommandBufferQueue() {
 }
 
 void CommandBufferQueue::requestExit() {
-    std::lock_guard const lock(mLock);
+    std::lock_guard<utils::Mutex> const lock(mLock);
     mExitRequested = EXIT_REQUESTED;
     mCondition.notify_one();
 }
 
 bool CommandBufferQueue::isPaused() const noexcept {
-    std::lock_guard const lock(mLock);
+    std::lock_guard<utils::Mutex> const lock(mLock);
     return mPaused;
 }
 
 void CommandBufferQueue::setPaused(bool paused) {
-    std::lock_guard const lock(mLock);
+    std::lock_guard<utils::Mutex> const lock(mLock);
     if (paused) {
         mPaused = true;
     } else {
@@ -74,13 +73,13 @@ void CommandBufferQueue::setPaused(bool paused) {
 }
 
 bool CommandBufferQueue::isExitRequested() const {
-    std::lock_guard const lock(mLock);
-    return bool(mExitRequested);
+    std::lock_guard<utils::Mutex> const lock(mLock);
+    return (bool)mExitRequested;
 }
 
 
-void CommandBufferQueue::flush() {
-    FILAMENT_TRACING_CALL(FILAMENT_TRACING_CATEGORY_FILAMENT);
+void CommandBufferQueue::flush() noexcept {
+    SYSTRACE_CALL();
 
     CircularBuffer& circularBuffer = mCircularBuffer;
     if (circularBuffer.empty()) {
@@ -103,7 +102,7 @@ void CommandBufferQueue::flush() {
             static_cast<char const*>(begin), static_cast<char const*>(end));
 
 
-    std::unique_lock lock(mLock);
+    std::unique_lock<utils::Mutex> lock(mLock);
 
     // circular buffer is too small, we corrupted the stream
     FILAMENT_CHECK_POSTCONDITION(used <= mFreeSpace) <<
@@ -130,7 +129,7 @@ void CommandBufferQueue::flush() {
         mHighWatermark = std::max(mHighWatermark, totalUsed);
 #endif
 
-        FILAMENT_TRACING_NAME(FILAMENT_TRACING_CATEGORY_FILAMENT, "waiting: CircularBuffer::flush()");
+        SYSTRACE_NAME("waiting: CircularBuffer::flush()");
 
         FILAMENT_CHECK_POSTCONDITION(!mPaused) <<
                 "CommandStream is full, but since the rendering thread is paused, "
@@ -147,7 +146,7 @@ std::vector<CommandBufferQueue::Range> CommandBufferQueue::waitForCommands() con
     if (!UTILS_HAS_THREADING) {
         return std::move(mCommandBuffersToExecute);
     }
-    std::unique_lock lock(mLock);
+    std::unique_lock<utils::Mutex> lock(mLock);
     while ((mCommandBuffersToExecute.empty() || mPaused) && !mExitRequested) {
         mCondition.wait(lock);
     }
@@ -157,7 +156,7 @@ std::vector<CommandBufferQueue::Range> CommandBufferQueue::waitForCommands() con
 void CommandBufferQueue::releaseBuffer(CommandBufferQueue::Range const& buffer) {
     size_t const used = std::distance(
             static_cast<char const*>(buffer.begin), static_cast<char const*>(buffer.end));
-    std::lock_guard const lock(mLock);
+    std::lock_guard<utils::Mutex> const lock(mLock);
     mFreeSpace += used;
     mCondition.notify_one();
 }

filament/backend/src/CommandStream.cpp

@@ -16,8 +16,6 @@
 
 #include "private/backend/CommandStream.h"
 
-#include <private/utils/Tracing.h>
-
 #if DEBUG_COMMAND_STREAM
 #include <utils/CallStack.h>
 #endif
@@ -26,6 +24,7 @@
 #include <utils/Log.h>
 #include <utils/ostream.h>
 #include <utils/Profiler.h>
+#include <utils/Systrace.h>
 
 #include <cstddef>
 #include <functional>
@@ -80,13 +79,12 @@ CommandStream::CommandStream(Driver& driver, CircularBuffer& buffer) noexcept
 }
 
 void CommandStream::execute(void* buffer) {
-    // NOTE: we can't use FILAMENT_TRACING_CALL() or similar here because, execute() below, also
+    // NOTE: we can't use SYSTRACE_CALL() or similar here because, execute() below, also
     // uses systrace BEGIN/END and the END is not guaranteed to be happening in this scope.
 
     Profiler profiler;
 
-
-    if constexpr (FILAMENT_TRACING_ENABLED) {
+    if (SYSTRACE_TAG) {
         if (UTILS_UNLIKELY(mUsePerformanceCounter)) {
             // we want to remove all this when tracing is completely disabled
             profiler.resetEvents(Profiler::EV_CPU_CYCLES  | Profiler::EV_BPU_MISSES);
@@ -102,17 +100,17 @@ void CommandStream::execute(void* buffer) {
         }
     });
 
-    if constexpr (FILAMENT_TRACING_ENABLED) {
+    if (SYSTRACE_TAG) {
         if (UTILS_UNLIKELY(mUsePerformanceCounter)) {
             // we want to remove all this when tracing is completely disabled
             profiler.stop();
             UTILS_UNUSED Profiler::Counters const counters = profiler.readCounters();
-            FILAMENT_TRACING_CONTEXT(FILAMENT_TRACING_CATEGORY_FILAMENT);
-            FILAMENT_TRACING_VALUE(FILAMENT_TRACING_CATEGORY_FILAMENT, "GLThread (I)", counters.getInstructions());
-            FILAMENT_TRACING_VALUE(FILAMENT_TRACING_CATEGORY_FILAMENT, "GLThread (C)", counters.getCpuCycles());
-            FILAMENT_TRACING_VALUE(FILAMENT_TRACING_CATEGORY_FILAMENT, "GLThread (CPI x10)", counters.getCPI() * 10);
-            FILAMENT_TRACING_VALUE(FILAMENT_TRACING_CATEGORY_FILAMENT, "GLThread (BPU miss)", counters.getBranchMisses());
-            FILAMENT_TRACING_VALUE(FILAMENT_TRACING_CATEGORY_FILAMENT, "GLThread (I / BPU miss)",
+            SYSTRACE_CONTEXT();
+            SYSTRACE_VALUE32("GLThread (I)", counters.getInstructions());
+            SYSTRACE_VALUE32("GLThread (C)", counters.getCpuCycles());
+            SYSTRACE_VALUE32("GLThread (CPI x10)", counters.getCPI() * 10);
+            SYSTRACE_VALUE32("GLThread (BPU miss)", counters.getBranchMisses());
+            SYSTRACE_VALUE32("GLThread (I / BPU miss)",
                     counters.getInstructions() / counters.getBranchMisses());
         }
     }

filament/backend/src/CommandStreamDispatcher.h

@@ -20,9 +20,8 @@
 #include "private/backend/Driver.h"
 #include "private/backend/CommandStream.h"
 
-#include <private/utils/Tracing.h>
-
 #include <utils/compiler.h>
+#include <utils/Systrace.h>
 
 #include <utility>
 
@@ -39,7 +38,7 @@
 #if DEBUG_LEVEL == DEBUG_LEVEL_NONE
 #   define SYSTRACE()
 #elif DEBUG_LEVEL == DEBUG_LEVEL_SYSTRACE
-#   define SYSTRACE() FILAMENT_TRACING_CALL(FILAMENT_TRACING_CATEGORY_FILAMENT);
+#   define SYSTRACE() SYSTRACE_CALL();
 #else
 #   error "invalid debug level"
 #endif

filament/backend/src/CompilerThreadPool.cpp

@@ -16,7 +16,7 @@
 
 #include "CompilerThreadPool.h"
 
-#include <private/utils/Tracing.h>
+#include <utils/Systrace.h>
 
 #include <memory>
 
@@ -41,7 +41,7 @@ void CompilerThreadPool::init(uint32_t threadCount,
 
     for (size_t i = 0; i < threadCount; i++) {
         mCompilerThreads.emplace_back([this, setup, cleanup]() {
-            FILAMENT_TRACING_CONTEXT(FILAMENT_TRACING_CATEGORY_FILAMENT);
+            SYSTRACE_CONTEXT();
 
             (*setup)();
 
@@ -54,7 +54,7 @@ void CompilerThreadPool::init(uint32_t threadCount,
                                     [](auto&& q) { return q.empty(); }));
                 });
 
-                FILAMENT_TRACING_VALUE(FILAMENT_TRACING_CATEGORY_FILAMENT, "CompilerThreadPool Jobs",
+                SYSTRACE_VALUE32("CompilerThreadPool Jobs",
                         mQueues[0].size() + mQueues[1].size());
 
                 if (UTILS_LIKELY(!mExitRequested)) {

filament/backend/src/Driver.cpp

@@ -23,12 +23,11 @@
 #include <backend/BufferDescriptor.h>
 #include <backend/DriverEnums.h>
 
-#include <private/utils/Tracing.h>
-
 #include <utils/compiler.h>
 #include <utils/debug.h>
 #include <utils/Log.h>
 #include <utils/ostream.h>
+#include <utils/Systrace.h>
 
 #include <math/half.h>
 #include <math/vec2.h>
@@ -152,31 +151,30 @@ void DriverBase::debugCommandBegin(CommandStream* cmds, bool synchronous, const
             utils::slog.d << methodName << utils::io::endl;
         }
         if constexpr (bool(FILAMENT_DEBUG_COMMANDS & FILAMENT_DEBUG_COMMANDS_SYSTRACE)) {
-            FILAMENT_TRACING_CONTEXT(FILAMENT_TRACING_CATEGORY_FILAMENT);
-            FILAMENT_TRACING_NAME_BEGIN(FILAMENT_TRACING_CATEGORY_FILAMENT, methodName);
+            SYSTRACE_CONTEXT();
+            SYSTRACE_NAME_BEGIN(methodName);
 
             if (!synchronous) {
                 cmds->queueCommand([=]() {
-                    FILAMENT_TRACING_CONTEXT(FILAMENT_TRACING_CATEGORY_FILAMENT);
-                    FILAMENT_TRACING_NAME_BEGIN(FILAMENT_TRACING_CATEGORY_FILAMENT, methodName);
+                    SYSTRACE_CONTEXT();
+                    SYSTRACE_NAME_BEGIN(methodName);
                 });
             }
         }
     }
 }
 
-void DriverBase::debugCommandEnd(CommandStream* cmds, bool synchronous,
-        const char* methodName) noexcept {
+void DriverBase::debugCommandEnd(CommandStream* cmds, bool synchronous, const char* methodName) noexcept {
     if constexpr (bool(FILAMENT_DEBUG_COMMANDS > FILAMENT_DEBUG_COMMANDS_NONE)) {
         if constexpr (bool(FILAMENT_DEBUG_COMMANDS & FILAMENT_DEBUG_COMMANDS_SYSTRACE)) {
             if (!synchronous) {
                 cmds->queueCommand([]() {
-                    FILAMENT_TRACING_CONTEXT(FILAMENT_TRACING_CATEGORY_FILAMENT);
-                    FILAMENT_TRACING_NAME_END(FILAMENT_TRACING_CATEGORY_FILAMENT);
+                    SYSTRACE_CONTEXT();
+                    SYSTRACE_NAME_END();
                 });
             }
-            FILAMENT_TRACING_CONTEXT(FILAMENT_TRACING_CATEGORY_FILAMENT);
-            FILAMENT_TRACING_NAME_END(FILAMENT_TRACING_CATEGORY_FILAMENT);
+            SYSTRACE_CONTEXT();
+            SYSTRACE_NAME_END();
         }
     }
 }

filament/backend/src/Platform.cpp

@@ -17,7 +17,6 @@
 #include <backend/Platform.h>
 
 #include <utils/compiler.h>
-#include <utils/ostream.h>
 
 #include <atomic>
 #include <utility>

filament/backend/src/PlatformFactory.cpp

@@ -16,8 +16,7 @@
 
 #include <private/backend/PlatformFactory.h>
 
-#include <private/utils/Tracing.h>
-
+#include <utils/Systrace.h>
 #include <utils/debug.h>
 
 // We need to keep this up top for the linux (X11) name collisions.
@@ -86,7 +85,7 @@ namespace filament::backend {
 // responsible for destroying it. Initialization of the backend API is deferred until
 // createDriver(). The passed-in backend hint is replaced with the resolved backend.
 Platform* PlatformFactory::create(Backend* backend) noexcept {
-    FILAMENT_TRACING_CALL(FILAMENT_TRACING_CATEGORY_FILAMENT);
+    SYSTRACE_CALL();
     assert_invariant(backend);
 
 #if defined(__ANDROID__)

filament/backend/src/SystraceProfile.h

@@ -17,7 +17,7 @@
 #ifndef TNT_FILAMENT_BACKEND_SYSTRACEPROFILE_H
 #define TNT_FILAMENT_BACKEND_SYSTRACEPROFILE_H
 
-#include <private/utils/Tracing.h>
+#include <utils/Systrace.h>
 
 #define PROFILE_SCOPE(marker)       SYSTRACE_NAME(marker)
 

filament/backend/src/VirtualMachineEnv.cpp

@@ -50,7 +50,7 @@ JavaVM* VirtualMachineEnv::getVirtualMachine() {
  */
 UTILS_PUBLIC
 UTILS_NOINLINE
-jint VirtualMachineEnv::JNI_OnLoad(JavaVM* vm) {
+jint VirtualMachineEnv::JNI_OnLoad(JavaVM* vm) noexcept {
     std::lock_guard const lock(sLock);
     if (sVirtualMachine) {
         // It doesn't make sense for JNI_OnLoad() to be called more than once
@@ -77,7 +77,7 @@ VirtualMachineEnv& VirtualMachineEnv::get() noexcept {
 }
 
 UTILS_NOINLINE
-JNIEnv* VirtualMachineEnv::getThreadEnvironment() {
+JNIEnv* VirtualMachineEnv::getThreadEnvironment() noexcept {
     JavaVM* const vm = getVirtualMachine();
     JNIEnv* env = nullptr;
     jint const result = vm->GetEnv(reinterpret_cast<void**>(&env), JNI_VERSION_1_6);
@@ -101,7 +101,7 @@ VirtualMachineEnv::~VirtualMachineEnv() noexcept {
 }
 
 UTILS_NOINLINE
-JNIEnv* VirtualMachineEnv::getEnvironmentSlow() {
+JNIEnv* VirtualMachineEnv::getEnvironmentSlow() noexcept {
     FILAMENT_CHECK_PRECONDITION(mVirtualMachine)
             << "JNI_OnLoad() has not been called";
 

filament/backend/src/metal/MetalBuffer.mm

@@ -19,8 +19,6 @@
 
 #include "MetalContext.h"
 
-#include <utils/Panic.h>
-
 namespace filament {
 namespace backend {
 

filament/backend/src/metal/MetalDriver.mm

@@ -672,8 +672,22 @@ void MetalDriver::createTimerQueryR(Handle<HwTimerQuery> tqh, int) {
     // nothing to do, timer query was constructed in createTimerQueryS
 }
 
-UTILS_UNUSED
-static const char* toString(ShaderStageFlags flags) {
+const char* toString(DescriptorType type) {
+    switch (type) {
+        case DescriptorType::UNIFORM_BUFFER:
+            return "UNIFORM_BUFFER";
+        case DescriptorType::SHADER_STORAGE_BUFFER:
+            return "SHADER_STORAGE_BUFFER";
+        case DescriptorType::SAMPLER:
+            return "SAMPLER";
+        case DescriptorType::INPUT_ATTACHMENT:
+            return "INPUT_ATTACHMENT";
+        case DescriptorType::SAMPLER_EXTERNAL:
+            return "SAMPLER_EXTERNAL";
+    }
+}
+
+const char* toString(ShaderStageFlags flags) {
     std::vector<const char*> stages;
     if (any(flags & ShaderStageFlags::VERTEX)) {
         stages.push_back("VERTEX");
@@ -707,25 +721,15 @@ const char* toString(DescriptorFlags flags) {
 
 void MetalDriver::createDescriptorSetLayoutR(
         Handle<HwDescriptorSetLayout> dslh, DescriptorSetLayout&& info) {
-#if FILAMENT_METAL_DEBUG_LOG == 1
-    const char* labelStr = "";
-    std::visit([&labelStr](auto&& arg) {
-        using T = std::decay_t<decltype(arg)>;
-        if constexpr (std::is_same_v<T, utils::CString> || std::is_same_v<T, utils::StaticString>) {
-            labelStr = arg.c_str();
-        }
-    }, info.label);
     std::sort(info.bindings.begin(), info.bindings.end(),
             [](const auto& a, const auto& b) { return a.binding < b.binding; });
-    DEBUG_LOG("createDescriptorSetLayoutR(dslh = %d, info = { label = %s,\n", dslh.getId(),
-            labelStr);
+    DEBUG_LOG("createDescriptorSetLayoutR(dslh = %d, info = {\n", dslh.getId());
     for (size_t i = 0; i < info.bindings.size(); i++) {
         DEBUG_LOG("    {binding = %d, type = %s, count = %d, stage = %s, flags = %s},\n",
                 info.bindings[i].binding, toString(info.bindings[i].type), info.bindings[i].count,
                 toString(info.bindings[i].stageFlags), toString(info.bindings[i].flags));
     }
     DEBUG_LOG("})\n");
-#endif
     construct_handle<MetalDescriptorSetLayout>(dslh, std::move(info));
 }
 

filament/backend/src/metal/MetalHandles.mm

@@ -1356,31 +1356,7 @@ id<MTLArgumentEncoder> MetalDescriptorSetLayout::getArgumentEncoderSlow(id<MTLDe
                 [arguments addObject:bufferArgument];
                 break;
             }
-            case DescriptorType::SAMPLER_2D_FLOAT:
-            case DescriptorType::SAMPLER_2D_INT:
-            case DescriptorType::SAMPLER_2D_UINT:
-            case DescriptorType::SAMPLER_2D_DEPTH:
-            case DescriptorType::SAMPLER_2D_ARRAY_FLOAT:
-            case DescriptorType::SAMPLER_2D_ARRAY_INT:
-            case DescriptorType::SAMPLER_2D_ARRAY_UINT:
-            case DescriptorType::SAMPLER_2D_ARRAY_DEPTH:
-            case DescriptorType::SAMPLER_CUBE_FLOAT:
-            case DescriptorType::SAMPLER_CUBE_INT:
-            case DescriptorType::SAMPLER_CUBE_UINT:
-            case DescriptorType::SAMPLER_CUBE_DEPTH:
-            case DescriptorType::SAMPLER_CUBE_ARRAY_FLOAT:
-            case DescriptorType::SAMPLER_CUBE_ARRAY_INT:
-            case DescriptorType::SAMPLER_CUBE_ARRAY_UINT:
-            case DescriptorType::SAMPLER_CUBE_ARRAY_DEPTH:
-            case DescriptorType::SAMPLER_3D_FLOAT:
-            case DescriptorType::SAMPLER_3D_INT:
-            case DescriptorType::SAMPLER_3D_UINT:
-            case DescriptorType::SAMPLER_2D_MS_FLOAT:
-            case DescriptorType::SAMPLER_2D_MS_INT:
-            case DescriptorType::SAMPLER_2D_MS_UINT:
-            case DescriptorType::SAMPLER_2D_MS_ARRAY_FLOAT:
-            case DescriptorType::SAMPLER_2D_MS_ARRAY_INT:
-            case DescriptorType::SAMPLER_2D_MS_ARRAY_UINT:
+            case DescriptorType::SAMPLER:
             case DescriptorType::SAMPLER_EXTERNAL: {
                 MTLArgumentDescriptor* textureArgument = [MTLArgumentDescriptor argumentDescriptor];
                 textureArgument.index = binding.binding * 2;
@@ -1406,9 +1382,6 @@ id<MTLArgumentEncoder> MetalDescriptorSetLayout::getArgumentEncoderSlow(id<MTLDe
                 break;
         }
     }
-    if (arguments.count == 0) {
-        return nil;
-    }
     return [device newArgumentEncoderWithArguments:arguments];
 }
 
@@ -1469,9 +1442,6 @@ id<MTLBuffer> MetalDescriptorSet::finalizeAndGetBuffer(MetalDriver* driver, Shad
 
     id<MTLArgumentEncoder> encoder =
             layout->getArgumentEncoder(context.device, stage, textureTypes);
-    if (!encoder) {
-        return nil;
-    }
 
     {
         ScopedAllocationTimer timer("descriptor_set");
@@ -1502,31 +1472,7 @@ id<MTLBuffer> MetalDescriptorSet::finalizeAndGetBuffer(MetalDriver* driver, Shad
                            atIndex:binding.binding * 2];
                 break;
             }
-            case DescriptorType::SAMPLER_2D_FLOAT:
-            case DescriptorType::SAMPLER_2D_INT:
-            case DescriptorType::SAMPLER_2D_UINT:
-            case DescriptorType::SAMPLER_2D_DEPTH:
-            case DescriptorType::SAMPLER_2D_ARRAY_FLOAT:
-            case DescriptorType::SAMPLER_2D_ARRAY_INT:
-            case DescriptorType::SAMPLER_2D_ARRAY_UINT:
-            case DescriptorType::SAMPLER_2D_ARRAY_DEPTH:
-            case DescriptorType::SAMPLER_CUBE_FLOAT:
-            case DescriptorType::SAMPLER_CUBE_INT:
-            case DescriptorType::SAMPLER_CUBE_UINT:
-            case DescriptorType::SAMPLER_CUBE_DEPTH:
-            case DescriptorType::SAMPLER_CUBE_ARRAY_FLOAT:
-            case DescriptorType::SAMPLER_CUBE_ARRAY_INT:
-            case DescriptorType::SAMPLER_CUBE_ARRAY_UINT:
-            case DescriptorType::SAMPLER_CUBE_ARRAY_DEPTH:
-            case DescriptorType::SAMPLER_3D_FLOAT:
-            case DescriptorType::SAMPLER_3D_INT:
-            case DescriptorType::SAMPLER_3D_UINT:
-            case DescriptorType::SAMPLER_2D_MS_FLOAT:
-            case DescriptorType::SAMPLER_2D_MS_INT:
-            case DescriptorType::SAMPLER_2D_MS_UINT:
-            case DescriptorType::SAMPLER_2D_MS_ARRAY_FLOAT:
-            case DescriptorType::SAMPLER_2D_MS_ARRAY_INT:
-            case DescriptorType::SAMPLER_2D_MS_ARRAY_UINT:
+            case DescriptorType::SAMPLER:
             case DescriptorType::SAMPLER_EXTERNAL: {
                 auto found = textures.find(binding.binding);
                 if (found == textures.end()) {

filament/backend/src/metal/MetalState.h

@@ -20,18 +20,17 @@
 #include <Metal/Metal.h>
 
 #include "private/backend/Driver.h"
+#include "backend/Program.h"
 
 #include <backend/DriverEnums.h>
-#include <backend/Program.h>
 
-#include <utils/bitset.h>
 #include <utils/FixedCapacityVector.h>
-#include <utils/Hash.h>
-#include <utils/Invocable.h>
-
-#include <tsl/robin_map.h>
 
 #include <memory>
+#include <tsl/robin_map.h>
+
+#include <utils/Hash.h>
+#include <utils/Invocable.h>
 
 namespace filament {
 namespace backend {

filament/backend/src/metal/PlatformMetal.mm

@@ -24,22 +24,14 @@
 #import <Foundation/Foundation.h>
 
 #include <atomic>
-#include <mutex>
 
 namespace filament::backend {
 
 struct PlatformMetalImpl {
-    std::mutex mLock;   // locks mDevice and mCommandQueue
-    id<MTLDevice> mDevice = nil;
     id<MTLCommandQueue> mCommandQueue = nil;
-
     // read form driver thread, read/written to from client thread
     std::atomic<PlatformMetal::DrawableFailureBehavior> mDrawableFailureBehavior =
             PlatformMetal::DrawableFailureBehavior::PANIC;
-
-    // These methods must be called with mLock held
-    void createDeviceImpl(MetalDevice& outDevice);
-    void createCommandQueueImpl(MetalDevice& device, MetalCommandQueue& outCommandQueue);
 };
 
 Platform* createDefaultMetalPlatform() {
@@ -56,59 +48,7 @@ Driver* PlatformMetal::createDriver(void* /*sharedContext*/, const Platform::Dri
     return MetalDriverFactory::create(this, driverConfig);
 }
 
-
-bool PlatformMetal::initialize() noexcept {
-    std::lock_guard<std::mutex> lock(pImpl->mLock);
-
-    MetalDevice device{};
-    pImpl->createDeviceImpl(device);
-    if (device.device == nil) {
-        return false;
-    }
-
-    MetalCommandQueue commandQueue{};
-    pImpl->createCommandQueueImpl(device, commandQueue);
-    if (commandQueue.commandQueue == nil) {
-        return false;
-    }
-
-    return true;
-}
-
 void PlatformMetal::createDevice(MetalDevice& outDevice) noexcept {
-    std::lock_guard<std::mutex> lock(pImpl->mLock);
-    pImpl->createDeviceImpl(outDevice);
-}
-
-void PlatformMetal::createCommandQueue(
-        MetalDevice& device, MetalCommandQueue& outCommandQueue) noexcept {
-    std::lock_guard<std::mutex> lock(pImpl->mLock);
-    pImpl->createCommandQueueImpl(device, outCommandQueue);
-}
-
-void PlatformMetal::createAndEnqueueCommandBuffer(MetalCommandBuffer& outCommandBuffer) noexcept {
-    std::lock_guard<std::mutex> lock(pImpl->mLock);
-    id<MTLCommandBuffer> commandBuffer = [pImpl->mCommandQueue commandBuffer];
-    [commandBuffer enqueue];
-    outCommandBuffer.commandBuffer = commandBuffer;
-}
-
-void PlatformMetal::setDrawableFailureBehavior(DrawableFailureBehavior behavior) noexcept {
-    pImpl->mDrawableFailureBehavior = behavior;
-}
-
-PlatformMetal::DrawableFailureBehavior PlatformMetal::getDrawableFailureBehavior() const noexcept {
-    return pImpl->mDrawableFailureBehavior;
-}
-
-// -------------------------------------------------------------------------------------------------
-
-void PlatformMetalImpl::createDeviceImpl(MetalDevice& outDevice) {
-    if (mDevice) {
-        outDevice.device = mDevice;
-        return;
-    }
-
     id<MTLDevice> result;
 
 #if !defined(FILAMENT_IOS)
@@ -134,17 +74,27 @@ void PlatformMetalImpl::createDeviceImpl(MetalDevice& outDevice) {
                   << utils::io::endl;
 
     outDevice.device = result;
-    mDevice = result;
 }
 
-void PlatformMetalImpl::createCommandQueueImpl(MetalDevice& device, MetalCommandQueue& outCommandQueue) {
-    if (mCommandQueue) {
-        outCommandQueue.commandQueue = mCommandQueue;
-        return;
-    }
-    mCommandQueue = [device.device newCommandQueue];
-    mCommandQueue.label = @"Filament";
-    outCommandQueue.commandQueue = mCommandQueue;
+void PlatformMetal::createCommandQueue(
+        MetalDevice& device, MetalCommandQueue& outCommandQueue) noexcept {
+    pImpl->mCommandQueue = [device.device newCommandQueue];
+    pImpl->mCommandQueue.label = @"Filament";
+    outCommandQueue.commandQueue = pImpl->mCommandQueue;
+}
+
+void PlatformMetal::createAndEnqueueCommandBuffer(MetalCommandBuffer& outCommandBuffer) noexcept {
+    id<MTLCommandBuffer> commandBuffer = [pImpl->mCommandQueue commandBuffer];
+    [commandBuffer enqueue];
+    outCommandBuffer.commandBuffer = commandBuffer;
+}
+
+void PlatformMetal::setDrawableFailureBehavior(DrawableFailureBehavior behavior) noexcept {
+    pImpl->mDrawableFailureBehavior = behavior;
+}
+
+PlatformMetal::DrawableFailureBehavior PlatformMetal::getDrawableFailureBehavior() const noexcept {
+    return pImpl->mDrawableFailureBehavior;
 }
 
 } // namespace filament

filament/backend/src/opengl/BindingMap.h

@@ -69,8 +69,9 @@ public:
         assert_invariant(set < MAX_DESCRIPTOR_SET_COUNT);
         assert_invariant(binding < MAX_DESCRIPTOR_COUNT);
         assert_invariant(entry.binding < 128); // we reserve 1 bit for the type right now
-        mStorage[set][binding] = { uint8_t(entry.binding),
-                                   DescriptorSetLayoutBinding::isSampler(entry.type) };
+        mStorage[set][binding] = { (uint8_t)entry.binding,
+                                   entry.type == DescriptorType::SAMPLER ||
+                                   entry.type == DescriptorType::SAMPLER_EXTERNAL };
         mActiveDescriptors[set].set(binding);
     }
 

filament/backend/src/opengl/GLDescriptorSet.cpp

@@ -95,32 +95,7 @@ GLDescriptorSet::GLDescriptorSet(OpenGLContext& gl, DescriptorSetLayoutHandle ds
                 }
                 break;
             }
-
-            case DescriptorType::SAMPLER_2D_FLOAT:
-            case DescriptorType::SAMPLER_2D_INT:
-            case DescriptorType::SAMPLER_2D_UINT:
-            case DescriptorType::SAMPLER_2D_DEPTH:
-            case DescriptorType::SAMPLER_2D_ARRAY_FLOAT:
-            case DescriptorType::SAMPLER_2D_ARRAY_INT:
-            case DescriptorType::SAMPLER_2D_ARRAY_UINT:
-            case DescriptorType::SAMPLER_2D_ARRAY_DEPTH:
-            case DescriptorType::SAMPLER_CUBE_FLOAT:
-            case DescriptorType::SAMPLER_CUBE_INT:
-            case DescriptorType::SAMPLER_CUBE_UINT:
-            case DescriptorType::SAMPLER_CUBE_DEPTH:
-            case DescriptorType::SAMPLER_CUBE_ARRAY_FLOAT:
-            case DescriptorType::SAMPLER_CUBE_ARRAY_INT:
-            case DescriptorType::SAMPLER_CUBE_ARRAY_UINT:
-            case DescriptorType::SAMPLER_CUBE_ARRAY_DEPTH:
-            case DescriptorType::SAMPLER_3D_FLOAT:
-            case DescriptorType::SAMPLER_3D_INT:
-            case DescriptorType::SAMPLER_3D_UINT:
-            case DescriptorType::SAMPLER_2D_MS_FLOAT:
-            case DescriptorType::SAMPLER_2D_MS_INT:
-            case DescriptorType::SAMPLER_2D_MS_UINT:
-            case DescriptorType::SAMPLER_2D_MS_ARRAY_FLOAT:
-            case DescriptorType::SAMPLER_2D_MS_ARRAY_INT:
-            case DescriptorType::SAMPLER_2D_MS_ARRAY_UINT:
+            case DescriptorType::SAMPLER:
             case DescriptorType::SAMPLER_EXTERNAL:
                 if (UTILS_UNLIKELY(gl.isES2())) {
                     desc.emplace<SamplerGLES2>();
@@ -162,11 +137,8 @@ void GLDescriptorSet::update(OpenGLContext&,
     }, descriptors[binding].desc);
 }
 
-void GLDescriptorSet::update(OpenGLContext& gl, HandleAllocatorGL& handleAllocator,
-        descriptor_binding_t binding, TextureHandle th, SamplerParams params) noexcept {
-
-    GLTexture* t = th ? handleAllocator.handle_cast<GLTexture*>(th) : nullptr;
-
+void GLDescriptorSet::update(OpenGLContext& gl,
+        descriptor_binding_t binding, GLTexture* t, SamplerParams params) noexcept {
     assert_invariant(binding < descriptors.size());
     std::visit([=, &gl](auto&& arg) mutable {
         using T = std::decay_t<decltype(arg)>;
@@ -199,12 +171,20 @@ void GLDescriptorSet::update(OpenGLContext& gl, HandleAllocatorGL& handleAllocat
                 }
             }
 
-            arg.handle = th;
+            arg.target = t ? t->gl.target : 0;
+            arg.id = t ? t->gl.id : 0;
+            arg.external = t ? t->gl.external :  false;
             if constexpr (std::is_same_v<T, Sampler> ||
                           std::is_same_v<T, SamplerWithAnisotropyWorkaround>) {
                 if constexpr (std::is_same_v<T, SamplerWithAnisotropyWorkaround>) {
                     arg.anisotropy = float(1u << params.anisotropyLog2);
                 }
+                if (t) {
+                    arg.ref = t->ref;
+                    arg.baseLevel = t->gl.baseLevel;
+                    arg.maxLevel = t->gl.maxLevel;
+                    arg.swizzle = t->gl.swizzle;
+                }
 #ifndef FILAMENT_SILENCE_NOT_SUPPORTED_BY_ES2
                 arg.sampler = gl.getSampler(params);
 #else
@@ -220,39 +200,39 @@ void GLDescriptorSet::update(OpenGLContext& gl, HandleAllocatorGL& handleAllocat
     }, descriptors[binding].desc);
 }
 
+template<typename T>
 void GLDescriptorSet::updateTextureView(OpenGLContext& gl,
-        HandleAllocatorGL& handleAllocator, GLuint unit, GLTexture const* t) noexcept {
+        HandleAllocatorGL& handleAllocator, GLuint unit, T const& desc) noexcept {
     // The common case is that we don't have a ref handle (we only have one if
     // the texture ever had a View on it).
-    assert_invariant(t);
-    assert_invariant(t->ref);
-    GLTextureRef* const ref = handleAllocator.handle_cast<GLTextureRef*>(t->ref);
-    if (UTILS_UNLIKELY((t->gl.baseLevel != ref->baseLevel || t->gl.maxLevel != ref->maxLevel))) {
+    assert_invariant(desc.ref);
+    GLTextureRef* const ref = handleAllocator.handle_cast<GLTextureRef*>(desc.ref);
+    if (UTILS_UNLIKELY((desc.baseLevel != ref->baseLevel || desc.maxLevel != ref->maxLevel))) {
         // If we have views, then it's still uncommon that we'll switch often
         // handle the case where we reset to the original texture
-        GLint baseLevel = GLint(t->gl.baseLevel); // NOLINT(*-signed-char-misuse)
-        GLint maxLevel = GLint(t->gl.maxLevel); // NOLINT(*-signed-char-misuse)
+        GLint baseLevel = GLint(desc.baseLevel); // NOLINT(*-signed-char-misuse)
+        GLint maxLevel = GLint(desc.maxLevel); // NOLINT(*-signed-char-misuse)
         if (baseLevel > maxLevel) {
             baseLevel = 0;
             maxLevel = 1000; // per OpenGL spec
         }
         // that is very unfortunate that we have to call activeTexture here
         gl.activeTexture(unit);
-        glTexParameteri(t->gl.target, GL_TEXTURE_BASE_LEVEL, baseLevel);
-        glTexParameteri(t->gl.target, GL_TEXTURE_MAX_LEVEL,  maxLevel);
-        ref->baseLevel = t->gl.baseLevel;
-        ref->maxLevel = t->gl.maxLevel;
+        glTexParameteri(desc.target, GL_TEXTURE_BASE_LEVEL, baseLevel);
+        glTexParameteri(desc.target, GL_TEXTURE_MAX_LEVEL,  maxLevel);
+        ref->baseLevel = desc.baseLevel;
+        ref->maxLevel = desc.maxLevel;
     }
-    if (UTILS_UNLIKELY(t->gl.swizzle != ref->swizzle)) {
+    if (UTILS_UNLIKELY(desc.swizzle != ref->swizzle)) {
         using namespace GLUtils;
         gl.activeTexture(unit);
 #if !defined(__EMSCRIPTEN__)  && !defined(FILAMENT_SILENCE_NOT_SUPPORTED_BY_ES2)
-        glTexParameteri(t->gl.target, GL_TEXTURE_SWIZZLE_R, (GLint)getSwizzleChannel(t->gl.swizzle[0]));
-        glTexParameteri(t->gl.target, GL_TEXTURE_SWIZZLE_G, (GLint)getSwizzleChannel(t->gl.swizzle[1]));
-        glTexParameteri(t->gl.target, GL_TEXTURE_SWIZZLE_B, (GLint)getSwizzleChannel(t->gl.swizzle[2]));
-        glTexParameteri(t->gl.target, GL_TEXTURE_SWIZZLE_A, (GLint)getSwizzleChannel(t->gl.swizzle[3]));
+        glTexParameteri(desc.target, GL_TEXTURE_SWIZZLE_R, (GLint)getSwizzleChannel(desc.swizzle[0]));
+        glTexParameteri(desc.target, GL_TEXTURE_SWIZZLE_G, (GLint)getSwizzleChannel(desc.swizzle[1]));
+        glTexParameteri(desc.target, GL_TEXTURE_SWIZZLE_B, (GLint)getSwizzleChannel(desc.swizzle[2]));
+        glTexParameteri(desc.target, GL_TEXTURE_SWIZZLE_A, (GLint)getSwizzleChannel(desc.swizzle[3]));
 #endif
-        ref->swizzle = t->gl.swizzle;
+        ref->swizzle = desc.swizzle;
     }
 }
 
@@ -305,31 +285,27 @@ void GLDescriptorSet::bind(
                 }
             } else if constexpr (std::is_same_v<T, Sampler>) {
                 GLuint const unit = p.getTextureUnit(set, binding);
-
-
-                if (arg.handle) {
-                    GLTexture const* const t = handleAllocator.handle_cast<GLTexture*>(arg.handle);
-                    gl.bindTexture(unit, t->gl.target, t->gl.id, t->gl.external);
+                if (arg.target) {
+                    gl.bindTexture(unit, arg.target, arg.id, arg.external);
                     gl.bindSampler(unit, arg.sampler);
-                    if (UTILS_UNLIKELY(t->ref)) {
-                        updateTextureView(gl, handleAllocator, unit, t);
+                    if (UTILS_UNLIKELY(arg.ref)) {
+                        updateTextureView(gl, handleAllocator, unit, arg);
                     }
                 } else {
                     gl.unbindTextureUnit(unit);
                 }
             } else if constexpr (std::is_same_v<T, SamplerWithAnisotropyWorkaround>) {
                 GLuint const unit = p.getTextureUnit(set, binding);
-                if (arg.handle) {
-                    GLTexture const* const t = handleAllocator.handle_cast<GLTexture*>(arg.handle);
-                    gl.bindTexture(unit, t->gl.target, t->gl.id, t->gl.external);
+                if (arg.target) {
+                    gl.bindTexture(unit, arg.target, arg.id, arg.external);
                     gl.bindSampler(unit, arg.sampler);
-                    if (UTILS_UNLIKELY(t->ref)) {
-                        updateTextureView(gl, handleAllocator, unit, t);
+                    if (UTILS_UNLIKELY(arg.ref)) {
+                        updateTextureView(gl, handleAllocator, unit, arg);
                     }
 #if defined(GL_EXT_texture_filter_anisotropic)
                     // Driver claims to support anisotropic filtering, but it fails when set on
                     // the sampler, we have to set it on the texture instead.
-                    glTexParameterf(t->gl.target, GL_TEXTURE_MAX_ANISOTROPY_EXT,
+                    glTexParameterf(arg.target, GL_TEXTURE_MAX_ANISOTROPY_EXT,
                             std::min(gl.gets.max_anisotropy, float(arg.anisotropy)));
 #endif
                 } else {
@@ -338,20 +314,19 @@ void GLDescriptorSet::bind(
             } else if constexpr (std::is_same_v<T, SamplerGLES2>) {
                 // in ES2 the sampler parameters need to be set on the texture itself
                 GLuint const unit = p.getTextureUnit(set, binding);
-                if (arg.handle) {
-                    GLTexture const* const t = handleAllocator.handle_cast<GLTexture*>(arg.handle);
-                    gl.bindTexture(unit, t->gl.target, t->gl.id, t->gl.external);
+                if (arg.target) {
+                    gl.bindTexture(unit, arg.target, arg.id, arg.external);
                     SamplerParams const params = arg.params;
-                    glTexParameteri(t->gl.target, GL_TEXTURE_MIN_FILTER,
+                    glTexParameteri(arg.target, GL_TEXTURE_MIN_FILTER,
                             (GLint)GLUtils::getTextureFilter(params.filterMin));
-                    glTexParameteri(t->gl.target, GL_TEXTURE_MAG_FILTER,
+                    glTexParameteri(arg.target, GL_TEXTURE_MAG_FILTER,
                             (GLint)GLUtils::getTextureFilter(params.filterMag));
-                    glTexParameteri(t->gl.target, GL_TEXTURE_WRAP_S,
+                    glTexParameteri(arg.target, GL_TEXTURE_WRAP_S,
                             (GLint)GLUtils::getWrapMode(params.wrapS));
-                    glTexParameteri(t->gl.target, GL_TEXTURE_WRAP_T,
+                    glTexParameteri(arg.target, GL_TEXTURE_WRAP_T,
                             (GLint)GLUtils::getWrapMode(params.wrapT));
 #if defined(GL_EXT_texture_filter_anisotropic)
-                    glTexParameterf(t->gl.target, GL_TEXTURE_MAX_ANISOTROPY_EXT,
+                    glTexParameterf(arg.target, GL_TEXTURE_MAX_ANISOTROPY_EXT,
                             std::min(gl.gets.max_anisotropy, arg.anisotropy));
 #endif
                 } else {

filament/backend/src/opengl/GLDescriptorSet.h

@@ -59,8 +59,8 @@ struct GLDescriptorSet : public HwDescriptorSet {
             descriptor_binding_t binding, GLBufferObject* bo, size_t offset, size_t size) noexcept;
 
     // update a sampler descriptor in the set
-    void update(OpenGLContext& gl, HandleAllocatorGL& handleAllocator,
-            descriptor_binding_t binding, TextureHandle th, SamplerParams params) noexcept;
+    void update(OpenGLContext& gl,
+            descriptor_binding_t binding, GLTexture* t, SamplerParams params) noexcept;
 
     // conceptually bind the set to the command buffer
     void bind(
@@ -111,19 +111,46 @@ private:
 
     // A sampler descriptor
     struct Sampler {
-        TextureHandle handle;                   // 4
+        uint16_t target;                        // 2 (GLenum)
+        bool external = false;                  // 1
+        bool reserved = false;                  // 1
+        GLuint id = 0;                          // 4
         GLuint sampler = 0;                     // 4
+        Handle<GLTextureRef> ref;               // 4
+        int8_t baseLevel = 0x7f;                // 1
+        int8_t maxLevel = -1;                   // 1
+        std::array<TextureSwizzle, 4> swizzle{  // 4
+                TextureSwizzle::CHANNEL_0,
+                TextureSwizzle::CHANNEL_1,
+                TextureSwizzle::CHANNEL_2,
+                TextureSwizzle::CHANNEL_3
+        };
     };
 
     struct SamplerWithAnisotropyWorkaround {
-        TextureHandle handle;                   // 4
+        uint16_t target;                        // 2 (GLenum)
+        bool external = false;                  // 1
+        bool reserved = false;                  // 1
+        GLuint id = 0;                          // 4
         GLuint sampler = 0;                     // 4
+        Handle<GLTextureRef> ref;               // 4
         math::half anisotropy = 1.0f;           // 2
+        int8_t baseLevel = 0x7f;                // 1
+        int8_t maxLevel = -1;                   // 1
+        std::array<TextureSwizzle, 4> swizzle{  // 4
+                TextureSwizzle::CHANNEL_0,
+                TextureSwizzle::CHANNEL_1,
+                TextureSwizzle::CHANNEL_2,
+                TextureSwizzle::CHANNEL_3
+        };
     };
 
     // A sampler descriptor for ES2
     struct SamplerGLES2 {
-        TextureHandle handle;                   // 4
+        uint16_t target;                        // 2 (GLenum)
+        bool external = false;                  // 1
+        bool reserved = false;                  // 1
+        GLuint id = 0;                          // 4
         SamplerParams params{};                 // 4
         float anisotropy = 1.0f;                // 4
     };
@@ -138,8 +165,9 @@ private:
     };
     static_assert(sizeof(Descriptor) <= 32);
 
+    template<typename T>
     static void updateTextureView(OpenGLContext& gl,
-            HandleAllocatorGL& handleAllocator, GLuint unit, GLTexture const* t) noexcept;
+            HandleAllocatorGL& handleAllocator, GLuint unit, T const& desc) noexcept;
 
     utils::FixedCapacityVector<Descriptor> descriptors;     // 16
     utils::bitset64 dynamicBuffers;                         // 8

filament/backend/src/opengl/OpenGLBlobCache.cpp

@@ -21,7 +21,7 @@
 #include <backend/Platform.h>
 #include <backend/Program.h>
 
-#include <private/utils/Tracing.h>
+#include <utils/Systrace.h>
 
 namespace filament::backend {
 
@@ -36,7 +36,7 @@ OpenGLBlobCache::OpenGLBlobCache(OpenGLContext& gl) noexcept
 
 GLuint OpenGLBlobCache::retrieve(BlobCacheKey* outKey, Platform& platform,
         Program const& program) const noexcept {
-    FILAMENT_TRACING_CALL(FILAMENT_TRACING_CATEGORY_FILAMENT);
+    SYSTRACE_CALL();
     if (!mCachingSupported || !platform.hasRetrieveBlobFunc()) {
         // the key is never updated in that case
         return 0;
@@ -68,7 +68,7 @@ GLuint OpenGLBlobCache::retrieve(BlobCacheKey* outKey, Platform& platform,
         programId = glCreateProgram();
 
         { // scope for systrace
-            FILAMENT_TRACING_NAME(FILAMENT_TRACING_CATEGORY_FILAMENT, "glProgramBinary");
+            SYSTRACE_NAME("glProgramBinary");
             glProgramBinary(programId, blob->format, blob->data, programBinarySize);
         }
 
@@ -90,7 +90,7 @@ GLuint OpenGLBlobCache::retrieve(BlobCacheKey* outKey, Platform& platform,
 
 void OpenGLBlobCache::insert(Platform& platform,
         BlobCacheKey const& key, GLuint program) noexcept {
-    FILAMENT_TRACING_CALL(FILAMENT_TRACING_CATEGORY_FILAMENT);
+    SYSTRACE_CALL();
     if (!mCachingSupported || !platform.hasInsertBlobFunc()) {
         // the key is never updated in that case
         return;
@@ -100,7 +100,7 @@ void OpenGLBlobCache::insert(Platform& platform,
     GLenum format;
     GLint programBinarySize = 0;
     { // scope for systrace
-        FILAMENT_TRACING_NAME(FILAMENT_TRACING_CATEGORY_FILAMENT, "glGetProgramiv");
+        SYSTRACE_NAME("glGetProgramiv");
         glGetProgramiv(program, GL_PROGRAM_BINARY_LENGTH, &programBinarySize);
     }
     if (programBinarySize) {
@@ -108,7 +108,7 @@ void OpenGLBlobCache::insert(Platform& platform,
         std::unique_ptr<Blob, decltype(&::free)> blob{ (Blob*)malloc(size), &::free };
         if (UTILS_LIKELY(blob)) {
             { // scope for systrace
-                FILAMENT_TRACING_NAME(FILAMENT_TRACING_CATEGORY_FILAMENT, "glGetProgramBinary");
+                SYSTRACE_NAME("glGetProgramBinary");
                 glGetProgramBinary(program, programBinarySize,
                         &programBinarySize, &format, blob->data);
             }

filament/backend/src/opengl/OpenGLContext.cpp

@@ -542,13 +542,6 @@ void OpenGLContext::initBugs(Bugs* bugs, Extensions const& exts,
         } else if (strstr(renderer, "Intel")) {
             // Intel GPU
             bugs->vao_doesnt_store_element_array_buffer_binding = true;
-
-            if (strstr(renderer, "Mesa")) {
-                // Mesa Intel driver on Linux/Android
-                // Renderer of the form [Mesa Intel(R) HD Graphics 505 (APL 3)]
-                // b/405252622
-                bugs->disable_invalidate_framebuffer = true;
-            }
         } else if (strstr(renderer, "PowerVR")) {
             // PowerVR GPU
             // On PowerVR (Rogue GE8320) glFlush doesn't seem to do anything, in particular,

filament/backend/src/opengl/OpenGLDriver.cpp

@@ -44,8 +44,6 @@
 #include "private/backend/Dispatcher.h"
 #include "private/backend/DriverApi.h"
 
-#include <private/utils/Tracing.h>
-
 #include <type_traits>
 #include <utils/BitmaskEnum.h>
 #include <utils/FixedCapacityVector.h>
@@ -53,6 +51,7 @@
 #include <utils/Invocable.h>
 #include <utils/Log.h>
 #include <utils/Panic.h>
+#include <utils/Systrace.h>
 #include <utils/Slice.h>
 #include <utils/compiler.h>
 #include <utils/debug.h>
@@ -99,13 +98,13 @@
 
 #define DEBUG_GROUP_MARKER_NONE       0x00    // no debug marker
 #define DEBUG_GROUP_MARKER_OPENGL     0x01    // markers in the gl command queue (req. driver support)
-#define DEBUG_GROUP_MARKER_BACKEND    0x02    // markers on the backend side (perfetto)
+#define DEBUG_GROUP_MARKER_BACKEND    0x02    // markers on the backend side (systrace)
 #define DEBUG_GROUP_MARKER_ALL        0xFF    // all markers
 
 #define DEBUG_MARKER_NONE             0x00    // no debug marker
 #define DEBUG_MARKER_OPENGL           0x01    // markers in the gl command queue (req. driver support)
-#define DEBUG_MARKER_BACKEND          0x02    // markers on the backend side (perfetto)
-#define DEBUG_MARKER_PROFILE          0x04    // profiling on the backend side (perfetto)
+#define DEBUG_MARKER_BACKEND          0x02    // markers on the backend side (systrace)
+#define DEBUG_MARKER_PROFILE          0x04    // profiling on the backend side (systrace)
 #define DEBUG_MARKER_ALL              (0xFF & ~DEBUG_MARKER_PROFILE) // all markers
 
 // set to the desired debug marker level (for user markers [default: All])
@@ -249,8 +248,8 @@ OpenGLDriver::DebugMarker::DebugMarker(OpenGLDriver& driver, const char* string)
 #endif
 
 #if DEBUG_MARKER_LEVEL & DEBUG_MARKER_BACKEND
-    FILAMENT_TRACING_CONTEXT(FILAMENT_TRACING_CATEGORY_FILAMENT);
-    FILAMENT_TRACING_NAME_BEGIN(FILAMENT_TRACING_CATEGORY_FILAMENT, string);
+    SYSTRACE_CONTEXT();
+    SYSTRACE_NAME_BEGIN(string);
 #endif
 #endif
 }
@@ -266,8 +265,8 @@ OpenGLDriver::DebugMarker::~DebugMarker() noexcept {
 #endif
 
 #if DEBUG_MARKER_LEVEL & DEBUG_MARKER_BACKEND
-    FILAMENT_TRACING_CONTEXT(FILAMENT_TRACING_CATEGORY_FILAMENT);
-    FILAMENT_TRACING_NAME_END(FILAMENT_TRACING_CATEGORY_FILAMENT);
+    SYSTRACE_CONTEXT();
+    SYSTRACE_NAME_END();
 #endif
 #endif
 }
@@ -643,25 +642,6 @@ void OpenGLDriver::createVertexBufferInfoR(
         AttributeArray attributes) {
     DEBUG_MARKER()
     construct<GLVertexBufferInfo>(vbih, bufferCount, attributeCount, attributes);
-
-    // test ----
-    int16_t returned_value = handle_set_value<GLVertexBufferInfo*>(vbih, 90);
-    uint8_t age = (uint8_t) (returned_value >> 8);
-    uint8_t test_value = (returned_value & 0xff);
-    switch (test_value) {
-        case -2:
-        case -1:
-        case 0:
-            utils::slog.w << "@@@ createVertexBufferInfoR: unexpected result, age:" << (int) age
-                          << ", test_value:" << (int) test_value << utils::io::endl;
-            break;
-        default:
-            FILAMENT_CHECK_POSTCONDITION(test_value == 1)
-                    << "@@@ createVertexBufferInfoR: shouldn't happen, age:" << (int) age
-                    << ", test_value:" << (int) test_value << utils::io::endl;
-            break;
-    }
-    //----------
 }
 
 void OpenGLDriver::createVertexBufferR(
@@ -780,25 +760,6 @@ void OpenGLDriver::createProgramR(Handle<HwProgram> ph, Program&& program) {
 
     construct<OpenGLProgram>(ph, *this, std::move(program));
     CHECK_GL_ERROR(utils::slog.e)
-
-    // test ----
-    int16_t returned_value = handle_set_value<OpenGLProgram*>(ph, 100);
-    uint8_t age = (uint8_t) (returned_value >> 8);
-    uint8_t test_value = (returned_value & 0xff);
-    switch (test_value) {
-        case -2:
-        case -1:
-        case 0:
-            utils::slog.w << "@@@ createProgramR: unexpected result, age:" << (int)age << ", test_value:" << (int)test_value
-                          << utils::io::endl;
-            break;
-        default:
-            FILAMENT_CHECK_POSTCONDITION(test_value == 1)
-                    << "@@@ createProgramR: shouldn't happen, age:" << (int)age
-                    << ", test_value:" << (int)test_value << utils::io::endl;
-            break;
-    }
-    //----------
 }
 
 UTILS_NOINLINE
@@ -970,12 +931,7 @@ void OpenGLDriver::createTextureR(Handle<HwTexture> th, SamplerType target, uint
 #if defined(BACKEND_OPENGL_LEVEL_GLES31)
                 if (gl.features.multisample_texture) {
                     // multi-sample texture on GL 3.2 / GLES 3.1 and above
-                    if (depth <= 1) {
-                        // We forcibly change the target to 2D-multisample only for flat texture.
-                        // A depth value greater than 1 may indicate multiview usage, which requires
-                        // GL_TEXTURE_2D_ARRAY. Also 2D MSAA won't work with non-flat texture anyway.
-                        t->gl.target = GL_TEXTURE_2D_MULTISAMPLE;
-                    }
+                    t->gl.target = GL_TEXTURE_2D_MULTISAMPLE;
                 } else {
                     // Turn off multi-sampling for that texture. It's just not supported.
                 }
@@ -1251,12 +1207,7 @@ void OpenGLDriver::importTextureR(Handle<HwTexture> th, intptr_t id,
 #if defined(BACKEND_OPENGL_LEVEL_GLES31)
         if (gl.features.multisample_texture) {
             // multi-sample texture on GL 3.2 / GLES 3.1 and above
-            if (depth <= 1) {
-                // We forcibly change the target to 2D-multisample only for flat texture.
-                // A depth value greater than 1 may indicate multiview usage, which requires
-                // GL_TEXTURE_2D_ARRAY. Also 2D MSAA won't work with non-flat texture anyway.
-                t->gl.target = GL_TEXTURE_2D_MULTISAMPLE;
-            }
+            t->gl.target = GL_TEXTURE_2D_MULTISAMPLE;
         } else {
             // Turn off multi-sampling for that texture. It's just not supported.
         }
@@ -1501,15 +1452,8 @@ void OpenGLDriver::framebufferTexture(TargetBufferInfo const& binfo,
 #if !defined(__EMSCRIPTEN__) && !defined(FILAMENT_IOS)
                 if (layerCount > 1) {
                     // if layerCount > 1, it means we use the multiview extension.
-                    if (rt->gl.samples > 1) {
-                        // For MSAA
-                        glFramebufferTextureMultisampleMultiviewOVR(GL_FRAMEBUFFER, attachment,
-                                t->gl.id, 0, rt->gl.samples, binfo.layer, layerCount);
-                    }
-                    else {
-                        glFramebufferTextureMultiviewOVR(GL_FRAMEBUFFER, attachment, t->gl.id, 0,
-                                binfo.layer, layerCount);
-                    }
+                    glFramebufferTextureMultiviewOVR(GL_FRAMEBUFFER, attachment,
+                        t->gl.id, 0, binfo.layer, layerCount);
                 } else
 #endif // !defined(__EMSCRIPTEN__) && !defined(FILAMENT_IOS)
                 {
@@ -1956,25 +1900,6 @@ void OpenGLDriver::destroyRenderPrimitive(Handle<HwRenderPrimitive> rph) {
 void OpenGLDriver::destroyProgram(Handle<HwProgram> ph) {
     DEBUG_MARKER()
     if (ph) {
-        // test ----
-        int16_t returned_value = handle_set_value<OpenGLProgram*>(ph, 101);
-        uint8_t age = (uint8_t) (returned_value >> 8);
-        uint8_t test_value = (returned_value & 0xff);
-        switch (test_value) {
-            case -2:
-            case -1:
-            case 0:
-                utils::slog.w << "@@@ destroyProgram: unexpected result, age:" << (int) age
-                              << ", test_value:" << (int) test_value << utils::io::endl;
-                break;
-            default:
-                FILAMENT_CHECK_POSTCONDITION(test_value == 1)
-                        << "@@@ destroyProgram: shouldn't happen, age:" << (int) age
-                        << ", test_value:" << (int) test_value << utils::io::endl;
-                break;
-        }
-        //----------
-
         OpenGLProgram* p = handle_cast<OpenGLProgram*>(ph);
         destruct(ph, p);
     }
@@ -2588,28 +2513,10 @@ void OpenGLDriver::makeCurrent(Handle<HwSwapChain> schDraw, Handle<HwSwapChain>
 
     mPlatform.makeCurrent(scDraw->swapChain, scRead->swapChain,
             [this]() {
-                for (auto t: mTexturesWithStreamsAttached) {
-                    if (t->hwStream->streamType == StreamType::NATIVE) {
-                        mPlatform.detach(t->hwStream->stream);
-                    }
-                }
                 // OpenGL context is about to change, unbind everything
                 mContext.unbindEverything();
             },
             [this](size_t index) {
-                for (auto t: mTexturesWithStreamsAttached) {
-                    if (t->hwStream->streamType == StreamType::NATIVE) {
-                        glGenTextures(1, &t->gl.id);
-                        mPlatform.attach(t->hwStream->stream, t->gl.id);
-                        mContext.updateTexImage(GL_TEXTURE_EXTERNAL_OES, t->gl.id);
-                    }
-                }
-
-                // force invalidation of all bound descriptor sets
-                decltype(mInvalidDescriptorSetBindings) changed;
-                changed.setValue((1 << MAX_DESCRIPTOR_SET_COUNT) - 1);
-                mInvalidDescriptorSetBindings |= changed;
-
                 // OpenGL context has changed, resynchronize the state with the cache
                 mContext.synchronizeStateAndCache(index);
                 slog.d << "*** OpenGL context change : " << (index ? "protected" : "default") << io::endl;
@@ -3441,8 +3348,8 @@ void OpenGLDriver::pushGroupMarker(char const* string) {
 #endif
 
 #if DEBUG_GROUP_MARKER_LEVEL & DEBUG_GROUP_MARKER_BACKEND
-    FILAMENT_TRACING_CONTEXT(FILAMENT_TRACING_CATEGORY_FILAMENT);
-    FILAMENT_TRACING_NAME_BEGIN(FILAMENT_TRACING_CATEGORY_FILAMENT, string);
+    SYSTRACE_CONTEXT();
+    SYSTRACE_NAME_BEGIN(string);
 #endif
 #endif
 }
@@ -3458,8 +3365,8 @@ void OpenGLDriver::popGroupMarker(int) {
 #endif
 
 #if DEBUG_GROUP_MARKER_LEVEL & DEBUG_GROUP_MARKER_BACKEND
-    FILAMENT_TRACING_CONTEXT(FILAMENT_TRACING_CATEGORY_FILAMENT);
-    FILAMENT_TRACING_NAME_END(FILAMENT_TRACING_CATEGORY_FILAMENT);
+    SYSTRACE_CONTEXT();
+    SYSTRACE_NAME_END();
 #endif
 #endif
 }
@@ -3778,7 +3685,7 @@ void OpenGLDriver::endFrame(UTILS_UNUSED uint32_t frameId) {
     gl.depthFunc(GL_LESS);
     gl.disable(GL_SCISSOR_TEST);
 #endif
-    //FILAMENT_TRACING_NAME(FILAMENT_TRACING_CATEGORY_FILAMENT, "glFinish");
+    //SYSTRACE_NAME("glFinish");
     //glFinish();
     mPlatform.endFrame(frameId);
     insertEventMarker("endFrame");
@@ -3800,7 +3707,8 @@ void OpenGLDriver::updateDescriptorSetTexture(
         TextureHandle th,
         SamplerParams params) {
     GLDescriptorSet* ds = handle_cast<GLDescriptorSet*>(dsh);
-    ds->update(mContext, mHandleAllocator, binding, th, params);
+    GLTexture* t = th ? handle_cast<GLTexture*>(th) : nullptr;
+    ds->update(mContext, binding, t, params);
 }
 
 void OpenGLDriver::flush(int) {
@@ -4123,24 +4031,6 @@ void OpenGLDriver::bindPipeline(PipelineState const& state) {
     setRasterState(state.rasterState);
     setStencilState(state.stencilState);
     gl.polygonOffset(state.polygonOffset.slope, state.polygonOffset.constant);
-    // test ----
-    Handle<HwProgram> pro = state.program;
-    int16_t returned_value = handle_get_value<OpenGLProgram*>(pro);
-    uint8_t age = (uint8_t)(returned_value >> 8);
-    uint8_t test_value = (returned_value & 0xff);
-    switch (test_value) {
-    case -2:
-    case -1:
-    case 0:
-        utils::slog.w << "@@@ bindPipeline: unexpected result, age:" << (int)age << ", test_value:" << (int)test_value << utils::io::endl;
-        break;
-    default:
-        if (test_value != 100) {
-            utils::slog.w << "@@@ bindPipeline: program is not valid OpenGLProgram, age:" << (int)age << ", test_value:" << (int)test_value << utils::io::endl;
-        }
-        break;
-    }
-    //----------
     OpenGLProgram* const p = handle_cast<OpenGLProgram*>(state.program);
     mValidProgram = useProgram(p);
     (*mCurrentPushConstants) = p->getPushConstants();

filament/backend/src/opengl/OpenGLDriver.h

@@ -282,20 +282,6 @@ private:
         return mHandleAllocator.handle_cast<Dp, B>(handle);
     }
 
-    template<typename Dp, typename B>
-    std::enable_if_t<std::is_pointer_v<Dp> && std::is_base_of_v<B, std::remove_pointer_t<Dp>>,
-            int16_t>
-    handle_set_value(Handle<B>& handle, uint8_t v) {
-        return mHandleAllocator.handle_set_value<Dp, B>(handle, v);
-    }
-
-    template<typename Dp, typename B>
-    std::enable_if_t<std::is_pointer_v<Dp> && std::is_base_of_v<B, std::remove_pointer_t<Dp>>,
-            int16_t>
-    handle_get_value(Handle<B>& handle) {
-        return mHandleAllocator.handle_get_value<Dp, B>(handle);
-    }
-
     friend class OpenGLProgram;
     friend class ShaderCompilerService;
 

filament/backend/src/opengl/OpenGLPlatform.cpp

@@ -64,7 +64,7 @@ utils::CString OpenGLPlatform::getRendererString(Driver const* driver) {
 }
 
 void OpenGLPlatform::makeCurrent(SwapChain* drawSwapChain, SwapChain* readSwapChain,
-        utils::Invocable<void()>, utils::Invocable<void(size_t)>) {
+        utils::Invocable<void()>, utils::Invocable<void(size_t)>) noexcept {
     makeCurrent(getCurrentContextType(), drawSwapChain, readSwapChain);
 }
 

filament/backend/src/opengl/OpenGLProgram.cpp

@@ -25,13 +25,12 @@
 #include <backend/Program.h>
 #include <backend/Handle.h>
 
-#include <private/utils/Tracing.h>
-
 #include <utils/BitmaskEnum.h>
 #include <utils/compiler.h>
 #include <utils/debug.h>
 #include <utils/FixedCapacityVector.h>
 #include <utils/Log.h>
+#include <utils/Systrace.h>
 
 #include <algorithm>
 #include <array>
@@ -97,7 +96,8 @@ OpenGLProgram::~OpenGLProgram() noexcept {
 }
 
 void OpenGLProgram::initialize(OpenGLDriver& gld) {
-    FILAMENT_TRACING_CALL(FILAMENT_TRACING_CATEGORY_FILAMENT);
+
+    SYSTRACE_CALL();
 
     assert_invariant(gl.program == 0);
     assert_invariant(mToken);
@@ -122,7 +122,8 @@ void OpenGLProgram::initialize(OpenGLDriver& gld) {
  */
 void OpenGLProgram::initializeProgramState(OpenGLContext& context, GLuint program,
         LazyInitializationData& lazyInitializationData) noexcept {
-    FILAMENT_TRACING_CALL(FILAMENT_TRACING_CATEGORY_FILAMENT);
+
+    SYSTRACE_CALL();
 
     // from the pipeline layout we compute a mapping from {set, binding} to {binding}
     // for both buffers and textures
@@ -174,31 +175,7 @@ void OpenGLProgram::initializeProgramState(OpenGLContext& context, GLuint progra
                     }
                     break;
                 }
-                case DescriptorType::SAMPLER_2D_FLOAT:
-                case DescriptorType::SAMPLER_2D_INT:
-                case DescriptorType::SAMPLER_2D_UINT:
-                case DescriptorType::SAMPLER_2D_DEPTH:
-                case DescriptorType::SAMPLER_2D_ARRAY_FLOAT:
-                case DescriptorType::SAMPLER_2D_ARRAY_INT:
-                case DescriptorType::SAMPLER_2D_ARRAY_UINT:
-                case DescriptorType::SAMPLER_2D_ARRAY_DEPTH:
-                case DescriptorType::SAMPLER_CUBE_FLOAT:
-                case DescriptorType::SAMPLER_CUBE_INT:
-                case DescriptorType::SAMPLER_CUBE_UINT:
-                case DescriptorType::SAMPLER_CUBE_DEPTH:
-                case DescriptorType::SAMPLER_CUBE_ARRAY_FLOAT:
-                case DescriptorType::SAMPLER_CUBE_ARRAY_INT:
-                case DescriptorType::SAMPLER_CUBE_ARRAY_UINT:
-                case DescriptorType::SAMPLER_CUBE_ARRAY_DEPTH:
-                case DescriptorType::SAMPLER_3D_FLOAT:
-                case DescriptorType::SAMPLER_3D_INT:
-                case DescriptorType::SAMPLER_3D_UINT:
-                case DescriptorType::SAMPLER_2D_MS_FLOAT:
-                case DescriptorType::SAMPLER_2D_MS_INT:
-                case DescriptorType::SAMPLER_2D_MS_UINT:
-                case DescriptorType::SAMPLER_2D_MS_ARRAY_FLOAT:
-                case DescriptorType::SAMPLER_2D_MS_ARRAY_INT:
-                case DescriptorType::SAMPLER_2D_MS_ARRAY_UINT:
+                case DescriptorType::SAMPLER:
                 case DescriptorType::SAMPLER_EXTERNAL: {
                     if (!entry.name.empty()) {
                         GLint const loc = glGetUniformLocation(program, entry.name.c_str());

filament/backend/src/opengl/OpenGLTimerQuery.cpp

@@ -23,13 +23,12 @@
 #include <backend/platforms/OpenGLPlatform.h>
 #include <backend/DriverEnums.h>
 
-#include <private/utils/Tracing.h>
-
 #include <utils/compiler.h>
 #include <utils/debug.h>
 #include <utils/JobSystem.h>
 #include <utils/Log.h>
 #include <utils/Mutex.h>
+#include <utils/Systrace.h>
 
 #include <atomic>
 #include <memory>
@@ -241,8 +240,8 @@ void TimerQueryFenceFactory::beginTimeElapsedQuery(GLTimerQuery* tq) {
         if (state) {
             platform.waitFence(fence, FENCE_WAIT_FOR_EVER);
             state->then = clock::now().time_since_epoch().count();
-            FILAMENT_TRACING_CONTEXT(FILAMENT_TRACING_CATEGORY_FILAMENT);
-            FILAMENT_TRACING_ASYNC_BEGIN(FILAMENT_TRACING_CATEGORY_FILAMENT, "OpenGLTimerQueryFence", intptr_t(state.get()));
+            SYSTRACE_CONTEXT();
+            SYSTRACE_ASYNC_BEGIN("OpenGLTimerQueryFence", intptr_t(state.get()));
         }
         platform.destroyFence(fence);
     });
@@ -258,8 +257,8 @@ void TimerQueryFenceFactory::endTimeElapsedQuery(OpenGLDriver&, GLTimerQuery* tq
             platform.waitFence(fence, FENCE_WAIT_FOR_EVER);
             int64_t const now = clock::now().time_since_epoch().count();
             state->elapsed.store(now - state->then, std::memory_order_relaxed);
-            FILAMENT_TRACING_CONTEXT(FILAMENT_TRACING_CATEGORY_FILAMENT);
-            FILAMENT_TRACING_ASYNC_END(FILAMENT_TRACING_CATEGORY_FILAMENT, "OpenGLTimerQueryFence", intptr_t(state.get()));
+            SYSTRACE_CONTEXT();
+            SYSTRACE_ASYNC_END("OpenGLTimerQueryFence", intptr_t(state.get()));
         }
         platform.destroyFence(fence);
     });

filament/backend/src/opengl/ShaderCompilerService.cpp

@@ -28,8 +28,6 @@
 #include <backend/DriverEnums.h>
 #include <backend/Program.h>
 
-#include <private/utils/Tracing.h>
-
 #include <utils/compiler.h>
 #include <utils/CString.h>
 #include <utils/debug.h>
@@ -38,6 +36,7 @@
 #include <utils/Log.h>
 #include <utils/ostream.h>
 #include <utils/Panic.h>
+#include <utils/Systrace.h>
 
 #include <algorithm>
 #include <array>
@@ -368,7 +367,7 @@ void ShaderCompilerService::notifyWhenAllProgramsAreReady(
 
 GLuint ShaderCompilerService::initialize(program_token_t& token) {
 
-    FILAMENT_TRACING_CALL(FILAMENT_TRACING_CATEGORY_FILAMENT);
+    SYSTRACE_CALL();
 
     assert_invariant(token);// This function should be called when the token is still alive.
 
@@ -455,8 +454,8 @@ void ShaderCompilerService::runAtNextTick(CompilerPriorityQueue priority,
             });
     ops.emplace(pos, priority, token, std::move(job));
 
-    FILAMENT_TRACING_CONTEXT(FILAMENT_TRACING_CATEGORY_FILAMENT);
-    FILAMENT_TRACING_VALUE(FILAMENT_TRACING_CATEGORY_FILAMENT, "ShaderCompilerService Jobs", mRunAtNextTickOps.size());
+    SYSTRACE_CONTEXT();
+    SYSTRACE_VALUE32("ShaderCompilerService Jobs", mRunAtNextTickOps.size());
 }
 
 bool ShaderCompilerService::cancelTickOp(program_token_t const& token) noexcept {
@@ -469,8 +468,8 @@ bool ShaderCompilerService::cancelTickOp(program_token_t const& token) noexcept
         ops.erase(pos);
         return true;
     }
-    FILAMENT_TRACING_CONTEXT(FILAMENT_TRACING_CATEGORY_FILAMENT);
-    FILAMENT_TRACING_VALUE(FILAMENT_TRACING_CATEGORY_FILAMENT, "ShaderCompilerService Jobs", ops.size());
+    SYSTRACE_CONTEXT();
+    SYSTRACE_VALUE32("ShaderCompilerService Jobs", ops.size());
     return false;
 }
 
@@ -486,15 +485,15 @@ void ShaderCompilerService::executeTickOps() noexcept {
             ++it;
         }
     }
-    FILAMENT_TRACING_CONTEXT(FILAMENT_TRACING_CATEGORY_FILAMENT);
-    FILAMENT_TRACING_VALUE(FILAMENT_TRACING_CATEGORY_FILAMENT, "ShaderCompilerService Jobs", ops.size());
+    SYSTRACE_CONTEXT();
+    SYSTRACE_VALUE32("ShaderCompilerService Jobs", ops.size());
 }
 
 /* static */ void ShaderCompilerService::compileShaders(OpenGLContext& context,
         Program::ShaderSource shadersSource,
         FixedCapacityVector<Program::SpecializationConstant> const& specializationConstants,
         bool multiview, program_token_t const& token) noexcept {
-    FILAMENT_TRACING_CALL(FILAMENT_TRACING_CATEGORY_FILAMENT);
+    SYSTRACE_CALL();
 
     auto const appendSpecConstantString = +[](std::string& s, Program::SpecializationConstant const& sc) {
         s += "#define SPIRV_CROSS_CONSTANT_ID_" + std::to_string(sc.id) + ' ';
@@ -617,7 +616,7 @@ void ShaderCompilerService::executeTickOps() noexcept {
 }
 
 /* static */ void ShaderCompilerService::checkCompileStatus(program_token_t const& token) noexcept {
-    FILAMENT_TRACING_CALL(FILAMENT_TRACING_CATEGORY_FILAMENT);
+    SYSTRACE_CALL();
 
     UTILS_NOUNROLL
     for (size_t i = 0; i < Program::SHADER_TYPE_COUNT; i++) {
@@ -640,7 +639,7 @@ void ShaderCompilerService::executeTickOps() noexcept {
 
 /* static */ void ShaderCompilerService::linkProgram(OpenGLContext const& context,
         program_token_t const& token) noexcept {
-    FILAMENT_TRACING_CALL(FILAMENT_TRACING_CATEGORY_FILAMENT);
+    SYSTRACE_CALL();
 
     // Shader compilation should be completed by now. Check the status and log errors on failure.
     checkCompileStatus(token);
@@ -676,7 +675,7 @@ void ShaderCompilerService::executeTickOps() noexcept {
 
 /* static */ bool ShaderCompilerService::checkLinkStatusAndCleanupShaders(
         program_token_t const& token) noexcept {
-    FILAMENT_TRACING_CALL(FILAMENT_TRACING_CATEGORY_FILAMENT);
+    SYSTRACE_CALL();
     assert_invariant(token->gl.program);
 
     bool linked = true;

filament/backend/src/opengl/gl_headers.cpp

@@ -70,9 +70,6 @@ PFNGLMAXSHADERCOMPILERTHREADSKHRPROC glMaxShaderCompilerThreadsKHR;
 #ifdef GL_OVR_multiview
 PFNGLFRAMEBUFFERTEXTUREMULTIVIEWOVRPROC glFramebufferTextureMultiviewOVR;
 #endif
-#ifdef GL_OVR_multiview_multisampled_render_to_texture
-PFNGLFRAMEBUFFERTEXTUREMULTISAMPLEMULTIVIEWOVRPROC glFramebufferTextureMultisampleMultiviewOVR;
-#endif
 
 #if defined(__ANDROID__) && !defined(FILAMENT_SILENCE_NOT_SUPPORTED_BY_ES2)
 // On Android, If we want to support a build system less than ANDROID_API 21, we need to
@@ -126,9 +123,6 @@ void importGLESExtensionsEntryPoints() {
 #ifdef GL_OVR_multiview
         getProcAddress(glFramebufferTextureMultiviewOVR, "glFramebufferTextureMultiviewOVR");
 #endif
-#ifdef GL_OVR_multiview_multisampled_render_to_texture
-        getProcAddress(glFramebufferTextureMultisampleMultiviewOVR, "glFramebufferTextureMultisampleMultiviewOVR");
-#endif
 #if defined(__ANDROID__) && !defined(FILAMENT_SILENCE_NOT_SUPPORTED_BY_ES2)
         getProcAddress(glDispatchCompute, "glDispatchCompute");
 #endif

filament/backend/src/opengl/gl_headers.h

@@ -154,9 +154,6 @@ extern PFNGLMAXSHADERCOMPILERTHREADSKHRPROC glMaxShaderCompilerThreadsKHR;
 #ifdef GL_OVR_multiview
 extern PFNGLFRAMEBUFFERTEXTUREMULTIVIEWOVRPROC glFramebufferTextureMultiviewOVR;
 #endif
-#ifdef GL_OVR_multiview_multisampled_render_to_texture
-extern PFNGLFRAMEBUFFERTEXTUREMULTISAMPLEMULTIVIEWOVRPROC glFramebufferTextureMultisampleMultiviewOVR;
-#endif
 #if defined(__ANDROID__) && !defined(FILAMENT_SILENCE_NOT_SUPPORTED_BY_ES2)
 extern PFNGLDISPATCHCOMPUTEPROC glDispatchCompute;
 #endif

filament/backend/src/opengl/platforms/PlatformCocoaGL.mm

@@ -54,7 +54,7 @@ struct PlatformCocoaGLImpl {
     CVOpenGLTextureCacheRef mTextureCache = nullptr;
     std::unique_ptr<CocoaExternalImage::SharedGl> mExternalImageSharedGl;
     void updateOpenGLContext(NSView *nsView, bool resetView, bool clearView);
-    struct ExternalImageCocoaGL final : public Platform::ExternalImage {
+    struct ExternalImageCocoaGL : public Platform::ExternalImage {
         CVPixelBufferRef cvBuffer;
     protected:
         ~ExternalImageCocoaGL() noexcept final;
@@ -255,7 +255,7 @@ void PlatformCocoaGL::destroySwapChain(Platform::SwapChain* swapChain) noexcept
 }
 
 bool PlatformCocoaGL::makeCurrent(ContextType type, SwapChain* drawSwapChain,
-        SwapChain* readSwapChain) {
+        SwapChain* readSwapChain) noexcept {
     ASSERT_PRECONDITION_NON_FATAL(drawSwapChain == readSwapChain,
             "ContextManagerCocoa does not support using distinct draw/read swap chains.");
     CocoaGLSwapChain* swapChain = (CocoaGLSwapChain*)drawSwapChain;

filament/backend/src/opengl/platforms/PlatformCocoaTouchGL.mm

@@ -155,7 +155,7 @@ uint32_t PlatformCocoaTouchGL::getDefaultFramebufferObject() noexcept {
 }
 
 bool PlatformCocoaTouchGL::makeCurrent(ContextType type, SwapChain* drawSwapChain,
-        SwapChain* readSwapChain) {
+        SwapChain* readSwapChain) noexcept {
     ASSERT_PRECONDITION_NON_FATAL(drawSwapChain == readSwapChain,
             "PlatformCocoaTouchGL does not support using distinct draw/read swap chains.");
     CAEAGLLayer* const glLayer = (__bridge CAEAGLLayer*) drawSwapChain;

filament/backend/src/opengl/platforms/PlatformEGL.cpp

@@ -577,18 +577,18 @@ OpenGLPlatform::ContextType PlatformEGL::getCurrentContextType() const noexcept
 }
 
 bool PlatformEGL::makeCurrent(ContextType type,
-        SwapChain* drawSwapChain, SwapChain* readSwapChain) {
+        SwapChain* drawSwapChain, SwapChain* readSwapChain) noexcept {
     SwapChainEGL const* const dsc = static_cast<SwapChainEGL const*>(drawSwapChain);
     SwapChainEGL const* const rsc = static_cast<SwapChainEGL const*>(readSwapChain);
     EGLContext context = getContextForType(type);
     EGLBoolean const success = egl.makeCurrent(context, dsc->sur, rsc->sur);
-    return success == EGL_TRUE;
+    return success == EGL_TRUE ? true : false;
 }
 
 void PlatformEGL::makeCurrent(SwapChain* drawSwapChain,
         SwapChain* readSwapChain,
         Invocable<void()> preContextChange,
-        Invocable<void(size_t index)> postContextChange) {
+        Invocable<void(size_t index)> postContextChange) noexcept {
 
     assert_invariant(drawSwapChain);
     assert_invariant(readSwapChain);
@@ -796,7 +796,7 @@ void PlatformEGL::Config::erase(EGLint name) noexcept {
 // ------------------------------------------------------------------------------------------------
 
 EGLBoolean PlatformEGL::EGL::makeCurrent(EGLContext context, EGLSurface drawSurface,
-        EGLSurface readSurface) {
+        EGLSurface readSurface) noexcept {
     if (UTILS_UNLIKELY((
             mCurrentContext != context ||
             drawSurface != mCurrentDrawSurface || readSurface != mCurrentReadSurface))) {

filament/backend/src/opengl/platforms/PlatformEGLAndroid.cpp

@@ -135,7 +135,7 @@ static constexpr const std::string_view kNativeWindowInvalidMsg =
 
 bool PlatformEGLAndroid::makeCurrent(ContextType type,
         SwapChain* drawSwapChain,
-        SwapChain* readSwapChain) {
+        SwapChain* readSwapChain) noexcept {
 
     // fast & safe path
     if (UTILS_LIKELY(!mAssertNativeWindowIsValid)) {
@@ -255,7 +255,6 @@ Platform::ExternalImageHandle PlatformEGLAndroid::createExternalImage(AHardwareB
         p->height = hardwareBufferDescription.height;
         p->width = hardwareBufferDescription.width;
         auto textureFormat = mapToFilamentFormat(hardwareBufferDescription.format, sRGB);
-        p->format = textureFormat;
         p->usage = mapToFilamentUsage(hardwareBufferDescription.usage, textureFormat);
         return ExternalImageHandle{ p };
     }

filament/backend/src/opengl/platforms/PlatformGLX.cpp

@@ -266,7 +266,7 @@ void PlatformGLX::destroySwapChain(Platform::SwapChain* swapChain) noexcept {
 }
 
 bool PlatformGLX::makeCurrent(ContextType type, SwapChain* drawSwapChain,
-        SwapChain* readSwapChain) {
+        SwapChain* readSwapChain) noexcept {
     g_glx.setCurrentContext(mGLXDisplay,
             (GLXDrawable)drawSwapChain, (GLXDrawable)readSwapChain, mGLXContext);
     return true;

filament/backend/src/opengl/platforms/PlatformOSMesa.cpp

@@ -169,7 +169,7 @@ void PlatformOSMesa::destroySwapChain(Platform::SwapChain* swapChain) noexcept {
 }
 
 bool PlatformOSMesa::makeCurrent(ContextType type, SwapChain* drawSwapChain,
-        SwapChain* readSwapChain) {
+        SwapChain* readSwapChain) noexcept {
     OSMesaAPI* api = (OSMesaAPI*) mOsMesaApi;
     OSMesaSwapchain* impl = (OSMesaSwapchain*) drawSwapChain;
 

filament/backend/src/opengl/platforms/PlatformWGL.cpp

@@ -262,7 +262,7 @@ void PlatformWGL::destroySwapChain(Platform::SwapChain* swapChain) noexcept {
 }
 
 bool PlatformWGL::makeCurrent(ContextType type, SwapChain* drawSwapChain,
-        SwapChain* readSwapChain) {
+        SwapChain* readSwapChain) noexcept {
     ASSERT_PRECONDITION_NON_FATAL(drawSwapChain == readSwapChain,
                                   "PlatformWGL does not support distinct draw/read swap chains.");
 

filament/backend/src/opengl/platforms/PlatformWebGL.cpp

@@ -47,7 +47,7 @@ void PlatformWebGL::destroySwapChain(Platform::SwapChain* swapChain) noexcept {
 }
 
 bool PlatformWebGL::makeCurrent(ContextType type, SwapChain* drawSwapChain,
-        SwapChain* readSwapChain) {
+        SwapChain* readSwapChain) noexcept {
     return true;
 }
 

filament/backend/src/vulkan/VulkanBuffer.cpp

@@ -28,7 +28,7 @@ VulkanBuffer::VulkanBuffer(VmaAllocator allocator, VulkanStagePool& stagePool,
     : mAllocator(allocator),
       mStagePool(stagePool),
       mUsage(usage),
-      mUpdatedOffset(0),
+	  mUpdatedOffset(0),
       mUpdatedBytes(0) {
     // for now make sure that only 1 bit is set in usage
     // (because loadFromCpu() assumes that somewhat)
@@ -56,12 +56,11 @@ void VulkanBuffer::loadFromCpu(VkCommandBuffer cmdbuf, const void* cpuData, uint
     vmaMapMemory(mAllocator, stage->memory, &mapped);
     memcpy(mapped, cpuData, numBytes);
     vmaUnmapMemory(mAllocator, stage->memory);
-    vmaFlushAllocation(mAllocator, stage->memory, 0, numBytes);
+    vmaFlushAllocation(mAllocator, stage->memory, byteOffset, numBytes);
 
     // If there was a previous update, then we need to make sure the following write is properly
     // synced with the previous read.
-    if (mUpdatedBytes > 0 &&
-            (byteOffset >= mUpdatedOffset && byteOffset <= (mUpdatedOffset + mUpdatedBytes))) {
+    if (mUpdatedBytes > 0) {
         VkAccessFlags srcAccess = 0;
         VkPipelineStageFlags srcStage = 0;
         if (mUsage & VK_BUFFER_USAGE_UNIFORM_BUFFER_BIT) {
@@ -75,28 +74,28 @@ void VulkanBuffer::loadFromCpu(VkCommandBuffer cmdbuf, const void* cpuData, uint
             srcStage = VK_PIPELINE_STAGE_VERTEX_INPUT_BIT;
         }
 
-        VkBufferMemoryBarrier barrier = {
+        VkBufferMemoryBarrier barrier{
             .sType = VK_STRUCTURE_TYPE_BUFFER_MEMORY_BARRIER,
             .srcAccessMask = srcAccess,
             .dstAccessMask = VK_ACCESS_TRANSFER_WRITE_BIT,
             .srcQueueFamilyIndex = VK_QUEUE_FAMILY_IGNORED,
             .dstQueueFamilyIndex = VK_QUEUE_FAMILY_IGNORED,
             .buffer = mGpuBuffer,
-            .offset = byteOffset,
-            .size = numBytes,
+			.offset = mUpdatedOffset,
+            .size = mUpdatedBytes,
         };
         vkCmdPipelineBarrier(cmdbuf, srcStage, VK_PIPELINE_STAGE_TRANSFER_BIT, 0, 0, nullptr, 1,
                 &barrier, 0, nullptr);
     }
 
-    VkBufferCopy region = {
-        .srcOffset = 0,
-        .dstOffset = byteOffset,
-        .size = numBytes,
+    VkBufferCopy region {
+            .srcOffset = 0,
+            .dstOffset = byteOffset,
+            .size = numBytes,
     };
     vkCmdCopyBuffer(cmdbuf, stage->buffer, mGpuBuffer, 1, &region);
 
-    mUpdatedOffset = byteOffset;
+	mUpdatedOffset = byteOffset;
     mUpdatedBytes = numBytes;
 
     // Firstly, ensure that the copy finishes before the next draw call.
@@ -113,21 +112,21 @@ void VulkanBuffer::loadFromCpu(VkCommandBuffer cmdbuf, const void* cpuData, uint
         dstAccessMask |= VK_ACCESS_INDEX_READ_BIT;
         dstStageMask |= VK_PIPELINE_STAGE_VERTEX_INPUT_BIT;
     } else if (mUsage & VK_BUFFER_USAGE_UNIFORM_BUFFER_BIT) {
-        dstAccessMask |= VK_ACCESS_SHADER_READ_BIT;
-        dstStageMask |= VK_PIPELINE_STAGE_FRAGMENT_SHADER_BIT | VK_PIPELINE_STAGE_VERTEX_SHADER_BIT;
+        dstAccessMask |= VK_ACCESS_UNIFORM_READ_BIT;
+        dstStageMask |=
+                (VK_PIPELINE_STAGE_VERTEX_SHADER_BIT | VK_PIPELINE_STAGE_FRAGMENT_SHADER_BIT);
     } else if (mUsage & VK_BUFFER_USAGE_STORAGE_BUFFER_BIT) {
         // TODO: implement me
     }
 
-    VkBufferMemoryBarrier barrier = {
+    VkBufferMemoryBarrier barrier{
         .sType = VK_STRUCTURE_TYPE_BUFFER_MEMORY_BARRIER,
         .srcAccessMask = VK_ACCESS_TRANSFER_WRITE_BIT,
         .dstAccessMask = dstAccessMask,
         .srcQueueFamilyIndex = VK_QUEUE_FAMILY_IGNORED,
         .dstQueueFamilyIndex = VK_QUEUE_FAMILY_IGNORED,
         .buffer = mGpuBuffer,
-        .offset = byteOffset,
-        .size = numBytes,
+        .size = VK_WHOLE_SIZE,
     };
 
     vkCmdPipelineBarrier(cmdbuf, VK_PIPELINE_STAGE_TRANSFER_BIT, dstStageMask, 0, 0, nullptr, 1,

filament/backend/src/vulkan/VulkanConstants.h

@@ -151,13 +151,13 @@ static_assert(FVK_ENABLED(FVK_DEBUG_VALIDATION));
 
 #elif FVK_ENABLED(FVK_DEBUG_SYSTRACE)
 
-    #include <private/utils/Tracing.h>
-
-    #define FVK_SYSTRACE_CONTEXT()      FILAMENT_TRACING_CONTEXT(FILAMENT_TRACING_CATEGORY_FILAMENT)
-    #define FVK_SYSTRACE_START(marker)  FILAMENT_TRACING_NAME_BEGIN(FILAMENT_TRACING_CATEGORY_FILAMENT, marker)
-    #define FVK_SYSTRACE_END()          FILAMENT_TRACING_NAME_END(FILAMENT_TRACING_CATEGORY_FILAMENT)
-    #define FVK_SYSTRACE_SCOPE()        FILAMENT_TRACING_CALL(FILAMENT_TRACING_CATEGORY_FILAMENT)
-    #define FVK_PROFILE_MARKER(marker)  FILAMENT_TRACING_CALL(FILAMENT_TRACING_CATEGORY_FILAMENT)
+    #include <utils/Systrace.h>
+    
+    #define FVK_SYSTRACE_CONTEXT()      SYSTRACE_CONTEXT()
+    #define FVK_SYSTRACE_START(marker)  SYSTRACE_NAME_BEGIN(marker)
+    #define FVK_SYSTRACE_END()          SYSTRACE_NAME_END()
+    #define FVK_SYSTRACE_SCOPE()        SYSTRACE_NAME(__func__)
+    #define FVK_PROFILE_MARKER(marker)  FVK_SYSTRACE_SCOPE()
 
 #else
     #define FVK_SYSTRACE_CONTEXT()

filament/backend/src/vulkan/VulkanDescriptorSetCache.cpp

@@ -358,11 +358,12 @@ void VulkanDescriptorSetCache::updateSamplerImpl(VkDescriptorSet vkset, uint8_t
         range.levelCount = 1;
         range.layerCount = 1;
     }
-    VkDescriptorImageInfo info = {
+    VkDescriptorImageInfo info{
         .sampler = sampler,
         .imageView = texture->getView(range),
-        .imageLayout = fvkutils::getVkLayout(texture->getSamplerLayout()),
+        .imageLayout = fvkutils::getVkLayout(texture->getDefaultLayout()),
     };
+
     VkWriteDescriptorSet descriptorWrite = {
         .sType = VK_STRUCTURE_TYPE_WRITE_DESCRIPTOR_SET,
         .pNext = nullptr,

filament/backend/src/vulkan/VulkanDriver.cpp

@@ -622,7 +622,7 @@ void VulkanDriver::createTextureExternalImage2R(Handle<HwTexture> th, backend::S
     auto& commands = mCommands.get();
     // Unlike uploaded textures or swapchains, we need to explicit transition this
     // texture into the read layout.
-    texture->transitionLayout(&commands, texture->getPrimaryViewRange(), VulkanLayout::FRAG_READ);
+    texture->transitionLayout(&commands, texture->getPrimaryViewRange(), VulkanLayout::READ_ONLY);
 
     if (imgData.external.valid()) {
         mExternalImageManager.addExternallySampledTexture(texture, externalImage);

filament/backend/src/vulkan/VulkanHandles.cpp

@@ -93,32 +93,7 @@ BitmaskGroup fromBackendLayout(DescriptorSetLayout const& layout) {
             case DescriptorType::SAMPLER_EXTERNAL:
                 fromStageFlags(binding.stageFlags, binding.binding, mask.externalSampler);
                 UTILS_FALLTHROUGH;
-
-            case DescriptorType::SAMPLER_2D_FLOAT:
-            case DescriptorType::SAMPLER_2D_INT:
-            case DescriptorType::SAMPLER_2D_UINT:
-            case DescriptorType::SAMPLER_2D_DEPTH:
-            case DescriptorType::SAMPLER_2D_ARRAY_FLOAT:
-            case DescriptorType::SAMPLER_2D_ARRAY_INT:
-            case DescriptorType::SAMPLER_2D_ARRAY_UINT:
-            case DescriptorType::SAMPLER_2D_ARRAY_DEPTH:
-            case DescriptorType::SAMPLER_CUBE_FLOAT:
-            case DescriptorType::SAMPLER_CUBE_INT:
-            case DescriptorType::SAMPLER_CUBE_UINT:
-            case DescriptorType::SAMPLER_CUBE_DEPTH:
-            case DescriptorType::SAMPLER_CUBE_ARRAY_FLOAT:
-            case DescriptorType::SAMPLER_CUBE_ARRAY_INT:
-            case DescriptorType::SAMPLER_CUBE_ARRAY_UINT:
-            case DescriptorType::SAMPLER_CUBE_ARRAY_DEPTH:
-            case DescriptorType::SAMPLER_3D_FLOAT:
-            case DescriptorType::SAMPLER_3D_INT:
-            case DescriptorType::SAMPLER_3D_UINT:
-            case DescriptorType::SAMPLER_2D_MS_FLOAT:
-            case DescriptorType::SAMPLER_2D_MS_INT:
-            case DescriptorType::SAMPLER_2D_MS_UINT:
-            case DescriptorType::SAMPLER_2D_MS_ARRAY_FLOAT:
-            case DescriptorType::SAMPLER_2D_MS_ARRAY_INT:
-            case DescriptorType::SAMPLER_2D_MS_ARRAY_UINT: {
+            case DescriptorType::SAMPLER: {
                 fromStageFlags(binding.stageFlags, binding.binding, mask.sampler);
                 break;
             }
@@ -520,8 +495,7 @@ void VulkanRenderTarget::emitBarriersEndRenderPass(VulkanCommandBuffer& commands
             }
         } else {
             texture->setLayout(range, VulkanFboCache::FINAL_COLOR_ATTACHMENT_LAYOUT);
-            if (texture->isSampleable() &&
-                    !texture->transitionLayout(&commands, range, VulkanLayout::FRAG_READ)) {
+            if (!texture->transitionLayout(&commands, range, VulkanLayout::READ_WRITE)) {
                 texture->attachmentToSamplerBarrier(&commands, range);
             }
         }

filament/backend/src/vulkan/VulkanReadPixels.cpp

@@ -234,7 +234,6 @@ void VulkanReadPixels::run(fvkmemory::resource_ptr<VulkanRenderTarget> srcTarget
 
     VulkanAttachment const srcAttachment = srcTarget->getColor0();
     VkImageSubresourceRange const srcRange = srcAttachment.getSubresourceRange();
-    VulkanLayout const srcLayout = srcAttachment.getLayout();
     srcTexture->transitionLayout(cmdbuffer, srcRange, VulkanLayout::TRANSFER_SRC);
 
     VkImageCopy const imageCopyRegion = {
@@ -271,7 +270,7 @@ void VulkanReadPixels::run(fvkmemory::resource_ptr<VulkanRenderTarget> srcTarget
             fvkutils::getVkLayout(VulkanLayout::TRANSFER_DST), 1, &imageCopyRegion);
 
     // Restore the source image layout.
-    srcTexture->transitionLayout(cmdbuffer, srcRange, srcLayout);
+    srcTexture->transitionLayout(cmdbuffer, srcRange, srcTexture->getDefaultLayout());
 
     vkEndCommandBuffer(cmdbuffer);
 

filament/backend/src/vulkan/VulkanStagePool.cpp

@@ -125,7 +125,7 @@ VulkanStageImage const* VulkanStagePool::acquireImage(PixelDataFormat format, Pi
     fvkutils::transitionLayout(cmdbuffer, {
             .image = image->image,
             .oldLayout = VulkanLayout::UNDEFINED,
-            .newLayout = VulkanLayout::STAGING, // (= VK_IMAGE_LAYOUT_GENERAL)
+            .newLayout = VulkanLayout::READ_WRITE, // (= VK_IMAGE_LAYOUT_GENERAL)
             .subresources = { aspectFlags, 0, 1, 0, 1 },
         });
     return image;

filament/backend/src/vulkan/VulkanTexture.cpp

@@ -125,7 +125,7 @@ inline VulkanLayout getDefaultLayoutImpl(TextureUsage usage) {
         return VulkanLayout::COLOR_ATTACHMENT;
     }
     // Finally, the layout for an immutable texture is optimal read-only.
-    return VulkanLayout::FRAG_READ;
+    return VulkanLayout::READ_ONLY;
 }
 
 inline VulkanLayout getDefaultLayoutImpl(VkImageUsageFlags vkusage) {
@@ -187,7 +187,7 @@ VkImageUsageFlags getUsage(VulkanContext const& context, uint8_t samples,
             VkFormatProperties props;
             vkGetPhysicalDeviceFormatProperties(physicalDevice, vkFormat, &props);
             if (!(props.optimalTilingFeatures & VK_FORMAT_FEATURE_SAMPLED_IMAGE_BIT)) {
-                FVK_LOGW << "Texture usage is SAMPLEABLE but format " << vkFormat << " is not "
+                FVK_LOGW << "Texture usage is SAMPLEABLE but format " << mState->mVkFormat << " is not "
                         "sampleable with optimal tiling." << utils::io::endl;
             }
         }
@@ -691,7 +691,6 @@ bool VulkanTexture::transitionLayout(VkCommandBuffer cmdbuf, VkImageSubresourceR
                  << " is skipped because of no change in layout" << utils::io::endl;
 #endif
     }
-
     return hasTransitions;
 }
 
@@ -701,15 +700,16 @@ void VulkanTexture::samplerToAttachmentBarrier(VulkanCommandBuffer* commands,
     VkImageLayout const layout =
             fvkutils::getVkLayout(getLayout(range.baseArrayLayer, range.baseMipLevel));
     VkImageMemoryBarrier barrier = {
-        .sType = VK_STRUCTURE_TYPE_IMAGE_MEMORY_BARRIER,
-        .srcAccessMask = VK_ACCESS_SHADER_READ_BIT,
-        .dstAccessMask = VK_ACCESS_COLOR_ATTACHMENT_READ_BIT | VK_ACCESS_COLOR_ATTACHMENT_WRITE_BIT,
-        .oldLayout = layout,
-        .newLayout = layout,
-        .srcQueueFamilyIndex = VK_QUEUE_FAMILY_IGNORED,
-        .dstQueueFamilyIndex = VK_QUEUE_FAMILY_IGNORED,
-        .image = mState->mTextureImage,
-        .subresourceRange = range,
+            .sType = VK_STRUCTURE_TYPE_IMAGE_MEMORY_BARRIER,
+            .srcAccessMask = VK_ACCESS_SHADER_READ_BIT,
+            .dstAccessMask =
+                    VK_ACCESS_COLOR_ATTACHMENT_READ_BIT | VK_ACCESS_COLOR_ATTACHMENT_WRITE_BIT,
+            .oldLayout = layout,
+            .newLayout = layout,
+            .srcQueueFamilyIndex = VK_QUEUE_FAMILY_IGNORED,
+            .dstQueueFamilyIndex = VK_QUEUE_FAMILY_IGNORED,
+            .image = mState->mTextureImage,
+            .subresourceRange = range,
     };
     vkCmdPipelineBarrier(cmdbuf, VK_PIPELINE_STAGE_FRAGMENT_SHADER_BIT,
             VK_PIPELINE_STAGE_EARLY_FRAGMENT_TESTS_BIT |
@@ -723,15 +723,15 @@ void VulkanTexture::attachmentToSamplerBarrier(VulkanCommandBuffer* commands,
     VkImageLayout const layout
             = fvkutils::getVkLayout(getLayout(range.baseArrayLayer, range.baseMipLevel));
     VkImageMemoryBarrier barrier = {
-        .sType = VK_STRUCTURE_TYPE_IMAGE_MEMORY_BARRIER,
-        .srcAccessMask = VK_ACCESS_COLOR_ATTACHMENT_WRITE_BIT,
-        .dstAccessMask = VK_ACCESS_SHADER_READ_BIT,
-        .oldLayout = layout,
-        .newLayout = layout,
-        .srcQueueFamilyIndex = VK_QUEUE_FAMILY_IGNORED,
-        .dstQueueFamilyIndex = VK_QUEUE_FAMILY_IGNORED,
-        .image = mState->mTextureImage,
-        .subresourceRange = range,
+            .sType = VK_STRUCTURE_TYPE_IMAGE_MEMORY_BARRIER,
+            .srcAccessMask = VK_ACCESS_COLOR_ATTACHMENT_WRITE_BIT,
+            .dstAccessMask = VK_ACCESS_SHADER_READ_BIT,
+            .oldLayout = layout,
+            .newLayout = layout,
+            .srcQueueFamilyIndex = VK_QUEUE_FAMILY_IGNORED,
+            .dstQueueFamilyIndex = VK_QUEUE_FAMILY_IGNORED,
+            .image = mState->mTextureImage,
+            .subresourceRange = range,
     };
     vkCmdPipelineBarrier(cmdbuf, VK_PIPELINE_STAGE_COLOR_ATTACHMENT_OUTPUT_BIT,
             VK_PIPELINE_STAGE_FRAGMENT_SHADER_BIT, 0, 0, nullptr, 0, nullptr, 1, &barrier);

filament/backend/src/vulkan/VulkanTexture.h

@@ -145,14 +145,8 @@ struct VulkanTexture : public HwTexture, fvkmemory::Resource {
 
     VkImageSubresourceRange const& getPrimaryViewRange() const { return mPrimaryViewRange; }
 
-    VulkanLayout getSamplerLayout() const {
-        if (!isSampleable()) {
-            return VulkanLayout::UNDEFINED;
-        }
-        if (mState->mUsage & VK_IMAGE_USAGE_DEPTH_STENCIL_ATTACHMENT_BIT) {
-            return VulkanLayout::DEPTH_SAMPLER;
-        }
-        return VulkanLayout::FRAG_READ;
+    VulkanLayout getPrimaryImageLayout() const {
+        return getLayout(mPrimaryViewRange.baseArrayLayer, mPrimaryViewRange.baseMipLevel);
     }
 
     // Returns the layout for the intended use of this texture (and not the expected layout at the
@@ -186,10 +180,6 @@ struct VulkanTexture : public HwTexture, fvkmemory::Resource {
         return mState->mUsage & VK_IMAGE_USAGE_TRANSIENT_ATTACHMENT_BIT;
     }
 
-    bool isSampleable() const {
-        return mState->mUsage & VK_IMAGE_USAGE_SAMPLED_BIT;
-    }
-
     bool getIsProtected() const {
         return mState->mIsProtected;
     }

filament/backend/src/vulkan/utils/Helper.h

@@ -21,7 +21,6 @@
 
 #include <utils/bitset.h>
 #include <utils/FixedCapacityVector.h>
-#include <utils/Panic.h>
 
 #include <bluevk/BlueVK.h>
 

filament/backend/src/vulkan/utils/Image.cpp

@@ -42,22 +42,20 @@ getVkTransition(const VulkanLayoutTransition& transition) {
             srcStage = VK_PIPELINE_STAGE_ALL_GRAPHICS_BIT;
             break;
         case VulkanLayout::COLOR_ATTACHMENT:
-            srcAccessMask = VK_ACCESS_COLOR_ATTACHMENT_READ_BIT |
+            srcAccessMask = VK_ACCESS_SHADER_READ_BIT | VK_ACCESS_SHADER_WRITE_BIT |
+                            VK_ACCESS_COLOR_ATTACHMENT_READ_BIT |
                             VK_ACCESS_COLOR_ATTACHMENT_WRITE_BIT;
-            srcStage = VK_PIPELINE_STAGE_COLOR_ATTACHMENT_OUTPUT_BIT;
+            srcStage = VK_PIPELINE_STAGE_VERTEX_SHADER_BIT | VK_PIPELINE_STAGE_FRAGMENT_SHADER_BIT |
+                       VK_PIPELINE_STAGE_COLOR_ATTACHMENT_OUTPUT_BIT;
             break;
-        case VulkanLayout::STAGING:
+        case VulkanLayout::READ_WRITE:
             srcAccessMask = VK_ACCESS_SHADER_READ_BIT | VK_ACCESS_SHADER_WRITE_BIT;
             srcStage = VK_PIPELINE_STAGE_FRAGMENT_SHADER_BIT;
             break;
-        case VulkanLayout::FRAG_READ:
+        case VulkanLayout::READ_ONLY:
             srcAccessMask = VK_ACCESS_SHADER_READ_BIT;
             srcStage = VK_PIPELINE_STAGE_FRAGMENT_SHADER_BIT;
             break;
-        case VulkanLayout::VERT_READ:
-            srcAccessMask = VK_ACCESS_SHADER_READ_BIT;
-            srcStage = VK_PIPELINE_STAGE_VERTEX_SHADER_BIT;
-            break;
         case VulkanLayout::TRANSFER_SRC:
             srcAccessMask = VK_ACCESS_TRANSFER_READ_BIT;
             srcStage = VK_PIPELINE_STAGE_TRANSFER_BIT;
@@ -71,7 +69,7 @@ getVkTransition(const VulkanLayoutTransition& transition) {
             srcStage = VK_PIPELINE_STAGE_LATE_FRAGMENT_TESTS_BIT;
             break;
         case VulkanLayout::DEPTH_SAMPLER:
-            srcAccessMask = VK_ACCESS_SHADER_READ_BIT;
+            srcAccessMask = VK_ACCESS_MEMORY_READ_BIT;
             srcStage = VK_PIPELINE_STAGE_FRAGMENT_SHADER_BIT;
             break;
         case VulkanLayout::COLOR_ATTACHMENT_RESOLVE:
@@ -86,21 +84,19 @@ getVkTransition(const VulkanLayoutTransition& transition) {
 
     switch (transition.newLayout) {
         case VulkanLayout::COLOR_ATTACHMENT:
-            dstAccessMask = VK_ACCESS_COLOR_ATTACHMENT_READ_BIT
+            dstAccessMask = VK_ACCESS_SHADER_READ_BIT | VK_ACCESS_SHADER_WRITE_BIT
+                            | VK_ACCESS_COLOR_ATTACHMENT_READ_BIT
                             | VK_ACCESS_COLOR_ATTACHMENT_WRITE_BIT;
-            dstStage = VK_PIPELINE_STAGE_COLOR_ATTACHMENT_OUTPUT_BIT | VK_PIPELINE_STAGE_FRAGMENT_SHADER_BIT;
+            dstStage = VK_PIPELINE_STAGE_VERTEX_SHADER_BIT | VK_PIPELINE_STAGE_FRAGMENT_SHADER_BIT
+                       | VK_PIPELINE_STAGE_COLOR_ATTACHMENT_OUTPUT_BIT;
             break;
-        case VulkanLayout::STAGING:
+        case VulkanLayout::READ_WRITE:
             dstAccessMask = VK_ACCESS_SHADER_READ_BIT | VK_ACCESS_SHADER_WRITE_BIT;
             dstStage = VK_PIPELINE_STAGE_FRAGMENT_SHADER_BIT;
             break;
-        case VulkanLayout::FRAG_READ:
+        case VulkanLayout::READ_ONLY:
             dstAccessMask = VK_ACCESS_SHADER_READ_BIT;
-            dstStage = VK_PIPELINE_STAGE_FRAGMENT_SHADER_BIT;
-            break;
-        case VulkanLayout::VERT_READ:
-            dstAccessMask = VK_ACCESS_SHADER_READ_BIT;
-            dstStage = VK_PIPELINE_STAGE_VERTEX_SHADER_BIT;
+            dstStage = VK_PIPELINE_STAGE_FRAGMENT_SHADER_BIT | VK_PIPELINE_STAGE_VERTEX_SHADER_BIT;
             break;
         case VulkanLayout::TRANSFER_SRC:
             dstAccessMask = VK_ACCESS_TRANSFER_READ_BIT;
@@ -116,8 +112,10 @@ getVkTransition(const VulkanLayoutTransition& transition) {
             dstStage = VK_PIPELINE_STAGE_EARLY_FRAGMENT_TESTS_BIT;
             break;
         case VulkanLayout::DEPTH_SAMPLER:
-            dstAccessMask = VK_ACCESS_SHADER_READ_BIT;
-            dstStage = VK_PIPELINE_STAGE_FRAGMENT_SHADER_BIT;
+            dstAccessMask =
+                    VK_ACCESS_SHADER_READ_BIT | VK_ACCESS_DEPTH_STENCIL_ATTACHMENT_WRITE_BIT;
+            dstStage = VK_PIPELINE_STAGE_FRAGMENT_SHADER_BIT |
+                       VK_PIPELINE_STAGE_EARLY_FRAGMENT_TESTS_BIT;
             break;
         case VulkanLayout::PRESENT:
         case VulkanLayout::COLOR_ATTACHMENT_RESOLVE:
@@ -140,6 +138,7 @@ bool transitionLayout(VkCommandBuffer cmdbuffer,
     }
     auto [srcAccessMask, dstAccessMask, srcStage, dstStage, oldLayout, newLayout]
             = getVkTransition(transition);
+
     if (oldLayout == newLayout) {
         return false;
     }
@@ -156,7 +155,7 @@ bool transitionLayout(VkCommandBuffer cmdbuffer,
             .image = transition.image,
             .subresourceRange = transition.subresources,
     };
-   vkCmdPipelineBarrier(cmdbuffer, srcStage, dstStage, 0, 0, nullptr, 0, nullptr, 1, &barrier);
+    vkCmdPipelineBarrier(cmdbuffer, srcStage, dstStage, 0, 0, nullptr, 0, nullptr, 1, &barrier);
     return true;
 }
 
@@ -265,9 +264,8 @@ utils::io::ostream& operator<<(utils::io::ostream& out,
         const filament::backend::VulkanLayout& layout) {
     switch (layout) {
         CASE(UNDEFINED)
-        CASE(FRAG_READ)
-        CASE(VERT_READ)
-        CASE(STAGING)
+        CASE(READ_ONLY)
+        CASE(READ_WRITE)
         CASE(TRANSFER_SRC)
         CASE(TRANSFER_DST)
         CASE(DEPTH_ATTACHMENT)

filament/backend/src/vulkan/utils/Image.h

@@ -32,11 +32,9 @@ enum class VulkanLayout : uint8_t {
     // any transition.
     UNDEFINED,
     // Fragment/vertex shader accessible layout for reading and writing.
-    STAGING,
-    // Fragment shader accessible layout for reading only.
-    FRAG_READ,
-    // Vertex shader accessible layout for reading only.
-    VERT_READ,
+    READ_WRITE,
+    // Fragment/vertex shader accessible layout for reading only.
+    READ_ONLY,
     // For the source of a copy operation.
     TRANSFER_SRC,
     // For the destination of a copy operation.
@@ -67,10 +65,9 @@ constexpr inline VkImageLayout getVkLayout(VulkanLayout layout) {
     switch (layout) {
         case VulkanLayout::UNDEFINED:
             return VK_IMAGE_LAYOUT_UNDEFINED;
-        case VulkanLayout::STAGING:
+        case VulkanLayout::READ_WRITE:
             return VK_IMAGE_LAYOUT_GENERAL;
-        case VulkanLayout::FRAG_READ:
-        case VulkanLayout::VERT_READ:
+        case VulkanLayout::READ_ONLY:
             return VK_IMAGE_LAYOUT_SHADER_READ_ONLY_OPTIMAL;
         case VulkanLayout::TRANSFER_SRC:
             return VK_IMAGE_LAYOUT_TRANSFER_SRC_OPTIMAL;
@@ -83,8 +80,9 @@ constexpr inline VkImageLayout getVkLayout(VulkanLayout layout) {
         case VulkanLayout::PRESENT:
             return VK_IMAGE_LAYOUT_PRESENT_SRC_KHR;
         // Filament sometimes samples from one miplevel while writing to another level in the
-        // same texture (e.g. bloom does this). So, keep it simple and use GENERAL for all
-        // color-attachable textures.
+        // same texture (e.g. bloom does this). Moreover we'd like to avoid lots of expensive
+        // layout transitions. So, keep it simple and use GENERAL for all color-attachable
+        // textures.
         case VulkanLayout::COLOR_ATTACHMENT:
             return VK_IMAGE_LAYOUT_GENERAL;
         case VulkanLayout::COLOR_ATTACHMENT_RESOLVE:

filament/backend/src/webgpu/WGPUProgram.cpp

@@ -17,7 +17,6 @@
 #include "WebGPUHandles.h"
 
 #include "WebGPUConstants.h"
-#include "WebGPUStrings.h"
 
 #include "DriverBase.h"
 #include <backend/DriverEnums.h>
@@ -29,116 +28,39 @@
 #include <webgpu/webgpu_cpp.h>
 
 #include <algorithm>
-#include <cstdint>
 #include <sstream>
-#include <string>
 #include <string_view>
-#include <unordered_map>
-#include <variant>
+#include <vector>
 
 namespace filament::backend {
 
 namespace {
 
-[[nodiscard]] std::string replaceSpecConstants(std::string_view shaderLabel,
-        std::string_view shaderSource,
-        std::unordered_map<uint32_t, std::variant<int32_t, float, bool>> const&
-                specConstants) {
-    assert_invariant(!specConstants.empty());
-    constexpr std::string_view specConstantPrefix = "FILAMENT_SPEC_CONST_";
-    constexpr size_t specConstantPrefixSize = specConstantPrefix.size();
-    const char* const sourceData = shaderSource.data();
-    std::stringstream processedShaderSourceStr{};
-    size_t pos = 0;
-    while (pos < shaderSource.size()) {
-        const size_t posOfNextSpecConstant = shaderSource.find(specConstantPrefix, pos);
-        if (posOfNextSpecConstant == std::string::npos) {
-            // no more spec constants, so just stream the rest of the source code string
-            processedShaderSourceStr
-                    << std::string_view(sourceData + pos, shaderSource.size() - pos);
-            break;
-        }
-        const size_t posOfId = posOfNextSpecConstant + specConstantPrefixSize;
-        const size_t posAfterId = shaderSource.find('_', posOfId);
-        FILAMENT_CHECK_POSTCONDITION(posAfterId != std::string::npos)
-                << "malformed " << shaderLabel << ". Found spec constant prefix '"
-                << specConstantPrefix << "' without an id or '_' after it.";
-        const std::string_view idStr =
-                std::string_view(sourceData + posOfId, posAfterId - posOfId);
-        const size_t posEndOfStatement = shaderSource.find(';', posAfterId);
-        FILAMENT_CHECK_POSTCONDITION(posEndOfStatement != std::string::npos)
-                << "malformed " << shaderLabel << ". Found spec constant assignment with id "
-                << idStr << " without a terminating ';' character?";
-        const std::string_view statementSegment =
-                std::string_view(sourceData + posAfterId, posEndOfStatement - posAfterId);
-        size_t posOfEqual = statementSegment.find('=');
-        if (posOfEqual == std::string::npos) {
-            // not an assignment statement, so stream to the end of the statement and continue...
-            processedShaderSourceStr
-                    << std::string_view(sourceData + pos, posEndOfStatement + 1 - pos);
-            pos = posEndOfStatement + 1;
-            continue;
-        }
-        posOfEqual += posAfterId; // position in original source, not just the segment
-        int id = 0;
-        try {
-            id = std::stoi(idStr.data());
-        } catch (const std::invalid_argument& e) {
-            PANIC_POSTCONDITION("Invalid spec constant id '%s' in %s (not a valid integer?): %s",
-                    idStr.data(), shaderLabel.data(), e.what());
-        } catch (const std::out_of_range& e) {
-            PANIC_POSTCONDITION(
-                    "Invalid spec constant id '%s' in %s (not an integer? out of range?): %s",
-                    idStr.data(), shaderLabel.data(), e.what());
-        }
-        const auto newValueItr = specConstants.find(static_cast<uint32_t>(id));
-        if (newValueItr == specConstants.end()) {
-            // not going to override the constant (stream to the end of the statement)...
-            processedShaderSourceStr
-                    << std::string_view(sourceData + pos, posEndOfStatement + 1 - pos);
-            pos = posEndOfStatement + 1;
-            continue;
-        }
-        // need to override the constant...
-        const std::variant<int32_t, float, bool> newValue = newValueItr->second;
-        // stream up to the equal sign...
-        processedShaderSourceStr << std::string_view(sourceData + pos, posOfEqual + 1 - pos);
-        // stream the new value...
-        if (auto* v = std::get_if<int32_t>(&newValue)) {
-            processedShaderSourceStr << " " << *v << "i";
-        } else if (auto* f = std::get_if<float>(&newValue)) {
-            processedShaderSourceStr << " " << *f << "f";
-        } else if (auto* b = std::get_if<bool>(&newValue)) {
-            processedShaderSourceStr << " " << ((*b) ? "true" : "false");
-        }
-        processedShaderSourceStr << ";";
-        // and skip to after the end of the statement in the original source...
-        pos = posEndOfStatement + 1;
+[[nodiscard]] constexpr std::string_view toString(ShaderStage stage) {
+    switch (stage) {
+        case ShaderStage::VERTEX:
+            return "vertex";
+        case ShaderStage::FRAGMENT:
+            return "fragment";
+        case ShaderStage::COMPUTE:
+            return "compute";
     }
-    return processedShaderSourceStr.str();
 }
 
-[[nodiscard]] wgpu::ShaderModule createShaderModule(wgpu::Device& device, Program& program,
-        ShaderStage stage,
-        std::unordered_map<uint32_t, std::variant<int32_t, float, bool>> const& specConstants) {
-    const char* const programName = program.getName().c_str_safe();
-    std::array<utils::FixedCapacityVector<uint8_t>, Program::SHADER_TYPE_COUNT> const&
-            shaderSource = program.getShadersSource();
+[[nodiscard]] wgpu::ShaderModule createShaderModule(wgpu::Device& device, const char* programName,
+        std::array<utils::FixedCapacityVector<uint8_t>, Program::SHADER_TYPE_COUNT> const&
+                shaderSource,
+        ShaderStage stage) {
     utils::FixedCapacityVector<uint8_t> const& sourceBytes =
             shaderSource[static_cast<size_t>(stage)];
     if (sourceBytes.empty()) {
         return nullptr;// nothing to compile, the shader was not provided
     }
-    std::stringstream labelStream;
-    labelStream << programName << " " << filamentShaderStageToString(stage) << " shader";
-    auto label = labelStream.str();
-    const std::string processedShaderSource =
-            specConstants.empty()
-                    ? reinterpret_cast<const char*>(sourceBytes.data())
-                    : replaceSpecConstants(label, reinterpret_cast<const char*>(sourceBytes.data()),
-                              specConstants);
     wgpu::ShaderModuleWGSLDescriptor wgslDescriptor{};
-    wgslDescriptor.code = wgpu::StringView(processedShaderSource);
+    wgslDescriptor.code = wgpu::StringView(reinterpret_cast<const char*>(sourceBytes.data()));
+    std::stringstream labelStream;
+    labelStream << programName << " " << toString(stage) << " shader";
+    auto label = labelStream.str();
     wgpu::ShaderModuleDescriptor descriptor{
         .nextInChain = &wgslDescriptor,
         .label = label.data()
@@ -197,33 +119,85 @@ namespace {
                                     << ":\n"
                                     << errorStream.str();
                         }
-#if FWGPU_ENABLED(FWGPU_DEBUG_VALIDATION)
                         FWGPU_LOGD << descriptor.label << " compiled successfully"
                                    << utils::io::endl;
-#endif
                     }),
-            SHADER_COMPILATION_TIMEOUT_NANOSECONDS);
+            UINT16_MAX);
     return module;
 }
 
-void toMap(utils::FixedCapacityVector<Program::SpecializationConstant> const& specConstants,
-        std::unordered_map<uint32_t, std::variant<int32_t, float, bool>>& constantById) {
-    constantById.reserve(specConstants.size());
-    for (auto const& specConstant: specConstants) {
-        constantById.emplace(specConstant.id, specConstant.value);
+// This is a 1 to 1 mapping of the ReservedSpecializationConstants enum in EngineEnums.h
+// The _hack is a workaround until https://issues.chromium.org/issues/42250586 is resolved
+// This workaround is the same one being used on the generateSpecializationConstant() function
+wgpu::StringView getSpecConstantStringId(uint32_t id) {
+    switch (id) {
+        case 0:
+            return "0";// BACKEND_FEATURE_LEVEL_hack
+        case 1:
+            return "1";// CONFIG_MAX_INSTANCES_hack
+        case 2:
+            return "2";// ONFIG_STATIC_TEXTURE_TARGET_WORKAROUND_hack
+        case 3:
+            return "3";// CONFIG_SRGB_SWAPCHAIN_EMULATION_hack
+        case 4:
+            return "4";// CONFIG_FROXEL_BUFFER_HEIGHT_hack
+        case 5:
+            return "5";// CONFIG_POWER_VR_SHADER_WORKAROUNDS_hack
+        case 6:
+            return "6";// CONFIG_DEBUG_DIRECTIONAL_SHADOWMAP_hack
+        case 7:
+            return "7";// CONFIG_DEBUG_FROXEL_VISUALIZATION_hack
+        case 8:
+            return "8";// CONFIG_STEREO_EYE_COUNT_hack
+        case 9:
+            return "9";// CONFIG_SH_BANDS_COUNT_hack
+        case 10:
+            return "10";// CONFIG_SHADOW_SAMPLING_METHOD_hack
+        default:
+            PANIC_POSTCONDITION("Unknown/unhandled spec constant key/id: %d", id);
     }
 }
 
+std::vector<wgpu::ConstantEntry> convertConstants(
+        utils::FixedCapacityVector<filament::backend::Program::SpecializationConstant> const&
+                constantsInfo) {
+    std::vector<wgpu::ConstantEntry> constants;
+    constants.reserve(constantsInfo.size());
+    for (filament::backend::Program::SpecializationConstant const& constant: constantsInfo) {
+        // CONFIG_MAX_INSTANCES (1) and CONFIG_FROXEL_BUFFER_HEIGHT (4) will not be present
+        // as constant overrides in the generated WGSL, because WGSL doesn't support specialization
+        // constants as an array length
+        // More information at https://github.com/gpuweb/gpuweb/issues/572#issuecomment-649760005
+        // CONFIG_SRGB_SWAPCHAIN_EMULATION (3) is being skipped all together since it's only
+        // included for the case of mFeatureLevel == FeatureLevel::FEATURE_LEVEL_0, which should
+        // not be possible for WebGPU
+        if (constant.id == 1 || constant.id == 3 || constant.id == 4) {
+            continue;
+        }
+        double value = 0.0;
+        if (auto* v = std::get_if<int32_t>(&constant.value)) {
+            value = static_cast<double>(*v);
+        } else if (auto* f = std::get_if<float>(&constant.value)) {
+            value = static_cast<double>(*f);
+        } else if (auto* b = std::get_if<bool>(&constant.value)) {
+            value = *b ? 0.0 : 1.0;
+        }
+        constants.push_back(
+                wgpu::ConstantEntry{ .key = getSpecConstantStringId(constant.id), .value = value });
+    }
+    return constants;
+}
+
 }// namespace
 
 WGPUProgram::WGPUProgram(wgpu::Device& device, Program& program)
-    : HwProgram(program.getName()) {
-    std::unordered_map<uint32_t, std::variant<int32_t, float, bool>> specConstants;
-    toMap(program.getSpecializationConstants(), specConstants);
-    vertexShaderModule = createShaderModule(device, program, ShaderStage::VERTEX, specConstants);
-    fragmentShaderModule =
-            createShaderModule(device, program, ShaderStage::FRAGMENT, specConstants);
-    computeShaderModule = createShaderModule(device, program, ShaderStage::COMPUTE, specConstants);
-}
+    : HwProgram(program.getName()),
+      vertexShaderModule(createShaderModule(device, name.c_str_safe(), program.getShadersSource(),
+              ShaderStage::VERTEX)),
+      fragmentShaderModule(createShaderModule(device, name.c_str_safe(), program.getShadersSource(),
+              ShaderStage::FRAGMENT)),
+      computeShaderModule(createShaderModule(device, name.c_str_safe(), program.getShadersSource(),
+              ShaderStage::COMPUTE)),
+      constants(convertConstants(program.getSpecializationConstants())) {}
 
 }// namespace filament::backend

filament/backend/src/webgpu/WebGPUConstants.h

@@ -63,13 +63,4 @@
     #define FWGPU_LOGI (utils::slog.i)
 #endif
 
-constexpr uint64_t REQUEST_ADAPTER_TIMEOUT_NANOSECONDS =
-        /* milliseconds */ 1000u * /* converted to ns */ 1000000u;
-
-constexpr uint64_t REQUEST_DEVICE_TIMEOUT_NANOSECONDS =
-        /* milliseconds */ 1000u * /* converted to ns */ 1000000u;
-
-constexpr uint64_t SHADER_COMPILATION_TIMEOUT_NANOSECONDS =
-        /* milliseconds */ 1000u * /* converted to ns */ 1000000u;
-
 #endif// TNT_FILAMENT_BACKEND_WEBGPUCONSTANTS_H

filament/backend/src/webgpu/WebGPUDriver.cpp

@@ -26,24 +26,193 @@
 #include <backend/DriverEnums.h>
 #include <backend/Handle.h>
 #include <backend/TargetBufferInfo.h>
-#include <private/backend/BackendUtils.h>
+
 #include <math/mat3.h>
 #include <utils/CString.h>
 #include <utils/Panic.h>
 #include <utils/ostream.h>
 
+#include <dawn/webgpu_cpp_print.h>
 #include <webgpu/webgpu_cpp.h>
 
 #include <algorithm>
 #include <array>
 #include <cstddef>
 #include <cstdint>
-#include <memory>
 #include <sstream>
+#include <string_view>
 #include <utility>
+#include <variant>
 
 namespace filament::backend {
 
+namespace {
+
+#if FWGPU_ENABLED(FWGPU_PRINT_SYSTEM)
+void printInstanceDetails(wgpu::Instance const& instance) {
+    wgpu::SupportedWGSLLanguageFeatures supportedWGSLLanguageFeatures{};
+    if (!instance.GetWGSLLanguageFeatures(&supportedWGSLLanguageFeatures)) {
+        FWGPU_LOGW << "Failed to get WebGPU instance supported WGSL language features"
+                   << utils::io::endl;
+    } else {
+        FWGPU_LOGI << "WebGPU instance supported WGSL language features ("
+                   << supportedWGSLLanguageFeatures.featureCount << "):" << utils::io::endl;
+        if (supportedWGSLLanguageFeatures.featureCount > 0 &&
+                supportedWGSLLanguageFeatures.features != nullptr) {
+            std::for_each(supportedWGSLLanguageFeatures.features,
+                    supportedWGSLLanguageFeatures.features +
+                            supportedWGSLLanguageFeatures.featureCount,
+                    [](wgpu::WGSLLanguageFeatureName const featureName) {
+                        std::stringstream nameStream{};
+                        nameStream << featureName;
+                        FWGPU_LOGI << "  " << nameStream.str() << utils::io::endl;
+                    });
+        }
+    }
+}
+#endif
+
+#if FWGPU_ENABLED(FWGPU_PRINT_SYSTEM)
+void printLimit(std::string_view name, const std::variant<uint32_t, uint64_t> value) {
+    FWGPU_LOGI << "  " << name.data() << ": ";
+    bool undefined = true;
+    if (std::holds_alternative<uint32_t>(value)) {
+        if (std::get<uint32_t>(value) != WGPU_LIMIT_U32_UNDEFINED) {
+            undefined = false;
+            FWGPU_LOGI << std::get<uint32_t>(value);
+        }
+    } else if (std::holds_alternative<uint64_t>(value)) {
+        if (std::get<uint64_t>(value) != WGPU_LIMIT_U64_UNDEFINED) {
+            undefined = false;
+            FWGPU_LOGI << std::get<uint64_t>(value);
+        }
+    }
+    if (undefined) {
+        FWGPU_LOGI << "UNDEFINED";
+    }
+    FWGPU_LOGI << utils::io::endl;
+}
+#endif
+
+#if FWGPU_ENABLED(FWGPU_PRINT_SYSTEM)
+void printLimits(wgpu::Limits const& limits) {
+    printLimit("maxTextureDimension1D", limits.maxTextureDimension1D);
+    printLimit("maxTextureDimension2D", limits.maxTextureDimension2D);
+    printLimit("maxTextureDimension3D", limits.maxTextureDimension3D);
+    printLimit("maxTextureArrayLayers", limits.maxTextureArrayLayers);
+    printLimit("maxBindGroups", limits.maxBindGroups);
+    printLimit("maxBindGroupsPlusVertexBuffers", limits.maxBindGroupsPlusVertexBuffers);
+    printLimit("maxBindingsPerBindGroup", limits.maxBindingsPerBindGroup);
+    printLimit("maxDynamicUniformBuffersPerPipelineLayout",
+            limits.maxDynamicUniformBuffersPerPipelineLayout);
+    printLimit("maxDynamicStorageBuffersPerPipelineLayout",
+            limits.maxDynamicStorageBuffersPerPipelineLayout);
+    printLimit("maxSampledTexturesPerShaderStage", limits.maxSampledTexturesPerShaderStage);
+    printLimit("maxSamplersPerShaderStage", limits.maxSamplersPerShaderStage);
+    printLimit("maxStorageBuffersPerShaderStage", limits.maxStorageBuffersPerShaderStage);
+    printLimit("maxStorageTexturesPerShaderStage", limits.maxStorageTexturesPerShaderStage);
+    printLimit("maxUniformBuffersPerShaderStage", limits.maxUniformBuffersPerShaderStage);
+    printLimit("maxUniformBufferBindingSize", limits.maxUniformBufferBindingSize);
+    printLimit("maxStorageBufferBindingSize", limits.maxStorageBufferBindingSize);
+    printLimit("minUniformBufferOffsetAlignment", limits.minUniformBufferOffsetAlignment);
+    printLimit("minStorageBufferOffsetAlignment", limits.minStorageBufferOffsetAlignment);
+    printLimit("maxVertexBuffers", limits.maxVertexBuffers);
+    printLimit("maxBufferSize", limits.maxBufferSize);
+    printLimit("maxVertexAttributes", limits.maxVertexAttributes);
+    printLimit("maxVertexBufferArrayStride", limits.maxVertexBufferArrayStride);
+    printLimit("maxInterStageShaderVariables", limits.maxInterStageShaderVariables);
+    printLimit("maxColorAttachments", limits.maxColorAttachments);
+    printLimit("maxColorAttachmentBytesPerSample", limits.maxColorAttachmentBytesPerSample);
+    printLimit("maxComputeWorkgroupStorageSize", limits.maxComputeWorkgroupStorageSize);
+    printLimit("maxComputeInvocationsPerWorkgroup", limits.maxComputeInvocationsPerWorkgroup);
+    printLimit("maxComputeWorkgroupSizeX", limits.maxComputeWorkgroupSizeX);
+    printLimit("maxComputeWorkgroupSizeY", limits.maxComputeWorkgroupSizeY);
+    printLimit("maxComputeWorkgroupSizeZ", limits.maxComputeWorkgroupSizeZ);
+    printLimit("maxComputeWorkgroupsPerDimension", limits.maxComputeWorkgroupsPerDimension);
+    printLimit("maxStorageBuffersInVertexStage", limits.maxStorageBuffersInVertexStage);
+    printLimit("maxStorageTexturesInVertexStage", limits.maxStorageTexturesInVertexStage);
+    printLimit("maxStorageBuffersInFragmentStage", limits.maxStorageBuffersInFragmentStage);
+    printLimit("maxStorageTexturesInFragmentStage", limits.maxStorageTexturesInFragmentStage);
+}
+#endif
+
+#if FWGPU_ENABLED(FWGPU_PRINT_SYSTEM)
+void printAdapterDetails(wgpu::Adapter const& adapter) {
+    wgpu::DawnAdapterPropertiesPowerPreference powerPreferenceProperties{};
+    wgpu::AdapterInfo adapterInfo{};
+    adapterInfo.nextInChain = &powerPreferenceProperties;
+    if (!adapter.GetInfo(&adapterInfo)) {
+        FWGPU_LOGW << "Failed to get WebGPU adapter info" << utils::io::endl;
+    } else {
+        std::stringstream backendTypeStream{};
+        backendTypeStream << adapterInfo.backendType;
+        std::stringstream adapterTypeStream{};
+        adapterTypeStream << adapterInfo.adapterType;
+        std::stringstream powerPreferenceStream{};
+        powerPreferenceStream << powerPreferenceProperties.powerPreference;
+        FWGPU_LOGI << "WebGPU adapter info:" << utils::io::endl;
+        FWGPU_LOGI << "  vendor: " << adapterInfo.vendor.data << utils::io::endl;
+        FWGPU_LOGI << "  architecture: " << adapterInfo.architecture.data << utils::io::endl;
+        FWGPU_LOGI << "  device: " << adapterInfo.device.data << utils::io::endl;
+        FWGPU_LOGI << "  description: " << adapterInfo.description.data << utils::io::endl;
+        FWGPU_LOGI << "  backend type: " << backendTypeStream.str().data() << utils::io::endl;
+        FWGPU_LOGI << "  adapter type: " << adapterTypeStream.str().data() << utils::io::endl;
+        FWGPU_LOGI << "  device ID: " << adapterInfo.deviceID << utils::io::endl;
+        FWGPU_LOGI << "  vendor ID: " << adapterInfo.vendorID << utils::io::endl;
+        FWGPU_LOGI << "  subgroup min size: " << adapterInfo.subgroupMinSize << utils::io::endl;
+        FWGPU_LOGI << "  subgroup max size: " << adapterInfo.subgroupMaxSize << utils::io::endl;
+        FWGPU_LOGI << "  power preference: " << powerPreferenceStream.str() << utils::io::endl;
+    }
+    wgpu::SupportedFeatures supportedFeatures{};
+    adapter.GetFeatures(&supportedFeatures);
+    FWGPU_LOGI << "WebGPU adapter supported features (" << supportedFeatures.featureCount
+               << "):" << utils::io::endl;
+    if (supportedFeatures.featureCount > 0 && supportedFeatures.features != nullptr) {
+        std::for_each(supportedFeatures.features,
+                supportedFeatures.features + supportedFeatures.featureCount,
+                [](wgpu::FeatureName const name) {
+                    std::stringstream nameStream{};
+                    nameStream << name;
+                    FWGPU_LOGI << "  " << nameStream.str().data() << utils::io::endl;
+                });
+    }
+    wgpu::Limits supportedLimits{};
+    if (!adapter.GetLimits(&supportedLimits)) {
+        FWGPU_LOGW << "Failed to get WebGPU adapter supported limits" << utils::io::endl;
+    } else {
+        FWGPU_LOGI << "WebGPU adapter supported limits:" << utils::io::endl;
+        printLimits(supportedLimits);
+    }
+}
+#endif
+
+#if FWGPU_ENABLED(FWGPU_PRINT_SYSTEM)
+void printDeviceDetails(wgpu::Device const& device) {
+    wgpu::SupportedFeatures supportedFeatures{};
+    device.GetFeatures(&supportedFeatures);
+    FWGPU_LOGI << "WebGPU device supported features (" << supportedFeatures.featureCount
+               << "):" << utils::io::endl;
+    if (supportedFeatures.featureCount > 0 && supportedFeatures.features != nullptr) {
+        std::for_each(supportedFeatures.features,
+                supportedFeatures.features + supportedFeatures.featureCount,
+                [](wgpu::FeatureName const name) {
+                    std::stringstream nameStream{};
+                    nameStream << name;
+                    FWGPU_LOGI << "  " << nameStream.str().data() << utils::io::endl;
+                });
+    }
+    wgpu::Limits supportedLimits{};
+    if (!device.GetLimits(&supportedLimits)) {
+        FWGPU_LOGW << "Failed to get WebGPU supported device limits" << utils::io::endl;
+    } else {
+        FWGPU_LOGI << "WebGPU device supported limits:" << utils::io::endl;
+        printLimits(supportedLimits);
+    }
+}
+#endif
+
+}// namespace
+
 Driver* WebGPUDriver::create(WebGPUPlatform& platform, const Platform::DriverConfig& driverConfig) noexcept {
     constexpr size_t defaultSize = FILAMENT_WEBGPU_HANDLE_ARENA_SIZE_IN_MB * 1024U * 1024U;
     Platform::DriverConfig validConfig {driverConfig};
@@ -51,16 +220,23 @@ Driver* WebGPUDriver::create(WebGPUPlatform& platform, const Platform::DriverCon
     return new WebGPUDriver(platform, validConfig);
 }
 
-WebGPUDriver::WebGPUDriver(WebGPUPlatform& platform,
-        const Platform::DriverConfig& driverConfig) noexcept
+WebGPUDriver::WebGPUDriver(WebGPUPlatform& platform, const Platform::DriverConfig& driverConfig) noexcept
     : mPlatform(platform),
-      mHandleAllocator("Handles", driverConfig.handleArenaSize,
-              driverConfig.disableHandleUseAfterFreeCheck, driverConfig.disableHeapHandleTags) {
+      mHandleAllocator("Handles",
+              driverConfig.handleArenaSize,
+              driverConfig.disableHandleUseAfterFreeCheck,
+              driverConfig.disableHeapHandleTags) {
+#if FWGPU_ENABLED(FWGPU_PRINT_SYSTEM)
+    printInstanceDetails(mPlatform.getInstance());
+#endif
     mAdapter = mPlatform.requestAdapter(nullptr);
+#if FWGPU_ENABLED(FWGPU_PRINT_SYSTEM)
+    printAdapterDetails(mAdapter);
+#endif
     mDevice = mPlatform.requestDevice(mAdapter);
-    wgpu::Limits supportedLimits{};
-    mDevice.GetLimits(&supportedLimits);
-    mMinUniformBufferOffsetAlignment = supportedLimits.minUniformBufferOffsetAlignment;
+#if FWGPU_ENABLED(FWGPU_PRINT_SYSTEM)
+    printDeviceDetails(mDevice);
+#endif
     mQueue = mDevice.GetQueue();
 }
 
@@ -174,20 +350,6 @@ void WebGPUDriver::destroyProgram(Handle<HwProgram> ph) {
 }
 
 void WebGPUDriver::destroyRenderTarget(Handle<HwRenderTarget> rth) {
-    if (rth) {
-        WGPURenderTarget* rt = handleCast<WGPURenderTarget>(rth);
-        if (rt == mDefaultRenderTarget) {
-            mDefaultRenderTarget = nullptr;
-        }
-        if (rt == mCurrentRenderTarget) {
-            mCurrentRenderTarget = nullptr;
-        }
-        // WGPURenderTarget destructor is trivial.
-        // The HwTexture handles stored within WGPURenderTarget (via MRT, TargetBufferInfo)
-        // are not owned by WGPURenderTarget, so they are not destroyed here.
-        // They are destroyed via WebGPUDriver::destroyTexture.
-        destructHandle<WGPURenderTarget>(rth);
-    }
 }
 
 void WebGPUDriver::destroySwapChain(Handle<HwSwapChain> sch) {
@@ -210,19 +372,6 @@ void WebGPUDriver::destroyDescriptorSetLayout(Handle<HwDescriptorSetLayout> tqh)
 }
 
 void WebGPUDriver::destroyDescriptorSet(Handle<HwDescriptorSet> tqh) {
-    auto* bindGroup = handleCast<WebGPUDescriptorSet>(tqh);
-    assert_invariant(bindGroup);
-    if (bindGroup->getBindGroup() != nullptr) {
-        for (size_t i = 0; i < MAX_DESCRIPTOR_SET_COUNT; i++) {
-            if (mCurrentDescriptorSets[i].bindGroup != nullptr &&
-                    bindGroup->getBindGroup().Get() == mCurrentDescriptorSets[i].bindGroup.Get()) {
-                // Clear this from our current entries
-                mCurrentDescriptorSets[i].bindGroup = nullptr;
-                mCurrentDescriptorSets[i].offsets.clear();
-                mCurrentDescriptorSets[i].offsetCount = 0;
-            }
-        }
-    }
     if (tqh) {
         destructHandle<WebGPUDescriptorSet>(tqh);
     }
@@ -319,10 +468,11 @@ void WebGPUDriver::createSwapChainR(Handle<HwSwapChain> sch, void* nativeWindow,
     mSwapChain = constructHandle<WebGPUSwapChain>(sch, std::move(surface), surfaceSize, mAdapter,
             mDevice, flags);
     assert_invariant(mSwapChain);
-
-    FWGPU_LOGW << "WebGPU support is highly experimental, in development, and tested for only a "
-                  "small set of simple samples (e.g. hellotriangle and texturedquad), thus issues "
-                  "are likely to be encountered at this stage."
+    WebGPUDescriptorSet::initializeDummyResourcesIfNotAlready(mDevice,
+            mSwapChain->getColorFormat());
+    FWGPU_LOGW << "WebGPU support is still essentially a no-op at this point in development (only "
+                  "background components have been instantiated/selected, such as surface/screen, "
+                  "graphics device/GPU, etc.), thus nothing is being drawn to the screen."
                << utils::io::endl;
 #if !FWGPU_ENABLED(FWGPU_PRINT_SYSTEM) && !defined(NDEBUG)
     FWGPU_LOGI << "If the FILAMENT_BACKEND_DEBUG_FLAG variable were set with the " << utils::io::hex
@@ -427,21 +577,7 @@ void WebGPUDriver::createDefaultRenderTargetR(Handle<HwRenderTarget> rth, int) {
 
 void WebGPUDriver::createRenderTargetR(Handle<HwRenderTarget> rth, TargetBufferFlags targets,
         uint32_t width, uint32_t height, uint8_t samples, uint8_t layerCount, MRT color,
-        TargetBufferInfo depth, TargetBufferInfo stencil) {
-    // The `targets` flags indicate which of the `color`, `depth`, `stencil` TargetBufferInfo
-    // are actually active for this render target.
-    // We'll pass all TargetBufferInfo to WGPURenderTarget; it will use them if their handles are valid.
-
-    // Ensure that textures intended for use as attachments were created with
-    // wgpu::TextureUsage::RenderAttachment. This check should ideally be in createTextureR
-    // or validated here if possible.
-
-    // The `layerCount` parameter might be for creating array textures that this RT targets.
-    // Individual attachments (color[i].layer, depth.layer, stencil.layer) specify which layer
-    // of an array texture to bind. For now, we assume textures are pre-configured.
-
-    constructHandle<WGPURenderTarget>(rth, width, height, samples, color, depth, stencil);
-}
+        TargetBufferInfo depth, TargetBufferInfo stencil) {}
 
 void WebGPUDriver::createFenceR(Handle<HwFence> fh, int) {}
 
@@ -585,20 +721,17 @@ size_t WebGPUDriver::getMaxArrayTextureLayers() {
 
 void WebGPUDriver::updateIndexBuffer(Handle<HwIndexBuffer> ibh, BufferDescriptor&& p,
         uint32_t byteOffset) {
-    handleCast<WGPUIndexBuffer>(ibh)->updateGPUBuffer(p, byteOffset, mQueue);
-    scheduleDestroy(std::move(p));
+    updateGPUBuffer(handleCast<WGPUIndexBuffer>(ibh), std::move(p), byteOffset);
 }
 
 void WebGPUDriver::updateBufferObject(Handle<HwBufferObject> ibh, BufferDescriptor&& p,
         uint32_t byteOffset) {
-    handleCast<WGPUBufferObject>(ibh)->updateGPUBuffer(p, byteOffset, mQueue);
-    scheduleDestroy(std::move(p));
+    updateGPUBuffer(handleCast<WGPUBufferObject>(ibh), std::move(p), byteOffset);
 }
 
 void WebGPUDriver::updateBufferObjectUnsynchronized(Handle<HwBufferObject> ibh,
         BufferDescriptor&& p, uint32_t byteOffset) {
-    handleCast<WGPUBufferObject>(ibh)->updateGPUBuffer(p, byteOffset, mQueue);
-    scheduleDestroy(std::move(p));
+    updateGPUBuffer(handleCast<WGPUBufferObject>(ibh), std::move(p), byteOffset);
 }
 
 void WebGPUDriver::resetBufferObject(Handle<HwBufferObject> boh) {
@@ -610,76 +743,15 @@ void WebGPUDriver::setVertexBufferObject(Handle<HwVertexBuffer> vbh, uint32_t in
     auto* vertexBuffer = handleCast<WGPUVertexBuffer>(vbh);
     auto* bufferObject = handleCast<WGPUBufferObject>(boh);
     assert_invariant(index < vertexBuffer->buffers.size());
-    assert_invariant(bufferObject->getBuffer().GetUsage() & wgpu::BufferUsage::Vertex);
-    vertexBuffer->buffers[index] = bufferObject->getBuffer();
+    assert_invariant(bufferObject->buffer.GetUsage() & wgpu::BufferUsage::Vertex);
+    vertexBuffer->buffers[index] = bufferObject->buffer;
 }
 
-void WebGPUDriver::update3DImage(Handle<HwTexture> th, uint32_t level, uint32_t xoffset,
-        uint32_t yoffset, uint32_t zoffset, uint32_t width, uint32_t height, uint32_t depth,
-        PixelBufferDescriptor&& p) {
-    PixelBufferDescriptor* data = &p;
-    PixelBufferDescriptor reshapedData;
-    if (reshape(p, reshapedData)) {
-        data = &reshapedData;
-    }
-    auto texture = handleCast<WGPUTexture>(th);
-
-    // TODO: Writing to a depth texture is illegal and errors. I'm not sure why Filament is trying
-    // to do so, but early returning is working?
-    if(texture->getAspect() == wgpu::TextureAspect::DepthOnly){
-        scheduleDestroy(std::move(p));
-        return;
-    }
-    size_t blockWidth = texture->getBlockWidth();
-    size_t blockHeight = texture->getBlockHeight();
-    // WebGPU specification requires that for compressed textures, the x and y offsets
-    // must be a multiple of the compressed texture format's block width and height.
-    // See: https://www.w3.org/TR/webgpu/#abstract-opdef-validating-gputexelcopytextureinfo
-    if (blockWidth > 1 || blockHeight > 1) {
-        FILAMENT_CHECK_PRECONDITION(xoffset % blockWidth == 0)
-                << "xoffset must be aligned to blockwidth, but offset is " << blockWidth
-                << "and offset is " << xoffset;
-        FILAMENT_CHECK_PRECONDITION(yoffset % blockHeight == 0)
-                << "yoffset must be aligned to blockHeight, but offset is " << blockHeight
-                << "and offset is " << yoffset;
-    }
-
-    auto copyInfo = wgpu::TexelCopyTextureInfo{ .texture = texture->getTexture(),
-        .mipLevel = level,
-        .origin = { .x = xoffset, .y = yoffset, .z = zoffset },
-        .aspect = texture->getAspect() };
-    uint32_t bytesPerRow = static_cast<uint32_t>(
-            PixelBufferDescriptor::computePixelSize(data->format, data->type) * width);
-    auto extent = wgpu::Extent3D{ .width = width, .height = height, .depthOrArrayLayers = depth };
-
-    const uint8_t* dataBuff = static_cast<const uint8_t*>(data->buffer);
-    size_t dataSize = data->size;
-    std::unique_ptr<uint8_t[]> paddedBuffer;
-
-    if (bytesPerRow % 256 != 0) {
-        uint32_t padding = 256 - (bytesPerRow % 256);
-        uint32_t paddedBytesPerRow = bytesPerRow + padding;
-
-        size_t paddedBufferSize = static_cast<size_t>(paddedBytesPerRow) * height * depth;
-        paddedBuffer = std::make_unique<uint8_t[]>(paddedBufferSize);
-        uint8_t* dest = paddedBuffer.get();
-
-        for (uint32_t z = 0; z < depth; ++z) {
-            for (uint32_t y = 0; y < height; ++y) {
-                std::memcpy(dest, dataBuff, bytesPerRow);
-                dest += paddedBytesPerRow;
-                dataBuff += bytesPerRow;
-            }
-        }
-        dataBuff = paddedBuffer.get();
-        dataSize = paddedBufferSize;
-        bytesPerRow = paddedBytesPerRow;
-    }
-
-    auto layout = wgpu::TexelCopyBufferLayout{ .bytesPerRow = bytesPerRow, .rowsPerImage = height };
-
-    mQueue.WriteTexture(&copyInfo, dataBuff, dataSize, &layout, &extent);
-    scheduleDestroy(std::move(p));
+void WebGPUDriver::update3DImage(Handle<HwTexture> th,
+        uint32_t level, uint32_t xoffset, uint32_t yoffset, uint32_t zoffset,
+        uint32_t width, uint32_t height, uint32_t depth,
+        PixelBufferDescriptor&& data) {
+    scheduleDestroy(std::move(data));
 }
 
 void WebGPUDriver::setupExternalImage(void* image) {
@@ -706,82 +778,56 @@ void WebGPUDriver::compilePrograms(CompilerPriorityQueue priority,
 
 void WebGPUDriver::beginRenderPass(Handle<HwRenderTarget> rth, RenderPassParams const& params) {
     assert_invariant(mCommandEncoder);
+
     auto* renderTarget = handleCast<WGPURenderTarget>(rth);
-
-    wgpu::TextureView defaultColorView = nullptr;
-    wgpu::TextureView defaultDepthStencilView = nullptr;
-
-    std::array<wgpu::TextureView, MRT::MAX_SUPPORTED_RENDER_TARGET_COUNT> customColorViews{};
-    uint32_t customColorViewCount = 0;
-    wgpu::TextureView customDepthView = nullptr;
-    wgpu::TextureFormat customDepthFormat = wgpu::TextureFormat::Undefined;
-    wgpu::TextureFormat customStencilFormat = wgpu::TextureFormat::Undefined;
-    wgpu::TextureView customStencilView = nullptr;
-
-    mCurrentRenderTarget = renderTarget;
-    if (renderTarget->isDefaultRenderTarget()) {
-        assert_invariant(mSwapChain && mTextureView);
-        defaultColorView = mTextureView;
-        defaultDepthStencilView = mSwapChain->getDepthTextureView();
+    // if (renderTarget == mDefaultRenderTarget) {
+    //     FWGPU_LOGW << "Default render target"
+    //                << utils::io::endl;
+    // } else {
+    //     FWGPU_LOGW << "Non Default render target"
+    //                << utils::io::endl;
+    // }
+    wgpu::RenderPassDescriptor renderPassDescriptor2;
+    wgpu::RenderPassDepthStencilAttachment depthStencilAttachment{
+        .view = mSwapChain->getDepthTextureView(),
+        .depthLoadOp = WGPURenderTarget::getLoadOperation(params, TargetBufferFlags::DEPTH),
+        .depthStoreOp = WGPURenderTarget::getStoreOperation(params, TargetBufferFlags::DEPTH),
+        .depthClearValue = static_cast<float>(params.clearDepth),
+        .depthReadOnly = (params.readOnlyDepthStencil & RenderPassParams::READONLY_DEPTH) > 0,
+        .stencilLoadOp = WGPURenderTarget::getLoadOperation(params, TargetBufferFlags::STENCIL),
+        .stencilStoreOp = WGPURenderTarget::getStoreOperation(params, TargetBufferFlags::STENCIL),
+        .stencilClearValue = params.clearStencil,
+        .stencilReadOnly = (params.readOnlyDepthStencil & RenderPassParams::READONLY_STENCIL) > 0
+    };
+    renderTarget->setUpRenderPassAttachments(renderPassDescriptor2, mTextureView, params);
+    renderPassDescriptor2.depthStencilAttachment = &depthStencilAttachment;
+    // TODO: Remove this code once WebGPU pipeline is implemented
+    static float red = 1.0f;
+    if (red - 0.01 > 0) {
+        red -= 0.01;
     } else {
-        // Resolve views for custom render target
-        const auto& colorInfos = renderTarget->getColorAttachmentInfos();
-        for (int i = 0; i < MRT::MAX_SUPPORTED_RENDER_TARGET_COUNT; ++i) {
-            if (colorInfos[i].handle) {
-                auto* hwTexture = handleCast<WGPUTexture>(colorInfos[i].handle);
-                if (hwTexture) {
-                    // TODO: Consider colorInfos[i].level and colorInfos[i].layer for view creation
-                    // if WGPUTexture::getTextureView() isn't sufficient or needs parameters.
-                    customColorViews[customColorViewCount++] = hwTexture->getTextureView();
-
-                }
-            }
-        }
-
-        const auto& depthInfo = renderTarget->getDepthAttachmentInfo();
-        if (depthInfo.handle) {
-            auto* hwTexture = handleCast<WGPUTexture>(depthInfo.handle);
-            if (hwTexture) {
-                customDepthView = hwTexture->getTextureView();
-                customDepthFormat = hwTexture->getFormat();
-            }
-        }
-
-        const auto& stencilInfo = renderTarget->getStencilAttachmentInfo();
-        if (stencilInfo.handle) {
-            // If depth and stencil use the same texture handle, this will re-cast but that's fine.
-            auto* hwTexture = handleCast<WGPUTexture>(stencilInfo.handle);
-            if (hwTexture) {
-                customStencilView = hwTexture->getTextureView();
-                customStencilFormat = hwTexture->getFormat();
-            }
-        }
+        red = 1.0f;
     }
-    wgpu::RenderPassDescriptor renderPassDescriptor{};
-    renderTarget->setUpRenderPassAttachments(renderPassDescriptor,
-            params,
-            defaultColorView,
-            defaultDepthStencilView,
-            customColorViews.data(),
-            customColorViewCount,
-            customDepthView,
-            customStencilView,
-            customDepthFormat,
-            customStencilFormat);
+    assert_invariant(mTextureView);
+    wgpu::RenderPassColorAttachment renderPassColorAttachment = {
+        .view = mTextureView,
+        // TODO: remove this code once WebGPU Pipeline is implemented with render targets, pipeline and buffers.
+        .depthSlice = wgpu::kDepthSliceUndefined,
+        .loadOp = wgpu::LoadOp::Clear,
+        .storeOp = wgpu::StoreOp::Store,
+        .clearValue = wgpu::Color{red, 0 , 0 , 1},
+    };
 
-    mRenderPassEncoder = mCommandEncoder.BeginRenderPass(&renderPassDescriptor);
+    wgpu::RenderPassDescriptor renderPassDescriptor = {
+        .colorAttachmentCount = 1,
+        .colorAttachments = &renderPassColorAttachment,
+        .depthStencilAttachment = nullptr,
+        .timestampWrites = nullptr,
+    };
 
-    // Ensure viewport dimensions are not 0
-    FILAMENT_CHECK_POSTCONDITION(params.viewport.width > 0) << "viewport width is 0?";
-    FILAMENT_CHECK_POSTCONDITION(params.viewport.height > 0) << "viewport height is 0?";
-
-    mRenderPassEncoder.SetViewport(
-            static_cast<float>(params.viewport.left),
-            static_cast<float>(params.viewport.bottom),
-            static_cast<float>(params.viewport.width),
-            static_cast<float>(params.viewport.height),
-            params.depthRange.near,
-            params.depthRange.far);
+    mRenderPassEncoder = mCommandEncoder.BeginRenderPass(&renderPassDescriptor2);
+    mRenderPassEncoder.SetViewport(params.viewport.left, params.viewport.bottom,
+            params.viewport.width, params.viewport.height, params.depthRange.near, params.depthRange.far);
 }
 
 void WebGPUDriver::endRenderPass(int /* dummy */) {
@@ -874,7 +920,7 @@ void WebGPUDriver::bindPipeline(PipelineState const& pipelineState) {
     // VulkanPipelineCache to handle this, may be missing nuance
     static auto pipleineStateHasher = utils::hash::MurmurHashFn<filament::backend::PipelineState>();
     auto hash = pipleineStateHasher(pipelineState);
-    if (mPipelineMap.find(hash) != mPipelineMap.end()) {
+    if(mPipelineMap.find(hash) != mPipelineMap.end()){
         mRenderPassEncoder.SetPipeline(mPipelineMap[hash]);
         return;
     }
@@ -910,95 +956,42 @@ void WebGPUDriver::bindPipeline(PipelineState const& pipelineState) {
             << layoutDescriptor.label;
     auto const* vertexBufferInfo = handleCast<WGPUVertexBufferInfo>(pipelineState.vertexBufferInfo);
     assert_invariant(vertexBufferInfo);
-
-    std::vector<wgpu::TextureFormat> pipelineColorFormats;
-    wgpu::TextureFormat pipelineDepthFormat = wgpu::TextureFormat::Undefined;
-    uint8_t pipelineSamples = 1;
-
-    if (mCurrentRenderTarget->isDefaultRenderTarget()) {
-        pipelineColorFormats.push_back(mSwapChain->getColorFormat());
-        pipelineDepthFormat = mSwapChain->getDepthFormat();
-        pipelineSamples =
-                mCurrentRenderTarget->getSamples();// Default RT should have samples (usually 1)
-    } else {
-        const auto& mrtColorAttachments = mCurrentRenderTarget->getColorAttachmentInfos();
-        for (size_t i = 0; i < MRT::MAX_SUPPORTED_RENDER_TARGET_COUNT; ++i) {
-            if (mrtColorAttachments[i].handle) {
-                const auto* colorTexture = handleCast<WGPUTexture>(mrtColorAttachments[i].handle);
-                if (colorTexture) {
-                    pipelineColorFormats.push_back(colorTexture->getTexture().GetFormat());
-                }
-            }
-        }
-
-        const auto& depthInfo = mCurrentRenderTarget->getDepthAttachmentInfo();
-        const auto& stencilInfo = mCurrentRenderTarget->getStencilAttachmentInfo();
-        if (depthInfo.handle) {
-            FILAMENT_CHECK_POSTCONDITION(!stencilInfo.handle)
-                    << "depth and stencil attachments cannot both be provided for WebGPU";
-            const auto* dfTexture = handleCast<WGPUTexture>(depthInfo.handle);
-            if (dfTexture) pipelineDepthFormat = dfTexture->getTexture().GetFormat();
-        } else {
-            if (stencilInfo.handle) {
-                const auto* sfTexture = handleCast<WGPUTexture>(stencilInfo.handle);
-                // Assuming combined depth/stencil format if only stencil is present
-                if (sfTexture) {
-                    pipelineDepthFormat = sfTexture->getTexture().GetFormat();
-                }
-            }
-        }
-        pipelineSamples = mCurrentRenderTarget->getSamples();
-    }
-
-    if (program->fragmentShaderModule != nullptr) {
-        FILAMENT_CHECK_POSTCONDITION(!pipelineColorFormats.empty())
-                << "Render pipeline with fragment shader must have at least one color target "
-                   "format.";
-    }
-    wgpu::RenderPipeline pipeline = createWebGPURenderPipeline(mDevice, *program, *vertexBufferInfo,
-            layout, pipelineState.rasterState, pipelineState.stencilState,
-            pipelineState.polygonOffset, pipelineState.primitiveType, pipelineColorFormats,
-            pipelineDepthFormat, pipelineSamples);
-    assert_invariant(pipeline);
+    const wgpu::RenderPipeline pipeline = createWebGPURenderPipeline(mDevice, *program,
+            *vertexBufferInfo, layout, pipelineState.rasterState, pipelineState.stencilState,
+            pipelineState.polygonOffset, pipelineState.primitiveType, mSwapChain->getColorFormat(),
+            mSwapChain->getDepthFormat());
     mPipelineMap[hash] = pipeline;
     mRenderPassEncoder.SetPipeline(pipeline);
 }
 
 void WebGPUDriver::bindRenderPrimitive(Handle<HwRenderPrimitive> rph) {
     auto* renderPrimitive = handleCast<WGPURenderPrimitive>(rph);
+
+    // This *must* match the WGPUVertexBufferInfo that was bound in bindPipeline(). But we want
+    // to allow to call this before bindPipeline(), so the validation can only happen in draw()
     auto vbi = handleCast<WGPUVertexBufferInfo>(renderPrimitive->vertexBuffer->vbih);
-    for (const auto& webGPUSlotBindings: vbi->getWebGPUSlotBindingInfos()) {
-        mRenderPassEncoder.SetVertexBuffer(webGPUSlotBindings.slot,
-                renderPrimitive->vertexBuffer->buffers[webGPUSlotBindings.sourceBuffer],
-                webGPUSlotBindings.bufferOffset);
+    assert_invariant(
+            vbi->getVertexBufferLayoutSize() == renderPrimitive->vertexBuffer->buffers.size());
+    for (uint32_t i = 0; i < vbi->getVertexBufferLayoutSize(); i++) {
+        mRenderPassEncoder.SetVertexBuffer(i, renderPrimitive->vertexBuffer->buffers[i]);
     }
 
-    mRenderPassEncoder.SetIndexBuffer(renderPrimitive->indexBuffer->getBuffer(),
+    mRenderPassEncoder.SetIndexBuffer(renderPrimitive->indexBuffer->buffer,
             renderPrimitive->indexBuffer->indexFormat);
 }
 
 void WebGPUDriver::draw2(uint32_t indexOffset, uint32_t indexCount, uint32_t instanceCount) {
-    // We defer actually binding until we actually draw
-    for (size_t i = 0; i < MAX_DESCRIPTOR_SET_COUNT; i++) {
-        auto& binding = mCurrentDescriptorSets[i];
-        if (binding.bindGroup) {
-            mRenderPassEncoder.SetBindGroup(i, binding.bindGroup, binding.offsetCount,
-                    binding.offsets.data());
-        }
-    }
-
-    mRenderPassEncoder.DrawIndexed(indexCount, instanceCount, indexOffset, 0, 0);
+    // Calling DrawIndexed with "firstInstance = 0" results in a NON spinning triangle
+    //    mRenderPassEncoder.DrawIndexed(indexCount, instanceCount, indexOffset, 0, 0);
+    // Calling DrawIndexed with "firstInstance = 1" results in a spinning triangle
+    mRenderPassEncoder.DrawIndexed(indexCount, instanceCount, indexOffset, 0, 1);
+    // Calling Draw with "firstInstance = 0" results in a NON spinning triangle
+    // Calling Draw with "firstInstance = 1" results in a spinning triangle
+    //    mRenderPassEncoder.Draw(indexCount, instanceCount, 0, 1);
 }
 
-void WebGPUDriver::draw(PipelineState pipelineState,
-        Handle<HwRenderPrimitive> renderPrimitiveHandle, uint32_t indexOffset, uint32_t indexCount,
-        uint32_t instanceCount) {
-    WGPURenderPrimitive const* const renderPrimitive =
-            handleCast<WGPURenderPrimitive>(renderPrimitiveHandle);
-    pipelineState.primitiveType = renderPrimitive->type;
-    pipelineState.vertexBufferInfo = renderPrimitive->vertexBuffer->vbih;
-    bindPipeline(pipelineState);
-    bindRenderPrimitive(renderPrimitiveHandle);
+void WebGPUDriver::draw(PipelineState, Handle<HwRenderPrimitive>, uint32_t indexOffset,
+        uint32_t indexCount, uint32_t instanceCount) {
     draw2(indexOffset, indexCount, instanceCount);
 }
 
@@ -1025,11 +1018,8 @@ void WebGPUDriver::updateDescriptorSetBuffer(Handle<HwDescriptorSet> dsh,
     auto buffer = handleCast<WGPUBufferObject>(boh);
     if (!bindGroup->getIsLocked()) {
         // TODO making assumptions that size and offset mean the same thing here.
-        FILAMENT_CHECK_PRECONDITION(offset % mMinUniformBufferOffsetAlignment == 0)
-                << "Binding offset must be multiple of " << mMinUniformBufferOffsetAlignment
-                << "But requested offset is " << offset;
         wgpu::BindGroupEntry entry{ .binding = static_cast<uint32_t>(binding * 2),
-            .buffer = buffer->getBuffer(),
+            .buffer = buffer->buffer,
             .offset = offset,
             .size = size };
         bindGroup->addEntry(entry.binding, std::move(entry));
@@ -1047,7 +1037,7 @@ void WebGPUDriver::updateDescriptorSetTexture(Handle<HwDescriptorSet> dsh,
         auto sampler = makeSampler(params);
         // TODO making assumptions that size and offset mean the same thing here.
         wgpu::BindGroupEntry tEntry{ .binding = static_cast<uint32_t>(binding * 2),
-            .textureView = texture->getTextureView() };
+            .textureView = texture->getTexView() };
         bindGroup->addEntry(tEntry.binding, std::move(tEntry));
 
         wgpu::BindGroupEntry sEntry{ .binding = static_cast<uint32_t>(binding * 2 + 1),
@@ -1058,26 +1048,27 @@ void WebGPUDriver::updateDescriptorSetTexture(Handle<HwDescriptorSet> dsh,
 
 void WebGPUDriver::bindDescriptorSet(Handle<HwDescriptorSet> dsh,
         backend::descriptor_set_t setIndex, backend::DescriptorSetOffsetArray&& offsets) {
-    assert_invariant(setIndex < MAX_DESCRIPTOR_SET_COUNT);
     const auto bindGroup = handleCast<WebGPUDescriptorSet>(dsh);
     const auto wbg = bindGroup->lockAndReturn(mDevice);
-
-    mCurrentDescriptorSets[setIndex] = { .bindGroup = wbg,
-        .offsetCount = bindGroup->countEntitiesWithDynamicOffsets(),
-        .offsets = std::move(offsets) };
+    assert_invariant(mRenderPassEncoder);
+    // TODO is this how we should be getting the dynamic offsets?
+    //      should we add offsets for unused entries or is the input already have them?
+    //      this implementation assumes unused entries are not provided, and adds dummy values.
+    //      The count also includes unused entities, as not doing so produces errors
+    const size_t dynamicOffsetCount = bindGroup->countEntitiesWithDynamicOffsets();
+    uint32_t const* const dynamicOffsetsWithUnused = bindGroup->setDynamicOffsets(offsets.data());
+    mRenderPassEncoder.SetBindGroup(setIndex, wbg, dynamicOffsetCount, dynamicOffsetsWithUnused);
 }
 
 void WebGPUDriver::setDebugTag(HandleBase::HandleId handleId, utils::CString tag) {
 }
-
 wgpu::Sampler WebGPUDriver::makeSampler(SamplerParams const& params) {
-    wgpu::SamplerDescriptor desc{};
+    wgpu::SamplerDescriptor desc;
 
     desc.label = "TODO";
     desc.addressModeU = fWrapModeToWAddressMode(params.wrapS);
     desc.addressModeV = fWrapModeToWAddressMode(params.wrapR);
     desc.addressModeW = fWrapModeToWAddressMode(params.wrapT);
-
     switch (params.filterMag) {
         case SamplerMagFilter::NEAREST: {
             desc.magFilter = wgpu::FilterMode::Nearest;
@@ -1088,16 +1079,20 @@ wgpu::Sampler WebGPUDriver::makeSampler(SamplerParams const& params) {
             break;
         }
     }
-
     switch (params.filterMin) {
         case SamplerMinFilter::NEAREST: {
             desc.minFilter = wgpu::FilterMode::Nearest;
-            desc.mipmapFilter = wgpu::MipmapFilterMode::Undefined;
+            // Metal Driver uses an explicit not-mipmapped value webgpu lacks. Nearest should
+            // suffice
+            desc.mipmapFilter = wgpu::MipmapFilterMode::Nearest;
             break;
         }
         case SamplerMinFilter::LINEAR: {
             desc.minFilter = wgpu::FilterMode::Linear;
-            desc.mipmapFilter = wgpu::MipmapFilterMode::Undefined;
+            // Metal Driver uses an explicit not-mipmapped value webgpu lacks. Nearest should
+            // suffice
+
+            desc.mipmapFilter = wgpu::MipmapFilterMode::Nearest;
             break;
         }
         case SamplerMinFilter::NEAREST_MIPMAP_NEAREST: {
@@ -1108,11 +1103,13 @@ wgpu::Sampler WebGPUDriver::makeSampler(SamplerParams const& params) {
         case SamplerMinFilter::LINEAR_MIPMAP_NEAREST: {
             desc.minFilter = wgpu::FilterMode::Linear;
             desc.mipmapFilter = wgpu::MipmapFilterMode::Nearest;
+
             break;
         }
         case SamplerMinFilter::NEAREST_MIPMAP_LINEAR: {
             desc.minFilter = wgpu::FilterMode::Nearest;
             desc.mipmapFilter = wgpu::MipmapFilterMode::Linear;
+
             break;
         }
         case SamplerMinFilter::LINEAR_MIPMAP_LINEAR: {
@@ -1121,48 +1118,48 @@ wgpu::Sampler WebGPUDriver::makeSampler(SamplerParams const& params) {
             break;
         }
     }
-    if (params.compareMode == SamplerCompareMode::COMPARE_TO_TEXTURE) {
-        switch (params.compareFunc) {
-            case SamplerCompareFunc::LE: {
-                desc.compare = wgpu::CompareFunction::LessEqual;
-                break;
-            }
-            case SamplerCompareFunc::GE: {
-                desc.compare = wgpu::CompareFunction::GreaterEqual;
-                break;
-            }
-            case SamplerCompareFunc::L: {
-                desc.compare = wgpu::CompareFunction::Less;
-                break;
-            }
-            case SamplerCompareFunc::G: {
-                desc.compare = wgpu::CompareFunction::Greater;
-                break;
-            }
-            case SamplerCompareFunc::E: {
-                desc.compare = wgpu::CompareFunction::Equal;
-                break;
-            }
-            case SamplerCompareFunc::NE: {
-                desc.compare = wgpu::CompareFunction::NotEqual;
-                break;
-            }
-            case SamplerCompareFunc::A: {
-                desc.compare = wgpu::CompareFunction::Always;
-                break;
-            }
-            case SamplerCompareFunc::N: {
-                desc.compare = wgpu::CompareFunction::Never;
-                break;
-            }
+    switch (params.compareFunc) {
+        case SamplerCompareFunc::LE: {
+            desc.compare = wgpu::CompareFunction::LessEqual;
+            break;
+        }
+        case SamplerCompareFunc::GE: {
+            desc.compare = wgpu::CompareFunction::GreaterEqual;
+            break;
+        }
+        case SamplerCompareFunc::L: {
+            desc.compare = wgpu::CompareFunction::Less;
+            break;
+        }
+        case SamplerCompareFunc::G: {
+            desc.compare = wgpu::CompareFunction::Greater;
+            break;
+        }
+        case SamplerCompareFunc::E: {
+            desc.compare = wgpu::CompareFunction::Equal;
+            break;
+        }
+        case SamplerCompareFunc::NE: {
+            desc.compare = wgpu::CompareFunction::NotEqual;
+            break;
+        }
+        case SamplerCompareFunc::A: {
+            desc.compare = wgpu::CompareFunction::Always;
+            break;
+        }
+        case SamplerCompareFunc::N: {
+            desc.compare = wgpu::CompareFunction::Never;
+            break;
         }
     }
 
     desc.maxAnisotropy = 1u << params.anisotropyLog2;
 
-    // Unused: WGPU lodMinClamp/lodMaxClamp unnecessary
 
-    return mDevice.CreateSampler(&desc);
+    // Unused: Filament's compareMode, WGPU lodMinClamp/lodMaxClamp
+
+    //TODO Once we can properly map to descriptorsetlayout use the sampler.
+    return mDevice.CreateSampler(/*&desc*/);
 }
 wgpu::AddressMode WebGPUDriver::fWrapModeToWAddressMode(const SamplerWrapMode& fWrapMode) {
     switch (fWrapMode) {
@@ -1182,4 +1179,5 @@ wgpu::AddressMode WebGPUDriver::fWrapModeToWAddressMode(const SamplerWrapMode& f
     return wgpu::AddressMode::Undefined;
 }
 
+
 } // namespace filament

filament/backend/src/webgpu/WebGPUDriver.h

@@ -58,13 +58,32 @@ private:
     [[nodiscard]] ShaderLanguage getShaderLanguage() const noexcept final;
     [[nodiscard]] wgpu::Sampler makeSampler(SamplerParams const& params);
     [[nodiscard]] static wgpu::AddressMode fWrapModeToWAddressMode(const filament::backend::SamplerWrapMode& fUsage);
+    template<typename GPUBufferObject>
+    void updateGPUBuffer(GPUBufferObject* gpuBufferObject, BufferDescriptor&& bufferDescriptor,
+            uint32_t byteOffset) {
+        FILAMENT_CHECK_PRECONDITION(bufferDescriptor.buffer)
+                << "copyIntoBuffer called with a null buffer";
+        FILAMENT_CHECK_PRECONDITION(
+                bufferDescriptor.size + byteOffset <= gpuBufferObject->buffer.GetSize())
+                << "Attempting to copy " << bufferDescriptor.size << " bytes into a buffer of size "
+                << gpuBufferObject->buffer.GetSize() << " at offset " << byteOffset;
+
+        // TODO: All buffer objects are created with CopyDst usage.
+        // This may have some performance implications. That should be investigated later.
+        assert_invariant(gpuBufferObject->buffer.GetUsage() & wgpu::BufferUsage::CopyDst);
+
+        // WriteBuffer is an async call. But cpu buffer data is already written to the staging
+        // buffer on return from the WriteBuffer.
+        mQueue.WriteBuffer(gpuBufferObject->buffer, byteOffset, bufferDescriptor.buffer,
+                bufferDescriptor.size);
+        scheduleDestroy(std::move(bufferDescriptor));
+    }
 
     // the platform (e.g. OS) specific aspects of the WebGPU backend are strictly only
     // handled in the WebGPUPlatform
     WebGPUPlatform& mPlatform;
     wgpu::Adapter mAdapter = nullptr;
     wgpu::Device mDevice = nullptr;
-    uint32_t mMinUniformBufferOffsetAlignment;
     wgpu::Queue mQueue = nullptr;
     void* mNativeWindow = nullptr;
     WebGPUSwapChain* mSwapChain = nullptr;
@@ -74,16 +93,8 @@ private:
     wgpu::RenderPassEncoder mRenderPassEncoder = nullptr;
     wgpu::CommandBuffer mCommandBuffer = nullptr;
     WGPURenderTarget* mDefaultRenderTarget = nullptr;
-    WGPURenderTarget* mCurrentRenderTarget = nullptr;
 
     tsl::robin_map<uint32_t, wgpu::RenderPipeline> mPipelineMap;
-
-    struct DescriptorSetBindingInfo{
-        wgpu::BindGroup bindGroup;
-        size_t offsetCount;
-        backend::DescriptorSetOffsetArray offsets;
-    };
-    std::array<DescriptorSetBindingInfo,MAX_DESCRIPTOR_SET_COUNT> mCurrentDescriptorSets;
     /*
      * Driver interface
      */

filament/backend/src/webgpu/WebGPUHandles.cpp

@@ -19,8 +19,7 @@
 #include <backend/DriverEnums.h>
 
 #include <utils/BitmaskEnum.h>
-#include <utils/Panic.h>
-#include <private/backend/BackendUtils.h>
+
 #include <webgpu/webgpu_cpp.h>
 
 #include <algorithm>
@@ -41,6 +40,15 @@ constexpr wgpu::BufferUsage getBufferObjectUsage(
     }
 }
 
+wgpu::Buffer createBuffer(wgpu::Device const& device, wgpu::BufferUsage usage, uint32_t size,
+        char const* label) {
+    wgpu::BufferDescriptor descriptor{ .label = label,
+        .usage = usage,
+        .size = size,
+        .mappedAtCreation = false };
+    return device.CreateBuffer(&descriptor);
+}
+
 wgpu::VertexFormat getVertexFormat(filament::backend::ElementType type, bool normalized, bool integer) {
     using ElementType = filament::backend::ElementType;
     using VertexFormat = wgpu::VertexFormat;
@@ -68,7 +76,7 @@ wgpu::VertexFormat getVertexFormat(filament::backend::ElementType type, bool nor
             case ElementType::BYTE4: return VertexFormat::Snorm8x4;
             case ElementType::UBYTE4: return VertexFormat::Unorm8x4;
             case ElementType::SHORT4: return VertexFormat::Snorm16x4;
-            case ElementType::USHORT4: return VertexFormat::Unorm16x4;
+            case ElementType::USHORT4: return VertexFormat::Unorm8x4;
             default:
                 FILAMENT_CHECK_POSTCONDITION(false) << "Normalized format does not exist.";
                 return VertexFormat::Float32x3;
@@ -126,7 +134,7 @@ wgpu::StringView getUserTextureLabel(filament::backend::SamplerType target) {
         case SamplerType::SAMPLER_3D:
             return "a_3D_user_texture";
         case SamplerType::SAMPLER_CUBEMAP_ARRAY:
-            return "a_cube_map_array_user_texture";
+            return "a_cube_mape_array_user_texture";
     }
 }
 
@@ -145,7 +153,7 @@ wgpu::StringView getUserTextureViewLabel(filament::backend::SamplerType target)
         case SamplerType::SAMPLER_3D:
             return "a_3D_user_texture_view";
         case SamplerType::SAMPLER_CUBEMAP_ARRAY:
-            return "a_cube_map_array_user_texture_view";
+            return "a_cube_mape_array_user_texture_view";
     }
 }
 
@@ -153,142 +161,51 @@ wgpu::StringView getUserTextureViewLabel(filament::backend::SamplerType target)
 
 namespace filament::backend {
 
-void WGPUBufferBase::createBuffer(const wgpu::Device& device, wgpu::BufferUsage usage,
-        uint32_t size, const char* label) {
-    // Write size must be divisible by 4. If the whole buffer is written to as is common, so must
-    // the buffer size.
-    size += (4 - (size % 4)) % 4;
-    wgpu::BufferDescriptor descriptor{ .label = label,
-        .usage = usage,
-        .size = size,
-        .mappedAtCreation = false };
-    buffer = device.CreateBuffer(&descriptor);
-}
-
-void WGPUBufferBase::updateGPUBuffer(BufferDescriptor& bufferDescriptor, uint32_t byteOffset,
-        wgpu::Queue queue) {
-    FILAMENT_CHECK_PRECONDITION(bufferDescriptor.buffer)
-            << "copyIntoBuffer called with a null buffer";
-    FILAMENT_CHECK_PRECONDITION(bufferDescriptor.size + byteOffset <= buffer.GetSize())
-            << "Attempting to copy " << bufferDescriptor.size << " bytes into a buffer of size "
-            << buffer.GetSize() << " at offset " << byteOffset;
-    FILAMENT_CHECK_PRECONDITION(byteOffset % 4 == 0)
-            << "Byte offset must be a multiple of 4 but is " << byteOffset;
-
-    // TODO: All buffer objects are created with CopyDst usage.
-    // This may have some performance implications. That should be investigated later.
-    assert_invariant(buffer.GetUsage() & wgpu::BufferUsage::CopyDst);
-
-    size_t remainder = bufferDescriptor.size % 4;
-
-    // WriteBuffer is an async call. But cpu buffer data is already written to the staging
-    // buffer on return from the WriteBuffer.
-    auto legalSize = bufferDescriptor.size - remainder;
-    queue.WriteBuffer(buffer, byteOffset, bufferDescriptor.buffer, legalSize);
-    if (remainder != 0) {
-        const uint8_t* remainderStart =
-                static_cast<const uint8_t*>(bufferDescriptor.buffer) + legalSize;
-        memcpy(mRemainderChunk.data(), remainderStart, remainder);
-        // Pad the remainder with zeros to ensure deterministic behavior, though GPU shouldn't
-        // access this
-        std::memset(mRemainderChunk.data() + remainder, 0, 4 - remainder);
-
-        queue.WriteBuffer(buffer, byteOffset + legalSize, &mRemainderChunk, 4);
-    }
-}
-
-static constexpr uint32_t DUMMY_WEBGPU_SLOT = 0;
-
 WGPUVertexBufferInfo::WGPUVertexBufferInfo(uint8_t bufferCount, uint8_t attributeCount,
         AttributeArray const& attributes)
     : HwVertexBufferInfo(bufferCount, attributeCount),
-      // TODO: max limits may not be supported by webgpu driver. This should be addressed in the
-      // hardening part.
-      mVertexBufferLayouts(MAX_VERTEX_BUFFER_COUNT),
-      mVertexAttributes(MAX_VERTEX_BUFFER_COUNT) {
-
-    // It starts from 1 because slot 0 is now reserved for the dummy.
-    uint32_t currentWebGPUSlotIndex = 1;
-    // A reasonable dummy stride (e.g., for vec4)
-    const uint32_t DUMMY_STRIDE = 16;
-
-    // Initialize the layout for the dummy slot (slot 0)
-    mVertexBufferLayouts[DUMMY_WEBGPU_SLOT].arrayStride = DUMMY_STRIDE;
-    mVertexBufferLayouts[DUMMY_WEBGPU_SLOT].stepMode = wgpu::VertexStepMode::Vertex;
-    mVertexBufferLayouts[DUMMY_WEBGPU_SLOT].attributeCount = 0;
-
-    mWebGPUSlotBindingInfos.push_back({
-        .sourceBuffer = 0,
-        .slot = DUMMY_WEBGPU_SLOT,
-        .bufferOffset = 0,
-        .stride = DUMMY_STRIDE,
-    });
-
-    for (uint32_t attributeIndex = 0; attributeIndex < attributes.size(); ++attributeIndex) {
-        const auto& attribute = attributes[attributeIndex];
-
-        bool const isInteger = attribute.flags & Attribute::FLAG_INTEGER_TARGET;
-        bool const isNormalized = attribute.flags & Attribute::FLAG_NORMALIZED;
-        wgpu::VertexFormat vertexFormat = getVertexFormat(attribute.type, isNormalized, isInteger);
-
-        if (attribute.buffer == Attribute::BUFFER_UNUSED) {
-            // Use some dummy format
-            vertexFormat = isInteger ? wgpu::VertexFormat::Uint8x4 : wgpu::VertexFormat::Unorm8x4;
-            mVertexAttributes[DUMMY_WEBGPU_SLOT].push_back({
-                .format = vertexFormat,
-                .offset = 0,
-                .shaderLocation = attributeIndex,
-            });
-            mVertexBufferLayouts[DUMMY_WEBGPU_SLOT].attributeCount++;
+      mVertexBufferLayout(bufferCount),
+      mAttributes(bufferCount) {
+    assert_invariant(attributeCount > 0);
+    assert_invariant(bufferCount > 0);
+    for (uint32_t attribIndex = 0; attribIndex < attributes.size(); attribIndex++) {
+        Attribute const& attrib = attributes[attribIndex];
+        // Ignore the attributes which are not bind to vertex buffers.
+        if (attrib.buffer == Attribute::BUFFER_UNUSED) {
             continue;
         }
 
-        auto it = std::find_if(mWebGPUSlotBindingInfos.begin(), mWebGPUSlotBindingInfos.end(),
-                [&](const auto& info) {
-                    return info.sourceBuffer == attribute.buffer && info.stride == attribute.stride;
-                });
+        assert_invariant(attrib.buffer < bufferCount);
+        bool const isInteger = attrib.flags & Attribute::FLAG_INTEGER_TARGET;
+        bool const isNormalized = attrib.flags & Attribute::FLAG_NORMALIZED;
+        wgpu::VertexFormat vertexFormat = getVertexFormat(attrib.type, isNormalized, isInteger);
 
-        uint32_t assignedSlot;
-        if (it != mWebGPUSlotBindingInfos.end()) {
-            assignedSlot = it->slot;
-        } else {
-            // New combination, allocate a new WebGPU slot
-            assert_invariant(currentWebGPUSlotIndex < MAX_VERTEX_BUFFER_COUNT);
-            assignedSlot = currentWebGPUSlotIndex++;
-
-            mWebGPUSlotBindingInfos.push_back({
-                .sourceBuffer = attribute.buffer,
-                .slot = assignedSlot,
-                .bufferOffset = attribute.offset - (attribute.offset % attribute.stride),
-                .stride = attribute.stride,
-            });
-
-            mVertexBufferLayouts[assignedSlot].arrayStride = attribute.stride;
-            mVertexBufferLayouts[assignedSlot].stepMode = wgpu::VertexStepMode::Vertex;
-            mVertexBufferLayouts[assignedSlot].attributeCount = 0;
-        }
-
-        mVertexAttributes[assignedSlot].push_back({
+        // Attributes are sequential per buffer
+        mAttributes[attrib.buffer].push_back({
             .format = vertexFormat,
-            .offset = attribute.offset % attribute.stride,
-            .shaderLocation = attributeIndex,
+            .offset = attrib.offset,
+            .shaderLocation = attribIndex,
         });
-        mVertexBufferLayouts[assignedSlot].attributeCount++;
+
+        mVertexBufferLayout[attrib.buffer].stepMode = wgpu::VertexStepMode::Vertex;
+        if (mVertexBufferLayout[attrib.buffer].arrayStride == 0) {
+            mVertexBufferLayout[attrib.buffer].arrayStride = attrib.stride;
+        } else {
+            assert_invariant(mVertexBufferLayout[attrib.buffer].arrayStride == attrib.stride);
+        }
     }
 
-    mVertexBufferLayouts.resize(currentWebGPUSlotIndex);
-
-    for (const auto& info: mWebGPUSlotBindingInfos) {
-        mVertexBufferLayouts[info.slot].attributes = mVertexAttributes[info.slot].data();
+    for (uint32_t bufferIndex = 0; bufferIndex < bufferCount; bufferIndex++) {
+        mVertexBufferLayout[bufferIndex].attributeCount = mAttributes[bufferIndex].size();
+        mVertexBufferLayout[bufferIndex].attributes = mAttributes[bufferIndex].data();
     }
 }
 
 WGPUIndexBuffer::WGPUIndexBuffer(wgpu::Device const& device, uint8_t elementSize,
         uint32_t indexCount)
-    : indexFormat(elementSize == 2 ? wgpu::IndexFormat::Uint16 : wgpu::IndexFormat::Uint32) {
-    createBuffer(device, wgpu::BufferUsage::CopyDst | wgpu::BufferUsage::Index,
-            elementSize * indexCount, "index_buffer");
-}
+    : buffer(createBuffer(device, wgpu::BufferUsage::CopyDst | wgpu::BufferUsage::Index,
+              elementSize * indexCount, "index_buffer")),
+      indexFormat(elementSize == 2 ? wgpu::IndexFormat::Uint16 : wgpu::IndexFormat::Uint32) {}
 
 
 WGPUVertexBuffer::WGPUVertexBuffer(wgpu::Device const& device, uint32_t vertexCount,
@@ -299,10 +216,10 @@ WGPUVertexBuffer::WGPUVertexBuffer(wgpu::Device const& device, uint32_t vertexCo
 
 WGPUBufferObject::WGPUBufferObject(wgpu::Device const& device, BufferObjectBinding bindingType,
         uint32_t byteCount)
-    : HwBufferObject(byteCount) {
-    createBuffer(device, wgpu::BufferUsage::CopyDst | getBufferObjectUsage(bindingType), byteCount,
-            "buffer_object");
-}
+    : HwBufferObject(byteCount),
+      buffer(createBuffer(device, wgpu::BufferUsage::CopyDst | getBufferObjectUsage(bindingType),
+              byteCount, "buffer_object")),
+      bufferObjectBinding(bindingType) {}
 
 wgpu::ShaderStage WebGPUDescriptorSetLayout::filamentStageToWGPUStage(ShaderStageFlags fFlags) {
     wgpu::ShaderStage retStages = wgpu::ShaderStage::None;
@@ -337,7 +254,8 @@ WebGPUDescriptorSetLayout::WebGPUDescriptorSetLayout(DescriptorSetLayout const&
 
     unsigned int samplerCount =
             std::count_if(layout.bindings.begin(), layout.bindings.end(), [](auto& fEntry) {
-                return DescriptorSetLayoutBinding::isSampler(fEntry.type);
+                return fEntry.type == DescriptorType::SAMPLER ||
+                       fEntry.type == DescriptorType::SAMPLER_EXTERNAL;
             });
 
 
@@ -353,45 +271,26 @@ WebGPUDescriptorSetLayout::WebGPUDescriptorSetLayout(DescriptorSetLayout const&
         entryInfo.binding = wEntry.binding;
 
         switch (fEntry.type) {
-            case DescriptorType::SAMPLER_2D_FLOAT:
-            case DescriptorType::SAMPLER_2D_INT:
-            case DescriptorType::SAMPLER_2D_UINT:
-            case DescriptorType::SAMPLER_2D_DEPTH:
-            case DescriptorType::SAMPLER_2D_ARRAY_FLOAT:
-            case DescriptorType::SAMPLER_2D_ARRAY_INT:
-            case DescriptorType::SAMPLER_2D_ARRAY_UINT:
-            case DescriptorType::SAMPLER_2D_ARRAY_DEPTH:
-            case DescriptorType::SAMPLER_CUBE_FLOAT:
-            case DescriptorType::SAMPLER_CUBE_INT:
-            case DescriptorType::SAMPLER_CUBE_UINT:
-            case DescriptorType::SAMPLER_CUBE_DEPTH:
-            case DescriptorType::SAMPLER_CUBE_ARRAY_FLOAT:
-            case DescriptorType::SAMPLER_CUBE_ARRAY_INT:
-            case DescriptorType::SAMPLER_CUBE_ARRAY_UINT:
-            case DescriptorType::SAMPLER_CUBE_ARRAY_DEPTH:
-            case DescriptorType::SAMPLER_3D_FLOAT:
-            case DescriptorType::SAMPLER_3D_INT:
-            case DescriptorType::SAMPLER_3D_UINT:
-            case DescriptorType::SAMPLER_2D_MS_FLOAT:
-            case DescriptorType::SAMPLER_2D_MS_INT:
-            case DescriptorType::SAMPLER_2D_MS_UINT:
-            case DescriptorType::SAMPLER_2D_MS_ARRAY_FLOAT:
-            case DescriptorType::SAMPLER_2D_MS_ARRAY_INT:
-            case DescriptorType::SAMPLER_2D_MS_ARRAY_UINT: {
+            case DescriptorType::SAMPLER_EXTERNAL:
+            case DescriptorType::SAMPLER: {
                 auto& samplerEntry = wEntries.emplace_back();
                 auto& samplerEntryInfo = mBindGroupEntries.emplace_back();
                 samplerEntry.binding = fEntry.binding * 2 + 1;
                 samplerEntryInfo.binding = samplerEntry.binding;
+                samplerEntryInfo.type = WebGPUDescriptorSetLayout::BindGroupEntryType::SAMPLER;
                 samplerEntry.visibility = wEntry.visibility;
-                wEntry.texture.multisampled = isMultiSampledTypeDescriptor(fEntry.type);
-                // TODO: Set once we have the filtering values
-                if (isDepthDescriptor(fEntry.type)) {
-                    samplerEntry.sampler.type = wgpu::SamplerBindingType::Comparison;
-                } else if (isIntDescriptor(fEntry.type)) {
-                    samplerEntry.sampler.type = wgpu::SamplerBindingType::NonFiltering;
+                // We are simply hoping that undefined and defaults suffices here.
+                samplerEntry.sampler.type = wgpu::SamplerBindingType::NonFiltering; // Example default
+                wEntry.texture.sampleType = wgpu::TextureSampleType::Float;      // Example default
+                // TODO: FIX! THIS IS HACK FOR HELLO-TRIANGLE!
+                if (baseLabel.find("Skybox") != std::string::npos ||
+                        (baseLabel == "Filament Default Material_perView" && wEntry.binding == 22)) {
+                    wEntry.texture.viewDimension = wgpu::TextureViewDimension::Cube;
                 } else {
-                    samplerEntry.sampler.type = wgpu::SamplerBindingType::Filtering;
+                    wEntry.texture.viewDimension =
+                            wgpu::TextureViewDimension::e2D;// Example default
                 }
+                entryInfo.type = WebGPUDescriptorSetLayout::BindGroupEntryType::TEXTURE_VIEW;
                 break;
             }
             case DescriptorType::UNIFORM_BUFFER: {
@@ -402,6 +301,7 @@ WebGPUDescriptorSetLayout::WebGPUDescriptorSetLayout(DescriptorSetLayout const&
                 // TODO: Ideally we fill minBindingSize
                 break;
             }
+
             case DescriptorType::INPUT_ATTACHMENT: {
                 PANIC_POSTCONDITION("Input Attachment is not supported");
                 break;
@@ -410,48 +310,6 @@ WebGPUDescriptorSetLayout::WebGPUDescriptorSetLayout(DescriptorSetLayout const&
                 PANIC_POSTCONDITION("Shader storage is not supported");
                 break;
             }
-            case DescriptorType::SAMPLER_EXTERNAL: {
-                PANIC_POSTCONDITION("External Sampler is not supported");
-                break;
-            }
-        }
-        if (isDepthDescriptor(fEntry.type))
-        {
-            wEntry.texture.sampleType = wgpu::TextureSampleType::Depth;
-        }
-        else if (isFloatDescriptor(fEntry.type))
-        {
-            // TODO: Set once we have the filtering values
-            wEntry.texture.sampleType = wgpu::TextureSampleType::Float;
-        }
-        else if (isIntDescriptor(fEntry.type))
-        {
-            wEntry.texture.sampleType = wgpu::TextureSampleType::Sint;
-        }
-        else if (isUnsignedIntDescriptor(fEntry.type))
-        {
-            wEntry.texture.sampleType = wgpu::TextureSampleType::Uint;
-        }
-
-        if (is3dTypeDescriptor(fEntry.type))
-        {
-            wEntry.texture.viewDimension = wgpu::TextureViewDimension::e3D;
-        }
-        else if (is2dTypeDescriptor(fEntry.type))
-        {
-            wEntry.texture.viewDimension = wgpu::TextureViewDimension::e2D;
-        }
-        else if (is2dArrayTypeDescriptor(fEntry.type))
-        {
-            wEntry.texture.viewDimension = wgpu::TextureViewDimension::e2DArray;
-        }
-        else if (isCubeTypeDescriptor(fEntry.type))
-        {
-            wEntry.texture.viewDimension = wgpu::TextureViewDimension::Cube;
-        }
-        else if (isCubeArrayTypeDescriptor(fEntry.type))
-        {
-            wEntry.texture.viewDimension = wgpu::TextureViewDimension::CubeArray;
         }
         // fEntry.count is unused currently
     }
@@ -466,26 +324,114 @@ WebGPUDescriptorSetLayout::WebGPUDescriptorSetLayout(DescriptorSetLayout const&
 
 WebGPUDescriptorSetLayout::~WebGPUDescriptorSetLayout() {}
 
+wgpu::Buffer WebGPUDescriptorSet::sDummyUniformBuffer = nullptr;
+wgpu::Texture WebGPUDescriptorSet::sDummyTexture = nullptr;
+wgpu::TextureView WebGPUDescriptorSet::sDummyTextureView = nullptr;
+wgpu::Sampler WebGPUDescriptorSet::sDummySampler = nullptr;
+
+void WebGPUDescriptorSet::initializeDummyResourcesIfNotAlready(wgpu::Device const& device,
+        wgpu::TextureFormat aColorFormat) {
+    if (!sDummyUniformBuffer) {
+        wgpu::BufferDescriptor bufferDescriptor{
+            .label = "dummy_uniform_not_to_be_used",
+            .usage = wgpu::BufferUsage::Uniform,
+            .size = 4
+        };
+        sDummyUniformBuffer = device.CreateBuffer(&bufferDescriptor);
+        FILAMENT_CHECK_POSTCONDITION(sDummyUniformBuffer)
+                << "Failed to create dummy uniform buffer?";
+    }
+    if (!sDummyTexture || !sDummyTextureView) {
+        wgpu::TextureDescriptor textureDescriptor{
+            .label = "dummy_texture_not_to_be_used",
+            .usage = wgpu::TextureUsage::TextureBinding,
+            .dimension = wgpu::TextureDimension::e2D,
+            .size = wgpu::Extent3D{ .width = 4, .height = 4, .depthOrArrayLayers = 1 },
+            .format = aColorFormat,
+        };
+        if (!sDummyTexture) {
+            sDummyTexture = device.CreateTexture(&textureDescriptor);
+            FILAMENT_CHECK_POSTCONDITION(sDummyUniformBuffer) << "Failed to create dummy texture?";
+        }
+        if (!sDummyTextureView) {
+            wgpu::TextureViewDescriptor textureViewDescriptor{
+                .label = "dummy_texture_view_not_to_be_used"
+            };
+            sDummyTextureView = sDummyTexture.CreateView(&textureViewDescriptor);
+            FILAMENT_CHECK_POSTCONDITION(sDummyUniformBuffer)
+                    << "Failed to create dummy texture view?";
+        }
+    }
+    if (!sDummySampler) {
+        wgpu::SamplerDescriptor samplerDescriptor{
+            .label = "dummy_sampler_not_to_be_used"
+        };
+        sDummySampler = device.CreateSampler(&samplerDescriptor);
+        FILAMENT_CHECK_POSTCONDITION(sDummyUniformBuffer) << "Failed to create dummy sampler?";
+    }
+}
+
+std::vector<wgpu::BindGroupEntry> WebGPUDescriptorSet::createDummyEntriesSortedByBinding(
+        std::vector<filament::backend::WebGPUDescriptorSetLayout::BindGroupEntryInfo> const&
+                bindGroupEntries) {
+    assert_invariant(WebGPUDescriptorSet::sDummyUniformBuffer &&
+                     "Dummy uniform buffer must have been created before "
+                     "creating dummy bind group entries.");
+    assert_invariant(
+            WebGPUDescriptorSet::sDummyTexture &&
+            "Dummy texture must have been created before creating dummy bind group entries.");
+    assert_invariant(
+            WebGPUDescriptorSet::sDummyTextureView &&
+            "Dummy texture view must have been created before creating dummy bind group entries.");
+    assert_invariant(
+            WebGPUDescriptorSet::sDummySampler &&
+            "Dummy sampler must have been created before creating dummy bind group entries.");
+    using filament::backend::WebGPUDescriptorSetLayout;
+    std::vector<wgpu::BindGroupEntry> entries;
+    entries.reserve(bindGroupEntries.size());
+    for (auto const& entryInfo: bindGroupEntries) {
+        auto& entry = entries.emplace_back();
+        entry.binding = entryInfo.binding;
+        switch (entryInfo.type) {
+            case WebGPUDescriptorSetLayout::BindGroupEntryType::UNIFORM_BUFFER:
+                entry.buffer = WebGPUDescriptorSet::sDummyUniformBuffer;
+                break;
+            case WebGPUDescriptorSetLayout::BindGroupEntryType::TEXTURE_VIEW:
+                entry.textureView = WebGPUDescriptorSet::sDummyTextureView;
+                break;
+            case WebGPUDescriptorSetLayout::BindGroupEntryType::SAMPLER:
+                entry.sampler = WebGPUDescriptorSet::sDummySampler;
+                break;
+        }
+    }
+    std::sort(entries.begin(), entries.end(),
+            [](wgpu::BindGroupEntry const& a, wgpu::BindGroupEntry const& b) {
+                return a.binding < b.binding;
+            });
+    return entries;
+}
+
 WebGPUDescriptorSet::WebGPUDescriptorSet(wgpu::BindGroupLayout const& layout,
         std::vector<WebGPUDescriptorSetLayout::BindGroupEntryInfo> const& bindGroupEntries)
     : mLayout(layout),
-      mEntriesWithDynamicOffsetsCount(std::count_if(bindGroupEntries.begin(),
-              bindGroupEntries.end(), [](auto const& entry) { return entry.hasDynamicOffset; })) {
-
-    mEntries.resize(bindGroupEntries.size());
-    for (size_t i = 0; i < bindGroupEntries.size(); ++i) {
-        mEntries[i].binding = bindGroupEntries[i].binding;
-    }
+      mEntriesSortedByBinding(createDummyEntriesSortedByBinding(bindGroupEntries)) {
     // Establish the size of entries based on the layout. This should be reliable and efficient.
     assert_invariant(INVALID_INDEX > mEntryIndexByBinding.size());
     for (size_t i = 0; i < mEntryIndexByBinding.size(); i++) {
         mEntryIndexByBinding[i] = INVALID_INDEX;
     }
-    for (size_t index = 0; index < mEntries.size(); index++) {
-        wgpu::BindGroupEntry const& entry = mEntries[index];
+    for (size_t index = 0; index < mEntriesSortedByBinding.size(); index++) {
+        wgpu::BindGroupEntry const& entry = mEntriesSortedByBinding[index];
         assert_invariant(entry.binding < mEntryIndexByBinding.size());
         mEntryIndexByBinding[entry.binding] = static_cast<uint8_t>(index);
     }
+    for (auto const& entry : bindGroupEntries) {
+        if (entry.hasDynamicOffset) {
+            assert_invariant(entry.binding < mEntriesByBindingWithDynamicOffsets.size());
+            mEntriesByBindingWithDynamicOffsets[entry.binding] = true;
+        }
+    }
+    mDynamicOffsets.reserve(mEntriesSortedByBinding.size());
 }
 
 WebGPUDescriptorSet::~WebGPUDescriptorSet() {
@@ -500,15 +446,15 @@ wgpu::BindGroup WebGPUDescriptorSet::lockAndReturn(const wgpu::Device& device) {
     // TODO label? Should we just copy layout label?
     wgpu::BindGroupDescriptor desc{
         .layout = mLayout,
-        .entryCount = mEntries.size(),
-        .entries = mEntries.data()
+        .entryCount = mEntriesSortedByBinding.size(),
+        .entries = mEntriesSortedByBinding.data()
     };
     mBindGroup = device.CreateBindGroup(&desc);
     FILAMENT_CHECK_POSTCONDITION(mBindGroup) << "Failed to create bind group?";
     // once we have created the bind group itself we should no longer need any other state
     mLayout = nullptr;
-    mEntries.clear();
-    mEntries.shrink_to_fit();
+    mEntriesSortedByBinding.clear();
+    mEntriesSortedByBinding.shrink_to_fit();
     return mBindGroup;
 }
 
@@ -526,16 +472,37 @@ void WebGPUDescriptorSet::addEntry(unsigned int index, wgpu::BindGroupEntry&& en
             << index;
     uint8_t entryIndex = mEntryIndexByBinding[index];
     FILAMENT_CHECK_POSTCONDITION(
-            entryIndex != INVALID_INDEX && entryIndex < mEntries.size())
+            entryIndex != INVALID_INDEX && entryIndex < mEntriesSortedByBinding.size())
             << "Invalid binding " << index;
     entry.binding = index;
-    mEntries[entryIndex] = std::move(entry);
+    mEntriesSortedByBinding[entryIndex] = std::move(entry);
+    mEntriesByBindingAdded[index] = true;
+}
+
+uint32_t const* WebGPUDescriptorSet::setDynamicOffsets(uint32_t const* offsets) {
+    // mDynamicOffsets already reserves enough memory for the number of entries in the set
+    mDynamicOffsets.clear();
+    // this implementation copies the offsets to mDynamicOffsets, but also adds values for
+    // unused entries TODO: is this necessary?
+    size_t inputIndex = 0;
+    size_t outputIndex = 0;
+    for (auto const& entry : mEntriesSortedByBinding) {
+        if (mEntriesByBindingWithDynamicOffsets[entry.binding]) {
+            if (mEntriesByBindingAdded[entry.binding]) {
+                mDynamicOffsets[outputIndex++] = offsets[inputIndex++];
+            } else {
+                mDynamicOffsets[outputIndex++] = 0; // dummy offset, as it was never added
+            }
+        }
+    }
+    return mDynamicOffsets.data();
 }
 
 size_t WebGPUDescriptorSet::countEntitiesWithDynamicOffsets() const {
-    return mEntriesWithDynamicOffsetsCount;
+    return mEntriesByBindingWithDynamicOffsets.count();
 }
 
+// From createTextureR
 WGPUTexture::WGPUTexture(SamplerType target, uint8_t levels, TextureFormat format, uint8_t samples,
         uint32_t width, uint32_t height, uint32_t depth, TextureUsage usage,
         wgpu::Device const& device) noexcept {
@@ -547,11 +514,8 @@ WGPUTexture::WGPUTexture(SamplerType target, uint8_t levels, TextureFormat forma
                     "the spec. See https://www.w3.org/TR/webgpu/#texture-creation or "
                     "https://gpuweb.github.io/gpuweb/#multisample-state");
     // First, the texture aspect, starting with the defaults/basic configuration
-    mUsage = fToWGPUTextureUsage(usage);
+    mUsage = fToWGPUTextureUsage(usage, device.HasFeature(wgpu::FeatureName::TransientAttachments));
     mFormat = fToWGPUTextureFormat(format);
-    mAspect = fToWGPUTextureViewAspect(usage, format);
-    mBlockWidth = filament::backend::getBlockWidth(format);
-    mBlockHeight = filament::backend::getBlockHeight(format);
     wgpu::TextureDescriptor textureDescriptor{
         .label = getUserTextureLabel(target),
         .usage = mUsage,
@@ -593,19 +557,17 @@ WGPUTexture::WGPUTexture(SamplerType target, uint8_t levels, TextureFormat forma
     FILAMENT_CHECK_POSTCONDITION(mTexture)
             << "Failed to create texture for " << textureDescriptor.label;
     // Second, the texture view aspect
-    mTexureView = makeTextureView(0, levels, target);
+    mTexView = makeTextureView(0, levels, target);
 }
 
+// From createTextureViewR
 WGPUTexture::WGPUTexture(WGPUTexture* src, uint8_t baseLevel, uint8_t levelCount) noexcept {
     mTexture = src->mTexture;
-    mAspect = src->mAspect;
-    mBlockWidth = src->mBlockWidth;
-    mBlockHeight = src->mBlockHeight;
-
-    mTexureView = makeTextureView(baseLevel, levelCount, target);
+    mTexView = makeTextureView(baseLevel, levelCount, target);
 }
 
-wgpu::TextureUsage WGPUTexture::fToWGPUTextureUsage(TextureUsage const& fUsage) {
+wgpu::TextureUsage WGPUTexture::fToWGPUTextureUsage(const TextureUsage& fUsage,
+        const bool supportsTransientAttachment) {
     wgpu::TextureUsage retUsage = wgpu::TextureUsage::None;
 
     // Basing this mapping off of VulkanTexture.cpp's getUsage func and suggestions from Gemini
@@ -631,6 +593,7 @@ wgpu::TextureUsage WGPUTexture::fToWGPUTextureUsage(TextureUsage const& fUsage)
     // This is from Vulkan logic- if there are any issues try disabling this first, allows perf
     // benefit though
     const bool useTransientAttachment =
+            supportsTransientAttachment &&
             // Usage consists of attachment flags only.
             none(fUsage & ~TextureUsage::ALL_ATTACHMENTS) &&
             // Usage contains at least one attachment flag.
@@ -653,9 +616,8 @@ wgpu::TextureUsage WGPUTexture::fToWGPUTextureUsage(TextureUsage const& fUsage)
     //  PROTECTED
     return retUsage;
 }
-
-wgpu::TextureFormat WGPUTexture::fToWGPUTextureFormat(TextureFormat const& fFormat) {
-    switch (fFormat) {
+wgpu::TextureFormat WGPUTexture::fToWGPUTextureFormat(const TextureFormat& fUsage) {
+    switch (fUsage) {
         case filament::backend::TextureFormat::R8:
             return wgpu::TextureFormat::R8Unorm;
         case filament::backend::TextureFormat::R8_SNORM:
@@ -894,57 +856,24 @@ wgpu::TextureFormat WGPUTexture::fToWGPUTextureFormat(TextureFormat const& fForm
     }
 }
 
-wgpu::TextureAspect WGPUTexture::fToWGPUTextureViewAspect(TextureUsage const& fUsage,
-        TextureFormat const& fFormat) {
-
-    const bool isDepth = any(fUsage & TextureUsage::DEPTH_ATTACHMENT);
-    const bool isStencil = any(fUsage & TextureUsage::STENCIL_ATTACHMENT);
-    const bool isColor = any(fUsage & TextureUsage::COLOR_ATTACHMENT);
-    const bool isSample = (fUsage == TextureUsage::SAMPLEABLE);
-
-    if (isDepth && !isColor && !isStencil) {
-        return wgpu::TextureAspect::DepthOnly;
-    }
-
-    if (isStencil && !isColor && !isDepth) {
-        return wgpu::TextureAspect::StencilOnly;
-    }
-
-    if (fFormat == filament::backend::TextureFormat::DEPTH32F ||
-            fFormat == filament::backend::TextureFormat::DEPTH24 ||
-            fFormat == filament::backend::TextureFormat::DEPTH16) {
-        return wgpu::TextureAspect::DepthOnly;
-    }
-
-    if (fFormat == filament::backend::TextureFormat::STENCIL8) {
-        return wgpu::TextureAspect::StencilOnly;
-    }
-
-    if (fFormat == filament::backend::TextureFormat::DEPTH24_STENCIL8 ||
-            fFormat == filament::backend::TextureFormat::DEPTH32F_STENCIL8) {
-        if (isSample) {
-            return wgpu::TextureAspect::DepthOnly;
-        }
-    }
-
-    return wgpu::TextureAspect::All;
-}
-
 wgpu::TextureView WGPUTexture::makeTextureView(const uint8_t& baseLevel, const uint8_t& levelCount,
         SamplerType target) {
-
+    // starting with the defaults/basic configuration
     wgpu::TextureViewDescriptor textureViewDescriptor{
         .label = getUserTextureViewLabel(target),
         .format = mFormat,
+        // dimension depends on target and is set below
         .baseMipLevel = baseLevel,
         .mipLevelCount = levelCount,
-        // TODO: check if this baseArrayLayer assumption is correct
+        // baseArrayLayer is required, making a guess
         .baseArrayLayer = 0,
         .arrayLayerCount = mArrayLayerCount,
-        .aspect = mAspect,
+        // Have not found an analog to aspect in other drivers, but ALL should be unrestrictive.
+        // TODO Can we make this better?
+        .aspect = wgpu::TextureAspect::All,
         .usage = mUsage
     };
-
+    // adjust for specific cases
     switch (target) {
         case SamplerType::SAMPLER_2D:
             textureViewDescriptor.dimension = wgpu::TextureViewDimension::e2D;
@@ -971,153 +900,58 @@ wgpu::TextureView WGPUTexture::makeTextureView(const uint8_t& baseLevel, const u
     return textureView;
 }
 
-WGPURenderTarget::WGPURenderTarget(uint32_t width, uint32_t height, uint8_t samples,
-        const MRT& colorAttachmentsMRT,
-        const Attachment& depthAttachmentInfo,
-        const Attachment& stencilAttachmentInfo)
-    : HwRenderTarget(width, height),
-      defaultRenderTarget(false),
-      samples(samples),
-      mColorAttachments(colorAttachmentsMRT),
-      mDepthAttachment(depthAttachmentInfo),
-      mStencilAttachment(stencilAttachmentInfo) {
-    // TODO Make this an array
-    mColorAttachmentDescriptors.reserve(MRT::MAX_SUPPORTED_RENDER_TARGET_COUNT);
+WGPURenderTarget::Attachment WGPURenderTarget::getDrawColorAttachment(size_t index) {
+    assert_invariant( index < MRT::MAX_SUPPORTED_RENDER_TARGET_COUNT);
+    auto result = color[index];
+    if (index == 0 && defaultRenderTarget) {
+
+    }
+
+    return result;
 }
 
 wgpu::LoadOp WGPURenderTarget::getLoadOperation(RenderPassParams const& params,
-                                                TargetBufferFlags bufferToOperateOn) {
-    if (any(params.flags.clear & bufferToOperateOn)) {
+                                             TargetBufferFlags buffer) {
+    auto clearFlags = params.flags.clear;
+    auto discardStartFlags = params.flags.discardStart;
+    if (any(clearFlags & buffer)) {
+        return wgpu::LoadOp::Clear;
+    } else if (any(discardStartFlags & buffer)) {
         return wgpu::LoadOp::Clear;
-    }
-    if (any(params.flags.discardStart & bufferToOperateOn)) {
-        return wgpu::LoadOp::Clear; // Or wgpu::LoadOp::Undefined if clear is not desired on discard
     }
     return wgpu::LoadOp::Load;
 }
 
 wgpu::StoreOp WGPURenderTarget::getStoreOperation(RenderPassParams const& params,
-                                                  TargetBufferFlags bufferToOperateOn) {
-    if (any(params.flags.discardEnd & bufferToOperateOn)) {
+                                               TargetBufferFlags buffer) {
+    const auto discardEndFlags = params.flags.discardEnd;
+    if (any(discardEndFlags & buffer)) {
         return wgpu::StoreOp::Discard;
     }
     return wgpu::StoreOp::Store;
 }
-
 void WGPURenderTarget::setUpRenderPassAttachments(wgpu::RenderPassDescriptor& descriptor,
-        RenderPassParams const& params, wgpu::TextureView const& defaultColorTextureView,
-        wgpu::TextureView const& defaultDepthStencilTextureView,
-        wgpu::TextureView const* customColorTextureViews, uint32_t customColorTextureViewCount,
-        wgpu::TextureView const& customDepthTextureView,
-        wgpu::TextureView const& customStencilTextureView, wgpu::TextureFormat customDepthFormat,
-        wgpu::TextureFormat customStencilFormat) {
-    mColorAttachmentDescriptors.clear();
-    mHasDepthStencilAttachment = false;
-
-    if (defaultRenderTarget) {
-        assert_invariant(defaultColorTextureView);
-        mColorAttachmentDescriptors.push_back({ .view = defaultColorTextureView,
-            .resolveTarget = nullptr,
-            .loadOp = WGPURenderTarget::getLoadOperation(params, TargetBufferFlags::COLOR0),
-            .storeOp = WGPURenderTarget::getStoreOperation(params, TargetBufferFlags::COLOR0),
-            .clearValue = { params.clearColor.r, params.clearColor.g, params.clearColor.b,
-                params.clearColor.a } });
-
-        if (defaultDepthStencilTextureView) {
-            mDepthStencilAttachmentDescriptor = {
-                .view = defaultDepthStencilTextureView,
-                .depthLoadOp = WGPURenderTarget::getLoadOperation(params, TargetBufferFlags::DEPTH),
-                .depthStoreOp =
-                        WGPURenderTarget::getStoreOperation(params, TargetBufferFlags::DEPTH),
-                .depthClearValue = static_cast<float>(params.clearDepth),
-                .depthReadOnly =
-                        (params.readOnlyDepthStencil & RenderPassParams::READONLY_DEPTH) > 0,
-                .stencilLoadOp =
-                        WGPURenderTarget::getLoadOperation(params, TargetBufferFlags::STENCIL),
-                .stencilStoreOp =
-                        WGPURenderTarget::getStoreOperation(params, TargetBufferFlags::STENCIL),
-                .stencilClearValue = params.clearStencil,
-                .stencilReadOnly =
-                        (params.readOnlyDepthStencil & RenderPassParams::READONLY_STENCIL) > 0,
-            };
-            mHasDepthStencilAttachment = true;
-        }
-    } else {// Custom Render Target
-        for (uint32_t i = 0; i < customColorTextureViewCount; ++i) {
-            if (customColorTextureViews[i]) {
-                mColorAttachmentDescriptors.push_back({ .view = customColorTextureViews[i],
-                    // .resolveTarget = nullptr; // TODO: MSAA resolve for custom RT
-                    .loadOp = WGPURenderTarget::getLoadOperation(params, getTargetBufferFlagsAt(i)),
-                    .storeOp =
-                            WGPURenderTarget::getStoreOperation(params, getTargetBufferFlagsAt(i)),
-                    .clearValue = { .r = params.clearColor.r,
-                        .g = params.clearColor.g,
-                        .b = params.clearColor.b,
-                        .a = params.clearColor.a } });
-            }
-        }
-
-        FILAMENT_CHECK_POSTCONDITION(!(customDepthTextureView && customStencilTextureView))
-                << "WebGPU CANNOT support separate texture views for depth + stencil. depth + "
-                   "stencil needs to be in one texture view";
-
-        const bool hasStencil =
-                customStencilTextureView ||
-                (customDepthFormat == wgpu::TextureFormat::Depth24PlusStencil8 ||
-                        customDepthFormat == wgpu::TextureFormat::Depth32FloatStencil8);
-
-        const bool hasDepth =
-                customDepthTextureView ||
-                (customStencilFormat == wgpu::TextureFormat::Depth24PlusStencil8 ||
-                        customDepthFormat == wgpu::TextureFormat::Depth32FloatStencil8);
-
-        if (customDepthTextureView || customStencilTextureView) {
-            assert_invariant((hasDepth || hasStencil) &&
-                             "Depth or Texture view without a valid texture format");
-            mDepthStencilAttachmentDescriptor = {};
-            mDepthStencilAttachmentDescriptor.view =
-                    customDepthTextureView ? customDepthTextureView : customStencilTextureView;
-
-            if (hasDepth) {
-                mDepthStencilAttachmentDescriptor.depthLoadOp =
-                        WGPURenderTarget::getLoadOperation(params, TargetBufferFlags::DEPTH);
-                mDepthStencilAttachmentDescriptor.depthStoreOp =
-                        WGPURenderTarget::getStoreOperation(params, TargetBufferFlags::DEPTH);
-                mDepthStencilAttachmentDescriptor.depthClearValue =
-                        static_cast<float>(params.clearDepth);
-                mDepthStencilAttachmentDescriptor.depthReadOnly =
-                        (params.readOnlyDepthStencil & RenderPassParams::READONLY_DEPTH) > 0;
-            } else {
-                mDepthStencilAttachmentDescriptor.depthLoadOp = wgpu::LoadOp::Undefined;
-                mDepthStencilAttachmentDescriptor.depthStoreOp = wgpu::StoreOp::Undefined;
-                mDepthStencilAttachmentDescriptor.depthReadOnly = true;
-            }
-
-            if (hasStencil) {
-                mDepthStencilAttachmentDescriptor.stencilLoadOp =
-                        WGPURenderTarget::getLoadOperation(params, TargetBufferFlags::STENCIL);
-                mDepthStencilAttachmentDescriptor.stencilStoreOp =
-                        WGPURenderTarget::getStoreOperation(params, TargetBufferFlags::STENCIL);
-                mDepthStencilAttachmentDescriptor.stencilClearValue = params.clearStencil;
-                mDepthStencilAttachmentDescriptor.stencilReadOnly =
-                        (params.readOnlyDepthStencil & RenderPassParams::READONLY_STENCIL) > 0;
-            } else {
-                mDepthStencilAttachmentDescriptor.stencilLoadOp = wgpu::LoadOp::Undefined;
-                mDepthStencilAttachmentDescriptor.stencilStoreOp = wgpu::StoreOp::Undefined;
-                mDepthStencilAttachmentDescriptor.stencilReadOnly = true;
-            }
-            mHasDepthStencilAttachment = true;
-        }
+        wgpu::TextureView const& textureView, RenderPassParams const& params) {
+    // auto discardFlags = params.flags.discardEnd;
+    // (void) discardFlags;
+    // std::vector<wgpu::RenderPassColorAttachment> colorAttachments;
+    colorAttachments.clear();
+    for (size_t i = 0; i < 1/*MRT::MAX_SUPPORTED_RENDER_TARGET_COUNT*/; i++) {
+        // auto attachment = getDrawColorAttachment(i);
+        // if (attachment) {
+            wgpu::RenderPassColorAttachment colorAttachment;
+            colorAttachment.view = textureView;
+            colorAttachment.loadOp  = getLoadOperation(params, getTargetBufferFlagsAt(i));
+            colorAttachment.storeOp = getStoreOperation(params, getTargetBufferFlagsAt(i));
+            colorAttachment.clearValue = { params.clearColor.r, params.clearColor.g, params.clearColor.b, params.clearColor.a };
+            colorAttachments.emplace_back(colorAttachment);
+        // }
     }
-
-    descriptor.colorAttachmentCount = mColorAttachmentDescriptors.size();
-    descriptor.colorAttachments = mColorAttachmentDescriptors.data();
-    descriptor.depthStencilAttachment =
-            mHasDepthStencilAttachment ? &mDepthStencilAttachmentDescriptor : nullptr;
-
-    // descriptor.sampleCount was removed from the core spec. If your webgpu.h still has it,
-    // and your Dawn version expects it, you might need to set it here based on this->samples.
-    // e.g., descriptor.sampleCount = this->samples;
+    descriptor.colorAttachments = colorAttachments.data();
+    descriptor.colorAttachmentCount = colorAttachments.size();
+    descriptor.depthStencilAttachment = nullptr;
+    descriptor.timestampWrites = nullptr;
 }
 
+
 }// namespace filament::backend

filament/backend/src/webgpu/WebGPUHandles.h

@@ -28,6 +28,7 @@
 #include <webgpu/webgpu_cpp.h>
 
 #include <array>
+#include <bitset>
 #include <cstdint>
 #include <vector>
 
@@ -43,47 +44,38 @@ public:
     std::vector<wgpu::ConstantEntry> constants;
 };
 
+struct WGPUBufferObject;
 
-// WGPUVertexBufferInfo maps Filament vertex attributes to WebGPU buffer binding model.
+// VertexBufferInfo contains layout info for Vertex Buffer based on WebGPU structs. In WebGPU each
+// VertexBufferLayout is associated with a single vertex buffer. So number of mVertexBufferLayout
+// is equal to bufferCount. Each VertexBufferLayout can contain multiple VertexAttribute. Bind index
+// of vertex buffer is implicitly calculated by the position of VertexBufferLayout in an array.
 class WGPUVertexBufferInfo : public HwVertexBufferInfo {
 public:
     WGPUVertexBufferInfo(uint8_t bufferCount, uint8_t attributeCount,
             AttributeArray const& attributes);
-
-    inline wgpu::VertexBufferLayout const* getVertexBufferLayouts() const {
-        return mVertexBufferLayouts.data();
-    }
-    inline uint32_t getVertexBufferLayoutCount() const {
-        return static_cast<uint32_t>(mVertexBufferLayouts.size());
+    inline  wgpu::VertexBufferLayout const* getVertexBufferLayout() const {
+        return mVertexBufferLayout.data();
     }
 
-    inline wgpu::VertexAttribute const* getVertexAttributes(uint32_t i) const {
-        return mVertexAttributes[i].data();
-    }
-    inline uint32_t getVertexAttributeCount(uint32_t i) const {
-        return static_cast<uint32_t>(mVertexAttributes[i].size());
+    inline uint32_t getVertexBufferLayoutSize() const {
+        return mVertexBufferLayout.size();
     }
 
-    struct WebGPUSlotBindingInfo {
-        uint8_t sourceBuffer;
-        uint32_t slot;
-        uint64_t bufferOffset;
-        uint32_t stride;
-    };
-    inline const std::vector<WebGPUSlotBindingInfo>& getWebGPUSlotBindingInfos() const {
-        return mWebGPUSlotBindingInfos;
+    inline wgpu::VertexAttribute const* getVertexAttributeForIndex(uint32_t index) const {
+        assert_invariant(index < mAttributes.size());
+        return mAttributes[index].data();
+    }
+
+    inline uint32_t getVertexAttributeSize(uint32_t index) const {
+        assert_invariant(index < mAttributes.size());
+        return mAttributes[index].size();
     }
 
 private:
-    // This stores the final wgpu::VertexBufferLayout objects, one per WebGPU slot.
-    std::vector<wgpu::VertexBufferLayout> mVertexBufferLayouts;
-
-    // This stores all wgpu::VertexAttribute structs, indexed by their original
-    // Filament attributeIndex.
-    std::vector<std::vector<wgpu::VertexAttribute>> mVertexAttributes;
-
-    // Stores information for the driver to perform setVertexBuffer calls
-    std::vector<WebGPUSlotBindingInfo> mWebGPUSlotBindingInfos;
+    // TODO: can we do better in terms on heap management.
+    std::vector<wgpu::VertexBufferLayout> mVertexBufferLayout {};
+    std::vector<std::vector<wgpu::VertexAttribute>> mAttributes {};
 };
 
 struct WGPUVertexBuffer : public HwVertexBuffer {
@@ -94,37 +86,33 @@ struct WGPUVertexBuffer : public HwVertexBuffer {
     utils::FixedCapacityVector<wgpu::Buffer> buffers;
 };
 
-class WGPUBufferBase {
-public:
-    void createBuffer(wgpu::Device const& device, wgpu::BufferUsage usage, uint32_t size,
-            char const* label);
-    void updateGPUBuffer(BufferDescriptor& bufferDescriptor, uint32_t byteOffset,
-            wgpu::Queue queue);
-    const wgpu::Buffer& getBuffer() const { return buffer; }
-protected:
-    wgpu::Buffer buffer;
-private:
-    // 4 bytes to hold any extra chunk we need.
-    std::array<uint8_t,4> mRemainderChunk;
-};
-
-class WGPUIndexBuffer : public HwIndexBuffer, public WGPUBufferBase {
-public:
+struct WGPUIndexBuffer : public HwIndexBuffer {
     WGPUIndexBuffer(wgpu::Device const &device, uint8_t elementSize,
                     uint32_t indexCount);
+
+    wgpu::Buffer buffer;
     wgpu::IndexFormat indexFormat;
 };
 
-class WGPUBufferObject : public HwBufferObject, public WGPUBufferBase {
-public:
+struct WGPUBufferObject : HwBufferObject {
     WGPUBufferObject(wgpu::Device const &device, BufferObjectBinding bindingType, uint32_t byteCount);
+
+    wgpu::Buffer buffer = nullptr;
+    const BufferObjectBinding bufferObjectBinding;
 };
 
 class WebGPUDescriptorSetLayout final : public HwDescriptorSetLayout {
 public:
 
+    enum class BindGroupEntryType : uint8_t {
+        UNIFORM_BUFFER,
+        TEXTURE_VIEW,
+        SAMPLER
+    };
+
     struct BindGroupEntryInfo final {
         uint8_t binding = 0;
+        BindGroupEntryType type = BindGroupEntryType::UNIFORM_BUFFER;
         bool hasDynamicOffset = false;
     };
 
@@ -137,7 +125,7 @@ public:
 
 private:
     // TODO: If this is useful elsewhere, remove it from this class
-    // Convert Filament Shader Stage Flags bitmask to webgpu equivalent
+    // Convert Filament Shader Stage Flags bitmask to webgpu equivilant
     static wgpu::ShaderStage filamentStageToWGPUStage(ShaderStageFlags fFlags);
     std::vector<BindGroupEntryInfo> mBindGroupEntries;
     wgpu::BindGroupLayout mLayout;
@@ -145,6 +133,8 @@ private:
 
 class WebGPUDescriptorSet final : public HwDescriptorSet {
 public:
+    static void initializeDummyResourcesIfNotAlready(wgpu::Device const&,
+            wgpu::TextureFormat aColorFormat);
 
     WebGPUDescriptorSet(wgpu::BindGroupLayout const& layout,
             std::vector<WebGPUDescriptorSetLayout::BindGroupEntryInfo> const& bindGroupEntries);
@@ -152,18 +142,30 @@ public:
 
     wgpu::BindGroup lockAndReturn(wgpu::Device const&);
     void addEntry(unsigned int index, wgpu::BindGroupEntry&& entry);
+    [[nodiscard]] uint32_t const* setDynamicOffsets(uint32_t const* offsets);
     [[nodiscard]] bool getIsLocked() const { return mBindGroup != nullptr; }
     [[nodiscard]] size_t countEntitiesWithDynamicOffsets() const;
-
-    // May be nullptr. Use lockAndReturn to create the bind group when appropriate
-    [[nodiscard]] const wgpu::BindGroup& getBindGroup() const { return mBindGroup; }
-
 private:
+
+    static wgpu::Buffer sDummyUniformBuffer;
+    static wgpu::Texture sDummyTexture;
+    static wgpu::TextureView sDummyTextureView;
+    static wgpu::Sampler sDummySampler;
+
+    static std::vector<wgpu::BindGroupEntry> createDummyEntriesSortedByBinding(
+            std::vector<filament::backend::WebGPUDescriptorSetLayout::BindGroupEntryInfo> const&);
+
+    // TODO: Consider storing what we used to make the layout. However we need to essentially
+    // Recreate some of the info (Sampler in slot X with the actual sampler) so letting Dawn confirm
+    // there isn't a mismatch may be easiest.
+    // Also storing the wgpu ObjectBase takes care of ownership challenges in theory
     wgpu::BindGroupLayout mLayout = nullptr;
     static constexpr uint8_t INVALID_INDEX = MAX_DESCRIPTOR_COUNT + 1;
-    std::array<uint8_t, MAX_DESCRIPTOR_COUNT> mEntryIndexByBinding{};
-    std::vector<wgpu::BindGroupEntry> mEntries;
-    const size_t mEntriesWithDynamicOffsetsCount;
+    std::array<uint8_t, MAX_DESCRIPTOR_COUNT> mEntryIndexByBinding {};
+    std::vector<wgpu::BindGroupEntry> mEntriesSortedByBinding;
+    std::bitset<MAX_DESCRIPTOR_COUNT> mEntriesByBindingWithDynamicOffsets {};
+    std::bitset<MAX_DESCRIPTOR_COUNT> mEntriesByBindingAdded {};
+    std::vector<uint32_t> mDynamicOffsets;
     wgpu::BindGroup mBindGroup = nullptr;
 };
 
@@ -174,19 +176,12 @@ public:
             wgpu::Device const& device) noexcept;
 
     WGPUTexture(WGPUTexture* src, uint8_t baseLevel, uint8_t levelCount) noexcept;
-    wgpu::TextureAspect getAspect() const { return mAspect; }
-    size_t getBlockWidth() const { return mBlockWidth; }
-    size_t getBlockHeight() const { return mBlockHeight; }
 
-    [[nodiscard]] const wgpu::Texture& getTexture() const { return mTexture; }
-    [[nodiscard]] const wgpu::TextureView& getTextureView() const { return mTexureView; }
-    [[nodiscard]] wgpu::TextureFormat getFormat() const { return mFormat; }
+    const wgpu::Texture& getTexture() const { return mTexture; }
+    const wgpu::TextureView& getTexView() const { return mTexView; }
 
-    static wgpu::TextureFormat fToWGPUTextureFormat(
-            filament::backend::TextureFormat const& fFormat);
-    static wgpu::TextureAspect fToWGPUTextureViewAspect(
-            filament::backend::TextureUsage const& fUsage,
-            filament::backend::TextureFormat const& fFormat);
+    // Public to allow checking for support of a texture format
+    static wgpu::TextureFormat fToWGPUTextureFormat(const filament::backend::TextureFormat& fUsage);
 
 private:
     wgpu::TextureView makeTextureView(const uint8_t& baseLevel, const uint8_t& levelCount,
@@ -197,12 +192,10 @@ private:
     wgpu::Texture mTexture = nullptr;
     wgpu::TextureUsage mUsage = wgpu::TextureUsage::None;
     wgpu::TextureFormat mFormat = wgpu::TextureFormat::Undefined;
-    wgpu::TextureAspect mAspect = wgpu::TextureAspect::Undefined;
     uint32_t mArrayLayerCount = 1;
-    wgpu::TextureView mTexureView = nullptr;
-    wgpu::TextureUsage fToWGPUTextureUsage(filament::backend::TextureUsage const& fUsage);
-    size_t mBlockWidth;
-    size_t mBlockHeight;
+    wgpu::TextureView mTexView = nullptr;
+    wgpu::TextureUsage fToWGPUTextureUsage(const filament::backend::TextureUsage& fUsage,
+            const bool supportsTransientAttachment);
 };
 
 struct WGPURenderPrimitive : public HwRenderPrimitive {
@@ -213,60 +206,55 @@ struct WGPURenderPrimitive : public HwRenderPrimitive {
 
 class WGPURenderTarget : public HwRenderTarget {
 public:
-    using Attachment = TargetBufferInfo; // Using TargetBufferInfo directly for attachments
+    class Attachment {
+    public:
+        friend class WGPURenderTarget;
+
+        Attachment() = default;
+        Attachment(WGPUTexture* gpuTexture, uint8_t level = 0, uint16_t layer = 0)
+            : level(level),
+              layer(layer),
+              texture(gpuTexture->getTexture()),
+              mWGPUTexture(gpuTexture) {}
+        operator bool() const {
+            return mWGPUTexture != nullptr;
+        }
+
+        uint8_t level = 0;
+        uint16_t layer = 0;
+
+    private:
+        wgpu::Texture texture = nullptr;
+        WGPUTexture* mWGPUTexture = nullptr;
+    };
 
     WGPURenderTarget(uint32_t width, uint32_t height, uint8_t samples,
-            const MRT& colorAttachments,
-            const Attachment& depthAttachment,
-            const Attachment& stencilAttachment);
-
-    // Default constructor for the default render target
+            Attachment colorAttachments[MRT::MAX_SUPPORTED_RENDER_TARGET_COUNT]);
     WGPURenderTarget()
         : HwRenderTarget(0, 0),
-          defaultRenderTarget(true),
-          samples(1) {}
+          defaultRenderTarget(true) {}
 
-    // Updated signature: takes resolved views for custom RTs, and default views for default RT
-    void setUpRenderPassAttachments(
-            wgpu::RenderPassDescriptor& descriptor,
-            RenderPassParams const& params,
-            // For default render target:
-            wgpu::TextureView const& defaultColorTextureView,
-            wgpu::TextureView const& defaultDepthStencilTextureView,
-            // For custom render targets:
-            wgpu::TextureView const* customColorTextureViews, // Array of views
-            uint32_t customColorTextureViewCount,
-            wgpu::TextureView const& customDepthTextureView,
-            wgpu::TextureView const& customStencilTextureView,
-            wgpu::TextureFormat customDepthFormat,
-            wgpu::TextureFormat customStencilFormat);
+    void setUpRenderPassAttachments(wgpu::RenderPassDescriptor& descriptor,
+            wgpu::TextureView const& textureView, RenderPassParams const& params);
 
+    math::uint2 getAttachmentSize() noexcept;
 
     bool isDefaultRenderTarget() const { return defaultRenderTarget; }
     uint8_t getSamples() const { return samples; }
 
-    // Accessors for the driver to get stored attachment info
-    const MRT& getColorAttachmentInfos() const { return mColorAttachments; }
-    const Attachment& getDepthAttachmentInfo() const { return mDepthAttachment; }
-    const Attachment& getStencilAttachmentInfo() const { return mStencilAttachment; }
+    Attachment getDrawColorAttachment(size_t index);
+    Attachment getReadColorAttachment(size_t index);
 
-    // Static helpers for load/store operations
     static wgpu::LoadOp getLoadOperation(const RenderPassParams& params, TargetBufferFlags buffer);
     static wgpu::StoreOp getStoreOperation(const RenderPassParams& params, TargetBufferFlags buffer);
-
 private:
     bool defaultRenderTarget = false;
     uint8_t samples = 1;
 
-    MRT mColorAttachments{};
-    // TODO WebGPU only supports a DepthStencil attachment, should this be just mDepthStencilAttachment?
-    Attachment mDepthAttachment{};
-    Attachment mStencilAttachment{};
-
-    // Cached descriptors for the render pass
-    std::vector<wgpu::RenderPassColorAttachment> mColorAttachmentDescriptors;
-    wgpu::RenderPassDepthStencilAttachment mDepthStencilAttachmentDescriptor{};
-    bool mHasDepthStencilAttachment = false;
+    Attachment color[MRT::MAX_SUPPORTED_RENDER_TARGET_COUNT] = {};
+    math::uint2 attachmentSize = {};
+    std::vector<wgpu::RenderPassColorAttachment> colorAttachments {};
 };
+
 }// namespace filament::backend
 #endif// TNT_FILAMENT_BACKEND_WEBGPUHANDLES_H

filament/backend/src/webgpu/WebGPUPipelineCreation.cpp

@@ -154,9 +154,9 @@ constexpr wgpu::BlendFactor toWebGPU(BlendFunction blendFunction) {
 wgpu::RenderPipeline createWebGPURenderPipeline(wgpu::Device const& device,
         WGPUProgram const& program, WGPUVertexBufferInfo const& vertexBufferInfo,
         wgpu::PipelineLayout const& layout, RasterState const& rasterState,
-        StencilState const& stencilState, PolygonOffset const& polygonOffset, PrimitiveType primitiveType,
-        std::vector<wgpu::TextureFormat> const& colorFormats,
-        wgpu::TextureFormat depthFormat, uint8_t samplesCount) {
+        StencilState const& stencilState, PolygonOffset const& polygonOffset,
+        PrimitiveType primitiveType, wgpu::TextureFormat colorFormat,
+        wgpu::TextureFormat depthFormat) {
     assert_invariant(program.vertexShaderModule);
     const wgpu::DepthStencilState depthStencilState {
         .format = depthFormat,
@@ -191,8 +191,8 @@ wgpu::RenderPipeline createWebGPURenderPipeline(wgpu::Device const& device,
             .entryPoint = "main",
             .constantCount = program.constants.size(),
             .constants = program.constants.data(),
-            .bufferCount = vertexBufferInfo.getVertexBufferLayoutCount(),
-            .buffers = vertexBufferInfo.getVertexBufferLayouts()
+            .bufferCount = vertexBufferInfo.getVertexBufferLayoutSize(),
+            .buffers = vertexBufferInfo.getVertexBufferLayout()
         },
         .primitive = {
             .topology = toWebGPU(primitiveType),
@@ -207,9 +207,9 @@ wgpu::RenderPipeline createWebGPURenderPipeline(wgpu::Device const& device,
             .unclippedDepth = !rasterState.depthClamp &&
                               device.HasFeature(wgpu::FeatureName::DepthClipControl)
         },
-        .depthStencil = depthFormat != wgpu::TextureFormat::Undefined ? &depthStencilState: nullptr,
+        .depthStencil = &depthStencilState,
         .multisample = {
-            .count = samplesCount,
+            .count = 1, // TODO need to get this from the render target
             .mask = 0xFFFFFFFF,
             .alphaToCoverageEnabled = rasterState.alphaToCoverage
         },
@@ -234,15 +234,12 @@ wgpu::RenderPipeline createWebGPURenderPipeline(wgpu::Device const& device,
         fragmentState.entryPoint = "main";
         fragmentState.constantCount = program.constants.size(),
         fragmentState.constants = program.constants.data(),
-        fragmentState.targetCount = colorFormats.size();
+        fragmentState.targetCount = 1; // TODO need to get this from the render target
         fragmentState.targets = colorTargets.data();
         assert_invariant(fragmentState.targetCount <= MRT::MAX_SUPPORTED_RENDER_TARGET_COUNT);
-        // A fragment shader implies at least one color target if it outputs color.
-        // This should be guaranteed by the caller ensuring colorFormats is not empty.
-        assert_invariant(fragmentState.targetCount > 0);
         for (size_t targetIndex = 0; targetIndex < fragmentState.targetCount; targetIndex++) {
             auto& colorTarget = colorTargets[targetIndex];
-            colorTarget.format = colorFormats[targetIndex];
+            colorTarget.format = colorFormat;
             colorTarget.blend = rasterState.hasBlending() ? &blendState : nullptr;
             colorTarget.writeMask =
                     rasterState.colorWrite ? wgpu::ColorWriteMask::All : wgpu::ColorWriteMask::None;