webgpu: debug descriptor sets option/functionality

Earlier I made mistakes. This hack fixes them but is suboptimal

README.md

@@ -31,7 +31,7 @@ repositories {
 }
 
 dependencies {
-    implementation 'com.google.android.filament:filament-android:1.59.5'
+    implementation 'com.google.android.filament:filament-android:1.59.4'
 }
 ```
 
@@ -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', '~> 1.59.5'
+pod 'Filament', '~> 1.59.4'
 ```
 
 ## Documentation

android/gradle.properties

@@ -1,5 +1,5 @@
 GROUP=com.google.android.filament
-VERSION_NAME=1.59.5
+VERSION_NAME=1.59.4
 
 POM_DESCRIPTION=Real-time physically based rendering engine for Android.
 

filament/backend/include/backend/DriverEnums.h

@@ -34,6 +34,9 @@
 #include <math/vec4.h>
 
 #include <array>
+#if !defined(NDEBUG)
+#include <string>
+#endif
 #include <type_traits>
 #include <variant>
 
@@ -1139,6 +1142,9 @@ struct ExternalSamplerDatum {
 static_assert(sizeof(ExternalSamplerDatum) == 12);
 
 struct DescriptorSetLayout {
+#if !defined(NDEBUG)
+    std::string label;
+#endif
     utils::FixedCapacityVector<DescriptorSetLayoutBinding> bindings;
 
 //  TODO: uncomment when needed

filament/backend/include/backend/Platform.h

@@ -149,13 +149,6 @@ public:
          *      - PlatformEGLAndroid
          */
         bool assertNativeWindowIsValid = false;
-
-        /**
-         * The action to take if a Drawable cannot be acquired. If true, the
-         * frame is aborted instead of panic. This is only supported for:
-         *      - PlatformMetal
-         */
-        bool metalDisablePanicOnDrawableFailure = false;
     };
 
     Platform() noexcept;

filament/backend/src/CommandStream.cpp

@@ -84,7 +84,7 @@ void CommandStream::execute(void* buffer) {
 
     Profiler profiler;
 
-    if (SYSTRACE_TAG) {
+    if constexpr (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);
@@ -100,7 +100,7 @@ void CommandStream::execute(void* buffer) {
         }
     });
 
-    if (SYSTRACE_TAG) {
+    if constexpr (SYSTRACE_TAG) {
         if (UTILS_UNLIKELY(mUsePerformanceCounter)) {
             // we want to remove all this when tracing is completely disabled
             profiler.stop();

filament/backend/src/metal/PlatformMetal.mm

@@ -45,9 +45,6 @@ PlatformMetal::~PlatformMetal() noexcept {
 }
 
 Driver* PlatformMetal::createDriver(void* /*sharedContext*/, const Platform::DriverConfig& driverConfig) noexcept {
-    pImpl->mDrawableFailureBehavior = driverConfig.metalDisablePanicOnDrawableFailure
-            ? DrawableFailureBehavior::ABORT_FRAME
-            : DrawableFailureBehavior::PANIC;
     return MetalDriverFactory::create(this, driverConfig);
 }
 

filament/backend/src/vulkan/VulkanConstants.h

@@ -152,12 +152,12 @@ static_assert(FVK_ENABLED(FVK_DEBUG_VALIDATION));
 #elif FVK_ENABLED(FVK_DEBUG_SYSTRACE)
 
     #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()
+    #define FVK_SYSTRACE_SCOPE()        SYSTRACE_CALL()
+    #define FVK_PROFILE_MARKER(marker)  SYSTRACE_CALL()
 
 #else
     #define FVK_SYSTRACE_CONTEXT()

filament/backend/src/webgpu/WGPUProgram.cpp

@@ -27,6 +27,7 @@
 
 #include <webgpu/webgpu_cpp.h>
 
+#include <algorithm>
 #include <sstream>
 #include <string_view>
 #include <vector>
@@ -125,21 +126,64 @@ namespace {
     return module;
 }
 
+// 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(constantsInfo.size());
-    for (size_t i = 0; i < constantsInfo.size(); i++) {
-        filament::backend::Program::SpecializationConstant const& specConstant = constantsInfo[i];
-        wgpu::ConstantEntry& constantEntry = constants[i];
-        constantEntry.key = wgpu::StringView(std::to_string(specConstant.id));
-        if (auto* v = std::get_if<int32_t>(&specConstant.value)) {
-            constantEntry.value = static_cast<double>(*v);
-        } else if (auto* f = std::get_if<float>(&specConstant.value)) {
-            constantEntry.value = static_cast<double>(*f);
-        } else if (auto* b = std::get_if<bool>(&specConstant.value)) {
-            constantEntry.value = *b ? 0.0 : 1.0;
+    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;
 }
@@ -154,6 +198,8 @@ WGPUProgram::WGPUProgram(wgpu::Device& device, Program& program)
               ShaderStage::FRAGMENT)),
       computeShaderModule(createShaderModule(device, name.c_str_safe(), program.getShadersSource(),
               ShaderStage::COMPUTE)),
-      constants(convertConstants(program.getSpecializationConstants())) {}
+      constants(convertConstants(program.getSpecializationConstants())) {
+    auto test = program.getShadersSource();
+}
 
 }// namespace filament::backend

filament/backend/src/webgpu/WebGPUConstants.h

@@ -34,6 +34,8 @@
 // order of calls).
 #define FWGPU_DEBUG_FORCE_LOG_TO_I 0x00000004
 
+#define FWGPU_DEBUG_DESCRIPTOR_SETS 0x00000008
+
 // Useful default combinations
 #define FWGPU_DEBUG_EVERYTHING     0xFFFFFFFF
 

filament/backend/src/webgpu/WebGPUDriver.cpp

@@ -389,9 +389,7 @@ Handle<HwTexture> WebGPUDriver::createTextureS() noexcept {
     return allocHandle<WGPUTexture>();
 }
 
-Handle<HwTexture> WebGPUDriver::importTextureS() noexcept {
-    return Handle<HwTexture>((Handle<HwTexture>::HandleId) mNextFakeHandle++);
-}
+Handle<HwTexture> WebGPUDriver::importTextureS() noexcept { return allocHandle<WGPUTexture>(); }
 
 Handle<HwProgram> WebGPUDriver::createProgramS() noexcept {
     return allocHandle<WGPUProgram>();
@@ -410,7 +408,7 @@ Handle<HwIndexBuffer> WebGPUDriver::createIndexBufferS() noexcept {
 }
 
 Handle<HwTexture> WebGPUDriver::createTextureViewS() noexcept {
-    return Handle<HwTexture>((Handle<HwTexture>::HandleId) mNextFakeHandle++);
+    return allocHandle<WGPUTexture>();
 }
 
 Handle<HwBufferObject> WebGPUDriver::createBufferObjectS() noexcept {
@@ -438,7 +436,7 @@ Handle<HwVertexBufferInfo> WebGPUDriver::createVertexBufferInfoS() noexcept {
 }
 
 Handle<HwTexture> WebGPUDriver::createTextureViewSwizzleS() noexcept {
-    return Handle<HwTexture>((Handle<HwTexture>::HandleId) mNextFakeHandle++);
+    return allocHandle<WGPUTexture>();
 }
 
 Handle<HwRenderTarget> WebGPUDriver::createDefaultRenderTargetS() noexcept {
@@ -450,15 +448,15 @@ Handle<HwDescriptorSetLayout> WebGPUDriver::createDescriptorSetLayoutS() noexcep
 }
 
 Handle<HwTexture> WebGPUDriver::createTextureExternalImageS() noexcept {
-    return Handle<HwTexture>((Handle<HwTexture>::HandleId) mNextFakeHandle++);
+    return allocHandle<WGPUTexture>();
 }
 
 Handle<HwTexture> WebGPUDriver::createTextureExternalImage2S() noexcept {
-    return Handle<HwTexture>((Handle<HwTexture>::HandleId) mNextFakeHandle++);
+    return allocHandle<WGPUTexture>();
 }
 
 Handle<HwTexture> WebGPUDriver::createTextureExternalImagePlaneS() noexcept {
-    return Handle<HwTexture>((Handle<HwTexture>::HandleId) mNextFakeHandle++);
+    return allocHandle<WGPUTexture>();
 }
 
 void WebGPUDriver::createSwapChainR(Handle<HwSwapChain> sch, void* nativeWindow, uint64_t flags) {
@@ -470,9 +468,10 @@ 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 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."
+    WebGPUDescriptorSet::initializeDummyResourcesIfNotAlready(mDevice,
+            mSwapChain->getColorFormat());
+    FWGPU_LOGW << "WebGPU support is highly limited, only supporting the hello-triangle sample in "
+                  "a brittle/hacked way and untested, likely, breaking in other samples."
                << 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
@@ -512,30 +511,46 @@ void WebGPUDriver::createBufferObjectR(Handle<HwBufferObject> boh, uint32_t byte
 
 void WebGPUDriver::createTextureR(Handle<HwTexture> th, SamplerType target, uint8_t levels,
         TextureFormat format, uint8_t samples, uint32_t w, uint32_t h, uint32_t depth,
-        TextureUsage usage) {}
+        TextureUsage usage) {
+    constructHandle<WGPUTexture>(th, target, levels, format, samples, w, h, depth, usage, mDevice);
+}
 
 void WebGPUDriver::createTextureViewR(Handle<HwTexture> th, Handle<HwTexture> srch,
-        uint8_t baseLevel, uint8_t levelCount) {}
+        uint8_t baseLevel, uint8_t levelCount) {
+    auto source = handleCast<WGPUTexture>(srch);
+
+    constructHandle<WGPUTexture>(th, source, baseLevel, levelCount);
+}
 
 void WebGPUDriver::createTextureViewSwizzleR(Handle<HwTexture> th, Handle<HwTexture> srch,
         backend::TextureSwizzle r, backend::TextureSwizzle g, backend::TextureSwizzle b,
-        backend::TextureSwizzle a) {}
+        backend::TextureSwizzle a) {
+    PANIC_POSTCONDITION("Swizzle WebGPU Texture is not supported");
+}
 
 void WebGPUDriver::createTextureExternalImage2R(Handle<HwTexture> th, backend::SamplerType target,
         backend::TextureFormat format, uint32_t width, uint32_t height, backend::TextureUsage usage,
-        Platform::ExternalImageHandleRef externalImage) {}
+        Platform::ExternalImageHandleRef externalImage) {
+    PANIC_POSTCONDITION("External WebGPU Texture is not supported");
+}
 
 void WebGPUDriver::createTextureExternalImageR(Handle<HwTexture> th, backend::SamplerType target,
         backend::TextureFormat format, uint32_t width, uint32_t height, backend::TextureUsage usage,
-        void* externalImage) {}
+        void* externalImage) {
+    PANIC_POSTCONDITION("External WebGPU Texture is not supported");
+}
 
 void WebGPUDriver::createTextureExternalImagePlaneR(Handle<HwTexture> th,
         backend::TextureFormat format, uint32_t width, uint32_t height, backend::TextureUsage usage,
-        void* image, uint32_t plane) {}
+        void* image, uint32_t plane) {
+    PANIC_POSTCONDITION("External WebGPU Texture is not supported");
+}
 
 void WebGPUDriver::importTextureR(Handle<HwTexture> th, intptr_t id, SamplerType target,
         uint8_t levels, TextureFormat format, uint8_t samples, uint32_t w, uint32_t h,
-        uint32_t depth, TextureUsage usage) {}
+        uint32_t depth, TextureUsage usage) {
+    PANIC_POSTCONDITION("Import WebGPU Texture is not supported");
+}
 
 void WebGPUDriver::createRenderPrimitiveR(Handle<HwRenderPrimitive> rph, Handle<HwVertexBuffer> vbh,
         Handle<HwIndexBuffer> ibh, PrimitiveType pt) {
@@ -575,7 +590,14 @@ void WebGPUDriver::createDescriptorSetLayoutR(Handle<HwDescriptorSetLayout> dslh
 void WebGPUDriver::createDescriptorSetR(Handle<HwDescriptorSet> dsh,
         Handle<HwDescriptorSetLayout> dslh) {
     auto layout = handleCast<WebGPUDescriptorSetLayout>(dslh);
-    constructHandle<WebGPUDescriptorSet>(dsh, layout->getLayout(), layout->getLayoutSize());
+    constructHandle<WebGPUDescriptorSet>(
+            dsh,
+#ifndef NDEBUG
+            wgpu::StringView(layout->getLabel()),
+#endif
+            layout->getLayout(),
+            layout->getBindGroupEntries()
+            );
 }
 
 Handle<HwStream> WebGPUDriver::createStreamNative(void* nativeStream) {
@@ -612,7 +634,7 @@ FenceStatus WebGPUDriver::getFenceStatus(Handle<HwFence> fh) {
 // We create all textures using VK_IMAGE_TILING_OPTIMAL, so our definition of "supported" is that
 // the GPU supports the given texture format with non-zero optimal tiling features.
 bool WebGPUDriver::isTextureFormatSupported(TextureFormat format) {
-    return true;
+    return WGPUTexture::fToWGPUTextureFormat(format) != wgpu::TextureFormat::Undefined;
 }
 
 bool WebGPUDriver::isTextureSwizzleSupported() {
@@ -760,8 +782,31 @@ void WebGPUDriver::compilePrograms(CompilerPriorityQueue priority,
     }
 }
 
-void WebGPUDriver::beginRenderPass(Handle<HwRenderTarget> rth, const RenderPassParams& params) {
+void WebGPUDriver::beginRenderPass(Handle<HwRenderTarget> rth, RenderPassParams const& params) {
     assert_invariant(mCommandEncoder);
+
+    auto* renderTarget = handleCast<WGPURenderTarget>(rth);
+    // 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) {
@@ -786,7 +831,7 @@ void WebGPUDriver::beginRenderPass(Handle<HwRenderTarget> rth, const RenderPassP
         .timestampWrites = nullptr,
     };
 
-    mRenderPassEncoder = mCommandEncoder.BeginRenderPass(&renderPassDescriptor);
+    mRenderPassEncoder = mCommandEncoder.BeginRenderPass(&renderPassDescriptor2);
     mRenderPassEncoder.SetViewport(params.viewport.left, params.viewport.bottom,
             params.viewport.width, params.viewport.height, params.depthRange.near, params.depthRange.far);
 }
@@ -914,7 +959,7 @@ void WebGPUDriver::bindPipeline(PipelineState const& pipelineState) {
             pipelineState.polygonOffset, pipelineState.primitiveType, mSwapChain->getColorFormat(),
             mSwapChain->getDepthFormat());
     // TODO: uncomment once we have a valid pipeline to set
-    // mRenderPassEncoder.SetPipeline(pipeline);
+    mRenderPassEncoder.SetPipeline(pipeline);
 }
 
 void WebGPUDriver::bindRenderPrimitive(Handle<HwRenderPrimitive> rph) {
@@ -934,10 +979,18 @@ void WebGPUDriver::bindRenderPrimitive(Handle<HwRenderPrimitive> rph) {
 }
 
 void WebGPUDriver::draw2(uint32_t indexOffset, uint32_t indexCount, uint32_t instanceCount) {
+    // 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> rph,
-        uint32_t indexOffset, uint32_t indexCount, uint32_t instanceCount) {
+void WebGPUDriver::draw(PipelineState, Handle<HwRenderPrimitive>, uint32_t indexOffset,
+        uint32_t indexCount, uint32_t instanceCount) {
+    draw2(indexOffset, indexCount, instanceCount);
 }
 
 void WebGPUDriver::dispatchCompute(Handle<HwProgram> program, math::uint3 workGroupCount) {
@@ -973,34 +1026,156 @@ void WebGPUDriver::updateDescriptorSetBuffer(Handle<HwDescriptorSet> dsh,
 
 void WebGPUDriver::updateDescriptorSetTexture(Handle<HwDescriptorSet> dsh,
         backend::descriptor_binding_t binding, Handle<HwTexture> th, SamplerParams params) {
-    /*
     auto bindGroup = handleCast<WebGPUDescriptorSet>(dsh);
     auto texture = handleCast<WGPUTexture>(th);
 
-    // TODO very high odds badd assumptions are in here about handling HwTexture. Revisit with more
-    // understanding. Right now assuming there is a wgpu::TextureView filled in
     if (!bindGroup->getIsLocked()) {
+        // Dawn will cache duplicate samplers, so we don't strictly need to maintain a cache.
+        //  Making a cache might save us minor perf by reducing param translation
+        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->texView };
+            .textureView = texture->getTexView() };
         bindGroup->addEntry(tEntry.binding, std::move(tEntry));
 
         wgpu::BindGroupEntry sEntry{ .binding = static_cast<uint32_t>(binding * 2 + 1),
-            .sampler = texture->sampler };
+            .sampler = sampler };
         bindGroup->addEntry(sEntry.binding, std::move(sEntry));
     }
-    //TODO Just the setup, this function stilll needs the rest of logic implemented
-     */
 }
 
-void WebGPUDriver::bindDescriptorSet(Handle<HwDescriptorSet> dsh, backend::descriptor_set_t set,
-        backend::DescriptorSetOffsetArray&& offsets) {
-    auto bindGroup = handleCast<WebGPUDescriptorSet>(dsh);
-    // TODO: presume we need this, use it. Probably Encoder::SetBindGroup
-    auto wbg = bindGroup->lockAndReturn(mDevice);
+void WebGPUDriver::bindDescriptorSet(Handle<HwDescriptorSet> dsh,
+        backend::descriptor_set_t setIndex, backend::DescriptorSetOffsetArray&& offsets) {
+    const auto bindGroup = handleCast<WebGPUDescriptorSet>(dsh);
+    const auto wbg = bindGroup->lockAndReturn(mDevice);
+    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;
+
+    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;
+            break;
+        }
+        case SamplerMagFilter::LINEAR: {
+            desc.magFilter = wgpu::FilterMode::Linear;
+            break;
+        }
+    }
+    switch (params.filterMin) {
+        case SamplerMinFilter::NEAREST: {
+            desc.minFilter = wgpu::FilterMode::Nearest;
+            // 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;
+            // Metal Driver uses an explicit not-mipmapped value webgpu lacks. Nearest should
+            // suffice
+
+            desc.mipmapFilter = wgpu::MipmapFilterMode::Nearest;
+            break;
+        }
+        case SamplerMinFilter::NEAREST_MIPMAP_NEAREST: {
+            desc.minFilter = wgpu::FilterMode::Nearest;
+            desc.mipmapFilter = wgpu::MipmapFilterMode::Nearest;
+            break;
+        }
+        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: {
+            desc.minFilter = wgpu::FilterMode::Linear;
+            desc.mipmapFilter = wgpu::MipmapFilterMode::Linear;
+            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: 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) {
+        case SamplerWrapMode::CLAMP_TO_EDGE: {
+            return wgpu::AddressMode::ClampToEdge;
+            break;
+        }
+        case SamplerWrapMode::REPEAT: {
+            return wgpu::AddressMode::Repeat;
+            break;
+        }
+        case SamplerWrapMode::MIRRORED_REPEAT: {
+            return wgpu::AddressMode::MirrorRepeat;
+            break;
+        }
+    }
+    return wgpu::AddressMode::Undefined;
+}
+
 
 } // namespace filament

filament/backend/src/webgpu/WebGPUDriver.h

@@ -56,7 +56,8 @@ private:
     explicit WebGPUDriver(WebGPUPlatform& platform, const Platform::DriverConfig& driverConfig) noexcept;
     [[nodiscard]] ShaderModel getShaderModel() const noexcept final;
     [[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/backend/src/webgpu/WebGPUHandles.h

@@ -14,7 +14,6 @@
  * limitations under the License.
  */
 
-
 #ifndef TNT_FILAMENT_BACKEND_WEBGPUHANDLES_H
 #define TNT_FILAMENT_BACKEND_WEBGPUHANDLES_H
 
@@ -27,7 +26,13 @@
 
 #include <webgpu/webgpu_cpp.h>
 
+#include <array>
+#include <bitset>
 #include <cstdint>
+#ifndef NDEBUG
+#include <string>
+#include <string_view>
+#endif
 #include <vector>
 
 namespace filament::backend {
@@ -98,80 +103,136 @@ struct WGPUBufferObject : HwBufferObject {
     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;
+    };
+
     WebGPUDescriptorSetLayout(DescriptorSetLayout const& layout, wgpu::Device const& device);
     ~WebGPUDescriptorSetLayout();
+#ifndef NDEBUG
+    [[nodiscard]] std::string const& getLabel() const { return mLabel; }
+#endif
     [[nodiscard]] const wgpu::BindGroupLayout& getLayout() const { return mLayout; }
-    [[nodiscard]] uint getLayoutSize() const { return mLayoutSize; }
+    [[nodiscard]] std::vector<BindGroupEntryInfo> const& getBindGroupEntries() const {
+        return mBindGroupEntries;
+    }
 
 private:
     // TODO: If this is useful elsewhere, remove it from this class
     // Convert Filament Shader Stage Flags bitmask to webgpu equivilant
     static wgpu::ShaderStage filamentStageToWGPUStage(ShaderStageFlags fFlags);
-    uint mLayoutSize;
+#ifndef NDEBUG
+    std::string const mLabel;
+#endif
+    std::vector<BindGroupEntryInfo> mBindGroupEntries;
     wgpu::BindGroupLayout mLayout;
 };
 
 class WebGPUDescriptorSet final : public HwDescriptorSet {
 public:
-    WebGPUDescriptorSet(const wgpu::BindGroupLayout& layout, uint layoutSize);
+    static void initializeDummyResourcesIfNotAlready(wgpu::Device const&,
+            wgpu::TextureFormat aColorFormat);
+
+    WebGPUDescriptorSet(
+#ifndef NDEBUG
+            wgpu::StringView const& label,
+#endif
+            wgpu::BindGroupLayout const& layout,
+            std::vector<WebGPUDescriptorSetLayout::BindGroupEntryInfo> const& bindGroupEntries);
     ~WebGPUDescriptorSet();
 
-    wgpu::BindGroup lockAndReturn(wgpu::Device const& device);
-    void addEntry(uint index, wgpu::BindGroupEntry&& entry);
+    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;
 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&);
+#ifndef NDEBUG
+    const wgpu::StringView mLabel;
+#endif
     // 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;
-    std::vector<wgpu::BindGroupEntry> entries;
-    wgpu::BindGroup mBindGroup;
+    wgpu::BindGroupLayout const& mLayout;
+    static constexpr uint8_t INVALID_INDEX = MAX_DESCRIPTOR_COUNT + 1;
+    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;
 };
 
-// TODO: Currently WGPUTexture is not used by WebGPU for useful task.
-// Update the struct when used by WebGPU driver.
-struct WGPUTexture : public HwTexture {
+class WGPUTexture : public HwTexture {
+public:
     WGPUTexture(SamplerType target, uint8_t levels, TextureFormat format, uint8_t samples,
-            uint32_t width, uint32_t height, uint32_t depth, TextureUsage usage) noexcept;
+            uint32_t width, uint32_t height, uint32_t depth, TextureUsage usage,
+            wgpu::Device const& device) noexcept;
 
-    // constructors for creating texture views
-    WGPUTexture(WGPUTexture const* src, uint8_t baseLevel, uint8_t levelCount) noexcept;
+    WGPUTexture(WGPUTexture* src, uint8_t baseLevel, uint8_t levelCount) noexcept;
 
-    wgpu::Texture texture = nullptr;
-    // TODO: Adding this but not yet setting it up. Filament "Textures" are combined image samplers,
-    // rep both.
-    wgpu::Sampler sampler = nullptr;
-    //TODO: Not sure all the ways HwTexture is used. Overloading like this might be entirely wrong.
-    wgpu::TextureView texView = nullptr;
+    const wgpu::Texture& getTexture() const { return mTexture; }
+    const wgpu::TextureView& getTexView() const { return mTexView; }
+
+    // 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,
+            SamplerType target);
+    // CreateTextureR has info for a texture and sampler. Texture Views are needed for binding,
+    // along with a sampler Current plan: Inherit the sampler and Texture to always exist (It is a
+    // ref counted pointer) when making views. View is optional
+    wgpu::Texture mTexture = nullptr;
+    wgpu::TextureUsage mUsage = wgpu::TextureUsage::None;
+    wgpu::TextureFormat mFormat = wgpu::TextureFormat::Undefined;
+    uint32_t mArrayLayerCount = 1;
+    wgpu::TextureView mTexView = nullptr;
+    wgpu::TextureUsage fToWGPUTextureUsage(const filament::backend::TextureUsage& fUsage);
 };
 
 struct WGPURenderPrimitive : public HwRenderPrimitive {
-    WGPURenderPrimitive() {}
-
-    void setBuffers(WGPUVertexBufferInfo const* const vbi,
-            WGPUVertexBuffer* vertexBuffer, WGPUIndexBuffer* indexBuffer);
 
     WGPUVertexBuffer* vertexBuffer = nullptr;
     WGPUIndexBuffer* indexBuffer = nullptr;
 };
 
-// TODO: Currently WGPURenderTarget is not used by WebGPU for useful task.
-// Update the struct when used by WebGPU driver.
-struct WGPURenderTarget : public HwRenderTarget {
+class WGPURenderTarget : public HwRenderTarget {
+public:
     class Attachment {
     public:
-        friend struct WGPURenderTarget;
+        friend class WGPURenderTarget;
 
         Attachment() = default;
         Attachment(WGPUTexture* gpuTexture, uint8_t level = 0, uint16_t layer = 0)
             : level(level),
               layer(layer),
-              texture(gpuTexture->texture),
+              texture(gpuTexture->getTexture()),
               mWGPUTexture(gpuTexture) {}
+        operator bool() const {
+            return mWGPUTexture != nullptr;
+        }
 
         uint8_t level = 0;
         uint16_t layer = 0;
@@ -187,8 +248,8 @@ struct WGPURenderTarget : public HwRenderTarget {
         : HwRenderTarget(0, 0),
           defaultRenderTarget(true) {}
 
-    void setUpRenderPassAttachments(wgpu::RenderPassDescriptor* descriptor,
-            const RenderPassParams& params);
+    void setUpRenderPassAttachments(wgpu::RenderPassDescriptor& descriptor,
+            wgpu::TextureView const& textureView, RenderPassParams const& params);
 
     math::uint2 getAttachmentSize() noexcept;
 
@@ -198,15 +259,15 @@ struct WGPURenderTarget : public HwRenderTarget {
     Attachment getDrawColorAttachment(size_t index);
     Attachment getReadColorAttachment(size_t index);
 
+    static wgpu::LoadOp getLoadOperation(const RenderPassParams& params, TargetBufferFlags buffer);
+    static wgpu::StoreOp getStoreOperation(const RenderPassParams& params, TargetBufferFlags buffer);
 private:
-    static wgpu::LoadOp getLoadAction(const RenderPassParams& params, TargetBufferFlags buffer);
-    static wgpu::LoadOp getStoreAction(const RenderPassParams& params, TargetBufferFlags buffer);
-
     bool defaultRenderTarget = false;
     uint8_t samples = 1;
 
     Attachment color[MRT::MAX_SUPPORTED_RENDER_TARGET_COUNT] = {};
     math::uint2 attachmentSize = {};
+    std::vector<wgpu::RenderPassColorAttachment> colorAttachments {};
 };
 
 }// namespace filament::backend

filament/backend/src/webgpu/WebGPUPipelineCreation.cpp

@@ -235,6 +235,7 @@ wgpu::RenderPipeline createWebGPURenderPipeline(wgpu::Device const& device,
         fragmentState.constantCount = program.constants.size(),
         fragmentState.constants = program.constants.data(),
         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);
         for (size_t targetIndex = 0; targetIndex < fragmentState.targetCount; targetIndex++) {
             auto& colorTarget = colorTargets[targetIndex];

filament/backend/src/webgpu/WebGPUSwapChain.cpp

@@ -105,7 +105,7 @@ void printSurfaceConfiguration(wgpu::SurfaceConfiguration const& config,
 }
 #endif
 
-constexpr wgpu::TextureFormat selectColorFormat(size_t availableFormatsCount,
+[[nodiscard]] constexpr wgpu::TextureFormat selectColorFormat(size_t availableFormatsCount,
         wgpu::TextureFormat const* availableFormats, bool useSRGBColorSpace) {
     const std::array expectedColorFormats =
             useSRGBColorSpace ?
@@ -123,7 +123,7 @@ constexpr wgpu::TextureFormat selectColorFormat(size_t availableFormatsCount,
     return *firstFoundColorFormat;
 }
 
-constexpr wgpu::TextureFormat selectDepthFormat(bool depth32FloatStencil8Enabled,
+[[nodiscard]] constexpr wgpu::TextureFormat selectDepthFormat(bool depth32FloatStencil8Enabled,
         bool needStencil) {
     if (needStencil) {
         if (depth32FloatStencil8Enabled) {
@@ -137,7 +137,7 @@ constexpr wgpu::TextureFormat selectDepthFormat(bool depth32FloatStencil8Enabled
     }
 }
 
-constexpr wgpu::PresentMode selectPresentMode(size_t availablePresentModesCount,
+[[nodiscard]] constexpr wgpu::PresentMode selectPresentMode(size_t availablePresentModesCount,
         wgpu::PresentMode const* availablePresentModes) {
     // Verify that our chosen present mode is supported. In practice all devices support the FIFO
     // mode, but we check for it anyway for completeness.  (and to avoid validation warnings)
@@ -151,7 +151,7 @@ constexpr wgpu::PresentMode selectPresentMode(size_t availablePresentModesCount,
     return desiredPresentMode;
 }
 
-constexpr wgpu::CompositeAlphaMode selectAlphaMode(size_t availableAlphaModesCount,
+[[nodiscard]] constexpr wgpu::CompositeAlphaMode selectAlphaMode(size_t availableAlphaModesCount,
         wgpu::CompositeAlphaMode const* availableAlphaModes) {
     bool autoAvailable = false;
     bool inheritAvailable = false;
@@ -222,13 +222,58 @@ void initConfig(wgpu::SurfaceConfiguration& config, wgpu::Device const& device,
     config.alphaMode = selectAlphaMode(capabilities.alphaModeCount, capabilities.alphaModes);
 }
 
+[[nodiscard]] wgpu::Texture createDepthTexture(wgpu::Device const& device,
+        wgpu::Extent2D const& extent, wgpu::TextureFormat depthFormat) {
+    wgpu::TextureDescriptor descriptor{ .label = "depth_texture",
+        .usage = wgpu::TextureUsage::TextureBinding | wgpu::TextureUsage::RenderAttachment,
+        .dimension = wgpu::TextureDimension::e2D,
+        .size = { .width = extent.width, .height = extent.height, .depthOrArrayLayers = 1 },
+        .format = depthFormat,
+        .mipLevelCount = 1,
+        .sampleCount = 1,
+        .viewFormatCount = 1,
+        .viewFormats = &depthFormat
+    };
+    wgpu::Texture depthTexture = device.CreateTexture(&descriptor);
+    FILAMENT_CHECK_POSTCONDITION(depthTexture) << "Failed to create depth texture with width "
+                                               << extent.width << " and height " << extent.height;
+    return depthTexture;
+}
+
+[[nodiscard]] wgpu::TextureView createDepthTextureView(wgpu::Texture const& depthTexture,
+        wgpu::TextureFormat depthFormat, bool needStencil) {
+    wgpu::TextureViewDescriptor descriptor{
+        .label = "depth_texture_view",
+        .format = depthFormat,
+        .dimension = wgpu::TextureViewDimension::e2D,
+        .baseMipLevel = 0,
+        .mipLevelCount = 1,
+        .baseArrayLayer = 0,
+        .arrayLayerCount = 1,
+        .aspect = wgpu::TextureAspect::DepthOnly,
+        .usage = wgpu::TextureUsage::TextureBinding | wgpu::TextureUsage::RenderAttachment
+    };
+    if (needStencil) {
+        descriptor.aspect = wgpu::TextureAspect::All;
+    }
+    wgpu::TextureView depthTextureView = depthTexture.CreateView(&descriptor);
+    FILAMENT_CHECK_POSTCONDITION(depthTextureView) << "Failed to create depth texture view";
+    return depthTextureView;
+}
+
 }// namespace
 
 namespace filament::backend {
 
 WebGPUSwapChain::WebGPUSwapChain(wgpu::Surface&& surface, wgpu::Extent2D const& surfaceSize,
         wgpu::Adapter const& adapter, wgpu::Device const& device, uint64_t flags)
-    : mSurface(surface) {
+    : mDevice(device),
+      mSurface(surface),
+      mNeedStencil((flags & SWAP_CHAIN_HAS_STENCIL_BUFFER) != 0),
+      mDepthFormat(selectDepthFormat(device.HasFeature(wgpu::FeatureName::Depth32FloatStencil8),
+              mNeedStencil)),
+      mDepthTexture(createDepthTexture(device, surfaceSize, mDepthFormat)),
+      mDepthTextureView(createDepthTextureView(mDepthTexture, mDepthFormat, mNeedStencil)) {
     wgpu::SurfaceCapabilities capabilities = {};
     if (!mSurface.GetCapabilities(adapter, &capabilities)) {
         FWGPU_LOGW << "Failed to get WebGPU surface capabilities" << utils::io::endl;
@@ -238,19 +283,14 @@ WebGPUSwapChain::WebGPUSwapChain(wgpu::Surface&& surface, wgpu::Extent2D const&
 #endif
     }
     const bool useSRGBColorSpace = (flags & SWAP_CHAIN_CONFIG_SRGB_COLORSPACE) != 0;
-    const bool needStencil = (flags & SWAP_CHAIN_HAS_STENCIL_BUFFER) != 0;
     initConfig(mConfig, device, capabilities, surfaceSize, useSRGBColorSpace);
-    mDepthFormat = selectDepthFormat(device.HasFeature(wgpu::FeatureName::Depth32FloatStencil8),
-            needStencil);
 #if FWGPU_ENABLED(FWGPU_PRINT_SYSTEM)
     printSurfaceConfiguration(mConfig, mDepthFormat);
 #endif
     mSurface.Configure(&mConfig);
 }
 
-WebGPUSwapChain::~WebGPUSwapChain() {
-    mSurface.Unconfigure();
-}
+WebGPUSwapChain::~WebGPUSwapChain() { mSurface.Unconfigure(); }
 
 void WebGPUSwapChain::setExtent(wgpu::Extent2D const& currentSurfaceSize) {
     FILAMENT_CHECK_POSTCONDITION(currentSurfaceSize.width > 0 || currentSurfaceSize.height > 0)
@@ -267,6 +307,8 @@ void WebGPUSwapChain::setExtent(wgpu::Extent2D const& currentSurfaceSize) {
         // TODO we may need to ensure no surface texture is in flight when we do this. some
         //      synchronization may be necessary
         mSurface.Configure(&mConfig);
+        mDepthTexture = createDepthTexture(mDevice, currentSurfaceSize, mDepthFormat);
+        mDepthTextureView = createDepthTextureView(mDepthTexture, mDepthFormat, mNeedStencil);
     }
 }
 

filament/backend/src/webgpu/WebGPUSwapChain.h

@@ -38,14 +38,20 @@ public:
 
     [[nodiscard]] wgpu::TextureView getCurrentSurfaceTextureView(wgpu::Extent2D const&);
 
+    [[nodiscard]] wgpu::TextureView getDepthTextureView() const { return mDepthTextureView; }
+
     void present();
 
 private:
     void setExtent(wgpu::Extent2D const&);
 
+    wgpu::Device mDevice = nullptr;
     wgpu::Surface mSurface = {};
     wgpu::SurfaceConfiguration mConfig = {};
+    bool mNeedStencil = false;
     wgpu::TextureFormat mDepthFormat = wgpu::TextureFormat::Undefined;
+    wgpu::Texture mDepthTexture = nullptr;
+    wgpu::TextureView mDepthTextureView = nullptr;
 };
 
 } // namespace filament::backend

filament/backend/src/webgpu/platform/WebGPUPlatform.cpp

@@ -99,10 +99,9 @@ wgpu::Adapter WebGPUPlatform::requestAdapter(wgpu::Surface const& surface) {
 
 wgpu::Device WebGPUPlatform::requestDevice(wgpu::Adapter const& adapter) {
     // TODO consider passing limits
-    constexpr std::array desiredFeatures = {
-        wgpu::FeatureName::DepthClipControl,
-        wgpu::FeatureName::Depth32FloatStencil8,
-        wgpu::FeatureName::CoreFeaturesAndLimits };
+    constexpr std::array desiredFeatures = { wgpu::FeatureName::DepthClipControl,
+        wgpu::FeatureName::Depth32FloatStencil8, wgpu::FeatureName::CoreFeaturesAndLimits,
+        wgpu::FeatureName::TransientAttachments };
     std::vector<wgpu::FeatureName> requiredFeatures;
     requiredFeatures.reserve(desiredFeatures.size());
     wgpu::SupportedFeatures supportedFeatures;

filament/include/filament/Engine.h

@@ -317,15 +317,6 @@ public:
          */
         size_t metalUploadBufferSizeBytes = 512 * 1024;
 
-        /**
-         * The action to take if a Drawable cannot be acquired.
-         *
-         * 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.
-         */
-        bool metalDisablePanicOnDrawableFailure = false;
-
         /**
          * Set to `true` to forcibly disable parallel shader compilation in the backend.
          * Currently only honored by the GL and Metal backends.

filament/src/details/Engine.cpp

@@ -138,7 +138,6 @@ Engine* FEngine::create(Builder const& builder) {
                 .forceGLES2Context = instance->getConfig().forceGLES2Context,
                 .stereoscopicType = instance->getConfig().stereoscopicType,
                 .assertNativeWindowIsValid = instance->features.backend.opengl.assert_native_window_is_valid,
-                .metalDisablePanicOnDrawableFailure = instance->getConfig().metalDisablePanicOnDrawableFailure,
         };
         instance->mDriver = platform->createDriver(sharedContext, driverConfig);
 
@@ -734,7 +733,6 @@ int FEngine::loop() {
             .forceGLES2Context = mConfig.forceGLES2Context,
             .stereoscopicType =  mConfig.stereoscopicType,
             .assertNativeWindowIsValid = features.backend.opengl.assert_native_window_is_valid,
-            .metalDisablePanicOnDrawableFailure = mConfig.metalDisablePanicOnDrawableFailure,
     };
     mDriver = mPlatform->createDriver(mSharedGLContext, driverConfig);
 

filament/src/details/Material.cpp

@@ -1139,6 +1139,8 @@ void FMaterial::precacheDepthVariants(FEngine& engine) {
 
 void FMaterial::processDescriptorSets(FEngine& engine, MaterialParser const* const parser) {
     UTILS_UNUSED_IN_RELEASE bool success;
+    utils::CString namestr;
+    parser->getName(&namestr);
 
     success = parser->getDescriptorBindings(&mProgramDescriptorBindings);
     assert_invariant(success);
@@ -1147,6 +1149,11 @@ void FMaterial::processDescriptorSets(FEngine& engine, MaterialParser const* con
     success = parser->getDescriptorSetLayout(&descriptorSetLayout);
     assert_invariant(success);
 
+    descriptorSetLayout[0].label =  namestr.c_str();
+    descriptorSetLayout[1].label = namestr.c_str();
+    descriptorSetLayout[0].label+="0\0";
+    descriptorSetLayout[1].label+="1\0";
+
     mDescriptorSetLayout = {
             engine.getDescriptorSetLayoutFactory(),
             engine.getDriverApi(), std::move(descriptorSetLayout[0]) };
@@ -1154,6 +1161,7 @@ void FMaterial::processDescriptorSets(FEngine& engine, MaterialParser const* con
     mPerViewDescriptorSetLayout = {
             engine.getDescriptorSetLayoutFactory(),
             engine.getDriverApi(), std::move(descriptorSetLayout[1]) };
+
 }
 
 descriptor_binding_t FMaterial::getSamplerBinding(

ios/CocoaPods/Filament.podspec

@@ -1,12 +1,12 @@
 Pod::Spec.new do |spec|
   spec.name = "Filament"
-  spec.version = "1.59.5"
+  spec.version = "1.59.4"
   spec.license = { :type => "Apache 2.0", :file => "LICENSE" }
   spec.homepage = "https://google.github.io/filament"
   spec.authors = "Google LLC."
   spec.summary = "Filament is a real-time physically based rendering engine for Android, iOS, Windows, Linux, macOS, and WASM/WebGL."
   spec.platform = :ios, "11.0"
-  spec.source = { :http => "https://github.com/google/filament/releases/download/v1.59.5/filament-v1.59.5-ios.tgz" }
+  spec.source = { :http => "https://github.com/google/filament/releases/download/v1.59.4/filament-v1.59.4-ios.tgz" }
 
   # Fix linking error with Xcode 12; we do not yet support the simulator on Apple silicon.
   spec.pod_target_xcconfig = {

libs/filabridge/src/DescriptorSets.cpp

@@ -33,11 +33,11 @@ namespace filament::descriptor_sets {
 
 using namespace backend;
 
-static DescriptorSetLayout const postProcessDescriptorSetLayout{{
+static DescriptorSetLayout const postProcessDescriptorSetLayout{"postProcess", {
     { DescriptorType::UNIFORM_BUFFER, ShaderStageFlags::VERTEX | ShaderStageFlags::FRAGMENT,  +PerViewBindingPoints::FRAME_UNIFORMS },
 }};
 
-static DescriptorSetLayout const depthVariantDescriptorSetLayout{{
+static DescriptorSetLayout const depthVariantDescriptorSetLayout{"depthVariant",{
     { DescriptorType::UNIFORM_BUFFER, ShaderStageFlags::VERTEX | ShaderStageFlags::FRAGMENT,  +PerViewBindingPoints::FRAME_UNIFORMS },
 }};
 
@@ -46,14 +46,14 @@ static DescriptorSetLayout const depthVariantDescriptorSetLayout{{
 // dedicated SSR vertex shader), which uses perViewDescriptorSetLayout.
 // This means that PerViewBindingPoints::SHADOWS must be in the layout even though it's not used
 // by the SSR variant.
-static DescriptorSetLayout const ssrVariantDescriptorSetLayout{{
+static DescriptorSetLayout const ssrVariantDescriptorSetLayout{"ssrVariant", {
    { DescriptorType::UNIFORM_BUFFER, ShaderStageFlags::VERTEX | ShaderStageFlags::FRAGMENT,  +PerViewBindingPoints::FRAME_UNIFORMS },
    { DescriptorType::UNIFORM_BUFFER, ShaderStageFlags::VERTEX | ShaderStageFlags::FRAGMENT,  +PerViewBindingPoints::SHADOWS        },
    { DescriptorType::SAMPLER,                                   ShaderStageFlags::FRAGMENT,  +PerViewBindingPoints::STRUCTURE      },
    { DescriptorType::SAMPLER,                                   ShaderStageFlags::FRAGMENT,  +PerViewBindingPoints::SSR            },
 }};
 
-static DescriptorSetLayout perViewDescriptorSetLayout = {{
+static DescriptorSetLayout perViewDescriptorSetLayout = {"perView", {
     { DescriptorType::UNIFORM_BUFFER, ShaderStageFlags::VERTEX | ShaderStageFlags::FRAGMENT,  +PerViewBindingPoints::FRAME_UNIFORMS },
     { DescriptorType::UNIFORM_BUFFER, ShaderStageFlags::VERTEX | ShaderStageFlags::FRAGMENT,  +PerViewBindingPoints::SHADOWS        },
     { DescriptorType::UNIFORM_BUFFER,                            ShaderStageFlags::FRAGMENT,  +PerViewBindingPoints::LIGHTS         },
@@ -68,7 +68,7 @@ static DescriptorSetLayout perViewDescriptorSetLayout = {{
     { DescriptorType::SAMPLER,                                   ShaderStageFlags::FRAGMENT,  +PerViewBindingPoints::FOG            },
 }};
 
-static DescriptorSetLayout perRenderableDescriptorSetLayout = {{
+static DescriptorSetLayout perRenderableDescriptorSetLayout = {"preRenderable",{
     { DescriptorType::UNIFORM_BUFFER, ShaderStageFlags::VERTEX | ShaderStageFlags::FRAGMENT,  +PerRenderableBindingPoints::OBJECT_UNIFORMS, DescriptorFlags::DYNAMIC_OFFSET },
     { DescriptorType::UNIFORM_BUFFER, ShaderStageFlags::VERTEX | ShaderStageFlags::FRAGMENT,  +PerRenderableBindingPoints::BONES_UNIFORMS,  DescriptorFlags::DYNAMIC_OFFSET },
     { DescriptorType::UNIFORM_BUFFER, ShaderStageFlags::VERTEX | ShaderStageFlags::FRAGMENT,  +PerRenderableBindingPoints::MORPHING_UNIFORMS         },

libs/gltfio/src/AssetLoader.cpp

@@ -50,6 +50,8 @@
 #include <utils/Log.h>
 #include <utils/Panic.h>
 #include <utils/NameComponentManager.h>
+
+#define SYSTRACE_TAG SYSTRACE_TAG_GLTFIO
 #include <utils/Systrace.h>
 
 #include <tsl/robin_map.h>

libs/gltfio/src/ResourceLoader.cpp

@@ -37,7 +37,10 @@
 #include <utils/compiler.h>
 #include <utils/JobSystem.h>
 #include <utils/Log.h>
+
+#define SYSTRACE_TAG SYSTRACE_TAG_GLTFIO
 #include <utils/Systrace.h>
+
 #include <utils/Path.h>
 
 #include <cgltf.h>

libs/gltfio/src/Utility.cpp

@@ -21,6 +21,8 @@
 #include "GltfEnums.h"
 
 #include <utils/Log.h>
+
+#define SYSTRACE_TAG SYSTRACE_TAG_GLTFIO
 #include <utils/Systrace.h>
 
 #define CGLTF_IMPLEMENTATION

libs/utils/include/utils/Systrace.h

@@ -17,24 +17,23 @@
 #ifndef TNT_UTILS_SYSTRACE_H
 #define TNT_UTILS_SYSTRACE_H
 
-
-#define SYSTRACE_TAG_NEVER          (0)
-#define SYSTRACE_TAG_ALWAYS         (1<<0)
-#define SYSTRACE_TAG_FILAMENT       (1<<1)  // don't change, used in makefiles
-#define SYSTRACE_TAG_JOBSYSTEM      (1<<2)
+#define SYSTRACE_TAG_DISABLED       (0)
+#define SYSTRACE_TAG_FILAMENT       (2) // don't change used in makefiles
+#define SYSTRACE_TAG_JOBSYSTEM      (3)
+#define SYSTRACE_TAG_GLTFIO         (4)
 
 /*
- * The SYSTRACE_ macros use SYSTRACE_TAG as a the TAG, which should be defined
- * before this file is included. If not, the SYSTRACE_TAG_ALWAYS tag will be used.
+ * The SYSTRACE_ macros use SYSTRACE_TAG as a category, which must be defined
+ * before this file is included.
  */
 
 #ifndef SYSTRACE_TAG
-#define SYSTRACE_TAG (SYSTRACE_TAG_ALWAYS)
+#   error SYSTRACE_TAG must be set to SYSTRACE_TAG_{DISABLED|FILAMENT|JOBSYSTEM}
 #endif
 
 // Systrace on Apple platforms is fragile and adds overhead, should only be enabled in dev builds.
 #ifndef FILAMENT_APPLE_SYSTRACE
-#define FILAMENT_APPLE_SYSTRACE 0
+#   define FILAMENT_APPLE_SYSTRACE 0
 #endif
 
 #if defined(__ANDROID__)
@@ -44,7 +43,6 @@
 #else
 
 #define SYSTRACE_ENABLE()
-#define SYSTRACE_DISABLE()
 #define SYSTRACE_CONTEXT()
 #define SYSTRACE_NAME(name)
 #define SYSTRACE_FRAME_ID(frame)
@@ -56,6 +54,6 @@
 #define SYSTRACE_VALUE32(name, val)
 #define SYSTRACE_VALUE64(name, val)
 
-#endif // ANDROID
+#endif
 
 #endif // TNT_UTILS_SYSTRACE_H

libs/utils/include/utils/android/Systrace.h

@@ -17,226 +17,75 @@
 #ifndef TNT_UTILS_ANDROID_SYSTRACE_H
 #define TNT_UTILS_ANDROID_SYSTRACE_H
 
-#include <atomic>
+#include <perfetto/perfetto.h>
 
 #include <stdint.h>
-#include <stdio.h>
-#include <unistd.h>
 
-#include <utils/compiler.h>
+PERFETTO_DEFINE_CATEGORIES_IN_NAMESPACE(systrace,
+        perfetto::Category("filament"),
+        perfetto::Category("jobsystem"),
+        perfetto::Category("gltfio"));
 
-// enable tracing
-#define SYSTRACE_ENABLE() ::utils::details::Systrace::enable(SYSTRACE_TAG)
+PERFETTO_USE_CATEGORIES_FROM_NAMESPACE(systrace);
 
-// disable tracing
-#define SYSTRACE_DISABLE() ::utils::details::Systrace::disable(SYSTRACE_TAG)
+#if SYSTRACE_TAG == SYSTRACE_TAG_FILAMENT
+#   define UTILS_PERFETTO_CATEGORY "filament"
+#elif SYSTRACE_TAG == SYSTRACE_TAG_JOBSYSTEM
+#   define UTILS_PERFETTO_CATEGORY "jobsystem"
+#elif SYSTRACE_TAG == SYSTRACE_TAG_GLTFIO
+#   define UTILS_PERFETTO_CATEGORY "gltfio"
+#endif
 
+#if SYSTRACE_TAG == SYSTRACE_TAG_DISABLED
 
-/**
- * Creates a Systrace context in the current scope. needed for calling all other systrace
- * commands below.
- */
-#define SYSTRACE_CONTEXT() ::utils::details::Systrace ___trctx(SYSTRACE_TAG)
+#define SYSTRACE_ENABLE()
+#define SYSTRACE_CONTEXT()
+#define SYSTRACE_NAME(name)
+#define SYSTRACE_FRAME_ID(frame)
+#define SYSTRACE_NAME_BEGIN(name)
+#define SYSTRACE_NAME_END()
+#define SYSTRACE_CALL()
+#define SYSTRACE_ASYNC_BEGIN(name, cookie)
+#define SYSTRACE_ASYNC_END(name, cookie)
+#define SYSTRACE_VALUE32(name, val)
+#define SYSTRACE_VALUE64(name, val)
 
+#else
 
-// SYSTRACE_NAME traces the beginning and end of the current scope.  To trace
-// the correct start and end times this macro should be declared first in the
-// scope body.
-// It also automatically creates a Systrace context
-#define SYSTRACE_NAME(name) ::utils::details::ScopedTrace ___tracer(SYSTRACE_TAG, name)
+#define SYSTRACE_ENABLE()
+#define SYSTRACE_CONTEXT()
 
-// Denotes that a new frame has started processing.
-#define SYSTRACE_FRAME_ID(frame) \
-    { /* scope for frame id trace */ \
-        char buf[64]; \
-        snprintf(buf, 64, "frame %u", frame); \
-        SYSTRACE_NAME(buf); \
-    }
+#define SYSTRACE_CALL() \
+    auto constexpr FILAMENT_SYSTRACE_FUNCTION = perfetto::StaticString(__FUNCTION__); \
+    TRACE_EVENT(UTILS_PERFETTO_CATEGORY, FILAMENT_SYSTRACE_FUNCTION)
 
-// SYSTRACE_CALL is an SYSTRACE_NAME that uses the current function name.
-#define SYSTRACE_CALL() SYSTRACE_NAME(__FUNCTION__)
+#define SYSTRACE_NAME(name) TRACE_EVENT(UTILS_PERFETTO_CATEGORY, nullptr,   \
+        [&](perfetto::EventContext ctx) {                                   \
+            ctx.event()->set_name(name);                                    \
+        })
 
-#define SYSTRACE_NAME_BEGIN(name) \
-        ___trctx.traceBegin(SYSTRACE_TAG, name)
+#define SYSTRACE_NAME_BEGIN(name) TRACE_EVENT_BEGIN(UTILS_PERFETTO_CATEGORY, nullptr,   \
+        [&](perfetto::EventContext ctx) {                                               \
+            ctx.event()->set_name(name);                                                \
+        })
 
-#define SYSTRACE_NAME_END() \
-        ___trctx.traceEnd(SYSTRACE_TAG)
+#define SYSTRACE_NAME_END() TRACE_EVENT_END(UTILS_PERFETTO_CATEGORY)
 
-
-/**
- * Trace the beginning of an asynchronous event. Unlike ATRACE_BEGIN/ATRACE_END
- * contexts, asynchronous events do not need to be nested. The name describes
- * the event, and the cookie provides a unique identifier for distinguishing
- * simultaneous events. The name and cookie used to begin an event must be
- * used to end it.
- */
 #define SYSTRACE_ASYNC_BEGIN(name, cookie) \
-        ___trctx.asyncBegin(SYSTRACE_TAG, name, cookie)
+        TRACE_EVENT_BEGIN(UTILS_PERFETTO_CATEGORY, name, perfetto::Track(cookie))
 
-/**
- * Trace the end of an asynchronous event.
- * This should have a corresponding SYSTRACE_ASYNC_BEGIN.
- */
 #define SYSTRACE_ASYNC_END(name, cookie) \
-        ___trctx.asyncEnd(SYSTRACE_TAG, name, cookie)
+        TRACE_EVENT_END(UTILS_PERFETTO_CATEGORY, perfetto::Track(cookie))
+
+#define SYSTRACE_FRAME_ID(frame) \
+    TRACE_EVENT_INSTANT(UTILS_PERFETTO_CATEGORY, "frame", "id", frame)
 
-/**
- * Traces an integer counter value.  name is used to identify the counter.
- * This can be used to track how a value changes over time.
- */
 #define SYSTRACE_VALUE32(name, val) \
-        ___trctx.value(SYSTRACE_TAG, name, int32_t(val))
+    TRACE_COUNTER(UTILS_PERFETTO_CATEGORY, name, val)
 
 #define SYSTRACE_VALUE64(name, val) \
-        ___trctx.value(SYSTRACE_TAG, name, int64_t(val))
+    TRACE_COUNTER(UTILS_PERFETTO_CATEGORY, name, val)
 
-// ------------------------------------------------------------------------------------------------
-// No user serviceable code below...
-// ------------------------------------------------------------------------------------------------
-
-namespace utils {
-namespace details {
-
-class UTILS_PUBLIC Systrace {
-   public:
-
-    enum tags {
-        NEVER       = SYSTRACE_TAG_NEVER,
-        ALWAYS      = SYSTRACE_TAG_ALWAYS,
-        FILAMENT    = SYSTRACE_TAG_FILAMENT,
-        JOBSYSTEM   = SYSTRACE_TAG_JOBSYSTEM
-        // we could define more TAGS here, as we need them.
-    };
-
-    explicit Systrace(uint32_t tag) noexcept {
-        if (tag) init(tag);
-    }
-
-    static void enable(uint32_t tags) noexcept;
-    static void disable(uint32_t tags) noexcept;
-
-
-    inline void traceBegin(uint32_t tag, const char* name) noexcept {
-        if (tag && UTILS_UNLIKELY(mIsTracingEnabled)) {
-            beginSection(this, name);
-        }
-    }
-
-    inline void traceEnd(uint32_t tag) noexcept {
-        if (tag && UTILS_UNLIKELY(mIsTracingEnabled)) {
-            endSection(this);
-        }
-    }
-
-    inline void asyncBegin(uint32_t tag, const char* name, int32_t cookie) noexcept {
-        if (tag && UTILS_UNLIKELY(mIsTracingEnabled)) {
-            beginAsyncSection(this, name, cookie);
-        }
-    }
-
-    inline void asyncEnd(uint32_t tag, const char* name, int32_t cookie) noexcept {
-        if (tag && UTILS_UNLIKELY(mIsTracingEnabled)) {
-            endAsyncSection(this, name, cookie);
-        }
-    }
-
-    inline void value(uint32_t tag, const char* name, int32_t value) noexcept {
-        if (tag && UTILS_UNLIKELY(mIsTracingEnabled)) {
-            setCounter(this, name, value);
-        }
-    }
-
-    inline void value(uint32_t tag, const char* name, int64_t value) noexcept {
-        if (tag && UTILS_UNLIKELY(mIsTracingEnabled)) {
-            setCounter(this, name, value);
-        }
-    }
-
-   private:
-    friend class ScopedTrace;
-
-    // whether tracing is supported at all by the platform
-
-    using ATrace_isEnabled_t          = bool (*)();
-    using ATrace_beginSection_t       = void (*)(const char* sectionName);
-    using ATrace_endSection_t         = void (*)();
-    using ATrace_beginAsyncSection_t  = void (*)(const char* sectionName, int32_t cookie);
-    using ATrace_endAsyncSection_t    = void (*)(const char* sectionName, int32_t cookie);
-    using ATrace_setCounter_t         = void (*)(const char* counterName, int64_t counterValue);
-
-    struct GlobalState {
-        bool isTracingAvailable;
-        std::atomic<uint32_t> isTracingEnabled;
-        int markerFd;
-
-        ATrace_isEnabled_t ATrace_isEnabled;
-        ATrace_beginSection_t ATrace_beginSection;
-        ATrace_endSection_t ATrace_endSection;
-        ATrace_beginAsyncSection_t ATrace_beginAsyncSection;
-        ATrace_endAsyncSection_t ATrace_endAsyncSection;
-        ATrace_setCounter_t ATrace_setCounter;
-
-        void (*beginSection)(Systrace* that, const char* name);
-        void (*endSection)(Systrace* that);
-        void (*beginAsyncSection)(Systrace* that, const char* name, int32_t cookie);
-        void (*endAsyncSection)(Systrace* that, const char* name, int32_t cookie);
-        void (*setCounter)(Systrace* that, const char* name, int64_t value);
-    };
-
-    static GlobalState sGlobalState;
-
-
-    // per-instance versions for better performance
-    ATrace_isEnabled_t ATrace_isEnabled;
-    ATrace_beginSection_t ATrace_beginSection;
-    ATrace_endSection_t ATrace_endSection;
-    ATrace_beginAsyncSection_t ATrace_beginAsyncSection;
-    ATrace_endAsyncSection_t ATrace_endAsyncSection;
-    ATrace_setCounter_t ATrace_setCounter;
-
-    void (*beginSection)(Systrace* that, const char* name);
-    void (*endSection)(Systrace* that);
-    void (*beginAsyncSection)(Systrace* that, const char* name, int32_t cookie);
-    void (*endAsyncSection)(Systrace* that, const char* name, int32_t cookie);
-    void (*setCounter)(Systrace* that, const char* name, int64_t value);
-
-    void init(uint32_t tag) noexcept;
-
-    // cached values for faster access, no need to be initialized
-    bool mIsTracingEnabled;
-    int mMarkerFd = -1;
-    pid_t mPid;
-
-    static void setup() noexcept;
-    static void init_once() noexcept;
-    static bool isTracingEnabled(uint32_t tag) noexcept;
-
-    static void begin_body(int fd, int pid, const char* name) noexcept;
-    static void end_body(int fd, int pid) noexcept;
-    static void async_begin_body(int fd, int pid, const char* name, int32_t cookie) noexcept;
-    static void async_end_body(int fd, int pid, const char* name, int32_t cookie) noexcept;
-    static void int64_body(int fd, int pid, const char* name, int64_t value) noexcept;
-};
-
-// ------------------------------------------------------------------------------------------------
-
-class UTILS_PUBLIC ScopedTrace {
-public:
-    // we don't inline this because it's relatively heavy due to a global check
-    ScopedTrace(uint32_t tag, const char* name) noexcept: mTrace(tag), mTag(tag) {
-        mTrace.traceBegin(tag, name);
-    }
-
-    inline ~ScopedTrace() noexcept {
-        mTrace.traceEnd(mTag);
-    }
-
-private:
-    Systrace mTrace;
-    const uint32_t mTag;
-};
-
-} // namespace details
-} // namespace utils
+#endif // SYSTRACE_TAG == SYSTRACE_TAG_DISABLED
 
 #endif // TNT_UTILS_ANDROID_SYSTRACE_H

libs/utils/include/utils/darwin/Systrace.h

@@ -29,13 +29,25 @@
 #include <utils/compiler.h>
 #include <stack>
 
+#if SYSTRACE_TAG == SYSTRACE_TAG_DISABLED
+
+#define SYSTRACE_ENABLE()
+#define SYSTRACE_CONTEXT()
+#define SYSTRACE_NAME(name)
+#define SYSTRACE_FRAME_ID(frame)
+#define SYSTRACE_NAME_BEGIN(name)
+#define SYSTRACE_NAME_END()
+#define SYSTRACE_CALL()
+#define SYSTRACE_ASYNC_BEGIN(name, cookie)
+#define SYSTRACE_ASYNC_END(name, cookie)
+#define SYSTRACE_VALUE32(name, val)
+#define SYSTRACE_VALUE64(name, val)
+
+#else
+
 // enable tracing
 #define SYSTRACE_ENABLE() ::utils::details::Systrace::enable(SYSTRACE_TAG)
 
-// disable tracing
-#define SYSTRACE_DISABLE() ::utils::details::Systrace::disable(SYSTRACE_TAG)
-
-
 /**
  * Creates a Systrace context in the current scope. needed for calling all other systrace
  * commands below.
@@ -93,6 +105,8 @@ extern thread_local std::stack<const char*> ___tracerSections;
 #define SYSTRACE_VALUE64(name, val) \
         ___tracer.value(SYSTRACE_TAG, name, int64_t(val))
 
+#endif // SYSTRACE_TAG == SYSTRACE_TAG_DISABLED
+
 // ------------------------------------------------------------------------------------------------
 // No user serviceable code below...
 // ------------------------------------------------------------------------------------------------
@@ -118,50 +132,40 @@ namespace utils {
 namespace details {
 
 class Systrace {
-   public:
-
-    enum tags {
-        NEVER       = SYSTRACE_TAG_NEVER,
-        ALWAYS      = SYSTRACE_TAG_ALWAYS,
-        FILAMENT    = SYSTRACE_TAG_FILAMENT,
-        JOBSYSTEM   = SYSTRACE_TAG_JOBSYSTEM
-        // we could define more TAGS here, as we need them.
-    };
-
+public:
     explicit Systrace(uint32_t tag) noexcept {
         if (tag) init(tag);
     }
 
-    static void enable(uint32_t tags) noexcept;
-    static void disable(uint32_t tags) noexcept;
+    static void enable(uint32_t tag) noexcept;
 
-    inline void traceBegin(uint32_t tag, const char* name) noexcept {
+    void traceBegin(uint32_t tag, const char* name) noexcept {
         if (tag && UTILS_UNLIKELY(mIsTracingEnabled)) {
             APPLE_SIGNPOST_EMIT(sGlobalState.systraceLog, OS_SIGNPOST_INTERVAL_BEGIN,
                     OS_SIGNPOST_ID_EXCLUSIVE, name, name)
         }
     }
 
-    inline void traceEnd(uint32_t tag, const char* name) noexcept {
+    void traceEnd(uint32_t tag, const char* name) noexcept {
         if (tag && UTILS_UNLIKELY(mIsTracingEnabled)) {
             APPLE_SIGNPOST_EMIT(sGlobalState.systraceLog, OS_SIGNPOST_INTERVAL_END,
                     OS_SIGNPOST_ID_EXCLUSIVE, name, "")
         }
     }
 
-    inline void asyncBegin(uint32_t tag, const char* name, int32_t cookie) noexcept {
+    void asyncBegin(uint32_t tag, const char* name, int32_t cookie) noexcept {
         if (tag && UTILS_UNLIKELY(mIsTracingEnabled)) {
             // TODO
         }
     }
 
-    inline void asyncEnd(uint32_t tag, const char* name, int32_t cookie) noexcept {
+    void asyncEnd(uint32_t tag, const char* name, int32_t cookie) noexcept {
         if (tag && UTILS_UNLIKELY(mIsTracingEnabled)) {
             // TODO
         }
     }
 
-    inline void value(uint32_t tag, const char* name, int32_t value) noexcept {
+    void value(uint32_t tag, const char* name, int32_t value) noexcept {
         if (tag && UTILS_UNLIKELY(mIsTracingEnabled)) {
             char buf[64];
             snprintf(buf, 64, "%s - %d", name, value);
@@ -170,7 +174,7 @@ class Systrace {
         }
     }
 
-    inline void value(uint32_t tag, const char* name, int64_t value) noexcept {
+    void value(uint32_t tag, const char* name, int64_t value) noexcept {
         if (tag && UTILS_UNLIKELY(mIsTracingEnabled)) {
             char buf[64];
             snprintf(buf, 64, "%s - %lld", name, value);
@@ -179,16 +183,16 @@ class Systrace {
         }
     }
 
-    inline void frameId(uint32_t tag, uint32_t frame) noexcept {
+    void frameId(uint32_t tag, uint32_t frame) noexcept {
         if (tag && UTILS_UNLIKELY(mIsTracingEnabled)) {
-            char buf[64]; \
-            snprintf(buf, 64, "frame %u", frame); \
+            char buf[64];
+            snprintf(buf, 64, "frame %u", frame);
             APPLE_SIGNPOST_EMIT(sGlobalState.frameIdLog, OS_SIGNPOST_EVENT,
                     OS_SIGNPOST_ID_EXCLUSIVE, "frame", buf)
         }
     }
 
-   private:
+private:
     friend class ScopedTrace;
 
     struct GlobalState {
@@ -213,25 +217,25 @@ class Systrace {
 // ------------------------------------------------------------------------------------------------
 
 class ScopedTrace {
-   public:
+public:
     // we don't inline this because it's relatively heavy due to a global check
     ScopedTrace(uint32_t tag, const char* name) noexcept : mTrace(tag), mName(name), mTag(tag) {
         mTrace.traceBegin(tag, name);
     }
 
-    inline ~ScopedTrace() noexcept {
+    ~ScopedTrace() noexcept {
         mTrace.traceEnd(mTag, mName);
     }
 
-    inline void value(uint32_t tag, const char* name, int32_t v) noexcept {
+    void value(uint32_t tag, const char* name, int32_t v) noexcept {
         mTrace.value(tag, name, v);
     }
 
-    inline void value(uint32_t tag, const char* name, int64_t v) noexcept {
+    void value(uint32_t tag, const char* name, int64_t v) noexcept {
         mTrace.value(tag, name, v);
     }
 
-   private:
+private:
     Systrace mTrace;
     const char* mName;
     const uint32_t mTag;

libs/utils/src/JobSystem.cpp

@@ -15,10 +15,8 @@
  */
 
 // Note: The overhead of SYSTRACE_TAG_JOBSYSTEM is not negligible especially with parallel_for().
-#ifndef SYSTRACE_TAG
+#define SYSTRACE_TAG SYSTRACE_TAG_DISABLED
 //#define SYSTRACE_TAG SYSTRACE_TAG_JOBSYSTEM
-#define SYSTRACE_TAG SYSTRACE_TAG_NEVER
-#endif
 
 // when SYSTRACE_TAG_JOBSYSTEM is used, enables even heavier systraces
 #define HEAVY_SYSTRACE  0

libs/utils/src/android/Systrace.cpp

@@ -14,206 +14,26 @@
  * limitations under the License.
  */
 
-#include <utils/Systrace.h>
-#include <utils/Log.h>
+#include <utils/compiler.h>
+#include <utils/android/Systrace.h>
 
-#include <cinttypes>
+#include <perfetto/perfetto.h>
 
-#include <string.h>
+PERFETTO_TRACK_EVENT_STATIC_STORAGE_IN_NAMESPACE(systrace);
 
-#include <errno.h>
-#include <fcntl.h>
-#include <pthread.h>
-#include <dlfcn.h>
+namespace {
 
-namespace utils {
-namespace details {
-
-static pthread_once_t atrace_once_control = PTHREAD_ONCE_INIT;
-
-template <typename T>
-static void loadSymbol(T*& pfn, const char *symbol) noexcept {
-    pfn = (T*)dlsym(RTLD_DEFAULT, symbol);
-}
-
-Systrace::GlobalState Systrace::sGlobalState = {};
-
-void Systrace::init_once() noexcept {
-    GlobalState& s = sGlobalState;
-
-    s.markerFd = -1;
-
-    // API 23
-    loadSymbol(s.ATrace_isEnabled, "ATrace_isEnabled");
-    loadSymbol(s.ATrace_beginSection, "ATrace_beginSection");
-    loadSymbol(s.ATrace_endSection, "ATrace_endSection");
-    // API 29
-    loadSymbol(s.ATrace_beginAsyncSection, "ATrace_beginAsyncSection");
-    loadSymbol(s.ATrace_endAsyncSection, "ATrace_endAsyncSection");
-    loadSymbol(s.ATrace_setCounter, "ATrace_setCounter");
-
-
-    const bool hasBasicAtrace = s.ATrace_isEnabled &&
-                                s.ATrace_beginSection &&
-                                s.ATrace_endSection;
-
-    const bool hasFullATrace = hasBasicAtrace &&
-                               s.ATrace_beginAsyncSection &&
-                               s.ATrace_endAsyncSection &&
-                               s.ATrace_setCounter;
-
-    if (!hasFullATrace) {
-        s.markerFd = open("/sys/kernel/debug/tracing/trace_marker", O_WRONLY | O_CLOEXEC);
+class SystraceStaticInitialization {
+public:
+    SystraceStaticInitialization() {
+        perfetto::TracingInitArgs args;
+        args.backends |= perfetto::kSystemBackend;
+        perfetto::Tracing::Initialize(args);
+        systrace::TrackEvent::Register();
     }
+};
 
-    if (hasBasicAtrace && !hasFullATrace) {
-        // no-op if we don't have all these
-        s.ATrace_beginAsyncSection = [](const char* sectionName, int32_t cookie){};
-        s.ATrace_endAsyncSection = [](const char* sectionName, int32_t cookie){};
-        s.ATrace_setCounter = [](const char* sectionName, int64_t counterValue){};
-    }
+UTILS_UNUSED SystraceStaticInitialization sSystraceStaticInitialization{};
 
-    const bool hasLegacySystrace = s.markerFd != -1;
-
-    if (hasLegacySystrace && !hasFullATrace) {
-        // use legacy
-        s.beginSection = [](Systrace* that, const char* name) {
-            begin_body(that->mMarkerFd, that->mPid, name);
-        };
-        s.endSection = [](Systrace* that) {
-            end_body(that->mMarkerFd, that->mPid);
-        };
-        s.beginAsyncSection = [](Systrace* that, const char* name, int32_t cookie) {
-            async_begin_body(that->mMarkerFd, that->mPid, name, cookie);
-        };
-        s.endAsyncSection = [](Systrace* that, const char* name, int32_t cookie) {
-            async_end_body(that->mMarkerFd, that->mPid, name, cookie);
-        };
-        s.setCounter = [](Systrace* that, const char* name, int64_t value) {
-            int64_body(that->mMarkerFd, that->mPid, name, value);
-        };
-    } else if (hasBasicAtrace) {
-        // we have at least basic ATrace
-        s.beginSection = [](Systrace* that, const char* name) {
-            that->ATrace_beginSection(name);
-        };
-        s.endSection = [](Systrace* that) {
-            that->ATrace_endSection();
-        };
-        s.beginAsyncSection = [](Systrace* that, const char* name, int32_t cookie) {
-            that->ATrace_beginAsyncSection(name, cookie);
-        };
-        s.endAsyncSection = [](Systrace* that, const char* name, int32_t cookie) {
-            that->ATrace_endAsyncSection(name, cookie);
-        };
-        s.setCounter = [](Systrace* that, const char* name, int64_t value) {
-            that->ATrace_setCounter(name, value);
-        };
-    }
-
-    s.isTracingAvailable = hasLegacySystrace || hasFullATrace || hasBasicAtrace;
 }
 
-void Systrace::setup() noexcept {
-    pthread_once(&atrace_once_control, init_once);
-}
-
-void Systrace::enable(uint32_t tags) noexcept {
-    setup();
-    if (UTILS_LIKELY(sGlobalState.isTracingAvailable)) {
-        sGlobalState.isTracingEnabled.fetch_or(tags, std::memory_order_relaxed);
-    }
-}
-
-void Systrace::disable(uint32_t tags) noexcept {
-    sGlobalState.isTracingEnabled.fetch_and(~tags, std::memory_order_relaxed);
-}
-
-// unfortunately, this generates quite a bit of code because reading a global is not
-// trivial. For this reason, we do not inline this method.
-bool Systrace::isTracingEnabled(uint32_t tag) noexcept {
-    if (tag) {
-        setup();
-        return bool((sGlobalState.isTracingEnabled.load(std::memory_order_relaxed) | SYSTRACE_TAG_ALWAYS) & tag);
-    }
-    return false;
-}
-
-// ------------------------------------------------------------------------------------------------
-
-void Systrace::init(uint32_t tag) noexcept {
-    // must be called first
-    mIsTracingEnabled = isTracingEnabled(tag);
-
-    // cache static variables for better efficiency
-    GlobalState& s = sGlobalState;
-    ATrace_isEnabled         = s.ATrace_isEnabled;
-    ATrace_beginSection      = s.ATrace_beginSection;
-    ATrace_endSection        = s.ATrace_endSection;
-    ATrace_beginAsyncSection = s.ATrace_beginAsyncSection;
-    ATrace_endAsyncSection   = s.ATrace_endAsyncSection;
-    ATrace_setCounter        = s.ATrace_setCounter;
-
-    beginSection = s.beginSection;
-    endSection = s.endSection;
-    beginAsyncSection = s.beginAsyncSection;
-    endAsyncSection = s.endAsyncSection;
-    setCounter = s.setCounter;
-
-    mMarkerFd = s.markerFd;
-
-    mPid = getpid();
-}
-
-// ------------------------------------------------------------------------------------------------
-
-/**
- * Maximum size of a message that can be logged to the trace buffer.
- * Note this message includes a tag, the pid, and the string given as the name.
- * Names should be kept short to get the most use of the trace buffer.
- */
-#define ATRACE_MESSAGE_LENGTH 512
-
-#define WRITE_MSG(format_begin, format_end, pid, name, value) {                 \
-    char buf[ATRACE_MESSAGE_LENGTH];                                            \
-    int len = snprintf(buf, sizeof(buf), format_begin "%s" format_end, pid,     \
-        name, value);                                                           \
-    if (len >= (int) sizeof(buf)) {                                             \
-        /* Given the sizeof(buf), and all of the current format buffers,        \
-         * it is impossible for name_len to be < 0 if len >= sizeof(buf). */    \
-        int name_len = strlen(name) - (len - sizeof(buf)) - 1;                  \
-        /* Truncate the name to make the message fit. */                        \
-        len = snprintf(buf, sizeof(buf), format_begin "%.*s" format_end, pid,   \
-            name_len, name, value);                                             \
-    }                                                                           \
-    write(fd, buf, len);                                                        \
-}
-
-void Systrace::begin_body(int fd, int pid, const char* name) noexcept {
-    char buf[ATRACE_MESSAGE_LENGTH];
-    ssize_t len = snprintf(buf, sizeof(buf), "B|%d|%s", pid, name);
-    if (len >= sizeof(buf)) {
-        len = sizeof(buf) - 1;
-    }
-    write(fd, buf, size_t(len));
-}
-
-void Systrace::end_body(int fd, int pid) noexcept {
-    const char END_TAG = 'E';
-    write(fd, &END_TAG, 1);
-}
-
-void Systrace::async_begin_body(int fd, int pid, const char* name, int32_t cookie) noexcept {
-    WRITE_MSG("S|%d|", "|%" PRId32, pid, name, cookie);
-}
-
-void Systrace::async_end_body(int fd, int pid, const char* name, int32_t cookie) noexcept {
-    WRITE_MSG("F|%d|", "|%" PRId32, pid, name, cookie);
-}
-
-void Systrace::int64_body(int fd, int pid, const char* name, int64_t value) noexcept {
-    WRITE_MSG("C|%d|", "|%" PRId64, pid, name, value);
-}
-
-} // namespace details
-} // namespace utils

libs/utils/src/darwin/Systrace.cpp

@@ -14,11 +14,17 @@
  * limitations under the License.
  */
 
-#include <utils/Systrace.h>
-#include <utils/Log.h>
+#include <utils/darwin/Systrace.h>
+
+#ifndef FILAMENT_APPLE_SYSTRACE
+#   define FILAMENT_APPLE_SYSTRACE 0
+#endif
 
 #if FILAMENT_APPLE_SYSTRACE
 
+#include <atomic>
+#include <stack>
+#include <stdint.h>
 #include <pthread.h>
 
 static pthread_once_t atrace_once_control = PTHREAD_ONCE_INIT;
@@ -41,21 +47,24 @@ void Systrace::setup() noexcept {
     pthread_once(&atrace_once_control, init_once);
 }
 
-void Systrace::enable(uint32_t tags) noexcept {
+void Systrace::enable(uint32_t tag) noexcept {
     setup();
-    sGlobalState.isTracingEnabled.fetch_or(tags, std::memory_order_relaxed);
+    uint32_t const mask = 1 << tag;
+    sGlobalState.isTracingEnabled.fetch_or(mask, std::memory_order_relaxed);
 }
 
-void Systrace::disable(uint32_t tags) noexcept {
-    sGlobalState.isTracingEnabled.fetch_and(~tags, std::memory_order_relaxed);
+void Systrace::disable(uint32_t tag) noexcept {
+    uint32_t const mask = 1 << tag;
+    sGlobalState.isTracingEnabled.fetch_and(~mask, std::memory_order_relaxed);
 }
 
-// unfortunately, this generates quite a bit of code because reading a global is not
+// Unfortunately, this generates quite a bit of code because reading a global is not
 // trivial. For this reason, we do not inline this method.
 bool Systrace::isTracingEnabled(uint32_t tag) noexcept {
     if (tag) {
         setup();
-        return bool((sGlobalState.isTracingEnabled.load(std::memory_order_relaxed) | SYSTRACE_TAG_ALWAYS) & tag);
+        uint32_t const mask = 1 << tag;
+        return bool(sGlobalState.isTracingEnabled.load(std::memory_order_relaxed) & mask);
     }
     return false;
 }

third_party/dawn/src/dawn/native/CommandValidation.cpp

@@ -229,10 +229,10 @@ MaybeError ValidateWriteBuffer(const DeviceBase* device,
                                uint64_t size) {
     DAWN_TRY(device->ValidateObject(buffer));
 
-    DAWN_INVALID_IF(bufferOffset % 4 != 0, "BufferOffset (%u) is not a multiple of 4.",
-                    bufferOffset);
-
-    DAWN_INVALID_IF(size % 4 != 0, "Size (%u) is not a multiple of 4.", size);
+    // DAWN_INVALID_IF(bufferOffset % 4 != 0, "BufferOffset (%u) is not a multiple of 4.",
+    //                 bufferOffset);
+    //
+    // DAWN_INVALID_IF(size % 4 != 0, "Size (%u) is not a multiple of 4.", size);
 
     uint64_t bufferSize = buffer->GetSize();
     DAWN_INVALID_IF(bufferOffset > bufferSize || size > (bufferSize - bufferOffset),

web/filament-js/package.json

@@ -1,6 +1,6 @@
 {
   "name": "filament",
-  "version": "1.59.5",
+  "version": "1.59.4",
   "description": "Real-time physically based rendering engine",
   "main": "filament.js",
   "module": "filament.js",