Compare commits

..
Author SHA1 Message Date
Sungun Park ba651d1671 Add defines to strip unused default materials
Add defines for trimming default materials. These enable binary size
reduction by omitting them. Referencing the trimmed material will cause
associated renderables to be skipped from rendering.

BUG=[415840223]
2025-05-09 10:49:20 -07:00
319 changed files with 17793 additions and 21729 deletions
+1 -1
View File
@@ -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
+3 -3
View File
@@ -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
+4
View File
@@ -45,6 +45,10 @@ option(FILAMENT_ENABLE_FEATURE_LEVEL_0 "Enable Feature Level 0" ON)
option(FILAMENT_ENABLE_MULTIVIEW "Enable multiview for Filament" OFF)
option(FILAMENT_TRIM_DEFAULT_MATERIAL "Trim default material for Filament" OFF)
option(FILAMENT_TRIM_SKYBOX_MATERIAL "Trim skybox material for Filament" OFF)
option(FILAMENT_SUPPORTS_OSMESA "Enable OSMesa (headless GL context) for Filament" OFF)
option(FILAMENT_ENABLE_FGVIEWER "Enable the frame graph viewer" OFF)
+2 -2
View File
@@ -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
+1 -12
View File
@@ -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
@@ -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
@@ -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
*
@@ -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;
}
/**
+1 -1
View File
@@ -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.
+11 -1
View File
@@ -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 {
+2 -6
View File
@@ -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
-1
View File
@@ -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)
-36
View File
@@ -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.
+35 -40
View File
@@ -237,7 +237,6 @@ set(MATERIAL_SRCS
src/materials/colorGrading/colorGradingAsSubpass.mat
src/materials/colorGrading/customResolveAsSubpass.mat
src/materials/debugShadowCascades.mat
src/materials/defaultMaterial.mat
src/materials/dof/dof.mat
src/materials/dof/dofCoc.mat
src/materials/dof/dofCombine.mat
@@ -255,27 +254,22 @@ set(MATERIAL_SRCS
src/materials/sgsr/sgsr1.mat
src/materials/resolveDepth.mat
src/materials/separableGaussianBlur.mat
src/materials/skybox.mat
src/materials/shadowmap.mat
src/materials/ssao/bilateralBlur.mat
src/materials/ssao/bilateralBlurBentNormals.mat
src/materials/ssao/mipmapDepth.mat
src/materials/ssao/sao.mat
src/materials/ssao/saoBentNormals.mat
src/materials/ssao/gtao.mat
src/materials/ssao/gtaoBentNormals.mat
src/materials/vsmMipmap.mat
)
set(MATERIAL_FL0_SRCS
src/materials/defaultMaterial.mat
src/materials/skybox.mat
)
set(MATERIAL_MULTIVIEW_SRCS
src/materials/defaultMaterial.mat
src/materials/skybox.mat
)
set(BASIC_MATERIAL_SRCS)
if (NOT FILAMENT_TRIM_DEFAULT_MATERIAL)
list(APPEND BASIC_MATERIAL_SRCS src/materials/defaultMaterial.mat)
endif()
if (NOT FILAMENT_TRIM_SKYBOX_MATERIAL)
list(APPEND BASIC_MATERIAL_SRCS src/materials/skybox.mat)
endif()
# Embed the binary resource blob for materials.
get_resgen_vars(${RESOURCE_DIR} materials)
@@ -311,6 +305,16 @@ if (FILAMENT_ENABLE_MULTIVIEW)
add_definitions(-DFILAMENT_ENABLE_MULTIVIEW)
endif()
# Whether to trim default material.
if (FILAMENT_TRIM_DEFAULT_MATERIAL)
add_definitions(-DFILAMENT_TRIM_DEFAULT_MATERIAL)
endif()
# Whether to trim skybox material.
if (FILAMENT_TRIM_SKYBOX_MATERIAL)
add_definitions(-DFILAMENT_TRIM_SKYBOX_MATERIAL)
endif()
# Whether to force the profiling mode.
if (FILAMENT_FORCE_PROFILING_MODE)
add_definitions(-DFILAMENT_FORCE_PROFILING_MODE)
@@ -320,6 +324,8 @@ endif()
# Definitions
# ==================================================================================================
# "2" corresponds to SYSTRACE_TAG_FILEMENT (See: utils/Systrace.h)
add_definitions(-DSYSTRACE_TAG=2)
add_definitions(-DFILAMENT_DFG_LUT_SIZE=${DFG_LUT_SIZE})
add_definitions(
-DFILAMENT_PER_RENDER_PASS_ARENA_SIZE_IN_MB=${FILAMENT_PER_RENDER_PASS_ARENA_SIZE_IN_MB}
@@ -352,9 +358,22 @@ foreach (mat_src ${MATERIAL_SRCS})
COMMENT "Compiling material ${fullname} to ${output_path}"
)
list(APPEND MATERIAL_BINS ${output_path})
endforeach()
list(FIND MATERIAL_FL0_SRCS ${mat_src} index)
if (${index} GREATER -1 AND FILAMENT_ENABLE_FEATURE_LEVEL_0)
foreach (mat_src ${BASIC_MATERIAL_SRCS})
get_filename_component(localname "${mat_src}" NAME_WE)
get_filename_component(fullname "${mat_src}" ABSOLUTE)
set(output_path "${MATERIAL_DIR}/${localname}.filamat")
add_custom_command(
OUTPUT ${output_path}
COMMAND matc ${MATC_BASE_FLAGS} -o ${output_path} ${fullname}
MAIN_DEPENDENCY ${fullname}
DEPENDS matc
COMMENT "Compiling material ${fullname} to ${output_path}"
)
list(APPEND MATERIAL_BINS ${output_path})
if (FILAMENT_ENABLE_FEATURE_LEVEL_0)
string(REGEX REPLACE "[.]filamat$" "_fl0.filamat" output_path_fl0 ${output_path})
add_custom_command(
OUTPUT ${output_path_fl0}
@@ -366,8 +385,7 @@ foreach (mat_src ${MATERIAL_SRCS})
list(APPEND MATERIAL_BINS ${output_path_fl0})
endif ()
list(FIND MATERIAL_MULTIVIEW_SRCS ${mat_src} index)
if (${index} GREATER -1 AND FILAMENT_ENABLE_MULTIVIEW)
if (FILAMENT_ENABLE_MULTIVIEW)
string(REGEX REPLACE "[.]filamat$" "_multiview.filamat" output_path_multiview ${output_path})
add_custom_command(
OUTPUT ${output_path_multiview}
@@ -378,7 +396,6 @@ foreach (mat_src ${MATERIAL_SRCS})
)
list(APPEND MATERIAL_BINS ${output_path_multiview})
endif ()
endforeach()
# Additional dependencies on included files for materials
@@ -463,28 +480,6 @@ add_custom_command(
APPEND
)
add_custom_command(
OUTPUT "${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 "${MATERIAL_DIR}/gtaoBentNormals.filamat"
DEPENDS src/materials/ssao/ssaoUtils.fs
DEPENDS src/materials/ssao/ssct.fs
DEPENDS src/materials/utils/depthUtils.fs
DEPENDS src/materials/utils/geometry.fs
DEPENDS src/materials/ssao/gtaoImpl.fs
DEPENDS src/materials/ssao/ssctImpl.fs
APPEND
)
add_custom_command(
OUTPUT "${MATERIAL_DIR}/bilateralBlur.filamat"
DEPENDS src/materials/ssao/ssaoUtils.fs
+6
View File
@@ -290,6 +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
# ==================================================================================================
@@ -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;
@@ -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;
+38 -323
View File
@@ -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);
}
+3 -4
View File
@@ -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;
@@ -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
@@ -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
+2 -4
View File
@@ -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 {
@@ -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];
}
@@ -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 {
/**
@@ -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>
-139
View File
@@ -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:
+3 -4
View File
@@ -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>
@@ -80,7 +79,7 @@ bool CommandBufferQueue::isExitRequested() const {
void CommandBufferQueue::flush() noexcept {
FILAMENT_TRACING_CALL(FILAMENT_TRACING_CATEGORY_FILAMENT);
SYSTRACE_CALL();
CircularBuffer& circularBuffer = mCircularBuffer;
if (circularBuffer.empty()) {
@@ -130,7 +129,7 @@ void CommandBufferQueue::flush() noexcept {
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, "
+10 -12
View File
@@ -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());
}
}
@@ -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
+3 -3
View File
@@ -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)) {
+10 -12
View File
@@ -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();
}
}
}
-1
View File
@@ -17,7 +17,6 @@
#include <backend/Platform.h>
#include <utils/compiler.h>
#include <utils/ostream.h>
#include <atomic>
#include <utility>
+2 -3
View File
@@ -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__)
+1 -1
View File
@@ -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)
@@ -19,8 +19,6 @@
#include "MetalContext.h"
#include <utils/Panic.h>
namespace filament {
namespace backend {
+17 -13
View File
@@ -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));
}
+2 -56
View File
@@ -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()) {
+5 -6
View File
@@ -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 {
+19 -69
View File
@@ -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
+3 -2
View File
@@ -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);
}
@@ -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>();
@@ -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);
}
@@ -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,
+13 -14
View File
@@ -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
}
@@ -3349,8 +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
}
@@ -3366,8 +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
}
@@ -3686,7 +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");
+6 -29
View File
@@ -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());
@@ -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);
});
@@ -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;
@@ -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 +255,6 @@ 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 };
}
+16 -17
View File
@@ -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,
@@ -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()
@@ -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,
+1 -1
View File
@@ -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);
+2 -28
View File
@@ -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);
}
}
@@ -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);
@@ -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;
+21 -21
View File
@@ -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);
+2 -12
View File
@@ -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;
}
+22 -24
View File
@@ -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)
+8 -10
View File
@@ -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:
+162 -258
View File
@@ -26,7 +26,7 @@
#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>
@@ -39,7 +39,6 @@
#include <array>
#include <cstddef>
#include <cstdint>
#include <memory>
#include <sstream>
#include <string_view>
#include <utility>
@@ -235,9 +234,6 @@ WebGPUDriver::WebGPUDriver(WebGPUPlatform& platform, const Platform::DriverConfi
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
@@ -354,17 +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;
}
// 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) {
@@ -483,10 +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
@@ -591,21 +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) {}
@@ -749,20 +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) {
@@ -774,76 +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) {
@@ -870,74 +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::RenderPassDescriptor renderPassDescriptor{};
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::TextureView customStencilView = nullptr;
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::getTexView() isn't sufficient or needs parameters.
customColorViews[customColorViewCount++] = hwTexture->getTexView();
}
}
}
const auto& depthInfo = renderTarget->getDepthAttachmentInfo();
if (depthInfo.handle) {
auto* hwTexture = handleCast<WGPUTexture>(depthInfo.handle);
if (hwTexture) {
customDepthView = hwTexture->getTexView();
}
}
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->getTexView();
}
}
red = 1.0f;
}
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},
};
renderTarget->setUpRenderPassAttachments(renderPassDescriptor,
params,
defaultColorView,
defaultDepthStencilView,
customColorViews.data(),
customColorViewCount,
customDepthView,
customStencilView);
wgpu::RenderPassDescriptor renderPassDescriptor = {
.colorAttachmentCount = 1,
.colorAttachments = &renderPassColorAttachment,
.depthStencilAttachment = nullptr,
.timestampWrites = nullptr,
};
mRenderPassEncoder = mCommandEncoder.BeginRenderPass(&renderPassDescriptor);
// Ensure viewport dimensions are positive
uint32_t viewportWidth = params.viewport.width > 0 ? params.viewport.width : 1;
uint32_t viewportHeight = params.viewport.height > 0 ? params.viewport.height : 1;
mRenderPassEncoder.SetViewport(
static_cast<float>(params.viewport.left),
static_cast<float>(params.viewport.bottom),
static_cast<float>(viewportWidth),
static_cast<float>(viewportHeight),
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 */) {
@@ -1086,12 +976,18 @@ void WebGPUDriver::bindRenderPrimitive(Handle<HwRenderPrimitive> rph) {
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) {
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, Handle<HwRenderPrimitive>, uint32_t indexOffset,
@@ -1122,11 +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));
@@ -1158,105 +1051,115 @@ void WebGPUDriver::bindDescriptorSet(Handle<HwDescriptorSet> dsh,
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();
mRenderPassEncoder.SetBindGroup(setIndex, wbg, dynamicOffsetCount, offsets.data());
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);
if (params.compareMode == SamplerCompareMode::COMPARE_TO_TEXTURE) {
switch (params.filterMag) {
case SamplerMagFilter::NEAREST: {
desc.magFilter = wgpu::FilterMode::Nearest;
break;
}
case SamplerMagFilter::LINEAR: {
desc.magFilter = wgpu::FilterMode::Linear;
break;
}
switch (params.filterMag) {
case SamplerMagFilter::NEAREST: {
desc.magFilter = wgpu::FilterMode::Nearest;
break;
}
switch (params.filterMin) {
case SamplerMinFilter::NEAREST: {
desc.minFilter = wgpu::FilterMode::Nearest;
desc.mipmapFilter = wgpu::MipmapFilterMode::Undefined;
break;
}
case SamplerMinFilter::LINEAR: {
desc.minFilter = wgpu::FilterMode::Linear;
desc.mipmapFilter = wgpu::MipmapFilterMode::Undefined;
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;
}
case SamplerMagFilter::LINEAR: {
desc.magFilter = wgpu::FilterMode::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;
}
}
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: 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) {
@@ -1276,4 +1179,5 @@ wgpu::AddressMode WebGPUDriver::fWrapModeToWAddressMode(const SamplerWrapMode& f
return wgpu::AddressMode::Undefined;
}
} // namespace filament
+20 -1
View File
@@ -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;
+207 -321
View File
@@ -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";
}
}
@@ -153,49 +161,6 @@ 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);
}
}
WGPUVertexBufferInfo::WGPUVertexBufferInfo(uint8_t bufferCount, uint8_t attributeCount,
AttributeArray const& attributes)
: HwVertexBufferInfo(bufferCount, attributeCount),
@@ -238,10 +203,9 @@ WGPUVertexBufferInfo::WGPUVertexBufferInfo(uint8_t bufferCount, uint8_t attribut
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,
@@ -252,10 +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;
@@ -290,7 +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;
});
@@ -306,44 +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;
// 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::NonFiltering;
wEntry.texture.viewDimension =
wgpu::TextureViewDimension::e2D;// Example default
}
entryInfo.type = WebGPUDescriptorSetLayout::BindGroupEntryType::TEXTURE_VIEW;
break;
}
case DescriptorType::UNIFORM_BUFFER: {
@@ -354,6 +301,7 @@ WebGPUDescriptorSetLayout::WebGPUDescriptorSetLayout(DescriptorSetLayout const&
// TODO: Ideally we fill minBindingSize
break;
}
case DescriptorType::INPUT_ATTACHMENT: {
PANIC_POSTCONDITION("Input Attachment is not supported");
break;
@@ -362,48 +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::UnfilterableFloat;
}
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
}
@@ -418,26 +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() {
@@ -452,15 +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;
}
@@ -478,16 +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 {
@@ -501,9 +516,6 @@ WGPUTexture::WGPUTexture(SamplerType target, uint8_t levels, TextureFormat forma
// First, the texture aspect, starting with the defaults/basic configuration
mUsage = fToWGPUTextureUsage(usage);
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,
@@ -548,16 +560,13 @@ WGPUTexture::WGPUTexture(SamplerType target, uint8_t levels, TextureFormat forma
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;
mTexView = makeTextureView(baseLevel, levelCount, target);
}
wgpu::TextureUsage WGPUTexture::fToWGPUTextureUsage(TextureUsage const& fUsage) {
wgpu::TextureUsage WGPUTexture::fToWGPUTextureUsage(const TextureUsage& fUsage) {
wgpu::TextureUsage retUsage = wgpu::TextureUsage::None;
// Basing this mapping off of VulkanTexture.cpp's getUsage func and suggestions from Gemini
@@ -605,9 +614,8 @@ 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:
@@ -846,57 +854,24 @@ 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;
@@ -923,147 +898,58 @@ 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) {
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) {
// Static helper to map MRT index to TargetBufferFlags
TargetBufferFlags WGPURenderTarget::getTargetBufferFlagsAt(int mrtIndex) {
if (mrtIndex < 0 || mrtIndex >= MRT::MAX_SUPPORTED_RENDER_TARGET_COUNT) {
return TargetBufferFlags::NONE;
}
// This mapping assumes TargetBufferFlags::COLOR_0, COLOR_1 etc. are contiguous
return static_cast<TargetBufferFlags>(
static_cast<uint32_t>(TargetBufferFlags::COLOR0) << mrtIndex);
return result;
}
// Corrected getLoadOperation
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;
}
// Corrected getStoreOperation
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) {
mColorAttachmentDescriptors.clear();
mHasDepthStencilAttachment = false;
if (defaultRenderTarget) {
assert_invariant(defaultColorTextureView);
wgpu::RenderPassColorAttachment colorAttDesc{};
colorAttDesc.view = defaultColorTextureView;
colorAttDesc.resolveTarget = nullptr;
colorAttDesc.loadOp = WGPURenderTarget::getLoadOperation(params, TargetBufferFlags::COLOR0);
colorAttDesc.storeOp = WGPURenderTarget::getStoreOperation(params, TargetBufferFlags::COLOR0);
colorAttDesc.clearValue = {params.clearColor.r, params.clearColor.g,
params.clearColor.b, params.clearColor.a};
mColorAttachmentDescriptors.push_back(colorAttDesc);
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]) {
wgpu::RenderPassColorAttachment colorAttDesc{};
colorAttDesc.view = customColorTextureViews[i];
colorAttDesc.resolveTarget = nullptr; // TODO: MSAA resolve for custom RT
colorAttDesc.loadOp = WGPURenderTarget::getLoadOperation(params, getTargetBufferFlagsAt(i));
colorAttDesc.storeOp = WGPURenderTarget::getStoreOperation(params, getTargetBufferFlagsAt(i));
colorAttDesc.clearValue = {params.clearColor.r, params.clearColor.g,
params.clearColor.b, params.clearColor.a};
mColorAttachmentDescriptors.push_back(colorAttDesc);
}
}
wgpu::TextureView combinedDsView = customDepthTextureView ? customDepthTextureView : customStencilTextureView;
if (combinedDsView) {
mDepthStencilAttachmentDescriptor = {};
mDepthStencilAttachmentDescriptor.view = combinedDsView;
if (customDepthTextureView) {
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 (customStencilTextureView) {
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;
}
void WGPURenderTarget::setUpRenderPassAttachments(wgpu::RenderPassDescriptor& descriptor,
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;
}
math::uint2 WGPURenderTarget::getAttachmentSize() const noexcept {
if (!defaultRenderTarget) {
return {width, height};
}
// For default RT, size is dynamic and usually obtained from the swapchain.
// The caller (WebGPUDriver::beginRenderPass) should know the current swapchain size.
return {0,0};
}
}// namespace filament::backend
+77 -80
View File
@@ -28,6 +28,7 @@
#include <webgpu/webgpu_cpp.h>
#include <array>
#include <bitset>
#include <cstdint>
#include <vector>
@@ -43,6 +44,7 @@ public:
std::vector<wgpu::ConstantEntry> constants;
};
struct WGPUBufferObject;
// 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
@@ -72,8 +74,8 @@ public:
private:
// TODO: can we do better in terms on heap management.
std::vector<wgpu::VertexBufferLayout> mVertexBufferLayout{};
std::vector<std::vector<wgpu::VertexAttribute>> mAttributes{};
std::vector<wgpu::VertexBufferLayout> mVertexBufferLayout {};
std::vector<std::vector<wgpu::VertexAttribute>> mAttributes {};
};
struct WGPUVertexBuffer : public HwVertexBuffer {
@@ -84,37 +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;
};
@@ -127,7 +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;
@@ -135,6 +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);
@@ -142,15 +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;
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;
};
@@ -161,18 +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& getTexView() const { return mTexView; }
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,
@@ -183,12 +192,9 @@ 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 mTexView = nullptr;
wgpu::TextureUsage fToWGPUTextureUsage(filament::backend::TextureUsage const& fUsage);
size_t mBlockWidth;
size_t mBlockHeight;
wgpu::TextureUsage fToWGPUTextureUsage(const filament::backend::TextureUsage& fUsage);
};
struct WGPURenderPrimitive : public HwRenderPrimitive {
@@ -197,66 +203,57 @@ struct WGPURenderPrimitive : public HwRenderPrimitive {
WGPUIndexBuffer* indexBuffer = nullptr;
};
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);
void setUpRenderPassAttachments(wgpu::RenderPassDescriptor& descriptor,
wgpu::TextureView const& textureView, RenderPassParams const& params);
math::uint2 getAttachmentSize() const noexcept;
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:
// Helper to map MRT index to TargetBufferFlags
static TargetBufferFlags getTargetBufferFlagsAt(int mrtIndex);
bool defaultRenderTarget = false;
uint8_t samples = 1;
MRT mColorAttachments{};
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
+15 -30
View File
@@ -32,7 +32,6 @@ static constexpr size_t CONFIG_COMMAND_BUFFERS_SIZE = 3 * CONFIG_MIN_COMMAND
using namespace filament;
using namespace filament::backend;
using namespace filament::math;
#ifndef FILAMENT_IOS
#include <imageio/ImageEncoder.h>
@@ -107,35 +106,16 @@ Handle<HwSwapChain> BackendTest::createSwapChain() {
return getDriverApi().createSwapChain(view.ptr, 0);
}
PipelineState BackendTest::getColorWritePipelineState() {
PipelineState result;
result.rasterState.colorWrite = true;
result.rasterState.depthWrite = false;
result.rasterState.depthFunc = RasterState::DepthFunc::A;
return result;
void BackendTest::fullViewport(RenderPassParams& params) {
fullViewport(params.viewport);
}
filament::backend::Viewport BackendTest::getFullViewport() const {
const NativeView& view = getNativeView();
return Viewport {
.left = 0,
.bottom = 0,
.width = static_cast<uint32_t>(view.width),
.height = static_cast<uint32_t>(view.height)
};
}
filament::backend::RenderPassParams BackendTest::getClearColorRenderPass(float4 color) {
RenderPassParams params = {};
params.flags.clear = TargetBufferFlags::COLOR;
params.flags.discardStart = TargetBufferFlags::ALL;
params.flags.discardEnd = TargetBufferFlags::NONE;
params.clearColor = color;
return params;
}
filament::backend::RenderPassParams BackendTest::getNoClearRenderPass() {
return RenderPassParams{};
void BackendTest::fullViewport(Viewport& viewport) {
const NativeView& view = getNativeView();
viewport.left = 0;
viewport.bottom = 0;
viewport.width = view.width;
viewport.height = view.height;
}
void BackendTest::renderTriangle(
@@ -143,9 +123,14 @@ void BackendTest::renderTriangle(
Handle<filament::backend::HwRenderTarget> renderTarget,
Handle<filament::backend::HwSwapChain> swapChain,
Handle<filament::backend::HwProgram> program) {
RenderPassParams params = getClearColorRenderPass();
params.viewport.width = 512;
RenderPassParams params = {};
fullViewport(params);
params.flags.clear = TargetBufferFlags::COLOR;
params.clearColor = {0.f, 0.f, 1.f, 1.f};
params.flags.discardStart = TargetBufferFlags::ALL;
params.flags.discardEnd = TargetBufferFlags::NONE;
params.viewport.height = 512;
params.viewport.width = 512;
renderTriangle(pipelineLayout, renderTarget, swapChain, program, params);
}
+3 -8
View File
@@ -52,14 +52,9 @@ protected:
filament::backend::Handle<filament::backend::HwSwapChain> createSwapChain();
static filament::backend::PipelineState getColorWritePipelineState();
// Gets the full back buffer's viewport
filament::backend::Viewport getFullViewport() const;
// If color is unset this defaults to using opaque cyan
static filament::backend::RenderPassParams getClearColorRenderPass(
filament::math::float4 color = filament::math::float4(0, 1, 1, 1));
static filament::backend::RenderPassParams getNoClearRenderPass();
// Helper methods to set the viewport to the full extent of the swap chain.
static void fullViewport(filament::backend::RenderPassParams& params);
static void fullViewport(filament::backend::Viewport& viewport);
void renderTriangle(
filament::backend::PipelineLayout const& pipelineLayout,
@@ -211,10 +211,6 @@ uint32_t RenderTargetDump::hash() const {
return mInternal->hash();
}
const std::vector<unsigned char>& RenderTargetDump::bytes() const {
return mInternal->bytes;
}
bool RenderTargetDump::bytesFilled() const {
return mInternal->bytesFilled;
}
@@ -85,12 +85,6 @@ public:
* @return The hash of the stored bytes.
*/
uint32_t hash() const;
/**
* Gets the bytes of the render target. The hash should usually be preferable for comparisons
* but this is available for debugging.
* @return The stored bytes.
*/
const std::vector<unsigned char>& bytes() const;
/**
* Thread safe as this is backed by an atomic.
* Once this returns true it will never return false.
+5 -14
View File
@@ -56,35 +56,26 @@ Shader::Shader(DriverApi& api, Cleanup& cleanup, ShaderConfig config) : mCleanup
mProgram = cleanup.add(api.createProgram(std::move(prog)));
if (!kLayouts.empty()) {
mDescriptorSetLayout = cleanup.add(
api.createDescriptorSetLayout(DescriptorSetLayout{ .bindings = kLayouts }));
mDescriptorSetLayout =
cleanup.add(api.createDescriptorSetLayout(DescriptorSetLayout{ .bindings = kLayouts }));
}
}
DescriptorSetHandle Shader::createDescriptorSet(DriverApi& api) const {
filament::backend::DescriptorSetHandle Shader::createDescriptorSet(DriverApi& api) const {
return mCleanup.add(api.createDescriptorSet(mDescriptorSetLayout));
}
ProgramHandle Shader::getProgram() const {
filament::backend::ProgramHandle Shader::getProgram() const {
assert(mProgram);
EXPECT_THAT(mProgram, ::testing::IsTrue())
<< "Shader program accessed despite being null.";
return mProgram;
}
DescriptorSetLayoutHandle Shader::getDescriptorSetLayout() const {
filament::backend::DescriptorSetLayoutHandle Shader::getDescriptorSetLayout() const {
EXPECT_THAT(mDescriptorSetLayout, ::testing::IsTrue())
<< "Shader descriptor set layout accessed despite being null.";
return mDescriptorSetLayout;
}
void Shader::addProgramToPipelineState(PipelineState& state) const {
state.program = getProgram();
// In case another shader was set first, clear the set layout and then set this shader's values.
state.pipelineLayout.setLayout = PipelineLayout::SetLayout();
if (mDescriptorSetLayout) {
state.pipelineLayout.setLayout[0] = { getDescriptorSetLayout() };
}
}
} // namespace test
-2
View File
@@ -90,8 +90,6 @@ public:
filament::backend::ProgramHandle getProgram() const;
filament::backend::DescriptorSetLayoutHandle getDescriptorSetLayout() const;
void addProgramToPipelineState(filament::backend::PipelineState& state) const;
filament::backend::DescriptorSetHandle createDescriptorSet(
filament::backend::DriverApi& api) const;
+2 -13
View File
@@ -17,6 +17,7 @@
#include "ShaderGenerator.h"
#include <GlslangToSpv.h>
#include <SPVRemapper.h>
#include <spirv_glsl.hpp>
#include <spirv_msl.hpp>
@@ -118,7 +119,7 @@ ShaderGenerator::Blob ShaderGenerator::transpileShader(ShaderStage stage, std::s
} else if (backend == Backend::VULKAN) {
shader.insert(pos, "#define TARGET_VULKAN_ENVIRONMENT\n");
} else if (backend == Backend::WEBGPU) {
shader.insert(pos, "#define TARGET_WEBGPU_ENVIRONMENT\n");
shader.insert(pos, "#define TARGET_VULKAN_ENVIRONMENT\n");
}
const char* shaderCString = shader.c_str();
@@ -186,16 +187,4 @@ Program ShaderGenerator::getProgram(filament::backend::DriverApi&) noexcept {
return program;
}
Program ShaderGenerator::getProgramWithPushConstants(filament::backend::DriverApi&,
std::array<PushConstants, filament::backend::Program::SHADER_TYPE_COUNT> constants) {
Program program;
program.shaderLanguage(mShaderLanguage);
program.shader(ShaderStage::VERTEX, mVertexBlob.data(), mVertexBlob.size());
program.shader(ShaderStage::FRAGMENT, mFragmentBlob.data(), mFragmentBlob.size());
for (auto const stage : {ShaderStage::VERTEX, ShaderStage::FRAGMENT }) {
program.pushConstants(stage, constants[uint8_t(stage)]);
}
return program;
}
} // namespace test
-4
View File
@@ -48,10 +48,6 @@ public:
filament::backend::Program getProgram(filament::backend::DriverApi&) noexcept;
using PushConstants = utils::FixedCapacityVector<filament::backend::Program::PushConstant>;
filament::backend::Program getProgramWithPushConstants(filament::backend::DriverApi&,
std::array<PushConstants, filament::backend::Program::SHADER_TYPE_COUNT> constants);
private:
using ShaderStage = filament::backend::ShaderStage;
+1 -1
View File
@@ -184,7 +184,7 @@ std::vector<UniformConfig> GetUniformConfig(ShaderUniformType type) {
"backend_test", "test_tex", 0,
SamplerType::SAMPLER_2D, SamplerFormat::FLOAT, Precision::HIGH, false };
return {{
"test_tex", DescriptorType::SAMPLER_2D_FLOAT, samplerInfo
"test_tex", DescriptorType::SAMPLER, samplerInfo
}};
}
default:
+1 -12
View File
@@ -32,24 +32,13 @@ do {
} \
} while (false)
#define NONFATAL_FAIL_IF(skipEnvironment, rationale) \
do { \
SkipEnvironment skip(skipEnvironment); \
if (skip.matches()) { \
ADD_FAILURE() \
<< "Failing test as the " << skip.describe() << "\n" \
<< " This test has a known failure where " \
<< rationale; \
} \
} while (false)
#define FAIL_IF(skipEnvironment, rationale) \
do { \
SkipEnvironment skip(skipEnvironment); \
if (skip.matches()) { \
GTEST_FAIL() \
<< "Failing test as the " << skip.describe() << "\n" \
<< " This test should be able to succeed but it needs to fail early because " \
<< " This test should be able to succeed but it needs to fail early because" \
<< rationale; \
} \
} while (false)
@@ -55,8 +55,6 @@ public:
void updateIndices(const index_type* indices) noexcept;
void updateIndices(const index_type* indices, int count, int offset) noexcept;
VertexInfoHandle getVertexBufferInfo() const { return mVertexBufferInfo; }
private:
size_t mVertexCount = 3;
Binary file not shown.

Before

Width:  |  Height:  |  Size: 3.7 KiB

After

Width:  |  Height:  |  Size: 3.7 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 1.3 KiB

After

Width:  |  Height:  |  Size: 1.4 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 4.1 KiB

After

Width:  |  Height:  |  Size: 4.1 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 4.1 KiB

After

Width:  |  Height:  |  Size: 4.1 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 4.1 KiB

After

Width:  |  Height:  |  Size: 4.1 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 4.1 KiB

After

Width:  |  Height:  |  Size: 4.1 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 4.1 KiB

After

Width:  |  Height:  |  Size: 4.1 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 4.1 KiB

After

Width:  |  Height:  |  Size: 4.1 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 4.1 KiB

After

Width:  |  Height:  |  Size: 4.1 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 4.1 KiB

After

Width:  |  Height:  |  Size: 4.1 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 4.1 KiB

After

Width:  |  Height:  |  Size: 4.1 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 4.1 KiB

After

Width:  |  Height:  |  Size: 4.1 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 4.1 KiB

After

Width:  |  Height:  |  Size: 4.1 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 4.1 KiB

After

Width:  |  Height:  |  Size: 4.1 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 4.1 KiB

After

Width:  |  Height:  |  Size: 4.1 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 4.1 KiB

After

Width:  |  Height:  |  Size: 4.1 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 4.1 KiB

After

Width:  |  Height:  |  Size: 4.1 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 4.1 KiB

After

Width:  |  Height:  |  Size: 4.1 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 4.1 KiB

After

Width:  |  Height:  |  Size: 4.1 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 3.9 KiB

After

Width:  |  Height:  |  Size: 4.0 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 3.2 KiB

After

Width:  |  Height:  |  Size: 3.2 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 4.1 KiB

After

Width:  |  Height:  |  Size: 4.1 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 4.1 KiB

After

Width:  |  Height:  |  Size: 4.1 KiB

Some files were not shown because too many files have changed in this diff Show More