Compare commits

..
10 Commits
Author SHA1 Message Date
swung0x48 4322427e78 [Fix] (DirectGLES): lower gl_ClipDistance for Adreno's ESSL compiler - shadow the builtin in a Private array with constant-index flushes before EmitVertex/return, loop-copy gl_in clip distances through dynamic indices (whole-array reads segfault the Qualcomm compiler, constant-index element reads miscompile), strip the SPIRV-Cross redeclaration Adreno rejects, and split const struct-array LUT initializers so they stay dynamically indexable; quirk-gated to Qualcomm with MOBILEGL_QUIRK_CLIP_DISTANCE override 2026-07-26 19:56:45 -04:00
swung0x48 203d4bce5e [Fix] (DirectGLES): piglit fixes batch 1 - keep enabled-but-unsourceable vertex attribs disabled on the backend VAO (Adreno memcpy-from-NULL SIGSEGV on gl-3.1-vao-broken-attrib), content-sync READ-framebuffer texture attachments before blits, clamp out-of-bounds access-chain indices via GraphicsRobustAccessPass before ESSL transpile (Adreno poisons whole-shader output on constant OOB), and fold ConstOffset into the coordinate for 1D texelFetch (SPIRV-Cross emulates 1D as 2D but leaves the scalar offset, which ESSL rejects) 2026-07-26 19:17:25 -04:00
swung0x48 761114d022 Merge remote-tracking branch 'origin/cts-gl33' into dev 2026-07-26 18:29:02 -04:00
swung0x48 9caf34d5b1 [Fix] (Logging): rank WARN/ERROR above INFO so release builds keep them - the old ordering (DEBUG=0, WARN=1, ERROR=2, INFO=3) compiled every MGLOG_W/MGLOG_E out of the default MOBILEGL_LOG_LEVEL_INFO build, silently hiding backend shader-compile failures, unsupported-path skips, and enum-conversion fallbacks during the piglit runs 2026-07-26 18:14:56 -04:00
swung0x48 5e676b338b [Fix] (DirectVulkan): back legacy low-bit formats (RGB565/RGB5A1/RGBA4/R3G3B2/RGB4/RGBA2/RGB10/12) with their UNorm8/16 canonical shadow layouts and add capability fallbacks - they mapped to VK_FORMAT_UNDEFINED and crashed or wedged the GPU on upload; also admit 2DMSArray/CubeMap/3D color attachment targets in the render pass 2026-07-26 13:28:30 -04:00
swung0x48 db01bfa3e8 [Fix] (DirectVulkan): general (format,type) readback conversion - hoist the CTS-verified StoreWideRowsToClient into shared ReadbackImpl and decode any color VkFormat to wide RGBA rows; readback previously supported only RGB/BGR/RGBA/BGRA x UNSIGNED_BYTE/FLOAT and silently returned zeros for everything else 2026-07-26 13:28:30 -04:00
swung0x48 cc3dcfd80e [Fix] (DirectVulkan): support UBO instance arrays as arrayed descriptors - uniform Block{...}b[N] reflected as one binding with descriptorCount=N, per-element GL block mapping, per-element buffer infos and dynamic offsets; non-UBO descriptor arrays now fail program creation cleanly instead of continuing corrupt 2026-07-26 12:25:24 -04:00
swung0x48 d9556ff041 [Fix] (DirectVulkan): implement color renderbuffer attachments - render pass/pipeline/blit/copy/readback/clear paths treated color renderbuffers as absent (writes masked to VK_ATTACHMENT_UNUSED, glClear dropped, readback zeros) 2026-07-26 11:30:54 -04:00
swung0x48 39f21e52ea [Test] (CTS): isolate the DirectVulkan renderbuffer-FBO readback defect so the rest of KHR-GL33 can be measured 2026-07-26 10:43:48 -04:00
swung0x48 0e933b8f2f [Test] (CTS): run VK-GL-CTS KHR-GL33 against MobileGL on Android via a standalone glcts binary 2026-07-26 08:05:02 -04:00
191 changed files with 3369 additions and 30200 deletions
+3 -10
View File
@@ -201,11 +201,6 @@ fetch_file_from_mirror() {
return 1
}
# Files no mirror could serve, even after retrying every mirror. Only these fall
# back to Git LFS, so a mirror that served the rest of the case still spares
# GitHub the bandwidth for those files.
mirror_failures=()
fetch_from_mirror() {
mkdir -p "${fixture_dir}"
for file in "${files[@]}"; do
@@ -224,19 +219,17 @@ fetch_from_mirror() {
echo "Mirror did not serve ${name}; trying the next mirror" >&2
done
if [ "${fetched}" -ne 1 ]; then
mirror_failures+=("${file}")
return 1
fi
done
[ "${#mirror_failures[@]}" -eq 0 ]
}
if fetch_from_mirror; then
echo "Fetched trace fixture files for ${case_name} from mirror: ${include}"
else
fallback_include="$(IFS=,; echo "${mirror_failures[*]}")"
echo "All mirrors failed for ${#mirror_failures[@]} of ${#files[@]} file(s) of ${case_name}; falling back to Git LFS: ${fallback_include}"
echo "All mirrors failed for ${case_name}; falling back to Git LFS: ${include}"
git lfs install --local
git lfs pull --include="${fallback_include}" --exclude=""
git lfs pull --include="${include}" --exclude=""
fi
for file in "${files[@]}"; do
+1 -5
View File
@@ -177,13 +177,9 @@ jobs:
uses: lukka/get-cmake@v4.3.3
- name: Install runtime dependencies
# libegl-mesa0 is the EGL vendor library itself: DriverBench brings up a
# real GL context, and libegl1 is only glvnd's dispatch. It normally
# arrives as a Recommends of libegl1, which is too quiet a dependency for
# the one job that needs a working driver.
run: |
sudo apt-get update
sudo apt-get install -y libvulkan1 libegl1 libegl-mesa0 libgles2 libgl1-mesa-dri mesa-vulkan-drivers
sudo apt-get install -y libvulkan1 libegl1 libgles2 libgl1-mesa-dri mesa-vulkan-drivers
- name: Download Linux runtime
uses: actions/download-artifact@v8
-2
View File
@@ -25,5 +25,3 @@ MobileGL/MG*/cmake-build*
/android-plugin/app/src/trace/jniLibs
/android-plugin/local.properties
tools/trace_replay/work/
__pycache__/
*.py[cod]
+3 -19
View File
@@ -190,12 +190,13 @@ set(SOURCE_FILES
MobileGL/MG_Util/ShaderTranspiler/SpirvPasses/DecomposeWorkgroupVec3Pass.cpp
MobileGL/MG_Util/ShaderTranspiler/SpirvPasses/DecoratePositionInvariantPass.cpp
MobileGL/MG_Util/ShaderTranspiler/SpirvPasses/LowerDrawParametersPass.cpp
MobileGL/MG_Util/ShaderTranspiler/SpirvPasses/PackDoubleVertexInputsPass.cpp
MobileGL/MG_Util/ShaderTranspiler/SpirvPasses/RebaseInstanceIndexPass.cpp
MobileGL/MG_Util/ShaderTranspiler/SpirvPasses/NormalizeRectCoordinatesPass.cpp
MobileGL/MG_Util/ShaderTranspiler/SpirvPasses/StripUboMemberRelaxedPrecisionPass.cpp
MobileGL/MG_Util/ShaderTranspiler/SpirvPasses/StripNoPerspectivePass.cpp
MobileGL/MG_Util/ShaderTranspiler/SpirvPasses/EmulateNoPerspectivePass.cpp
MobileGL/MG_Util/ShaderTranspiler/SpirvPasses/FoldConstOffsetFor1DFetchPass.cpp
MobileGL/MG_Util/ShaderTranspiler/SpirvPasses/LowerClipDistanceForEsslPass.cpp
MobileGL/MG_Util/ShaderTranspiler/SpirvPasses/DefeatConstStructArrayLutPass.cpp
MobileGL/MG_Util/BackendLoaders/OpenGL/Loader.cpp
MobileGL/MG_Util/BackendLoaders/Vulkan/Loader.cpp
@@ -206,7 +207,6 @@ set(SOURCE_FILES
MobileGL/MG_Util/Texture/TextureFormatProcessor.cpp
MobileGL/MG_Impl/GLXImpl/Exporting/Definitions.cpp
MobileGL/MG_Impl/GLXImpl/GLXImpl.cpp
MobileGL/MG_Impl/GLXImpl/LookUp/LookUp.cpp
MobileGL/MG_Impl/EGLImpl/Exporting/Definitions.cpp
@@ -220,7 +220,6 @@ set(SOURCE_FILES
MobileGL/MG_Impl/GLImpl/Framebuffer/Validators.cpp
MobileGL/MG_Impl/GLImpl/Framebuffer/GL_Framebuffer.cpp
MobileGL/MG_Impl/GLImpl/Program/GL_Program.cpp
MobileGL/MG_Impl/GLImpl/Program/GL_ProgramPipeline.cpp
MobileGL/MG_Impl/GLImpl/Texture/GL_Texture.cpp
MobileGL/MG_Impl/GLImpl/Texture/Validators.cpp
MobileGL/MG_Impl/GLImpl/Texture/ProxyTexture.cpp
@@ -304,7 +303,6 @@ endif()
if (ANDROID)
list(APPEND SOURCE_FILES
MobileGL/MG_Util/SelfTest/DriverPostJni.cpp
MobileGL/MG_Util/SelfTest/DriverBenchJni.cpp
)
endif()
@@ -460,21 +458,8 @@ if (ANDROID)
endif()
if (APPLE AND NOT MOBILEGL_IOS)
# MobileGL statically embeds glslang, SPIRV-Tools, and SPIRV-Cross. When
# this dylib is injected with DYLD_INSERT_LIBRARIES, exporting those C++
# symbols interposes incompatible copies embedded by host libraries such
# as shaderc. Keep only the public GL/EGL/CGL loader surface globally
# visible; GetProcAddress can still return pointers to hidden internals.
set(MOBILEGL_MACOS_EXPORTED_SYMBOLS
"${CMAKE_CURRENT_SOURCE_DIR}/MobileGL/MG_Impl/DyldInterpose/ExportedSymbols.txt")
target_link_options(${CMAKE_PROJECT_NAME} PRIVATE
"LINKER:-exported_symbols_list,${MOBILEGL_MACOS_EXPORTED_SYMBOLS}")
set_property(TARGET ${CMAKE_PROJECT_NAME} APPEND PROPERTY
LINK_DEPENDS "${MOBILEGL_MACOS_EXPORTED_SYMBOLS}")
target_link_libraries(${CMAKE_PROJECT_NAME} PUBLIC
"-framework Cocoa"
"-framework CoreVideo"
"-framework QuartzCore"
"-framework Foundation"
"-framework OpenGL"
@@ -482,7 +467,6 @@ if (APPLE AND NOT MOBILEGL_IOS)
if(TARGET ${CMAKE_PROJECT_NAME}_s)
target_link_libraries(${CMAKE_PROJECT_NAME}_s PUBLIC
"-framework Cocoa"
"-framework CoreVideo"
"-framework QuartzCore"
"-framework Foundation"
"-framework OpenGL"
+6 -1
View File
@@ -14,7 +14,7 @@ namespace MobileGL::MG_Config {
inline const String ProjectName = "MobileGL";
inline const String CoreName = "MobileGL Core";
inline const String CoreVendor = "MobileGL-Dev (BZLZHH, Swung0x48, Tungsten)";
inline const Version CoreVersion = {26, 8, 0, "-dev", VersionType::Development};
inline const Version CoreVersion = {26, 7, 0, "-dev", VersionType::Development};
inline const VersionStringFormatAttrib DefaultVersionStringFormatAttrib = {2, 2, 0, true, true};
inline const Uint64 CacheVersion = 0;
@@ -80,6 +80,11 @@ namespace MobileGL::MG_Config {
// rewrites the recognized workgroup prefix-scan template on Qualcomm devices with
// subgroups wider than 32 lanes (see ShaderSourceProcessor's quirk registry).
QuirkOverride SubgroupPrefixScanQuirk = QuirkOverride::Auto;
// MOBILEGL_QUIRK_CLIP_DISTANCE: overrides the DirectGLES quirk that lowers
// gl_ClipDistance for Adreno's ESSL compiler (shadow Private arrays with
// constant-index builtin flushes, dynamic-index gl_in copy loop, redeclaration
// strip, and const struct-array LUT splitting). Auto detects Qualcomm.
QuirkOverride ClipDistanceQuirk = QuirkOverride::Auto;
// MOBILEGL_MAGMA_DISABLE_BLENDED_DEPTH_WRITE: overrides the DirectVulkan quirk that
// strips depth writes from accumulation-blended pipelines (MIN/MAX or additive
// ONE+ONE - the multi-pass depth-equality signature) on drivers without
+1
View File
@@ -135,6 +135,7 @@ namespace MobileGL::MG_ConfigLoader {
features.DisableUboRing = QueryEnvFlag("MOBILEGL_DISABLE_UBO_RING");
features.RelaxedSemantics = QueryEnvFlag("MOBILEGL_RELAXED_SEMANTICS");
features.SubgroupPrefixScanQuirk = QueryEnvQuirkOverride("MOBILEGL_QUIRK_SUBGROUP_PREFIX_SCAN");
features.ClipDistanceQuirk = QueryEnvQuirkOverride("MOBILEGL_QUIRK_CLIP_DISTANCE");
features.MagmaDisableBlendedDepthWriteQuirk =
QueryEnvQuirkOverride("MOBILEGL_MAGMA_DISABLE_BLENDED_DEPTH_WRITE");
features.DisableRobustBufferAccess = QueryEnvFlag("MOBILEGL_DISABLE_ROBUST_BUFFER_ACCESS");
+4 -13
View File
@@ -14,7 +14,6 @@
#include <MG_State/EGLState/Core.h>
#include <MG_Impl/GLImpl/Texture/ProxyTexture.h>
#include <MG_Impl/GLImpl/Framebuffer/GL_Framebuffer.h>
#include <MG_Impl/GLImpl/Sync/GL_Sync.h>
#include <atomic>
#include <mutex>
@@ -38,12 +37,6 @@ namespace MobileGL {
MGLOG_I("MobileGL closing...");
}
glslang::FinalizeProcess();
// GL syncs die with their contexts, and every context is gone by the
// time full teardown runs: drain the live-sync registry while the
// backend function table can still release the backend handles (and
// before a re-initialized library could pair them with the wrong
// backend's DeleteSync).
MG_Impl::GLImpl::DestroyAllSyncObjects();
MG_Backend::pActiveBackendObject.reset();
MG_State::pGLContext.reset();
MG_State::pEGLContext.reset();
@@ -107,11 +100,9 @@ namespace MobileGL {
// (EGL/WGL/CGL): initialization happens lazily on the first entry point
// via EnsureInitialized(), and full teardown happens deterministically
// when the last EGL display is terminated with nothing current (EGLImpl
// calls Destroy()). There is intentionally no backend-initializing static
// constructor, no static destructor, and no DllMain: the global singletons
// use leak-at-exit storage (see GlobalObjects.cpp), so a process that exits
// calls Destroy()). There is intentionally no static constructor, no
// static destructor, and no DllMain: the global singletons use
// leak-at-exit storage (see GlobalObjects.cpp), so a process that exits
// without eglTerminate simply leaks them to the OS instead of running
// backend destructors during static teardown. macOS has a lightweight
// dyld constructor that installs NSOpenGL dispatch hooks only; full backend
// initialization still enters here from the first hooked CGL context.
// backend destructors during static teardown.
} // namespace MobileGL
+3 -4
View File
@@ -13,10 +13,9 @@ namespace MobileGL {
void Initialize();
// Thread-safe, idempotent, and re-entrant wrapper around Initialize().
// Host layers (EGL/WGL/CGL entry points) call this lazily on first use so
// full backend initialization never depends on ELF/DLL static constructors,
// and so a fresh init can follow a full Destroy() (e.g. after the last
// eglTerminate). The macOS dyld bootstrap installs only lightweight
// NSOpenGL method hooks.
// MobileGL's lifecycle never depends on ELF/DLL static constructors, and
// so a fresh init can follow a full Destroy() (e.g. after the last
// eglTerminate).
void EnsureInitialized();
void Destroy();
-86
View File
@@ -145,10 +145,6 @@ namespace MobileGL {
GLenum buffer, GLint drawbuffer, const GLfloat* value);
void (*ClearNamedFramebufferfi)(const SharedPtr<MG_State::GLState::FramebufferObject>& framebuffer,
GLenum buffer, GLint drawbuffer, GLfloat depth, GLint stencil);
void (*ClearNamedFramebufferiv)(const SharedPtr<MG_State::GLState::FramebufferObject>& framebuffer,
GLenum buffer, GLint drawbuffer, const GLint* value);
void (*ClearNamedFramebufferuiv)(const SharedPtr<MG_State::GLState::FramebufferObject>& framebuffer,
GLenum buffer, GLint drawbuffer, const GLuint* value);
void (*BlitFramebuffer)(GLint srcX0, GLint srcY0, GLint srcX1, GLint srcY1, GLint dstX0, GLint dstY0,
GLint dstX1, GLint dstY1, GLbitfield mask, GLenum filter);
void (*BlitNamedFramebuffer)(const SharedPtr<MG_State::GLState::FramebufferObject>& readFramebuffer,
@@ -224,31 +220,6 @@ namespace MobileGL {
// and leave the query readable later.
Bool (*GetQueryResult64)(BackendQueryHandle query, Bool wait, Uint64* outNanoseconds);
void (*DeleteBackendQuery)(BackendQueryHandle query);
// GL_SAMPLES_PASSED occlusion queries (optional; null = unsupported,
// the frontend then rejects the target). Results/deletion flow through
// GetQueryResult64 / DeleteBackendQuery like timer queries.
BackendQueryHandle (*BeginOcclusionQuery)();
void (*EndOcclusionQuery)(BackendQueryHandle query);
// Transform feedback primitive queries backed by real GPU query pools
// (optional; null = frontend falls back to CPU accounting).
BackendQueryHandle (*BeginXfbPrimitivesQuery)(Bool generated);
void (*EndXfbPrimitivesQuery)(BackendQueryHandle query);
// Transform feedback capture spans, for backends whose own GL/ES driver
// performs the capture (DirectGLES). Both optional; null means the backend
// drives capture from its draw recording instead (DirectVulkan). End is
// called while the frontend capture state is still active, so the backend
// can still see the capture program and buffer bindings.
// GL_PATCH_VERTICES; ES 3.2 spells it the same way.
void (*PatchParameteri)(GLenum pname, GLint value);
void (*BeginTransformFeedback)(GLenum primitiveMode);
void (*EndTransformFeedback)();
// ARB_transform_feedback2. A backend that leaves these null keeps the single
// implicit capture span the frontend has always modelled; the frontend state
// (paused flag, per-object bindings) is tracked either way.
void (*PauseTransformFeedback)();
void (*ResumeTransformFeedback)();
void (*BindTransformFeedback)(GLuint name);
void (*DeleteTransformFeedback)(GLuint name);
Int64 (*GetGpuTimestampNs)(); // glGetInteger64v(GL_TIMESTAMP); 0 if unsupported
};
struct GlobalBackendFunctionsTable {
@@ -301,13 +272,6 @@ namespace MobileGL {
Int MaxIntegerSamples = 1;
Int MaxSamples = 1;
Int MaxSampleMaskWords = 1;
// Tessellation limits; defaults are the GL 4.0 core minimums.
Int MaxPatchVertices = 32;
Int MaxTessGenLevel = 64;
// GL_MIN/MAX_PROGRAM_TEXTURE_GATHER_OFFSET. Defaults are the GL 4.0 core
// minimums, which every ES 3.1 driver also guarantees.
Int MinProgramTextureGatherOffset = -8;
Int MaxProgramTextureGatherOffset = 7;
Int MaxTextureImageUnits = 32;
Int MaxVertexTextureImageUnits = 32;
Int MaxComputeTextureImageUnits = 32;
@@ -319,8 +283,6 @@ namespace MobileGL {
Int MaxComputeWorkGroupInvocations = 128;
Int MaxShaderStorageBufferBindings = 8;
Int MaxTextureBufferSize = 65536;
// GL_TEXTURE_BUFFER_OFFSET_ALIGNMENT; 1 means the offset is unconstrained.
Int TextureBufferOffsetAlignment = 1;
Int MaxUniformBufferBindings = 24;
Int MaxUniformBlockSize = 16384;
Int MaxImageUnits = 8;
@@ -338,55 +300,7 @@ namespace MobileGL {
Float ViewportBoundsRangeMin = 0.0f;
Float ViewportBoundsRangeMax = 0.0f;
Int ViewportSubpixelBits = 0;
// GL 4.x fragment-interpolation offset limits. These defaults are the
// core minimums and are replaced by live GLES/Vulkan device limits.
Float MinFragmentInterpolationOffset = -0.5f;
// For four fractional bits the greatest required legal offset is
// 0.5 - 2^-4 = 0.4375 (GL 4.6 table 23.70).
Float MaxFragmentInterpolationOffset = 0.4375f;
Int FragmentInterpolationOffsetBits = 4;
Bool SupportsWideLines = false;
// Whether a framebuffer whose depth and stencil attachments are distinct
// images can be rendered to. GL only requires support when both refer to the
// same image and lets an implementation answer GL_FRAMEBUFFER_UNSUPPORTED
// otherwise, which is what DirectVulkan (one combined attachment) and the
// real ES drivers behind DirectGLES both do. Defaults to true so a backend
// that never sets it keeps the permissive behaviour.
Bool SupportsDistinctDepthStencilAttachments = true;
// Whether attaching a single layer of a 3D or array texture to a framebuffer actually
// renders to that layer. DirectGLES hands the layer straight to
// glFramebufferTextureLayer, so it does; DirectVulkan maps a GL layer onto a Vulkan
// array layer with no notion of a 3D depth slice, so it does not yet. Defaults to false
// so a backend that never sets it gets the conservative answer.
// Which layered texture targets this backend can attach ONE layer of to a framebuffer
// and then really clear, render and read back that layer. Bit (1u << TextureTarget) is
// set for each supported target. Deliberately per target rather than one flag: the three
// ways a GL layer maps onto Vulkan are independent capabilities. A 2D or 2D multisample
// array layer IS a VkImage array layer and needs nothing extra; a 3D texture's layer is
// a z slice, which needs a 2D-array-compatible image and a per-slice clear that
// vkCmdClearColorImage cannot express; a cube map array needs an image shape and the
// imageCubeArray feature before it can be attached at any layer at all. Defaults to 0 so
// a backend that never sets it gets the conservative answer.
Uint32 PerLayerFramebufferAttachmentTargets = 0;
static constexpr Uint32 PerLayerFramebufferAttachmentBit(TextureTarget target) {
return (static_cast<Int>(target) >= 0 &&
static_cast<Int>(target) < static_cast<Int>(TextureTarget::TextureTargetCount))
? (1u << static_cast<Uint32>(target))
: 0u;
}
Bool SupportsPerLayerFramebufferAttachment(TextureTarget target) const {
const Uint32 bit = PerLayerFramebufferAttachmentBit(target);
return bit != 0 && (PerLayerFramebufferAttachmentTargets & bit) != 0;
}
// Whether glVertexAttribLFormat / glVertexArrayAttribLFormat can be honoured, i.e.
// whether a 64-bit vertex attribute can actually reach a shader unconverted. Detected,
// never assumed: DirectVulkan needs VkPhysicalDeviceFeatures::shaderFloat64 (the
// attribute travels as its 32-bit word pair, so no VK_FORMAT_R64* is required, but the
// bitcast result is Float64); DirectGLES can never have it, ESSL having no fp64 type at
// all. Defaults to false so a backend that never sets it gets the conservative answer.
Bool SupportsFloat64VertexAttributes = false;
SizeT MaxShaderStorageBlockSize = 128 * 1024 * 1024;
Uint32 SubgroupSize = 0;
Uint32 SubgroupSupportedStages = 0;
@@ -20,7 +20,6 @@
#include <MG_Util/Texture/TextureFormatProcessor.h>
#include <Config.h>
#include <algorithm>
#include <cmath>
#include <format>
namespace MobileGL::MG_Backend::DirectGLES {
@@ -32,7 +31,8 @@ namespace MobileGL::MG_Backend::DirectGLES {
void ClearGLErrors(const MG_External::GLESFunctionsTable& gl) {
if (!gl.glGetError) return;
while (gl.glGetError() != GL_NO_ERROR) {}
while (gl.glGetError() != GL_NO_ERROR) {
}
}
Bool CheckNoGLError(const MG_External::GLESFunctionsTable& gl) {
@@ -76,7 +76,8 @@ namespace MobileGL::MG_Backend::DirectGLES {
}
Bool IsGLESProbeMultisampleTarget(TextureTarget target) {
return target == TextureTarget::Texture2DMultisample || target == TextureTarget::Texture2DMultisampleArray;
return target == TextureTarget::Texture2DMultisample ||
target == TextureTarget::Texture2DMultisampleArray;
}
GLenum GetFramebufferAttachment(TextureInternalFormat format) {
@@ -113,8 +114,8 @@ namespace MobileGL::MG_Backend::DirectGLES {
GLenum normalizedInternalFormat = glFormat;
GLenum imageFormat = GL_RGBA;
GLenum imageType = GL_UNSIGNED_BYTE;
MG_Util::TextureFormatProcessor::NormalizePixelFormat(glFormat, PixelFormatNormalizeOptionBit::None,
&normalizedInternalFormat, &imageFormat, &imageType);
MG_Util::TextureFormatProcessor::NormalizePixelFormat(
glFormat, PixelFormatNormalizeOptionBit::None, &normalizedInternalFormat, &imageFormat, &imageType);
return imageFormat != GL_RED_INTEGER && imageFormat != GL_RG_INTEGER && imageFormat != GL_RGB_INTEGER &&
imageFormat != GL_RGBA_INTEGER && !MG_Util::IsDepthFormatInternalFormat(format) &&
!MG_Util::IsStencilFormatInternalFormat(format);
@@ -152,9 +153,9 @@ namespace MobileGL::MG_Backend::DirectGLES {
GLESProbeFormatInfo BuildNativeProbeFormatInfo(GLenum requestedInternalFormat) {
GLESProbeFormatInfo info;
info.InternalFormat = requestedInternalFormat;
MG_Util::TextureFormatProcessor::NormalizePixelFormat(requestedInternalFormat,
PixelFormatNormalizeOptionBit::None, nullptr,
&info.ImageFormat, &info.ImageType);
MG_Util::TextureFormatProcessor::NormalizePixelFormat(
requestedInternalFormat, PixelFormatNormalizeOptionBit::None, nullptr, &info.ImageFormat,
&info.ImageType);
return info;
}
@@ -208,12 +209,6 @@ namespace MobileGL::MG_Backend::DirectGLES {
if (options & PixelFormatNormalizeOptionBit::NoDepthComponent32) {
reasons.push_back("GL_DEPTH_COMPONENT32 native probe failed on OpenGL ES");
}
if (options & PixelFormatNormalizeOptionBit::NoThreeChannelRenderTarget) {
reasons.push_back("no three-channel multisample storage format on OpenGL ES");
}
if (options & PixelFormatNormalizeOptionBit::NoSnorm16RenderTarget) {
reasons.push_back("EXT_render_snorm not supported");
}
String reason;
for (SizeT i = 0; i < reasons.size(); ++i) {
@@ -231,16 +226,20 @@ namespace MobileGL::MG_Backend::DirectGLES {
return MG_Util::ConvertGLEnumToString(internalFormat);
}
void LogGLESFormatCaveat(TextureInternalFormat logicalFormat, SizeT targetIndex,
void LogGLESFormatCaveat(TextureInternalFormat logicalFormat,
SizeT targetIndex,
const GLESProbeFormatInfo& fallbackInfo) {
MGLOG_D("Caveat: %s %s not fully supported. Reason: %s. Fallback: %s",
GetFormatCapabilityTargetName(targetIndex).c_str(),
MG_Util::ConvertTextureInternalFormatToString(logicalFormat).c_str(), fallbackInfo.Reason.c_str(),
MG_Util::ConvertTextureInternalFormatToString(logicalFormat).c_str(),
fallbackInfo.Reason.c_str(),
ConvertFallbackInternalFormatToString(fallbackInfo.InternalFormat).c_str());
}
Bool BuildFallbackProbeFormatInfo(GLenum requestedInternalFormat, Flags<PixelFormatNormalizeOptionBit> options,
Bool forced, GLESProbeFormatInfo& outInfo) {
Bool BuildFallbackProbeFormatInfo(GLenum requestedInternalFormat,
Flags<PixelFormatNormalizeOptionBit> options,
Bool forced,
GLESProbeFormatInfo& outInfo) {
const Flags<PixelFormatNormalizeOptionBit> applicableOptions =
MG_Util::TextureFormatProcessor::GetApplicablePixelFormatNormalizeOptions(requestedInternalFormat,
options);
@@ -255,7 +254,8 @@ namespace MobileGL::MG_Backend::DirectGLES {
return outInfo.InternalFormat != GL_UNKNOWN_MGL;
}
FormatCapabilityFlags BuildTextureCapsFromProbe(TextureInternalFormat logicalFormat, TextureTarget target,
FormatCapabilityFlags BuildTextureCapsFromProbe(TextureInternalFormat logicalFormat,
TextureTarget target,
Bool renderable) {
FormatCapabilityFlags caps = GetTextureFeatureCaps(logicalFormat, target);
if (renderable) {
@@ -269,12 +269,16 @@ namespace MobileGL::MG_Backend::DirectGLES {
return caps;
}
void AddFullFormatCaps(FormatCapabilityCache& cache, SizeT targetIndex, SizeT formatIndex,
void AddFullFormatCaps(FormatCapabilityCache& cache,
SizeT targetIndex,
SizeT formatIndex,
FormatCapabilityFlags caps) {
cache.FullCaps[targetIndex][formatIndex] |= caps;
}
Bool AddCaveatFormatCaps(FormatCapabilityCache& cache, SizeT targetIndex, SizeT formatIndex,
Bool AddCaveatFormatCaps(FormatCapabilityCache& cache,
SizeT targetIndex,
SizeT formatIndex,
FormatCapabilityFlags caps) {
Bool added = false;
for (FormatCapability capability : kReportedFormatCapabilities) {
@@ -288,7 +292,8 @@ namespace MobileGL::MG_Backend::DirectGLES {
}
Int GetGLESFormatMaxSamples(const MG_External::GLESCapabilities& capabilities,
TextureInternalFormat logicalFormat, GLenum imageFormat) {
TextureInternalFormat logicalFormat,
GLenum imageFormat) {
const Bool isDepth = MG_Util::IsDepthFormatInternalFormat(logicalFormat);
const Bool isStencil = MG_Util::IsStencilFormatInternalFormat(logicalFormat);
const Bool isInteger = imageFormat == GL_RED_INTEGER || imageFormat == GL_RG_INTEGER ||
@@ -302,8 +307,10 @@ namespace MobileGL::MG_Backend::DirectGLES {
return capabilities.MaxColorTextureSamples;
}
Bool ProbeFramebufferCompletenessForTexture(const MG_External::GLESFunctionsTable& gl, TextureTarget target,
GLuint texture, TextureInternalFormat format) {
Bool ProbeFramebufferCompletenessForTexture(const MG_External::GLESFunctionsTable& gl,
TextureTarget target,
GLuint texture,
TextureInternalFormat format) {
GLuint framebuffer = 0;
GLint prevFramebuffer = 0;
if (!gl.glGenFramebuffers || !gl.glBindFramebuffer || !gl.glCheckFramebufferStatus ||
@@ -349,44 +356,9 @@ namespace MobileGL::MG_Backend::DirectGLES {
return complete;
}
// Whether the driver renders to a framebuffer whose depth and stencil come from
// two different renderbuffers. GL only requires support when both attachments are
// the same image, and ES drivers commonly answer GL_FRAMEBUFFER_UNSUPPORTED here;
// reporting COMPLETE from the frontend and then rendering into a framebuffer the
// driver refuses leaves the results silently empty.
Bool ProbeDistinctDepthStencilAttachments(const MG_External::GLESFunctionsTable& gl) {
if (!gl.glGenFramebuffers || !gl.glBindFramebuffer || !gl.glFramebufferRenderbuffer ||
!gl.glCheckFramebufferStatus || !gl.glDeleteFramebuffers || !gl.glGenRenderbuffers ||
!gl.glBindRenderbuffer || !gl.glRenderbufferStorage || !gl.glDeleteRenderbuffers) {
return true;
}
GLint prevFramebuffer = 0, prevRenderbuffer = 0;
gl.glGetIntegerv(GL_FRAMEBUFFER_BINDING, &prevFramebuffer);
gl.glGetIntegerv(GL_RENDERBUFFER_BINDING, &prevRenderbuffer);
GLuint framebuffer = 0;
GLuint renderbuffers[2] = {0, 0};
gl.glGenFramebuffers(1, &framebuffer);
gl.glGenRenderbuffers(2, renderbuffers);
gl.glBindRenderbuffer(GL_RENDERBUFFER, renderbuffers[0]);
gl.glRenderbufferStorage(GL_RENDERBUFFER, GL_DEPTH_COMPONENT16, 4, 4);
gl.glBindRenderbuffer(GL_RENDERBUFFER, renderbuffers[1]);
gl.glRenderbufferStorage(GL_RENDERBUFFER, GL_STENCIL_INDEX8, 4, 4);
gl.glBindFramebuffer(GL_FRAMEBUFFER, framebuffer);
gl.glFramebufferRenderbuffer(GL_FRAMEBUFFER, GL_DEPTH_ATTACHMENT, GL_RENDERBUFFER, renderbuffers[0]);
gl.glFramebufferRenderbuffer(GL_FRAMEBUFFER, GL_STENCIL_ATTACHMENT, GL_RENDERBUFFER, renderbuffers[1]);
const Bool supported = gl.glCheckFramebufferStatus(GL_FRAMEBUFFER) == GL_FRAMEBUFFER_COMPLETE;
gl.glBindFramebuffer(GL_FRAMEBUFFER, static_cast<GLuint>(prevFramebuffer));
gl.glBindRenderbuffer(GL_RENDERBUFFER, static_cast<GLuint>(prevRenderbuffer));
gl.glDeleteFramebuffers(1, &framebuffer);
gl.glDeleteRenderbuffers(2, renderbuffers);
return supported;
}
Bool ProbeFramebufferCompletenessForRenderbuffer(const MG_External::GLESFunctionsTable& gl, GLuint renderbuffer,
TextureInternalFormat format) {
Bool ProbeFramebufferCompletenessForRenderbuffer(const MG_External::GLESFunctionsTable& gl,
GLuint renderbuffer,
TextureInternalFormat format) {
GLuint framebuffer = 0;
GLint prevFramebuffer = 0;
if (!gl.glGenFramebuffers || !gl.glBindFramebuffer || !gl.glFramebufferRenderbuffer ||
@@ -453,16 +425,16 @@ namespace MobileGL::MG_Backend::DirectGLES {
}
break;
case TextureTarget::Texture3D:
gl.glTexImage3D(glTarget, 0, static_cast<GLint>(internalFormat), 2, 2, 2, 0, imageFormat, imageType,
nullptr);
gl.glTexImage3D(glTarget, 0, static_cast<GLint>(internalFormat), 2, 2, 2, 0, imageFormat,
imageType, nullptr);
break;
case TextureTarget::Texture2DArray:
gl.glTexImage3D(glTarget, 0, static_cast<GLint>(internalFormat), 2, 2, 1, 0, imageFormat, imageType,
nullptr);
gl.glTexImage3D(glTarget, 0, static_cast<GLint>(internalFormat), 2, 2, 1, 0, imageFormat,
imageType, nullptr);
break;
case TextureTarget::TextureCubeMapArray:
gl.glTexImage3D(glTarget, 0, static_cast<GLint>(internalFormat), 2, 2, 6, 0, imageFormat, imageType,
nullptr);
gl.glTexImage3D(glTarget, 0, static_cast<GLint>(internalFormat), 2, 2, 6, 0, imageFormat,
imageType, nullptr);
break;
default:
break;
@@ -483,8 +455,11 @@ namespace MobileGL::MG_Backend::DirectGLES {
return created;
}
Bool ProbeRenderbuffer(const MG_External::GLESFunctionsTable& gl, GLenum internalFormat,
TextureInternalFormat logicalFormat, Bool multisample, Int samples) {
Bool ProbeRenderbuffer(const MG_External::GLESFunctionsTable& gl,
GLenum internalFormat,
TextureInternalFormat logicalFormat,
Bool multisample,
Int samples) {
if (!gl.glGenRenderbuffers || !gl.glBindRenderbuffer || !gl.glDeleteRenderbuffers) {
return false;
}
@@ -506,16 +481,17 @@ namespace MobileGL::MG_Backend::DirectGLES {
gl.glRenderbufferStorage(GL_RENDERBUFFER, internalFormat, 1, 1);
}
const Bool created = CheckNoGLError(gl);
const Bool complete =
created && ProbeFramebufferCompletenessForRenderbuffer(gl, renderbuffer, logicalFormat);
const Bool complete = created && ProbeFramebufferCompletenessForRenderbuffer(gl, renderbuffer, logicalFormat);
gl.glBindRenderbuffer(GL_RENDERBUFFER, static_cast<GLuint>(prevRenderbuffer));
gl.glDeleteRenderbuffers(1, &renderbuffer);
ClearGLErrors(gl);
return complete;
}
Vector<Int> ProbeRenderbufferSampleCounts(const MG_External::GLESFunctionsTable& gl, GLenum internalFormat,
TextureInternalFormat logicalFormat, Int maxSamples) {
Vector<Int> ProbeRenderbufferSampleCounts(const MG_External::GLESFunctionsTable& gl,
GLenum internalFormat,
TextureInternalFormat logicalFormat,
Int maxSamples) {
Vector<Int> sampleCounts;
for (Int samples = std::max(maxSamples, 1); samples > 1; samples >>= 1) {
if (ProbeRenderbuffer(gl, internalFormat, logicalFormat, true, samples)) {
@@ -543,50 +519,20 @@ namespace MobileGL::MG_Backend::DirectGLES {
}
const GLESProbeFormatInfo nativeInfo = BuildNativeProbeFormatInfo(requestedInternalFormat);
GLESProbeFormatInfo outerFallbackInfo;
const Bool outerHasForcedFallback =
BuildFallbackProbeFormatInfo(requestedInternalFormat, forcedOptions, true, outerFallbackInfo);
if (!outerHasForcedFallback) {
BuildFallbackProbeFormatInfo(requestedInternalFormat, driverOptions, false, outerFallbackInfo);
GLESProbeFormatInfo fallbackInfo;
const Bool hasForcedFallback =
BuildFallbackProbeFormatInfo(requestedInternalFormat, forcedOptions, true, fallbackInfo);
if (!hasForcedFallback) {
BuildFallbackProbeFormatInfo(requestedInternalFormat, driverOptions, false, fallbackInfo);
}
for (SizeT targetIndex = 0; targetIndex < kFormatCapabilityTextureTargetCount; ++targetIndex) {
const auto target = static_cast<TextureTarget>(targetIndex);
// A multisample texture can only ever be rendered into, so its storage format
// has to stay colour-renderable; the ordinary fallback for a three-channel
// format is a three-channel one, which ES accepts as a texture but rejects as
// multisample storage. Recompute the fallback per target so those formats get
// widened here and nowhere else.
Flags<PixelFormatNormalizeOptionBit> targetOptions;
if (IsGLESProbeMultisampleTarget(target)) {
targetOptions |= PixelFormatNormalizeOptionBit::NoThreeChannelRenderTarget;
if (!capabilities.SupportsRenderSnorm || !capabilities.SupportsNorm16Texture) {
targetOptions |= PixelFormatNormalizeOptionBit::NoSnorm16RenderTarget;
}
}
GLESProbeFormatInfo fallbackInfo = outerFallbackInfo;
Bool hasForcedFallback = outerHasForcedFallback;
if (targetOptions) {
hasForcedFallback = BuildFallbackProbeFormatInfo(
requestedInternalFormat, forcedOptions | targetOptions, true, fallbackInfo);
if (!hasForcedFallback) {
BuildFallbackProbeFormatInfo(requestedInternalFormat, driverOptions | targetOptions, false,
fallbackInfo);
}
}
// 1D, 1D-array and rectangle textures live on an ES target (see
// TextureImpl::MapToBackendTextureTarget), so they have to be probed there too -
// probing the desktop-only target itself always failed, which left those slots
// of the cache empty and stopped any fallback format from being selected for
// them (a GL_DEPTH_COMPONENT32 1D texture then got no storage at all).
const TextureTarget probeTarget = TextureImpl::MapToBackendTextureTarget(target);
Bool shouldProbeFallback = hasForcedFallback;
if (!hasForcedFallback) {
Bool nativeRenderable = false;
const Bool nativeCreated =
ProbeTexture(gl, probeTarget, nativeInfo.InternalFormat, nativeInfo.ImageFormat,
ProbeTexture(gl, target, nativeInfo.InternalFormat, nativeInfo.ImageFormat,
nativeInfo.ImageType, logicalFormat, &nativeRenderable);
if (nativeCreated) {
AddFullFormatCaps(cache, targetIndex, formatIndex,
@@ -601,12 +547,12 @@ namespace MobileGL::MG_Backend::DirectGLES {
if (shouldProbeFallback && fallbackInfo.InternalFormat != GL_UNKNOWN_MGL) {
Bool fallbackRenderable = false;
const Bool fallbackCreated =
ProbeTexture(gl, probeTarget, fallbackInfo.InternalFormat, fallbackInfo.ImageFormat,
ProbeTexture(gl, target, fallbackInfo.InternalFormat, fallbackInfo.ImageFormat,
fallbackInfo.ImageType, logicalFormat, &fallbackRenderable);
if (fallbackCreated) {
if (AddCaveatFormatCaps(
cache, targetIndex, formatIndex,
BuildTextureCapsFromProbe(logicalFormat, target, fallbackRenderable))) {
if (AddCaveatFormatCaps(cache, targetIndex, formatIndex,
BuildTextureCapsFromProbe(logicalFormat, target,
fallbackRenderable))) {
LogGLESFormatCaveat(logicalFormat, targetIndex, fallbackInfo);
}
if (IsGLESProbeMultisampleTarget(target)) {
@@ -617,8 +563,8 @@ namespace MobileGL::MG_Backend::DirectGLES {
}
const SizeT renderbufferTargetIndex = GetRenderbufferFormatCapabilityTargetIndex();
Bool shouldProbeFallbackRenderbuffer = outerHasForcedFallback;
if (!outerHasForcedFallback) {
Bool shouldProbeFallbackRenderbuffer = hasForcedFallback;
if (!hasForcedFallback) {
const Bool nativeRenderbufferComplete =
ProbeRenderbuffer(gl, nativeInfo.InternalFormat, logicalFormat, false, 1);
if (nativeRenderbufferComplete) {
@@ -632,16 +578,16 @@ namespace MobileGL::MG_Backend::DirectGLES {
shouldProbeFallbackRenderbuffer = true;
}
}
if (shouldProbeFallbackRenderbuffer && outerFallbackInfo.InternalFormat != GL_UNKNOWN_MGL &&
ProbeRenderbuffer(gl, outerFallbackInfo.InternalFormat, logicalFormat, false, 1)) {
if (shouldProbeFallbackRenderbuffer && fallbackInfo.InternalFormat != GL_UNKNOWN_MGL &&
ProbeRenderbuffer(gl, fallbackInfo.InternalFormat, logicalFormat, false, 1)) {
if (AddCaveatFormatCaps(cache, renderbufferTargetIndex, formatIndex,
GetRenderbufferFeatureCaps(logicalFormat))) {
LogGLESFormatCaveat(logicalFormat, renderbufferTargetIndex, outerFallbackInfo);
LogGLESFormatCaveat(logicalFormat, renderbufferTargetIndex, fallbackInfo);
}
const Int maxSamples =
GetGLESFormatMaxSamples(capabilities, logicalFormat, outerFallbackInfo.ImageFormat);
GetGLESFormatMaxSamples(capabilities, logicalFormat, fallbackInfo.ImageFormat);
cache.SampleCounts[renderbufferTargetIndex][formatIndex] =
ProbeRenderbufferSampleCounts(gl, outerFallbackInfo.InternalFormat, logicalFormat, maxSamples);
ProbeRenderbufferSampleCounts(gl, fallbackInfo.InternalFormat, logicalFormat, maxSamples);
}
}
}
@@ -657,7 +603,7 @@ namespace MobileGL::MG_Backend::DirectGLES {
.ExtraVendor = Nullopt, // Extra vendor
.RendererGLInfo =
{
.TargetGLVersion = {4, 0, 0}, // GL target version
.TargetGLVersion = {3, 3, 0}, // Target OpenGL Version
.TargetGLSLVersion = {4, 6, 0}, // Target Shading Language Version
// Baseline advertisement (no timer queries / anisotropy yet); reconciled
// once the ES capabilities exist, see UpdateAdvertisedCapabilityExtensions.
@@ -688,7 +634,8 @@ namespace MobileGL::MG_Backend::DirectGLES {
} // namespace
void PopulateFormatCapabilities(const MG_External::GLESFunctionsTable& gl,
const MG_External::GLESCapabilities& capabilities, FormatCapabilityCache& cache) {
const MG_External::GLESCapabilities& capabilities,
FormatCapabilityCache& cache) {
PopulateFormatCapabilitiesImpl(gl, capabilities, cache);
}
@@ -752,8 +699,10 @@ namespace MobileGL::MG_Backend::DirectGLES {
return false;
}
if ((handle.Backend != WindowBackend::Android && handle.Backend != WindowBackend::X11 &&
handle.Backend != WindowBackend::MetalLayer && handle.Backend != WindowBackend::Win32) ||
if ((handle.Backend != WindowBackend::Android &&
handle.Backend != WindowBackend::X11 &&
handle.Backend != WindowBackend::MetalLayer &&
handle.Backend != WindowBackend::Win32) ||
!handle.Handle) {
MGLOG_E("DirectGLES backend only supports Android, X11, CAMetalLayer, and Win32 native windows");
return false;
@@ -872,25 +821,17 @@ namespace MobileGL::MG_Backend::DirectGLES {
}
Vector<GLExtension> BuildAdvertisedExtensions(Bool timerQueriesSupported, Bool anisotropicFilteringSupported) {
Vector<GLExtension> extensions = {
V_OpenGL30, V_OpenGL31, V_OpenGL32, V_OpenGL33, V_OpenGL40, E_GL_ARB_draw_buffers_blend,
E_GL_ARB_compute_shader, E_GL_ARB_shader_storage_buffer_object, E_GL_ARB_shader_image_load_store,
E_GL_ARB_program_interface_query, E_GL_ARB_framebuffer_object, E_GL_EXT_framebuffer_object,
E_GL_ARB_depth_texture, E_GL_ARB_buffer_storage, E_GL_ARB_texture_storage,
E_GL_ARB_texture_storage_multisample, E_GL_ARB_clear_texture, E_GL_ARB_direct_state_access,
E_GL_ARB_multi_draw_indirect, E_GL_ARB_indirect_parameters, E_GL_ARB_shader_draw_parameters,
E_GL_ARB_gpu_shader5, E_GL_ARB_multi_bind, E_GL_ARB_shading_language_420pack,
E_GL_ARB_vertex_attrib_binding,
// Both are core from GL 3.2/3.3 on and implemented here for
// every advertised version, but an app targeting 3.0/3.1
// only reaches them through the extension string - the CTS
// picks a whole different shader for draw_buffers without
// explicit_attrib_location. DirectVulkan advertises both.
E_GL_ARB_explicit_attrib_location, E_GL_ARB_texture_multisample, E_GL_ARB_shader_image_size,
// Advertised with GL_NUM_PROGRAM_BINARY_FORMATS = 0, which the
// extension explicitly permits. It is also the only thing that
// exposes glProgramParameteri before GL 4.1.
E_GL_ARB_get_program_binary};
Vector<GLExtension> extensions = {V_OpenGL30, V_OpenGL31, V_OpenGL32,
V_OpenGL33, E_GL_ARB_draw_buffers_blend, E_GL_ARB_compute_shader,
E_GL_ARB_shader_storage_buffer_object, E_GL_ARB_shader_image_load_store,
E_GL_ARB_program_interface_query, E_GL_ARB_framebuffer_object,
E_GL_EXT_framebuffer_object, E_GL_ARB_depth_texture, E_GL_ARB_buffer_storage,
E_GL_ARB_texture_storage, E_GL_ARB_texture_storage_multisample,
E_GL_ARB_clear_texture, E_GL_ARB_direct_state_access,
E_GL_ARB_multi_draw_indirect, E_GL_ARB_indirect_parameters,
E_GL_ARB_shader_draw_parameters, E_GL_ARB_gpu_shader5, E_GL_ARB_multi_bind,
E_GL_ARB_shading_language_420pack, E_GL_ARB_vertex_attrib_binding,
E_GL_ARB_shader_image_size};
// Only advertised when the device driver actually has usable timer queries
// (GL_EXT_disjoint_timer_query plus its entry points) and the
// MOBILEGL_DISABLE_TIMERQUERY escape hatch is off.
@@ -964,8 +905,6 @@ namespace MobileGL::MG_Backend::DirectGLES {
funcsTable.GL.ClearBufferuiv = ClearBufferuiv;
funcsTable.GL.ClearBufferiv = ClearBufferiv;
funcsTable.GL.ClearNamedFramebufferfv = ClearNamedFramebufferfv;
funcsTable.GL.ClearNamedFramebufferiv = ClearNamedFramebufferiv;
funcsTable.GL.ClearNamedFramebufferuiv = ClearNamedFramebufferuiv;
funcsTable.GL.ClearNamedFramebufferfi = ClearNamedFramebufferfi;
funcsTable.GL.BlitFramebuffer = BlitFramebuffer;
funcsTable.GL.BlitNamedFramebuffer = BlitNamedFramebuffer;
@@ -995,30 +934,11 @@ namespace MobileGL::MG_Backend::DirectGLES {
funcsTable.GL.BeginTimeElapsedQuery = BeginTimeElapsedQuery;
funcsTable.GL.EndTimeElapsedQuery = EndTimeElapsedQuery;
funcsTable.GL.QueryCounterTimestamp = QueryCounterTimestamp;
funcsTable.GL.IsQueryResultAvailable = IsQueryResultAvailable;
funcsTable.GL.GetQueryResult64 = GetQueryResult64;
funcsTable.GL.DeleteBackendQuery = DeleteBackendQuery;
funcsTable.GL.GetGpuTimestampNs = GetGpuTimestampNs;
}
// Occlusion queries are core ES3 (independent of MOBILEGL_DISABLE_TIMERQUERY)
// and share the handle-based result/delete entries, which must exist even
// when the timer-query group above is disabled.
funcsTable.GL.BeginOcclusionQuery = BeginOcclusionQuery;
funcsTable.GL.EndOcclusionQuery = EndOcclusionQuery;
// Real driver primitive counters: the frontend's CPU accounting cannot see a
// geometry shader's amplification.
funcsTable.GL.BeginXfbPrimitivesQuery = BeginXfbPrimitivesQuery;
funcsTable.GL.EndXfbPrimitivesQuery = EndXfbPrimitivesQuery;
funcsTable.GL.IsQueryResultAvailable = IsQueryResultAvailable;
funcsTable.GL.GetQueryResult64 = GetQueryResult64;
funcsTable.GL.DeleteBackendQuery = DeleteBackendQuery;
// Transform feedback is captured by the real ES driver rather than
// reconstructed from the draw recording, so the frontend has to hand the
// span boundaries over.
funcsTable.GL.PatchParameteri = DirectGLES::PatchParameteri;
funcsTable.GL.BeginTransformFeedback = XfbImpl::BeginTransformFeedback;
funcsTable.GL.EndTransformFeedback = XfbImpl::EndTransformFeedback;
funcsTable.GL.PauseTransformFeedback = XfbImpl::PauseTransformFeedback;
funcsTable.GL.ResumeTransformFeedback = XfbImpl::ResumeTransformFeedback;
funcsTable.GL.BindTransformFeedback = XfbImpl::BindTransformFeedback;
funcsTable.GL.DeleteTransformFeedback = XfbImpl::DeleteTransformFeedback;
funcsTableInitialized = true;
}
return funcsTable;
@@ -1028,7 +948,8 @@ namespace MobileGL::MG_Backend::DirectGLES {
return m_dynamicParameters;
}
void BackendObject_DirectGLES::ApplyGLESCapabilitiesForTesting(const MG_External::GLESCapabilities& capabilities) {
void BackendObject_DirectGLES::ApplyGLESCapabilitiesForTesting(
const MG_External::GLESCapabilities& capabilities) {
m_GLESCapabilities = capabilities;
UpdateDynamicBackendParameters();
}
@@ -1058,10 +979,6 @@ namespace MobileGL::MG_Backend::DirectGLES {
m_dynamicParameters.MaxIntegerSamples = m_GLESCapabilities.MaxIntegerSamples;
m_dynamicParameters.MaxSamples = m_GLESCapabilities.MaxSamples;
m_dynamicParameters.MaxSampleMaskWords = m_GLESCapabilities.MaxSampleMaskWords;
m_dynamicParameters.MaxPatchVertices = m_GLESCapabilities.MaxPatchVertices;
m_dynamicParameters.MaxTessGenLevel = m_GLESCapabilities.MaxTessGenLevel;
m_dynamicParameters.MinProgramTextureGatherOffset = m_GLESCapabilities.MinProgramTextureGatherOffset;
m_dynamicParameters.MaxProgramTextureGatherOffset = m_GLESCapabilities.MaxProgramTextureGatherOffset;
// Clamp the advertised sampler limits the same way the DirectVulkan backend does: per-stage
// GL_MAX_TEXTURE_IMAGE_UNITS must never exceed host-side fixed arrays sized off it (e.g.
// Minecraft's 128-entry Blaze3D GlStateManager.TEXTURES[], iterated by Iris), and the combined
@@ -1089,10 +1006,10 @@ namespace MobileGL::MG_Backend::DirectGLES {
m_dynamicParameters.MaxComputeWorkGroupInvocations = m_GLESCapabilities.MaxComputeWorkGroupInvocations;
m_dynamicParameters.MaxShaderStorageBufferBindings = m_GLESCapabilities.MaxShaderStorageBufferBindings;
m_dynamicParameters.MaxTextureBufferSize = m_GLESCapabilities.MaxTextureBufferSize;
m_dynamicParameters.TextureBufferOffsetAlignment = m_GLESCapabilities.TextureBufferOffsetAlignment;
m_dynamicParameters.MaxUniformBufferBindings = m_GLESCapabilities.MaxUniformBufferBindings;
m_dynamicParameters.MaxUniformBlockSize = m_GLESCapabilities.MaxUniformBlockSize;
const Int maxSupportedTextureUnits = static_cast<Int>(MG_State::GLState::TextureState::MAX_TEXTURE_IMAGE_UNITS);
const Int maxSupportedTextureUnits =
static_cast<Int>(MG_State::GLState::TextureState::MAX_TEXTURE_IMAGE_UNITS);
m_dynamicParameters.MaxImageUnits =
std::max(std::min(m_GLESCapabilities.MaxImageUnits, maxSupportedTextureUnits), 0);
m_dynamicParameters.MaxCombinedImageUniforms = std::max(m_GLESCapabilities.MaxCombinedImageUniforms, 0);
@@ -1100,40 +1017,14 @@ namespace MobileGL::MG_Backend::DirectGLES {
return std::min({std::max(stageLimit, 0), m_dynamicParameters.MaxImageUnits,
m_dynamicParameters.MaxCombinedImageUniforms});
};
m_dynamicParameters.MaxVertexImageUniforms = clampStageImageUniforms(m_GLESCapabilities.MaxVertexImageUniforms);
m_dynamicParameters.MaxVertexImageUniforms =
clampStageImageUniforms(m_GLESCapabilities.MaxVertexImageUniforms);
m_dynamicParameters.MaxGeometryImageUniforms =
clampStageImageUniforms(m_GLESCapabilities.MaxGeometryImageUniforms);
m_dynamicParameters.MaxFragmentImageUniforms =
clampStageImageUniforms(m_GLESCapabilities.MaxFragmentImageUniforms);
m_dynamicParameters.MaxComputeImageUniforms =
clampStageImageUniforms(m_GLESCapabilities.MaxComputeImageUniforms);
m_dynamicParameters.SupportsDistinctDepthStencilAttachments =
ProbeDistinctDepthStencilAttachments(DirectGLES::g_GLESFuncs);
// SyncAttachmentObject routes a layered upload target to glFramebufferTextureLayer with the
// attachment's layer passed through, so this backend really does render to the layer it was
// given - provided the driver resolved the entry point at all.
// SyncAttachmentObject (Managers.cpp, the glFramebufferTextureLayer branch) routes exactly
// five upload targets to glFramebufferTextureLayer with the attachment's layer passed
// through, so this backend really does render to the layer it was given - provided the driver
// resolved the entry point at all. The cube map array is the one target that also needs
// ES-level support before it has any storage to attach.
m_dynamicParameters.PerLayerFramebufferAttachmentTargets = 0;
if (DirectGLES::g_GLESFuncs.glFramebufferTextureLayer != nullptr) {
using DynParams = MG_Backend::DynamicBackendParameters;
m_dynamicParameters.PerLayerFramebufferAttachmentTargets |=
DynParams::PerLayerFramebufferAttachmentBit(TextureTarget::Texture3D) |
DynParams::PerLayerFramebufferAttachmentBit(TextureTarget::Texture1DArray) |
DynParams::PerLayerFramebufferAttachmentBit(TextureTarget::Texture2DArray) |
DynParams::PerLayerFramebufferAttachmentBit(TextureTarget::Texture2DMultisampleArray);
if (m_GLESCapabilities.SupportsTextureCubeMapArray) {
m_dynamicParameters.PerLayerFramebufferAttachmentTargets |=
DynParams::PerLayerFramebufferAttachmentBit(TextureTarget::TextureCubeMapArray);
}
}
// Not a driver question and never will be: OpenGL ES has no double-precision vertex format
// and ESSL has no fp64 type to consume one with, so a 64-bit vertex attribute has nowhere to
// land on this backend regardless of what the driver underneath happens to support.
m_dynamicParameters.SupportsFloat64VertexAttributes = false;
m_dynamicParameters.MaxDrawBuffers = m_GLESCapabilities.MaxDrawBuffers;
m_dynamicParameters.MaxColorAttachments = m_GLESCapabilities.MaxColorAttachments;
m_dynamicParameters.MaxClipDistances = m_GLESCapabilities.MaxClipDistances;
@@ -1143,29 +1034,13 @@ namespace MobileGL::MG_Backend::DirectGLES {
m_dynamicParameters.ViewportBoundsRangeMin = m_GLESCapabilities.ViewportBoundsRangeMin;
m_dynamicParameters.ViewportBoundsRangeMax = m_GLESCapabilities.ViewportBoundsRangeMax;
m_dynamicParameters.ViewportSubpixelBits = m_GLESCapabilities.ViewportSubpixelBits;
m_dynamicParameters.MinFragmentInterpolationOffset =
std::isfinite(m_GLESCapabilities.MinFragmentInterpolationOffset) &&
m_GLESCapabilities.MinFragmentInterpolationOffset <= -0.5f
? m_GLESCapabilities.MinFragmentInterpolationOffset
: -0.5f;
m_dynamicParameters.MaxFragmentInterpolationOffset = 0.4375f;
m_dynamicParameters.FragmentInterpolationOffsetBits = 4;
if (m_GLESCapabilities.FragmentInterpolationOffsetBits >= 4 &&
std::isfinite(m_GLESCapabilities.MaxFragmentInterpolationOffset)) {
const Float requiredMaxOffset =
0.5f - std::ldexp(1.0f, -m_GLESCapabilities.FragmentInterpolationOffsetBits);
if (m_GLESCapabilities.MaxFragmentInterpolationOffset >= requiredMaxOffset) {
m_dynamicParameters.MaxFragmentInterpolationOffset = m_GLESCapabilities.MaxFragmentInterpolationOffset;
m_dynamicParameters.FragmentInterpolationOffsetBits =
m_GLESCapabilities.FragmentInterpolationOffsetBits;
}
}
m_dynamicParameters.SupportsWideLines =
m_GLESCapabilities.AliasedLineWidthRangeMax > 1.0f || m_GLESCapabilities.SmoothLineWidthRangeMax > 1.0f;
const auto containsAny = [](const String& haystack, std::initializer_list<const char*> needles) {
return std::any_of(needles.begin(), needles.end(),
[&](const char* needle) { return haystack.find(needle) != String::npos; });
return std::any_of(needles.begin(), needles.end(), [&](const char* needle) {
return haystack.find(needle) != String::npos;
});
};
const String vendorAndRenderer =
m_GLESCapabilities.GLESVendorString + " " + m_GLESCapabilities.GLESRendererString;
File diff suppressed because it is too large Load Diff
@@ -59,10 +59,6 @@ namespace MobileGL::MG_Backend::DirectGLES {
GLenum buffer, GLint drawbuffer, const GLfloat* value);
void ClearNamedFramebufferfi(const SharedPtr<MG_State::GLState::FramebufferObject>& framebuffer,
GLenum buffer, GLint drawbuffer, GLfloat depth, GLint stencil);
void ClearNamedFramebufferiv(const SharedPtr<MG_State::GLState::FramebufferObject>& framebuffer,
GLenum buffer, GLint drawbuffer, const GLint* value);
void ClearNamedFramebufferuiv(const SharedPtr<MG_State::GLState::FramebufferObject>& framebuffer,
GLenum buffer, GLint drawbuffer, const GLuint* value);
void BlitFramebuffer(GLint srcX0, GLint srcY0, GLint srcX1, GLint srcY1, GLint dstX0, GLint dstY0, GLint dstX1,
GLint dstY1, GLbitfield mask, GLenum filter);
void BlitNamedFramebuffer(const SharedPtr<MG_State::GLState::FramebufferObject>& readFramebuffer,
@@ -134,16 +130,6 @@ namespace MobileGL::MG_Backend::DirectGLES {
BackendQueryHandle BeginTimeElapsedQuery();
void EndTimeElapsedQuery(BackendQueryHandle query);
BackendQueryHandle QueryCounterTimestamp();
// GL_ANY_SAMPLES_PASSED(_CONSERVATIVE) occlusion queries: core ES3, independent of
// GL_EXT_disjoint_timer_query and of MOBILEGL_DISABLE_TIMERQUERY. Results/deletion
// flow through GetQueryResult64/DeleteBackendQuery like the timer queries above.
BackendQueryHandle BeginOcclusionQuery();
void EndOcclusionQuery(BackendQueryHandle query);
// GL_TRANSFORM_FEEDBACK_PRIMITIVES_WRITTEN / GL_PRIMITIVES_GENERATED, also core ES
// (GL_PRIMITIVES_GENERATED from ES 3.2 on). Null when the target is unavailable, in
// which case the frontend falls back to counting primitives from the draw calls.
BackendQueryHandle BeginXfbPrimitivesQuery(Bool generated);
void EndXfbPrimitivesQuery(BackendQueryHandle query);
Bool IsQueryResultAvailable(BackendQueryHandle query);
// Returns true when a final value landed in *outNanoseconds (a zero for
// null or stale-generation handles IS final: the frontend may cache it
@@ -160,11 +146,6 @@ namespace MobileGL::MG_Backend::DirectGLES {
// A buffer retired during frame N is safe to recycle once CompletedFrameSerial() >= N.
Uint64 CurrentFrameSerial();
Uint64 CompletedFrameSerial();
// Block (up to timeoutNs) until the given frame serial provably retired on the
// GPU, using the per-frame fence ring. False when no usable fence covers the
// serial (fence-less context, foreign thread, or the slot was recycled);
// completion state is untouched in that case.
Bool WaitForFrameSerialCompleted(Uint64 serial, Uint64 timeoutNs);
// Applies (or defers until the window surface exists) the app-requested
// eglSwapInterval on the native EGL surface.
void SetSwapInterval(Int interval);
@@ -173,24 +154,6 @@ namespace MobileGL::MG_Backend::DirectGLES {
void SetGLESCapabilities(const MG_External::GLESCapabilities& capabilities);
void DestroyEGLContext();
// Transform feedback capture spans, performed by the real ES driver. The
// capture set is declared on the backend program at link time; the driver-side
// begin is deferred to the first draw of the span (ES needs the capturing
// program current and the capture buffers bound), and the end also mirrors the
// captured bytes back into the frontend buffer shadows.
void PatchParameteri(GLenum pname, GLint value);
namespace XfbImpl {
Bool AreTransformFeedbacksSupported();
void BeginTransformFeedback(GLenum primitiveMode);
void EndTransformFeedback();
void PauseTransformFeedback();
void ResumeTransformFeedback();
void BindTransformFeedback(GLuint name);
void DeleteTransformFeedback(GLuint name);
void OnBackendContextDestroyed();
} // namespace XfbImpl
extern MG_External::EGLFunctionsTable g_EGLFuncs;
extern MG_External::GLESFunctionsTable g_GLESFuncs;
extern MG_External::GLESCapabilities g_GLESCapabilities;
File diff suppressed because it is too large Load Diff
+52 -324
View File
@@ -27,54 +27,39 @@ namespace MobileGL::MG_Backend::DirectGLES {
using StatePtr = SharedPtr<StateObject>;
using StateWeakPtr = std::weak_ptr<StateObject>;
using BackendPtr = SharedPtr<BackendObject>;
// The backend twin and the weak reference that decides whether the raw key still
// names the state object the twin was built for. Both live in one entry: a
// separate liveness map answered nothing the backend probe had not already found
// and cost a second hash lookup on every Find, which the draw path runs ~10 times.
struct Entry {
BackendPtr backend;
StateWeakPtr stateRef;
};
using BackendMap = UnorderedMap<StateObject*, Entry>;
using BackendMap = UnorderedMap<StateObject*, BackendPtr>;
using StateRefMap = UnorderedMap<StateObject*, StateWeakPtr>;
using iterator = typename BackendMap::iterator;
using const_iterator = typename BackendMap::const_iterator;
BackendPtr& GetOrCreate(const StatePtr& stateObj) {
MOBILEGL_ASSERT(stateObj != nullptr, "State object must not be null");
auto& entry = m_entries[stateObj.get()];
if (entry.stateRef.expired()) {
// The previous owner of this address is gone and the allocator handed it
// to a new object: its twin describes ids the new state object never made.
entry.backend.reset();
auto* key = stateObj.get();
auto trackedStateIt = m_stateRefs.find(key);
if (trackedStateIt != m_stateRefs.end() && trackedStateIt->second.expired()) {
EraseByKey(key);
}
entry.stateRef = stateObj;
return entry.backend;
m_stateRefs[key] = stateObj;
return m_backendObjects[key];
}
// Null when no live state object owns this key. The result points into the map, so
// it stays valid only until the next GetOrCreate/Find/CollectGarbage on this registry.
BackendPtr* Find(StateObject* stateObj) {
const auto entryIt = m_entries.find(stateObj);
if (entryIt == m_entries.end()) {
return nullptr;
iterator find(StateObject* stateObj) {
if (!IsAlive(stateObj)) {
EraseByKey(stateObj);
return m_backendObjects.end();
}
if (entryIt->second.stateRef.expired()) {
m_entries.erase(entryIt);
return nullptr;
}
return &entryIt->second.backend;
return m_backendObjects.find(stateObj);
}
const BackendPtr* Find(StateObject* stateObj) const {
return const_cast<StateBackendObjectRegistry*>(this)->Find(stateObj);
const_iterator find(StateObject* stateObj) const {
return const_cast<StateBackendObjectRegistry*>(this)->find(stateObj);
}
iterator begin() { return m_entries.begin(); }
const_iterator begin() const { return m_entries.begin(); }
iterator end() { return m_entries.end(); }
const_iterator end() const { return m_entries.end(); }
iterator begin() { return m_backendObjects.begin(); }
const_iterator begin() const { return m_backendObjects.begin(); }
iterator end() { return m_backendObjects.end(); }
const_iterator end() const { return m_backendObjects.end(); }
void CollectGarbageIfNeeded() {
++m_gcTick;
@@ -88,6 +73,19 @@ namespace MobileGL::MG_Backend::DirectGLES {
void CollectGarbageNow() { CollectGarbage(); }
private:
bool IsAlive(StateObject* stateObj) const {
const auto trackedStateIt = m_stateRefs.find(stateObj);
if (trackedStateIt == m_stateRefs.end()) {
return false;
}
return !trackedStateIt->second.expired();
}
void EraseByKey(StateObject* stateObj) {
m_stateRefs.erase(stateObj);
m_backendObjects.erase(stateObj);
}
void CollectGarbage() {
if (m_isCollecting) {
return;
@@ -96,15 +94,16 @@ namespace MobileGL::MG_Backend::DirectGLES {
m_isCollecting = true;
Vector<StateObject*> staleKeys;
staleKeys.reserve(m_entries.size());
for (const auto& [stateKey, entry] : m_entries) {
if (entry.stateRef.expired()) {
staleKeys.reserve(m_stateRefs.size());
for (const auto& [stateKey, stateWeakRef] : m_stateRefs) {
if (stateWeakRef.expired()) {
staleKeys.push_back(stateKey);
}
}
for (auto* stateKey : staleKeys) {
m_entries.erase(stateKey);
m_stateRefs.erase(stateKey);
m_backendObjects.erase(stateKey);
}
m_isCollecting = false;
@@ -112,7 +111,8 @@ namespace MobileGL::MG_Backend::DirectGLES {
private:
static constexpr Uint32 kGCInterval = 1024;
BackendMap m_entries;
StateRefMap m_stateRefs;
BackendMap m_backendObjects;
Uint32 m_gcTick = 0;
Bool m_isCollecting = false;
};
@@ -120,43 +120,6 @@ namespace MobileGL::MG_Backend::DirectGLES {
namespace BufferImpl {
const GLenum TempBufferTarget = GL_ARRAY_BUFFER;
// --- Buffer-mutation epoch -------------------------------------------------
// Manager-wide monotonic counter: it moves whenever ANY buffer resource may
// have gone from draw-clean to dirty. Draw-path memos read it once per pass
// (CurrentBufferMutationEpoch, acquire), re-run their IsBufferDrawClean
// probes only when it moved, and stamp the PRE-pass value after a pass in
// which every probe came up clean - so a concurrent bump lands strictly
// after the stamped value and forces a re-probe on the next pass no matter
// how the probe interleaved with the mutation. Conservative-correct: a bump
// never skips work, it only re-runs the probes once.
//
// Every clean->dirty transition path bumps it (BumpBufferMutationEpoch,
// release, AFTER the mutation lands so an acquire reader that still sees
// the old epoch cannot have missed the mutation):
// * the frontend BufferBackendOps table - Respecify, SubData,
// FlushMappedRange, AcquirePersistentMap, ReadbackFromGpu, OnDestroy -
// which every frontend change-serial bump and every pending-range
// queueing reaches while ops are registered (upload, orphan/respecify,
// map flush/unmap writeback, persistent-map adoption, delete/pooling);
// * backend-initiated shadow writebacks that bump the frontend change
// serial without an op: transform-feedback capture readback
// (XfbImpl::ReadbackCapturedRanges and the scatter path) and every
// pack-PBO WritebackFromBackend site (glReadPixels/glGetTexImage);
// * RegisterBufferBackendOps/UnregisterBufferBackendOps - while ops are
// unregistered, frontend writes advance serials silently, so both edges
// of that window re-open every memo;
// * OnBackendContextDestroyed - the buffer context generation moved, so
// every previously clean resource is invalid.
// NOT bumped (cleanliness provably unchanged): MarkGpuWritten (the backend
// copy is authoritative; IsBufferDrawClean does not consult it),
// NotifyContentWrite on a GPU-resident buffer (persistent-mapped resources
// are clean by construction), and EnsureBufferResource itself (it only
// repairs toward clean). A non-persistent map (draws on it are GL errors
// the frontend rejects) sets IsMapped without an op; persistent maps reach
// AcquirePersistentMap or (FLUSH_EXPLICIT) publish only via FlushMappedRange.
Uint64 CurrentBufferMutationEpoch();
void BumpBufferMutationEpoch();
// The DirectGLES storage behind one frontend buffer. Owned (refcounted) by
// the frontend BufferObject; immediate BufferBackendOps keep it current, so
// draw-time "sync" reduces to ensuring the storage exists.
@@ -182,12 +145,6 @@ namespace MobileGL::MG_Backend::DirectGLES {
Bool pendingRespecify = false;
VecRange1D pendingRanges;
std::mutex pendingMutex;
// Buffer-mutation epoch (see CurrentBufferMutationEpoch) at which this
// resource last probed IsBufferDrawClean == true, 0 = never (epochs start
// at 1). Written only on the draw thread; per-draw resource consumers
// (the UBO binding walk) skip the probe while their pre-pass epoch read
// matches, exactly like the per-VAO memo stamps.
Uint64 drawCleanEpoch = 0;
// Zero-copy coherent persistent map (EXT_buffer_storage): the GL store is
// immutable, persistently+coherently mapped, and persistentPtr is what the app
// (and the frontend PipeResource) write into directly. While set, draw-time
@@ -213,17 +170,6 @@ namespace MobileGL::MG_Backend::DirectGLES {
GLESBufferResource* EnsureBufferResource(const SharedPtr<MG_State::GLState::BufferObject>& bufferObject);
// Existing resource or nullptr; performs no GL calls.
GLESBufferResource* GetBufferResource(MG_State::GLState::BufferObject* bufferObject);
// True when EnsureBufferResource(frontend) would provably fall straight through
// every branch and do no work — i.e. `resource` is still the frontend's own
// resource, its id belongs to the live ES context, and either it is the
// zero-copy coherent persistent store (draw-time sync is a no-op by design) or
// the storage is initialized at the right size with no pending ops and a synced
// change serial while the buffer is not mapped (an active map may owe a
// per-draw persistent-range push, so it always takes the full path).
// `frontend` must be non-null and alive; the caller guarantees that by holding
// (or shadowing something that holds) a SharedPtr to it. Enables the per-VAO
// resolved-buffers memo to skip EnsureBufferResource on clean static buffers.
Bool IsBufferDrawClean(const MG_State::GLState::BufferObject* frontend, const GLESBufferResource* resource);
// Deletes GL buffers whose owning frontend objects died (possibly on a
// thread without a current ES context). Called from draw-time sync.
@@ -309,104 +255,38 @@ namespace MobileGL::MG_Backend::DirectGLES {
Uint GetBackendVertexArrayId() const { return m_backendVAOId; }
void Bind() const;
// Draw-path memo of SyncNeccessaryBuffers' attribute walk for this VAO: the
// distinct enabled-attribute buffers (deduped) and the index buffer, resolved
// to their backend resources once. Valid while the VAO's config version is
// unchanged — every attach/enable/disable/format mutation bumps it (the same
// invariant SyncToBackend's gate already leans on), and the VAO's attribute
// SharedPtrs pin each memoed frontend buffer for exactly that long, so the raw
// pointers cannot dangle on a hit. Per-buffer cleanliness is NOT memoed here:
// each hit re-checks IsBufferDrawClean (resource identity, context generation,
// pending ops, change serial) and falls back to EnsureBufferResource for just
// the dirty entries via their attribute index. The IBO entry is keyed on the
// slot's bound-object identity instead (its slot version is a wrapping Uint16
// and is not covered by the config version).
struct ResolvedDrawBuffers {
struct Entry {
MG_State::GLState::BufferObject* frontend = nullptr;
BufferImpl::GLESBufferResource* resource = nullptr;
Uint8 attribIndex = 0;
};
Bool valid = false;
Uint32 configVersion = 0;
Uint count = 0;
Array<Entry, MG_State::GLState::VertexArrayObject::MAX_VERTEX_ATTRIBS> entries;
MG_State::GLState::BufferObject* iboFrontend = nullptr;
BufferImpl::GLESBufferResource* iboResource = nullptr;
// Buffer-mutation epoch (BufferImpl::CurrentBufferMutationEpoch) at which
// the LAST probe pass found every entry / the IBO clean; 0 = not stamped
// (epochs start at 1). While a stamp matches the pre-pass epoch read, the
// probes are skipped outright: any path that can dirty ANY buffer bumps
// the epoch (the exhaustive site list lives at the epoch declaration).
// The IBO stamp is only trusted together with the bound-object identity
// compare - the VAO's index slot can rebind with no epoch or config move.
Uint64 vboCleanEpoch = 0;
Uint64 iboCleanEpoch = 0;
};
ResolvedDrawBuffers& GetResolvedDrawBuffersMemo() { return m_resolvedDrawBuffers; }
// Memo for SyncCurrentVertexAttributeValues: which of a program's ACTIVE
// attribute locations lack an enabled array in this VAO (those read the
// context's current generic value instead of a buffer). Keyed on the VAO
// config version (enable/disable bumps it) and the program's active-location
// mask. Hosted per twin — the former function-static single entry missed on
// every draw once the app cycled VAOs, re-reading the cold attribute slots.
struct PendingAttribValueMask {
Bool valid = false;
Uint32 configVersion = 0;
Uint32 activeMask = 0;
Uint32 pendingMask = 0;
};
PendingAttribValueMask& GetPendingAttribValueMaskMemo() { return m_pendingAttribValueMask; }
private:
ResolvedDrawBuffers m_resolvedDrawBuffers;
PendingAttribValueMask m_pendingAttribValueMask;
Uint m_backendVAOId = 0;
Array<Uint, MG_State::GLState::VertexArrayObject::MAX_VERTEX_ATTRIBS> m_clientAttributeBufferIds;
// Attribs the frontend has Enabled but that have no source at all (no buffer object
// and NULL client pointer). GL keeps such attribs latently enabled, but Adreno's ES
// driver treats them as client arrays and memcpys from address 0 at draw time
// (SIGSEGV), so they are kept disabled on the backend VAO until they gain a source.
Uint32 m_forceDisabledAttribsMask = 0;
Bool m_isInitialized = false;
Uint16 m_syncedIndexBufferVersion = 0;
// Aggregate gate over the per-attribute walk below: the frontend bumps its config
// version on every per-attribute version bump (the three Bump*Version functions are
// its only writers), so an unchanged config version proves every per-attribute
// compare in SyncToBackend would come up clean. The index-buffer slot has its own
// version and is NOT covered. The Bool (not a sentinel value) marks "never synced".
Bool m_hasSyncedConfigVersion = false;
Uint32 m_syncedConfigVersion = 0;
Array<MG_State::GLState::VertexAttributeVersion, MG_State::GLState::VertexArrayObject::MAX_VERTEX_ATTRIBS>
m_syncedAttributeVersions;
};
extern StateBackendObjectRegistry<MG_State::GLState::VertexArrayObject, BackendVertexArrayObject>
g_backendVertexArrayObjects;
// Shadowed glBindVertexArray: every backend VAO bind goes through here so a
// draw's second bind of the same VAO (SyncToBackend, then PrepareForDraw's
// re-bind) reaches the driver once. Invalidate whenever the ES context is
// replaced - ids restart and the resting binding is 0 again.
void BindBackendVAOId(Uint id);
void InvalidateVAOBindingCache();
// ES resets the binding to 0 when the currently bound VAO is deleted.
void NoteVAOIdDeleted(Uint id);
} // namespace VertexArrayImpl
namespace TextureImpl {
inline Bool IsSupportedTextureTarget(TextureTarget target) {
// Every desktop-only target is stored on an ES one; see MapToBackendTextureTarget.
(void)target;
return true;
// Rectangle textures need non-normalized sampling ES cannot express; everything else is
// either native or emulated (1D -> 2D with height 1, 1D array -> 2D array, see
// MapToBackendTextureTarget). SPIRV-Cross already emits the matching ESSL samplers and
// coordinate padding for 1D/1D-array shaders.
return target != TextureTarget::TextureRectangle;
}
// ES has none of the desktop-only targets: 1D textures are stored as 2D (height 1), 1D
// arrays as 2D arrays (height 1, layers in depth), and rectangle textures as plain 2D -
// they are single-level and already clamp, so only the non-normalized coordinates differ.
// Must match the shader-side emulation: SPIRV-Cross handles 1D/1D-array itself, and
// ShaderCompiler::LowerRectImages rewrites rectangle images (declining any module
// whose lookups are not integer-coordinate, which SPIRV-Cross then still rejects).
// ES has no 1D targets: 1D textures are stored as 2D (height 1) and 1D arrays as 2D arrays
// (height 1, layers in depth). Must match SPIRV-Cross's ES 1D-as-2D shader emulation.
inline TextureTarget MapToBackendTextureTarget(TextureTarget target) {
switch (target) {
case TextureTarget::Texture1D:
case TextureTarget::TextureRectangle:
return TextureTarget::Texture2D;
case TextureTarget::Texture1DArray:
return TextureTarget::Texture2DArray;
@@ -422,7 +302,6 @@ namespace MobileGL::MG_Backend::DirectGLES {
inline GLenum ConvertTextureUploadTargetToBackendGLEnum(TextureUploadTarget uploadTarget) {
switch (uploadTarget) {
case TextureUploadTarget::Texture1D:
case TextureUploadTarget::TextureRectangle:
return GL_TEXTURE_2D;
case TextureUploadTarget::Texture1DArray:
return GL_TEXTURE_2D_ARRAY;
@@ -486,38 +365,6 @@ namespace MobileGL::MG_Backend::DirectGLES {
void Bind(GLenum target, Uint unit = TempTextureUnit);
Uint GetBackendTextureId() const;
// Aggregate first-level clean gate for the per-draw trio
// SyncTextureParamsToBackend + SyncBuiltinSamplerToBackend +
// SyncMipmapsToBackend: EXACTLY the conjunction of their own early-outs
// (params version == synced params version; builtin-sampler version ==
// synced sampler version; and SyncMipmapsToBackend's cheap gate - stamped
// trio + content version + Mipmap storage). True means each of the three
// would provably return without work, so the caller may skip the calls;
// false only falls through to the three calls, whose own gates re-decide
// individually - this gate must never be MORE permissive than they are.
// `contextId`/`samplingGeneration` are the frontend context's current
// values, hoisted by the caller so a per-draw list walk reads them once
// instead of per texture. `t` must be the live frontend texture.
Bool IsDrawSyncClean(const MG_State::GLState::ITextureObject* t, Uint64 contextId,
Uint64 samplingGeneration) const {
if (!m_isInitialized || m_syncedShapeContextId == 0 || m_syncedShapeContextId != contextId ||
m_syncedShapeGeneration != samplingGeneration) {
return false;
}
const Uint16 paramsVersion = t->GetTextureParamsVersion();
if (m_syncedShapeParamsVersion != paramsVersion || m_syncedTextureParamsVersion != paramsVersion) {
return false;
}
if (m_syncedContentVersion == 0 || m_syncedContentVersion != t->GetContentVersion()) {
return false;
}
const auto& samplerObject = t->GetSamplerObject();
if (!samplerObject || m_syncedSamplerVersion != samplerObject->GetVersion()) {
return false;
}
return t->GetStorageType() == TextureStorageType::Mipmap;
}
private:
void RecreateBackendTexture();
@@ -529,25 +376,6 @@ namespace MobileGL::MG_Backend::DirectGLES {
Bool m_imageBindableStorageRequired = false;
Bool m_backendStorageImmutable = false;
StateTextureBasicInfo m_prevTextureInfo;
// Frontend content version at the last completed mipmap sync. The per-draw
// clean probe compares this before rebuilding shape info and scanning
// per-level dirty flags; 0 never matches a real version (they start at 1).
Uint64 m_syncedContentVersion = 0;
// First-level clean gate for SyncMipmapsToBackend, checked before even the
// IsComplete()/shape-probe walk. Valid only as a trio with the content and
// texture-params versions: the context's sampling-resolution generation moves on
// EVERY texture-shape mutation (BumpShapeVersion is the only writer of shape and
// unconditionally bumps it), the content version on every CPU pixel mutation, and
// the params version covers SetSamples/SetFixedSampleLocations, which bump neither
// of the other two but feed the shape probe. The context id pins the generation to
// the context that produced it - generations restart at 0 with a new context, and a
// texture is owned by exactly one context (share groups are not implemented), so a
// mutation can never happen under a context this key does not name. 0 = never
// stamped (real context ids start at 1). Backend-side invalidation rides on
// m_isInitialized: RequireImageBindableStorage and RecreateBackendTexture clear it.
Uint64 m_syncedShapeContextId = 0;
Uint64 m_syncedShapeGeneration = 0;
Uint16 m_syncedShapeParamsVersion = 0;
SamplerParameters m_cacheSamplerParameters;
UintVec2 m_cacheLodRange = {0, 1000};
FloatVec4 m_cacheBorderColor = {0.0f, 0.0f, 0.0f, 0.0f};
@@ -606,28 +434,6 @@ namespace MobileGL::MG_Backend::DirectGLES {
this array could be provided as data directly to ES `glDrawBuffers` function
*/
GLenum m_backendDrawBuffers[MG_State::GLState::FramebufferObject::MAX_DRAW_BUFFERS] = {GL_NONE};
static constexpr Uint MAX_COLOR_ATTACHMENT_SLOTS =
static_cast<Uint>(FramebufferAttachmentType::Color31) -
static_cast<Uint>(FramebufferAttachmentType::Color0) + 1;
/* Where each frontend GL_COLOR_ATTACHMENTn image physically lives in the backend ES
framebuffer, as a GL_COLOR_ATTACHMENTm enum. ES only accepts glDrawBuffers bufs[s] ==
GL_COLOR_ATTACHMENTs, so a GL draw-buffer slot s naming attachment a forces a's image
under backend slot s. This table is the single owner of that decision and is kept a
PERMUTATION of the backend colour slots: every other attachment keeps its identity
slot when that slot survived, and is parked on the lowest free slot when it did not.
Deriving the point per-query from the draw-buffer array instead handed the identity
point to any attachment that was not a draw buffer - i.e. exactly the point a
relocated draw buffer had just taken over. The permutation is only true of the
PHYSICAL framebuffer because the attachment loop detaches a point whose frontend
owner is empty; do not remove that detach. */
GLenum m_backendColorSlots[MAX_COLOR_ATTACHMENT_SLOTS] = {GL_NONE};
/* Rebuild m_backendColorSlots from the frontend draw-buffer array. Returns true when any
attachment moved, i.e. when the physical attachments and the memoised read buffer have
to be re-applied. */
Bool RecomputeBackendColorSlots(
const MG_State::GLState::FramebufferObject::FramebufferAttachmentArray& stateDrawBuffers);
FramebufferAttachmentType m_frontendReadBuffer = FramebufferAttachmentType::Color0;
GLenum m_backendReadBuffer = GL_COLOR_ATTACHMENT0;
@@ -637,27 +443,11 @@ namespace MobileGL::MG_Backend::DirectGLES {
extern StateBackendObjectRegistry<MG_State::GLState::FramebufferObject, BackendFramebufferObject>
g_backendFramebufferObjects;
// True when the read buffer names a fixed-point (norm/snorm) attachment that the
// backend actually stores in a floating-point format. GL clamps a read from a
// fixed-point colour buffer to [0,1] (GL_CLAMP_READ_COLOR defaults to
// GL_FIXED_ONLY); the substituted float storage would not, so the readback path
// has to apply the clamp itself.
Bool IsFixedPointFallbackReadAttachment();
// What SyncCurrentFBO last pushed for each target, as a (binding, object, revision)
// triple; it re-syncs unless all three still match. Stamped by SyncCurrentFBO and
// ForceBindCurrentFBO, cleared by InvalidateFramebufferBindingCache. The three are
// only meaningful together - see SyncCurrentFBO.
//
// The binding slot's own version, which changes whenever a different object is bound
// to this target. Distinguishes a rebind from an in-place edit, and keeps the raw
// pointer below from matching an address the allocator recycled for a new FBO.
extern Array<Uint16, SizeT(FramebufferTarget::FramebufferTargetCount)> g_fboSyncedSlotVersions;
extern Array<Uint16, SizeT(FramebufferTarget::FramebufferTargetCount)> g_fboBindVersions;
// Tracks the bound FBO's object version (bumped on any attachment/drawbuffer change)
// per target: re-attaching textures or changing draw buffers on an already-bound FBO
// must re-sync it even when the binding-slot version has not moved.
extern Array<Uint16, SizeT(FramebufferTarget::FramebufferTargetCount)> g_fboSyncedObjectVersions;
// Which object was synced. Raw and never dereferenced: only compared for identity.
extern Array<MG_State::GLState::FramebufferObject*, SizeT(FramebufferTarget::FramebufferTargetCount)>
g_fboSyncedObjects;
@@ -753,10 +543,6 @@ namespace MobileGL::MG_Backend::DirectGLES {
void InvalidatePackStateCache();
} // namespace PixelStoreImpl
namespace SamplerImpl {
class BackendSamplerObject; // for PrgramImpl's sampler-pass memo rows below
}
// Image uniforms take their unit from the layout(binding=N) qualifier baked into
// the transpiled ESSL; unlike samplers they must not (and in ES cannot) be
// assigned through glUniform1i.
@@ -795,49 +581,6 @@ namespace MobileGL::MG_Backend::DirectGLES {
Int backendLocation = -1;
GLenum uniformType = 0;
Int lastAssignedUnit = -1;
// Location of this sampler's emulated GL_TEXTURE_LOD_BIAS uniform
// (PrgramImpl::EmulateTextureLodBias), -1 when the shader has none.
// lastAssignedLodBias mirrors the value the program currently holds,
// so an unbiased shader issues no per-draw glUniform1f at all.
Int lodBiasLocation = -1;
Float lastAssignedLodBias = 0.0f;
};
// Memo of the whole per-draw sampler-uniform pass (glUniform1i unit
// assignments, lod-bias uniform, raw-depth-fetch substitution and the
// per-unit sampler-object binds) in BindCurrentProgramWithResources.
// The pass is a pure function of the keys below, and its only driver-side
// effect is the sampler binding of each sampled unit, so replaying it as
// "do nothing" additionally requires those bindings to still be on the
// driver - the per-entry row compare against g_boundSamplersCache (the
// shadow every sampler bind in this backend already routes through).
//
// Invalidation enumeration:
// * sampler-uniform unit assignment (glUniform1i) and uniform-block
// binding edits -> frontend backendStateVersion;
// * any texture/sampler bind moving on any unit (incl. the high-water
// mark moving) -> unitBindingsEpoch;
// * any sampler parameter (incl. lod bias, compare mode) or texture
// shape/format change -> samplingGeneration;
// * another frontend context -> contextId (never-reused id);
// * ES context recreation -> textureContextGeneration;
// * relink / backend program rebuild -> SyncToBackend resets `valid`
// (it rebuilds m_samplerUniformBindings, whose lastAssignedUnit /
// lastAssignedLodBias dedup state this memo leans on);
// * any other writer moving a sampled unit's sampler binding
// (BindCurrentUnitSamplers on a unit-sampler change, scratch binds)
// -> the row snapshot compare.
struct SamplerPassMemo {
static constexpr SizeT kMaxEntries = 16;
Bool valid = false;
Uint8 count = 0;
Uint64 contextId = 0;
Uint64 unitBindingsEpoch = 0;
Uint64 samplingGeneration = 0;
Uint32 backendStateVersion = 0;
Uint textureContextGeneration = 0;
Array<Uint8, kMaxEntries> units{};
Array<SamplerImpl::BackendSamplerObject*, kMaxEntries> rows{};
};
BackendProgramObjectImpl();
@@ -849,14 +592,9 @@ namespace MobileGL::MG_Backend::DirectGLES {
void SetDrawID(Uint32 drawId) const;
Int GetIndirectParamsBinding() const { return m_indirectParamsBinding; }
Uint GetBackendProgramId() const { return m_backendProgramId; }
// False when the last SyncToBackend could not produce a usable program (a
// shader failed to transpile or compile, or the link itself failed). Use()
// must not leave the previously bound program current in that case.
Bool IsBackendProgramUsable() const { return m_backendProgramUsable; }
Uint GetBackendGlobalUBOId() const { return m_backendGlobalUBOId; }
Uint32 GetSnormFallbackClampOutputMask() const { return m_snormFallbackClampOutputMask; }
Uint32 GetUnormFallbackClampOutputMask() const { return m_unormFallbackClampOutputMask; }
Uint GetFragColorBroadcastCount() const { return m_fragColorBroadcastCount; }
Bool HasGlobalUboBlock() const { return m_globalUboBackendBlockIndex >= 0; }
const Vector<Int>& GetUniformBlockBackendIndices() const { return m_uniformBlockBackendIndices; }
@@ -868,7 +606,6 @@ namespace MobileGL::MG_Backend::DirectGLES {
// reflected size when the transpiled block pads differently).
Int GetGlobalUboBackendBlockSize() const { return m_globalUboBackendBlockSize; }
BufferImpl::UboRingAllocation& GetGlobalUboRingAllocation() { return m_globalUboRingAllocation; }
SamplerPassMemo& GetSamplerPassMemo() { return m_samplerPassMemo; }
// Frontend link version this backend program (and its resource caches) was
// built from; a mismatch means every link-derived cache here is stale.
Uint32 GetSyncedLinkVersion() const { return m_syncedLinkVersion; }
@@ -884,11 +621,7 @@ namespace MobileGL::MG_Backend::DirectGLES {
Int m_indirectParamsBinding = -1;
Uint32 m_snormFallbackClampOutputMask = 0;
Uint32 m_unormFallbackClampOutputMask = 0;
// Draw buffers a legacy gl_FragColor write has to reach (see
// PrgramImpl::BroadcastLegacyFragColor); 1 keeps the plain single-output shader.
Uint m_fragColorBroadcastCount = 1;
Bool m_isInitialized = false;
Bool m_backendProgramUsable = false;
Int m_globalUboBackendBlockIndex = -1;
Int m_globalUboBackendBlockSize = 0;
@@ -897,15 +630,10 @@ namespace MobileGL::MG_Backend::DirectGLES {
Uint32 m_lastUploadedGlobalUboVersion = ~0u;
BufferImpl::UboRingAllocation m_globalUboRingAllocation;
Uint32 m_syncedLinkVersion = ~0u;
SamplerPassMemo m_samplerPassMemo;
};
extern Uint32 g_snormFallbackClampOutputMask;
extern Uint32 g_unormFallbackClampOutputMask;
// Draw buffers the current draw framebuffer enables. Like the clamp masks above it
// is framebuffer state that the shader has to be compiled against, so a program
// whose snapshot no longer matches is relinked.
extern Uint g_fragColorBroadcastCount;
// Backend id of the last glUseProgram issued through this backend; lets Use()
// skip redundant rebinds. Reset to 0 wherever glUseProgram(0) is issued or the
// ES context is recreated.
+30 -255
View File
@@ -22,9 +22,6 @@
#include <MG_Util/Math/SmallFloat.h>
#include <cmath>
#include <cctype>
#include <cstring>
#include <regex>
namespace MobileGL::MG_Backend::DirectGLES {
namespace {
@@ -48,40 +45,15 @@ namespace MobileGL::MG_Backend::DirectGLES {
return options;
}
Flags<PixelFormatNormalizeOptionBit>
GetRuntimeFallbackNormalizeOptions(GLenum requestedInternalFormat,
Flags<PixelFormatNormalizeOptionBit> extraOptions) {
Flags<PixelFormatNormalizeOptionBit> GetRuntimeFallbackNormalizeOptions(GLenum requestedInternalFormat) {
using namespace MG_Util::TextureFormatProcessor;
const Flags<PixelFormatNormalizeOptionBit> forcedOptions = GetApplicablePixelFormatNormalizeOptions(
requestedInternalFormat, GetForcedPixelFormatNormalizeOptions() | extraOptions);
const Flags<PixelFormatNormalizeOptionBit> forcedOptions =
GetApplicablePixelFormatNormalizeOptions(requestedInternalFormat, GetForcedPixelFormatNormalizeOptions());
if (forcedOptions) {
return forcedOptions;
}
return GetApplicablePixelFormatNormalizeOptions(
requestedInternalFormat, GetDriverPixelFormatNormalizeOptions() | extraOptions);
}
// Multisample textures can only ever be rendered into, never uploaded to, so a fallback
// format for them has to stay colour-renderable - a three-channel float fallback is a legal
// ES texture format but not a legal multisample storage format. Widening to four channels
// is safe here precisely because there is no transfer path that would have to expand
// three-channel client data, and the alpha the draw writes for a three-channel source is
// already the 1.0 the frontend format implies.
Bool TargetRequiresRenderableFormat(SizeT targetIndex) {
return targetIndex == static_cast<SizeT>(TextureTarget::Texture2DMultisample) ||
targetIndex == static_cast<SizeT>(TextureTarget::Texture2DMultisampleArray);
}
Flags<PixelFormatNormalizeOptionBit> GetRenderTargetNormalizeOptions(SizeT targetIndex) {
Flags<PixelFormatNormalizeOptionBit> options;
if (!TargetRequiresRenderableFormat(targetIndex)) {
return options;
}
options |= PixelFormatNormalizeOptionBit::NoThreeChannelRenderTarget;
if (!g_GLESCapabilities.SupportsRenderSnorm || !g_GLESCapabilities.SupportsNorm16Texture) {
options |= PixelFormatNormalizeOptionBit::NoSnorm16RenderTarget;
}
return options;
return GetApplicablePixelFormatNormalizeOptions(requestedInternalFormat,
GetDriverPixelFormatNormalizeOptions());
}
Bool HasCachedFormatCapability(TextureInternalFormat internalFormat,
@@ -141,8 +113,7 @@ namespace MobileGL::MG_Backend::DirectGLES {
const GLenum requestedInternalFormat = MG_Util::ConvertTextureInternalFormatToGLEnum(internalFormat);
Flags<PixelFormatNormalizeOptionBit> options;
if (!pActiveBackendObject || ShouldUseCaveatFormat(internalFormat, targetIndex)) {
options = GetRuntimeFallbackNormalizeOptions(requestedInternalFormat,
GetRenderTargetNormalizeOptions(targetIndex));
options = GetRuntimeFallbackNormalizeOptions(requestedInternalFormat);
}
NormalizePixelFormat(requestedInternalFormat, options, outInternalFormat, outFormat, outType);
}
@@ -177,22 +148,6 @@ namespace MobileGL::MG_Backend::DirectGLES {
Bool ShouldUseCaveatRenderbufferFormat(TextureInternalFormat internalFormat) {
return ShouldUseCaveatFormat(internalFormat, GetRenderbufferFormatCapabilityTargetIndex());
}
Bool BackendTextureFormatAddsAlpha(TextureInternalFormat internalFormat, TextureTarget target) {
const SizeT targetIndex =
target == TextureTarget::Unknown ? kFormatCapabilityTargetCount : GetFormatCapabilityTargetIndex(target);
if (!TargetRequiresRenderableFormat(targetIndex)) {
return false;
}
if (pActiveBackendObject && !ShouldUseCaveatFormat(internalFormat, targetIndex)) {
return false;
}
const GLenum requestedInternalFormat = MG_Util::ConvertTextureInternalFormatToGLEnum(internalFormat);
const Flags<PixelFormatNormalizeOptionBit> options =
GetRuntimeFallbackNormalizeOptions(requestedInternalFormat,
GetRenderTargetNormalizeOptions(targetIndex));
return static_cast<Bool>(options & PixelFormatNormalizeOptionBit::NoThreeChannelRenderTarget);
}
} // namespace TextureImpl
namespace PrgramImpl {
String ProcessOutColorLocations(const String& glslCode) {
@@ -321,55 +276,6 @@ namespace MobileGL::MG_Backend::DirectGLES {
return glslCode;
}
String BroadcastLegacyFragColor(String glslCode, GLenum shaderType, Uint drawBufferCount) {
#ifdef TRACY_ENABLE
ZoneScopedC(TRACY_ZONECOLOR_BACKEND);
#endif
// The name is the marker: ShaderSourceProcessor only emits it when the source
// wrote gl_FragColor, and such a shader can have no other output.
static const char* const kLoweredName = "mg_FragColor";
if (shaderType != GL_FRAGMENT_SHADER || drawBufferCount <= 1) {
return glslCode;
}
static const std::regex declRegex(
R"(layout\s*\(\s*location\s*=\s*0\s*\)\s*out\s+((?:lowp|mediump|highp)\s+)?vec4\s+mg_FragColor\s*;)");
std::smatch declMatch;
if (!std::regex_search(glslCode, declMatch, declRegex)) {
return glslCode;
}
const String precision = declMatch[1].matched ? declMatch[1].str() : String();
String replicaDecls;
String replicaCopies;
for (Uint location = 1; location < drawBufferCount; ++location) {
const String name = String(kLoweredName) + "_" + std::to_string(location);
replicaDecls += "\nlayout(location = " + std::to_string(location) + ") out " + precision + "vec4 " +
name + ";";
replicaCopies += "\n " + name + " = " + kLoweredName + ";";
}
static const std::regex mainRegex(R"(void\s+main\s*\([^)]*\)\s*\{)");
std::smatch mainMatch;
if (!std::regex_search(glslCode, mainMatch, mainRegex)) {
return glslCode;
}
SizeT bracePos = static_cast<SizeT>(mainMatch.position(0) + mainMatch.length(0) - 1);
Int depth = 0;
for (SizeT pos = bracePos; pos < glslCode.size(); ++pos) {
if (glslCode[pos] == '{') {
++depth;
} else if (glslCode[pos] == '}') {
--depth;
if (depth == 0) {
glslCode.insert(pos, replicaCopies + "\n");
break;
}
}
}
glslCode.insert(static_cast<SizeT>(declMatch.position(0)) + declMatch[0].str().size(), replicaDecls);
return glslCode;
}
String ForceFlatIntegerVaryings(const String& glslCode, GLenum shaderType) {
#ifdef TRACY_ENABLE
ZoneScopedC(TRACY_ZONECOLOR_BACKEND);
@@ -437,166 +343,40 @@ namespace MobileGL::MG_Backend::DirectGLES {
return result;
}
namespace {
// How a lookup carries its level of detail, and how many arguments it takes
// before the optional bias.
struct LodLookupForm {
const char* name;
Int requiredArgs; // arguments before the optional bias (implicit form)
Int explicitLodArg; // index of the explicit LOD argument, -1 for implicit
};
// texelFetch* is deliberately absent: an integer fetch names its level directly
// and takes no LOD bias. textureGather has no bias either. textureGrad* derives
// the LOD from gradients and offers no argument to fold a bias into, so it is
// left alone rather than rewritten incorrectly.
constexpr LodLookupForm LOD_LOOKUP_FORMS[] = {
{"textureProjLodOffset", 0, 2}, {"textureProjOffset", 4, -1}, {"textureProjLod", 0, 2},
{"textureLodOffset", 0, 2}, {"textureOffset", 3, -1}, {"textureProj", 2, -1},
{"textureLod", 0, 2}, {"texture", 2, -1},
};
// Sampler types with no mip chain, or whose GLSL lookups have no bias overload
// at all (the array-shadow forms), so nothing can or should be folded in.
Bool IsBiasableSamplerType(const String& samplerType) {
if (samplerType.find("MS") != String::npos) return false; // multisample
if (samplerType.find("Buffer") != String::npos) return false; // texture buffer
if (samplerType.find("Rect") != String::npos) return false; // rectangle: no mips
if (samplerType == "sampler2DArrayShadow") return false;
if (samplerType == "samplerCubeArrayShadow") return false;
return true;
}
Bool IsIdentifierChar(char c) { return std::isalnum(static_cast<unsigned char>(c)) || c == '_'; }
// Byte offsets of the top-level argument separators and of the closing paren,
// starting from the '(' at openParen. Empty when the parentheses do not balance.
Vector<SizeT> SplitCallArguments(const String& code, SizeT openParen) {
Vector<SizeT> marks;
Int depth = 0;
for (SizeT i = openParen; i < code.size(); ++i) {
const char c = code[i];
if (c == '(' || c == '[') {
++depth;
} else if (c == ']') {
--depth;
} else if (c == ')') {
--depth;
if (depth == 0) {
marks.push_back(i);
return marks;
}
} else if (c == ',' && depth == 1) {
marks.push_back(i);
}
}
return {};
}
} // namespace
String EmulateTextureLodBias(const String& glslCode) {
String RemoveClipDistanceRedeclaration(const String& glslCode) {
#ifdef TRACY_ENABLE
ZoneScopedC(TRACY_ZONECOLOR_BACKEND);
#endif
if (glslCode.find("sampler") == String::npos || glslCode.find("texture") == String::npos) {
return glslCode;
}
// Adreno rejects any redeclaration of gl_ClipDistance/gl_CullDistance ("reserved
// built-in name") even with GL_EXT_clip_cull_distance required, but accepts plain
// usage of the builtin. Drop the desktop-style redeclaration line SPIRV-Cross
// prints; the "#extension GL_EXT_clip_cull_distance : require" line stays.
static const std::regex redeclarationRegex(
R"(^\s*(?:out|in)\s+(?:(?:high|medium|low)p\s+)?float\s+gl_(?:Clip|Cull)Distance\[[0-9]+\];\s*$)");
// Collect the mip-capable sampler uniforms this shader declares.
static const std::regex samplerDeclRegex(
R"(uniform\s+(?:(?:highp|mediump|lowp)\s+)?([iu]?sampler[A-Za-z0-9]*)\s+([A-Za-z_][A-Za-z0-9_]*)\s*;)");
UnorderedMap<String, String> samplerNames; // name -> bias uniform name
for (std::sregex_iterator it(glslCode.begin(), glslCode.end(), samplerDeclRegex), end; it != end; ++it) {
const String samplerType = (*it)[1].str();
if (!IsBiasableSamplerType(samplerType)) continue;
const String name = (*it)[2].str();
samplerNames.emplace(name, String(LOD_BIAS_UNIFORM_PREFIX) + name);
}
if (samplerNames.empty()) {
return glslCode;
}
String result;
result.reserve(glslCode.size());
SizeT lineStart = 0;
Bool firstLine = true;
while (lineStart <= glslCode.size()) {
SizeT lineEnd = glslCode.find('\n', lineStart);
const Bool lastLine = lineEnd == String::npos;
String line = glslCode.substr(lineStart, lastLine ? String::npos : lineEnd - lineStart);
// Rewrite the lookups. Right-to-left so earlier offsets stay valid, and only for
// samplers named directly as the first argument (SPIRV-Cross never produces an
// expression there for ES output, which has no separate sampler objects).
String result = glslCode;
Vector<String> usedSamplers;
for (SizeT scan = result.size(); scan-- > 0;) {
if (result[scan] != 't') continue;
if (scan > 0 && IsIdentifierChar(result[scan - 1])) continue;
const LodLookupForm* form = nullptr;
SizeT openParen = 0;
for (const auto& candidate : LOD_LOOKUP_FORMS) {
const SizeT nameLength = std::strlen(candidate.name);
if (result.compare(scan, nameLength, candidate.name) != 0) continue;
SizeT after = result.find_first_not_of(" \t", scan + nameLength);
if (after == String::npos || result[after] != '(') continue;
form = &candidate;
openParen = after;
if (!std::regex_match(line, redeclarationRegex)) {
if (!firstLine) {
result += '\n';
}
result += line;
firstLine = false;
}
if (lastLine) {
break;
}
if (form == nullptr) continue;
const Vector<SizeT> marks = SplitCallArguments(result, openParen);
if (marks.empty()) continue;
const SizeT argCount = marks.size();
const SizeT closeParen = marks.back();
// First argument must be one of our samplers.
const SizeT firstArgStart = result.find_first_not_of(" \t", openParen + 1);
SizeT firstArgEnd = marks.front();
while (firstArgEnd > firstArgStart && (result[firstArgEnd - 1] == ' ' || result[firstArgEnd - 1] == '\t')) {
--firstArgEnd;
}
if (firstArgStart == String::npos || firstArgEnd <= firstArgStart) continue;
const String samplerName = result.substr(firstArgStart, firstArgEnd - firstArgStart);
const auto samplerIt = samplerNames.find(samplerName);
if (samplerIt == samplerNames.end()) continue;
const String& biasName = samplerIt->second;
if (form->explicitLodArg >= 0) {
// Explicit LOD: the bias adds to it, as Vulkan does for
// OpImageSampleExplicitLod and as the CTS reference expects.
const SizeT lodIndex = static_cast<SizeT>(form->explicitLodArg);
if (argCount <= lodIndex) continue;
const SizeT lodStart = marks[lodIndex - 1] + 1;
const SizeT lodEnd = marks[lodIndex];
result.insert(lodEnd, String(") + ") + biasName + ")");
result.insert(lodStart, "((");
} else {
const SizeT required = static_cast<SizeT>(form->requiredArgs);
if (argCount == required) {
result.insert(closeParen, String(", ") + biasName);
} else if (argCount == required + 1) {
const SizeT biasStart = marks[argCount - 2] + 1;
result.insert(closeParen, String(") + ") + biasName + ")");
result.insert(biasStart, "((");
} else {
continue;
}
}
usedSamplers.push_back(samplerName);
}
if (usedSamplers.empty()) {
return glslCode;
}
// Declare the bias uniforms that were actually referenced, right after the
// sampler declaration line they belong to.
for (const auto& samplerName : usedSamplers) {
const String& biasName = samplerNames[samplerName];
if (result.find(String("float ") + biasName + ";") != String::npos) continue;
const std::regex declRegex(
R"(uniform\s+(?:(?:highp|mediump|lowp)\s+)?[iu]?sampler[A-Za-z0-9]*\s+)" + samplerName + R"(\s*;)");
std::smatch match;
if (!std::regex_search(result, match, declRegex)) continue;
const SizeT declEnd = static_cast<SizeT>(match.position(0)) + match[0].str().size();
result.insert(declEnd, String("\nuniform highp float ") + biasName + ";");
lineStart = lineEnd + 1;
}
return result;
}
} // namespace PrgramImpl
namespace Utils {
@@ -1107,11 +887,6 @@ namespace MobileGL::MG_Backend::DirectGLES {
}
}
}
if (pixelPackBufferObject) {
// WritebackFromBackend bumps change serials with no backend op; re-open
// the buffer draw-clean memos (once for the whole row loop).
BufferImpl::BumpBufferMutationEpoch();
}
return true;
}
} // namespace ReadbackImpl
+1 -24
View File
@@ -40,11 +40,6 @@ namespace MobileGL::MG_Backend::DirectGLES {
void GenerateRenderbufferFormatInfo(TextureInternalFormat internalFormat, GLenum* outInternalFormat,
GLenum* outFormat, GLenum* outType);
Bool ShouldUseCaveatTextureFormat(TextureInternalFormat internalFormat, TextureTarget target);
// True when the format the texture is actually created with has an alpha channel the
// frontend format does not (the three-channel multisample widening). GL reads such a
// channel back as 1.0, so any swizzle source of ALPHA has to be answered with ONE.
Bool BackendTextureFormatAddsAlpha(TextureInternalFormat internalFormat, TextureTarget target);
Bool ShouldUseCaveatRenderbufferFormat(TextureInternalFormat internalFormat);
} // namespace TextureImpl
@@ -109,26 +104,8 @@ namespace MobileGL::MG_Backend::DirectGLES {
String ClampNormFallbackOutputs(String glslCode, GLenum shaderType, Uint32 snormOutputMask,
Uint32 unormOutputMask);
String ForceFlatIntegerVaryings(const String& glslCode, GLenum shaderType);
// Legacy GLSL's gl_FragColor is broadcast to every enabled draw buffer (GL 4.6
// 15.2.3), but ShaderSourceProcessor lowers it to the single output mg_FragColor,
// which only ever reaches draw buffer 0. Replicates it across `drawBufferCount`
// outputs and copies the value into them at the end of main. A no-op for
// drawBufferCount <= 1, i.e. for everything but a framebuffer that actually
// enables several draw buffers, so the ordinary single-target shader is untouched.
String BroadcastLegacyFragColor(String glslCode, GLenum shaderType, Uint drawBufferCount);
String RemoveLayoutBinding(const String& glslCode);
// Prefix of the per-sampler float uniform that carries GL_TEXTURE_LOD_BIAS into
// the shader (see EmulateTextureLodBias); the suffix is the sampler's own name.
constexpr const char* LOD_BIAS_UNIFORM_PREFIX = "mg_lodBias_";
// ES has no per-texture/sampler LOD bias at all (GL_TEXTURE_LOD_BIAS is desktop
// only; Vulkan spells it VkSamplerCreateInfo::mipLodBias), so it has to reach the
// shader as a uniform and be folded into every lookup's level of detail. Declares
// one `uniform highp float mg_lodBias_<sampler>;` per mip-capable sampler and adds
// it to the bias / explicit-LOD argument of every lookup that takes one. Draws push
// the bound texture's (or sampler object's) value into it; a shader whose samplers
// all have a zero bias is therefore unaffected. Returns the source unchanged when
// there is nothing to rewrite.
String EmulateTextureLodBias(const String& glslCode);
String RemoveClipDistanceRedeclaration(const String& glslCode);
} // namespace PrgramImpl
namespace Utils {
@@ -18,7 +18,6 @@
#include "MG_Util/Texture/TextureFormatProcessor.h"
#include <Config.h>
#include <cmath>
#include <cstdlib>
#include <cstring>
@@ -41,11 +40,13 @@ namespace MobileGL::MG_Backend::DirectVulkan {
Bool IsLayeredTarget(TextureTarget target) {
return target == TextureTarget::Texture3D || target == TextureTarget::Texture1DArray ||
target == TextureTarget::Texture2DArray || target == TextureTarget::TextureCubeMap ||
target == TextureTarget::TextureCubeMapArray || target == TextureTarget::Texture2DMultisampleArray;
target == TextureTarget::TextureCubeMapArray ||
target == TextureTarget::Texture2DMultisampleArray;
}
Bool IsMultisampleTarget(TextureTarget target) {
return target == TextureTarget::Texture2DMultisample || target == TextureTarget::Texture2DMultisampleArray;
return target == TextureTarget::Texture2DMultisample ||
target == TextureTarget::Texture2DMultisampleArray;
}
Bool IsTextureBufferTarget(TextureTarget target) {
@@ -57,8 +58,8 @@ namespace MobileGL::MG_Backend::DirectVulkan {
GLenum normalizedInternalFormat = glFormat;
GLenum imageFormat = GL_RGBA;
GLenum imageType = GL_UNSIGNED_BYTE;
MG_Util::TextureFormatProcessor::NormalizePixelFormat(glFormat, PixelFormatNormalizeOptionBit::None,
&normalizedInternalFormat, &imageFormat, &imageType);
MG_Util::TextureFormatProcessor::NormalizePixelFormat(
glFormat, PixelFormatNormalizeOptionBit::None, &normalizedInternalFormat, &imageFormat, &imageType);
return imageFormat == GL_RED_INTEGER || imageFormat == GL_RG_INTEGER || imageFormat == GL_RGB_INTEGER ||
imageFormat == GL_RGBA_INTEGER;
}
@@ -79,7 +80,8 @@ namespace MobileGL::MG_Backend::DirectVulkan {
return caps;
}
FormatCapabilityFlags BuildVulkanCaps(TextureInternalFormat logicalFormat, TextureTarget target,
FormatCapabilityFlags BuildVulkanCaps(TextureInternalFormat logicalFormat,
TextureTarget target,
VkFormatFeatureFlags features) {
FormatCapabilityFlags caps;
const Bool isDepth = MG_Util::IsDepthFormatInternalFormat(logicalFormat);
@@ -98,7 +100,8 @@ namespace MobileGL::MG_Backend::DirectVulkan {
const Bool sampled = (features & VK_FORMAT_FEATURE_SAMPLED_IMAGE_BIT) != 0;
const Bool linearFilter = (features & VK_FORMAT_FEATURE_SAMPLED_IMAGE_FILTER_LINEAR_BIT) != 0;
const Bool colorRenderable = (features & VK_FORMAT_FEATURE_COLOR_ATTACHMENT_BIT) != 0;
const Bool depthStencilRenderable = (features & VK_FORMAT_FEATURE_DEPTH_STENCIL_ATTACHMENT_BIT) != 0;
const Bool depthStencilRenderable =
(features & VK_FORMAT_FEATURE_DEPTH_STENCIL_ATTACHMENT_BIT) != 0;
const Bool renderable = (isDepth || isStencil) ? depthStencilRenderable : colorRenderable;
if (sampled || renderable) {
@@ -195,20 +198,21 @@ namespace MobileGL::MG_Backend::DirectVulkan {
Bool HasNewCaveatFormatCaps(FormatCapabilityFlags nativeCaps, FormatCapabilityFlags fallbackCaps) {
for (FormatCapability capability : kReportedFormatCapabilities) {
if (HasFormatCapability(fallbackCaps, capability) && !HasFormatCapability(nativeCaps, capability)) {
if (HasFormatCapability(fallbackCaps, capability) &&
!HasFormatCapability(nativeCaps, capability)) {
return true;
}
}
return false;
}
void LogVulkanFormatCaveat(TextureInternalFormat logicalFormat, SizeT targetIndex,
void LogVulkanFormatCaveat(TextureInternalFormat logicalFormat,
SizeT targetIndex,
TextureInternalFormat fallbackFormat) {
MGLOG_D(
"Caveat: %s %s not fully supported. Reason: native Vulkan format is not fully supported. Fallback: %s",
GetFormatCapabilityTargetName(targetIndex).c_str(),
MG_Util::ConvertTextureInternalFormatToString(logicalFormat).c_str(),
MG_Util::ConvertTextureInternalFormatToString(fallbackFormat).c_str());
MGLOG_D("Caveat: %s %s not fully supported. Reason: native Vulkan format is not fully supported. Fallback: %s",
GetFormatCapabilityTargetName(targetIndex).c_str(),
MG_Util::ConvertTextureInternalFormatToString(logicalFormat).c_str(),
MG_Util::ConvertTextureInternalFormatToString(fallbackFormat).c_str());
}
Vector<Int> BuildSampleCounts(Int maxSamples) {
@@ -252,15 +256,15 @@ namespace MobileGL::MG_Backend::DirectVulkan {
for (SizeT targetIndex = 0; targetIndex < kFormatCapabilityTextureTargetCount; ++targetIndex) {
const auto target = static_cast<TextureTarget>(targetIndex);
const VkFormatFeatureFlags nativeFeatures = IsTextureBufferTarget(target)
? nativeProperties.bufferFeatures
: nativeProperties.optimalTilingFeatures;
const VkFormatFeatureFlags nativeFeatures =
IsTextureBufferTarget(target) ? nativeProperties.bufferFeatures
: nativeProperties.optimalTilingFeatures;
FormatCapabilityFlags nativeCaps = BuildVulkanCaps(logicalFormat, target, nativeFeatures);
cache.FullCaps[targetIndex][formatIndex] |= nativeCaps;
const VkFormatFeatureFlags fallbackFeatures = IsTextureBufferTarget(target)
? fallbackProperties.bufferFeatures
: fallbackProperties.optimalTilingFeatures;
const VkFormatFeatureFlags fallbackFeatures =
IsTextureBufferTarget(target) ? fallbackProperties.bufferFeatures
: fallbackProperties.optimalTilingFeatures;
FormatCapabilityFlags fallbackCaps = BuildVulkanCaps(logicalFormat, target, fallbackFeatures);
if (fallbackFormat != VK_FORMAT_UNDEFINED && fallbackFormat != nativeFormat) {
cache.CaveatCaps[targetIndex][formatIndex] |= fallbackCaps;
@@ -295,8 +299,9 @@ namespace MobileGL::MG_Backend::DirectVulkan {
cache.FullCaps[renderbufferTargetIndex][formatIndex] |= renderbufferCaps;
if (fallbackFormat != VK_FORMAT_UNDEFINED && fallbackFormat != nativeFormat) {
FormatCapabilityFlags fallbackRenderbufferCaps = BuildVulkanCaps(
logicalFormat, TextureTarget::Texture2D, fallbackProperties.optimalTilingFeatures);
FormatCapabilityFlags fallbackRenderbufferCaps =
BuildVulkanCaps(logicalFormat, TextureTarget::Texture2D,
fallbackProperties.optimalTilingFeatures);
fallbackRenderbufferCaps &= FormatCapability::Creatable;
if ((fallbackProperties.optimalTilingFeatures &
(VK_FORMAT_FEATURE_COLOR_ATTACHMENT_BIT | VK_FORMAT_FEATURE_DEPTH_STENCIL_ATTACHMENT_BIT)) !=
@@ -305,7 +310,8 @@ namespace MobileGL::MG_Backend::DirectVulkan {
fallbackRenderbufferCaps |= FormatCapability::MultisampleRenderbuffer;
}
cache.CaveatCaps[renderbufferTargetIndex][formatIndex] |= fallbackRenderbufferCaps;
if (fallbackLogicalFormat && HasNewCaveatFormatCaps(renderbufferCaps, fallbackRenderbufferCaps)) {
if (fallbackLogicalFormat &&
HasNewCaveatFormatCaps(renderbufferCaps, fallbackRenderbufferCaps)) {
LogVulkanFormatCaveat(logicalFormat, renderbufferTargetIndex, *fallbackLogicalFormat);
}
}
@@ -322,13 +328,14 @@ namespace MobileGL::MG_Backend::DirectVulkan {
void PopulateFormatCapabilities(VkPhysicalDevice physicalDevice,
PFN_vkGetPhysicalDeviceFormatProperties getFormatProperties,
const MG_External::VulkanCapabilities& capabilities, FormatCapabilityCache& cache) {
const MG_External::VulkanCapabilities& capabilities,
FormatCapabilityCache& cache) {
PopulateFormatCapabilitiesImpl(physicalDevice, getFormatProperties, capabilities, cache);
}
BackendObject_DirectVulkan::~BackendObject_DirectVulkan() = default;
BackendObject_DirectVulkan::BackendObject_DirectVulkan() : m_rendererInfo{GetRendererIdentity()} {}
BackendObject_DirectVulkan::BackendObject_DirectVulkan(): m_rendererInfo{GetRendererIdentity()} {}
Bool BackendObject_DirectVulkan::InitWindowSurface() {
if (!m_windowHandle.Handle) {
@@ -402,8 +409,10 @@ namespace MobileGL::MG_Backend::DirectVulkan {
MGLOG_E("DirectVulkan backend not initialized");
return false;
}
if (!handle.Handle || (handle.Backend != WindowBackend::Android && handle.Backend != WindowBackend::X11 &&
handle.Backend != WindowBackend::MetalLayer && handle.Backend != WindowBackend::Win32)) {
if (!handle.Handle || (handle.Backend != WindowBackend::Android &&
handle.Backend != WindowBackend::X11 &&
handle.Backend != WindowBackend::MetalLayer &&
handle.Backend != WindowBackend::Win32)) {
MGLOG_E("DirectVulkan backend only supports Android, X11, CAMetalLayer, and Win32 native windows");
return false;
}
@@ -460,9 +469,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
// treat them as signaled/available with zero results from here on.
BumpRendererGeneration();
pVulkanRenderer.reset();
// The reflection cache is file-scope, not renderer-owned; without this the
// deleted programs' reflection strings survive full context teardown.
ClearProgramResourceCaches();
BackendObject::ReleaseEGLResources();
}
@@ -472,9 +478,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
// treat them as signaled/available with zero results from here on.
BumpRendererGeneration();
pVulkanRenderer.reset();
// The reflection cache is file-scope, not renderer-owned; without this the
// deleted programs' reflection strings survive full context teardown.
ClearProgramResourceCaches();
}
const RendererInfo& BackendObject_DirectVulkan::GetRendererInfo() const {
@@ -494,32 +497,32 @@ namespace MobileGL::MG_Backend::DirectVulkan {
.RendererName = "Magma",
.BackendName = "Direct (Vulkan)",
.ExtraVendor = Nullopt,
.RendererGLInfo = {.TargetGLVersion = {4, 0, 0},
.TargetGLSLVersion = {4, 6, 0},
// Baseline advertisement (no shader subgroup, no timer queries); a
// live backend reconciles its copy in UpdateAdvertisedExtensions.
.Extensions = BuildAdvertisedExtensions(false, false, false),
.IsCompatibilityProfile = false},
.RendererGLInfo =
{
.TargetGLVersion = {3, 3, 0},
.TargetGLSLVersion = {4, 6, 0},
// Baseline advertisement (no shader subgroup, no timer queries); a
// live backend reconciles its copy in UpdateAdvertisedExtensions.
.Extensions = BuildAdvertisedExtensions(false, false, false),
.IsCompatibilityProfile = false
},
.StaticBackendCapability = {.AllowVSOnlyPrograms = false}};
return rendererInfo;
}
Vector<GLExtension> BuildAdvertisedExtensions(Bool shaderSubgroupSupported, Bool timerQueriesSupported,
Bool anisotropicFilteringSupported) {
Vector<GLExtension> extensions = {
V_OpenGL30, V_OpenGL31, V_OpenGL32, V_OpenGL33, V_OpenGL40, E_GL_ARB_draw_buffers_blend,
E_GL_ARB_compute_shader, E_GL_ARB_shader_storage_buffer_object, E_GL_ARB_shader_image_load_store,
E_GL_ARB_program_interface_query, E_GL_ARB_framebuffer_object, E_GL_ARB_multi_draw_indirect,
E_GL_ARB_indirect_parameters, E_GL_EXT_framebuffer_object, E_GL_ARB_depth_texture, E_GL_ARB_buffer_storage,
E_GL_ARB_texture_storage, E_GL_ARB_texture_storage_multisample, E_GL_ARB_texture_multisample,
E_GL_ARB_clear_texture, E_GL_ARB_direct_state_access, E_GL_ARB_shader_draw_parameters,
E_GL_ARB_gpu_shader_int64, E_GL_KHR_debug, E_GL_ARB_gpu_shader5, E_GL_ARB_multi_bind,
E_GL_ARB_shading_language_420pack, E_GL_ARB_vertex_attrib_binding, E_GL_ARB_shader_image_size,
E_GL_ARB_explicit_attrib_location,
// Advertised with GL_NUM_PROGRAM_BINARY_FORMATS = 0, which the
// extension explicitly permits. It is also the only thing that
// exposes glProgramParameteri before GL 4.1.
E_GL_ARB_get_program_binary};
Vector<GLExtension> extensions = {V_OpenGL30, V_OpenGL31, V_OpenGL32,
V_OpenGL33, E_GL_ARB_draw_buffers_blend, E_GL_ARB_compute_shader,
E_GL_ARB_shader_storage_buffer_object, E_GL_ARB_shader_image_load_store,
E_GL_ARB_program_interface_query, E_GL_ARB_framebuffer_object,
E_GL_ARB_multi_draw_indirect, E_GL_ARB_indirect_parameters,
E_GL_EXT_framebuffer_object, E_GL_ARB_depth_texture, E_GL_ARB_buffer_storage,
E_GL_ARB_texture_storage, E_GL_ARB_texture_storage_multisample,
E_GL_ARB_clear_texture, E_GL_ARB_direct_state_access,
E_GL_ARB_shader_draw_parameters, E_GL_ARB_gpu_shader_int64, E_GL_KHR_debug,
E_GL_ARB_gpu_shader5, E_GL_ARB_multi_bind, E_GL_ARB_shading_language_420pack,
E_GL_ARB_vertex_attrib_binding, E_GL_ARB_shader_image_size};
if (shaderSubgroupSupported && !MG_Config::Features.DisableSubgroup) {
extensions.push_back(E_GL_KHR_shader_subgroup);
}
@@ -582,8 +585,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
funcsTable.GL.ClearBufferiv = ClearBufferiv;
funcsTable.GL.ClearNamedFramebufferfv = ClearNamedFramebufferfv;
funcsTable.GL.ClearNamedFramebufferfi = ClearNamedFramebufferfi;
funcsTable.GL.ClearNamedFramebufferiv = ClearNamedFramebufferiv;
funcsTable.GL.ClearNamedFramebufferuiv = ClearNamedFramebufferuiv;
funcsTable.GL.BlitFramebuffer = BlitFramebuffer;
funcsTable.GL.BlitNamedFramebuffer = BlitNamedFramebuffer;
funcsTable.GL.CopyTexImage2D = CopyTexImage2D;
@@ -627,15 +628,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
funcsTable.GL.DeleteBackendQuery = DeleteBackendQuery;
funcsTable.GL.GetGpuTimestampNs = GetGpuTimestampNs;
}
// Occlusion queries share the handle-based result/delete entries, which must
// exist even when timer queries are disabled.
funcsTable.GL.BeginOcclusionQuery = BeginOcclusionQuery;
funcsTable.GL.EndOcclusionQuery = EndOcclusionQuery;
funcsTable.GL.BeginXfbPrimitivesQuery = BeginXfbPrimitivesQuery;
funcsTable.GL.EndXfbPrimitivesQuery = EndXfbPrimitivesQuery;
funcsTable.GL.IsQueryResultAvailable = IsQueryResultAvailable;
funcsTable.GL.GetQueryResult64 = GetQueryResult64;
funcsTable.GL.DeleteBackendQuery = DeleteBackendQuery;
funcsTableInitialized = true;
}
return funcsTable;
@@ -716,7 +708,7 @@ namespace MobileGL::MG_Backend::DirectVulkan {
// rather than a maximum the sampler manager will never apply.
m_dynamicParameters.MaxTextureMaxAnisotropy =
(pVulkanRenderer && pVulkanRenderer->IsSamplerAnisotropySupported()) ? m_vulkanCaps.MaxSamplerAnisotropy
: 1.0f;
: 1.0f;
m_dynamicParameters.SmoothLineWidthRangeMin = m_vulkanCaps.SmoothLineWidthRangeMin;
m_dynamicParameters.SmoothLineWidthRangeMax = m_vulkanCaps.SmoothLineWidthRangeMax;
m_dynamicParameters.SmoothLineWidthGranularity = m_vulkanCaps.SmoothLineWidthGranularity;
@@ -737,7 +729,8 @@ namespace MobileGL::MG_Backend::DirectVulkan {
m_dynamicParameters.MaxIntegerSamples = m_vulkanCaps.MaxIntegerSamples;
m_dynamicParameters.MaxSamples = m_vulkanCaps.MaxSamples;
m_dynamicParameters.MaxSampleMaskWords = m_vulkanCaps.MaxSampleMaskWords;
const Int maxSupportedTextureUnits = static_cast<Int>(MG_State::GLState::TextureState::MAX_TEXTURE_IMAGE_UNITS);
const Int maxSupportedTextureUnits =
static_cast<Int>(MG_State::GLState::TextureState::MAX_TEXTURE_IMAGE_UNITS);
// GL_MAX_TEXTURE_IMAGE_UNITS is a *per-stage* sampler limit. Adreno/Qualcomm report a huge
// maxPerStageDescriptorSampledImages (descriptor-indexing scale), so clamping it only to our
// combined array capacity (192) still advertises 192 per stage. Host code treats this value as
@@ -747,7 +740,8 @@ namespace MobileGL::MG_Backend::DirectVulkan {
// limits while keeping the combined limit at our texture-unit array capacity.
constexpr Int maxPerStageTextureUnits =
static_cast<Int>(MG_State::GLState::TextureState::MAX_PER_STAGE_TEXTURE_IMAGE_UNITS);
m_dynamicParameters.MaxTextureImageUnits = std::min(m_vulkanCaps.MaxTextureImageUnits, maxPerStageTextureUnits);
m_dynamicParameters.MaxTextureImageUnits =
std::min(m_vulkanCaps.MaxTextureImageUnits, maxPerStageTextureUnits);
m_dynamicParameters.MaxVertexTextureImageUnits =
std::min(m_vulkanCaps.MaxVertexTextureImageUnits, maxPerStageTextureUnits);
m_dynamicParameters.MaxComputeTextureImageUnits =
@@ -756,18 +750,19 @@ namespace MobileGL::MG_Backend::DirectVulkan {
std::min(m_vulkanCaps.MaxCombinedTextureImageUnits, maxSupportedTextureUnits);
// Never advertise more attributes than the state layer can store: the current-value array and
// the Uint32 attribute masks the draw path passes around are both bounded by MAX_VERTEX_ATTRIBS.
m_dynamicParameters.MaxVertexAttribs = std::min(
m_vulkanCaps.MaxVertexAttribs, static_cast<Int>(MG_State::GLState::VertexArrayObject::MAX_VERTEX_ATTRIBS));
m_dynamicParameters.MaxVertexAttribs =
std::min(m_vulkanCaps.MaxVertexAttribs,
static_cast<Int>(MG_State::GLState::VertexArrayObject::MAX_VERTEX_ATTRIBS));
m_dynamicParameters.MaxComputeShaderStorageBlocks = m_vulkanCaps.MaxComputeShaderStorageBlocks;
m_dynamicParameters.MaxCombinedShaderStorageBlocks = m_vulkanCaps.MaxCombinedShaderStorageBlocks;
m_dynamicParameters.MaxComputeUniformBlocks = m_vulkanCaps.MaxComputeUniformBlocks;
m_dynamicParameters.MaxComputeWorkGroupInvocations = m_vulkanCaps.MaxComputeWorkGroupInvocations;
m_dynamicParameters.MaxShaderStorageBufferBindings = m_vulkanCaps.MaxShaderStorageBufferBindings;
m_dynamicParameters.MaxTextureBufferSize = m_vulkanCaps.MaxTextureBufferSize;
m_dynamicParameters.TextureBufferOffsetAlignment = m_vulkanCaps.TextureBufferOffsetAlignment;
m_dynamicParameters.MaxUniformBufferBindings = m_vulkanCaps.MaxUniformBufferBindings;
m_dynamicParameters.MaxUniformBlockSize = m_vulkanCaps.MaxUniformBlockSize;
m_dynamicParameters.MaxImageUnits = std::max(std::min(m_vulkanCaps.MaxImageUnits, maxSupportedTextureUnits), 0);
m_dynamicParameters.MaxImageUnits =
std::max(std::min(m_vulkanCaps.MaxImageUnits, maxSupportedTextureUnits), 0);
m_dynamicParameters.MaxCombinedImageUniforms = std::max(m_vulkanCaps.MaxCombinedImageUniforms, 0);
const Int maxPerStageImageUniforms =
std::min(m_dynamicParameters.MaxImageUnits, m_dynamicParameters.MaxCombinedImageUniforms);
@@ -784,7 +779,8 @@ namespace MobileGL::MG_Backend::DirectVulkan {
m_vulkanCaps.SupportsFragmentStoresAndAtomics ? maxPerStageImageUniforms : 0;
m_dynamicParameters.MaxComputeImageUniforms =
std::min(std::max(m_vulkanCaps.MaxComputeImageUniforms, 0), maxPerStageImageUniforms);
const Int maxSupportedDrawBuffers = static_cast<Int>(MG_State::GLState::FramebufferObject::MAX_DRAW_BUFFERS);
const Int maxSupportedDrawBuffers =
static_cast<Int>(MG_State::GLState::FramebufferObject::MAX_DRAW_BUFFERS);
m_dynamicParameters.MaxDrawBuffers = std::min(m_vulkanCaps.MaxDrawBuffers, maxSupportedDrawBuffers);
m_dynamicParameters.MaxColorAttachments = std::min(m_vulkanCaps.MaxColorAttachments, maxSupportedDrawBuffers);
m_dynamicParameters.MaxClipDistances = m_vulkanCaps.MaxClipDistances;
@@ -794,53 +790,13 @@ namespace MobileGL::MG_Backend::DirectVulkan {
m_dynamicParameters.ViewportBoundsRangeMin = m_vulkanCaps.ViewportBoundsRangeMin;
m_dynamicParameters.ViewportBoundsRangeMax = m_vulkanCaps.ViewportBoundsRangeMax;
m_dynamicParameters.ViewportSubpixelBits = m_vulkanCaps.ViewportSubpixelBits;
m_dynamicParameters.MinFragmentInterpolationOffset =
std::isfinite(m_vulkanCaps.MinFragmentInterpolationOffset) &&
m_vulkanCaps.MinFragmentInterpolationOffset <= -0.5f
? m_vulkanCaps.MinFragmentInterpolationOffset
: -0.5f;
m_dynamicParameters.MaxFragmentInterpolationOffset = 0.4375f;
m_dynamicParameters.FragmentInterpolationOffsetBits = 4;
if (m_vulkanCaps.FragmentInterpolationOffsetBits >= 4 &&
std::isfinite(m_vulkanCaps.MaxFragmentInterpolationOffset)) {
const Float requiredMaxOffset = 0.5f - std::ldexp(1.0f, -m_vulkanCaps.FragmentInterpolationOffsetBits);
if (m_vulkanCaps.MaxFragmentInterpolationOffset >= requiredMaxOffset) {
m_dynamicParameters.MaxFragmentInterpolationOffset = m_vulkanCaps.MaxFragmentInterpolationOffset;
m_dynamicParameters.FragmentInterpolationOffsetBits = m_vulkanCaps.FragmentInterpolationOffsetBits;
}
}
m_dynamicParameters.SupportsWideLines = m_vulkanCaps.SupportsWideLines;
// A 2D or 2D multisample array texture is a VK_IMAGE_TYPE_2D image whose GL depth IS its
// arrayLayers, so a GL layer is a Vulkan array layer with nothing to translate.
// ResolveAttachmentBaseArrayLayer already passes the attachment's layer through. The other
// layered targets are declared separately as their own machinery lands.
{
using DynParams = MG_Backend::DynamicBackendParameters;
m_dynamicParameters.PerLayerFramebufferAttachmentTargets |=
DynParams::PerLayerFramebufferAttachmentBit(TextureTarget::Texture2DArray) |
DynParams::PerLayerFramebufferAttachmentBit(TextureTarget::Texture2DMultisampleArray);
// A cube map array is one 2D image with arrayLayers = 6 * cubeCount, so a GL layer is a
// Vulkan array layer here too - but the image cannot be created without imageCubeArray.
// A 3D texture's GL layer is a z slice, which only a 2D view over a 2D-array-compatible
// image can name. Optimistic: a format that refuses the flag is caught at image creation
// and declines the slice view there, which the clear path handles as a soft miss.
if (m_vulkanCaps.Supports2DArrayCompatible3DImages) {
m_dynamicParameters.PerLayerFramebufferAttachmentTargets |=
DynParams::PerLayerFramebufferAttachmentBit(TextureTarget::Texture3D);
}
if (m_vulkanCaps.SupportsImageCubeArray) {
m_dynamicParameters.PerLayerFramebufferAttachmentTargets |=
DynParams::PerLayerFramebufferAttachmentBit(TextureTarget::TextureCubeMapArray);
}
}
m_dynamicParameters.SupportsFloat64VertexAttributes = m_vulkanCaps.SupportsShaderFloat64;
m_dynamicParameters.MaxShaderStorageBlockSize =
std::min(m_vulkanCaps.MaxShaderStorageBlockSize, kMaxAdvertisedShaderStorageBlockSize);
if (m_vulkanCaps.SupportsShaderSubgroup) {
m_dynamicParameters.SubgroupSize = m_vulkanCaps.SubgroupSize;
m_dynamicParameters.SubgroupSupportedStages = mapShaderStages(m_vulkanCaps.SubgroupSupportedStages);
m_dynamicParameters.SubgroupSupportedFeatures =
mapSubgroupFeatures(m_vulkanCaps.SubgroupSupportedOperations);
m_dynamicParameters.SubgroupSupportedFeatures = mapSubgroupFeatures(m_vulkanCaps.SubgroupSupportedOperations);
m_dynamicParameters.SubgroupQuadOperationsInAllStages = m_vulkanCaps.SubgroupQuadOperationsInAllStages;
} else {
m_dynamicParameters.SubgroupSize = 0;
@@ -850,7 +806,8 @@ namespace MobileGL::MG_Backend::DirectVulkan {
}
if (m_dynamicParameters.MaxShaderStorageBlockSize != m_vulkanCaps.MaxShaderStorageBlockSize) {
MGLOG_I("DirectVulkan: clamped GL_MAX_SHADER_STORAGE_BLOCK_SIZE from %zu to %zu",
m_vulkanCaps.MaxShaderStorageBlockSize, m_dynamicParameters.MaxShaderStorageBlockSize);
m_vulkanCaps.MaxShaderStorageBlockSize,
m_dynamicParameters.MaxShaderStorageBlockSize);
}
switch (m_vulkanCaps.VendorId) {
case 0x5143u: // VK_VENDOR_ID: Qualcomm
@@ -16,7 +16,6 @@
#include "MG_Util/Metrics/TextureMetrics.h"
#include "MG_Util/Miscellany/IndexGenerator.h"
#include <atomic>
#include <bit>
#include <cstring>
#include <spirv_reflect.h>
@@ -62,12 +61,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
};
struct ProgramResourceCache {
// Lifetime id of the program the cached reflection belongs to. GL names are
// recycled (IndexGenerator hands freed indices straight back), and a
// recreated program's backendStateVersion restarts at the same small values,
// so the version alone can collide; the never-reused lifetime id makes the
// slot's ownership unambiguous.
Uint64 programLifetimeId = 0;
Uint32 backendStateVersion = 0;
Vector<StorageBlockResource> storageBlocks;
Vector<BufferVariableResource> bufferVariables;
@@ -89,11 +82,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
Uint32 baseInstance = 0;
};
// Keyed by GL program name so the freed-name reuse in IndexGenerator bounds the
// map at the peak-simultaneous-program high-water mark; each slot's ownership is
// checked against the program's lifetime id before it is served (see
// GetProgramResourceCache). Cleared wholesale at EGL teardown via
// ClearProgramResourceCaches.
UnorderedMap<GLuint, ProgramResourceCache> g_programResourceCaches;
void ClearReadPixelsOutput(GLsizei width, GLsizei height, GLenum format, GLenum type, void* pixels) {
@@ -154,19 +142,13 @@ namespace MobileGL::MG_Backend::DirectVulkan {
ProgramResourceCache& GetProgramResourceCache(const MG_State::GLState::ProgramObject& program) {
auto& cache = g_programResourceCaches[program.GetExternalIndex()];
const Uint64 programLifetimeId = program.GetLifetimeId();
const Uint32 backendStateVersion = program.GetBackendStateVersion();
// The lifetime id must match too: a new program that reuses a deleted
// program's name and happens to land on the same backendStateVersion (both
// count from zero) would otherwise be served the dead program's reflection.
if (cache.programLifetimeId == programLifetimeId &&
cache.backendStateVersion == backendStateVersion &&
if (cache.backendStateVersion == backendStateVersion &&
(!cache.storageBlocks.empty() || !cache.bufferVariables.empty())) {
return cache;
}
cache = {};
cache.programLifetimeId = programLifetimeId;
cache.backendStateVersion = backendStateVersion;
Vector<SpvReflectShaderModule> modules;
@@ -384,15 +366,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
}
} // namespace
void ClearProgramResourceCaches() {
// Called from EGL teardown while the backend's m_eglStateMutex is held; GL
// calls are serialized in this codebase (contexts migrate threads but never
// run concurrently), so no other thread can be inside the unsynchronized map.
// Live programs in another context self-heal: their entry rebuilds from the
// retained generated SPIR-V on the next resource query.
g_programResourceCaches.clear();
}
GLuint GetShaderStorageBlockIndex(const MG_State::GLState::ProgramObject& program, const String& name) {
auto& cache = GetProgramResourceCache(program);
const auto it = std::find_if(cache.storageBlocks.begin(), cache.storageBlocks.end(),
@@ -441,20 +414,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
pVulkanRenderer->ClearNamedFramebufferfv(framebuffer, buffer, drawbuffer, value);
}
void ClearNamedFramebufferiv(const SharedPtr<MG_State::GLState::FramebufferObject>& framebuffer, GLenum buffer,
GLint drawbuffer, const GLint* value) {
MOBILEGL_ASSERT(pVulkanRenderer, "DirectVulkan::ClearNamedFramebufferiv called with null VulkanRenderer");
MOBILEGL_ASSERT(MG_State::pGLContext, "DirectVulkan::ClearNamedFramebufferiv called with null GL context");
pVulkanRenderer->ClearNamedFramebufferiv(framebuffer, buffer, drawbuffer, value);
}
void ClearNamedFramebufferuiv(const SharedPtr<MG_State::GLState::FramebufferObject>& framebuffer, GLenum buffer,
GLint drawbuffer, const GLuint* value) {
MOBILEGL_ASSERT(pVulkanRenderer, "DirectVulkan::ClearNamedFramebufferuiv called with null VulkanRenderer");
MOBILEGL_ASSERT(MG_State::pGLContext, "DirectVulkan::ClearNamedFramebufferuiv called with null GL context");
pVulkanRenderer->ClearNamedFramebufferuiv(framebuffer, buffer, drawbuffer, value);
}
void ClearNamedFramebufferfi(const SharedPtr<MG_State::GLState::FramebufferObject>& framebuffer, GLenum buffer,
GLint drawbuffer, GLfloat depth, GLint stencil) {
MOBILEGL_ASSERT(pVulkanRenderer, "DirectVulkan::ClearNamedFramebufferfi called with null VulkanRenderer");
@@ -1265,76 +1224,10 @@ namespace MobileGL::MG_Backend::DirectVulkan {
pVulkanRenderer->Clear(mask);
}
// Vulkan has no LINE_LOOP topology; rewrite the draw as an indexed LINE_STRIP
// whose synthesized index list revisits the first vertex at the end.
static void DrawLineLoopAsIndexedStrip(const Vector<Uint32>& closedIndices, GLint basevertex) {
DrawIndexedCmd payload{};
payload.mode = GL_LINE_STRIP;
payload.indexBufferView.indexType = GL_UNSIGNED_INT;
payload.indexBufferView.indexByteOffset = reinterpret_cast<SizeT>(closedIndices.data());
payload.indexBufferView.indexByteSize = closedIndices.size() * sizeof(Uint32);
payload.indexBufferView.forceClientMemory = true;
payload.params.indexCount = static_cast<Uint32>(closedIndices.size());
payload.params.instanceCount = 1;
payload.params.vertexOffset = basevertex;
pVulkanRenderer->DrawElements(payload);
}
// Resolve a DrawElements index list (bound element-array buffer or client
// memory) into uint32 values with the loop-closing first index appended.
static Bool BuildClosedLineLoopIndices(GLsizei count, GLenum type, const void* indices,
Vector<Uint32>& outIndices) {
const SizeT indexSize = MG_Util::GetGLTypeSize(type);
if (indexSize == 0 || count < 2) {
return false;
}
const Uint8* indexBytes = nullptr;
const auto& vao = *MG_State::pGLContext->GetBoundVertexArray();
const auto& indexBufferShared = vao.GetIndexBufferBindingSlot().GetBoundObject();
if (indexBufferShared != nullptr) {
const SizeT offset = reinterpret_cast<SizeT>(indices);
const SizeT bufferSize = indexBufferShared->GetSize();
if (indexBufferShared->MappedData() == nullptr || offset > bufferSize ||
static_cast<SizeT>(count) * indexSize > bufferSize - offset) {
return false;
}
indexBufferShared->SyncPersistentMappedRange();
indexBytes = indexBufferShared->MappedData() + offset;
} else {
indexBytes = static_cast<const Uint8*>(indices);
if (indexBytes == nullptr) {
return false;
}
}
outIndices.resize(static_cast<SizeT>(count) + 1);
for (GLsizei i = 0; i < count; ++i) {
switch (indexSize) {
case 1: outIndices[i] = indexBytes[i]; break;
case 2: outIndices[i] = reinterpret_cast<const Uint16*>(indexBytes)[i]; break;
default: outIndices[i] = reinterpret_cast<const Uint32*>(indexBytes)[i]; break;
}
}
outIndices[count] = outIndices[0];
return true;
}
void DrawArrays(GLenum mode, GLint first, GLsizei count) {
MOBILEGL_ASSERT(pVulkanRenderer, "DirectVulkan::DrawArrays called with null VulkanRenderer");
MOBILEGL_ASSERT(MG_State::pGLContext, "DirectVulkan::DrawArrays called with null GL context");
if (mode == GL_LINE_LOOP) {
if (count < 2) {
return;
}
Vector<Uint32> closedIndices(static_cast<SizeT>(count) + 1);
for (GLsizei i = 0; i < count; ++i) {
closedIndices[i] = static_cast<Uint32>(first + i);
}
closedIndices[count] = static_cast<Uint32>(first);
DrawLineLoopAsIndexedStrip(closedIndices, 0);
return;
}
DrawCmd payload{};
payload.mode = mode;
payload.params.firstVertex = first;
@@ -1347,14 +1240,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
MOBILEGL_ASSERT(pVulkanRenderer, "DirectVulkan::DrawElements called with null VulkanRenderer");
MOBILEGL_ASSERT(MG_State::pGLContext, "DirectVulkan::DrawElements called with null GL context");
if (mode == GL_LINE_LOOP) {
Vector<Uint32> closedIndices;
if (BuildClosedLineLoopIndices(count, type, indices, closedIndices)) {
DrawLineLoopAsIndexedStrip(closedIndices, 0);
}
return;
}
DrawIndexedCmd payload{};
payload.mode = mode;
payload.indexBufferView.indexType = type;
@@ -1423,13 +1308,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
void DrawElementsBaseVertex(GLenum mode, GLsizei count, GLenum type, const GLvoid* indices, GLint basevertex) {
MOBILEGL_ASSERT(pVulkanRenderer, "DirectVulkan::DrawElementsBaseVertex called with null VulkanRenderer");
MOBILEGL_ASSERT(MG_State::pGLContext, "DirectVulkan::DrawElementsBaseVertex called with null GL context");
if (mode == GL_LINE_LOOP) {
Vector<Uint32> closedIndices;
if (BuildClosedLineLoopIndices(count, type, indices, closedIndices)) {
DrawLineLoopAsIndexedStrip(closedIndices, basevertex);
}
return;
}
DrawIndexedCmd payload{};
payload.mode = mode;
payload.indexBufferView.indexType = type;
@@ -1451,18 +1329,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
payload.mode = mode;
payload.indexBufferView.indexType = type;
// Loop-invariant: the index type is fixed for the whole multi-draw, so resolve
// its byte size once instead of twice per sub-draw (a cross-TU switch that
// showed up in per-frame profiles of sodium-style 132x32 multi-draws). Index
// sizes are 1/2/4, so the per-sub-draw offset division below reduces to a
// shift - the hardware divide was the hottest instruction of this loop.
const SizeT indexSize = MG_Util::GetGLTypeSize(type);
if (indexSize == 0) {
MGLOG_E("MultiDrawElementsBaseVertex skipped: unsupported index type 0x%x", type);
return;
}
const Uint32 indexSizeShift = static_cast<Uint32>(std::countr_zero(indexSize));
// TODO: allocate draw cmd buf elsewhere
static Vector<DrawIndexedCmdParam> params;
params.clear();
@@ -1477,14 +1343,14 @@ namespace MobileGL::MG_Backend::DirectVulkan {
payload.indexBufferView.indexByteOffset = 0;
payload.indexBufferView.indexByteSize =
std::max(reinterpret_cast<SizeT>(indices[i]) + count[i] * indexSize,
std::max(reinterpret_cast<SizeT>(indices[i]) + count[i] * MG_Util::GetGLTypeSize(type),
payload.indexBufferView.indexByteSize);
auto& param = params[i];
param.indexCount = count[i];
param.instanceCount = 1;
param.firstIndex = reinterpret_cast<SizeT>(indices[i]) >> indexSizeShift;
param.firstIndex = reinterpret_cast<SizeT>(indices[i]) / MG_Util::GetGLTypeSize(type);
param.vertexOffset = basevertex[i];
param.firstInstance = 0;
}
@@ -1591,12 +1457,8 @@ namespace MobileGL::MG_Backend::DirectVulkan {
// records are shared (SharedPtr) with the owning pool's pending list,
// so deleting the query while results are still in flight is safe.
struct VulkanTimerQuery {
enum class Kind : Uint8 { Timer, Occlusion, XfbWritten, XfbGenerated };
Kind kind = Kind::Timer;
SharedPtr<VkTimerQueryManager::TimestampRecord> begin;
SharedPtr<VkTimerQueryManager::TimestampRecord> end;
// Kind::Occlusion - pool slots recorded between Begin/End; summed at result time.
Vector<Uint32> occlusionSlots;
// Renderer generation the records were written under (see
// g_rendererGeneration). A stale generation resolves as available
// with a final zero result: the records' pool indices and frame
@@ -1605,12 +1467,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
// (and, via the SharedPtrs, the records), never pool slots, so
// stale queries are always safe to delete.
Uint64 rendererGeneration = 0;
// Kind::XfbGenerated - the frontend's paused-draw primitive counter when the
// query began. VK_QUERY_TYPE_TRANSFORM_FEEDBACK_STREAM_EXT counts only what the
// capture saw, so a draw made while the span was paused is invisible to it -
// but GL_PRIMITIVES_GENERATED counts what the last vertex processing stage
// emitted regardless. The delta closes that gap at result time.
Uint64 pausedPrimitiveSnapshot = 0;
};
} // namespace
@@ -1692,30 +1548,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
// ever be produced, so resolve with a final 0.
return true;
}
if (query->kind == VulkanTimerQuery::Kind::Occlusion) {
Uint64 samples = 0;
if (!pVulkanRenderer->ResolveOcclusionQueryResult(query->occlusionSlots, samples)) {
return false;
}
query->occlusionSlots.clear(); // slots are recycled by the resolve
*outNanoseconds = samples;
return true;
}
if (query->kind == VulkanTimerQuery::Kind::XfbWritten ||
query->kind == VulkanTimerQuery::Kind::XfbGenerated) {
Uint64 primitives = 0;
if (!pVulkanRenderer->ResolveXfbQueryResult(query->occlusionSlots,
query->kind == VulkanTimerQuery::Kind::XfbGenerated,
primitives)) {
return false;
}
if (query->kind == VulkanTimerQuery::Kind::XfbGenerated && MG_State::pGLContext != nullptr) {
primitives += MG_State::pGLContext->GetTransformFeedbackPausedPrimitiveCounter() -
query->pausedPrimitiveSnapshot;
}
*outNanoseconds = primitives;
return true;
}
// With wait, mirrors ClientWaitSync: a query ended this frame cannot
// complete until Present submits the commands, so the wait refuses to
// block on the current unsubmitted serial. Returning false keeps the
@@ -1748,49 +1580,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
delete static_cast<VulkanTimerQuery*>(handle);
}
BackendQueryHandle BeginXfbPrimitivesQuery(Bool generated) {
MOBILEGL_ASSERT(pVulkanRenderer, "DirectVulkan::BeginXfbPrimitivesQuery called with null VulkanRenderer");
if (!pVulkanRenderer->StartXfbQueryCapture(generated ? 1u : 0u)) {
return nullptr;
}
auto* query = new VulkanTimerQuery{};
query->kind = generated ? VulkanTimerQuery::Kind::XfbGenerated : VulkanTimerQuery::Kind::XfbWritten;
query->rendererGeneration = GetRendererGeneration();
query->pausedPrimitiveSnapshot =
MG_State::pGLContext ? MG_State::pGLContext->GetTransformFeedbackPausedPrimitiveCounter() : 0;
return query;
}
void EndXfbPrimitivesQuery(BackendQueryHandle handle) {
auto* query = static_cast<VulkanTimerQuery*>(handle);
MOBILEGL_ASSERT(pVulkanRenderer, "DirectVulkan::EndXfbPrimitivesQuery called with null VulkanRenderer");
if (query == nullptr || query->rendererGeneration != GetRendererGeneration()) {
return;
}
pVulkanRenderer->StopXfbQueryCapture(
query->kind == VulkanTimerQuery::Kind::XfbGenerated ? 1u : 0u, query->occlusionSlots);
}
BackendQueryHandle BeginOcclusionQuery() {
MOBILEGL_ASSERT(pVulkanRenderer, "DirectVulkan::BeginOcclusionQuery called with null VulkanRenderer");
if (!pVulkanRenderer->StartOcclusionQueryCapture()) {
return nullptr;
}
auto* query = new VulkanTimerQuery{};
query->kind = VulkanTimerQuery::Kind::Occlusion;
query->rendererGeneration = GetRendererGeneration();
return query;
}
void EndOcclusionQuery(BackendQueryHandle handle) {
auto* query = static_cast<VulkanTimerQuery*>(handle);
MOBILEGL_ASSERT(pVulkanRenderer, "DirectVulkan::EndOcclusionQuery called with null VulkanRenderer");
if (query == nullptr || query->rendererGeneration != GetRendererGeneration()) {
return;
}
pVulkanRenderer->StopOcclusionQueryCapture(query->occlusionSlots);
}
Int64 GetGpuTimestampNs() {
// Vulkan cannot synchronously sample the GPU clock: timestamps only
// exist as vkCmdWriteTimestamp results read back later, and
@@ -23,22 +23,12 @@ namespace MobileGL::MG_Backend::DirectVulkan {
Uint64 GetRendererGeneration();
void BumpRendererGeneration();
// Drops every cached program-resource reflection entry (CPU-side strings/vectors
// only, no Vulkan handles). Called at EGL teardown next to the renderer reset;
// safe because GL calls are serialized in this codebase, and any still-live
// program rebuilds its entry from the retained generated SPIR-V on demand.
void ClearProgramResourceCaches();
void ClearBufferfi(GLenum buffer, GLint drawbuffer, GLfloat depth, GLint stencil);
void ClearBufferfv(GLenum buffer, GLint drawbuffer, const GLfloat* value);
void ClearBufferuiv(GLenum buffer, GLint drawbuffer, const GLuint* value);
void ClearBufferiv(GLenum buffer, GLint drawbuffer, const GLint* value);
void ClearNamedFramebufferfv(const SharedPtr<MG_State::GLState::FramebufferObject>& framebuffer, GLenum buffer,
GLint drawbuffer, const GLfloat* value);
void ClearNamedFramebufferiv(const SharedPtr<MG_State::GLState::FramebufferObject>& framebuffer, GLenum buffer,
GLint drawbuffer, const GLint* value);
void ClearNamedFramebufferuiv(const SharedPtr<MG_State::GLState::FramebufferObject>& framebuffer, GLenum buffer,
GLint drawbuffer, const GLuint* value);
void ClearNamedFramebufferfi(const SharedPtr<MG_State::GLState::FramebufferObject>& framebuffer, GLenum buffer,
GLint drawbuffer, GLfloat depth, GLint stencil);
void Clear(GLbitfield mask);
@@ -127,10 +117,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
// only while a live renderer exists whose device can actually time.
Bool IsTimerQuerySupported();
BackendQueryHandle BeginTimeElapsedQuery();
BackendQueryHandle BeginXfbPrimitivesQuery(Bool generated);
void EndXfbPrimitivesQuery(BackendQueryHandle query);
BackendQueryHandle BeginOcclusionQuery();
void EndOcclusionQuery(BackendQueryHandle query);
void EndTimeElapsedQuery(BackendQueryHandle query);
BackendQueryHandle QueryCounterTimestamp();
Bool IsQueryResultAvailable(BackendQueryHandle query);
@@ -16,19 +16,18 @@ namespace MobileGL::MG_Backend::DirectVulkan {
m_device = device;
m_commandPool = commandPool;
Vector<VkCommandBuffer> commandBuffers(frameCount * 2, VK_NULL_HANDLE);
Vector<VkCommandBuffer> commandBuffers(frameCount, VK_NULL_HANDLE);
VkCommandBufferAllocateInfo allocInfo{};
allocInfo.sType = VK_STRUCTURE_TYPE_COMMAND_BUFFER_ALLOCATE_INFO;
allocInfo.commandPool = commandPool;
allocInfo.level = VK_COMMAND_BUFFER_LEVEL_PRIMARY;
allocInfo.commandBufferCount = frameCount * 2;
allocInfo.commandBufferCount = frameCount;
VkResult result = vkAllocateCommandBuffers(device, &allocInfo, commandBuffers.data());
if (result != VK_SUCCESS) {
return result;
}
for (Uint32 i = 0; i < frameCount; ++i) {
m_frames[i].commandBuffer = commandBuffers[i];
m_frames[i].preCommandBuffer = commandBuffers[frameCount + i];
}
VkSemaphoreCreateInfo semaphoreInfo{VK_STRUCTURE_TYPE_SEMAPHORE_CREATE_INFO};
@@ -48,10 +47,9 @@ namespace MobileGL::MG_Backend::DirectVulkan {
void FrameContext::Destroy(VkDevice device, VkCommandPool commandPool) {
const Uint32 frameCount = static_cast<Uint32>(m_frames.size());
Vector<VkCommandBuffer> commandBuffers(frameCount * 2, VK_NULL_HANDLE);
Vector<VkCommandBuffer> commandBuffers(frameCount, VK_NULL_HANDLE);
for (Uint32 i = 0; i < frameCount; ++i) {
commandBuffers[i] = m_frames[i].commandBuffer;
commandBuffers[frameCount + i] = m_frames[i].preCommandBuffer;
}
for (Uint32 i = 0; i < frameCount; ++i) {
@@ -62,7 +60,7 @@ namespace MobileGL::MG_Backend::DirectVulkan {
for (auto& frame : m_frames) {
FreeRetiredCommandBuffers(frame);
}
vkFreeCommandBuffers(device, commandPool, frameCount * 2, commandBuffers.data());
vkFreeCommandBuffers(device, commandPool, frameCount, commandBuffers.data());
}
m_frames.clear();
currentFrameIndex = 0;
@@ -89,8 +87,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
currentFrameIndex = (currentFrameIndex + 1) % static_cast<Uint32>(m_frames.size());
GetCurrent().isCommandRecording = false;
GetCurrent().hasCommandBufferRecorded = false;
GetCurrent().isPreCommandRecording = false;
GetCurrent().hasPreCommandBufferRecorded = false;
}
VkCommandBuffer& FrameContext::BeginCommandRecording(VkCommandBufferUsageFlags flags,
@@ -122,41 +118,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
frame.hasCommandBufferRecorded = true;
}
VkCommandBuffer FrameContext::BeginPreCommandRecording() {
auto& frame = GetCurrent();
if (frame.isPreCommandRecording) {
return frame.preCommandBuffer;
}
MOBILEGL_ASSERT(!frame.hasPreCommandBufferRecorded,
"BeginPreCommandRecording: a recorded pre stream is still awaiting submission");
VK_VERIFY(vkResetCommandBuffer(frame.preCommandBuffer, 0), "BeginPreCommandRecording, vkResetCommandBuffer");
VkCommandBufferBeginInfo beginInfo{};
beginInfo.sType = VK_STRUCTURE_TYPE_COMMAND_BUFFER_BEGIN_INFO;
VK_VERIFY(vkBeginCommandBuffer(frame.preCommandBuffer, &beginInfo),
"BeginPreCommandRecording, vkBeginCommandBuffer");
frame.isPreCommandRecording = true;
return frame.preCommandBuffer;
}
void FrameContext::EndPreCommandRecordingIfOpen() {
auto& frame = GetCurrent();
if (!frame.isPreCommandRecording) {
return;
}
VK_VERIFY(vkEndCommandBuffer(frame.preCommandBuffer), "EndPreCommandRecordingIfOpen, vkEndCommandBuffer");
frame.isPreCommandRecording = false;
frame.hasPreCommandBufferRecorded = true;
}
void FrameContext::AbandonPreCommandRecording() {
auto& frame = GetCurrent();
if (frame.isPreCommandRecording) {
VK_VERIFY(vkEndCommandBuffer(frame.preCommandBuffer), "AbandonPreCommandRecording, vkEndCommandBuffer");
}
frame.isPreCommandRecording = false;
frame.hasPreCommandBufferRecorded = false;
}
VkResult FrameContext::InitializeSwapchainSemaphores(VkDevice device, Uint32 swapchainImageCount) {
DestroySwapchainSemaphores(device);
if (swapchainImageCount == 0) {
@@ -189,30 +150,12 @@ namespace MobileGL::MG_Backend::DirectVulkan {
Bool FrameContext::TransitionToPresent(VkImage image, VkImageLayout oldLayout, VkImageLayout presentLayout) {
auto& frame = GetCurrent();
if (oldLayout == presentLayout || oldLayout == VK_IMAGE_LAYOUT_SHARED_PRESENT_KHR) {
if (frame.hasCommandBufferRecorded || frame.isCommandRecording || oldLayout == presentLayout ||
oldLayout == VK_IMAGE_LAYOUT_SHARED_PRESENT_KHR) {
return false;
}
// The barrier belongs in the frame's own recording. Bailing out because
// something was already recorded (the previous behaviour) dropped the
// transition entirely for every frame that never ran a default-framebuffer
// render pass - the only other thing that carries the image to
// PRESENT_SRC_KHR, via that pass's finalLayout - so the swapchain image was
// handed to the WSI still in the layout it was acquired in.
// A closed-but-unsubmitted buffer can only come from a submit that already
// failed (SubmitPendingCommandBuffer leaves the flag set on error), and
// appending to it is illegal while reopening would reset the frame's own
// commands away. The device is gone on that path anyway - stay silent-safe
// rather than trade a lost device for a barrier into a closed buffer.
if (frame.hasCommandBufferRecorded) {
MGLOG_E("TransitionToPresent: command buffer already closed; skipping the present barrier");
return false;
}
// Reopening a recording here would vkResetCommandBuffer this frame's own
// commands away, so append to the open one and let the caller close it.
const Bool openedRecording = !frame.isCommandRecording;
VkCommandBuffer commandBuffer = openedRecording ? BeginCommandRecording() : frame.commandBuffer;
auto& commandBuffer = BeginCommandRecording();
VkImageMemoryBarrier presentBarrier{};
presentBarrier.sType = VK_STRUCTURE_TYPE_IMAGE_MEMORY_BARRIER;
@@ -231,9 +174,7 @@ namespace MobileGL::MG_Backend::DirectVulkan {
vkCmdPipelineBarrier(commandBuffer, VK_PIPELINE_STAGE_TOP_OF_PIPE_BIT, VK_PIPELINE_STAGE_BOTTOM_OF_PIPE_BIT, 0, 0,
nullptr, 0, nullptr, 1, &presentBarrier);
if (openedRecording) {
EndCommandRecording();
}
EndCommandRecording();
return true;
}
@@ -241,27 +182,17 @@ namespace MobileGL::MG_Backend::DirectVulkan {
Uint32 swapchainImageIndex) const {
const auto& frame = GetCurrent();
MOBILEGL_ASSERT(!frame.isCommandRecording, "GetSubmitInfo called while command buffer recording is still active");
MOBILEGL_ASSERT(!frame.isPreCommandRecording,
"GetSubmitInfo called while the pre-pass stream is still recording");
AssertValidSwapchainImageIndex(swapchainImageIndex);
SubmitInfoPacket packet{};
packet.waitSemaphore = frame.imageAvailableSemaphore;
packet.signalSemaphore = m_swapchainImageRenderFinishedSemaphores[swapchainImageIndex];
Uint32 commandBufferCount = 0;
// The pre-pass stream executes strictly before the frame's commands.
if (frame.hasPreCommandBufferRecorded) {
packet.commandBuffers[commandBufferCount++] = frame.preCommandBuffer;
}
if (shouldSubmitCommandBuffer) {
packet.commandBuffers[commandBufferCount++] = frame.commandBuffer;
}
packet.commandBuffer = frame.commandBuffer;
packet.submitInfo.waitSemaphoreCount = frame.imageAvailableSemaphoreConsumed ? 0U : 1U;
packet.submitInfo.pWaitSemaphores = frame.imageAvailableSemaphoreConsumed ? nullptr : &packet.waitSemaphore;
packet.submitInfo.pWaitDstStageMask = frame.imageAvailableSemaphoreConsumed ? nullptr : &packet.waitDstStageMask;
packet.submitInfo.commandBufferCount = commandBufferCount;
packet.submitInfo.pCommandBuffers = commandBufferCount > 0 ? packet.commandBuffers : nullptr;
packet.submitInfo.commandBufferCount = shouldSubmitCommandBuffer ? 1U : 0U;
packet.submitInfo.pCommandBuffers = shouldSubmitCommandBuffer ? &packet.commandBuffer : nullptr;
packet.submitInfo.signalSemaphoreCount = 1;
packet.submitInfo.pSignalSemaphores = &packet.signalSemaphore;
return packet;
@@ -296,21 +227,12 @@ namespace MobileGL::MG_Backend::DirectVulkan {
result = vkAcquireNextImageKHR(device, swapchain, timeout, frame.imageAvailableSemaphore, acquireFence,
&outImageIndex);
// VK_SUBOPTIMAL_KHR is a success code: an image *was* acquired and
// imageAvailableSemaphore *will* be signaled. Bailing out on it skipped both
// the consumed-flag reset (leaving a stale "already consumed", so the next
// submit never waited on the pending signal) and the fence reset (leaving
// the slot's fence signaled for the next submit to reuse). Only a genuine
// failure - VK_ERROR_OUT_OF_DATE_KHR and friends, where nothing is acquired
// and nothing is signaled - skips the bookkeeping.
if (result != VK_SUCCESS && result != VK_SUBOPTIMAL_KHR) {
if (result != VK_SUCCESS) {
return result;
}
frame.imageAvailableSemaphoreConsumed = false;
const VkResult resetResult = vkResetFences(device, 1, &frame.imageInFlightFence);
// Hand the acquire's own code back so the caller can schedule a rebuild.
return resetResult == VK_SUCCESS ? result : resetResult;
return vkResetFences(device, 1, &frame.imageInFlightFence);
}
Uint32 FrameContext::GetCurrentFrameIndex() const {
@@ -325,14 +247,12 @@ namespace MobileGL::MG_Backend::DirectVulkan {
m_recordingObserver = observer;
}
VkResult FrameContext::RetireCurrentCommandBuffer(Bool retirePreCommandBuffer) {
VkResult FrameContext::RetireCurrentCommandBuffer() {
MOBILEGL_ASSERT(m_device != VK_NULL_HANDLE && m_commandPool != VK_NULL_HANDLE,
"RetireCurrentCommandBuffer requires an initialized FrameContext");
auto& frame = GetCurrent();
MOBILEGL_ASSERT(!frame.isCommandRecording,
"RetireCurrentCommandBuffer called while the command buffer is still recording");
MOBILEGL_ASSERT(!frame.isPreCommandRecording,
"RetireCurrentCommandBuffer called while the pre-pass stream is still recording");
VkCommandBufferAllocateInfo allocInfo{};
allocInfo.sType = VK_STRUCTURE_TYPE_COMMAND_BUFFER_ALLOCATE_INFO;
@@ -340,23 +260,11 @@ namespace MobileGL::MG_Backend::DirectVulkan {
allocInfo.level = VK_COMMAND_BUFFER_LEVEL_PRIMARY;
allocInfo.commandBufferCount = 1;
VkCommandBuffer replacement = VK_NULL_HANDLE;
VkResult result = vkAllocateCommandBuffers(m_device, &allocInfo, &replacement);
const VkResult result = vkAllocateCommandBuffers(m_device, &allocInfo, &replacement);
if (result != VK_SUCCESS) {
return result;
}
if (retirePreCommandBuffer) {
VkCommandBuffer preReplacement = VK_NULL_HANDLE;
result = vkAllocateCommandBuffers(m_device, &allocInfo, &preReplacement);
if (result != VK_SUCCESS) {
vkFreeCommandBuffers(m_device, m_commandPool, 1, &replacement);
return result;
}
frame.retiredCommandBuffers.push_back({frame.preCommandBuffer, frame.lastSubmitIndex});
frame.preCommandBuffer = preReplacement;
}
// lastSubmitIndex was just written by the renderer for the submission
// that carried this command buffer.
frame.retiredCommandBuffers.push_back({frame.commandBuffer, frame.lastSubmitIndex});
frame.retiredCommandBuffers.push_back(frame.commandBuffer);
frame.commandBuffer = replacement;
return VK_SUCCESS;
}
@@ -366,40 +274,12 @@ namespace MobileGL::MG_Backend::DirectVulkan {
return;
}
if (m_device != VK_NULL_HANDLE && m_commandPool != VK_NULL_HANDLE) {
for (const auto& retired : frame.retiredCommandBuffers) {
vkFreeCommandBuffers(m_device, m_commandPool, 1, &retired.commandBuffer);
}
vkFreeCommandBuffers(m_device, m_commandPool, static_cast<Uint32>(frame.retiredCommandBuffers.size()),
frame.retiredCommandBuffers.data());
}
frame.retiredCommandBuffers.clear();
}
void FrameContext::FreeRetiredCommandBuffersCompletedUpTo(Uint64 completedSubmitIndex) {
if (m_device == VK_NULL_HANDLE || m_commandPool == VK_NULL_HANDLE) {
return;
}
for (auto& frame : m_frames) {
// Retired buffers are appended in submit order, so the completed
// ones form a prefix.
SizeT completedCount = 0;
while (completedCount < frame.retiredCommandBuffers.size() &&
frame.retiredCommandBuffers[completedCount].submitIndex <= completedSubmitIndex) {
vkFreeCommandBuffers(m_device, m_commandPool, 1,
&frame.retiredCommandBuffers[completedCount].commandBuffer);
++completedCount;
}
if (completedCount > 0) {
frame.retiredCommandBuffers.erase(frame.retiredCommandBuffers.begin(),
frame.retiredCommandBuffers.begin() + completedCount);
}
}
}
void FrameContext::FreeAllRetiredCommandBuffers() {
for (auto& frame : m_frames) {
FreeRetiredCommandBuffers(frame);
}
}
void FrameContext::AssertValidFrameIndex(Uint32 frameIndex) const {
MOBILEGL_ASSERT(frameIndex < m_frames.size(), "FrameContext index out of range");
}
@@ -29,9 +29,7 @@ namespace MobileGL::MG_Backend::DirectVulkan {
VkPipelineStageFlags waitDstStageMask = VK_PIPELINE_STAGE_TOP_OF_PIPE_BIT;
VkSemaphore waitSemaphore = VK_NULL_HANDLE;
VkSemaphore signalSemaphore = VK_NULL_HANDLE;
// [0] = pre-pass command buffer (when recorded), then the frame
// command buffer; submitInfo.pCommandBuffers points here.
VkCommandBuffer commandBuffers[2] = {VK_NULL_HANDLE, VK_NULL_HANDLE};
VkCommandBuffer commandBuffer = VK_NULL_HANDLE;
VkSubmitInfo submitInfo{VK_STRUCTURE_TYPE_SUBMIT_INFO};
};
@@ -42,35 +40,17 @@ namespace MobileGL::MG_Backend::DirectVulkan {
VkPresentInfoKHR presentInfo{VK_STRUCTURE_TYPE_PRESENT_INFO_KHR};
};
// A command buffer submitted mid-frame (FlushPendingCommands), tagged
// with the submit-tracker index it was submitted under so it can be
// freed as soon as that submission is observed complete - without
// waiting for the slot's fence to be waited again (present-less flush
// loops never wait it).
struct RetiredCommandBuffer {
VkCommandBuffer commandBuffer = VK_NULL_HANDLE;
Uint64 submitIndex = 0;
};
struct FrameData {
VkCommandBuffer commandBuffer = VK_NULL_HANDLE;
// Pre-pass work stream: out-of-pass commands (deferred clear
// materialization, sampled-layout transitions) for resources the
// frame's recording has not touched yet. Submitted immediately
// BEFORE commandBuffer in the same vkQueueSubmit, so recording
// into it never has to split the frame's active render pass.
VkCommandBuffer preCommandBuffer = VK_NULL_HANDLE;
VkSemaphore imageAvailableSemaphore = VK_NULL_HANDLE;
VkFence imageInFlightFence = VK_NULL_HANDLE;
Bool isCommandRecording = false;
Bool hasCommandBufferRecorded = false;
Bool isPreCommandRecording = false;
Bool hasPreCommandBufferRecorded = false;
Bool imageAvailableSemaphoreConsumed = false;
// Command buffers submitted mid-frame (FlushPendingCommands),
// appended in submit order; freed once their submission is known
// complete (fence wait or completion poll).
Vector<RetiredCommandBuffer> retiredCommandBuffers;
// Command buffers submitted mid-frame (FlushPendingCommands) whose
// execution is only known complete once this slot's fence has been
// waited again; freed at that point.
Vector<VkCommandBuffer> retiredCommandBuffers;
// Submit-tracker index of this slot's most recent queue submission
// (written by the renderer at submit time).
Uint64 lastSubmitIndex = 0;
@@ -87,14 +67,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
VkCommandBuffer& BeginCommandRecording(VkCommandBufferUsageFlags flags = 0,
const VkCommandBufferInheritanceInfo* pInheritanceInfo = nullptr);
void EndCommandRecording();
// Lazily opens the pre-pass work stream (see FrameData::preCommandBuffer).
VkCommandBuffer BeginPreCommandRecording();
// Closes the pre stream if open, marking it for submission ahead of the
// frame command buffer. Safe to call when it never opened.
void EndPreCommandRecordingIfOpen();
// Drops an in-progress or recorded-but-unsubmitted pre stream (dropped
// frame recordings, swapchain recreation).
void AbandonPreCommandRecording();
VkResult InitializeSwapchainSemaphores(VkDevice device, Uint32 swapchainImageCount);
void DestroySwapchainSemaphores(VkDevice device);
Bool TransitionToPresent(VkImage image, VkImageLayout oldLayout,
@@ -107,18 +79,8 @@ namespace MobileGL::MG_Backend::DirectVulkan {
// Parks the current (already ended and submitted) command buffer on the
// slot's retired list and installs a freshly allocated one, so recording
// can restart while the submitted buffer is still executing. Retired
// buffers are freed after the slot's fence is next waited, or as soon
// as their submission is observed complete.
VkResult RetireCurrentCommandBuffer(Bool retirePreCommandBuffer = false);
// Frees every retired command buffer whose tagged submission index is
// known complete. Driven by the renderer's submit tracker on completion
// events (fence waits and non-blocking polls), so present-less flush
// loops reclaim their buffers without any extra wait.
void FreeRetiredCommandBuffersCompletedUpTo(Uint64 completedSubmitIndex);
// Frees every slot's retired command buffers. Only valid when the
// caller has proven every queue submission complete.
void FreeAllRetiredCommandBuffers();
// buffers are freed after the slot's fence is next waited.
VkResult RetireCurrentCommandBuffer();
Uint32 GetCurrentFrameIndex() const;
Uint32 GetFrameCount() const;
@@ -8,7 +8,6 @@
#include "PipelineFactory.h"
#include <algorithm>
namespace MobileGL::MG_Backend::DirectVulkan {
static const char* PrimitiveTopologyToString(VkPrimitiveTopology topology) {
@@ -205,12 +204,9 @@ namespace MobileGL::MG_Backend::DirectVulkan {
XXHASH_VERIFY(XXH64_update(m_hashState, &payload.topology, sizeof(payload.topology)));
XXHASH_VERIFY(
XXH64_update(m_hashState, &payload.primitiveRestartEnable, sizeof(payload.primitiveRestartEnable)));
XXHASH_VERIFY(XXH64_update(m_hashState, &payload.patchControlPoints, sizeof(payload.patchControlPoints)));
XXHASH_VERIFY(XXH64_update(m_hashState, &payload.polygonMode, sizeof(payload.polygonMode)));
XXHASH_VERIFY(XXH64_update(m_hashState, &payload.cullMode, sizeof(payload.cullMode)));
XXHASH_VERIFY(XXH64_update(m_hashState, &payload.frontFace, sizeof(payload.frontFace)));
XXHASH_VERIFY(
XXH64_update(m_hashState, &payload.provokingVertexMode, sizeof(payload.provokingVertexMode)));
XXHASH_VERIFY(XXH64_update(m_hashState, &payload.depthTestEnable, sizeof(payload.depthTestEnable)));
XXHASH_VERIFY(XXH64_update(m_hashState, &payload.depthWriteEnable, sizeof(payload.depthWriteEnable)));
XXHASH_VERIFY(XXH64_update(m_hashState, &payload.depthBiasEnable, sizeof(payload.depthBiasEnable)));
@@ -247,108 +243,23 @@ namespace MobileGL::MG_Backend::DirectVulkan {
const HashType hash = ComputeHash(payload);
auto it = m_cache.find(hash);
if (it != m_cache.end()) {
it->second.lastUsedFrame = m_frameCounter;
return it->second.pipeline;
return it->second;
}
VkPipeline pipeline = CreatePipeline(payload);
m_cache.emplace(hash, PipelineCacheEntry{pipeline, payload.programHash, payload.renderPass,
m_frameCounter});
m_cache.emplace(hash, pipeline);
return pipeline;
}
void PipelineFactory::DestroyAll() {
for (auto& pair : m_cache) {
if (pair.second.pipeline != VK_NULL_HANDLE) {
vkDestroyPipeline(m_device, pair.second.pipeline, nullptr);
if (pair.second != VK_NULL_HANDLE) {
vkDestroyPipeline(m_device, pair.second, nullptr);
}
}
m_cache.clear();
}
Uint32 PipelineFactory::OnFrameBoundary() {
++m_frameCounter;
// Sweep cadence and retire age mirror VkRenderPassManager::OnPresent: an entry
// idle for more than kRetireAgeFrames frame boundaries cannot be referenced by
// any in-flight command buffer (frames-in-flight <= MOBILEGL_MAGMA_FRAMESINFLIGHT),
// so immediate vkDestroyPipeline is safe. The caller must drop its "last
// pipeline" memo when this returns non-zero: the memo can return a cached
// handle without touching this cache, so an evicted pipeline may still be
// memoized (present-less flush loops never reset the memo per frame).
constexpr Uint64 kSweepInterval = 256;
constexpr Uint64 kRetireAgeFrames = 1024;
if ((m_frameCounter % kSweepInterval) != 0) {
return 0;
}
Uint32 evicted = 0;
for (auto it = m_cache.begin(); it != m_cache.end();) {
if (m_frameCounter - it->second.lastUsedFrame > kRetireAgeFrames) {
if (it->second.pipeline != VK_NULL_HANDLE) {
vkDestroyPipeline(m_device, it->second.pipeline, nullptr);
}
it = m_cache.erase(it);
++evicted;
} else {
++it;
}
}
if (evicted > 0) {
MGLOG_D("PipelineFactory::OnFrameBoundary: evicted %u idle pipelines (%zu remain)", evicted,
m_cache.size());
}
return evicted;
}
Uint32 PipelineFactory::EvictByRenderPasses(const Vector<VkRenderPass>& renderPasses) {
if (renderPasses.empty() || m_cache.empty()) {
return 0;
}
// Sorted-batch membership test keeps a mass eviction (shader-pack switch,
// dimension exit) at one O(cache * log batch) scan instead of one full scan
// per dying pass.
Vector<VkRenderPass> sortedPasses = renderPasses;
std::sort(sortedPasses.begin(), sortedPasses.end());
Uint32 evicted = 0;
for (auto it = m_cache.begin(); it != m_cache.end();) {
if (std::binary_search(sortedPasses.begin(), sortedPasses.end(), it->second.renderPass)) {
if (it->second.pipeline != VK_NULL_HANDLE) {
vkDestroyPipeline(m_device, it->second.pipeline, nullptr);
}
it = m_cache.erase(it);
++evicted;
} else {
++it;
}
}
if (evicted > 0) {
MGLOG_D("PipelineFactory::EvictByRenderPasses: evicted %u pipelines for %zu destroyed render passes",
evicted, sortedPasses.size());
}
return evicted;
}
Uint32 PipelineFactory::EvictByProgramHash(HashType programHash) {
Uint32 evicted = 0;
for (auto it = m_cache.begin(); it != m_cache.end();) {
if (it->second.programHash == programHash) {
if (it->second.pipeline != VK_NULL_HANDLE) {
vkDestroyPipeline(m_device, it->second.pipeline, nullptr);
}
it = m_cache.erase(it);
++evicted;
} else {
++it;
}
}
if (evicted > 0) {
MGLOG_D("PipelineFactory::EvictByProgramHash: evicted %u pipelines for program hash 0x%llx",
evicted, static_cast<unsigned long long>(programHash));
}
return evicted;
}
VkPipeline PipelineFactory::CreatePipeline(const PipelineCreatePayload& payload) const {
MOBILEGL_ASSERT(payload.stages != nullptr && !payload.stages->empty(), "PipelineFactory: stages are empty");
MOBILEGL_ASSERT(payload.vertexInputState != nullptr, "PipelineFactory: vertexInputState is null");
@@ -383,11 +294,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
ia.topology = payload.topology;
ia.primitiveRestartEnable = payload.primitiveRestartEnable ? VK_TRUE : VK_FALSE;
// Only a patch topology has a tessellation stage to configure; leaving the pointer null
// otherwise is what the spec expects.
VkPipelineTessellationStateCreateInfo tessellation{VK_STRUCTURE_TYPE_PIPELINE_TESSELLATION_STATE_CREATE_INFO};
tessellation.patchControlPoints = payload.patchControlPoints;
VkPipelineViewportStateCreateInfo vpci{VK_STRUCTURE_TYPE_PIPELINE_VIEWPORT_STATE_CREATE_INFO};
vpci.viewportCount = 1;
vpci.scissorCount = 1;
@@ -399,17 +305,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
raster.depthBiasEnable = payload.depthBiasEnable ? VK_TRUE : VK_FALSE;
raster.rasterizerDiscardEnable = payload.rasterizerDiscardEnable ? VK_TRUE : VK_FALSE;
raster.lineWidth = 1.0f;
// Only chain the struct when the mode is not Vulkan's implicit default: a device without
// VK_EXT_provoking_vertex enabled must never see this pNext entry, and the renderer's
// selector already collapses to FIRST in exactly that case - so a device without the
// extension produces a byte-identical VkGraphicsPipelineCreateInfo to before.
VkPipelineRasterizationProvokingVertexStateCreateInfoEXT provokingVertexState{
VK_STRUCTURE_TYPE_PIPELINE_RASTERIZATION_PROVOKING_VERTEX_STATE_CREATE_INFO_EXT};
if (payload.provokingVertexMode != VK_PROVOKING_VERTEX_MODE_FIRST_VERTEX_EXT) {
provokingVertexState.provokingVertexMode = payload.provokingVertexMode;
provokingVertexState.pNext = raster.pNext;
raster.pNext = &provokingVertexState;
}
VkPipelineMultisampleStateCreateInfo ms{VK_STRUCTURE_TYPE_PIPELINE_MULTISAMPLE_STATE_CREATE_INFO};
ms.rasterizationSamples = payload.rasterizationSamples;
@@ -463,8 +358,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
gpi.pStages = payload.stages->data();
gpi.pVertexInputState = payload.vertexInputState;
gpi.pInputAssemblyState = &ia;
gpi.pTessellationState =
payload.topology == VK_PRIMITIVE_TOPOLOGY_PATCH_LIST ? &tessellation : nullptr;
gpi.pViewportState = &vpci;
gpi.pRasterizationState = &raster;
gpi.pMultisampleState = &ms;
@@ -30,16 +30,9 @@ namespace MobileGL::MG_Backend::DirectVulkan {
Uint32 subpass = 0;
VkPrimitiveTopology topology = VK_PRIMITIVE_TOPOLOGY_TRIANGLE_LIST;
Bool primitiveRestartEnable = false;
// GL_PATCH_VERTICES; only read for a PATCH_LIST topology.
Uint32 patchControlPoints = 3;
VkPolygonMode polygonMode = VK_POLYGON_MODE_FILL;
VkCullModeFlags cullMode = VK_CULL_MODE_BACK_BIT;
VkFrontFace frontFace = VK_FRONT_FACE_CLOCKWISE;
// GL's provoking vertex, baked into the pipeline (VK_EXT_provoking_vertex). It selects
// which vertex a flat varying takes AND the vertex order transform feedback records for
// strips/fans, so it is part of the pipeline's identity, not dynamic state. Defaults to
// Vulkan's own convention, which is what a device without the extension gets.
VkProvokingVertexModeEXT provokingVertexMode = VK_PROVOKING_VERTEX_MODE_FIRST_VERTEX_EXT;
Bool depthTestEnable = false;
Bool depthWriteEnable = false;
Bool depthBiasEnable = false;
@@ -72,26 +65,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
VkPipeline GetOrCreatePipeline(const PipelineCreatePayload& payload);
void DestroyAll();
// Frame boundary hook: ages the pipeline cache and destroys long-unused entries
// (their command buffers retired many frames ago), mirroring
// VkRenderPassManager::OnPresent's sweep. Returns the number of pipelines
// destroyed so the caller can drop any memoized VkPipeline handle.
Uint32 OnFrameBoundary();
// Destroys every cached pipeline hashed on one of `renderPasses`. Only safe
// when the caller guarantees GPU idleness for them - the render-pass manager
// calls this (via the renderer) for passes its own >1024-boundary-idle sweep
// just evicted, and a pipeline hashed on those handles is only ever bound by
// draws that also hit the render-pass entries. Also closes the handle-recycling
// hazard: a recycled VkRenderPass value must never serve a stale pipeline.
// Batched: one cache scan regardless of how many passes died in the sweep.
// Returns the number destroyed (callers invalidate memos when non-zero).
Uint32 EvictByRenderPasses(const Vector<VkRenderPass>& renderPasses);
// Destroys every cached pipeline built from the program with content hash
// `programHash`. Called from the ProgramFactory eviction path, which proves the
// same >1024-boundary idleness (the program's pipelines are only bound by draws
// that stamp its factory entry). Returns the number destroyed.
Uint32 EvictByProgramHash(HashType programHash);
// Driver quirk: suppress depth writes on accumulation-blended pipelines. Multi-pass
// depth-equality rendering (a blended prepass writes depth that later passes re-test
// with an equality-inclusive compare on the re-rasterized geometry) requires
@@ -114,26 +87,12 @@ namespace MobileGL::MG_Backend::DirectVulkan {
static Bool ShouldSuppressDepthWrite(const PipelineCreatePayload& payload);
private:
struct PipelineCacheEntry {
VkPipeline pipeline = VK_NULL_HANDLE;
// The hashed inputs the eviction paths key on: programHash ties the entry to
// its ProgramFactory entry, renderPass records the exact handle the hash
// folded in (the hash is one-way, so targeted eviction needs them verbatim).
HashType programHash = 0;
VkRenderPass renderPass = VK_NULL_HANDLE;
// Frame-boundary counter value of the last GetOrCreatePipeline hit; drives
// cache eviction (see OnFrameBoundary).
Uint64 lastUsedFrame = 0;
};
VkPipeline CreatePipeline(const PipelineCreatePayload& payload) const;
VkDevice m_device = VK_NULL_HANDLE;
const VulkanRendererConfig& m_config;
VkPipelineCache m_pipelineCache = VK_NULL_HANDLE;
UnorderedMap<HashType, PipelineCacheEntry> m_cache;
// Monotonic frame-boundary counter (bumped in OnFrameBoundary) for cache aging.
Uint64 m_frameCounter = 0;
UnorderedMap<HashType, VkPipeline> m_cache;
static inline XXH64_state_t* m_hashState = XXH64_createState();
static inline Bool s_suppressBlendedDepthWrite = false;
};
@@ -923,403 +923,11 @@ namespace MobileGL::MG_Backend::DirectVulkan {
ProgramFactory::CompileOptionFlags m_transformFlags;
};
// Decorates the module's captured varyings for VK_EXT_transform_feedback:
// user outputs get XfbBuffer/XfbStride/Offset directly; a captured
// gl_Position (a gl_PerVertex member) is mirrored into a dedicated output
// variable copied before every OpReturn, BEFORE the position fixup runs,
// so the captured value is the shader's own (pre-remap) gl_Position.
class XfbCaptureDecoratePass final : public spvtools::opt::Pass {
public:
struct CapturedVarying {
std::string name;
Uint32 bufferIndex = 0;
Uint32 offsetBytes = 0;
};
const char* name() const override { return "mobilegl-xfb-capture-decorate"; }
XfbCaptureDecoratePass(Vector<CapturedVarying> varyings, Vector<Uint32> strides)
: m_varyings(Move(varyings)), m_strides(Move(strides)) {}
Status Process() override {
using namespace spvtools::opt;
if (m_varyings.empty()) return Status::SuccessWithoutChange;
auto entryPointIter = get_module()->entry_points().begin();
if (entryPointIter == get_module()->entry_points().end()) return Status::SuccessWithoutChange;
spvtools::opt::Instruction* entryPoint = &*entryPointIter;
const Uint32 entryFunctionId = entryPoint->GetSingleWordInOperand(1);
// Name -> result id map from the debug section.
std::unordered_map<std::string, Uint32> idsByName;
for (auto& debugInst : get_module()->debugs2()) {
if (debugInst.opcode() != spv::Op::OpName) continue;
idsByName[debugInst.GetInOperand(1).AsString()] = debugInst.GetSingleWordInOperand(0);
}
auto* decorationManager = context()->get_decoration_mgr();
const auto decorateForXfb = [&](Uint32 targetId, Uint32 bufferIndex, Uint32 offsetBytes) {
const Uint32 stride = bufferIndex < m_strides.size() ? m_strides[bufferIndex] : 0;
decorationManager->AddDecorationVal(targetId, static_cast<Uint32>(spv::Decoration::XfbBuffer),
bufferIndex);
decorationManager->AddDecorationVal(targetId, static_cast<Uint32>(spv::Decoration::XfbStride),
stride);
decorationManager->AddDecorationVal(targetId, static_cast<Uint32>(spv::Decoration::Offset),
offsetBytes);
};
Bool modified = false;
Bool needsPositionMirror = false;
Uint32 positionBufferIndex = 0;
Uint32 positionOffset = 0;
for (const auto& varying : m_varyings) {
if (varying.name == "gl_Position") {
needsPositionMirror = true;
positionBufferIndex = varying.bufferIndex;
positionOffset = varying.offsetBytes;
continue;
}
const auto idIt = idsByName.find(varying.name);
if (idIt == idsByName.end()) {
MGLOG_E("XfbCaptureDecoratePass: no SPIR-V variable named '%s'", varying.name.c_str());
continue;
}
decorateForXfb(idIt->second, varying.bufferIndex, varying.offsetBytes);
modified = true;
}
if (needsPositionMirror) {
modified |= MirrorPositionForCapture(entryFunctionId, *entryPoint, positionBufferIndex,
positionOffset, decorateForXfb);
}
if (!modified) return Status::SuccessWithoutChange;
context()->AddCapability(spv::Capability::TransformFeedback);
{
auto executionMode = MakeUnique<spvtools::opt::Instruction>(
context(), spv::Op::OpExecutionMode, 0, 0,
std::initializer_list<spvtools::opt::Operand>{
{SPV_OPERAND_TYPE_ID, {entryPoint->GetSingleWordInOperand(1)}},
{SPV_OPERAND_TYPE_EXECUTION_MODE, {static_cast<Uint32>(spv::ExecutionMode::Xfb)}}});
get_module()->AddExecutionMode(Move(executionMode));
}
context()->InvalidateAnalysesExceptFor(spvtools::opt::IRContext::kAnalysisNone);
return Status::SuccessWithChange;
}
private:
template <typename DecorateFn>
Bool MirrorPositionForCapture(Uint32 entryFunctionId, spvtools::opt::Instruction& entryPoint,
Uint32 bufferIndex, Uint32 offsetBytes, const DecorateFn& decorateForXfb) {
const Uint32 entryPointModel = entryPoint.GetSingleWordInOperand(0);
using namespace spvtools::opt;
PositionTargetInfo target{};
if (!FindPositionTarget(context(), &target)) {
MGLOG_E("XfbCaptureDecoratePass: gl_Position capture requested but no position output found");
return false;
}
if (!target.isMember) {
// Standalone gl_Position variable: decorate it directly.
decorateForXfb(target.variableId, bufferIndex, offsetBytes);
return true;
}
auto* typeManager = context()->get_type_mgr();
const Uint32 mirrorPointerTypeId =
typeManager->FindPointerToType(target.vectorTypeId, spv::StorageClass::Output);
if (mirrorPointerTypeId == 0) return false;
const Uint32 mirrorVariableId = context()->TakeNextId();
auto mirrorVariable = MakeUnique<Instruction>(
context(), spv::Op::OpVariable, mirrorPointerTypeId, mirrorVariableId,
std::initializer_list<Operand>{
{SPV_OPERAND_TYPE_STORAGE_CLASS, {static_cast<Uint32>(spv::StorageClass::Output)}}});
get_module()->AddGlobalValue(Move(mirrorVariable));
// A free output location: past every explicitly decorated output.
Uint32 mirrorLocation = 0;
for (auto& annotation : get_module()->annotations()) {
if (annotation.opcode() != spv::Op::OpDecorate ||
annotation.GetSingleWordInOperand(1) != static_cast<Uint32>(spv::Decoration::Location)) {
continue;
}
mirrorLocation = std::max(mirrorLocation, annotation.GetSingleWordInOperand(2) + 1);
}
auto* decorationManager = context()->get_decoration_mgr();
decorationManager->AddDecorationVal(mirrorVariableId,
static_cast<Uint32>(spv::Decoration::Location), mirrorLocation);
decorateForXfb(mirrorVariableId, bufferIndex, offsetBytes);
entryPoint.AddOperand({SPV_OPERAND_TYPE_ID, {mirrorVariableId}});
auto* function = context()->GetFunction(entryFunctionId);
if (function == nullptr) return false;
const auto model = static_cast<spv::ExecutionModel>(entryPointModel);
Bool injected = false;
for (auto& block : *function) {
for (auto instIter = block.begin(); instIter != block.end(); ++instIter) {
// Geometry stages capture per emitted vertex; other stages at return.
const Bool isInjectionSite =
model == spv::ExecutionModel::Geometry
? instIter->opcode() == spv::Op::OpEmitVertex
: instIter->opcode() == spv::Op::OpReturn;
if (!isInjectionSite) continue;
InstructionBuilder builder(context(), &*instIter, IRContext::kAnalysisNone);
const Uint32 memberIndexId = builder.GetUintConstantId(target.memberIndex);
auto* access =
builder.AddAccessChain(target.vectorPtrTypeId, target.variableId, {memberIndexId});
if (access == nullptr) return injected;
auto* value = builder.AddLoad(target.vectorTypeId, access->result_id());
if (value == nullptr) return injected;
builder.AddStore(mirrorVariableId, value->result_id());
injected = true;
}
}
return injected;
}
Vector<CapturedVarying> m_varyings;
Vector<Uint32> m_strides;
};
// Adreno 650 (driver 512.502) faults the GPU on an implicit-LOD sample of a full-screen
// colour render target: the texture unit's derivative path reads outside the image's
// allocation even though the sampler clamps LOD to 0 and the mapping is 1:1. MobileGL's
// own default-framebuffer blit shader works around it with textureLod, but an
// application's shader (Minecraft's blit.fsh is `texture(InSampler, texCoord)`) cannot be
// edited - so rewrite the sample at the SPIR-V level instead.
//
// The rewrite is only requested for draws whose every sampler binding is clamped to one
// mip level, where explicit LOD 0 is exactly what the implicit form must already produce:
// lambda' = clamp(lambda + bias, minLod, maxLod) with minLod = maxLod = 0. Bias and MinLod
// operands are therefore dropped rather than translated.
class ForceExplicitLod0SamplePass final : public spvtools::opt::Pass {
public:
const char* name() const override { return "force-explicit-lod0-sample"; }
Status Process() override {
Bool isFragment = false;
for (auto& entryPoint : get_module()->entry_points()) {
if (entryPoint.opcode() != spv::Op::OpEntryPoint) continue;
if (static_cast<spv::ExecutionModel>(entryPoint.GetSingleWordInOperand(0)) ==
spv::ExecutionModel::Fragment) {
isFragment = true;
break;
}
}
if (!isFragment) return Status::SuccessWithoutChange;
// Plan first, mutate second. Materializing the LOD constant is itself a module
// change, so it must not happen unless at least one rewrite is going to follow -
// otherwise the pass would grow the binary while reporting SuccessWithoutChange.
Vector<RewritePlan> plans;
for (auto& function : *get_module()) {
for (auto& block : function) {
for (auto& inst : block) {
RewritePlan plan{};
if (PlanRewrite(&inst, plan)) plans.push_back(Move(plan));
}
}
}
if (plans.empty()) return Status::SuccessWithoutChange;
const Uint32 zeroId = GetFloatZeroId();
if (zeroId == 0) return Status::SuccessWithoutChange;
for (auto& plan : plans) {
plan.operands.push_back({SPV_OPERAND_TYPE_ID, {zeroId}});
for (auto& operand : plan.trailingOperands) {
plan.operands.push_back(operand);
}
plan.instruction->SetOpcode(plan.opcode);
plan.instruction->SetInOperands(Move(plan.operands));
}
// Opcodes and operand lists changed underneath every cached analysis.
context()->InvalidateAnalysesExceptFor(spvtools::opt::IRContext::kAnalysisNone);
return Status::SuccessWithChange;
}
private:
struct RewritePlan {
spvtools::opt::Instruction* instruction = nullptr;
spv::Op opcode = spv::Op::OpNop;
// Everything up to and including the Image Operands mask; the Lod id and the
// trailing operand values are appended once the constant exists.
Vector<spvtools::opt::Operand> operands;
Vector<spvtools::opt::Operand> trailingOperands;
};
// Image Operands bits that may accompany an implicit-LOD sample, in the canonical
// ascending order SPIR-V requires the operand values to appear in.
static constexpr Uint32 kBias = 0x1;
static constexpr Uint32 kLod = 0x2;
static constexpr Uint32 kGrad = 0x4;
static constexpr Uint32 kConstOffset = 0x8;
static constexpr Uint32 kOffset = 0x10;
static constexpr Uint32 kConstOffsets = 0x20;
static constexpr Uint32 kSample = 0x40;
static constexpr Uint32 kMinLod = 0x80;
static constexpr Uint32 kKnownMask = 0xFF;
Uint32 GetFloatZeroId() {
// Reuse a 32-bit float type already in the module; a shader that samples always has
// one, and looking it up avoids depending on type-creation API details.
Uint32 floatTypeId = 0;
for (auto& inst : get_module()->types_values()) {
if (inst.opcode() == spv::Op::OpTypeFloat && inst.NumInOperands() >= 1 &&
inst.GetSingleWordInOperand(0) == 32) {
floatTypeId = inst.result_id();
break;
}
}
if (floatTypeId == 0) return 0;
const auto* floatType = context()->get_type_mgr()->GetType(floatTypeId);
if (floatType == nullptr) return 0;
const auto zeroBits = std::bit_cast<Uint32>(0.0f);
const auto* zeroConst = context()->get_constant_mgr()->GetConstant(floatType, {zeroBits});
if (zeroConst == nullptr) return 0;
auto* zeroInst = context()->get_constant_mgr()->GetDefiningInstruction(zeroConst);
return zeroInst != nullptr ? zeroInst->result_id() : 0;
}
static Bool MapOpcode(spv::Op op, spv::Op& outOpcode, Uint32& outFixedOperandCount) {
switch (op) {
case spv::Op::OpImageSampleImplicitLod:
outOpcode = spv::Op::OpImageSampleExplicitLod;
outFixedOperandCount = 2; // sampled image, coordinate
return true;
case spv::Op::OpImageSampleProjImplicitLod:
outOpcode = spv::Op::OpImageSampleProjExplicitLod;
outFixedOperandCount = 2;
return true;
case spv::Op::OpImageSampleDrefImplicitLod:
outOpcode = spv::Op::OpImageSampleDrefExplicitLod;
outFixedOperandCount = 3; // sampled image, coordinate, Dref
return true;
case spv::Op::OpImageSampleProjDrefImplicitLod:
outOpcode = spv::Op::OpImageSampleProjDrefExplicitLod;
outFixedOperandCount = 3;
return true;
default:
return false;
}
}
static Bool PlanRewrite(spvtools::opt::Instruction* inst, RewritePlan& outPlan) {
spv::Op newOpcode = spv::Op::OpNop;
Uint32 fixedCount = 0;
if (!MapOpcode(inst->opcode(), newOpcode, fixedCount)) return false;
if (inst->NumInOperands() < fixedCount) return false;
Uint32 mask = 0;
Uint32 next = fixedCount;
if (inst->NumInOperands() > fixedCount) {
mask = inst->GetSingleWordInOperand(fixedCount);
next = fixedCount + 1;
}
// An operand this pass does not model would be silently reordered or dropped, and
// Grad cannot legally accompany an implicit-LOD sample: leave such an instruction be.
if ((mask & ~kKnownMask) != 0 || (mask & kGrad) != 0) return false;
Vector<spvtools::opt::Operand> fixedOperands;
fixedOperands.reserve(fixedCount + 1);
for (Uint32 i = 0; i < fixedCount; ++i) {
fixedOperands.push_back(inst->GetInOperand(i));
}
// Collect the surviving operand values in the same ascending-bit order they were
// encoded in, so the rebuilt list stays canonical.
Uint32 keptMask = kLod;
Vector<spvtools::opt::Operand> keptOperands;
static constexpr Uint32 kOrderedBits[] = {kBias, kLod, kGrad, kConstOffset,
kOffset, kConstOffsets, kSample, kMinLod};
for (const Uint32 bit : kOrderedBits) {
if ((mask & bit) == 0) continue;
if (next >= inst->NumInOperands()) return false;
const spvtools::opt::Operand value = inst->GetInOperand(next++);
// Bias and MinLod only shift a lambda that is already clamped to 0, and any
// original Lod is replaced by the constant the caller appends.
if (bit == kBias || bit == kMinLod || bit == kLod) continue;
keptMask |= bit;
keptOperands.push_back(value);
}
fixedOperands.push_back({SPV_OPERAND_TYPE_IMAGE, {keptMask}});
outPlan.instruction = inst;
outPlan.opcode = newOpcode;
outPlan.operands = Move(fixedOperands);
outPlan.trailingOperands = Move(keptOperands);
return true;
}
};
spvtools::Optimizer::PassToken CreateForceExplicitLod0SamplePass() {
return spvtools::Optimizer::PassToken(MakeUnique<ForceExplicitLod0SamplePass>());
}
Bool TransformSpirvForExplicitLod0Sampling(const Vector<Uint>& input, Vector<Uint>& output) {
if (input.empty()) {
output.clear();
return true;
}
spvtools::Optimizer optimizer(SPV_ENV_VULKAN_1_3);
spvtools::OptimizerOptions options;
// Matches the position-fix pass: this build of spirv-tools asserts rather than
// reporting, so validation stays off in the shipping path.
options.set_run_validator(false);
optimizer.SetMessageConsumer([](spv_message_level_t, const char*, const spv_position_t&,
const char* message) {
MGLOG_E("Vulkan: explicit-LOD0 pass: %s", message != nullptr ? message : "");
});
optimizer.RegisterPass(CreateForceExplicitLod0SamplePass());
const Bool success = optimizer.Run(input.data(), input.size(), &output, options);
if (!success) {
MGLOG_E("Vulkan: explicit-LOD0 sampling pass failed; keeping the original module");
output = input;
}
return success;
}
spvtools::Optimizer::PassToken CreateGlToVulkanPositionFixPass(
ProgramFactory::CompileOptionFlags transformFlags) {
return spvtools::Optimizer::PassToken(MakeUnique<GlToVulkanPositionFixPass>(transformFlags));
}
Bool TransformSpirvForXfbCapture(const Vector<Uint>& input, Vector<Uint>& output,
const MG_State::GLState::ProgramObject& program) {
if (input.empty()) {
output.clear();
return true;
}
Vector<XfbCaptureDecoratePass::CapturedVarying> varyings;
varyings.reserve(program.GetTransformFeedbackVaryingCount());
for (const auto& varying : program.GetTransformFeedbackVaryings()) {
varyings.push_back({varying.name, varying.bufferIndex, varying.offsetBytes});
}
Vector<Uint32> strides;
strides.reserve(program.GetTransformFeedbackBufferCount());
for (SizeT i = 0; i < program.GetTransformFeedbackBufferCount(); ++i) {
strides.push_back(program.GetTransformFeedbackStride(static_cast<Uint32>(i)));
}
spvtools::Optimizer optimizer(SPV_ENV_VULKAN_1_3);
spvtools::OptimizerOptions options;
options.set_run_validator(false);
optimizer.SetMessageConsumer([](spv_message_level_t, const char*, const spv_position_t&,
const char* message) {
MGLOG_E("Vulkan: xfb capture pass: %s", message != nullptr ? message : "");
});
optimizer.RegisterPass(spvtools::Optimizer::PassToken(
MakeUnique<XfbCaptureDecoratePass>(Move(varyings), Move(strides))));
const Bool success = optimizer.Run(input.data(), input.size(), &output, options);
if (!success) {
MGLOG_E("Vulkan: xfb capture decoration pass failed; keeping the original module");
output = input;
}
return success;
}
Bool TransformSpirvForVulkanPositionFix(const Vector<Uint>& input, Vector<Uint>& output,
ProgramFactory::CompileOptionFlags transformFlags) {
if (input.empty()) {
@@ -1761,25 +1369,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
XXHASH_VERIFY(XXH64_update(m_hashState, &binding, sizeof(binding)));
}
// The transform feedback capture layout is baked into the modules by
// XfbCaptureDecoratePass rather than coming from the SPIR-V, so it has to be part of
// the key: two programs can share every shader and still capture differently, which
// is exactly what changing the buffer mode does (glTransformFeedbackVaryings with the
// same varyings but GL_SEPARATE_ATTRIBS instead of GL_INTERLEAVED_ATTRIBS). Only
// hashed for a capturing compile, so nothing else changes key.
if (flags & CompileOptionBit::XfbCapture) {
for (const auto& varying : program.GetTransformFeedbackVaryings()) {
XXHASH_VERIFY(XXH64_update(m_hashState, varying.name.data(), varying.name.size()));
XXHASH_VERIFY(XXH64_update(m_hashState, &varying.bufferIndex, sizeof(varying.bufferIndex)));
XXHASH_VERIFY(XXH64_update(m_hashState, &varying.offsetBytes, sizeof(varying.offsetBytes)));
}
const SizeT bufferCount = program.GetTransformFeedbackBufferCount();
for (SizeT i = 0; i < bufferCount; ++i) {
const Uint32 stride = program.GetTransformFeedbackStride(static_cast<Uint32>(i));
XXHASH_VERIFY(XXH64_update(m_hashState, &stride, sizeof(stride)));
}
}
HashType hash = XXH64_digest(m_hashState);
return hash;
}
@@ -2348,16 +1937,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
pipelineLayoutInfo.pSetLayouts = &entry.descriptorSetLayout;
VK_VERIFY(vkCreatePipelineLayout(m_device, &pipelineLayoutInfo, nullptr, &entry.pipelineLayout),
"ProgramFactory::ReflectLayout, vkCreatePipelineLayout");
// Built here rather than where bindingKinds is sized: at that point the vector is only
// zero-initialised and the kinds are assigned further down, so a list built there would be
// empty. Ascending by construction because the index walks upward.
entry.activeBindings.clear();
for (Uint32 binding = 0; binding < static_cast<Uint32>(entry.bindingKinds.size()); ++binding) {
if (entry.bindingKinds[binding] != DescriptorBindingKind::None) {
entry.activeBindings.push_back(binding);
}
}
}
const ProgramFactory::VkProgramObject& ProgramFactory::GetOrCreateProgram(
@@ -2371,20 +1950,11 @@ namespace MobileGL::MG_Backend::DirectVulkan {
}
auto it = m_cache.find(hash);
if (it != m_cache.end()) {
// Every draw/dispatch funnels through this lookup (the renderer memos only
// skip re-hashing, never the factory lookup), so an actively-used entry is
// stamped at least once per frame boundary and can never be aged out while
// any in-flight command buffer still references it.
it->second.lastUsedFrame = m_frameCounter;
return it->second;
}
// Structural change: the insert below can move every entry of this
// open-addressing map, so all memoised entry pointers die here.
++m_cacheStructureEpoch;
auto& entry = m_cache[hash];
entry.hash = hash;
entry.lastUsedFrame = m_frameCounter;
auto& shaders = program.GetAttachedShaders();
auto& spirv = program.GetGeneratedSpirv();
Vector<Vector<Uint>> moduleSpirvs(spirv.size());
@@ -2397,40 +1967,11 @@ namespace MobileGL::MG_Backend::DirectVulkan {
// Apply position fixup if needed
if (fixupStage != ShaderStage::Unknown && shaders[i] && shaders[i]->GetShaderStage() == fixupStage) {
const Vector<Uint>* fixupInput = &spv;
Vector<Uint> xfbSpirv;
if ((flags & ProgramFactory::CompileOptionBit::XfbCapture) &&
program.GetTransformFeedbackVaryingCount() > 0) {
// Decorate BEFORE the position fixup so a captured gl_Position
// mirror copies the shader's own (pre-remap) value.
if (TransformSpirvForXfbCapture(spv, xfbSpirv, program)) {
fixupInput = &xfbSpirv;
}
}
TransformSpirvForVulkanPositionFix(*fixupInput, moduleSpirvs[i], flags);
TransformSpirvForVulkanPositionFix(spv, moduleSpirvs[i], flags);
} else {
moduleSpirvs[i] = spv;
}
if ((flags & ProgramFactory::CompileOptionBit::ExplicitLod0Sampling) && shaders[i] &&
shaders[i]->GetShaderStage() == ShaderStage::Fragment) {
Vector<Uint> explicitLodSpirv;
if (TransformSpirvForExplicitLod0Sampling(moduleSpirvs[i], explicitLodSpirv)) {
moduleSpirvs[i] = Move(explicitLodSpirv);
}
}
// Vulkan's SPIR-V environment has no rectangle image dimension, so a
// GL_TEXTURE_RECTANGLE lookup has to become the 2D one the texture is really
// stored as - which addresses [0,1] where the application addressed texels.
{
Vector<Uint> rectLoweredSpirv;
if (MG_Util::ShaderTranspiler::ShaderCompiler::LowerRectImages(moduleSpirvs[i], rectLoweredSpirv) &&
!rectLoweredSpirv.empty()) {
moduleSpirvs[i] = Move(rectLoweredSpirv);
}
}
// GL apps depend on cross-program position invariance for multi-pass equality
// depth tests (MC 26.3's OIT re-draws the cloud geometry with GEQUAL against the
// depth its own first pass wrote); decorate Position outputs Invariant so
@@ -2471,33 +2012,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
}
}
// A 64-bit vertex input has to arrive as its 32-bit word pair: VK_FORMAT_R64*_SFLOAT is
// optional and lavapipe advertises none of them at all. The pass is unconditional so it
// always agrees with the Float64 case in VertexInputStateFactory::ToVkVertexFormat, and
// ReflectVertexInputs below then sees an ordinary uvec2/uvec4 input.
//
// Failure here is not recoverable and must not be swallowed: ToVkVertexFormat has already
// committed to R32G32{,B32A32}_UINT for the attribute, so a module still declaring
// `in double` would reconcile to Unknown and build a pipeline with a UINT format under a
// double input - garbage with no diagnostic anywhere.
if (shaders[i] && shaders[i]->GetShaderStage() == ShaderStage::Vertex) {
Vector<Uint> packedSpirv;
const Bool packOk = MG_Util::ShaderTranspiler::ShaderCompiler::PackDoubleVertexInputsForVulkan(
moduleSpirvs[i], packedSpirv);
MOBILEGL_ASSERT(packOk,
"ProgramFactory: 64-bit vertex input packing failed for program %u; the "
"vertex-input format and the shader input type now disagree",
program.GetExternalIndex());
if (packOk) {
moduleSpirvs[i] = std::move(packedSpirv);
} else {
MGLOG_E("ProgramFactory: failed to pack 64-bit vertex inputs for program %u; "
"double-typed vertex attributes will be fetched as uint32 words and not "
"reinterpreted",
program.GetExternalIndex());
}
}
// When Vulkan can legally access storage images without a statically declared
// format, let GL's glBindImageTexture format select the runtime image view. This
// provides desktop-driver-compatible behavior for packs such as iterationRP, whose
@@ -2554,43 +2068,4 @@ namespace MobileGL::MG_Backend::DirectVulkan {
return entry;
}
void ProgramFactory::OnFrameBoundary() {
++m_frameCounter;
// Sweep cadence and retire age mirror VkRenderPassManager::OnPresent: an entry
// idle for more than kRetireAgeFrames frame boundaries cannot be referenced by
// any in-flight command buffer (frames-in-flight <= MOBILEGL_MAGMA_FRAMESINFLIGHT),
// so its shader modules and layouts are destroyed immediately - no deferred-
// destroy machinery needed. Eviction is content-based, never tied to
// glDeleteProgram: the cache is content-hash-shared across GL programs, so a
// delete-driven erase could free an entry another live program still resolves.
// An evicted entry self-heals - the frontend program keeps its generated
// SPIR-V, so the next GetOrCreateProgram rebuilds it (this also covers the
// renderer's internal blit/depth-mipmap programs).
constexpr Uint64 kSweepInterval = 256;
constexpr Uint64 kRetireAgeFrames = 1024;
if ((m_frameCounter % kSweepInterval) != 0) {
return;
}
for (auto it = m_cache.begin(); it != m_cache.end();) {
if (m_frameCounter - it->second.lastUsedFrame > kRetireAgeFrames) {
const HashType hash = it->first;
const VkDescriptorSetLayout descriptorSetLayout = it->second.descriptorSetLayout;
MGLOG_D("ProgramFactory::OnFrameBoundary: evicting idle program entry hash=0x%llx",
static_cast<unsigned long long>(hash));
// erase runs ~VkProgramObject (modules/layouts destroyed); notify after
// so an observer never observes a half-destroyed entry through a lookup.
// Observers only need the handle values to purge their keyed caches.
++m_cacheStructureEpoch; // erase moves/kills entries: memoised pointers die
it = m_cache.erase(it);
if (m_evictionObserver != nullptr) {
m_evictionObserver->OnProgramEvicted(hash, descriptorSetLayout);
}
} else {
++it;
}
}
}
} // namespace MobileGL::MG_Backend::DirectVulkan
@@ -42,16 +42,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
SurfaceRotate90 = 1 << 2,
SurfaceRotate180 = 1 << 3,
SurfaceRotate270 = 1 << 4,
// Rewrites the fragment stage's implicit-LOD image samples to explicit LOD 0.
// Only ever set for a draw whose every sampler binding is clamped to a single mip
// level, which makes the two forms produce identical texels (the implicit lambda is
// clamped into [minLod, maxLod] = [0, 0] regardless of derivatives or bias).
ExplicitLod0Sampling = 1 << 5,
// Decorates the last vertex-processing stage's captured varyings with
// XfbBuffer/XfbStride/Offset (VK_EXT_transform_feedback). Set only for draws
// recorded while GL transform feedback is active, so plain draws keep the
// undecorated variant.
XfbCapture = 1 << 6,
};
using CompileOptionFlags = Flags<CompileOptionBit>;
using HashType = Uint64;
@@ -67,12 +57,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
VkDescriptorSetLayout descriptorSetLayout = VK_NULL_HANDLE;
VkPipelineLayout pipelineLayout = VK_NULL_HANDLE;
Vector<DescriptorBindingKind> bindingKinds;
// The bindings this program actually declares, ascending. bindingKinds is sized to the
// 256-binding cap while a real GL program uses 1-8, so the per-draw descriptor walk was
// scanning 256 slots to find a handful. MUST stay ascending: Vulkan consumes
// pDynamicOffsets in binding order and the writer pushes them in iteration order, so an
// unordered list would silently mis-pair dynamic offsets with their uniform blocks.
Vector<Uint32> activeBindings;
Vector<Uint32> dynamicBindings;
Vector<Int> uniformBlockIndexByBinding;
// Descriptor count per binding (1 except for UBO instance arrays, which occupy one
@@ -104,10 +88,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
// gl_FragDepth); shader-computed depth is immune to the cross-pipeline
// position-invariance quirk (see PipelineFactory::ShouldSuppressDepthWrite).
Bool fragmentReplacesDepth = false;
// Frame-boundary counter value of the last GetOrCreateProgram hit; drives
// cache eviction (see OnFrameBoundary). Mutable: the draw snapshot's memoised
// entry pointer re-stamps use through a const reference (StampProgramUse).
mutable Uint64 lastUsedFrame = 0;
static inline VkDevice s_device = VK_NULL_HANDLE;
@@ -121,7 +101,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
descriptorSetLayout = other.descriptorSetLayout;
pipelineLayout = other.pipelineLayout;
bindingKinds = std::move(other.bindingKinds);
activeBindings = std::move(other.activeBindings);
dynamicBindings = std::move(other.dynamicBindings);
uniformBlockIndexByBinding = std::move(other.uniformBlockIndexByBinding);
bindingDescriptorCounts = std::move(other.bindingDescriptorCounts);
@@ -145,7 +124,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
producerOutputComponentCount = other.producerOutputComponentCount;
fragmentInputComponentCount = other.fragmentInputComponentCount;
fragmentReplacesDepth = other.fragmentReplacesDepth;
lastUsedFrame = other.lastUsedFrame;
other.hash = 0;
other.descriptorSetLayout = VK_NULL_HANDLE;
other.pipelineLayout = VK_NULL_HANDLE;
@@ -157,7 +135,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
other.producerOutputComponentCount = 0;
other.fragmentInputComponentCount = 0;
other.fragmentReplacesDepth = false;
other.lastUsedFrame = 0;
}
VkProgramObject& operator=(VkProgramObject&& other) noexcept {
if (this == &other) {
@@ -170,7 +147,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
descriptorSetLayout = other.descriptorSetLayout;
pipelineLayout = other.pipelineLayout;
bindingKinds = std::move(other.bindingKinds);
activeBindings = std::move(other.activeBindings);
dynamicBindings = std::move(other.dynamicBindings);
uniformBlockIndexByBinding = std::move(other.uniformBlockIndexByBinding);
bindingDescriptorCounts = std::move(other.bindingDescriptorCounts);
@@ -194,7 +170,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
producerOutputComponentCount = other.producerOutputComponentCount;
fragmentInputComponentCount = other.fragmentInputComponentCount;
fragmentReplacesDepth = other.fragmentReplacesDepth;
lastUsedFrame = other.lastUsedFrame;
other.hash = 0;
other.descriptorSetLayout = VK_NULL_HANDLE;
other.pipelineLayout = VK_NULL_HANDLE;
@@ -206,7 +181,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
other.producerOutputComponentCount = 0;
other.fragmentInputComponentCount = 0;
other.fragmentReplacesDepth = false;
other.lastUsedFrame = 0;
return *this;
}
@@ -236,18 +210,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
}
};
// Notified when the OnFrameBoundary sweep destroys an aged-out cache entry,
// carrying the entry's content hash and the VkDescriptorSetLayout it owned.
// Dependent caches (compute pipelines, PipelineFactory entries, UniformManager's
// per-layout descriptor sets) must purge in the same step: after vkDestroy the
// layout handle value may be recycled for an unrelated layout, and the program
// hash may be re-inserted by a later rebuild of the same content.
class IEvictionObserver {
public:
virtual ~IEvictionObserver() = default;
virtual void OnProgramEvicted(HashType programHash, VkDescriptorSetLayout descriptorSetLayout) = 0;
};
explicit ProgramFactory(VkDevice device, const VulkanRendererConfig& config, Uint32 maxBindings = 16,
Bool shaderDrawParametersEnabled = false,
Bool unformattedFloatStorageImagesEnabled = false)
@@ -263,23 +225,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
const VkProgramObject& GetOrCreateProgram(
const MG_State::GLState::ProgramObject& program, CompileOptionFlags flags);
// Bumped whenever m_cache's STRUCTURE changes (any insert or erase): the cache is
// an open-addressing map holding entries by value, so both moves existing entries.
// A caller that memoised a VkProgramObject* may keep dereferencing it only while
// this is unchanged; on a bump it must re-run GetOrCreateProgram.
Uint64 GetCacheStructureEpoch() const { return m_cacheStructureEpoch; }
// A memoised entry pointer bypasses GetOrCreateProgram, whose per-lookup stamp is
// what keeps an in-use entry out of OnFrameBoundary's idle sweep - so such a
// caller must re-stamp the entry itself, at least once per frame boundary.
void StampProgramUse(const VkProgramObject& entry) const { entry.lastUsedFrame = m_frameCounter; }
// Observer may be null (no notifications). Not owned.
void SetEvictionObserver(IEvictionObserver* observer) { m_evictionObserver = observer; }
// Frame boundary hook: ages the program cache and evicts long-unused entries
// (their command buffers retired many frames ago), mirroring
// VkRenderPassManager::OnPresent's sweep.
void OnFrameBoundary();
static VkShaderStageFlagBits ToVkStage(ShaderStage stage);
static VkFormat ConvertSpirvImageFormatToVkFormat(SpvImageFormat format);
static SamplerNumericDomain UniformTypeToSamplerNumericDomain(GLenum glType);
@@ -321,11 +266,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
// shaderStorageImageReadWithoutFormat and shaderStorageImageWriteWithoutFormat.
Bool m_unformattedFloatStorageImagesEnabled = false;
mutable ProgramLookupCache m_lastLookup;
// Monotonic frame-boundary counter (bumped in OnFrameBoundary) for cache aging.
Uint64 m_frameCounter = 0;
// See GetCacheStructureEpoch(). Starts at 1 so a zero-initialized memo can never match.
Uint64 m_cacheStructureEpoch = 1;
IEvictionObserver* m_evictionObserver = nullptr;
static inline XXH64_state_t* m_hashState = XXH64_createState();
};
} // namespace MobileGL::MG_Backend::DirectVulkan
@@ -247,11 +247,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
m_surfaceFormat = {createInfo.imageFormat, createInfo.imageColorSpace};
m_extent = createInfo.imageExtent;
// The surface-space extent this swapchain was built from, i.e. before the
// quarter-turn swap above. Out-of-date checks must compare in THIS space: comparing a
// freshly queried currentExtent against the swapped m_extent flips axes every rotation
// and makes the comparison alternate forever.
m_surfaceExtent = defaultFramebufferExtent;
m_preTransform = createInfo.preTransform;
VK_VERIFY(vkCreateSwapchainKHR(device, &createInfo, nullptr, &m_swapchain));
@@ -262,9 +257,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
m_images.resize(imageCount, VK_NULL_HANDLE);
VK_VERIFY(vkGetSwapchainImagesKHR(device, m_swapchain, &imageCount, m_images.data()));
m_imageLayouts.assign(imageCount, VK_IMAGE_LAYOUT_UNDEFINED);
// Fresh swapchain images hold garbage until a render pass stores into them.
m_imageContentDefined.assign(imageCount, false);
m_depthStencilContentDefined.assign(imageCount, false);
CreateImageViews(device);
CreateDepthStencilResources(device, physicalDevice);
@@ -436,39 +428,9 @@ namespace MobileGL::MG_Backend::DirectVulkan {
m_images.clear();
m_imageLayouts.clear();
m_imageContentDefined.clear();
m_depthStencilContentDefined.clear();
m_preTransform = VK_SURFACE_TRANSFORM_IDENTITY_BIT_KHR;
}
Bool SwapchainObject::IsImageContentDefined(Uint32 index) const {
MOBILEGL_ASSERT(index < m_imageContentDefined.size(), "Swapchain image content index out of range");
return m_imageContentDefined[index];
}
void SwapchainObject::SetImageContentDefined(Uint32 index, Bool defined) {
MOBILEGL_ASSERT(index < m_imageContentDefined.size(), "Swapchain image content index out of range");
m_imageContentDefined[index] = defined;
}
Bool SwapchainObject::IsDepthStencilContentDefined(Uint32 index) const {
MOBILEGL_ASSERT(index < m_depthStencilContentDefined.size(),
"Swapchain depth/stencil content index out of range");
return m_depthStencilContentDefined[index];
}
void SwapchainObject::SetDepthStencilContentDefined(Uint32 index, Bool defined) {
MOBILEGL_ASSERT(index < m_depthStencilContentDefined.size(),
"Swapchain depth/stencil content index out of range");
m_depthStencilContentDefined[index] = defined;
}
void SwapchainObject::SetAllDepthStencilContentUndefined() {
for (SizeT i = 0; i < m_depthStencilContentDefined.size(); ++i) {
m_depthStencilContentDefined[i] = false;
}
}
VkImage SwapchainObject::GetImage(Uint32 index) const {
MOBILEGL_ASSERT(index < m_images.size(), "Swapchain image index out of range");
return m_images[index];
@@ -35,9 +35,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
VkSwapchainKHR GetHandle() const { return m_swapchain; }
const VkSurfaceFormatKHR& GetSurfaceFormat() const { return m_surfaceFormat; }
VkExtent2D GetExtent() const { return m_extent; }
// Surface-space extent (before the pre-rotation quarter-turn swap) this swapchain was
// created from - the value to compare a freshly queried currentExtent against.
VkExtent2D GetSurfaceExtent() const { return m_surfaceExtent; }
VkSurfaceTransformFlagBitsKHR GetPreTransform() const { return m_preTransform; }
const Vector<VkImage>& GetImages() const { return m_images; }
const Vector<VkImageView>& GetImageViews() const { return m_imageViews; }
@@ -52,21 +49,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
void SetImageLayout(Uint32 index, VkImageLayout layout);
SizeT GetImageCount() const { return m_images.size(); }
// EGL content-validity tracking for the default framebuffer. A color
// buffer's content is undefined once its image has been presented
// (EGL_BUFFER_DESTROYED swap behaviour, the implementation default),
// and every ancillary (depth/stencil) buffer's content is undefined
// after ANY swap regardless of swap behaviour (EGL 1.5 §3.10.1). The
// render-pass manager turns an undefined attachment's tile load into
// LOAD_OP_DONT_CARE. Flags start false (a fresh swapchain image holds
// garbage) and a render pass storing into an attachment sets it back
// to defined.
Bool IsImageContentDefined(Uint32 index) const;
void SetImageContentDefined(Uint32 index, Bool defined);
Bool IsDepthStencilContentDefined(Uint32 index) const;
void SetDepthStencilContentDefined(Uint32 index, Bool defined);
void SetAllDepthStencilContentUndefined();
private:
void CreateImageViews(VkDevice device);
void CreateDepthStencilResources(VkDevice device, VkPhysicalDevice physicalDevice);
@@ -81,7 +63,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
VkSwapchainKHR m_swapchain = VK_NULL_HANDLE;
VkSurfaceFormatKHR m_surfaceFormat{};
VkExtent2D m_extent{};
VkExtent2D m_surfaceExtent{};
VkSurfaceTransformFlagBitsKHR m_preTransform = VK_SURFACE_TRANSFORM_IDENTITY_BIT_KHR;
Vector<VkImage> m_images;
Vector<VkImageView> m_imageViews;
@@ -92,7 +73,5 @@ namespace MobileGL::MG_Backend::DirectVulkan {
Vector<VkDeviceMemory> m_depthStencilImageMemories;
Vector<VkImageView> m_depthStencilImageViews;
Vector<VkImageLayout> m_depthStencilImageLayouts;
Vector<Bool> m_imageContentDefined;
Vector<Bool> m_depthStencilContentDefined;
};
} // namespace MobileGL::MG_Backend::DirectVulkan
@@ -18,7 +18,6 @@
#include "MG_Util/Converters/MGToVk/TextureEnumConverter.h"
#include "MG_Util/Metrics/TextureMetrics.h"
#include <Config.h>
#include <algorithm>
#include <cstdio>
#include <cstdlib>
#include <cstring>
@@ -202,75 +201,22 @@ namespace MobileGL::MG_Backend::DirectVulkan {
for (auto& cacheEntryPair : frame.descriptorSetCacheByLayout) {
cacheEntryPair.second.cursor = 0;
}
// The frame's descriptor sets are recycled above, so last frame's reuse targets
// are gone: start the per-draw descriptor-reuse cache fresh this frame.
for (auto& entry : m_descriptorReuseMemo) {
entry.valid = false;
}
m_fastRebindMemo.valid = false;
m_lastBindValid = false;
// The frame's descriptor sets are recycled above, so last frame's reuse target
// is gone: start the per-draw descriptor-reuse cache fresh this frame.
m_hasLastDescriptor = false;
// Re-fingerprint the bound sampler set fresh this frame so any GL object address
// reuse cannot outlive a single frame (see SamplerResolveMemo).
for (auto& memo : m_samplerResolveMemo) {
memo.valid = false;
memo.infoValid = false;
}
}
void UniformManager::OnDescriptorSetLayoutDestroyed(VkDescriptorSetLayout descriptorSetLayout) {
SizeT purgedSets = 0;
for (auto& frame : m_frames) {
const auto it = frame.descriptorSetCacheByLayout.find(descriptorSetLayout);
if (it == frame.descriptorSetCacheByLayout.end()) {
continue;
}
// Free the sets back to their pools and credit the bucket accounting, so
// program churn recycles pool capacity instead of abandoning the slots.
// GPU-safe: the layout only dies after >1024 idle frame boundaries, so no
// in-flight command buffer references these sets.
for (const auto& cached : it->second.sets) {
if (cached.set == VK_NULL_HANDLE) {
continue;
}
vkFreeDescriptorSets(m_device, cached.pool, 1, &cached.set);
const auto bucket = std::find_if(
frame.descriptorPools.begin(), frame.descriptorPools.end(),
[&cached](const DescriptorPoolBucket& candidate) { return candidate.handle == cached.pool; });
if (bucket != frame.descriptorPools.end() && bucket->allocatedSets > 0) {
--bucket->allocatedSets;
}
}
purgedSets += it->second.sets.size();
frame.descriptorSetCacheByLayout.erase(it);
}
if (purgedSets > 0) {
// The per-draw reuse memo folds the layout handle into its signature; drop
// every entry so a recycled handle value cannot revive a purged set mid-frame.
for (auto& entry : m_descriptorReuseMemo) {
entry.valid = false;
}
// The rebind memo's set may be among the freed ones.
m_fastRebindMemo.valid = false;
MGLOG_D("UniformDescriptorBinder: freed %zu descriptor sets for destroyed layout", purgedSets);
}
}
Bool UniformManager::ResolveSamplerDescriptor(VkCommandBuffer commandBuffer,
const MG_State::GLState::ProgramObject& program,
const ProgramFactory::VkProgramObject& programObj,
Uint32 binding, VkDescriptorImageInfo& outImageInfo,
Bool trustUnchangedHint) const {
Uint32 binding, VkDescriptorImageInfo& outImageInfo) const {
MOBILEGL_ASSERT(m_textureManager != nullptr, "ResolveSamplerDescriptor: texture manager is null");
MOBILEGL_ASSERT(m_samplerManager != nullptr, "ResolveSamplerDescriptor: sampler manager is null");
// The caller proved every input of this binding's resolution unchanged since the
// last full resolve (which also filled the cache), so the whole chain below -
// texture/sampler resolution, completeness probe, sync, layout handling, sampler
// and view lookups - would recompute the identical descriptor.
if (trustUnchangedHint && binding < m_samplerResolveMemo.size() &&
m_samplerResolveMemo[binding].infoValid) {
outImageInfo = m_samplerResolveMemo[binding].info;
return true;
}
MOBILEGL_ASSERT(binding < programObj.samplerNameByBinding.size(),
"ResolveSamplerDescriptor: sampler binding %u name lookup out of range", binding);
// Raw-pointer resolve to skip the SharedPtr atomic refcount churn: the bound texture stays
@@ -284,24 +230,12 @@ namespace MobileGL::MG_Backend::DirectVulkan {
const auto& samplerOverride = textureUnit.GetSamplerObject();
const auto preferredTarget = programObj.samplerTextureTargetByBinding[binding];
SharedPtr<MG_State::GLState::ITextureObject> fallbackHolder;
// A texture that fails the completeness rules for the filter in effect reads
// (0, 0, 0, 1), which is exactly what the fallback texture holds - so it takes the
// same route as a sampler with nothing bound.
if (texture != nullptr &&
MG_State::GLState::SamplesAsIncompleteTexture(
texture, samplerOverride ? samplerOverride.get() : texture->GetSamplerObject().get())) {
texture = nullptr;
}
if (texture == nullptr) {
fallbackHolder = GetFallbackTexture(preferredTarget);
texture = fallbackHolder.get();
if (texture == nullptr) {
MGLOG_E("ResolveSamplerDescriptor: no fallback texture available for binding=%u ('%s') "
"location=%d unit=%d target=%d",
binding, programObj.samplerNameByBinding[binding].c_str(), location, unit,
static_cast<Int>(preferredTarget));
return false;
}
MOBILEGL_ASSERT(texture != nullptr,
"ResolveSamplerDescriptor: no fallback texture available for binding=%u location=%d unit=%d target=%d",
binding, location, unit, static_cast<Int>(preferredTarget));
MGLOG_W(
"ResolveSamplerDescriptor: using fallback texture for unbound sampler binding=%u ('%s') location=%d unit=%d target=%d",
binding, programObj.samplerNameByBinding[binding].c_str(), location, unit,
@@ -416,42 +350,31 @@ namespace MobileGL::MG_Backend::DirectVulkan {
const Uint16 samplerVersion = samplerToUse->GetVersion();
const Uint64 textureLifetimeId = texture->GetLifetimeId();
const Uint16 textureParamsVersion = texture->GetTextureParamsVersion();
// The sampler's LOD clamp depends on how many levels the sampled view exposes, and that
// follows uploads as well as GL parameters - so it belongs in the memo key too.
const Uint32 viewLevelCount = resource->sampledLevelCount;
if (memo.valid && memo.samplerLifetimeId == samplerLifetimeId && memo.samplerVersion == samplerVersion &&
memo.textureLifetimeId == textureLifetimeId && memo.textureParamsVersion == textureParamsVersion &&
memo.forceNearestFiltering == forceNearestFiltering && memo.viewLevelCount == viewLevelCount) {
memo.forceNearestFiltering == forceNearestFiltering) {
resolvedSampler = memo.sampler;
} else {
resolvedSampler = m_samplerManager->GetOrCreateSampler(*samplerToUse, *texture,
forceNearestFiltering, viewLevelCount);
resolvedSampler =
m_samplerManager->GetOrCreateSampler(*samplerToUse, *texture, forceNearestFiltering);
memo.samplerLifetimeId = samplerLifetimeId;
memo.samplerVersion = samplerVersion;
memo.textureLifetimeId = textureLifetimeId;
memo.textureParamsVersion = textureParamsVersion;
memo.forceNearestFiltering = forceNearestFiltering;
memo.viewLevelCount = viewLevelCount;
memo.sampler = resolvedSampler;
memo.valid = true;
}
} else {
resolvedSampler = m_samplerManager->GetOrCreateSampler(*samplerToUse, *texture, forceNearestFiltering,
resource->sampledLevelCount);
resolvedSampler =
m_samplerManager->GetOrCreateSampler(*samplerToUse, *texture, forceNearestFiltering);
}
outImageInfo = {
.sampler = resolvedSampler,
.imageView = sampledImageView,
.imageLayout = resource->layout,
};
if (outImageInfo.sampler == VK_NULL_HANDLE) {
return false;
}
if (binding < m_samplerResolveMemo.size()) {
m_samplerResolveMemo[binding].info = outImageInfo;
m_samplerResolveMemo[binding].infoValid = true;
}
return true;
return outImageInfo.sampler != VK_NULL_HANDLE;
}
Bool UniformManager::ResolveSamplerDescriptorOverride(
@@ -485,48 +408,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
return outImageInfo.sampler != VK_NULL_HANDLE;
}
Bool UniformManager::ProgramSamplesOnlySingleLevelTextures(
const MG_State::GLState::ProgramObject& program, const ProgramFactory::VkProgramObject& programObj) {
Bool sawSampler = false;
for (Uint32 binding = 0; binding < programObj.bindingKinds.size(); ++binding) {
if (programObj.bindingKinds[binding] != ProgramFactory::DescriptorBindingKind::CombinedImageSampler) {
continue;
}
const auto* texture = ResolveSamplerTextureRaw(program, programObj, binding);
if (texture == nullptr) return false;
const auto& levelRange = texture->GetLevelRange();
if (levelRange.x() != levelRange.y()) return false;
// An explicit-LOD sample is a single filtered tap, so it also gives up anisotropic
// filtering - which a single-level view can still have. Resolve the sampler exactly
// the way ResolveSamplerDescriptor does and bail if anisotropy would apply.
const Int location = programObj.samplerUniformLocationByBinding[binding];
const Int unit = ResolveSamplerUnitIndex(program, location, binding);
const auto& samplerOverride = MG_State::pGLContext->GetTextureUnitObject(unit).GetSamplerObject();
const auto* effectiveSampler =
samplerOverride ? samplerOverride.get() : texture->GetSamplerObject().get();
if (effectiveSampler == nullptr) return false;
if (effectiveSampler->GetMaxAnisotropy() > 1.0f &&
effectiveSampler->GetMinFilter() == SamplerFilterMode::Linear &&
effectiveSampler->GetMagFilter() == SamplerFilterMode::Linear) {
return false;
}
// An explicit LOD 0 makes lambda exactly 0, which is the magnification side of the
// min/mag decision. That only matches the implicit form when lambda could not have been
// positive anyway (the LOD clamp already pins it at or below 0), or when the two
// filters are the same and the choice cannot be observed.
const Float effectiveMaxLod = effectiveSampler->GetMipmapMode() == SamplerMipmapMode::None
? 0.0f
: effectiveSampler->GetMaxLod();
if (effectiveMaxLod > 0.0f && effectiveSampler->GetMinFilter() != effectiveSampler->GetMagFilter()) {
return false;
}
sawSampler = true;
}
return sawSampler;
}
Bool UniformManager::ResolveSamplerTexture(const MG_State::GLState::ProgramObject& program,
const ProgramFactory::VkProgramObject& programObj, Uint32 binding,
SharedPtr<MG_State::GLState::ITextureObject>& outTexture) {
@@ -629,11 +510,7 @@ namespace MobileGL::MG_Backend::DirectVulkan {
const VkDeviceSize texelSize =
static_cast<VkDeviceSize>(MG_Util::GetSizedInternalFormatSizeInBytes(internalFormat));
// glTextureBufferRange addresses a window of the buffer, not all of it; the whole-buffer
// forms report the buffer's current size here, so both go through the same clamp.
const VkDeviceSize rangeOffset = static_cast<VkDeviceSize>(textureBuffer->GetBufferRangeOffset());
const VkDeviceSize rangeSize = static_cast<VkDeviceSize>(textureBuffer->GetBufferRangeSizeInBytes());
VkDeviceSize viewRange = std::min(rangeSize, slice.size > rangeOffset ? slice.size - rangeOffset : 0);
VkDeviceSize viewRange = slice.size;
if (texelSize > 0) {
viewRange = (viewRange / texelSize) * texelSize;
}
@@ -646,7 +523,7 @@ namespace MobileGL::MG_Backend::DirectVulkan {
viewInfo.sType = VK_STRUCTURE_TYPE_BUFFER_VIEW_CREATE_INFO;
viewInfo.buffer = slice.buffer;
viewInfo.format = vkFormat;
viewInfo.offset = slice.offset + rangeOffset;
viewInfo.offset = slice.offset;
viewInfo.range = viewRange;
VkBufferView bufferView = VK_NULL_HANDLE;
@@ -691,14 +568,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
return false;
}
// The shader may write this buffer, and those writes land in GPU memory behind the
// frontend's CPU shadow - which is what MapBuffer and GetBufferSubData read.
// Host-visible coherent GPU residency makes the shadow BE that memory, so the
// results are visible without a readback path, exactly as for a capture buffer.
bufferObject->EnsureGpuResidentStorage();
// ... and the read that follows has to wait for this draw or dispatch to retire.
bufferObject->MarkGpuWritten();
BufferSlice slice{};
if (!m_bufferManager->AcquireResidentSlice(BufferKind::ShaderStorage, bufferObject, slice) || !slice.IsValid()) {
MGLOG_E("ResolveStorageBufferDescriptor: failed to sync GL buffer %u for block '%s'",
@@ -801,27 +670,15 @@ namespace MobileGL::MG_Backend::DirectVulkan {
}
SharedPtr<MG_State::GLState::ITextureObject> UniformManager::GetFallbackTexture(TextureTarget target) const {
// The fallback is a single-sampled 2D image, so it can only stand in for a sampler that
// would accept one. A multisample sampler in particular cannot: its descriptor demands a
// multisample view, and handing it this one is invalid Vulkan, not a degraded picture.
// Report that there is no fallback and let the caller decline the draw - aborting the
// process over an unbound sampler is never the right answer.
if (target != TextureTarget::Texture2D && target != TextureTarget::TextureRectangle) {
MGLOG_E("UniformManager::GetFallbackTexture: no fallback exists for target=%d",
static_cast<Int>(target));
return nullptr;
}
MOBILEGL_ASSERT(target == TextureTarget::Texture2D || target == TextureTarget::TextureRectangle,
"UniformManager::GetFallbackTexture: unsupported fallback target=%d",
static_cast<Int>(target));
if (m_fallbackTexture2D == nullptr) {
auto fallbackTexture = MakeShared<MG_State::GLState::TextureObject2D>(kFallbackTexture2DExternalIndex);
fallbackTexture->SetInternalFormat(TextureInternalFormat::RGBA8);
fallbackTexture->AllocateStorage(TextureUploadTarget::Texture2D, 0,
{.texelSize = {1, 1, 1}, .byteSize = 4});
// (0, 0, 0, 1): what GL reads from a texture that is not complete, and the only
// sensible answer for a sampler with nothing bound.
static Uint8 kOpaqueBlackTexel[4] = {0, 0, 0, 255};
fallbackTexture->UpdateMipmapSubData(TextureUploadTarget::Texture2D, 0,
{kOpaqueBlackTexel, sizeof(kOpaqueBlackTexel)});
fallbackTexture->MarkStorageDirty(TextureUploadTarget::Texture2D, 0, true);
m_fallbackTexture2D = fallbackTexture;
}
@@ -829,55 +686,10 @@ namespace MobileGL::MG_Backend::DirectVulkan {
return m_fallbackTexture2D;
}
Bool UniformManager::ResolveSampledBinding(const MG_State::GLState::ProgramObject& program,
const ProgramFactory::VkProgramObject& programObj,
Uint32 binding,
MG_State::GLState::ITextureObject*& outTexture,
const MG_State::GLState::SamplerObject*& outSampler) const {
// Open-coded ResolveSamplerTextureRaw so the unit is resolved once for both the
// texture and the sampler override - this runs per binding per full-path draw,
// and program-alternating draw streams take the full path on every draw.
MOBILEGL_ASSERT(MG_State::pGLContext != nullptr, "ResolveSampledBinding: GL context is null");
MOBILEGL_ASSERT(binding < programObj.samplerUniformLocationByBinding.size(),
"ResolveSampledBinding: sampler location binding %u out of range", binding);
MOBILEGL_ASSERT(binding < programObj.samplerTextureTargetByBinding.size(),
"ResolveSampledBinding: sampler target binding %u out of range", binding);
const Int location = programObj.samplerUniformLocationByBinding[binding];
const Int unit = ResolveSamplerUnitIndex(program, location, binding);
auto& textureUnit = MG_State::pGLContext->GetTextureUnitObject(unit);
const TextureTarget preferredTarget = programObj.samplerTextureTargetByBinding[binding];
MG_State::GLState::ITextureObject* texture =
textureUnit.GetBindingSlot(preferredTarget).GetBoundObject().get();
// Undefined default texture (name 0, no image) resolves as "unbound", exactly
// like ResolveSamplerTextureRaw reports it.
if (MG_State::GLState::IsUndefinedDefaultTexture(texture)) {
texture = nullptr;
}
if (texture == nullptr) {
// ResolveSamplerDescriptor will substitute the fallback texture for this binding;
// include it in the sampled set so the pre-render-pass sync/transition pass covers
// its first use instead of leaving that work to happen inside an active pass.
if (preferredTarget != TextureTarget::Texture2D &&
preferredTarget != TextureTarget::TextureRectangle) {
return false;
}
texture = GetFallbackTexture(preferredTarget).get();
}
const auto& samplerOverride = textureUnit.GetSamplerObject();
outTexture = texture;
outSampler = samplerOverride ? samplerOverride.get()
: (texture != nullptr ? texture->GetSamplerObject().get() : nullptr);
return true;
}
Bool UniformManager::CollectSampledTextures(const MG_State::GLState::ProgramObject& program,
const ProgramFactory::VkProgramObject& programObj,
Vector<MG_State::GLState::ITextureObject*>& outTextures,
Vector<SampledBindingRecord>* outBindingRecords) {
Vector<MG_State::GLState::ITextureObject*>& outTextures) {
outTextures.clear();
if (outBindingRecords != nullptr) {
outBindingRecords->clear();
}
const Uint32 bindingCount =
std::min<Uint32>(m_maxBindings, static_cast<Uint32>(programObj.bindingKinds.size()));
@@ -886,14 +698,17 @@ namespace MobileGL::MG_Backend::DirectVulkan {
continue;
}
MG_State::GLState::ITextureObject* texture = nullptr;
const MG_State::GLState::SamplerObject* sampler = nullptr;
if (!ResolveSampledBinding(program, programObj, binding, texture, sampler)) {
continue;
}
if (outBindingRecords != nullptr) {
outBindingRecords->push_back({texture != nullptr ? texture->GetLifetimeId() : 0,
sampler != nullptr ? sampler->GetLifetimeId() : 0});
MG_State::GLState::ITextureObject* texture = ResolveSamplerTextureRaw(program, programObj, binding);
if (!texture) {
// ResolveSamplerDescriptor will substitute the fallback texture for this binding;
// include it in the sampled set so the pre-render-pass sync/transition pass covers
// its first use instead of leaving that work to happen inside an active pass.
const TextureTarget preferredTarget = programObj.samplerTextureTargetByBinding[binding];
if (preferredTarget != TextureTarget::Texture2D &&
preferredTarget != TextureTarget::TextureRectangle) {
continue;
}
texture = GetFallbackTexture(preferredTarget).get();
}
auto found = std::find(outTextures.begin(), outTextures.end(), texture);
@@ -904,38 +719,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
return true;
}
Bool UniformManager::SampledBindingsUnchanged(const MG_State::GLState::ProgramObject& program,
const ProgramFactory::VkProgramObject& programObj,
const Vector<SampledBindingRecord>& previousRecords) const {
SizeT recordIndex = 0;
// Iterate only the bindings this program declares (ascending), exactly like
// BindProgramUniformBuffers: this runs per draw whenever the texture bind
// generation moved, and walking all m_maxBindings slots to find the 1-8 real
// ones dominated it.
for (const Uint32 binding : programObj.activeBindings) {
if (binding >= m_maxBindings) {
break; // ascending, so nothing past the cap can follow
}
if (programObj.bindingKinds[binding] != ProgramFactory::DescriptorBindingKind::CombinedImageSampler) {
continue;
}
MG_State::GLState::ITextureObject* texture = nullptr;
const MG_State::GLState::SamplerObject* sampler = nullptr;
if (!ResolveSampledBinding(program, programObj, binding, texture, sampler)) {
continue;
}
if (recordIndex >= previousRecords.size()) {
return false;
}
const SampledBindingRecord& record = previousRecords[recordIndex++];
if (record.textureLifetimeId != (texture != nullptr ? texture->GetLifetimeId() : 0) ||
record.samplerLifetimeId != (sampler != nullptr ? sampler->GetLifetimeId() : 0)) {
return false;
}
}
return recordIndex == previousRecords.size();
}
Bool UniformManager::CollectStorageImageTextures(
const MG_State::GLState::ProgramObject& program,
const ProgramFactory::VkProgramObject& programObj,
@@ -1107,17 +890,7 @@ namespace MobileGL::MG_Backend::DirectVulkan {
return false;
}
// Sized from what a real program declares, not from the 256-binding cap. A GL program's
// single descriptor set holds the bindings shader reflection found - typically 2 to 8 - so
// scaling by m_maxBindings declared 5 x 64 x 256 = 81,920 descriptors per pool and 245,760
// across the three frames in flight, which drivers that reserve backing store proportional
// to the declared count pay for at init. An outlier program is absorbed by the existing
// VK_ERROR_OUT_OF_POOL_MEMORY -> GrowFrameDescriptorPool path: pool sizes are aggregate
// budgets rather than per-set limits, and vkAllocateDescriptorSets is spec-required to
// report that error rather than fail hard.
static constexpr Uint32 kEstimatedBindingsPerSet = 8;
const Uint64 descriptorCount64 =
static_cast<Uint64>(maxSets) * static_cast<Uint64>(std::min(m_maxBindings, kEstimatedBindingsPerSet));
const Uint64 descriptorCount64 = static_cast<Uint64>(maxSets) * static_cast<Uint64>(m_maxBindings);
if (descriptorCount64 > static_cast<Uint64>(std::numeric_limits<Uint32>::max())) {
MGLOG_E("UniformDescriptorBinder::CreateDescriptorPool failed: descriptorCount overflow");
return false;
@@ -1138,11 +911,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
VkDescriptorPoolCreateInfo poolInfo{};
poolInfo.sType = VK_STRUCTURE_TYPE_DESCRIPTOR_POOL_CREATE_INFO;
// FREE_DESCRIPTOR_SET_BIT lets a destroyed layout's cached sets be freed back
// (OnDescriptorSetLayoutDestroyed) so program churn recycles pool capacity.
// The cost is on set allocation only, which happens when a layout's per-frame
// cache grows - never on the per-draw reuse path.
poolInfo.flags = VK_DESCRIPTOR_POOL_CREATE_FREE_DESCRIPTOR_SET_BIT;
poolInfo.maxSets = maxSets;
poolInfo.poolSizeCount = static_cast<Uint32>(std::size(poolSizes));
poolInfo.pPoolSizes = poolSizes;
@@ -1222,7 +990,7 @@ namespace MobileGL::MG_Backend::DirectVulkan {
auto& frame = m_frames[frameIndex];
auto& cache = frame.descriptorSetCacheByLayout[programObj.descriptorSetLayout];
if (cache.cursor < cache.sets.size()) {
outDescriptorSet = cache.sets[cache.cursor++].set;
outDescriptorSet = cache.sets[cache.cursor++];
} else {
VkResult allocResult = AllocateDescriptorSetsFromActivePool(frameIndex, programObj, outDescriptorSet);
if (allocResult == VK_ERROR_OUT_OF_POOL_MEMORY || allocResult == VK_ERROR_FRAGMENTED_POOL) {
@@ -1236,9 +1004,7 @@ namespace MobileGL::MG_Backend::DirectVulkan {
return allocResult;
}
// The successful allocation came from the bucket the alloc helper left
// active; record it so a layout-destroyed purge can free the set back.
cache.sets.push_back({outDescriptorSet, frame.descriptorPools[frame.activeDescriptorPoolIndex].handle});
cache.sets.push_back(outDescriptorSet);
++cache.cursor;
MGLOG_D("UniformDescriptorBinder: cached descriptor set count for frame=%u grew to %zu", frameIndex,
cache.sets.size());
@@ -1250,101 +1016,12 @@ namespace MobileGL::MG_Backend::DirectVulkan {
return VK_SUCCESS;
}
Bool UniformManager::ResolveDynamicUboDescriptor(const MG_State::GLState::ProgramObject& program,
const ProgramFactory::VkProgramObject& programObj,
Uint32 binding, Uint32 arrayElement, Uint32 frameIndex,
VkBuffer& outBuffer, VkDeviceSize& outRange,
Uint32& outDynamicOffset) {
UboBindResult ubo{};
const Bool hasPayload = ResolveUniformBufferPayload(program, programObj, binding, arrayElement, ubo);
MOBILEGL_ASSERT(hasPayload && (ubo.directBindable || (ubo.payload != nullptr && ubo.payloadSize > 0)),
"UniformDescriptorBinder::ResolveDynamicUboDescriptor failed: missing UBO payload on binding %u element %u",
binding, arrayElement);
if (ubo.directBindable) {
// Zero-copy: bind the app's resident VkBuffer directly, no per-draw memcpy.
outBuffer = ubo.buffer;
outRange = ubo.range;
outDynamicOffset = static_cast<Uint32>(ubo.dynamicOffset);
return true;
}
// Global-UBO slice reuse (see GlobalUboSliceMemo): unchanged
// uniform bytes re-use the slice already uploaded this frame.
const Bool isGlobalUbo = programObj.globalUboBinding == static_cast<Int>(binding) && arrayElement == 0;
const Uint64 uboFrameSerial = m_bufferManager->GetFrameSerial();
const Uint64 uboProgramLifetimeId = program.GetLifetimeId();
const Uint32 uboContentVersion = program.GetUBOContentVersion();
if (isGlobalUbo) {
for (const auto& memo : m_globalUboMemo) {
if (memo.buffer != VK_NULL_HANDLE && memo.programLifetimeId == uboProgramLifetimeId &&
memo.frameSerial == uboFrameSerial && memo.uboContentVersion == uboContentVersion &&
memo.range == static_cast<VkDeviceSize>(ubo.payloadSize)) {
outBuffer = memo.buffer;
outRange = memo.range;
outDynamicOffset = static_cast<Uint32>(memo.offset);
return true;
}
}
}
BufferSlice slice{};
if (!m_bufferManager->UploadTransient(BufferKind::Uniform, frameIndex, ubo.payload, ubo.payloadSize,
m_minDynamicOffsetAlignment, slice)) {
MOBILEGL_ASSERT(false,
"UniformDescriptorBinder::ResolveDynamicUboDescriptor failed: UBO upload failed on binding %u element %u",
binding, arrayElement);
return false;
}
outBuffer = slice.buffer;
outRange = ubo.payloadSize;
outDynamicOffset = static_cast<Uint32>(slice.offset);
if (isGlobalUbo) {
m_globalUboMemo[m_globalUboMemoNext] =
GlobalUboSliceMemo{uboProgramLifetimeId, uboFrameSerial, uboContentVersion,
slice.buffer, slice.offset, static_cast<VkDeviceSize>(ubo.payloadSize)};
m_globalUboMemoNext = (m_globalUboMemoNext + 1) % kGlobalUboMemoSize;
}
return true;
}
void UniformManager::BindDescriptorSetDeduped(VkCommandBuffer commandBuffer, VkPipelineBindPoint bindPoint,
VkPipelineLayout pipelineLayout, VkDescriptorSet descriptorSet,
const Vector<Uint32>& dynamicOffsets) {
// Skip the driver call when this exact binding is already live on the
// command buffer (see the bind-dedup shadow in the header).
const Uint32 offsetCount = static_cast<Uint32>(dynamicOffsets.size());
Bool identicalBind = m_lastBindValid && m_lastBindSet == descriptorSet &&
m_lastBindLayout == pipelineLayout && m_lastBindPoint == bindPoint &&
m_lastBindOffsetCount == offsetCount && offsetCount <= kMaxShadowedDynamicOffsets;
if (identicalBind) {
for (Uint32 i = 0; i < offsetCount; ++i) {
if (m_lastBindOffsets[i] != dynamicOffsets[i]) {
identicalBind = false;
break;
}
}
}
if (!identicalBind) {
vkCmdBindDescriptorSets(commandBuffer, bindPoint, pipelineLayout, 0, 1,
&descriptorSet, offsetCount, dynamicOffsets.data());
if (offsetCount <= kMaxShadowedDynamicOffsets) {
m_lastBindValid = true;
m_lastBindSet = descriptorSet;
m_lastBindLayout = pipelineLayout;
m_lastBindPoint = bindPoint;
m_lastBindOffsetCount = offsetCount;
std::copy_n(dynamicOffsets.data(), offsetCount, m_lastBindOffsets);
} else {
m_lastBindValid = false;
}
}
}
Bool UniformManager::BindProgramUniformBuffers(VkCommandBuffer commandBuffer,
const MG_State::GLState::ProgramObject& program,
const ProgramFactory::VkProgramObject& programObj,
Uint32 frameIndex,
VkPipelineBindPoint bindPoint,
const SamplerBindingOverride* samplerBindingOverride,
Bool samplerDescriptorsUnchangedHint) {
const SamplerBindingOverride* samplerBindingOverride) {
auto& frame = m_frames[frameIndex];
if (frame.descriptorPools.empty()) {
MGLOG_E("UniformDescriptorBinder::BindProgramUniformBuffers failed: frame descriptor pools are invalid");
@@ -1354,34 +1031,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
frame.activeDescriptorPoolIndex = 0;
}
// Dynamic-offset-only rebind (see FastRebindMemo in the header): the last
// cacheable walk of this exact program selected a set whose contents are
// provably still what this walk would write - the hint covers every
// sampler binding, and an unchanged (buffer, range) for the single
// dynamic UBO covers the rest - except the dynamic offset, which rebinding
// the SAME set delivers without any descriptor write.
const Bool cacheable = (samplerBindingOverride == nullptr);
if (cacheable && samplerDescriptorsUnchangedHint && m_fastRebindMemo.valid &&
m_fastRebindMemo.frameIndex == frameIndex &&
m_fastRebindMemo.programLifetimeId == program.GetLifetimeId() &&
m_fastRebindMemo.programHash == programObj.hash) {
VkBuffer uboBuffer = VK_NULL_HANDLE;
VkDeviceSize uboRange = 0;
Uint32 uboDynamicOffset = 0;
if (ResolveDynamicUboDescriptor(program, programObj, m_fastRebindMemo.uboBinding, 0, frameIndex,
uboBuffer, uboRange, uboDynamicOffset) &&
uboBuffer == m_fastRebindMemo.uboBuffer && uboRange == m_fastRebindMemo.uboRange) {
auto& fastOffsets = m_dynamicOffsetsScratch;
fastOffsets.clear();
fastOffsets.push_back(uboDynamicOffset);
BindDescriptorSetDeduped(commandBuffer, bindPoint, programObj.pipelineLayout,
m_fastRebindMemo.set, fastOffsets);
return true;
}
// Any mismatch (arena wrap or growth, direct-bind retarget, upload
// failure) falls through to the full walk, which re-records the memo.
}
// The descriptor set is chosen AFTER the writes are built (below), so a draw
// whose resolved descriptor content matches the previous draw can reuse that
// set and skip both AcquireDescriptorSet and vkUpdateDescriptorSets.
@@ -1413,21 +1062,13 @@ namespace MobileGL::MG_Backend::DirectVulkan {
texelBufferViews.reserve(m_maxBindings);
dynamicOffsets.reserve(programObj.dynamicBindings.size() + uboArrayExtra);
// Eligibility probe for FastRebindMemo, filled by this walk: exactly one
// dynamic-UBO descriptor (no arrayed elements) and otherwise only
// combined-image samplers, so the whole set's content is pinned by the
// sampler hint plus one (buffer, range) compare.
Uint32 dynamicUboDescriptorCount = 0;
Uint32 fastRebindUboBinding = 0;
Bool fastRebindKindsEligible = true;
// Iterate only the bindings this program declares. The old walk covered all 256 slots of
// bindingKinds on every draw to find the 1-8 a real program uses.
for (const Uint32 binding : programObj.activeBindings) {
if (binding >= m_maxBindings) {
break; // ascending, so nothing past the cap can follow
}
const Uint32 bindingCount =
std::min<Uint32>(m_maxBindings, static_cast<Uint32>(programObj.bindingKinds.size()));
for (Uint32 binding = 0; binding < bindingCount; ++binding) {
const auto kind = programObj.bindingKinds[binding];
if (kind == ProgramFactory::DescriptorBindingKind::None) {
continue;
}
VkWriteDescriptorSet write{};
write.sType = VK_STRUCTURE_TYPE_WRITE_DESCRIPTOR_SET;
@@ -1441,18 +1082,36 @@ namespace MobileGL::MG_Backend::DirectVulkan {
binding < programObj.bindingDescriptorCounts.size()
? std::max<Uint32>(1, programObj.bindingDescriptorCounts[binding])
: 1u;
dynamicUboDescriptorCount += descriptorCount;
fastRebindUboBinding = binding;
const SizeT firstBufferInfoIndex = bufferInfos.size();
for (Uint32 element = 0; element < descriptorCount; ++element) {
UboBindResult ubo{};
const Bool hasPayload =
ResolveUniformBufferPayload(program, programObj, binding, element, ubo);
MOBILEGL_ASSERT(hasPayload && ubo.payload != nullptr && ubo.payloadSize > 0,
"UniformDescriptorBinder::BindProgramUniformBuffers failed: missing UBO payload on binding %u element %u",
binding, element);
VkDescriptorBufferInfo bufferInfo{};
// Keep offset 0 (sub-range selected via the dynamic offset) so the hashed bufferInfo
// is stable across draws and the descriptor-set reuse cache keeps hitting.
bufferInfo.offset = 0;
Uint32 dynOffset = 0;
if (!ResolveDynamicUboDescriptor(program, programObj, binding, element, frameIndex,
bufferInfo.buffer, bufferInfo.range, dynOffset)) {
return false;
Uint32 dynOffset;
if (ubo.directBindable) {
// Zero-copy: bind the app's resident VkBuffer directly, no per-draw memcpy.
bufferInfo.buffer = ubo.buffer;
bufferInfo.range = ubo.range;
dynOffset = static_cast<Uint32>(ubo.dynamicOffset);
} else {
BufferSlice slice{};
if (!m_bufferManager->UploadTransient(BufferKind::Uniform, frameIndex, ubo.payload,
ubo.payloadSize, m_minDynamicOffsetAlignment, slice)) {
MOBILEGL_ASSERT(false, "UniformDescriptorBinder::BindProgramUniformBuffers failed: UBO upload failed on binding %u element %u",
binding, element);
return false;
}
bufferInfo.buffer = slice.buffer;
bufferInfo.range = ubo.payloadSize;
dynOffset = static_cast<Uint32>(slice.offset);
}
bufferInfos.push_back(bufferInfo);
// Dynamic offsets are consumed in binding order, then array element order,
@@ -1475,7 +1134,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
}
texelBufferViews.push_back(bufferView);
fastRebindKindsEligible = false;
write.descriptorType = VK_DESCRIPTOR_TYPE_UNIFORM_TEXEL_BUFFER;
write.pTexelBufferView = &texelBufferViews.back();
writes.push_back(write);
@@ -1489,7 +1147,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
}
bufferInfos.push_back(bufferInfo);
fastRebindKindsEligible = false;
write.descriptorType = VK_DESCRIPTOR_TYPE_STORAGE_BUFFER;
write.pBufferInfo = &bufferInfos.back();
writes.push_back(write);
@@ -1502,7 +1159,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
return false;
}
imageInfos.push_back(imageInfo);
fastRebindKindsEligible = false;
write.descriptorType = VK_DESCRIPTOR_TYPE_STORAGE_IMAGE;
write.pImageInfo = &imageInfos.back();
writes.push_back(write);
@@ -1515,8 +1171,7 @@ namespace MobileGL::MG_Backend::DirectVulkan {
samplerBindingOverride->sampler != nullptr) {
hasImage = ResolveSamplerDescriptorOverride(*samplerBindingOverride, imageInfo);
} else {
hasImage = ResolveSamplerDescriptor(commandBuffer, program, programObj, binding, imageInfo,
samplerDescriptorsUnchangedHint);
hasImage = ResolveSamplerDescriptor(commandBuffer, program, programObj, binding, imageInfo);
}
if (!hasImage) {
MGLOG_E(
@@ -1537,16 +1192,17 @@ namespace MobileGL::MG_Backend::DirectVulkan {
}
}
// Reuse a recent draw's descriptor set when the resolved content is
// Reuse the previous draw's descriptor set when the resolved content is
// byte-identical (only the bind-time dynamic offsets differ). The signature
// covers the descriptor-set layout + every write's binding/type/count + the
// pointed-to buffer/image/texel-buffer infos (all value-initialized, so no
// padding noise). Correctness: bindings are re-resolved every draw, so the
// signature always reflects the current state and reuse happens only on an
// exact match; a reused set is never re-acquired within a frame (the acquire
// exact match; the reused set is never re-acquired within a frame (the acquire
// cursor only advances), so its written contents survive; the layout is part of
// the signature so reuse never crosses programs. Sampler overrides (blits)
// bypass and invalidate the cache.
const Bool cacheable = (samplerBindingOverride == nullptr);
Uint64 signature = 0xcbf29ce484222325ULL;
{
const auto mix64 = [&signature](Uint64 word) {
@@ -1574,17 +1230,8 @@ namespace MobileGL::MG_Backend::DirectVulkan {
mixWords(texelBufferViews.data(), texelBufferViews.size() * sizeof(VkBufferView));
}
VkDescriptorSet reusedSet = VK_NULL_HANDLE;
if (cacheable) {
for (const auto& entry : m_descriptorReuseMemo) {
if (entry.valid && entry.signature == signature) {
reusedSet = entry.set;
break;
}
}
}
if (reusedSet != VK_NULL_HANDLE) {
descriptorSet = reusedSet;
if (cacheable && m_hasLastDescriptor && signature == m_lastDescriptorSignature) {
descriptorSet = m_lastBoundDescriptorSet;
} else {
VkResult allocResult = AcquireDescriptorSet(frameIndex, programObj, descriptorSet);
if (allocResult != VK_SUCCESS || descriptorSet == VK_NULL_HANDLE) {
@@ -1598,33 +1245,13 @@ namespace MobileGL::MG_Backend::DirectVulkan {
if (!writes.empty()) {
vkUpdateDescriptorSets(m_device, static_cast<Uint32>(writes.size()), writes.data(), 0, nullptr);
}
if (cacheable) {
m_descriptorReuseMemo[m_descriptorReuseMemoNext] =
DescriptorReuseEntry{signature, descriptorSet, true};
m_descriptorReuseMemoNext = (m_descriptorReuseMemoNext + 1) % kDescriptorReuseMemoSize;
} else {
for (auto& entry : m_descriptorReuseMemo) {
entry.valid = false;
}
}
m_lastBoundDescriptorSet = descriptorSet;
m_lastDescriptorSignature = signature;
m_hasLastDescriptor = cacheable;
}
// (Re)record the dynamic-offset-only rebind memo. Recording on every
// cacheable walk (allocated or reused set alike - both hold exactly the
// content just computed) keeps the single slot tracking the most recent
// program; a non-cacheable override walk drops it alongside the reuse
// memo above.
if (cacheable && fastRebindKindsEligible && dynamicUboDescriptorCount == 1) {
m_fastRebindMemo = FastRebindMemo{
/*valid=*/true, frameIndex, program.GetLifetimeId(), programObj.hash,
fastRebindUboBinding, bufferInfos[0].buffer,
bufferInfos[0].range, descriptorSet};
} else {
m_fastRebindMemo.valid = false;
}
BindDescriptorSetDeduped(commandBuffer, bindPoint, programObj.pipelineLayout, descriptorSet,
dynamicOffsets);
vkCmdBindDescriptorSets(commandBuffer, bindPoint, programObj.pipelineLayout, 0, 1,
&descriptorSet, static_cast<Uint32>(dynamicOffsets.size()), dynamicOffsets.data());
return true;
}
} // namespace MobileGL::MG_Backend::DirectVulkan
@@ -39,56 +39,18 @@ namespace MobileGL::MG_Backend::DirectVulkan {
void Shutdown();
void BeginFrame(Uint32 frameIndex);
// A command buffer (re)began recording: descriptor bindings recorded into
// the previous buffer do not carry over, so drop the bind-dedup shadow.
void OnCommandBufferBoundary() { m_lastBindValid = false; }
// A ProgramFactory eviction just destroyed this layout: purge every frame
// slot's cached descriptor sets for it, so a recycled handle value can never
// stale-hit sets written for the dead layout's bindings. The sets are
// vkFreeDescriptorSets'd back to their pools (created with
// FREE_DESCRIPTOR_SET_BIT) and the pool accounting is credited, so program
// churn recycles pool capacity instead of abandoning it. GPU-safe: the layout
// only dies after >1024 idle frame boundaries, so no in-flight command buffer
// references its sets. This is the only eviction path for the per-layout
// caches - a live layout's entry must never be purged (its sets would be
// unreachable pool slots), so there is deliberately no age-based sweep here.
void OnDescriptorSetLayoutDestroyed(VkDescriptorSetLayout descriptorSetLayout);
// One record per visited CombinedImageSampler binding (post fallback substitution,
// in binding order): the resolved texture and effective sampler, as never-reused
// lifetime ids so a freed-and-reallocated object at the same heap address can only
// MISS a comparison, never false-hit it (same ABA rule as SamplerResolveMemo).
struct SampledBindingRecord {
Uint64 textureLifetimeId = 0;
Uint64 samplerLifetimeId = 0;
};
Bool CollectSampledTextures(const MG_State::GLState::ProgramObject& program,
const ProgramFactory::VkProgramObject& programObj,
Vector<MG_State::GLState::ITextureObject*>& outTextures,
Vector<SampledBindingRecord>* outBindingRecords = nullptr);
// Shadow-compare for the SetupDraw fast path: re-runs the CollectSampledTextures
// walk and reports whether every visited binding still resolves to the recorded
// (texture, effective sampler) pair. A texture bind generation bump alone (e.g. a
// redundant glBindSampler, which always bumps it) does not prove the sampled set
// moved; this walk does, without rebuilding the set or falling off the fast path.
Bool SampledBindingsUnchanged(const MG_State::GLState::ProgramObject& program,
const ProgramFactory::VkProgramObject& programObj,
const Vector<SampledBindingRecord>& previousRecords) const;
Vector<MG_State::GLState::ITextureObject*>& outTextures);
Bool CollectStorageImageTextures(const MG_State::GLState::ProgramObject& program,
const ProgramFactory::VkProgramObject& programObj,
Vector<MG_State::GLState::ITextureObject*>& outTextures) const;
// samplerDescriptorsUnchangedHint: the caller (SetupDraw fast path) proved that
// every input of every combined-image-sampler resolution is unchanged since the
// previous draw's resolve - same (texture, sampler) per binding, texture params
// sum, sampling-resolution generation (sampler params + texture shape), image
// epochs AND per-resource layout values - so the per-binding cached
// VkDescriptorImageInfo may be reused without re-running the resolve chain.
Bool BindProgramUniformBuffers(VkCommandBuffer commandBuffer,
const MG_State::GLState::ProgramObject& program,
const ProgramFactory::VkProgramObject& programObj,
Uint32 frameIndex,
VkPipelineBindPoint bindPoint = VK_PIPELINE_BIND_POINT_GRAPHICS,
const SamplerBindingOverride* samplerBindingOverride = nullptr,
Bool samplerDescriptorsUnchangedHint = false);
const SamplerBindingOverride* samplerBindingOverride = nullptr);
// Pure format-policy helper kept public for host regression tests. Formatted storage
// images use their shader qualifier; transformed float images use glBindImageTexture's
@@ -96,16 +58,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
static VkFormat ResolveStorageImageViewFormat(VkFormat reflectedFormat, GLenum bindingFormat,
VkFormat resourceFormat, Bool useBindingFormat);
// True when the program reads at least one sampler and every one of them is bound to a
// texture whose GL level range is a single level. Such a sampler resolves to
// minLod = maxLod = 0 (see VkSamplerManager::GetOrCreateSampler), so an implicit-LOD sample
// and an explicit LOD 0 sample must read the same texel - which is what makes the
// ExplicitLod0Sampling SPIR-V rewrite safe to request. Deliberately conservative: it reads
// only GL state, so a texture that ends up single-level for another reason (one uploaded
// level under a wide level range) merely misses the rewrite.
static Bool ProgramSamplesOnlySingleLevelTextures(const MG_State::GLState::ProgramObject& program,
const ProgramFactory::VkProgramObject& programObj);
private:
struct DescriptorPoolBucket {
VkDescriptorPool handle = VK_NULL_HANDLE;
@@ -113,16 +65,8 @@ namespace MobileGL::MG_Backend::DirectVulkan {
Uint32 allocatedSets = 0;
};
// A cached descriptor set together with the pool it was allocated from, so a
// layout-destroyed purge can vkFreeDescriptorSets it back and credit the
// owning bucket's accounting.
struct CachedDescriptorSet {
VkDescriptorSet set = VK_NULL_HANDLE;
VkDescriptorPool pool = VK_NULL_HANDLE;
};
struct DescriptorSetCacheEntry {
Vector<CachedDescriptorSet> sets;
Vector<VkDescriptorSet> sets;
Uint32 cursor = 0;
};
@@ -138,15 +82,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
static Bool ResolveSamplerTexture(const MG_State::GLState::ProgramObject& program,
const ProgramFactory::VkProgramObject& programObj, Uint32 binding,
SharedPtr<MG_State::GLState::ITextureObject>& outTexture);
// Shared per-binding resolution for CollectSampledTextures and
// SampledBindingsUnchanged, so membership and comparison can never diverge:
// texture after the fallback substitution (may still be null when no fallback
// exists), effective sampler = unit override else the texture's own sampler.
// False = the binding is skipped (unbound with a non-2D fallback target).
Bool ResolveSampledBinding(const MG_State::GLState::ProgramObject& program,
const ProgramFactory::VkProgramObject& programObj, Uint32 binding,
MG_State::GLState::ITextureObject*& outTexture,
const MG_State::GLState::SamplerObject*& outSampler) const;
// Raw-pointer variant for the per-draw sampled-texture walk (CollectSampledTextures):
// the bound texture stays alive through the draw via GL binding state, so callers that
// only need the pointer skip the SharedPtr copy's atomic refcount churn.
@@ -154,13 +89,9 @@ namespace MobileGL::MG_Backend::DirectVulkan {
const MG_State::GLState::ProgramObject& program,
const ProgramFactory::VkProgramObject& programObj, Uint32 binding);
SharedPtr<MG_State::GLState::ITextureObject> GetFallbackTexture(TextureTarget target) const;
// trustUnchangedHint: reuse this binding's cached VkDescriptorImageInfo outright
// (see BindProgramUniformBuffers' samplerDescriptorsUnchangedHint for the proof
// obligations the caller carries).
Bool ResolveSamplerDescriptor(VkCommandBuffer commandBuffer, const MG_State::GLState::ProgramObject& program,
const ProgramFactory::VkProgramObject& programObj, Uint32 binding,
VkDescriptorImageInfo& outImageInfo,
Bool trustUnchangedHint = false) const;
VkDescriptorImageInfo& outImageInfo) const;
Bool ResolveSamplerDescriptorOverride(const SamplerBindingOverride& samplerBindingOverride,
VkDescriptorImageInfo& outImageInfo) const;
Bool ResolveTexelBufferDescriptor(const MG_State::GLState::ProgramObject& program,
@@ -186,21 +117,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
Bool ResolveUniformBufferPayload(const MG_State::GLState::ProgramObject& program,
const ProgramFactory::VkProgramObject& programObj, Uint32 binding,
Uint32 arrayElement, UboBindResult& out) const;
// Shared resolution of one dynamic-UBO binding element into the
// (buffer, range, dynamicOffset) triple the descriptor consumes: direct
// bind, global-slice reuse, or transient upload. Used by the full walk
// and by the dynamic-offset-only rebind (see FastRebindMemo).
Bool ResolveDynamicUboDescriptor(const MG_State::GLState::ProgramObject& program,
const ProgramFactory::VkProgramObject& programObj, Uint32 binding,
Uint32 arrayElement, Uint32 frameIndex, VkBuffer& outBuffer,
VkDeviceSize& outRange, Uint32& outDynamicOffset);
// The vkCmdBindDescriptorSets tail shared by the full walk and the
// dynamic-offset-only rebind: skips the driver call when this exact
// binding is already live on the command buffer (see the bind-dedup
// shadow below), otherwise binds and refreshes the shadow.
void BindDescriptorSetDeduped(VkCommandBuffer commandBuffer, VkPipelineBindPoint bindPoint,
VkPipelineLayout pipelineLayout, VkDescriptorSet descriptorSet,
const Vector<Uint32>& dynamicOffsets);
Bool CreateDescriptorPool(Uint32 maxSets, VkDescriptorPool& outPool) const;
Bool GrowFrameDescriptorPool(FrameResources& frame, Uint32 frameIndex);
VkResult AllocateDescriptorSetsFromActivePool(
@@ -231,82 +147,14 @@ namespace MobileGL::MG_Backend::DirectVulkan {
Vector<VkBufferView> m_texelBufferViewsScratch;
Vector<Uint32> m_dynamicOffsetsScratch;
// Descriptor-set reuse across recent draws (see BindProgramUniformBuffers).
// When a draw's resolved descriptor content is byte-identical to one memoized
// earlier, reuse that VkDescriptorSet and skip AcquireDescriptorSet +
// vkUpdateDescriptorSets - only the bind-time dynamic offsets differ. Four
// entries with round-robin replacement rather than one: draws alternating
// between two programs (MC's chunk<->entity ping-pong) would thrash a single
// slot into a full re-allocate+write every draw. Reset each frame in BeginFrame
// because the frame's descriptor sets are recycled there.
struct DescriptorReuseEntry {
Uint64 signature = 0;
VkDescriptorSet set = VK_NULL_HANDLE;
Bool valid = false;
};
static constexpr Uint32 kDescriptorReuseMemoSize = 4;
DescriptorReuseEntry m_descriptorReuseMemo[kDescriptorReuseMemoSize];
Uint32 m_descriptorReuseMemoNext = 0;
// Dynamic-offset-only rebind (see BindProgramUniformBuffers): records the
// descriptor set selected by the last cacheable full walk of a program
// whose active bindings are exactly one dynamic UBO (single descriptor)
// plus combined-image samplers. When the next call proves every sampler
// descriptor input unchanged (samplerDescriptorsUnchangedHint) and the
// UBO re-resolves to the SAME VkBuffer+range - only the dynamic offset
// moved, the per-draw glUniform case - the walk collapses to: resolve one
// offset, rebind the recorded set with new pDynamicOffsets (Vulkan allows
// rebinding the same set with different dynamic offsets).
// Invalidation inventory: BeginFrame clears it (the frame's sets are
// recycled) and the frameIndex field guards cross-frame confusion on top;
// OnDescriptorSetLayoutDestroyed clears it (the set may be freed); a
// sampler-override walk clears it (mirrors m_descriptorReuseMemo); a
// program relink bumps the backend state version and thus programObj.hash
// so the key misses; the program lifetime id is never reused, so a
// deleted-and-recreated program misses; a texture/sampler/binding change
// drops the hint upstream; an arena wrap or growth resolves a different
// VkBuffer and misses. AcquireDescriptorSet's per-frame cursor only
// advances, so the recorded set is never re-written within its frame.
struct FastRebindMemo {
Bool valid = false;
Uint32 frameIndex = 0;
Uint64 programLifetimeId = 0;
ProgramFactory::HashType programHash = 0;
Uint32 uboBinding = 0;
VkBuffer uboBuffer = VK_NULL_HANDLE;
VkDeviceSize uboRange = 0;
VkDescriptorSet set = VK_NULL_HANDLE;
};
FastRebindMemo m_fastRebindMemo;
// vkCmdBindDescriptorSets dedup: consecutive draws with a static uniform
// block resolve to the same set AND the same dynamic offsets, so the
// driver call can be skipped outright. Command-buffer-scope state; reset
// via OnCommandBufferBoundary whenever a recording (re)begins. Keyed on
// layout+bind point, so a pipeline-layout switch always rebinds.
static constexpr Uint32 kMaxShadowedDynamicOffsets = 8;
Bool m_lastBindValid = false;
VkDescriptorSet m_lastBindSet = VK_NULL_HANDLE;
VkPipelineLayout m_lastBindLayout = VK_NULL_HANDLE;
VkPipelineBindPoint m_lastBindPoint = VK_PIPELINE_BIND_POINT_GRAPHICS;
Uint32 m_lastBindOffsetCount = 0;
Uint32 m_lastBindOffsets[kMaxShadowedDynamicOffsets] = {};
// Global-UBO transient-slice reuse: MC leaves the default uniform block
// untouched across long GUI/terrain runs, so the per-draw re-upload of
// the same bytes can reuse the slice uploaded earlier THIS frame (frame
// serial guards arena recycling; the content version guards writes).
struct GlobalUboSliceMemo {
Uint64 programLifetimeId = 0;
Uint64 frameSerial = 0;
Uint32 uboContentVersion = 0;
VkBuffer buffer = VK_NULL_HANDLE;
VkDeviceSize offset = 0;
VkDeviceSize range = 0;
};
static constexpr Uint32 kGlobalUboMemoSize = 4;
GlobalUboSliceMemo m_globalUboMemo[kGlobalUboMemoSize];
Uint32 m_globalUboMemoNext = 0;
// Descriptor-set reuse across consecutive draws (see BindProgramUniformBuffers).
// When a draw's resolved descriptor content is byte-identical to the previous
// draw's, reuse the same VkDescriptorSet and skip AcquireDescriptorSet +
// vkUpdateDescriptorSets - only the bind-time dynamic offsets differ. Reset each
// frame in BeginFrame because the frame's descriptor sets are recycled there.
VkDescriptorSet m_lastBoundDescriptorSet = VK_NULL_HANDLE;
Uint64 m_lastDescriptorSignature = 0;
Bool m_hasLastDescriptor = false;
// Per-binding fast path over VkSamplerManager's content-hashed sampler cache, which
// stays the source of truth: its key hashes all sampler+texture state, so two distinct
@@ -324,7 +172,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
Uint64 samplerLifetimeId = 0;
Uint64 textureLifetimeId = 0;
VkSampler sampler = VK_NULL_HANDLE;
Uint32 viewLevelCount = 0;
Uint16 samplerVersion = 0;
Uint16 textureParamsVersion = 0;
Bool forceNearestFiltering = false;
@@ -336,13 +183,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
SamplerNumericDomain viewFormatDomain = SamplerNumericDomain::Unknown;
VkFormat viewFormat = VK_FORMAT_UNDEFINED;
Bool viewFormatValid = false;
// Whole resolved descriptor from this binding's last full resolve. Reused
// ONLY under ResolveSamplerDescriptor's trustUnchangedHint, whose caller
// proves every resolve input unchanged; cleared with the per-frame reset
// (the cached VkSampler outlives a frame only via a fresh resolve, which
// also re-stamps it against VkSamplerManager's frame-boundary sweep).
VkDescriptorImageInfo info{};
Bool infoValid = false;
};
mutable Vector<SamplerResolveMemo> m_samplerResolveMemo;
};
@@ -29,17 +29,9 @@ namespace MobileGL::MG_Backend::DirectVulkan {
XXHASH_VERIFY(XXH64_update(m_hashState, &attr.Stride, sizeof(attr.Stride)));
XXHASH_VERIFY(XXH64_update(m_hashState, &attr.Offset, sizeof(attr.Offset)));
XXHASH_VERIFY(XXH64_update(m_hashState, &attr.IsInteger, sizeof(attr.IsInteger)));
XXHASH_VERIFY(XXH64_update(m_hashState, &attr.IsLong, sizeof(attr.IsLong)));
XXHASH_VERIFY(XXH64_update(m_hashState, &attr.IsBgra, sizeof(attr.IsBgra)));
XXHASH_VERIFY(XXH64_update(m_hashState, &attr.Divisor, sizeof(attr.Divisor)));
// The buffer's heap address is an identity component of the key: a freed
// buffer's reused address can alias an old cache entry, but only under a
// byte-identical attribute layout - and the entry payload is a pure function
// of the hashed inputs, with the draw path re-resolving bindingBufferKeys
// against the live VAO attribute pointers, so an aliased hit returns exactly
// what a rebuild would. Address drift only grows the map; the OnFrameBoundary
// aging sweep bounds that.
const SizeT bufferKey = reinterpret_cast<SizeT>(attr.Buffer.get());
XXHASH_VERIFY(XXH64_update(m_hashState, &bufferKey, sizeof(bufferKey)));
}
@@ -59,33 +51,14 @@ namespace MobileGL::MG_Backend::DirectVulkan {
const VertexInputStateFactory::BackendVertexInputState& VertexInputStateFactory::GetOrCreateVertexInputState(
const MG_State::GLState::VertexArrayObject& vao) {
// Per-draw fast path: the VAO carries a pointer to its resolved entry,
// valid while its config version and the cache's eviction epoch both
// match - no re-hash, no map lookup.
const void* memoState = nullptr;
Uint64 memoEpoch = 0;
if (vao.GetBackendStateMemo(memoState, memoEpoch) && memoEpoch == m_evictionEpoch) {
const auto* entry = static_cast<const BackendVertexInputState*>(memoState);
entry->lastUsedFrameBoundary = m_frameBoundaryCounter;
return *entry;
}
const BackendVertexInputState& entry = GetOrCreateVertexInputState(vao, GetOrComputeHash(vao));
vao.SetBackendStateMemo(&entry, m_evictionEpoch);
// Also mirror the layout identity and the two per-draw masks into the VAO's aux
// memo (pure VALUES derived from the VAO configuration, so config-version
// guarding alone is sound). The draw fast path reads them from the VAO object it
// already touched instead of chasing into this entry - see PackVertexInputAuxMemo.
vao.SetBackendAuxMemo(entry.layoutHash,
PackVertexInputAuxMasks(entry.unsupportedAttribMask, entry.attributeLocationMask));
return entry;
return GetOrCreateVertexInputState(vao, GetOrComputeHash(vao));
}
const VertexInputStateFactory::BackendVertexInputState& VertexInputStateFactory::GetOrCreateVertexInputState(
const MG_State::GLState::VertexArrayObject& vao, HashType hash) {
auto it = m_cache.find(hash);
if (it != m_cache.end()) {
it->second->lastUsedFrameBoundary = m_frameBoundaryCounter;
return *it->second;
return it->second;
}
VertexInputStateBuilder builder;
@@ -94,7 +67,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
Vector<Uint32> bindingAttributeLocations;
Vector<Bool> bindingUsesClientMemory;
Vector<VertexStreamConversion> bindingConversions;
Vector<VkVertexInputBindingDivisorDescriptionEXT> bindingDivisors;
Uint32 unsupportedAttribMask = 0;
for (Uint32 location = 0; location < MG_State::GLState::VertexArrayObject::MAX_VERTEX_ATTRIBS; ++location) {
@@ -104,7 +76,7 @@ namespace MobileGL::MG_Backend::DirectVulkan {
}
const VkFormat sourceVkFormat =
ToVkVertexFormat(attr.Type, attr.Size, attr.Normalized, attr.IsInteger, attr.IsBgra, attr.IsLong);
ToVkVertexFormat(attr.Type, attr.Size, attr.Normalized, attr.IsInteger, attr.IsBgra);
if (sourceVkFormat == VK_FORMAT_UNDEFINED) {
MGLOG_E("Unsupported vertex attribute layout (location=%u, type=%s, size=%d): the array is "
"enabled but cannot be mapped to a VkFormat",
@@ -188,51 +160,14 @@ namespace MobileGL::MG_Backend::DirectVulkan {
bindingConversions.push_back(conversion);
builder.AddBinding(binding, stride, inputRate);
builder.AddAttribute(location, binding, vkFormat, 0);
// Divisor 1 is what VK_VERTEX_INPUT_RATE_INSTANCE already means; only anything
// else needs the extension to say it.
if (inputRate == VK_VERTEX_INPUT_RATE_INSTANCE && attr.Divisor != 1) {
bindingDivisors.push_back({binding, static_cast<Uint32>(attr.Divisor)});
}
}
const auto& state = builder.Build();
auto& slot = m_cache[hash];
if (!slot) {
slot = MakeUnique<BackendVertexInputState>();
}
BackendVertexInputState& entry = *slot;
auto& entry = m_cache[hash];
entry.hash = hash;
entry.lastUsedFrameBoundary = m_frameBoundaryCounter;
entry.bindingDivisors = Move(bindingDivisors);
entry.bindings = builder.GetBindings();
entry.attributes = builder.GetAttributes();
// See the layoutHash declaration: hash only the resolved layout, never
// buffer identities, so identical layouts across VAOs/buffers agree.
XXHASH_VERIFY(XXH64_reset(m_hashState, 0));
for (const auto& binding : entry.bindings) {
XXHASH_VERIFY(XXH64_update(m_hashState, &binding.binding, sizeof(binding.binding)));
XXHASH_VERIFY(XXH64_update(m_hashState, &binding.stride, sizeof(binding.stride)));
XXHASH_VERIFY(XXH64_update(m_hashState, &binding.inputRate, sizeof(binding.inputRate)));
}
for (const auto& attribute : entry.attributes) {
XXHASH_VERIFY(XXH64_update(m_hashState, &attribute.location, sizeof(attribute.location)));
XXHASH_VERIFY(XXH64_update(m_hashState, &attribute.binding, sizeof(attribute.binding)));
XXHASH_VERIFY(XXH64_update(m_hashState, &attribute.format, sizeof(attribute.format)));
XXHASH_VERIFY(XXH64_update(m_hashState, &attribute.offset, sizeof(attribute.offset)));
}
for (const auto& divisor : entry.bindingDivisors) {
XXHASH_VERIFY(XXH64_update(m_hashState, &divisor.binding, sizeof(divisor.binding)));
XXHASH_VERIFY(XXH64_update(m_hashState, &divisor.divisor, sizeof(divisor.divisor)));
}
XXHASH_VERIFY(XXH64_update(m_hashState, &unsupportedAttribMask, sizeof(unsupportedAttribMask)));
entry.layoutHash = XXH64_digest(m_hashState);
entry.attributeLocationMask = 0;
for (const auto& attribute : entry.attributes) {
if (attribute.location < 32u) {
entry.attributeLocationMask |= (1u << attribute.location);
}
}
entry.bindingBufferKeys = std::move(bindingBufferKeys);
entry.bindingBaseOffsets = std::move(bindingBaseOffsets);
entry.bindingAttributeLocations = std::move(bindingAttributeLocations);
@@ -242,45 +177,11 @@ namespace MobileGL::MG_Backend::DirectVulkan {
entry.state = state;
entry.state.pVertexBindingDescriptions = entry.bindings.empty() ? nullptr : entry.bindings.data();
entry.state.pVertexAttributeDescriptions = entry.attributes.empty() ? nullptr : entry.attributes.data();
if (!entry.bindingDivisors.empty()) {
entry.divisorState.vertexBindingDivisorCount = static_cast<Uint32>(entry.bindingDivisors.size());
entry.divisorState.pVertexBindingDivisors = entry.bindingDivisors.data();
entry.state.pNext = &entry.divisorState;
} else {
entry.state.pNext = nullptr;
}
return entry;
}
void VertexInputStateFactory::OnFrameBoundary() {
++m_frameBoundaryCounter;
// Sweep occasionally; evict entries whose last hit is far in the past.
// Erasure happens only here, never mid-frame: the draw path holds a
// reference into the current entry across its setup, and unordered_map
// erase would invalidate it. Entries are CPU-side only, so no GPU-idle
// proof is needed; an evicted entry that is used again is simply rebuilt
// from the VAO state (same hash, same content).
constexpr Uint64 kSweepInterval = 256;
constexpr Uint64 kRetireAgeBoundaries = 1024;
if ((m_frameBoundaryCounter % kSweepInterval) != 0) {
return;
}
for (auto it = m_cache.begin(); it != m_cache.end();) {
if (m_frameBoundaryCounter - it->second->lastUsedFrameBoundary > kRetireAgeBoundaries) {
it = m_cache.erase(it);
// Invalidate every VAO's state-pointer memo: the erased node's
// address may be reused by a future insert.
++m_evictionEpoch;
} else {
++it;
}
}
}
VkFormat VertexInputStateFactory::ToVkVertexFormat(DataType type, Int size, Bool normalized, Bool isInteger,
Bool isBgra, Bool isLong) {
Bool isBgra) {
if (isBgra) {
// GL_BGRA: four reversed-order components, always normalized (enforced at validation), only
// legal with GL_UNSIGNED_BYTE or a 2_10_10_10 type. The reversed VkFormats put the
@@ -305,22 +206,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
case DataType::Int2101010Rev:
if (isInteger || size != 4) return VK_FORMAT_UNDEFINED;
return normalized ? VK_FORMAT_A2B10G10R10_SNORM_PACK32 : VK_FORMAT_A2B10G10R10_SSCALED_PACK32;
case DataType::Float64:
// A 64-bit attribute is fetched as its 32-bit word pair and bitcast back to double in the
// shader (PackDoubleVertexInputsPass does the shader half). That is bit-exact and, unlike
// VK_FORMAT_R64*_SFLOAT, needs no format capability: lavapipe reports bufferFeatures = 0
// for every R64 float format, so a native 64-bit vertex fetch is simply unavailable there
// while shaderFloat64 is not. Both halves key off nothing but the attribute being long,
// so they always agree without extra plumbing.
if (!isLong || isInteger || normalized) return VK_FORMAT_UNDEFINED;
switch (size) {
case 1: return VK_FORMAT_R32G32_UINT;
case 2: return VK_FORMAT_R32G32B32A32_UINT;
// A dvec3/dvec4 input is 6/8 uint32 components: no single VkFormat, and GL spreads it
// over two attribute locations, which the location-per-VAO-index model here does not
// express. Declined rather than fetched wrong.
default: return VK_FORMAT_UNDEFINED;
}
case DataType::Float32:
switch (size) {
case 1: return VK_FORMAT_R32_SFLOAT;
@@ -27,18 +27,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
struct BackendVertexInputState {
HashType hash = 0;
// Hash of the resolved Vulkan vertex layout only (bindings, attributes,
// unsupported mask) - NO buffer identities. `hash` mixes buffer heap
// addresses so per-chunk VBOs mint a fresh identity per buffer; keying
// pipelines on that minted one VkPipeline per chunk section for an
// identical layout, defeating pipeline reuse and the per-draw memo.
// Pipelines depend only on the layout, so they key on this instead.
HashType layoutHash = 0;
// Frame boundary of the last cache hit; entries idle past the
// OnFrameBoundary retirement age are evicted (CPU heap only).
// Mutable: the VAO's state-pointer memo fast path stamps it through
// a const entry reference.
mutable Uint64 lastUsedFrameBoundary = 0;
Vector<VkVertexInputBindingDescription> bindings;
Vector<VkVertexInputAttributeDescription> attributes;
Vector<SizeT> bindingBufferKeys;
@@ -50,17 +38,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
// absent from `attributes`, so without this mask the draw path cannot tell them apart from
// a genuinely disabled array and would silently feed the shader the current attribute value.
Uint32 unsupportedAttribMask = 0;
// Bitmask of `attributes[i].location` - the draw path needs it up to
// three times per draw, so it is baked once at build time.
Uint32 attributeLocationMask = 0;
// Per-binding glVertexAttribDivisor values other than 1. Vulkan's instance input
// rate advances once per instance and nothing else, so anything else has to be
// stated through VK_EXT_vertex_attribute_divisor. Empty when every instanced
// binding uses divisor 1, which is what the plain input rate already means.
Vector<VkVertexInputBindingDivisorDescriptionEXT> bindingDivisors;
VkPipelineVertexInputDivisorStateCreateInfoEXT divisorState{
VK_STRUCTURE_TYPE_PIPELINE_VERTEX_INPUT_DIVISOR_STATE_CREATE_INFO_EXT
};
VkPipelineVertexInputStateCreateInfo state{
VK_STRUCTURE_TYPE_PIPELINE_VERTEX_INPUT_STATE_CREATE_INFO
};
@@ -71,13 +48,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
~VertexInputStateFactory() = default;
VertexInputStateFactory(const VertexInputStateFactory&) = delete;
// The VAO aux-memo payload GetOrCreateVertexInputState(vao) stamps: aux0 is the
// entry's layoutHash, aux1 packs (unsupportedAttribMask << 32) | attributeLocationMask.
// Readers that find the aux memo valid can use these without resolving the entry.
static Uint64 PackVertexInputAuxMasks(Uint32 unsupportedAttribMask, Uint32 attributeLocationMask) {
return (static_cast<Uint64>(unsupportedAttribMask) << 32) | attributeLocationMask;
}
HashType ComputeHash(const MG_State::GLState::VertexArrayObject& vao) const;
// Memoized ComputeHash: reuses the VAO's cached hash while its config version
// is unchanged. Use this on per-draw paths.
@@ -85,14 +55,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
const BackendVertexInputState& GetOrCreateVertexInputState(
const MG_State::GLState::VertexArrayObject& vao, HashType hash);
const BackendVertexInputState& GetOrCreateVertexInputState(const MG_State::GLState::VertexArrayObject& vao);
// Frame boundary hook: ages the cache and evicts entries not hit for many
// frames. The key mixes buffer heap addresses, so buffer/VAO churn keeps
// minting fresh keys; without eviction the map grows for the whole session.
// Entries hold no Vulkan handles (pipeline creation copies the descriptions)
// and the draw path's entry reference never spans a frame boundary, so
// eviction here needs no GPU-idle proof. Self-gated: one counter bump and
// compare except on sweep boundaries.
void OnFrameBoundary();
static SizeT GetComponentSize(DataType type);
// Tightly-packed byte size of one vertex element for this attribute: componentSize * size for
// normal types, and 4 (one packed word) for the 2_10_10_10 types and GL_BGRA. Returns 0 for
@@ -100,27 +62,14 @@ namespace MobileGL::MG_Backend::DirectVulkan {
static SizeT GetAttributeByteSize(DataType type, Int size, Bool isBgra);
private:
static VkFormat ToVkVertexFormat(DataType type, Int size, Bool normalized, Bool isInteger, Bool isBgra = false,
Bool isLong = false);
static VkFormat ToVkVertexFormat(DataType type, Int size, Bool normalized, Bool isInteger, Bool isBgra = false);
static Bool IsScaledIntegerVertexFormat(VkFormat format);
static VkFormat ToFloat32VertexFormat(Int componentCount);
Bool SupportsVertexBufferFormat(VkFormat format) const;
const VulkanRendererConfig& m_config;
VkPhysicalDevice m_physicalDevice = VK_NULL_HANDLE;
// Values are heap-allocated: FastSTL::unordered_map is open-addressing,
// so INSERT invalidates references to stored values. The draw path (and
// the VAOs' state-pointer memos) hold entry pointers across inserts;
// only the unique_ptr cell moves, never the pointee.
UnorderedMap<HashType, UniquePtr<BackendVertexInputState>> m_cache;
// Monotonic frame-boundary counter (bumped in OnFrameBoundary) for cache aging.
Uint64 m_frameBoundaryCounter = 0;
// Bumped whenever any cache entry is erased. VAOs memo a raw pointer to
// their heap-allocated entry (stable across map insert/rehash by
// construction); a memo is honored only while its recorded epoch
// matches, so an evicted entry can never be dereferenced through a
// stale memo.
Uint64 m_evictionEpoch = 1;
UnorderedMap<HashType, BackendVertexInputState> m_cache;
static inline XXH64_state_t* m_hashState = XXH64_createState();
};
} // namespace MobileGL::MG_Backend::DirectVulkan
@@ -7,8 +7,6 @@
// End of Source File Header
#include "VkBufferManager.h"
#include "../DirectVulkan.h"
#include "VulkanRenderer.h"
namespace MobileGL::MG_Backend::DirectVulkan {
namespace {
@@ -24,10 +22,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
VK_BUFFER_USAGE_UNIFORM_BUFFER_BIT | VK_BUFFER_USAGE_STORAGE_BUFFER_BIT |
VK_BUFFER_USAGE_INDIRECT_BUFFER_BIT | VK_BUFFER_USAGE_UNIFORM_TEXEL_BUFFER_BIT |
VK_BUFFER_USAGE_TRANSFER_SRC_BIT;
// Appended to kPersistentBackedUsage when VK_EXT_transform_feedback is enabled
// (see VkBufferManagerInitInfo::transformFeedbackUsageEnabled).
constexpr VkBufferUsageFlags kTransformFeedbackUsage =
VK_BUFFER_USAGE_TRANSFORM_FEEDBACK_BUFFER_BIT_EXT;
// The app writes into the persistent map with no explicit flush, so its memory must
// be host-coherent (Adreno host-visible memory is; requiring it keeps us portable).
constexpr VkMemoryPropertyFlags kPersistentBackedRequiredFlags =
@@ -59,18 +53,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
}
}
// The CPU is about to read a buffer a shader wrote. Its bytes live in coherent
// host-visible GPU storage (EnsureGpuResidentStorage adopts it when the buffer is
// bound as a shader storage buffer), so nothing needs copying - but coherence only
// says the writes are visible once they have happened, so the work has to retire
// first.
void Ops_ReadbackFromGpu(BufferObject& bufferObject) {
(void)bufferObject;
if (pVulkanRenderer) {
pVulkanRenderer->FinishPendingGpuWork();
}
}
void* Ops_AcquirePersistentMap(BufferObject& bufferObject) {
if (g_activeBufferManager) {
return g_activeBufferManager->AcquirePersistentMap(bufferObject);
@@ -94,7 +76,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
.FlushMappedRange = Ops_FlushMappedRange,
.OnDestroy = Ops_OnDestroy,
.AcquirePersistentMap = Ops_AcquirePersistentMap,
.ReadbackFromGpu = Ops_ReadbackFromGpu,
};
} // namespace
@@ -160,15 +141,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
m_transientUploadArena.BeginFrame(frameIndex);
}
void VkBufferManager::CollectAllDeferredReleases() {
for (Uint32 frameIndex = 0; frameIndex < m_deferredBufferReleases.size(); ++frameIndex) {
CollectDeferredReleases(frameIndex);
}
for (Uint32 frameIndex = 0; frameIndex < m_transientUploadArena.GetFrameCount(); ++frameIndex) {
m_transientUploadArena.CollectDeferredReleases(frameIndex);
}
}
void VkBufferManager::NotifyDeviceIdle() {
// Everything submitted so far has completed. Work recorded for the
// current frame has not been submitted yet, so the current serial
@@ -242,15 +214,8 @@ namespace MobileGL::MG_Backend::DirectVulkan {
}
void VkBufferManager::TrackLiveResource(const SharedPtr<VkBufferResource>& resource) {
// Sweep on a doubling watermark rather than on every insert past the threshold. The old
// form walked the whole vector for each new buffer once the list passed 256, and when the
// buffers are all live the walk removes nothing and the list grows by one - so creating N
// live buffers cost ~N^2/2 expired() checks. Reclamation semantics are unchanged: the sweep
// still removes exactly the expired entries, just less often and with the same bound on how
// much dead weight can accumulate (at most as many entries as were live at the last sweep).
if (m_liveResources.size() >= std::max<SizeT>(kLiveResourcePruneThreshold, 2 * m_liveResourcesLastPruned)) {
if (m_liveResources.size() >= kLiveResourcePruneThreshold) {
std::erase_if(m_liveResources, [](const WeakPtr<VkBufferResource>& weak) { return weak.expired(); });
m_liveResourcesLastPruned = m_liveResources.size();
}
m_liveResources.push_back(resource);
}
@@ -258,7 +223,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
void VkBufferManager::ReleaseAllLiveResources() {
for (auto& weak : m_liveResources) {
if (auto resource = weak.lock()) {
BumpSliceEpoch(*resource);
resource->buffer.Destroy();
resource->storageSize = 0;
resource->usageFlags = 0;
@@ -273,9 +237,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
Bool VkBufferManager::CreateResidentStorage(VkBufferResource& resource, VkDeviceSize size,
VkBufferUsageFlags usage, VkMemoryPropertyFlags requiredFlags) {
// The only place a resident VkBuffer handle is minted, so every resident slice
// change funnels through here (callers release the old handle first).
BumpSliceEpoch(resource);
// Staged range copies write resident storage with vkCmdCopyBuffer.
usage |= VK_BUFFER_USAGE_TRANSFER_DST_BIT;
const Bool created = resource.buffer.Create({
@@ -362,10 +323,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
if (!resource) {
return; // lazy: AcquireResidentSlice performs a full upload on creation
}
// A respecify can change the size, the usage hint (so the resident/streamed
// route), and the contents at once; retire every memo before deciding what to
// do about the storage.
BumpSliceEpoch(*resource);
// Any cached streaming slice refers to the previous contents.
resource->transientFrameSerial = 0;
if (!resource->buffer.IsValid()) {
@@ -398,9 +355,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
if (!resource) {
return;
}
// Drops the streaming memo below and may end in a storage swap or a deferred
// full re-upload, so no memoised slice survives this.
BumpSliceEpoch(*resource);
resource->transientFrameSerial = 0;
if (!resource->buffer.IsValid() || resource->pendingFullUpload) {
return;
@@ -433,7 +387,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
if (!resource) {
return;
}
BumpSliceEpoch(*resource);
resource->transientFrameSerial = 0;
if (!resource->buffer.IsValid() || resource->pendingFullUpload) {
return;
@@ -493,13 +446,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
TrackLiveResource(resource);
}
// Bumped for the request, not just for the storage it may create. This is the
// one call the frontend makes when a buffer becomes persistently mapped for
// writing (BufferObject::AcquireMemoryRange), and a map the backend declines
// keeps mutating its shadow with no further API call - so it is what lets
// GetSliceEpochCounter stand for "no buffer needs a persistent-map range push".
BumpSliceEpoch(*resource);
// Idempotent: an already-backed buffer returns the same mapped base.
if (resource->persistentMapped && resource->buffer.IsValid() && resource->storageSize == size) {
return resource->buffer.GetMappedData();
@@ -510,10 +456,7 @@ namespace MobileGL::MG_Backend::DirectVulkan {
// it from the current shadow - MappedData() is still the shadow here because the
// frontend adopts (and drops) the shadow only after this returns.
DeferRelease(std::move(resource->buffer));
const VkBufferUsageFlags persistentUsage =
kPersistentBackedUsage |
(m_initInfo.transformFeedbackUsageEnabled ? kTransformFeedbackUsage : 0);
if (!CreateResidentStorage(*resource, size, persistentUsage, kPersistentBackedRequiredFlags)) {
if (!CreateResidentStorage(*resource, size, kPersistentBackedUsage, kPersistentBackedRequiredFlags)) {
resource->persistentMapped = false;
resource->storageSize = 0;
resource->usageFlags = 0;
@@ -587,16 +530,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
auto resource = GetOrCreateResource(bufferObject);
bufferObject->SyncPersistentMappedRange();
// A persistently mapped resource's storage IS the application's copy of the bytes -
// the frontend adopted it in place of the shadow and hands out pointers into it, and
// a shader can have written bytes the shadow never saw (a transform feedback
// capture). Streaming a second copy would feed this draw the stale shadow, and the
// downgrade below would release the storage the application still points at,
// breaking the "never recreated" promise AcquirePersistentMap makes.
if (resource->persistentMapped) {
return AcquireResidentSlice(kind, bufferObject, outSlice);
}
const VkDeviceSize size = static_cast<VkDeviceSize>(bufferObject->GetSize());
if (size == 0) {
MGLOG_E("VkBufferManager::AcquireStreamedSlice failed: buffer size is zero");
@@ -610,41 +543,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
return true;
}
// Idle-content promotion: see the field comments in VkBufferResource. The
// streak counts frame BOUNDARIES survived unchanged (the same-frame memo
// above swallows repeat draws), so a promotion needs the content stable
// for kStreamedPromotionStreak whole frames - one no-op frame does not
// trigger the resident round-trip, whose creation upload is itself a
// staged copy worth avoiding for content that is about to change again.
constexpr Uint32 kStreamedPromotionStreak = 2;
if (resource->promotedResident) {
if (resource->promotedChangeSerial == changeSerial &&
static_cast<VkDeviceSize>(bufferObject->GetSize()) == size) {
return AcquireResidentSlice(kind, bufferObject, outSlice);
}
resource->promotedResident = false;
resource->unchangedStreak = 0;
} else if (resource->transientChangeSerial == changeSerial && resource->transientSize == size &&
resource->transientFrameSerial != 0) {
if (++resource->unchangedStreak >= kStreamedPromotionStreak) {
// Promotion moves the buffer off the arena and onto resident storage.
resource->promotedResident = true;
resource->promotedChangeSerial = changeSerial;
BumpSliceEpoch(*resource);
if (AcquireResidentSlice(kind, bufferObject, outSlice)) {
return true;
}
resource->promotedResident = false; // resident creation failed: stream as before
}
} else {
resource->unchangedStreak = 0;
}
// A fresh arena allocation: a different slice than the last call handed back,
// and (below) the point where a promoted buffer's resident storage is released.
// The stable-promotion exit above returns before this, so a buffer the app has
// stopped touching keeps one slice for as long as it keeps its resident storage.
BumpSliceEpoch(*resource);
if (!m_transientUploadArena.Upload(m_currentFrameIndex, bufferObject->MappedData(), size, 16,
outSlice)) {
return false;
@@ -31,9 +31,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
VmaMemoryUsage transientMemoryUsage = VMA_MEMORY_USAGE_AUTO;
VmaAllocationCreateFlags transientAllocationFlags = VMA_ALLOCATION_CREATE_HOST_ACCESS_SEQUENTIAL_WRITE_BIT;
Bool transientPersistentMapping = false;
// VK_EXT_transform_feedback is enabled: persistent-map storage additionally
// carries the transform feedback usage so capture targets can bind directly.
Bool transformFeedbackUsageEnabled = false;
};
// The DirectVulkan storage behind one frontend buffer (pipe_resource analogue).
@@ -57,33 +54,11 @@ namespace MobileGL::MG_Backend::DirectVulkan {
// never orphaned or recreated. Draw-time acquire binds it directly, no re-upload.
Bool persistentMapped = false;
// Bumped from a manager-wide counter every time anything that decides which
// BufferSlice an Acquire*Slice call hands back changes: storage created or
// released, a full re-upload becoming due, a promotion/demotion between
// resident and streamed storage, or a new per-frame arena slice. Callers that
// memoise a resolved slice compare this to prove the memo still describes the
// buffer. The counter is manager-wide (never per-resource) so a freshly
// created resource - including one that replaces a destroyed resource at the
// same address - can never reproduce a value some memo already holds. 0 means
// "no slice has ever been handed out", which no memo can match.
Uint64 sliceEpoch = 0;
// Cached transient (streaming) slice for the current frame.
BufferSlice transientSlice{};
Uint64 transientFrameSerial = 0;
Uint64 transientChangeSerial = 0;
VkDeviceSize transientSize = 0;
// Streaming re-copies the whole store into the per-frame arena on every
// frame, which is right for genuinely per-frame data but pure waste for a
// Dynamic-hinted buffer the app stopped touching. After the content
// survives kStreamedPromotionStreak frame boundaries unchanged it is
// promoted to resident storage (one final upload, then zero per-frame
// cost); the first content change demotes it back to streaming, and the
// streaming path's existing downgrade releases the resident store.
Uint32 unchangedStreak = 0;
Bool promotedResident = false;
Uint64 promotedChangeSerial = 0;
};
// Supplies a command buffer that is recording and outside any render pass,
@@ -102,11 +77,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
// Recreate all per-frame transient arenas
Bool RecreateTransientArenas(Uint32 frameCount);
void BeginFrame(Uint32 frameIndex);
// Drains every frame slot's deferred buffer/resource releases (and the
// transient arena's parked superseded blocks). Only valid when the
// caller has proven every queue submission complete; used by the
// present-less frame-boundary drain.
void CollectAllDeferredReleases();
// All previously submitted GPU work has completed (vkDeviceWaitIdle).
void NotifyDeviceIdle();
// A frame slot's submission fence has been waited: every serial up to
@@ -143,11 +113,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
void OnResourceDestroyed(SharedPtr<MG_State::GLState::BackendBufferResource>&& resource);
Uint64 GetFrameSerial() const { return m_frameSerial; }
// Highest value handed to any VkBufferResource::sliceEpoch. Unchanged since a
// memo was taken means no buffer this manager owns changed which slice it hands
// back, and none was persistently mapped, in between - so a memo of resolved
// slices needs no per-buffer re-check. See AcquirePersistentMap for the mapping half.
Uint64 GetSliceEpochCounter() const { return m_sliceEpochCounter; }
// Highest frame serial whose GPU work is known complete; serials at or
// below it may be considered signaled. Drives IsResourceBusy and the
// backend GL fence objects.
@@ -174,8 +139,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
void DestroyAllDeferredReleases();
void TrackLiveResource(const SharedPtr<VkBufferResource>& resource);
void ReleaseAllLiveResources();
// See VkBufferResource::sliceEpoch.
void BumpSliceEpoch(VkBufferResource& resource) { resource.sliceEpoch = ++m_sliceEpochCounter; }
VkBufferManagerInitInfo m_initInfo{};
BufferArena m_transientUploadArena;
@@ -183,14 +146,8 @@ namespace MobileGL::MG_Backend::DirectVulkan {
Vector<Vector<VkBufferObject>> m_deferredBufferReleases;
Vector<Vector<SharedPtr<VkBufferResource>>> m_deferredResourceReleases;
Vector<WeakPtr<VkBufferResource>> m_liveResources;
// Size m_liveResources had just after the last sweep; the next sweep waits for it to double.
SizeT m_liveResourcesLastPruned = 0;
Uint32 m_currentFrameIndex = 0;
Uint64 m_frameSerial = 1;
Uint64 m_completedSerialFloor = 0;
// Never reset (not even by Shutdown): a value handed to a resource must stay
// unique for the process, or a memo taken before a re-initialize could match
// a different resource's state after it.
Uint64 m_sliceEpochCounter = 0;
};
} // namespace MobileGL::MG_Backend::DirectVulkan
@@ -176,4 +176,16 @@ namespace MobileGL::MG_Backend::DirectVulkan {
return true;
}
BufferSlice VkBufferObject::GetSlice(VkDeviceSize offset, VkDeviceSize size) const {
MOBILEGL_ASSERT(offset <= m_size, "VkBufferObject::GetSlice offset out of range");
const VkDeviceSize resolvedSize = (size == VK_WHOLE_SIZE) ? (m_size - offset) : size;
MOBILEGL_ASSERT(offset + resolvedSize <= m_size, "VkBufferObject::GetSlice range out of bounds");
BufferSlice slice{};
slice.buffer = m_buffer;
slice.offset = offset;
slice.size = resolvedSize;
slice.mapped = (m_mappedData != nullptr) ? static_cast<Uint8*>(m_mappedData) + offset : nullptr;
return slice;
}
} // namespace MobileGL::MG_Backend::DirectVulkan
@@ -48,20 +48,7 @@ namespace MobileGL::MG_Backend::DirectVulkan {
VkBuffer GetHandle() const { return m_buffer; }
VkDeviceSize GetSize() const { return m_size; }
// Inline: runs on the per-draw acquire path (a resident buffer bind is a
// GetSlice per binding), where an out-of-line call was measurable.
BufferSlice GetSlice(VkDeviceSize offset = 0, VkDeviceSize size = VK_WHOLE_SIZE) const {
MOBILEGL_ASSERT(offset <= m_size, "VkBufferObject::GetSlice offset out of range");
const VkDeviceSize resolvedSize = (size == VK_WHOLE_SIZE) ? (m_size - offset) : size;
MOBILEGL_ASSERT(offset + resolvedSize <= m_size, "VkBufferObject::GetSlice range out of bounds");
BufferSlice slice{};
slice.buffer = m_buffer;
slice.offset = offset;
slice.size = resolvedSize;
slice.mapped = (m_mappedData != nullptr) ? static_cast<Uint8*>(m_mappedData) + offset : nullptr;
return slice;
}
BufferSlice GetSlice(VkDeviceSize offset = 0, VkDeviceSize size = VK_WHOLE_SIZE) const;
void* GetMappedData() const { return m_mappedData; }
Bool IsMapped() const { return m_mappedData != nullptr; }
Bool IsValid() const { return m_allocator != nullptr && m_buffer != VK_NULL_HANDLE && m_allocation != nullptr; }
@@ -8,75 +8,15 @@
#include "VkClearManager.h"
#include "MG_State/GLState/Core.h"
#include "MG_Util/Converters/MGToStr/FramebufferEnumConverter.h"
#include "MG_Util/Converters/MGToStr/TextureEnumConverter.h"
#include <algorithm>
#include <cmath>
namespace MobileGL::MG_Backend::DirectVulkan {
static Bool IsCubeMapFaceUploadTarget(TextureUploadTarget target) {
return target >= TextureUploadTarget::CubeMapPositiveX &&
target <= TextureUploadTarget::CubeMapNegativeZ;
}
VkClearColorValue MakeVkClearColorValue(const ClearAttachmentPayload& payload, Bool formatLacksAlpha) {
VkClearColorValue clearValue{};
switch (payload.colorEncoding) {
case ClearColorEncoding::Int:
clearValue.int32[0] = payload.colorInt.x();
clearValue.int32[1] = payload.colorInt.y();
clearValue.int32[2] = payload.colorInt.z();
clearValue.int32[3] = formatLacksAlpha ? 1 : payload.colorInt.w();
break;
case ClearColorEncoding::Uint:
clearValue.uint32[0] = payload.colorUint.x();
clearValue.uint32[1] = payload.colorUint.y();
clearValue.uint32[2] = payload.colorUint.z();
clearValue.uint32[3] = formatLacksAlpha ? 1u : payload.colorUint.w();
break;
case ClearColorEncoding::Float:
clearValue.float32[0] = payload.color.x();
clearValue.float32[1] = payload.color.y();
clearValue.float32[2] = payload.color.z();
clearValue.float32[3] = formatLacksAlpha ? 1.0f : payload.color.w();
break;
}
return clearValue;
}
void PreCompensateSrgbClearColor(ClearAttachmentPayload& payload, VkFormat destinationFormat) {
if (payload.colorEncoding != ClearColorEncoding::Float) return;
// With GL_FRAMEBUFFER_SRGB enabled GL performs the encoding itself, so the driver doing it
// is exactly right and there is nothing to undo.
if (MG_State::pGLContext->IsCapabilityEnabled(MobileGL::CapabilityInput::FramebufferSrgb)) return;
if (ResolveSrgbAttachmentWriteFormat(destinationFormat, false) == destinationFormat) return;
// sRGB -> linear (GL 4.6 core 8.24), applied to the colour channels only: alpha is stored
// linearly in an sRGB format and must pass through untouched.
const auto toLinear = [](Float encoded) {
const Float value = std::clamp(encoded, 0.0f, 1.0f);
return value <= 0.04045f ? value / 12.92f : std::pow((value + 0.055f) / 1.055f, 2.4f);
};
payload.color = FloatVec4(toLinear(payload.color.x()), toLinear(payload.color.y()),
toLinear(payload.color.z()), payload.color.w());
}
void ForceOpaqueClearAlpha(ClearAttachmentPayload& payload) {
switch (payload.colorEncoding) {
case ClearColorEncoding::Int:
payload.colorInt = IntVec4(payload.colorInt.x(), payload.colorInt.y(), payload.colorInt.z(), 1);
break;
case ClearColorEncoding::Uint:
payload.colorUint = UintVec4(payload.colorUint.x(), payload.colorUint.y(), payload.colorUint.z(), 1u);
break;
case ClearColorEncoding::Float:
payload.color = FloatVec4(payload.color.x(), payload.color.y(), payload.color.z(), 1.0f);
break;
}
}
static Bool PendingClearMatchesTextureIdentity(const PendingClearKey& key, const TextureIdentity& identity) {
return key.texture == identity.texture && key.textureLifetimeId == identity.lifetimeId;
}
@@ -153,7 +93,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
const std::lock_guard<std::mutex> lock(m_mutex);
m_pendingClears.clear();
m_aliveObjects.clear();
m_pendingCount.store(static_cast<Uint32>(m_pendingClears.size()), std::memory_order_relaxed);
}
TextureIdentity VkClearManager::MakeTextureIdentity(MG_State::GLState::ITextureObject* texture) {
@@ -188,7 +127,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
m_pendingClears.erase(key);
}
m_aliveObjects.erase(identity);
m_pendingCount.store(static_cast<Uint32>(m_pendingClears.size()), std::memory_order_relaxed);
}
Bool VkClearManager::LockTextureIdentityLocked(const TextureIdentity& identity,
@@ -283,7 +221,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
m_aliveObjects[MakeTextureIdentity(texture.get())] = texture;
auto& pending = m_pendingClears[key];
MergeClearPayload(pending, clearPayload);
m_pendingCount.store(static_cast<Uint32>(m_pendingClears.size()), std::memory_order_relaxed);
}
void VkClearManager::QueueClear(const ClearAttachmentPayload& clearPayload,
@@ -301,7 +238,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
m_aliveObjects[MakeTextureIdentity(texture.get())] = texture;
auto& pending = m_pendingClears[key];
MergeClearPayload(pending, clearPayload);
m_pendingCount.store(static_cast<Uint32>(m_pendingClears.size()), std::memory_order_relaxed);
}
Bool VkClearManager::HasPendingClear(MG_State::GLState::ITextureObject* texture) {
@@ -309,10 +245,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
return false;
}
if (m_pendingCount.load(std::memory_order_relaxed) == 0) {
return false; // per-draw hot path: nothing pending anywhere
}
const Uint64 lifetimeId = texture->GetLifetimeId();
const std::lock_guard<std::mutex> lock(m_mutex);
for (auto it = m_pendingClears.begin(); it != m_pendingClears.end(); ++it) {
@@ -328,9 +260,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
if (key.texture == nullptr) {
return false;
}
if (m_pendingCount.load(std::memory_order_relaxed) == 0) {
return false; // per-draw hot path: nothing pending anywhere
}
const std::lock_guard<std::mutex> lock(m_mutex);
if (m_pendingClears.find(key) == m_pendingClears.end()) {
@@ -358,9 +287,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
if (key.texture == nullptr) {
return false;
}
if (m_pendingCount.load(std::memory_order_relaxed) == 0) {
return false; // per-draw hot path: nothing pending anywhere
}
const std::lock_guard<std::mutex> lock(m_mutex);
if (!LockTextureLocked(key, outTexture)) {
@@ -399,9 +325,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
if (texture == nullptr) {
return false;
}
if (m_pendingCount.load(std::memory_order_relaxed) == 0) {
return false; // per-draw hot path: nothing pending anywhere
}
const Uint64 lifetimeId = texture->GetLifetimeId();
const std::lock_guard<std::mutex> lock(m_mutex);
@@ -422,9 +345,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
return;
}
if (m_pendingCount.load(std::memory_order_relaxed) == 0) {
return; // per-draw hot path: nothing pending anywhere
}
const TextureIdentity identity = MakeTextureIdentity(texture);
MGLOG_D("%s: Pop all pending clears for texture %d", __func__, texture->GetExternalIndex());
const std::lock_guard<std::mutex> lock(m_mutex);
@@ -441,7 +361,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
auto it = m_pendingClears.find(key);
if (it != m_pendingClears.end()) {
m_pendingClears.erase(it);
m_pendingCount.store(static_cast<Uint32>(m_pendingClears.size()), std::memory_order_relaxed);
}
}
@@ -14,7 +14,6 @@
#include "MG_Util/Math/VectorTypes.h"
#include <Includes.h>
#include <atomic>
#include <unordered_map>
namespace MobileGL::MG_Backend::DirectVulkan {
@@ -24,41 +23,13 @@ namespace MobileGL::MG_Backend::DirectVulkan {
Uint32 stencil{};
};
// A colour clear reaches us from one of glClear/ClearBufferfv, ClearBufferiv or
// ClearBufferuiv, and Vulkan reads VkClearColorValue's union according to the destination
// image's format rather than converting between the members - a float written where an
// integer format is expected is reinterpreted bit for bit, not rounded. Remember which entry
// point supplied the value so the member written when the clear is materialized matches.
enum class ClearColorEncoding : Uint8 { Float, Int, Uint };
struct ClearAttachmentPayload {
GLbitfield mask = 0;
FloatVec4 color = FloatVec4(0.0f, 0.0f, 0.0f, 0.0f);
ClearColorEncoding colorEncoding = ClearColorEncoding::Float;
IntVec4 colorInt = IntVec4(0, 0, 0, 0);
UintVec4 colorUint = UintVec4(0u, 0u, 0u, 0u);
Float depth = 1.0f;
Uint32 stencil = 0;
};
// Builds the clear value for `payload` in the union member its encoding calls for.
// `formatLacksAlpha` applies GL's rule that a format without an alpha channel reads as one,
// expressed in whichever type matches (GL 4.6 core 15.2.3).
VkClearColorValue MakeVkClearColorValue(const ClearAttachmentPayload& payload, Bool formatLacksAlpha);
// Applies that same rule in place, for the paths that have to bake it into the payload before
// the destination is known.
void ForceOpaqueClearAlpha(ClearAttachmentPayload& payload);
// vkCmdClearColorImage names the image, so the driver applies the destination format's transfer
// function to whatever value it is handed. Every other write path in this backend goes through
// the UNORM twin view while GL_FRAMEBUFFER_SRGB is off (ResolveSrgbAttachmentWriteFormat) and
// therefore stores the raw value GL asked for. Rewrites `payload` to the linear colour whose
// encoding is that raw value, so a direct image clear of an sRGB destination agrees with them.
// A no-op for every other format, for integer clear encodings, and when GL is doing the
// encoding itself.
void PreCompensateSrgbClearColor(ClearAttachmentPayload& payload, VkFormat destinationFormat);
struct PendingClearKey {
MG_State::GLState::ITextureObject* texture = nullptr;
Uint64 textureLifetimeId = 0;
@@ -149,19 +120,7 @@ namespace MobileGL::MG_Backend::DirectVulkan {
SharedPtr<MG_State::GLState::ITextureObject>& outTexture);
Uint8 m_gcCounter = 0;
public:
// Lock-free probe for the consecutive-draw fast path: any pending clear
// forces the full SetupDraw path (which materializes/consumes it).
Bool HasAnyPendingClears() const { return m_pendingCount.load(std::memory_order_relaxed) != 0; }
private:
mutable std::mutex m_mutex;
// Lock-free mirror of m_pendingClears.size(), maintained under m_mutex
// by every mutation. The per-draw probes (HasPendingClear/GetPending*)
// read it before taking the lock: during draw batches the pending set
// is almost always empty, so this turns several locked map probes per
// draw into one relaxed load.
std::atomic<Uint32> m_pendingCount{0};
std::unordered_map<PendingClearKey, ClearAttachmentPayload, PendingClearKeyHash> m_pendingClears;
std::unordered_map<TextureIdentity, WeakPtr<MG_State::GLState::ITextureObject>, TextureIdentityHash> m_aliveObjects;
};
@@ -16,21 +16,31 @@
namespace MobileGL::MG_Backend::DirectVulkan {
static Bool TryResolveSampleCountFlagBits(Int requestedSamples, VkSampleCountFlagBits& outSampleCount) {
// GL promises "at least the requested samples", so a non-power-of-two
// request (legal in GL, e.g. 3) rounds up to the next Vulkan bit.
if (requestedSamples <= 1) {
switch (requestedSamples <= 0 ? 1 : requestedSamples) {
case 1:
outSampleCount = VK_SAMPLE_COUNT_1_BIT;
return true;
}
if (requestedSamples > 64) {
case 2:
outSampleCount = VK_SAMPLE_COUNT_2_BIT;
return true;
case 4:
outSampleCount = VK_SAMPLE_COUNT_4_BIT;
return true;
case 8:
outSampleCount = VK_SAMPLE_COUNT_8_BIT;
return true;
case 16:
outSampleCount = VK_SAMPLE_COUNT_16_BIT;
return true;
case 32:
outSampleCount = VK_SAMPLE_COUNT_32_BIT;
return true;
case 64:
outSampleCount = VK_SAMPLE_COUNT_64_BIT;
return true;
default:
return false;
}
Uint32 bit = 1;
while (bit < static_cast<Uint32>(requestedSamples)) {
bit <<= 1;
}
outSampleCount = static_cast<VkSampleCountFlagBits>(bit);
return true;
}
static VkImageAspectFlags ResolveImageAspectMaskForFormat(VkFormat format) {
@@ -50,11 +60,7 @@ namespace MobileGL::MG_Backend::DirectVulkan {
}
}
static Bool ColorFormatLacksAlpha(const MG_State::GLState::ITextureObject* texture) {
return texture != nullptr && MG_Util::GetBaseInternalFormatComponentCount(texture->GetFormat()) == 3;
}
[[maybe_unused]] static Float ResolveColorClearAlpha(const MG_State::GLState::ITextureObject* texture, Float requestedAlpha) {
static Float ResolveColorClearAlpha(const MG_State::GLState::ITextureObject* texture, Float requestedAlpha) {
if (texture != nullptr && MG_Util::GetBaseInternalFormatComponentCount(texture->GetFormat()) == 3) {
return 1.0f;
}
@@ -87,20 +93,9 @@ namespace MobileGL::MG_Backend::DirectVulkan {
static VkImageViewType ResolveAttachmentViewType(
const MG_State::GLState::FramebufferAttachmentObject& attachment,
const VkTextureManager::TextureResource& resource) {
if (attachment.IsLayered()) {
return resource.viewType;
}
// A non-layered attachment names ONE layer, so the view over it is a plain 2D view whatever
// the image's own view type is. The cube-face upload targets always meant this; a cube map
// array attached through glFramebufferTextureLayer means it too, and a CUBE_ARRAY view over
// a single layer is not a legal attachment. The CUBE arm is inert today - no frontend path
// produces a non-layered cube attachment without a face upload target - and is kept for
// symmetry with CUBE_ARRAY.
if (IsCubeMapFaceUploadTarget(attachment.GetTextureUploadTarget()) ||
resource.viewType == VK_IMAGE_VIEW_TYPE_CUBE_ARRAY || resource.viewType == VK_IMAGE_VIEW_TYPE_CUBE) {
return VK_IMAGE_VIEW_TYPE_2D;
}
return resource.viewType;
return !attachment.IsLayered() && IsCubeMapFaceUploadTarget(attachment.GetTextureUploadTarget()) ?
VK_IMAGE_VIEW_TYPE_2D :
resource.viewType;
}
static MG_State::GLState::ITextureObject* ResolveCompleteColorAttachmentTexture(
@@ -171,9 +166,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
if (view != VK_NULL_HANDLE) {
vkDestroyImageView(device, view, nullptr);
}
if (unormTwinView != VK_NULL_HANDLE) {
vkDestroyImageView(device, unormTwinView, nullptr);
}
if (image != VK_NULL_HANDLE && allocation != nullptr) {
vmaDestroyImage(allocator, image, allocation);
}
@@ -181,7 +173,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
image = VK_NULL_HANDLE;
allocation = nullptr;
view = VK_NULL_HANDLE;
unormTwinView = VK_NULL_HANDLE;
layout = VK_IMAGE_LAYOUT_UNDEFINED;
format = VK_FORMAT_UNDEFINED;
aspect = VK_IMAGE_ASPECT_NONE;
@@ -189,7 +180,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
sampleCount = VK_SAMPLE_COUNT_1_BIT;
internalFormat = TextureInternalFormat::Unknown;
samples = 0;
deadSinceFrame = kNeverObservedDead;
}
VkRenderPassManager::VkRenderPassManager(VkDevice device,
@@ -216,7 +206,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
resource.Destroy(m_device, m_allocator);
}
m_renderbufferResources.clear();
CollectDeferredRenderbufferReleases(/*destroyAll=*/true); // caller guarantees device idle
m_pendingRenderbufferClears.clear();
RenderPassEntry::s_textureResourcesScratch.clear();
s_activeRenderPass = {};
@@ -224,80 +213,22 @@ namespace MobileGL::MG_Backend::DirectVulkan {
m_rpFastValid = false;
}
Uint64 VkRenderPassManager::RetireAgeFrames() const {
// MaxFramesInFlight + 2 covers the frame ring plus one boundary for the
// recording-to-submit gap and one because OnPresent runs ahead of Present's
// fence wait; the floor of 8 keeps a margin over the default ring of 3 while
// still releasing multi-MB attachment memory promptly (the render-pass cache's
// 1024-frame retirement would pin it for no additional safety).
return std::max<Uint64>(8, static_cast<Uint64>(m_config.MaxFramesInFlight) + 2);
}
void VkRenderPassManager::DeferRenderbufferBackingRelease(RenderbufferResource& resource) {
// The superseded backing may still be referenced by in-flight command buffers
// (glRenderbufferStorage can respecify a renderbuffer drawn this very frame),
// so it is parked and destroyed only after RetireAgeFrames() boundaries.
if (resource.image == VK_NULL_HANDLE && resource.view == VK_NULL_HANDLE) {
return;
}
m_deferredRenderbufferReleases.push_back(
{resource.image, resource.allocation, resource.view, resource.unormTwinView, m_frameCounter});
resource.image = VK_NULL_HANDLE;
resource.allocation = nullptr;
resource.view = VK_NULL_HANDLE;
resource.unormTwinView = VK_NULL_HANDLE;
}
void VkRenderPassManager::CollectDeferredRenderbufferReleases(Bool destroyAll) {
if (m_deferredRenderbufferReleases.empty()) {
return;
}
const Uint64 retireAgeFrames = RetireAgeFrames();
std::erase_if(m_deferredRenderbufferReleases, [&](DeferredRenderbufferRelease& release) {
if (!destroyAll && m_frameCounter - release.deferredAtFrame < retireAgeFrames) {
return false;
}
if (release.view != VK_NULL_HANDLE) {
vkDestroyImageView(m_device, release.view, nullptr);
}
if (release.unormTwinView != VK_NULL_HANDLE) {
vkDestroyImageView(m_device, release.unormTwinView, nullptr);
}
if (release.image != VK_NULL_HANDLE) {
vmaDestroyImage(m_allocator, release.image, release.allocation);
}
return true;
});
}
void VkRenderPassManager::CollectRenderbufferGarbage() {
// Two-phase reclamation: a dead renderbuffer's VkImage may still be referenced by
// command buffers submitted up to frames-in-flight frames ago (it was legally
// attached and drawn right up to its deletion), so the first observation of an
// expired weak reference only stamps the current frame counter; Destroy runs once
// enough frame boundaries have passed that the stamping frame's submission fence
// has provably been waited (see RetireAgeFrames).
const Uint64 retireAgeFrames = RetireAgeFrames();
for (auto it = m_renderbufferResources.begin(); it != m_renderbufferResources.end();) {
auto& resource = it->second;
Vector<MG_State::GLState::RenderbufferObject*> deadRenderbuffers;
deadRenderbuffers.reserve(m_renderbufferResources.size());
for (auto& [renderbuffer, resource] : m_renderbufferResources) {
const auto liveRenderbuffer = resource.renderbuffer.lock();
if (liveRenderbuffer && liveRenderbuffer.get() == it->first) {
resource.deadSinceFrame = RenderbufferResource::kNeverObservedDead;
++it;
continue;
if (!liveRenderbuffer || liveRenderbuffer.get() != renderbuffer) {
deadRenderbuffers.emplace_back(renderbuffer);
}
if (resource.deadSinceFrame == RenderbufferResource::kNeverObservedDead) {
resource.deadSinceFrame = m_frameCounter;
++it;
continue;
}
for (auto* renderbuffer : deadRenderbuffers) {
auto resourceIt = m_renderbufferResources.find(renderbuffer);
if (resourceIt != m_renderbufferResources.end()) {
resourceIt->second.Destroy(m_device, m_allocator);
m_renderbufferResources.erase(resourceIt);
}
if (m_frameCounter - resource.deadSinceFrame < retireAgeFrames) {
++it;
continue;
}
m_pendingRenderbufferClears.erase(it->first);
resource.Destroy(m_device, m_allocator);
it = m_renderbufferResources.erase(it);
m_pendingRenderbufferClears.erase(renderbuffer);
}
}
@@ -318,47 +249,7 @@ namespace MobileGL::MG_Backend::DirectVulkan {
}
const auto internalFormat = renderbuffer->GetInternalFormat();
// Three-channel color formats widen to their RGBA twin exactly like textures do
// (VkTextureManager::ResolveTextureFormatInfo): blits/resolves between a
// renderbuffer and a texture of the same GL format then see one VkFormat.
const VkFormat format = [&]() -> VkFormat {
switch (internalFormat) {
case TextureInternalFormat::RGB:
case TextureInternalFormat::RGB8:
case TextureInternalFormat::R3G3B2:
case TextureInternalFormat::RGB4:
case TextureInternalFormat::RGB5:
return VK_FORMAT_R8G8B8A8_UNORM;
case TextureInternalFormat::SRGB8:
return VK_FORMAT_R8G8B8A8_SRGB;
case TextureInternalFormat::RGB8Snorm:
return VK_FORMAT_R8G8B8A8_SNORM;
case TextureInternalFormat::RGB10:
case TextureInternalFormat::RGB12:
case TextureInternalFormat::RGB16:
return VK_FORMAT_R16G16B16A16_UNORM;
case TextureInternalFormat::RGB16Snorm:
return VK_FORMAT_R16G16B16A16_SNORM;
case TextureInternalFormat::RGB16F:
return VK_FORMAT_R16G16B16A16_SFLOAT;
case TextureInternalFormat::RGB32F:
return VK_FORMAT_R32G32B32A32_SFLOAT;
case TextureInternalFormat::RGB8I:
return VK_FORMAT_R8G8B8A8_SINT;
case TextureInternalFormat::RGB8UI:
return VK_FORMAT_R8G8B8A8_UINT;
case TextureInternalFormat::RGB16I:
return VK_FORMAT_R16G16B16A16_SINT;
case TextureInternalFormat::RGB16UI:
return VK_FORMAT_R16G16B16A16_UINT;
case TextureInternalFormat::RGB32I:
return VK_FORMAT_R32G32B32A32_SINT;
case TextureInternalFormat::RGB32UI:
return VK_FORMAT_R32G32B32A32_UINT;
default:
return MG_Util::ConvertTextureInternalFormatToVkEnum(internalFormat);
}
}();
const VkFormat format = MG_Util::ConvertTextureInternalFormatToVkEnum(internalFormat);
const VkImageAspectFlags aspect = ResolveImageAspectMaskForFormat(format);
// Renderbuffers are never sampled (GL has no way to bind one to a sampler), so the
// usage set is attachment + transfer: transfer covers readback (vkCmdCopyImageToBuffer),
@@ -368,46 +259,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
: VK_IMAGE_USAGE_DEPTH_STENCIL_ATTACHMENT_BIT) |
VK_IMAGE_USAGE_TRANSFER_SRC_BIT | VK_IMAGE_USAGE_TRANSFER_DST_BIT;
// GL allows the implementation to allocate more samples than requested
// (glRenderbufferStorageMultisample only promises "at least"), and devices
// like llvmpipe expose 1x/4x but not 2x. Round the request up to the
// nearest supported count for this format.
if (renderbuffer->GetSamples() > 0) {
auto supportedIt = m_attachmentSampleCountsByFormat.find(format);
if (supportedIt == m_attachmentSampleCountsByFormat.end()) {
VkImageFormatProperties formatProperties{};
VkSampleCountFlags supported = VK_SAMPLE_COUNT_1_BIT;
if (vkGetPhysicalDeviceImageFormatProperties(m_physicalDevice, format, VK_IMAGE_TYPE_2D,
VK_IMAGE_TILING_OPTIMAL, imageUsage, 0,
&formatProperties) == VK_SUCCESS) {
supported = formatProperties.sampleCounts;
}
supportedIt = m_attachmentSampleCountsByFormat.emplace(format, supported).first;
}
const VkSampleCountFlags supported = supportedIt->second;
if ((supported & sampleCount) == 0) {
// Smallest supported count above the request, else the largest below it.
Uint32 rounded = 0;
for (Uint32 bit = static_cast<Uint32>(sampleCount) << 1; bit <= VK_SAMPLE_COUNT_64_BIT; bit <<= 1) {
if ((supported & bit) != 0) {
rounded = bit;
break;
}
}
if (rounded == 0) {
for (Uint32 bit = static_cast<Uint32>(sampleCount) >> 1; bit != 0; bit >>= 1) {
if ((supported & bit) != 0) {
rounded = bit;
break;
}
}
}
if (rounded != 0) {
sampleCount = static_cast<VkSampleCountFlagBits>(rounded);
}
}
}
auto& resource = m_renderbufferResources[renderbuffer.get()];
const Bool needsCreate =
resource.image == VK_NULL_HANDLE ||
@@ -419,15 +270,9 @@ namespace MobileGL::MG_Backend::DirectVulkan {
resource.samples != renderbuffer->GetSamples();
if (!needsCreate) {
resource.renderbuffer = renderbuffer;
// A new renderbuffer at a recycled address may adopt a compatible entry that
// was already stamped dead; it is alive again, so cancel the aging.
resource.deadSinceFrame = RenderbufferResource::kNeverObservedDead;
return &resource;
}
// Respecify: park the old backing for aged destruction instead of destroying
// inline - it may still be referenced by in-flight command buffers.
DeferRenderbufferBackingRelease(resource);
resource.Destroy(m_device, m_allocator);
resource.renderbuffer = renderbuffer;
@@ -445,12 +290,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
imageInfo.usage = imageUsage;
imageInfo.samples = sampleCount;
imageInfo.sharingMode = VK_SHARING_MODE_EXCLUSIVE;
// sRGB renderbuffers attach through their UNORM twin while GL_FRAMEBUFFER_SRGB
// is disabled, which needs a format-reinterpreting second view.
const Bool hasUnormTwin = ResolveSrgbAttachmentWriteFormat(format, false) != format;
if (hasUnormTwin) {
imageInfo.flags |= VK_IMAGE_CREATE_MUTABLE_FORMAT_BIT;
}
VkImageFormatProperties imageFormatProperties{};
const VkResult imageFormatResult = vkGetPhysicalDeviceImageFormatProperties(
@@ -485,11 +324,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
viewInfo.subresourceRange.layerCount = 1;
VK_VERIFY(vkCreateImageView(m_device, &viewInfo, nullptr, &resource.view),
"vkCreateImageView(renderbuffer)");
if (hasUnormTwin) {
viewInfo.format = ResolveSrgbAttachmentWriteFormat(format, false);
VK_VERIFY(vkCreateImageView(m_device, &viewInfo, nullptr, &resource.unormTwinView),
"vkCreateImageView(renderbuffer unorm twin)");
}
resource.layout = VK_IMAGE_LAYOUT_UNDEFINED;
resource.format = format;
@@ -541,13 +375,7 @@ namespace MobileGL::MG_Backend::DirectVulkan {
pending.renderbuffer = renderbuffer;
pending.payload.mask |= clearPayload.mask;
if ((clearPayload.mask & GL_COLOR_BUFFER_BIT) != 0) {
// The whole colour description, not just the float vector: an integer clear keeps its
// value in colorInt/colorUint, and dropping the encoding here would leave the pending
// clear reading as an all-zero float one.
pending.payload.color = clearPayload.color;
pending.payload.colorEncoding = clearPayload.colorEncoding;
pending.payload.colorInt = clearPayload.colorInt;
pending.payload.colorUint = clearPayload.colorUint;
}
if ((clearPayload.mask & GL_DEPTH_BUFFER_BIT) != 0) {
pending.payload.depth = clearPayload.depth;
@@ -592,18 +420,12 @@ namespace MobileGL::MG_Backend::DirectVulkan {
}
VkRenderPassManager::HashType VkRenderPassManager::ComputeHash(
const MG_State::GLState::FramebufferObject& fbo, Uint32 swapchainImageIndex, Bool includePendingClear,
Bool includeDefaultFboDepthStencil) {
const MG_State::GLState::FramebufferObject& fbo, Uint32 swapchainImageIndex, Bool includePendingClear) {
XXHASH_VERIFY(XXH64_reset(m_hashState, m_config.CacheVersion));
const Bool isDefaultFbo = fbo.IsDefaultFramebuffer();
if (isDefaultFbo) {
XXHASH_VERIFY(XXH64_update(m_hashState, &swapchainImageIndex, sizeof(swapchainImageIndex)));
}
// sRGB attachments switch between their sRGB and UNORM-twin views with this
// capability (ResolveSrgbAttachmentWriteFormat), changing the render pass formats.
const Bool framebufferSrgbEnabled =
MG_State::pGLContext->IsCapabilityEnabled(MobileGL::CapabilityInput::FramebufferSrgb);
XXHASH_VERIFY(XXH64_update(m_hashState, &framebufferSrgbEnabled, sizeof(framebufferSrgbEnabled)));
auto& drawBuffers = fbo.GetDrawBuffers();
XXHASH_VERIFY(XXH64_update(m_hashState, drawBuffers.data(), drawBuffers.size() * sizeof(drawBuffers[0])));
auto readBuffer = fbo.GetReadBuffer();
@@ -677,17 +499,9 @@ namespace MobileGL::MG_Backend::DirectVulkan {
attachment <= FramebufferAttachmentType::BackRight);
if (isDefaultColorAttachment) {
currentLayout = m_swapchainObject.GetImageLayout(swapchainImageIndex);
// Content validity feeds the attachment's loadOp (see the
// creation path), so it must key the cache as well.
if (!m_swapchainObject.IsImageContentDefined(swapchainImageIndex)) {
currentLayout = VK_IMAGE_LAYOUT_UNDEFINED;
}
} else if (attachment == FramebufferAttachmentType::Depth ||
attachment == FramebufferAttachmentType::Stencil) {
currentLayout = m_swapchainObject.GetDepthStencilImageLayout(swapchainImageIndex);
if (!m_swapchainObject.IsDepthStencilContentDefined(swapchainImageIndex)) {
currentLayout = VK_IMAGE_LAYOUT_UNDEFINED;
}
}
} else {
auto* textureResource = m_textureManager.SyncTextureAndGetDescriptor(*texture);
@@ -742,49 +556,14 @@ namespace MobileGL::MG_Backend::DirectVulkan {
combineFramebufferAttachmentObjHash(drawbuf);
}
// The depth-less default-FBO flavor omits the depth/stencil attachment
// entirely, so it must hash differently from the depth-full flavor.
const Bool depthStencilIncluded = !isDefaultFbo || includeDefaultFboDepthStencil;
XXHASH_VERIFY(XXH64_update(m_hashState, &depthStencilIncluded, sizeof(depthStencilIncluded)));
if (depthStencilIncluded) {
combineFramebufferAttachmentObjHash(FramebufferAttachmentType::Depth);
combineFramebufferAttachmentObjHash(FramebufferAttachmentType::Stencil);
}
combineFramebufferAttachmentObjHash(FramebufferAttachmentType::Depth);
combineFramebufferAttachmentObjHash(FramebufferAttachmentType::Stencil);
return XXH64_digest(m_hashState);
}
RenderPassEntry& VkRenderPassManager::GetOrCreateRenderPass(const MG_State::GLState::FramebufferObject& fbo,
Uint32 swapchainImageIndex,
Bool drawUsesDepthStencil) {
// Resolve the default-FBO depth flavor (see the header comment): keep the
// depth attachment when the caller needs it, when a depth/stencil clear is
// pending, or when the active pass already carries it (escalate-only, so
// alternating depth-less draws never split an established depth pass).
Bool includeDefaultFboDepthStencil = true;
if (fbo.IsDefaultFramebuffer()) {
Bool activeDefaultHasDepthStencil = false;
if (const auto* active = GetActiveRenderPass()) {
Bool activeIsSwapchainPass = false;
Bool activeHasSwapchainDepthStencil = false;
for (const auto& tracked : active->trackedAttachmentLayouts) {
activeIsSwapchainPass |= tracked.target == TrackedAttachmentTarget::SwapchainColor;
activeHasSwapchainDepthStencil |=
tracked.target == TrackedAttachmentTarget::SwapchainDepthStencil;
}
activeDefaultHasDepthStencil = activeIsSwapchainPass && activeHasSwapchainDepthStencil;
}
const auto& defaultDepthAtt = fbo.GetAttachment(FramebufferAttachmentType::Depth);
const auto& defaultStencilAtt = fbo.GetAttachment(FramebufferAttachmentType::Stencil);
const Bool pendingDepthStencilClear =
(defaultDepthAtt.IsTexture() && m_clearManager.HasPendingClear(defaultDepthAtt)) ||
HasPendingRenderbufferClear(defaultDepthAtt) ||
(defaultStencilAtt.IsTexture() && m_clearManager.HasPendingClear(defaultStencilAtt)) ||
HasPendingRenderbufferClear(defaultStencilAtt);
includeDefaultFboDepthStencil =
drawUsesDepthStencil || activeDefaultHasDepthStencil || pendingDepthStencilClear;
}
Uint32 swapchainImageIndex) {
auto hasPendingClearOnFramebuffer = [&]() -> Bool {
const auto& drawBuffers = fbo.GetDrawBuffers();
for (auto attachment : drawBuffers) {
@@ -834,7 +613,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
m_rpFastFboVersion == fbo.GetObjectVersion() && m_rpFastSwapchainIndex == swapchainImageIndex &&
m_rpFastTexEpoch == m_textureManager.GetTextureImageEpoch() &&
m_rpFastRbEpoch == m_renderbufferImageEpoch &&
(!fbo.IsDefaultFramebuffer() || m_rpFastHadDepthStencil == includeDefaultFboDepthStencil) &&
m_rpFastRenderPassHash == activeRenderPass->hash && !hasPendingClearOnFramebuffer()) {
auto activeIt = m_renderPasses.find(activeRenderPass->hash);
if (activeIt != m_renderPasses.end()) {
@@ -843,7 +621,7 @@ namespace MobileGL::MG_Backend::DirectVulkan {
}
}
auto compatibilityHash = ComputeHash(fbo, swapchainImageIndex, false, includeDefaultFboDepthStencil);
auto compatibilityHash = ComputeHash(fbo, swapchainImageIndex, false);
if (activeRenderPass != nullptr &&
activeRenderPass->CompatibleWith(compatibilityHash) &&
!hasPendingClearOnFramebuffer()) {
@@ -860,11 +638,10 @@ namespace MobileGL::MG_Backend::DirectVulkan {
m_rpFastTexEpoch = m_textureManager.GetTextureImageEpoch();
m_rpFastRbEpoch = m_renderbufferImageEpoch;
m_rpFastRenderPassHash = activeRenderPass->hash;
m_rpFastHadDepthStencil = activeIt->second.hasDepthStencilAttachment;
activeIt->second.lastUsedFrame = m_frameCounter;
return activeIt->second;
}
auto hash = ComputeHash(fbo, swapchainImageIndex, true, includeDefaultFboDepthStencil);
auto hash = ComputeHash(fbo, swapchainImageIndex, true);
auto it = m_renderPasses.find(hash);
if (it != m_renderPasses.end()) {
it->second.lastUsedFrame = m_frameCounter;
@@ -945,16 +722,14 @@ namespace MobileGL::MG_Backend::DirectVulkan {
if (rbHasClear &&
MG_Util::GetBaseInternalFormatComponentCount(renderbuffer->GetInternalFormat()) == 3) {
// RGB renderbuffers are backed by an RGBA image; the missing alpha reads as 1.
ForceOpaqueClearAlpha(rbClearPayload);
rbClearPayload.color =
FloatVec4(rbClearPayload.color.x(), rbClearPayload.color.y(),
rbClearPayload.color.z(), 1.0f);
}
const VkImageLayout trackedRbLayout = rbResource->layout;
const Bool rbFramebufferSrgb =
MG_State::pGLContext->IsCapabilityEnabled(MobileGL::CapabilityInput::FramebufferSrgb);
const VkFormat rbAttachmentFormat =
ResolveSrgbAttachmentWriteFormat(rbResource->format, rbFramebufferSrgb);
rbDesc.flags = 0;
rbDesc.format = rbAttachmentFormat;
rbDesc.format = rbResource->format;
rbDesc.samples = rbResource->sampleCount;
rbDesc.loadOp = rbHasClear ? VK_ATTACHMENT_LOAD_OP_CLEAR :
(trackedRbLayout == VK_IMAGE_LAYOUT_UNDEFINED ? VK_ATTACHMENT_LOAD_OP_DONT_CARE
@@ -989,8 +764,7 @@ namespace MobileGL::MG_Backend::DirectVulkan {
.finalLayout = rbDesc.finalLayout,
});
textureResources.emplace_back(nullptr);
attachmentViews.emplace_back(rbAttachmentFormat != rbResource->format ? rbResource->unormTwinView
: rbResource->view);
attachmentViews.emplace_back(rbResource->view);
MOBILEGL_ASSERT(attachmentViews.back() != VK_NULL_HANDLE,
"GetOrCreateRenderPass: renderbuffer view missing at color attachment %d", i);
@@ -1059,13 +833,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
MOBILEGL_ASSERT(swapchainImageIndex < swapchainViews.size(),
"GetOrCreateRenderPass: swapchain image index out of range");
trackedColorLayout = m_swapchainObject.GetImageLayout(swapchainImageIndex);
// EGL: a presented color buffer's content is undefined when its
// image comes back around (EGL_BUFFER_DESTROYED, the default
// swap behaviour) - skip the tile load instead of reloading
// stale pixels nobody may rely on.
if (!hasClear && !m_swapchainObject.IsImageContentDefined(swapchainImageIndex)) {
trackedColorLayout = VK_IMAGE_LAYOUT_UNDEFINED;
}
trackedAttachmentLayouts.emplace_back(TrackedAttachmentLayoutInfo {
.target = TrackedAttachmentTarget::SwapchainColor,
.swapchainImageIndex = swapchainImageIndex,
@@ -1079,15 +846,12 @@ namespace MobileGL::MG_Backend::DirectVulkan {
MOBILEGL_ASSERT(textureResource,
"GetOrCreateRenderPass: SyncTextureAndGetDescriptor failed at color attachment %d", i);
textureResources.emplace_back(textureResource);
desc.format = ResolveSrgbAttachmentWriteFormat(
textureResource->format,
MG_State::pGLContext->IsCapabilityEnabled(MobileGL::CapabilityInput::FramebufferSrgb));
desc.format = textureResource->format;
attachmentSampleCount = textureResource->sampleCount;
trackedColorLayout = textureResource->layout;
trackedAttachmentLayouts.emplace_back(TrackedAttachmentLayoutInfo {
.target = TrackedAttachmentTarget::Texture,
.texture = att.GetTexture(),
.textureRaw = att.GetTexture().get(),
.textureMipLevel = attachmentMipLevel,
.finalLayout = desc.finalLayout,
});
@@ -1151,12 +915,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
};
const auto* selectedDepthStencilAttachment = isUsableDepthStencilAttachment(depthAtt) ? &depthAtt :
(isUsableDepthStencilAttachment(stencilAtt) ? &stencilAtt : nullptr);
// Depth-less default-FBO flavor: nothing in this pass touches depth/stencil
// and their content is undefined anyway (EGL swap), so drop the attachment
// and its whole tile load + store.
if (isDefaultFbo && !includeDefaultFboDepthStencil) {
selectedDepthStencilAttachment = nullptr;
}
const Bool hasDistinctDepthAndStencilAttachments =
isUsableDepthStencilAttachment(depthAtt) && isUsableDepthStencilAttachment(stencilAtt) &&
!sameDepthStencilAttachmentObject(depthAtt, stencilAtt);
@@ -1175,12 +933,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
VkImageLayout trackedDepthLayout = isDefaultFbo ?
m_swapchainObject.GetDepthStencilImageLayout(swapchainImageIndex) :
VK_IMAGE_LAYOUT_DEPTH_STENCIL_ATTACHMENT_OPTIMAL;
// EGL 1.5 §3.10.1: every ancillary (depth/stencil) buffer's content is
// undefined after a swap, so the first default-FBO pass of a frame can
// skip the depth/stencil tile load outright.
if (isDefaultFbo && !m_swapchainObject.IsDepthStencilContentDefined(swapchainImageIndex)) {
trackedDepthLayout = VK_IMAGE_LAYOUT_UNDEFINED;
}
depthAttachmentDescription.flags = 0;
VkSampleCountFlagBits depthAttachmentSampleCount = VK_SAMPLE_COUNT_1_BIT;
Int depthAttachmentId = 0;
@@ -1264,7 +1016,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
trackedAttachmentLayouts.emplace_back(TrackedAttachmentLayoutInfo {
.target = TrackedAttachmentTarget::Texture,
.texture = selectedDepthStencilAttachment->GetTexture(),
.textureRaw = selectedDepthStencilAttachment->GetTexture().get(),
.textureMipLevel = attachmentMipLevel,
.finalLayout = depthAttachmentDescription.finalLayout,
});
@@ -1310,22 +1061,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
}
const Bool hasDepthStencilAttachment = depthAttachmentRef.attachment != VK_ATTACHMENT_UNUSED;
// Declare only the used colour-reference span. The GL draw-buffer array
// always spans 8 slots, so passes used to declare colorAttachmentCount=8
// with trailing VK_ATTACHMENT_UNUSED holes - and Adreno configures its
// per-pixel render-backend/export path from the DECLARED count, so every
// fragment of every pass paid the 8-target export cost (measured on
// Adreno 650 / MC 26.2: 11.9 -> 7.5 ms of GPU time per frame, with the
// single-quad swapchain blit pass alone dropping 1.26 -> 0.40 ms).
// Interior GL_NONE holes keep their slots so fragment-output locations
// still line up; a fragment output at a location past the trimmed count
// is discarded, which is exactly GL's semantic for writing to a draw
// buffer set to GL_NONE.
while (!colorAttachmentRefs.empty() &&
colorAttachmentRefs.back().attachment == VK_ATTACHMENT_UNUSED) {
colorAttachmentRefs.pop_back();
}
// Subpass
VkSubpassDescription subpassDesc;
subpassDesc.flags = 0;
@@ -1443,14 +1178,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
void VkRenderPassManager::OnPresent() {
++m_frameCounter;
// Runs every frame boundary, ahead of the render-pass sweep gate below: the walk
// is O(#renderbuffer resources) — single digits in practice — and per-frame
// invocation keeps dead-resource reclaim latency at the aging bound instead of
// coupling it to renderbuffer *use* (the GetOrCreateRenderbufferResource call
// site never runs again once an app stops using renderbuffers).
CollectRenderbufferGarbage();
CollectDeferredRenderbufferReleases(/*destroyAll=*/false);
// Sweep occasionally; evict entries whose last use is far past every
// in-flight frame so their VkRenderPass/VkFramebuffer can be destroyed
// safely (RenderPassEntry's destructor releases the handles).
@@ -1460,12 +1187,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
return;
}
// Collect the dying handles and notify once after the loop: pipelines hashed
// on them share the entries' >kRetireAgeFrames idleness (they are only bound
// by draws that hit those entries), so the observer may destroy them
// immediately - and a single batched notification costs one pipeline-cache
// scan instead of one per evicted pass.
Vector<VkRenderPass> destroyedRenderPasses;
const Uint64 activeHash = s_hasActiveRenderPass ? s_activeRenderPass.hash : 0;
for (auto it = m_renderPasses.begin(); it != m_renderPasses.end();) {
const Bool isActive = s_hasActiveRenderPass && it->first == activeHash;
@@ -1473,15 +1194,11 @@ namespace MobileGL::MG_Backend::DirectVulkan {
if (m_rpFastValid && m_rpFastRenderPassHash == it->first) {
m_rpFastValid = false;
}
destroyedRenderPasses.push_back(it->second.renderPass);
it = m_renderPasses.erase(it);
} else {
++it;
}
}
if (!destroyedRenderPasses.empty() && m_evictionObserver != nullptr) {
m_evictionObserver->OnRenderPassesDestroyed(destroyedRenderPasses);
}
}
Bool VkRenderPassManager::BeginRenderPass(VkCommandBuffer commandBuffer, RenderPassEntry& renderPassEntry) {
@@ -1515,8 +1232,12 @@ namespace MobileGL::MG_Backend::DirectVulkan {
}
}
if ((clearPayload.mask & GL_COLOR_BUFFER_BIT) != 0) {
clearValues[pending.attachmentIndex].color =
MakeVkClearColorValue(clearPayload, ColorFormatLacksAlpha(liveTexture.get()));
clearValues[pending.attachmentIndex].color = {
clearPayload.color.x(),
clearPayload.color.y(),
clearPayload.color.z(),
ResolveColorClearAlpha(liveTexture.get(), clearPayload.color.w())
};
}
if ((clearPayload.mask & GL_DEPTH_BUFFER_BIT) != 0) {
clearValues[pending.attachmentIndex].depthStencil.depth = clearPayload.depth;
@@ -1530,17 +1251,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
renderPassBeginInfo.pClearValues = clearValues.data();
vkCmdBeginRenderPass(commandBuffer, &renderPassBeginInfo, VK_SUBPASS_CONTENTS_INLINE);
// Pre-pass stream bookkeeping: this pass's attachment images are now
// referenced by the open frame recording.
if (s_textureManager != nullptr) {
for (const auto& tracked : renderPassEntry.trackedAttachmentLayouts) {
if (tracked.target == TrackedAttachmentTarget::Texture) {
if (const auto texture = tracked.texture.lock()) {
s_textureManager->StampTextureRecordingUse(texture.get());
}
}
}
}
for (const auto& pending: renderPassEntry.pendingClearAttachments) {
if (pending.hasInlinePayload) {
if (s_renderPassManager != nullptr) {
@@ -1593,15 +1303,11 @@ namespace MobileGL::MG_Backend::DirectVulkan {
case TrackedAttachmentTarget::SwapchainColor:
MOBILEGL_ASSERT(s_swapchainObject != nullptr, "EndRenderPass: swapchain object is null");
s_swapchainObject->SetImageLayout(trackedAttachment.swapchainImageIndex, trackedAttachment.finalLayout);
// The pass stored into the attachment: its content is defined
// until the image is next presented.
s_swapchainObject->SetImageContentDefined(trackedAttachment.swapchainImageIndex, true);
break;
case TrackedAttachmentTarget::SwapchainDepthStencil:
MOBILEGL_ASSERT(s_swapchainObject != nullptr, "EndRenderPass: swapchain object is null");
s_swapchainObject->SetDepthStencilImageLayout(trackedAttachment.swapchainImageIndex,
trackedAttachment.finalLayout);
s_swapchainObject->SetDepthStencilContentDefined(trackedAttachment.swapchainImageIndex, true);
break;
default:
MOBILEGL_ASSERT(false, "EndRenderPass: unsupported tracked attachment target=%d",
@@ -16,7 +16,6 @@
#include "MG_State/GLState/FramebufferState/FramebufferObject.h"
#include <Includes.h>
#include <unordered_map>
#include <vk_mem_alloc.h>
namespace MobileGL::MG_Backend::DirectVulkan {
@@ -43,11 +42,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
struct TrackedAttachmentLayoutInfo {
TrackedAttachmentTarget target = TrackedAttachmentTarget::Texture;
WeakPtr<MG_State::GLState::ITextureObject> texture;
// Identity-compare shortcut for the per-draw "does the active pass use
// this sampled texture" probe: comparing this against a LIVE texture's
// address needs no weak_ptr::lock (two refcount atomics per probe).
// May dangle once the texture dies - compare only, never dereference.
MG_State::GLState::ITextureObject* textureRaw = nullptr;
WeakPtr<MG_State::GLState::RenderbufferObject> renderbuffer;
Uint32 textureMipLevel = 0;
Uint32 swapchainImageIndex = 0;
@@ -163,53 +157,19 @@ namespace MobileGL::MG_Backend::DirectVulkan {
class VkRenderPassManager {
public:
using HashType = Uint64;
// Notified once per OnPresent sweep with every aged-out entry's VkRenderPass
// value: pipelines are hashed on the raw handle, and once destroyed the value
// may be recycled for an incompatible pass, so dependent caches must purge
// everything keyed on them before any new pass can be created (the sweep and
// the notification run back-to-back with no creation in between; observers
// compare the values, never dereference them). Batched so a mass-idle cohort
// (shader-pack switch, dimension exit) costs the observer one pipeline-cache
// scan, not one per dying pass. The wholesale paths
// (Shutdown/RecreateSwapchain) do not notify - their callers already drop
// every pipeline outright.
class IEvictionObserver {
public:
virtual ~IEvictionObserver() = default;
virtual void OnRenderPassesDestroyed(const Vector<VkRenderPass>& renderPasses) = 0;
};
VkRenderPassManager(VkDevice device,
VkPhysicalDevice physicalDevice, VmaAllocator allocator, const VulkanRendererConfig& config,
VkClearManager& clearManager, VkTextureManager& textureManager, SwapchainObject& swapchainObject);
~VkRenderPassManager();
// Observer may be null (no notifications). Not owned.
void SetEvictionObserver(IEvictionObserver* observer) { m_evictionObserver = observer; }
Bool Initialize();
void Shutdown();
HashType ComputeHash(
const MG_State::GLState::FramebufferObject& fbo,
Uint32 swapchainImageIndex,
Bool includePendingClear = true,
Bool includeDefaultFboDepthStencil = true);
// drawUsesDepthStencil: whether the operation about to run inside the pass
// reads or writes the depth/stencil buffer (depth test or stencil test
// enabled, or a depth/stencil clear). Only consulted for the DEFAULT
// framebuffer: EGL undefines its ancillary buffers at every swap, so a
// default-FBO pass whose draws provably never touch depth/stencil is
// created WITHOUT the depth attachment - on a tiler that skips the whole
// depth tile load AND store. The flavor only escalates: once a pass with
// depth is active, later depth-less draws keep using it, and a depth-using
// draw against a depth-less active pass resolves to a new (incompatible)
// entry, which the caller's compatibility check turns into a pass split;
// the new pass's depth loads DONT_CARE (content was undefined all along).
RenderPassEntry& GetOrCreateRenderPass(const MG_State::GLState::FramebufferObject& fbo,
Uint32 swapchainImageIndex,
Bool drawUsesDepthStencil = true);
Bool includePendingClear = true);
RenderPassEntry& GetOrCreateRenderPass(const MG_State::GLState::FramebufferObject& fbo, Uint32 swapchainImageIndex);
void QueueRenderbufferClear(GLbitfield mask, const ClearFramebufferPayload& clearPayload,
const MG_State::GLState::FramebufferObject& drawFbo);
void QueueRenderbufferClear(const ClearAttachmentPayload& clearPayload,
@@ -232,20 +192,12 @@ namespace MobileGL::MG_Backend::DirectVulkan {
UnorderedMap<Uint64, RenderPassEntry> m_renderPasses;
// Monotonic frame counter (bumped in OnPresent) for render-pass cache aging.
Uint64 m_frameCounter = 0;
IEvictionObserver* m_evictionObserver = nullptr;
// Bumped whenever a renderbuffer VkImage is (re)created; together with the texture
// manager's image epoch this invalidates the render-pass fast path on any attachment
// image recreation.
Uint64 m_renderbufferImageEpoch = 1;
public:
// Bumped whenever a renderbuffer backing is (re)created; consecutive-draw
// snapshots include it so an attachment respecify forces a re-resolve.
Uint64 GetRenderbufferImageEpoch() const { return m_renderbufferImageEpoch; }
private:
// Per-draw fast-path memo for GetOrCreateRenderPass (dirty-flag state tracking): when the
// framebuffer state is provably unchanged since the last resolution, the active render pass
// is reused WITHOUT recomputing the expensive per-draw hash. Invalidated by FBO switch /
@@ -258,26 +210,13 @@ namespace MobileGL::MG_Backend::DirectVulkan {
Uint64 m_rpFastTexEpoch = 0;
Uint64 m_rpFastRbEpoch = 0;
Uint64 m_rpFastRenderPassHash = 0;
// Whether the memoized entry carries a depth/stencil attachment; a
// default-FBO resolution whose effective depth request differs must
// miss the memo (the depth-less/depth-full flavors hash differently).
Bool m_rpFastHadDepthStencil = false;
public:
struct RenderbufferResource {
// deadSinceFrame sentinel: the owning weak reference has not been observed
// expired. Dead resources age past every in-flight frame before Destroy
// (see CollectRenderbufferGarbage); the GPU may still reference the image
// for frames-in-flight frames after the GL object dies.
static constexpr Uint64 kNeverObservedDead = UINT64_MAX;
WeakPtr<MG_State::GLState::RenderbufferObject> renderbuffer;
VkImage image = VK_NULL_HANDLE;
VmaAllocation allocation = nullptr;
VkImageView view = VK_NULL_HANDLE;
// UNORM reinterpretation of an sRGB image, used as the attachment view while
// GL_FRAMEBUFFER_SRGB is disabled (raw writes). Null for non-sRGB formats.
VkImageView unormTwinView = VK_NULL_HANDLE;
VkImageLayout layout = VK_IMAGE_LAYOUT_UNDEFINED;
VkFormat format = VK_FORMAT_UNDEFINED;
VkImageAspectFlags aspect = VK_IMAGE_ASPECT_NONE;
@@ -285,8 +224,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
VkSampleCountFlagBits sampleCount = VK_SAMPLE_COUNT_1_BIT;
TextureInternalFormat internalFormat = TextureInternalFormat::Unknown;
Int samples = 0;
// m_frameCounter value at which the weak reference was first seen expired.
Uint64 deadSinceFrame = kNeverObservedDead;
void Destroy(VkDevice device, VmaAllocator allocator);
};
@@ -304,52 +241,12 @@ namespace MobileGL::MG_Backend::DirectVulkan {
ClearAttachmentPayload payload{};
};
// A superseded renderbuffer backing (glRenderbufferStorage respecify) parked
// until enough frame boundaries have passed that no in-flight command buffer
// can still reference it; destroyed in OnPresent (see RetireAgeFrames).
struct DeferredRenderbufferRelease {
VkImage image = VK_NULL_HANDLE;
VmaAllocation allocation = nullptr;
VkImageView view = VK_NULL_HANDLE;
VkImageView unormTwinView = VK_NULL_HANDLE;
Uint64 deferredAtFrame = 0;
};
// Node-based std::unordered_map, deliberately not FastSTL's open-addressing UnorderedMap:
// callers cache a RenderbufferResource* - or a bare &resource->layout - and then make further
// calls that touch this map. BlitFramebuffer is the one that bit: it resolves the source and
// destination colour bindings (ResolveColorBlitBinding caches &rbResource->layout), then
// materializes the source's pending clear, which looks that same resource up again. FastSTL's
// operator[] runs its load-factor check before find_key and reallocates the whole bucket array
// when occupancy crosses it, so even a plain lookup relocates every element; erase only
// tombstones and never decrements the occupancy, so the doubling keeps firing. After a
// relocation the cached pointer names freed storage still holding the pre-clear
// VK_IMAGE_LAYOUT_UNDEFINED, and BlitFramebuffer bails out at "source image layout is
// undefined", silently dropping the blit - renderbuffers_storage_multisample read back zero
// instead of the clear colour on exactly the iterations that grew the table.
//
// Reordering the materialize ahead of the resolves - the fix ReadPixels got - does not cover
// this: the destination resolve still runs after the source pointer is taken. The depth blit,
// GetOrCreateRenderPass's depthRenderbufferResource and ReadDepthStencilPixels cache the same
// kind of pointer, so the invariant belongs in the container rather than in a per-call-site
// ordering rule. m_textureResources is node-based for the same reason. This buys stability
// across rehash and insert only - erase still invalidates the erased element, which is safe
// here because a renderbuffer that is an FBO attachment is held alive by that attachment.
std::unordered_map<MG_State::GLState::RenderbufferObject*, RenderbufferResource> m_renderbufferResources;
UnorderedMap<MG_State::GLState::RenderbufferObject*, RenderbufferResource> m_renderbufferResources;
UnorderedMap<MG_State::GLState::RenderbufferObject*, PendingRenderbufferClear> m_pendingRenderbufferClears;
Vector<DeferredRenderbufferRelease> m_deferredRenderbufferReleases;
// Supported sample counts per attachment format, so per-draw resource lookups
// do not repeat vkGetPhysicalDeviceImageFormatProperties.
UnorderedMap<VkFormat, VkSampleCountFlags> m_attachmentSampleCountsByFormat;
Bool HasPendingRenderbufferClear(
const MG_State::GLState::FramebufferAttachmentObject& attachment) const;
void CollectRenderbufferGarbage();
// Frame-boundary margin after which a resource last referenced by a retired
// GL object (or superseded backing) is provably past every in-flight frame.
Uint64 RetireAgeFrames() const;
void DeferRenderbufferBackingRelease(RenderbufferResource& resource);
void CollectDeferredRenderbufferReleases(Bool destroyAll);
static inline XXH64_state_t* m_hashState = XXH64_createState();
static inline ActiveRenderPassInfo s_activeRenderPass{};
@@ -51,18 +51,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
Float ResolveEffectiveMinLod(const MG_State::GLState::SamplerObject& sampler, Float effectiveMaxLod) {
return std::min(sampler.GetMinLod(), effectiveMaxLod);
}
// A single-level view can only ever deliver the base level, but the LOD clamp must not be
// collapsed to exactly 0: both GL and Vulkan pick magFilter over minFilter from the
// *clamped* lambda, so maxLod = 0 would make every fragment magnify and quietly retire the
// min filter. 0.25 is the value VkSamplerCreateInfo's own note prescribes for emulating
// GL's non-mipmapped minification - large enough for lambda to stay positive, small enough
// that a NEAREST mip mode still rounds down to level 0. Clamped rather than assigned, so a
// texture whose GL_TEXTURE_MAX_LOD really is 0 keeps magnifying as GL says it must.
Float ResolveSingleLevelMaxLod(const MG_State::GLState::SamplerObject& sampler, Bool singleLevelView) {
const Float maxLod = ResolveEffectiveMaxLod(sampler);
return singleLevelView ? std::min(maxLod, 0.25f) : maxLod;
}
} // namespace
Bool VkSamplerManager::Initialize(const InitInfo& initInfo) {
@@ -101,43 +89,15 @@ namespace MobileGL::MG_Backend::DirectVulkan {
m_device = VK_NULL_HANDLE;
m_config = nullptr;
m_frameBoundaryCounter = 0;
}
void VkSamplerManager::OnFrameBoundary() {
++m_frameBoundaryCounter;
// Sweep occasionally; destroy samplers whose last use is far past every
// in-flight frame. Destroy and erase must stay atomic, or Shutdown would
// double-free the handle; an evicted key that recurs simply re-creates
// its sampler on the next miss.
constexpr Uint64 kSweepInterval = 256;
constexpr Uint64 kRetireAgeBoundaries = 1024;
if ((m_frameBoundaryCounter % kSweepInterval) != 0) {
return;
}
for (auto it = m_samplers.begin(); it != m_samplers.end();) {
auto& entry = it->second;
if (m_frameBoundaryCounter - entry.lastUsedFrameBoundary > kRetireAgeBoundaries) {
if (m_device != VK_NULL_HANDLE && entry.handle != VK_NULL_HANDLE) {
vkDestroySampler(m_device, entry.handle, nullptr);
}
it = m_samplers.erase(it);
} else {
++it;
}
}
}
Uint64 VkSamplerManager::BuildSamplerKey(const MG_State::GLState::SamplerObject& sampler,
const MG_State::GLState::ITextureObject& texture,
Bool forceNearestFiltering, Bool singleLevelView) const {
Bool forceNearestFiltering) const {
MOBILEGL_ASSERT(m_config != nullptr, "VkSamplerManager::BuildSamplerKey: m_config is null");
XXHASH_VERIFY(XXH64_reset(m_hashState, m_config->CacheVersion));
XXHASH_VERIFY(XXH64_update(m_hashState, &forceNearestFiltering, sizeof(forceNearestFiltering)));
XXHASH_VERIFY(XXH64_update(m_hashState, &singleLevelView, sizeof(singleLevelView)));
const auto minFilter = sampler.GetMinFilter();
XXHASH_VERIFY(XXH64_update(m_hashState, &minFilter, sizeof(minFilter)));
@@ -151,7 +111,7 @@ namespace MobileGL::MG_Backend::DirectVulkan {
XXHASH_VERIFY(XXH64_update(m_hashState, &wrapT, sizeof(wrapT)));
const auto wrapR = sampler.GetWrapR();
XXHASH_VERIFY(XXH64_update(m_hashState, &wrapR, sizeof(wrapR)));
const auto maxLod = ResolveSingleLevelMaxLod(sampler, singleLevelView);
const auto maxLod = ResolveEffectiveMaxLod(sampler);
const auto minLod = ResolveEffectiveMinLod(sampler, maxLod);
XXHASH_VERIFY(XXH64_update(m_hashState, &minLod, sizeof(minLod)));
XXHASH_VERIFY(XXH64_update(m_hashState, &maxLod, sizeof(maxLod)));
@@ -164,7 +124,7 @@ namespace MobileGL::MG_Backend::DirectVulkan {
XXHASH_VERIFY(XXH64_update(m_hashState, &maxAnisotropy, sizeof(maxAnisotropy)));
const auto compareMode = sampler.GetCompareMode();
XXHASH_VERIFY(XXH64_update(m_hashState, &compareMode, sizeof(compareMode)));
const auto compareFunc = sampler.GetSamplerCompareFunc();
const auto compareFunc = ResolveCompareFunc(sampler, texture);
XXHASH_VERIFY(XXH64_update(m_hashState, &compareFunc, sizeof(compareFunc)));
const auto borderColor = ResolveVkBorderColor(sampler, texture);
XXHASH_VERIFY(XXH64_update(m_hashState, &borderColor, sizeof(borderColor)));
@@ -173,20 +133,10 @@ namespace MobileGL::MG_Backend::DirectVulkan {
VkSampler VkSamplerManager::GetOrCreateSampler(const MG_State::GLState::SamplerObject& sampler,
const MG_State::GLState::ITextureObject& texture,
Bool forceNearestFiltering, Uint32 viewLevelCount) {
// A view that exposes a single mip level has no second level to blend with, so GL's
// *_MIPMAP_* minification filters degenerate to plain filtering on the base level -
// sampling is unchanged by pinning the Vulkan sampler to NEAREST mip mode at LOD 0.
// It is not cosmetic: MobileGL backs such a view with a fully allocated mip chain whose
// tail is never written, and a LINEAR mip mode lets the texture unit issue the level+1
// fetch anyway. On Adreno that fetch lands in uninitialized UBWC pages (or past the
// allocation for a genuinely single-level image) and faults the GPU - the same failure
// the default-framebuffer blit shader had to work around with an explicit-LOD sample.
const Bool singleLevelView = viewLevelCount == 1;
const Uint64 key = BuildSamplerKey(sampler, texture, forceNearestFiltering, singleLevelView);
Bool forceNearestFiltering) {
const Uint64 key = BuildSamplerKey(sampler, texture, forceNearestFiltering);
auto it = m_samplers.find(key);
if (it != m_samplers.end()) {
it->second.lastUsedFrameBoundary = m_frameBoundaryCounter;
return it->second.handle;
}
@@ -194,9 +144,8 @@ namespace MobileGL::MG_Backend::DirectVulkan {
samplerInfo.sType = VK_STRUCTURE_TYPE_SAMPLER_CREATE_INFO;
samplerInfo.magFilter = forceNearestFiltering ? VK_FILTER_NEAREST : ToVkFilter(sampler.GetMagFilter());
samplerInfo.minFilter = forceNearestFiltering ? VK_FILTER_NEAREST : ToVkFilter(sampler.GetMinFilter());
samplerInfo.mipmapMode = (forceNearestFiltering || singleLevelView)
? VK_SAMPLER_MIPMAP_MODE_NEAREST
: ToVkMipmapMode(sampler.GetMipmapMode());
samplerInfo.mipmapMode = forceNearestFiltering ? VK_SAMPLER_MIPMAP_MODE_NEAREST
: ToVkMipmapMode(sampler.GetMipmapMode());
samplerInfo.addressModeU = ToVkAddressMode(sampler.GetWrapS());
samplerInfo.addressModeV = ToVkAddressMode(sampler.GetWrapT());
samplerInfo.addressModeW = ToVkAddressMode(sampler.GetWrapR());
@@ -207,9 +156,8 @@ namespace MobileGL::MG_Backend::DirectVulkan {
samplerInfo.anisotropyEnable = maxAnisotropy > 1.0f ? VK_TRUE : VK_FALSE;
samplerInfo.maxAnisotropy = maxAnisotropy;
samplerInfo.compareEnable = sampler.GetCompareMode() == SamplerCompareMode::CompareToTexture ? VK_TRUE : VK_FALSE;
samplerInfo.compareOp = ToVkCompareOp(sampler.GetSamplerCompareFunc());
// Must match BuildSamplerKey's resolution exactly.
samplerInfo.maxLod = ResolveSingleLevelMaxLod(sampler, singleLevelView);
samplerInfo.compareOp = ToVkCompareOp(ResolveCompareFunc(sampler, texture));
samplerInfo.maxLod = ResolveEffectiveMaxLod(sampler);
samplerInfo.minLod = ResolveEffectiveMinLod(sampler, samplerInfo.maxLod);
samplerInfo.borderColor = ResolveVkBorderColor(sampler, texture);
samplerInfo.unnormalizedCoordinates = VK_FALSE;
@@ -221,7 +169,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
entry.handle = vkSampler;
entry.externalIndex = sampler.GetExternalIndex();
entry.version = sampler.GetVersion();
entry.lastUsedFrameBoundary = m_frameBoundaryCounter;
m_samplers[key] = entry;
return vkSampler;
}
@@ -281,15 +228,24 @@ namespace MobileGL::MG_Backend::DirectVulkan {
}
}
SamplerCompareFunc VkSamplerManager::ResolveCompareFunc(const MG_State::GLState::SamplerObject& sampler,
const MG_State::GLState::ITextureObject& texture) {
const auto compareFunc = sampler.GetSamplerCompareFunc();
if (sampler.GetCompareMode() == SamplerCompareMode::CompareToTexture &&
IsDepthTextureFormat(texture.GetFormat()) && compareFunc == SamplerCompareFunc::Always) {
return SamplerCompareFunc::LessEqual;
}
return compareFunc;
}
VkBorderColor VkSamplerManager::ResolveVkBorderColor(const MG_State::GLState::SamplerObject& sampler,
const MG_State::GLState::ITextureObject& texture) {
if (!UsesBorderColor(sampler)) {
return VK_BORDER_COLOR_FLOAT_TRANSPARENT_BLACK;
}
// Border colour is sampler state: a bound sampler object supplies its own, and a texture
// with none reaches the very same value through the sampler object it owns.
const auto& borderColor = sampler.GetBorderColor();
const auto& borderColor = texture.GetBorderColor();
const Bool isDepthTexture = IsDepthTextureFormat(texture.GetFormat());
if (isDepthTexture) {
@@ -33,42 +33,26 @@ public:
Bool Initialize(const InitInfo& initInfo);
void Shutdown();
// viewLevelCount is the mip-level count of the image view this sampler will be paired
// with; 0 means "unknown, do not narrow". See GetOrCreateSampler for why it matters.
VkSampler GetOrCreateSampler(const MG_State::GLState::SamplerObject& sampler,
const MG_State::GLState::ITextureObject& texture,
Bool forceNearestFiltering = false,
Uint32 viewLevelCount = 0);
// Frame boundary hook: ages the sampler cache and destroys samplers not used
// for many frames. The key hashes continuous float state (lodBias, LOD clamps,
// anisotropy), so an app animating those would otherwise mint an unbounded
// stream of never-destroyed VkSamplers and eventually exhaust the device's
// maxSamplerAllocationCount. A sampler idle for over a thousand frame
// boundaries cannot be referenced by any in-flight command buffer (frames in
// flight are single digits), and every descriptor set the GPU consumes is
// written that same frame with live handles (the per-binding resolve memo and
// descriptor-set reuse are both frame-reset), so destruction here needs no
// fence wait. Self-gated: one counter bump and compare except on sweep
// boundaries.
void OnFrameBoundary();
Bool forceNearestFiltering = false);
private:
struct SamplerCacheEntry {
VkSampler handle = VK_NULL_HANDLE;
Uint externalIndex = 0;
Uint16 version = 0;
// Frame boundary of the last cache hit; entries idle past the
// OnFrameBoundary retirement age have their VkSampler destroyed.
Uint64 lastUsedFrameBoundary = 0;
};
Uint64 BuildSamplerKey(const MG_State::GLState::SamplerObject& sampler,
const MG_State::GLState::ITextureObject& texture,
Bool forceNearestFiltering, Bool singleLevelView) const;
Bool forceNearestFiltering) const;
static VkFilter ToVkFilter(SamplerFilterMode mode);
static VkSamplerMipmapMode ToVkMipmapMode(SamplerMipmapMode mode);
static VkSamplerAddressMode ToVkAddressMode(SamplerWrapMode mode);
static VkCompareOp ToVkCompareOp(SamplerCompareFunc func);
static SamplerCompareFunc ResolveCompareFunc(const MG_State::GLState::SamplerObject& sampler,
const MG_State::GLState::ITextureObject& texture);
static VkBorderColor ResolveVkBorderColor(const MG_State::GLState::SamplerObject& sampler,
const MG_State::GLState::ITextureObject& texture);
// The anisotropy Vulkan will actually apply: 1.0 (i.e. disabled) unless the feature is on and
@@ -83,8 +67,6 @@ private:
Bool m_samplerAnisotropySupported = false;
Float m_maxSamplerAnisotropy = 1.0f;
UnorderedMap<Uint64, SamplerCacheEntry> m_samplers;
// Monotonic frame-boundary counter (bumped in OnFrameBoundary) for cache aging.
Uint64 m_frameBoundaryCounter = 0;
static inline XXH64_state_t* m_hashState = XXH64_createState();
};
} // namespace MobileGL::MG_Backend::DirectVulkan
File diff suppressed because it is too large Load Diff
@@ -28,9 +28,6 @@ public:
// manager keys its per-draw fast path on this so an attachment's image recreation
// invalidates the cached render pass (dirty-flag tracking; portable to Vulkan 1.1).
Uint64 GetTextureImageEpoch() const { return m_textureImageEpoch; }
// Bumped whenever any tracked texture resource is erased; cached
// TextureResource pointers are valid only while this is unchanged.
Uint64 GetResourceEraseEpoch() const { return m_resourceEraseEpoch; }
struct TextureIdentity {
MG_State::GLState::ITextureObject* texture = nullptr;
@@ -56,20 +53,6 @@ public:
VkCommandPool commandPool = VK_NULL_HANDLE;
VkQueue graphicsQueue = VK_NULL_HANDLE;
Uint32 frameCount = 0;
// VK_KHR_image_format_list is enabled: MUTABLE_FORMAT images can name the exact set of
// formats they will be viewed as, which is what lets a tiler keep them compressed.
Bool imageFormatListSupported = false;
// Union of shader stages sampled-read barriers may name on this device; the renderer
// builds it from the enabled features because geometry/tessellation stage bits are
// invalid in a barrier when their feature is off.
VkPipelineStageFlags sampledReadStageMask = VK_PIPELINE_STAGE_VERTEX_SHADER_BIT |
VK_PIPELINE_STAGE_FRAGMENT_SHADER_BIT |
VK_PIPELINE_STAGE_COMPUTE_SHADER_BIT;
// Family of `graphicsQueue`; the manager creates its own command pool
// on it for the recycled upload-batch command buffers, so their parked
// allocations never sit in (and fragment) the renderer's shared pool
// that frame command buffers churn through every frame.
Uint32 graphicsQueueFamilyIndex = 0;
};
struct TextureResource {
@@ -78,16 +61,12 @@ public:
Uint32 baseArrayLayer = 0;
Uint32 layerCount = 1;
VkImageViewType viewType = VK_IMAGE_VIEW_TYPE_2D;
// May differ from the image format: sRGB images attach through their UNORM
// twin while GL_FRAMEBUFFER_SRGB is disabled.
VkFormat viewFormat = VK_FORMAT_UNDEFINED;
Bool operator==(const AttachmentViewKey& other) const {
return mipLevel == other.mipLevel &&
baseArrayLayer == other.baseArrayLayer &&
layerCount == other.layerCount &&
viewType == other.viewType &&
viewFormat == other.viewFormat;
viewType == other.viewType;
}
};
@@ -98,8 +77,6 @@ public:
hash ^= std::hash<Uint32>{}(key.layerCount) + 0x9e3779b9u + (hash << 6) + (hash >> 2);
hash ^= std::hash<Uint32>{}(static_cast<Uint32>(key.viewType)) +
0x9e3779b9u + (hash << 6) + (hash >> 2);
hash ^= std::hash<Uint32>{}(static_cast<Uint32>(key.viewFormat)) +
0x9e3779b9u + (hash << 6) + (hash >> 2);
return hash;
}
};
@@ -180,25 +157,7 @@ public:
VkImageViewType viewType = VK_IMAGE_VIEW_TYPE_2D;
VkSampleCountFlagBits sampleCount = VK_SAMPLE_COUNT_1_BIT;
VkImageCreateFlags imageCreateFlags = 0;
// Usage the live image was created with. STORAGE is only requested for textures that
// have actually been bound to a GL image unit, because on Adreno a storage-capable
// image loses UBWC bandwidth compression; a later image binding upgrades the usage
// and recreates the image, so the resolved usage has to be part of the compatibility
// check that decides whether the existing image can be kept.
VkImageUsageFlags usageFlags = 0;
// True once this image was (re)resolved while the texture was already marked as an
// image-unit texture. Distinguishes "not upgraded yet" from "cannot be upgraded"
// (a format whose optimalTilingFeatures lack STORAGE_IMAGE never gains the bit), so
// NeedsStorageImagePreparation cannot ask for a recreate that will never happen.
Bool storageUsageResolved = false;
Uint16 syncedTextureParamsVersion = 0;
// Recording generation (VkTextureManager::GetRecordingGeneration) of the last
// command referencing this image that was recorded into the CURRENT frame
// command buffer. An image untouched by the open recording may have its
// out-of-pass work (deferred clears, sampled-layout transitions) recorded
// into the frame's PRE command buffer - which executes strictly before the
// frame's commands - instead of splitting the active render pass.
Uint64 lastRecordingGeneration = 0;
// Snapshot of ITextureObject::GetContentVersion() at the last successful sync;
// lets SyncTexture skip the whole re-check/re-upload when content is unchanged.
Uint64 syncedContentVersion = 0;
@@ -231,10 +190,7 @@ public:
std::swap(this->viewType, that.viewType);
std::swap(this->sampleCount, that.sampleCount);
std::swap(this->imageCreateFlags, that.imageCreateFlags);
std::swap(this->usageFlags, that.usageFlags);
std::swap(this->storageUsageResolved, that.storageUsageResolved);
std::swap(this->syncedTextureParamsVersion, that.syncedTextureParamsVersion);
std::swap(this->lastRecordingGeneration, that.lastRecordingGeneration);
std::swap(this->syncedContentVersion, that.syncedContentVersion);
std::swap(this->syncedMipLevelCount, that.syncedMipLevelCount);
}
@@ -295,8 +251,6 @@ public:
viewType = VK_IMAGE_VIEW_TYPE_2D;
sampleCount = VK_SAMPLE_COUNT_1_BIT;
imageCreateFlags = 0;
usageFlags = 0;
storageUsageResolved = false;
syncedTextureParamsVersion = 0;
syncedContentVersion = 0;
syncedMipLevelCount = 0;
@@ -313,18 +267,6 @@ public:
Bool Initialize(const InitInfo& initInfo);
void Shutdown();
void BeginFrame(Uint32 frameIndex);
// Submits the accumulated texture-upload batch (one command buffer, one
// vkQueueSubmit, one pooled fence) if any uploads are pending. MUST run
// before any other vkQueueSubmit on the shared graphics queue whose
// commands may consume an image the batch writes - the frame command
// buffer submit (mid-frame flush, readback, Present) and the
// preserve-on-recreate copy are the existing callers. No-op when the
// batch is empty.
void FlushPendingUploads();
// Drains every frame slot's deferred image/view releases. Only valid when
// the caller has proven every queue submission complete; used by the
// present-less frame-boundary drain.
void CollectAllDeferredReleases();
TextureResource* SyncTextureAndGetDescriptor(
MG_State::GLState::ITextureObject& texture);
@@ -343,36 +285,6 @@ public:
VkImageLayout newLayout);
Bool TransitionTextureForSampling(VkCommandBuffer commandBuffer, MG_State::GLState::ITextureObject& texture);
Bool TransitionTextureForStorageImage(VkCommandBuffer commandBuffer, MG_State::GLState::ITextureObject& texture);
// Recording-generation bookkeeping for the pre-pass command stream. The
// generation advances every time the frame command buffer (re)begins
// recording; a resource whose stamp does not match was not referenced by
// any command in the open recording, so its out-of-pass work may safely
// execute ahead of the whole recording (in the pre command buffer).
void AdvanceRecordingGeneration() { ++m_recordingGeneration; }
void StampResourceRecordingUse(TextureResource& resource) const {
resource.lastRecordingGeneration = m_recordingGeneration;
}
// Map-lookup variant for callers that only hold the GL texture object.
void StampTextureRecordingUse(MG_State::GLState::ITextureObject* texture);
Bool WasTouchedThisRecording(const TextureResource& resource) const {
return resource.lastRecordingGeneration == m_recordingGeneration;
}
// Records that this texture is bound to a GL image unit, so its image must carry
// VK_IMAGE_USAGE_STORAGE_BIT. Must be called before NeedsStorageImagePreparation, and
// therefore before the render pass is committed: an image that has to be upgraded is
// recreated, which is illegal inside a render pass. Sticky for the texture's lifetime -
// GL lets an image binding come and go, and re-creating the image every time it does
// would cost far more than the compression it wins back.
void MarkStorageImageTexture(MG_State::GLState::ITextureObject& texture);
// True when this texture is marked but its live image predates the mark, i.e. the next sync
// will recreate it with STORAGE usage and copy the old contents forward. Callers use this to
// submit their pending recording first, so that copy cannot read pre-flush content.
Bool NeedsStorageUsageUpgrade(MG_State::GLState::ITextureObject& texture) const;
// The same ordering question for the other recreate-and-preserve trigger: true when this
// texture's live image carries a shorter mip chain than a full one, so defining the missing
// levels recreates it and copies the old contents forward.
Bool NeedsMipChainGrowth(MG_State::GLState::ITextureObject& texture) const;
// Non-mutating probe for the per-draw storage-image fast path: true when preparing this
// texture as a storage image may need work that is illegal inside a render pass (resource
// creation, dirty-content upload, or a layout transition to GENERAL). Unknown state reports
@@ -419,9 +331,6 @@ public:
private:
// Bumped in SyncTextureResource right after vmaCreateImage(texture). See GetTextureImageEpoch().
Uint64 m_textureImageEpoch = 1;
// See AdvanceRecordingGeneration. Starts above every resource's default
// stamp of 0 so a fresh resource counts as untouched.
Uint64 m_recordingGeneration = 1;
Bool SyncTexture(MG_State::GLState::ITextureObject &texture,
TextureResource &outResource);
@@ -452,31 +361,18 @@ private:
void DeferViewRelease(VkImageView view);
void CollectDeferredReleases(Uint32 frameIndex);
void DestroyDeferredReleases();
// Frees the fence/command buffer/staging buffer of every in-flight texture
// upload whose fence has signaled (submission order = completion order on
// the single queue, so the scan stops at the first still-pending entry).
// waitAll blocks on every entry - Shutdown's drain.
void ReclaimCompletedUploads(Bool waitAll = false);
static TextureIdentity MakeTextureIdentity(MG_State::GLState::ITextureObject* texture);
void EraseTrackedTexture(const TextureIdentity& identity);
void PruneStaleTextureAliases(MG_State::GLState::ITextureObject* texture);
SizeT PruneDeadTextures();
VkDevice m_device = VK_NULL_HANDLE;
VkPhysicalDevice m_physicalDevice = VK_NULL_HANDLE;
VmaAllocator m_allocator = nullptr;
VkCommandPool m_commandPool = VK_NULL_HANDLE;
// Dedicated pool for the recycled upload-batch command buffers (see
// InitInfo::graphicsQueueFamilyIndex).
VkCommandPool m_uploadCommandPool = VK_NULL_HANDLE;
VkQueue m_graphicsQueue = VK_NULL_HANDLE;
Bool m_imageFormatListSupported = false;
Uint32 m_currentFrameIndex = 0;
Uint8 m_gcCounter = 0;
// Frame-boundary GC gate: counts BeginFrame calls, not draws, so texture churn
// through non-draw paths (FBO clears, readbacks) still reaches the prune.
Uint32 m_gcFrameCounter = 0;
// Active only between BeginDrawSyncScope/EndDrawSyncScope; identities of
// textures already fully synced in the current draw (small N -> flat scan).
Bool m_drawSyncScopeActive = false;
@@ -489,92 +385,12 @@ private:
TextureResource* resource = nullptr;
};
Vector<DrawSyncedTexture> m_drawSyncedThisDraw;
// Cross-draw sampled-texture memo: the same few textures (atlas, lightmap)
// are resolved on every draw, so cache their resource pointers and skip the
// alive/resource map lookups. Node-based std::unordered_map keeps the
// pointees stable across inserts; erases bump m_resourceEraseEpoch, which
// every memo entry must match. SyncTexture still runs on memo hits, so
// content/param freshness is unaffected. A dead-then-reused texture address
// cannot false-hit: the new object carries a new lifetime id.
struct SyncedTextureMemoEntry {
const MG_State::GLState::ITextureObject* texture = nullptr;
Uint64 lifetimeId = 0;
Uint64 eraseEpoch = 0;
TextureResource* resource = nullptr;
};
static constexpr Uint32 kSyncedTextureMemoSize = 8;
SyncedTextureMemoEntry m_syncedTextureMemo[kSyncedTextureMemoSize];
Uint32 m_syncedTextureMemoNext = 0;
Uint64 m_resourceEraseEpoch = 1;
// Formats whose mutable-image probe failed on this device; their images are created
// without MUTABLE_FORMAT_BIT so repeat syncs neither re-probe nor flag-mismatch.
std::unordered_set<VkFormat> m_mutableFormatUnsupported;
// Formats whose 3D images refused VK_IMAGE_CREATE_2D_ARRAY_COMPATIBLE_BIT. Per format+usage,
// exactly like the mutable-format verdict above, so it is answered at image creation and
// remembered rather than probed once globally.
std::unordered_set<VkFormat> m_2dArrayCompatibleUnsupported;
std::unordered_map<TextureIdentity, WeakPtr<MG_State::GLState::ITextureObject>, TextureIdentityHash> m_aliveObjects;
std::unordered_map<TextureIdentity, TextureResource, TextureIdentityHash> m_textureResources;
// Textures that have been bound to a GL image unit (see MarkStorageImageTexture).
std::unordered_set<TextureIdentity, TextureIdentityHash> m_storageImageTextures;
// Supported multisample counts per format, so repeat texture syncs do not
// re-query vkGetPhysicalDeviceImageFormatProperties.
std::unordered_map<VkFormat, VkSampleCountFlags> m_multisampleCountsByFormat;
Vector<Vector<TextureResource>> m_deferredReleases;
Vector<Vector<VkImageView>> m_deferredViewReleases;
// --- Batched upload machinery ---
// Uploads within a frame are recorded into ONE shared command buffer and
// submitted with ONE vkQueueSubmit at FlushPendingUploads (the renderer
// flushes before every frame-command-buffer submit). Staging memory comes
// from a pool of persistently-mapped, reusable blocks instead of a
// vmaCreateBuffer per upload.
struct UploadStagingBlock {
VkBuffer buffer = VK_NULL_HANDLE;
VmaAllocation allocation = nullptr;
Uint8* mapped = nullptr; // persistently mapped for the block's lifetime
VkDeviceSize capacity = 0;
VkDeviceSize cursor = 0; // bump cursor while the block backs the open batch
};
// Opens the batch command buffer lazily (allocates/reuses + begins recording).
VkCommandBuffer EnsureUploadBatchOpen();
// Bump-allocates `size` staging bytes for the open batch, growing onto a
// new/pooled block when the current one cannot fit. Returns the write
// pointer; outBuffer/outBaseOffset locate the space for copy commands.
Uint8* AcquireUploadStagingSpace(VkDeviceSize size, VkBuffer& outBuffer, VkDeviceSize& outBaseOffset);
void RecycleUploadStagingBlock(UploadStagingBlock&& block);
// Drops a recorded-but-unsubmitted batch on the floor. Shutdown only: the
// device is being torn down, so the lost texel data is unobservable.
void DiscardPendingUploadBatch();
void DestroyUploadPools();
Vector<UploadStagingBlock> m_freeUploadStagingBlocks;
VkDeviceSize m_freeUploadStagingBytes = 0;
Vector<VkCommandBuffer> m_freeUploadCommandBuffers;
Vector<VkFence> m_freeUploadFences;
Bool m_uploadBatchOpen = false;
VkCommandBuffer m_uploadBatchCommandBuffer = VK_NULL_HANDLE;
// Blocks whose staging bytes the open batch's copies reference (last =
// the block the bump cursor is currently allocating from).
Vector<UploadStagingBlock> m_uploadBatchBlocks;
// Images the open batch writes; consulted for the rare re-upload-after-
// draw flush and by DeferResourceRelease (an unsubmitted command buffer
// referencing a deferred-released image would escape every fence-based
// destruction proof, so the batch is flushed before the image is parked).
Vector<VkImage> m_uploadBatchImages;
VkDeviceSize m_uploadBatchStagingBytes = 0;
// Texture uploads are submitted out-of-band but NOT waited on (waiting
// behind the queue serialized the CPU against the previous frame's GPU
// work every time an animated atlas re-uploaded). Each flushed batch's
// transients are parked here and RECYCLED (fence reset to the fence pool,
// command buffer reset to the CB pool, staging blocks back to the block
// pool) once the batch fence signals.
struct PendingUploadReclaim {
VkFence fence = VK_NULL_HANDLE;
VkCommandBuffer commandBuffer = VK_NULL_HANDLE;
Vector<UploadStagingBlock> stagingBlocks;
};
Vector<PendingUploadReclaim> m_pendingUploadReclaims;
};
} // namespace MobileGL::MG_Backend::DirectVulkan
File diff suppressed because it is too large Load Diff
@@ -76,10 +76,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
GLenum indexType = GL_UNSIGNED_SHORT;
SizeT indexByteOffset = 0;
SizeT indexByteSize = 0;
// Interpret indexByteOffset as a raw client pointer even when an element
// array buffer is bound (backend-synthesized index lists, e.g. the
// GL_LINE_LOOP -> LINE_STRIP rewrite).
Bool forceClientMemory = false;
};
struct DrawIndexedCmd {
@@ -118,10 +114,7 @@ namespace MobileGL::MG_Backend::DirectVulkan {
}
};
class VulkanRenderer : public IBufferCopyCommandProvider,
public FrameContext::IRecordingObserver,
public VkRenderPassManager::IEvictionObserver,
public ProgramFactory::IEvictionObserver {
class VulkanRenderer : public IBufferCopyCommandProvider, public FrameContext::IRecordingObserver {
public:
VulkanRenderer(NativeWindowType window, const VulkanRendererConfig& cfg = {});
~VulkanRenderer();
@@ -138,31 +131,9 @@ namespace MobileGL::MG_Backend::DirectVulkan {
// recording, before any render pass.
void OnFrameCommandRecordingBegan(VkCommandBuffer commandBuffer) override;
// VkRenderPassManager::IEvictionObserver: the render-pass aging sweep just
// destroyed these VkRenderPasses; evict every graphics pipeline hashed on a
// dying handle (they share its >1024-boundary idleness, so immediate
// destruction is safe) and drop the last-pipeline memo if any went.
void OnRenderPassesDestroyed(const Vector<VkRenderPass>& renderPasses) override;
// ProgramFactory::IEvictionObserver: an aged-out program entry was
// destroyed; evict its compute pipeline and graphics pipelines (same
// idleness guarantee - they are only bound through draws/dispatches that
// stamp the program entry) and purge the descriptor-set cache entries
// keyed by its now-recyclable VkDescriptorSetLayout handle.
void OnProgramEvicted(ProgramFactory::HashType programHash,
VkDescriptorSetLayout descriptorSetLayout) override;
Bool SetupDraw(FrameContext::FrameData& frame, GLenum mode, Flags<DrawSetupAspect> aspects,
const DrawCmdParam& drawParams,
const IndexBufferView* pIndexBufferView = nullptr);
// ANGLE-style consecutive-draw fast path: SetupDraw snapshots the fully
// resolved draw configuration; the next draw whose cheap version/identity
// checks all match skips the resolution half (LOD probe, sampled-set
// walk, render-pass and pipeline resolution) and jumps straight to the
// per-draw tail. Returns false (leaving no side effects that the full
// path cannot redo idempotently) whenever anything might have changed.
Bool TrySetupDrawFastPath(FrameContext::FrameData& frame, GLenum mode, Flags<DrawSetupAspect> aspects,
const DrawCmdParam& drawParams, const IndexBufferView* pIndexBufferView);
void ClearAttachmentsOnActiveRenderPass(VkCommandBuffer commandBuffer,
const RenderPassEntry& compatibleRenderPassEntry);
@@ -181,10 +152,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
void ClearBufferiv(GLenum buffer, GLint drawbuffer, const GLint* value);
void ClearNamedFramebufferfv(const SharedPtr<MG_State::GLState::FramebufferObject>& framebuffer,
GLenum buffer, GLint drawbuffer, const GLfloat* value);
void ClearNamedFramebufferiv(const SharedPtr<MG_State::GLState::FramebufferObject>& framebuffer,
GLenum buffer, GLint drawbuffer, const GLint* value);
void ClearNamedFramebufferuiv(const SharedPtr<MG_State::GLState::FramebufferObject>& framebuffer,
GLenum buffer, GLint drawbuffer, const GLuint* value);
void ClearNamedFramebufferfi(const SharedPtr<MG_State::GLState::FramebufferObject>& framebuffer,
GLenum buffer, GLint drawbuffer, GLfloat depth, GLint stencil);
void BlitFramebuffer(GLint srcX0, GLint srcY0, GLint srcX1, GLint srcY1,
@@ -204,25 +171,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
GLsizei srcWidth, GLsizei srcHeight, GLsizei srcDepth);
void GenerateMipmap(GLenum target);
void ReadPixels(GLint x, GLint y, GLsizei width, GLsizei height, GLenum format, GLenum type, void* pixels);
// GL_DEPTH_COMPONENT / GL_DEPTH_STENCIL / GL_STENCIL_INDEX readback from the
// read framebuffer's depth/stencil attachment (per-aspect buffer copies with
// CPU repacking into the requested client layout).
void ReadDepthStencilPixels(MG_State::GLState::FramebufferObject& readFbo, GLint x, GLint y, GLsizei width,
GLsizei height, GLenum format, GLenum type, void* pixels);
// Copy-and-repack core shared by depth-stencil ReadPixels and GetTexImage;
// expects command recording to be active and any render pass already ended.
void ReadDepthStencilImageToClient(VkImage image, VkFormat vkFormat, VkImageLayout* trackedLayout,
VkImageAspectFlags imageAspect, Uint32 mipLevel, Uint32 baseArrayLayer,
GLint x, GLint y, GLsizei width, GLsizei height, GLenum format, GLenum type,
void* pixels);
// Same-extent depth blit between images of different depth formats: host
// round-trip with a per-texel re-encode (see BlitNamedFramebuffer).
Bool BlitDepthAcrossFormats(FrameContext::FrameData& frame, VkImage srcImage, VkFormat srcFormat,
VkImageLayout* srcTrackedLayout, Uint32 srcMipLevel, Uint32 srcBaseArrayLayer,
VkImage dstImage, VkFormat dstFormat, VkImageLayout* dstTrackedLayout,
Uint32 dstMipLevel, Uint32 dstBaseArrayLayer, GLint srcX, GLint srcY, GLint dstX,
GLint dstY, GLint width, GLint height, VkImageLayout srcRestoreLayout,
VkImageLayout dstRestoreLayout, Bool stencilAspect);
static SizeT GetReadbackTexelSize(VkFormat sourceFormat);
static Bool ConvertReadbackPixels(const Uint8* sourcePixels, VkFormat sourceFormat,
GLsizei width, GLsizei height, GLenum destinationFormat,
@@ -308,20 +256,7 @@ namespace MobileGL::MG_Backend::DirectVulkan {
const VkTimerQueryManager::TimestampRecord& end) const;
Uint64 GetTimerQueryTimestampNs(const VkTimerQueryManager::TimestampRecord& record) const;
// GL_SAMPLES_PASSED occlusion queries: every app draw between Start and Stop is
// wrapped in a Vulkan occlusion query slot; the result is the slot sum. Requires
// hostQueryReset for slot recycling - Start fails (frontend keeps the query
// unsupported) when the device lacks it.
Bool StartOcclusionQueryCapture();
void StopOcclusionQueryCapture(Vector<Uint32>& outSlots);
// Flushes pending commands, waits, sums the slots, and recycles them.
Bool ResolveOcclusionQueryResult(const Vector<Uint32>& slots, Uint64& outSamples);
void RequestSwapchainResize(Uint32 width, Uint32 height);
// Re-query the surface and report whether the live swapchain no longer matches it
// (size or orientation). This - not a VK_SUBOPTIMAL_KHR result - is what decides a
// rebuild, so a surface the driver merely considers suboptimal cannot thrash.
Bool SwapchainIsOutOfDate();
// Returns false when the surface is zero-area (minimized/hidden window):
// no new swapchain is installed and presentation must stay suspended.
Bool RecreateSwapchain();
@@ -410,46 +345,16 @@ namespace MobileGL::MG_Backend::DirectVulkan {
VkFence AcquirePooledSubmitFence();
void DestroySubmitFencePool();
Bool HasPendingRecordedWork() const;
// Frame-boundary housekeeping for paths that never reach Present's
// tail (present-less readback loops, suspended presentation, blocking
// sync waits): runs the same per-frame drains Present performs, but
// only when every queue submission has been observed complete AND no
// recorded-but-unsubmitted commands exist - i.e. when CPU-GPU overlap
// is provably already zero. Never blocks (non-blocking fence poll
// only), so the presenting path's frames-in-flight pipelining is
// untouched. Returns true when the drain ran.
Bool TryDrainFrameTransients();
Vector<SubmitRecord> m_inFlightSubmits;
Vector<VkFence> m_freeSubmitFences;
Uint64 m_submitCounter = 0;
Uint64 m_completedSubmitCounter = 0;
// Drains since the last Present, gating the drain's frame-boundary-equivalent
// work (arena rewind + cache aging): a presenting app's mid-frame
// readbacks/waits must neither churn the transient caches nor accelerate the
// aging clocks, while present-less loops still cross a boundary every few
// iterations. Reset in Present.
Uint32 m_drainsSinceLastPresent = 0;
NativeWindowType m_window = 0;
void* m_platformDisplay = nullptr;
void* m_platformLibrary = nullptr;
void* m_platformCloseDisplay = nullptr;
// Some real ICDs (e.g. NVIDIA's proprietary Linux driver) don't implement
// VK_EXT_headless_surface at all. Detected once in CreateInstance() from the
// enumerated instance extensions; when false, CreateSurface() falls back to a
// hidden Xlib window instead of vkCreateHeadlessSurfaceEXT.
Bool m_headlessSurfaceSupported = true;
// Set when CreateSurface() had to create its own Xlib window for the fallback
// above (rather than being handed one by the caller), so Shutdown() knows it
// owns that window and must destroy it.
Bool m_ownsFallbackXlibWindow = false;
// Android has the same shortfall: no Mali/Adreno driver seen so far exposes
// VK_EXT_headless_surface, so a windowless (EGL pbuffer) context gets an
// AImageReader's ANativeWindow to hand the WSI instead. Nothing is ever
// displayed - the reader's images are simply never acquired. Owned here, so
// Shutdown() deletes it.
void* m_fallbackImageReader = nullptr;
VulkanRendererConfig m_config;
Bool m_swapchainResizeRequested = false;
// Presentation is suspended while the window is zero-area (minimized): the
@@ -462,9 +367,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
Vector<VkExtensionProperties> m_extensions;
VkInstance m_instance = VK_NULL_HANDLE;
VkDebugUtilsMessengerEXT m_debugMessenger = VK_NULL_HANDLE;
// Fallback reporting channel for drivers that ship the validation layers but
// only expose the older VK_EXT_debug_report (Adreno 650 / Vulkan 1.1.128).
VkDebugReportCallbackEXT m_debugReportCallback = VK_NULL_HANDLE;
PhysicalDevice m_physicalDevice;
VkDevice m_device = VK_NULL_HANDLE;
VmaAllocator m_allocator = nullptr;
@@ -491,13 +393,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
// needs no feature). Both cached at device creation and drive a hard-fail-at-draw when absent.
Bool m_dualSrcBlendFeatureEnabled = false;
Bool m_primitiveTopologyListRestartFeatureEnabled = false;
// Union of shader stages sampled-read barriers may name; built at device creation
// because geometry/tessellation stage bits are invalid in a barrier when their
// feature is off (VUID-vkCmdPipelineBarrier-srcStageMask-04090/-04091), and
// ALL_GRAPHICS would also serialize against non-shader stages.
VkPipelineStageFlags m_sampledReadStageMask = VK_PIPELINE_STAGE_VERTEX_SHADER_BIT |
VK_PIPELINE_STAGE_FRAGMENT_SHADER_BIT |
VK_PIPELINE_STAGE_COMPUTE_SHADER_BIT;
// Cached at device creation from the graphics queue family properties
// and device limits; drives timer-query support.
Uint32 m_timestampValidBits = 0;
@@ -509,98 +404,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
Uint32 stride);
static inline PFNDrawIndexedIndirectCountFunc s_vkCmdDrawIndexedIndirectCount = nullptr;
// VK_EXT_transform_feedback (GL transform feedback capture)
Bool m_transformFeedbackFeatureEnabled = false;
// VK_EXT_provoking_vertex. Vulkan's built-in convention is "provoking vertex first"; GL's
// default is LAST_VERTEX_CONVENTION, and GL derives BOTH flat shading and the transform
// feedback vertex order from it. provokingVertexLast alone fixes flat shading and the
// input-assembler capture order and has no dependency on transform feedback; only
// transformFeedbackPreservesProvokingVertex does.
Bool m_provokingVertexLastEnabled = false;
// transformFeedbackPreservesProvokingVertex was actually enabled at device creation. Kept
// separate because it is the only thing that arms
// VUID-VkGraphicsPipelineCreateInfo-topology-04884, the rule that forbids a TRIANGLE_FAN
// pipeline from asking for LAST on a device that cannot preserve a fan's provoking vertex.
Bool m_provokingVertexXfbPreserveEnabled = false;
// provokingVertexModePerPipeline: when VK_FALSE every pipeline in one render pass instance
// must agree on the mode, so glProvokingVertex(GL_FIRST_VERTEX_CONVENTION) cannot be honoured
// per draw and every pipeline takes GL's default (LAST) instead.
Bool m_provokingVertexModePerPipeline = false;
// transformFeedbackPreservesTriangleFanProvokingVertex.
Bool m_provokingVertexFanPreserved = false;
// Per-pipeline provoking-vertex mode. capturesXfbFromGeometryStage must be a LINK-TIME
// property of the program, never the dynamic "is transform feedback active" flag: the
// 8-entry m_pipelineMemo and the SetupDrawSnapshot fast path key on programObj.hash and
// the pipeline-state value hash, neither of which moves when glBeginTransformFeedback is
// called, so a dynamic input here would hand back a stale VkPipeline.
VkProvokingVertexModeEXT SelectProvokingVertexMode(VkPrimitiveTopology topology,
Bool capturesXfbFromGeometryStage) const;
// VK_EXT_vertex_attribute_divisor: without it every non-zero glVertexAttribDivisor
// behaves as 1, because that is all Vulkan's instance input rate can express.
Bool m_vertexAttributeDivisorEnabled = false;
static inline PFN_vkCmdBindTransformFeedbackBuffersEXT s_vkCmdBindTransformFeedbackBuffersEXT = nullptr;
static inline PFN_vkCmdBeginTransformFeedbackEXT s_vkCmdBeginTransformFeedbackEXT = nullptr;
static inline PFN_vkCmdEndTransformFeedbackEXT s_vkCmdEndTransformFeedbackEXT = nullptr;
// Counter buffers (one 4-byte slot per capture binding) let consecutive
// draws within one glBeginTransformFeedback append GL-style. Transform feedback
// objects can each hold an open, paused span at the same time, so the counters are
// per object: one group of four slots each, handed out on first use.
static constexpr SizeT kXfbCounterObjectSlots = 16;
VkBufferObject m_xfbCounterBuffer;
UnorderedMap<Uint, Uint32> m_xfbCounterSlotByObject;
Uint32 m_xfbNextCounterSlot = 0;
// Set for a slot once a captured draw has been recorded into its span; selects
// counter-buffer resume on the next captured draw of the same span.
Array<Bool, kXfbCounterObjectSlots> m_xfbCountersValid{};
Array<Uint64, kXfbCounterObjectSlots> m_xfbLastSeenGeneration{};
// Counter slot group of the bound transform feedback object.
Uint32 CurrentXfbCounterSlot();
// Wraps a recorded draw with BeginTransformFeedbackEXT/EndTransformFeedbackEXT
// when GL transform feedback is active; binds capture buffers on demand.
Bool BeginXfbCaptureForDraw(FrameContext::FrameData& frame);
void EndXfbCaptureForDraw(FrameContext::FrameData& frame, Bool began);
// Makes the captured bytes visible to whatever reads them next. Deferred rather than
// recorded next to the capture, because the capturing draw runs inside a render pass
// that declares no self-dependency.
void MakeXfbWritesVisible();
Bool m_xfbWritesPendingVisibility = false;
// Wrap one app draw in an occlusion-query slot while a GL_SAMPLES_PASSED
// query is active. Returns whether a slot was begun (End must mirror it).
Bool BeginOcclusionForDraw(VkCommandBuffer commandBuffer);
void EndOcclusionForDraw(VkCommandBuffer commandBuffer, Bool began);
Bool m_occlusionQueryPreciseEnabled = false;
Bool m_hostQueryResetEnabled = false;
PFN_vkResetQueryPool s_vkResetQueryPool = nullptr;
VkQueryPool m_occlusionQueryPool = VK_NULL_HANDLE;
static constexpr Uint32 kOcclusionQuerySlots = 8192;
Uint32 m_occlusionSlotCursor = 0;
Bool m_occlusionCaptureActive = false;
Vector<Uint32> m_occlusionActiveSlots;
// Transform feedback primitive queries: one pool slot per captured draw yields
// the (written, needed) pair; GL_TRANSFORM_FEEDBACK_PRIMITIVES_WRITTEN sums the
// first, GL_PRIMITIVES_GENERATED the second - exact with geometry shaders,
// unlike the CPU fallback accounting.
Bool m_xfbQueriesSupported = false;
PFN_vkCmdBeginQueryIndexedEXT s_vkCmdBeginQueryIndexedEXT = nullptr;
PFN_vkCmdEndQueryIndexedEXT s_vkCmdEndQueryIndexedEXT = nullptr;
VkQueryPool m_xfbQueryPool = VK_NULL_HANDLE;
static constexpr Uint32 kXfbQuerySlots = 8192;
Uint32 m_xfbQuerySlotCursor = 0;
Bool m_xfbQueryCaptureActive[2] = {false, false}; // [0]=written, [1]=generated
Vector<Uint32> m_xfbQueryActiveSlots[2];
Bool m_xfbQuerySlotOpen = false;
Uint32 m_xfbQueryOpenSlot = 0;
public:
// kind: 0 = PRIMITIVES_WRITTEN, 1 = PRIMITIVES_GENERATED.
Bool StartXfbQueryCapture(Uint32 kind);
void StopXfbQueryCapture(Uint32 kind, Vector<Uint32>& outSlots);
Bool ResolveXfbQueryResult(const Vector<Uint32>& slots, Bool wantGenerated, Uint64& outPrimitives);
private:
void BeginXfbQueryForDraw(VkCommandBuffer commandBuffer);
void EndXfbQueryForDraw(VkCommandBuffer commandBuffer);
VkCommandPool m_commandPool = VK_NULL_HANDLE;
VkBufferManager m_bufferManager;
@@ -613,57 +416,14 @@ namespace MobileGL::MG_Backend::DirectVulkan {
// gather + synthetic vertex-input rebuild + payload hash + lookup) when the full pipeline
// state is unchanged from the previous draw. The key provably covers every pipeline field.
// Reset per-frame and on pipeline destruction so the cached handle can never dangle.
// Small N-way pipeline-resolution memo (round-robin replacement). A
// single-entry memo thrashed on draw sequences that alternate a few
// pipelines (GUI text/quad program ping-pong), paying the full
// payload-hash lookup per draw; eight entries cover such working sets
// while keeping the hit path a trivial linear scan.
struct PipelineMemoEntry {
GLenum mode = 0;
Uint64 programHash = 0;
Uint64 vertexInputHash = 0;
Uint64 renderPassHash = 0;
// VALUE hash of the pipeline-relevant fixed-function state (see
// ComputePipelineStateHash), not the monotonic pipeline-state version:
// the version never repeats, so a per-draw GL_BLEND toggle would miss
// all entries forever even though the state alternates between two
// values the memo already holds.
Uint64 pipelineStateHash = 0;
ProgramFactory::CompileOptionFlags transformFlags = {};
VkPipeline pipeline = VK_NULL_HANDLE;
};
static constexpr Uint32 kPipelineMemoSize = 8;
PipelineMemoEntry m_pipelineMemo[kPipelineMemoSize];
Uint32 m_pipelineMemoCount = 0;
Uint32 m_pipelineMemoNext = 0;
// Hash of every fixed-function GL state the pipeline payload reads that the
// memo key's other fields (mode / program / vertex input / render pass /
// transform flags) do not already pin down. Equal hash under an equal rest
// of key => byte-identical PipelineCreatePayload. Cached per pipeline-state
// version: the version is monotonic and bumps on every pipeline-state
// change, so an unchanged (version, colorAttachmentCount) proves the state
// bytes are unchanged and the hash can be reused without re-reading them.
Uint64 ComputePipelineStateHash(Uint32 colorAttachmentCount) const;
Uint m_pipelineStateHashVersion = 0;
Uint32 m_pipelineStateHashColorCount = 0;
Uint64 m_pipelineStateHash = 0;
Bool m_pipelineStateHashValid = false;
// GetShaderTransformFlags(preTransform) memo: a pure function of the swapchain
// pre-transform, re-evaluated only when that value changes (surface rotation).
// No other invalidation input exists.
VkSurfaceTransformFlagBitsKHR m_baseTransformFlagsPreTransform =
VK_SURFACE_TRANSFORM_FLAG_BITS_MAX_ENUM_KHR;
Uint32 m_baseTransformFlagsCache = 0;
Uint32 GetBaseTransformFlagsRaw();
// Drops every memoized pipeline handle. Required at command-buffer
// boundaries and whenever any pipeline may have been destroyed. Also drops
// the cached pipeline-state hash: the same boundaries can retire the GL
// context whose monotonic version the cache is keyed on.
void InvalidatePipelineMemo() {
m_pipelineMemoCount = 0;
m_pipelineMemoNext = 0;
m_pipelineStateHashValid = false;
}
Bool m_lastPipelineValid = false;
GLenum m_lastPipelineMode = 0;
Uint64 m_lastPipelineProgramHash = 0;
Uint64 m_lastPipelineVertexInputHash = 0;
Uint64 m_lastPipelineRenderPassHash = 0;
Uint m_lastPipelineRenderStateVersion = 0;
ProgramFactory::CompileOptionFlags m_lastPipelineTransformFlags = {};
VkPipeline m_lastPipelineResult = VK_NULL_HANDLE;
UnorderedMap<ProgramFactory::HashType, VkPipeline> m_computePipelines;
UniquePtr<ProgramFactory> m_programFactory;
UniquePtr<UniformManager> m_uniformManager;
@@ -692,103 +452,9 @@ namespace MobileGL::MG_Backend::DirectVulkan {
ProgramFactory::CompileOptionFlags m_lastSampledSetTransformFlags = {};
Uint64 m_lastSampledSetBindGeneration = 0;
// Memo for the per-draw explicit-LOD-0 eligibility probe
// (ProgramSamplesOnlySingleLevelTextures): same key family as the
// sampled-set memo, plus the sampled textures' params-version sum so a
// level-range or filter change re-probes. On a hit the resolved
// transform flags are reused, which also collapses the two
// GetOrCreateProgram lookups into one.
Bool m_lastLodDecisionValid = false;
Uint64 m_lastLodProgramLifetimeId = 0;
Uint32 m_lastLodProgramVersion = 0;
Uint64 m_lastLodBindGeneration = 0;
Uint64 m_lastLodParamsSum = 0;
ProgramFactory::CompileOptionFlags m_lastLodBaseFlags = {};
ProgramFactory::CompileOptionFlags m_lastLodResultFlags = {};
// Snapshot behind TrySetupDrawFastPath. Values only: the program and
// render-pass caches are open-addressing maps whose entries move on
// insert, so no pointers into them are cached; the pipeline handle is
// protected by the command-buffer-boundary reset plus the mid-frame
// pipeline-destruction resets, and monotonic epochs guard everything
// that can be destroyed or recreated between draws.
struct SetupDrawSnapshot {
Bool valid = false;
Uint8 aspects = 0;
GLenum mode = 0;
Uint64 programLifetimeId = 0;
Uint32 programVersion = 0;
const void* vao = nullptr;
Uint32 vaoConfigVersion = 0;
const void* drawFbo = nullptr;
Uint16 fboVersion = 0;
Bool drawFboIsDefault = false;
Uint renderStateVersion = 0;
Uint64 bindGeneration = 0;
Uint32 baseTransformFlags = 0;
Uint32 resolvedTransformFlags = 0;
Uint64 renderPassHash = 0;
Uint32 imageIndex = 0;
Uint64 textureEraseEpoch = 0;
Uint64 textureImageEpoch = 0;
Uint64 renderbufferImageEpoch = 0;
Uint64 sampledContentSum = 0;
Uint64 sampledParamsSum = 0;
// Guards the sampler-descriptor reuse hint: bumped by any sampler-object
// parameter or texture shape change (see GetSamplingResolutionGeneration),
// none of which the sums above cover.
Uint64 samplingResolutionGeneration = 0;
// Render-pass flavor input (DepthTest || StencilTest at snapshot time).
// A pipeline-state change that leaves this equal cannot change which
// render pass GetOrCreateRenderPass would pick, so the fast path may
// re-resolve just the pipeline against the active pass; a change that
// flips it must fall back to the full path's pass selection.
Bool drawUsesDepthStencil = false;
IntVec2 renderPassExtent = {0, 0};
// colorAttachmentCount of the snapshotting draw's render pass: the
// pipeline-state hash input, so the fast path can refresh that hash and
// probe the pipeline memo after a state change without re-fetching the
// render-pass entry (the pass itself is pinned by renderPassHash above).
Uint32 renderPassColorCount = 0;
VkPipeline pipeline = VK_NULL_HANDLE;
// layoutHash of the snapshotting draw's vertex-input state. The pipeline and
// the vertex-input pre-flight depend on the VAO only through this (plus the
// program, pinned separately), so a changed VAO whose aux memo carries the
// same layoutHash re-uses the snapshot's pipeline and pre-flight verdict
// outright - the VAO-cycling case Minecraft chunk rendering hits every draw.
Uint64 vaoLayoutHash = 0;
// Memoised ProgramFactory entry of the snapshotting draw, valid while
// (programLifetimeId, programVersion, resolvedTransformFlags) match - all
// checked above - AND the factory's cache structure epoch is unchanged (the
// cache is open-addressing and holds entries by value, so any insert/erase
// moves them). The fast path must re-stamp use through StampProgramUse when
// it bypasses GetOrCreateProgram, or the idle sweep could evict a live entry.
const ProgramFactory::VkProgramObject* programObj = nullptr;
Uint64 programFactoryEpoch = 0;
};
SetupDrawSnapshot m_setupDrawSnapshot;
// Per-draw scratch buffers (clear keeps capacity) — these paths run for every
// draw call and must not allocate.
Vector<MG_State::GLState::ITextureObject*> m_sampledTexturesScratch;
// Per-binding (texture, effective sampler) lifetime-id records from the same
// CollectSampledTextures walk that filled m_sampledTexturesScratch. The fast
// path shadow-compares against them (SampledBindingsUnchanged) when the
// texture bind generation moved, so a redundant glBindSampler/glBindTexture
// storm that resolves to the same bindings keeps the fast path.
Vector<UniformManager::SampledBindingRecord> m_sampledBindingRecordsScratch;
// Parallel to m_sampledTexturesScratch, refilled by every SetupDraw's
// first sampled-texture loop: the resolved backend resources, so the
// post-transition loop can skip re-resolving textures whose layout is
// already sampleable.
Vector<VkTextureManager::TextureResource*> m_sampledResourcesScratch;
// Layout VALUE of each sampled resource when the snapshot (and so the cached
// sampler descriptors) was built, parallel to m_sampledResourcesScratch. The
// fast path's validity check only proves the layout is still sampleable; the
// descriptor-reuse hint additionally needs it to be the SAME sampleable
// layout (a mid-frame compute dispatch can move a sampled texture from
// READ_ONLY_OPTIMAL to GENERAL, both valid, different descriptor).
Vector<VkImageLayout> m_sampledLayoutSnapshots;
Vector<MG_State::GLState::ITextureObject*> m_storageImageTexturesScratch;
Vector<VkBuffer> m_vertexBuffersScratch;
Vector<VkDeviceSize> m_vertexOffsetsScratch;
@@ -848,132 +514,9 @@ namespace MobileGL::MG_Backend::DirectVulkan {
UnorderedMap<ConvertedVertexStreamKey, ConvertedVertexStream, ConvertedVertexStreamKeyHash>
m_convertedVertexStreams;
// One VAO's resolved vkCmdBindVertexBuffers arguments, reusable by a later draw
// that would resolve them to the same thing. Consecutive draws in a chunk-renderer
// frame keep the program and the vertex layout and only swap the VAO, so a
// per-VAO memo turns the second and later draws through each VAO into a validate
// plus (usually skipped) rebind.
//
// Only whole-buffer bindings are memoised. Client-memory and format-converted
// streams re-upload from a range that depends on the draw's own vertex/index
// range, and synthetic bindings carry glVertexAttrib* values that are not part
// of any key here; a layout using any of them is never stored.
// Field order is hit-path cache locality, hot to cold: the per-draw validate
// reads the scalars and the EBO memo head, then only the first bindingCount
// elements of vkBuffers/vkOffsets; the per-binding revalidation arrays at the
// tail are touched once per frame at most.
struct ResolvedVertexBindings {
// Must equal DynamicStateShadow::kMaxShadowedVertexBindings (static_assert in
// the .cpp): past that width the bind shadow cannot skip a redundant bind
// either, so a wider layout resolves per draw. Minecraft-shaped layouts use four.
static constexpr Uint32 kMaxBindings = 8;
// Frame serial of the last completed resolve OR cross-frame revalidation.
// Zero until a resolve completes, and reset to zero before one starts, so a
// resolve that bails out midway cannot leave a half-filled entry matchable.
// Unlike the original frame-scoped memo, an entry whose buffers are all
// resident and unmapped is revalidated across frames (per-binding slice
// epoch compares) instead of re-resolved - see TryBindResolvedVertexBindings.
Uint64 frameSerial = 0;
// Identity of the resolved Vulkan layout: the VAO's content hash
// (VertexInputStateFactory::GetOrComputeHash - the same value the factory
// keys its entries on) fixes bindings.size(), each binding's base offset,
// which bindings are client/converted, and (through the mixed-in buffer
// addresses) which buffer each binding reads. Compared against the VAO's
// own hash memo on the hit path, so a hit never touches the factory entry.
VertexInputStateFactory::HashType vertexInputHash = 0;
// The program's vertex input layout: decides the synthetic-binding set and
// hence the total binding count.
Uint32 activeAttribMask = 0;
Uint32 bindingCount = 0;
// VkBufferManager::GetSliceEpochCounter() at resolve time. Still equal means
// no buffer anywhere changed its slice or was persistently mapped since, which
// settles every per-binding question below in one compare.
Uint64 sliceEpochCounter = 0;
// Any bound buffer already carrying a host map when the slice was resolved.
// Such a buffer can mutate its shadow with no API call, so it has to be
// re-pushed per draw and the one-compare path above cannot apply.
Bool anyBufferMapped = true;
// Resident element-buffer slice memo (skips the per-draw AcquireResidentSlice
// for the VAO's EBO, which cold-chases 500+ distinct resources in a
// chunk-cycling frame). Self-validating exactly like the bindings above: a hit
// requires the LIVE bound EBO pointer to equal indexBuffer AND either an
// unmoved manager-wide slice-epoch counter (nothing anywhere changed slices
// or gained a host map, the same one-compare rescue the vertex half uses) or
// that buffer's resource still carrying indexSliceEpoch (epochs are minted
// from a process-lifetime counter, so a recycled address can never
// revalidate). Restart-substituted and streamed EBOs are never stored.
// indexFrameSerial tracks the last frame the resource's GPU-use serial was
// stamped through this memo; 0 means no index memo. Independent of the
// vertex half: both are (pointer, epoch)-validated, so neither can serve
// stale state for the other.
const MG_State::GLState::BufferObject* indexBuffer = nullptr;
Uint64 indexSliceEpoch = 0;
// GetSliceEpochCounter() when the resource's epoch was last verified; only
// meaningful while indexFrameSerial matches the current frame serial.
Uint64 indexSliceEpochCounter = 0;
VkBuffer indexVkBuffer = VK_NULL_HANDLE;
VkDeviceSize indexSliceOffset = 0;
Uint64 indexFrameSerial = 0;
// Bound per draw (first bindingCount elements).
VkBuffer vkBuffers[kMaxBindings] = {};
VkDeviceSize vkOffsets[kMaxBindings] = {};
// Per binding: the VAO attribute location its buffer comes from, that buffer,
// and the buffer's VkBufferManager slice epoch when the slice was resolved.
// Only read by the per-frame revalidation and the something-moved fallback.
Uint8 attributeLocations[kMaxBindings] = {};
const MG_State::GLState::BufferObject* buffers[kMaxBindings] = {};
Uint64 sliceEpochs[kMaxBindings] = {};
};
// One direct-mapped slot of the per-VAO draw-memo table below. The key is a
// lookup hint only - a slot is never dereferenced through vaoKey; every fact it
// carries is validated against live state before use:
// - layoutHash/layoutAuxMasks are valid only while contentHash equals the LIVE
// VAO's own hash memo (which the VAO's config version guards), so a config
// change, a buffer rebind, or a recycled VAO address with a different
// configuration all miss. A recycled address with a byte-identical
// configuration AND identical bound buffers reproduces the content hash, and
// then the facts are correct by construction (they are a pure function of it).
// - bindings revalidates per draw exactly as before (frame serial, content
// hash, per-binding live buffer pointers and slice epochs).
struct alignas(64) VaoDrawMemo {
const MG_State::GLState::VertexArrayObject* vaoKey = nullptr;
// The VAO content hash (VertexInputStateFactory::GetOrComputeHash) the two
// layout facts below were derived from; 0 while nothing valid is stored.
Uint64 contentHash = 0;
Bool layoutFactsValid = false;
// The resolved layout identity + packed (unsupported, location) masks -
// the exact values GetBackendAuxMemo used to serve, moved here so the
// per-draw probe stays inside this table's one hot line instead of
// touching a second cold line of every cycled VAO object.
Uint64 layoutHash = 0;
Uint64 layoutAuxMasks = 0;
ResolvedVertexBindings bindings;
};
// Fixed-size, allocated on first use, never rehashed or swept: entries are
// recycled in place on slot collisions (two-slot probe, older frame serial
// evicted), and stale entries self-invalidate through the compares above. A
// fixed table also makes every VaoDrawMemo/ResolvedVertexBindings pointer
// stable for the duration of a draw, which the EBO memo handoff
// (m_currentDrawResolvedEntry) relies on.
static constexpr Uint32 kVaoDrawMemoSlotCount = 2048; // power of two
Vector<VaoDrawMemo> m_vaoDrawMemoTable;
// Finds the slot holding `vao`, or recycles the older of its two candidate
// slots into an empty memo keyed on `vao`. Never returns null.
VaoDrawMemo* LookupVaoDrawMemo(const MG_State::GLState::VertexArrayObject* vao);
// The current draw's memo entry, set by UploadAndBindVertexBuffers and consumed
// by the same draw's UploadAndBindIndexBuffer (the EBO memo lives in the same
// entry). Valid ONLY within that window: the next draw's lookup can recycle the
// slot. Null when the draw's layout is not memoisable.
ResolvedVertexBindings* m_currentDrawResolvedEntry = nullptr;
void CreateInstance();
VkResult SetupDebugMessenger();
VkResult DestroyDebugMessenger();
VkResult SetupDebugReportCallback();
void DestroyDebugReportCallback();
VkDebugUtilsMessengerCreateInfoEXT PopulateDebugMessengerCreateInfo();
void CreateSurface();
void PickPhysicalDevice();
@@ -992,32 +535,15 @@ namespace MobileGL::MG_Backend::DirectVulkan {
const RenderPassEntry& renderPassEntry);
VkPipeline GetOrCreateComputePipeline(const ProgramFactory::VkProgramObject& programObj);
void DestroyComputePipelines();
// Takes the frame rather than a command buffer: a first-time storage-usage upgrade has to
// flush the pending recording (see the body), which retires the current command buffer.
Bool PrepareStorageImageTextures(
FrameContext::FrameData& frame,
VkCommandBuffer commandBuffer,
const MG_State::GLState::ProgramObject& program,
const ProgramFactory::VkProgramObject& programObj);
// The per-draw dynamic-state tail (viewport, scissor, blend constants, depth
// bias, line width, stencil), gated behind one render-state-parameters-version
// compare per command buffer - see the gate fields in DynamicStateShadow.
void ApplyDynamicDrawStateTail(FrameContext::FrameData& frame, const IntVec2& extent, Bool isDefaultFbo);
Bool UploadAndBindVertexBuffers(VkCommandBuffer commandBuffer, const MG_State::GLState::VertexArrayObject& vao,
const ProgramFactory::VkProgramObject& programObj,
const DrawCmdParam& drawParams,
const IndexBufferView* pIndexBufferView);
// Binds `entry`'s memoised buffers when every input it was resolved from is
// still live and unchanged, else returns false and leaves nothing bound.
// vaoContentHash is the VAO's memoised content hash (GetBackendHashMemo), which
// pins the layout AND the bound buffers without resolving the factory entry.
// Non-const entry: a cross-frame revalidation refreshes its serial/epoch stamps.
Bool TryBindResolvedVertexBindings(VkCommandBuffer commandBuffer,
const MG_State::GLState::VertexArrayObject& vao,
ResolvedVertexBindings& entry,
Uint64 vaoContentHash,
Uint32 activeAttribMask, Uint64 frameSerial);
Bool UploadAndBindIndexBuffer(FrameContext::FrameData& frame,
const MG_State::GLState::VertexArrayObject& vao,
const IndexBufferView* pIndexBufferView = nullptr);
@@ -1033,11 +559,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
GLint srcX0, GLint srcY0, GLint srcX1, GLint srcY1,
GLint dstX0, GLint dstY0, GLint dstX1, GLint dstY1,
GLenum filter);
// Clears one z slice of a VK_IMAGE_TYPE_3D colour image. See the call site in
// MaterializePendingClearForTexture for why a transfer clear cannot do this.
Bool ClearDepthSliceWithRenderPass(VkCommandBuffer commandBuffer,
MG_State::GLState::ITextureObject& texture, Uint32 mipLevel,
Uint32 depthSlice, const VkClearValue& clearValue);
Bool MaterializePendingClearForTexture(VkCommandBuffer commandBuffer,
MG_State::GLState::ITextureObject& texture);
Bool MaterializePendingClearForRenderbuffer(
@@ -1054,14 +575,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
VkImageLayout finalLayout);
Bool SubmitReadbackCommandsAndWait(FrameContext::FrameData& frame);
public:
// Submits whatever is recorded and waits for it. The CPU is about to read memory
// a shader wrote (a mapped shader storage buffer), and coherent host-visible
// storage only guarantees visibility once the work that produced it has retired.
Bool FinishPendingGpuWork();
private:
void ShutdownSwapchain();
// Static functions
@@ -1085,10 +598,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
const PhysicalDevice& compareWithDevice,
PhysicalDevice& outBetterDevice);
static constexpr const char* s_validationLayerNames[] = {"VK_LAYER_KHRONOS_validation"};
// VK_KHR_image_format_list: lets MUTABLE_FORMAT images declare their exact view-format
// set so the driver can keep bandwidth compression (see CreateLogicalDeviceAndQueues).
Bool m_imageFormatListExtensionEnabled = false;
static constexpr const char* s_deviceExtensionNames[] = {VK_KHR_SWAPCHAIN_EXTENSION_NAME};
static Bool CheckValidationLayerSupport();
+3 -32
View File
@@ -52,48 +52,19 @@ namespace MobileGL::MG_Backend::DirectVulkan {
}
} // namespace MobileGL::MG_Backend::DirectVulkan
namespace MobileGL::MG_Backend::DirectVulkan {
// GL renders into sRGB color attachments RAW while GL_FRAMEBUFFER_SRGB is disabled
// (the core-profile default); Vulkan sRGB attachments always encode on write. The
// attachment view (and render pass format) therefore drops to the UNORM twin
// whenever the capability is off. Sampled views keep the sRGB format (decode on
// sample is unconditional in GL).
inline VkFormat ResolveSrgbAttachmentWriteFormat(VkFormat format, bool framebufferSrgbEnabled) {
if (framebufferSrgbEnabled) return format;
switch (format) {
case VK_FORMAT_R8G8B8A8_SRGB:
return VK_FORMAT_R8G8B8A8_UNORM;
case VK_FORMAT_B8G8R8A8_SRGB:
return VK_FORMAT_B8G8R8A8_UNORM;
default:
return format;
}
}
} // namespace MobileGL::MG_Backend::DirectVulkan
// The context line (__VA_ARGS__ = its own format string + args) must be a SEPARATE log
// call: appending its format to the base format while its arguments precede the base
// arguments makes every conversion read the wrong slot (a %s pulling an int crashes).
#define VK_VERIFY(expr, ...) \
do { \
VkResult _vk_verify_result = (expr); \
if (_vk_verify_result != VK_SUCCESS) { \
__VA_OPT__(MGLOG_F(__VA_ARGS__);) \
MGLOG_F("Vulkan error %s (%d) at %s:%d", \
MGLOG_F("Vulkan error %s (%d) at %s:%d" __VA_OPT__(" - ") __VA_ARGS__, \
MobileGL::MG_Backend::DirectVulkan::VkResultToString(_vk_verify_result), \
_vk_verify_result, __FILE__, __LINE__); \
} \
MOBILEGL_ASSERT(_vk_verify_result == VK_SUCCESS, "Vulkan error %s (%d) at %s:%d", \
MobileGL::MG_Backend::DirectVulkan::VkResultToString(_vk_verify_result), \
_vk_verify_result, __FILE__, __LINE__); \
MOBILEGL_ASSERT(_vk_verify_result == VK_SUCCESS, "Vulkan error %s (%d) at %s:%d" __VA_OPT__(" - ") __VA_ARGS__, MobileGL::MG_Backend::DirectVulkan::VkResultToString(_vk_verify_result), _vk_verify_result, __FILE__, __LINE__); \
} while (0)
#define XXHASH_VERIFY(expr, ...) \
do { \
XXH_errorcode _xxh_verify_result = (expr); \
if (_xxh_verify_result != XXH_OK) { \
__VA_OPT__(MGLOG_F(__VA_ARGS__);) \
} \
MOBILEGL_ASSERT(_xxh_verify_result == XXH_OK, "XXHash error %d at %s:%d", _xxh_verify_result, __FILE__, \
__LINE__); \
MOBILEGL_ASSERT(_xxh_verify_result == XXH_OK, "XXHash error %d at %s:%d" __VA_OPT__(" - ") __VA_ARGS__, _xxh_verify_result, __FILE__, __LINE__); \
} while (0)
+1 -2
View File
@@ -41,5 +41,4 @@ add_test(NAME SanityBench COMMAND SanityBench --benchmark_counters_tabular=true)
set_tests_properties(SanityBench PROPERTIES LABELS benchmark)
add_subdirectory(Program)
add_subdirectory(Buffer)
add_subdirectory(Driver)
add_subdirectory(Buffer)
@@ -1,15 +0,0 @@
cmake_minimum_required(VERSION 3.24)
# A real, headless EGL client, deliberately NOT linked against MobileGL: it
# dlopens one EGL provider at runtime ($DRIVERBENCH_EGL_LIB - the system
# libEGL.so.1 for the native driver, or a libMobileGL.so path for either
# MobileGL backend), so the same binary measures all three stacks.
if (NOT UNIX OR APPLE OR ANDROID)
return()
endif()
add_executable(DriverBench DriverBench.c)
target_link_libraries(DriverBench PRIVATE dl)
add_test(NAME DriverBench COMMAND DriverBench draw_tiny)
set_tests_properties(DriverBench PROPERTIES LABELS benchmark)
-501
View File
@@ -1,501 +0,0 @@
/* MobileGL - MobileGL/MG_Benchmark/Driver/DriverBench.c
* Copyright (c) 2025-2026 MobileGL-Dev
* Licensed under the GNU Lesser General Public License v3.0:
* https://www.gnu.org/licenses/gpl-3.0.txt
* https://www.gnu.org/licenses/lgpl-3.0.txt
* SPDX-License-Identifier: LGPL-3.0-only
* End of Source File Header
*
* Headless, EGL-based driver benchmark shaped like Minecraft's GL usage.
* Unlike the MobileGL_s microbenches next door this exercises a full GL
* stack: it dlopens ONE EGL provider ($DRIVERBENCH_EGL_LIB - the system
* libEGL.so.1 for the native driver, or a libMobileGL.so path for either
* MobileGL backend selected with MOBILEGL_BACKEND_TYPE), creates a desktop-GL
* context on a small pbuffer, renders into its own FBO and paces frames with
* glFinish. No window system is required: the default display is tried first
* so a desktop run reaches the real driver, and a headless box (CI, a build
* server) falls back to EGL_MESA_platform_surfaceless - see
* run_driver_bench.sh.
*
* Every case models one hot pattern from captured Minecraft traces:
* draw_tiny back-to-back glDrawElements, shared state (chunk batch)
* draw_uniform per-draw vec3 offset uniform + draw (chunk sections)
* draw_multi_vao per-draw VAO/VBO switch + draw (per-section buffers)
* tex_pingpong per-draw texture bind churn on one unit
* program_pingpong alternate two programs + mat4 upload (chunk<->entity)
* chunk_upload glBufferData(NULL) orphan + glBufferSubData + draw
* atlas_sprite N 16x16 glTexSubImage2D into a 1024x512 atlas + draw
* lightmap full 16x16 lightmap respecify per frame + draw
* scene_mix composite frame built from the knobs below
*
* Output: one CSV line per case:
* case,frames,ops_per_frame,median_frame_ms,ns_per_op,fps
*/
#include <dlfcn.h>
#include <stdint.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <time.h>
/* ---- EGL constants ---- */
typedef void* EGLDisplay;
typedef void* EGLConfig;
typedef void* EGLContext;
typedef void* EGLSurface;
typedef int EGLint;
typedef unsigned int EGLBoolean;
typedef unsigned int EGLenum;
#define EGL_DEFAULT_DISPLAY ((void*)0)
#define EGL_NO_CONTEXT ((EGLContext)0)
#define EGL_NO_SURFACE ((EGLSurface)0)
#define EGL_FALSE 0
#define EGL_SURFACE_TYPE 0x3033
#define EGL_PBUFFER_BIT 0x0001
#define EGL_RENDERABLE_TYPE 0x3040
#define EGL_OPENGL_BIT 0x0008
#define EGL_RED_SIZE 0x3024
#define EGL_GREEN_SIZE 0x3023
#define EGL_BLUE_SIZE 0x3022
#define EGL_DEPTH_SIZE 0x3025
#define EGL_WIDTH 0x3057
#define EGL_HEIGHT 0x3056
#define EGL_NONE 0x3038
#define EGL_OPENGL_API 0x30A2
#define EGL_OPENGL_ES_API 0x30A0
#define EGL_OPENGL_ES3_BIT 0x0040
#define EGL_CONTEXT_CLIENT_VERSION 0x3098
#define EGL_CONTEXT_MAJOR_VERSION 0x3098
#define EGL_CONTEXT_MINOR_VERSION 0x30FB
#define EGL_CONTEXT_OPENGL_PROFILE_MASK 0x30FD
#define EGL_CONTEXT_OPENGL_CORE_PROFILE_BIT 0x00000001
#define EGL_PLATFORM_SURFACELESS_MESA 0x31DD
/* ---- GL constants ---- */
#define GL_COLOR_BUFFER_BIT 0x00004000
#define GL_DEPTH_BUFFER_BIT 0x00000100
#define GL_TRIANGLES 0x0004
#define GL_UNSIGNED_INT 0x1405
#define GL_SHORT 0x1402
#define GL_FLOAT 0x1406
#define GL_UNSIGNED_BYTE 0x1401
#define GL_ARRAY_BUFFER 0x8892
#define GL_ELEMENT_ARRAY_BUFFER 0x8893
#define GL_STATIC_DRAW 0x88E4
#define GL_TEXTURE_2D 0x0DE1
#define GL_TEXTURE0 0x84C0
#define GL_RGBA 0x1908
#define GL_RGBA8 0x8058
#define GL_DEPTH_COMPONENT24 0x81A6
#define GL_TEXTURE_MIN_FILTER 0x2801
#define GL_TEXTURE_MAG_FILTER 0x2800
#define GL_NEAREST 0x2600
#define GL_NEAREST_MIPMAP_LINEAR 0x2702
#define GL_DEPTH_TEST 0x0B71
#define GL_BLEND 0x0BE2
#define GL_SRC_ALPHA 0x0302
#define GL_ONE_MINUS_SRC_ALPHA 0x0303
#define GL_ONE 1
#define GL_ZERO 0
#define GL_VERTEX_SHADER 0x8B31
#define GL_FRAGMENT_SHADER 0x8B30
#define GL_COMPILE_STATUS 0x8B81
#define GL_LINK_STATUS 0x8B82
#define GL_VERSION 0x1F02
#define GL_RENDERER 0x1F01
#define GL_NO_ERROR 0
#define GL_FRAMEBUFFER 0x8D40
#define GL_RENDERBUFFER 0x8D41
#define GL_COLOR_ATTACHMENT0 0x8CE0
#define GL_DEPTH_ATTACHMENT 0x8D00
#define GL_FRAMEBUFFER_COMPLETE 0x8CD5
#define GL_SYNC_GPU_COMMANDS_COMPLETE 0x9117
#define GL_SYNC_FLUSH_COMMANDS_BIT 0x00000001
#define GL_UNIFORM_BUFFER 0x8A11
#define GL_UNIFORM_BUFFER_OFFSET_ALIGNMENT 0x8A34
#define GL_DYNAMIC_DRAW 0x88E8
#define GL_STREAM_DRAW 0x88E0
#define GL_UNPACK_ALIGNMENT 0x0CF5
#define GL_UNPACK_ROW_LENGTH 0x0CF2
#define GL_UNPACK_SKIP_ROWS 0x0CF3
#define GL_UNPACK_SKIP_PIXELS 0x0CF4
#define GL_TEXTURE_WRAP_S 0x2802
#define GL_TEXTURE_WRAP_T 0x2803
#define GL_CLAMP_TO_EDGE 0x812F
#define GL_REPEAT 0x2901
typedef unsigned int GLuint;
typedef int GLint;
typedef int GLsizei;
typedef unsigned int GLenum;
typedef char GLchar;
typedef unsigned char GLboolean;
typedef long GLsizeiptr;
typedef long GLintptr;
/* ---- resolved entry points ---- */
static void* (*g_eglGetProcAddress)(const char*);
static void* g_provider;
#define GLF(ret, name, args) static ret(*name) args;
GLF(void, glClear, (unsigned))
GLF(void, glClearColor, (float, float, float, float))
GLF(void, glEnable, (GLenum))
GLF(void, glDisable, (GLenum))
GLF(void, glBlendFuncSeparate, (GLenum, GLenum, GLenum, GLenum))
GLF(void, glDrawBuffers, (GLsizei, const GLenum*))
GLF(void, glViewport, (GLint, GLint, GLsizei, GLsizei))
GLF(const unsigned char*, glGetString, (GLenum))
GLF(GLenum, glGetError, (void))
GLF(void, glFinish, (void))
GLF(void, glFlush, (void))
GLF(void, glGenBuffers, (GLsizei, GLuint*))
GLF(void, glBindBuffer, (GLenum, GLuint))
GLF(void, glBufferData, (GLenum, GLsizeiptr, const void*, GLenum))
GLF(void, glBufferSubData, (GLenum, GLintptr, GLsizeiptr, const void*))
GLF(void, glGenVertexArrays, (GLsizei, GLuint*))
GLF(void, glBindVertexArray, (GLuint))
GLF(void, glEnableVertexAttribArray, (GLuint))
GLF(void, glVertexAttribPointer, (GLuint, GLint, GLenum, GLboolean, GLsizei, const void*))
GLF(void, glGenTextures, (GLsizei, GLuint*))
GLF(void, glBindTexture, (GLenum, GLuint))
GLF(void, glActiveTexture, (GLenum))
GLF(void, glTexImage2D, (GLenum, GLint, GLint, GLsizei, GLsizei, GLint, GLenum, GLenum, const void*))
GLF(void, glTexSubImage2D, (GLenum, GLint, GLint, GLint, GLsizei, GLsizei, GLenum, GLenum, const void*))
GLF(void, glTexParameteri, (GLenum, GLenum, GLint))
GLF(void, glPixelStorei, (GLenum, GLint))
GLF(void, glGetIntegerv, (GLenum, GLint*))
GLF(void, glGenerateMipmap, (GLenum))
GLF(GLuint, glCreateShader, (GLenum))
GLF(void, glShaderSource, (GLuint, GLsizei, const GLchar* const*, const GLint*))
GLF(void, glCompileShader, (GLuint))
GLF(void, glGetShaderiv, (GLuint, GLenum, GLint*))
GLF(void, glGetShaderInfoLog, (GLuint, GLsizei, GLsizei*, GLchar*))
GLF(GLuint, glCreateProgram, (void))
GLF(void, glAttachShader, (GLuint, GLuint))
GLF(void, glLinkProgram, (GLuint))
GLF(void, glGetProgramiv, (GLuint, GLenum, GLint*))
GLF(void, glUseProgram, (GLuint))
GLF(GLint, glGetUniformLocation, (GLuint, const GLchar*))
GLF(void, glUniform1i, (GLint, GLint))
GLF(void, glUniform3f, (GLint, float, float, float))
GLF(void, glUniformMatrix4fv, (GLint, GLsizei, GLboolean, const float*))
GLF(void, glDrawElements, (GLenum, GLsizei, GLenum, const void*))
GLF(void, glBindAttribLocation, (GLuint, GLuint, const GLchar*))
GLF(void, glUniform3fv, (GLint, GLsizei, const float*))
GLF(void, glDrawArrays, (GLenum, GLint, GLsizei))
GLF(void, glDrawElementsBaseVertex, (GLenum, GLsizei, GLenum, const void*, GLint))
GLF(void, glMultiDrawElementsBaseVertex,
(GLenum, const GLsizei*, GLenum, const void* const*, GLsizei, const GLint*))
GLF(void, glBindBufferRange, (GLenum, GLuint, GLuint, GLintptr, GLsizeiptr))
GLF(void, glBindBufferBase, (GLenum, GLuint, GLuint))
GLF(GLuint, glGetUniformBlockIndex, (GLuint, const GLchar*))
GLF(void, glUniformBlockBinding, (GLuint, GLuint, GLuint))
GLF(void, glGenSamplers, (GLsizei, GLuint*))
GLF(void, glBindSampler, (GLuint, GLuint))
GLF(void, glSamplerParameteri, (GLuint, GLenum, GLint))
GLF(void, glGenFramebuffers, (GLsizei, GLuint*))
GLF(void, glBindFramebuffer, (GLenum, GLuint))
GLF(void, glGenRenderbuffers, (GLsizei, GLuint*))
GLF(void, glBindRenderbuffer, (GLenum, GLuint))
GLF(void, glRenderbufferStorage, (GLenum, GLenum, GLsizei, GLsizei))
GLF(void, glFramebufferRenderbuffer, (GLenum, GLenum, GLenum, GLuint))
GLF(GLenum, glCheckFramebufferStatus, (GLenum))
GLF(void*, glFenceSync, (GLenum, unsigned))
GLF(GLenum, glClientWaitSync, (void*, unsigned, unsigned long long))
GLF(void, glDeleteSync, (void*))
static uint64_t now_ns(void) {
struct timespec ts;
clock_gettime(CLOCK_MONOTONIC, &ts);
return (uint64_t)ts.tv_sec * 1000000000ull + (uint64_t)ts.tv_nsec;
}
static int cmp_u64(const void* a, const void* b) {
uint64_t x = *(const uint64_t*)a, y = *(const uint64_t*)b;
return x < y ? -1 : x > y;
}
/* Scene, cases and the case table live next door so the Android plugin's
* in-process benchmark runs byte-identical bodies. */
static void bench_gl_failed(const char* what, const char* detail) {
fprintf(stderr, "FAIL: %s %s\n", what, detail ? detail : "");
exit(1);
}
/* GLES has glDrawElementsBaseVertex (3.2 core) but no multi-draw form of it, so
* against a native mobile driver the multi-draw case issues the same sub-draws
* one at a time - which is what the extension folds up, and what an application
* without it would have to write. Desktop GL and MobileGL take the real call. */
static void bench_multi_draw_elements_base_vertex(GLenum mode, const GLsizei* counts, GLenum type,
const void* const* offsets, GLsizei drawCount,
const GLint* baseVertices) {
if (glMultiDrawElementsBaseVertex) {
glMultiDrawElementsBaseVertex(mode, counts, type, offsets, drawCount, baseVertices);
return;
}
for (GLsizei i = 0; i < drawCount; ++i) {
glDrawElementsBaseVertex(mode, counts[i], type, offsets[i], baseVertices[i]);
}
}
#include "DriverBenchCases.inc"
/* ---- bench driver: fence-paced frames on the offscreen FBO ----------------
* Frames are closed with a real fence wait, not glFinish: MobileGL implements
* glFinish and glFlush as no-ops (MG_Impl/GLImpl/Exporting/Definitions.cpp),
* so a glFinish-paced loop would time only the CPU-side submit on a MobileGL
* backend while timing submit-plus-GPU on the native driver - the two numbers
* would not describe the same work. A sync object is honoured by every stack
* measured here.
*/
typedef void (*case_fn)(int frame, long a, long b);
static int g_warmup = 30, g_frames = 120;
static void end_frame_wait(void) {
if (glFenceSync && glClientWaitSync && glDeleteSync) {
void* sync = glFenceSync(GL_SYNC_GPU_COMMANDS_COMPLETE, 0);
if (sync) {
glClientWaitSync(sync, GL_SYNC_FLUSH_COMMANDS_BIT, 1000000000ull);
glDeleteSync(sync);
return;
}
}
glFinish();
}
static void run_case(const char* name, case_fn body, long a, long b, long opsPerFrame) {
static uint64_t samples[4096];
if (g_frames > 4096) g_frames = 4096;
end_frame_wait();
for (int i = 0; i < g_warmup; ++i) {
glClear(GL_COLOR_BUFFER_BIT | GL_DEPTH_BUFFER_BIT);
body(i, a, b);
end_frame_wait();
}
for (int i = 0; i < g_frames; ++i) {
uint64_t t0 = now_ns();
glClear(GL_COLOR_BUFFER_BIT | GL_DEPTH_BUFFER_BIT);
body(i, a, b);
end_frame_wait();
samples[i] = now_ns() - t0;
}
qsort(samples, g_frames, sizeof(uint64_t), cmp_u64);
uint64_t med = samples[g_frames / 2];
double frameMs = med / 1e6;
double nsPerOp = opsPerFrame > 0 ? (double)med / (double)opsPerFrame : 0.0;
printf("%s,%d,%ld,%.3f,%.1f,%.1f\n", name, g_frames, opsPerFrame, frameMs, nsPerOp,
1e9 / (double)med);
fflush(stdout);
if (glGetError() != GL_NO_ERROR) fprintf(stderr, "WARN: GL error after %s\n", name);
}
/* A display that needs no window system. eglGetPlatformDisplay is EGL 1.5
* core and eglGetPlatformDisplayEXT is the EGL_EXT_platform_base spelling
* older loaders ship; both are client entry points, so they resolve before
* any display exists. Only the attribute-list types differ between the two
* and this passes none, so one cast covers both. */
static EGLDisplay surfaceless_display(void) {
void* fn = dlsym(g_provider, "eglGetPlatformDisplay");
if (!fn) fn = g_eglGetProcAddress("eglGetPlatformDisplay");
if (!fn) fn = dlsym(g_provider, "eglGetPlatformDisplayEXT");
if (!fn) fn = g_eglGetProcAddress("eglGetPlatformDisplayEXT");
if (!fn) return NULL;
return ((EGLDisplay(*)(EGLenum, void*, const void*))fn)(EGL_PLATFORM_SURFACELESS_MESA,
EGL_DEFAULT_DISPLAY, NULL);
}
/* ---- EGL bootstrap: one provider library, pbuffer, desktop-GL context ---- */
static int boot_egl(void) {
const char* libpath = getenv("DRIVERBENCH_EGL_LIB");
if (!libpath) libpath = "libEGL.so.1";
g_provider = dlopen(libpath, RTLD_LAZY | RTLD_LOCAL);
if (!g_provider) {
fprintf(stderr, "FAIL: dlopen %s: %s\n", libpath, dlerror());
return 1;
}
#define ESYM(name) \
void* p_##name = dlsym(g_provider, #name); \
if (!p_##name) { fprintf(stderr, "FAIL: dlsym %s\n", #name); return 1; }
ESYM(eglGetDisplay)
ESYM(eglInitialize)
ESYM(eglChooseConfig)
ESYM(eglBindAPI)
ESYM(eglCreateContext)
ESYM(eglCreatePbufferSurface)
ESYM(eglMakeCurrent)
ESYM(eglGetProcAddress)
ESYM(eglGetError)
g_eglGetProcAddress = (void* (*)(const char*))p_eglGetProcAddress;
EGLint (*getError)(void) = (EGLint(*)(void))p_eglGetError;
EGLBoolean (*initialize)(EGLDisplay, EGLint*, EGLint*) =
(EGLBoolean(*)(EGLDisplay, EGLint*, EGLint*))p_eglInitialize;
/* The default display first: it is the one a windowed app would get, and
* on a desktop it is the one that reaches the real GPU - which is the
* driver this bench exists to measure. It does need a window system,
* though; Mesa's default platform is X11, so with no $DISPLAY (CI, a
* build server, ssh without forwarding) eglInitialize fails. Fall back to
* EGL_MESA_platform_surfaceless rather than give up: every case draws into
* the FBO built by build_resources(), so no window is needed for any of
* the work being timed. */
EGLint maj = 0, min = 0;
const char* how = "default display";
EGLDisplay dpy = ((EGLDisplay(*)(void*))p_eglGetDisplay)(EGL_DEFAULT_DISPLAY);
if (!dpy || !initialize(dpy, &maj, &min)) {
dpy = surfaceless_display();
how = "surfaceless display";
if (!dpy || !initialize(dpy, &maj, &min)) {
fprintf(stderr, "FAIL: eglInitialize (0x%x)\n", getError());
return 1;
}
}
fprintf(stderr, "EGL %d.%d via %s (%s)\n", maj, min, libpath, how);
// Desktop GL first (that is what MobileGL exposes and what the cases are
// written against), GLES 3 second so the same binary can measure a device's
// native driver as the baseline. The .inc picks ESSL shader sources when the
// context turns out to be ES.
EGLBoolean (*chooseConfig)(EGLDisplay, const EGLint*, EGLConfig*, EGLint, EGLint*) =
(EGLBoolean(*)(EGLDisplay, const EGLint*, EGLConfig*, EGLint, EGLint*))p_eglChooseConfig;
EGLContext (*createContext)(EGLDisplay, EGLConfig, EGLContext, const EGLint*) =
(EGLContext(*)(EGLDisplay, EGLConfig, EGLContext, const EGLint*))p_eglCreateContext;
EGLBoolean (*bindApi)(EGLenum) = (EGLBoolean(*)(EGLenum))p_eglBindAPI;
EGLConfig cfg = NULL;
EGLint ncfg = 0;
EGLContext ctx = EGL_NO_CONTEXT;
if (bindApi(EGL_OPENGL_API)) {
const EGLint cfgAttribs[] = {EGL_SURFACE_TYPE, EGL_PBUFFER_BIT, EGL_RED_SIZE, 8,
EGL_DEPTH_SIZE, 24, EGL_RENDERABLE_TYPE, EGL_OPENGL_BIT, EGL_NONE};
if (chooseConfig(dpy, cfgAttribs, &cfg, 1, &ncfg) && ncfg >= 1) {
const EGLint ctxAttribs[] = {EGL_CONTEXT_MAJOR_VERSION, 3, EGL_CONTEXT_MINOR_VERSION, 2,
EGL_CONTEXT_OPENGL_PROFILE_MASK,
EGL_CONTEXT_OPENGL_CORE_PROFILE_BIT, EGL_NONE};
ctx = createContext(dpy, cfg, EGL_NO_CONTEXT, ctxAttribs);
if (ctx == EGL_NO_CONTEXT) ctx = createContext(dpy, cfg, EGL_NO_CONTEXT, NULL);
}
}
if (ctx == EGL_NO_CONTEXT) {
if (!bindApi(EGL_OPENGL_ES_API)) {
fprintf(stderr, "FAIL: neither OpenGL nor OpenGL ES is bindable on this provider\n");
return 1;
}
const EGLint esCfgAttribs[] = {EGL_SURFACE_TYPE, EGL_PBUFFER_BIT, EGL_RED_SIZE, 8,
EGL_GREEN_SIZE, 8, EGL_BLUE_SIZE, 8, EGL_DEPTH_SIZE, 24,
EGL_RENDERABLE_TYPE, EGL_OPENGL_ES3_BIT, EGL_NONE};
ncfg = 0;
if (!chooseConfig(dpy, esCfgAttribs, &cfg, 1, &ncfg) || ncfg < 1) {
// EGL_SURFACE_TYPE 0 matches any config: a stack that offers no
// pbuffer at all is still usable through the surfaceless context
// path below.
const EGLint relaxed[] = {EGL_SURFACE_TYPE, 0, EGL_RED_SIZE, 8, EGL_NONE};
if (!chooseConfig(dpy, relaxed, &cfg, 1, &ncfg) || ncfg < 1) {
fprintf(stderr, "FAIL: eglChooseConfig\n");
return 1;
}
}
const EGLint esCtxAttribs[] = {EGL_CONTEXT_CLIENT_VERSION, 3, EGL_NONE};
ctx = createContext(dpy, cfg, EGL_NO_CONTEXT, esCtxAttribs);
}
if (ctx == EGL_NO_CONTEXT) {
fprintf(stderr, "FAIL: eglCreateContext (0x%x)\n", getError());
return 1;
}
/* The pbuffer only exists to have something to make current - nothing is
* ever drawn to it. Where there is no pbuffer config, EGL_NO_SURFACE is
* exactly what EGL_KHR_surfaceless_context takes, so the same call covers
* both. */
const EGLint pbAttribs[] = {EGL_WIDTH, 64, EGL_HEIGHT, 64, EGL_NONE};
EGLSurface surf = ((EGLSurface(*)(EGLDisplay, EGLConfig, const EGLint*))p_eglCreatePbufferSurface)(
dpy, cfg, pbAttribs);
if (surf == EGL_NO_SURFACE)
fprintf(stderr, "no pbuffer (0x%x), using a surfaceless context\n", getError());
if (!((EGLBoolean(*)(EGLDisplay, EGLSurface, EGLSurface, EGLContext))p_eglMakeCurrent)(dpy, surf,
surf, ctx)) {
fprintf(stderr, "FAIL: eglMakeCurrent (0x%x)\n", getError());
return 1;
}
/* Core GL entry points: eglGetProcAddress first (EGL 1.5 serves core
* functions), provider dlsym as fallback (both glvnd and MobileGL export
* the gl* symbols directly). */
#define RESOLVE(name) \
do { \
*(void**)&name = g_eglGetProcAddress(#name); \
if (!name) *(void**)&name = dlsym(g_provider, #name); \
if (!name) { fprintf(stderr, "FAIL: resolve %s\n", #name); return 1; } \
} while (0)
RESOLVE(glClear); RESOLVE(glClearColor); RESOLVE(glEnable); RESOLVE(glViewport);
RESOLVE(glDisable); RESOLVE(glBlendFuncSeparate); RESOLVE(glDrawBuffers);
RESOLVE(glGetString); RESOLVE(glGetError); RESOLVE(glFinish); RESOLVE(glFlush);
RESOLVE(glGenBuffers); RESOLVE(glBindBuffer); RESOLVE(glBufferData); RESOLVE(glBufferSubData);
RESOLVE(glGenVertexArrays); RESOLVE(glBindVertexArray); RESOLVE(glEnableVertexAttribArray);
RESOLVE(glVertexAttribPointer); RESOLVE(glGenTextures); RESOLVE(glBindTexture);
RESOLVE(glActiveTexture); RESOLVE(glTexImage2D); RESOLVE(glTexSubImage2D);
RESOLVE(glTexParameteri); RESOLVE(glGenerateMipmap); RESOLVE(glCreateShader);
RESOLVE(glPixelStorei); RESOLVE(glGetIntegerv);
RESOLVE(glShaderSource); RESOLVE(glCompileShader); RESOLVE(glGetShaderiv);
RESOLVE(glGetShaderInfoLog); RESOLVE(glCreateProgram); RESOLVE(glAttachShader);
RESOLVE(glLinkProgram); RESOLVE(glGetProgramiv); RESOLVE(glUseProgram);
RESOLVE(glGetUniformLocation); RESOLVE(glUniform1i); RESOLVE(glUniform3f);
RESOLVE(glUniformMatrix4fv); RESOLVE(glDrawElements); RESOLVE(glBindAttribLocation);
RESOLVE(glUniform3fv); RESOLVE(glDrawArrays); RESOLVE(glDrawElementsBaseVertex);
RESOLVE(glBindBufferRange); RESOLVE(glBindBufferBase);
RESOLVE(glGetUniformBlockIndex); RESOLVE(glUniformBlockBinding);
RESOLVE(glGenSamplers); RESOLVE(glBindSampler); RESOLVE(glSamplerParameteri);
RESOLVE(glGenFramebuffers); RESOLVE(glBindFramebuffer); RESOLVE(glGenRenderbuffers);
RESOLVE(glBindRenderbuffer); RESOLVE(glRenderbufferStorage); RESOLVE(glFramebufferRenderbuffer);
RESOLVE(glCheckFramebufferStatus);
// Optional: end_frame_wait() falls back to glFinish when a stack has no
// sync objects, so resolve without failing the run.
*(void**)&glFenceSync = g_eglGetProcAddress("glFenceSync");
if (!glFenceSync) *(void**)&glFenceSync = dlsym(g_provider, "glFenceSync");
*(void**)&glClientWaitSync = g_eglGetProcAddress("glClientWaitSync");
if (!glClientWaitSync) *(void**)&glClientWaitSync = dlsym(g_provider, "glClientWaitSync");
*(void**)&glDeleteSync = g_eglGetProcAddress("glDeleteSync");
if (!glDeleteSync) *(void**)&glDeleteSync = dlsym(g_provider, "glDeleteSync");
// Desktop-only: GLES 3.2 has DrawElementsBaseVertex but no multi-draw form,
// so bench_multi_draw_elements_base_vertex() emulates it when this is null.
*(void**)&glMultiDrawElementsBaseVertex = g_eglGetProcAddress("glMultiDrawElementsBaseVertex");
if (!glMultiDrawElementsBaseVertex)
*(void**)&glMultiDrawElementsBaseVertex = dlsym(g_provider, "glMultiDrawElementsBaseVertex");
fprintf(stderr, "renderer: %s\n", glGetString(GL_RENDERER));
fprintf(stderr, "version: %s\n", glGetString(GL_VERSION));
return 0;
}
int main(int argc, char** argv) {
long draws = 2048;
if (getenv("DRIVERBENCH_DRAWS")) draws = atol(getenv("DRIVERBENCH_DRAWS"));
if (getenv("DRIVERBENCH_FRAMES")) g_frames = atoi(getenv("DRIVERBENCH_FRAMES"));
if (getenv("DRIVERBENCH_SPRITES")) g_mixSprites = atol(getenv("DRIVERBENCH_SPRITES"));
if (boot_egl()) return 1;
build_resources();
printf("case,frames,ops_per_frame,median_frame_ms,ns_per_op,fps\n");
for (int i = 0; i < kBenchCaseCount; ++i) {
const BenchCaseDesc* c = &kBenchCases[i];
if (argc > 1) {
int wanted = 0;
for (int j = 1; j < argc; ++j)
if (strcmp(argv[j], c->name) == 0) wanted = 1;
if (!wanted) continue;
}
// The generic cases scale with DRIVERBENCH_DRAWS; the mc_* rates are
// measured and must not move, or the numbers stop being comparable.
long a = c->a, ops = c->opsPerFrame;
if (strncmp(c->name, "mc_", 3) != 0 && a > 100) {
a = draws * a / 2048;
ops = c->opsPerFrame * draws / 2048;
}
run_case(c->name, c->fn, a, c->b, ops);
}
return 0;
}
@@ -1,640 +0,0 @@
/* MobileGL - MobileGL/MG_Benchmark/Driver/DriverBenchCases.inc
* Copyright (c) 2025-2026 MobileGL-Dev
* Licensed under the GNU Lesser General Public License v3.0:
* https://www.gnu.org/licenses/gpl-3.0.txt
* https://www.gnu.org/licenses/lgpl-3.0.txt
* SPDX-License-Identifier: LGPL-3.0-only
* End of Source File Header
*
* The benchmark scene and its cases, with no harness and no GL loader: the
* includer supplies both. DriverBench.c drives it through function pointers
* resolved from one EGL provider; MG_Util/SelfTest/DriverBenchJni.cpp drives
* it through MobileGL's own frontend entry points inside the Android plugin.
* Sharing the bodies is the point - a number from the phone and a number from
* the desktop have to describe the same work.
*
* The includer must have declared, before including this file: the GL types
* and enums used below, and callable gl* entry points with the standard
* signatures. bench_gl_failed() is called (and must be defined) when shader
* compilation or linking fails, so a caller can report the failure instead of
* dying inside a benchmark.
*/
/* ---- shared scene resources (Minecraft-shaped) ---- */
#define MAX_SECTIONS 512
static GLuint g_progChunk, g_progEntity;
static GLint g_uOffsetChunk, g_uMvpChunk, g_uMvpEntity;
static GLuint g_vao[MAX_SECTIONS], g_vbo[MAX_SECTIONS];
static GLuint g_sharedIbo;
static GLuint g_texAtlas, g_texLight, g_texEntity;
static int g_quadsPerSection = 128; /* 128 quads = 512 verts, 768 indices */
static unsigned char* g_scratch;
/* Uniform ring + sampler for the 26.2-shaped cases (see the case block below). */
static GLuint g_uboRing;
static GLint g_uboAlign = 256;
static size_t g_uboSlot = 256;
static GLuint g_sampler;
/* Two small offscreen targets for the 26.2-style render-pass churn case. */
static GLuint g_passFbo[2];
static GLuint g_passColor[2];
static float g_mvp[16] = {0.002f, 0, 0, 0, 0, 0.002f, 0, 0, 0, 0, -0.001f, 0, -1.f, -1.f, 0.f, 1.f};
/* Minecraft chunk vertex: pos 3f, color 4ub, uv 2f, packed light 2s -> 32 B */
#define VERT_STRIDE 32
static void fill_section_vertices(unsigned char* dst, int quads, unsigned seed) {
for (int q = 0; q < quads * 4; ++q) {
float* f = (float*)(dst + q * VERT_STRIDE);
unsigned r = seed = seed * 1664525u + 1013904223u;
f[0] = (float)(q & 31) * 8.0f + (float)(r & 7);
f[1] = (float)((q >> 5) & 31) * 8.0f;
f[2] = (float)(q % 7) * 0.1f;
dst[q * VERT_STRIDE + 12] = (unsigned char)r;
dst[q * VERT_STRIDE + 13] = (unsigned char)(r >> 8);
dst[q * VERT_STRIDE + 14] = (unsigned char)(r >> 16);
dst[q * VERT_STRIDE + 15] = 255;
f[4] = (float)(r & 1023) / 1024.0f;
f[5] = (float)((r >> 10) & 511) / 512.0f;
((short*)(dst + q * VERT_STRIDE + 24))[0] = 15 << 4;
((short*)(dst + q * VERT_STRIDE + 24))[1] = 15 << 4;
}
}
static GLuint make_shader(GLenum kind, const char* src) {
GLuint sh = glCreateShader(kind);
glShaderSource(sh, 1, &src, NULL);
glCompileShader(sh);
GLint ok = 0;
glGetShaderiv(sh, GL_COMPILE_STATUS, &ok);
if (!ok) {
char log[1024];
glGetShaderInfoLog(sh, sizeof log, NULL, log);
bench_gl_failed("shader compile", log);
return 0;
}
return sh;
}
static GLuint make_program(const char* vs_src, const char* fs_src) {
GLuint prog = glCreateProgram();
glAttachShader(prog, make_shader(GL_VERTEX_SHADER, vs_src));
glAttachShader(prog, make_shader(GL_FRAGMENT_SHADER, fs_src));
glBindAttribLocation(prog, 0, "aPos");
glBindAttribLocation(prog, 1, "aColor");
glBindAttribLocation(prog, 2, "aUv");
glBindAttribLocation(prog, 3, "aLight");
glLinkProgram(prog);
GLint ok = 0;
glGetProgramiv(prog, GL_LINK_STATUS, &ok);
if (!ok) {
bench_gl_failed("program link", "");
return 0;
}
return prog;
}
static const char* kChunkVs =
"#version 150 core\n"
"in vec3 aPos; in vec4 aColor; in vec2 aUv; in vec2 aLight;\n"
"uniform mat4 uMvp; uniform vec3 uOffset;\n"
"out vec4 vColor; out vec2 vUv; out vec2 vLight;\n"
"void main(){ gl_Position = uMvp * vec4(aPos + uOffset, 1.0);\n"
" vColor = aColor; vUv = aUv; vLight = aLight * (1.0/256.0); }\n";
static const char* kChunkFs =
"#version 150 core\n"
"in vec4 vColor; in vec2 vUv; in vec2 vLight; out vec4 o;\n"
"uniform sampler2D uAtlas; uniform sampler2D uLight;\n"
"void main(){ o = texture(uAtlas, vUv) * vColor * texture(uLight, vLight); }\n";
static const char* kEntityVs =
"#version 150 core\n"
"in vec3 aPos; in vec4 aColor; in vec2 aUv; in vec2 aLight;\n"
"uniform mat4 uMvp; uniform mat4 uModel;\n"
"out vec4 vColor; out vec2 vUv;\n"
"void main(){ gl_Position = uMvp * uModel * vec4(aPos, 1.0); vColor = aColor; vUv = aUv; }\n";
static const char* kEntityFs =
"#version 150 core\n"
"in vec4 vColor; in vec2 vUv; out vec4 o; uniform sampler2D uTex;\n"
"void main(){ o = texture(uTex, vUv) * vColor; }\n";
// ESSL 3.20 twins of the four shaders above. The bodies are identical; only the
// version line and the precision qualifiers differ, so the two paths compile the
// same work. Needed because this bench also runs against a device's native GLES
// driver as the baseline MobileGL is measured against, and that driver rejects
// desktop GLSL - while MobileGL is fed desktop GLSL on purpose, since translating
// it is the thing under test.
static const char* kChunkVsEs =
"#version 320 es\n"
"precision highp float;\n"
"in vec3 aPos; in vec4 aColor; in vec2 aUv; in vec2 aLight;\n"
"uniform mat4 uMvp; uniform vec3 uOffset;\n"
"out vec4 vColor; out vec2 vUv; out vec2 vLight;\n"
"void main(){ gl_Position = uMvp * vec4(aPos + uOffset, 1.0);\n"
" vColor = aColor; vUv = aUv; vLight = aLight * (1.0/256.0); }\n";
static const char* kChunkFsEs =
"#version 320 es\n"
"precision mediump float;\n"
"in vec4 vColor; in vec2 vUv; in vec2 vLight; out vec4 o;\n"
"uniform sampler2D uAtlas; uniform sampler2D uLight;\n"
"void main(){ o = texture(uAtlas, vUv) * vColor * texture(uLight, vLight); }\n";
static const char* kEntityVsEs =
"#version 320 es\n"
"precision highp float;\n"
"in vec3 aPos; in vec4 aColor; in vec2 aUv; in vec2 aLight;\n"
"uniform mat4 uMvp; uniform mat4 uModel;\n"
"out vec4 vColor; out vec2 vUv;\n"
"void main(){ gl_Position = uMvp * uModel * vec4(aPos, 1.0); vColor = aColor; vUv = aUv; }\n";
static const char* kEntityFsEs =
"#version 320 es\n"
"precision mediump float;\n"
"in vec4 vColor; in vec2 vUv; out vec4 o; uniform sampler2D uTex;\n"
"void main(){ o = texture(uTex, vUv) * vColor; }\n";
// True once build_resources() has seen a GL_VERSION beginning with "OpenGL ES".
static int g_isGlesContext = 0;
static void setup_vao(GLuint vao, GLuint vbo, GLuint ibo) {
glBindVertexArray(vao);
glBindBuffer(GL_ARRAY_BUFFER, vbo);
glEnableVertexAttribArray(0);
glEnableVertexAttribArray(1);
glEnableVertexAttribArray(2);
glEnableVertexAttribArray(3);
glVertexAttribPointer(0, 3, GL_FLOAT, 0, VERT_STRIDE, (void*)0);
glVertexAttribPointer(1, 4, GL_UNSIGNED_BYTE, 1, VERT_STRIDE, (void*)12);
glVertexAttribPointer(2, 2, GL_FLOAT, 0, VERT_STRIDE, (void*)16);
glVertexAttribPointer(3, 2, GL_SHORT, 0, VERT_STRIDE, (void*)24);
glBindBuffer(GL_ELEMENT_ARRAY_BUFFER, ibo);
}
static GLuint g_mainFbo;
static void build_resources(void) {
/* offscreen render target: 1280x720 RBO FBO, like CTS fbo surface mode */
GLuint fbo, rboColor, rboDepth;
glGenFramebuffers(1, &fbo);
g_mainFbo = fbo;
glBindFramebuffer(GL_FRAMEBUFFER, fbo);
glGenRenderbuffers(1, &rboColor);
glBindRenderbuffer(GL_RENDERBUFFER, rboColor);
glRenderbufferStorage(GL_RENDERBUFFER, GL_RGBA8, 1280, 720);
glFramebufferRenderbuffer(GL_FRAMEBUFFER, GL_COLOR_ATTACHMENT0, GL_RENDERBUFFER, rboColor);
glGenRenderbuffers(1, &rboDepth);
glBindRenderbuffer(GL_RENDERBUFFER, rboDepth);
glRenderbufferStorage(GL_RENDERBUFFER, GL_DEPTH_COMPONENT24, 1280, 720);
glFramebufferRenderbuffer(GL_FRAMEBUFFER, GL_DEPTH_ATTACHMENT, GL_RENDERBUFFER, rboDepth);
if (glCheckFramebufferStatus(GL_FRAMEBUFFER) != GL_FRAMEBUFFER_COMPLETE) {
bench_gl_failed("FBO incomplete", "");
return;
}
const char* versionString = (const char*)glGetString(GL_VERSION);
g_isGlesContext = versionString != NULL && strncmp(versionString, "OpenGL ES", 9) == 0;
g_progChunk = g_isGlesContext ? make_program(kChunkVsEs, kChunkFsEs) : make_program(kChunkVs, kChunkFs);
g_progEntity = g_isGlesContext ? make_program(kEntityVsEs, kEntityFsEs) : make_program(kEntityVs, kEntityFs);
glUseProgram(g_progChunk);
g_uMvpChunk = glGetUniformLocation(g_progChunk, "uMvp");
g_uOffsetChunk = glGetUniformLocation(g_progChunk, "uOffset");
glUniform1i(glGetUniformLocation(g_progChunk, "uAtlas"), 0);
glUniform1i(glGetUniformLocation(g_progChunk, "uLight"), 2);
glUniformMatrix4fv(g_uMvpChunk, 1, 0, g_mvp);
glUseProgram(g_progEntity);
g_uMvpEntity = glGetUniformLocation(g_progEntity, "uMvp");
glUniform1i(glGetUniformLocation(g_progEntity, "uTex"), 0);
glUniformMatrix4fv(g_uMvpEntity, 1, 0, g_mvp);
glUseProgram(g_progChunk);
/* shared quad index buffer, like Blaze3D's RenderSystem shared sequences */
int maxQuads = 4096;
unsigned* idx = (unsigned*)malloc((size_t)maxQuads * 6 * 4);
for (int q = 0; q < maxQuads; ++q) {
unsigned base = q * 4;
unsigned* p = idx + q * 6;
p[0] = base; p[1] = base + 1; p[2] = base + 2;
p[3] = base + 2; p[4] = base + 3; p[5] = base;
}
glGenBuffers(1, &g_sharedIbo);
glBindBuffer(GL_ELEMENT_ARRAY_BUFFER, g_sharedIbo);
glBufferData(GL_ELEMENT_ARRAY_BUFFER, maxQuads * 6 * 4, idx, GL_STATIC_DRAW);
free(idx);
g_scratch = (unsigned char*)malloc(4 * 1024 * 1024);
memset(g_scratch, 0x5a, 4 * 1024 * 1024);
glGenVertexArrays(MAX_SECTIONS, g_vao);
glGenBuffers(MAX_SECTIONS, g_vbo);
int bytes = g_quadsPerSection * 4 * VERT_STRIDE;
for (int i = 0; i < MAX_SECTIONS; ++i) {
fill_section_vertices(g_scratch, g_quadsPerSection, i * 7919u + 1);
glBindBuffer(GL_ARRAY_BUFFER, g_vbo[i]);
glBufferData(GL_ARRAY_BUFFER, bytes, g_scratch, GL_STATIC_DRAW);
setup_vao(g_vao[i], g_vbo[i], g_sharedIbo);
}
glGenTextures(1, &g_texAtlas);
glActiveTexture(GL_TEXTURE0);
glBindTexture(GL_TEXTURE_2D, g_texAtlas);
glTexImage2D(GL_TEXTURE_2D, 0, GL_RGBA8, 1024, 512, 0, GL_RGBA, GL_UNSIGNED_BYTE, g_scratch);
glTexParameteri(GL_TEXTURE_2D, GL_TEXTURE_MIN_FILTER, GL_NEAREST_MIPMAP_LINEAR);
glTexParameteri(GL_TEXTURE_2D, GL_TEXTURE_MAG_FILTER, GL_NEAREST);
glGenerateMipmap(GL_TEXTURE_2D);
glGenTextures(1, &g_texLight);
glActiveTexture(GL_TEXTURE0 + 2);
glBindTexture(GL_TEXTURE_2D, g_texLight);
glTexImage2D(GL_TEXTURE_2D, 0, GL_RGBA8, 16, 16, 0, GL_RGBA, GL_UNSIGNED_BYTE, g_scratch);
glTexParameteri(GL_TEXTURE_2D, GL_TEXTURE_MIN_FILTER, GL_NEAREST);
glTexParameteri(GL_TEXTURE_2D, GL_TEXTURE_MAG_FILTER, GL_NEAREST);
glGenTextures(1, &g_texEntity);
glActiveTexture(GL_TEXTURE0);
glBindTexture(GL_TEXTURE_2D, g_texEntity);
glTexImage2D(GL_TEXTURE_2D, 0, GL_RGBA8, 64, 64, 0, GL_RGBA, GL_UNSIGNED_BYTE, g_scratch);
glTexParameteri(GL_TEXTURE_2D, GL_TEXTURE_MIN_FILTER, GL_NEAREST);
glTexParameteri(GL_TEXTURE_2D, GL_TEXTURE_MAG_FILTER, GL_NEAREST);
glBindTexture(GL_TEXTURE_2D, g_texAtlas);
// Uniform ring the 26.2-style case sub-ranges into, sized like a real
// frame's worth of per-draw uniform slots.
GLint align = 256;
glGetIntegerv(GL_UNIFORM_BUFFER_OFFSET_ALIGNMENT, &align);
g_uboAlign = align > 0 ? align : 256;
g_uboSlot = (size_t)g_uboAlign;
glGenBuffers(1, &g_uboRing);
glBindBuffer(GL_UNIFORM_BUFFER, g_uboRing);
glBufferData(GL_UNIFORM_BUFFER, 4 * 1024 * 1024, g_scratch, GL_DYNAMIC_DRAW);
glBindBuffer(GL_UNIFORM_BUFFER, 0);
for (int i = 0; i < 2; ++i) {
glGenFramebuffers(1, &g_passFbo[i]);
glBindFramebuffer(GL_FRAMEBUFFER, g_passFbo[i]);
glGenRenderbuffers(1, &g_passColor[i]);
glBindRenderbuffer(GL_RENDERBUFFER, g_passColor[i]);
glRenderbufferStorage(GL_RENDERBUFFER, GL_RGBA8, 256, 256);
glFramebufferRenderbuffer(GL_FRAMEBUFFER, GL_COLOR_ATTACHMENT0, GL_RENDERBUFFER, g_passColor[i]);
if (glCheckFramebufferStatus(GL_FRAMEBUFFER) != GL_FRAMEBUFFER_COMPLETE) {
bench_gl_failed("pass FBO incomplete", "");
return;
}
}
/* back to the main offscreen target the harness set up */
glBindFramebuffer(GL_FRAMEBUFFER, g_mainFbo);
glGenSamplers(1, &g_sampler);
glSamplerParameteri(g_sampler, GL_TEXTURE_MIN_FILTER, GL_NEAREST);
glSamplerParameteri(g_sampler, GL_TEXTURE_MAG_FILTER, GL_NEAREST);
glEnable(GL_DEPTH_TEST);
glClearColor(0.3f, 0.5f, 0.9f, 1.0f);
glViewport(0, 0, 1280, 720);
const GLenum setupError = glGetError();
if (setupError != GL_NO_ERROR) {
char message[64];
snprintf(message, sizeof message, "0x%04x", setupError);
bench_gl_failed("GL error during resource setup", message);
}
}
static void case_draw_tiny(int frame, long a, long b) {
(void)frame; (void)b;
glBindVertexArray(g_vao[0]);
for (long i = 0; i < a; ++i) glDrawElements(GL_TRIANGLES, g_quadsPerSection * 6, GL_UNSIGNED_INT, 0);
}
static void case_draw_uniform(int frame, long a, long b) {
(void)frame; (void)b;
glBindVertexArray(g_vao[0]);
for (long i = 0; i < a; ++i) {
glUniform3f(g_uOffsetChunk, (float)(i & 15), (float)((i >> 4) & 15), 0.0f);
glDrawElements(GL_TRIANGLES, g_quadsPerSection * 6, GL_UNSIGNED_INT, 0);
}
}
static void case_draw_multi_vao(int frame, long a, long b) {
(void)frame; (void)b;
for (long i = 0; i < a; ++i) {
glBindVertexArray(g_vao[i % MAX_SECTIONS]);
glUniform3f(g_uOffsetChunk, (float)(i & 15), (float)((i >> 4) & 15), 0.0f);
glDrawElements(GL_TRIANGLES, g_quadsPerSection * 6, GL_UNSIGNED_INT, 0);
}
}
static void case_tex_pingpong(int frame, long a, long b) {
(void)frame; (void)b;
glBindVertexArray(g_vao[0]);
for (long i = 0; i < a; ++i) {
glBindTexture(GL_TEXTURE_2D, (i & 1) ? g_texEntity : g_texAtlas);
glDrawElements(GL_TRIANGLES, g_quadsPerSection * 6, GL_UNSIGNED_INT, 0);
}
glBindTexture(GL_TEXTURE_2D, g_texAtlas);
}
static void case_program_pingpong(int frame, long a, long b) {
(void)frame; (void)b;
glBindVertexArray(g_vao[0]);
for (long i = 0; i < a; ++i) {
if (i & 1) {
glUseProgram(g_progEntity);
glUniformMatrix4fv(g_uMvpEntity, 1, 0, g_mvp);
} else {
glUseProgram(g_progChunk);
glUniform3f(g_uOffsetChunk, (float)(i & 15), 0.0f, 0.0f);
}
glDrawElements(GL_TRIANGLES, g_quadsPerSection * 6, GL_UNSIGNED_INT, 0);
}
glUseProgram(g_progChunk);
}
/* a = uploads per frame, b = bytes per upload (0 => section size) */
static void case_chunk_upload(int frame, long a, long b) {
if (b <= 0) b = g_quadsPerSection * 4 * VERT_STRIDE;
if (b > 4 * 1024 * 1024) b = 4 * 1024 * 1024;
for (long i = 0; i < a; ++i) {
int slot = (int)(((long)frame * a + i) % MAX_SECTIONS);
glBindBuffer(GL_ARRAY_BUFFER, g_vbo[slot]);
glBufferData(GL_ARRAY_BUFFER, b, NULL, GL_STATIC_DRAW); /* orphan */
glBufferSubData(GL_ARRAY_BUFFER, 0, b, g_scratch);
glBindVertexArray(g_vao[slot]);
glDrawElements(GL_TRIANGLES, g_quadsPerSection * 6, GL_UNSIGNED_INT, 0);
}
}
/* a = sprite updates per frame */
static void case_atlas_sprite(int frame, long a, long b) {
(void)b;
glBindVertexArray(g_vao[0]);
glBindTexture(GL_TEXTURE_2D, g_texAtlas);
for (long i = 0; i < a; ++i) {
int x = (int)((frame * 13 + i * 17) % (1024 - 16));
int y = (int)((frame * 7 + i * 29) % (512 - 16));
glTexSubImage2D(GL_TEXTURE_2D, 0, x, y, 16, 16, GL_RGBA, GL_UNSIGNED_BYTE, g_scratch);
}
glDrawElements(GL_TRIANGLES, g_quadsPerSection * 6, GL_UNSIGNED_INT, 0);
}
/* a = lightmap updates (+draw) per frame */
static void case_lightmap(int frame, long a, long b) {
(void)frame; (void)b;
glBindVertexArray(g_vao[0]);
for (long i = 0; i < a; ++i) {
glActiveTexture(GL_TEXTURE0 + 2);
glBindTexture(GL_TEXTURE_2D, g_texLight);
glTexSubImage2D(GL_TEXTURE_2D, 0, 0, 0, 16, 16, GL_RGBA, GL_UNSIGNED_BYTE, g_scratch);
glActiveTexture(GL_TEXTURE0);
glDrawElements(GL_TRIANGLES, g_quadsPerSection * 6, GL_UNSIGNED_INT, 0);
}
}
/* Composite: a = total draws, b = uploads per frame. Mix modeled on trace
* analysis: chunk draws with per-draw offset uniform across sections, 10%
* entity-style program flips, per-frame lightmap + sprite updates, b chunk
* re-uploads. */
static long g_mixSprites = 8;
static void case_scene_mix(int frame, long a, long b) {
glActiveTexture(GL_TEXTURE0 + 2);
glBindTexture(GL_TEXTURE_2D, g_texLight);
glTexSubImage2D(GL_TEXTURE_2D, 0, 0, 0, 16, 16, GL_RGBA, GL_UNSIGNED_BYTE, g_scratch);
glActiveTexture(GL_TEXTURE0);
glBindTexture(GL_TEXTURE_2D, g_texAtlas);
for (long i = 0; i < g_mixSprites; ++i) {
int x = (int)((frame * 13 + i * 17) % (1024 - 16));
int y = (int)((frame * 7 + i * 29) % (512 - 16));
glTexSubImage2D(GL_TEXTURE_2D, 0, x, y, 16, 16, GL_RGBA, GL_UNSIGNED_BYTE, g_scratch);
}
for (long i = 0; i < b; ++i) {
int slot = (int)(((long)frame * b + i) % MAX_SECTIONS);
long bytes = g_quadsPerSection * 4 * VERT_STRIDE;
glBindBuffer(GL_ARRAY_BUFFER, g_vbo[slot]);
glBufferData(GL_ARRAY_BUFFER, bytes, NULL, GL_STATIC_DRAW);
glBufferSubData(GL_ARRAY_BUFFER, 0, bytes, g_scratch);
}
long entityEvery = 10;
for (long i = 0; i < a; ++i) {
if (i % entityEvery == entityEvery - 1) {
glUseProgram(g_progEntity);
glUniformMatrix4fv(g_uMvpEntity, 1, 0, g_mvp);
glBindTexture(GL_TEXTURE_2D, g_texEntity);
glBindVertexArray(g_vao[i % MAX_SECTIONS]);
glDrawElements(GL_TRIANGLES, g_quadsPerSection * 6, GL_UNSIGNED_INT, 0);
glUseProgram(g_progChunk);
glBindTexture(GL_TEXTURE_2D, g_texAtlas);
} else {
glBindVertexArray(g_vao[i % MAX_SECTIONS]);
glUniform3f(g_uOffsetChunk, (float)(i & 15), (float)((i >> 4) & 15), 0.0f);
glDrawElements(GL_TRIANGLES, g_quadsPerSection * 6, GL_UNSIGNED_INT, 0);
}
}
}
/* ---- Trace-derived cases -------------------------------------------------
* Per-frame call mixes measured from the three captured Minecraft traces
* (render distance 32, 1280x720, hovering in-world). Each case reproduces one
* renderer's dominant per-draw sequence at its measured rate, so the number a
* backend posts here is directly comparable to what that game version asks of
* the driver every frame.
*
* vanilla 1.21.1 : 5495 glDrawElements, 5490 glBindVertexArray,
* 5487 glUniform3fv, 95 glTexSubImage2D (+382 glPixelStorei,
* 247 glTexParameteri), 23 glBufferData per frame
* fabric+sodium : 132 glMultiDrawElementsBaseVertex, 279 glBindVertexArray,
* 132 glUniform3f, 32 glBufferData per frame
* 26.2 snapshot : 3401 glDrawElementsBaseVertex, each preceded by
* glBindBufferRange + glBindBuffer (3639/3412 per frame)
*/
/* vanilla: bind VAO, push the chunk offset, draw. a = draws per frame. */
static void case_mc_vanilla_draw(int frame, long a, long b) {
(void)frame; (void)b;
float offset[3];
for (long i = 0; i < a; ++i) {
glBindVertexArray(g_vao[i % MAX_SECTIONS]);
offset[0] = (float)(i & 15);
offset[1] = (float)((i >> 4) & 15);
offset[2] = 0.0f;
glUniform3fv(g_uOffsetChunk, 1, offset);
glDrawElements(GL_TRIANGLES, g_quadsPerSection * 6, GL_UNSIGNED_INT, 0);
}
}
/* sodium: one multi-draw covers many chunk sections out of a shared buffer.
* a = multi-draws per frame, b = sub-draws inside each. */
static void case_mc_sodium_multidraw(int frame, long a, long b) {
(void)frame;
enum { kMaxSub = 64 };
if (b <= 0 || b > kMaxSub) b = 32;
GLsizei counts[kMaxSub];
const void* offsets[kMaxSub];
GLint baseVertices[kMaxSub];
for (long s = 0; s < b; ++s) {
counts[s] = (GLsizei)(g_quadsPerSection * 6 / b);
offsets[s] = (const void*)(uintptr_t)(s * (g_quadsPerSection * 6 / b) * 4);
baseVertices[s] = 0;
}
for (long i = 0; i < a; ++i) {
glBindVertexArray(g_vao[i % MAX_SECTIONS]);
glBindVertexArray(g_vao[i % MAX_SECTIONS]); /* sodium rebinds ~2x per draw */
glUniform3f(g_uOffsetChunk, (float)(i & 15), (float)((i >> 4) & 15), 0.0f);
// Routed through the includer: GLES has no multi-draw-with-base-vertex, so
// a native-driver harness emulates it with the loop the extension folds up.
bench_multi_draw_elements_base_vertex(GL_TRIANGLES, counts, GL_UNSIGNED_INT, offsets,
(GLsizei)b, baseVertices);
}
}
/* 26.2: every draw rebinds a fresh uniform-buffer range out of a ring.
* a = draws per frame. */
static void case_mc_ubo_range(int frame, long a, long b) {
(void)b;
const size_t slots = (4u * 1024u * 1024u) / g_uboSlot;
for (long i = 0; i < a; ++i) {
const size_t slot = (size_t)(((long)frame * a + i) % (long)slots);
glBindBufferRange(GL_UNIFORM_BUFFER, 0, g_uboRing, (GLintptr)(slot * g_uboSlot),
(GLsizeiptr)g_uboSlot);
glBindBuffer(GL_UNIFORM_BUFFER, g_uboRing);
glDrawElementsBaseVertex(GL_TRIANGLES, g_quadsPerSection * 6, GL_UNSIGNED_INT, 0, 0);
}
}
/* vanilla's animated-sprite path: every upload is wrapped in the pixel-store
* and filter state Blaze3D re-sets around it. a = uploads per frame. */
static void case_mc_tex_stream(int frame, long a, long b) {
(void)b;
glBindVertexArray(g_vao[0]);
glBindTexture(GL_TEXTURE_2D, g_texAtlas);
for (long i = 0; i < a; ++i) {
glPixelStorei(GL_UNPACK_ALIGNMENT, 4);
glPixelStorei(GL_UNPACK_ROW_LENGTH, 0);
glPixelStorei(GL_UNPACK_SKIP_ROWS, 0);
glPixelStorei(GL_UNPACK_SKIP_PIXELS, 0);
glTexParameteri(GL_TEXTURE_2D, GL_TEXTURE_WRAP_S, GL_CLAMP_TO_EDGE);
glTexParameteri(GL_TEXTURE_2D, GL_TEXTURE_WRAP_T, GL_CLAMP_TO_EDGE);
int x = (int)((frame * 13 + i * 17) % (1024 - 16));
int y = (int)((frame * 7 + i * 29) % (512 - 16));
glTexSubImage2D(GL_TEXTURE_2D, 0, x, y, 16, 16, GL_RGBA, GL_UNSIGNED_BYTE, g_scratch);
}
glDrawElements(GL_TRIANGLES, g_quadsPerSection * 6, GL_UNSIGNED_INT, 0);
}
/* Blaze3D re-resolves uniform locations by name every frame. a = lookups. */
static void case_mc_uniform_lookup(int frame, long a, long b) {
(void)frame; (void)b;
static const char* names[4] = {"uMvp", "uOffset", "uAtlas", "uLight"};
volatile GLint sink = 0;
for (long i = 0; i < a; ++i) sink += glGetUniformLocation(g_progChunk, names[i & 3]);
(void)sink;
glBindVertexArray(g_vao[0]);
glDrawElements(GL_TRIANGLES, g_quadsPerSection * 6, GL_UNSIGNED_INT, 0);
}
/* 26.2 rebinds a sampler object per texture unit switch. a = switches. */
static void case_mc_sampler_churn(int frame, long a, long b) {
(void)frame; (void)b;
glBindVertexArray(g_vao[0]);
for (long i = 0; i < a; ++i) {
glActiveTexture(GL_TEXTURE0 + (GLenum)(i & 3));
glBindTexture(GL_TEXTURE_2D, (i & 1) ? g_texEntity : g_texAtlas);
glBindSampler((GLuint)(i & 3), g_sampler);
glDrawElements(GL_TRIANGLES, g_quadsPerSection * 6, GL_UNSIGNED_INT, 0);
}
glActiveTexture(GL_TEXTURE0);
}
/* 26.2 switches render targets constantly: 132 glBindFramebuffer and 198
* glDrawBuffers per frame. Pass switching is where a Vulkan backend pays for
* render-pass breaks, so this case is the one to watch on Magma. a = passes. */
static void case_mc_pass_switch(int frame, long a, long b) {
(void)frame; (void)b;
static const GLenum kColor0[1] = {GL_COLOR_ATTACHMENT0};
glBindVertexArray(g_vao[0]);
for (long i = 0; i < a; ++i) {
glBindFramebuffer(GL_FRAMEBUFFER, g_passFbo[i & 1]);
glDrawBuffers(1, kColor0);
glViewport(0, 0, 256, 256);
glDrawElements(GL_TRIANGLES, g_quadsPerSection * 6, GL_UNSIGNED_INT, 0);
glDrawElements(GL_TRIANGLES, g_quadsPerSection * 6, GL_UNSIGNED_INT, 0);
}
glBindFramebuffer(GL_FRAMEBUFFER, g_mainFbo);
glViewport(0, 0, 1280, 720);
}
/* Blaze3D toggles blend around batches: 46 glEnable/glDisable pairs and 28
* glBlendFuncSeparate per vanilla frame. a = toggle pairs. */
static void case_mc_state_toggle(int frame, long a, long b) {
(void)frame; (void)b;
glBindVertexArray(g_vao[0]);
for (long i = 0; i < a; ++i) {
glEnable(GL_BLEND);
glBlendFuncSeparate(GL_SRC_ALPHA, GL_ONE_MINUS_SRC_ALPHA, GL_ONE, GL_ZERO);
glDrawElements(GL_TRIANGLES, g_quadsPerSection * 6, GL_UNSIGNED_INT, 0);
glDisable(GL_BLEND);
glDrawElements(GL_TRIANGLES, g_quadsPerSection * 6, GL_UNSIGNED_INT, 0);
}
}
/* 26.2 re-sets texture parameters relentlessly - 612 glTexParameteri per frame,
* almost always to the value already in place. Measures redundant-param
* filtering. a = parameter writes. */
static void case_mc_tex_param(int frame, long a, long b) {
(void)frame; (void)b;
glBindVertexArray(g_vao[0]);
glBindTexture(GL_TEXTURE_2D, g_texAtlas);
for (long i = 0; i < a; i += 4) {
glTexParameteri(GL_TEXTURE_2D, GL_TEXTURE_WRAP_S, GL_CLAMP_TO_EDGE);
glTexParameteri(GL_TEXTURE_2D, GL_TEXTURE_WRAP_T, GL_CLAMP_TO_EDGE);
glTexParameteri(GL_TEXTURE_2D, GL_TEXTURE_MIN_FILTER, GL_NEAREST_MIPMAP_LINEAR);
glTexParameteri(GL_TEXTURE_2D, GL_TEXTURE_MAG_FILTER, GL_NEAREST);
}
glDrawElements(GL_TRIANGLES, g_quadsPerSection * 6, GL_UNSIGNED_INT, 0);
}
/* Sodium switches programs mid-frame far more than vanilla: 62 glUseProgram and
* 60 mat4 uploads per frame. a = program switches. */
static void case_mc_use_program(int frame, long a, long b) {
(void)frame; (void)b;
glBindVertexArray(g_vao[0]);
for (long i = 0; i < a; ++i) {
if (i & 1) {
glUseProgram(g_progEntity);
glUniformMatrix4fv(g_uMvpEntity, 1, 0, g_mvp);
} else {
glUseProgram(g_progChunk);
glUniformMatrix4fv(g_uMvpChunk, 1, 0, g_mvp);
}
glDrawElements(GL_TRIANGLES, g_quadsPerSection * 6, GL_UNSIGNED_INT, 0);
}
glUseProgram(g_progChunk);
}
/* ---- the case table both harnesses iterate --------------------------------
* a/b are the case's own knobs; opsPerFrame is what one bench frame is
* normalised by, so ns_per_op compares across renderers. The mc_* rates are
* the per-frame call counts measured from the captured traces.
*/
typedef void (*bench_case_fn)(int frame, long a, long b);
typedef struct {
const char* name;
bench_case_fn fn;
long a, b, opsPerFrame;
} BenchCaseDesc;
static const BenchCaseDesc kBenchCases[] = {
{"mc_vanilla_draw", case_mc_vanilla_draw, 5495, 0, 5495},
{"mc_sodium_multidraw", case_mc_sodium_multidraw, 132, 32, 132},
{"mc_ubo_range", case_mc_ubo_range, 3401, 0, 3401},
{"mc_tex_stream", case_mc_tex_stream, 95, 0, 95},
{"mc_uniform_lookup", case_mc_uniform_lookup, 41, 0, 41},
{"mc_sampler_churn", case_mc_sampler_churn, 306, 0, 306},
{"mc_pass_switch", case_mc_pass_switch, 132, 0, 132},
{"mc_state_toggle", case_mc_state_toggle, 46, 0, 46},
{"mc_tex_param", case_mc_tex_param, 612, 0, 612},
{"mc_use_program", case_mc_use_program, 62, 0, 62},
{"draw_tiny", case_draw_tiny, 2048, 0, 2048},
{"draw_uniform", case_draw_uniform, 2048, 0, 2048},
{"draw_multi_vao", case_draw_multi_vao, 2048, 0, 2048},
{"tex_pingpong", case_tex_pingpong, 1024, 0, 1024},
{"program_pingpong", case_program_pingpong, 512, 0, 512},
{"chunk_upload", case_chunk_upload, 24, 0, 24},
{"atlas_sprite", case_atlas_sprite, 32, 0, 32},
{"lightmap", case_lightmap, 4, 0, 4},
{"scene_mix", case_scene_mix, 2048, 12, 2048},
};
static const int kBenchCaseCount = (int)(sizeof kBenchCases / sizeof kBenchCases[0]);
@@ -1,41 +0,0 @@
#!/bin/bash
# Run the headless EGL DriverBench on one renderer:
# ./run_driver_bench.sh native [bench args...]
# ./run_driver_bench.sh espryt <libMobileGL.so> [bench args...]
# ./run_driver_bench.sh magma <libMobileGL.so> [bench args...]
# The bench dlopens exactly one EGL provider (DRIVERBENCH_EGL_LIB): the system
# libEGL.so.1 for native, or the given libMobileGL.so for a MobileGL backend -
# no LD_LIBRARY_PATH shadowing, so MobileGL's own loader still finds the real
# driver underneath.
#
# Pin the vendor libraries explicitly. A bare libEGL.so.1 on a glvnd system
# picks whatever vendor eglGetDisplay(EGL_DEFAULT_DISPLAY) resolves first,
# which is Mesa/llvmpipe here - a software rasteriser silently replacing the
# GPU under a benchmark. Override MGL_EGL_VENDOR / MGL_VK_ICD to test another
# driver.
set -eu
HERE=$(cd "$(dirname "$0")" && pwd)
BENCH=${DRIVERBENCH_BIN:-$HERE/DriverBench}
EGL_VENDOR=${MGL_EGL_VENDOR:-/usr/share/glvnd/egl_vendor.d/10_nvidia.json}
VK_ICD=${MGL_VK_ICD:-/usr/share/vulkan/icd.d/nvidia_icd.x86_64.json}
MODE=$1; shift
export __EGL_VENDOR_LIBRARY_FILENAMES=$EGL_VENDOR
export EGL_PLATFORM=${EGL_PLATFORM:-x11}
case "$MODE" in
native)
export DRIVERBENCH_EGL_LIB=${DRIVERBENCH_EGL_LIB:-libEGL.so.1}
;;
espryt)
export DRIVERBENCH_EGL_LIB=$(readlink -f "$1"); shift
export MOBILEGL_BACKEND_TYPE=DirectGLES
;;
magma)
export DRIVERBENCH_EGL_LIB=$(readlink -f "$1"); shift
export MOBILEGL_BACKEND_TYPE=DirectVulkan
export VK_ICD_FILENAMES=$VK_ICD
;;
*) echo "unknown mode: $MODE (native|espryt|magma)"; exit 1 ;;
esac
exec "$BENCH" "$@"
-33
View File
@@ -24,7 +24,6 @@ namespace MobileGL::MG_Impl::CGLImpl {
GLint Samples = 0;
GLint Profile = kCGLOGLPVersion_3_2_Core;
GLint RendererId = 0x4d474c;
GLint DisplayMask = 0;
};
struct ContextObject {
@@ -135,9 +134,6 @@ namespace MobileGL::MG_Impl::CGLImpl {
case kCGLPFARendererID:
pixelFormat.RendererId = value;
break;
case kCGLPFADisplayMask:
pixelFormat.DisplayMask = value;
break;
default:
break;
}
@@ -347,9 +343,6 @@ namespace MobileGL::MG_Impl::CGLImpl {
case kCGLPFARendererID:
*value = pixelFormat->RendererId;
return kCGLNoError;
case kCGLPFADisplayMask:
*value = pixelFormat->DisplayMask;
return kCGLNoError;
case kCGLPFAOpenGLProfile:
*value = pixelFormat->Profile;
return kCGLNoError;
@@ -488,32 +481,6 @@ namespace MobileGL::MG_Impl::CGLImpl {
return it == currentContexts.end() ? nullptr : it->second;
}
CGLError SetVirtualScreen(CGLContextObj ctx, GLint screen) {
const std::lock_guard<std::recursive_mutex> lock(RegistryMutex());
auto* object = TryGetContext(ctx);
if (!object) {
return kCGLBadContext;
}
if (screen != 0) {
return kCGLBadValue;
}
object->VirtualScreen = screen;
return kCGLNoError;
}
CGLError GetVirtualScreen(CGLContextObj ctx, GLint* screen) {
const std::lock_guard<std::recursive_mutex> lock(RegistryMutex());
auto* object = TryGetContext(ctx);
if (!object) {
return kCGLBadContext;
}
if (!screen) {
return kCGLBadAddress;
}
*screen = object->VirtualScreen;
return kCGLNoError;
}
CGLError SetParameter(CGLContextObj ctx, CGLContextParameter pname, const GLint* params) {
const std::lock_guard<std::recursive_mutex> lock(RegistryMutex());
auto* object = TryGetContext(ctx);
-2
View File
@@ -32,8 +32,6 @@ namespace MobileGL::MG_Impl::CGLImpl {
CGLError SetCurrentContext(CGLContextObj ctx);
CGLContextObj GetCurrentContext();
CGLError SetVirtualScreen(CGLContextObj ctx, GLint screen);
CGLError GetVirtualScreen(CGLContextObj ctx, GLint* screen);
CGLError SetParameter(CGLContextObj ctx, CGLContextParameter pname, const GLint* params);
CGLError GetParameter(CGLContextObj ctx, CGLContextParameter pname, GLint* params);
CGLError UpdateContext(CGLContextObj ctx);
@@ -71,14 +71,6 @@ MOBILEGL_CGL_API CGLContextObj CGLGetCurrentContext(void) {
return MobileGL::MG_Impl::CGLImpl::GetCurrentContext();
}
MOBILEGL_CGL_API CGLError CGLSetVirtualScreen(CGLContextObj ctx, GLint screen) {
return MobileGL::MG_Impl::CGLImpl::SetVirtualScreen(ctx, screen);
}
MOBILEGL_CGL_API CGLError CGLGetVirtualScreen(CGLContextObj ctx, GLint* screen) {
return MobileGL::MG_Impl::CGLImpl::GetVirtualScreen(ctx, screen);
}
MOBILEGL_CGL_API CGLError CGLSetParameter(CGLContextObj ctx, CGLContextParameter pname, const GLint* params) {
return MobileGL::MG_Impl::CGLImpl::SetParameter(ctx, pname, params);
}
@@ -10,12 +10,8 @@
#if defined(__APPLE__)
#include "MG_Impl/CGLImpl/CGLImpl.h"
#include "MG_Impl/GetProcAddress.h"
#include <CoreGraphics/CoreGraphics.h>
#include <CoreVideo/CVDisplayLink.h>
#include <cstdint>
#include <dlfcn.h>
namespace {
@@ -51,52 +47,10 @@ namespace {
return dlsym(handle, symbol);
}
CGDirectDisplayID DisplayForMask(GLint displayMask) {
constexpr std::uint32_t MaxDisplays = sizeof(CGOpenGLDisplayMask) * 8;
CGDirectDisplayID displays[MaxDisplays] = {};
std::uint32_t displayCount = 0;
if (displayMask != 0 &&
CGGetActiveDisplayList(MaxDisplays, displays, &displayCount) == kCGErrorSuccess) {
const auto mask = static_cast<CGOpenGLDisplayMask>(displayMask);
for (std::uint32_t i = 0; i < displayCount; ++i) {
if ((CGDisplayIDToOpenGLDisplayMask(displays[i]) & mask) != 0) {
return displays[i];
}
}
}
return CGMainDisplayID();
}
#pragma clang diagnostic push
#pragma clang diagnostic ignored "-Wdeprecated-declarations"
CVReturn MobileGLCVDisplayLinkSetCurrentCGDisplayFromOpenGLContext(
CVDisplayLinkRef displayLink,
CGLContextObj context,
CGLPixelFormatObj pixelFormat) {
GLint virtualScreen = 0;
if (MobileGL::MG_Impl::CGLImpl::GetVirtualScreen(context, &virtualScreen) == kCGLNoError) {
GLint displayMask = 0;
if (!displayLink ||
MobileGL::MG_Impl::CGLImpl::DescribePixelFormat(
pixelFormat, virtualScreen, kCGLPFADisplayMask, &displayMask) != kCGLNoError) {
return kCVReturnInvalidArgument;
}
return CVDisplayLinkSetCurrentCGDisplay(displayLink, DisplayForMask(displayMask));
}
using OriginalFunction = CVReturn (*)(CVDisplayLinkRef, CGLContextObj, CGLPixelFormatObj);
static const auto original = reinterpret_cast<OriginalFunction>(
dlsym(RTLD_NEXT, "CVDisplayLinkSetCurrentCGDisplayFromOpenGLContext"));
return original ? original(displayLink, context, pixelFormat) : kCVReturnError;
}
__attribute__((used)) static const DyldInterposeEntry kMobileGLDyldInterpose[]
__attribute__((section("__DATA,__interpose"))) = {
{reinterpret_cast<const void*>(MobileGLDlsym), reinterpret_cast<const void*>(dlsym)},
{reinterpret_cast<const void*>(MobileGLCVDisplayLinkSetCurrentCGDisplayFromOpenGLContext),
reinterpret_cast<const void*>(CVDisplayLinkSetCurrentCGDisplayFromOpenGLContext)},
};
#pragma clang diagnostic pop
} // namespace
#endif
@@ -1,10 +0,0 @@
# Public CGL entry points.
_CGL*
# Public EGL entry points.
_egl*
# Public OpenGL and GLX entry points. OpenGL function names always use an
# uppercase letter or digit after the "gl" prefix; excluding lowercase here
# deliberately prevents glslang_* from matching this pattern.
_gl[A-Z0-9]*
+14 -137
View File
@@ -8,9 +8,6 @@
#include "GL_Buffer.h"
#include "Validators.h"
#include "../Texture/GL_Texture.h"
#include <MG_Util/Converters/GLToMG/TextureEnumConverter.h>
#include <MG_Util/Metrics/TextureMetrics.h>
#include <Config.h>
#include <MG_State/GLState/Core.h>
#include <MG_State/GLState/ErrorState/Error.h>
@@ -41,7 +38,6 @@ namespace MobileGL::MG_Impl::GLImpl {
GetNamedBufferParameteriv,
GetNamedBufferParameteri64v,
GetNamedBufferPointerv,
GetNamedBufferSubData,
};
const char* GetBufferOpName(BufferOp op) {
@@ -80,8 +76,6 @@ namespace MobileGL::MG_Impl::GLImpl {
return "UnmapNamedBuffer";
case BufferOp::FlushMappedNamedBufferRange:
return "FlushMappedNamedBufferRange";
case BufferOp::GetNamedBufferSubData:
return "GetNamedBufferSubData";
case BufferOp::GetNamedBufferParameteriv:
return "GetNamedBufferParameteriv";
case BufferOp::GetNamedBufferParameteri64v:
@@ -95,64 +89,25 @@ namespace MobileGL::MG_Impl::GLImpl {
SharedPtr<MG_State::GLState::BufferObject> GetNamedBufferObject(GLuint buffer, BufferOp op);
// The size of one cleared element, which is what offset and size must be multiples of
// (GL 4.6 core 6.3). `internalformat` is restricted to the buffer-texture format table, and
// `format`/`type` describe the client-side pattern, so both are validated here and the
// caller only has to know how wide an element is.
SizeT GetClearPatternSize(GLenum internalformat, GLenum format, GLenum type, BufferOp op) {
if (!IsBufferTextureInternalFormat(internalformat)) {
MG_State::pGLContext->RecordError(
ErrorCode::InvalidEnum,
MakeUnique<GenericErrorInfo>(
"MG_Impl/GLImpl", GetBufferOpName(op),
std::format("internalformat 0x{:X} is not one of the sized formats a buffer clear accepts.",
internalformat)));
return 0;
}
// Unlike internalformat, a bad format or type here is INVALID_VALUE rather than
// INVALID_ENUM (GL 4.6 core 6.3) - the odd one out among the enum arguments.
const TextureInputFormat inputFormat = MG_Util::ConvertGLEnumToTextureInputFormat(format);
if (inputFormat == TextureInputFormat::Unknown) {
MG_State::pGLContext->RecordError(
ErrorCode::InvalidValue,
MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", GetBufferOpName(op),
std::format("format 0x{:X} is not a pixel format.", format)));
return 0;
}
const TexturePixelDataType pixelType = MG_Util::ConvertGLEnumToTexturePixelDataType(type);
if (pixelType == TexturePixelDataType::Unknown) {
MG_State::pGLContext->RecordError(
ErrorCode::InvalidValue,
MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", GetBufferOpName(op),
std::format("type 0x{:X} is not a pixel type.", type)));
return 0;
}
const TextureInternalFormat internal =
MG_Util::ConvertGLEnumToTextureInternalFormat(internalformat);
const SizeT elementSize = MG_Util::GetSizedInternalFormatSizeInBytes(internal);
if (elementSize == 0) {
if (format != GL_RED_INTEGER) {
MG_State::pGLContext->RecordError(
ErrorCode::InvalidEnum,
MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", GetBufferOpName(op),
std::format("internalformat 0x{:X} has no known element size.",
internalformat)));
"Only GL_RED_INTEGER buffer clears are currently supported."));
return 0;
}
// The pattern is replicated verbatim, which is only the whole story while the client
// layout already matches the internal format - the case every entry point in practice
// uses, and the only one the conversion machinery here can express. Say so rather than
// quietly writing a differently-sized pattern.
const SizeT sourceSize = MG_Util::GetInputBytesPerPixel(inputFormat, pixelType);
if (sourceSize != elementSize) {
MGLOG_W("%s: clear pattern is %zu bytes but internalformat 0x%X stores %zu; "
"converting between them is not implemented",
GetBufferOpName(op), sourceSize, internalformat, elementSize);
}
return elementSize;
if (internalformat == GL_R8UI && type == GL_UNSIGNED_BYTE) return sizeof(GLubyte);
if (internalformat == GL_R32UI && type == GL_UNSIGNED_INT) return sizeof(GLuint);
MG_State::pGLContext->RecordError(
ErrorCode::InvalidEnum,
MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", GetBufferOpName(op),
std::format("Unsupported clear format tuple: internalformat=0x{:X}, "
"format=0x{:X}, type=0x{:X}",
internalformat, format, type)));
return 0;
}
Bool ValidateBufferClearRange(const SharedPtr<MG_State::GLState::BufferObject>& bufferObject, GLintptr offset,
@@ -375,21 +330,12 @@ namespace MobileGL::MG_Impl::GLImpl {
} else if (access & BufferMappingAccessBit::Write) {
*params = GL_WRITE_ONLY;
} else {
*params = GL_READ_WRITE;
*params = 0;
}
} else {
// Initial value, and what glUnmapBuffer restores (GL 4.6 core table 6.2).
*params = GL_READ_WRITE;
*params = 0;
}
break;
case GL_BUFFER_ACCESS_FLAGS:
// The MapBufferRange flags verbatim; glMapBuffer's access enum has already been
// normalised into the same bits. Zero while the buffer is not mapped.
*params = bufferObject->IsMapped()
? static_cast<GLint>(
MG_Util::ConvertBufferMappingAccessToGLEnum(bufferObject->GetMappingAccess()))
: 0;
break;
case GL_BUFFER_MAPPED:
*params = bufferObject->IsMapped() ? GL_TRUE : GL_FALSE;
break;
@@ -932,45 +878,6 @@ namespace MobileGL::MG_Impl::GLImpl {
return;
}
bufferObject->SyncGpuWrites();
bufferObject->DownloadSubData(data, static_cast<SizeT>(offset), static_cast<SizeT>(size));
}
void GetNamedBufferSubData_State(GLuint buffer, GLintptr offset, GLsizeiptr size, void* data) {
if (!data) {
// Match GetBufferSubData_State: a null pointer is a caller bug, not a GL-specified error.
return;
}
if (size < 0 || offset < 0) {
MG_State::pGLContext->RecordError(
ErrorCode::InvalidValue,
MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", "GetNamedBufferSubData_State",
"Offset and size must be non-negative."));
return;
}
auto bufferObject = GetNamedBufferObject(buffer, BufferOp::GetNamedBufferSubData);
if (!bufferObject) return;
if (static_cast<SizeT>(offset) + static_cast<SizeT>(size) > bufferObject->GetSize()) {
MG_State::pGLContext->RecordError(
ErrorCode::InvalidValue,
MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", "GetNamedBufferSubData_State",
"Offset and size exceed buffer size."));
return;
}
if (bufferObject->IsMapped() &&
!(bufferObject->GetMappingAccess() & BufferMappingAccessBit::Persistent)) {
MG_State::pGLContext->RecordError(
ErrorCode::InvalidOperation,
MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", "GetNamedBufferSubData_State",
"Cannot read from a buffer object mapped without GL_MAP_PERSISTENT_BIT."));
return;
}
bufferObject->SyncGpuWrites();
bufferObject->DownloadSubData(data, static_cast<SizeT>(offset), static_cast<SizeT>(size));
}
@@ -1444,14 +1351,6 @@ namespace MobileGL::MG_Impl::GLImpl {
BufferTarget bufferTarget = MG_Util::ConvertGLEnumToBufferTarget(target);
if (!BufferImpl::ValidateBufferBindingPointTarget(bufferTarget)) return;
if (!BufferImpl::ValidateBufferBindingPointIndex(bufferTarget, pointIndex)) return;
if (bufferTarget == BufferTarget::TransformFeedback && MG_State::pGLContext->IsTransformFeedbackActive()) {
MG_State::pGLContext->RecordError(
ErrorCode::InvalidOperation,
MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", __func__,
"Transform feedback buffer bindings cannot change while transform "
"feedback is active."));
return;
}
MG_State::pGLContext->TouchBufferBindingPoint(bufferTarget, pointIndex);
auto& point = MG_State::pGLContext->GetBufferBindingPoint(bufferTarget, pointIndex);
@@ -1459,7 +1358,6 @@ namespace MobileGL::MG_Impl::GLImpl {
if (buffer == 0) {
point.Bind(nullptr);
point.SetRange(Range1D(0, 0));
GetBufferBindingSlot(bufferTarget).Bind(nullptr);
return;
}
@@ -1478,12 +1376,6 @@ namespace MobileGL::MG_Impl::GLImpl {
} else {
point.ClearRange();
}
// The indexed bind also binds to the generic binding point of the same target
// (GL 4.6 core 6.1.1). Callers rely on it: the texture_gather tests set up their
// SSBO with BindBufferBase and then size it through glBufferData on the generic
// target alone, which would otherwise raise GL_INVALID_OPERATION and leave the
// buffer with no storage.
GetBufferBindingSlot(bufferTarget).Bind(bufferObject);
}
void BindBufferRange_State(GLenum target, GLuint index, GLuint buffer, GLintptr offset, GLsizeiptr size) {
@@ -1492,14 +1384,6 @@ namespace MobileGL::MG_Impl::GLImpl {
BufferTarget bufferTarget = MG_Util::ConvertGLEnumToBufferTarget(target);
if (!BufferImpl::ValidateBufferBindingPointTarget(bufferTarget)) return;
if (!BufferImpl::ValidateBufferBindingPointIndex(bufferTarget, index)) return;
if (bufferTarget == BufferTarget::TransformFeedback && MG_State::pGLContext->IsTransformFeedbackActive()) {
MG_State::pGLContext->RecordError(
ErrorCode::InvalidOperation,
MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", __func__,
"Transform feedback buffer bindings cannot change while transform "
"feedback is active."));
return;
}
MG_State::pGLContext->TouchBufferBindingPoint(bufferTarget, index);
auto& point = MG_State::pGLContext->GetBufferBindingPoint(bufferTarget, index);
@@ -1507,7 +1391,6 @@ namespace MobileGL::MG_Impl::GLImpl {
if (buffer == 0) {
point.Bind(nullptr);
point.SetRange(Range1D(0, 0));
GetBufferBindingSlot(bufferTarget).Bind(nullptr);
return;
}
@@ -1525,8 +1408,6 @@ namespace MobileGL::MG_Impl::GLImpl {
} else {
point.ClearRange();
}
// Also the generic binding point, exactly as BindBufferBase (GL 4.6 core 6.1.1).
GetBufferBindingSlot(bufferTarget).Bind(bufferObject);
}
/* @INSERTION_POINT:FUNCTION_IMPLEMENTATION@ */
@@ -1636,10 +1517,6 @@ namespace MobileGL::MG_Impl::GLImpl {
BufferSubData_State(target, offset, size, data);
}
void GetNamedBufferSubData(GLuint buffer, GLintptr offset, GLsizeiptr size, void* data) {
GetNamedBufferSubData_State(buffer, offset, size, data);
}
void GetBufferSubData(GLenum target, GLintptr offset, GLsizeiptr size, void* data) {
GetBufferSubData_State(target, offset, size, data);
}
@@ -41,7 +41,6 @@ namespace MobileGL::MG_Impl::GLImpl {
GLsizeiptr size);
void BufferSubData(GLenum target, GLintptr offset, GLsizeiptr size, const void* data);
void GetBufferSubData(GLenum target, GLintptr offset, GLsizeiptr size, void* data);
void GetNamedBufferSubData(GLuint buffer, GLintptr offset, GLsizeiptr size, void* data);
void BufferData(GLenum target, GLsizeiptr size, const void* data, GLenum usage);
void BindBuffer(GLenum target, GLuint buffer);
void GenBuffers(GLsizei n, GLuint* buffers);
@@ -60,11 +60,6 @@ namespace MobileGL::MG_Impl::GLImpl::BufferImpl {
MG_Backend::pActiveBackendObject->GetDynamicParameters().MaxShaderStorageBufferBindings;
pointCount = std::min(pointCount, static_cast<SizeT>(std::max(backendCount, 0)));
}
if (target == BufferTarget::TransformFeedback) {
// GL_MAX_TRANSFORM_FEEDBACK_SEPARATE_ATTRIBS bounds the indexed capture
// binding points in GL 3.3 (no ARB_transform_feedback3).
pointCount = std::min<SizeT>(pointCount, 4);
}
if (index < pointCount) {
return true;
@@ -112,10 +107,14 @@ namespace MobileGL::MG_Impl::GLImpl::BufferImpl {
}
Bool ValidateBufferMappingAccess(Flags<BufferMappingAccessBit> accessBits) {
// An empty mask is a legal value for a bitfield - it just fails the rule that a mapping
// must ask for read or write access, which is INVALID_OPERATION and belongs to the callers
// (both of them check it immediately after this). Rejecting it here as INVALID_ENUM
// reported the wrong error and hid theirs.
if (accessBits == BufferMappingAccessBit::Null) {
MG_State::pGLContext->RecordError(ErrorCode::InvalidEnum,
MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl/BufferImpl",
"ValidateBufferMappingAccess",
"Access bits cannot be null."));
return false;
}
const auto validBits = BufferMappingAccessBit::Read | BufferMappingAccessBit::Write |
BufferMappingAccessBit::InvalidateRange | BufferMappingAccessBit::InvalidateBuffer |
BufferMappingAccessBit::FlushExplicit | BufferMappingAccessBit::Unsynchronized |
+11 -736
View File
@@ -11,11 +11,10 @@
#include <MG_State/GLState/Core.h>
#include <MG_State/EGLState/Core.h>
#include <MG_Backend/BackendObjects.h>
#include "../Getter/GL_Getter.h"
namespace MobileGL::MG_Impl::GLImpl {
static Bool ValidateCurrentProgramForExecution(const char* functionName) {
const auto& currentProgram = MG_State::pGLContext->GetProgramForDraw();
const auto& currentProgram = MG_State::pGLContext->GetCurrentProgram();
if (!currentProgram) {
MG_State::pGLContext->RecordError(
ErrorCode::InvalidOperation,
@@ -37,7 +36,7 @@ namespace MobileGL::MG_Impl::GLImpl {
static Bool ValidateCurrentProgramForCompute(const char* functionName) {
if (!ValidateCurrentProgramForExecution(functionName)) return false;
const auto& currentProgram = MG_State::pGLContext->GetProgramForDraw();
const auto& currentProgram = MG_State::pGLContext->GetCurrentProgram();
if (currentProgram->GetShaderIndexByStage(ShaderStage::Compute) < 0) {
MG_State::pGLContext->RecordError(
ErrorCode::InvalidOperation,
@@ -49,109 +48,7 @@ namespace MobileGL::MG_Impl::GLImpl {
return true;
}
// Primitives a draw of `count` vertices in `mode` assembles (0 for
// incomplete primitives). Used for the CPU-side transform feedback
// primitive accounting.
static Uint64 CountPrimitivesForDraw(GLenum mode, GLsizei count) {
if (count <= 0) return 0;
switch (mode) {
case GL_POINTS: return static_cast<Uint64>(count);
case GL_LINES: return static_cast<Uint64>(count / 2);
case GL_LINE_STRIP: return count >= 2 ? static_cast<Uint64>(count - 1) : 0;
case GL_LINE_LOOP: return count >= 2 ? static_cast<Uint64>(count) : 0;
case GL_TRIANGLES: return static_cast<Uint64>(count / 3);
case GL_TRIANGLE_STRIP:
case GL_TRIANGLE_FAN: return count >= 3 ? static_cast<Uint64>(count - 2) : 0;
default: return 0;
}
}
// Accumulate the transform feedback primitive counter for a captured draw.
// Draws without a geometry stage write exactly the primitives they assemble,
// clamped by the capture buffers' remaining capacity (a full buffer stops
// recording whole primitives, which is what PRIMITIVES_WRITTEN reports).
// Geometry amplification is not modelled here.
static void AccountTransformFeedbackPrimitives(GLenum mode, GLsizei count) {
if (!MG_State::pGLContext->IsTransformFeedbackActive()) return;
// A paused span captures nothing, so a draw made while paused contributes to
// PRIMITIVES_GENERATED but not to TRANSFORM_FEEDBACK_PRIMITIVES_WRITTEN.
if (MG_State::pGLContext->IsTransformFeedbackPaused()) {
MG_State::pGLContext->AddTransformFeedbackPausedPrimitives(CountPrimitivesForDraw(mode, count));
return;
}
Uint64 primitives = CountPrimitivesForDraw(mode, count);
if (primitives == 0) return;
MG_State::pGLContext->AddTransformFeedbackInputPrimitives(primitives);
Uint64 verticesPerPrimitive = 1;
switch (mode) {
case GL_LINES:
case GL_LINE_STRIP:
case GL_LINE_LOOP:
verticesPerPrimitive = 2;
break;
case GL_TRIANGLES:
case GL_TRIANGLE_STRIP:
case GL_TRIANGLE_FAN:
verticesPerPrimitive = 3;
break;
default:
break;
}
const auto& program = MG_State::pGLContext->GetTransformFeedbackProgram();
if (program != nullptr) {
// Capacity in captured vertices = the tightest bound buffer.
Uint64 capacityVertices = ~0ull;
for (SizeT i = 0; i < program->GetTransformFeedbackBufferCount(); ++i) {
const Uint32 stride = program->GetTransformFeedbackStride(static_cast<Uint32>(i));
if (stride == 0) continue;
const auto& point = MG_State::pGLContext->GetBufferBindingPoint(BufferTarget::TransformFeedback,
static_cast<Uint>(i));
const Range1D range = point.GetRange();
const Uint64 bytes = range.end > range.start ? static_cast<Uint64>(range.end - range.start) : 0;
capacityVertices = std::min<Uint64>(capacityVertices, bytes / stride);
}
if (capacityVertices != ~0ull) {
const Uint64 usedVertices = MG_State::pGLContext->GetTransformFeedbackCapturedVertices();
const Uint64 remainingVertices = capacityVertices > usedVertices ? capacityVertices - usedVertices : 0;
primitives = std::min<Uint64>(primitives, remainingVertices / verticesPerPrimitive);
}
}
MG_State::pGLContext->AddTransformFeedbackPrimitives(primitives);
MG_State::pGLContext->AddTransformFeedbackCapturedVertices(primitives * verticesPerPrimitive);
}
// Every primitive mode a draw command accepts (GL 4.6 core table 10.1, plus
// GL_PATCHES for the tessellation pipeline). Anything else is GL_INVALID_ENUM.
static Bool IsAcceptedPrimitiveMode(GLenum mode) {
switch (mode) {
case GL_POINTS:
case GL_LINES:
case GL_LINE_LOOP:
case GL_LINE_STRIP:
case GL_LINES_ADJACENCY:
case GL_LINE_STRIP_ADJACENCY:
case GL_TRIANGLES:
case GL_TRIANGLE_STRIP:
case GL_TRIANGLE_FAN:
case GL_TRIANGLES_ADJACENCY:
case GL_TRIANGLE_STRIP_ADJACENCY:
case GL_PATCHES:
return true;
default:
return false;
}
}
static Bool ValidatePrimitiveModeForBackend(const char* functionName, GLenum mode) {
if (!IsAcceptedPrimitiveMode(mode)) {
MG_State::pGLContext->RecordError(
ErrorCode::InvalidEnum,
MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", functionName, "mode is not an accepted primitive type."));
return false;
}
const auto& activeBackendObject = MG_Backend::pActiveBackendObject;
if (!activeBackendObject) {
MG_State::pGLContext->RecordError(
@@ -160,6 +57,15 @@ namespace MobileGL::MG_Impl::GLImpl {
return false;
}
if (activeBackendObject->GetBackendType() == BackendType::DirectVulkan && mode == GL_LINE_LOOP) {
MG_State::pGLContext->RecordError(
ErrorCode::InvalidOperation,
MakeUnique<GenericErrorInfo>(
"MG_Impl/GLImpl", functionName,
"Primitive mode GL_LINE_LOOP is not supported by the DirectVulkan backend."));
return false;
}
const auto& vao = MG_State::pGLContext->GetBoundVertexArray();
if (vao && vao->GetExternalIndex() == 0 && !MG_State::IsRelaxedSemanticsActive()) {
MG_State::pGLContext->RecordError(
@@ -169,133 +75,9 @@ namespace MobileGL::MG_Impl::GLImpl {
return false;
}
// A geometry stage only accepts the primitive types that decompose into its declared
// input primitive (GL 4.6 core 11.3.1); anything else is INVALID_OPERATION. GL_PATCHES
// is the tessellation pipeline's input and reaches the geometry stage already
// converted, so it is not constrained here.
const auto& currentProgram = MG_State::pGLContext->GetProgramForDraw();
const GLenum gsInput = currentProgram ? currentProgram->GetGeometryInputType() : GL_NONE;
if (gsInput != GL_NONE && mode != GL_PATCHES) {
Bool compatible = false;
switch (gsInput) {
case GL_POINTS:
compatible = mode == GL_POINTS;
break;
case GL_LINES:
compatible = mode == GL_LINES || mode == GL_LINE_STRIP || mode == GL_LINE_LOOP;
break;
case GL_LINES_ADJACENCY:
compatible = mode == GL_LINES_ADJACENCY || mode == GL_LINE_STRIP_ADJACENCY;
break;
case GL_TRIANGLES:
compatible = mode == GL_TRIANGLES || mode == GL_TRIANGLE_STRIP || mode == GL_TRIANGLE_FAN;
break;
case GL_TRIANGLES_ADJACENCY:
compatible = mode == GL_TRIANGLES_ADJACENCY || mode == GL_TRIANGLE_STRIP_ADJACENCY;
break;
default:
break;
}
if (!compatible) {
MG_State::pGLContext->RecordError(
ErrorCode::InvalidOperation,
MakeUnique<GenericErrorInfo>(
"MG_Impl/GLImpl", functionName,
"Primitive mode is incompatible with the geometry shader's input primitive type."));
return false;
}
}
// While transform feedback is active the draw's primitive type must match
// the feedback primitive mode (GL 3.3 core 13.2.2). With a geometry shader
// the constraint moves to the shader's output primitive type instead, so
// the draw mode itself is unconstrained here. A paused span is exempt: it
// captures nothing, so there is nothing for the mode to be incompatible with
// (GL 4.6 core 13.2.3).
if (MG_State::pGLContext->IsTransformFeedbackActive() &&
!MG_State::pGLContext->IsTransformFeedbackPaused() &&
!(MG_State::pGLContext->GetTransformFeedbackProgram() &&
MG_State::pGLContext->GetTransformFeedbackProgram()->GetShaderIndexByStage(ShaderStage::Geometry) >= 0)) {
const GLenum feedbackMode = MG_State::pGLContext->GetTransformFeedbackPrimitiveMode();
Bool compatible = false;
switch (feedbackMode) {
case GL_POINTS:
compatible = mode == GL_POINTS;
break;
case GL_LINES:
compatible = mode == GL_LINES || mode == GL_LINE_STRIP || mode == GL_LINE_LOOP;
break;
case GL_TRIANGLES:
compatible = mode == GL_TRIANGLES || mode == GL_TRIANGLE_STRIP || mode == GL_TRIANGLE_FAN;
break;
default:
break;
}
if (!compatible) {
MG_State::pGLContext->RecordError(
ErrorCode::InvalidOperation,
MakeUnique<GenericErrorInfo>(
"MG_Impl/GLImpl", functionName,
"Primitive mode is incompatible with the active transform feedback primitive mode."));
return false;
}
}
return true;
}
// Byte size of the command structures the indirect draws read (GL 4.6 core 10.3.10).
constexpr SizeT kDrawArraysIndirectCommandBytes = 4 * sizeof(Uint32);
constexpr SizeT kDrawElementsIndirectCommandBytes = 5 * sizeof(Uint32);
// Shared preconditions of every *Indirect draw: `indirect` is a byte offset into the
// buffer bound to GL_DRAW_INDIRECT_BUFFER, must be 4-byte aligned, and the whole
// command has to lie inside that buffer.
static Bool ValidateIndirectDrawSource(const char* functionName, const void* indirect, SizeT commandBytes) {
const auto offset = reinterpret_cast<uintptr_t>(indirect);
if (offset % 4 != 0) {
MG_State::pGLContext->RecordError(
ErrorCode::InvalidValue,
MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", functionName,
"indirect offset must be a multiple of 4."));
return false;
}
const auto& buffer = MG_State::pGLContext->GetBufferBindingSlot(BufferTarget::DrawIndirect).GetBoundObject();
if (!buffer) {
MG_State::pGLContext->RecordError(
ErrorCode::InvalidOperation,
MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", functionName,
"No buffer is bound to GL_DRAW_INDIRECT_BUFFER."));
return false;
}
if (offset + commandBytes > buffer->GetSize()) {
MG_State::pGLContext->RecordError(
ErrorCode::InvalidOperation,
MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", functionName,
"The indirect command extends past the end of the bound "
"GL_DRAW_INDIRECT_BUFFER."));
return false;
}
return true;
}
// Index type accepted by the DrawElements family (GL 4.6 core 10.3.9).
static Bool ValidateDrawElementsIndexType(const char* functionName, GLenum type) {
switch (type) {
case GL_UNSIGNED_BYTE:
case GL_UNSIGNED_SHORT:
case GL_UNSIGNED_INT:
return true;
default:
MG_State::pGLContext->RecordError(
ErrorCode::InvalidEnum,
MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", functionName, "type is not an accepted index type."));
return false;
}
}
void Clear_Backend(GLbitfield mask) {
#ifdef TRACY_ENABLE
ZoneScopedC(TRACY_ZONECOLOR_BACKEND);
@@ -490,28 +272,6 @@ namespace MobileGL::MG_Impl::GLImpl {
dispatchComputeIndirect(indirect);
}
void PatchParameteri(GLenum pname, GLint value) {
if (pname != GL_PATCH_VERTICES) {
MG_State::pGLContext->RecordError(
ErrorCode::InvalidEnum,
MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", __func__, "pname must be GL_PATCH_VERTICES."));
return;
}
GLint maxPatchVertices = 32;
GetIntegerv(GL_MAX_PATCH_VERTICES, &maxPatchVertices);
if (value <= 0 || value > maxPatchVertices) {
MG_State::pGLContext->RecordError(
ErrorCode::InvalidValue,
MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", __func__,
"value must be in [1, GL_MAX_PATCH_VERTICES]."));
return;
}
MG_State::pGLContext->SetPatchVertices(static_cast<Uint>(value));
if (const auto patchParameteri = MG_Backend::gBackendFunctionsTable.GL.PatchParameteri) {
patchParameteri(pname, value);
}
}
void MemoryBarrier(GLbitfield barriers) {
auto memoryBarrier = MG_Backend::gBackendFunctionsTable.GL.MemoryBarrier;
if (!memoryBarrier) {
@@ -617,8 +377,6 @@ namespace MobileGL::MG_Impl::GLImpl {
void DrawElementsIndirect(GLenum mode, GLenum type, const void* indirect) {
if (!ValidateCurrentProgramForExecution(__func__)) return;
if (!ValidatePrimitiveModeForBackend(__func__, mode)) return;
if (!ValidateDrawElementsIndexType(__func__, type)) return;
if (!ValidateIndirectDrawSource(__func__, indirect, kDrawElementsIndirectCommandBytes)) return;
DrawElementsIndirect_Backend(mode, type, indirect);
}
@@ -638,21 +396,18 @@ namespace MobileGL::MG_Impl::GLImpl {
void DrawArraysIndirect(GLenum mode, const void* indirect) {
if (!ValidateCurrentProgramForExecution(__func__)) return;
if (!ValidatePrimitiveModeForBackend(__func__, mode)) return;
if (!ValidateIndirectDrawSource(__func__, indirect, kDrawArraysIndirectCommandBytes)) return;
DrawArraysIndirect_Backend(mode, indirect);
}
void DrawElementsBaseVertex(GLenum mode, GLsizei count, GLenum type, const void* indices, GLint basevertex) {
if (!ValidateCurrentProgramForExecution(__func__)) return;
if (!ValidatePrimitiveModeForBackend(__func__, mode)) return;
AccountTransformFeedbackPrimitives(mode, count);
DrawElementsBaseVertex_Backend(mode, count, type, indices, basevertex);
}
void DrawArrays(GLenum mode, GLint first, GLsizei count) {
if (!ValidateCurrentProgramForExecution(__func__)) return;
if (!ValidatePrimitiveModeForBackend(__func__, mode)) return;
AccountTransformFeedbackPrimitives(mode, count);
DrawArrays_Backend(mode, first, count);
}
@@ -689,487 +444,7 @@ namespace MobileGL::MG_Impl::GLImpl {
void DrawElements(GLenum mode, GLsizei count, GLenum type, const void* indices) {
if (!ValidateCurrentProgramForExecution(__func__)) return;
if (!ValidatePrimitiveModeForBackend(__func__, mode)) return;
AccountTransformFeedbackPrimitives(mode, count);
DrawElements_Backend(mode, count, type, indices);
}
void BeginTransformFeedback(GLenum primitiveMode) {
if (primitiveMode != GL_POINTS && primitiveMode != GL_LINES && primitiveMode != GL_TRIANGLES) {
MG_State::pGLContext->RecordError(
ErrorCode::InvalidEnum,
MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", __func__,
"primitiveMode must be GL_POINTS, GL_LINES or GL_TRIANGLES."));
return;
}
if (MG_State::pGLContext->IsTransformFeedbackActive()) {
MG_State::pGLContext->RecordError(
ErrorCode::InvalidOperation,
MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", __func__, "Transform feedback is already active."));
return;
}
const auto& program = MG_State::pGLContext->GetProgramForDraw();
if (!program || !program->GetLinkStatus() || program->GetTransformFeedbackVaryingCount() == 0) {
MG_State::pGLContext->RecordError(
ErrorCode::InvalidOperation,
MakeUnique<GenericErrorInfo>(
"MG_Impl/GLImpl", __func__,
"No program with transform feedback varyings is active."));
return;
}
// Every capture buffer slot the program's mode uses must have a buffer bound. A slot
// of stride 0 - two consecutive gl_NextBuffer entries - captures nothing and so needs
// no binding.
const SizeT usedBufferCount = program->GetTransformFeedbackBufferCount();
for (SizeT i = 0; i < usedBufferCount; ++i) {
if (program->GetTransformFeedbackStride(static_cast<Uint32>(i)) == 0) continue;
const auto& point = MG_State::pGLContext->GetBufferBindingPoint(BufferTarget::TransformFeedback,
static_cast<Uint>(i));
if (point.GetBoundObject() == nullptr) {
MG_State::pGLContext->RecordError(
ErrorCode::InvalidOperation,
MakeUnique<GenericErrorInfo>(
"MG_Impl/GLImpl", __func__,
"Transform feedback buffer binding point " + std::to_string(i) + " has no buffer bound."));
return;
}
}
MG_State::pGLContext->BeginTransformFeedback(primitiveMode, program);
if (const auto beginXfb = MG_Backend::gBackendFunctionsTable.GL.BeginTransformFeedback) {
beginXfb(primitiveMode);
}
}
// Vulkan transform feedback captures triangle strips in plain (i, i+1, i+2)
// vertex order, but GL decomposes odd strip triangles as (i+1, i, i+2)
// (GL 4.6 table 10.1). With the geometry stage's statically-known strip
// lengths the captured records are reordered in place: swap the first two
// vertex records of every odd triangle within each emitted strip.
static void FixupGsStripCaptureOrder(const SharedPtr<MG_State::GLState::ProgramObject>& program,
Uint64 inputPrimitives) {
// Only Vulkan-order captures need this. A backend that runs the capture on its
// own GL/ES driver (it owns the span, hence the EndTransformFeedback entry) has
// already produced GL's vertex order, and reordering it again would corrupt it.
if (MG_Backend::gBackendFunctionsTable.GL.EndTransformFeedback != nullptr) {
return;
}
if (program == nullptr || !program->HasGsTriangleStripCaptureFixup() || inputPrimitives == 0) {
return;
}
const auto& stripTriangles = program->GetGsStripTriangles();
// Global triangle indices whose leading vertex pair must swap.
Vector<Uint64> swapTriangles;
Uint64 triangleBase = 0;
for (Uint64 input = 0; input < inputPrimitives; ++input) {
for (const Uint32 stripLength : stripTriangles) {
for (Uint32 t = 1; t < stripLength; t += 2) {
swapTriangles.push_back(triangleBase + t);
}
triangleBase += stripLength;
}
}
if (swapTriangles.empty()) {
return;
}
for (SizeT bufferIndex = 0; bufferIndex < program->GetTransformFeedbackBufferCount(); ++bufferIndex) {
const Uint32 stride = program->GetTransformFeedbackStride(static_cast<Uint32>(bufferIndex));
if (stride == 0) continue;
const auto& bindingPoint =
MG_State::pGLContext->GetBufferBindingPoint(BufferTarget::TransformFeedback,
static_cast<Uint>(bufferIndex));
const auto& buffer = bindingPoint.GetBoundObject();
if (buffer == nullptr) continue;
const Range1D range = bindingPoint.GetRange();
const Uint8* mapped = buffer->MappedData();
if (mapped == nullptr) continue;
// The geometry stage amplifies, so the CPU vertex counter does not bound
// the capture; the binding range's whole-triangle capacity does.
const Uint64 rangeBytes = range.end > range.start ? static_cast<Uint64>(range.end - range.start) : 0;
const Uint64 capturedTriangles = std::min<Uint64>(triangleBase, (rangeBytes / stride) / 3);
// Observed Vulkan capture order for odd strip triangles is (i, i+2, i+1)
// (winding preserved by swapping the trailing pair); GL wants
// (i+1, i, i+2), which is one rotation away: (a,b,c) -> (c,a,b).
Vector<Uint8> scratch(stride);
for (const Uint64 triangle : swapTriangles) {
if (triangle >= capturedTriangles) break;
const SizeT v0Offset = static_cast<SizeT>(range.start) + static_cast<SizeT>(triangle * 3) * stride;
const SizeT v1Offset = v0Offset + stride;
const SizeT v2Offset = v1Offset + stride;
Memcpy(scratch.data(), mapped + v2Offset, stride);
buffer->WritebackFromBackend({const_cast<Uint8*>(mapped) + v1Offset, stride}, v2Offset);
buffer->WritebackFromBackend({const_cast<Uint8*>(mapped) + v0Offset, stride}, v1Offset);
buffer->WritebackFromBackend({scratch.data(), stride}, v0Offset);
}
}
}
void EndTransformFeedback(void) {
if (!MG_State::pGLContext->IsTransformFeedbackActive()) {
MG_State::pGLContext->RecordError(
ErrorCode::InvalidOperation,
MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", __func__, "Transform feedback is not active."));
return;
}
const auto capturedProgram = MG_State::pGLContext->GetTransformFeedbackProgram();
const Uint64 inputPrimitives = MG_State::pGLContext->GetTransformFeedbackInputPrimitives();
// Closed while the capture state is still active: a backend that captures
// through its own driver reads the capture program and buffer bindings here.
if (const auto endXfb = MG_Backend::gBackendFunctionsTable.GL.EndTransformFeedback) {
endXfb();
}
MG_State::pGLContext->EndTransformFeedback();
// Captured results must be visible to MapBuffer/GetBufferSubData after
// End; the capture targets are host-coherent GPU memory, so completing
// the GPU work is all that is required.
auto& backendGL = MG_Backend::gBackendFunctionsTable.GL;
if (backendGL.FenceSync && backendGL.ClientWaitSync) {
if (auto sync = backendGL.FenceSync()) {
backendGL.ClientWaitSync(sync, GL_SYNC_FLUSH_COMMANDS_BIT, ~0ull);
if (backendGL.DeleteSync) {
backendGL.DeleteSync(sync);
}
}
}
FixupGsStripCaptureOrder(capturedProgram, inputPrimitives);
}
void PauseTransformFeedback(void) {
if (!MG_State::pGLContext->IsTransformFeedbackActive() ||
MG_State::pGLContext->IsTransformFeedbackPaused()) {
MG_State::pGLContext->RecordError(
ErrorCode::InvalidOperation,
MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", __func__,
"Transform feedback is not active, or is already paused."));
return;
}
MG_State::pGLContext->SetTransformFeedbackPaused(true);
if (const auto pauseXfb = MG_Backend::gBackendFunctionsTable.GL.PauseTransformFeedback) {
pauseXfb();
}
}
void ResumeTransformFeedback(void) {
if (!MG_State::pGLContext->IsTransformFeedbackActive() ||
!MG_State::pGLContext->IsTransformFeedbackPaused()) {
MG_State::pGLContext->RecordError(
ErrorCode::InvalidOperation,
MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", __func__, "Transform feedback is not paused."));
return;
}
MG_State::pGLContext->SetTransformFeedbackPaused(false);
if (const auto resumeXfb = MG_Backend::gBackendFunctionsTable.GL.ResumeTransformFeedback) {
resumeXfb();
}
}
void GenTransformFeedbacks(GLsizei n, GLuint* ids) {
if (n < 0) {
MG_State::pGLContext->RecordError(
ErrorCode::InvalidValue,
MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", __func__, "n must be non-negative."));
return;
}
if (n == 0 || ids == nullptr) return;
Vector<Uint> names;
MG_State::pGLContext->GenTransformFeedbackNames(static_cast<Uint>(n), names);
Memcpy(ids, names.data(), static_cast<SizeT>(n) * sizeof(GLuint));
}
void CreateTransformFeedbacks(GLsizei n, GLuint* ids) {
if (n < 0) {
MG_State::pGLContext->RecordError(
ErrorCode::InvalidValue,
MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", __func__, "n must be non-negative."));
return;
}
if (n == 0 || ids == nullptr) return;
Vector<Uint> names;
MG_State::pGLContext->GenTransformFeedbackNames(static_cast<Uint>(n), names);
// Unlike glGenTransformFeedbacks, the names are objects immediately: there is no bind step
// to create them from (GL 4.6 core 13.2.1).
for (const Uint name : names) {
MG_State::pGLContext->CreateTransformFeedbackObject(name);
}
Memcpy(ids, names.data(), static_cast<SizeT>(n) * sizeof(GLuint));
}
namespace {
// Shared front half of the by-name transform feedback entry points: the object has to exist
// (INVALID_OPERATION otherwise) before anything else about the call is looked at.
Bool ValidateNamedTransformFeedback(GLuint xfb, const char* functionName) {
if (!MG_State::pGLContext->IsTransformFeedbackObject(xfb)) {
MG_State::pGLContext->RecordError(
ErrorCode::InvalidOperation,
MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", functionName,
std::to_string(xfb) + " is not a transform feedback object."));
return false;
}
return true;
}
Bool ValidateTransformFeedbackBufferIndex(GLuint index, const char* functionName) {
if (index >= MG_State::GLState::GLContext::MAX_TRANSFORM_FEEDBACK_BUFFERS) {
MG_State::pGLContext->RecordError(
ErrorCode::InvalidValue,
MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", functionName,
"index exceeds GL_MAX_TRANSFORM_FEEDBACK_BUFFERS."));
return false;
}
return true;
}
// A capture binding may not be changed while the object is capturing (GL 4.6 core 13.2.2).
Bool ValidateNamedTransformFeedbackNotActive(GLuint xfb, const char* functionName) {
if (MG_State::pGLContext->IsNamedTransformFeedbackActive(xfb)) {
MG_State::pGLContext->RecordError(
ErrorCode::InvalidOperation,
MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", functionName,
"The transform feedback object is capturing."));
return false;
}
return true;
}
SharedPtr<MG_State::GLState::BufferObject> ResolveTransformFeedbackBuffer(GLuint buffer,
const char* functionName) {
if (buffer == 0) return nullptr;
if (!MG_State::pGLContext->ValidateBufferName(buffer)) {
MG_State::pGLContext->RecordError(
ErrorCode::InvalidOperation,
MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", functionName,
std::to_string(buffer) + " is not a buffer object."));
return nullptr;
}
return MG_State::pGLContext->GetBufferObject(buffer);
}
} // namespace
void TransformFeedbackBufferBase(GLuint xfb, GLuint index, GLuint buffer) {
if (!ValidateNamedTransformFeedback(xfb, __func__)) return;
if (!ValidateTransformFeedbackBufferIndex(index, __func__)) return;
if (!ValidateNamedTransformFeedbackNotActive(xfb, __func__)) return;
if (buffer != 0 && !MG_State::pGLContext->ValidateBufferName(buffer)) {
MG_State::pGLContext->RecordError(
ErrorCode::InvalidOperation,
MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", __func__,
std::to_string(buffer) + " is not a buffer object."));
return;
}
MG_State::pGLContext->SetNamedTransformFeedbackBinding(xfb, index,
ResolveTransformFeedbackBuffer(buffer, __func__), {},
false);
}
void TransformFeedbackBufferRange(GLuint xfb, GLuint index, GLuint buffer, GLintptr offset, GLsizeiptr size) {
if (!ValidateNamedTransformFeedback(xfb, __func__)) return;
if (!ValidateTransformFeedbackBufferIndex(index, __func__)) return;
if (!ValidateNamedTransformFeedbackNotActive(xfb, __func__)) return;
if (offset < 0 || size <= 0 || (offset % 4) != 0 || (size % 4) != 0) {
MG_State::pGLContext->RecordError(
ErrorCode::InvalidValue,
MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", __func__,
"offset and size must be non-negative multiples of 4."));
return;
}
if (buffer != 0 && !MG_State::pGLContext->ValidateBufferName(buffer)) {
MG_State::pGLContext->RecordError(
ErrorCode::InvalidOperation,
MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", __func__,
std::to_string(buffer) + " is not a buffer object."));
return;
}
auto bufferObject = ResolveTransformFeedbackBuffer(buffer, __func__);
const Range1D range{static_cast<SizeT>(offset), static_cast<SizeT>(offset) + static_cast<SizeT>(size)};
MG_State::pGLContext->SetNamedTransformFeedbackBinding(xfb, index, bufferObject, range,
bufferObject != nullptr);
}
void GetTransformFeedbackiv(GLuint xfb, GLenum pname, GLint* param) {
if (!ValidateNamedTransformFeedback(xfb, __func__)) return;
if (!param) return;
switch (pname) {
case GL_TRANSFORM_FEEDBACK_ACTIVE:
*param = MG_State::pGLContext->IsNamedTransformFeedbackActive(xfb) ? GL_TRUE : GL_FALSE;
return;
case GL_TRANSFORM_FEEDBACK_PAUSED:
*param = MG_State::pGLContext->IsNamedTransformFeedbackPaused(xfb) ? GL_TRUE : GL_FALSE;
return;
default:
MG_State::pGLContext->RecordError(
ErrorCode::InvalidEnum,
MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", __func__,
"pname must be GL_TRANSFORM_FEEDBACK_ACTIVE or _PAUSED."));
return;
}
}
void GetTransformFeedbacki_v(GLuint xfb, GLenum pname, GLuint index, GLint* param) {
if (!ValidateNamedTransformFeedback(xfb, __func__)) return;
if (pname != GL_TRANSFORM_FEEDBACK_BUFFER_BINDING) {
MG_State::pGLContext->RecordError(
ErrorCode::InvalidEnum,
MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", __func__,
"pname must be GL_TRANSFORM_FEEDBACK_BUFFER_BINDING."));
return;
}
if (!ValidateTransformFeedbackBufferIndex(index, __func__)) return;
if (!param) return;
const auto binding = MG_State::pGLContext->GetNamedTransformFeedbackBinding(xfb, index);
*param = binding.Buffer ? static_cast<GLint>(binding.Buffer->GetExternalIndex()) : 0;
}
void GetTransformFeedbacki64_v(GLuint xfb, GLenum pname, GLuint index, GLint64* param) {
if (!ValidateNamedTransformFeedback(xfb, __func__)) return;
if (pname != GL_TRANSFORM_FEEDBACK_BUFFER_START && pname != GL_TRANSFORM_FEEDBACK_BUFFER_SIZE) {
MG_State::pGLContext->RecordError(
ErrorCode::InvalidEnum,
MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", __func__,
"pname must be GL_TRANSFORM_FEEDBACK_BUFFER_START or _SIZE."));
return;
}
if (!ValidateTransformFeedbackBufferIndex(index, __func__)) return;
if (!param) return;
const auto binding = MG_State::pGLContext->GetNamedTransformFeedbackBinding(xfb, index);
// glTransformFeedbackBufferBase leaves both at zero; only the range form sets them
// (GL 4.6 core table 23.48).
if (!binding.Buffer || !binding.HasExplicitRange) {
*param = 0;
return;
}
*param = (pname == GL_TRANSFORM_FEEDBACK_BUFFER_START)
? static_cast<GLint64>(binding.Range.start)
: static_cast<GLint64>(binding.Range.end - binding.Range.start);
}
void DeleteTransformFeedbacks(GLsizei n, const GLuint* ids) {
if (n < 0) {
MG_State::pGLContext->RecordError(
ErrorCode::InvalidValue,
MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", __func__, "n must be non-negative."));
return;
}
if (ids == nullptr) return;
for (GLsizei i = 0; i < n; ++i) {
const GLuint id = ids[i];
// Unknown names and 0 are silently ignored; an object whose capture span is
// still open is not (GL 4.6 core 13.2.1).
if (id == 0 || !MG_State::pGLContext->ValidateTransformFeedbackName(id)) continue;
if (id == MG_State::pGLContext->GetBoundTransformFeedbackName() &&
MG_State::pGLContext->IsTransformFeedbackActive()) {
MG_State::pGLContext->RecordError(
ErrorCode::InvalidOperation,
MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", __func__,
"Cannot delete a transform feedback object whose capture is active."));
continue;
}
if (const auto deleteXfb = MG_Backend::gBackendFunctionsTable.GL.DeleteTransformFeedback) {
deleteXfb(id);
}
MG_State::pGLContext->MarkTransformFeedbackObjectForDeletion(id);
}
}
void BindTransformFeedback(GLenum target, GLuint id) {
if (target != GL_TRANSFORM_FEEDBACK) {
MG_State::pGLContext->RecordError(
ErrorCode::InvalidEnum,
MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", __func__, "target must be GL_TRANSFORM_FEEDBACK."));
return;
}
// A running capture pins its object; only a paused one may be swapped out.
if (MG_State::pGLContext->IsTransformFeedbackActive() &&
!MG_State::pGLContext->IsTransformFeedbackPaused()) {
MG_State::pGLContext->RecordError(
ErrorCode::InvalidOperation,
MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", __func__,
"Transform feedback is active and not paused."));
return;
}
if (!MG_State::pGLContext->ValidateTransformFeedbackName(id)) {
MG_State::pGLContext->RecordError(
ErrorCode::InvalidOperation,
MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", __func__,
std::to_string(id) + " is not a transform feedback object name."));
return;
}
MG_State::pGLContext->BindTransformFeedbackObject(id);
if (const auto bindXfb = MG_Backend::gBackendFunctionsTable.GL.BindTransformFeedback) {
bindXfb(id);
}
}
GLboolean IsTransformFeedback(GLuint id) {
// Name 0 is the default object, and a name glGenTransformFeedbacks handed out only
// becomes the name of an object once it has been bound.
return MG_State::pGLContext->IsTransformFeedbackObject(id) ? GL_TRUE : GL_FALSE;
}
// glDrawTransformFeedback[Stream][Instanced]: replays the vertices the named object
// captured in its last completed span, as if by glDrawArraysInstanced with that count
// (GL 4.6 core 10.3.7).
static void DrawTransformFeedbackImpl(const char* functionName, GLenum mode, GLuint id, GLuint stream,
GLsizei instancecount) {
if (!ValidateCurrentProgramForExecution(functionName)) return;
if (!ValidatePrimitiveModeForBackend(functionName, mode)) return;
if (instancecount < 0) {
MG_State::pGLContext->RecordError(
ErrorCode::InvalidValue,
MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", functionName, "instancecount must be non-negative."));
return;
}
if (!MG_State::pGLContext->ValidateTransformFeedbackName(id)) {
MG_State::pGLContext->RecordError(
ErrorCode::InvalidValue,
MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", functionName,
std::to_string(id) + " is not a transform feedback object name."));
return;
}
// GL_MAX_VERTEX_STREAMS is 1, so stream 0 is the only one that exists.
if (stream != 0) {
MG_State::pGLContext->RecordError(
ErrorCode::InvalidValue,
MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", functionName,
"stream must be less than GL_MAX_VERTEX_STREAMS."));
return;
}
// Drawing from an object whose capture is currently open is legal and deliberate:
// it is how a transform feedback result is fed straight back into the next span
// (ARB_transform_feedback2 lists no such restriction).
if (!MG_State::pGLContext->HasTransformFeedbackCompletedSpan(id)) {
MG_State::pGLContext->RecordError(
ErrorCode::InvalidOperation,
MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", functionName,
"glEndTransformFeedback has never been called for this object."));
return;
}
const Uint64 vertices = MG_State::pGLContext->GetTransformFeedbackRecordedVertices(id);
if (vertices == 0) return;
const auto count = static_cast<GLsizei>(vertices);
AccountTransformFeedbackPrimitives(mode, count);
if (instancecount == 1) {
DrawArrays_Backend(mode, 0, count);
} else {
DrawArraysInstanced_Backend(mode, 0, count, instancecount);
}
}
void DrawTransformFeedback(GLenum mode, GLuint id) {
DrawTransformFeedbackImpl(__func__, mode, id, 0, 1);
}
void DrawTransformFeedbackInstanced(GLenum mode, GLuint id, GLsizei instancecount) {
DrawTransformFeedbackImpl(__func__, mode, id, 0, instancecount);
}
void DrawTransformFeedbackStream(GLenum mode, GLuint id, GLuint stream) {
DrawTransformFeedbackImpl(__func__, mode, id, stream, 1);
}
void DrawTransformFeedbackStreamInstanced(GLenum mode, GLuint id, GLuint stream, GLsizei instancecount) {
DrawTransformFeedbackImpl(__func__, mode, id, stream, instancecount);
}
} // namespace MobileGL::MG_Impl::GLImpl
@@ -11,27 +11,8 @@
namespace MobileGL::MG_Impl::GLImpl {
/* @INSERTION_POINT:FUNCTION_DECLARATION@ */
void BeginTransformFeedback(GLenum primitiveMode);
void EndTransformFeedback(void);
void PauseTransformFeedback(void);
void ResumeTransformFeedback(void);
void GenTransformFeedbacks(GLsizei n, GLuint* ids);
void CreateTransformFeedbacks(GLsizei n, GLuint* ids);
void DeleteTransformFeedbacks(GLsizei n, const GLuint* ids);
void TransformFeedbackBufferBase(GLuint xfb, GLuint index, GLuint buffer);
void TransformFeedbackBufferRange(GLuint xfb, GLuint index, GLuint buffer, GLintptr offset, GLsizeiptr size);
void GetTransformFeedbackiv(GLuint xfb, GLenum pname, GLint* param);
void GetTransformFeedbacki_v(GLuint xfb, GLenum pname, GLuint index, GLint* param);
void GetTransformFeedbacki64_v(GLuint xfb, GLenum pname, GLuint index, GLint64* param);
void BindTransformFeedback(GLenum target, GLuint id);
GLboolean IsTransformFeedback(GLuint id);
void DrawTransformFeedback(GLenum mode, GLuint id);
void DrawTransformFeedbackInstanced(GLenum mode, GLuint id, GLsizei instancecount);
void DrawTransformFeedbackStream(GLenum mode, GLuint id, GLuint stream);
void DrawTransformFeedbackStreamInstanced(GLenum mode, GLuint id, GLuint stream, GLsizei instancecount);
void DispatchCompute(GLuint numGroupsX, GLuint numGroupsY, GLuint numGroupsZ);
void DispatchComputeIndirect(GLintptr indirect);
void PatchParameteri(GLenum pname, GLint value);
void MemoryBarrier(GLbitfield barriers);
void MemoryBarrierByRegion(GLbitfield barriers);
void MultiDrawElementsIndirect(GLenum mode, GLenum type, const void* indirect, GLsizei drawcount, GLsizei stride);
+107 -102
View File
@@ -15,7 +15,6 @@
#include "../Texture/GL_Texture.h"
#include "../Drawing/GL_Drawing.h"
#include "../Program/GL_Program.h"
#include "../Program/GL_ProgramPipeline.h"
#include "../RenderState/GL_RenderState.h"
#include "../Framebuffer/GL_Framebuffer.h"
#include "../VertexArray/GL_VertexArray.h"
@@ -237,12 +236,12 @@ DECLARE_GL_FUNCTION_HEAD(void, DeleteVertexArrays, GLsizei n, const GLuint* arra
DECLARE_GL_FUNCTION_HEAD(void, GenVertexArrays, GLsizei n, GLuint* arrays) DECLARE_GL_FUNCTION_END_NO_RETURN(void, GenVertexArrays, n, arrays)
DECLARE_GL_FUNCTION_HEAD(GLboolean, IsVertexArray, GLuint array) DECLARE_GL_FUNCTION_END(GLboolean, IsVertexArray, array)
DECLARE_GL_FUNCTION_HEAD(void, GetIntegeri_v, GLenum target, GLuint index, GLint* data) DECLARE_GL_FUNCTION_END_NO_RETURN(void, GetIntegeri_v, target, index, data)
DECLARE_GL_FUNCTION_HEAD(void, BeginTransformFeedback, GLenum primitiveMode) DECLARE_GL_FUNCTION_END_NO_RETURN(void, BeginTransformFeedback, primitiveMode)
DECLARE_GL_FUNCTION_HEAD(void, EndTransformFeedback) DECLARE_GL_FUNCTION_END_NO_RETURN(void, EndTransformFeedback)
DECLARE_GL_FUNCTION_STUB_HEAD(void, BeginTransformFeedback, GLenum primitiveMode) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, BeginTransformFeedback, primitiveMode)
DECLARE_GL_FUNCTION_STUB_HEAD(void, EndTransformFeedback) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, EndTransformFeedback)
DECLARE_GL_FUNCTION_HEAD(void, BindBufferRange, GLenum target, GLuint index, GLuint buffer, GLintptr offset, GLsizeiptr size) DECLARE_GL_FUNCTION_END_NO_RETURN(void, BindBufferRange, target, index, buffer, offset, size)
DECLARE_GL_FUNCTION_HEAD(void, BindBufferBase, GLenum target, GLuint index, GLuint buffer) DECLARE_GL_FUNCTION_END_NO_RETURN(void, BindBufferBase, target, index, buffer)
DECLARE_GL_FUNCTION_HEAD(void, TransformFeedbackVaryings, GLuint program, GLsizei count, const GLchar* const* varyings, GLenum bufferMode) DECLARE_GL_FUNCTION_END_NO_RETURN(void, TransformFeedbackVaryings, program, count, varyings, bufferMode)
DECLARE_GL_FUNCTION_HEAD(void, GetTransformFeedbackVarying, GLuint program, GLuint index, GLsizei bufSize, GLsizei* length, GLsizei* size, GLenum* type, GLchar* name) DECLARE_GL_FUNCTION_END_NO_RETURN(void, GetTransformFeedbackVarying, program, index, bufSize, length, size, type, name)
DECLARE_GL_FUNCTION_STUB_HEAD(void, TransformFeedbackVaryings, GLuint program, GLsizei count, const GLchar* const* varyings, GLenum bufferMode) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, TransformFeedbackVaryings, program, count, varyings, bufferMode)
DECLARE_GL_FUNCTION_STUB_HEAD(void, GetTransformFeedbackVarying, GLuint program, GLuint index, GLsizei bufSize, GLsizei* length, GLsizei* size, GLenum* type, GLchar* name) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, GetTransformFeedbackVarying, program, index, bufSize, length, size, type, name)
DECLARE_GL_FUNCTION_HEAD(void, VertexAttribIPointer, GLuint index, GLint size, GLenum type, GLsizei stride, const void* pointer) DECLARE_GL_FUNCTION_END_NO_RETURN(void, VertexAttribIPointer, index, size, type, stride, pointer)
DECLARE_GL_FUNCTION_HEAD(void, GetVertexAttribIiv, GLuint index, GLenum pname, GLint* params) DECLARE_GL_FUNCTION_END_NO_RETURN(void, GetVertexAttribIiv, index, pname, params)
DECLARE_GL_FUNCTION_HEAD(void, GetVertexAttribIuiv, GLuint index, GLenum pname, GLuint* params) DECLARE_GL_FUNCTION_END_NO_RETURN(void, GetVertexAttribIuiv, index, pname, params)
@@ -293,17 +292,23 @@ DECLARE_GL_FUNCTION_HEAD(void, SamplerParameterfv, GLuint sampler, GLenum pname,
DECLARE_GL_FUNCTION_HEAD(void, GetSamplerParameteriv, GLuint sampler, GLenum pname, GLint* params) DECLARE_GL_FUNCTION_END_NO_RETURN(void, GetSamplerParameteriv, sampler, pname, params)
DECLARE_GL_FUNCTION_HEAD(void, GetSamplerParameterfv, GLuint sampler, GLenum pname, GLfloat* params) DECLARE_GL_FUNCTION_END_NO_RETURN(void, GetSamplerParameterfv, sampler, pname, params)
DECLARE_GL_FUNCTION_HEAD(void, VertexAttribDivisor, GLuint index, GLuint divisor) DECLARE_GL_FUNCTION_END_NO_RETURN(void, VertexAttribDivisor, index, divisor)
DECLARE_GL_FUNCTION_HEAD(void, BindTransformFeedback, GLenum target, GLuint id) DECLARE_GL_FUNCTION_END_NO_RETURN(void, BindTransformFeedback, target, id)
DECLARE_GL_FUNCTION_HEAD(void, DeleteTransformFeedbacks, GLsizei n, const GLuint* ids) DECLARE_GL_FUNCTION_END_NO_RETURN(void, DeleteTransformFeedbacks, n, ids)
DECLARE_GL_FUNCTION_HEAD(void, GenTransformFeedbacks, GLsizei n, GLuint* ids) DECLARE_GL_FUNCTION_END_NO_RETURN(void, GenTransformFeedbacks, n, ids)
DECLARE_GL_FUNCTION_HEAD(GLboolean, IsTransformFeedback, GLuint id) DECLARE_GL_FUNCTION_END(GLboolean, IsTransformFeedback, id)
DECLARE_GL_FUNCTION_HEAD(void, PauseTransformFeedback) DECLARE_GL_FUNCTION_END_NO_RETURN(void, PauseTransformFeedback)
DECLARE_GL_FUNCTION_HEAD(void, ResumeTransformFeedback) DECLARE_GL_FUNCTION_END_NO_RETURN(void, ResumeTransformFeedback)
DECLARE_GL_FUNCTION_HEAD(void, GetProgramBinary, GLuint program, GLsizei bufSize, GLsizei* length, GLenum* binaryFormat, void* binary) DECLARE_GL_FUNCTION_END_NO_RETURN(void, GetProgramBinary, program, bufSize, length, binaryFormat, binary)
DECLARE_GL_FUNCTION_HEAD(void, ProgramBinary, GLuint program, GLenum binaryFormat, const void* binary, GLsizei length) DECLARE_GL_FUNCTION_END_NO_RETURN(void, ProgramBinary, program, binaryFormat, binary, length)
DECLARE_GL_FUNCTION_HEAD(void, ProgramParameteri, GLuint program, GLenum pname, GLint value) DECLARE_GL_FUNCTION_END_NO_RETURN(void, ProgramParameteri, program, pname, value)
DECLARE_GL_FUNCTION_HEAD(void, InvalidateFramebuffer, GLenum target, GLsizei numAttachments, const GLenum* attachments) DECLARE_GL_FUNCTION_END_NO_RETURN(void, InvalidateFramebuffer, target, numAttachments, attachments)
DECLARE_GL_FUNCTION_HEAD(void, InvalidateSubFramebuffer, GLenum target, GLsizei numAttachments, const GLenum* attachments, GLint x, GLint y, GLsizei width, GLsizei height) DECLARE_GL_FUNCTION_END_NO_RETURN(void, InvalidateSubFramebuffer, target, numAttachments, attachments, x, y, width, height)
DECLARE_GL_FUNCTION_STUB_HEAD(void, BindTransformFeedback, GLenum target, GLuint id) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, BindTransformFeedback, target, id)
DECLARE_GL_FUNCTION_STUB_HEAD(void, DeleteTransformFeedbacks, GLsizei n, const GLuint* ids) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, DeleteTransformFeedbacks, n, ids)
DECLARE_GL_FUNCTION_STUB_HEAD(void, GenTransformFeedbacks, GLsizei n, GLuint* ids) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, GenTransformFeedbacks, n, ids)
// Transform feedback objects are not implemented, so no name is ever a live object. The shared
// stub returns (type)1, telling a probing caller that every id it invents already exists; GL_FALSE
// is both truthful and what the spec requires for a name that was never generated.
MOBILEGL_GL_API GLboolean glIsTransformFeedback(GLuint id) {
MGLOG_W("Stub function: %s(...)", __FUNCTION__);
return GL_FALSE;
}
DECLARE_GL_FUNCTION_STUB_HEAD(void, PauseTransformFeedback) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, PauseTransformFeedback)
DECLARE_GL_FUNCTION_STUB_HEAD(void, ResumeTransformFeedback) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, ResumeTransformFeedback)
DECLARE_GL_FUNCTION_STUB_HEAD(void, GetProgramBinary, GLuint program, GLsizei bufSize, GLsizei* length, GLenum* binaryFormat, void* binary) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, GetProgramBinary, program, bufSize, length, binaryFormat, binary)
DECLARE_GL_FUNCTION_STUB_HEAD(void, ProgramBinary, GLuint program, GLenum binaryFormat, const void* binary, GLsizei length) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, ProgramBinary, program, binaryFormat, binary, length)
DECLARE_GL_FUNCTION_STUB_HEAD(void, ProgramParameteri, GLuint program, GLenum pname, GLint value) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, ProgramParameteri, program, pname, value)
DECLARE_GL_FUNCTION_STUB_HEAD(void, InvalidateFramebuffer, GLenum target, GLsizei numAttachments, const GLenum* attachments) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, InvalidateFramebuffer, target, numAttachments, attachments)
DECLARE_GL_FUNCTION_STUB_HEAD(void, InvalidateSubFramebuffer, GLenum target, GLsizei numAttachments, const GLenum* attachments, GLint x, GLint y, GLsizei width, GLsizei height) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, InvalidateSubFramebuffer, target, numAttachments, attachments, x, y, width, height)
DECLARE_GL_FUNCTION_HEAD(void, TexStorage2D, GLenum target, GLsizei levels, GLenum internalformat, GLsizei width, GLsizei height) DECLARE_GL_FUNCTION_END_NO_RETURN(void, TexStorage2D, target, levels, internalformat, width, height)
DECLARE_GL_FUNCTION_HEAD(void, TexStorage3D, GLenum target, GLsizei levels, GLenum internalformat, GLsizei width, GLsizei height, GLsizei depth) DECLARE_GL_FUNCTION_END_NO_RETURN(void, TexStorage3D, target, levels, internalformat, width, height, depth)
DECLARE_GL_FUNCTION_HEAD(void, GetInternalformativ, GLenum target, GLenum internalformat, GLenum pname, GLsizei bufSize, GLint* params) DECLARE_GL_FUNCTION_END_NO_RETURN(void, GetInternalformativ, target, internalformat, pname, bufSize, params)
@@ -311,21 +316,21 @@ DECLARE_GL_FUNCTION_HEAD(void, DispatchCompute, GLuint num_groups_x, GLuint num_
DECLARE_GL_FUNCTION_HEAD(void, DispatchComputeIndirect, GLintptr indirect) DECLARE_GL_FUNCTION_END_NO_RETURN(void, DispatchComputeIndirect, indirect)
DECLARE_GL_FUNCTION_HEAD(void, DrawArraysIndirect, GLenum mode, const void* indirect) DECLARE_GL_FUNCTION_END_NO_RETURN(void, DrawArraysIndirect, mode, indirect)
DECLARE_GL_FUNCTION_HEAD(void, DrawElementsIndirect, GLenum mode, GLenum type, const void* indirect) DECLARE_GL_FUNCTION_END_NO_RETURN(void, DrawElementsIndirect, mode, type, indirect)
DECLARE_GL_FUNCTION_HEAD(void, FramebufferParameteri, GLenum target, GLenum pname, GLint param) DECLARE_GL_FUNCTION_END_NO_RETURN(void, FramebufferParameteri, target, pname, param)
DECLARE_GL_FUNCTION_HEAD(void, GetFramebufferParameteriv, GLenum target, GLenum pname, GLint* params) DECLARE_GL_FUNCTION_END_NO_RETURN(void, GetFramebufferParameteriv, target, pname, params)
DECLARE_GL_FUNCTION_STUB_HEAD(void, FramebufferParameteri, GLenum target, GLenum pname, GLint param) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, FramebufferParameteri, target, pname, param)
DECLARE_GL_FUNCTION_STUB_HEAD(void, GetFramebufferParameteriv, GLenum target, GLenum pname, GLint* params) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, GetFramebufferParameteriv, target, pname, params)
DECLARE_GL_FUNCTION_HEAD(void, GetProgramInterfaceiv, GLuint program, GLenum programInterface, GLenum pname, GLint* params) DECLARE_GL_FUNCTION_END_NO_RETURN(void, GetProgramInterfaceiv, program, programInterface, pname, params)
DECLARE_GL_FUNCTION_HEAD(GLuint, GetProgramResourceIndex, GLuint program, GLenum programInterface, const GLchar* name) DECLARE_GL_FUNCTION_END(GLuint, GetProgramResourceIndex, program, programInterface, name)
DECLARE_GL_FUNCTION_HEAD(void, GetProgramResourceName, GLuint program, GLenum programInterface, GLuint index, GLsizei bufSize, GLsizei* length, GLchar* name) DECLARE_GL_FUNCTION_END_NO_RETURN(void, GetProgramResourceName, program, programInterface, index, bufSize, length, name)
DECLARE_GL_FUNCTION_HEAD(void, GetProgramResourceiv, GLuint program, GLenum programInterface, GLuint index, GLsizei propCount, const GLenum* props, GLsizei bufSize, GLsizei* length, GLint* params) DECLARE_GL_FUNCTION_END_NO_RETURN(void, GetProgramResourceiv, program, programInterface, index, propCount, props, bufSize, length, params)
DECLARE_GL_FUNCTION_HEAD(GLint, GetProgramResourceLocation, GLuint program, GLenum programInterface, const GLchar* name) DECLARE_GL_FUNCTION_END(GLint, GetProgramResourceLocation, program, programInterface, name)
DECLARE_GL_FUNCTION_HEAD(void, UseProgramStages, GLuint pipeline, GLbitfield stages, GLuint program) DECLARE_GL_FUNCTION_END_NO_RETURN(void, UseProgramStages, pipeline, stages, program)
DECLARE_GL_FUNCTION_HEAD(void, ActiveShaderProgram, GLuint pipeline, GLuint program) DECLARE_GL_FUNCTION_END_NO_RETURN(void, ActiveShaderProgram, pipeline, program)
DECLARE_GL_FUNCTION_HEAD(GLuint, CreateShaderProgramv, GLenum type, GLsizei count, const GLchar* const* strings) DECLARE_GL_FUNCTION_END(GLuint, CreateShaderProgramv, type, count, strings)
DECLARE_GL_FUNCTION_HEAD(void, BindProgramPipeline, GLuint pipeline) DECLARE_GL_FUNCTION_END_NO_RETURN(void, BindProgramPipeline, pipeline)
DECLARE_GL_FUNCTION_HEAD(void, DeleteProgramPipelines, GLsizei n, const GLuint* pipelines) DECLARE_GL_FUNCTION_END_NO_RETURN(void, DeleteProgramPipelines, n, pipelines)
DECLARE_GL_FUNCTION_HEAD(void, GenProgramPipelines, GLsizei n, GLuint* pipelines) DECLARE_GL_FUNCTION_END_NO_RETURN(void, GenProgramPipelines, n, pipelines)
DECLARE_GL_FUNCTION_HEAD(GLboolean, IsProgramPipeline, GLuint pipeline) DECLARE_GL_FUNCTION_END(GLboolean, IsProgramPipeline, pipeline)
DECLARE_GL_FUNCTION_HEAD(void, GetProgramPipelineiv, GLuint pipeline, GLenum pname, GLint* params) DECLARE_GL_FUNCTION_END_NO_RETURN(void, GetProgramPipelineiv, pipeline, pname, params)
DECLARE_GL_FUNCTION_STUB_HEAD(void, UseProgramStages, GLuint pipeline, GLbitfield stages, GLuint program) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, UseProgramStages, pipeline, stages, program)
DECLARE_GL_FUNCTION_STUB_HEAD(void, ActiveShaderProgram, GLuint pipeline, GLuint program) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, ActiveShaderProgram, pipeline, program)
DECLARE_GL_FUNCTION_STUB_HEAD(GLuint, CreateShaderProgramv, GLenum type, GLsizei count, const GLchar* const* strings) DECLARE_GL_FUNCTION_STUB_END(GLuint, CreateShaderProgramv, type, count, strings)
DECLARE_GL_FUNCTION_STUB_HEAD(void, BindProgramPipeline, GLuint pipeline) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, BindProgramPipeline, pipeline)
DECLARE_GL_FUNCTION_STUB_HEAD(void, DeleteProgramPipelines, GLsizei n, const GLuint* pipelines) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, DeleteProgramPipelines, n, pipelines)
DECLARE_GL_FUNCTION_STUB_HEAD(void, GenProgramPipelines, GLsizei n, GLuint* pipelines) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, GenProgramPipelines, n, pipelines)
DECLARE_GL_FUNCTION_STUB_HEAD(GLboolean, IsProgramPipeline, GLuint pipeline) DECLARE_GL_FUNCTION_STUB_END(GLboolean, IsProgramPipeline, pipeline)
DECLARE_GL_FUNCTION_STUB_HEAD(void, GetProgramPipelineiv, GLuint pipeline, GLenum pname, GLint* params) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, GetProgramPipelineiv, pipeline, pname, params)
DECLARE_GL_FUNCTION_HEAD(void, ProgramUniform1i, GLuint program, GLint location, GLint v0) DECLARE_GL_FUNCTION_END_NO_RETURN(void, ProgramUniform1i, program, location, v0)
DECLARE_GL_FUNCTION_HEAD(void, ProgramUniform2i, GLuint program, GLint location, GLint v0, GLint v1) DECLARE_GL_FUNCTION_END_NO_RETURN(void, ProgramUniform2i, program, location, v0, v1)
DECLARE_GL_FUNCTION_HEAD(void, ProgramUniform3i, GLuint program, GLint location, GLint v0, GLint v1, GLint v2) DECLARE_GL_FUNCTION_END_NO_RETURN(void, ProgramUniform3i, program, location, v0, v1, v2)
@@ -359,8 +364,8 @@ DECLARE_GL_FUNCTION_HEAD(void, ProgramUniformMatrix2x4fv, GLuint program, GLint
DECLARE_GL_FUNCTION_HEAD(void, ProgramUniformMatrix4x2fv, GLuint program, GLint location, GLsizei count, GLboolean transpose, const GLfloat* value) DECLARE_GL_FUNCTION_END_NO_RETURN(void, ProgramUniformMatrix4x2fv, program, location, count, transpose, value)
DECLARE_GL_FUNCTION_HEAD(void, ProgramUniformMatrix3x4fv, GLuint program, GLint location, GLsizei count, GLboolean transpose, const GLfloat* value) DECLARE_GL_FUNCTION_END_NO_RETURN(void, ProgramUniformMatrix3x4fv, program, location, count, transpose, value)
DECLARE_GL_FUNCTION_HEAD(void, ProgramUniformMatrix4x3fv, GLuint program, GLint location, GLsizei count, GLboolean transpose, const GLfloat* value) DECLARE_GL_FUNCTION_END_NO_RETURN(void, ProgramUniformMatrix4x3fv, program, location, count, transpose, value)
DECLARE_GL_FUNCTION_HEAD(void, ValidateProgramPipeline, GLuint pipeline) DECLARE_GL_FUNCTION_END_NO_RETURN(void, ValidateProgramPipeline, pipeline)
DECLARE_GL_FUNCTION_HEAD(void, GetProgramPipelineInfoLog, GLuint pipeline, GLsizei bufSize, GLsizei* length, GLchar* infoLog) DECLARE_GL_FUNCTION_END_NO_RETURN(void, GetProgramPipelineInfoLog, pipeline, bufSize, length, infoLog)
DECLARE_GL_FUNCTION_STUB_HEAD(void, ValidateProgramPipeline, GLuint pipeline) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, ValidateProgramPipeline, pipeline)
DECLARE_GL_FUNCTION_STUB_HEAD(void, GetProgramPipelineInfoLog, GLuint pipeline, GLsizei bufSize, GLsizei* length, GLchar* infoLog) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, GetProgramPipelineInfoLog, pipeline, bufSize, length, infoLog)
DECLARE_GL_FUNCTION_HEAD(void, BindImageTexture, GLuint unit, GLuint texture, GLint level, GLboolean layered, GLint layer, GLenum access, GLenum format) DECLARE_GL_FUNCTION_END_NO_RETURN(void, BindImageTexture, unit, texture, level, layered, layer, access, format)
DECLARE_GL_FUNCTION_HEAD(void, GetBooleani_v, GLenum target, GLuint index, GLboolean* data) DECLARE_GL_FUNCTION_END_NO_RETURN(void, GetBooleani_v, target, index, data)
DECLARE_GL_FUNCTION_HEAD(void, MemoryBarrier, GLbitfield barriers) DECLARE_GL_FUNCTION_END_NO_RETURN(void, MemoryBarrier, barriers)
@@ -420,12 +425,12 @@ DECLARE_GL_FUNCTION_HEAD(void, DrawElementsInstancedBaseVertex, GLenum mode, GLs
DECLARE_GL_FUNCTION_HEAD(void, FramebufferTexture, GLenum target, GLenum attachment, GLuint texture, GLint level) DECLARE_GL_FUNCTION_END_NO_RETURN(void, FramebufferTexture, target, attachment, texture, level)
DECLARE_GL_FUNCTION_STUB_HEAD(void, PrimitiveBoundingBox, GLfloat minX, GLfloat minY, GLfloat minZ, GLfloat minW, GLfloat maxX, GLfloat maxY, GLfloat maxZ, GLfloat maxW) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, PrimitiveBoundingBox, minX, minY, minZ, minW, maxX, maxY, maxZ, maxW)
DECLARE_GL_FUNCTION_HEAD(GLenum, GetGraphicsResetStatus) DECLARE_GL_FUNCTION_END(GLenum, GetGraphicsResetStatus)
DECLARE_GL_FUNCTION_HEAD(void, ReadnPixels, GLint x, GLint y, GLsizei width, GLsizei height, GLenum format, GLenum type, GLsizei bufSize, void* data) DECLARE_GL_FUNCTION_END_NO_RETURN(void, ReadnPixels, x, y, width, height, format, type, bufSize, data)
DECLARE_GL_FUNCTION_STUB_HEAD(void, ReadnPixels, GLint x, GLint y, GLsizei width, GLsizei height, GLenum format, GLenum type, GLsizei bufSize, void* data) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, ReadnPixels, x, y, width, height, format, type, bufSize, data)
DECLARE_GL_FUNCTION_STUB_HEAD(void, GetnUniformfv, GLuint program, GLint location, GLsizei bufSize, GLfloat* params) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, GetnUniformfv, program, location, bufSize, params)
DECLARE_GL_FUNCTION_STUB_HEAD(void, GetnUniformiv, GLuint program, GLint location, GLsizei bufSize, GLint* params) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, GetnUniformiv, program, location, bufSize, params)
DECLARE_GL_FUNCTION_STUB_HEAD(void, GetnUniformuiv, GLuint program, GLint location, GLsizei bufSize, GLuint* params) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, GetnUniformuiv, program, location, bufSize, params)
DECLARE_GL_FUNCTION_STUB_HEAD(void, MinSampleShading, GLfloat value) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, MinSampleShading, value)
DECLARE_GL_FUNCTION_HEAD(void, PatchParameteri, GLenum pname, GLint value) DECLARE_GL_FUNCTION_END_NO_RETURN(void, PatchParameteri, pname, value)
DECLARE_GL_FUNCTION_STUB_HEAD(void, PatchParameteri, GLenum pname, GLint value) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, PatchParameteri, pname, value)
DECLARE_GL_FUNCTION_HEAD(void, TexParameterIiv, GLenum target, GLenum pname, const GLint* params) DECLARE_GL_FUNCTION_END_NO_RETURN(void, TexParameterIiv, target, pname, params)
DECLARE_GL_FUNCTION_HEAD(void, TexParameterIuiv, GLenum target, GLenum pname, const GLuint* params) DECLARE_GL_FUNCTION_END_NO_RETURN(void, TexParameterIuiv, target, pname, params)
DECLARE_GL_FUNCTION_HEAD(void, GetTexParameterIiv, GLenum target, GLenum pname, GLint* params) DECLARE_GL_FUNCTION_END_NO_RETURN(void, GetTexParameterIiv, target, pname, params)
@@ -435,7 +440,7 @@ DECLARE_GL_FUNCTION_HEAD(void, SamplerParameterIuiv, GLuint sampler, GLenum pnam
DECLARE_GL_FUNCTION_HEAD(void, GetSamplerParameterIiv, GLuint sampler, GLenum pname, GLint* params) DECLARE_GL_FUNCTION_END_NO_RETURN(void, GetSamplerParameterIiv, sampler, pname, params)
DECLARE_GL_FUNCTION_HEAD(void, GetSamplerParameterIuiv, GLuint sampler, GLenum pname, GLuint* params) DECLARE_GL_FUNCTION_END_NO_RETURN(void, GetSamplerParameterIuiv, sampler, pname, params)
DECLARE_GL_FUNCTION_HEAD(void, TexBuffer, GLenum target, GLenum internalformat, GLuint buffer) DECLARE_GL_FUNCTION_END_NO_RETURN(void, TexBuffer, target, internalformat, buffer)
DECLARE_GL_FUNCTION_HEAD(void, TexBufferRange, GLenum target, GLenum internalformat, GLuint buffer, GLintptr offset, GLsizeiptr size) DECLARE_GL_FUNCTION_END_NO_RETURN(void, TexBufferRange, target, internalformat, buffer, offset, size)
DECLARE_GL_FUNCTION_STUB_HEAD(void, TexBufferRange, GLenum target, GLenum internalformat, GLuint buffer, GLintptr offset, GLsizeiptr size) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, TexBufferRange, target, internalformat, buffer, offset, size)
DECLARE_GL_FUNCTION_HEAD(void, TexStorage3DMultisample, GLenum target, GLsizei samples, GLenum internalformat, GLsizei width, GLsizei height, GLsizei depth, GLboolean fixedsamplelocations) DECLARE_GL_FUNCTION_END_NO_RETURN(void, TexStorage3DMultisample, target, samples, internalformat, width, height, depth, fixedsamplelocations)
DECLARE_GL_FUNCTION_HEAD(void*, MapBufferRange, GLenum target, GLintptr offset, GLsizeiptr length, GLbitfield access) DECLARE_GL_FUNCTION_END(void*, MapBufferRange, target, offset, length, access)
DECLARE_GL_FUNCTION_STUB_HEAD(void, ClearIndex, GLfloat c) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, ClearIndex, c)
@@ -910,24 +915,24 @@ DECLARE_GL_FUNCTION_STUB_HEAD(void, ColorP4ui, GLenum type, GLuint color) DECLAR
DECLARE_GL_FUNCTION_STUB_HEAD(void, ColorP4uiv, GLenum type, const GLuint* color) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, ColorP4uiv, type, color)
DECLARE_GL_FUNCTION_STUB_HEAD(void, SecondaryColorP3ui, GLenum type, GLuint color) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, SecondaryColorP3ui, type, color)
DECLARE_GL_FUNCTION_STUB_HEAD(void, SecondaryColorP3uiv, GLenum type, const GLuint* color) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, SecondaryColorP3uiv, type, color)
DECLARE_GL_FUNCTION_HEAD(void, Uniform1d, GLint location, GLdouble x) DECLARE_GL_FUNCTION_END_NO_RETURN(void, Uniform1d, location, x)
DECLARE_GL_FUNCTION_HEAD(void, Uniform2d, GLint location, GLdouble x, GLdouble y) DECLARE_GL_FUNCTION_END_NO_RETURN(void, Uniform2d, location, x, y)
DECLARE_GL_FUNCTION_HEAD(void, Uniform3d, GLint location, GLdouble x, GLdouble y, GLdouble z) DECLARE_GL_FUNCTION_END_NO_RETURN(void, Uniform3d, location, x, y, z)
DECLARE_GL_FUNCTION_HEAD(void, Uniform4d, GLint location, GLdouble x, GLdouble y, GLdouble z, GLdouble w) DECLARE_GL_FUNCTION_END_NO_RETURN(void, Uniform4d, location, x, y, z, w)
DECLARE_GL_FUNCTION_HEAD(void, Uniform1dv, GLint location, GLsizei count, const GLdouble* value) DECLARE_GL_FUNCTION_END_NO_RETURN(void, Uniform1dv, location, count, value)
DECLARE_GL_FUNCTION_HEAD(void, Uniform2dv, GLint location, GLsizei count, const GLdouble* value) DECLARE_GL_FUNCTION_END_NO_RETURN(void, Uniform2dv, location, count, value)
DECLARE_GL_FUNCTION_HEAD(void, Uniform3dv, GLint location, GLsizei count, const GLdouble* value) DECLARE_GL_FUNCTION_END_NO_RETURN(void, Uniform3dv, location, count, value)
DECLARE_GL_FUNCTION_HEAD(void, Uniform4dv, GLint location, GLsizei count, const GLdouble* value) DECLARE_GL_FUNCTION_END_NO_RETURN(void, Uniform4dv, location, count, value)
DECLARE_GL_FUNCTION_HEAD(void, UniformMatrix2dv, GLint location, GLsizei count, GLboolean transpose, const GLdouble* value) DECLARE_GL_FUNCTION_END_NO_RETURN(void, UniformMatrix2dv, location, count, transpose, value)
DECLARE_GL_FUNCTION_HEAD(void, UniformMatrix3dv, GLint location, GLsizei count, GLboolean transpose, const GLdouble* value) DECLARE_GL_FUNCTION_END_NO_RETURN(void, UniformMatrix3dv, location, count, transpose, value)
DECLARE_GL_FUNCTION_HEAD(void, UniformMatrix4dv, GLint location, GLsizei count, GLboolean transpose, const GLdouble* value) DECLARE_GL_FUNCTION_END_NO_RETURN(void, UniformMatrix4dv, location, count, transpose, value)
DECLARE_GL_FUNCTION_HEAD(void, UniformMatrix2x3dv, GLint location, GLsizei count, GLboolean transpose, const GLdouble* value) DECLARE_GL_FUNCTION_END_NO_RETURN(void, UniformMatrix2x3dv, location, count, transpose, value)
DECLARE_GL_FUNCTION_HEAD(void, UniformMatrix2x4dv, GLint location, GLsizei count, GLboolean transpose, const GLdouble* value) DECLARE_GL_FUNCTION_END_NO_RETURN(void, UniformMatrix2x4dv, location, count, transpose, value)
DECLARE_GL_FUNCTION_HEAD(void, UniformMatrix3x2dv, GLint location, GLsizei count, GLboolean transpose, const GLdouble* value) DECLARE_GL_FUNCTION_END_NO_RETURN(void, UniformMatrix3x2dv, location, count, transpose, value)
DECLARE_GL_FUNCTION_HEAD(void, UniformMatrix3x4dv, GLint location, GLsizei count, GLboolean transpose, const GLdouble* value) DECLARE_GL_FUNCTION_END_NO_RETURN(void, UniformMatrix3x4dv, location, count, transpose, value)
DECLARE_GL_FUNCTION_HEAD(void, UniformMatrix4x2dv, GLint location, GLsizei count, GLboolean transpose, const GLdouble* value) DECLARE_GL_FUNCTION_END_NO_RETURN(void, UniformMatrix4x2dv, location, count, transpose, value)
DECLARE_GL_FUNCTION_HEAD(void, UniformMatrix4x3dv, GLint location, GLsizei count, GLboolean transpose, const GLdouble* value) DECLARE_GL_FUNCTION_END_NO_RETURN(void, UniformMatrix4x3dv, location, count, transpose, value)
DECLARE_GL_FUNCTION_HEAD(void, GetUniformdv, GLuint program, GLint location, GLdouble* params) DECLARE_GL_FUNCTION_END_NO_RETURN(void, GetUniformdv, program, location, params)
DECLARE_GL_FUNCTION_STUB_HEAD(void, Uniform1d, GLint location, GLdouble x) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, Uniform1d, location, x)
DECLARE_GL_FUNCTION_STUB_HEAD(void, Uniform2d, GLint location, GLdouble x, GLdouble y) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, Uniform2d, location, x, y)
DECLARE_GL_FUNCTION_STUB_HEAD(void, Uniform3d, GLint location, GLdouble x, GLdouble y, GLdouble z) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, Uniform3d, location, x, y, z)
DECLARE_GL_FUNCTION_STUB_HEAD(void, Uniform4d, GLint location, GLdouble x, GLdouble y, GLdouble z, GLdouble w) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, Uniform4d, location, x, y, z, w)
DECLARE_GL_FUNCTION_STUB_HEAD(void, Uniform1dv, GLint location, GLsizei count, const GLdouble* value) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, Uniform1dv, location, count, value)
DECLARE_GL_FUNCTION_STUB_HEAD(void, Uniform2dv, GLint location, GLsizei count, const GLdouble* value) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, Uniform2dv, location, count, value)
DECLARE_GL_FUNCTION_STUB_HEAD(void, Uniform3dv, GLint location, GLsizei count, const GLdouble* value) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, Uniform3dv, location, count, value)
DECLARE_GL_FUNCTION_STUB_HEAD(void, Uniform4dv, GLint location, GLsizei count, const GLdouble* value) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, Uniform4dv, location, count, value)
DECLARE_GL_FUNCTION_STUB_HEAD(void, UniformMatrix2dv, GLint location, GLsizei count, GLboolean transpose, const GLdouble* value) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, UniformMatrix2dv, location, count, transpose, value)
DECLARE_GL_FUNCTION_STUB_HEAD(void, UniformMatrix3dv, GLint location, GLsizei count, GLboolean transpose, const GLdouble* value) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, UniformMatrix3dv, location, count, transpose, value)
DECLARE_GL_FUNCTION_STUB_HEAD(void, UniformMatrix4dv, GLint location, GLsizei count, GLboolean transpose, const GLdouble* value) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, UniformMatrix4dv, location, count, transpose, value)
DECLARE_GL_FUNCTION_STUB_HEAD(void, UniformMatrix2x3dv, GLint location, GLsizei count, GLboolean transpose, const GLdouble* value) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, UniformMatrix2x3dv, location, count, transpose, value)
DECLARE_GL_FUNCTION_STUB_HEAD(void, UniformMatrix2x4dv, GLint location, GLsizei count, GLboolean transpose, const GLdouble* value) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, UniformMatrix2x4dv, location, count, transpose, value)
DECLARE_GL_FUNCTION_STUB_HEAD(void, UniformMatrix3x2dv, GLint location, GLsizei count, GLboolean transpose, const GLdouble* value) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, UniformMatrix3x2dv, location, count, transpose, value)
DECLARE_GL_FUNCTION_STUB_HEAD(void, UniformMatrix3x4dv, GLint location, GLsizei count, GLboolean transpose, const GLdouble* value) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, UniformMatrix3x4dv, location, count, transpose, value)
DECLARE_GL_FUNCTION_STUB_HEAD(void, UniformMatrix4x2dv, GLint location, GLsizei count, GLboolean transpose, const GLdouble* value) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, UniformMatrix4x2dv, location, count, transpose, value)
DECLARE_GL_FUNCTION_STUB_HEAD(void, UniformMatrix4x3dv, GLint location, GLsizei count, GLboolean transpose, const GLdouble* value) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, UniformMatrix4x3dv, location, count, transpose, value)
DECLARE_GL_FUNCTION_STUB_HEAD(void, GetUniformdv, GLuint program, GLint location, GLdouble* params) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, GetUniformdv, program, location, params)
DECLARE_GL_FUNCTION_STUB_HEAD(GLint, GetSubroutineUniformLocation, GLuint program, GLenum shadertype, const GLchar* name) DECLARE_GL_FUNCTION_STUB_END(GLint, GetSubroutineUniformLocation, program, shadertype, name)
DECLARE_GL_FUNCTION_STUB_HEAD(GLuint, GetSubroutineIndex, GLuint program, GLenum shadertype, const GLchar* name) DECLARE_GL_FUNCTION_STUB_END(GLuint, GetSubroutineIndex, program, shadertype, name)
DECLARE_GL_FUNCTION_STUB_HEAD(void, GetActiveSubroutineUniformiv, GLuint program, GLenum shadertype, GLuint index, GLenum pname, GLint* values) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, GetActiveSubroutineUniformiv, program, shadertype, index, pname, values)
@@ -937,28 +942,28 @@ DECLARE_GL_FUNCTION_STUB_HEAD(void, UniformSubroutinesuiv, GLenum shadertype, GL
DECLARE_GL_FUNCTION_STUB_HEAD(void, GetUniformSubroutineuiv, GLenum shadertype, GLint location, GLuint* params) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, GetUniformSubroutineuiv, shadertype, location, params)
DECLARE_GL_FUNCTION_STUB_HEAD(void, GetProgramStageiv, GLuint program, GLenum shadertype, GLenum pname, GLint* values) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, GetProgramStageiv, program, shadertype, pname, values)
DECLARE_GL_FUNCTION_STUB_HEAD(void, PatchParameterfv, GLenum pname, const GLfloat* values) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, PatchParameterfv, pname, values)
DECLARE_GL_FUNCTION_HEAD(void, DrawTransformFeedback, GLenum mode, GLuint id) DECLARE_GL_FUNCTION_END_NO_RETURN(void, DrawTransformFeedback, mode, id)
DECLARE_GL_FUNCTION_HEAD(void, DrawTransformFeedbackStream, GLenum mode, GLuint id, GLuint stream) DECLARE_GL_FUNCTION_END_NO_RETURN(void, DrawTransformFeedbackStream, mode, id, stream)
DECLARE_GL_FUNCTION_HEAD(void, BeginQueryIndexed, GLenum target, GLuint index, GLuint id) DECLARE_GL_FUNCTION_END_NO_RETURN(void, BeginQueryIndexed, target, index, id)
DECLARE_GL_FUNCTION_HEAD(void, EndQueryIndexed, GLenum target, GLuint index) DECLARE_GL_FUNCTION_END_NO_RETURN(void, EndQueryIndexed, target, index)
DECLARE_GL_FUNCTION_HEAD(void, GetQueryIndexediv, GLenum target, GLuint index, GLenum pname, GLint* params) DECLARE_GL_FUNCTION_END_NO_RETURN(void, GetQueryIndexediv, target, index, pname, params)
DECLARE_GL_FUNCTION_HEAD(void, ProgramUniform1d, GLuint program, GLint location, GLdouble v0) DECLARE_GL_FUNCTION_END_NO_RETURN(void, ProgramUniform1d, program, location, v0)
DECLARE_GL_FUNCTION_HEAD(void, ProgramUniform1dv, GLuint program, GLint location, GLsizei count, const GLdouble* value) DECLARE_GL_FUNCTION_END_NO_RETURN(void, ProgramUniform1dv, program, location, count, value)
DECLARE_GL_FUNCTION_HEAD(void, ProgramUniform2d, GLuint program, GLint location, GLdouble v0, GLdouble v1) DECLARE_GL_FUNCTION_END_NO_RETURN(void, ProgramUniform2d, program, location, v0, v1)
DECLARE_GL_FUNCTION_HEAD(void, ProgramUniform2dv, GLuint program, GLint location, GLsizei count, const GLdouble* value) DECLARE_GL_FUNCTION_END_NO_RETURN(void, ProgramUniform2dv, program, location, count, value)
DECLARE_GL_FUNCTION_HEAD(void, ProgramUniform3d, GLuint program, GLint location, GLdouble v0, GLdouble v1, GLdouble v2) DECLARE_GL_FUNCTION_END_NO_RETURN(void, ProgramUniform3d, program, location, v0, v1, v2)
DECLARE_GL_FUNCTION_HEAD(void, ProgramUniform3dv, GLuint program, GLint location, GLsizei count, const GLdouble* value) DECLARE_GL_FUNCTION_END_NO_RETURN(void, ProgramUniform3dv, program, location, count, value)
DECLARE_GL_FUNCTION_HEAD(void, ProgramUniform4d, GLuint program, GLint location, GLdouble v0, GLdouble v1, GLdouble v2, GLdouble v3) DECLARE_GL_FUNCTION_END_NO_RETURN(void, ProgramUniform4d, program, location, v0, v1, v2, v3)
DECLARE_GL_FUNCTION_HEAD(void, ProgramUniform4dv, GLuint program, GLint location, GLsizei count, const GLdouble* value) DECLARE_GL_FUNCTION_END_NO_RETURN(void, ProgramUniform4dv, program, location, count, value)
DECLARE_GL_FUNCTION_HEAD(void, ProgramUniformMatrix2dv, GLuint program, GLint location, GLsizei count, GLboolean transpose, const GLdouble* value) DECLARE_GL_FUNCTION_END_NO_RETURN(void, ProgramUniformMatrix2dv, program, location, count, transpose, value)
DECLARE_GL_FUNCTION_HEAD(void, ProgramUniformMatrix3dv, GLuint program, GLint location, GLsizei count, GLboolean transpose, const GLdouble* value) DECLARE_GL_FUNCTION_END_NO_RETURN(void, ProgramUniformMatrix3dv, program, location, count, transpose, value)
DECLARE_GL_FUNCTION_HEAD(void, ProgramUniformMatrix4dv, GLuint program, GLint location, GLsizei count, GLboolean transpose, const GLdouble* value) DECLARE_GL_FUNCTION_END_NO_RETURN(void, ProgramUniformMatrix4dv, program, location, count, transpose, value)
DECLARE_GL_FUNCTION_HEAD(void, ProgramUniformMatrix2x3dv, GLuint program, GLint location, GLsizei count, GLboolean transpose, const GLdouble* value) DECLARE_GL_FUNCTION_END_NO_RETURN(void, ProgramUniformMatrix2x3dv, program, location, count, transpose, value)
DECLARE_GL_FUNCTION_HEAD(void, ProgramUniformMatrix3x2dv, GLuint program, GLint location, GLsizei count, GLboolean transpose, const GLdouble* value) DECLARE_GL_FUNCTION_END_NO_RETURN(void, ProgramUniformMatrix3x2dv, program, location, count, transpose, value)
DECLARE_GL_FUNCTION_HEAD(void, ProgramUniformMatrix2x4dv, GLuint program, GLint location, GLsizei count, GLboolean transpose, const GLdouble* value) DECLARE_GL_FUNCTION_END_NO_RETURN(void, ProgramUniformMatrix2x4dv, program, location, count, transpose, value)
DECLARE_GL_FUNCTION_HEAD(void, ProgramUniformMatrix4x2dv, GLuint program, GLint location, GLsizei count, GLboolean transpose, const GLdouble* value) DECLARE_GL_FUNCTION_END_NO_RETURN(void, ProgramUniformMatrix4x2dv, program, location, count, transpose, value)
DECLARE_GL_FUNCTION_HEAD(void, ProgramUniformMatrix3x4dv, GLuint program, GLint location, GLsizei count, GLboolean transpose, const GLdouble* value) DECLARE_GL_FUNCTION_END_NO_RETURN(void, ProgramUniformMatrix3x4dv, program, location, count, transpose, value)
DECLARE_GL_FUNCTION_HEAD(void, ProgramUniformMatrix4x3dv, GLuint program, GLint location, GLsizei count, GLboolean transpose, const GLdouble* value) DECLARE_GL_FUNCTION_END_NO_RETURN(void, ProgramUniformMatrix4x3dv, program, location, count, transpose, value)
DECLARE_GL_FUNCTION_STUB_HEAD(void, DrawTransformFeedback, GLenum mode, GLuint id) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, DrawTransformFeedback, mode, id)
DECLARE_GL_FUNCTION_STUB_HEAD(void, DrawTransformFeedbackStream, GLenum mode, GLuint id, GLuint stream) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, DrawTransformFeedbackStream, mode, id, stream)
DECLARE_GL_FUNCTION_STUB_HEAD(void, BeginQueryIndexed, GLenum target, GLuint index, GLuint id) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, BeginQueryIndexed, target, index, id)
DECLARE_GL_FUNCTION_STUB_HEAD(void, EndQueryIndexed, GLenum target, GLuint index) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, EndQueryIndexed, target, index)
DECLARE_GL_FUNCTION_STUB_HEAD(void, GetQueryIndexediv, GLenum target, GLuint index, GLenum pname, GLint* params) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, GetQueryIndexediv, target, index, pname, params)
DECLARE_GL_FUNCTION_STUB_HEAD(void, ProgramUniform1d, GLuint program, GLint location, GLdouble v0) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, ProgramUniform1d, program, location, v0)
DECLARE_GL_FUNCTION_STUB_HEAD(void, ProgramUniform1dv, GLuint program, GLint location, GLsizei count, const GLdouble* value) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, ProgramUniform1dv, program, location, count, value)
DECLARE_GL_FUNCTION_STUB_HEAD(void, ProgramUniform2d, GLuint program, GLint location, GLdouble v0, GLdouble v1) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, ProgramUniform2d, program, location, v0, v1)
DECLARE_GL_FUNCTION_STUB_HEAD(void, ProgramUniform2dv, GLuint program, GLint location, GLsizei count, const GLdouble* value) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, ProgramUniform2dv, program, location, count, value)
DECLARE_GL_FUNCTION_STUB_HEAD(void, ProgramUniform3d, GLuint program, GLint location, GLdouble v0, GLdouble v1, GLdouble v2) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, ProgramUniform3d, program, location, v0, v1, v2)
DECLARE_GL_FUNCTION_STUB_HEAD(void, ProgramUniform3dv, GLuint program, GLint location, GLsizei count, const GLdouble* value) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, ProgramUniform3dv, program, location, count, value)
DECLARE_GL_FUNCTION_STUB_HEAD(void, ProgramUniform4d, GLuint program, GLint location, GLdouble v0, GLdouble v1, GLdouble v2, GLdouble v3) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, ProgramUniform4d, program, location, v0, v1, v2, v3)
DECLARE_GL_FUNCTION_STUB_HEAD(void, ProgramUniform4dv, GLuint program, GLint location, GLsizei count, const GLdouble* value) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, ProgramUniform4dv, program, location, count, value)
DECLARE_GL_FUNCTION_STUB_HEAD(void, ProgramUniformMatrix2dv, GLuint program, GLint location, GLsizei count, GLboolean transpose, const GLdouble* value) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, ProgramUniformMatrix2dv, program, location, count, transpose, value)
DECLARE_GL_FUNCTION_STUB_HEAD(void, ProgramUniformMatrix3dv, GLuint program, GLint location, GLsizei count, GLboolean transpose, const GLdouble* value) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, ProgramUniformMatrix3dv, program, location, count, transpose, value)
DECLARE_GL_FUNCTION_STUB_HEAD(void, ProgramUniformMatrix4dv, GLuint program, GLint location, GLsizei count, GLboolean transpose, const GLdouble* value) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, ProgramUniformMatrix4dv, program, location, count, transpose, value)
DECLARE_GL_FUNCTION_STUB_HEAD(void, ProgramUniformMatrix2x3dv, GLuint program, GLint location, GLsizei count, GLboolean transpose, const GLdouble* value) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, ProgramUniformMatrix2x3dv, program, location, count, transpose, value)
DECLARE_GL_FUNCTION_STUB_HEAD(void, ProgramUniformMatrix3x2dv, GLuint program, GLint location, GLsizei count, GLboolean transpose, const GLdouble* value) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, ProgramUniformMatrix3x2dv, program, location, count, transpose, value)
DECLARE_GL_FUNCTION_STUB_HEAD(void, ProgramUniformMatrix2x4dv, GLuint program, GLint location, GLsizei count, GLboolean transpose, const GLdouble* value) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, ProgramUniformMatrix2x4dv, program, location, count, transpose, value)
DECLARE_GL_FUNCTION_STUB_HEAD(void, ProgramUniformMatrix4x2dv, GLuint program, GLint location, GLsizei count, GLboolean transpose, const GLdouble* value) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, ProgramUniformMatrix4x2dv, program, location, count, transpose, value)
DECLARE_GL_FUNCTION_STUB_HEAD(void, ProgramUniformMatrix3x4dv, GLuint program, GLint location, GLsizei count, GLboolean transpose, const GLdouble* value) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, ProgramUniformMatrix3x4dv, program, location, count, transpose, value)
DECLARE_GL_FUNCTION_STUB_HEAD(void, ProgramUniformMatrix4x3dv, GLuint program, GLint location, GLsizei count, GLboolean transpose, const GLdouble* value) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, ProgramUniformMatrix4x3dv, program, location, count, transpose, value)
DECLARE_GL_FUNCTION_STUB_HEAD(void, VertexAttribL1d, GLuint index, GLdouble x) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, VertexAttribL1d, index, x)
DECLARE_GL_FUNCTION_STUB_HEAD(void, VertexAttribL2d, GLuint index, GLdouble x, GLdouble y) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, VertexAttribL2d, index, x, y)
DECLARE_GL_FUNCTION_STUB_HEAD(void, VertexAttribL3d, GLuint index, GLdouble x, GLdouble y, GLdouble z) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, VertexAttribL3d, index, x, y, z)
@@ -983,8 +988,8 @@ DECLARE_GL_FUNCTION_HEAD(void, DrawArraysInstancedBaseInstance, GLenum mode, GLi
DECLARE_GL_FUNCTION_HEAD(void, DrawElementsInstancedBaseInstance, GLenum mode, GLsizei count, GLenum type, const void* indices, GLsizei instancecount, GLuint baseinstance) DECLARE_GL_FUNCTION_END_NO_RETURN(void, DrawElementsInstancedBaseInstance, mode, count, type, indices, instancecount, baseinstance)
DECLARE_GL_FUNCTION_HEAD(void, DrawElementsInstancedBaseVertexBaseInstance, GLenum mode, GLsizei count, GLenum type, const void* indices, GLsizei instancecount, GLint basevertex, GLuint baseinstance) DECLARE_GL_FUNCTION_END_NO_RETURN(void, DrawElementsInstancedBaseVertexBaseInstance, mode, count, type, indices, instancecount, basevertex, baseinstance)
DECLARE_GL_FUNCTION_STUB_HEAD(void, GetActiveAtomicCounterBufferiv, GLuint program, GLuint bufferIndex, GLenum pname, GLint* params) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, GetActiveAtomicCounterBufferiv, program, bufferIndex, pname, params)
DECLARE_GL_FUNCTION_HEAD(void, DrawTransformFeedbackInstanced, GLenum mode, GLuint id, GLsizei instancecount) DECLARE_GL_FUNCTION_END_NO_RETURN(void, DrawTransformFeedbackInstanced, mode, id, instancecount)
DECLARE_GL_FUNCTION_HEAD(void, DrawTransformFeedbackStreamInstanced, GLenum mode, GLuint id, GLuint stream, GLsizei instancecount) DECLARE_GL_FUNCTION_END_NO_RETURN(void, DrawTransformFeedbackStreamInstanced, mode, id, stream, instancecount)
DECLARE_GL_FUNCTION_STUB_HEAD(void, DrawTransformFeedbackInstanced, GLenum mode, GLuint id, GLsizei instancecount) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, DrawTransformFeedbackInstanced, mode, id, instancecount)
DECLARE_GL_FUNCTION_STUB_HEAD(void, DrawTransformFeedbackStreamInstanced, GLenum mode, GLuint id, GLuint stream, GLsizei instancecount) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, DrawTransformFeedbackStreamInstanced, mode, id, stream, instancecount)
DECLARE_GL_FUNCTION_STUB_HEAD(void, ClearBufferData, GLenum target, GLenum internalformat, GLenum format, GLenum type, const void* data) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, ClearBufferData, target, internalformat, format, type, data)
DECLARE_GL_FUNCTION_STUB_HEAD(void, ClearBufferSubData, GLenum target, GLenum internalformat, GLintptr offset, GLsizeiptr size, GLenum format, GLenum type, const void* data) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, ClearBufferSubData, target, internalformat, offset, size, format, type, data)
DECLARE_GL_FUNCTION_STUB_HEAD(void, GetInternalformati64v, GLenum target, GLenum internalformat, GLenum pname, GLsizei count, GLint64* params) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, GetInternalformati64v, target, internalformat, pname, count, params)
@@ -997,7 +1002,7 @@ DECLARE_GL_FUNCTION_HEAD(void, MultiDrawElementsIndirect, GLenum mode, GLenum ty
DECLARE_GL_FUNCTION_HEAD(GLint, GetProgramResourceLocationIndex, GLuint program, GLenum programInterface, const GLchar* name) DECLARE_GL_FUNCTION_END(GLint, GetProgramResourceLocationIndex, program, programInterface, name)
DECLARE_GL_FUNCTION_HEAD(void, ShaderStorageBlockBinding, GLuint program, GLuint storageBlockIndex, GLuint storageBlockBinding) DECLARE_GL_FUNCTION_END_NO_RETURN(void, ShaderStorageBlockBinding, program, storageBlockIndex, storageBlockBinding)
DECLARE_GL_FUNCTION_STUB_HEAD(void, TextureView, GLuint texture, GLenum target, GLuint origtexture, GLenum internalformat, GLuint minlevel, GLuint numlevels, GLuint minlayer, GLuint numlayers) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, TextureView, texture, target, origtexture, internalformat, minlevel, numlevels, minlayer, numlayers)
DECLARE_GL_FUNCTION_HEAD(void, VertexAttribLFormat, GLuint attribindex, GLint size, GLenum type, GLuint relativeoffset) DECLARE_GL_FUNCTION_END_NO_RETURN(void, VertexAttribLFormat, attribindex, size, type, relativeoffset)
DECLARE_GL_FUNCTION_STUB_HEAD(void, VertexAttribLFormat, GLuint attribindex, GLint size, GLenum type, GLuint relativeoffset) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, VertexAttribLFormat, attribindex, size, type, relativeoffset)
DECLARE_GL_FUNCTION_HEAD(void, BufferStorage, GLenum target, GLsizeiptr size, const void* data, GLbitfield flags) DECLARE_GL_FUNCTION_END_NO_RETURN(void, BufferStorage, target, size, data, flags)
DECLARE_GL_FUNCTION_HEAD(void, ClearTexImage, GLuint texture, GLint level, GLenum format, GLenum type, const void* data) DECLARE_GL_FUNCTION_END_NO_RETURN(void, ClearTexImage, texture, level, format, type, data)
DECLARE_GL_FUNCTION_HEAD(void, ClearTexSubImage, GLuint texture, GLint level, GLint xoffset, GLint yoffset, GLint zoffset, GLsizei width, GLsizei height, GLsizei depth, GLenum format, GLenum type, const void* data) DECLARE_GL_FUNCTION_END_NO_RETURN(void, ClearTexSubImage, texture, level, xoffset, yoffset, zoffset, width, height, depth, format, type, data)
@@ -1008,12 +1013,12 @@ DECLARE_GL_FUNCTION_HEAD(void, BindSamplers, GLuint first, GLsizei count, const
DECLARE_GL_FUNCTION_STUB_HEAD(void, BindImageTextures, GLuint first, GLsizei count, const GLuint* textures) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, BindImageTextures, first, count, textures)
DECLARE_GL_FUNCTION_HEAD(void, BindVertexBuffers, GLuint first, GLsizei count, const GLuint* buffers, const GLintptr* offsets, const GLsizei* strides) DECLARE_GL_FUNCTION_END_NO_RETURN(void, BindVertexBuffers, first, count, buffers, offsets, strides)
DECLARE_GL_FUNCTION_STUB_HEAD(void, ClipControl, GLenum origin, GLenum depth) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, ClipControl, origin, depth)
DECLARE_GL_FUNCTION_HEAD(void, CreateTransformFeedbacks, GLsizei n, GLuint* ids) DECLARE_GL_FUNCTION_END_NO_RETURN(void, CreateTransformFeedbacks, n, ids)
DECLARE_GL_FUNCTION_HEAD(void, TransformFeedbackBufferBase, GLuint xfb, GLuint index, GLuint buffer) DECLARE_GL_FUNCTION_END_NO_RETURN(void, TransformFeedbackBufferBase, xfb, index, buffer)
DECLARE_GL_FUNCTION_HEAD(void, TransformFeedbackBufferRange, GLuint xfb, GLuint index, GLuint buffer, GLintptr offset, GLsizeiptr size) DECLARE_GL_FUNCTION_END_NO_RETURN(void, TransformFeedbackBufferRange, xfb, index, buffer, offset, size)
DECLARE_GL_FUNCTION_HEAD(void, GetTransformFeedbackiv, GLuint xfb, GLenum pname, GLint* param) DECLARE_GL_FUNCTION_END_NO_RETURN(void, GetTransformFeedbackiv, xfb, pname, param)
DECLARE_GL_FUNCTION_HEAD(void, GetTransformFeedbacki_v, GLuint xfb, GLenum pname, GLuint index, GLint* param) DECLARE_GL_FUNCTION_END_NO_RETURN(void, GetTransformFeedbacki_v, xfb, pname, index, param)
DECLARE_GL_FUNCTION_HEAD(void, GetTransformFeedbacki64_v, GLuint xfb, GLenum pname, GLuint index, GLint64* param) DECLARE_GL_FUNCTION_END_NO_RETURN(void, GetTransformFeedbacki64_v, xfb, pname, index, param)
DECLARE_GL_FUNCTION_STUB_HEAD(void, CreateTransformFeedbacks, GLsizei n, GLuint* ids) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, CreateTransformFeedbacks, n, ids)
DECLARE_GL_FUNCTION_STUB_HEAD(void, TransformFeedbackBufferBase, GLuint xfb, GLuint index, GLuint buffer) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, TransformFeedbackBufferBase, xfb, index, buffer)
DECLARE_GL_FUNCTION_STUB_HEAD(void, TransformFeedbackBufferRange, GLuint xfb, GLuint index, GLuint buffer, GLintptr offset, GLsizeiptr size) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, TransformFeedbackBufferRange, xfb, index, buffer, offset, size)
DECLARE_GL_FUNCTION_STUB_HEAD(void, GetTransformFeedbackiv, GLuint xfb, GLenum pname, GLint* param) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, GetTransformFeedbackiv, xfb, pname, param)
DECLARE_GL_FUNCTION_STUB_HEAD(void, GetTransformFeedbacki_v, GLuint xfb, GLenum pname, GLuint index, GLint* param) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, GetTransformFeedbacki_v, xfb, pname, index, param)
DECLARE_GL_FUNCTION_STUB_HEAD(void, GetTransformFeedbacki64_v, GLuint xfb, GLenum pname, GLuint index, GLint64* param) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, GetTransformFeedbacki64_v, xfb, pname, index, param)
DECLARE_GL_FUNCTION_HEAD(void, CreateBuffers, GLsizei n, GLuint* buffers) DECLARE_GL_FUNCTION_END_NO_RETURN(void, CreateBuffers, n, buffers)
DECLARE_GL_FUNCTION_HEAD(void, NamedBufferStorage, GLuint buffer, GLsizeiptr size, const void* data, GLbitfield flags) DECLARE_GL_FUNCTION_END_NO_RETURN(void, NamedBufferStorage, buffer, size, data, flags)
DECLARE_GL_FUNCTION_HEAD(void, NamedBufferData, GLuint buffer, GLsizeiptr size, const void* data, GLenum usage) DECLARE_GL_FUNCTION_END_NO_RETURN(void, NamedBufferData, buffer, size, data, usage)
@@ -1026,32 +1031,32 @@ DECLARE_GL_FUNCTION_HEAD(void, FlushMappedNamedBufferRange, GLuint buffer, GLint
DECLARE_GL_FUNCTION_HEAD(void, GetNamedBufferParameteriv, GLuint buffer, GLenum pname, GLint* params) DECLARE_GL_FUNCTION_END_NO_RETURN(void, GetNamedBufferParameteriv, buffer, pname, params)
DECLARE_GL_FUNCTION_HEAD(void, GetNamedBufferParameteri64v, GLuint buffer, GLenum pname, GLint64* params) DECLARE_GL_FUNCTION_END_NO_RETURN(void, GetNamedBufferParameteri64v, buffer, pname, params)
DECLARE_GL_FUNCTION_HEAD(void, GetNamedBufferPointerv, GLuint buffer, GLenum pname, void** params) DECLARE_GL_FUNCTION_END_NO_RETURN(void, GetNamedBufferPointerv, buffer, pname, params)
DECLARE_GL_FUNCTION_HEAD(void, GetNamedBufferSubData, GLuint buffer, GLintptr offset, GLsizeiptr size, void* data) DECLARE_GL_FUNCTION_END_NO_RETURN(void, GetNamedBufferSubData, buffer, offset, size, data)
DECLARE_GL_FUNCTION_STUB_HEAD(void, GetNamedBufferSubData, GLuint buffer, GLintptr offset, GLsizeiptr size, void* data) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, GetNamedBufferSubData, buffer, offset, size, data)
DECLARE_GL_FUNCTION_HEAD(void, CreateFramebuffers, GLsizei n, GLuint* framebuffers) DECLARE_GL_FUNCTION_END_NO_RETURN(void, CreateFramebuffers, n, framebuffers)
DECLARE_GL_FUNCTION_HEAD(void, NamedFramebufferRenderbuffer, GLuint framebuffer, GLenum attachment, GLenum renderbuffertarget, GLuint renderbuffer) DECLARE_GL_FUNCTION_END_NO_RETURN(void, NamedFramebufferRenderbuffer, framebuffer, attachment, renderbuffertarget, renderbuffer)
DECLARE_GL_FUNCTION_HEAD(void, NamedFramebufferParameteri, GLuint framebuffer, GLenum pname, GLint param) DECLARE_GL_FUNCTION_END_NO_RETURN(void, NamedFramebufferParameteri, framebuffer, pname, param)
DECLARE_GL_FUNCTION_STUB_HEAD(void, NamedFramebufferParameteri, GLuint framebuffer, GLenum pname, GLint param) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, NamedFramebufferParameteri, framebuffer, pname, param)
DECLARE_GL_FUNCTION_HEAD(void, NamedFramebufferTexture, GLuint framebuffer, GLenum attachment, GLuint texture, GLint level) DECLARE_GL_FUNCTION_END_NO_RETURN(void, NamedFramebufferTexture, framebuffer, attachment, texture, level)
DECLARE_GL_FUNCTION_HEAD(void, NamedFramebufferTextureLayer, GLuint framebuffer, GLenum attachment, GLuint texture, GLint level, GLint layer) DECLARE_GL_FUNCTION_END_NO_RETURN(void, NamedFramebufferTextureLayer, framebuffer, attachment, texture, level, layer)
DECLARE_GL_FUNCTION_HEAD(void, NamedFramebufferDrawBuffer, GLuint framebuffer, GLenum buf) DECLARE_GL_FUNCTION_END_NO_RETURN(void, NamedFramebufferDrawBuffer, framebuffer, buf)
DECLARE_GL_FUNCTION_HEAD(void, NamedFramebufferDrawBuffers, GLuint framebuffer, GLsizei n, const GLenum* bufs) DECLARE_GL_FUNCTION_END_NO_RETURN(void, NamedFramebufferDrawBuffers, framebuffer, n, bufs)
DECLARE_GL_FUNCTION_HEAD(void, NamedFramebufferReadBuffer, GLuint framebuffer, GLenum src) DECLARE_GL_FUNCTION_END_NO_RETURN(void, NamedFramebufferReadBuffer, framebuffer, src)
DECLARE_GL_FUNCTION_HEAD(void, InvalidateNamedFramebufferData, GLuint framebuffer, GLsizei numAttachments, const GLenum* attachments) DECLARE_GL_FUNCTION_END_NO_RETURN(void, InvalidateNamedFramebufferData, framebuffer, numAttachments, attachments)
DECLARE_GL_FUNCTION_HEAD(void, InvalidateNamedFramebufferSubData, GLuint framebuffer, GLsizei numAttachments, const GLenum* attachments, GLint x, GLint y, GLsizei width, GLsizei height) DECLARE_GL_FUNCTION_END_NO_RETURN(void, InvalidateNamedFramebufferSubData, framebuffer, numAttachments, attachments, x, y, width, height)
DECLARE_GL_FUNCTION_HEAD(void, ClearNamedFramebufferiv, GLuint framebuffer, GLenum buffer, GLint drawbuffer, const GLint* value) DECLARE_GL_FUNCTION_END_NO_RETURN(void, ClearNamedFramebufferiv, framebuffer, buffer, drawbuffer, value)
DECLARE_GL_FUNCTION_HEAD(void, ClearNamedFramebufferuiv, GLuint framebuffer, GLenum buffer, GLint drawbuffer, const GLuint* value) DECLARE_GL_FUNCTION_END_NO_RETURN(void, ClearNamedFramebufferuiv, framebuffer, buffer, drawbuffer, value)
DECLARE_GL_FUNCTION_STUB_HEAD(void, InvalidateNamedFramebufferData, GLuint framebuffer, GLsizei numAttachments, const GLenum* attachments) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, InvalidateNamedFramebufferData, framebuffer, numAttachments, attachments)
DECLARE_GL_FUNCTION_STUB_HEAD(void, InvalidateNamedFramebufferSubData, GLuint framebuffer, GLsizei numAttachments, const GLenum* attachments, GLint x, GLint y, GLsizei width, GLsizei height) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, InvalidateNamedFramebufferSubData, framebuffer, numAttachments, attachments, x, y, width, height)
DECLARE_GL_FUNCTION_STUB_HEAD(void, ClearNamedFramebufferiv, GLuint framebuffer, GLenum buffer, GLint drawbuffer, const GLint* value) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, ClearNamedFramebufferiv, framebuffer, buffer, drawbuffer, value)
DECLARE_GL_FUNCTION_STUB_HEAD(void, ClearNamedFramebufferuiv, GLuint framebuffer, GLenum buffer, GLint drawbuffer, const GLuint* value) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, ClearNamedFramebufferuiv, framebuffer, buffer, drawbuffer, value)
DECLARE_GL_FUNCTION_HEAD(void, ClearNamedFramebufferfv, GLuint framebuffer, GLenum buffer, GLint drawbuffer, const GLfloat* value) DECLARE_GL_FUNCTION_END_NO_RETURN(void, ClearNamedFramebufferfv, framebuffer, buffer, drawbuffer, value)
DECLARE_GL_FUNCTION_HEAD(void, ClearNamedFramebufferfi, GLuint framebuffer, GLenum buffer, GLint drawbuffer, GLfloat depth, GLint stencil) DECLARE_GL_FUNCTION_END_NO_RETURN(void, ClearNamedFramebufferfi, framebuffer, buffer, drawbuffer, depth, stencil)
DECLARE_GL_FUNCTION_HEAD(void, BlitNamedFramebuffer, GLuint readFramebuffer, GLuint drawFramebuffer, GLint srcX0, GLint srcY0, GLint srcX1, GLint srcY1, GLint dstX0, GLint dstY0, GLint dstX1, GLint dstY1, GLbitfield mask, GLenum filter) DECLARE_GL_FUNCTION_END_NO_RETURN(void, BlitNamedFramebuffer, readFramebuffer, drawFramebuffer, srcX0, srcY0, srcX1, srcY1, dstX0, dstY0, dstX1, dstY1, mask, filter)
DECLARE_GL_FUNCTION_HEAD(GLenum, CheckNamedFramebufferStatus, GLuint framebuffer, GLenum target) DECLARE_GL_FUNCTION_END(GLenum, CheckNamedFramebufferStatus, framebuffer, target)
DECLARE_GL_FUNCTION_HEAD(void, GetNamedFramebufferParameteriv, GLuint framebuffer, GLenum pname, GLint* param) DECLARE_GL_FUNCTION_END_NO_RETURN(void, GetNamedFramebufferParameteriv, framebuffer, pname, param)
DECLARE_GL_FUNCTION_STUB_HEAD(void, GetNamedFramebufferParameteriv, GLuint framebuffer, GLenum pname, GLint* param) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, GetNamedFramebufferParameteriv, framebuffer, pname, param)
DECLARE_GL_FUNCTION_HEAD(void, GetNamedFramebufferAttachmentParameteriv, GLuint framebuffer, GLenum attachment, GLenum pname, GLint* params) DECLARE_GL_FUNCTION_END_NO_RETURN(void, GetNamedFramebufferAttachmentParameteriv, framebuffer, attachment, pname, params)
DECLARE_GL_FUNCTION_HEAD(void, CreateRenderbuffers, GLsizei n, GLuint* renderbuffers) DECLARE_GL_FUNCTION_END_NO_RETURN(void, CreateRenderbuffers, n, renderbuffers)
DECLARE_GL_FUNCTION_HEAD(void, NamedRenderbufferStorage, GLuint renderbuffer, GLenum internalformat, GLsizei width, GLsizei height) DECLARE_GL_FUNCTION_END_NO_RETURN(void, NamedRenderbufferStorage, renderbuffer, internalformat, width, height)
DECLARE_GL_FUNCTION_HEAD(void, NamedRenderbufferStorageMultisample, GLuint renderbuffer, GLsizei samples, GLenum internalformat, GLsizei width, GLsizei height) DECLARE_GL_FUNCTION_END_NO_RETURN(void, NamedRenderbufferStorageMultisample, renderbuffer, samples, internalformat, width, height)
DECLARE_GL_FUNCTION_HEAD(void, GetNamedRenderbufferParameteriv, GLuint renderbuffer, GLenum pname, GLint* params) DECLARE_GL_FUNCTION_END_NO_RETURN(void, GetNamedRenderbufferParameteriv, renderbuffer, pname, params)
DECLARE_GL_FUNCTION_HEAD(void, CreateTextures, GLenum target, GLsizei n, GLuint* textures) DECLARE_GL_FUNCTION_END_NO_RETURN(void, CreateTextures, target, n, textures)
DECLARE_GL_FUNCTION_HEAD(void, TextureBuffer, GLuint texture, GLenum internalformat, GLuint buffer) DECLARE_GL_FUNCTION_END_NO_RETURN(void, TextureBuffer, texture, internalformat, buffer)
DECLARE_GL_FUNCTION_HEAD(void, TextureBufferRange, GLuint texture, GLenum internalformat, GLuint buffer, GLintptr offset, GLsizeiptr size) DECLARE_GL_FUNCTION_END_NO_RETURN(void, TextureBufferRange, texture, internalformat, buffer, offset, size)
DECLARE_GL_FUNCTION_STUB_HEAD(void, TextureBuffer, GLuint texture, GLenum internalformat, GLuint buffer) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, TextureBuffer, texture, internalformat, buffer)
DECLARE_GL_FUNCTION_STUB_HEAD(void, TextureBufferRange, GLuint texture, GLenum internalformat, GLuint buffer, GLintptr offset, GLsizeiptr size) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, TextureBufferRange, texture, internalformat, buffer, offset, size)
DECLARE_GL_FUNCTION_HEAD(void, TextureStorage1D, GLuint texture, GLsizei levels, GLenum internalformat, GLsizei width) DECLARE_GL_FUNCTION_END_NO_RETURN(void, TextureStorage1D, texture, levels, internalformat, width)
DECLARE_GL_FUNCTION_HEAD(void, TextureStorage2D, GLuint texture, GLsizei levels, GLenum internalformat, GLsizei width, GLsizei height) DECLARE_GL_FUNCTION_END_NO_RETURN(void, TextureStorage2D, texture, levels, internalformat, width, height)
DECLARE_GL_FUNCTION_HEAD(void, TextureStorage3D, GLuint texture, GLsizei levels, GLenum internalformat, GLsizei width, GLsizei height, GLsizei depth) DECLARE_GL_FUNCTION_END_NO_RETURN(void, TextureStorage3D, texture, levels, internalformat, width, height, depth)
@@ -1063,9 +1068,9 @@ DECLARE_GL_FUNCTION_HEAD(void, TextureSubImage3D, GLuint texture, GLint level, G
DECLARE_GL_FUNCTION_STUB_HEAD(void, CompressedTextureSubImage1D, GLuint texture, GLint level, GLint xoffset, GLsizei width, GLenum format, GLsizei imageSize, const void* data) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, CompressedTextureSubImage1D, texture, level, xoffset, width, format, imageSize, data)
DECLARE_GL_FUNCTION_STUB_HEAD(void, CompressedTextureSubImage2D, GLuint texture, GLint level, GLint xoffset, GLint yoffset, GLsizei width, GLsizei height, GLenum format, GLsizei imageSize, const void* data) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, CompressedTextureSubImage2D, texture, level, xoffset, yoffset, width, height, format, imageSize, data)
DECLARE_GL_FUNCTION_STUB_HEAD(void, CompressedTextureSubImage3D, GLuint texture, GLint level, GLint xoffset, GLint yoffset, GLint zoffset, GLsizei width, GLsizei height, GLsizei depth, GLenum format, GLsizei imageSize, const void* data) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, CompressedTextureSubImage3D, texture, level, xoffset, yoffset, zoffset, width, height, depth, format, imageSize, data)
DECLARE_GL_FUNCTION_HEAD(void, CopyTextureSubImage1D, GLuint texture, GLint level, GLint xoffset, GLint x, GLint y, GLsizei width) DECLARE_GL_FUNCTION_END_NO_RETURN(void, CopyTextureSubImage1D, texture, level, xoffset, x, y, width)
DECLARE_GL_FUNCTION_STUB_HEAD(void, CopyTextureSubImage1D, GLuint texture, GLint level, GLint xoffset, GLint x, GLint y, GLsizei width) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, CopyTextureSubImage1D, texture, level, xoffset, x, y, width)
DECLARE_GL_FUNCTION_HEAD(void, CopyTextureSubImage2D, GLuint texture, GLint level, GLint xoffset, GLint yoffset, GLint x, GLint y, GLsizei width, GLsizei height) DECLARE_GL_FUNCTION_END_NO_RETURN(void, CopyTextureSubImage2D, texture, level, xoffset, yoffset, x, y, width, height)
DECLARE_GL_FUNCTION_HEAD(void, CopyTextureSubImage3D, GLuint texture, GLint level, GLint xoffset, GLint yoffset, GLint zoffset, GLint x, GLint y, GLsizei width, GLsizei height) DECLARE_GL_FUNCTION_END_NO_RETURN(void, CopyTextureSubImage3D, texture, level, xoffset, yoffset, zoffset, x, y, width, height)
DECLARE_GL_FUNCTION_STUB_HEAD(void, CopyTextureSubImage3D, GLuint texture, GLint level, GLint xoffset, GLint yoffset, GLint zoffset, GLint x, GLint y, GLsizei width, GLsizei height) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, CopyTextureSubImage3D, texture, level, xoffset, yoffset, zoffset, x, y, width, height)
DECLARE_GL_FUNCTION_HEAD(void, TextureParameterf, GLuint texture, GLenum pname, GLfloat param) DECLARE_GL_FUNCTION_END_NO_RETURN(void, TextureParameterf, texture, pname, param)
DECLARE_GL_FUNCTION_HEAD(void, TextureParameterfv, GLuint texture, GLenum pname, const GLfloat* param) DECLARE_GL_FUNCTION_END_NO_RETURN(void, TextureParameterfv, texture, pname, param)
DECLARE_GL_FUNCTION_HEAD(void, TextureParameteri, GLuint texture, GLenum pname, GLint param) DECLARE_GL_FUNCTION_END_NO_RETURN(void, TextureParameteri, texture, pname, param)
@@ -1075,7 +1080,7 @@ DECLARE_GL_FUNCTION_HEAD(void, TextureParameteriv, GLuint texture, GLenum pname,
DECLARE_GL_FUNCTION_HEAD(void, GenerateTextureMipmap, GLuint texture) DECLARE_GL_FUNCTION_END_NO_RETURN(void, GenerateTextureMipmap, texture)
DECLARE_GL_FUNCTION_HEAD(void, BindTextureUnit, GLuint unit, GLuint texture) DECLARE_GL_FUNCTION_END_NO_RETURN(void, BindTextureUnit, unit, texture)
DECLARE_GL_FUNCTION_HEAD(void, GetTextureImage, GLuint texture, GLint level, GLenum format, GLenum type, GLsizei bufSize, void* pixels) DECLARE_GL_FUNCTION_END_NO_RETURN(void, GetTextureImage, texture, level, format, type, bufSize, pixels)
DECLARE_GL_FUNCTION_HEAD(void, GetCompressedTextureImage, GLuint texture, GLint level, GLsizei bufSize, void* pixels) DECLARE_GL_FUNCTION_END_NO_RETURN(void, GetCompressedTextureImage, texture, level, bufSize, pixels)
DECLARE_GL_FUNCTION_STUB_HEAD(void, GetCompressedTextureImage, GLuint texture, GLint level, GLsizei bufSize, void* pixels) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, GetCompressedTextureImage, texture, level, bufSize, pixels)
DECLARE_GL_FUNCTION_HEAD(void, GetTextureLevelParameterfv, GLuint texture, GLint level, GLenum pname, GLfloat* params) DECLARE_GL_FUNCTION_END_NO_RETURN(void, GetTextureLevelParameterfv, texture, level, pname, params)
DECLARE_GL_FUNCTION_HEAD(void, GetTextureLevelParameteriv, GLuint texture, GLint level, GLenum pname, GLint* params) DECLARE_GL_FUNCTION_END_NO_RETURN(void, GetTextureLevelParameteriv, texture, level, pname, params)
DECLARE_GL_FUNCTION_HEAD(void, GetTextureParameterfv, GLuint texture, GLenum pname, GLfloat* params) DECLARE_GL_FUNCTION_END_NO_RETURN(void, GetTextureParameterfv, texture, pname, params)
@@ -1091,18 +1096,18 @@ DECLARE_GL_FUNCTION_HEAD(void, VertexArrayVertexBuffers, GLuint vaobj, GLuint fi
DECLARE_GL_FUNCTION_HEAD(void, VertexArrayAttribBinding, GLuint vaobj, GLuint attribindex, GLuint bindingindex) DECLARE_GL_FUNCTION_END_NO_RETURN(void, VertexArrayAttribBinding, vaobj, attribindex, bindingindex)
DECLARE_GL_FUNCTION_HEAD(void, VertexArrayAttribFormat, GLuint vaobj, GLuint attribindex, GLint size, GLenum type, GLboolean normalized, GLuint relativeoffset) DECLARE_GL_FUNCTION_END_NO_RETURN(void, VertexArrayAttribFormat, vaobj, attribindex, size, type, normalized, relativeoffset)
DECLARE_GL_FUNCTION_HEAD(void, VertexArrayAttribIFormat, GLuint vaobj, GLuint attribindex, GLint size, GLenum type, GLuint relativeoffset) DECLARE_GL_FUNCTION_END_NO_RETURN(void, VertexArrayAttribIFormat, vaobj, attribindex, size, type, relativeoffset)
DECLARE_GL_FUNCTION_HEAD(void, VertexArrayAttribLFormat, GLuint vaobj, GLuint attribindex, GLint size, GLenum type, GLuint relativeoffset) DECLARE_GL_FUNCTION_END_NO_RETURN(void, VertexArrayAttribLFormat, vaobj, attribindex, size, type, relativeoffset)
DECLARE_GL_FUNCTION_STUB_HEAD(void, VertexArrayAttribLFormat, GLuint vaobj, GLuint attribindex, GLint size, GLenum type, GLuint relativeoffset) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, VertexArrayAttribLFormat, vaobj, attribindex, size, type, relativeoffset)
DECLARE_GL_FUNCTION_HEAD(void, VertexArrayBindingDivisor, GLuint vaobj, GLuint bindingindex, GLuint divisor) DECLARE_GL_FUNCTION_END_NO_RETURN(void, VertexArrayBindingDivisor, vaobj, bindingindex, divisor)
DECLARE_GL_FUNCTION_HEAD(void, GetVertexArrayiv, GLuint vaobj, GLenum pname, GLint* param) DECLARE_GL_FUNCTION_END_NO_RETURN(void, GetVertexArrayiv, vaobj, pname, param)
DECLARE_GL_FUNCTION_HEAD(void, GetVertexArrayIndexediv, GLuint vaobj, GLuint index, GLenum pname, GLint* param) DECLARE_GL_FUNCTION_END_NO_RETURN(void, GetVertexArrayIndexediv, vaobj, index, pname, param)
DECLARE_GL_FUNCTION_HEAD(void, GetVertexArrayIndexed64iv, GLuint vaobj, GLuint index, GLenum pname, GLint64* param) DECLARE_GL_FUNCTION_END_NO_RETURN(void, GetVertexArrayIndexed64iv, vaobj, index, pname, param)
DECLARE_GL_FUNCTION_STUB_HEAD(void, GetVertexArrayiv, GLuint vaobj, GLenum pname, GLint* param) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, GetVertexArrayiv, vaobj, pname, param)
DECLARE_GL_FUNCTION_STUB_HEAD(void, GetVertexArrayIndexediv, GLuint vaobj, GLuint index, GLenum pname, GLint* param) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, GetVertexArrayIndexediv, vaobj, index, pname, param)
DECLARE_GL_FUNCTION_STUB_HEAD(void, GetVertexArrayIndexed64iv, GLuint vaobj, GLuint index, GLenum pname, GLint64* param) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, GetVertexArrayIndexed64iv, vaobj, index, pname, param)
DECLARE_GL_FUNCTION_HEAD(void, CreateSamplers, GLsizei n, GLuint* samplers) DECLARE_GL_FUNCTION_END_NO_RETURN(void, CreateSamplers, n, samplers)
DECLARE_GL_FUNCTION_HEAD(void, CreateProgramPipelines, GLsizei n, GLuint* pipelines) DECLARE_GL_FUNCTION_END_NO_RETURN(void, CreateProgramPipelines, n, pipelines)
DECLARE_GL_FUNCTION_HEAD(void, CreateQueries, GLenum target, GLsizei n, GLuint* ids) DECLARE_GL_FUNCTION_END_NO_RETURN(void, CreateQueries, target, n, ids)
DECLARE_GL_FUNCTION_HEAD(void, GetQueryBufferObjecti64v, GLuint id, GLuint buffer, GLenum pname, GLintptr offset) DECLARE_GL_FUNCTION_END_NO_RETURN(void, GetQueryBufferObjecti64v, id, buffer, pname, offset)
DECLARE_GL_FUNCTION_HEAD(void, GetQueryBufferObjectiv, GLuint id, GLuint buffer, GLenum pname, GLintptr offset) DECLARE_GL_FUNCTION_END_NO_RETURN(void, GetQueryBufferObjectiv, id, buffer, pname, offset)
DECLARE_GL_FUNCTION_HEAD(void, GetQueryBufferObjectui64v, GLuint id, GLuint buffer, GLenum pname, GLintptr offset) DECLARE_GL_FUNCTION_END_NO_RETURN(void, GetQueryBufferObjectui64v, id, buffer, pname, offset)
DECLARE_GL_FUNCTION_HEAD(void, GetQueryBufferObjectuiv, GLuint id, GLuint buffer, GLenum pname, GLintptr offset) DECLARE_GL_FUNCTION_END_NO_RETURN(void, GetQueryBufferObjectuiv, id, buffer, pname, offset)
DECLARE_GL_FUNCTION_STUB_HEAD(void, CreateProgramPipelines, GLsizei n, GLuint* pipelines) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, CreateProgramPipelines, n, pipelines)
DECLARE_GL_FUNCTION_STUB_HEAD(void, CreateQueries, GLenum target, GLsizei n, GLuint* ids) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, CreateQueries, target, n, ids)
DECLARE_GL_FUNCTION_STUB_HEAD(void, GetQueryBufferObjecti64v, GLuint id, GLuint buffer, GLenum pname, GLintptr offset) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, GetQueryBufferObjecti64v, id, buffer, pname, offset)
DECLARE_GL_FUNCTION_STUB_HEAD(void, GetQueryBufferObjectiv, GLuint id, GLuint buffer, GLenum pname, GLintptr offset) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, GetQueryBufferObjectiv, id, buffer, pname, offset)
DECLARE_GL_FUNCTION_STUB_HEAD(void, GetQueryBufferObjectui64v, GLuint id, GLuint buffer, GLenum pname, GLintptr offset) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, GetQueryBufferObjectui64v, id, buffer, pname, offset)
DECLARE_GL_FUNCTION_STUB_HEAD(void, GetQueryBufferObjectuiv, GLuint id, GLuint buffer, GLenum pname, GLintptr offset) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, GetQueryBufferObjectuiv, id, buffer, pname, offset)
DECLARE_GL_FUNCTION_HEAD(void, GetTextureSubImage, GLuint texture, GLint level, GLint xoffset, GLint yoffset, GLint zoffset, GLsizei width, GLsizei height, GLsizei depth, GLenum format, GLenum type, GLsizei bufSize, void* pixels) DECLARE_GL_FUNCTION_END_NO_RETURN(void, GetTextureSubImage, texture, level, xoffset, yoffset, zoffset, width, height, depth, format, type, bufSize, pixels)
DECLARE_GL_FUNCTION_STUB_HEAD(void, GetCompressedTextureSubImage, GLuint texture, GLint level, GLint xoffset, GLint yoffset, GLint zoffset, GLsizei width, GLsizei height, GLsizei depth, GLsizei bufSize, void* pixels) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, GetCompressedTextureSubImage, texture, level, xoffset, yoffset, zoffset, width, height, depth, bufSize, pixels)
DECLARE_GL_FUNCTION_STUB_HEAD(void, GetnCompressedTexImage, GLenum target, GLint lod, GLsizei bufSize, void* pixels) DECLARE_GL_FUNCTION_STUB_END_NO_RETURN(void, GetnCompressedTexImage, target, lod, bufSize, pixels)
File diff suppressed because it is too large Load Diff
@@ -14,8 +14,6 @@
namespace MobileGL::MG_Impl::GLImpl {
/* @INSERTION_POINT:FUNCTION_DECLARATION@ */
void ReadPixels(GLint x, GLint y, GLsizei width, GLsizei height, GLenum format, GLenum type, void* pixels);
void ReadnPixels(GLint x, GLint y, GLsizei width, GLsizei height, GLenum format, GLenum type, GLsizei bufSize,
void* data);
void ClearBufferfi(GLenum buffer, GLint drawbuffer, GLfloat depth, GLint stencil);
void ClearBufferfv(GLenum buffer, GLint drawbuffer, const GLfloat* value);
void ClearBufferuiv(GLenum buffer, GLint drawbuffer, const GLuint* value);
@@ -58,19 +56,7 @@ namespace MobileGL::MG_Impl::GLImpl {
void NamedFramebufferReadBuffer(GLuint framebuffer, GLenum src);
void ClearNamedFramebufferfv(GLuint framebuffer, GLenum buffer, GLint drawbuffer, const GLfloat* value);
void ClearNamedFramebufferfi(GLuint framebuffer, GLenum buffer, GLint drawbuffer, GLfloat depth, GLint stencil);
void InvalidateNamedFramebufferData(GLuint framebuffer, GLsizei numAttachments, const GLenum* attachments);
void InvalidateNamedFramebufferSubData(GLuint framebuffer, GLsizei numAttachments, const GLenum* attachments,
GLint x, GLint y, GLsizei width, GLsizei height);
void InvalidateFramebuffer(GLenum target, GLsizei numAttachments, const GLenum* attachments);
void InvalidateSubFramebuffer(GLenum target, GLsizei numAttachments, const GLenum* attachments, GLint x, GLint y,
GLsizei width, GLsizei height);
void ClearNamedFramebufferiv(GLuint framebuffer, GLenum buffer, GLint drawbuffer, const GLint* value);
void ClearNamedFramebufferuiv(GLuint framebuffer, GLenum buffer, GLint drawbuffer, const GLuint* value);
GLenum CheckNamedFramebufferStatus(GLuint framebuffer, GLenum target);
void GetFramebufferParameteriv(GLenum target, GLenum pname, GLint* params);
void FramebufferParameteri(GLenum target, GLenum pname, GLint param);
void GetNamedFramebufferParameteriv(GLuint framebuffer, GLenum pname, GLint* params);
void NamedFramebufferParameteri(GLuint framebuffer, GLenum pname, GLint param);
void GetNamedFramebufferAttachmentParameteriv(GLuint framebuffer, GLenum attachment, GLenum pname, GLint* params);
void BlitNamedFramebuffer(GLuint readFramebuffer, GLuint drawFramebuffer, GLint srcX0, GLint srcY0, GLint srcX1,
GLint srcY1, GLint dstX0, GLint dstY0, GLint dstX1, GLint dstY1, GLbitfield mask,
@@ -7,7 +7,6 @@
// End of Source File Header
#include "Validators.h"
#include <MG_Backend/BackendObjects.h>
#include <MG_State/GLState/Core.h>
#include <MG_State/GLState/ErrorState/Error.h>
#include <MG_Util/Converters/GLToStr/GLEnumConverter.h>
@@ -61,26 +60,6 @@ namespace MobileGL::MG_Impl::GLImpl::FramebufferImpl {
return true;
}
Bool ValidateColorAttachmentInRange(FramebufferAttachmentType attachment, const char* caller) {
const auto first = static_cast<SizeT>(FramebufferAttachmentType::Color0);
const auto index = static_cast<SizeT>(attachment);
if (index < first) return true;
const auto colorIndex = index - first;
const auto limit = static_cast<SizeT>(
MG_Backend::pActiveBackendObject ? MG_Backend::pActiveBackendObject->GetDynamicParameters()
.MaxColorAttachments
: static_cast<Int>(MG_State::GLState::FramebufferObject::MAX_DRAW_BUFFERS));
if (colorIndex >= limit) {
MG_State::pGLContext->RecordError(
ErrorCode::InvalidOperation,
MakeUnique<GenericErrorInfo>(
"MG_Impl/GLImpl/FramebufferImpl", caller,
std::format("Colour attachment {} is beyond GL_MAX_COLOR_ATTACHMENTS ({}).", colorIndex, limit)));
return false;
}
return true;
}
Bool ValidateRenderbufferTarget(RenderbufferTarget target) {
if (target == RenderbufferTarget::Unknown) {
using namespace MG_Util;
@@ -118,100 +97,4 @@ namespace MobileGL::MG_Impl::GLImpl::FramebufferImpl {
std::format("Renderbuffer name {} is not valid.", index)));
return false;
}
Bool ValidateFramebufferParameterPname(GLenum pname, Bool isDefaultFramebuffer, Bool forSetter,
const char* caller) {
Bool isDefaultParameter = false;
switch (pname) {
case GL_FRAMEBUFFER_DEFAULT_WIDTH:
case GL_FRAMEBUFFER_DEFAULT_HEIGHT:
case GL_FRAMEBUFFER_DEFAULT_LAYERS:
case GL_FRAMEBUFFER_DEFAULT_SAMPLES:
case GL_FRAMEBUFFER_DEFAULT_FIXED_SAMPLE_LOCATIONS:
isDefaultParameter = true;
break;
case GL_DOUBLEBUFFER:
case GL_IMPLEMENTATION_COLOR_READ_FORMAT:
case GL_IMPLEMENTATION_COLOR_READ_TYPE:
case GL_SAMPLES:
case GL_SAMPLE_BUFFERS:
case GL_STEREO:
// Queryable only; glFramebufferParameteri sets none of these.
if (forSetter) {
MG_State::pGLContext->RecordError(
ErrorCode::InvalidEnum,
MakeUnique<GenericErrorInfo>(
"MG_Impl/GLImpl/FramebufferImpl", caller,
std::format("pname {} is not settable on a framebuffer.",
MG_Util::ConvertGLEnumToString(pname))));
return false;
}
break;
default:
MG_State::pGLContext->RecordError(
ErrorCode::InvalidEnum,
MakeUnique<GenericErrorInfo>(
"MG_Impl/GLImpl/FramebufferImpl", caller,
std::format("pname {} is not a framebuffer parameter.",
MG_Util::ConvertGLEnumToString(pname))));
return false;
}
// The default framebuffer has no DEFAULT_* state of its own - its shape comes from the
// surface - so those names are accepted enums it simply cannot answer or accept.
if (isDefaultFramebuffer && isDefaultParameter) {
MG_State::pGLContext->RecordError(
ErrorCode::InvalidOperation,
MakeUnique<GenericErrorInfo>(
"MG_Impl/GLImpl/FramebufferImpl", caller,
std::format("pname {} does not apply to the default framebuffer.",
MG_Util::ConvertGLEnumToString(pname))));
return false;
}
return true;
}
Bool ValidateReadFramebufferForCopy(const char* caller) {
auto& framebufferObject =
MG_State::pGLContext->GetFramebufferBindingSlot(FramebufferTarget::Read).GetBoundObject();
if (!framebufferObject || !framebufferObject->CheckCompleteness()) {
MG_State::pGLContext->RecordError(
ErrorCode::InvalidFramebufferOperation,
MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl/FramebufferImpl", caller,
"Read framebuffer is not framebuffer complete."));
return false;
}
const FramebufferAttachmentType readBuffer = framebufferObject->GetReadBuffer();
if (readBuffer == FramebufferAttachmentType::None ||
!framebufferObject->GetAttachment(readBuffer).IsValid()) {
MG_State::pGLContext->RecordError(
ErrorCode::InvalidOperation,
MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl/FramebufferImpl", caller,
"Read buffer names no attachment of the read framebuffer."));
return false;
}
// SAMPLE_BUFFERS is one whenever the read buffer resolves to multisample storage. A
// multisample texture says so by its target - its sample count can legally be one - while a
// renderbuffer says so by having been given a non-zero sample count.
const auto& readAttachment = framebufferObject->GetAttachment(readBuffer);
Bool isMultisampled = false;
if (readAttachment.IsRenderbuffer() && readAttachment.GetRenderbuffer()) {
isMultisampled = readAttachment.GetRenderbuffer()->GetSamples() > 0;
} else if (readAttachment.IsTexture() && readAttachment.GetTexture()) {
const auto target = readAttachment.GetTexture()->GetTarget();
isMultisampled = target == TextureTarget::Texture2DMultisample ||
target == TextureTarget::Texture2DMultisampleArray;
}
if (isMultisampled) {
MG_State::pGLContext->RecordError(
ErrorCode::InvalidOperation,
MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl/FramebufferImpl", caller,
"Cannot copy from a multisampled read framebuffer."));
return false;
}
return true;
}
} // namespace MobileGL::MG_Impl::GLImpl::FramebufferImpl
@@ -14,21 +14,6 @@ namespace MobileGL::MG_Impl::GLImpl::FramebufferImpl {
Bool ValidateFramebufferTarget(FramebufferTarget target);
Bool ValidateFramebufferName(Uint index, Bool allowZero = true);
Bool ValidateFramebufferAttachmentType(FramebufferAttachmentType attachment);
// GL_COLOR_ATTACHMENTn is a token per n up to 31, but only the first GL_MAX_COLOR_ATTACHMENTS of
// them name an attachment point of a framebuffer object; the rest are INVALID_OPERATION for the
// attaching entry points (GL 4.6 core 9.2.7). Non-colour attachments pass through unchanged.
Bool ValidateColorAttachmentInRange(FramebufferAttachmentType attachment, const char* caller);
Bool ValidateRenderbufferTarget(RenderbufferTarget target);
Bool ValidateRenderbufferName(Uint index, Bool allowZero = true);
// The read-framebuffer preconditions the CopyTexSubImage family shares (GL 4.6 core 8.6): the
// read framebuffer must be complete, its read buffer must name a real attachment, and it must
// not be multisampled. Incompleteness is INVALID_FRAMEBUFFER_OPERATION, the other two are
// INVALID_OPERATION.
Bool ValidateReadFramebufferForCopy(const char* caller);
// The pname sets of glGet/FramebufferParameteri (GL 4.6 core 9.2.3). Order matters and is part
// of the contract: a name outside the table is INVALID_ENUM, and only then is a name that the
// DEFAULT framebuffer does not answer INVALID_OPERATION. Testing the framebuffer kind first
// would turn GL_FRAMEBUFFER_DEFAULT_WIDTH on framebuffer zero into the wrong error.
Bool ValidateFramebufferParameterPname(GLenum pname, Bool isDefaultFramebuffer, Bool forSetter,
const char* caller);
} // namespace MobileGL::MG_Impl::GLImpl::FramebufferImpl
+11 -121
View File
@@ -213,13 +213,8 @@ namespace MobileGL::MG_Impl::GLImpl {
GLint maxSamples = 0;
for (const auto& attachment : drawFbo->GetAllAttachmentObjects()) {
if (attachment.IsRenderbuffer() && attachment.GetRenderbuffer()) {
maxSamples = std::max(maxSamples, static_cast<GLint>(attachment.GetRenderbuffer()->GetSamples()));
} else if (attachment.IsTexture() && attachment.GetTexture()) {
// Multisample texture attachments count too (GL_SAMPLE_BUFFERS must
// report 1 for any multisampled draw framebuffer).
maxSamples = std::max(maxSamples, static_cast<GLint>(attachment.GetTexture()->GetSamples()));
}
if (!attachment.IsRenderbuffer() || !attachment.GetRenderbuffer()) continue;
maxSamples = std::max(maxSamples, static_cast<GLint>(attachment.GetRenderbuffer()->GetSamples()));
}
return maxSamples;
}
@@ -470,14 +465,6 @@ namespace MobileGL::MG_Impl::GLImpl {
case GL_STENCIL_TEST:
*params = MG_State::pGLContext->IsCapabilityEnabled(CapabilityInput::StencilTest) ? GL_TRUE : GL_FALSE;
return;
case GL_MIN_FRAGMENT_INTERPOLATION_OFFSET:
case GL_MAX_FRAGMENT_INTERPOLATION_OFFSET:
case GL_FRAGMENT_INTERPOLATION_OFFSET_BITS: {
GLfloat value = 0.0f;
GetFloatv(pname, &value);
*params = value != 0.0f ? GL_TRUE : GL_FALSE;
return;
}
default:
break;
}
@@ -533,19 +520,6 @@ namespace MobileGL::MG_Impl::GLImpl {
params[1] = dynamicParameters.ViewportBoundsRangeMax;
return;
}
case GL_MIN_FRAGMENT_INTERPOLATION_OFFSET:
case GL_MAX_FRAGMENT_INTERPOLATION_OFFSET:
case GL_FRAGMENT_INTERPOLATION_OFFSET_BITS: {
const auto& dynamicParameters = MG_Backend::pActiveBackendObject->GetDynamicParameters();
if (pname == GL_MIN_FRAGMENT_INTERPOLATION_OFFSET) {
params[0] = dynamicParameters.MinFragmentInterpolationOffset;
} else if (pname == GL_MAX_FRAGMENT_INTERPOLATION_OFFSET) {
params[0] = dynamicParameters.MaxFragmentInterpolationOffset;
} else {
params[0] = static_cast<GLfloat>(dynamicParameters.FragmentInterpolationOffsetBits);
}
return;
}
case GL_DEPTH_CLEAR_VALUE:
params[0] = MG_State::pGLContext->GetClearDepth();
return;
@@ -671,40 +645,6 @@ namespace MobileGL::MG_Impl::GLImpl {
}
switch (target) {
// The vertex buffer binding points of the vertex array object that is bound. Indexed by
// binding point, not by attribute (GL 4.6 core 10.3.1).
case GL_VERTEX_BINDING_BUFFER:
case GL_VERTEX_BINDING_DIVISOR:
case GL_VERTEX_BINDING_OFFSET:
case GL_VERTEX_BINDING_STRIDE: {
if (index >= VertexArrayImpl::GetMaxVertexAttribBindings()) {
MG_State::pGLContext->RecordError(
ErrorCode::InvalidValue,
MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", __func__,
"Vertex buffer binding index is out of range."));
return;
}
const auto& vao = MG_State::pGLContext->GetBoundVertexArray();
if (!vao) {
*data = 0;
return;
}
const auto& binding = vao->GetBindingPoint(index);
switch (target) {
case GL_VERTEX_BINDING_BUFFER:
*data = binding.Buffer ? static_cast<GLint>(binding.Buffer->GetExternalIndex()) : 0;
return;
case GL_VERTEX_BINDING_DIVISOR:
*data = static_cast<GLint>(binding.Divisor);
return;
case GL_VERTEX_BINDING_OFFSET:
*data = static_cast<GLint>(binding.Offset);
return;
default:
*data = static_cast<GLint>(binding.Stride);
return;
}
}
case GL_IMAGE_BINDING_NAME:
case GL_IMAGE_BINDING_LEVEL:
case GL_IMAGE_BINDING_LAYERED:
@@ -1064,11 +1004,6 @@ namespace MobileGL::MG_Impl::GLImpl {
*params = obj ? static_cast<GLint>(obj->GetExternalIndex()) : 0;
return;
}
case GL_DRAW_INDIRECT_BUFFER_BINDING: {
auto& obj = MG_State::pGLContext->GetBufferBindingSlot(BufferTarget::DrawIndirect).GetBoundObject();
*params = obj ? static_cast<GLint>(obj->GetExternalIndex()) : 0;
return;
}
case GL_MAX_DEBUG_GROUP_STACK_DEPTH:
*params = 0; // debug-group entrypoints are stubbed
return;
@@ -1432,7 +1367,7 @@ namespace MobileGL::MG_Impl::GLImpl {
*params = 0; // program-binary entrypoints are stubbed
return;
case GL_PROGRAM_PIPELINE_BINDING:
*params = static_cast<GLint>(MG_State::pGLContext->GetBoundProgramPipelineName());
*params = 0; // program-pipeline entrypoints are stubbed
return;
case GL_PROGRAM_POINT_SIZE:
*params = MG_State::pGLContext->IsCapabilityEnabled(CapabilityInput::ProgramPointSize) ? GL_TRUE : GL_FALSE;
@@ -1703,7 +1638,7 @@ namespace MobileGL::MG_Impl::GLImpl {
*params = static_cast<GLint>(MG_State::pGLContext->GetHint(pname));
return;
case GL_TEXTURE_BUFFER_OFFSET_ALIGNMENT:
*params = MG_Backend::pActiveBackendObject->GetDynamicParameters().TextureBufferOffsetAlignment;
*params = 0; // texture-buffer range entrypoints are stubbed
return;
case GL_TIMESTAMP: {
Int64 timestamp = 0;
@@ -1772,22 +1707,20 @@ namespace MobileGL::MG_Impl::GLImpl {
*params = vao ? static_cast<GLint>(vao->GetExternalIndex()) : 0;
return;
}
// The vertex buffer binding points are per-binding-index state, so the non-indexed getter
// has nothing to answer with (GL 4.6 core table 23.4).
case GL_VERTEX_BINDING_BUFFER:
case GL_VERTEX_BINDING_DIVISOR:
*params = 0; // vertex-binding entrypoints are stubbed
return;
case GL_VERTEX_BINDING_OFFSET:
*params = 0; // vertex-binding entrypoints are stubbed
return;
case GL_VERTEX_BINDING_STRIDE:
RecordIndexedOnlyGetterError(__func__, pname);
*params = 0; // vertex-binding entrypoints are stubbed
return;
case GL_MAX_VERTEX_ATTRIB_RELATIVE_OFFSET:
*params = static_cast<GLint>(VertexArrayImpl::GetMaxVertexAttribRelativeOffset());
*params = 0; // vertex-binding entrypoints are stubbed
return;
case GL_MAX_VERTEX_ATTRIB_BINDINGS:
*params = static_cast<GLint>(VertexArrayImpl::GetMaxVertexAttribBindings());
return;
case GL_MAX_VERTEX_ATTRIB_STRIDE:
*params = static_cast<GLint>(VertexArrayImpl::GetMaxVertexAttribStride());
*params = 0; // vertex-binding entrypoints are stubbed
return;
case GL_VIEWPORT: {
const auto& vp = MG_State::pGLContext->GetViewport();
@@ -1953,21 +1886,6 @@ namespace MobileGL::MG_Impl::GLImpl {
case GL_MAX_SAMPLE_MASK_WORDS:
*params = dynamicParameters.MaxSampleMaskWords;
break;
case GL_PATCH_VERTICES:
*params = static_cast<GLint>(MG_State::pGLContext->GetPatchVertices());
break;
case GL_MAX_PATCH_VERTICES:
*params = dynamicParameters.MaxPatchVertices;
break;
case GL_MAX_TESS_GEN_LEVEL:
*params = dynamicParameters.MaxTessGenLevel;
break;
case GL_MIN_PROGRAM_TEXTURE_GATHER_OFFSET:
*params = dynamicParameters.MinProgramTextureGatherOffset;
break;
case GL_MAX_PROGRAM_TEXTURE_GATHER_OFFSET:
*params = dynamicParameters.MaxProgramTextureGatherOffset;
break;
case GL_MAX_SHADER_STORAGE_BUFFER_BINDINGS:
*params = static_cast<GLint>(GetIndexedBufferQueryPointCount(BufferTarget::ShaderStorage));
break;
@@ -1983,25 +1901,6 @@ namespace MobileGL::MG_Impl::GLImpl {
case GL_MAX_TRANSFORM_FEEDBACK_SEPARATE_COMPONENTS:
*params = kFrontendMaxTransformFeedbackSeparateComponents;
break;
// ARB_transform_feedback3 limits. The GL CTS queries these before checking
// whether the extension is advertised and requires no GL error; desktop
// drivers all accept them, so answer with the separate-attrib capacity and
// the single vertex stream the backends provide.
case GL_MAX_TRANSFORM_FEEDBACK_BUFFERS:
*params = kFrontendMaxTransformFeedbackSeparateAttribs;
break;
case GL_MAX_VERTEX_STREAMS:
*params = 1;
break;
case GL_TRANSFORM_FEEDBACK_ACTIVE:
*params = MG_State::pGLContext->IsTransformFeedbackActive() ? 1 : 0;
break;
case GL_TRANSFORM_FEEDBACK_PAUSED:
*params = MG_State::pGLContext->IsTransformFeedbackPaused() ? 1 : 0;
break;
case GL_TRANSFORM_FEEDBACK_BINDING:
*params = static_cast<GLint>(MG_State::pGLContext->GetBoundTransformFeedbackName());
break;
case GL_MAX_TEXTURE_IMAGE_UNITS:
*params = dynamicParameters.MaxTextureImageUnits;
break;
@@ -2058,15 +1957,6 @@ namespace MobileGL::MG_Impl::GLImpl {
case GL_SUBPIXEL_BITS:
*params = std::max(dynamicParameters.ViewportSubpixelBits, kFrontendSubpixelBits);
break;
case GL_MIN_FRAGMENT_INTERPOLATION_OFFSET:
*params = static_cast<GLint>(std::lround(dynamicParameters.MinFragmentInterpolationOffset));
break;
case GL_MAX_FRAGMENT_INTERPOLATION_OFFSET:
*params = static_cast<GLint>(std::lround(dynamicParameters.MaxFragmentInterpolationOffset));
break;
case GL_FRAGMENT_INTERPOLATION_OFFSET_BITS:
*params = dynamicParameters.FragmentInterpolationOffsetBits;
break;
case GL_UNIFORM_BUFFER_OFFSET_ALIGNMENT:
*params = static_cast<Int>(dynamicParameters.UniformBufferOffsetAlignment);
break;
+19 -736
View File
@@ -8,8 +8,6 @@
#include "GL_Program.h"
#include "Config.h"
#include <cmath>
#include <limits>
#include <MG_Impl/GLImpl/VertexArray/Validators.h>
#include <MG_State/GLState/Core.h>
#include <MG_Util/Converters/GLToStr/GLEnumConverter.h>
@@ -51,18 +49,10 @@ namespace MobileGL::MG_Impl::GLImpl {
static bool CheckProgramNameValidity(GLuint program) {
if (!MG_State::pGLContext->ValidateProgramName(program)) {
// Programs and shaders share one name space: a name that exists but
// belongs to a shader is INVALID_OPERATION, a name GL never handed
// out is INVALID_VALUE (GL 3.3 core 2.11.x).
const ErrorCode error = MG_State::pGLContext->ValidateShaderName(program)
? ErrorCode::InvalidOperation
: ErrorCode::InvalidValue;
MG_State::pGLContext->RecordError(
error,
ErrorCode::InvalidValue,
MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", __func__,
std::to_string(program) +
(error == ErrorCode::InvalidOperation ? " is not a program object."
: " is not a valid name.")));
std::to_string(program) + " is not a valid name."));
return false;
}
return true;
@@ -205,50 +195,6 @@ namespace MobileGL::MG_Impl::GLImpl {
}
}
// The GL_UNIFORM interface and glGetActiveUniform(s)iv are the same query in two
// spellings, so they answer from the same place - the frontend reflection. The backend
// program is not that place: it does not exist at all for a program whose types its
// shading language cannot express (a double-precision uniform has no ESSL form), and
// the interface queries would then describe a program with no uniforms.
//
// Writes the GL_UNIFORM value of `prop` for active uniform `index`; false for a prop
// the reflection does not model, which the caller forwards to the backend instead.
Bool GetUniformResourceProp(const SharedPtr<MG_State::GLState::ProgramObject>& programObject, Uint index,
GLenum prop, GLint* out) {
switch (prop) {
case GL_TYPE:
*out = static_cast<GLint>(programObject->GetActiveUniformType(index));
return true;
case GL_ARRAY_SIZE:
*out = programObject->GetActiveUniformArraySize(index);
return true;
case GL_NAME_LENGTH:
*out = static_cast<GLint>(programObject->GetActiveUniformName(index).length() + 1);
return true;
case GL_BLOCK_INDEX:
*out = programObject->GetActiveUniformBlockIndex(index);
return true;
case GL_OFFSET:
*out = programObject->GetActiveUniformOffset(index);
return true;
case GL_ARRAY_STRIDE:
*out = programObject->GetActiveUniformArrayStride(index);
return true;
case GL_MATRIX_STRIDE:
*out = programObject->GetActiveUniformMatrixStride(index);
return true;
case GL_IS_ROW_MAJOR:
*out = programObject->GetActiveUniformIsRowMajor(index);
return true;
case GL_LOCATION:
// A block member has no location; GetUniformLocation already reports -1 for one.
*out = programObject->GetUniformLocation(programObject->GetActiveUniformName(index));
return true;
default:
return false;
}
}
void CopyStr(GLsizei bufSize, GLsizei* length, GLchar* dst, const char* src, GLsizei srcLength) {
if (bufSize <= 0) {
if (length) *length = 0;
@@ -371,16 +317,11 @@ namespace MobileGL::MG_Impl::GLImpl {
}
void DeleteProgram_State(GLuint program) {
// "If program is zero, it is silently ignored" (GL 4.6 core 7.3) - unlike every
// other program entry point, where 0 is a name GL never handed out.
if (program == 0) return;
if (!CheckProgramNameValidity(program)) return;
MG_State::pGLContext->MarkProgramForDeletion(program);
}
void DeleteShader_State(GLuint shader) {
// Same silent-zero rule as glDeleteProgram (GL 4.6 core 7.1).
if (shader == 0) return;
if (!CheckShaderNameValidity(shader)) return;
MG_State::pGLContext->MarkShaderForDeletion(shader);
}
@@ -664,18 +605,6 @@ namespace MobileGL::MG_Impl::GLImpl {
*params = programObject->GetActiveUniformBlocksMaxNameLength() + 1;
MGLOG_D("%s: %s = %d", __func__, MG_Util::ConvertGLEnumToString(pname).c_str(), *params);
break;
case GL_TRANSFORM_FEEDBACK_VARYINGS:
*params = static_cast<GLint>(programObject->GetTransformFeedbackVaryingCount());
MGLOG_D("%s: %s = %d", __func__, MG_Util::ConvertGLEnumToString(pname).c_str(), *params);
break;
case GL_TRANSFORM_FEEDBACK_BUFFER_MODE:
*params = static_cast<GLint>(programObject->GetTransformFeedbackBufferMode());
MGLOG_D("%s: %s = %d", __func__, MG_Util::ConvertGLEnumToString(pname).c_str(), *params);
break;
case GL_TRANSFORM_FEEDBACK_VARYING_MAX_LENGTH:
*params = programObject->GetTransformFeedbackVaryingMaxLength();
MGLOG_D("%s: %s = %d", __func__, MG_Util::ConvertGLEnumToString(pname).c_str(), *params);
break;
case GL_COMPUTE_WORK_GROUP_SIZE: { // GL >= 4.3
if (!programObject->GetLinkStatus() || programObject->GetShaderIndexByStage(ShaderStage::Compute) < 0) {
MG_State::pGLContext->RecordError(
@@ -694,17 +623,10 @@ namespace MobileGL::MG_Impl::GLImpl {
}
case GL_PROGRAM_BINARY_LENGTH:
// No program binary format is exposed, so a program never has a retrievable
// binary and its length is zero (ARB_get_program_binary).
*params = 0;
break;
case GL_PROGRAM_BINARY_RETRIEVABLE_HINT:
*params = programObject->GetBinaryRetrievableHint() ? GL_TRUE : GL_FALSE;
break;
case GL_PROGRAM_SEPARABLE:
*params = programObject->GetSeparable() ? GL_TRUE : GL_FALSE;
break;
case GL_TRANSFORM_FEEDBACK_BUFFER_MODE:
case GL_TRANSFORM_FEEDBACK_VARYINGS:
case GL_TRANSFORM_FEEDBACK_VARYING_MAX_LENGTH:
case GL_GEOMETRY_VERTICES_OUT:
case GL_GEOMETRY_INPUT_TYPE:
case GL_GEOMETRY_OUTPUT_TYPE:
@@ -879,8 +801,7 @@ namespace MobileGL::MG_Impl::GLImpl {
}
if constexpr (std::is_same_v<T, GLfloat>) {
if (ttype->getBasicType() != glslang::EbtDouble && ttype->isMatrix() &&
ttype->getMatrixCols() == 3) {
if (ttype->isMatrix() && ttype->getMatrixCols() == 3) {
auto* pBase = pUBO + offset;
for (int i = 0; i < ttype->getMatrixRows(); i++) {
Memcpy(reinterpret_cast<char*>(params) + ttype->getMatrixCols() * sizeof(GLfloat) * i,
@@ -890,46 +811,9 @@ namespace MobileGL::MG_Impl::GLImpl {
}
}
// A double-precision uniform is the one case where the stored component type can
// differ from the queried one for a non-opaque uniform, and the difference is not
// just a reinterpretation: it is twice as wide, so a raw copy would overrun the
// caller's buffer as well as return nonsense. Read component by component and let
// GL's conversion rules (7.6: round to nearest for the integer queries) apply.
if (ttype->getBasicType() == glslang::EbtDouble) {
const Int columns = ttype->isMatrix() ? ttype->getMatrixCols() : 1;
const Int rows = ttype->isMatrix() ? ttype->getMatrixRows()
: (ttype->isVector() ? ttype->getVectorSize() : 1);
// The slot the linker handed out is exactly `columns` columns wide, so it also
// states the column stride - which for a double matrix is not a float's 16 bytes.
const SizeT columnStride = columns > 0 ? size / static_cast<SizeT>(columns) : size;
for (Int column = 0; column < columns; ++column) {
for (Int row = 0; row < rows; ++row) {
GLdouble component = 0.0;
Memcpy(&component, pUBO + offset + column * columnStride + row * sizeof(GLdouble),
sizeof(component));
if constexpr (std::is_integral_v<T>) {
// Rounded to the nearest integer and clamped into the queried type's
// range, so a negative double read through glGetUniformuiv is 0
// rather than its two's complement.
const GLdouble rounded = std::nearbyint(component);
const GLdouble lowest = static_cast<GLdouble>(std::numeric_limits<T>::lowest());
const GLdouble highest = static_cast<GLdouble>(std::numeric_limits<T>::max());
params[column * rows + row] = static_cast<T>(std::clamp(rounded, lowest, highest));
} else {
params[column * rows + row] = static_cast<T>(component);
}
}
}
return;
}
Memcpy(params, pUBO + offset, size);
}
void GetUniformdv_State(GLuint program, GLint location, GLdouble* params) {
GetUniformScalar_State(program, location, params);
}
void GetUniformfv_State(GLuint program, GLint location, GLfloat* params) {
GetUniformScalar_State(program, location, params);
}
@@ -943,13 +827,19 @@ namespace MobileGL::MG_Impl::GLImpl {
}
GLboolean IsProgram_State(GLuint program) {
// Deletion-flagged names stay valid while the object is still GL-visible (program in
// use, shader attached), so name validity is exactly the Is* answer.
/* FIXME: Handle situations that:
* A program object marked for deletion with glDeleteProgram but still in use as part of current
* rendering state is still considered a program object and glIsProgram will return GL_TRUE.
*/
if (program == 0) return GL_FALSE;
return MG_State::pGLContext->ValidateProgramName(program) ? GL_TRUE : GL_FALSE;
}
GLboolean IsShader_State(GLuint shader) {
/* FIXME: Handle situations that:
* A shader object marked for deletion with glDeleteShader but still attached to a program object is still
* considered a shader object and glIsShader will return GL_TRUE.
*/
if (shader == 0) return GL_FALSE;
return MG_State::pGLContext->ValidateShaderName(shader) ? GL_TRUE : GL_FALSE;
}
@@ -959,18 +849,6 @@ namespace MobileGL::MG_Impl::GLImpl {
if (!programObject) return;
MGLOG_D("%s: linking program %d", __func__, program);
// Relinking the program an active transform feedback captures from would
// invalidate its varyings mid-capture (GL 3.3 core 2.11.3).
if (MG_State::pGLContext->IsTransformFeedbackActive() &&
MG_State::pGLContext->GetTransformFeedbackProgram().get() == programObject.get()) {
MG_State::pGLContext->RecordError(
ErrorCode::InvalidOperation,
MakeUnique<GenericErrorInfo>(
"MG_Impl/GLImpl", __func__,
"The program used by active transform feedback cannot be relinked."));
return;
}
static Bool allowVSOnlyPrograms;
static Bool initialized = false;
if (!initialized) {
@@ -1014,18 +892,6 @@ namespace MobileGL::MG_Impl::GLImpl {
void UseProgram_State(GLuint program) {
MGLOG_D("UseProgram_State: program=%u", program);
// The program in use may not change while transform feedback is active - unless
// the capture is paused, which is exactly what ARB_transform_feedback2 added the
// pause for (GL 4.6 core 7.3).
if (MG_State::pGLContext->IsTransformFeedbackActive() &&
!MG_State::pGLContext->IsTransformFeedbackPaused()) {
MG_State::pGLContext->RecordError(
ErrorCode::InvalidOperation,
MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", __func__,
"The current program cannot change while transform feedback is active."));
return;
}
if (program == 0) {
MG_State::pGLContext->UseProgram(0);
return;
@@ -1073,14 +939,6 @@ namespace MobileGL::MG_Impl::GLImpl {
}
MGLOG_D("%s: program = %d, location = %d, byteOffset = %d", __func__, programObject.GetExternalIndex(),
location, offset + byteOffsetInsideUniform);
// Apps re-set identical uniform values constantly (Minecraft re-uploads the same
// matrices and sampler indices every frame), and any content-version move makes both
// backends re-upload the whole UBO on the next draw. Every glUniform entry point
// funnels its final bytes through here - after any transpose/stride conversion, with
// the exact destination range known - and the scratch is zero-filled at link (matching
// the GL zero defaults), so a bytes-equal write can be dropped without moving the
// version.
if (std::memcmp(pUBO + offset + byteOffsetInsideUniform, value, writeSize) == 0) return;
Memcpy(pUBO + offset + byteOffsetInsideUniform, value, writeSize);
programObject.MarkUBOContentDirty();
} else {
@@ -1105,7 +963,7 @@ namespace MobileGL::MG_Impl::GLImpl {
void Uniformv_State(GLint location, GLsizei count, T* value) {
if (location == -1) return;
auto& programObject = MG_State::pGLContext->GetProgramForUniform();
auto& programObject = MG_State::pGLContext->GetCurrentProgram();
if (programObject == nullptr) {
MG_State::pGLContext->RecordError(
ErrorCode::InvalidOperation,
@@ -1156,38 +1014,6 @@ namespace MobileGL::MG_Impl::GLImpl {
}
}
// glUniform*d / glUniformMatrix*dv. The vector forms need nothing beyond the shared
// upload template - it is already typed on the component - but a matrix does: the
// column stride the linker used for a double matrix is not the 16 bytes a float one
// gets. It is not guessed here; the slot the uniform was given is exactly `columns`
// columns wide, so dividing states the stride the rest of the pipeline agreed on.
template <typename Program>
void UniformMatrixdv_Object(Program& programObject, GLint location, GLsizei count, GLboolean transpose,
const GLdouble* value, Int columns, Int rows) {
const SizeT slotSize = programObject.GetUniformSizesInBytes(location);
const SizeT columnStride = columns > 0 ? slotSize / static_cast<SizeT>(columns) : slotSize;
const SizeT componentCount = static_cast<SizeT>(columns) * static_cast<SizeT>(rows);
Vector<GLdouble> column(static_cast<SizeT>(rows));
for (GLint matrix = 0; matrix < count; ++matrix) {
if (matrix > 0 && !programObject.UniformLocationsAliasSameUniform(location, location + matrix)) break;
if (!programObject.IsValidUniformLocation(location + matrix)) {
RecordInvalidUniformLocationError(__func__, location + matrix, "the current program object");
return;
}
const GLdouble* source = value + matrix * componentCount;
for (Int c = 0; c < columns; ++c) {
for (Int r = 0; r < rows; ++r) {
column[r] = transpose == GL_TRUE ? source[r * columns + c] : source[c * rows + r];
}
Uniform_State<1>(programObject, location + matrix, column.data(), c * columnStride);
for (Int r = 1; r < rows; ++r) {
Uniform_State<1>(programObject, location + matrix, column.data() + r,
c * columnStride + r * sizeof(GLdouble));
}
}
}
}
// Helper function to transpose a 2x2 matrix
void TransposeMatrix2x2(const GLfloat* input, GLfloat* output) {
// Input matrix is in column-major order (OpenGL default)
@@ -1297,7 +1123,7 @@ namespace MobileGL::MG_Impl::GLImpl {
// If transpose is GL_TRUE, we need to transpose the matrix data
if (location == -1) return;
auto& programObject = MG_State::pGLContext->GetProgramForUniform();
auto& programObject = MG_State::pGLContext->GetCurrentProgram();
if (programObject == nullptr) {
MG_State::pGLContext->RecordError(
ErrorCode::InvalidOperation,
@@ -1332,7 +1158,7 @@ namespace MobileGL::MG_Impl::GLImpl {
// If transpose is GL_TRUE, we need to transpose the matrix data
if (location == -1) return;
auto& programObject = MG_State::pGLContext->GetProgramForUniform();
auto& programObject = MG_State::pGLContext->GetCurrentProgram();
if (programObject == nullptr) {
MG_State::pGLContext->RecordError(
ErrorCode::InvalidOperation,
@@ -1372,7 +1198,7 @@ namespace MobileGL::MG_Impl::GLImpl {
// If transpose is GL_TRUE, we need to transpose the matrix data
if (location == -1) return;
auto& programObject = MG_State::pGLContext->GetProgramForUniform();
auto& programObject = MG_State::pGLContext->GetCurrentProgram();
if (programObject == nullptr) {
MG_State::pGLContext->RecordError(
ErrorCode::InvalidOperation,
@@ -1405,7 +1231,7 @@ namespace MobileGL::MG_Impl::GLImpl {
void UniformMatrixNonSquarefv_State(const char* caller, GLint location, GLsizei count) {
if (location == -1) return;
auto& programObject = MG_State::pGLContext->GetProgramForUniform();
auto& programObject = MG_State::pGLContext->GetCurrentProgram();
if (programObject == nullptr) {
MG_State::pGLContext->RecordError(
ErrorCode::InvalidOperation,
@@ -1996,312 +1822,6 @@ namespace MobileGL::MG_Impl::GLImpl {
GLuint v[] = {v0, v1, v2, v3};
Uniform4uiv(location, 1, v);
}
void Uniform1d(GLint location, GLdouble v0) {
const GLdouble v[] = {v0};
Uniformv_State<1>(location, 1, v);
}
void Uniform1dv(GLint location, GLsizei count, const GLdouble* value) {
Uniformv_State<1>(location, count, value);
}
void ProgramUniform1d(GLuint program, GLint location, GLdouble v0) {
const GLdouble v[] = {v0};
ProgramUniformv_State<1>(program, location, 1, v);
}
void ProgramUniform1dv(GLuint program, GLint location, GLsizei count, const GLdouble* value) {
ProgramUniformv_State<1>(program, location, count, value);
}
void Uniform2d(GLint location, GLdouble v0, GLdouble v1) {
const GLdouble v[] = {v0, v1};
Uniformv_State<2>(location, 1, v);
}
void Uniform2dv(GLint location, GLsizei count, const GLdouble* value) {
Uniformv_State<2>(location, count, value);
}
void ProgramUniform2d(GLuint program, GLint location, GLdouble v0, GLdouble v1) {
const GLdouble v[] = {v0, v1};
ProgramUniformv_State<2>(program, location, 1, v);
}
void ProgramUniform2dv(GLuint program, GLint location, GLsizei count, const GLdouble* value) {
ProgramUniformv_State<2>(program, location, count, value);
}
void Uniform3d(GLint location, GLdouble v0, GLdouble v1, GLdouble v2) {
const GLdouble v[] = {v0, v1, v2};
Uniformv_State<3>(location, 1, v);
}
void Uniform3dv(GLint location, GLsizei count, const GLdouble* value) {
Uniformv_State<3>(location, count, value);
}
void ProgramUniform3d(GLuint program, GLint location, GLdouble v0, GLdouble v1, GLdouble v2) {
const GLdouble v[] = {v0, v1, v2};
ProgramUniformv_State<3>(program, location, 1, v);
}
void ProgramUniform3dv(GLuint program, GLint location, GLsizei count, const GLdouble* value) {
ProgramUniformv_State<3>(program, location, count, value);
}
void Uniform4d(GLint location, GLdouble v0, GLdouble v1, GLdouble v2, GLdouble v3) {
const GLdouble v[] = {v0, v1, v2, v3};
Uniformv_State<4>(location, 1, v);
}
void Uniform4dv(GLint location, GLsizei count, const GLdouble* value) {
Uniformv_State<4>(location, count, value);
}
void ProgramUniform4d(GLuint program, GLint location, GLdouble v0, GLdouble v1, GLdouble v2, GLdouble v3) {
const GLdouble v[] = {v0, v1, v2, v3};
ProgramUniformv_State<4>(program, location, 1, v);
}
void ProgramUniform4dv(GLuint program, GLint location, GLsizei count, const GLdouble* value) {
ProgramUniformv_State<4>(program, location, count, value);
}
void UniformMatrix2dv(GLint location, GLsizei count, GLboolean transpose, const GLdouble* value) {
if (location == -1) return;
auto& programObject = MG_State::pGLContext->GetProgramForUniform();
if (programObject == nullptr) {
MG_State::pGLContext->RecordError(
ErrorCode::InvalidOperation,
MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", __func__, "There is no current program object."));
return;
}
UniformMatrixdv_Object(*programObject, location, count, transpose, value, 2, 2);
}
void ProgramUniformMatrix2dv(GLuint program, GLint location, GLsizei count, GLboolean transpose,
const GLdouble* value) {
if (location == -1) return;
auto& programObject = TryToGetProgramObject(program);
if (!programObject) return;
if (!programObject->GetLinkStatus()) {
MG_State::pGLContext->RecordError(
ErrorCode::InvalidOperation,
MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", __func__,
"program " + std::to_string(program) + " is not linked."));
return;
}
UniformMatrixdv_Object(*programObject, location, count, transpose, value, 2, 2);
}
void UniformMatrix3dv(GLint location, GLsizei count, GLboolean transpose, const GLdouble* value) {
if (location == -1) return;
auto& programObject = MG_State::pGLContext->GetProgramForUniform();
if (programObject == nullptr) {
MG_State::pGLContext->RecordError(
ErrorCode::InvalidOperation,
MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", __func__, "There is no current program object."));
return;
}
UniformMatrixdv_Object(*programObject, location, count, transpose, value, 3, 3);
}
void ProgramUniformMatrix3dv(GLuint program, GLint location, GLsizei count, GLboolean transpose,
const GLdouble* value) {
if (location == -1) return;
auto& programObject = TryToGetProgramObject(program);
if (!programObject) return;
if (!programObject->GetLinkStatus()) {
MG_State::pGLContext->RecordError(
ErrorCode::InvalidOperation,
MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", __func__,
"program " + std::to_string(program) + " is not linked."));
return;
}
UniformMatrixdv_Object(*programObject, location, count, transpose, value, 3, 3);
}
void UniformMatrix4dv(GLint location, GLsizei count, GLboolean transpose, const GLdouble* value) {
if (location == -1) return;
auto& programObject = MG_State::pGLContext->GetProgramForUniform();
if (programObject == nullptr) {
MG_State::pGLContext->RecordError(
ErrorCode::InvalidOperation,
MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", __func__, "There is no current program object."));
return;
}
UniformMatrixdv_Object(*programObject, location, count, transpose, value, 4, 4);
}
void ProgramUniformMatrix4dv(GLuint program, GLint location, GLsizei count, GLboolean transpose,
const GLdouble* value) {
if (location == -1) return;
auto& programObject = TryToGetProgramObject(program);
if (!programObject) return;
if (!programObject->GetLinkStatus()) {
MG_State::pGLContext->RecordError(
ErrorCode::InvalidOperation,
MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", __func__,
"program " + std::to_string(program) + " is not linked."));
return;
}
UniformMatrixdv_Object(*programObject, location, count, transpose, value, 4, 4);
}
void UniformMatrix2x3dv(GLint location, GLsizei count, GLboolean transpose, const GLdouble* value) {
if (location == -1) return;
auto& programObject = MG_State::pGLContext->GetProgramForUniform();
if (programObject == nullptr) {
MG_State::pGLContext->RecordError(
ErrorCode::InvalidOperation,
MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", __func__, "There is no current program object."));
return;
}
UniformMatrixdv_Object(*programObject, location, count, transpose, value, 2, 3);
}
void ProgramUniformMatrix2x3dv(GLuint program, GLint location, GLsizei count, GLboolean transpose,
const GLdouble* value) {
if (location == -1) return;
auto& programObject = TryToGetProgramObject(program);
if (!programObject) return;
if (!programObject->GetLinkStatus()) {
MG_State::pGLContext->RecordError(
ErrorCode::InvalidOperation,
MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", __func__,
"program " + std::to_string(program) + " is not linked."));
return;
}
UniformMatrixdv_Object(*programObject, location, count, transpose, value, 2, 3);
}
void UniformMatrix2x4dv(GLint location, GLsizei count, GLboolean transpose, const GLdouble* value) {
if (location == -1) return;
auto& programObject = MG_State::pGLContext->GetProgramForUniform();
if (programObject == nullptr) {
MG_State::pGLContext->RecordError(
ErrorCode::InvalidOperation,
MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", __func__, "There is no current program object."));
return;
}
UniformMatrixdv_Object(*programObject, location, count, transpose, value, 2, 4);
}
void ProgramUniformMatrix2x4dv(GLuint program, GLint location, GLsizei count, GLboolean transpose,
const GLdouble* value) {
if (location == -1) return;
auto& programObject = TryToGetProgramObject(program);
if (!programObject) return;
if (!programObject->GetLinkStatus()) {
MG_State::pGLContext->RecordError(
ErrorCode::InvalidOperation,
MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", __func__,
"program " + std::to_string(program) + " is not linked."));
return;
}
UniformMatrixdv_Object(*programObject, location, count, transpose, value, 2, 4);
}
void UniformMatrix3x2dv(GLint location, GLsizei count, GLboolean transpose, const GLdouble* value) {
if (location == -1) return;
auto& programObject = MG_State::pGLContext->GetProgramForUniform();
if (programObject == nullptr) {
MG_State::pGLContext->RecordError(
ErrorCode::InvalidOperation,
MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", __func__, "There is no current program object."));
return;
}
UniformMatrixdv_Object(*programObject, location, count, transpose, value, 3, 2);
}
void ProgramUniformMatrix3x2dv(GLuint program, GLint location, GLsizei count, GLboolean transpose,
const GLdouble* value) {
if (location == -1) return;
auto& programObject = TryToGetProgramObject(program);
if (!programObject) return;
if (!programObject->GetLinkStatus()) {
MG_State::pGLContext->RecordError(
ErrorCode::InvalidOperation,
MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", __func__,
"program " + std::to_string(program) + " is not linked."));
return;
}
UniformMatrixdv_Object(*programObject, location, count, transpose, value, 3, 2);
}
void UniformMatrix3x4dv(GLint location, GLsizei count, GLboolean transpose, const GLdouble* value) {
if (location == -1) return;
auto& programObject = MG_State::pGLContext->GetProgramForUniform();
if (programObject == nullptr) {
MG_State::pGLContext->RecordError(
ErrorCode::InvalidOperation,
MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", __func__, "There is no current program object."));
return;
}
UniformMatrixdv_Object(*programObject, location, count, transpose, value, 3, 4);
}
void ProgramUniformMatrix3x4dv(GLuint program, GLint location, GLsizei count, GLboolean transpose,
const GLdouble* value) {
if (location == -1) return;
auto& programObject = TryToGetProgramObject(program);
if (!programObject) return;
if (!programObject->GetLinkStatus()) {
MG_State::pGLContext->RecordError(
ErrorCode::InvalidOperation,
MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", __func__,
"program " + std::to_string(program) + " is not linked."));
return;
}
UniformMatrixdv_Object(*programObject, location, count, transpose, value, 3, 4);
}
void UniformMatrix4x2dv(GLint location, GLsizei count, GLboolean transpose, const GLdouble* value) {
if (location == -1) return;
auto& programObject = MG_State::pGLContext->GetProgramForUniform();
if (programObject == nullptr) {
MG_State::pGLContext->RecordError(
ErrorCode::InvalidOperation,
MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", __func__, "There is no current program object."));
return;
}
UniformMatrixdv_Object(*programObject, location, count, transpose, value, 4, 2);
}
void ProgramUniformMatrix4x2dv(GLuint program, GLint location, GLsizei count, GLboolean transpose,
const GLdouble* value) {
if (location == -1) return;
auto& programObject = TryToGetProgramObject(program);
if (!programObject) return;
if (!programObject->GetLinkStatus()) {
MG_State::pGLContext->RecordError(
ErrorCode::InvalidOperation,
MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", __func__,
"program " + std::to_string(program) + " is not linked."));
return;
}
UniformMatrixdv_Object(*programObject, location, count, transpose, value, 4, 2);
}
void UniformMatrix4x3dv(GLint location, GLsizei count, GLboolean transpose, const GLdouble* value) {
if (location == -1) return;
auto& programObject = MG_State::pGLContext->GetProgramForUniform();
if (programObject == nullptr) {
MG_State::pGLContext->RecordError(
ErrorCode::InvalidOperation,
MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", __func__, "There is no current program object."));
return;
}
UniformMatrixdv_Object(*programObject, location, count, transpose, value, 4, 3);
}
void ProgramUniformMatrix4x3dv(GLuint program, GLint location, GLsizei count, GLboolean transpose,
const GLdouble* value) {
if (location == -1) return;
auto& programObject = TryToGetProgramObject(program);
if (!programObject) return;
if (!programObject->GetLinkStatus()) {
MG_State::pGLContext->RecordError(
ErrorCode::InvalidOperation,
MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", __func__,
"program " + std::to_string(program) + " is not linked."));
return;
}
UniformMatrixdv_Object(*programObject, location, count, transpose, value, 4, 3);
}
void GetUniformdv(GLuint program, GLint location, GLdouble* params) {
GetUniformdv_State(program, location, params);
}
void Uniform1fv(GLint location, GLsizei count, const GLfloat* value) {
Uniform1fv_State(location, count, value);
}
@@ -2581,17 +2101,6 @@ namespace MobileGL::MG_Impl::GLImpl {
"Backend does not support program interface queries."));
return;
}
if (programInterface == GL_UNIFORM) {
if (pname == GL_ACTIVE_RESOURCES) {
*params = static_cast<GLint>(programObject->GetUniformCount());
return;
}
if (pname == GL_MAX_NAME_LENGTH) {
// Stored as the bare length; GL_MAX_NAME_LENGTH counts the terminator.
*params = programObject->GetUniformMaxLength() + 1;
return;
}
}
getProgramInterfaceiv(program, programInterface, pname, params);
}
@@ -2600,10 +2109,6 @@ namespace MobileGL::MG_Impl::GLImpl {
if (!programObject) return GL_INVALID_INDEX;
if (!ValidateNamedProgramResourceInterface(programInterface, __func__)) return GL_INVALID_INDEX;
if (!name) return GL_INVALID_INDEX;
if (programInterface == GL_UNIFORM) {
const Int uniformIndex = programObject->GetActiveUniformIndex(name);
return uniformIndex < 0 ? GL_INVALID_INDEX : static_cast<GLuint>(uniformIndex);
}
auto getProgramResourceIndex = MG_Backend::gBackendFunctionsTable.GL.GetProgramResourceIndex;
if (!getProgramResourceIndex) {
MG_State::pGLContext->RecordError(
@@ -2640,13 +2145,6 @@ namespace MobileGL::MG_Impl::GLImpl {
MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", __func__, "bufSize must be non-negative."));
return;
}
if (programInterface == GL_UNIFORM) {
// Same index space GetProgramResourceIndex answers in, and the range check above
// already used it.
const String& uniformName = programObject->GetActiveUniformName(index);
CopyStr(bufSize, length, name, uniformName.c_str(), static_cast<GLsizei>(uniformName.length()));
return;
}
auto getProgramResourceName = MG_Backend::gBackendFunctionsTable.GL.GetProgramResourceName;
if (!getProgramResourceName) {
MG_State::pGLContext->RecordError(
@@ -2668,36 +2166,6 @@ namespace MobileGL::MG_Impl::GLImpl {
"propCount and bufSize must be non-negative."));
return;
}
if (programInterface == GL_UNIFORM) {
if (index >= programObject->GetUniformCount()) {
MG_State::pGLContext->RecordError(
ErrorCode::InvalidValue,
MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", __func__, "index is out of range."));
return;
}
if (props == nullptr || params == nullptr) return;
GLsizei written = 0;
for (GLsizei i = 0; i < propCount && written < bufSize; ++i) {
GLint value = 0;
if (!GetUniformResourceProp(programObject, index, props[i], &value)) {
// GL_ATOMIC_COUNTER_BUFFER_INDEX and the GL_REFERENCED_BY_* stage props are
// not modelled here; ask the backend, which indexes resources by name.
auto backendGetIndex = MG_Backend::gBackendFunctionsTable.GL.GetProgramResourceIndex;
auto backendGetiv = MG_Backend::gBackendFunctionsTable.GL.GetProgramResourceiv;
if (backendGetIndex && backendGetiv) {
const GLuint backendIndex = backendGetIndex(program, GL_UNIFORM,
programObject->GetActiveUniformName(index).c_str());
if (backendIndex != GL_INVALID_INDEX) {
GLsizei one = 0;
backendGetiv(program, GL_UNIFORM, backendIndex, 1, &props[i], 1, &one, &value);
}
}
}
params[written++] = value;
}
if (length) *length = written;
return;
}
auto getProgramResourceiv = MG_Backend::gBackendFunctionsTable.GL.GetProgramResourceiv;
if (!getProgramResourceiv) {
MG_State::pGLContext->RecordError(
@@ -2749,189 +2217,4 @@ namespace MobileGL::MG_Impl::GLImpl {
void ValidateProgram(GLuint program) {
ValidateProgram_State(program);
}
// ARB_get_program_binary with no supported binary format (GL_NUM_PROGRAM_BINARY_FORMATS
// is 0, which the extension explicitly allows). The three entry points below are what an
// application - and dEQP's function loader - reach through the extension; without it
// glProgramParameteri is not exposed in a 4.0 context at all.
void ProgramParameteri(GLuint program, GLenum pname, GLint value) {
auto& programObject = TryToGetProgramObject(program);
if (!programObject) return;
if (pname != GL_PROGRAM_BINARY_RETRIEVABLE_HINT && pname != GL_PROGRAM_SEPARABLE) {
MG_State::pGLContext->RecordError(
ErrorCode::InvalidEnum,
MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", __func__, "pname is not an accepted value."));
return;
}
if (value != GL_TRUE && value != GL_FALSE) {
MG_State::pGLContext->RecordError(
ErrorCode::InvalidValue,
MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", __func__, "value must be GL_TRUE or GL_FALSE."));
return;
}
if (pname == GL_PROGRAM_SEPARABLE) {
programObject->SetSeparable(value == GL_TRUE);
return;
}
programObject->SetBinaryRetrievableHint(value == GL_TRUE);
}
// GL 4.6 core 7.3: glCreateShaderProgramv is defined as the exact sequence below, so it
// is written as that sequence rather than as a private shortcut - every error it can
// raise is one of theirs, raised at the point they would raise it.
GLuint CreateShaderProgramv(GLenum type, GLsizei count, const GLchar* const* strings) {
const GLuint shader = CreateShader_State(type);
if (shader == 0) return 0;
ShaderSource_State(shader, count, strings, nullptr);
CompileShader_State(shader);
const GLuint program = CreateProgram_State();
if (program != 0) {
const auto& shaderObject = MG_State::pGLContext->GetShaderObject(shader);
const auto& programObject = MG_State::pGLContext->GetProgramObject(program);
// The program is separable whether or not the shader compiled: a failed
// compile leaves an unlinked but otherwise well-formed separable program.
if (programObject) programObject->SetSeparable(true);
if (shaderObject && programObject && shaderObject->GetCompileStatus()) {
AttachShader_State(program, shader);
// Not LinkProgram_State: that injects a default fragment shader into a
// program that has none, which is exactly wrong for a separable
// vertex-stage program - the pipeline supplies the real one.
programObject->Link(false);
// glDetachShader defers the removal to the next link, so the program keeps
// the shader object it was built from while no longer reporting it attached.
DetachShader_State(program, shader);
}
if (shaderObject && programObject && !shaderObject->GetInfoLog().empty()) {
programObject->AppendInfoLog(shaderObject->GetInfoLog());
}
}
DeleteShader_State(shader);
return program;
}
void GetProgramBinary(GLuint program, GLsizei bufSize, GLsizei* length, GLenum* binaryFormat, void* binary) {
(void)binaryFormat;
(void)binary;
auto& programObject = TryToGetProgramObject(program);
if (!programObject) return;
if (bufSize < 0) {
MG_State::pGLContext->RecordError(
ErrorCode::InvalidValue,
MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", __func__, "bufSize must be non-negative."));
return;
}
if (length) *length = 0;
// GL_PROGRAM_BINARY_LENGTH is always zero here, which the spec makes an error to ask for.
MG_State::pGLContext->RecordError(
ErrorCode::InvalidOperation,
MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", __func__, "The program has no retrievable binary."));
}
void ProgramBinary(GLuint program, GLenum binaryFormat, const void* binary, GLsizei length) {
(void)binaryFormat;
(void)binary;
auto& programObject = TryToGetProgramObject(program);
if (!programObject) return;
if (length < 0) {
MG_State::pGLContext->RecordError(
ErrorCode::InvalidValue,
MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", __func__, "length must be non-negative."));
return;
}
// No format is supported, so every binary is rejected - and the program's link status
// has to read FALSE afterwards.
programObject->MarkLinkFailedByProgramBinary();
MG_State::pGLContext->RecordError(
ErrorCode::InvalidEnum,
MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", __func__, "binaryFormat is not a supported format."));
}
void TransformFeedbackVaryings(GLuint program, GLsizei count, const GLchar* const* varyings, GLenum bufferMode) {
auto& programObject = TryToGetProgramObject(program);
if (!programObject) return;
if (bufferMode != GL_INTERLEAVED_ATTRIBS && bufferMode != GL_SEPARATE_ATTRIBS) {
MG_State::pGLContext->RecordError(
ErrorCode::InvalidEnum,
MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", __func__, "bufferMode is not a valid capture mode."));
return;
}
if (count < 0) {
MG_State::pGLContext->RecordError(
ErrorCode::InvalidValue,
MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", __func__, "count must be non-negative."));
return;
}
// GL 3.3 core: SEPARATE_ATTRIBS count may not exceed the separate-attrib limit.
if (bufferMode == GL_SEPARATE_ATTRIBS && count > 4) {
MG_State::pGLContext->RecordError(
ErrorCode::InvalidValue,
MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", __func__,
"count exceeds GL_MAX_TRANSFORM_FEEDBACK_SEPARATE_ATTRIBS."));
return;
}
Vector<String> names;
names.reserve(static_cast<SizeT>(count));
for (GLsizei i = 0; i < count; ++i) {
names.emplace_back(varyings != nullptr && varyings[i] != nullptr ? varyings[i] : "");
}
// ARB_transform_feedback3's special names only mean anything in an interleaved
// capture, and gl_NextBuffer cannot advance past the last capture buffer.
constexpr Uint maxTransformFeedbackBuffers = 4;
Uint nextBufferCount = 0;
for (const String& name : names) {
const Bool isNextBuffer = name == "gl_NextBuffer";
const Bool isSkipComponents = name.size() == 18 && name.compare(0, 17, "gl_SkipComponents") == 0 &&
name[17] >= '1' && name[17] <= '4';
if (!isNextBuffer && !isSkipComponents) continue;
if (bufferMode != GL_INTERLEAVED_ATTRIBS) {
MG_State::pGLContext->RecordError(
ErrorCode::InvalidOperation,
MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", __func__,
"'" + name + "' requires GL_INTERLEAVED_ATTRIBS."));
return;
}
if (isNextBuffer && ++nextBufferCount >= maxTransformFeedbackBuffers) {
MG_State::pGLContext->RecordError(
ErrorCode::InvalidOperation,
MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", __func__,
"More gl_NextBuffer entries than "
"GL_MAX_TRANSFORM_FEEDBACK_BUFFERS allows."));
return;
}
}
programObject->SetTransformFeedbackVaryings(Move(names), bufferMode);
}
void GetTransformFeedbackVarying(GLuint program, GLuint index, GLsizei bufSize, GLsizei* length, GLsizei* size,
GLenum* type, GLchar* name) {
auto& programObject = TryToGetProgramObject(program);
if (!programObject) return;
if (!programObject->GetLinkStatus()) {
MG_State::pGLContext->RecordError(
ErrorCode::InvalidOperation,
MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", __func__,
std::to_string(program) + " has not been successfully linked."));
return;
}
const auto* varying = programObject->GetTransformFeedbackVarying(index);
if (varying == nullptr) {
MG_State::pGLContext->RecordError(
ErrorCode::InvalidValue,
MakeUnique<GenericErrorInfo>(
"MG_Impl/GLImpl", __func__,
"index is not an active transform feedback varying of the program."));
return;
}
if (size != nullptr) *size = varying->size;
if (type != nullptr) *type = varying->type;
GLsizei written = 0;
if (name != nullptr && bufSize > 0) {
written = std::min<GLsizei>(bufSize - 1, static_cast<GLsizei>(varying->name.size()));
Memcpy(name, varying->name.data(), static_cast<SizeT>(written));
name[written] = '\0';
}
if (length != nullptr) *length = written;
}
} // namespace MobileGL::MG_Impl::GLImpl
@@ -137,47 +137,5 @@ namespace MobileGL::MG_Impl::GLImpl {
GLint GetProgramResourceLocation(GLuint program, GLenum programInterface, const GLchar* name);
GLint GetProgramResourceLocationIndex(GLuint program, GLenum programInterface, const GLchar* name);
void ShaderStorageBlockBinding(GLuint program, GLuint storageBlockIndex, GLuint storageBlockBinding);
void Uniform1d(GLint location, GLdouble v0);
void Uniform1dv(GLint location, GLsizei count, const GLdouble* value);
void ProgramUniform1d(GLuint program, GLint location, GLdouble v0);
void ProgramUniform1dv(GLuint program, GLint location, GLsizei count, const GLdouble* value);
void Uniform2d(GLint location, GLdouble v0, GLdouble v1);
void Uniform2dv(GLint location, GLsizei count, const GLdouble* value);
void ProgramUniform2d(GLuint program, GLint location, GLdouble v0, GLdouble v1);
void ProgramUniform2dv(GLuint program, GLint location, GLsizei count, const GLdouble* value);
void Uniform3d(GLint location, GLdouble v0, GLdouble v1, GLdouble v2);
void Uniform3dv(GLint location, GLsizei count, const GLdouble* value);
void ProgramUniform3d(GLuint program, GLint location, GLdouble v0, GLdouble v1, GLdouble v2);
void ProgramUniform3dv(GLuint program, GLint location, GLsizei count, const GLdouble* value);
void Uniform4d(GLint location, GLdouble v0, GLdouble v1, GLdouble v2, GLdouble v3);
void Uniform4dv(GLint location, GLsizei count, const GLdouble* value);
void ProgramUniform4d(GLuint program, GLint location, GLdouble v0, GLdouble v1, GLdouble v2, GLdouble v3);
void ProgramUniform4dv(GLuint program, GLint location, GLsizei count, const GLdouble* value);
void UniformMatrix2dv(GLint location, GLsizei count, GLboolean transpose, const GLdouble* value);
void ProgramUniformMatrix2dv(GLuint program, GLint location, GLsizei count, GLboolean transpose, const GLdouble* value);
void UniformMatrix3dv(GLint location, GLsizei count, GLboolean transpose, const GLdouble* value);
void ProgramUniformMatrix3dv(GLuint program, GLint location, GLsizei count, GLboolean transpose, const GLdouble* value);
void UniformMatrix4dv(GLint location, GLsizei count, GLboolean transpose, const GLdouble* value);
void ProgramUniformMatrix4dv(GLuint program, GLint location, GLsizei count, GLboolean transpose, const GLdouble* value);
void UniformMatrix2x3dv(GLint location, GLsizei count, GLboolean transpose, const GLdouble* value);
void ProgramUniformMatrix2x3dv(GLuint program, GLint location, GLsizei count, GLboolean transpose, const GLdouble* value);
void UniformMatrix2x4dv(GLint location, GLsizei count, GLboolean transpose, const GLdouble* value);
void ProgramUniformMatrix2x4dv(GLuint program, GLint location, GLsizei count, GLboolean transpose, const GLdouble* value);
void UniformMatrix3x2dv(GLint location, GLsizei count, GLboolean transpose, const GLdouble* value);
void ProgramUniformMatrix3x2dv(GLuint program, GLint location, GLsizei count, GLboolean transpose, const GLdouble* value);
void UniformMatrix3x4dv(GLint location, GLsizei count, GLboolean transpose, const GLdouble* value);
void ProgramUniformMatrix3x4dv(GLuint program, GLint location, GLsizei count, GLboolean transpose, const GLdouble* value);
void UniformMatrix4x2dv(GLint location, GLsizei count, GLboolean transpose, const GLdouble* value);
void ProgramUniformMatrix4x2dv(GLuint program, GLint location, GLsizei count, GLboolean transpose, const GLdouble* value);
void UniformMatrix4x3dv(GLint location, GLsizei count, GLboolean transpose, const GLdouble* value);
void ProgramUniformMatrix4x3dv(GLuint program, GLint location, GLsizei count, GLboolean transpose, const GLdouble* value);
void GetUniformdv(GLuint program, GLint location, GLdouble* params);
void ValidateProgram(GLuint program);
void ProgramParameteri(GLuint program, GLenum pname, GLint value);
GLuint CreateShaderProgramv(GLenum type, GLsizei count, const GLchar* const* strings);
void GetProgramBinary(GLuint program, GLsizei bufSize, GLsizei* length, GLenum* binaryFormat, void* binary);
void ProgramBinary(GLuint program, GLenum binaryFormat, const void* binary, GLsizei length);
void TransformFeedbackVaryings(GLuint program, GLsizei count, const GLchar* const* varyings, GLenum bufferMode);
void GetTransformFeedbackVarying(GLuint program, GLuint index, GLsizei bufSize, GLsizei* length, GLsizei* size,
GLenum* type, GLchar* name);
} // namespace MobileGL::MG_Impl::GLImpl
@@ -1,231 +0,0 @@
// MobileGL - MobileGL/MG_Impl/GLImpl/Program/GL_ProgramPipeline.cpp
// Copyright (c) 2025-2026 MobileGL-Dev
// Licensed under the GNU Lesser General Public License v3.0:
// https://www.gnu.org/licenses/gpl-3.0.txt
// https://www.gnu.org/licenses/lgpl-3.0.txt
// SPDX-License-Identifier: LGPL-3.0-only
// End of Source File Header
#include "GL_ProgramPipeline.h"
#include <MG_State/GLState/Core.h>
#include <MG_State/GLState/ErrorState/ErrorInfo.h>
#include <MG_Util/Converters/GLToStr/GLEnumConverter.h>
namespace MobileGL::MG_Impl::GLImpl {
namespace {
void RecordPipelineError(ErrorCode code, const char* function, String message) {
MG_State::pGLContext->RecordError(
code, MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", function, Move(message)));
}
// A pipeline name only names an object once it has been bound or created; querying a
// reserved-but-unmaterialised name is INVALID_OPERATION (GL 4.6 core 7.4).
const SharedPtr<MG_State::GLState::ProgramPipelineObject>* TryGetPipeline(GLuint pipeline,
const char* function) {
if (!MG_State::pGLContext->IsProgramPipelineObject(pipeline)) {
RecordPipelineError(ErrorCode::InvalidOperation, function,
std::format("Program pipeline {} does not exist.", pipeline));
return nullptr;
}
return &MG_State::pGLContext->GetProgramPipelineObject(pipeline);
}
Bool ValidatePipelineCount(GLsizei n, const char* function) {
if (n < 0) {
RecordPipelineError(ErrorCode::InvalidValue, function, "n must be non-negative.");
return false;
}
return true;
}
// GL 4.6 core table 7.1 maps each stage bit onto a shader stage.
Bool TryResolveStageBit(GLbitfield bit, ShaderStage& outStage) {
switch (bit) {
case GL_VERTEX_SHADER_BIT: outStage = ShaderStage::Vertex; return true;
case GL_TESS_CONTROL_SHADER_BIT: outStage = ShaderStage::TessControl; return true;
case GL_TESS_EVALUATION_SHADER_BIT: outStage = ShaderStage::TessEval; return true;
case GL_GEOMETRY_SHADER_BIT: outStage = ShaderStage::Geometry; return true;
case GL_FRAGMENT_SHADER_BIT: outStage = ShaderStage::Fragment; return true;
case GL_COMPUTE_SHADER_BIT: outStage = ShaderStage::Compute; return true;
default: return false;
}
}
constexpr GLbitfield kAllStageBits = GL_VERTEX_SHADER_BIT | GL_TESS_CONTROL_SHADER_BIT |
GL_TESS_EVALUATION_SHADER_BIT | GL_GEOMETRY_SHADER_BIT |
GL_FRAGMENT_SHADER_BIT | GL_COMPUTE_SHADER_BIT;
} // namespace
void GenProgramPipelines(GLsizei n, GLuint* pipelines) {
if (!ValidatePipelineCount(n, __func__)) return;
if (n == 0 || !pipelines) return;
static thread_local Vector<GLuint> names;
MG_State::pGLContext->GenProgramPipelineNames(static_cast<Uint>(n), names);
Memcpy(pipelines, names.data(), static_cast<SizeT>(n) * sizeof(GLuint));
}
void CreateProgramPipelines(GLsizei n, GLuint* pipelines) {
if (!ValidatePipelineCount(n, __func__)) return;
if (n == 0 || !pipelines) return;
static thread_local Vector<GLuint> names;
MG_State::pGLContext->GenProgramPipelineNames(static_cast<Uint>(n), names);
for (GLsizei i = 0; i < n; ++i) {
pipelines[i] = names[static_cast<SizeT>(i)];
MG_State::pGLContext->CreateProgramPipelineObject(names[static_cast<SizeT>(i)]);
}
}
void DeleteProgramPipelines(GLsizei n, const GLuint* pipelines) {
if (!ValidatePipelineCount(n, __func__)) return;
if (!pipelines) return;
for (GLsizei i = 0; i < n; ++i) {
// Deleting zero, an unknown name, or a name that was only reserved is silently ignored.
MG_State::pGLContext->MarkProgramPipelineForDeletion(pipelines[i]);
}
}
void BindProgramPipeline(GLuint pipeline) {
if (pipeline != 0 && !MG_State::pGLContext->ValidateProgramPipelineName(pipeline)) {
RecordPipelineError(ErrorCode::InvalidOperation, __func__,
std::format("Program pipeline name {} is not valid.", pipeline));
return;
}
MG_State::pGLContext->BindProgramPipelineObject(pipeline);
}
GLboolean IsProgramPipeline(GLuint pipeline) {
return MG_State::pGLContext->IsProgramPipelineObject(pipeline) ? GL_TRUE : GL_FALSE;
}
void GetProgramPipelineiv(GLuint pipeline, GLenum pname, GLint* params) {
const auto* pipelineObject = TryGetPipeline(pipeline, __func__);
if (!pipelineObject || !params) return;
const auto stageProgramName = [&](ShaderStage stage) -> GLint {
const auto& program = (*pipelineObject)->GetStageProgram(stage);
return program ? static_cast<GLint>(program->GetExternalIndex()) : 0;
};
switch (pname) {
case GL_ACTIVE_PROGRAM: {
const auto& active = (*pipelineObject)->GetActiveProgram();
*params = active ? static_cast<GLint>(active->GetExternalIndex()) : 0;
break;
}
case GL_VERTEX_SHADER: *params = stageProgramName(ShaderStage::Vertex); break;
case GL_TESS_CONTROL_SHADER: *params = stageProgramName(ShaderStage::TessControl); break;
case GL_TESS_EVALUATION_SHADER: *params = stageProgramName(ShaderStage::TessEval); break;
case GL_GEOMETRY_SHADER: *params = stageProgramName(ShaderStage::Geometry); break;
case GL_FRAGMENT_SHADER: *params = stageProgramName(ShaderStage::Fragment); break;
case GL_COMPUTE_SHADER: *params = stageProgramName(ShaderStage::Compute); break;
case GL_VALIDATE_STATUS: *params = (*pipelineObject)->GetValidateStatus() ? GL_TRUE : GL_FALSE; break;
case GL_INFO_LOG_LENGTH: {
// GL counts the null terminator, and reports 0 rather than 1 for an empty log.
const auto& log = (*pipelineObject)->GetInfoLog();
*params = log.empty() ? 0 : static_cast<GLint>(log.length()) + 1;
break;
}
default:
RecordPipelineError(ErrorCode::InvalidEnum, __func__,
std::format("pname {} is not a program pipeline parameter.",
MG_Util::ConvertGLEnumToString(pname)));
break;
}
}
void GetProgramPipelineInfoLog(GLuint pipeline, GLsizei bufSize, GLsizei* length, GLchar* infoLog) {
const auto* pipelineObject = TryGetPipeline(pipeline, __func__);
if (!pipelineObject) return;
if (bufSize < 0) {
RecordPipelineError(ErrorCode::InvalidValue, __func__, "bufSize must be non-negative.");
return;
}
if (bufSize == 0 || !infoLog) {
if (length) *length = 0;
return;
}
const auto& log = (*pipelineObject)->GetInfoLog();
const auto copied = std::min<GLsizei>(bufSize - 1, static_cast<GLsizei>(log.length()));
if (copied > 0) Memcpy(infoLog, log.data(), static_cast<SizeT>(copied));
infoLog[copied] = '\0';
if (length) *length = copied;
}
void UseProgramStages(GLuint pipeline, GLbitfield stages, GLuint program) {
if (stages != GL_ALL_SHADER_BITS && (stages & ~kAllStageBits) != 0) {
RecordPipelineError(ErrorCode::InvalidValue, __func__, "stages names a bit that is not a shader stage.");
return;
}
const auto* pipelineObject = TryGetPipeline(pipeline, __func__);
if (!pipelineObject) return;
SharedPtr<MG_State::GLState::ProgramObject> programObject;
if (program != 0) {
if (!MG_State::pGLContext->ValidateProgramName(program)) {
RecordPipelineError(ErrorCode::InvalidValue, __func__,
std::format("{} is not the name of a program object.", program));
return;
}
programObject = MG_State::pGLContext->GetProgramObject(program);
if (!programObject) {
RecordPipelineError(ErrorCode::InvalidValue, __func__,
std::format("{} is not the name of a program object.", program));
return;
}
if (!programObject->GetLinkStatus()) {
RecordPipelineError(ErrorCode::InvalidOperation, __func__,
std::format("Program {} has not been linked successfully.", program));
return;
}
}
const GLbitfield selected = stages == GL_ALL_SHADER_BITS ? kAllStageBits : stages;
for (GLbitfield bit = 1; bit != 0 && bit <= kAllStageBits; bit <<= 1) {
if ((selected & bit) == 0) continue;
ShaderStage stage = ShaderStage::Unknown;
if (!TryResolveStageBit(bit, stage)) continue;
// program == 0 clears the stage, which is what a null program reference means here.
(*pipelineObject)->SetStageProgram(stage, programObject);
}
}
void ActiveShaderProgram(GLuint pipeline, GLuint program) {
const auto* pipelineObject = TryGetPipeline(pipeline, __func__);
if (!pipelineObject) return;
if (program == 0) {
(*pipelineObject)->SetActiveProgram(nullptr);
return;
}
if (!MG_State::pGLContext->ValidateProgramName(program)) {
RecordPipelineError(ErrorCode::InvalidValue, __func__,
std::format("{} is not the name of a program object.", program));
return;
}
auto programObject = MG_State::pGLContext->GetProgramObject(program);
if (!programObject) {
RecordPipelineError(ErrorCode::InvalidValue, __func__,
std::format("{} is not the name of a program object.", program));
return;
}
if (!programObject->GetLinkStatus()) {
RecordPipelineError(ErrorCode::InvalidOperation, __func__,
std::format("Program {} has not been linked successfully.", program));
return;
}
(*pipelineObject)->SetActiveProgram(programObject);
}
void ValidateProgramPipeline(GLuint pipeline) {
const auto* pipelineObject = TryGetPipeline(pipeline, __func__);
if (!pipelineObject) return;
// Nothing here can fail today: MobileGL links each stage program on its own, so there is no
// cross-stage interface to re-check at validation time. The log stays empty, which GL allows.
(*pipelineObject)->SetValidateStatus(true);
}
} // namespace MobileGL::MG_Impl::GLImpl
@@ -1,23 +0,0 @@
// MobileGL - MobileGL/MG_Impl/GLImpl/Program/GL_ProgramPipeline.h
// Copyright (c) 2025-2026 MobileGL-Dev
// Licensed under the GNU Lesser General Public License v3.0:
// https://www.gnu.org/licenses/gpl-3.0.txt
// https://www.gnu.org/licenses/lgpl-3.0.txt
// SPDX-License-Identifier: LGPL-3.0-only
// End of Source File Header
#pragma once
#include <Includes.h>
namespace MobileGL::MG_Impl::GLImpl {
void GenProgramPipelines(GLsizei n, GLuint* pipelines);
void CreateProgramPipelines(GLsizei n, GLuint* pipelines);
void DeleteProgramPipelines(GLsizei n, const GLuint* pipelines);
void BindProgramPipeline(GLuint pipeline);
GLboolean IsProgramPipeline(GLuint pipeline);
void GetProgramPipelineiv(GLuint pipeline, GLenum pname, GLint* params);
void GetProgramPipelineInfoLog(GLuint pipeline, GLsizei bufSize, GLsizei* length, GLchar* infoLog);
void UseProgramStages(GLuint pipeline, GLbitfield stages, GLuint program);
void ActiveShaderProgram(GLuint pipeline, GLuint program);
void ValidateProgramPipeline(GLuint pipeline);
} // namespace MobileGL::MG_Impl::GLImpl
+29 -318
View File
@@ -7,7 +7,6 @@
// End of Source File Header
#include "GL_Query.h"
#include "../Getter/GL_Getter.h"
#include <Config.h>
#include <MG_Backend/BackendObjects.h>
#include <MG_State/GLState/Core.h>
@@ -23,16 +22,11 @@ namespace MobileGL::MG_Impl::GLImpl {
struct QueryObject {
GLuint id = 0;
GLenum target = 0; // 0 = gen'd but never used with BeginQuery/QueryCounter
// glCreateQueries makes the object outright; glGenQueries only reserves the name,
// and the object appears when the name is first used (GL 4.6 core 4.2.1).
Bool created = false;
MG_Backend::BackendQueryHandle backendHandle = nullptr;
Bool active = false;
Bool ended = false;
Bool resultCached = false;
Uint64 cachedResult = 0;
// Transform feedback primitive counter at BeginQuery time.
Uint64 counterSnapshot = 0;
};
// Query calls may arrive from any thread (launchers migrate the context
@@ -47,11 +41,6 @@ namespace MobileGL::MG_Impl::GLImpl {
GLuint g_nextQueryId = 1;
// Id of the query currently active on GL_TIME_ELAPSED (0 = none).
GLuint g_activeTimeElapsedQueryId = 0;
// Ids of the queries active on the transform feedback targets (0 = none).
GLuint g_activePrimitivesWrittenQueryId = 0;
GLuint g_activePrimitivesGeneratedQueryId = 0;
// Id of the query active on GL_SAMPLES_PASSED (0 = none).
GLuint g_activeSamplesPassedQueryId = 0;
Bool TimerQueryDisabled() {
return MG_Config::Features.DisableTimerQuery;
@@ -62,34 +51,6 @@ namespace MobileGL::MG_Impl::GLImpl {
MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", function, message));
}
// The by-buffer query getters write the result into a buffer object instead of client
// memory. Everything about the query itself - the name, whether it is still active, the
// parameter - is checked by GetQueryObjectValue; what is left is the destination, so this
// resolves the buffer and confirms the write lands inside it (GL 4.6 core 4.2.1).
Bool ResolveQueryResultDestination(GLuint buffer, GLintptr offset, SizeT writeSize, const char* function,
SharedPtr<MG_State::GLState::BufferObject>& outBuffer) {
if (offset < 0) {
RecordQueryError(ErrorCode::InvalidValue, function, "Offset cannot be negative.");
return false;
}
if (!MG_State::pGLContext->ValidateBufferObject(buffer)) {
RecordQueryError(ErrorCode::InvalidOperation, function, "Buffer object does not exist.");
return false;
}
auto bufferObject = MG_State::pGLContext->GetBufferObject(buffer);
if (!bufferObject) {
RecordQueryError(ErrorCode::InvalidOperation, function, "Buffer object does not exist.");
return false;
}
if (static_cast<SizeT>(offset) + writeSize > bufferObject->GetSize()) {
RecordQueryError(ErrorCode::InvalidOperation, function,
"The query result does not fit in the buffer object at this offset.");
return false;
}
outBuffer = bufferObject;
return true;
}
// Callers must hold g_queryObjectsMutex.
QueryObject* FindQueryObjectLocked(GLuint id) {
const auto it = g_liveQueryObjects.find(id);
@@ -123,13 +84,8 @@ namespace MobileGL::MG_Impl::GLImpl {
}
// Shared GetQueryObject* implementation. Returns false when an error
// was recorded and no value should be written back. `outValueProduced`, when given,
// additionally distinguishes "succeeded with a value" from "succeeded but the result is not
// ready" - the GL_QUERY_RESULT_NO_WAIT case, where GL_ARB_query_buffer_object says the
// destination is left alone rather than written with a placeholder.
Bool GetQueryObjectValue(GLuint id, GLenum pname, const char* function, Uint64& outValue,
Bool* outValueProduced = nullptr) {
if (outValueProduced) *outValueProduced = true;
// was recorded and no value should be written back.
Bool GetQueryObjectValue(GLuint id, GLenum pname, const char* function, Uint64& outValue) {
const std::lock_guard<std::mutex> lock(g_queryObjectsMutex);
auto* queryObject = FindQueryObjectLocked(id);
if (!queryObject) {
@@ -142,41 +98,6 @@ namespace MobileGL::MG_Impl::GLImpl {
}
switch (pname) {
case GL_QUERY_TARGET:
// The target a query was begun with (or created with, for glCreateQueries) - state
// the object has carried all along, GL 4.6 core table 23.35.
outValue = queryObject->target;
return true;
case GL_QUERY_RESULT_NO_WAIT: {
if (queryObject->resultCached) {
outValue = queryObject->cachedResult;
return true;
}
Uint64 result = 0;
const auto getQueryResult64 = MG_Backend::gBackendFunctionsTable.GL.GetQueryResult64;
if (queryObject->backendHandle && getQueryResult64 &&
!getQueryResult64(queryObject->backendHandle, /*wait=*/false, &result)) {
// Not ready. The whole point of the no-wait form is that the caller's
// destination keeps whatever it already held.
if (outValueProduced) *outValueProduced = false;
outValue = 0;
return true;
}
if (queryObject->target == GL_ANY_SAMPLES_PASSED ||
queryObject->target == GL_ANY_SAMPLES_PASSED_CONSERVATIVE) {
result = result != 0 ? 1 : 0;
}
if (queryObject->backendHandle) {
if (const auto deleteBackendQuery = MG_Backend::gBackendFunctionsTable.GL.DeleteBackendQuery) {
deleteBackendQuery(queryObject->backendHandle);
}
queryObject->backendHandle = nullptr;
}
queryObject->cachedResult = result;
queryObject->resultCached = true;
outValue = result;
return true;
}
case GL_QUERY_RESULT_AVAILABLE: {
if (queryObject->resultCached || !queryObject->backendHandle) {
outValue = 1;
@@ -205,11 +126,6 @@ namespace MobileGL::MG_Impl::GLImpl {
outValue = 0;
return true;
}
// ANY_SAMPLES_PASSED* report a boolean.
if (queryObject->target == GL_ANY_SAMPLES_PASSED ||
queryObject->target == GL_ANY_SAMPLES_PASSED_CONSERVATIVE) {
result = result != 0 ? 1 : 0;
}
// Final value produced (or no GetQueryResult64 hook: the
// query degrades to a zero result); the backend handle is
// consumed and the value cached for later reads.
@@ -228,21 +144,6 @@ namespace MobileGL::MG_Impl::GLImpl {
return false;
}
}
template <typename T>
void GetQueryBufferObject(GLuint id, GLuint buffer, GLenum pname, GLintptr offset, const char* function) {
SharedPtr<MG_State::GLState::BufferObject> bufferObject;
if (!ResolveQueryResultDestination(buffer, offset, sizeof(T), function, bufferObject)) return;
Uint64 value = 0;
Bool valueProduced = false;
if (!GetQueryObjectValue(id, pname, function, value, &valueProduced)) return;
// GL_QUERY_RESULT_NO_WAIT on a result that has not landed writes nothing at all.
if (!valueProduced) return;
const T narrowed = static_cast<T>(value);
bufferObject->UploadSubData({const_cast<T*>(&narrowed), sizeof(T)}, static_cast<SizeT>(offset));
}
} // namespace
void GenQueries(GLsizei n, GLuint* ids) {
@@ -263,41 +164,6 @@ namespace MobileGL::MG_Impl::GLImpl {
}
}
// glCreateQueries differs from glGenQueries in creating the objects outright, with their
// target already fixed and the rest of their state at the defaults (GL 4.6 core 4.2.1).
void CreateQueries(GLenum target, GLsizei n, GLuint* ids) {
switch (target) {
case GL_SAMPLES_PASSED:
case GL_ANY_SAMPLES_PASSED:
case GL_ANY_SAMPLES_PASSED_CONSERVATIVE:
case GL_TIME_ELAPSED:
case GL_TIMESTAMP:
case GL_PRIMITIVES_GENERATED:
case GL_TRANSFORM_FEEDBACK_PRIMITIVES_WRITTEN:
break;
default:
RecordQueryError(ErrorCode::InvalidEnum, __FUNCTION__, "Query target is not accepted.");
return;
}
if (n < 0) {
RecordQueryError(ErrorCode::InvalidValue, __FUNCTION__, "n cannot be negative.");
return;
}
if (!ids) {
return;
}
const std::lock_guard<std::mutex> lock(g_queryObjectsMutex);
for (GLsizei i = 0; i < n; ++i) {
const GLuint id = g_nextQueryId++;
auto* queryObject = new QueryObject;
queryObject->id = id;
queryObject->target = target;
queryObject->created = true;
g_liveQueryObjects[id] = queryObject;
ids[i] = id;
}
}
void DeleteQueries(GLsizei n, const GLuint* ids) {
if (n < 0) {
RecordQueryError(ErrorCode::InvalidValue, __FUNCTION__, "n cannot be negative.");
@@ -314,24 +180,7 @@ namespace MobileGL::MG_Impl::GLImpl {
}
QueryObject* queryObject = it->second;
if (queryObject->active) {
// Implicitly end before deletion, releasing the matching active slot.
if (queryObject->target == GL_SAMPLES_PASSED || queryObject->target == GL_ANY_SAMPLES_PASSED ||
queryObject->target == GL_ANY_SAMPLES_PASSED_CONSERVATIVE) {
if (const auto endOcclusionQuery = MG_Backend::gBackendFunctionsTable.GL.EndOcclusionQuery;
endOcclusionQuery && queryObject->backendHandle) {
endOcclusionQuery(queryObject->backendHandle);
}
queryObject->active = false;
g_activeSamplesPassedQueryId = 0;
} else if (queryObject->target == GL_TRANSFORM_FEEDBACK_PRIMITIVES_WRITTEN ||
queryObject->target == GL_PRIMITIVES_GENERATED) {
queryObject->active = false;
(queryObject->target == GL_TRANSFORM_FEEDBACK_PRIMITIVES_WRITTEN
? g_activePrimitivesWrittenQueryId
: g_activePrimitivesGeneratedQueryId) = 0;
} else {
EndTimeElapsedQueryLocked(queryObject);
}
EndTimeElapsedQueryLocked(queryObject); // implicitly end before deletion
}
if (queryObject->backendHandle) {
if (const auto deleteBackendQuery = MG_Backend::gBackendFunctionsTable.GL.DeleteBackendQuery) {
@@ -349,23 +198,16 @@ namespace MobileGL::MG_Impl::GLImpl {
return GL_FALSE;
}
const std::lock_guard<std::mutex> lock(g_queryObjectsMutex);
// A name from glGenQueries is not yet a query object: it becomes one when it is first
// used with BeginQuery/QueryCounter (which is what a non-zero target records), or
// immediately if it came from glCreateQueries.
const auto* queryObject = FindQueryObjectLocked(id);
return (queryObject != nullptr && (queryObject->created || queryObject->target != 0)) ? GL_TRUE : GL_FALSE;
// Gen'd ids count as query objects here: the registry creates live
// objects at GenQueries time.
return FindQueryObjectLocked(id) != nullptr ? GL_TRUE : GL_FALSE;
}
void BeginQuery(GLenum target, GLuint id) {
const Bool isTransformFeedbackQuery =
target == GL_TRANSFORM_FEEDBACK_PRIMITIVES_WRITTEN || target == GL_PRIMITIVES_GENERATED;
const Bool isOcclusionQuery =
(target == GL_SAMPLES_PASSED || target == GL_ANY_SAMPLES_PASSED ||
target == GL_ANY_SAMPLES_PASSED_CONSERVATIVE) &&
MG_Backend::gBackendFunctionsTable.GL.BeginOcclusionQuery != nullptr;
if (target != GL_TIME_ELAPSED && !isTransformFeedbackQuery && !isOcclusionQuery) {
// GL_TIMESTAMP is not a valid BeginQuery target; the occlusion targets
// need backend support.
if (target != GL_TIME_ELAPSED) {
// Only GL_TIME_ELAPSED timer queries are implemented (occlusion and
// primitive queries remain stubs); GL_TIMESTAMP is not a valid
// BeginQuery target either.
RecordQueryError(ErrorCode::InvalidEnum, __FUNCTION__, "Query target is not supported.");
return;
}
@@ -379,13 +221,9 @@ namespace MobileGL::MG_Impl::GLImpl {
RecordQueryError(ErrorCode::InvalidOperation, __FUNCTION__, "Query object does not exist.");
return;
}
GLuint& activeQueryId = isTransformFeedbackQuery
? (target == GL_TRANSFORM_FEEDBACK_PRIMITIVES_WRITTEN ? g_activePrimitivesWrittenQueryId
: g_activePrimitivesGeneratedQueryId)
: (isOcclusionQuery ? g_activeSamplesPassedQueryId : g_activeTimeElapsedQueryId);
if (activeQueryId != 0) {
if (g_activeTimeElapsedQueryId != 0) {
RecordQueryError(ErrorCode::InvalidOperation, __FUNCTION__,
"A query is already active on this target.");
"A query is already active on GL_TIME_ELAPSED.");
return;
}
if (queryObject->active) {
@@ -401,72 +239,25 @@ namespace MobileGL::MG_Impl::GLImpl {
ResetQueryObjectLocked(queryObject); // discard any previous result
queryObject->target = target;
queryObject->active = true;
if (isTransformFeedbackQuery) {
// Prefer real GPU transform-feedback queries (exact with geometry shaders);
// the CPU accounting delta stays as the fallback when the backend lacks them.
const auto beginXfbPrimitivesQuery = MG_Backend::gBackendFunctionsTable.GL.BeginXfbPrimitivesQuery;
queryObject->backendHandle =
beginXfbPrimitivesQuery ? beginXfbPrimitivesQuery(target == GL_PRIMITIVES_GENERATED) : nullptr;
queryObject->counterSnapshot = MG_State::pGLContext->GetTransformFeedbackPrimitiveCounter();
} else if (isOcclusionQuery) {
queryObject->backendHandle = MG_Backend::gBackendFunctionsTable.GL.BeginOcclusionQuery();
} else {
const auto beginTimeElapsedQuery = MG_Backend::gBackendFunctionsTable.GL.BeginTimeElapsedQuery;
queryObject->backendHandle =
(!TimerQueryDisabled() && beginTimeElapsedQuery) ? beginTimeElapsedQuery() : nullptr;
}
activeQueryId = id;
const auto beginTimeElapsedQuery = MG_Backend::gBackendFunctionsTable.GL.BeginTimeElapsedQuery;
queryObject->backendHandle =
(!TimerQueryDisabled() && beginTimeElapsedQuery) ? beginTimeElapsedQuery() : nullptr;
g_activeTimeElapsedQueryId = id;
}
void EndQuery(GLenum target) {
const Bool isTransformFeedbackQuery =
target == GL_TRANSFORM_FEEDBACK_PRIMITIVES_WRITTEN || target == GL_PRIMITIVES_GENERATED;
const Bool isOcclusionQuery =
(target == GL_SAMPLES_PASSED || target == GL_ANY_SAMPLES_PASSED ||
target == GL_ANY_SAMPLES_PASSED_CONSERVATIVE) &&
MG_Backend::gBackendFunctionsTable.GL.BeginOcclusionQuery != nullptr;
if (target != GL_TIME_ELAPSED && !isTransformFeedbackQuery && !isOcclusionQuery) {
if (target != GL_TIME_ELAPSED) {
RecordQueryError(ErrorCode::InvalidEnum, __FUNCTION__, "Query target is not supported.");
return;
}
const std::lock_guard<std::mutex> lock(g_queryObjectsMutex);
GLuint& activeQueryId = isTransformFeedbackQuery
? (target == GL_TRANSFORM_FEEDBACK_PRIMITIVES_WRITTEN ? g_activePrimitivesWrittenQueryId
: g_activePrimitivesGeneratedQueryId)
: (isOcclusionQuery ? g_activeSamplesPassedQueryId : g_activeTimeElapsedQueryId);
if (activeQueryId == 0) {
RecordQueryError(ErrorCode::InvalidOperation, __FUNCTION__, "No query is active on this target.");
if (g_activeTimeElapsedQueryId == 0) {
RecordQueryError(ErrorCode::InvalidOperation, __FUNCTION__, "No query is active on GL_TIME_ELAPSED.");
return;
}
auto* queryObject = FindQueryObjectLocked(activeQueryId);
auto* queryObject = FindQueryObjectLocked(g_activeTimeElapsedQueryId);
if (!queryObject) {
activeQueryId = 0; // should not happen; keep state consistent
return;
}
if (isTransformFeedbackQuery) {
if (queryObject->backendHandle) {
if (const auto endXfbPrimitivesQuery = MG_Backend::gBackendFunctionsTable.GL.EndXfbPrimitivesQuery) {
endXfbPrimitivesQuery(queryObject->backendHandle);
}
// Result comes from the GPU query at read time.
} else {
queryObject->cachedResult =
MG_State::pGLContext->GetTransformFeedbackPrimitiveCounter() - queryObject->counterSnapshot;
queryObject->resultCached = true;
}
queryObject->active = false;
queryObject->ended = true;
activeQueryId = 0;
return;
}
if (isOcclusionQuery) {
if (const auto endOcclusionQuery = MG_Backend::gBackendFunctionsTable.GL.EndOcclusionQuery;
endOcclusionQuery && queryObject->backendHandle) {
endOcclusionQuery(queryObject->backendHandle);
}
queryObject->active = false;
queryObject->ended = true;
activeQueryId = 0;
g_activeTimeElapsedQueryId = 0; // should not happen; keep state consistent
return;
}
EndTimeElapsedQueryLocked(queryObject);
@@ -512,25 +303,9 @@ namespace MobileGL::MG_Impl::GLImpl {
switch (pname) {
case GL_CURRENT_QUERY: {
const std::lock_guard<std::mutex> lock(g_queryObjectsMutex);
switch (target) {
case GL_TIME_ELAPSED:
*params = static_cast<GLint>(g_activeTimeElapsedQueryId);
break;
case GL_SAMPLES_PASSED:
case GL_ANY_SAMPLES_PASSED:
case GL_ANY_SAMPLES_PASSED_CONSERVATIVE:
*params = static_cast<GLint>(g_activeSamplesPassedQueryId);
break;
case GL_TRANSFORM_FEEDBACK_PRIMITIVES_WRITTEN:
*params = static_cast<GLint>(g_activePrimitivesWrittenQueryId);
break;
case GL_PRIMITIVES_GENERATED:
*params = static_cast<GLint>(g_activePrimitivesGeneratedQueryId);
break;
default:
*params = 0;
break;
}
// Only GL_TIME_ELAPSED queries can be active; GL_TIMESTAMP queries
// never are, and other targets remain unimplemented.
*params = target == GL_TIME_ELAPSED ? static_cast<GLint>(g_activeTimeElapsedQueryId) : 0;
return;
}
case GL_QUERY_COUNTER_BITS: {
@@ -538,13 +313,7 @@ namespace MobileGL::MG_Impl::GLImpl {
// time: IsTimerQuerySupported is the dynamic truth (extension /
// entry points / timestamp valid bits at call time, not at table
// init), and the MOBILEGL_DISABLE_TIMERQUERY kill switch always
// wins.
if (target == GL_SAMPLES_PASSED || target == GL_ANY_SAMPLES_PASSED ||
target == GL_ANY_SAMPLES_PASSED_CONSERVATIVE) {
const Bool occlusionSupported = MG_Backend::gBackendFunctionsTable.GL.BeginOcclusionQuery != nullptr;
*params = occlusionSupported ? (target == GL_SAMPLES_PASSED ? 32 : 1) : 0;
return;
}
// wins. Non-timer targets remain unimplemented and report 0.
const Bool timerTarget = target == GL_TIME_ELAPSED || target == GL_TIMESTAMP;
const auto isTimerQuerySupported = MG_Backend::gBackendFunctionsTable.GL.IsTimerQuerySupported;
const Bool supported =
@@ -558,26 +327,9 @@ namespace MobileGL::MG_Impl::GLImpl {
}
}
void GetQueryBufferObjectiv(GLuint id, GLuint buffer, GLenum pname, GLintptr offset) {
GetQueryBufferObject<GLint>(id, buffer, pname, offset, __FUNCTION__);
}
void GetQueryBufferObjectuiv(GLuint id, GLuint buffer, GLenum pname, GLintptr offset) {
GetQueryBufferObject<GLuint>(id, buffer, pname, offset, __FUNCTION__);
}
void GetQueryBufferObjecti64v(GLuint id, GLuint buffer, GLenum pname, GLintptr offset) {
GetQueryBufferObject<GLint64>(id, buffer, pname, offset, __FUNCTION__);
}
void GetQueryBufferObjectui64v(GLuint id, GLuint buffer, GLenum pname, GLintptr offset) {
GetQueryBufferObject<GLuint64>(id, buffer, pname, offset, __FUNCTION__);
}
void GetQueryObjectiv(GLuint id, GLenum pname, GLint* params) {
Uint64 value = 0;
Bool valueProduced = false;
if (!GetQueryObjectValue(id, pname, __FUNCTION__, value, &valueProduced) || !valueProduced || !params) {
if (!GetQueryObjectValue(id, pname, __FUNCTION__, value) || !params) {
return;
}
constexpr Uint64 kMaxInt = static_cast<Uint64>(INT_MAX);
@@ -586,8 +338,7 @@ namespace MobileGL::MG_Impl::GLImpl {
void GetQueryObjectuiv(GLuint id, GLenum pname, GLuint* params) {
Uint64 value = 0;
Bool valueProduced = false;
if (!GetQueryObjectValue(id, pname, __FUNCTION__, value, &valueProduced) || !valueProduced || !params) {
if (!GetQueryObjectValue(id, pname, __FUNCTION__, value) || !params) {
return;
}
*params = static_cast<GLuint>(value & 0xFFFFFFFFull);
@@ -595,8 +346,7 @@ namespace MobileGL::MG_Impl::GLImpl {
void GetQueryObjecti64v(GLuint id, GLenum pname, GLint64* params) {
Uint64 value = 0;
Bool valueProduced = false;
if (!GetQueryObjectValue(id, pname, __FUNCTION__, value, &valueProduced) || !valueProduced || !params) {
if (!GetQueryObjectValue(id, pname, __FUNCTION__, value) || !params) {
return;
}
*params = static_cast<GLint64>(value);
@@ -604,48 +354,9 @@ namespace MobileGL::MG_Impl::GLImpl {
void GetQueryObjectui64v(GLuint id, GLenum pname, GLuint64* params) {
Uint64 value = 0;
Bool valueProduced = false;
if (!GetQueryObjectValue(id, pname, __FUNCTION__, value, &valueProduced) || !valueProduced || !params) {
if (!GetQueryObjectValue(id, pname, __FUNCTION__, value) || !params) {
return;
}
*params = static_cast<GLuint64>(value);
}
namespace {
// The indexed query entry points differ from the plain ones only in the vertex
// stream they address (GL 4.6 core 4.2.1): index must be below GL_MAX_VERTEX_STREAMS
// for the two transform feedback targets and zero for every other target. With a
// single vertex stream both bounds are 1, so a valid call is always index 0 and
// forwards to the unindexed implementation.
Bool ValidateQueryStreamIndex(const char* function, GLenum target, GLuint index) {
const Bool perStreamTarget =
target == GL_PRIMITIVES_GENERATED || target == GL_TRANSFORM_FEEDBACK_PRIMITIVES_WRITTEN;
GLint maxVertexStreams = 1;
if (perStreamTarget) {
GetIntegerv(GL_MAX_VERTEX_STREAMS, &maxVertexStreams);
}
if (index < static_cast<GLuint>(std::max(maxVertexStreams, 1))) {
return true;
}
RecordQueryError(ErrorCode::InvalidValue, function,
perStreamTarget ? "index is not less than GL_MAX_VERTEX_STREAMS."
: "index must be zero for this query target.");
return false;
}
} // namespace
void BeginQueryIndexed(GLenum target, GLuint index, GLuint id) {
if (!ValidateQueryStreamIndex(__FUNCTION__, target, index)) return;
BeginQuery(target, id);
}
void EndQueryIndexed(GLenum target, GLuint index) {
if (!ValidateQueryStreamIndex(__FUNCTION__, target, index)) return;
EndQuery(target);
}
void GetQueryIndexediv(GLenum target, GLuint index, GLenum pname, GLint* params) {
if (!ValidateQueryStreamIndex(__FUNCTION__, target, index)) return;
GetQueryiv(target, pname, params);
}
} // namespace MobileGL::MG_Impl::GLImpl
-8
View File
@@ -11,22 +11,14 @@
namespace MobileGL::MG_Impl::GLImpl {
void GenQueries(GLsizei n, GLuint* ids);
void CreateQueries(GLenum target, GLsizei n, GLuint* ids);
void DeleteQueries(GLsizei n, const GLuint* ids);
GLboolean IsQuery(GLuint id);
void BeginQuery(GLenum target, GLuint id);
void EndQuery(GLenum target);
void GetQueryiv(GLenum target, GLenum pname, GLint* params);
void BeginQueryIndexed(GLenum target, GLuint index, GLuint id);
void EndQueryIndexed(GLenum target, GLuint index);
void GetQueryIndexediv(GLenum target, GLuint index, GLenum pname, GLint* params);
void GetQueryObjectiv(GLuint id, GLenum pname, GLint* params);
void GetQueryObjectuiv(GLuint id, GLenum pname, GLuint* params);
void GetQueryObjecti64v(GLuint id, GLenum pname, GLint64* params);
void GetQueryObjectui64v(GLuint id, GLenum pname, GLuint64* params);
void GetQueryBufferObjectiv(GLuint id, GLuint buffer, GLenum pname, GLintptr offset);
void GetQueryBufferObjectuiv(GLuint id, GLuint buffer, GLenum pname, GLintptr offset);
void GetQueryBufferObjecti64v(GLuint id, GLuint buffer, GLenum pname, GLintptr offset);
void GetQueryBufferObjectui64v(GLuint id, GLuint buffer, GLenum pname, GLintptr offset);
void QueryCounter(GLuint id, GLenum target);
} // namespace MobileGL::MG_Impl::GLImpl
@@ -28,11 +28,6 @@ namespace MobileGL::MG_Impl::GLImpl {
case GL_TEXTURE_MAX_LOD:
case GL_TEXTURE_LOD_BIAS:
return true;
// Four components, and GL puts no range on them - a border colour outside [0,1] is
// clamped when a fixed-point format is sampled, not rejected here. The scalar readers
// below would look at one component and invent an error.
case GL_TEXTURE_BORDER_COLOR:
return true;
case GL_TEXTURE_MAX_ANISOTROPY_EXT:
if (ReadSamplerScalar(param, isFloat, isUnsignedInteger) >= 1.0f) return true;
MG_State::pGLContext->RecordError(
@@ -104,20 +99,6 @@ namespace MobileGL::MG_Impl::GLImpl {
case GL_TEXTURE_COMPARE_FUNC:
samplerObj->SetSamplerCompareFunc(MG_Util::ConvertGLEnumToSamplerCompareFunc(*(const GLint*)param));
break;
case GL_TEXTURE_BORDER_COLOR:
// The only four-component sampler parameter: the caller's form decides which
// representation is authoritative, and SamplerObject keeps the other two in step.
if (isFloat) {
const auto* values = (const GLfloat*)param;
samplerObj->SetBorderColor(FloatVec4(values[0], values[1], values[2], values[3]));
} else if (isUnsignedInteger) {
const auto* values = (const GLuint*)param;
samplerObj->SetBorderColorUI(UintVec4(values[0], values[1], values[2], values[3]));
} else {
const auto* values = (const GLint*)param;
samplerObj->SetBorderColorI(IntVec4(values[0], values[1], values[2], values[3]));
}
break;
default:
MG_State::pGLContext->RecordError(ErrorCode::InvalidEnum,
MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", "SetSamplerParam_State",
@@ -181,31 +162,6 @@ namespace MobileGL::MG_Impl::GLImpl {
case GL_TEXTURE_COMPARE_FUNC:
*(GLuint*)params = MG_Util::ConvertSamplerCompareFuncToGLEnum(samplerObj->GetSamplerCompareFunc());
break;
case GL_TEXTURE_BORDER_COLOR: {
if (isFloat) {
const auto& color = samplerObj->GetBorderColor();
auto* out = (GLfloat*)params;
out[0] = color.x();
out[1] = color.y();
out[2] = color.z();
out[3] = color.w();
} else if (isUnsignedInteger) {
const auto& color = samplerObj->GetBorderColorUI();
auto* out = (GLuint*)params;
out[0] = color.x();
out[1] = color.y();
out[2] = color.z();
out[3] = color.w();
} else {
const auto& color = samplerObj->GetBorderColorI();
auto* out = (GLint*)params;
out[0] = color.x();
out[1] = color.y();
out[2] = color.z();
out[3] = color.w();
}
break;
}
default:
MG_State::pGLContext->RecordError(ErrorCode::InvalidEnum,
MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", "GetSamplerParam_State",
@@ -229,11 +185,6 @@ namespace MobileGL::MG_Impl::GLImpl {
static thread_local Vector<GLuint> names;
MG_State::pGLContext->GenSamplerNames(count, names);
Memcpy(samplers, names.data(), count * sizeof(GLuint));
// Unlike textures/buffers, glGenSamplers CREATES the sampler objects: each name
// is immediately a sampler (glIsSampler == GL_TRUE before any bind).
for (GLsizei i = 0; i < count; ++i) {
MG_State::pGLContext->CreateSamplerObject(names[i]);
}
}
void DeleteSamplers_State(GLsizei count, const GLuint* samplers) {
-29
View File
@@ -133,33 +133,4 @@ namespace MobileGL::MG_Impl::GLImpl {
values[0] = value;
}
}
void DestroyAllSyncObjects() {
// Detach the registry under the lock, release outside it. Entries the app
// already deleted were erased by DeleteSync, so nothing here double-frees;
// a DeleteSync racing this sweep finds an empty registry and returns. A
// thread still blocked inside ClientWaitSync/GetSynciv during teardown
// holds a raw SyncObject* these deletes invalidate - the same undefined
// race an app-driven DeleteSync already has.
UnorderedMap<GLsync, SyncObject*> orphans;
{
const std::lock_guard<std::mutex> lock(g_syncObjectsMutex);
orphans.swap(g_liveSyncObjects);
}
if (orphans.empty()) {
return;
}
// Both backends' DeleteSync only free the heap wrapper once their GL
// context/renderer is gone (generation/current-thread guards), so this is
// safe after the backend has released its EGL resources - but not after
// the function table itself is cleared.
const auto backendDeleteSync = MG_Backend::gBackendFunctionsTable.GL.DeleteSync;
for (const auto& [_, syncObject] : orphans) {
if (backendDeleteSync && syncObject->backendHandle) {
backendDeleteSync(syncObject->backendHandle);
}
delete syncObject;
}
MGLOG_D("DestroyAllSyncObjects: reclaimed %zu sync object(s) the app left undeleted", orphans.size());
}
} // namespace MobileGL::MG_Impl::GLImpl
-8
View File
@@ -16,12 +16,4 @@ namespace MobileGL::MG_Impl::GLImpl {
void WaitSync(GLsync sync, GLbitfield flags, GLuint64 timeout);
void DeleteSync(GLsync sync);
void GetSynciv(GLsync sync, GLenum pname, GLsizei bufSize, GLsizei* length, GLint* values);
// Destroys every still-registered sync object exactly as DeleteSync would.
// GL requires syncs to die with their context; called only from full library
// teardown (DestroyImpl), where no context survives on any thread, so the
// process-global registry can be drained wholesale. Must run while the
// backend function table is still populated: each backend handle has to be
// released by the backend that created it, never by a later re-initialized
// one.
void DestroyAllSyncObjects();
} // namespace MobileGL::MG_Impl::GLImpl
File diff suppressed because it is too large Load Diff
@@ -11,10 +11,6 @@
namespace MobileGL::MG_Impl::GLImpl {
/* @INSERTION_POINT:FUNCTION_DECLARATION@ */
// The sized internal formats a buffer texture accepts (GL 4.6 core table 8.16). The buffer
// clears take the same list, so it is shared rather than written out twice.
Bool IsBufferTextureInternalFormat(GLenum internalformat);
void ClearTexImage(GLuint texture, GLint level, GLenum format, GLenum type, const void* data);
void ClearTexSubImage(GLuint texture, GLint level, GLint xoffset, GLint yoffset, GLint zoffset, GLsizei width,
GLsizei height, GLsizei depth, GLenum format, GLenum type, const void* data);
@@ -46,10 +42,6 @@ namespace MobileGL::MG_Impl::GLImpl {
void GenerateTextureMipmap(GLuint texture);
void BindTextureUnit(GLuint unit, GLuint texture);
void GetTextureImage(GLuint texture, GLint level, GLenum format, GLenum type, GLsizei bufSize, void* pixels);
void GetCompressedTextureImage(GLuint texture, GLint level, GLsizei bufSize, void* pixels);
void TexBufferRange(GLenum target, GLenum internalformat, GLuint buffer, GLintptr offset, GLsizeiptr size);
void TextureBuffer(GLuint texture, GLenum internalformat, GLuint buffer);
void TextureBufferRange(GLuint texture, GLenum internalformat, GLuint buffer, GLintptr offset, GLsizeiptr size);
void GetTextureSubImage(GLuint texture, GLint level, GLint xoffset, GLint yoffset, GLint zoffset, GLsizei width,
GLsizei height, GLsizei depth, GLenum format, GLenum type, GLsizei bufSize, void* pixels);
void GetTextureParameterfv(GLuint texture, GLenum pname, GLfloat* params);
@@ -106,9 +98,6 @@ namespace MobileGL::MG_Impl::GLImpl {
GLsizei width, GLsizei height);
void CopyTexSubImage2D(GLenum target, GLint level, GLint xoffset, GLint yoffset, GLint x, GLint y, GLsizei width,
GLsizei height);
void CopyTextureSubImage1D(GLuint texture, GLint level, GLint xoffset, GLint x, GLint y, GLsizei width);
void CopyTextureSubImage3D(GLuint texture, GLint level, GLint xoffset, GLint yoffset, GLint zoffset, GLint x,
GLint y, GLsizei width, GLsizei height);
void CopyTextureSubImage2D(GLuint texture, GLint level, GLint xoffset, GLint yoffset, GLint x, GLint y,
GLsizei width, GLsizei height);
void CopyTexSubImage1D(GLenum target, GLint level, GLint xoffset, GLint x, GLint y, GLsizei width);
@@ -226,9 +226,6 @@ namespace MobileGL::MG_Impl::GLImpl::TextureImpl {
case TextureInternalFormat::Depth24Stencil8:
case TextureInternalFormat::Depth32FStencil8:
case TextureInternalFormat::DepthStencil:
// Stencil-only is not a colour format either: a colour client format read against a
// STENCIL_INDEX8 texture has to be the same INVALID_OPERATION as against a depth one.
case TextureInternalFormat::StencilIndex8:
return true;
default:
return false;
@@ -353,7 +350,7 @@ namespace MobileGL::MG_Impl::GLImpl::TextureImpl {
return true;
}
Bool ValidateTextureObject(const SharedPtr<MG_State::GLState::ITextureObject>& textureObject) {
Bool ValidateTextureObject(SharedPtr<MG_State::GLState::ITextureObject> textureObject) {
if (!textureObject) {
MG_State::pGLContext->RecordError(
ErrorCode::InvalidOperation,
@@ -376,7 +373,7 @@ namespace MobileGL::MG_Impl::GLImpl::TextureImpl {
return true;
}
Bool ValidateTextureTargetUniformity(const SharedPtr<MG_State::GLState::ITextureObject>& textureObject,
Bool ValidateTextureTargetUniformity(SharedPtr<MG_State::GLState::ITextureObject> textureObject,
TextureTarget target) {
if (!textureObject) return true; // should be created later
TextureTarget prevTarget = textureObject->GetTarget();
@@ -390,7 +387,7 @@ namespace MobileGL::MG_Impl::GLImpl::TextureImpl {
return true;
}
Bool ValidateTextureSubImageOffsets(const SharedPtr<MG_State::GLState::ITextureObject>& textureObject, Int xoffset,
Bool ValidateTextureSubImageOffsets(SharedPtr<MG_State::GLState::ITextureObject> textureObject, Int xoffset,
Int width, Int yoffset, Int height, Int zoffset, Int depth) {
auto baseSize = textureObject->GetBaseSize();
if (xoffset < 0 || (xoffset + width) > baseSize.x()) {
+3 -3
View File
@@ -30,15 +30,15 @@ namespace MobileGL::MG_Impl::GLImpl::TextureImpl {
TextureInternalFormat internalFormat,
TexturePixelDataType type);
Bool ValidateTextureLevelWithUploadTarget(TextureUploadTarget target, Int level);
Bool ValidateTextureObject(const SharedPtr<MG_State::GLState::ITextureObject>& textureObject);
Bool ValidateTextureObject(SharedPtr<MG_State::GLState::ITextureObject> textureObject);
// Rejects the per-target default texture objects (name 0) with GL_INVALID_OPERATION for entry
// points that require a GenTextures-created texture, e.g. TexStorage* ("An INVALID_OPERATION
// error is generated if zero is bound to target", ARB_texture_storage).
Bool ValidateTextureNotDefault(const SharedPtr<MG_State::GLState::ITextureObject>& textureObject,
const char* caller);
Bool ValidateTextureTargetUniformity(const SharedPtr<MG_State::GLState::ITextureObject>& textureObject,
Bool ValidateTextureTargetUniformity(SharedPtr<MG_State::GLState::ITextureObject> textureObject,
TextureTarget target);
Bool ValidateTextureSubImageOffsets(const SharedPtr<MG_State::GLState::ITextureObject>& textureObject, Int xoffset,
Bool ValidateTextureSubImageOffsets(SharedPtr<MG_State::GLState::ITextureObject> textureObject, Int xoffset,
Int width, Int yoffset = 0, Int height = 0, Int zoffset = 0, Int depth = 0);
Bool ValidateBaseInternalFormatMatch(TextureInternalFormat format1, TextureInternalFormat format2);
} // namespace MobileGL::MG_Impl::GLImpl::TextureImpl
@@ -8,7 +8,6 @@
#include "GL_VertexArray.h"
#include "Validators.h"
#include <MG_Backend/BackendObjects.h>
#include <MG_Impl/GLImpl/Buffer/Validators.h>
#include <MG_State/GLState/Core.h>
#include <MG_State/GLState/ErrorState/Error.h>
@@ -106,45 +105,12 @@ namespace MobileGL::MG_Impl::GLImpl {
return pname == GL_CURRENT_VERTEX_ATTRIB;
}
// The stride a pointer-style call gives its binding point: the argument when it is non-zero,
// otherwise the tightly packed element size (GL 4.6 core 10.3.2). A packed 2_10_10_10 or
// 10F_11F_11F attribute is one 32-bit word regardless of its component count.
static int EffectiveVertexStride(GLsizei stride, GLint size, GLenum type) {
if (stride != 0) return static_cast<int>(stride);
switch (type) {
case GL_INT_2_10_10_10_REV:
case GL_UNSIGNED_INT_2_10_10_10_REV:
case GL_UNSIGNED_INT_10F_11F_11F_REV:
return 4;
default:
break;
}
return static_cast<int>(size * MG_Util::GetGLTypeSize(type));
}
// glBindVertexBuffers / glVertexArrayVertexBuffers take a range of binding points, and a
// range that runs past the last one is INVALID_OPERATION rather than the INVALID_VALUE a
// single out-of-range index gets (GL 4.6 core 10.3.1).
static bool ValidateVertexBindingRange(GLuint first, GLsizei count, const char* funcName) {
if (count < 0) {
MG_State::pGLContext->RecordError(
ErrorCode::InvalidValue,
MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", funcName, "count must be non-negative."));
return false;
}
if (static_cast<Uint64>(first) + static_cast<Uint64>(count) >
VertexArrayImpl::GetMaxVertexAttribBindings()) {
MG_State::pGLContext->RecordError(
ErrorCode::InvalidOperation,
MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", funcName,
"first + count exceeds GL_MAX_VERTEX_ATTRIB_BINDINGS."));
return false;
}
return true;
}
static bool ValidateVertexBindingIndex(GLuint bindingindex, const char* funcName) {
if (bindingindex >= VertexArrayImpl::GetMaxVertexAttribBindings()) {
// Bound by the same dynamic limit as attribute indices: the default attribute -> binding
// mapping is the identity, so a binding point the backend cannot address as an attribute
// would resolve into an attribute the backend must then reject on every draw. Real drivers
// likewise report MAX_VERTEX_ATTRIB_BINDINGS == MAX_VERTEX_ATTRIBS.
if (bindingindex >= VertexArrayImpl::GetMaxVertexAttribs()) {
MG_State::pGLContext->RecordError(
ErrorCode::InvalidValue,
MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", funcName,
@@ -174,9 +140,6 @@ namespace MobileGL::MG_Impl::GLImpl {
case GL_CURRENT_VERTEX_ATTRIB:
case GL_VERTEX_ATTRIB_ARRAY_BUFFER_BINDING:
case GL_VERTEX_ATTRIB_ARRAY_INTEGER:
// Core since GL 4.1 (ARB_vertex_attrib_64bit). It was rejected while no attribute could
// ever be long; now that IsLong is real state the pname has to be accepted.
case GL_VERTEX_ATTRIB_ARRAY_LONG:
case GL_VERTEX_ATTRIB_ARRAY_DIVISOR:
case GL_VERTEX_ATTRIB_ARRAY_POINTER:
return true;
@@ -192,17 +155,6 @@ namespace MobileGL::MG_Impl::GLImpl {
SharedPtr<MG_State::GLState::VertexArrayObject> GetNamedVertexArrayObject_State(GLuint vaobj,
const char* caller) {
// Name zero is not a vertex array object in a core profile: it names the default vertex
// array, which the by-name (direct state access) entry points never accept. MobileGL keeps a
// real object at index 0 for the compatibility paths, so the generic name validation below
// would otherwise let it through (GL 4.6 core 10.3.1).
if (vaobj == 0) {
MG_State::pGLContext->RecordError(
ErrorCode::InvalidOperation,
MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", caller,
"Vertex array name 0 is not a vertex array object."));
return nullptr;
}
if (!VertexArrayImpl::ValidateVertexArrayName(vaobj)) return nullptr;
if (!VertexArrayImpl::ValidateVertexArrayObject(vaobj)) return nullptr;
return MG_State::pGLContext->GetVertexArrayObject(vaobj);
@@ -258,7 +210,7 @@ namespace MobileGL::MG_Impl::GLImpl {
DataType dataType = MG_Util::ConvertGLEnumToDataType(type);
// Integer path: never normalized, never BGRA/packed (the validator rejects those).
if (!VertexArrayImpl::ValidateVertexAttribFormat(index, size, type, dataType, false, stride, true)) return;
if (!VertexArrayImpl::ValidateVertexAttribFormat(index, size, dataType, false, stride, true)) return;
auto& vao = MG_State::pGLContext->GetBoundVertexArray();
if (!vao) {
@@ -275,7 +227,6 @@ namespace MobileGL::MG_Impl::GLImpl {
vao->SetAttributeFormat(index, size, dataType, false, stride, offset, true, false);
vao->BindAttributeBuffer(index, vbo);
vao->MirrorPointerIntoBinding(index, vbo, offset, EffectiveVertexStride(stride, size, type));
}
void VertexAttribPointer_State(GLuint index, GLint size, GLenum type, GLboolean normalized, GLsizei stride,
@@ -283,7 +234,7 @@ namespace MobileGL::MG_Impl::GLImpl {
if (!VertexArrayImpl::ValidateVertexAttributeIndex(index)) return;
DataType dataType = MG_Util::ConvertGLEnumToDataType(type);
if (!VertexArrayImpl::ValidateVertexAttribFormat(index, size, type, dataType, normalized == GL_TRUE, stride, false))
if (!VertexArrayImpl::ValidateVertexAttribFormat(index, size, dataType, normalized == GL_TRUE, stride, false))
return;
auto& vao = MG_State::pGLContext->GetBoundVertexArray();
@@ -305,7 +256,6 @@ namespace MobileGL::MG_Impl::GLImpl {
const int effectiveSize = isBgra ? 4 : size;
vao->SetAttributeFormat(index, effectiveSize, dataType, normalized, stride, offset, false, isBgra);
vao->BindAttributeBuffer(index, vbo);
vao->MirrorPointerIntoBinding(index, vbo, offset, EffectiveVertexStride(stride, effectiveSize, type));
}
void BindVertexArray_State(GLuint array) {
@@ -409,13 +359,6 @@ namespace MobileGL::MG_Impl::GLImpl {
MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", caller, "offset and stride must be non-negative."));
return;
}
if (static_cast<Uint>(stride) > VertexArrayImpl::GetMaxVertexAttribStride()) {
MG_State::pGLContext->RecordError(
ErrorCode::InvalidValue,
MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", caller,
"stride exceeds GL_MAX_VERTEX_ATTRIB_STRIDE."));
return;
}
auto bufferObject = GetVertexArrayBufferObject_State(buffer, caller);
if (buffer != 0 && !bufferObject) return;
@@ -433,7 +376,6 @@ namespace MobileGL::MG_Impl::GLImpl {
const GLintptr* offsets, const GLsizei* strides) {
auto vao = GetNamedVertexArrayObject_State(vaobj, "VertexArrayVertexBuffers_State");
if (!vao) return;
if (!ValidateVertexBindingRange(first, count, "VertexArrayVertexBuffers_State")) return;
for (GLsizei i = 0; i < count; ++i) {
if (!buffers) {
VertexBufferBinding_State(vao, first + i, 0, 0, 16, "VertexArrayVertexBuffers_State");
@@ -447,55 +389,12 @@ namespace MobileGL::MG_Impl::GLImpl {
static void VertexAttribFormatSeparate_State(const SharedPtr<MG_State::GLState::VertexArrayObject>& vao,
GLuint attribindex, GLint size, GLenum type, GLboolean normalized,
GLuint relativeoffset, Bool isInteger, const char* caller) {
static_cast<void>(caller);
if (!VertexArrayImpl::ValidateVertexAttributeIndex(attribindex)) return;
DataType dataType = MG_Util::ConvertGLEnumToDataType(type);
// The separate-format entry points take the same size/type rules as the pointer ones,
// GL_BGRA included, so they need the full format validation rather than the pointer-only
// subset - that one reports GL_BGRA as an out-of-range size.
if (!VertexArrayImpl::ValidateVertexAttribFormat(attribindex, size, type, dataType, normalized == GL_TRUE, 0,
isInteger))
return;
if (!VertexArrayImpl::ValidateVertexAttribRelativeOffset(relativeoffset)) return;
if (!VertexArrayImpl::ValidateVertexAttribPointerParams(attribindex, size, dataType, 0)) return;
const Bool isBgra = (size == static_cast<GLint>(GL_BGRA));
vao->SetAttributeFormatSeparate(attribindex, isBgra ? 4 : size, dataType, normalized, isInteger,
relativeoffset, isBgra);
}
// The long (64-bit) attribute format: the values reach the shader as doubles, unconverted
// (GL 4.6 core 10.3.2). ValidateVertexAttribLFormat has already pinned type to GL_DOUBLE, so the
// recorded DataType is always Float64 - what IsLong adds is that this is the *unconverted* form,
// as opposed to VertexAttribFormat(GL_DOUBLE), which asks for a float conversion.
//
// Whether the backend can feed it is detected, not assumed: DirectVulkan needs shaderFloat64,
// and DirectGLES can never have it at all. A backend without it declines here, loudly - GL error
// plus a log line naming the reason - rather than accepting state no draw could honour and
// rendering garbage. The matching startup POST row is in MG_Util/SelfTest/DriverPost.cpp.
static void VertexAttribLFormatSeparate_State(const SharedPtr<MG_State::GLState::VertexArrayObject>& vao,
GLuint attribindex, GLint size, GLenum type,
GLuint relativeoffset) {
if (!VertexArrayImpl::ValidateVertexAttributeIndex(attribindex)) return;
if (!VertexArrayImpl::ValidateVertexAttribLFormat(attribindex, size, type)) return;
if (!VertexArrayImpl::ValidateVertexAttribRelativeOffset(relativeoffset)) return;
if (!MG_Backend::pActiveBackendObject ||
!MG_Backend::pActiveBackendObject->GetDynamicParameters().SupportsFloat64VertexAttributes) {
MGLOG_I("VertexAttribLFormat: attribute %u asked for a 64-bit (GL_DOUBLE) format, but this "
"backend has no double-precision vertex attribute support - see the "
"\"64-bit vertex attributes\" / \"shaderFloat64\" POST row for what that costs",
attribindex);
MG_State::pGLContext->RecordError(
ErrorCode::InvalidOperation,
MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", "VertexAttribLFormat",
"64-bit vertex attributes are not supported by this backend."));
return;
}
vao->SetAttributeFormatSeparate(attribindex, size, MG_Util::ConvertGLEnumToDataType(type),
/*normalized: */ false, /*isInteger: */ false, relativeoffset,
/*isBgra: */ false, /*isLong: */ true);
vao->SetAttributeFormatSeparate(attribindex, size, dataType, normalized, isInteger, relativeoffset);
}
void VertexArrayAttribFormat_State(GLuint vaobj, GLuint attribindex, GLint size, GLenum type,
@@ -938,9 +837,6 @@ namespace MobileGL::MG_Impl::GLImpl {
case GL_VERTEX_ATTRIB_ARRAY_INTEGER:
params[0] = attr->IsInteger ? 1.0f : 0.0f;
return;
case GL_VERTEX_ATTRIB_ARRAY_LONG:
params[0] = attr->IsLong ? 1.0f : 0.0f;
return;
case GL_VERTEX_ATTRIB_ARRAY_DIVISOR:
params[0] = static_cast<GLfloat>(attr->Divisor);
return;
@@ -1001,9 +897,6 @@ namespace MobileGL::MG_Impl::GLImpl {
case GL_VERTEX_ATTRIB_ARRAY_INTEGER:
params[0] = attr->IsInteger ? 1.0 : 0.0;
return;
case GL_VERTEX_ATTRIB_ARRAY_LONG:
params[0] = attr->IsLong ? 1.0 : 0.0;
return;
case GL_VERTEX_ATTRIB_ARRAY_DIVISOR:
params[0] = static_cast<GLdouble>(attr->Divisor);
return;
@@ -1060,9 +953,6 @@ namespace MobileGL::MG_Impl::GLImpl {
case GL_VERTEX_ATTRIB_ARRAY_INTEGER:
params[0] = attr->IsInteger ? GL_TRUE : GL_FALSE;
return;
case GL_VERTEX_ATTRIB_ARRAY_LONG:
params[0] = attr->IsLong ? GL_TRUE : GL_FALSE;
return;
case GL_VERTEX_ATTRIB_ARRAY_DIVISOR:
params[0] = static_cast<GLint>(attr->Divisor);
return;
@@ -1154,82 +1044,6 @@ namespace MobileGL::MG_Impl::GLImpl {
VertexArrayVertexBuffer_State(vaobj, bindingindex, buffer, offset, stride);
}
// glGetVertexArrayiv reports exactly one thing (GL 4.6 core table 23.4): which buffer the
// named vertex array takes its indices from. Everything else about a vertex array is
// per-attribute and belongs to the indexed queries below.
void GetVertexArrayiv(GLuint vaobj, GLenum pname, GLint* param) {
auto vao = GetNamedVertexArrayObject_State(vaobj, __func__);
if (!vao || !param) return;
if (pname != GL_ELEMENT_ARRAY_BUFFER_BINDING) {
MG_State::pGLContext->RecordError(
ErrorCode::InvalidEnum,
MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", __func__,
"pname must be GL_ELEMENT_ARRAY_BUFFER_BINDING."));
return;
}
const auto& indexBuffer = vao->GetIndexBufferBindingSlot().GetBoundObject();
*param = indexBuffer ? static_cast<GLint>(indexBuffer->GetExternalIndex()) : 0;
}
void GetVertexArrayIndexediv(GLuint vaobj, GLuint index, GLenum pname, GLint* param) {
auto vao = GetNamedVertexArrayObject_State(vaobj, __func__);
if (!vao || !param) return;
if (!VertexArrayImpl::ValidateVertexAttributeIndex(index)) return;
const auto& attr = vao->GetAttribute(index);
switch (pname) {
case GL_VERTEX_ATTRIB_ARRAY_ENABLED:
*param = attr.Enabled ? GL_TRUE : GL_FALSE;
return;
case GL_VERTEX_ATTRIB_ARRAY_SIZE:
*param = static_cast<GLint>(attr.Size);
return;
case GL_VERTEX_ATTRIB_ARRAY_STRIDE:
*param = static_cast<GLint>(attr.Stride);
return;
case GL_VERTEX_ATTRIB_ARRAY_TYPE:
*param = static_cast<GLint>(MG_Util::ConvertDataTypeToGLEnum(attr.Type));
return;
case GL_VERTEX_ATTRIB_ARRAY_NORMALIZED:
*param = attr.Normalized ? GL_TRUE : GL_FALSE;
return;
case GL_VERTEX_ATTRIB_ARRAY_INTEGER:
*param = attr.IsInteger ? GL_TRUE : GL_FALSE;
return;
case GL_VERTEX_ATTRIB_ARRAY_LONG:
*param = attr.IsLong ? GL_TRUE : GL_FALSE;
return;
case GL_VERTEX_ATTRIB_ARRAY_DIVISOR:
*param = static_cast<GLint>(attr.Divisor);
return;
case GL_VERTEX_ATTRIB_RELATIVE_OFFSET:
*param = static_cast<GLint>(vao->GetAttributeRelativeOffset(index));
return;
default:
MG_State::pGLContext->RecordError(
ErrorCode::InvalidEnum,
MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", __func__,
"pname is not an accepted indexed vertex array query."));
return;
}
}
// Only GL_VERTEX_BINDING_OFFSET needs 64 bits. Its `index` names a vertex buffer binding
// point directly (GL 4.6 core 10.3.1), not an attribute - unlike every pname the 32-bit
// indexed query above accepts, which is why this one does not go through an attribute's
// binding index.
void GetVertexArrayIndexed64iv(GLuint vaobj, GLuint index, GLenum pname, GLint64* param) {
auto vao = GetNamedVertexArrayObject_State(vaobj, __func__);
if (!vao || !param) return;
if (!VertexArrayImpl::ValidateVertexAttributeIndex(index)) return;
if (pname != GL_VERTEX_BINDING_OFFSET) {
MG_State::pGLContext->RecordError(
ErrorCode::InvalidEnum,
MakeUnique<GenericErrorInfo>("MG_Impl/GLImpl", __func__, "pname must be GL_VERTEX_BINDING_OFFSET."));
return;
}
*param = static_cast<GLint64>(vao->GetBindingPoint(index).Offset);
}
void VertexArrayAttribFormat(GLuint vaobj, GLuint attribindex, GLint size, GLenum type, GLboolean normalized,
GLuint relativeoffset) {
VertexArrayAttribFormat_State(vaobj, attribindex, size, type, normalized, relativeoffset);
@@ -1262,7 +1076,6 @@ namespace MobileGL::MG_Impl::GLImpl {
const GLsizei* strides) {
auto vao = GetBoundVertexArrayOrError("BindVertexBuffers");
if (!vao) return;
if (!ValidateVertexBindingRange(first, count, "BindVertexBuffers")) return;
for (GLsizei i = 0; i < count; ++i) {
if (!buffers) {
VertexBufferBinding_State(vao, first + i, 0, 0, 16, "BindVertexBuffers");
@@ -1287,18 +1100,6 @@ namespace MobileGL::MG_Impl::GLImpl {
"VertexAttribIFormat");
}
void VertexAttribLFormat(GLuint attribindex, GLint size, GLenum type, GLuint relativeoffset) {
auto vao = GetBoundVertexArrayOrError("VertexAttribLFormat");
if (!vao) return;
VertexAttribLFormatSeparate_State(vao, attribindex, size, type, relativeoffset);
}
void VertexArrayAttribLFormat(GLuint vaobj, GLuint attribindex, GLint size, GLenum type, GLuint relativeoffset) {
auto vao = GetNamedVertexArrayObject_State(vaobj, "VertexArrayAttribLFormat");
if (!vao) return;
VertexAttribLFormatSeparate_State(vao, attribindex, size, type, relativeoffset);
}
void VertexAttribBinding(GLuint attribindex, GLuint bindingindex) {
auto vao = GetBoundVertexArrayOrError("VertexAttribBinding");
if (!vao) return;
@@ -92,13 +92,9 @@ namespace MobileGL::MG_Impl::GLImpl {
void EnableVertexArrayAttrib(GLuint vaobj, GLuint index);
void VertexArrayElementBuffer(GLuint vaobj, GLuint buffer);
void VertexArrayVertexBuffer(GLuint vaobj, GLuint bindingindex, GLuint buffer, GLintptr offset, GLsizei stride);
void GetVertexArrayiv(GLuint vaobj, GLenum pname, GLint* param);
void GetVertexArrayIndexediv(GLuint vaobj, GLuint index, GLenum pname, GLint* param);
void GetVertexArrayIndexed64iv(GLuint vaobj, GLuint index, GLenum pname, GLint64* param);
void VertexArrayAttribFormat(GLuint vaobj, GLuint attribindex, GLint size, GLenum type, GLboolean normalized,
GLuint relativeoffset);
void VertexArrayAttribIFormat(GLuint vaobj, GLuint attribindex, GLint size, GLenum type, GLuint relativeoffset);
void VertexArrayAttribLFormat(GLuint vaobj, GLuint attribindex, GLint size, GLenum type, GLuint relativeoffset);
void VertexArrayAttribBinding(GLuint vaobj, GLuint attribindex, GLuint bindingindex);
void VertexArrayBindingDivisor(GLuint vaobj, GLuint bindingindex, GLuint divisor);
void VertexArrayVertexBuffers(GLuint vaobj, GLuint first, GLsizei count, const GLuint* buffers,
@@ -108,7 +104,6 @@ namespace MobileGL::MG_Impl::GLImpl {
const GLsizei* strides);
void VertexAttribFormat(GLuint attribindex, GLint size, GLenum type, GLboolean normalized, GLuint relativeoffset);
void VertexAttribIFormat(GLuint attribindex, GLint size, GLenum type, GLuint relativeoffset);
void VertexAttribLFormat(GLuint attribindex, GLint size, GLenum type, GLuint relativeoffset);
void VertexAttribBinding(GLuint attribindex, GLuint bindingindex);
void VertexBindingDivisor(GLuint bindingindex, GLuint divisor);
void VertexAttribDivisor(GLuint index, GLuint divisor);
@@ -23,18 +23,6 @@ namespace MobileGL::MG_Impl::GLImpl::VertexArrayImpl {
return std::min(static_cast<Uint>(backendLimit), capacity);
}
Uint GetMaxVertexAttribBindings() {
return GetMaxVertexAttribs();
}
Uint GetMaxVertexAttribRelativeOffset() {
return 2047;
}
Uint GetMaxVertexAttribStride() {
return 2048;
}
Bool ValidateVertexArrayName(Uint index) {
Bool isValid = MG_State::pGLContext->ValidateVertexArrayName(index);
if (!isValid) {
@@ -102,31 +90,9 @@ namespace MobileGL::MG_Impl::GLImpl::VertexArrayImpl {
return true;
}
Bool ValidateVertexAttribFormat(Uint index, GLint sizeRaw, GLenum glType, DataType type, Bool normalized,
Int stride, Bool integerPath) {
Bool ValidateVertexAttribFormat(Uint index, GLint sizeRaw, DataType type, Bool normalized, Int stride,
Bool integerPath) {
constexpr const char* fn = "ValidateVertexAttribFormat";
// GL_UNSIGNED_INT_10F_11F_11F_REV is a three-component float-path-only packing that has no
// DataType of its own, so it has to be recognised by name before the conversion below turns
// it into Unknown and reports the wrong error (GL 4.6 core 10.3.2).
if (glType == GL_UNSIGNED_INT_10F_11F_11F_REV) {
if (integerPath) {
MG_State::pGLContext->RecordError(
ErrorCode::InvalidEnum,
MakeUnique<GenericErrorInfo>(
"MG_Impl/GLImpl", fn,
std::format("GL_UNSIGNED_INT_10F_11F_11F_REV is not an integer-path type (attribute {}).",
index)));
return false;
}
if (sizeRaw != 3) {
MG_State::pGLContext->RecordError(
ErrorCode::InvalidOperation,
MakeUnique<GenericErrorInfo>(
"MG_Impl/GLImpl", fn,
std::format("GL_UNSIGNED_INT_10F_11F_11F_REV requires size 3 (attribute {}).", index)));
return false;
}
}
if (type == DataType::Unknown) {
MG_State::pGLContext->RecordError(
ErrorCode::InvalidEnum,
@@ -204,40 +170,4 @@ namespace MobileGL::MG_Impl::GLImpl::VertexArrayImpl {
}
return true;
}
Bool ValidateVertexAttribLFormat(Uint index, GLint size, GLenum type) {
constexpr const char* fn = "ValidateVertexAttribLFormat";
if (size < 1 || size > 4) {
MG_State::pGLContext->RecordError(
ErrorCode::InvalidValue,
MakeUnique<GenericErrorInfo>(
"MG_Impl/GLImpl", fn,
std::format("Invalid size {} for attribute {}. Must be 1-4.", size, index)));
return false;
}
// GL 4.6 core 10.3.2: the long form takes GL_DOUBLE and nothing else.
if (type != GL_DOUBLE) {
MG_State::pGLContext->RecordError(
ErrorCode::InvalidEnum,
MakeUnique<GenericErrorInfo>(
"MG_Impl/GLImpl", fn,
std::format("Type 0x{:X} is not GL_DOUBLE (attribute {}).", type, index)));
return false;
}
return true;
}
Bool ValidateVertexAttribRelativeOffset(Uint relativeOffset) {
const Uint limit = GetMaxVertexAttribRelativeOffset();
if (relativeOffset > limit) {
MG_State::pGLContext->RecordError(
ErrorCode::InvalidValue,
MakeUnique<GenericErrorInfo>(
"MG_Impl/GLImpl", "ValidateVertexAttribRelativeOffset",
std::format("relativeoffset {} exceeds GL_MAX_VERTEX_ATTRIB_RELATIVE_OFFSET ({}).", relativeOffset,
limit)));
return false;
}
return true;
}
} // namespace MobileGL::MG_Impl::GLImpl::VertexArrayImpl
@@ -15,20 +15,6 @@ namespace MobileGL::MG_Impl::GLImpl::VertexArrayImpl {
// capacity). Falls back to the capacity when no backend is active (unit tests).
Uint GetMaxVertexAttribs();
// GL_MAX_VERTEX_ATTRIB_BINDINGS. The default attribute -> binding mapping is the identity, so a
// binding point that cannot also be an attribute index would resolve into an attribute the
// backend has to reject on every draw; real drivers report the two limits equal as well.
Uint GetMaxVertexAttribBindings();
// GL_MAX_VERTEX_ATTRIB_RELATIVE_OFFSET. The relative offset is folded into the resolved
// attribute offset in the frontend and never reaches a backend limit, so this is the value the
// spec requires an implementation to support at minimum (GL 4.6 core table 23.63).
Uint GetMaxVertexAttribRelativeOffset();
// GL_MAX_VERTEX_ATTRIB_STRIDE. Like the relative offset above, the stride never reaches a
// backend limit of its own, so this is the spec minimum (GL 4.6 core table 23.63).
Uint GetMaxVertexAttribStride();
Bool ValidateVertexArrayName(Uint index);
Bool ValidateVertexArrayObject(Uint index);
Bool ValidateVertexAttributeIndex(Uint index);
@@ -36,13 +22,6 @@ namespace MobileGL::MG_Impl::GLImpl::VertexArrayImpl {
// Full glVertexAttribPointer / glVertexAttribIPointer format validation, including the packed
// 2_10_10_10 types and GL_BGRA size. sizeRaw is the untranslated GL size (possibly GL_BGRA);
// integerPath selects the glVertexAttribIPointer rules.
Bool ValidateVertexAttribFormat(Uint index, GLint sizeRaw, GLenum glType, DataType type, Bool normalized,
Int stride, Bool integerPath);
// glVertexAttribLFormat / glVertexArrayAttribLFormat: the only accepted type is GL_DOUBLE and
// the size range is 1-4 (GL_BGRA is a float-path size). Separate from the function above
// because the long path shares none of its type or size rules.
Bool ValidateVertexAttribLFormat(Uint index, GLint size, GLenum type);
// Shared by every *Format entry point: INVALID_VALUE once relativeoffset leaves the range the
// implementation advertises.
Bool ValidateVertexAttribRelativeOffset(Uint relativeOffset);
Bool ValidateVertexAttribFormat(Uint index, GLint sizeRaw, DataType type, Bool normalized, Int stride,
Bool integerPath);
} // namespace MobileGL::MG_Impl::GLImpl::VertexArrayImpl
@@ -15,257 +15,4 @@ MOBILEGL_GLX_API void* glXGetProcAddress(const char* name) {
MOBILEGL_GLX_API void* glXGetProcAddressARB(const char* name) {
return MG_Impl::GLXImpl::GetProcAddressARB(name);
}
#if defined(__linux__) && !defined(__ANDROID__)
#include "../GLXImpl.h"
namespace GLXImpl = MobileGL::MG_Impl::GLXImpl;
// GLX handle/type spellings from GL/glx.h, expressed without including it:
// GLXContext/GLXFBConfig are opaque pointers, drawables are XIDs, Bool is int,
// and XVisualInfo* crosses as void*.
MOBILEGL_GLX_API int glXQueryExtension(Display* dpy, int* errorBase, int* eventBase) {
return GLXImpl::QueryExtension(dpy, errorBase, eventBase);
}
MOBILEGL_GLX_API int glXQueryVersion(Display* dpy, int* major, int* minor) {
return GLXImpl::QueryVersion(dpy, major, minor);
}
MOBILEGL_GLX_API const char* glXQueryExtensionsString(Display* dpy, int screen) {
return GLXImpl::QueryExtensionsString(dpy, screen);
}
MOBILEGL_GLX_API const char* glXGetClientString(Display* dpy, int name) {
return GLXImpl::GetClientString(dpy, name);
}
MOBILEGL_GLX_API const char* glXQueryServerString(Display* dpy, int screen, int name) {
return GLXImpl::QueryServerString(dpy, screen, name);
}
MOBILEGL_GLX_API void** glXGetFBConfigs(Display* dpy, int screen, int* nelements) {
return GLXImpl::GetFBConfigs(dpy, screen, nelements);
}
MOBILEGL_GLX_API void** glXChooseFBConfig(Display* dpy, int screen, const int* attribList,
int* nelements) {
return GLXImpl::ChooseFBConfig(dpy, screen, attribList, nelements);
}
MOBILEGL_GLX_API int glXGetFBConfigAttrib(Display* dpy, void* config, int attribute, int* value) {
return GLXImpl::GetFBConfigAttrib(dpy, config, attribute, value);
}
MOBILEGL_GLX_API void* glXGetVisualFromFBConfig(Display* dpy, void* config) {
return GLXImpl::GetVisualFromFBConfig(dpy, config);
}
MOBILEGL_GLX_API void* glXChooseVisual(Display* dpy, int screen, int* attribList) {
return GLXImpl::ChooseVisual(dpy, screen, attribList);
}
MOBILEGL_GLX_API int glXGetConfig(Display* dpy, void* visualInfo, int attribute, int* value) {
return GLXImpl::GetConfig(dpy, visualInfo, attribute, value);
}
MOBILEGL_GLX_API void* glXCreateContext(Display* dpy, void* visualInfo, void* shareList, int direct) {
return GLXImpl::CreateContext(dpy, visualInfo, shareList, direct);
}
MOBILEGL_GLX_API void* glXCreateNewContext(Display* dpy, void* config, int renderType,
void* shareList, int direct) {
return GLXImpl::CreateNewContext(dpy, config, renderType, shareList, direct);
}
MOBILEGL_GLX_API void* glXCreateContextAttribsARB(Display* dpy, void* config, void* shareContext,
int direct, const int* attribList) {
return GLXImpl::CreateContextAttribsARB(dpy, config, shareContext, direct, attribList);
}
MOBILEGL_GLX_API void glXDestroyContext(Display* dpy, void* context) {
GLXImpl::DestroyContext(dpy, context);
}
MOBILEGL_GLX_API int glXMakeCurrent(Display* dpy, unsigned long drawable, void* context) {
return GLXImpl::MakeCurrent(dpy, drawable, context);
}
MOBILEGL_GLX_API int glXMakeContextCurrent(Display* dpy, unsigned long draw, unsigned long read,
void* context) {
return GLXImpl::MakeContextCurrent(dpy, draw, read, context);
}
MOBILEGL_GLX_API void glXSwapBuffers(Display* dpy, unsigned long drawable) {
GLXImpl::SwapBuffers(dpy, drawable);
}
MOBILEGL_GLX_API unsigned long glXCreateWindow(Display* dpy, void* config, unsigned long window,
const int* attribList) {
return GLXImpl::CreateWindow(dpy, config, window, attribList);
}
MOBILEGL_GLX_API void glXDestroyWindow(Display* dpy, unsigned long window) {
GLXImpl::DestroyWindow(dpy, window);
}
MOBILEGL_GLX_API void* glXGetCurrentContext() {
return GLXImpl::GetCurrentContext();
}
MOBILEGL_GLX_API unsigned long glXGetCurrentDrawable() {
return GLXImpl::GetCurrentDrawable();
}
MOBILEGL_GLX_API unsigned long glXGetCurrentReadDrawable() {
return GLXImpl::GetCurrentReadDrawable();
}
MOBILEGL_GLX_API Display* glXGetCurrentDisplay() {
return GLXImpl::GetCurrentDisplay();
}
MOBILEGL_GLX_API int glXIsDirect(Display* dpy, void* context) {
return GLXImpl::IsDirect(dpy, context);
}
MOBILEGL_GLX_API void glXWaitGL() {
GLXImpl::WaitGL();
}
MOBILEGL_GLX_API void glXWaitX() {
GLXImpl::WaitX();
}
MOBILEGL_GLX_API int glXQueryContext(Display* dpy, void* context, int attribute, int* value) {
return GLXImpl::QueryContext(dpy, context, attribute, value);
}
MOBILEGL_GLX_API void glXQueryDrawable(Display* dpy, unsigned long drawable, int attribute,
unsigned int* value) {
GLXImpl::QueryDrawable(dpy, drawable, attribute, value);
}
MOBILEGL_GLX_API void glXSwapIntervalEXT(Display* dpy, unsigned long drawable, int interval) {
GLXImpl::SwapIntervalEXT(dpy, drawable, interval);
}
MOBILEGL_GLX_API int glXSwapIntervalMESA(unsigned int interval) {
return GLXImpl::SwapIntervalMESA(interval);
}
MOBILEGL_GLX_API int glXGetSwapIntervalMESA() {
return GLXImpl::GetSwapIntervalMESA();
}
MOBILEGL_GLX_API int glXSwapIntervalSGI(int interval) {
return GLXImpl::SwapIntervalSGI(interval);
}
// Legacy entry points some loaders probe for; harmless no-op stubs.
MOBILEGL_GLX_API void glXCopyContext(Display*, void*, void*, unsigned long) {
MGLOG_W("glx: glXCopyContext is not supported");
}
MOBILEGL_GLX_API unsigned long glXCreateGLXPixmap(Display*, void*, unsigned long) {
MGLOG_W("glx: glXCreateGLXPixmap is not supported");
return 0;
}
MOBILEGL_GLX_API void glXDestroyGLXPixmap(Display*, unsigned long) {}
MOBILEGL_GLX_API unsigned long glXCreatePixmap(Display*, void*, unsigned long, const int*) {
MGLOG_W("glx: glXCreatePixmap is not supported");
return 0;
}
MOBILEGL_GLX_API void glXDestroyPixmap(Display*, unsigned long) {}
MOBILEGL_GLX_API unsigned long glXCreatePbuffer(Display*, void*, const int*) {
MGLOG_W("glx: glXCreatePbuffer is not supported");
return 0;
}
MOBILEGL_GLX_API void glXDestroyPbuffer(Display*, unsigned long) {}
MOBILEGL_GLX_API void glXUseXFont(unsigned long, int, int, int) {
MGLOG_W("glx: glXUseXFont is not supported");
}
MOBILEGL_GLX_API void glXSelectEvent(Display*, unsigned long, unsigned long) {}
MOBILEGL_GLX_API void glXGetSelectedEvent(Display*, unsigned long, unsigned long* eventMask) {
if (eventMask) {
*eventMask = 0;
}
}
namespace MobileGL::MG_Impl::GLXImpl {
namespace {
struct GLXEntryPoint {
const char* Name;
void* Proc;
};
const GLXEntryPoint kGLXEntryPoints[] = {
{"glXChooseFBConfig", reinterpret_cast<void*>(glXChooseFBConfig)},
{"glXChooseVisual", reinterpret_cast<void*>(glXChooseVisual)},
{"glXCopyContext", reinterpret_cast<void*>(glXCopyContext)},
{"glXCreateContext", reinterpret_cast<void*>(glXCreateContext)},
{"glXCreateContextAttribsARB", reinterpret_cast<void*>(glXCreateContextAttribsARB)},
{"glXCreateGLXPixmap", reinterpret_cast<void*>(glXCreateGLXPixmap)},
{"glXCreateNewContext", reinterpret_cast<void*>(glXCreateNewContext)},
{"glXCreatePbuffer", reinterpret_cast<void*>(glXCreatePbuffer)},
{"glXCreatePixmap", reinterpret_cast<void*>(glXCreatePixmap)},
{"glXCreateWindow", reinterpret_cast<void*>(glXCreateWindow)},
{"glXDestroyContext", reinterpret_cast<void*>(glXDestroyContext)},
{"glXDestroyGLXPixmap", reinterpret_cast<void*>(glXDestroyGLXPixmap)},
{"glXDestroyPbuffer", reinterpret_cast<void*>(glXDestroyPbuffer)},
{"glXDestroyPixmap", reinterpret_cast<void*>(glXDestroyPixmap)},
{"glXDestroyWindow", reinterpret_cast<void*>(glXDestroyWindow)},
{"glXGetClientString", reinterpret_cast<void*>(glXGetClientString)},
{"glXGetConfig", reinterpret_cast<void*>(glXGetConfig)},
{"glXGetCurrentContext", reinterpret_cast<void*>(glXGetCurrentContext)},
{"glXGetCurrentDisplay", reinterpret_cast<void*>(glXGetCurrentDisplay)},
{"glXGetCurrentDrawable", reinterpret_cast<void*>(glXGetCurrentDrawable)},
{"glXGetCurrentReadDrawable", reinterpret_cast<void*>(glXGetCurrentReadDrawable)},
{"glXGetFBConfigAttrib", reinterpret_cast<void*>(glXGetFBConfigAttrib)},
{"glXGetFBConfigs", reinterpret_cast<void*>(glXGetFBConfigs)},
{"glXGetProcAddress", reinterpret_cast<void*>(glXGetProcAddress)},
{"glXGetProcAddressARB", reinterpret_cast<void*>(glXGetProcAddressARB)},
{"glXGetSelectedEvent", reinterpret_cast<void*>(glXGetSelectedEvent)},
{"glXGetSwapIntervalMESA", reinterpret_cast<void*>(glXGetSwapIntervalMESA)},
{"glXGetVisualFromFBConfig", reinterpret_cast<void*>(glXGetVisualFromFBConfig)},
{"glXIsDirect", reinterpret_cast<void*>(glXIsDirect)},
{"glXMakeContextCurrent", reinterpret_cast<void*>(glXMakeContextCurrent)},
{"glXMakeCurrent", reinterpret_cast<void*>(glXMakeCurrent)},
{"glXQueryContext", reinterpret_cast<void*>(glXQueryContext)},
{"glXQueryDrawable", reinterpret_cast<void*>(glXQueryDrawable)},
{"glXQueryExtension", reinterpret_cast<void*>(glXQueryExtension)},
{"glXQueryExtensionsString", reinterpret_cast<void*>(glXQueryExtensionsString)},
{"glXQueryServerString", reinterpret_cast<void*>(glXQueryServerString)},
{"glXQueryVersion", reinterpret_cast<void*>(glXQueryVersion)},
{"glXSelectEvent", reinterpret_cast<void*>(glXSelectEvent)},
{"glXSwapBuffers", reinterpret_cast<void*>(glXSwapBuffers)},
{"glXSwapIntervalEXT", reinterpret_cast<void*>(glXSwapIntervalEXT)},
{"glXSwapIntervalMESA", reinterpret_cast<void*>(glXSwapIntervalMESA)},
{"glXSwapIntervalSGI", reinterpret_cast<void*>(glXSwapIntervalSGI)},
{"glXUseXFont", reinterpret_cast<void*>(glXUseXFont)},
{"glXWaitGL", reinterpret_cast<void*>(glXWaitGL)},
{"glXWaitX", reinterpret_cast<void*>(glXWaitX)},
};
} // namespace
void* GetGLXEntryPoint(const char* name) {
for (const auto& entry : kGLXEntryPoints) {
if (std::strcmp(entry.Name, name) == 0) {
return entry.Proc;
}
}
return nullptr;
}
} // namespace MobileGL::MG_Impl::GLXImpl
#endif // __linux__ && !__ANDROID__
}
File diff suppressed because it is too large Load Diff
-69
View File
@@ -1,69 +0,0 @@
// MobileGL - MobileGL/MG_Impl/GLXImpl/GLXImpl.h
// Copyright (c) 2025-2026 MobileGL-Dev
// Licensed under the GNU Lesser General Public License v3.0:
// https://www.gnu.org/licenses/gpl-3.0.txt
// https://www.gnu.org/licenses/lgpl-3.0.txt
// SPDX-License-Identifier: LGPL-3.0-only
// End of Source File Header
#pragma once
#include <Includes.h>
#if defined(__linux__) && !defined(__ANDROID__)
namespace MobileGL::MG_Impl::GLXImpl {
// GLX layered on MobileGL's own EGL, mirroring WGLImpl/CGLImpl. Handles are
// opaque to callers; XVisualInfo crosses the ABI as void* so this header
// needs no Xlib includes (Includes.h forward-declares Display/XID/Window).
using GLXFBConfigHandle = void*;
using GLXContextHandle = void*;
using GLXDrawableHandle = unsigned long; // XID
int QueryExtension(Display* dpy, int* errorBase, int* eventBase);
int QueryVersion(Display* dpy, int* major, int* minor);
const char* QueryExtensionsString(Display* dpy, int screen);
const char* GetClientString(Display* dpy, int name);
const char* QueryServerString(Display* dpy, int screen, int name);
GLXFBConfigHandle* GetFBConfigs(Display* dpy, int screen, int* nelements);
GLXFBConfigHandle* ChooseFBConfig(Display* dpy, int screen, const int* attribList, int* nelements);
int GetFBConfigAttrib(Display* dpy, GLXFBConfigHandle config, int attribute, int* value);
void* GetVisualFromFBConfig(Display* dpy, GLXFBConfigHandle config);
void* ChooseVisual(Display* dpy, int screen, int* attribList);
int GetConfig(Display* dpy, void* visualInfo, int attribute, int* value);
GLXContextHandle CreateContext(Display* dpy, void* visualInfo, GLXContextHandle share, int direct);
GLXContextHandle CreateNewContext(Display* dpy, GLXFBConfigHandle config, int renderType,
GLXContextHandle share, int direct);
GLXContextHandle CreateContextAttribsARB(Display* dpy, GLXFBConfigHandle config, GLXContextHandle share,
int direct, const int* attribList);
void DestroyContext(Display* dpy, GLXContextHandle context);
int MakeCurrent(Display* dpy, GLXDrawableHandle drawable, GLXContextHandle context);
int MakeContextCurrent(Display* dpy, GLXDrawableHandle draw, GLXDrawableHandle read,
GLXContextHandle context);
void SwapBuffers(Display* dpy, GLXDrawableHandle drawable);
GLXDrawableHandle CreateWindow(Display* dpy, GLXFBConfigHandle config, GLXDrawableHandle window,
const int* attribList);
void DestroyWindow(Display* dpy, GLXDrawableHandle window);
GLXContextHandle GetCurrentContext();
GLXDrawableHandle GetCurrentDrawable();
GLXDrawableHandle GetCurrentReadDrawable();
Display* GetCurrentDisplay();
int IsDirect(Display* dpy, GLXContextHandle context);
void WaitGL();
void WaitX();
int QueryContext(Display* dpy, GLXContextHandle context, int attribute, int* value);
void QueryDrawable(Display* dpy, GLXDrawableHandle drawable, int attribute, unsigned int* value);
void SwapIntervalEXT(Display* dpy, GLXDrawableHandle drawable, int interval);
int SwapIntervalMESA(unsigned int interval);
int GetSwapIntervalMESA();
int SwapIntervalSGI(int interval);
// Name -> exported glX entry point (table lives with the exports).
void* GetGLXEntryPoint(const char* name);
} // namespace MobileGL::MG_Impl::GLXImpl
#endif // __linux__ && !__ANDROID__
+3 -19
View File
@@ -8,27 +8,11 @@
#include "LookUp.h"
#if defined(__linux__) && !defined(__ANDROID__)
#include "../GLXImpl.h"
#endif
namespace MG_Impl::GLXImpl {
// TODO: implement complete GLX functionality
void* GetProcAddress(const char* name) {
if (!name) {
return nullptr;
}
MGLOG_D("glXGetProcAddress(\"%s\")", name);
#if defined(__linux__) && !defined(__ANDROID__)
if (name[0] == 'g' && name[1] == 'l' && name[2] == 'X') {
// glX entry points resolve from the GLX layer's own table; GL/EGL
// names fall through to the shared resolver below.
void* proc = MobileGL::MG_Impl::GLXImpl::GetGLXEntryPoint(name);
if (!proc) {
MGLOG_D("glXGetProcAddress: unknown glX entry point %s", name);
}
return proc;
}
#endif
void* proc = MobileGL::MG_Impl::GetProcAddress(name);
if (!proc) {
MGLOG_W("Failed to get function: %s", (const char*)name);
@@ -41,4 +25,4 @@ namespace MG_Impl::GLXImpl {
void* GetProcAddressARB(const char* name) {
return GetProcAddress(name);
}
} // namespace MG_Impl::GLXImpl
} // namespace MG_Impl::GLXImpl
-2
View File
@@ -85,8 +85,6 @@ namespace MobileGL::MG_Impl {
GETPROC(CGLGetPixelFormat, name);
GETPROC(CGLSetCurrentContext, name);
GETPROC(CGLGetCurrentContext, name);
GETPROC(CGLSetVirtualScreen, name);
GETPROC(CGLGetVirtualScreen, name);
GETPROC(CGLSetParameter, name);
GETPROC(CGLGetParameter, name);
GETPROC(CGLUpdateContext, name);
+4 -36
View File
@@ -29,19 +29,10 @@ namespace MobileGL::MG_Impl::NSOpenGLImpl {
char kContextViewKey;
char kContextLayerKey;
std::once_flag g_installOnce;
IMP g_pixelFormatDealloc = nullptr;
IMP g_contextDealloc = nullptr;
std::mutex& HookInstallMutex() {
static auto* mutex = new std::mutex();
return *mutex;
}
Bool& HooksInstalled() {
static auto* installed = new Bool(false);
return *installed;
}
template <typename Fn>
Fn ObjcMsgSend() {
return reinterpret_cast<Fn>(objc_msgSend);
@@ -440,12 +431,12 @@ namespace MobileGL::MG_Impl::NSOpenGLImpl {
method_setImplementation(method, replacement);
}
Bool InstallHooksOnce() {
void InstallHooksOnce() {
Class pixelFormatClass = objc_getClass("NSOpenGLPixelFormat");
Class contextClass = objc_getClass("NSOpenGLContext");
if (!pixelFormatClass || !contextClass) {
MGLOG_W("NSOpenGLImpl: NSOpenGL classes are not loaded; hooks not installed");
return false;
return;
}
ReplaceInstanceMethod(pixelFormatClass, "initWithAttributes:",
@@ -480,34 +471,11 @@ namespace MobileGL::MG_Impl::NSOpenGLImpl {
ReplaceInstanceMethod(contextClass, "dealloc", reinterpret_cast<IMP>(ContextDealloc), &g_contextDealloc);
MGLOG_I("NSOpenGLImpl hooks installed");
return true;
}
} // namespace
void InstallHooks() {
const std::lock_guard<std::mutex> lock(HookInstallMutex());
if (!HooksInstalled()) {
// Do not permanently consume the install attempt when the OpenGL
// framework has not registered its Objective-C classes yet. The
// dyld bootstrap normally runs after framework dependencies, but
// an explicitly loaded/static-linked MobileGL can arrive earlier.
HooksInstalled() = InstallHooksOnce();
}
std::call_once(g_installOnce, InstallHooksOnce);
}
} // namespace MobileGL::MG_Impl::NSOpenGLImpl
namespace {
// SDL's Cocoa backend creates NSOpenGLPixelFormat/NSOpenGLContext before
// its first dlsym("glGetString") or other MobileGL host-API call. Install
// only the lightweight Objective-C dispatch hooks while the injected dylib
// is loading so those first Cocoa objects are routed through CGLImpl. The
// hooked context constructor reaches EGLImpl::GetDisplay(), which performs
// the full, thread-safe MobileGL initialization outside this bootstrap.
//
// There is intentionally no matching destructor: backend teardown remains
// owned by the EGL lifecycle and process-exit globals remain leak-at-exit.
__attribute__((constructor)) void BootstrapNSOpenGLHooks() {
MobileGL::MG_Impl::NSOpenGLImpl::InstallHooks();
}
} // namespace
#endif
@@ -41,7 +41,6 @@ namespace MobileGL::MG_State::GLState {
void BufferObject::NotifySubData(SizeT offset, SizeT size) {
++m_changeSerial;
if (size == 0) return;
m_hasDefinedContent = true;
if (g_bufferBackendOps && g_bufferBackendOps->SubData) {
g_bufferBackendOps->SubData(*this, offset, size);
}
@@ -50,14 +49,12 @@ namespace MobileGL::MG_State::GLState {
void BufferObject::NotifyFlushMappedRange(Range1D range, Flags<BufferMappingAccessBit> appAccess) {
++m_changeSerial;
if (range.start >= range.end) return;
m_hasDefinedContent = true;
if (g_bufferBackendOps && g_bufferBackendOps->FlushMappedRange) {
g_bufferBackendOps->FlushMappedRange(*this, range, appAccess);
}
}
void BufferObject::NotifyContentWrite(SizeT offset, SizeT size) {
m_hasDefinedContent = true;
if (m_resource.IsGpuResident()) {
// The write already landed in coherent GPU memory; the backend has no separate
// copy to sync. Only bump the serial so cached transient slices invalidate.
@@ -74,9 +71,6 @@ namespace MobileGL::MG_State::GLState {
if (data && size > 0) {
Memcpy(m_resource.Bytes(), data, size);
}
// A NULL-data respecify (the orphaning idiom) leaves the store undefined;
// record that so backends skip uploading the stale shadow bytes.
m_hasDefinedContent = (data != nullptr) || size == 0;
m_isImmutableStorage = false;
m_storageFlags = 0;
NotifyRespecify();
@@ -95,7 +89,6 @@ namespace MobileGL::MG_State::GLState {
} else if (size > 0) {
Memset(m_resource.Bytes(), 0, size);
}
m_hasDefinedContent = true;
m_isImmutableStorage = true;
m_storageFlags = storageFlags;
NotifyRespecify();
@@ -181,22 +174,6 @@ namespace MobileGL::MG_State::GLState {
++m_changeSerial;
}
void BufferObject::MarkGpuWritten() {
m_hasDefinedContent = true;
m_gpuWritePending = true;
}
void BufferObject::SyncGpuWrites() {
if (!m_gpuWritePending) return;
// Cleared unconditionally: without a readback op the shadow can never catch up,
// and retrying on every subsequent read would only repeat the same no-op.
m_gpuWritePending = false;
if (m_size == 0 || g_bufferBackendOps == nullptr || g_bufferBackendOps->ReadbackFromGpu == nullptr) {
return;
}
g_bufferBackendOps->ReadbackFromGpu(*this);
}
void BufferObject::UploadSubData(DataPtr data, SizeT atOffset) {
MOBILEGL_ASSERT(!m_isMapped || (m_mappingAccess & BufferMappingAccessBit::Persistent),
"Cannot upload sub data while buffer is non-persistently mapped.");
@@ -227,13 +204,11 @@ namespace MobileGL::MG_State::GLState {
"Destination buffer copy out of bounds: dstOffset (%zu) + size (%zu) > m_size (%zu)", dstOffset,
size, m_size);
src->SyncGpuWrites();
Memcpy(m_resource.Bytes() + dstOffset, src->m_resource.Bytes() + srcOffset, size);
NotifyContentWrite(dstOffset, size);
}
void* BufferObject::AcquireMemory(Bool markMapped, Bool read, Bool write) {
SyncGpuWrites();
if (markMapped) {
m_isMapped = true;
m_mappingAccess = (read ? BufferMappingAccessBit::Read : BufferMappingAccessBit::Null) |
@@ -256,29 +231,10 @@ namespace MobileGL::MG_State::GLState {
return m_resource.Bytes();
}
Bool BufferObject::EnsureGpuResidentStorage() {
if (m_resource.IsGpuResident()) {
return true;
}
if (m_size == 0 || g_bufferBackendOps == nullptr || g_bufferBackendOps->AcquirePersistentMap == nullptr) {
return false;
}
void* base = g_bufferBackendOps->AcquirePersistentMap(*this);
if (base == nullptr) {
return false;
}
m_resource.AdoptPersistentMap(base);
return true;
}
void* BufferObject::AcquireMemoryRange(Range1D range, Flags<BufferMappingAccessBit> access) {
MOBILEGL_ASSERT(range.end <= m_size && range.start <= range.end,
"AcquireMemoryRange out of bounds: range (%zu, %zu) exceeds m_size (%zu)", range.start,
range.end, m_size);
// The app is about to look at the bytes; a shader may have rewritten them since
// the shadow was last authoritative. Also needed for a write map without an
// invalidate bit, whose staging copy is seeded from the shadow.
SyncGpuWrites();
m_isMapped = true;
m_mappingAccess = access;
m_mappedRange = range;
@@ -340,10 +296,6 @@ namespace MobileGL::MG_State::GLState {
return m_changeSerial;
}
Bool BufferObject::HasDefinedContent() const {
return m_hasDefinedContent;
}
const SharedPtr<BackendBufferResource>& BufferObject::GetBackendResource() const {
return m_resource.Backend();
}
@@ -99,13 +99,6 @@ namespace MobileGL {
// Must be idempotent: a second call for an already-backed buffer returns the
// same base pointer.
void* (*AcquirePersistentMap)(BufferObject& bufferObject) = nullptr;
// Pulls the backend's current contents for the whole buffer into the shadow
// (through WritebackFromBackend). Only ever called for a buffer the GPU may
// have written behind the frontend's back - a shader storage or atomic counter
// binding of a draw or dispatch - because nothing else can desynchronise the
// shadow. Backends that cannot read their storage back leave this null; the
// shadow then keeps its pre-dispatch bytes, which is the old behaviour.
void (*ReadbackFromGpu)(BufferObject& bufferObject) = nullptr;
};
// Registered by the active backend at init, cleared at shutdown.
@@ -140,11 +133,6 @@ namespace MobileGL {
void* AcquireMemory(Bool markMapped, Bool read, Bool write);
void* AcquireMemoryRange(Range1D range, Flags<BufferMappingAccessBit> access);
// Adopt backend host-visible coherent GPU storage as the source of truth
// (used for GPU-written targets like transform feedback capture, so
// MapBuffer/GetBufferSubData read real GPU results). No-op when already
// resident or when the backend declines.
Bool EnsureGpuResidentStorage();
void ReleaseMemory();
void FlushMemoryRange(SizeT offset, SizeT length);
@@ -156,16 +144,6 @@ namespace MobileGL {
// backend op: the backend storage already holds these bytes.
void WritebackFromBackend(DataPtr data, SizeT atOffset);
// A draw or dispatch just ran with this buffer bound where a shader can write
// it (shader storage / atomic counter). The next read has to reconcile with
// that: pull the bytes back, or - when the shadow already IS coherent GPU
// memory - wait for the work that wrote them to retire. Which of the two is
// the backend's business; the flag only says a GPU write is outstanding.
void MarkGpuWritten();
// Refreshes the shadow from the backend when a GPU write is outstanding. Called
// from every path that reads the shadow on the app's behalf.
void SyncGpuWrites();
Bool IsMapped() const;
Bool IsImmutableStorage() const;
SizeT GetSize() const;
@@ -188,11 +166,6 @@ namespace MobileGL {
// Monotonic counter bumped on every shadow mutation; backends use it to
// validate cached transient slices.
Uint64 GetChangeSerial() const;
// False after a NULL-data (re)specification until the first content
// write: the app's orphaning idiom (glBufferData with nullptr) leaves
// the store undefined, so backends may (re)allocate GPU storage without
// uploading the stale CPU shadow.
Bool HasDefinedContent() const;
const SharedPtr<BackendBufferResource>& GetBackendResource() const;
void SetBackendResource(SharedPtr<BackendBufferResource> resource);
@@ -218,10 +191,6 @@ namespace MobileGL {
Bool m_isImmutableStorage = false;
GLbitfield m_storageFlags = 0;
Uint64 m_changeSerial = 0;
// See HasDefinedContent().
Bool m_hasDefinedContent = true;
// Set by MarkGpuWritten, cleared by SyncGpuWrites once the shadow is refreshed.
Bool m_gpuWritePending = false;
Range1D m_mappedRange;
Vector<Uint8> m_stagingData;
Bool m_ownsStagingData;
@@ -31,9 +31,6 @@ namespace MobileGL::MG_State::GLState {
BindingSlot<BufferObject>& GetBindingSlot(BufferTarget target);
// For glBindBufferBase / glBindBufferRange
BindingSlotRange1D<BufferObject>& GetBindingPoint(BufferTarget target, Uint index);
const BindingSlotRange1D<BufferObject>& GetBindingPoint(BufferTarget target, Uint index) const {
return const_cast<BufferState*>(this)->GetBindingPoint(target, index);
}
constexpr SizeT GetBindingPointCount(const BufferTarget target) const {
auto it = std::find(BufferBindPointTargets.begin(), BufferBindPointTargets.end(), target);
auto index = std::distance(BufferBindPointTargets.begin(), it);
-281
View File
@@ -241,32 +241,6 @@ namespace MobileGL::MG_State {
}
void GLContext::MarkTextureObjectForDeletion(Uint index) {
// GL 3.3 core 4.4.2: deleting a texture whose image is attached to the framebuffer
// that is currently bound acts as if FramebufferTexture* had been called with texture
// zero for every attachment point it occupied there. Framebuffers that are NOT bound
// keep the orphaned attachment, so only the bound ones are touched.
//
// Without this the framebuffer object goes on holding the deleted texture alive as its
// attachment, and a later read through that framebuffer returns the dead texture's
// contents rather than those of whatever the application put in its place - the name
// it deleted usually comes straight back from the next glGenTextures, so the two are
// indistinguishable from the outside (KHR-GL32.packed_pixels read a stale gradient).
if (const auto& textureObject = m_textureState.GetTextureObject(index)) {
for (SizeT targetIndex = 0; targetIndex < SizeT(FramebufferTarget::FramebufferTargetCount);
++targetIndex) {
const auto& framebuffer =
GetFramebufferBindingSlot(static_cast<FramebufferTarget>(targetIndex)).GetBoundObject();
if (!framebuffer || framebuffer->IsDefaultFramebuffer()) {
continue;
}
const auto& attachments = framebuffer->GetAllAttachmentObjects();
for (SizeT i = 0; i < attachments.size(); ++i) {
if (attachments[i].IsTexture() && attachments[i].GetTexture() == textureObject) {
framebuffer->Detach(static_cast<FramebufferAttachmentType>(i));
}
}
}
}
m_textureState.MarkTextureObjectForDeletion(index, IsRelaxedSemanticsActive());
}
@@ -343,60 +317,7 @@ namespace MobileGL::MG_State {
return m_programState.GetCurrentProgram();
}
const SharedPtr<ProgramObject>& GLContext::GetProgramForDraw() {
static const SharedPtr<ProgramObject> nullProgram = nullptr;
const auto& currentProgram = m_programState.GetCurrentProgram();
if (currentProgram) return currentProgram;
if (m_boundProgramPipeline == 0) return nullProgram;
const auto& pipeline = GetBoundProgramPipeline();
if (!pipeline) return nullProgram;
const auto signature = pipeline->ComputeDrawProgramSignature();
if (const auto& cached = pipeline->GetCachedDrawProgram(signature)) return cached;
// Everything downstream of here - the backends, the uniform plumbing, the draw
// validation - is written against a single linked program, so the pipeline is
// flattened into one. Each stage contributes only the shaders that serve it, so a
// program bound to two stages is not pulled in twice and a program bound to a
// stage it does not implement contributes nothing.
// Deliberately not a named program: it is reachable only through the pipeline, it
// must not answer glIsProgram, and it must not consume a name the application
// could otherwise be handed. Backend registries key on the object, not the name.
auto composite = MakeShared<ProgramObject>(0u);
Bool anyStage = false;
for (SizeT stage = 0; stage < static_cast<SizeT>(ShaderStage::ShaderStageCount); ++stage) {
const auto& stageProgram = pipeline->GetStageProgram(static_cast<ShaderStage>(stage));
if (!stageProgram) continue;
for (const auto& shader : stageProgram->GetAttachedShaders()) {
if (!shader || static_cast<SizeT>(shader->GetShaderStage()) != stage) continue;
composite->AttachShader(shader);
anyStage = true;
}
}
if (!anyStage) return nullProgram;
// A pipeline with no fragment stage still rasterises, so the default fragment
// shader is wanted here even though the separable stage programs never get one.
composite->Link(true);
pipeline->SetCachedDrawProgram(signature, Move(composite));
return pipeline->GetCachedDrawProgram(signature);
}
const SharedPtr<ProgramObject>& GLContext::GetProgramForUniform() {
const auto& currentProgram = m_programState.GetCurrentProgram();
if (currentProgram) return currentProgram;
static const SharedPtr<ProgramObject> nullProgram = nullptr;
if (m_boundProgramPipeline == 0) return nullProgram;
const auto& pipeline = GetBoundProgramPipeline();
if (!pipeline) return nullProgram;
return pipeline->GetActiveProgram();
}
// RenderState
Uint GLContext::GetPipelineStateVersion() const {
return m_renderState.GetPipelineStateVersion();
}
Uint GLContext::GetRenderStateParametersVersion() const {
return m_renderState.GetVersion();
}
@@ -477,14 +398,6 @@ namespace MobileGL::MG_State {
m_renderState.SetPointSize(size);
}
void GLContext::SetPatchVertices(Uint vertices) {
m_renderState.SetPatchVertices(vertices);
}
Uint GLContext::GetPatchVertices() const {
return m_renderState.GetPatchVertices();
}
Float GLContext::GetPointSize() const {
return m_renderState.GetPointSize();
}
@@ -806,200 +719,6 @@ namespace MobileGL::MG_State {
Bool GLContext::ValidateRenderbufferObject(Uint index) const {
return m_renderbufferState.ValidateRenderbufferObject(index);
}
void GLContext::SaveBoundTransformFeedbackState() {
auto& object = m_transformFeedbackObjects[m_boundTransformFeedback];
for (Uint i = 0; i < MAX_TRANSFORM_FEEDBACK_BUFFERS; ++i) {
const auto& point = m_bufferState.GetBindingPoint(BufferTarget::TransformFeedback, i);
object.bindings[i] = {point.GetBoundObject(), point.GetRange(), point.HasExplicitRange()};
}
object.active = m_transformFeedbackActive;
object.paused = m_transformFeedbackPaused;
object.primitiveMode = m_transformFeedbackPrimitiveMode;
object.program = m_transformFeedbackProgram;
object.generation = m_transformFeedbackGeneration;
object.capturedVertices = m_transformFeedbackCapturedVertices;
object.inputPrimitives = m_transformFeedbackInputPrimitives;
}
void GLContext::RestoreBoundTransformFeedbackState() {
const auto& object = m_transformFeedbackObjects[m_boundTransformFeedback];
for (Uint i = 0; i < MAX_TRANSFORM_FEEDBACK_BUFFERS; ++i) {
auto& point = m_bufferState.GetBindingPoint(BufferTarget::TransformFeedback, i);
point.Bind(object.bindings[i].buffer);
if (object.bindings[i].buffer) {
point.SetRange(object.bindings[i].range, object.bindings[i].hasExplicitRange);
} else {
point.ClearRange();
}
}
m_transformFeedbackActive = object.active;
m_transformFeedbackPaused = object.paused;
m_transformFeedbackPrimitiveMode = object.primitiveMode;
m_transformFeedbackProgram = object.program;
// The generation identifies one capture span, and a span belongs to the object
// that opened it - a backend keys its append state on it, so switching objects
// has to bring the right one back.
m_transformFeedbackGeneration = object.generation;
m_transformFeedbackCapturedVertices = object.capturedVertices;
m_transformFeedbackInputPrimitives = object.inputPrimitives;
}
void GLContext::GenTransformFeedbackNames(Uint number, Vector<Uint>& ids) {
ids.resize(number);
if (number == 0) return;
m_transformFeedbackNames.Generate(number, ids.data());
// A generated name already denotes an object with the default state, so that a
// bind never has to distinguish "first use" from any later one.
for (const Uint id : ids) {
m_transformFeedbackObjects[id] = {};
}
}
// Program pipeline
void GLContext::GenProgramPipelineNames(Uint number, Vector<Uint>& pipelines) {
pipelines.resize(number);
// Names only: glIsProgramPipeline must answer GL_FALSE until one is bound or created.
m_programPipelineNames.Generate(number, pipelines.data());
}
void GLContext::CreateProgramPipelineObject(Uint index) {
m_programPipelines[index] = MakeShared<ProgramPipelineObject>(index);
}
Bool GLContext::ValidateProgramPipelineName(Uint index) const {
return index == 0 || m_programPipelineNames.IsValid(index);
}
Bool GLContext::IsProgramPipelineObject(Uint index) const {
if (index == 0 || !m_programPipelineNames.IsValid(index)) return false;
return m_programPipelines.find(index) != m_programPipelines.end();
}
void GLContext::BindProgramPipelineObject(Uint index) {
if (index != 0 && m_programPipelines.find(index) == m_programPipelines.end()) {
// First bind is what turns a reserved name into an object.
m_programPipelines[index] = MakeShared<ProgramPipelineObject>(index);
}
m_boundProgramPipeline = index;
}
void GLContext::MarkProgramPipelineForDeletion(Uint index) {
if (index == 0 || !m_programPipelineNames.IsValid(index)) return;
if (index == m_boundProgramPipeline) {
m_boundProgramPipeline = 0;
}
m_programPipelines.erase(index);
m_programPipelineNames.Delete(index);
}
const SharedPtr<ProgramPipelineObject>& GLContext::GetProgramPipelineObject(Uint index) const {
static const SharedPtr<ProgramPipelineObject> kNone;
const auto it = m_programPipelines.find(index);
return it == m_programPipelines.end() ? kNone : it->second;
}
const SharedPtr<ProgramPipelineObject>& GLContext::GetBoundProgramPipeline() const {
return GetProgramPipelineObject(m_boundProgramPipeline);
}
Bool GLContext::ValidateTransformFeedbackName(Uint index) const {
return index == 0 || m_transformFeedbackNames.IsValid(index);
}
void GLContext::BindTransformFeedbackObject(Uint index) {
if (index == m_boundTransformFeedback) return;
SaveBoundTransformFeedbackState();
m_boundTransformFeedback = index;
m_transformFeedbackObjects[index].everBound = true;
RestoreBoundTransformFeedbackState();
}
Bool GLContext::IsTransformFeedbackObject(Uint index) const {
if (index == 0 || !m_transformFeedbackNames.IsValid(index)) return false;
const auto it = m_transformFeedbackObjects.find(index);
return it != m_transformFeedbackObjects.end() && it->second.everBound;
}
void GLContext::MarkTransformFeedbackObjectForDeletion(Uint index) {
if (index == 0 || !m_transformFeedbackNames.IsValid(index)) return;
// Deleting the bound object reverts to the default one (GL 4.6 core 13.2.1);
// its state is dropped rather than saved back into the dying object.
if (index == m_boundTransformFeedback) {
m_boundTransformFeedback = 0;
RestoreBoundTransformFeedbackState();
}
m_transformFeedbackObjects.erase(index);
m_transformFeedbackNames.Delete(index);
}
Uint64 GLContext::GetTransformFeedbackRecordedVertices(Uint index) const {
const auto it = m_transformFeedbackObjects.find(index);
return it == m_transformFeedbackObjects.end() ? 0 : it->second.recordedVertices;
}
Bool GLContext::HasTransformFeedbackCompletedSpan(Uint index) const {
const auto it = m_transformFeedbackObjects.find(index);
return it != m_transformFeedbackObjects.end() && it->second.hasCompletedSpan;
}
void GLContext::CreateTransformFeedbackObject(Uint index) {
// glCreateTransformFeedbacks has no bind step to infer existence from, so the name it
// hands out is already the name of an object (GL 4.6 core 13.2.1).
m_transformFeedbackObjects[index] = {};
m_transformFeedbackObjects[index].everBound = true;
}
Bool GLContext::IsNamedTransformFeedbackActive(Uint index) const {
if (index == m_boundTransformFeedback) return m_transformFeedbackActive;
const auto it = m_transformFeedbackObjects.find(index);
return it != m_transformFeedbackObjects.end() && it->second.active;
}
Bool GLContext::IsNamedTransformFeedbackPaused(Uint index) const {
if (index == m_boundTransformFeedback) return m_transformFeedbackPaused;
const auto it = m_transformFeedbackObjects.find(index);
return it != m_transformFeedbackObjects.end() && it->second.paused;
}
NamedTransformFeedbackBinding GLContext::GetNamedTransformFeedbackBinding(Uint index, Uint bufferIndex) const {
NamedTransformFeedbackBinding result;
if (bufferIndex >= MAX_TRANSFORM_FEEDBACK_BUFFERS) return result;
// The bound object's capture bindings live in the context's own binding points, not in
// the saved copy - that one is only written when the object is swapped out.
if (index == m_boundTransformFeedback) {
const auto& point = m_bufferState.GetBindingPoint(BufferTarget::TransformFeedback, bufferIndex);
result.Buffer = point.GetBoundObject();
result.Range = point.GetRange();
result.HasExplicitRange = point.HasExplicitRange();
return result;
}
const auto it = m_transformFeedbackObjects.find(index);
if (it == m_transformFeedbackObjects.end()) return result;
const auto& saved = it->second.bindings[bufferIndex];
result.Buffer = saved.buffer;
result.Range = saved.range;
result.HasExplicitRange = saved.hasExplicitRange;
return result;
}
void GLContext::SetNamedTransformFeedbackBinding(Uint index, Uint bufferIndex,
const SharedPtr<BufferObject>& buffer, Range1D range,
Bool hasExplicitRange) {
if (bufferIndex >= MAX_TRANSFORM_FEEDBACK_BUFFERS) return;
if (index == m_boundTransformFeedback) {
auto& point = m_bufferState.GetBindingPoint(BufferTarget::TransformFeedback, bufferIndex);
point.Bind(buffer);
if (buffer && hasExplicitRange) {
point.SetRange(range, true);
} else {
point.ClearRange();
}
return;
}
auto& object = m_transformFeedbackObjects[index];
object.bindings[bufferIndex] = {buffer, range, hasExplicitRange};
}
} // namespace GLState
// Leak-at-exit storage; see GlobalObjects.cpp.
+1 -189
View File
@@ -14,7 +14,6 @@
#include "MG_State/GLState/RenderbufferState/RenderbufferState.h"
#include "RenderState/RenderState.h"
#include "ProgramState/ProgramState.h"
#include "ProgramState/ProgramPipelineObject.h"
#include "SamplerState/SamplerState.h"
#include "TextureState/TextureState.h"
#include "FramebufferState/FramebufferState.h"
@@ -46,14 +45,6 @@ namespace MobileGL {
// translates the result into its own API call.
VertexAttribTypeInfo ClassifyVertexAttribType(GLenum glType);
// One indexed capture binding of a transform feedback object, as the by-name queries
// report it. An empty Buffer means the binding point is unbound.
struct NamedTransformFeedbackBinding {
SharedPtr<BufferObject> Buffer;
Range1D Range{};
Bool HasExplicitRange = false;
};
class GLContext {
public:
GLContext() = default;
@@ -111,27 +102,13 @@ namespace MobileGL {
TextureUnit& GetTextureUnitObject(Int unit);
ImageTextureBinding& GetImageTextureBinding(Int unit);
const ImageTextureBinding& GetImageTextureBinding(Int unit) const;
void NoteTextureUnitTouched(Int unit, Bool bindingChanged = true) {
m_textureState.NoteUnitTouched(unit, bindingChanged);
}
void NoteTextureUnitTouched(Int unit) { m_textureState.NoteUnitTouched(unit); }
Int GetMaxTouchedTextureUnit() const { return m_textureState.GetMaxTouchedUnit(); }
// Monotonic counter bumped whenever a texture bind/unbind/delete changes which
// texture is bound at a unit; lets a backend skip re-resolving an unchanged
// per-draw sampled-texture set.
Uint64 GetTextureBindGeneration() const { return m_textureState.GetTextureBindGeneration(); }
void BumpTextureBindGeneration() { m_textureState.BumpTextureBindGeneration(); }
// Monotonic counter bumped whenever a texture's shape or a sampler object's
// parameters change, i.e. whenever a bound texture's mipmap-completeness (and so
// whether a backend binds it at all) can have flipped without any bind moving;
// see TextureState::GetSamplingResolutionGeneration.
Uint64 GetSamplingResolutionGeneration() const {
return m_textureState.GetSamplingResolutionGeneration();
}
void BumpSamplingResolutionGeneration() { m_textureState.BumpSamplingResolutionGeneration(); }
// Never-reused id of this context, for backend memos keyed on the two counters
// above: both restart at 0 in a new context, and a recreated context can land on
// the old heap address. See TextureState::GetContextId.
Uint64 GetTextureContextId() const { return m_textureState.GetContextId(); }
Bool ValidateTextureName(Uint index) const;
Bool ValidateTextureObject(Uint index) const;
Int GetActiveTextureUnit() const;
@@ -151,30 +128,9 @@ namespace MobileGL {
const SharedPtr<ShaderObject>& GetShaderObject(Uint index);
void UseProgram(Uint program);
const SharedPtr<ProgramObject>& GetCurrentProgram();
// What a draw or dispatch actually executes: the program in use, or - when
// there is none - the bound pipeline's stages composited into one program.
const SharedPtr<ProgramObject>& GetProgramForDraw();
// What glUniform* addresses: the program in use, or the bound pipeline's
// active program (GL 4.6 core 7.6.1).
const SharedPtr<ProgramObject>& GetProgramForUniform();
// Program pipeline (GL_ARB_separate_shader_objects, GL 4.6 core 7.4). Like queries
// and transform feedbacks, glGenProgramPipelines only RESERVES a name - the object
// appears on first bind - while glCreateProgramPipelines makes it immediately.
void GenProgramPipelineNames(Uint number, Vector<Uint>& pipelines);
void CreateProgramPipelineObject(Uint index);
Bool ValidateProgramPipelineName(Uint index) const;
Bool IsProgramPipelineObject(Uint index) const;
void BindProgramPipelineObject(Uint index);
void MarkProgramPipelineForDeletion(Uint index);
const SharedPtr<ProgramPipelineObject>& GetProgramPipelineObject(Uint index) const;
Uint GetBoundProgramPipelineName() const { return m_boundProgramPipeline; }
const SharedPtr<ProgramPipelineObject>& GetBoundProgramPipeline() const;
// RenderState
Uint GetRenderStateParametersVersion() const;
// Only the pipeline-relevant subset - see RenderState::m_pipelineStateVersion.
Uint GetPipelineStateVersion() const;
const RenderStateParameters& GetRenderStateParameters() const;
void SetViewport(IntVec4 viewport); // x, y, width, height
const IntVec4& GetViewport() const; // x, y, width, height
@@ -182,8 +138,6 @@ namespace MobileGL {
Float GetLineWidth() const;
void SetPointSize(Float size);
Float GetPointSize() const;
void SetPatchVertices(Uint vertices);
Uint GetPatchVertices() const;
void SetPolygonOffset(Float factor, Float units);
Float GetPolygonOffsetFactor() const;
Float GetPolygonOffsetUnits() const;
@@ -257,103 +211,6 @@ namespace MobileGL {
void SetScissorBox(IntVec4 box); // x, y, width, height
const IntVec4& GetScissorBox() const; // x, y, width, height
// Transform feedback. The fields below are the state of the transform
// feedback object currently bound to GL_TRANSFORM_FEEDBACK; see the object
// block further down for how a bind swaps them.
void BeginTransformFeedback(GLenum primitiveMode, const SharedPtr<ProgramObject>& program) {
m_transformFeedbackActive = true;
m_transformFeedbackPaused = false;
m_transformFeedbackPrimitiveMode = primitiveMode;
m_transformFeedbackProgram = program;
m_transformFeedbackGeneration = ++m_transformFeedbackNextGeneration;
m_transformFeedbackCapturedVertices = 0;
m_transformFeedbackInputPrimitives = 0;
}
void EndTransformFeedback() {
m_transformFeedbackActive = false;
m_transformFeedbackPaused = false;
m_transformFeedbackProgram.reset();
// What glDrawTransformFeedback on this object replays from now on.
auto& object = m_transformFeedbackObjects[m_boundTransformFeedback];
object.recordedVertices = m_transformFeedbackCapturedVertices;
object.hasCompletedSpan = true;
}
Bool IsTransformFeedbackActive() const { return m_transformFeedbackActive; }
Bool IsTransformFeedbackPaused() const { return m_transformFeedbackPaused; }
void SetTransformFeedbackPaused(Bool paused) { m_transformFeedbackPaused = paused; }
GLenum GetTransformFeedbackPrimitiveMode() const { return m_transformFeedbackPrimitiveMode; }
const SharedPtr<ProgramObject>& GetTransformFeedbackProgram() const {
return m_transformFeedbackProgram;
}
// Bumped on every BeginTransformFeedback; the backend uses it to
// distinguish "resume appending" from "fresh capture".
Uint64 GetTransformFeedbackGeneration() const { return m_transformFeedbackGeneration; }
// CPU-side primitive accounting for the transform feedback queries:
// every captured draw adds its primitive count (draws without a
// geometry stage write exactly what they generate).
void AddTransformFeedbackPrimitives(Uint64 primitives) {
m_transformFeedbackPrimitiveCounter += primitives;
}
Uint64 GetTransformFeedbackPrimitiveCounter() const { return m_transformFeedbackPrimitiveCounter; }
// Primitives a draw assembled while the capture was paused. GL counts those in
// PRIMITIVES_GENERATED, but a backend that answers the query with its own
// transform feedback counter cannot see them - nothing was being captured.
void AddTransformFeedbackPausedPrimitives(Uint64 primitives) {
m_transformFeedbackPausedPrimitiveCounter += primitives;
}
Uint64 GetTransformFeedbackPausedPrimitiveCounter() const {
return m_transformFeedbackPausedPrimitiveCounter;
}
// Vertices already captured since BeginTransformFeedback (drives the
// buffer-capacity clamp on the primitives-written accounting).
void AddTransformFeedbackCapturedVertices(Uint64 vertices) {
m_transformFeedbackCapturedVertices += vertices;
}
Uint64 GetTransformFeedbackCapturedVertices() const { return m_transformFeedbackCapturedVertices; }
// Raw assembled input primitives fed to the capture stage since Begin
// (pre-clamp; drives the GS strip capture-order fixup at EndTF).
void AddTransformFeedbackInputPrimitives(Uint64 primitives) {
m_transformFeedbackInputPrimitives += primitives;
}
Uint64 GetTransformFeedbackInputPrimitives() const { return m_transformFeedbackInputPrimitives; }
// Transform feedback objects (ARB_transform_feedback2 / GL 4.0 core).
// The capture state above and the indexed GL_TRANSFORM_FEEDBACK_BUFFER
// binding points are object state, but the context keeps exactly one live
// copy of both so that every existing reader - the backends' per-draw sync,
// the drawing and getter paths - needs no notion of which object owns them.
// A bind therefore saves the live copy into the outgoing object and restores
// the incoming one's. Object 0 is the default object and always exists.
static constexpr Uint MAX_TRANSFORM_FEEDBACK_BUFFERS = 4;
void GenTransformFeedbackNames(Uint number, Vector<Uint>& ids);
// A name glGenTransformFeedbacks handed out and glDeleteTransformFeedbacks
// has not taken back. Name 0 is always valid.
Bool ValidateTransformFeedbackName(Uint index) const;
// What glIsTransformFeedback reports: a generated name only becomes the name
// of an object once it has been bound at least once (GL 4.6 core 13.2.1).
Bool IsTransformFeedbackObject(Uint index) const;
void BindTransformFeedbackObject(Uint index);
void MarkTransformFeedbackObjectForDeletion(Uint index);
Uint GetBoundTransformFeedbackName() const { return m_boundTransformFeedback; }
// Vertices the object captured in its last completed span; the vertex count
// glDrawTransformFeedback replays.
Uint64 GetTransformFeedbackRecordedVertices(Uint index) const;
// Whether the object has ever completed a capture span. glDrawTransformFeedback
// on an object that has not is INVALID_OPERATION, which a zero vertex count
// cannot express: an empty completed span is legal and draws nothing.
Bool HasTransformFeedbackCompletedSpan(Uint index) const;
// The by-name (direct state access) view. A named object that happens to be the
// bound one is answered from the live copy, since that is where its state actually
// is until a bind swaps it out.
void CreateTransformFeedbackObject(Uint index);
Bool IsNamedTransformFeedbackActive(Uint index) const;
Bool IsNamedTransformFeedbackPaused(Uint index) const;
NamedTransformFeedbackBinding GetNamedTransformFeedbackBinding(Uint index, Uint bufferIndex) const;
void SetNamedTransformFeedbackBinding(Uint index, Uint bufferIndex,
const SharedPtr<BufferObject>& buffer, Range1D range,
Bool hasExplicitRange);
// Framebuffer
void GenFramebufferNames(Uint number, Vector<Uint>& framebuffers);
const SharedPtr<FramebufferObject>& GetFramebufferObject(Uint index);
@@ -386,51 +243,6 @@ namespace MobileGL {
BufferState m_bufferState;
VertexArrayState m_vertexArrayState;
Array<CurrentVertexAttributeValue, VertexArrayObject::MAX_VERTEX_ATTRIBS> m_currentVertexAttributes{};
Bool m_transformFeedbackActive = false;
Bool m_transformFeedbackPaused = false;
GLenum m_transformFeedbackPrimitiveMode = GL_POINTS;
SharedPtr<ProgramObject> m_transformFeedbackProgram;
Uint64 m_transformFeedbackGeneration = 0;
// Source of the per-span ids above; never rolls back with an object switch.
Uint64 m_transformFeedbackNextGeneration = 0;
// Not object state: the transform feedback queries snapshot it at BeginQuery
// and take the delta at EndQuery, which spans whatever objects were used.
Uint64 m_transformFeedbackPrimitiveCounter = 0;
Uint64 m_transformFeedbackPausedPrimitiveCounter = 0;
Uint64 m_transformFeedbackCapturedVertices = 0;
Uint64 m_transformFeedbackInputPrimitives = 0;
// Everything a transform feedback object owns while it is NOT the bound one.
struct TransformFeedbackObjectState {
struct SavedBufferBinding {
SharedPtr<BufferObject> buffer;
Range1D range;
Bool hasExplicitRange = false;
};
Array<SavedBufferBinding, MAX_TRANSFORM_FEEDBACK_BUFFERS> bindings;
Bool active = false;
Bool paused = false;
GLenum primitiveMode = GL_POINTS;
SharedPtr<ProgramObject> program;
Uint64 generation = 0;
Uint64 capturedVertices = 0;
Uint64 inputPrimitives = 0;
Uint64 recordedVertices = 0;
Bool hasCompletedSpan = false;
Bool everBound = false;
};
void SaveBoundTransformFeedbackState();
void RestoreBoundTransformFeedbackState();
// operator[] materialises an entry with the default state on first touch, so
// the default object (name 0) needs no seeding here.
UnorderedMap<Uint, TransformFeedbackObjectState> m_transformFeedbackObjects;
IndexGenerator<Uint> m_transformFeedbackNames;
Uint m_boundTransformFeedback = 0;
// Map membership IS object existence here: a pipeline has no stateful default
// object 0, so no everBound flag is needed.
UnorderedMap<Uint, SharedPtr<ProgramPipelineObject>> m_programPipelines;
IndexGenerator<Uint> m_programPipelineNames;
Uint m_boundProgramPipeline = 0;
TextureState m_textureState;
ProgramState m_programState;
RenderState m_renderState;
@@ -185,20 +185,6 @@ namespace MobileGL::MG_State::GLState {
return m_externalIndex;
}
#define MOBILEGL_DEFINE_FRAMEBUFFER_DEFAULT_SETTER(name, member, type) \
void FramebufferObject::Set##name(type value) { \
if (member == value) return; \
member = value; \
++m_objectVersion; \
}
MOBILEGL_DEFINE_FRAMEBUFFER_DEFAULT_SETTER(DefaultWidth, m_defaultWidth, Int)
MOBILEGL_DEFINE_FRAMEBUFFER_DEFAULT_SETTER(DefaultHeight, m_defaultHeight, Int)
MOBILEGL_DEFINE_FRAMEBUFFER_DEFAULT_SETTER(DefaultLayers, m_defaultLayers, Int)
MOBILEGL_DEFINE_FRAMEBUFFER_DEFAULT_SETTER(DefaultSamples, m_defaultSamples, Int)
MOBILEGL_DEFINE_FRAMEBUFFER_DEFAULT_SETTER(DefaultFixedSampleLocations, m_defaultFixedSampleLocations, Bool)
#undef MOBILEGL_DEFINE_FRAMEBUFFER_DEFAULT_SETTER
void FramebufferObject::BumpAttachmentVersion(FramebufferAttachmentType type) {
++m_attachmentVersions[static_cast<SizeT>(type)];
++m_objectVersion;
@@ -129,19 +129,6 @@ namespace MobileGL {
void SetReadBuffer(FramebufferAttachmentType buf);
FramebufferAttachmentType GetReadBuffer() const { return m_readBuffer; }
// GL_ARB_framebuffer_no_attachments state (GL 4.6 core table 23.24). The shape a
// framebuffer with no attachments would rasterize at; all zero / FALSE until set.
Int GetDefaultWidth() const { return m_defaultWidth; }
Int GetDefaultHeight() const { return m_defaultHeight; }
Int GetDefaultLayers() const { return m_defaultLayers; }
Int GetDefaultSamples() const { return m_defaultSamples; }
Bool GetDefaultFixedSampleLocations() const { return m_defaultFixedSampleLocations; }
void SetDefaultWidth(Int value);
void SetDefaultHeight(Int value);
void SetDefaultLayers(Int value);
void SetDefaultSamples(Int value);
void SetDefaultFixedSampleLocations(Bool value);
FramebufferAttachmentVersionArray GetAllFramebufferAttachmentVersions() const {
return m_attachmentVersions;
}
@@ -161,12 +148,6 @@ namespace MobileGL {
FramebufferAttachmentArray m_drawBuffers; // Probably no versioning needed for this, just check equality
FramebufferAttachmentType m_readBuffer = FramebufferAttachmentType::None;
Int m_defaultWidth = 0;
Int m_defaultHeight = 0;
Int m_defaultLayers = 0;
Int m_defaultSamples = 0;
Bool m_defaultFixedSampleLocations = false;
// This version will bump when draw/read buffer changes (by `glDrawBuffer(s)`/`glReadBuffer`)
Uint16 m_objectVersion = 0;
};
@@ -170,280 +170,9 @@ namespace MobileGL::MG_State::GLState {
m_uniformNameMaxLength = 0;
m_attribInNameMaxLength = 0;
m_uniformBlockNameMaxLength = 0;
m_xfbVaryings.clear();
m_xfbStrides.clear();
m_xfbBufferMode = GL_INTERLEAVED_ATTRIBS;
m_xfbVaryingNameMaxLength = 0;
m_xfbNeedsScatteredCapture = false;
m_xfbPackedStride = 0;
m_gsInputPrimitive = GL_NONE;
m_linkStatus = false;
}
namespace {
// GL type enum for a vertex-stage output symbol captured by transform
// feedback. Covers the scalar/vector/matrix float+integer types transform
// feedback may legally capture in GL 3.3.
Bool ResolveXfbSymbolType(const glslang::TType& type, GLenum& outType, GLint& outArraySize,
Uint32& outBytesPerElement) {
outArraySize = type.isArray() ? type.getOuterArraySize() : 1;
const Int columns = type.isMatrix() ? type.getMatrixCols() : 1;
const Int components = type.isMatrix() ? type.getMatrixRows()
: (type.isVector() ? type.getVectorSize() : 1);
const glslang::TBasicType basic = type.getBasicType();
static constexpr GLenum kFloatTypes[5] = {0, GL_FLOAT, GL_FLOAT_VEC2, GL_FLOAT_VEC3, GL_FLOAT_VEC4};
static constexpr GLenum kIntTypes[5] = {0, GL_INT, GL_INT_VEC2, GL_INT_VEC3, GL_INT_VEC4};
static constexpr GLenum kUintTypes[5] = {0, GL_UNSIGNED_INT, GL_UNSIGNED_INT_VEC2, GL_UNSIGNED_INT_VEC3,
GL_UNSIGNED_INT_VEC4};
static constexpr GLenum kDoubleTypes[5] = {0, GL_DOUBLE, GL_DOUBLE_VEC2, GL_DOUBLE_VEC3,
GL_DOUBLE_VEC4};
if (type.isMatrix()) {
if (basic != glslang::EbtFloat && basic != glslang::EbtDouble) return false;
static constexpr GLenum kMatTypes[5][5] = {
{}, {},
{0, 0, GL_FLOAT_MAT2, GL_FLOAT_MAT2x3, GL_FLOAT_MAT2x4},
{0, 0, GL_FLOAT_MAT3x2, GL_FLOAT_MAT3, GL_FLOAT_MAT3x4},
{0, 0, GL_FLOAT_MAT4x2, GL_FLOAT_MAT4x3, GL_FLOAT_MAT4},
};
static constexpr GLenum kDoubleMatTypes[5][5] = {
{}, {},
{0, 0, GL_DOUBLE_MAT2, GL_DOUBLE_MAT2x3, GL_DOUBLE_MAT2x4},
{0, 0, GL_DOUBLE_MAT3x2, GL_DOUBLE_MAT3, GL_DOUBLE_MAT3x4},
{0, 0, GL_DOUBLE_MAT4x2, GL_DOUBLE_MAT4x3, GL_DOUBLE_MAT4},
};
if (columns < 2 || columns > 4 || components < 2 || components > 4) return false;
outType = basic == glslang::EbtDouble ? kDoubleMatTypes[columns][components]
: kMatTypes[columns][components];
} else if (components >= 1 && components <= 4) {
switch (basic) {
case glslang::EbtFloat: outType = kFloatTypes[components]; break;
case glslang::EbtInt: outType = kIntTypes[components]; break;
case glslang::EbtUint: outType = kUintTypes[components]; break;
// A double-typed varying is capturable like any other; rejecting it here reported
// the varying as "not an output of the vertex stage", which it plainly was.
case glslang::EbtDouble: outType = kDoubleTypes[components]; break;
default: return false;
}
} else {
return false;
}
// GL 4.6 core 11.1.2.1: a double component occupies eight basic machine units, and
// counts as two components against the transform feedback limits.
const Uint32 bytesPerComponent = basic == glslang::EbtDouble ? 8u : 4u;
outBytesPerElement = static_cast<Uint32>(columns * components) * bytesPerComponent;
return true;
}
} // namespace
Bool ProgramObject::ResolveTransformFeedbackVaryings() {
m_xfbVaryings.clear();
m_xfbStrides.clear();
m_xfbBufferMode = m_requestedXfbBufferMode;
m_xfbVaryingNameMaxLength = 0;
m_xfbNeedsScatteredCapture = false;
m_xfbPackedStride = 0;
if (m_requestedXfbVaryings.empty()) {
return true;
}
// Capture happens at the last vertex-processing stage (geometry, then
// tessellation evaluation, then vertex).
const glslang::TIntermediate* captureIntermediate = nullptr;
for (EShLanguage stage : {EShLangGeometry, EShLangTessEvaluation, EShLangVertex}) {
captureIntermediate = m_program->getIntermediate(stage);
if (captureIntermediate != nullptr) {
break;
}
}
if (captureIntermediate == nullptr) {
m_infoLog = "Transform feedback varyings requested but the program has no vertex-processing stage.";
return false;
}
const glslang::TIntermAggregate* linkerObjects = captureIntermediate->findLinkerObjects();
const Bool interleaved = m_xfbBufferMode == GL_INTERLEAVED_ATTRIBS;
Uint32 interleavedOffset = 0;
// ARB_transform_feedback3 lets an interleaved capture leave holes (gl_SkipComponents1..4)
// and move on to the next buffer (gl_NextBuffer). Both only affect where the following
// varyings land, so they are consumed here and never become XfbVaryings of their own -
// which also keeps them out of the name list a backend declares on its own driver.
Uint32 interleavedBufferIndex = 0;
Vector<Uint32> interleavedStrides;
for (SizeT i = 0; i < m_requestedXfbVaryings.size(); ++i) {
const String& name = m_requestedXfbVaryings[i];
if (interleaved && name == "gl_NextBuffer") {
interleavedStrides.push_back(interleavedOffset);
interleavedOffset = 0;
++interleavedBufferIndex;
m_xfbNeedsScatteredCapture = true;
continue;
}
if (interleaved && name.size() == 18 && name.compare(0, 17, "gl_SkipComponents") == 0 &&
name[17] >= '1' && name[17] <= '4') {
interleavedOffset += static_cast<Uint32>(name[17] - '0') * 4;
m_xfbNeedsScatteredCapture = true;
continue;
}
for (SizeT j = 0; j < i; ++j) {
if (m_requestedXfbVaryings[j] == name) {
m_infoLog = "Transform feedback varying '" + name + "' is specified more than once.";
return false;
}
}
XfbVarying varying;
varying.name = name;
Uint32 bytesPerElement = 0;
Bool resolved = false;
if (name == "gl_Position") {
varying.type = GL_FLOAT_VEC4;
varying.size = 1;
bytesPerElement = 16;
resolved = true;
} else if (name == "gl_PointSize") {
varying.type = GL_FLOAT;
varying.size = 1;
bytesPerElement = 4;
resolved = true;
} else if (linkerObjects != nullptr) {
for (const auto* node : linkerObjects->getSequence()) {
const glslang::TIntermSymbol* symbol = node->getAsSymbolNode();
if (symbol == nullptr || symbol->getType().getQualifier().storage != glslang::EvqVaryingOut) {
continue;
}
if (symbol->getName() != name.c_str()) {
continue;
}
resolved = ResolveXfbSymbolType(symbol->getType(), varying.type, varying.size, bytesPerElement);
break;
}
}
if (!resolved) {
m_infoLog = "Transform feedback varying '" + name + "' is not an output of the vertex stage.";
return false;
}
varying.byteSize = bytesPerElement * static_cast<Uint32>(varying.size);
varying.packedOffsetBytes = m_xfbPackedStride;
m_xfbPackedStride += varying.byteSize;
if (interleaved) {
varying.bufferIndex = interleavedBufferIndex;
varying.offsetBytes = interleavedOffset;
interleavedOffset += varying.byteSize;
} else {
varying.bufferIndex = static_cast<Uint32>(m_xfbVaryings.size());
varying.offsetBytes = 0;
}
m_xfbVaryingNameMaxLength =
std::max(m_xfbVaryingNameMaxLength, static_cast<Int>(name.size()) + 1);
m_xfbVaryings.push_back(Move(varying));
}
constexpr Uint32 kMaxSeparateAttribs = 4;
constexpr Uint32 kMaxSeparateComponents = 4;
constexpr Uint32 kMaxInterleavedComponents = 64;
constexpr Uint32 kMaxTransformFeedbackBuffers = 4;
if (interleaved) {
interleavedStrides.push_back(interleavedOffset);
if (interleavedStrides.size() > kMaxTransformFeedbackBuffers) {
m_infoLog = "Transform feedback capture uses more buffers than "
"GL_MAX_TRANSFORM_FEEDBACK_BUFFERS.";
return false;
}
for (const Uint32 stride : interleavedStrides) {
if (stride > kMaxInterleavedComponents * 4) {
m_infoLog = "Transform feedback interleaved capture exceeds "
"GL_MAX_TRANSFORM_FEEDBACK_INTERLEAVED_COMPONENTS.";
return false;
}
}
m_xfbStrides = Move(interleavedStrides);
} else {
if (m_xfbVaryings.size() > kMaxSeparateAttribs) {
m_infoLog = "Transform feedback separate capture exceeds "
"GL_MAX_TRANSFORM_FEEDBACK_SEPARATE_ATTRIBS.";
return false;
}
m_xfbStrides.resize(m_xfbVaryings.size());
for (SizeT i = 0; i < m_xfbVaryings.size(); ++i) {
if (m_xfbVaryings[i].byteSize > kMaxSeparateComponents * 4) {
m_infoLog = "Transform feedback varying '" + m_xfbVaryings[i].name +
"' exceeds GL_MAX_TRANSFORM_FEEDBACK_SEPARATE_COMPONENTS.";
return false;
}
m_xfbStrides[i] = m_xfbVaryings[i].byteSize;
}
}
ResolveGsTriangleStripCapture(captureIntermediate);
return true;
}
namespace {
// Extracts a geometry shader's per-invocation EmitVertex/EndPrimitive sequence
// when it is statically knowable (no emit inside selection/loop/switch). Vulkan
// transform feedback captures triangle strips in plain (i, i+1, i+2) order while
// GL decomposes odd strip triangles as (i+1, i, i+2) (GL 4.6 table 10.1); with
// the static strip lengths the capture buffer can be reordered after EndTF.
class GsEmitSequenceTraverser final : public glslang::TIntermTraverser {
public:
bool visitAggregate(glslang::TVisit, glslang::TIntermAggregate* node) override {
if (node->getOp() == glslang::EOpEmitVertex) {
++emitCount;
hasEmit = true;
} else if (node->getOp() == glslang::EOpEndPrimitive) {
FlushStrip();
}
return true;
}
bool visitSelection(glslang::TVisit, glslang::TIntermSelection*) override {
inControlFlow = true;
return true;
}
bool visitLoop(glslang::TVisit, glslang::TIntermLoop*) override {
inControlFlow = true;
return true;
}
bool visitSwitch(glslang::TVisit, glslang::TIntermSwitch*) override {
inControlFlow = true;
return true;
}
void FlushStrip() {
if (emitCount >= 3) {
stripTriangles.push_back(static_cast<Uint32>(emitCount - 2));
}
emitCount = 0;
}
Vector<Uint32> stripTriangles;
Uint32 emitCount = 0;
Bool hasEmit = false;
Bool inControlFlow = false;
};
} // namespace
void ProgramObject::ResolveGsTriangleStripCapture(const glslang::TIntermediate* captureIntermediate) {
m_gsStripTriangles.clear();
m_gsStripCaptureFixup = false;
if (captureIntermediate == nullptr || m_program == nullptr) {
return;
}
if (m_program->getIntermediate(EShLangGeometry) != captureIntermediate) {
return;
}
if (captureIntermediate->getOutputPrimitive() != glslang::ElgTriangleStrip) {
return;
}
GsEmitSequenceTraverser traverser;
const_cast<glslang::TIntermediate*>(captureIntermediate)->getTreeRoot()->traverse(&traverser);
traverser.FlushStrip(); // the invocation end acts as an implicit EndPrimitive
if (!traverser.hasEmit || traverser.inControlFlow || traverser.stripTriangles.empty()) {
return;
}
m_gsStripTriangles = Move(traverser.stripTriangles);
m_gsStripCaptureFixup = true;
}
bool ProgramObject::ShaderIsAttached(const SharedPtr<ShaderObject>& shader) {
MGLOG_D("ProgramObject %u: ShaderIsAttached check for shader %p", m_externalIndex, shader.get());
auto it = std::find_if(m_shaders.begin(), m_shaders.end(),
@@ -592,32 +321,12 @@ namespace MobileGL::MG_State::GLState {
return;
}
// GL_GEOMETRY_INPUT_TYPE. A draw's primitive type has to be compatible with it
// (GL 4.6 core 11.3.1), so it is resolved for every link, not only a capturing one.
m_gsInputPrimitive = GL_NONE;
if (const glslang::TIntermediate* gs = m_program->getIntermediate(EShLangGeometry)) {
switch (gs->getInputPrimitive()) {
case glslang::ElgPoints: m_gsInputPrimitive = GL_POINTS; break;
case glslang::ElgLines: m_gsInputPrimitive = GL_LINES; break;
case glslang::ElgLinesAdjacency: m_gsInputPrimitive = GL_LINES_ADJACENCY; break;
case glslang::ElgTriangles: m_gsInputPrimitive = GL_TRIANGLES; break;
case glslang::ElgTrianglesAdjacency: m_gsInputPrimitive = GL_TRIANGLES_ADJACENCY; break;
default: break;
}
}
MGLOG_D("ProgramObject %u: Starting reflection", m_externalIndex);
DoReflection();
MGLOG_D("ProgramObject %u: Reflection done (linkStatus=%d)", m_externalIndex, (int)m_linkStatus);
if (!ValidateFragmentOutputLocations()) {
return;
}
if (!ResolveTransformFeedbackVaryings()) {
m_linkStatus = false;
MGLOG_E("ProgramObject %u: transform feedback varying resolution failed: %s", m_externalIndex,
m_infoLog.c_str());
return;
}
MGLOG_D("ProgramObject %u: Starting binary generation", m_externalIndex);
GenerateBinary();
@@ -45,13 +45,6 @@ namespace MobileGL::MG_State::GLState {
Vector<SharedPtr<ShaderObject>>& GetAttachedShaders();
const Vector<SharedPtr<ShaderObject>>& GetAttachedShaders() const;
const String& GetInfoLog() const { return m_infoLog; }
// glCreateShaderProgramv folds the shader's compile log into the program's log, which
// is the only place a caller can read it from once the shader name is gone.
void AppendInfoLog(const String& text) {
if (text.empty()) return;
if (!m_infoLog.empty() && m_infoLog.back() != '\n') m_infoLog += '\n';
m_infoLog += text;
}
Int GetUniformMaxLength() const { return m_uniformNameMaxLength; }
Uint GetUniformCount() const { return m_activeUniformCount; }
Uint GetMaxUniformLocation() const { return m_maxUniformLocation; }
@@ -341,32 +334,16 @@ namespace MobileGL::MG_State::GLState {
// draw. The memo is keyed by (backendStateVersion, flags); ResetLinkArtifacts and
// the binding setters below invalidate it by bumping m_backendStateVersion.
Bool GetBackendHashMemo(Uint flags, Uint64& outHash) const {
if (m_backendHashMemoVersion != m_backendStateVersion) return false;
for (const auto& slot : m_backendHashMemoSlots) {
if (slot.valid && slot.flags == flags) {
outHash = slot.hash;
return true;
}
if (m_backendHashMemoVersion != m_backendStateVersion || m_backendHashMemoFlags != flags) {
return false;
}
return false;
outHash = m_backendHashMemo;
return true;
}
void SetBackendHashMemo(Uint flags, Uint64 hash) const {
if (m_backendHashMemoVersion != m_backendStateVersion) {
for (auto& slot : m_backendHashMemoSlots) slot.valid = false;
m_backendHashMemoVersion = m_backendStateVersion;
m_backendHashMemoNextSlot = 0;
}
for (auto& slot : m_backendHashMemoSlots) {
if (slot.valid && slot.flags == flags) {
slot.hash = hash;
return;
}
}
auto& slot = m_backendHashMemoSlots[m_backendHashMemoNextSlot];
slot.flags = flags;
slot.hash = hash;
slot.valid = true;
m_backendHashMemoNextSlot = (m_backendHashMemoNextSlot + 1) % kBackendHashMemoSlotCount;
m_backendHashMemo = hash;
m_backendHashMemoVersion = m_backendStateVersion;
m_backendHashMemoFlags = flags;
}
void SetUniformSamplerOrImageUnitIndex(Uint location, Int unit) {
@@ -384,22 +361,6 @@ namespace MobileGL::MG_State::GLState {
Bool GetDeleteStatus() const { return m_deleteStatus; }
Bool GetLinkStatus() const { return m_linkStatus; }
// GL_PROGRAM_BINARY_RETRIEVABLE_HINT. MobileGL exposes no program binary format
// (GL_NUM_PROGRAM_BINARY_FORMATS is 0), so the hint is pure state - which is all
// ARB_get_program_binary requires of it.
Bool GetBinaryRetrievableHint() const { return m_binaryRetrievableHint; }
void SetBinaryRetrievableHint(Bool hint) { m_binaryRetrievableHint = hint; }
// GL_PROGRAM_SEPARABLE (GL_ARB_separate_shader_objects): the program may supply a
// subset of the stages of a program pipeline. Only takes effect on the next link,
// which is why it is plain state here rather than something Link() consults.
Bool GetSeparable() const { return m_separable; }
void SetSeparable(Bool separable) { m_separable = separable; }
// glProgramBinary always fails here (there is no format it could accept) and the
// spec then requires the program's LINK_STATUS to read FALSE.
void MarkLinkFailedByProgramBinary() {
ResetLinkArtifacts();
m_infoLog = "No program binary format is supported.";
}
Bool GetValidateStatus() const { return m_validateStatus; }
Int GetActiveAtomicCounterCount() const { return m_program->getNumAtomicCounters(); }
Int GetActiveAttributesCount() const { return m_program->getNumPipeInputs(); }
@@ -488,55 +449,6 @@ namespace MobileGL::MG_State::GLState {
return it == m_shaders.end() ? -1 : (Int)std::distance(m_shaders.begin(), it);
}
// Transform feedback (GL 3.0 core: glTransformFeedbackVaryings applies on
// the NEXT link; the linked snapshot below is what draws and queries see).
struct XfbVarying {
String name;
GLenum type = GL_FLOAT;
GLint size = 1; // array element count
Uint32 bufferIndex = 0; // capture buffer slot
Uint32 offsetBytes = 0; // offset within the capture buffer
Uint32 byteSize = 0; // bytes captured per vertex for this varying
// Offset within the gap-free record a backend that cannot express the GL
// layout captures into; see NeedsScatteredTransformFeedbackCapture.
Uint32 packedOffsetBytes = 0;
};
void SetTransformFeedbackVaryings(Vector<String>&& names, GLenum bufferMode) {
m_requestedXfbVaryings = Move(names);
m_requestedXfbBufferMode = bufferMode;
}
GLenum GetTransformFeedbackBufferMode() const { return m_xfbBufferMode; }
SizeT GetTransformFeedbackVaryingCount() const { return m_xfbVaryings.size(); }
const XfbVarying* GetTransformFeedbackVarying(SizeT index) const {
return index < m_xfbVaryings.size() ? &m_xfbVaryings[index] : nullptr;
}
const Vector<XfbVarying>& GetTransformFeedbackVaryings() const { return m_xfbVaryings; }
// Stride of one captured vertex in the given capture buffer slot.
Uint32 GetTransformFeedbackStride(Uint32 bufferIndex) const {
return bufferIndex < m_xfbStrides.size() ? m_xfbStrides[bufferIndex] : 0;
}
SizeT GetTransformFeedbackBufferCount() const { return m_xfbStrides.size(); }
Int GetTransformFeedbackVaryingMaxLength() const { return m_xfbVaryingNameMaxLength; }
// True when the capture layout uses gl_SkipComponents / gl_NextBuffer
// (ARB_transform_feedback3), which no ES driver can express: it can only pack every
// captured varying into one record with no gaps. A backend that captures through
// such a driver has to capture into scratch storage and scatter the records into the
// application's buffers itself, using packedOffsetBytes as the source offset and
// (bufferIndex, offsetBytes, stride) as the destination.
Bool NeedsScatteredTransformFeedbackCapture() const { return m_xfbNeedsScatteredCapture; }
// Bytes one gap-free captured record occupies.
Uint32 GetTransformFeedbackPackedStride() const { return m_xfbPackedStride; }
// True when the capture stage is a triangle-strip geometry shader with a
// statically-known emit sequence: the Vulkan capture order then needs the GL
// odd-triangle vertex swap after EndTransformFeedback.
Bool HasGsTriangleStripCaptureFixup() const { return m_gsStripCaptureFixup; }
// Triangles per strip, in emission order, for ONE geometry invocation.
const Vector<Uint32>& GetGsStripTriangles() const { return m_gsStripTriangles; }
// GL_GEOMETRY_INPUT_TYPE of the linked geometry stage (GL_POINTS, GL_LINES,
// GL_LINES_ADJACENCY, GL_TRIANGLES or GL_TRIANGLES_ADJACENCY), or GL_NONE when the
// program has no geometry stage. Draws must present a compatible primitive type.
GLenum GetGeometryInputType() const { return m_gsInputPrimitive; }
Uint GetExternalIndex() const { return m_externalIndex; }
// Globally-unique, never-reused id for this program object's lifetime. Unlike the GL
// name (external index), which is freed to a LIFO list and immediately handed back by
@@ -547,11 +459,6 @@ namespace MobileGL::MG_State::GLState {
private:
void ResetLinkArtifacts();
void DoReflection();
// Resolves the requested transform feedback varyings against the linked
// vertex stage; fails the link (GL semantics) on unknown or duplicate
// names or exceeded capture limits.
Bool ResolveTransformFeedbackVaryings();
void ResolveGsTriangleStripCapture(const glslang::TIntermediate* captureIntermediate);
void GenerateBinary();
void WaitUntilGenerationCompleted() const;
void AddDefaultFragmentShaderIfMissing();
@@ -616,39 +523,15 @@ namespace MobileGL::MG_State::GLState {
String m_infoLog;
Bool m_deleteStatus = false;
Bool m_linkStatus = false;
Bool m_binaryRetrievableHint = false;
Bool m_separable = false;
Bool m_validateStatus = true;
Uint32 m_backendStateVersion = 0;
// Backend-owned content-hash memo (see GetBackendHashMemo): valid only while
// m_backendStateVersion matches. Several slots, not one: a backend may resolve the same
// program under more than one compile-flag set within a frame (surface rotation, and the
// explicit-LOD sampling variant), and a single slot would then miss on every lookup and
// re-hash the program's whole SPIR-V once per draw.
static constexpr SizeT kBackendHashMemoSlotCount = 4;
struct BackendHashMemoSlot {
Uint64 hash = 0;
Uint flags = 0;
Bool valid = false;
};
mutable Array<BackendHashMemoSlot, kBackendHashMemoSlotCount> m_backendHashMemoSlots{};
mutable SizeT m_backendHashMemoNextSlot = 0;
// m_backendStateVersion and the compile flags match the recorded values.
mutable Uint64 m_backendHashMemo = 0;
mutable Uint32 m_backendHashMemoVersion = ~0u;
mutable Uint m_backendHashMemoFlags = 0;
Uint32 m_uboContentVersion = 0;
Uint32 m_linkVersion = 0;
// Transform feedback: request (applies at next link) and linked snapshot.
Vector<String> m_requestedXfbVaryings;
GLenum m_requestedXfbBufferMode = GL_INTERLEAVED_ATTRIBS;
Vector<XfbVarying> m_xfbVaryings;
Vector<Uint32> m_xfbStrides;
Vector<Uint32> m_gsStripTriangles;
Bool m_gsStripCaptureFixup = false;
GLenum m_gsInputPrimitive = GL_NONE;
GLenum m_xfbBufferMode = GL_INTERLEAVED_ATTRIBS;
Int m_xfbVaryingNameMaxLength = 0;
Bool m_xfbNeedsScatteredCapture = false;
Uint32 m_xfbPackedStride = 0;
};
} // namespace MobileGL::MG_State::GLState

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