swung0x48/MobileGL
1
0
Fork 0
mirror of https://github.com/MobileGL-Dev/MobileGL synced 2026-09-08 20:28:32 +09:00
Code Issues Packages Projects Releases Wiki Activity

[Fix] (DirectVulkan, ShaderTranspiler, MG_IntegrationTest, SelfTest, TraceReplay): use native subgroups and patch iterationRP's under-declared scratch

Browse Source 
iterationRP's Program 203 declares shared vec2 prefixSumCache[32] for a
512-invocation workgroup indexed by gl_SubgroupID; any device narrower
than 16 lanes partitions into more than 32 subgroups and the pack writes
shared memory out of bounds (heap corruption on lavapipe's CPU
rasterizer, ssim 0.028 on the CI retrace). Fix it where the fault lies -
in the fixture - and keep the GL contract sound everywhere else:

- FixIterationRPSubgroupScratchPass: fingerprint-gated SPIR-V pass that
  grows exactly that array to ceil(invocations/width) entries on sub-16-lane devices; every other module passes through byte-identical.
- DeriveNumSubgroupsPass stays default-on for the Adreno topology bug
  and is made spec-sound: pipelines request REQUIRE_FULL_SUBGROUPS
  whenever the workgroup shape makes the flag legal (computeFullSubgroups
  enabled, local_size_x a multiple of the native width, subgroup count
  within maxComputeWorkgroupSubgroups).
- EmulateSubgroupsPass: 32-lane virtual-subgroup lowering kept in-tree
  as a last resort, enabled only by MOBILEGL_MAGMA_EMULATE_SUBGROUP=1 on
  devices with no native subgroup support; fails closed on extended
  subgroup instructions and on modules whose added scratch would exceed
  maxComputeSharedMemorySize.
- IterationRPFirstReductionScenario skips gracefully outside the pack's
  16..256-lane source domain; the new IterationRPScratchFixScenario runs
  the fixture-shaped reduction on any width and asserts the exact
  width-independent total. DriverPost keeps reporting FAIL on
  out-of-domain devices.
- Program203 -> IterationRP rename throughout; the per-trace
  num_subgroups_quirk plumbing is removed from the trace replayer, JNI
  chain, and CI workflows.
This commit is contained in:
swung0x48
2026-08-19 09:48:11 -04:00
parent 2b6c2b561c
commit d8576a2ed3
38 changed files with 3354 additions and 396 deletions
Download Patch File Download Diff File Expand all files Collapse all files
MobileGL/MG_Backend/DirectVulkan/Renderer/VulkanRenderer.cpp
+80 -1
View File
@@ -8,6 +8,7 @@
#include "VulkanRenderer.h"
#include "MG_Backend/DirectVulkan/SubgroupSupportPolicy.h"
#include "MG_Backend/DirectGLES/Utils.h"
#include "VertexInputStateFactory.h"
#include "VertexInputStateBuilder.h"
@@ -3058,11 +3059,22 @@ void main() {
}
PipelineFactory::SetSuppressBlendedDepthWrite(suppressBlendedDepthWrite);
}
ProgramFactory::SubgroupLoweringPolicy subgroupPolicy{};
subgroupPolicy.emulateSubgroups = ShouldEmulateSubgroups(m_nativeSubgroupSupported);
subgroupPolicy.fixIterationRPSubgroupScratch =
m_nativeSubgroupSupported && ShouldFixIterationRPSubgroupScratch();
subgroupPolicy.deriveNumSubgroups =
m_nativeSubgroupSupported && ShouldDeriveNumSubgroups();
subgroupPolicy.requireFullSubgroups = m_computeFullSubgroupsFeatureEnabled;
subgroupPolicy.nativeSubgroupSize = m_nativeSubgroupSize;
subgroupPolicy.maxComputeWorkgroupSubgroups = m_maxComputeWorkgroupSubgroups;
subgroupPolicy.maxComputeSharedMemoryBytes =
m_physicalDevice.properties.limits.maxComputeSharedMemorySize;
m_programFactory = MakeUnique<ProgramFactory>(m_device, m_config, maxProgramBindings,
m_shaderDrawParametersFeatureEnabled,
m_unformattedFloatStorageImagesEnabled,
MG_Config::Features.EnableSpirvValidation,
m_updateAfterBindLimits);
m_updateAfterBindLimits, subgroupPolicy);
MOBILEGL_ASSERT(m_programFactory != nullptr, "ProgramFactory creation failed.");
// The swapchain already exists at this point (Initialize creates it first), so seed the
// height the factory could not be told about from CreateSwapchain.
@@ -12740,6 +12752,73 @@ void main() {
}
}
// Native subgroup topology, and VK_EXT_subgroup_size_control's
// computeFullSubgroups feature. REQUIRE_FULL_SUBGROUPS on a compute stage is what
// turns the derived gl_NumSubgroups (DeriveNumSubgroupsPass) from
// encouraged-but-unspecified driver behaviour into a spec guarantee: with the bit
// set and local_size_x a multiple of the subgroup size, every subgroup launches
// full, so the subgroup count is exactly invocations / size ("Full Subgroups",
// VUID-VkPipelineShaderStageCreateInfo-flags-02759/-02785).
m_nativeSubgroupSize = 0;
m_nativeSubgroupSupported = false;
m_computeFullSubgroupsFeatureEnabled = false;
if (getPhysicalDeviceProperties2 != nullptr) {
VkPhysicalDeviceSubgroupProperties subgroupProperties{};
subgroupProperties.sType = VK_STRUCTURE_TYPE_PHYSICAL_DEVICE_SUBGROUP_PROPERTIES;
VkPhysicalDeviceProperties2 subgroupPropertyQuery{};
subgroupPropertyQuery.sType = VK_STRUCTURE_TYPE_PHYSICAL_DEVICE_PROPERTIES_2;
subgroupPropertyQuery.pNext = &subgroupProperties;
getPhysicalDeviceProperties2(m_physicalDevice.handle, &subgroupPropertyQuery);
// Mirrors the loader's HasUsableShaderSubgroupSupport gate, including the
// MOBILEGL_DISABLE_SUBGROUP escape hatch, so the module lowerings can never
// disagree with the advertised capabilities.
const Bool usableSubgroups =
subgroupProperties.subgroupSize > 0 &&
(subgroupProperties.supportedStages & VK_SHADER_STAGE_COMPUTE_BIT) != 0 &&
(subgroupProperties.supportedOperations & VK_SUBGROUP_FEATURE_BASIC_BIT) != 0;
if (usableSubgroups && !MG_Config::Features.DisableSubgroup) {
m_nativeSubgroupSize = subgroupProperties.subgroupSize;
m_nativeSubgroupSupported = true;
}
}
VkPhysicalDeviceSubgroupSizeControlFeaturesEXT subgroupSizeControlFeatures{};
subgroupSizeControlFeatures.sType =
VK_STRUCTURE_TYPE_PHYSICAL_DEVICE_SUBGROUP_SIZE_CONTROL_FEATURES_EXT;
m_maxComputeWorkgroupSubgroups = 0;
if (m_nativeSubgroupSupported &&
IsExtensionSupported(availableExtensions, VK_EXT_SUBGROUP_SIZE_CONTROL_EXTENSION_NAME) &&
getPhysicalDeviceFeatures2 != nullptr) {
VkPhysicalDeviceFeatures2 featureQuery{};
featureQuery.sType = VK_STRUCTURE_TYPE_PHYSICAL_DEVICE_FEATURES_2;
featureQuery.pNext = &subgroupSizeControlFeatures;
getPhysicalDeviceFeatures2(m_physicalDevice.handle, &featureQuery);
if (getPhysicalDeviceProperties2 != nullptr) {
VkPhysicalDeviceSubgroupSizeControlPropertiesEXT subgroupSizeControlProperties{};
subgroupSizeControlProperties.sType =
VK_STRUCTURE_TYPE_PHYSICAL_DEVICE_SUBGROUP_SIZE_CONTROL_PROPERTIES_EXT;
VkPhysicalDeviceProperties2 propertyQuery{};
propertyQuery.sType = VK_STRUCTURE_TYPE_PHYSICAL_DEVICE_PROPERTIES_2;
propertyQuery.pNext = &subgroupSizeControlProperties;
getPhysicalDeviceProperties2(m_physicalDevice.handle, &propertyQuery);
m_maxComputeWorkgroupSubgroups =
subgroupSizeControlProperties.maxComputeWorkgroupSubgroups;
}
if (subgroupSizeControlFeatures.computeFullSubgroups == VK_TRUE) {
if (!IsExtensionAlreadyEnabled(enabledDeviceExtensions,
VK_EXT_SUBGROUP_SIZE_CONTROL_EXTENSION_NAME)) {
enabledDeviceExtensions.push_back(VK_EXT_SUBGROUP_SIZE_CONTROL_EXTENSION_NAME);
}
// Only the full-subgroups guarantee is wanted; required/varying subgroup
// sizes stay unrequested.
subgroupSizeControlFeatures.subgroupSizeControl = VK_FALSE;
subgroupSizeControlFeatures.pNext = const_cast<void*>(deviceCreateInfo.pNext);
deviceCreateInfo.pNext = &subgroupSizeControlFeatures;
m_computeFullSubgroupsFeatureEnabled = true;
MGLOG_I("Enabled optional device extension: %s (computeFullSubgroups)",
VK_EXT_SUBGROUP_SIZE_CONTROL_EXTENSION_NAME);
}
}
// VK_EXT_transform_feedback backs GL transform feedback capture.
m_transformFeedbackFeatureEnabled = false;
VkPhysicalDeviceTransformFeedbackFeaturesEXT transformFeedbackFeatures{};