Merge pull request #1596 from spnda/google_display_timing_osx
Implement vkGetRefreshCycleDurationGOOGLE() for macOS
diff --git a/Docs/MoltenVK_Runtime_UserGuide.md b/Docs/MoltenVK_Runtime_UserGuide.md
index ca1c436..23c4bf6 100644
--- a/Docs/MoltenVK_Runtime_UserGuide.md
+++ b/Docs/MoltenVK_Runtime_UserGuide.md
@@ -271,6 +271,7 @@
- `VK_KHR_device_group_creation`
- `VK_KHR_driver_properties`
- `VK_KHR_dynamic_rendering`
+- `VK_KHR_fragment_shader_barycentric` *(requires Metal 2.2 on Mac or Metal 2.3 on iOS)*
- `VK_KHR_get_memory_requirements2`
- `VK_KHR_get_physical_device_properties2`
- `VK_KHR_get_surface_capabilities2`
@@ -328,6 +329,7 @@
- `VK_AMD_shader_trinary_minmax` *(requires Metal 2.1)*
- `VK_IMG_format_pvrtc` *(requires Apple GPU)*
- `VK_INTEL_shader_integer_functions2`
+- `VK_NV_fragment_shader_barycentric` *(requires Metal 2.2 on Mac or Metal 2.3 on iOS)*
- `VK_NV_glsl_shader`
In order to visibly display your content on *macOS*, *iOS*, or *tvOS*, you must enable the
diff --git a/Docs/Whats_New.md b/Docs/Whats_New.md
index d35900a..34e7e5f 100644
--- a/Docs/Whats_New.md
+++ b/Docs/Whats_New.md
@@ -25,11 +25,13 @@
- `VK_KHR_dynamic_rendering`
- `VK_KHR_separate_depth_stencil_layouts`
- `VK_EXT_separate_stencil_usage`
+ - `VK_KHR_fragment_shader_barycentric`
- Support attachment clearing when some clearing formats are not specified.
- Fix error where previously bound push constants can override a descriptor buffer binding
used by a subsequent pipeline that does not use push constants.
- Fix error on some Apple GPU's where a `vkCmdTimestampQuery()` after a renderpass was
writing timestamp before renderpass activity was complete.
+- Fix regression error in vertex buffer binding counts when establishing implicit buffers binding indexes.
- Work around zombie memory bug in Intel Iris Plus Graphics driver when repeatedly retrieving GPU counter sets.
- Update to latest SPIRV-Cross:
- MSL: Emit interface block members of array length 1 as arrays instead of scalars.
diff --git a/ExternalRevisions/Vulkan-Headers_repo_revision b/ExternalRevisions/Vulkan-Headers_repo_revision
index 30e1cdb..c14cbd0 100644
--- a/ExternalRevisions/Vulkan-Headers_repo_revision
+++ b/ExternalRevisions/Vulkan-Headers_repo_revision
@@ -1 +1 @@
-76f00ef6cbb1886eb1162d1fa39bee8b51e22ee8
+245d25ce8c3337919dc7916d0e62e31a0d8748ab
diff --git a/MoltenVK/MoltenVK/Commands/MVKCmdDraw.mm b/MoltenVK/MoltenVK/Commands/MVKCmdDraw.mm
index 8a826fa..3f9a52e 100644
--- a/MoltenVK/MoltenVK/Commands/MVKCmdDraw.mm
+++ b/MoltenVK/MoltenVK/Commands/MVKCmdDraw.mm
@@ -193,7 +193,7 @@
if (pipeline->needsVertexOutputBuffer()) {
[mtlTessCtlEncoder setBuffer: vtxOutBuff->_mtlBuffer
offset: vtxOutBuff->_offset
- atIndex: kMVKTessCtlInputBufferIndex];
+ atIndex: cmdEncoder->getDevice()->getMetalBufferIndexForVertexAttributeBinding(kMVKTessCtlInputBufferBinding)];
}
NSUInteger sgSize = pipeline->getTessControlStageState().threadExecutionWidth;
@@ -221,16 +221,16 @@
if (pipeline->needsTessCtlOutputBuffer()) {
[cmdEncoder->_mtlRenderEncoder setVertexBuffer: tcOutBuff->_mtlBuffer
offset: tcOutBuff->_offset
- atIndex: kMVKTessEvalInputBufferIndex];
+ atIndex: cmdEncoder->getDevice()->getMetalBufferIndexForVertexAttributeBinding(kMVKTessEvalInputBufferBinding)];
}
if (pipeline->needsTessCtlPatchOutputBuffer()) {
[cmdEncoder->_mtlRenderEncoder setVertexBuffer: tcPatchOutBuff->_mtlBuffer
offset: tcPatchOutBuff->_offset
- atIndex: kMVKTessEvalPatchInputBufferIndex];
+ atIndex: cmdEncoder->getDevice()->getMetalBufferIndexForVertexAttributeBinding(kMVKTessEvalPatchInputBufferBinding)];
}
[cmdEncoder->_mtlRenderEncoder setVertexBuffer: tcLevelBuff->_mtlBuffer
offset: tcLevelBuff->_offset
- atIndex: kMVKTessEvalLevelBufferIndex];
+ atIndex: cmdEncoder->getDevice()->getMetalBufferIndexForVertexAttributeBinding(kMVKTessEvalLevelBufferBinding)];
[cmdEncoder->_mtlRenderEncoder setTessellationFactorBuffer: tcLevelBuff->_mtlBuffer
offset: tcLevelBuff->_offset
instanceStride: 0];
@@ -395,7 +395,7 @@
if (pipeline->needsVertexOutputBuffer()) {
[mtlTessCtlEncoder setBuffer: vtxOutBuff->_mtlBuffer
offset: vtxOutBuff->_offset
- atIndex: kMVKTessCtlInputBufferIndex];
+ atIndex: cmdEncoder->getDevice()->getMetalBufferIndexForVertexAttributeBinding(kMVKTessCtlInputBufferBinding)];
}
// The vertex shader produced output in the correct order, so there's no need to use
// an index buffer here.
@@ -424,16 +424,16 @@
if (pipeline->needsTessCtlOutputBuffer()) {
[cmdEncoder->_mtlRenderEncoder setVertexBuffer: tcOutBuff->_mtlBuffer
offset: tcOutBuff->_offset
- atIndex: kMVKTessEvalInputBufferIndex];
+ atIndex: cmdEncoder->getDevice()->getMetalBufferIndexForVertexAttributeBinding(kMVKTessEvalInputBufferBinding)];
}
if (pipeline->needsTessCtlPatchOutputBuffer()) {
[cmdEncoder->_mtlRenderEncoder setVertexBuffer: tcPatchOutBuff->_mtlBuffer
offset: tcPatchOutBuff->_offset
- atIndex: kMVKTessEvalPatchInputBufferIndex];
+ atIndex: cmdEncoder->getDevice()->getMetalBufferIndexForVertexAttributeBinding(kMVKTessEvalPatchInputBufferBinding)];
}
[cmdEncoder->_mtlRenderEncoder setVertexBuffer: tcLevelBuff->_mtlBuffer
offset: tcLevelBuff->_offset
- atIndex: kMVKTessEvalLevelBufferIndex];
+ atIndex: cmdEncoder->getDevice()->getMetalBufferIndexForVertexAttributeBinding(kMVKTessEvalLevelBufferBinding)];
[cmdEncoder->_mtlRenderEncoder setTessellationFactorBuffer: tcLevelBuff->_mtlBuffer
offset: tcLevelBuff->_offset
instanceStride: 0];
@@ -741,7 +741,7 @@
if (pipeline->needsVertexOutputBuffer()) {
[mtlTessCtlEncoder setBuffer: vtxOutBuff->_mtlBuffer
offset: vtxOutBuff->_offset
- atIndex: kMVKTessCtlInputBufferIndex];
+ atIndex: cmdEncoder->getDevice()->getMetalBufferIndexForVertexAttributeBinding(kMVKTessCtlInputBufferBinding)];
}
[mtlTessCtlEncoder dispatchThreadgroupsWithIndirectBuffer: mtlIndBuff
indirectBufferOffset: mtlIndBuffOfst
@@ -757,16 +757,16 @@
if (pipeline->needsTessCtlOutputBuffer()) {
[cmdEncoder->_mtlRenderEncoder setVertexBuffer: tcOutBuff->_mtlBuffer
offset: tcOutBuff->_offset
- atIndex: kMVKTessEvalInputBufferIndex];
+ atIndex: cmdEncoder->getDevice()->getMetalBufferIndexForVertexAttributeBinding(kMVKTessEvalInputBufferBinding)];
}
if (pipeline->needsTessCtlPatchOutputBuffer()) {
[cmdEncoder->_mtlRenderEncoder setVertexBuffer: tcPatchOutBuff->_mtlBuffer
offset: tcPatchOutBuff->_offset
- atIndex: kMVKTessEvalPatchInputBufferIndex];
+ atIndex: cmdEncoder->getDevice()->getMetalBufferIndexForVertexAttributeBinding(kMVKTessEvalPatchInputBufferBinding)];
}
[cmdEncoder->_mtlRenderEncoder setVertexBuffer: tcLevelBuff->_mtlBuffer
offset: tcLevelBuff->_offset
- atIndex: kMVKTessEvalLevelBufferIndex];
+ atIndex: cmdEncoder->getDevice()->getMetalBufferIndexForVertexAttributeBinding(kMVKTessEvalLevelBufferBinding)];
[cmdEncoder->_mtlRenderEncoder setTessellationFactorBuffer: tcLevelBuff->_mtlBuffer
offset: tcLevelBuff->_offset
instanceStride: 0];
@@ -1076,7 +1076,7 @@
if (pipeline->needsVertexOutputBuffer()) {
[mtlTessCtlEncoder setBuffer: vtxOutBuff->_mtlBuffer
offset: vtxOutBuff->_offset
- atIndex: kMVKTessCtlInputBufferIndex];
+ atIndex: cmdEncoder->getDevice()->getMetalBufferIndexForVertexAttributeBinding(kMVKTessCtlInputBufferBinding)];
}
[mtlTessCtlEncoder dispatchThreadgroupsWithIndirectBuffer: mtlIndBuff
indirectBufferOffset: mtlTempIndBuffOfst
@@ -1092,16 +1092,16 @@
if (pipeline->needsTessCtlOutputBuffer()) {
[cmdEncoder->_mtlRenderEncoder setVertexBuffer: tcOutBuff->_mtlBuffer
offset: tcOutBuff->_offset
- atIndex: kMVKTessEvalInputBufferIndex];
+ atIndex: cmdEncoder->getDevice()->getMetalBufferIndexForVertexAttributeBinding(kMVKTessEvalInputBufferBinding)];
}
if (pipeline->needsTessCtlPatchOutputBuffer()) {
[cmdEncoder->_mtlRenderEncoder setVertexBuffer: tcPatchOutBuff->_mtlBuffer
offset: tcPatchOutBuff->_offset
- atIndex: kMVKTessEvalPatchInputBufferIndex];
+ atIndex: cmdEncoder->getDevice()->getMetalBufferIndexForVertexAttributeBinding(kMVKTessEvalPatchInputBufferBinding)];
}
[cmdEncoder->_mtlRenderEncoder setVertexBuffer: tcLevelBuff->_mtlBuffer
offset: tcLevelBuff->_offset
- atIndex: kMVKTessEvalLevelBufferIndex];
+ atIndex: cmdEncoder->getDevice()->getMetalBufferIndexForVertexAttributeBinding(kMVKTessEvalLevelBufferBinding)];
[cmdEncoder->_mtlRenderEncoder setTessellationFactorBuffer: tcLevelBuff->_mtlBuffer
offset: tcLevelBuff->_offset
instanceStride: 0];
diff --git a/MoltenVK/MoltenVK/Commands/MVKCommandEncoderState.h b/MoltenVK/MoltenVK/Commands/MVKCommandEncoderState.h
index d7d2c48..c6e7280 100644
--- a/MoltenVK/MoltenVK/Commands/MVKCommandEncoderState.h
+++ b/MoltenVK/MoltenVK/Commands/MVKCommandEncoderState.h
@@ -407,6 +407,7 @@
// Template function that executes a lambda expression on each dirty element of
// a vector of bindings, and marks the bindings and the vector as no longer dirty.
+ // Clear isDirty flag before operation to allow operation to possibly override.
template<class T, class V>
void encodeBinding(V& bindings,
bool& bindingsDirtyFlag,
@@ -415,8 +416,9 @@
bindingsDirtyFlag = false;
for (auto& b : bindings) {
if (b.isDirty) {
- mtlOperation(_cmdEncoder, b);
b.isDirty = false;
+ mtlOperation(_cmdEncoder, b);
+ if (b.isDirty) { bindingsDirtyFlag = true; }
}
}
}
diff --git a/MoltenVK/MoltenVK/Commands/MVKCommandEncoderState.mm b/MoltenVK/MoltenVK/Commands/MVKCommandEncoderState.mm
index 7d47598..dfb8c1c 100644
--- a/MoltenVK/MoltenVK/Commands/MVKCommandEncoderState.mm
+++ b/MoltenVK/MoltenVK/Commands/MVKCommandEncoderState.mm
@@ -775,26 +775,33 @@
} else if (!forTessellation && stage == kMVKGraphicsStageRasterization) {
encodeBindings(kMVKShaderStageVertex, "vertex", fullImageViewSwizzle,
[pipeline](MVKCommandEncoder* cmdEncoder, MVKMTLBufferBinding& b)->void {
- if (b.isInline) {
- cmdEncoder->setVertexBytes(cmdEncoder->_mtlRenderEncoder,
- b.mtlBytes,
- b.size,
- b.index);
- } else {
- [cmdEncoder->_mtlRenderEncoder setVertexBuffer: b.mtlBuffer
- offset: b.offset
- atIndex: b.index];
+ // The app may have bound more vertex attribute buffers than used by the pipeline.
+ // We must not bind those extra buffers to the shader because they might overwrite
+ // any implicit buffers used by the pipeline.
+ if (pipeline->isValidVertexBufferIndex(kMVKShaderStageVertex, b.index)) {
+ if (b.isInline) {
+ cmdEncoder->setVertexBytes(cmdEncoder->_mtlRenderEncoder,
+ b.mtlBytes,
+ b.size,
+ b.index);
+ } else {
+ [cmdEncoder->_mtlRenderEncoder setVertexBuffer: b.mtlBuffer
+ offset: b.offset
+ atIndex: b.index];
- // Add any translated vertex bindings for this binding
- auto xltdVtxBindings = pipeline->getTranslatedVertexBindings();
- for (auto& xltdBind : xltdVtxBindings) {
- if (b.index == pipeline->getMetalBufferIndexForVertexAttributeBinding(xltdBind.binding)) {
- [cmdEncoder->_mtlRenderEncoder setVertexBuffer: b.mtlBuffer
- offset: b.offset + xltdBind.translationOffset
- atIndex: pipeline->getMetalBufferIndexForVertexAttributeBinding(xltdBind.translationBinding)];
- }
- }
- }
+ // Add any translated vertex bindings for this binding
+ auto xltdVtxBindings = pipeline->getTranslatedVertexBindings();
+ for (auto& xltdBind : xltdVtxBindings) {
+ if (b.index == pipeline->getMetalBufferIndexForVertexAttributeBinding(xltdBind.binding)) {
+ [cmdEncoder->_mtlRenderEncoder setVertexBuffer: b.mtlBuffer
+ offset: b.offset + xltdBind.translationOffset
+ atIndex: pipeline->getMetalBufferIndexForVertexAttributeBinding(xltdBind.translationBinding)];
+ }
+ }
+ }
+ } else {
+ b.isDirty = true; // We haven't written it out, so leave dirty until next time.
+ }
},
[](MVKCommandEncoder* cmdEncoder, MVKMTLBufferBinding& b, const MVKArrayRef<uint32_t> s)->void {
cmdEncoder->setVertexBytes(cmdEncoder->_mtlRenderEncoder,
diff --git a/MoltenVK/MoltenVK/GPUObjects/MVKDevice.mm b/MoltenVK/MoltenVK/GPUObjects/MVKDevice.mm
index a929eeb..0693632 100644
--- a/MoltenVK/MoltenVK/GPUObjects/MVKDevice.mm
+++ b/MoltenVK/MoltenVK/GPUObjects/MVKDevice.mm
@@ -287,6 +287,11 @@
separateDepthStencilLayoutsFeatures->separateDepthStencilLayouts = true;
break;
}
+ case VK_STRUCTURE_TYPE_PHYSICAL_DEVICE_FRAGMENT_SHADER_BARYCENTRIC_FEATURES_KHR: {
+ auto* barycentricProperties = (VkPhysicalDeviceFragmentShaderBarycentricFeaturesKHR*)next;
+ barycentricProperties->fragmentShaderBarycentric = true;
+ break;
+ }
default:
break;
}
@@ -480,6 +485,11 @@
sampLocnProps->variableSampleLocations = VK_FALSE;
break;
}
+ case VK_STRUCTURE_TYPE_PHYSICAL_DEVICE_FRAGMENT_SHADER_BARYCENTRIC_PROPERTIES_KHR: {
+ auto* barycentricProperties = (VkPhysicalDeviceFragmentShaderBarycentricPropertiesKHR*)next;
+ barycentricProperties->triStripVertexOrderIndependentOfProvokingVertex = false;
+ break;
+ }
default:
break;
}
diff --git a/MoltenVK/MoltenVK/GPUObjects/MVKPipeline.h b/MoltenVK/MoltenVK/GPUObjects/MVKPipeline.h
index 21ffc44..88b71b1 100644
--- a/MoltenVK/MoltenVK/GPUObjects/MVKPipeline.h
+++ b/MoltenVK/MoltenVK/GPUObjects/MVKPipeline.h
@@ -112,13 +112,13 @@
#pragma mark -
#pragma mark MVKPipeline
-static const uint32_t kMVKTessCtlInputBufferIndex = 30;
static const uint32_t kMVKTessCtlNumReservedBuffers = 1;
+static const uint32_t kMVKTessCtlInputBufferBinding = 0;
-static const uint32_t kMVKTessEvalInputBufferIndex = 30;
-static const uint32_t kMVKTessEvalPatchInputBufferIndex = 29;
-static const uint32_t kMVKTessEvalLevelBufferIndex = 28;
static const uint32_t kMVKTessEvalNumReservedBuffers = 3;
+static const uint32_t kMVKTessEvalInputBufferBinding = 0;
+static const uint32_t kMVKTessEvalPatchInputBufferBinding = 1;
+static const uint32_t kMVKTessEvalLevelBufferBinding = 2;
/** Represents an abstract Vulkan pipeline. */
class MVKPipeline : public MVKVulkanAPIDeviceObject {
@@ -259,6 +259,13 @@
/** Returns whether this pipeline has custom sample positions enabled. */
bool isUsingCustomSamplePositions() { return _isUsingCustomSamplePositions; }
+ /**
+ * Returns whether the MTLBuffer vertex shader buffer index is valid for a stage of this pipeline.
+ * It is if it is a descriptor binding within the descriptor binding range,
+ * or a vertex attribute binding above any implicit buffer bindings.
+ */
+ bool isValidVertexBufferIndex(MVKShaderStage stage, uint32_t mtlBufferIndex);
+
/** Returns the custom samples used by this pipeline. */
MVKArrayRef<MTLSamplePosition> getCustomSamplePositions() { return _customSamplePositions.contents(); }
@@ -293,6 +300,7 @@
void initCustomSamplePositions(const VkGraphicsPipelineCreateInfo* pCreateInfo);
void initMTLRenderPipelineState(const VkGraphicsPipelineCreateInfo* pCreateInfo, const SPIRVTessReflectionData& reflectData);
void initShaderConversionConfig(SPIRVToMSLConversionConfiguration& shaderConfig, const VkGraphicsPipelineCreateInfo* pCreateInfo, const SPIRVTessReflectionData& reflectData);
+ void initReservedVertexAttributeBufferCount(const VkGraphicsPipelineCreateInfo* pCreateInfo);
void addVertexInputToShaderConversionConfig(SPIRVToMSLConversionConfiguration& shaderConfig, const VkGraphicsPipelineCreateInfo* pCreateInfo);
void addPrevStageOutputToShaderConversionConfig(SPIRVToMSLConversionConfiguration& shaderConfig, SPIRVShaderOutputs& outputs);
MTLRenderPipelineDescriptor* newMTLRenderPipelineDescriptor(const VkGraphicsPipelineCreateInfo* pCreateInfo, const SPIRVTessReflectionData& reflectData);
@@ -313,8 +321,7 @@
bool isRasterizationDisabled(const VkGraphicsPipelineCreateInfo* pCreateInfo);
bool verifyImplicitBuffer(bool needsBuffer, MVKShaderImplicitRezBinding& index, MVKShaderStage stage, const char* name);
uint32_t getTranslatedVertexBinding(uint32_t binding, uint32_t translationOffset, uint32_t maxBinding);
- uint32_t getImplicitBufferIndex(const VkGraphicsPipelineCreateInfo* pCreateInfo, MVKShaderStage stage, uint32_t bufferIndexOffset);
- uint32_t getReservedBufferCount(const VkGraphicsPipelineCreateInfo* pCreateInfo, MVKShaderStage stage);
+ uint32_t getImplicitBufferIndex(MVKShaderStage stage, uint32_t bufferIndexOffset);
const VkPipelineShaderStageCreateInfo* _pVertexSS = nullptr;
const VkPipelineShaderStageCreateInfo* _pTessCtlSS = nullptr;
@@ -351,6 +358,7 @@
float _blendConstants[4] = { 0.0, 0.0, 0.0, 1.0 };
uint32_t _outputControlPointCount;
+ MVKShaderImplicitRezBinding _reservedVertexAttributeBufferCount;
MVKShaderImplicitRezBinding _viewRangeBufferIndex;
MVKShaderImplicitRezBinding _outputBufferIndex;
uint32_t _tessCtlPatchOutputBufferIndex = 0;
diff --git a/MoltenVK/MoltenVK/GPUObjects/MVKPipeline.mm b/MoltenVK/MoltenVK/GPUObjects/MVKPipeline.mm
index bb50b01..f801d3f 100644
--- a/MoltenVK/MoltenVK/GPUObjects/MVKPipeline.mm
+++ b/MoltenVK/MoltenVK/GPUObjects/MVKPipeline.mm
@@ -869,7 +869,7 @@
}
innerLoc = location;
}
- plDesc.vertexDescriptor.attributes[location].bufferIndex = kMVKTessEvalLevelBufferIndex;
+ plDesc.vertexDescriptor.attributes[location].bufferIndex = getMetalBufferIndexForVertexAttributeBinding(kMVKTessEvalLevelBufferBinding);
if (reflectData.patchKind == spv::ExecutionModeTriangles || output.builtin == spv::BuiltInTessLevelOuter) {
plDesc.vertexDescriptor.attributes[location].offset = 0;
plDesc.vertexDescriptor.attributes[location].format = MTLVertexFormatHalf4; // FIXME Should use Float4
@@ -879,7 +879,7 @@
}
} else if (output.perPatch) {
patchOffset = (uint32_t)mvkAlignByteCount(patchOffset, getShaderOutputAlignment(output));
- plDesc.vertexDescriptor.attributes[output.location].bufferIndex = kMVKTessEvalPatchInputBufferIndex;
+ plDesc.vertexDescriptor.attributes[output.location].bufferIndex = getMetalBufferIndexForVertexAttributeBinding(kMVKTessEvalPatchInputBufferBinding);
plDesc.vertexDescriptor.attributes[output.location].format = getPixelFormats()->getMTLVertexFormat(mvkFormatFromOutput(output));
plDesc.vertexDescriptor.attributes[output.location].offset = patchOffset;
patchOffset += getShaderOutputSize(output);
@@ -887,7 +887,7 @@
usedPerPatch = true;
} else {
offset = (uint32_t)mvkAlignByteCount(offset, getShaderOutputAlignment(output));
- plDesc.vertexDescriptor.attributes[output.location].bufferIndex = kMVKTessEvalInputBufferIndex;
+ plDesc.vertexDescriptor.attributes[output.location].bufferIndex = getMetalBufferIndexForVertexAttributeBinding(kMVKTessEvalInputBufferBinding);
plDesc.vertexDescriptor.attributes[output.location].format = getPixelFormats()->getMTLVertexFormat(mvkFormatFromOutput(output));
plDesc.vertexDescriptor.attributes[output.location].offset = offset;
offset += getShaderOutputSize(output);
@@ -896,16 +896,19 @@
}
}
if (usedPerVertex) {
- plDesc.vertexDescriptor.layouts[kMVKTessEvalInputBufferIndex].stepFunction = MTLVertexStepFunctionPerPatchControlPoint;
- plDesc.vertexDescriptor.layouts[kMVKTessEvalInputBufferIndex].stride = mvkAlignByteCount(offset, getShaderOutputAlignment(*firstVertex));
+ uint32_t mtlVBIdx = getMetalBufferIndexForVertexAttributeBinding(kMVKTessEvalInputBufferBinding);
+ plDesc.vertexDescriptor.layouts[mtlVBIdx].stepFunction = MTLVertexStepFunctionPerPatchControlPoint;
+ plDesc.vertexDescriptor.layouts[mtlVBIdx].stride = mvkAlignByteCount(offset, getShaderOutputAlignment(*firstVertex));
}
if (usedPerPatch) {
- plDesc.vertexDescriptor.layouts[kMVKTessEvalPatchInputBufferIndex].stepFunction = MTLVertexStepFunctionPerPatch;
- plDesc.vertexDescriptor.layouts[kMVKTessEvalPatchInputBufferIndex].stride = mvkAlignByteCount(patchOffset, getShaderOutputAlignment(*firstPatch));
+ uint32_t mtlVBIdx = getMetalBufferIndexForVertexAttributeBinding(kMVKTessEvalPatchInputBufferBinding);
+ plDesc.vertexDescriptor.layouts[mtlVBIdx].stepFunction = MTLVertexStepFunctionPerPatch;
+ plDesc.vertexDescriptor.layouts[mtlVBIdx].stride = mvkAlignByteCount(patchOffset, getShaderOutputAlignment(*firstPatch));
}
if (outerLoc != (uint32_t)(-1) || innerLoc != (uint32_t)(-1)) {
- plDesc.vertexDescriptor.layouts[kMVKTessEvalLevelBufferIndex].stepFunction = MTLVertexStepFunctionPerPatch;
- plDesc.vertexDescriptor.layouts[kMVKTessEvalLevelBufferIndex].stride =
+ uint32_t mtlVBIdx = getMetalBufferIndexForVertexAttributeBinding(kMVKTessEvalLevelBufferBinding);
+ plDesc.vertexDescriptor.layouts[mtlVBIdx].stepFunction = MTLVertexStepFunctionPerPatch;
+ plDesc.vertexDescriptor.layouts[mtlVBIdx].stride =
reflectData.patchKind == spv::ExecutionModeTriangles ? sizeof(MTLTriangleTessellationFactorsHalf) :
sizeof(MTLQuadTessellationFactorsHalf);
}
@@ -1074,7 +1077,7 @@
shaderConfig.options.entryPointName = _pTessCtlSS->pName;
shaderConfig.options.mslOptions.swizzle_buffer_index = _swizzleBufferIndex.stages[kMVKShaderStageTessCtl];
shaderConfig.options.mslOptions.indirect_params_buffer_index = _indirectParamsIndex.stages[kMVKShaderStageTessCtl];
- shaderConfig.options.mslOptions.shader_input_buffer_index = kMVKTessCtlInputBufferIndex;
+ shaderConfig.options.mslOptions.shader_input_buffer_index = getMetalBufferIndexForVertexAttributeBinding(kMVKTessCtlInputBufferBinding);
shaderConfig.options.mslOptions.shader_output_buffer_index = _outputBufferIndex.stages[kMVKShaderStageTessCtl];
shaderConfig.options.mslOptions.shader_patch_output_buffer_index = _tessCtlPatchOutputBufferIndex;
shaderConfig.options.mslOptions.shader_tess_factor_buffer_index = _tessCtlLevelBufferIndex;
@@ -1571,16 +1574,17 @@
// FIXME: Many of these are optional. We shouldn't set the ones that aren't
// present--or at least, we should move the ones that are down to avoid running over
// the limit of available buffers. But we can't know that until we compile the shaders.
+ initReservedVertexAttributeBufferCount(pCreateInfo);
for (uint32_t i = kMVKShaderStageVertex; i < kMVKShaderStageCount; i++) {
MVKShaderStage stage = (MVKShaderStage)i;
- _dynamicOffsetBufferIndex.stages[stage] = getImplicitBufferIndex(pCreateInfo, stage, 0);
- _bufferSizeBufferIndex.stages[stage] = getImplicitBufferIndex(pCreateInfo, stage, 1);
- _swizzleBufferIndex.stages[stage] = getImplicitBufferIndex(pCreateInfo, stage, 2);
- _indirectParamsIndex.stages[stage] = getImplicitBufferIndex(pCreateInfo, stage, 3);
- _outputBufferIndex.stages[stage] = getImplicitBufferIndex(pCreateInfo, stage, 4);
+ _dynamicOffsetBufferIndex.stages[stage] = getImplicitBufferIndex(stage, 0);
+ _bufferSizeBufferIndex.stages[stage] = getImplicitBufferIndex(stage, 1);
+ _swizzleBufferIndex.stages[stage] = getImplicitBufferIndex(stage, 2);
+ _indirectParamsIndex.stages[stage] = getImplicitBufferIndex(stage, 3);
+ _outputBufferIndex.stages[stage] = getImplicitBufferIndex(stage, 4);
if (stage == kMVKShaderStageTessCtl) {
- _tessCtlPatchOutputBufferIndex = getImplicitBufferIndex(pCreateInfo, stage, 5);
- _tessCtlLevelBufferIndex = getImplicitBufferIndex(pCreateInfo, stage, 6);
+ _tessCtlPatchOutputBufferIndex = getImplicitBufferIndex(stage, 5);
+ _tessCtlLevelBufferIndex = getImplicitBufferIndex(stage, 6);
}
}
// Since we currently can't use multiview with tessellation or geometry shaders,
@@ -1630,17 +1634,48 @@
shaderConfig.options.numTessControlPoints = reflectData.numControlPoints;
}
-uint32_t MVKGraphicsPipeline::getImplicitBufferIndex(const VkGraphicsPipelineCreateInfo* pCreateInfo, MVKShaderStage stage, uint32_t bufferIndexOffset) {
- return _device->_pMetalFeatures->maxPerStageBufferCount - (getReservedBufferCount(pCreateInfo, stage) + bufferIndexOffset + 1);
+uint32_t MVKGraphicsPipeline::getImplicitBufferIndex(MVKShaderStage stage, uint32_t bufferIndexOffset) {
+ return getMetalBufferIndexForVertexAttributeBinding(_reservedVertexAttributeBufferCount.stages[stage] + bufferIndexOffset);
}
-uint32_t MVKGraphicsPipeline::getReservedBufferCount(const VkGraphicsPipelineCreateInfo* pCreateInfo, MVKShaderStage stage) {
- switch (stage) {
- case kMVKShaderStageVertex: return pCreateInfo->pVertexInputState->vertexBindingDescriptionCount;
- case kMVKShaderStageTessCtl: return kMVKTessCtlNumReservedBuffers;
- case kMVKShaderStageTessEval: return kMVKTessEvalNumReservedBuffers;
- default: return 0;
+// Set the number of vertex attribute buffers consumed by this pipeline at each stage.
+// Any implicit buffers needed by this pipeline will be assigned indexes below the range
+// defined by this count below the max number of Metal buffer bindings per stage.
+// Must be called before any calls to getImplicitBufferIndex().
+void MVKGraphicsPipeline::initReservedVertexAttributeBufferCount(const VkGraphicsPipelineCreateInfo* pCreateInfo) {
+ int32_t maxBinding = -1;
+ uint32_t xltdBuffCnt = 0;
+
+ const VkPipelineVertexInputStateCreateInfo* pVI = pCreateInfo->pVertexInputState;
+ uint32_t vaCnt = pVI->vertexAttributeDescriptionCount;
+ uint32_t vbCnt = pVI->vertexBindingDescriptionCount;
+
+ // Determine the highest binding number used by the vertex buffers
+ for (uint32_t vbIdx = 0; vbIdx < vbCnt; vbIdx++) {
+ const VkVertexInputBindingDescription* pVKVB = &pVI->pVertexBindingDescriptions[vbIdx];
+ maxBinding = max<int32_t>(pVKVB->binding, maxBinding);
+
+ // Iterate through the vertex attributes and determine if any need a synthetic binding buffer to
+ // accommodate offsets that are outside the stride, which Vulkan supports, but Metal does not.
+ // This value will be worst case, as some synthetic buffers may end up being shared.
+ for (uint32_t vaIdx = 0; vaIdx < vaCnt; vaIdx++) {
+ const VkVertexInputAttributeDescription* pVKVA = &pVI->pVertexAttributeDescriptions[vaIdx];
+ if ((pVKVA->binding == pVKVB->binding) && (pVKVA->offset + getPixelFormats()->getBytesPerBlock(pVKVA->format) > pVKVB->stride)) {
+ xltdBuffCnt++;
+ }
+ }
}
+
+ // The number of reserved bindings we need for the vertex stage is determined from the largest vertex
+ // attribute binding number, plus any synthetic buffer bindings created to support translated offsets.
+ mvkClear<uint32_t>(_reservedVertexAttributeBufferCount.stages, kMVKShaderStageCount);
+ _reservedVertexAttributeBufferCount.stages[kMVKShaderStageVertex] = (maxBinding + 1) + xltdBuffCnt;
+ _reservedVertexAttributeBufferCount.stages[kMVKShaderStageTessCtl] = kMVKTessCtlNumReservedBuffers;
+ _reservedVertexAttributeBufferCount.stages[kMVKShaderStageTessEval] = kMVKTessEvalNumReservedBuffers;
+}
+
+bool MVKGraphicsPipeline::isValidVertexBufferIndex(MVKShaderStage stage, uint32_t mtlBufferIndex) {
+ return mtlBufferIndex < _descriptorBufferCounts.stages[stage] || mtlBufferIndex > getImplicitBufferIndex(stage, 0);
}
// Initializes the vertex attributes in a shader conversion configuration.
diff --git a/MoltenVK/MoltenVK/Layers/MVKExtensions.def b/MoltenVK/MoltenVK/Layers/MVKExtensions.def
index 019b23b..927e233 100644
--- a/MoltenVK/MoltenVK/Layers/MVKExtensions.def
+++ b/MoltenVK/MoltenVK/Layers/MVKExtensions.def
@@ -58,6 +58,7 @@
MVK_EXTENSION(KHR_external_memory_capabilities, KHR_EXTERNAL_MEMORY_CAPABILITIES, INSTANCE, 10.11, 8.0)
MVK_EXTENSION(KHR_external_semaphore, KHR_EXTERNAL_SEMAPHORE, DEVICE, 10.11, 8.0)
MVK_EXTENSION(KHR_external_semaphore_capabilities, KHR_EXTERNAL_SEMAPHORE_CAPABILITIES, INSTANCE, 10.11, 8.0)
+MVK_EXTENSION(KHR_fragment_shader_barycentric, KHR_FRAGMENT_SHADER_BARYCENTRIC, DEVICE, 10.15, 14.0)
MVK_EXTENSION(KHR_get_memory_requirements2, KHR_GET_MEMORY_REQUIREMENTS_2, DEVICE, 10.11, 8.0)
MVK_EXTENSION(KHR_get_physical_device_properties2, KHR_GET_PHYSICAL_DEVICE_PROPERTIES_2, INSTANCE, 10.11, 8.0)
MVK_EXTENSION(KHR_get_surface_capabilities2, KHR_GET_SURFACE_CAPABILITIES_2, INSTANCE, 10.11, 8.0)
@@ -117,6 +118,7 @@
MVK_EXTENSION(MVK_ios_surface, MVK_IOS_SURFACE, INSTANCE, MVK_NA, 8.0)
MVK_EXTENSION(MVK_macos_surface, MVK_MACOS_SURFACE, INSTANCE, 10.11, MVK_NA)
MVK_EXTENSION(MVK_moltenvk, MVK_MOLTENVK, INSTANCE, 10.11, 8.0)
+MVK_EXTENSION(NV_fragment_shader_barycentric, NV_FRAGMENT_SHADER_BARYCENTRIC, DEVICE, 10.15, 14.0)
MVK_EXTENSION_LAST(NV_glsl_shader, NV_GLSL_SHADER, DEVICE, 10.11, 8.0)
#undef MVK_EXTENSION
