vkCmdDispatchTileQCOM - Dispatch per-tile work items

Description

This command operates in the per-tile execution model, invoking a separate dispatch for each covered tile. The global workgroup count and local workgroup size of each dispatch are defined by the implementation to efficiently iterate over a uniform grid of pixel blocks within the area of its active tile.

Each shader invocation operates on a single pixel block and its size is determined by the shader’s tiling rate, which must be defined by shaders executed by this command. The TileShadingRateQCOM execution mode operand defines the shader’s tiling rate. Its x and y must be a power of two and less than or equal to the maxTileShadingRate limit. Its z must be less than or equal to the active tile’s depth as reported by VK_QCOM_tile_properties, and TilePropertiesQCOM.tileSize.z % TileShadingRateQCOM::z must equal 0.

The start location of the shader invocation’s pixel block is vec3(TileOffsetQCOM, 0) + (GlobalInvocationId * TileShadingRateQCOM)

Shader invocations can perform tile attachment load/store operations at any location within the active tile, but the most efficient access may be limited to fragment locations within and local to the shader invocation’s pixel block.

Valid Usage

• If a Sampler created with magFilter or minFilter equal to FILTER_LINEAR, reductionMode equal to SAMPLER_REDUCTION_MODE_WEIGHTED_AVERAGE, and compareEnable equal to FALSE is used to sample a ImageView as a result of this command, then the image view’s format features must contain FORMAT_FEATURE_SAMPLED_IMAGE_FILTER_LINEAR_BIT

• If a Sampler created with magFilter or minFilter equal to FILTER_LINEAR and reductionMode equal to either SAMPLER_REDUCTION_MODE_MIN or SAMPLER_REDUCTION_MODE_MAX is used to sample a ImageView as a result of this command, then the image view’s format features must contain FORMAT_FEATURE_SAMPLED_IMAGE_FILTER_MINMAX_BIT
• If a Sampler created with mipmapMode equal to SAMPLER_MIPMAP_MODE_LINEAR, reductionMode equal to SAMPLER_REDUCTION_MODE_WEIGHTED_AVERAGE, and compareEnable equal to FALSE is used to sample a ImageView as a result of this command, then the image view’s format features must contain FORMAT_FEATURE_SAMPLED_IMAGE_FILTER_LINEAR_BIT
• If a Sampler created with mipmapMode equal to SAMPLER_MIPMAP_MODE_LINEAR and reductionMode equal to either SAMPLER_REDUCTION_MODE_MIN or SAMPLER_REDUCTION_MODE_MAX is used to sample a ImageView as a result of this command, then the image view’s format features must contain FORMAT_FEATURE_SAMPLED_IMAGE_FILTER_MINMAX_BIT
• If a Sampler created with unnormalizedCoordinates equal to TRUE is used to sample a ImageView as a result of this command, then the image view’s levelCount and layerCount must be 1
• If a Sampler created with unnormalizedCoordinates equal to TRUE is used to sample a ImageView as a result of this command, then the image view’s viewType must be IMAGE_VIEW_TYPE_1D or IMAGE_VIEW_TYPE_2D
• If a Sampler created with unnormalizedCoordinates equal to TRUE is used to sample a ImageView as a result of this command, then the sampler must not be used with any of the SPIR-V OpImageSample* or OpImageSparseSample* instructions with ImplicitLod, Dref or Proj in their name
• If a Sampler created with unnormalizedCoordinates equal to TRUE is used to sample a ImageView as a result of this command, then the sampler must not be used with any of the SPIR-V OpImageSample* or OpImageSparseSample* instructions that includes a LOD bias or any offset values
• If a ImageView is sampled with depth comparison, the image view’s format features must contain FORMAT_FEATURE_2_SAMPLED_IMAGE_DEPTH_COMPARISON_BIT
• If a ImageView is accessed using atomic operations as a result of this command, then the image view’s format features must contain FORMAT_FEATURE_STORAGE_IMAGE_ATOMIC_BIT
• If a DESCRIPTOR_TYPE_STORAGE_TEXEL_BUFFER descriptor is accessed using atomic operations as a result of this command, then the storage texel buffer’s format features must contain FORMAT_FEATURE_STORAGE_TEXEL_BUFFER_ATOMIC_BIT
• If a ImageView is sampled with FILTER_CUBIC_EXT as a result of this command, then the image view’s format features must contain FORMAT_FEATURE_SAMPLED_IMAGE_FILTER_CUBIC_BIT_EXT
• If the VK_EXT_filter_cubic extension is not enabled and any ImageView is sampled with FILTER_CUBIC_EXT as a result of this command, it must not have a ImageViewType of IMAGE_VIEW_TYPE_3D, IMAGE_VIEW_TYPE_CUBE, or IMAGE_VIEW_TYPE_CUBE_ARRAY
• Any ImageView being sampled with FILTER_CUBIC_EXT as a result of this command must have a ImageViewType and format that supports cubic filtering, as specified by FilterCubicImageViewImageFormatPropertiesEXT::filterCubic returned by getPhysicalDeviceImageFormatProperties2
• Any ImageView being sampled with FILTER_CUBIC_EXT with a reduction mode of either SAMPLER_REDUCTION_MODE_MIN or SAMPLER_REDUCTION_MODE_MAX as a result of this command must have a ImageViewType and format that supports cubic filtering together with minmax filtering, as specified by FilterCubicImageViewImageFormatPropertiesEXT::filterCubicMinmax returned by getPhysicalDeviceImageFormatProperties2
• If the cubicRangeClamp feature is not enabled, then any ImageView being sampled with FILTER_CUBIC_EXT as a result of this command must not have a SamplerReductionModeCreateInfo::reductionMode equal to SAMPLER_REDUCTION_MODE_WEIGHTED_AVERAGE_RANGECLAMP_QCOM
• Any ImageView being sampled with a SamplerReductionModeCreateInfo::reductionMode equal to SAMPLER_REDUCTION_MODE_WEIGHTED_AVERAGE_RANGECLAMP_QCOM as a result of this command must sample with FILTER_CUBIC_EXT
• If the selectableCubicWeights feature is not enabled, then any ImageView being sampled with FILTER_CUBIC_EXT as a result of this command must have SamplerCubicWeightsCreateInfoQCOM::cubicWeights equal to CUBIC_FILTER_WEIGHTS_CATMULL_ROM_QCOM
• Any Image created with a ImageCreateInfo::flags containing IMAGE_CREATE_CORNER_SAMPLED_BIT_NV sampled as a result of this command must only be sampled using a SamplerAddressMode of SAMPLER_ADDRESS_MODE_CLAMP_TO_EDGE
• For any ImageView being written as a storage image where the image format field of the OpTypeImage is Unknown, the view’s format features must contain FORMAT_FEATURE_2_STORAGE_WRITE_WITHOUT_FORMAT_BIT
• For any ImageView being read as a storage image where the image format field of the OpTypeImage is Unknown, the view’s format features must contain FORMAT_FEATURE_2_STORAGE_READ_WITHOUT_FORMAT_BIT
• For any BufferView being written as a storage texel buffer where the image format field of the OpTypeImage is Unknown, the view’s buffer features must contain FORMAT_FEATURE_2_STORAGE_WRITE_WITHOUT_FORMAT_BIT
• Any BufferView being read as a storage texel buffer where the image format field of the OpTypeImage is Unknown then the view’s buffer features must contain FORMAT_FEATURE_2_STORAGE_READ_WITHOUT_FORMAT_BIT
• If a a bound shader was created as a ShaderEXT without the SHADER_CREATE_DESCRIPTOR_HEAP_BIT_EXT flag or as part of a pipeline without the PIPELINE_CREATE_2_DESCRIPTOR_HEAP_BIT_EXT flag, and that shader statically uses a set n, a descriptor set must have been bound to n at the same pipeline bind point, with a PipelineLayout that is compatible for set n, with the PipelineLayout used to create the current Pipeline or the DescriptorSetLayout array used to create the current ShaderEXT , as described in ???
• If a a bound shader was created as a ShaderEXT without the SHADER_CREATE_DESCRIPTOR_HEAP_BIT_EXT flag or as part of a pipeline without the PIPELINE_CREATE_2_DESCRIPTOR_HEAP_BIT_EXT flag, and that shader statically uses a push constant value, that value must have been set for the same pipeline bind point, with a PipelineLayout that is compatible for push constants with the PipelineLayout used to create the current Pipeline or the DescriptorSetLayout array used to create the current ShaderEXT
• For each array of resources that is used by a bound shader, the indices used to access members of the array must be less than the descriptor count for the identified binding in the descriptor sets used by this command
• If a a bound shader was created as a ShaderEXT without the SHADER_CREATE_DESCRIPTOR_HEAP_BIT_EXT flag or as part of a pipeline without the PIPELINE_CREATE_2_DESCRIPTOR_HEAP_BIT_EXT flag, and that shader statically uses a push constant value, that value must have been set for the same pipeline bind point, with a PipelineLayout that is compatible for push constants with the PipelineLayout used to create the current Pipeline or the DescriptorSetLayout and PushConstantRange arrays used to create the current ShaderEXT
• Descriptors in each bound descriptor set, specified via cmdBindDescriptorSets, must be valid if they are accessed as described by descriptor validity by the Pipeline bound to the pipeline bind point used by this command and the bound Pipeline was not created with PIPELINE_CREATE_DESCRIPTOR_BUFFER_BIT_EXT
• If an image descriptor is accessed by a shader, the ImageLayout must match the subresource accessible from the ImageView as defined by the image layout matching rules
• If the descriptors used by the Pipeline bound to the pipeline bind point were specified via cmdBindDescriptorSets, the bound Pipeline must have been created without PIPELINE_CREATE_DESCRIPTOR_BUFFER_BIT_EXT
• Descriptors in bound descriptor buffers, specified via cmdSetDescriptorBufferOffsetsEXT, must be valid if they are dynamically used by the Pipeline bound to the pipeline bind point used by this command and the bound Pipeline was created with PIPELINE_CREATE_DESCRIPTOR_BUFFER_BIT_EXT
• Descriptors in bound descriptor buffers, specified via cmdSetDescriptorBufferOffsetsEXT, must be valid if they are dynamically used by any ShaderEXT bound to a stage corresponding to the pipeline bind point used by this command
• If the descriptors used by the Pipeline bound to the pipeline bind point were specified via cmdSetDescriptorBufferOffsetsEXT, the bound Pipeline must have been created with PIPELINE_CREATE_DESCRIPTOR_BUFFER_BIT_EXT
• If a descriptor is dynamically used with a Pipeline created with PIPELINE_CREATE_DESCRIPTOR_BUFFER_BIT_EXT, the descriptor memory must be resident
• If a descriptor is dynamically used with a ShaderEXT created with a DescriptorSetLayout that was created with DESCRIPTOR_SET_LAYOUT_CREATE_DESCRIPTOR_BUFFER_BIT_EXT, the descriptor memory must be resident
• If the shaderObject feature is not enabled, a valid pipeline must be bound to the pipeline bind point used by this command
• If a pipeline is bound to the pipeline bind point used by this command, there must not have been any calls to dynamic state setting commands for any state specified statically in the Pipeline object bound to the pipeline bind point used by this command, since that pipeline was bound
• If any stage of the Pipeline object bound to the pipeline bind point used by this command accesses a uniform buffer, and that stage was created without enabling either PIPELINE_ROBUSTNESS_BUFFER_BEHAVIOR_ROBUST_BUFFER_ACCESS or PIPELINE_ROBUSTNESS_BUFFER_BEHAVIOR_ROBUST_BUFFER_ACCESS_2 for uniformBuffers, and the robustBufferAccess feature is not enabled, that stage must not access values outside of the range of the buffer as specified in the descriptor set bound to the same pipeline bind point
• If the robustBufferAccess feature is not enabled, and any ShaderEXT bound to a stage corresponding to the pipeline bind point used by this command accesses a uniform buffer, it must not access values outside of the range of the buffer as specified in the descriptor set bound to the same pipeline bind point
• If any stage of the Pipeline object bound to the pipeline bind point used by this command accesses a storage buffer, and that stage was created without enabling either PIPELINE_ROBUSTNESS_BUFFER_BEHAVIOR_ROBUST_BUFFER_ACCESS or PIPELINE_ROBUSTNESS_BUFFER_BEHAVIOR_ROBUST_BUFFER_ACCESS_2 for storageBuffers, and the robustBufferAccess feature is not enabled, that stage must not access values outside of the range of the buffer as specified in the descriptor set bound to the same pipeline bind point
• If the robustBufferAccess feature is not enabled, and any ShaderEXT bound to a stage corresponding to the pipeline bind point used by this command accesses a storage buffer, it must not access values outside of the range of the buffer as specified in the descriptor set bound to the same pipeline bind point
• If commandBuffer is an unprotected command buffer and protectedNoFault is not supported, any resource accessed by bound shaders must not be a protected resource
• If a ImageView is accessed as a result of this command, then the image view’s viewType must match the Dim operand of the OpTypeImage as described in ???
• If a ImageView or BufferView is accessed as a result of this command, then the numeric type of the view’s format and the Sampled Type operand of the OpTypeImage must match
• If a ImageView created with a format other than FORMAT_A8_UNORM is accessed using OpImageWrite as a result of this command, then the Type of the Texel operand of that instruction must have at least as many components as the image view’s format
• If a ImageView created with the format FORMAT_A8_UNORM is accessed using OpImageWrite as a result of this command, then the Type of the Texel operand of that instruction must have four components
• If a BufferView is accessed using OpImageWrite as a result of this command, then the Type of the Texel operand of that instruction must have at least as many components as the buffer view’s format
• If a ImageView with a Format that has a 64-bit component width is accessed as a result of this command, the SampledType of the OpTypeImage operand of that instruction must have a Width of 64
• If a ImageView with a Format that has a component width less than 64-bit is accessed as a result of this command, the SampledType of the OpTypeImage operand of that instruction must have a Width of 32
• If a BufferView with a Format that has a 64-bit component width is accessed as a result of this command, the SampledType of the OpTypeImage operand of that instruction must have a Width of 64
• If a BufferView with a Format that has a component width less than 64-bit is accessed as a result of this command, the SampledType of the OpTypeImage operand of that instruction must have a Width of 32
• If the sparseImageInt64Atomics feature is not enabled, Image objects created with the IMAGE_CREATE_SPARSE_RESIDENCY_BIT flag must not be accessed by atomic instructions through an OpTypeImage with a SampledType with a Width of 64 by this command
• If the sparseImageInt64Atomics feature is not enabled, Buffer objects created with the BUFFER_CREATE_SPARSE_RESIDENCY_BIT flag must not be accessed by atomic instructions through an OpTypeImage with a SampledType with a Width of 64 by this command
• If OpImageSampleWeightedQCOM is used to sample a ImageView as a result of this command, then the image view’s format features must contain FORMAT_FEATURE_2_WEIGHT_SAMPLED_IMAGE_BIT_QCOM
• If OpImageSampleWeightedQCOM uses a ImageView as a sample weight image as a result of this command, then the image view’s format features must contain FORMAT_FEATURE_2_WEIGHT_IMAGE_BIT_QCOM
• If OpImageBoxFilterQCOM is used to sample a ImageView as a result of this command, then the image view’s format features must contain FORMAT_FEATURE_2_BOX_FILTER_SAMPLED_BIT_QCOM
• If OpImageBlockMatchSSDQCOM is used to read from an ImageView as a result of this command, then the image view’s format features must contain FORMAT_FEATURE_2_BLOCK_MATCHING_BIT_QCOM
• If OpImageBlockMatchSADQCOM is used to read from an ImageView as a result of this command, then the image view’s format features must contain FORMAT_FEATURE_2_BLOCK_MATCHING_BIT_QCOM
• If OpImageBlockMatchSADQCOM or OpImageBlockMatchSSDQCOM is used to read from a reference image as result of this command, then the specified reference coordinates must not fail integer texel coordinate validation
• If OpImageSampleWeightedQCOM, OpImageBoxFilterQCOM, OpImageBlockMatchWindowSSDQCOM, OpImageBlockMatchWindowSADQCOM, OpImageBlockMatchGatherSSDQCOM, OpImageBlockMatchGatherSADQCOM, OpImageBlockMatchSSDQCOM, or OpImageBlockMatchSADQCOM uses a Sampler as a result of this command, then the sampler must have been created with SAMPLER_CREATE_IMAGE_PROCESSING_BIT_QCOM
• If any command other than OpImageSampleWeightedQCOM, OpImageBoxFilterQCOM, OpImageBlockMatchWindowSSDQCOM, OpImageBlockMatchWindowSADQCOM, OpImageBlockMatchGatherSSDQCOM, OpImageBlockMatchGatherSADQCOM, OpImageBlockMatchSSDQCOM, or OpImageBlockMatchSADQCOM uses a Sampler as a result of this command, then the sampler must not have been created with SAMPLER_CREATE_IMAGE_PROCESSING_BIT_QCOM
• If a OpImageBlockMatchWindow*QCOM or OpImageBlockMatchGather*QCOM instruction is used to read from an ImageView as a result of this command, then the image view’s format features must contain FORMAT_FEATURE_2_BLOCK_MATCHING_BIT_QCOM
• If a OpImageBlockMatchWindow*QCOM or OpImageBlockMatchGather*QCOM instruction is used to read from an ImageView as a result of this command, then the image view’s format must be a single-component format
• If a OpImageBlockMatchWindow*QCOM or OpImageBlockMatchGather*QCOM read from a reference image as result of this command, then the specified reference coordinates must not fail integer texel coordinate validation
• Any shader invocation executed by this command must terminate
• If a descriptor with type equal to any of DESCRIPTOR_TYPE_SAMPLE_WEIGHT_IMAGE_QCOM, DESCRIPTOR_TYPE_BLOCK_MATCH_IMAGE_QCOM, DESCRIPTOR_TYPE_SAMPLED_IMAGE, DESCRIPTOR_TYPE_STORAGE_IMAGE, or DESCRIPTOR_TYPE_INPUT_ATTACHMENT is accessed as a result of this command, all image subresources identified by that descriptor must be in the image layout identified when the descriptor was written
• The DeviceMemory object allocated from a MemoryHeap with the MEMORY_HEAP_TILE_MEMORY_BIT_QCOM property that is bound to a resource accessed as a result of this command must be the active bound bound tile memory object in commandBuffer
• If this command is recorded inside a tile shading render pass instance, the stages corresponding to the pipeline bind point used by this command must only include SHADER_STAGE_VERTEX_BIT, SHADER_STAGE_FRAGMENT_BIT, and/or SHADER_STAGE_COMPUTE_BIT
• If this command is recorded where per-tile execution model is enabled, there must be no access to any image while the image was be transitioned to the IMAGE_LAYOUT_ATTACHMENT_FEEDBACK_LOOP_OPTIMAL_EXT layout
• If a DESCRIPTOR_TYPE_TENSOR_ARM descriptor is accessed as a result of this command, then the underlying TensorARM object must have been created with the TENSOR_USAGE_SHADER_BIT_ARM usage flag set
• If a DESCRIPTOR_TYPE_TENSOR_ARM descriptor is accessed as a result of this command, then the Rank of the OpTypeTensorARM of the tensor resource variable must be equal to the dimensionCount provided via TensorCreateInfoARM::pDescription when creating the underlying TensorARM object
• If a DESCRIPTOR_TYPE_TENSOR_ARM descriptor is accessed as a result of this command, then the element type of the OpTypeTensorARM of the tensor resource variable must be compatible with the Format of the TensorViewARM used for the access
• If a pipeline is bound to the pipeline bind point used by this command, or shader is bound to a shader stage used by this command, and it was created with a descriptor mapping using DESCRIPTOR_MAPPING_SOURCE_HEAP_WITH_PUSH_INDEX_EXT, DESCRIPTOR_MAPPING_SOURCE_HEAP_WITH_SHADER_RECORD_INDEX_EXT, DESCRIPTOR_MAPPING_SOURCE_HEAP_WITH_INDIRECT_INDEX_ARRAY_EXT, or DESCRIPTOR_MAPPING_SOURCE_HEAP_WITH_INDIRECT_INDEX_EXT, and a shader accesses a OpTypeStruct decorated with Block or BufferBlock using that mapping, the calculated offset for the resource heap must be a multiple of bufferDescriptorAlignment
• If a pipeline is bound to the pipeline bind point used by this command, or shader is bound to a shader stage used by this command, and it was created with a descriptor mapping using DESCRIPTOR_MAPPING_SOURCE_HEAP_WITH_PUSH_INDEX_EXT, DESCRIPTOR_MAPPING_SOURCE_HEAP_WITH_SHADER_RECORD_INDEX_EXT, DESCRIPTOR_MAPPING_SOURCE_HEAP_WITH_INDIRECT_INDEX_ARRAY_EXT, or DESCRIPTOR_MAPPING_SOURCE_HEAP_WITH_INDIRECT_INDEX_EXT, and a shader accesses an OpTypeImage or OpTypeSampledImage using that mapping, the calculated offset for the resource heap must be a multiple of imageDescriptorAlignment
• If a pipeline is bound to the pipeline bind point used by this command, or shader is bound to a shader stage used by this command, and it was created with a descriptor mapping using DESCRIPTOR_MAPPING_SOURCE_HEAP_WITH_PUSH_INDEX_EXT, DESCRIPTOR_MAPPING_SOURCE_HEAP_WITH_SHADER_RECORD_INDEX_EXT, DESCRIPTOR_MAPPING_SOURCE_HEAP_WITH_INDIRECT_INDEX_ARRAY_EXT, or DESCRIPTOR_MAPPING_SOURCE_HEAP_WITH_INDIRECT_INDEX_EXT, and a shader accesses an OpTypeSampler or OpTypeSampledImage using that mapping, the calculated offset for the sampler heap must be a multiple of samplerDescriptorAlignment
• If a pipeline is bound to the pipeline bind point used by this command, or shader is bound to a shader stage used by this command, and it was created with a descriptor mapping using DESCRIPTOR_MAPPING_SOURCE_HEAP_WITH_PUSH_INDEX_EXT, DESCRIPTOR_MAPPING_SOURCE_HEAP_WITH_SHADER_RECORD_INDEX_EXT, DESCRIPTOR_MAPPING_SOURCE_HEAP_WITH_INDIRECT_INDEX_ARRAY_EXT, or DESCRIPTOR_MAPPING_SOURCE_HEAP_WITH_INDIRECT_INDEX_EXT, and a shader accesses an OpTypeTensorARM using that mapping, the calculated offset for the resource heap must be a multiple of tensorDescriptorAlignment
• If a pipeline is bound to the pipeline bind point used by this command, or shader is bound to a shader stage used by this command, and it was created with a descriptor mapping using DESCRIPTOR_MAPPING_SOURCE_HEAP_WITH_INDIRECT_INDEX_ARRAY_EXT or DESCRIPTOR_MAPPING_SOURCE_HEAP_WITH_INDIRECT_INDEX_EXT, and a shader accesses a resource using that mapping, the value of the address at the expected location in push data must be a multiple of 4
• If a pipeline is bound to the pipeline bind point used by this command, or shader is bound to a shader stage used by this command, and it was created with a descriptor mapping using DESCRIPTOR_MAPPING_SOURCE_HEAP_WITH_INDIRECT_INDEX_ARRAY_EXT or DESCRIPTOR_MAPPING_SOURCE_HEAP_WITH_INDIRECT_INDEX_EXT, and a shader accesses a resource using that mapping, the value of the address at the expected location in push data must be a valid DeviceAddress backed by physical memory at every offset specified by each mapping
• If a pipeline is bound to the pipeline bind point used by this command, or shader is bound to a shader stage used by this command, and it was created with a descriptor mapping using DESCRIPTOR_MAPPING_SOURCE_PUSH_ADDRESS_EXT, and a shader accesses a resource using that mapping, the value of the address at the expected location in push data must be a valid DeviceAddress
• If a pipeline is bound to the pipeline bind point used by this command, or shader is bound to a shader stage used by this command, and it was created with a descriptor mapping using DESCRIPTOR_MAPPING_SOURCE_INDIRECT_ADDRESS_EXT, and a shader accesses a resource using that mapping, the value of the address at the expected location in push data must be a multiple of 8
• If a pipeline is bound to the pipeline bind point used by this command, or shader is bound to a shader stage used by this command, and it was created with a descriptor mapping using DESCRIPTOR_MAPPING_SOURCE_INDIRECT_ADDRESS_EXT, and a shader accesses a resource using that mapping, the value of the address at the expected location in push data must be a valid DeviceAddress backed by physical memory at every offset specified by each mapping
• If a pipeline is bound to the pipeline bind point used by this command, or shader is bound to a shader stage used by this command, and it was created with a descriptor mapping using DESCRIPTOR_MAPPING_SOURCE_INDIRECT_ADDRESS_EXT, and a shader accesses a resource using that mapping, the value of the address pointed to by the address in push data must be a valid DeviceAddress
• For each descriptor heap that is statically used by a bound shader, either directly or via a descriptor mapping, a valid descriptor heap must be bound
• If a bound shader was created as a ShaderEXT with the SHADER_CREATE_DESCRIPTOR_HEAP_BIT_EXT flag or as part of a pipeline with the PIPELINE_CREATE_2_DESCRIPTOR_HEAP_BIT_EXT flag, execution of this command must not result in any descriptor read accessing data outside of the user range of the respective heap bound by vkCmdBind*HeapEXT commands
• If any stage of the Pipeline object bound to the pipeline bind point used by this command accesses a uniform buffer or uniform texel buffer through a descriptor in the bound resource heap, that stage was created without enabling either PIPELINE_ROBUSTNESS_BUFFER_BEHAVIOR_ROBUST_BUFFER_ACCESS or PIPELINE_ROBUSTNESS_BUFFER_BEHAVIOR_ROBUST_BUFFER_ACCESS_2 for uniformBuffers, the robustBufferAccess2 feature is not enabled, and the robustBufferAccess feature is not enabled, that stage must not access values outside of the range of the descriptor specified via DeviceAddressRangeEXT when the descriptor was written
• If any stage of the Pipeline object bound to the pipeline bind point used by this command accesses a storage buffer or storage texel buffer through a descriptor in the bound resource heap, that stage was created without enabling either PIPELINE_ROBUSTNESS_BUFFER_BEHAVIOR_ROBUST_BUFFER_ACCESS or PIPELINE_ROBUSTNESS_BUFFER_BEHAVIOR_ROBUST_BUFFER_ACCESS_2 for storageBuffers, the robustBufferAccess2 feature is not enabled, and the robustBufferAccess feature is not enabled, that stage must not access values outside of the range of the descriptor specified by DeviceAddressRangeEXT when the descriptor was written
• If the robustBufferAccess2 feature is not enabled, the robustBufferAccess feature is not enabled, and any ShaderEXT bound to a stage corresponding to the pipeline bind point used by this command accesses a uniform buffer, uniform texel buffer, storage buffer, or storage texel buffer, that shader must not access values outside of the range of the buffer as specified by DeviceAddressRangeEXT when the descriptor was written
• If any bound shader uses an embedded sampler via a descriptor mapping, the value of pBindInfo->reservedRangeSize set for cmdBindSamplerHeapEXT must be greater than or equal to minSamplerHeapReservedRangeWithEmbedded
• If a bound shader was created as a ShaderEXT with the SHADER_CREATE_DESCRIPTOR_HEAP_BIT_EXT flag or as part of a pipeline with the PIPELINE_CREATE_2_DESCRIPTOR_HEAP_BIT_EXT flag, and that shader statically uses a push constant value, that value must have been set by cmdPushDataEXT
• If a bound shader was created with a descriptor mapping using DESCRIPTOR_MAPPING_SOURCE_PUSH_DATA_EXT, DESCRIPTOR_MAPPING_SOURCE_PUSH_ADDRESS_EXT, DESCRIPTOR_MAPPING_SOURCE_SHADER_RECORD_DATA_EXT, DESCRIPTOR_MAPPING_SOURCE_SHADER_RECORD_ADDRESS_EXT, DESCRIPTOR_MAPPING_SOURCE_RESOURCE_HEAP_DATA_EXT, or DESCRIPTOR_MAPPING_SOURCE_INDIRECT_ADDRESS_EXT, and a shader accesses a resource using that mapping, the access must not be out of bounds
• If a pipeline is bound to the pipeline bind point used by this command, or shader is bound to a shader stage used by this command, and it was created with a descriptor mapping using DESCRIPTOR_MAPPING_SOURCE_HEAP_WITH_INDIRECT_INDEX_ARRAY_EXT, DESCRIPTOR_MAPPING_SOURCE_HEAP_WITH_INDIRECT_INDEX_EXT, or DESCRIPTOR_MAPPING_SOURCE_INDIRECT_ADDRESS_EXT, and a shader accesses a resource using that mapping, the buffer from which the address in push data was queried must have been created with the BUFFER_USAGE_UNIFORM_BUFFER_BIT usage flag set
• If a pipeline is bound to the pipeline bind point used by this command, or shader is bound to a shader stage used by this command, and it was created with a descriptor mapping using DESCRIPTOR_MAPPING_SOURCE_PUSH_ADDRESS_EXT, DESCRIPTOR_MAPPING_SOURCE_SHADER_RECORD_ADDRESS_EXT, or DESCRIPTOR_MAPPING_SOURCE_INDIRECT_ADDRESS_EXT, and a shader accesses a uniform buffer using that mapping, the address that the uniform buffer is mapped to must have been queried from a buffer created with the BUFFER_USAGE_UNIFORM_BUFFER_BIT usage flag set
• If a pipeline is bound to the pipeline bind point used by this command, or shader is bound to a shader stage used by this command, and it was created with a descriptor mapping using DESCRIPTOR_MAPPING_SOURCE_PUSH_ADDRESS_EXT, DESCRIPTOR_MAPPING_SOURCE_SHADER_RECORD_ADDRESS_EXT, or DESCRIPTOR_MAPPING_SOURCE_INDIRECT_ADDRESS_EXT, and a shader accesses a uniform buffer using that mapping, the address that the uniform buffer is mapped to must be aligned to minUniformBufferOffsetAlignment
• If a pipeline is bound to the pipeline bind point used by this command, or shader is bound to a shader stage used by this command, and it was created with a descriptor mapping using DESCRIPTOR_MAPPING_SOURCE_PUSH_ADDRESS_EXT, DESCRIPTOR_MAPPING_SOURCE_SHADER_RECORD_ADDRESS_EXT, or DESCRIPTOR_MAPPING_SOURCE_INDIRECT_ADDRESS_EXT, and a shader accesses a storage buffer using that mapping, the address that the storage buffer is mapped to must have been queried from a buffer created with the BUFFER_USAGE_STORAGE_BUFFER_BIT usage flag set
• If a pipeline is bound to the pipeline bind point used by this command, or shader is bound to a shader stage used by this command, and it was created with a descriptor mapping using DESCRIPTOR_MAPPING_SOURCE_PUSH_ADDRESS_EXT, DESCRIPTOR_MAPPING_SOURCE_SHADER_RECORD_ADDRESS_EXT, or DESCRIPTOR_MAPPING_SOURCE_INDIRECT_ADDRESS_EXT, and a shader accesses a storage buffer using that mapping, the address that the storage buffer is mapped to must be aligned to minStorageBufferOffsetAlignment
• If a pipeline is bound to the pipeline bind point used by this command, or shader is bound to a shader stage used by this command, and it was created with a descriptor mapping using DESCRIPTOR_MAPPING_SOURCE_PUSH_ADDRESS_EXT, DESCRIPTOR_MAPPING_SOURCE_SHADER_RECORD_ADDRESS_EXT, or DESCRIPTOR_MAPPING_SOURCE_INDIRECT_ADDRESS_EXT, and a shader accesses an acceleration structure using that mapping, the address that the acceleration structure is mapped to must be an acceleration structure address retrieved from a AccelerationStructureKHR object via getAccelerationStructureDeviceAddressKHR or handle retrieved from a AccelerationStructureNV object via getAccelerationStructureHandleNV
• If a shader uses a sampler descriptor to sample an image as a result of this command, and that sampler descriptor uses a custom border color with an index defined by SamplerCustomBorderColorIndexCreateInfoEXT, the value of SamplerCustomBorderColorIndexCreateInfoEXT::index must have been registered before this command was recorded, and still be registered during the sampling operation, with an identically defined color
• If protectedNoFault is not supported, a pipeline is bound to the pipeline bind point used by this command, or a shader is bound to a shader stage used by this command, and it was created with a descriptor mapping using DESCRIPTOR_MAPPING_SOURCE_PUSH_ADDRESS_EXT, DESCRIPTOR_MAPPING_SOURCE_SHADER_RECORD_ADDRESS_EXT, or DESCRIPTOR_MAPPING_SOURCE_INDIRECT_ADDRESS_EXT, the address that the resource is mapped to must have been queried from a buffer created without the BUFFER_CREATE_PROTECTED_BIT create flag set
• If protectedNoFault is not supported, a pipeline is bound to the pipeline bind point used by this command, or a shader is bound to a shader stage used by this command, and it was created with a descriptor mapping using DESCRIPTOR_MAPPING_SOURCE_HEAP_WITH_INDIRECT_INDEX_EXT or DESCRIPTOR_MAPPING_SOURCE_HEAP_WITH_INDIRECT_INDEX_ARRAY_EXT, the address of the indirect memory must have been queried from a buffer created without the BUFFER_CREATE_PROTECTED_BIT create flag set
• If the per-tile execution model is not enabled, this command must be called outside of a render pass instance
• If this command is recorded where per-tile execution model is enabled, and if the Pipeline object bound to the pipeline bind point used by this command writes to a variable of storage class Storage Class TileAttachmentQCOM, the corresponding ImageView using must not have been created with an aspectMask that contains IMAGE_ASPECT_DEPTH_BIT or IMAGE_ASPECT_STENCIL_BIT
• If the per-tile execution model is enabled, the tileShadingPerTileDispatch feature must be enabled
• Memory backing image subresources used as tile attachments in the current render pass must not be written in any way other than as a tile attachment by this command
• If any recorded command in the current subpass will write to an image subresource as a tile attachment, this command must not read from the memory backing that image subresource in any other way than as a tile attachment
• If there is no bound compute pipeline, a valid ShaderEXT must be bound to the SHADER_STAGE_COMPUTE_BIT stage
• If commandBuffer is a protected command buffer and protectedNoFault is not supported, any resource written to by the Pipeline object bound to the pipeline bind point used by this command must not be an unprotected resource
• If commandBuffer is a protected command buffer and protectedNoFault is not supported, pipeline stages other than the framebuffer-space and compute stages in the Pipeline object bound to the pipeline bind point used by this command must not write to any resource
• If any of the shader stages of the Pipeline bound to the pipeline bind point used by this command uses the RayQueryKHR capability, then commandBuffer must not be a protected command buffer
• When this command is recorded per-tile execution model must be enabled
• The tileShadingDispatchTile must enabled

Valid Usage (Implicit)

• commandBuffer must be a valid CommandBuffer handle

• pDispatchTileInfo must be a valid pointer to a valid DispatchTileInfoQCOM structure
• commandBuffer must be in the recording state
• The CommandPool that commandBuffer was allocated from must support QUEUE_COMPUTE_BIT operations
• This command must only be called inside of a render pass instance
• This command must not be called between suspended render pass instances
• This command must only be called outside of a video coding scope

Host Synchronization

• Host access to the CommandPool that commandBuffer was allocated from must be externally synchronized

Command Properties

'

Conditional Rendering

vkCmdDispatchTileQCOM is affected by conditional rendering

See Also

VK_QCOM_tile_shading, CommandBuffer, DispatchTileInfoQCOM

vkCmdBeginPerTileExecutionQCOM - Begin per-tile execution mode

Description

When per-tile execution model is enabled, recorded vkCmdDraw* or vkCmdDispatch* commands are invoked per tile. That is, the recorded draw or dispatch is invoked exactly once for each covered tile. The set of covered tiles for a given render pass instance consists of the set of render pass tiles, which can be queried with VK_QCOM_tile_properties, that are completely or partially covered by the renderArea for the render pass instance. The draw or dispatch commands may be invoked for uncovered tiles.

Each per-tile command invocation is associated with a single tile, the active tile. These per-tile invocations are not specified to execute in any particular order, but the size and offset of the active tile is available via shader built-ins.

When per-tile execution model is enabled, the following restrictions apply:

• Transform feedback commands such as cmdBeginTransformFeedbackEXT, cmdEndTransformFeedbackEXT, cmdBeginQueryIndexedEXT, and cmdEndQueryIndexedEXT, must not be recorded.
• Query commands such as cmdWriteTimestamp, cmdDebugMarkerBeginEXT, cmdDebugMarkerEndEXT, cmdDebugMarkerInsertEXT, cmdBeginQuery, and cmdEndQuery, must not be recorded.
• Event commands such as cmdWaitEvents2 and cmdWaitEvents must not be recorded.
• Render pass clears like cmdClearAttachments must not be recorded
• Access of an attachment with layout IMAGE_LAYOUT_ATTACHMENT_FEEDBACK_LOOP_OPTIMAL_EXT as provided by VK_EXT_attachment_feedback_loop_layout is disallowed

• Any commands that would cause a invocations of one of the following shader stages are not allowed

  • tessellation
  • geometry
  • ray tracing
  • mesh shading

Valid Usage

• The current render pass must be a tile shading render pass

• The tileShadingPerTileDispatch or tileShadingPerTileDraw feature must be enabled

Valid Usage (Implicit)

• commandBuffer must be a valid CommandBuffer handle

• pPerTileBeginInfo must be a valid pointer to a valid PerTileBeginInfoQCOM structure
• commandBuffer must be in the recording state
• The CommandPool that commandBuffer was allocated from must support QUEUE_COMPUTE_BIT, or QUEUE_GRAPHICS_BIT operations
• This command must only be called inside of a render pass instance
• This command must only be called outside of a video coding scope

Host Synchronization

• Host access to the CommandPool that commandBuffer was allocated from must be externally synchronized

Command Properties

'

Conditional Rendering

vkCmdBeginPerTileExecutionQCOM is not affected by conditional rendering

See Also

VK_QCOM_tile_shading, CommandBuffer, PerTileBeginInfoQCOM

vkCmdEndPerTileExecutionQCOM - End per-tile execution mode

Description

This command disables per-tile execution model.

Valid Usage

• The /per-tile execution model must/ have been enabled in the current render pass

• The current render pass must be a tile shading render pass

Valid Usage (Implicit)

• commandBuffer must be a valid CommandBuffer handle

• pPerTileEndInfo must be a valid pointer to a valid PerTileEndInfoQCOM structure
• commandBuffer must be in the recording state
• The CommandPool that commandBuffer was allocated from must support QUEUE_COMPUTE_BIT, or QUEUE_GRAPHICS_BIT operations
• This command must only be called inside of a render pass instance
• This command must only be called outside of a video coding scope

Host Synchronization

• Host access to the CommandPool that commandBuffer was allocated from must be externally synchronized

Command Properties

'

Conditional Rendering

vkCmdEndPerTileExecutionQCOM is not affected by conditional rendering

See Also

VK_QCOM_tile_shading, CommandBuffer, PerTileEndInfoQCOM

VkPhysicalDeviceTileShadingFeaturesQCOM - Structure describing tile shading features that can be supported by an implementation

Members

This structure describes the following features:

Description

If the PhysicalDeviceTileShadingFeaturesQCOM structure is included in the pNext chain of the PhysicalDeviceFeatures2 structure passed to getPhysicalDeviceFeatures2, it is filled in to indicate whether each corresponding feature is supported. If the application wishes to use a Device with any features described by PhysicalDeviceTileShadingFeaturesQCOM, it must add an instance of the structure, with the desired feature members set to TRUE, to the pNext chain of DeviceCreateInfo when creating the Device.

Valid Usage (Implicit)

See Also

VK_QCOM_tile_shading, Bool32, StructureType

VkPhysicalDeviceTileShadingPropertiesQCOM - Structure describing properties supported by VK_QCOM_tile_shading

Description

If the PhysicalDeviceTileShadingPropertiesQCOM structure is included in the pNext chain of the PhysicalDeviceProperties2 structure passed to getPhysicalDeviceProperties2, it is filled in with each corresponding implementation-dependent property.

Valid Usage (Implicit)

See Also

VK_QCOM_tile_shading, Bool32, Extent2D, StructureType

VkRenderPassTileShadingCreateInfoQCOM - Structure specifying, tile shading information for a render pass object.

Description

If this structure is not present, the render pass will have flags set to 0 and tileApronSize is set to (0,0).

Valid Usage

• If the tileShading feature is not enabled, TILE_SHADING_RENDER_PASS_ENABLE_BIT_QCOM must not be included in flags

• If TILE_SHADING_RENDER_PASS_ENABLE_BIT_QCOM is not included in flags or the tileShadingApron feature is not enabled, tileApronSize must be (0,0)
• If TILE_SHADING_RENDER_PASS_ENABLE_BIT_QCOM is not included in flags, or neither the tileShadingPerTileDispatch and tileShadingPerTileDraw features are enabled, flags must not include TILE_SHADING_RENDER_PASS_PER_TILE_EXECUTION_BIT_QCOM
• If the tileShadingAnisotropicApron feature is not enabled, tileApronSize.x and must be equal to tileApronSize.y
• tileApronSize.x must be less than or equal to maxApronSize
• tileApronSize.y must be less than or equal to maxApronSize

Valid Usage (Implicit)

• sType must be STRUCTURE_TYPE_RENDER_PASS_TILE_SHADING_CREATE_INFO_QCOM

• flags must be a valid combination of TileShadingRenderPassFlagBitsQCOM values

See Also

VK_QCOM_tile_shading, Extent2D, StructureType, TileShadingRenderPassFlagsQCOM

VkPerTileBeginInfoQCOM - Structure specifying per-tile begin information

Valid Usage (Implicit)

See Also

VK_QCOM_tile_shading, StructureType, cmdBeginPerTileExecutionQCOM

VkPerTileEndInfoQCOM - Structure specifying per-tile end information

Valid Usage (Implicit)

See Also

VK_QCOM_tile_shading, StructureType, cmdEndPerTileExecutionQCOM

VkDispatchTileInfoQCOM - Structure specifying dispatch tile info

Valid Usage (Implicit)

See Also

VK_QCOM_tile_shading, StructureType, cmdDispatchTileQCOM

VkTileShadingRenderPassFlagBitsQCOM - Bitmask specifying flags for tile shading

Description

• TILE_SHADING_RENDER_PASS_ENABLE_BIT_QCOM specifies that the render pass has tile shading enabled.

• TILE_SHADING_RENDER_PASS_PER_TILE_EXECUTION_BIT_QCOM specifies that the secondary command buffer will be executed within a per-tile execution block.

See Also

VK_QCOM_tile_shading, TileShadingRenderPassFlagsQCOM