derek.holloway
7502bf64a4
CodeQL / Analyze (actions) (push) Canceled after 0s
CodeQL / Analyze (python) (push) Canceled after 0s
pre-commit / pre-commit (push) Canceled after 0s
Multi-Arch CI / setup (push) Canceled after 0s
Publish build_manylinux_x86_64 images / publish_build_manylinux_x86_64 (push) Canceled after 0s
Setup (Multi-Arch) / setup (push) Canceled after 0s
Multi-Arch CI / Linux::${{ fromJSON(needs.setup.outputs.linux_build_config || '{}').build_variant_label || 'skip' }} (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish no_rocm_image_ubi10 image / publish_no_rocm_image_ubi10 (push) Canceled after 0s
Multi-Arch CI / Windows::${{ fromJSON(needs.setup.outputs.windows_build_config || '{}').build_variant_label || 'skip' }} (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Multi-Arch CI / Manifest Diff (push) Canceled after 0s
TheRock Manifest Diff Report / Generate Manifest Diff Report (push) Canceled after 0s
Multi-Arch CI / CI Summary (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04 (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04_ocl_rt images / publish_no_rocm_image_ubuntu24_04_ocl_rt (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_rocgdb (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04_rocgdb images / publish_no_rocm_image_ubuntu24_04_rocgdb (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_ocl_rt (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Unit Tests / Unit Tests :: ubuntu-24.04 (push) Canceled after 0s
Unit Tests / Unit Tests :: windows-2022 (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_media (push) Canceled after 0s
Unit Tests / Unit Tests Summary (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_openmpi (push) Canceled after 0s
459 lines
13 KiB
YAML
459 lines
13 KiB
YAML
TestParameters:
|
|
marks: [skip-gfx1100, skip-gfx1101, skip-gfx1102, skip-gfx1200, skip-gfx1201, skip-gfx1250] # not supported yet
|
|
|
|
GlobalParameters:
|
|
SyncsPerBenchmark: 0
|
|
MinimumRequiredVersion: 5.0.0
|
|
PrintLevel: 1
|
|
PrintSolutionRejectionReason: True
|
|
Device: 0
|
|
CMakeBuildType: Release
|
|
KernelTime: True
|
|
MaxWorkspaceSize: 13421772800
|
|
DataInitTypeAlpha: 1
|
|
DataInitTypeBeta: 0
|
|
# DataInitTypeA: 1
|
|
# DataInitTypeB: 1
|
|
UseUserArgs: False
|
|
NumElementsToValidate: 128
|
|
BoundsCheck: 2
|
|
|
|
BenchmarkProblems:
|
|
#########################################
|
|
# SHHS
|
|
#########################################
|
|
-
|
|
- # ProblemType
|
|
OperationType: GEMM
|
|
DataType: h
|
|
DataTypeA: s
|
|
DestDataType: h
|
|
ComputeDataType: s
|
|
HighPrecisionAccumulate: True
|
|
TransposeA: False
|
|
TransposeB: False
|
|
UseBeta: True
|
|
Batched: True
|
|
UseBias: 1
|
|
- # BenchmarkProblemSizeGroup - Standard
|
|
InitialSolutionParameters:
|
|
BenchmarkCommonParameters:
|
|
- KernelLanguage: ["Assembly"]
|
|
ForkParameters:
|
|
- MatrixInstruction:
|
|
- [32, 32, 8, 1, 1, 1, 1, 2,2 ]
|
|
- AssertFree0ElementMultiple: [1]
|
|
- PrefetchGlobalRead: [2]
|
|
- PrefetchLocalRead: [1]
|
|
- ClusterLocalRead: [1]
|
|
- DepthU: [32]
|
|
- VectorWidthA: [1]
|
|
- VectorWidthB: [1]
|
|
- ScheduleIterAlg: [3]
|
|
- InnerUnroll: [1]
|
|
- ExpandPointerSwap: [false]
|
|
- TransposeLDS: [0]
|
|
- LdsBlockSizePerPadA: [0]
|
|
- LdsBlockSizePerPadB: [0]
|
|
- LdsPadA: [0]
|
|
- LdsPadB: [0]
|
|
- WaveSeparateGlobalReadB: [1]
|
|
- 1LDSBuffer: [-1]
|
|
- GlobalSplitU: [1]
|
|
- GlobalSplitUAlgorithm: ["MultipleBuffer"]
|
|
- GlobalReadPerMfma: [1.0]
|
|
- LocalWritePerMfma: [-1]
|
|
- StoreVectorWidth: [-1]
|
|
- SourceSwap: [true]
|
|
- NumElementsPerBatchStore: [2]
|
|
- StorePriorityOpt: [true]
|
|
BenchmarkJoinParameters:
|
|
BenchmarkFinalParameters:
|
|
- ProblemSizes:
|
|
- Exact: [128, 128, 1, 128]
|
|
# - Exact: []
|
|
- BiasTypeArgs: ['s']
|
|
- ActivationArgs:
|
|
- [Enum: none]
|
|
|
|
-
|
|
- # ProblemType
|
|
OperationType: GEMM
|
|
DataType: h
|
|
DataTypeA: s
|
|
DestDataType: h
|
|
ComputeDataType: s
|
|
HighPrecisionAccumulate: True
|
|
TransposeA: True
|
|
TransposeB: False
|
|
UseBeta: True
|
|
Batched: True
|
|
UseBias: 1
|
|
- # BenchmarkProblemSizeGroup - Standard
|
|
InitialSolutionParameters:
|
|
BenchmarkCommonParameters:
|
|
- KernelLanguage: ["Assembly"]
|
|
ForkParameters:
|
|
- MatrixInstruction:
|
|
- [32, 32, 8, 1, 1, 1, 1, 2,2 ]
|
|
- AssertFree0ElementMultiple: [1]
|
|
- PrefetchGlobalRead: [2]
|
|
- PrefetchLocalRead: [1]
|
|
- ClusterLocalRead: [1]
|
|
- DepthU: [32]
|
|
- VectorWidthA: [1]
|
|
- VectorWidthB: [1]
|
|
- ScheduleIterAlg: [3]
|
|
- InnerUnroll: [1]
|
|
- ExpandPointerSwap: [false]
|
|
- TransposeLDS: [0]
|
|
- LdsBlockSizePerPadA: [0]
|
|
- LdsBlockSizePerPadB: [0]
|
|
- LdsPadA: [0]
|
|
- LdsPadB: [0]
|
|
- WaveSeparateGlobalReadB: [1]
|
|
- 1LDSBuffer: [-1]
|
|
- GlobalSplitU: [1]
|
|
- GlobalSplitUAlgorithm: ["MultipleBuffer"]
|
|
- GlobalReadPerMfma: [1.0]
|
|
- LocalWritePerMfma: [-1]
|
|
- StoreVectorWidth: [-1]
|
|
- SourceSwap: [true]
|
|
- NumElementsPerBatchStore: [2]
|
|
- StorePriorityOpt: [true]
|
|
BenchmarkJoinParameters:
|
|
BenchmarkFinalParameters:
|
|
- ProblemSizes:
|
|
- Exact: [128, 128, 1, 128]
|
|
# - Exact: []
|
|
- BiasTypeArgs: ['s']
|
|
- ActivationArgs:
|
|
- [Enum: none]
|
|
|
|
-
|
|
- # ProblemType
|
|
OperationType: GEMM
|
|
DataType: h
|
|
DataTypeA: s
|
|
DestDataType: h
|
|
ComputeDataType: s
|
|
HighPrecisionAccumulate: True
|
|
TransposeA: False
|
|
TransposeB: True
|
|
UseBeta: True
|
|
Batched: True
|
|
UseBias: 1
|
|
- # BenchmarkProblemSizeGroup - Standard
|
|
InitialSolutionParameters:
|
|
BenchmarkCommonParameters:
|
|
- KernelLanguage: ["Assembly"]
|
|
ForkParameters:
|
|
- MatrixInstruction:
|
|
- [32, 32, 8, 1, 1, 1, 1, 2,2 ]
|
|
- AssertFree0ElementMultiple: [1]
|
|
- PrefetchGlobalRead: [2]
|
|
- PrefetchLocalRead: [1]
|
|
- ClusterLocalRead: [1]
|
|
- DepthU: [32]
|
|
- VectorWidthA: [1]
|
|
- VectorWidthB: [1]
|
|
- ScheduleIterAlg: [3]
|
|
- InnerUnroll: [1]
|
|
- ExpandPointerSwap: [false]
|
|
- TransposeLDS: [0]
|
|
- LdsBlockSizePerPadA: [0]
|
|
- LdsBlockSizePerPadB: [0]
|
|
- LdsPadA: [0]
|
|
- LdsPadB: [0]
|
|
- WaveSeparateGlobalReadB: [1]
|
|
- 1LDSBuffer: [-1]
|
|
- GlobalSplitU: [1]
|
|
- GlobalSplitUAlgorithm: ["MultipleBuffer"]
|
|
- GlobalReadPerMfma: [1.0]
|
|
- LocalWritePerMfma: [-1]
|
|
- StoreVectorWidth: [-1]
|
|
- SourceSwap: [true]
|
|
- NumElementsPerBatchStore: [2]
|
|
- StorePriorityOpt: [true]
|
|
BenchmarkJoinParameters:
|
|
BenchmarkFinalParameters:
|
|
- ProblemSizes:
|
|
- Exact: [128, 128, 1, 128]
|
|
# - Exact: []
|
|
- BiasTypeArgs: ['s']
|
|
- ActivationArgs:
|
|
- [Enum: none]
|
|
|
|
-
|
|
- # ProblemType
|
|
OperationType: GEMM
|
|
DataType: h
|
|
DataTypeA: s
|
|
DestDataType: h
|
|
ComputeDataType: s
|
|
HighPrecisionAccumulate: True
|
|
TransposeA: True
|
|
TransposeB: True
|
|
UseBeta: True
|
|
Batched: True
|
|
UseBias: 1
|
|
- # BenchmarkProblemSizeGroup - Standard
|
|
InitialSolutionParameters:
|
|
BenchmarkCommonParameters:
|
|
- KernelLanguage: ["Assembly"]
|
|
ForkParameters:
|
|
- MatrixInstruction:
|
|
- [32, 32, 8, 1, 1, 1, 1, 2,2 ]
|
|
- AssertFree0ElementMultiple: [1]
|
|
- PrefetchGlobalRead: [2]
|
|
- PrefetchLocalRead: [1]
|
|
- ClusterLocalRead: [1]
|
|
- DepthU: [32]
|
|
- VectorWidthA: [1]
|
|
- VectorWidthB: [1]
|
|
- ScheduleIterAlg: [3]
|
|
- InnerUnroll: [1]
|
|
- ExpandPointerSwap: [false]
|
|
- TransposeLDS: [0]
|
|
- LdsBlockSizePerPadA: [0]
|
|
- LdsBlockSizePerPadB: [0]
|
|
- LdsPadA: [0]
|
|
- LdsPadB: [0]
|
|
- WaveSeparateGlobalReadB: [1]
|
|
- 1LDSBuffer: [-1]
|
|
- GlobalSplitU: [1]
|
|
- GlobalSplitUAlgorithm: ["MultipleBuffer"]
|
|
- GlobalReadPerMfma: [1.0]
|
|
- LocalWritePerMfma: [-1]
|
|
- StoreVectorWidth: [-1]
|
|
- SourceSwap: [true]
|
|
- NumElementsPerBatchStore: [2]
|
|
- StorePriorityOpt: [true]
|
|
BenchmarkJoinParameters:
|
|
BenchmarkFinalParameters:
|
|
- ProblemSizes:
|
|
- Exact: [128, 128, 1, 128]
|
|
# - Exact: []
|
|
- BiasTypeArgs: ['s']
|
|
- ActivationArgs:
|
|
- [Enum: none]
|
|
|
|
#########################################
|
|
# HSHS
|
|
#########################################
|
|
-
|
|
- # ProblemType
|
|
OperationType: GEMM
|
|
DataType: h
|
|
DataTypeB: s
|
|
DestDataType: h
|
|
ComputeDataType: s
|
|
HighPrecisionAccumulate: True
|
|
TransposeA: False
|
|
TransposeB: False
|
|
UseBeta: True
|
|
Batched: True
|
|
UseBias: 1
|
|
- # BenchmarkProblemSizeGroup - Standard
|
|
InitialSolutionParameters:
|
|
BenchmarkCommonParameters:
|
|
- KernelLanguage: ["Assembly"]
|
|
ForkParameters:
|
|
- MatrixInstruction:
|
|
- [32, 32, 8, 1, 1, 1, 1, 2,2 ]
|
|
- AssertFree0ElementMultiple: [1]
|
|
- PrefetchGlobalRead: [2]
|
|
- PrefetchLocalRead: [1]
|
|
- ClusterLocalRead: [1]
|
|
- DepthU: [32]
|
|
- VectorWidthA: [1]
|
|
- VectorWidthB: [1]
|
|
- ScheduleIterAlg: [3]
|
|
- InnerUnroll: [1]
|
|
- ExpandPointerSwap: [false]
|
|
- TransposeLDS: [0]
|
|
- LdsBlockSizePerPadA: [0]
|
|
- LdsBlockSizePerPadB: [0]
|
|
- LdsPadA: [0]
|
|
- LdsPadB: [0]
|
|
- WaveSeparateGlobalReadB: [1]
|
|
- 1LDSBuffer: [-1]
|
|
- GlobalSplitU: [1]
|
|
- GlobalSplitUAlgorithm: ["MultipleBuffer"]
|
|
- GlobalReadPerMfma: [1.0]
|
|
- LocalWritePerMfma: [-1]
|
|
- StoreVectorWidth: [-1]
|
|
- SourceSwap: [true]
|
|
- NumElementsPerBatchStore: [2]
|
|
- StorePriorityOpt: [true]
|
|
BenchmarkJoinParameters:
|
|
BenchmarkFinalParameters:
|
|
- ProblemSizes:
|
|
- Exact: [128, 128, 1, 128]
|
|
# - Exact: []
|
|
- BiasTypeArgs: ['s']
|
|
- ActivationArgs:
|
|
- [Enum: none]
|
|
|
|
-
|
|
- # ProblemType
|
|
OperationType: GEMM
|
|
DataType: h
|
|
DataTypeB: s
|
|
DestDataType: h
|
|
ComputeDataType: s
|
|
HighPrecisionAccumulate: True
|
|
TransposeA: False
|
|
TransposeB: True
|
|
UseBeta: True
|
|
Batched: True
|
|
UseBias: 1
|
|
- # BenchmarkProblemSizeGroup - Standard
|
|
InitialSolutionParameters:
|
|
BenchmarkCommonParameters:
|
|
- KernelLanguage: ["Assembly"]
|
|
ForkParameters:
|
|
- MatrixInstruction:
|
|
- [32, 32, 8, 1, 1, 1, 1, 2,2 ]
|
|
- AssertFree0ElementMultiple: [1]
|
|
- PrefetchGlobalRead: [2]
|
|
- PrefetchLocalRead: [1]
|
|
- ClusterLocalRead: [1]
|
|
- DepthU: [32]
|
|
- VectorWidthA: [1]
|
|
- VectorWidthB: [1]
|
|
- ScheduleIterAlg: [3]
|
|
- InnerUnroll: [1]
|
|
- ExpandPointerSwap: [false]
|
|
- TransposeLDS: [0]
|
|
- LdsBlockSizePerPadA: [0]
|
|
- LdsBlockSizePerPadB: [0]
|
|
- LdsPadA: [0]
|
|
- LdsPadB: [0]
|
|
- WaveSeparateGlobalReadB: [1]
|
|
- 1LDSBuffer: [-1]
|
|
- GlobalSplitU: [1]
|
|
- GlobalSplitUAlgorithm: ["MultipleBuffer"]
|
|
- GlobalReadPerMfma: [1.0]
|
|
- LocalWritePerMfma: [-1]
|
|
- StoreVectorWidth: [-1]
|
|
- SourceSwap: [true]
|
|
- NumElementsPerBatchStore: [2]
|
|
- StorePriorityOpt: [true]
|
|
BenchmarkJoinParameters:
|
|
BenchmarkFinalParameters:
|
|
- ProblemSizes:
|
|
- Exact: [128, 128, 1, 128]
|
|
# - Exact: []
|
|
- BiasTypeArgs: ['s']
|
|
- ActivationArgs:
|
|
- [Enum: none]
|
|
|
|
-
|
|
- # ProblemType
|
|
OperationType: GEMM
|
|
DataType: h
|
|
DataTypeB: s
|
|
DestDataType: h
|
|
ComputeDataType: s
|
|
HighPrecisionAccumulate: True
|
|
TransposeA: True
|
|
TransposeB: False
|
|
UseBeta: True
|
|
Batched: True
|
|
UseBias: 1
|
|
- # BenchmarkProblemSizeGroup - Standard
|
|
InitialSolutionParameters:
|
|
BenchmarkCommonParameters:
|
|
- KernelLanguage: ["Assembly"]
|
|
ForkParameters:
|
|
- MatrixInstruction:
|
|
- [32, 32, 8, 1, 1, 1, 1, 2,2 ]
|
|
- AssertFree0ElementMultiple: [1]
|
|
- PrefetchGlobalRead: [2]
|
|
- PrefetchLocalRead: [1]
|
|
- ClusterLocalRead: [1]
|
|
- DepthU: [32]
|
|
- VectorWidthA: [1]
|
|
- VectorWidthB: [1]
|
|
- ScheduleIterAlg: [3]
|
|
- InnerUnroll: [1]
|
|
- ExpandPointerSwap: [false]
|
|
- TransposeLDS: [0]
|
|
- LdsBlockSizePerPadA: [0]
|
|
- LdsBlockSizePerPadB: [0]
|
|
- LdsPadA: [0]
|
|
- LdsPadB: [0]
|
|
- WaveSeparateGlobalReadB: [1]
|
|
- 1LDSBuffer: [-1]
|
|
- GlobalSplitU: [1]
|
|
- GlobalSplitUAlgorithm: ["MultipleBuffer"]
|
|
- GlobalReadPerMfma: [1.0]
|
|
- LocalWritePerMfma: [-1]
|
|
- StoreVectorWidth: [-1]
|
|
- SourceSwap: [true]
|
|
- NumElementsPerBatchStore: [2]
|
|
- StorePriorityOpt: [true]
|
|
BenchmarkJoinParameters:
|
|
BenchmarkFinalParameters:
|
|
- ProblemSizes:
|
|
- Exact: [128, 128, 1, 128]
|
|
# - Exact: []
|
|
- BiasTypeArgs: ['s']
|
|
- ActivationArgs:
|
|
- [Enum: none]
|
|
|
|
-
|
|
- # ProblemType
|
|
OperationType: GEMM
|
|
DataType: h
|
|
DataTypeB: s
|
|
DestDataType: h
|
|
ComputeDataType: s
|
|
HighPrecisionAccumulate: True
|
|
TransposeA: True
|
|
TransposeB: True
|
|
UseBeta: True
|
|
Batched: True
|
|
UseBias: 1
|
|
- # BenchmarkProblemSizeGroup - Standard
|
|
InitialSolutionParameters:
|
|
BenchmarkCommonParameters:
|
|
- KernelLanguage: ["Assembly"]
|
|
ForkParameters:
|
|
- MatrixInstruction:
|
|
- [32, 32, 8, 1, 1, 1, 1, 2,2 ]
|
|
- AssertFree0ElementMultiple: [1]
|
|
- PrefetchGlobalRead: [2]
|
|
- PrefetchLocalRead: [1]
|
|
- ClusterLocalRead: [1]
|
|
- DepthU: [32]
|
|
- VectorWidthA: [1]
|
|
- VectorWidthB: [1]
|
|
- ScheduleIterAlg: [3]
|
|
- InnerUnroll: [1]
|
|
- ExpandPointerSwap: [false]
|
|
- TransposeLDS: [0]
|
|
- LdsBlockSizePerPadA: [0]
|
|
- LdsBlockSizePerPadB: [0]
|
|
- LdsPadA: [0]
|
|
- LdsPadB: [0]
|
|
- WaveSeparateGlobalReadB: [1]
|
|
- 1LDSBuffer: [-1]
|
|
- GlobalSplitU: [1]
|
|
- GlobalSplitUAlgorithm: ["MultipleBuffer"]
|
|
- GlobalReadPerMfma: [1.0]
|
|
- LocalWritePerMfma: [-1]
|
|
- StoreVectorWidth: [-1]
|
|
- SourceSwap: [true]
|
|
- NumElementsPerBatchStore: [2]
|
|
- StorePriorityOpt: [true]
|
|
BenchmarkJoinParameters:
|
|
BenchmarkFinalParameters:
|
|
- ProblemSizes:
|
|
- Exact: [128, 128, 1, 128]
|
|
# - Exact: []
|
|
- BiasTypeArgs: ['s']
|
|
- ActivationArgs:
|
|
- [Enum: none]
|