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
175 lines
4.8 KiB
YAML
175 lines
4.8 KiB
YAML
TestParameters:
|
|
marks: [skip-gfx950, skip-gfx1100, skip-gfx1101, skip-gfx1102, skip-gfx1200, skip-gfx1201, skip-gfx1250] # not supported yet
|
|
|
|
GlobalParameters:
|
|
SyncsPerBenchmark: 0
|
|
NumElementsToValidate: -1
|
|
MinimumRequiredVersion: 5.0.0
|
|
PrintLevel: 1
|
|
PrintSolutionRejectionReason: True
|
|
Device: 0
|
|
CMakeBuildType: Release
|
|
KernelTime: True
|
|
MaxWorkspaceSize: 13421772800
|
|
DataInitTypeAlpha: 1
|
|
DataInitTypeBeta: 0
|
|
DataInitTypeA: 1
|
|
DataInitTypeB: 1
|
|
|
|
BenchmarkProblems:
|
|
########################################
|
|
# NN - standard
|
|
########################################
|
|
-
|
|
- # ProblemType
|
|
OperationType: GEMM
|
|
DataType: d
|
|
TransposeA: False
|
|
TransposeB: False
|
|
UseBeta: True
|
|
Batched: True
|
|
Activation: False
|
|
B2BGemm: False
|
|
|
|
|
|
- # BenchmarkProblemSizeGroup - Standard
|
|
InitialSolutionParameters:
|
|
BenchmarkCommonParameters:
|
|
ForkParameters:
|
|
- KernelLanguage: ["Assembly"]
|
|
- DepthU: [8, 16]
|
|
- GlobalSplitU: [1]
|
|
- ScheduleIterAlg: [3]
|
|
- MatrixInstruction:
|
|
- [16, 16, 4, 1, 1, 1, 1, 1, 1]
|
|
- AssertFree0ElementMultiple: [1]
|
|
- VectorWidthA: [1, 2]
|
|
- VectorWidthB: [1, 2]
|
|
- GlobalSplitU: [1,2]
|
|
- GlobalSplitUAlgorithm: ["MultipleBuffer", "MultipleBufferSingleKernel"]
|
|
- SourceSwap: [false, true]
|
|
BenchmarkForkParameters:
|
|
JoinParameters:
|
|
BenchmarkJoinParameters:
|
|
BenchmarkFinalParameters:
|
|
- ProblemSizes:
|
|
- Exact: [128, 128, 1, 1024]
|
|
- Exact: [4608, 1335, 1, 640]
|
|
|
|
########################################
|
|
# TN - standard
|
|
########################################
|
|
-
|
|
- # ProblemType
|
|
OperationType: GEMM
|
|
DataType: d
|
|
TransposeA: True
|
|
TransposeB: False
|
|
UseBeta: True
|
|
Batched: True
|
|
Activation: False
|
|
B2BGemm: False
|
|
|
|
|
|
- # BenchmarkProblemSizeGroup - Standard
|
|
InitialSolutionParameters:
|
|
BenchmarkCommonParameters:
|
|
ForkParameters:
|
|
- KernelLanguage: ["Assembly"]
|
|
- DepthU: [8, 16]
|
|
- GlobalSplitU: [1]
|
|
- ScheduleIterAlg: [3]
|
|
- MatrixInstruction:
|
|
- [16, 16, 4, 1, 1, 1, 1, 1, 1]
|
|
- AssertFree0ElementMultiple: [1]
|
|
- VectorWidthA: [1, 2]
|
|
- VectorWidthB: [1, 2]
|
|
- GlobalSplitU: [1,2]
|
|
- GlobalSplitUAlgorithm: ["MultipleBuffer", "MultipleBufferSingleKernel"]
|
|
- SourceSwap: [false, true]
|
|
BenchmarkForkParameters:
|
|
JoinParameters:
|
|
BenchmarkJoinParameters:
|
|
BenchmarkFinalParameters:
|
|
- ProblemSizes:
|
|
- Exact: [128, 128, 1, 1024]
|
|
- Exact: [4608, 1335, 1, 640]
|
|
|
|
########################################
|
|
# NT - standard
|
|
########################################
|
|
-
|
|
- # ProblemType
|
|
OperationType: GEMM
|
|
DataType: d
|
|
TransposeA: False
|
|
TransposeB: True
|
|
UseBeta: True
|
|
Batched: True
|
|
Activation: False
|
|
B2BGemm: False
|
|
|
|
|
|
- # BenchmarkProblemSizeGroup - Standard
|
|
InitialSolutionParameters:
|
|
BenchmarkCommonParameters:
|
|
ForkParameters:
|
|
- KernelLanguage: ["Assembly"]
|
|
- DepthU: [8, 16]
|
|
- GlobalSplitU: [1]
|
|
- ScheduleIterAlg: [3]
|
|
- MatrixInstruction:
|
|
- [16, 16, 4, 1, 1, 1, 1, 1, 1]
|
|
- AssertFree0ElementMultiple: [1]
|
|
- VectorWidthA: [1, 2]
|
|
- VectorWidthB: [1, 2]
|
|
- GlobalSplitU: [1,2]
|
|
- GlobalSplitUAlgorithm: ["MultipleBuffer", "MultipleBufferSingleKernel"]
|
|
- SourceSwap: [false, true]
|
|
BenchmarkForkParameters:
|
|
JoinParameters:
|
|
BenchmarkJoinParameters:
|
|
BenchmarkFinalParameters:
|
|
- ProblemSizes:
|
|
- Exact: [128, 128, 1, 1024]
|
|
- Exact: [4608, 1335, 1, 640]
|
|
|
|
########################################
|
|
# TT - standard
|
|
########################################
|
|
-
|
|
- # ProblemType
|
|
OperationType: GEMM
|
|
DataType: d
|
|
TransposeA: True
|
|
TransposeB: True
|
|
UseBeta: True
|
|
Batched: True
|
|
Activation: False
|
|
B2BGemm: False
|
|
|
|
|
|
- # BenchmarkProblemSizeGroup - Standard
|
|
InitialSolutionParameters:
|
|
BenchmarkCommonParameters:
|
|
ForkParameters:
|
|
- KernelLanguage: ["Assembly"]
|
|
- DepthU: [8, 16]
|
|
- GlobalSplitU: [1]
|
|
- ScheduleIterAlg: [3]
|
|
- MatrixInstruction:
|
|
- [16, 16, 4, 1, 1, 1, 1, 1, 1]
|
|
- AssertFree0ElementMultiple: [1]
|
|
- VectorWidthA: [1, 2]
|
|
- VectorWidthB: [1, 2]
|
|
- GlobalSplitU: [1,2]
|
|
- GlobalSplitUAlgorithm: ["MultipleBuffer", "MultipleBufferSingleKernel"]
|
|
- SourceSwap: [false, true]
|
|
BenchmarkForkParameters:
|
|
JoinParameters:
|
|
BenchmarkJoinParameters:
|
|
BenchmarkFinalParameters:
|
|
- ProblemSizes:
|
|
- Exact: [128, 128, 1, 1024]
|
|
- Exact: [4608, 1335, 1, 640]
|