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
86 lines
2.4 KiB
YAML
86 lines
2.4 KiB
YAML
GlobalParameters:
|
|
MinimumRequiredVersion: 4.0.1
|
|
ForceRedoBenchmarkProblems: True
|
|
PrintLevel: 1
|
|
CMakeBuildType: Release
|
|
NumElementsToValidate: 1000
|
|
ValidationMaxToPrint: 4
|
|
ValidationPrintValids: False
|
|
DataInitTypeA: 3 # 0=0, 1=1, 2=serial, 3=rand, 4=NaN
|
|
DataInitTypeB: 3 # 0=0, 1=1, 2=serial, 3=rand, 4=NaN
|
|
DataInitTypeC : 3 # 0=0, 1=1, 2=serial, 3=rand, 4=NaN
|
|
MergeFiles: False
|
|
|
|
BenchmarkProblems:
|
|
########################################
|
|
# NT - standard
|
|
########################################
|
|
-
|
|
- # ProblemType
|
|
OperationType: GEMM
|
|
DataType: s
|
|
DestDataType: s
|
|
TransposeA: True
|
|
TransposeB: True
|
|
UseBeta: True
|
|
Batched: True
|
|
|
|
- # BenchmarkProblemSizeGroup - Standard
|
|
InitialSolutionParameters:
|
|
BenchmarkCommonParameters:
|
|
- KernelLanguage: ["Source"]
|
|
- EdgeType: ["ShiftPtr"]
|
|
ForkParameters:
|
|
- GlobalSplitU: [1, 3, 5]
|
|
- PersistentKernel: [1]
|
|
- ThreadTile:
|
|
- [ 8, 8 ]
|
|
- WorkGroup:
|
|
- [ 32, 4, 1 ]
|
|
- [ 8, 8, 1 ]
|
|
- WorkGroupMapping: [1,2,8]
|
|
- DepthU: [ 8 ]
|
|
- GlobalReadVectorWidth: [2]
|
|
- VectorWidth: [2]
|
|
BenchmarkFinalParameters:
|
|
- ProblemSizes:
|
|
#- Exact: [ 1, 1, 1, 1]
|
|
- Range: [ [256,128,1024], [512], [1], [64] ]
|
|
- Range: [ [127,1,129], 0, [2], [63,1,65] ]
|
|
|
|
|
|
- # ProblemType - Half Precision test
|
|
OperationType: GEMM
|
|
DataType: s
|
|
DestDataType: s
|
|
TransposeA: False
|
|
TransposeB: False
|
|
UseBeta: True
|
|
Batched: True
|
|
|
|
- # BenchmarkProblemSizeGroup - Standard
|
|
InitialSolutionParameters:
|
|
BenchmarkCommonParameters:
|
|
- KernelLanguage: ["Source"]
|
|
- EdgeType: ["ShiftPtr"]
|
|
ForkParameters:
|
|
- GlobalSplitU: [1, 3, 5]
|
|
- PersistentKernel: [1]
|
|
- ThreadTile:
|
|
- [ 8, 8 ]
|
|
- WorkGroup:
|
|
- [ 32, 4, 1 ]
|
|
- [ 8, 8, 1 ]
|
|
- WorkGroupMapping: [1,2,8]
|
|
- DepthU: [ 8 ]
|
|
- GlobalReadVectorWidth: [2]
|
|
- VectorWidth: [2]
|
|
BenchmarkFinalParameters:
|
|
- ProblemSizes:
|
|
- Exact: [ 2, 2, 2, 2]
|
|
- Range: [ [256,128,1024], [512], [1], [64] ]
|
|
- Range: [ [256,128,1024], [256], [1], [16] ]
|
|
- Range: [ [127,1,129], 0, [2], [63,1,65] ]
|
|
|
|
########################################
|