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
94 lines
2.7 KiB
YAML
94 lines
2.7 KiB
YAML
TestParameters:
|
|
marks: [skip-gfx900, skip-gfx906, skip-gfx908, skip-gfx90a, skip-gfx950, skip-gfx1010, skip-gfx1011, skip-gfx1012, skip-gfx1030, skip-gfx1100, skip-gfx1101, skip-gfx1102, skip-gfx1200, skip-gfx1201, skip-gfx1250] # not supported by arch
|
|
|
|
GlobalParameters:
|
|
SyncsPerBenchmark: 1
|
|
# SyncsPerBenchmark is not set to 0: this test uses LibraryLogic which
|
|
# requires benchmark data to build the library table.
|
|
NumElementsToValidate: -1
|
|
MinimumRequiredVersion: 5.0.0
|
|
PrintLevel: 1
|
|
PrintSolutionRejectionReason: True
|
|
Device: 0
|
|
CMakeBuildType: Release
|
|
KernelTime: True
|
|
MaxWorkspaceSize: 13421772800
|
|
DataInitTypeAlpha: 1
|
|
DataInitTypeBeta: 0
|
|
BoundsCheck: 2
|
|
|
|
BenchmarkProblems:
|
|
########################################
|
|
# F32X NT
|
|
########################################
|
|
-
|
|
- # ProblemType
|
|
OperationType: GEMM
|
|
DataType: S
|
|
DestDataType: S
|
|
ComputeDataType: S
|
|
F32XdlMathOp: X
|
|
TransposeA: False
|
|
TransposeB: True
|
|
UseBeta: True
|
|
Batched: True
|
|
- # BenchmarkProblemSizeGroup - Standard
|
|
InitialSolutionParameters:
|
|
BenchmarkCommonParameters:
|
|
- KernelLanguage: ["Assembly"]
|
|
ForkParameters:
|
|
- MatrixInstruction:
|
|
- [16, 16,8, 1, 1, 4, 4, 2,2 ] # 128x128
|
|
- DepthU: [ 16 ]
|
|
- PrefetchGlobalRead: [2]
|
|
- PrefetchLocalRead: [1]
|
|
- VectorWidthA: [1,2,4]
|
|
- VectorWidthB: [1,2,4]
|
|
- ScheduleIterAlg: [3]
|
|
- SourceSwap: [false, true]
|
|
BenchmarkJoinParameters:
|
|
BenchmarkFinalParameters:
|
|
- ProblemSizes:
|
|
- Exact: [128, 128, 1, 128]
|
|
########################################
|
|
# F32X TN
|
|
########################################
|
|
-
|
|
- # ProblemType
|
|
OperationType: GEMM
|
|
DataType: S
|
|
DestDataType: S
|
|
ComputeDataType: S
|
|
F32XdlMathOp: X
|
|
TransposeA: True
|
|
TransposeB: False
|
|
UseBeta: True
|
|
Batched: True
|
|
- # BenchmarkProblemSizeGroup - Standard
|
|
InitialSolutionParameters:
|
|
BenchmarkCommonParameters:
|
|
- KernelLanguage: ["Assembly"]
|
|
ForkParameters:
|
|
- MatrixInstruction:
|
|
- [16, 16,8, 1, 1, 4, 4, 2,2 ] # 128x128
|
|
- DepthU: [ 16 ]
|
|
- PrefetchGlobalRead: [2]
|
|
- PrefetchLocalRead: [1]
|
|
- VectorWidthA: [1,2,4]
|
|
- VectorWidthB: [1,2,4]
|
|
- ScheduleIterAlg: [3]
|
|
- SourceSwap: [false, true]
|
|
- LocalReadVectorWidth: [1,2,4]
|
|
BenchmarkJoinParameters:
|
|
BenchmarkFinalParameters:
|
|
- ProblemSizes:
|
|
- Exact: [128, 128, 1, 128]
|
|
|
|
LibraryLogic:
|
|
ScheduleName: "aquavanjaram"
|
|
DeviceNames: ["Device 0049", "Device 0050"]
|
|
ArchitectureName: "gfx942"
|
|
LibraryType: "GridBased"
|
|
|
|
LibraryClient:
|