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
164 lines
4.9 KiB
YAML
164 lines
4.9 KiB
YAML
TestParameters:
|
|
marks: [skip-gfx900, skip-gfx906, skip-gfx1010, skip-gfx1011, skip-gfx1012, skip-gfx1030, skip-gfx1031, skip-gfx1032, skip-gfx1033, skip-gfx1034, skip-gfx1035, skip-gfx1036, skip-gfx1100, skip-gfx1101, skip-gfx1102, skip-gfx1103, skip-gfx1150, skip-gfx1151, skip-gfx1152, skip-gfx1153, skip-gfx1200, skip-gfx1201, skip-gfx1250] # not supported by arch
|
|
|
|
GlobalParameters:
|
|
NumElementsToValidate: -1
|
|
BoundsCheck: True
|
|
KernelTime: True
|
|
|
|
BenchmarkProblems:
|
|
########################################
|
|
# TN - standard
|
|
########################################
|
|
-
|
|
- # ProblemType
|
|
OperationType: GEMM
|
|
DataType: s
|
|
TransposeA: True
|
|
TransposeB: False
|
|
UseBeta: True
|
|
Batched: True
|
|
- # BenchmarkProblemSizeGroup - Standard
|
|
InitialSolutionParameters:
|
|
BenchmarkCommonParameters:
|
|
- KernelLanguage: ["Assembly"]
|
|
- EdgeType: ["ShiftPtr"]
|
|
ForkParameters:
|
|
- MatrixInstruction:
|
|
- [32, 32, 1, 2]
|
|
- [32, 32, 2, 1]
|
|
- [16, 16, 1, 4]
|
|
- [16, 16, 4, 1]
|
|
- ThreadTile:
|
|
- [ 1, 32 ]
|
|
- [ 2, 64 ]
|
|
- WorkGroup:
|
|
- [ 64, 4, 1 ]
|
|
- AssertSummationElementMultiple: [1]
|
|
- AssertFree0ElementMultiple: [1]
|
|
- AssertFree1ElementMultiple: [1]
|
|
- VectorWidth: [1]
|
|
- PrefetchGlobalRead: [1]
|
|
- PrefetchLocalRead: [1,5,9,17]
|
|
- DepthU: [16,32]
|
|
- GlobalReadVectorWidth: [1]
|
|
- LocalReadVectorWidth: [-1,1,2,4]
|
|
- ScheduleIterAlg: [3]
|
|
- InnerUnroll: [1,2,4]
|
|
- TransposeLDS: [0,1]
|
|
- LdsBlockSizePerPadA: [-1]
|
|
- LdsBlockSizePerPadB: [-1]
|
|
- LdsPadA: [-1]
|
|
- LdsPadB: [-1]
|
|
- 1LDSBuffer: [1]
|
|
BenchmarkJoinParameters:
|
|
BenchmarkFinalParameters:
|
|
- ProblemSizes:
|
|
- Range: [ [128], [256], [1], [255,1,257] ]
|
|
|
|
-
|
|
- # ProblemType
|
|
OperationType: GEMM
|
|
DataType: b
|
|
DestDataType: B
|
|
ComputeDataType: s
|
|
HighPrecisionAccumulate: True
|
|
TransposeA: True
|
|
TransposeB: False
|
|
UseBeta: True
|
|
Batched: True
|
|
- # BenchmarkProblemSizeGroup - Standard
|
|
InitialSolutionParameters:
|
|
BenchmarkCommonParameters:
|
|
- KernelLanguage: ["Assembly"]
|
|
- EdgeType: ["ShiftPtr"]
|
|
ForkParameters:
|
|
- MatrixInstruction:
|
|
- [32, 32, 2, 2]
|
|
- [32, 32, 4, 1]
|
|
- [32, 32, 4, 2]
|
|
- [32, 32, 8, 1]
|
|
- [16, 16, 2, 4]
|
|
- [16, 16, 8, 1]
|
|
- [16, 16, 4, 4]
|
|
- [16, 16, 16, 1]
|
|
- ThreadTile:
|
|
- [ 1, 32 ]
|
|
- [ 2, 64 ]
|
|
- WorkGroup:
|
|
- [ 64, 4, 1 ]
|
|
- AssertSummationElementMultiple: [1]
|
|
- AssertFree0ElementMultiple: [1]
|
|
- AssertFree1ElementMultiple: [1]
|
|
- VectorWidth: [2]
|
|
- PrefetchGlobalRead: [1]
|
|
- PrefetchLocalRead: [1,5,9,17]
|
|
- DepthU: [32,64]
|
|
- GlobalReadVectorWidth: [2]
|
|
- LocalReadVectorWidth: [-1,2,4,8]
|
|
- ScheduleIterAlg: [3]
|
|
- InnerUnroll: [1,2,4]
|
|
- TransposeLDS: [0,1]
|
|
- LdsBlockSizePerPadA: [-1,0]
|
|
- LdsBlockSizePerPadB: [-1]
|
|
- LdsPadA: [-1]
|
|
- LdsPadB: [-1]
|
|
- 1LDSBuffer: [1]
|
|
BenchmarkJoinParameters:
|
|
BenchmarkFinalParameters:
|
|
- ProblemSizes:
|
|
- Range: [ [128], [256], [1], [255,1,257] ]
|
|
|
|
-
|
|
- # ProblemType
|
|
OperationType: GEMM
|
|
DataType: h
|
|
ComputeDataType: s
|
|
HighPrecisionAccumulate: True
|
|
TransposeA: True
|
|
TransposeB: False
|
|
UseBeta: True
|
|
Batched: True
|
|
- # BenchmarkProblemSizeGroup - Standard
|
|
InitialSolutionParameters:
|
|
BenchmarkCommonParameters:
|
|
- KernelLanguage: ["Assembly"]
|
|
- EdgeType: ["ShiftPtr"]
|
|
ForkParameters:
|
|
- MatrixInstruction:
|
|
- [32, 32, 4, 2]
|
|
- [32, 32, 8, 1]
|
|
- [16, 16, 4, 4]
|
|
- [16, 16, 16, 1]
|
|
- ThreadTile:
|
|
- [ 1, 32 ]
|
|
- [ 2, 64 ]
|
|
- WorkGroup:
|
|
- [ 64, 4, 1 ]
|
|
- AssertSummationElementMultiple: [1]
|
|
- AssertFree0ElementMultiple: [1]
|
|
- AssertFree1ElementMultiple: [1]
|
|
- VectorWidth: [2]
|
|
- PrefetchGlobalRead: [1]
|
|
- PrefetchLocalRead: [1,3,5,9]
|
|
- DepthU: [32,64]
|
|
- GlobalReadVectorWidth: [2,4]
|
|
- LocalReadVectorWidth: [-1,2,4,8]
|
|
- ScheduleIterAlg: [3]
|
|
- InnerUnroll: [1,2]
|
|
- TransposeLDS: [0,1]
|
|
- LdsBlockSizePerPadA: [-1]
|
|
- LdsBlockSizePerPadB: [-1,0]
|
|
- LdsPadA: [-1]
|
|
- LdsPadB: [-1]
|
|
- 1LDSBuffer: [1]
|
|
BenchmarkJoinParameters:
|
|
BenchmarkFinalParameters:
|
|
- ProblemSizes:
|
|
- Range: [ [128], [256], [1], [255,1,257] ]
|
|
|
|
LibraryLogic:
|
|
ScheduleName: "arcturus"
|
|
DeviceNames: ["Device 7380", "Device 7388", "Device 738c", "Device 7390"]
|
|
ArchitectureName: "gfx908"
|