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
275 lines
7.3 KiB
YAML
275 lines
7.3 KiB
YAML
TestParameters:
|
|
marks: [emulation2]
|
|
|
|
# benchmark assembly and source kernels
|
|
GlobalParameters:
|
|
MinimumRequiredVersion: 4.2.0
|
|
CMakeBuildType: Release
|
|
PrintLevel: 1
|
|
ForceRedoBenchmarkProblems: True
|
|
ForceRedoLibraryLogic: True
|
|
ForceRedoLibraryClient: True
|
|
EnqueuesPerSync: 1
|
|
SyncsPerBenchmark: 1
|
|
NumElementsToValidate: -1
|
|
BoundsCheck: True
|
|
ValidationMaxToPrint: 4
|
|
ValidationPrintValids: False
|
|
ShortNames: False
|
|
MergeFiles: True
|
|
DataInitTypeAB: 3
|
|
DataInitTypeC: 3
|
|
KernelTime: True
|
|
|
|
BenchmarkProblems:
|
|
|
|
- # sgemm NN
|
|
- # ProblemType
|
|
OperationType: GEMM
|
|
DataType: d
|
|
DestDataType: d
|
|
TransposeA: False
|
|
TransposeB: False
|
|
UseBeta: True
|
|
Batched: True
|
|
|
|
- # BenchmarkProblemSizeGroup - Assembly
|
|
InitialSolutionParameters:
|
|
BenchmarkCommonParameters:
|
|
- LoopTail: [True]
|
|
- EdgeType: ["ShiftPtr"]
|
|
- KernelLanguage: ["Assembly"]
|
|
ForkParameters:
|
|
- GlobalSplitU: [1, 3]
|
|
- PrefetchLocalRead: [False]
|
|
- PrefetchGlobalRead: [True]
|
|
- ThreadTile:
|
|
- [ 3, 5 ]
|
|
- [ 4, 8 ]
|
|
#- [ 8, 8 ]
|
|
- WorkGroup:
|
|
- [ 32, 4, 1 ]
|
|
- [ 8, 8, 1 ]
|
|
- DepthU: [-3]
|
|
- VectorWidth: [-1]
|
|
BenchmarkForkParameters:
|
|
JoinParameters:
|
|
BenchmarkJoinParameters:
|
|
BenchmarkFinalParameters:
|
|
- ProblemSizes:
|
|
- Range: [ [127,1,129], 0, [2], [63,1,64] ]
|
|
|
|
# - # BenchmarkProblemSizeGroup - Assembly
|
|
# InitialSolutionParameters:
|
|
# BenchmarkCommonParameters:
|
|
# - LoopTail: [True]
|
|
# - EdgeType: ["ShiftPtr"]
|
|
# ForkParameters:
|
|
# - KernelLanguage: ["Assembly"]
|
|
# - GlobalSplitU: [1, 3]
|
|
# - PrefetchLocalRead: [False]
|
|
# - PrefetchGlobalRead: [True]
|
|
# - ThreadTile:
|
|
# #- [ 3, 3 ]
|
|
# - [ 4, 4 ]
|
|
# - [ 5, 5 ]
|
|
# #- [ 8, 8 ]
|
|
# - WorkGroup:
|
|
# - [ 16, 16, 1 ]
|
|
# - [ 8, 8, 1 ]
|
|
# - DepthU: [-1]
|
|
# - VectorWidth: [1]
|
|
# BenchmarkForkParameters:
|
|
# JoinParameters:
|
|
# BenchmarkJoinParameters:
|
|
# BenchmarkFinalParameters:
|
|
# - ProblemSizes:
|
|
# - Range: [ [127,1,129], 0, [2], [63,1,64] ]
|
|
|
|
- # sgemm NT
|
|
- # ProblemType
|
|
OperationType: GEMM
|
|
DataType: d
|
|
DestDataType: d
|
|
TransposeA: False
|
|
TransposeB: True
|
|
UseBeta: True
|
|
Batched: True
|
|
|
|
- # BenchmarkProblemSizeGroup - Assembly
|
|
InitialSolutionParameters:
|
|
BenchmarkCommonParameters:
|
|
- LoopTail: [True]
|
|
- EdgeType: ["ShiftPtr"]
|
|
- KernelLanguage: ["Assembly"]
|
|
ForkParameters:
|
|
- GlobalSplitU: [1, 3]
|
|
- PrefetchLocalRead: [True]
|
|
- PrefetchGlobalRead: [True]
|
|
- ThreadTile:
|
|
- [ 3, 5 ]
|
|
- [ 4, 8 ]
|
|
#- [ 8, 8 ]
|
|
- WorkGroup:
|
|
- [ 16, 16, 1 ]
|
|
- [ 8, 16, 1 ]
|
|
- DepthU: [-3]
|
|
- VectorWidth: [-1]
|
|
BenchmarkForkParameters:
|
|
JoinParameters:
|
|
BenchmarkJoinParameters:
|
|
BenchmarkFinalParameters:
|
|
- ProblemSizes:
|
|
- Range: [ [127,1,129], 0, [2], [63,1,64] ]
|
|
|
|
# - # BenchmarkProblemSizeGroup - Assembly
|
|
# InitialSolutionParameters:
|
|
# BenchmarkCommonParameters:
|
|
# - LoopTail: [True]
|
|
# - EdgeType: ["ShiftPtr"]
|
|
# ForkParameters:
|
|
# - KernelLanguage: ["Assembly"]
|
|
# - GlobalSplitU: [1, 3]
|
|
# - PrefetchLocalRead: [True]
|
|
# - PrefetchGlobalRead: [True]
|
|
# - ThreadTile:
|
|
# - [ 3, 3 ]
|
|
# - [ 4, 4 ]
|
|
# #- [ 5, 5 ]
|
|
# #- [ 8, 8 ]
|
|
# - WorkGroup:
|
|
# - [ 16, 16, 1 ]
|
|
# - [ 16, 8, 1 ]
|
|
# - DepthU: [-1]
|
|
# - VectorWidth: [1]
|
|
# BenchmarkForkParameters:
|
|
# JoinParameters:
|
|
# BenchmarkJoinParameters:
|
|
# BenchmarkFinalParameters:
|
|
# - ProblemSizes:
|
|
# - Range: [ [127,1,129], 0, [2], [63,1,64] ]
|
|
|
|
- # sgemm TN
|
|
- # ProblemType
|
|
OperationType: GEMM
|
|
DataType: d
|
|
DestDataType: d
|
|
TransposeA: True
|
|
TransposeB: False
|
|
UseBeta: True
|
|
Batched: True
|
|
|
|
- # BenchmarkProblemSizeGroup - Assembly
|
|
InitialSolutionParameters:
|
|
BenchmarkCommonParameters:
|
|
- LoopTail: [True]
|
|
- EdgeType: ["ShiftPtr"]
|
|
- KernelLanguage: ["Assembly"]
|
|
ForkParameters:
|
|
- GlobalSplitU: [1, 3]
|
|
- PrefetchLocalRead: [True]
|
|
- PrefetchGlobalRead: [False]
|
|
- ThreadTile:
|
|
- [ 3, 5 ]
|
|
- [ 4, 8 ]
|
|
#- [ 8, 8 ]
|
|
- WorkGroup:
|
|
- [ 16, 16, 1 ]
|
|
- [ 32, 4, 1 ]
|
|
- DepthU: [-4]
|
|
- VectorWidth: [-1]
|
|
BenchmarkForkParameters:
|
|
JoinParameters:
|
|
BenchmarkJoinParameters:
|
|
BenchmarkFinalParameters:
|
|
- ProblemSizes:
|
|
- Range: [ [127,1,129], 0, [2], [63,1,64] ]
|
|
|
|
# - # BenchmarkProblemSizeGroup - Assembly
|
|
# InitialSolutionParameters:
|
|
# BenchmarkCommonParameters:
|
|
# - LoopTail: [True]
|
|
# - EdgeType: ["ShiftPtr"]
|
|
# ForkParameters:
|
|
# - KernelLanguage: ["Assembly"]
|
|
# - GlobalSplitU: [1, 3]
|
|
# - PrefetchLocalRead: [True]
|
|
# - PrefetchGlobalRead: [False]
|
|
# - ThreadTile:
|
|
# - [ 3, 3 ]
|
|
# - [ 4, 4 ]
|
|
# #- [ 5, 5 ]
|
|
# #- [ 8, 8 ]
|
|
# - WorkGroup:
|
|
# - [ 16, 16, 1 ]
|
|
# - [ 8, 8, 1 ]
|
|
# - DepthU: [-1]
|
|
# - VectorWidth: [1]
|
|
# BenchmarkForkParameters:
|
|
# JoinParameters:
|
|
# BenchmarkJoinParameters:
|
|
# BenchmarkFinalParameters:
|
|
# - ProblemSizes:
|
|
# - Range: [ [127,1,129], 0, [2], [63,1,64] ]
|
|
|
|
- # sgemm TT
|
|
- # ProblemType
|
|
OperationType: GEMM
|
|
DataType: d
|
|
DestDataType: d
|
|
TransposeA: True
|
|
TransposeB: True
|
|
UseBeta: True
|
|
Batched: True
|
|
|
|
- # BenchmarkProblemSizeGroup - Assembly
|
|
InitialSolutionParameters:
|
|
BenchmarkCommonParameters:
|
|
- LoopTail: [True]
|
|
- EdgeType: ["ShiftPtr"]
|
|
- KernelLanguage: ["Assembly"]
|
|
ForkParameters:
|
|
- PrefetchLocalRead: [False]
|
|
- PrefetchGlobalRead: [False]
|
|
- ThreadTile:
|
|
- [ 3, 5 ]
|
|
- [ 4, 8 ]
|
|
#- [ 8, 8 ]
|
|
- WorkGroup:
|
|
- [ 16, 16, 1 ]
|
|
- [ 8, 8, 1 ]
|
|
- DepthU: [-3]
|
|
- VectorWidth: [-1]
|
|
BenchmarkForkParameters:
|
|
JoinParameters:
|
|
BenchmarkJoinParameters:
|
|
BenchmarkFinalParameters:
|
|
- ProblemSizes:
|
|
- Range: [ [127,1,129], 0, [2], [63,1,64] ]
|
|
|
|
# - # BenchmarkProblemSizeGroup - Assembly
|
|
# InitialSolutionParameters:
|
|
# BenchmarkCommonParameters:
|
|
# - LoopTail: [True]
|
|
# - EdgeType: ["ShiftPtr"]
|
|
# ForkParameters:
|
|
# - KernelLanguage: ["Assembly"]
|
|
# - PrefetchLocalRead: [False]
|
|
# - PrefetchGlobalRead: [False]
|
|
# - ThreadTile:
|
|
# - [ 3, 3 ]
|
|
# - [ 4, 4 ]
|
|
# #- [ 5, 5 ]
|
|
# #- [ 8, 8 ]
|
|
# - WorkGroup:
|
|
# - [ 16, 16, 1 ]
|
|
# - [ 8, 8, 1 ]
|
|
# - DepthU: [-1]
|
|
# - VectorWidth: [1]
|
|
# BenchmarkForkParameters:
|
|
# JoinParameters:
|
|
# BenchmarkJoinParameters:
|
|
# BenchmarkFinalParameters:
|
|
# - ProblemSizes:
|
|
# - Range: [ [127,1,129], 0, [2], [63,1,64] ]
|