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
165 lines
5.0 KiB
YAML
165 lines
5.0 KiB
YAML
TestParameters:
|
|
marks: [skip-gfx900, skip-gfx906, skip-gfx908, skip-gfx1010, skip-gfx1011, skip-gfx1012, skip-gfx1030, skip-gfx1031, skip-gfx1032, skip-gfx1033, skip-gfx1034, skip-gfx1035, skip-gfx1036, emulation1] # not supported by arch
|
|
|
|
GlobalParameters:
|
|
NumElementsToValidate: -1
|
|
BoundsCheck: True
|
|
KernelTime: True
|
|
PrintSolutionRejectionReason: True
|
|
|
|
BenchmarkProblems:
|
|
########################################
|
|
# NT - standard
|
|
########################################
|
|
- # sgemm TN
|
|
- # ProblemType
|
|
OperationType: GEMM
|
|
DataType: d
|
|
TransposeA: True
|
|
TransposeB: False
|
|
UseBeta: True
|
|
Batched: True
|
|
|
|
- # BenchmarkProblemSizeGroup - Standard
|
|
InitialSolutionParameters:
|
|
BenchmarkCommonParameters:
|
|
- KernelLanguage: ["Assembly"]
|
|
- EdgeType: ["ShiftPtr"]
|
|
- PrefetchLocalRead: [True]
|
|
ForkParameters:
|
|
- MatrixInstruction:
|
|
- [16, 16, 4, 1, 1, 8,2, 1,4] # 128x128
|
|
# - [16, 16, 4, 1, 1, 4,4, 2,2] # 128x128
|
|
# - [16, 16, 4, 1, 1, 2,8, 4,1] # 128x128
|
|
- SourceSwap: [1]
|
|
- PrefetchGlobalRead: [1]
|
|
- ThreadTile:
|
|
- [ 1, 32 ]
|
|
- WorkGroup:
|
|
- [ 16, 16, 1 ]
|
|
- WorkGroupMapping: [8]
|
|
- GlobalSplitU: [1]
|
|
- DepthU: [ 8 ]
|
|
- VectorWidth: [1]
|
|
BenchmarkForkParameters:
|
|
JoinParameters:
|
|
BenchmarkJoinParameters:
|
|
BenchmarkFinalParameters:
|
|
- ProblemSizes:
|
|
# - Range: [ [1024], [1024], [1], [1024] ]
|
|
- Range: [ [1031], [1031], [8], [1031] ]
|
|
|
|
# - # sgemm NN
|
|
# - # ProblemType
|
|
# OperationType: GEMM
|
|
# DataType: d
|
|
# TransposeA: False
|
|
# TransposeB: False
|
|
# UseBeta: True
|
|
# Batched: True
|
|
|
|
# - # BenchmarkProblemSizeGroup - Standard
|
|
# InitialSolutionParameters:
|
|
# BenchmarkCommonParameters:
|
|
# - KernelLanguage: ["Assembly"]
|
|
# - EdgeType: ["ShiftPtr"]
|
|
# - PrefetchLocalRead: [True]
|
|
# ForkParameters:
|
|
# - MatrixInstruction:
|
|
# - [16, 16, 4, 1, 1, 8,2, 1,4] # 128x128
|
|
# - [16, 16, 4, 1, 1, 4,4, 2,2] # 128x128
|
|
# - [16, 16, 4, 1, 1, 2,8, 4,1] # 128x128
|
|
# - SourceSwap: [1]
|
|
# - PrefetchGlobalRead: [1]
|
|
# - ThreadTile:
|
|
# - [ 1, 32 ]
|
|
# - WorkGroup:
|
|
# - [ 16, 16, 1 ]
|
|
# - WorkGroupMapping: [8]
|
|
# - GlobalSplitU: [1]
|
|
# - DepthU: [ 8 ]
|
|
# - VectorWidth: [1]
|
|
# BenchmarkForkParameters:
|
|
# JoinParameters:
|
|
# BenchmarkJoinParameters:
|
|
# BenchmarkFinalParameters:
|
|
# - ProblemSizes:
|
|
# - Range: [ [1024], [1024], [1], [1024] ]
|
|
# - Range: [ [1031], [1031], [8], [1031] ]
|
|
|
|
# - # sgemm NT
|
|
# - # ProblemType
|
|
# OperationType: GEMM
|
|
# DataType: d
|
|
# TransposeA: False
|
|
# TransposeB: True
|
|
# UseBeta: True
|
|
# Batched: True
|
|
|
|
# - # BenchmarkProblemSizeGroup - Standard
|
|
# InitialSolutionParameters:
|
|
# BenchmarkCommonParameters:
|
|
# - KernelLanguage: ["Assembly"]
|
|
# - EdgeType: ["ShiftPtr"]
|
|
# - PrefetchLocalRead: [True]
|
|
# ForkParameters:
|
|
# - MatrixInstruction:
|
|
# - [16, 16, 4, 1, 1, 8,2, 1,4] # 128x128
|
|
# - [16, 16, 4, 1, 1, 4,4, 2,2] # 128x128
|
|
# - [16, 16, 4, 1, 1, 2,8, 4,1] # 128x128
|
|
# - SourceSwap: [1]
|
|
# - PrefetchGlobalRead: [1]
|
|
# - ThreadTile:
|
|
# - [ 1, 32 ]
|
|
# - WorkGroup:
|
|
# - [ 16, 16, 1 ]
|
|
# - WorkGroupMapping: [8]
|
|
# - GlobalSplitU: [1]
|
|
# - DepthU: [ 8 ]
|
|
# - VectorWidth: [1]
|
|
# BenchmarkForkParameters:
|
|
# JoinParameters:
|
|
# BenchmarkJoinParameters:
|
|
# BenchmarkFinalParameters:
|
|
# - ProblemSizes:
|
|
# - Range: [ [1024], [1024], [1], [1024] ]
|
|
# - Range: [ [1031], [1031], [8], [1031] ]
|
|
|
|
# - # sgemm TT
|
|
# - # ProblemType
|
|
# OperationType: GEMM
|
|
# DataType: d
|
|
# TransposeA: True
|
|
# TransposeB: True
|
|
# UseBeta: True
|
|
# Batched: True
|
|
|
|
# - # BenchmarkProblemSizeGroup - Standard
|
|
# InitialSolutionParameters:
|
|
# BenchmarkCommonParameters:
|
|
# - KernelLanguage: ["Assembly"]
|
|
# - EdgeType: ["ShiftPtr"]
|
|
# - PrefetchLocalRead: [True]
|
|
# ForkParameters:
|
|
# - MatrixInstruction:
|
|
# - [16, 16, 4, 1, 1, 8,2, 1,4] # 128x128
|
|
# - [16, 16, 4, 1, 1, 4,4, 2,2] # 128x128
|
|
# - [16, 16, 4, 1, 1, 2,8, 4,1] # 128x128
|
|
# - SourceSwap: [1]
|
|
# - PrefetchGlobalRead: [1]
|
|
# - ThreadTile:
|
|
# - [ 1, 32 ]
|
|
# - WorkGroup:
|
|
# - [ 16, 16, 1 ]
|
|
# - WorkGroupMapping: [8]
|
|
# - GlobalSplitU: [1]
|
|
# - DepthU: [ 8 ]
|
|
# - VectorWidth: [1]
|
|
# BenchmarkForkParameters:
|
|
# JoinParameters:
|
|
# BenchmarkJoinParameters:
|
|
# BenchmarkFinalParameters:
|
|
# - ProblemSizes:
|
|
# - Range: [ [1024], [1024], [1], [1024] ]
|
|
# - Range: [ [1031], [1031], [8], [1031] ]
|