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
153 lines
4.3 KiB
YAML
153 lines
4.3 KiB
YAML
# A config to generate a fast kernel(s) for BDAS workload problem sizes
|
|
# kmeans workload
|
|
|
|
GlobalParameters:
|
|
MinimumRequiredVersion: 4.14.0
|
|
PrintLevel: 1
|
|
ForceRedoBenchmarkProblems: True
|
|
ForceRedoLibraryLogic: True
|
|
ForceRedoLibraryClient: True
|
|
CMakeBuildType: Release
|
|
EnqueuesPerSync: 1
|
|
NumBenchmarks: 1
|
|
SyncsPerBenchmark: 1
|
|
LibraryPrintDebug: False
|
|
NumElementsToValidate: 100
|
|
ValidationMaxToPrint: 4
|
|
ValidationPrintValids: False
|
|
ShortNames: False
|
|
MergeFiles: True
|
|
Platform: 0
|
|
Device: 0
|
|
KernelTime: True
|
|
PinClocks: True
|
|
SleepPercent: 0
|
|
PrintSolutionRejectionReason: True
|
|
DataInitTypeBeta : 0
|
|
DataInitTypeAlpha : 1
|
|
NewKernel: 2
|
|
|
|
BenchmarkProblems:
|
|
########################################
|
|
# TN - standard
|
|
########################################
|
|
-
|
|
- # ProblemType
|
|
OperationType: GEMM
|
|
DataType: d
|
|
TransposeA: True
|
|
TransposeB: False
|
|
UseBeta: True
|
|
Batched: True
|
|
|
|
- # BenchmarkProblemSizeGroup - Standard
|
|
InitialSolutionParameters:
|
|
BenchmarkCommonParameters:
|
|
- KernelLanguage: ["Assembly"]
|
|
- EdgeType: ["ShiftPtr"]
|
|
- LoopTail: [True]
|
|
ForkParameters:
|
|
- PrefetchLocalRead: [True]
|
|
- PrefetchGlobalRead: [True]
|
|
- ThreadTile:
|
|
- [ 1, 3 ]
|
|
- [ 4, 1 ]
|
|
- [ 8, 1 ]
|
|
- WorkGroup:
|
|
- [ 64, 4, 1 ]
|
|
- [ 32, 8, 1 ]
|
|
- WorkGroupMapping: [1,4,8]
|
|
- GlobalSplitU: [32]
|
|
- DepthU: [ 16 ]
|
|
- VectorWidth: [1,2]
|
|
- FractionalLoad: [1]
|
|
- GlobalSplitUWorkGroupMappingRoundRobin: [True,False]
|
|
- GlobalSplitUSummationAssignmentRoundRobin: [True,False]
|
|
#- VectorAtomicWidth: [1]
|
|
- GlobalReadVectorWidth: [2,4]
|
|
- OptNoLoadLoop: [2]
|
|
- StaggerUStride: [256]
|
|
- StaggerUMapping: [0]
|
|
BenchmarkForkParameters:
|
|
JoinParameters:
|
|
BenchmarkJoinParameters:
|
|
BenchmarkFinalParameters:
|
|
- ProblemSizes:
|
|
- Exact: [ 250, 9, 1, 500000,266,266,500016,500032 ]
|
|
|
|
- # BenchmarkProblemSizeGroup - Standard
|
|
InitialSolutionParameters:
|
|
BenchmarkCommonParameters:
|
|
- KernelLanguage: ["Assembly"]
|
|
- EdgeType: ["ShiftPtr"]
|
|
- LoopTail: [True]
|
|
ForkParameters:
|
|
- PrefetchLocalRead: [True]
|
|
- PrefetchGlobalRead: [True]
|
|
- ThreadTile:
|
|
- [ 1, 3 ]
|
|
- [ 1, 3 ]
|
|
- [ 4, 1 ]
|
|
- [ 8, 1 ]
|
|
- WorkGroup:
|
|
- [ 64, 4, 1 ]
|
|
- [ 32, 8, 1 ]
|
|
- WorkGroupMapping: [1,4,8]
|
|
- GlobalSplitUWorkGroupMappingRoundRobin: [True,False]
|
|
- GlobalSplitUSummationAssignmentRoundRobin: [True,False]
|
|
- GlobalSplitU: [16]
|
|
- DepthU: [ 16 ]
|
|
- VectorWidth: [1,2]
|
|
- FractionalLoad: [1]
|
|
#- VectorAtomicWidth: [1]
|
|
- GlobalReadVectorWidth: [2,4]
|
|
- OptNoLoadLoop: [2]
|
|
- StaggerUStride: [256]
|
|
- StaggerUMapping: [0]
|
|
BenchmarkForkParameters:
|
|
JoinParameters:
|
|
BenchmarkJoinParameters:
|
|
BenchmarkFinalParameters:
|
|
- ProblemSizes:
|
|
- Exact: [ 250, 9, 1, 500000,266,266,500016,500032 ]
|
|
|
|
- # BenchmarkProblemSizeGroup - Standard
|
|
InitialSolutionParameters:
|
|
BenchmarkCommonParameters:
|
|
- KernelLanguage: ["Assembly"]
|
|
- EdgeType: ["ShiftPtr"]
|
|
- LoopTail: [True]
|
|
ForkParameters:
|
|
- PrefetchLocalRead: [True]
|
|
- PrefetchGlobalRead: [True]
|
|
- ThreadTile:
|
|
- [ 1, 3 ]
|
|
- [ 1, 3 ]
|
|
- [ 4, 1 ]
|
|
- [ 8, 1 ]
|
|
- WorkGroup:
|
|
- [ 64, 4, 1 ]
|
|
- [ 32, 8, 1 ]
|
|
- WorkGroupMapping: [1,4,8]
|
|
- FractionalLoad: [1]
|
|
- GlobalSplitUWorkGroupMappingRoundRobin: [True,False]
|
|
- GlobalSplitUSummationAssignmentRoundRobin: [True,False]
|
|
- GlobalSplitU: [16]
|
|
- DepthU: [ 16 ]
|
|
- VectorWidth: [1,2]
|
|
- FractionalLoad: [1]
|
|
#- VectorAtomicWidth: [1]
|
|
- GlobalReadVectorWidth: [2,4]
|
|
- OptNoLoadLoop: [2]
|
|
- StaggerUStride: [512]
|
|
- StaggerUMapping: [0]
|
|
BenchmarkForkParameters:
|
|
JoinParameters:
|
|
BenchmarkJoinParameters:
|
|
BenchmarkFinalParameters:
|
|
- ProblemSizes:
|
|
- Exact: [ 250, 9, 1, 500000,266,266,500016,500032 ]
|
|
|
|
########################################
|
|
LibraryLogic:
|