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
482 lines
14 KiB
YAML
482 lines
14 KiB
YAML
GlobalParameters:
|
|
MinimumRequiredVersion: 4.4.0
|
|
PrintLevel: 1
|
|
ForceRedoBenchmarkProblems: True
|
|
ForceRedoLibraryLogic: True
|
|
ForceRedoLibraryClient: True
|
|
CMakeBuildType: Release
|
|
EnqueuesPerSync: 1
|
|
SyncsPerBenchmark: 2
|
|
LibraryPrintDebug: False
|
|
NumElementsToValidate: 128
|
|
ValidationMaxToPrint: 4
|
|
ValidationPrintValids: False
|
|
ShortNames: False
|
|
MergeFiles: True
|
|
Platform: 0
|
|
Device: 0
|
|
KernelTime: True
|
|
PinClocks: True
|
|
SleepPercent: 200
|
|
DataInitTypeBeta : 0
|
|
|
|
BenchmarkProblems:
|
|
|
|
########################################
|
|
# NN
|
|
########################################
|
|
-
|
|
- # ProblemType
|
|
OperationType: GEMM
|
|
DataType: d
|
|
TransposeA: False
|
|
TransposeB: False
|
|
UseBeta: True
|
|
Batched: True
|
|
|
|
- # BenchmarkProblemSizeGroup - Standard
|
|
InitialSolutionParameters:
|
|
BenchmarkCommonParameters:
|
|
- KernelLanguage: ["Source"]
|
|
- EdgeType: ["ShiftPtr"]
|
|
- LoopTail: [True]
|
|
- WorkGroupMapping: [8]
|
|
- PrefetchLocalRead: [True]
|
|
- PrefetchGlobalRead: [True]
|
|
- VectorWidth: [-1]
|
|
ForkParameters:
|
|
- ThreadTile:
|
|
- [ 4, 4 ]
|
|
- WorkGroup:
|
|
- [ 16, 16, 1 ]
|
|
- DepthU: [ 8 ]
|
|
BenchmarkForkParameters:
|
|
JoinParameters:
|
|
BenchmarkJoinParameters:
|
|
BenchmarkFinalParameters:
|
|
- ProblemSizes:
|
|
- Range: [ [64], [64], [1], [128] ] #source for k<=128
|
|
|
|
- # BenchmarkProblemSizeGroup - Standard
|
|
InitialSolutionParameters:
|
|
BenchmarkCommonParameters:
|
|
- KernelLanguage: ["Assembly"]
|
|
- EdgeType: ["ShiftPtr"]
|
|
- LoopTail: [True]
|
|
- WorkGroupMapping: [8]
|
|
- PrefetchLocalRead: [True]
|
|
- PrefetchGlobalRead: [True]
|
|
- VectorWidth: [-1]
|
|
ForkParameters:
|
|
- ThreadTile:
|
|
- [ 4, 4 ]
|
|
- WorkGroup:
|
|
- [ 16, 16, 1 ]
|
|
- DepthU: [ 8 ]
|
|
BenchmarkForkParameters:
|
|
JoinParameters:
|
|
BenchmarkJoinParameters:
|
|
BenchmarkFinalParameters:
|
|
- ProblemSizes:
|
|
- Range: [ [64], [64], [1], [256] ]
|
|
|
|
- # BenchmarkProblemSizeGroup - M,N < VW
|
|
InitialSolutionParameters:
|
|
BenchmarkCommonParameters:
|
|
- KernelLanguage: ["Source"]
|
|
- EdgeType: ["ShiftPtr"]
|
|
- LoopTail: [True]
|
|
- WorkGroupMapping: [8]
|
|
- PrefetchLocalRead: [True]
|
|
- PrefetchGlobalRead: [True]
|
|
- VectorWidth: [-1]
|
|
ForkParameters:
|
|
- ThreadTile:
|
|
- [ 4, 4 ]
|
|
- WorkGroup:
|
|
- [ 16, 16, 1 ]
|
|
- DepthU: [ 4 ]
|
|
BenchmarkForkParameters:
|
|
JoinParameters:
|
|
BenchmarkJoinParameters:
|
|
BenchmarkFinalParameters:
|
|
- ProblemSizes:
|
|
- Range: [ [1], [1], [1], [128] ] #source for k<=128
|
|
- Range: [ [1], [64], [1], [128] ] #source for k<=128
|
|
- Range: [ [64], [1], [1], [128] ] #source for k<=128
|
|
|
|
- # BenchmarkProblemSizeGroup - M,N < VW
|
|
InitialSolutionParameters:
|
|
BenchmarkCommonParameters:
|
|
- KernelLanguage: ["Assembly"]
|
|
- EdgeType: ["ShiftPtr"]
|
|
- LoopTail: [True]
|
|
- WorkGroupMapping: [8]
|
|
- PrefetchLocalRead: [True]
|
|
- PrefetchGlobalRead: [True]
|
|
- VectorWidth: [-1]
|
|
ForkParameters:
|
|
- ThreadTile:
|
|
- [ 4, 4 ]
|
|
- WorkGroup:
|
|
- [ 16, 16, 1 ]
|
|
- DepthU: [ 4 ]
|
|
BenchmarkForkParameters:
|
|
JoinParameters:
|
|
BenchmarkJoinParameters:
|
|
BenchmarkFinalParameters:
|
|
- ProblemSizes:
|
|
- Range: [ [1], [1], [1], [256] ]
|
|
- Range: [ [1], [64], [1], [256] ]
|
|
- Range: [ [64], [1], [1], [256] ]
|
|
|
|
########################################
|
|
# NT
|
|
########################################
|
|
-
|
|
- # ProblemType
|
|
OperationType: GEMM
|
|
DataType: d
|
|
TransposeA: False
|
|
TransposeB: True
|
|
UseBeta: True
|
|
Batched: True
|
|
|
|
- # BenchmarkProblemSizeGroup - Standard
|
|
InitialSolutionParameters:
|
|
BenchmarkCommonParameters:
|
|
- KernelLanguage: ["Source"]
|
|
- EdgeType: ["ShiftPtr"]
|
|
- LoopTail: [True]
|
|
- WorkGroupMapping: [8]
|
|
- PrefetchLocalRead: [True]
|
|
- PrefetchGlobalRead: [True]
|
|
- VectorWidth: [-1]
|
|
ForkParameters:
|
|
- ThreadTile:
|
|
- [ 4, 4 ]
|
|
- WorkGroup:
|
|
- [ 16, 16, 1 ]
|
|
- DepthU: [ 8 ]
|
|
BenchmarkForkParameters:
|
|
JoinParameters:
|
|
BenchmarkJoinParameters:
|
|
BenchmarkFinalParameters:
|
|
- ProblemSizes:
|
|
- Range: [ [64], [64], [1], [128] ] # source for k<=128
|
|
|
|
- # BenchmarkProblemSizeGroup - Standard
|
|
InitialSolutionParameters:
|
|
BenchmarkCommonParameters:
|
|
- KernelLanguage: ["Assembly"]
|
|
- EdgeType: ["ShiftPtr"]
|
|
- LoopTail: [True]
|
|
- WorkGroupMapping: [8]
|
|
- PrefetchLocalRead: [True]
|
|
- PrefetchGlobalRead: [True]
|
|
- VectorWidth: [-1]
|
|
ForkParameters:
|
|
- ThreadTile:
|
|
- [ 4, 4 ]
|
|
- WorkGroup:
|
|
- [ 16, 16, 1 ]
|
|
- DepthU: [ 8 ]
|
|
BenchmarkForkParameters:
|
|
JoinParameters:
|
|
BenchmarkJoinParameters:
|
|
BenchmarkFinalParameters:
|
|
- ProblemSizes:
|
|
- Range: [ [64], [64], [1], [256] ]
|
|
|
|
- # BenchmarkProblemSizeGroup - M,N < VW
|
|
InitialSolutionParameters:
|
|
BenchmarkCommonParameters:
|
|
- KernelLanguage: ["Source"]
|
|
- EdgeType: ["ShiftPtr"]
|
|
- LoopTail: [True]
|
|
- WorkGroupMapping: [8]
|
|
- PrefetchLocalRead: [True]
|
|
- PrefetchGlobalRead: [True]
|
|
- VectorWidth: [-1]
|
|
ForkParameters:
|
|
- ThreadTile:
|
|
- [ 4, 4 ]
|
|
- WorkGroup:
|
|
- [ 16, 16, 1 ]
|
|
- DepthU: [ 4 ]
|
|
BenchmarkForkParameters:
|
|
JoinParameters:
|
|
BenchmarkJoinParameters:
|
|
BenchmarkFinalParameters:
|
|
- ProblemSizes:
|
|
- Range: [ [1], [1], [1], [128] ] # source for k<=128
|
|
- Range: [ [1], [64], [1], [128] ] # source for k<=128
|
|
- Range: [ [64], [1], [1], [128] ] # source for k<=128
|
|
|
|
- # BenchmarkProblemSizeGroup - M,N < VW
|
|
InitialSolutionParameters:
|
|
BenchmarkCommonParameters:
|
|
- KernelLanguage: ["Assembly"]
|
|
- EdgeType: ["ShiftPtr"]
|
|
- LoopTail: [True]
|
|
- WorkGroupMapping: [8]
|
|
- PrefetchLocalRead: [True]
|
|
- PrefetchGlobalRead: [True]
|
|
- VectorWidth: [-1]
|
|
ForkParameters:
|
|
- ThreadTile:
|
|
- [ 4, 4 ]
|
|
- WorkGroup:
|
|
- [ 16, 16, 1 ]
|
|
- DepthU: [ 4 ]
|
|
BenchmarkForkParameters:
|
|
JoinParameters:
|
|
BenchmarkJoinParameters:
|
|
BenchmarkFinalParameters:
|
|
- ProblemSizes:
|
|
- Range: [ [1], [1], [1], [256] ]
|
|
- Range: [ [1], [64], [1], [256] ]
|
|
- Range: [ [64], [1], [1], [256] ]
|
|
|
|
|
|
########################################
|
|
# TN
|
|
########################################
|
|
-
|
|
- # ProblemType
|
|
OperationType: GEMM
|
|
DataType: d
|
|
TransposeA: True
|
|
TransposeB: False
|
|
UseBeta: True
|
|
Batched: True
|
|
|
|
- # BenchmarkProblemSizeGroup - Standard
|
|
InitialSolutionParameters:
|
|
BenchmarkCommonParameters:
|
|
- KernelLanguage: ["Source"]
|
|
- EdgeType: ["ShiftPtr"]
|
|
- LoopTail: [True]
|
|
- WorkGroupMapping: [8]
|
|
- PrefetchLocalRead: [True]
|
|
- PrefetchGlobalRead: [True]
|
|
- VectorWidth: [-1]
|
|
ForkParameters:
|
|
- ThreadTile:
|
|
- [ 4, 4 ]
|
|
- WorkGroup:
|
|
- [ 16, 16, 1 ]
|
|
- DepthU: [ 8 ]
|
|
BenchmarkForkParameters:
|
|
JoinParameters:
|
|
BenchmarkJoinParameters:
|
|
BenchmarkFinalParameters:
|
|
- ProblemSizes:
|
|
- Range: [ [64], [64], [1], [128] ] # source for k<=128
|
|
|
|
- # BenchmarkProblemSizeGroup - Standard
|
|
InitialSolutionParameters:
|
|
BenchmarkCommonParameters:
|
|
- KernelLanguage: ["Assembly"]
|
|
- EdgeType: ["ShiftPtr"]
|
|
- LoopTail: [True]
|
|
- WorkGroupMapping: [8]
|
|
- PrefetchLocalRead: [True]
|
|
- PrefetchGlobalRead: [True]
|
|
- VectorWidth: [-1]
|
|
ForkParameters:
|
|
- ThreadTile:
|
|
- [ 4, 4 ]
|
|
- WorkGroup:
|
|
- [ 16, 16, 1 ]
|
|
- DepthU: [ 8 ]
|
|
BenchmarkForkParameters:
|
|
JoinParameters:
|
|
BenchmarkJoinParameters:
|
|
BenchmarkFinalParameters:
|
|
- ProblemSizes:
|
|
- Range: [ [64], [64], [1], [256] ]
|
|
|
|
- # BenchmarkProblemSizeGroup - M,N < VW
|
|
InitialSolutionParameters:
|
|
BenchmarkCommonParameters:
|
|
- KernelLanguage: ["Source"]
|
|
- EdgeType: ["ShiftPtr"]
|
|
- LoopTail: [True]
|
|
- WorkGroupMapping: [8]
|
|
- PrefetchLocalRead: [True]
|
|
- PrefetchGlobalRead: [True]
|
|
- VectorWidth: [-1]
|
|
ForkParameters:
|
|
- ThreadTile:
|
|
- [ 4, 4 ]
|
|
- WorkGroup:
|
|
- [ 16, 16, 1 ]
|
|
- DepthU: [ 4 ]
|
|
BenchmarkForkParameters:
|
|
JoinParameters:
|
|
BenchmarkJoinParameters:
|
|
BenchmarkFinalParameters:
|
|
- ProblemSizes:
|
|
- Range: [ [1], [1], [1], [128] ] # source for k<=128
|
|
- Range: [ [1], [64], [1], [128] ] # source for k<=128
|
|
- Range: [ [64], [1], [1], [128] ] # source for k<=128
|
|
|
|
- # BenchmarkProblemSizeGroup - M,N < VW
|
|
InitialSolutionParameters:
|
|
BenchmarkCommonParameters:
|
|
- KernelLanguage: ["Assembly"]
|
|
- EdgeType: ["ShiftPtr"]
|
|
- LoopTail: [True]
|
|
- WorkGroupMapping: [8]
|
|
- PrefetchLocalRead: [True]
|
|
- PrefetchGlobalRead: [True]
|
|
- VectorWidth: [-1]
|
|
ForkParameters:
|
|
- ThreadTile:
|
|
- [ 4, 4 ]
|
|
- WorkGroup:
|
|
- [ 16, 16, 1 ]
|
|
- DepthU: [ 4 ]
|
|
BenchmarkForkParameters:
|
|
JoinParameters:
|
|
BenchmarkJoinParameters:
|
|
BenchmarkFinalParameters:
|
|
- ProblemSizes:
|
|
- Range: [ [1], [1], [1], [256] ]
|
|
- Range: [ [1], [64], [1], [256] ]
|
|
- Range: [ [64], [1], [1], [256] ]
|
|
|
|
########################################
|
|
# TT
|
|
########################################
|
|
-
|
|
- # ProblemType
|
|
OperationType: GEMM
|
|
DataType: d
|
|
TransposeA: True
|
|
TransposeB: True
|
|
UseBeta: True
|
|
Batched: True
|
|
|
|
- # BenchmarkProblemSizeGroup - Standard
|
|
InitialSolutionParameters:
|
|
BenchmarkCommonParameters:
|
|
- KernelLanguage: ["Source"]
|
|
- EdgeType: ["ShiftPtr"]
|
|
- LoopTail: [True]
|
|
- WorkGroupMapping: [8]
|
|
- PrefetchLocalRead: [True]
|
|
- PrefetchGlobalRead: [True]
|
|
- VectorWidth: [-1]
|
|
ForkParameters:
|
|
- ThreadTile:
|
|
- [ 4, 4 ]
|
|
- WorkGroup:
|
|
- [ 16, 16, 1 ]
|
|
- DepthU: [ 8 ]
|
|
BenchmarkForkParameters:
|
|
JoinParameters:
|
|
BenchmarkJoinParameters:
|
|
BenchmarkFinalParameters:
|
|
- ProblemSizes:
|
|
- Range: [ [64], [64], [1], [128] ] # source for k<=128
|
|
|
|
- # BenchmarkProblemSizeGroup - Standard
|
|
InitialSolutionParameters:
|
|
BenchmarkCommonParameters:
|
|
- KernelLanguage: ["Assembly"]
|
|
- EdgeType: ["ShiftPtr"]
|
|
- LoopTail: [True]
|
|
- WorkGroupMapping: [8]
|
|
- PrefetchLocalRead: [True]
|
|
- PrefetchGlobalRead: [True]
|
|
- VectorWidth: [-1]
|
|
ForkParameters:
|
|
- ThreadTile:
|
|
- [ 4, 4 ]
|
|
- WorkGroup:
|
|
- [ 16, 16, 1 ]
|
|
- DepthU: [ 8 ]
|
|
BenchmarkForkParameters:
|
|
JoinParameters:
|
|
BenchmarkJoinParameters:
|
|
BenchmarkFinalParameters:
|
|
- ProblemSizes:
|
|
- Range: [ [64], [64], [1], [256] ]
|
|
|
|
- # BenchmarkProblemSizeGroup - M,N < VW
|
|
InitialSolutionParameters:
|
|
BenchmarkCommonParameters:
|
|
- KernelLanguage: ["Source"]
|
|
- EdgeType: ["ShiftPtr"]
|
|
- LoopTail: [True]
|
|
- WorkGroupMapping: [8]
|
|
- PrefetchLocalRead: [True]
|
|
- PrefetchGlobalRead: [True]
|
|
- VectorWidth: [-1]
|
|
ForkParameters:
|
|
- ThreadTile:
|
|
- [ 4, 4 ]
|
|
- WorkGroup:
|
|
- [ 16, 16, 1 ]
|
|
- DepthU: [ 4 ]
|
|
BenchmarkForkParameters:
|
|
JoinParameters:
|
|
BenchmarkJoinParameters:
|
|
BenchmarkFinalParameters:
|
|
- ProblemSizes:
|
|
- Range: [ [1], [1], [1], [128] ] # source for k<=128
|
|
- Range: [ [1], [64], [1], [128] ] # source for k<=128
|
|
- Range: [ [64], [1], [1], [128] ] # source for k<=128
|
|
|
|
- # BenchmarkProblemSizeGroup - M,N < VW
|
|
InitialSolutionParameters:
|
|
BenchmarkCommonParameters:
|
|
- KernelLanguage: ["Assembly"]
|
|
- EdgeType: ["ShiftPtr"]
|
|
- LoopTail: [True]
|
|
- WorkGroupMapping: [8]
|
|
- PrefetchLocalRead: [True]
|
|
- PrefetchGlobalRead: [True]
|
|
- VectorWidth: [-1]
|
|
ForkParameters:
|
|
- ThreadTile:
|
|
- [ 4, 4 ]
|
|
- WorkGroup:
|
|
- [ 16, 16, 1 ]
|
|
- DepthU: [ 4 ]
|
|
BenchmarkForkParameters:
|
|
JoinParameters:
|
|
BenchmarkJoinParameters:
|
|
BenchmarkFinalParameters:
|
|
- ProblemSizes:
|
|
- Range: [ [1], [1], [1], [256] ]
|
|
- Range: [ [1], [64], [1], [256] ]
|
|
- Range: [ [64], [1], [1], [256] ]
|
|
|
|
|
|
LibraryLogic:
|
|
# ScheduleName: "vega20"
|
|
# DeviceNames: ["Device 66a0", "Device 66a1", "Device 66a7", "Device 66af", "Vega 20"]
|
|
# ArchitectureName: "gfx906"
|
|
|
|
ScheduleName: "vega10"
|
|
DeviceNames: ["Device 6863", "Device 6862", "Device 687f", "Device 6860", "Device 6861", "Vega 10 XTX [Radeon Vega Frontier Edition]", "Vega [Radeon RX Vega]",
|
|
Vega, Device 6864, Device 686c]
|
|
ArchitectureName: "gfx900"
|
|
|
|
# ScheduleName: "mi25"
|
|
# DeviceNames: ["Device 6860"]
|
|
# ArchitectureName: "gfx900"
|
|
|
|
# ScheduleName: "r9nano"
|
|
# DeviceNames: ["Device 7300"]
|
|
# ArchitectureName: "gfx803"
|
|
|
|
# ScheduleName: "hip"
|
|
# DeviceNames: ["Device 0000"]
|
|
# ArchitectureName: "fallback"
|
|
|
|
LibraryClient:
|