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
513 lines
16 KiB
YAML
513 lines
16 KiB
YAML
TestParameters:
|
|
marks: [skip-gfx900, skip-gfx906, skip-gfx908, skip-gfx90a, skip-gfx940, skip-gfx941, skip-gfx1010, skip-gfx1011, skip-gfx1012, skip-gfx1030, skip-gfx1100, skip-gfx1101, skip-gfx1102, skip-gfx1200, skip-gfx1201, skip-gfx1250] # not supported by arch
|
|
|
|
# benchmark assembly and source kernels
|
|
GlobalParameters:
|
|
# MinimumRequiredVersion: 4.2.0
|
|
CMakeBuildType: Release
|
|
PrintLevel: 1
|
|
ForceRedoBenchmarkProblems: True
|
|
ForceRedoLibraryLogic: True
|
|
ForceRedoLibraryClient: True
|
|
EnqueuesPerSync: 1
|
|
SyncsPerBenchmark: 0
|
|
NumElementsToValidate: -1
|
|
ValidationMaxToPrint: 4
|
|
ValidationPrintValids: False
|
|
# PrintTensorD: 0x3
|
|
# PrintTensorC: 0x3
|
|
# PrintTensorB: 0x3
|
|
# PrintTensorA: 0x3 #0x1
|
|
# PrintTensorRef: 0x3
|
|
# ShortNames: False
|
|
# - Problem-Independent: 0=0, 1=1, 2=2, 3=rand, 4=Nan, 5=Infinity, 6=BadInput(Nan), 7=BadOutput(Inf), 16=RandomNarrow,
|
|
DataInitTypeA: 3 #12 #3
|
|
DataInitTypeB: 3 #13 #3
|
|
DataInitTypeC: 3 #3
|
|
DataInitTypeAlpha: 1
|
|
DataInitTypeBeta: 0
|
|
KernelTime: True
|
|
# PrintSolutionRejectionReason: True
|
|
|
|
BenchmarkProblems:
|
|
|
|
- # cgemm NN
|
|
- # ProblemType
|
|
OperationType: GEMM
|
|
DataType: C
|
|
DestDataType: C
|
|
ComputeDataType: C
|
|
UseBeta: True
|
|
Batched: True
|
|
TransposeA: False
|
|
TransposeB: False
|
|
ComplexConjugateA: False
|
|
ComplexConjugateB: False
|
|
|
|
- # BenchmarkProblemSizeGroup - Assembly
|
|
InitialSolutionParameters:
|
|
BenchmarkCommonParameters:
|
|
# - LoopTail: [True]
|
|
# - EdgeType: ["ShiftPtr"]
|
|
- KernelLanguage: ["Assembly"]
|
|
ForkParameters:
|
|
- MatrixInstruction:
|
|
- [16, 16, 4, 1, 1, 1, 1, 1, 1] #16x16
|
|
- [16, 16, 4, 1, 1, 4, 4, 2, 2] #128x128
|
|
- [16, 16, 4, 1, 1, 4, 2, 2, 2] #128x64
|
|
- [16, 16, 4, 1, 1, 2, 4, 2, 2] #64x128
|
|
- [16, 16, 4, 1, 1, 2, 2, 2, 2] #64x64
|
|
- [16, 16, 4, 1, 1, 1, 1, 2, 2] #32x32
|
|
- [16, 16, 4, 1, 1, 2, 2, 2, 1]
|
|
- [16, 16, 4, 1, 1, 2, 2, 1, 2]
|
|
- ScheduleIterAlg: [1, 3]
|
|
- MIArchVgpr: [false, true]
|
|
- 1LDSBuffer: [0, 1]
|
|
- GlobalSplitU: [1, 2, 4, 8]
|
|
- GlobalSplitUAlgorithm: [MultipleBuffer]
|
|
- PrefetchLocalRead: [1]
|
|
- PrefetchGlobalRead: [0, 2]
|
|
- 1LDSBuffer: [0, 1]
|
|
- DepthU: [4, 8, 16, 32]
|
|
- WorkGroup:
|
|
- [16, 4, 1]
|
|
- [16, 4, 2]
|
|
- [16, 4, 4]
|
|
# - ThreadTile:
|
|
##- [ 3, 5 ]
|
|
# - [ 2, 2 ]
|
|
# - [ 8, 8 ]
|
|
# - VectorWidth: [-1]
|
|
BenchmarkForkParameters:
|
|
JoinParameters:
|
|
BenchmarkJoinParameters:
|
|
BenchmarkFinalParameters:
|
|
- ProblemSizes:
|
|
# - Exact: [32, 32, 1, 8]
|
|
# - Exact: [16, 16, 1, 2]
|
|
# - Exact: [2048, 2048, 1, 256] #128x128(times16)
|
|
# - Exact: [1024, 1024, 1, 64] #64x64(times16)
|
|
# - Exact: [512, 512, 1, 32] #32x32
|
|
# - Exact: [64, 64, 1, 16]
|
|
# - Exact: [64, 64, 1, 128]
|
|
# - Exact: [4096, 4096, 1, 8192]
|
|
|
|
# - Range: [[16,37, 512],[16,57,512],[1],[1,1,64]]
|
|
- Range: [ [127,1,129], 0, [2], [63,1,64] ]
|
|
|
|
- # cgemm NT
|
|
- # ProblemType
|
|
OperationType: GEMM
|
|
DataType: C
|
|
DestDataType: C
|
|
ComputeDataType: C
|
|
UseBeta: True
|
|
Batched: True
|
|
TransposeA: False
|
|
TransposeB: True
|
|
ComplexConjugateA: False
|
|
ComplexConjugateB: False
|
|
|
|
- # BenchmarkProblemSizeGroup - Assembly
|
|
InitialSolutionParameters:
|
|
BenchmarkCommonParameters:
|
|
- KernelLanguage: ["Assembly"]
|
|
ForkParameters:
|
|
- MatrixInstruction:
|
|
- [16, 16, 4, 1, 1, 1, 1, 1, 1] #16x16
|
|
- [16, 16, 4, 1, 1, 4, 4, 2, 2] #128x128
|
|
- [16, 16, 4, 1, 1, 4, 2, 2, 2] #128x64
|
|
- [16, 16, 4, 1, 1, 2, 4, 2, 2] #64x128
|
|
- [16, 16, 4, 1, 1, 2, 2, 2, 2] #64x64
|
|
- [16, 16, 4, 1, 1, 1, 1, 2, 2] #32x32
|
|
- [16, 16, 4, 1, 1, 2, 2, 2, 1]
|
|
- [16, 16, 4, 1, 1, 2, 2, 1, 2]
|
|
- ScheduleIterAlg: [1, 3]
|
|
- MIArchVgpr: [false, true]
|
|
- 1LDSBuffer: [0, 1]
|
|
- GlobalSplitU: [1, 2, 4, 8]
|
|
- GlobalSplitUAlgorithm: [MultipleBuffer]
|
|
- PrefetchLocalRead: [1]
|
|
- PrefetchGlobalRead: [0, 2]
|
|
- 1LDSBuffer: [0, 1]
|
|
- DepthU: [4, 8, 16, 32]
|
|
- WorkGroup:
|
|
- [16, 4, 1]
|
|
- [16, 4, 2]
|
|
- [16, 4, 4]
|
|
BenchmarkForkParameters:
|
|
JoinParameters:
|
|
BenchmarkJoinParameters:
|
|
BenchmarkFinalParameters:
|
|
- ProblemSizes:
|
|
# - Exact: [16, 16, 1, 2]
|
|
# - Exact: [2048, 2048, 1, 256] #128x128(times16)
|
|
# - Exact: [1024, 1024, 1, 64] #64x64(times16)
|
|
# - Exact: [512, 512, 1, 32] #32x32
|
|
|
|
- Range: [ [127,1,129], 0, [2], [63,1,64] ]
|
|
|
|
- # cgemm TN
|
|
- # ProblemType
|
|
OperationType: GEMM
|
|
DataType: C
|
|
DestDataType: C
|
|
ComputeDataType: C
|
|
UseBeta: True
|
|
Batched: True
|
|
TransposeA: True
|
|
TransposeB: False
|
|
ComplexConjugateA: False
|
|
ComplexConjugateB: False
|
|
|
|
- # BenchmarkProblemSizeGroup - Assembly
|
|
InitialSolutionParameters:
|
|
BenchmarkCommonParameters:
|
|
- KernelLanguage: ["Assembly"]
|
|
ForkParameters:
|
|
- MatrixInstruction:
|
|
- [16, 16, 4, 1, 1, 1, 1, 1, 1] #16x16
|
|
- [16, 16, 4, 1, 1, 4, 4, 2, 2] #128x128
|
|
- [16, 16, 4, 1, 1, 4, 2, 2, 2] #128x64
|
|
- [16, 16, 4, 1, 1, 2, 4, 2, 2] #64x128
|
|
- [16, 16, 4, 1, 1, 2, 2, 2, 2] #64x64
|
|
- [16, 16, 4, 1, 1, 1, 1, 2, 2] #32x32
|
|
- [16, 16, 4, 1, 1, 2, 2, 2, 1]
|
|
- [16, 16, 4, 1, 1, 2, 2, 1, 2]
|
|
- ScheduleIterAlg: [1, 3]
|
|
- MIArchVgpr: [false, true]
|
|
- 1LDSBuffer: [0, 1]
|
|
- GlobalSplitU: [1, 2, 4, 8]
|
|
- GlobalSplitUAlgorithm: [MultipleBuffer]
|
|
- PrefetchLocalRead: [1]
|
|
- PrefetchGlobalRead: [0, 2]
|
|
- 1LDSBuffer: [0, 1]
|
|
- DepthU: [4, 8, 16, 32]
|
|
- WorkGroup:
|
|
- [16, 4, 1]
|
|
- [16, 4, 2]
|
|
- [16, 4, 4]
|
|
BenchmarkForkParameters:
|
|
JoinParameters:
|
|
BenchmarkJoinParameters:
|
|
BenchmarkFinalParameters:
|
|
- ProblemSizes:
|
|
# - Exact: [16, 16, 1, 2]
|
|
# - Exact: [2048, 2048, 1, 256] #128x128(times16)
|
|
# - Exact: [1024, 1024, 1, 64] #64x64(times16)
|
|
# - Exact: [512, 512, 1, 32] #32x32
|
|
|
|
- Range: [ [127,1,129], 0, [2], [63,1,64] ]
|
|
|
|
- # cgemm TT
|
|
- # ProblemType
|
|
OperationType: GEMM
|
|
DataType: C
|
|
DestDataType: C
|
|
ComputeDataType: C
|
|
UseBeta: True
|
|
Batched: True
|
|
TransposeA: True
|
|
TransposeB: True
|
|
ComplexConjugateA: False
|
|
ComplexConjugateB: False
|
|
|
|
- # BenchmarkProblemSizeGroup - Assembly
|
|
InitialSolutionParameters:
|
|
BenchmarkCommonParameters:
|
|
- KernelLanguage: ["Assembly"]
|
|
ForkParameters:
|
|
- MatrixInstruction:
|
|
- [16, 16, 4, 1, 1, 1, 1, 1, 1] #16x16
|
|
- [16, 16, 4, 1, 1, 4, 4, 2, 2] #128x128
|
|
- [16, 16, 4, 1, 1, 4, 2, 2, 2] #128x64
|
|
- [16, 16, 4, 1, 1, 2, 4, 2, 2] #64x128
|
|
- [16, 16, 4, 1, 1, 2, 2, 2, 2] #64x64
|
|
- [16, 16, 4, 1, 1, 1, 1, 2, 2] #32x32
|
|
- [16, 16, 4, 1, 1, 2, 2, 2, 1]
|
|
- [16, 16, 4, 1, 1, 2, 2, 1, 2]
|
|
- ScheduleIterAlg: [1, 3]
|
|
- MIArchVgpr: [false, true]
|
|
- 1LDSBuffer: [0, 1]
|
|
- GlobalSplitU: [1, 2, 4, 8]
|
|
- GlobalSplitUAlgorithm: [MultipleBuffer]
|
|
- PrefetchLocalRead: [1]
|
|
- PrefetchGlobalRead: [0, 2]
|
|
- 1LDSBuffer: [0, 1]
|
|
- DepthU: [4, 8, 16, 32]
|
|
- WorkGroup:
|
|
- [16, 4, 1]
|
|
- [16, 4, 2]
|
|
- [16, 4, 4]
|
|
BenchmarkForkParameters:
|
|
JoinParameters:
|
|
BenchmarkJoinParameters:
|
|
BenchmarkFinalParameters:
|
|
- ProblemSizes:
|
|
# - Exact: [16, 16, 1, 2]
|
|
# - Exact: [2048, 2048, 1, 256] #128x128(times16)
|
|
# - Exact: [1024, 1024, 1, 64] #64x64(times16)
|
|
# - Exact: [512, 512, 1, 32] #32x32
|
|
|
|
- Range: [ [127,1,129], 0, [2], [63,1,64] ]
|
|
|
|
- # cgemm NC
|
|
- # ProblemType
|
|
OperationType: GEMM
|
|
DataType: C
|
|
DestDataType: C
|
|
ComputeDataType: C
|
|
UseBeta: True
|
|
Batched: True
|
|
TransposeA: False
|
|
TransposeB: True
|
|
ComplexConjugateA: False
|
|
ComplexConjugateB: True
|
|
|
|
- # BenchmarkProblemSizeGroup - Assembly
|
|
InitialSolutionParameters:
|
|
BenchmarkCommonParameters:
|
|
- KernelLanguage: ["Assembly"]
|
|
ForkParameters:
|
|
- MatrixInstruction:
|
|
- [16, 16, 4, 1, 1, 1, 1, 1, 1] #16x16
|
|
- [16, 16, 4, 1, 1, 4, 4, 2, 2] #128x128
|
|
- [16, 16, 4, 1, 1, 4, 2, 2, 2] #128x64
|
|
- [16, 16, 4, 1, 1, 2, 4, 2, 2] #64x128
|
|
- [16, 16, 4, 1, 1, 2, 2, 2, 2] #64x64
|
|
- [16, 16, 4, 1, 1, 1, 1, 2, 2] #32x32
|
|
- [16, 16, 4, 1, 1, 2, 2, 2, 1]
|
|
- [16, 16, 4, 1, 1, 2, 2, 1, 2]
|
|
- ScheduleIterAlg: [1, 3]
|
|
- MIArchVgpr: [false, true]
|
|
- 1LDSBuffer: [0, 1]
|
|
- GlobalSplitU: [1, 2, 4, 8]
|
|
- GlobalSplitUAlgorithm: [MultipleBuffer]
|
|
- PrefetchLocalRead: [1]
|
|
- PrefetchGlobalRead: [0, 2]
|
|
- 1LDSBuffer: [0, 1]
|
|
- DepthU: [4, 8, 16, 32]
|
|
- WorkGroup:
|
|
- [16, 4, 1]
|
|
- [16, 4, 2]
|
|
- [16, 4, 4]
|
|
BenchmarkForkParameters:
|
|
JoinParameters:
|
|
BenchmarkJoinParameters:
|
|
BenchmarkFinalParameters:
|
|
- ProblemSizes:
|
|
# - Exact: [16, 16, 1, 2]
|
|
# - Exact: [2048, 2048, 1, 256] #128x128(times16)
|
|
# - Exact: [1024, 1024, 1, 64] #64x64(times16)
|
|
# - Exact: [512, 512, 1, 32] #32x32
|
|
|
|
- Range: [ [127,1,129], 0, [2], [63,1,64] ]
|
|
|
|
- # cgemm CN
|
|
- # ProblemType
|
|
OperationType: GEMM
|
|
DataType: C
|
|
DestDataType: C
|
|
ComputeDataType: C
|
|
UseBeta: True
|
|
Batched: True
|
|
TransposeA: True
|
|
TransposeB: False
|
|
ComplexConjugateA: True
|
|
ComplexConjugateB: False
|
|
|
|
- # BenchmarkProblemSizeGroup - Assembly
|
|
InitialSolutionParameters:
|
|
BenchmarkCommonParameters:
|
|
- KernelLanguage: ["Assembly"]
|
|
ForkParameters:
|
|
- MatrixInstruction:
|
|
- [16, 16, 4, 1, 1, 1, 1, 1, 1] #16x16
|
|
- [16, 16, 4, 1, 1, 4, 4, 2, 2] #128x128
|
|
- [16, 16, 4, 1, 1, 4, 2, 2, 2] #128x64
|
|
- [16, 16, 4, 1, 1, 2, 4, 2, 2] #64x128
|
|
- [16, 16, 4, 1, 1, 2, 2, 2, 2] #64x64
|
|
- [16, 16, 4, 1, 1, 1, 1, 2, 2] #32x32
|
|
- [16, 16, 4, 1, 1, 2, 2, 2, 1]
|
|
- [16, 16, 4, 1, 1, 2, 2, 1, 2]
|
|
- ScheduleIterAlg: [1, 3]
|
|
- MIArchVgpr: [false, true]
|
|
- 1LDSBuffer: [0, 1]
|
|
- GlobalSplitU: [1, 2, 4, 8]
|
|
- GlobalSplitUAlgorithm: [MultipleBuffer]
|
|
- PrefetchLocalRead: [1]
|
|
- PrefetchGlobalRead: [0, 2]
|
|
- 1LDSBuffer: [0, 1]
|
|
- DepthU: [4, 8, 16, 32]
|
|
- WorkGroup:
|
|
- [16, 4, 1]
|
|
- [16, 4, 2]
|
|
- [16, 4, 4]
|
|
BenchmarkForkParameters:
|
|
JoinParameters:
|
|
BenchmarkJoinParameters:
|
|
BenchmarkFinalParameters:
|
|
- ProblemSizes:
|
|
# - Exact: [16, 16, 1, 2]
|
|
# - Exact: [2048, 2048, 1, 256] #128x128(times16)
|
|
# - Exact: [1024, 1024, 1, 64] #64x64(times16)
|
|
# - Exact: [512, 512, 1, 32] #32x32
|
|
|
|
- Range: [ [127,1,129], 0, [2], [63,1,64] ]
|
|
|
|
- # cgemm TC
|
|
- # ProblemType
|
|
OperationType: GEMM
|
|
DataType: C
|
|
DestDataType: C
|
|
ComputeDataType: C
|
|
UseBeta: True
|
|
Batched: True
|
|
TransposeA: True
|
|
TransposeB: True
|
|
ComplexConjugateA: False
|
|
ComplexConjugateB: True
|
|
|
|
- # BenchmarkProblemSizeGroup - Assembly
|
|
InitialSolutionParameters:
|
|
BenchmarkCommonParameters:
|
|
- KernelLanguage: ["Assembly"]
|
|
ForkParameters:
|
|
- MatrixInstruction:
|
|
- [16, 16, 4, 1, 1, 1, 1, 1, 1] #16x16
|
|
- [16, 16, 4, 1, 1, 4, 4, 2, 2] #128x128
|
|
- [16, 16, 4, 1, 1, 4, 2, 2, 2] #128x64
|
|
- [16, 16, 4, 1, 1, 2, 4, 2, 2] #64x128
|
|
- [16, 16, 4, 1, 1, 2, 2, 2, 2] #64x64
|
|
- [16, 16, 4, 1, 1, 1, 1, 2, 2] #32x32
|
|
- [16, 16, 4, 1, 1, 2, 2, 2, 1]
|
|
- [16, 16, 4, 1, 1, 2, 2, 1, 2]
|
|
- ScheduleIterAlg: [1, 3]
|
|
- MIArchVgpr: [false, true]
|
|
- 1LDSBuffer: [0, 1]
|
|
- GlobalSplitU: [1, 2, 4, 8]
|
|
- GlobalSplitUAlgorithm: [MultipleBuffer]
|
|
- PrefetchLocalRead: [1]
|
|
- PrefetchGlobalRead: [0, 2]
|
|
- 1LDSBuffer: [0, 1]
|
|
- DepthU: [4, 8, 16, 32]
|
|
- WorkGroup:
|
|
- [16, 4, 1]
|
|
- [16, 4, 2]
|
|
- [16, 4, 4]
|
|
BenchmarkForkParameters:
|
|
JoinParameters:
|
|
BenchmarkJoinParameters:
|
|
BenchmarkFinalParameters:
|
|
- ProblemSizes:
|
|
# - Exact: [16, 16, 1, 2]
|
|
# - Exact: [2048, 2048, 1, 256] #128x128(times16)
|
|
# - Exact: [1024, 1024, 1, 64] #64x64(times16)
|
|
# - Exact: [512, 512, 1, 32] #32x32
|
|
|
|
- Range: [ [127,1,129], 0, [2], [63,1,64] ]
|
|
|
|
- # cgemm CT
|
|
- # ProblemType
|
|
OperationType: GEMM
|
|
DataType: C
|
|
DestDataType: C
|
|
ComputeDataType: C
|
|
UseBeta: True
|
|
Batched: True
|
|
TransposeA: True
|
|
TransposeB: True
|
|
ComplexConjugateA: True
|
|
ComplexConjugateB: False
|
|
|
|
- # BenchmarkProblemSizeGroup - Assembly
|
|
InitialSolutionParameters:
|
|
BenchmarkCommonParameters:
|
|
- KernelLanguage: ["Assembly"]
|
|
ForkParameters:
|
|
- MatrixInstruction:
|
|
- [16, 16, 4, 1, 1, 1, 1, 1, 1] #16x16
|
|
- [16, 16, 4, 1, 1, 4, 4, 2, 2] #128x128
|
|
- [16, 16, 4, 1, 1, 4, 2, 2, 2] #128x64
|
|
- [16, 16, 4, 1, 1, 2, 4, 2, 2] #64x128
|
|
- [16, 16, 4, 1, 1, 2, 2, 2, 2] #64x64
|
|
- [16, 16, 4, 1, 1, 1, 1, 2, 2] #32x32
|
|
- [16, 16, 4, 1, 1, 2, 2, 2, 1]
|
|
- [16, 16, 4, 1, 1, 2, 2, 1, 2]
|
|
- ScheduleIterAlg: [1, 3]
|
|
- MIArchVgpr: [false, true]
|
|
- 1LDSBuffer: [0, 1]
|
|
- GlobalSplitU: [1, 2, 4, 8]
|
|
- GlobalSplitUAlgorithm: [MultipleBuffer]
|
|
- PrefetchLocalRead: [1]
|
|
- PrefetchGlobalRead: [0, 2]
|
|
- 1LDSBuffer: [0, 1]
|
|
- DepthU: [4, 8, 16, 32]
|
|
- WorkGroup:
|
|
- [16, 4, 1]
|
|
- [16, 4, 2]
|
|
- [16, 4, 4]
|
|
BenchmarkForkParameters:
|
|
JoinParameters:
|
|
BenchmarkJoinParameters:
|
|
BenchmarkFinalParameters:
|
|
- ProblemSizes:
|
|
# - Exact: [16, 16, 1, 2]
|
|
# - Exact: [2048, 2048, 1, 256] #128x128(times16)
|
|
# - Exact: [1024, 1024, 1, 64] #64x64(times16)
|
|
# - Exact: [512, 512, 1, 32] #32x32
|
|
|
|
- Range: [ [127,1,129], 0, [2], [63,1,64] ]
|
|
|
|
- # cgemm CC
|
|
- # ProblemType
|
|
OperationType: GEMM
|
|
DataType: C
|
|
DestDataType: C
|
|
ComputeDataType: C
|
|
UseBeta: True
|
|
Batched: True
|
|
TransposeA: True
|
|
TransposeB: True
|
|
ComplexConjugateA: True
|
|
ComplexConjugateB: True
|
|
|
|
- # BenchmarkProblemSizeGroup - Assembly
|
|
InitialSolutionParameters:
|
|
BenchmarkCommonParameters:
|
|
- KernelLanguage: ["Assembly"]
|
|
ForkParameters:
|
|
- MatrixInstruction:
|
|
- [16, 16, 4, 1, 1, 1, 1, 1, 1] #16x16
|
|
- [16, 16, 4, 1, 1, 4, 4, 2, 2] #128x128
|
|
- [16, 16, 4, 1, 1, 4, 2, 2, 2] #128x64
|
|
- [16, 16, 4, 1, 1, 2, 4, 2, 2] #64x128
|
|
- [16, 16, 4, 1, 1, 2, 2, 2, 2] #64x64
|
|
- [16, 16, 4, 1, 1, 1, 1, 2, 2] #32x32
|
|
- [16, 16, 4, 1, 1, 2, 2, 2, 1]
|
|
- [16, 16, 4, 1, 1, 2, 2, 1, 2]
|
|
- ScheduleIterAlg: [1, 3]
|
|
- MIArchVgpr: [false, true]
|
|
- 1LDSBuffer: [0, 1]
|
|
- GlobalSplitU: [1, 2, 4, 8]
|
|
- GlobalSplitUAlgorithm: [MultipleBuffer]
|
|
- PrefetchLocalRead: [1]
|
|
- PrefetchGlobalRead: [0, 2]
|
|
- 1LDSBuffer: [0, 1]
|
|
- DepthU: [4, 8, 16, 32]
|
|
- WorkGroup:
|
|
- [16, 4, 1]
|
|
- [16, 4, 2]
|
|
- [16, 4, 4]
|
|
BenchmarkForkParameters:
|
|
JoinParameters:
|
|
BenchmarkJoinParameters:
|
|
BenchmarkFinalParameters:
|
|
- ProblemSizes:
|
|
# - Exact: [16, 16, 1, 2]
|
|
# - Exact: [2048, 2048, 1, 256] #128x128(times16)
|
|
# - Exact: [1024, 1024, 1, 64] #64x64(times16)
|
|
# - Exact: [512, 512, 1, 32] #32x32
|
|
|
|
- Range: [ [127,1,129], 0, [2], [63,1,64] ]
|