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
72 lines
2.3 KiB
YAML
72 lines
2.3 KiB
YAML
# A config to generate a fast kernel for large DGEMMs
|
|
GlobalParameters:
|
|
EnqueuesPerSync: 30
|
|
LibraryPrintDebug: False
|
|
NumElementsToValidate: 000
|
|
KernelTime: True
|
|
#PinClocks: True
|
|
SleepPercent: 0
|
|
DataInitTypeBeta : 0
|
|
PrintSolutionRejectionReason: 0
|
|
PrintWinnersOnly: 1
|
|
|
|
BenchmarkProblems:
|
|
########################################
|
|
# NT - standard
|
|
########################################
|
|
-
|
|
- # ProblemType
|
|
OperationType: TensorContraction
|
|
IndexAssignmentsA: [ 3, 0, 2]
|
|
IndexAssignmentsB: [ 3, 1, 2]
|
|
DataType: s
|
|
UseBeta: False
|
|
NumIndicesC: 2
|
|
|
|
- # BenchmarkProblemSizeGroup - Standard
|
|
InitialSolutionParameters:
|
|
BenchmarkCommonParameters:
|
|
- KernelLanguage: ["Assembly"]
|
|
- EdgeType: ["ShiftPtr"]
|
|
ForkParameters:
|
|
- PrefetchLocalRead: [False,True]
|
|
- PrefetchGlobalRead: [False,True]
|
|
- ThreadTile:
|
|
- [ 4, 4 ]
|
|
- [ 8, 4 ]
|
|
- [ 4, 8 ]
|
|
- [ 8, 8 ]
|
|
- WorkGroup:
|
|
#- [ 4, 16, 1 ]
|
|
- [ 8, 8, 1 ]
|
|
- [ 8, 16, 1 ]
|
|
- [ 8, 32, 1 ]
|
|
#- [ 16, 32, 1 ]
|
|
#- [ 32, 16, 1 ]
|
|
#- [ 16, 16, 1 ]
|
|
- WorkGroupMapping: [1,8,64]
|
|
- StaggerU: [0,32]
|
|
- DepthU: [ 8,16 ]
|
|
- VectorWidth: [1,-1]
|
|
- FractionalLoad: [0]
|
|
- AssertSummationElementMultiple: [4]
|
|
- AssertFree0ElementMultiple: [4]
|
|
- AssertFree1ElementMultiple: [4]
|
|
#- GlobalSplitU: [1,2,4,8, 16, 32]
|
|
- GlobalSplitU: [16, 32, 48, 56, 64, 80, 128]
|
|
#- DisableKernelPieces: [1]
|
|
BenchmarkForkParameters:
|
|
BenchmarkJoinParameters:
|
|
BenchmarkFinalParameters:
|
|
- ProblemSizes:
|
|
# ./rocblas-bench -f gemm_ex --transposeA T --transposeB N -m 64 -n 256 -k 3136 --alpha 1 --a_type f32_r --lda 3136 --b_type f32_r --ldb 3136 --beta 1 --c_type f32_r --ldc 64 --d_type f32_r --ldd 64 --compute_type f32_r --algo 0 --solution_index 0 --flags 0
|
|
- Exact: [64, 256, 64, 3136]
|
|
- Exact: [64, 256, 2, 100352]
|
|
|
|
#- Range: [ [192], [1024], [64], [256] ]
|
|
#- Range: [ [192], [1024], [64], [272] ]
|
|
#- Range: [ [192], [1024], [64], [240] ]
|
|
#- Range: [ [256,256,1024], [1024], [64], [256] ] # sweep
|
|
|
|
########################################
|