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
69 lines
1.9 KiB
YAML
69 lines
1.9 KiB
YAML
# A config to generate a fast kernel for large DGEMMs
|
|
GlobalParameters:
|
|
EnqueuesPerSync: 1
|
|
LibraryPrintDebug: False
|
|
NumElementsToValidate: 0
|
|
ValidationMaxToPrint: 4
|
|
ValidationPrintValids: False
|
|
KernelTime: True
|
|
#PinClocks: True
|
|
SleepPercent: 0
|
|
DataInitTypeBeta : 0
|
|
PrintSolutionRejectionReason: 1
|
|
ClientArgs: "--stride_b 0"
|
|
|
|
BenchmarkProblems:
|
|
-
|
|
- # ProblemType
|
|
OperationType: GEMM
|
|
DataType: s
|
|
TransposeA: False
|
|
TransposeB: True
|
|
UseBeta: True
|
|
Batched: True
|
|
|
|
- # BenchmarkProblemSizeGroup - Standard
|
|
InitialSolutionParameters:
|
|
BenchmarkCommonParameters:
|
|
- KernelLanguage: ["Assembly"]
|
|
- EdgeType: ["ShiftPtr"]
|
|
ForkParameters:
|
|
- FractionalLoad: [1]
|
|
- PrefetchGlobalRead: [ False, True ]
|
|
- PrefetchLocalRead: [ True]
|
|
- ThreadTile:
|
|
- [ 4, 4 ]
|
|
- [ 7, 8 ]
|
|
- [ 9, 8 ]
|
|
- [ 5, 8 ]
|
|
- [ 8, 4 ]
|
|
- [ 8, 8 ]
|
|
- [ 10, 6 ]
|
|
- [ 6, 10 ]
|
|
- WorkGroup:
|
|
#- [ 16, 8, 2 ]
|
|
#- [ 16, 4, 4 ]
|
|
- [ 16, 8, 1 ]
|
|
- [ 8, 32, 1 ]
|
|
- [ 16, 16, 1 ]
|
|
- [ 32, 8, 1 ]
|
|
- WorkGroupMapping: [1,8,64]
|
|
- DepthU: [ 8,16,32 ]
|
|
- VectorWidth: [-1] # use biggest available
|
|
- GlobalReadVectorWidth: [1,-1] # 1 allows D2LDS
|
|
- LdsPadA: [0, -1 ]
|
|
- LdsPadB: [0, -1 ]
|
|
- AssertSummationElementMultiple: [4]
|
|
- AssertFree0ElementMultiple: [4]
|
|
- AssertFree1ElementMultiple: [4]
|
|
BenchmarkForkParameters:
|
|
BenchmarkJoinParameters:
|
|
BenchmarkFinalParameters:
|
|
- ProblemSizes:
|
|
# This example is from ResNet50 1x1 conv layer batch64, suffers from granularity loss:
|
|
- Exact: [192, 1024, 64, 256 ] # much higher perf with smaller size
|
|
- Exact: [196, 1024, 64, 256 ] # granularity loss
|
|
|
|
|
|
########################################
|