Files
TheRock/rocm-libraries/shared/tensile/Tensile/Tests/bugs/swizzlec1.yaml
T
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
Flatten subprojects into a single base monorepo
2026-09-02 16:34:47 -07:00

53 lines
1.8 KiB
YAML

BenchmarkProblems:
- - DataType: s
IndexAssignmentsA: [3, 1, 2]
IndexAssignmentsB: [3, 0, 2]
NumIndicesC: 3
OperationType: TensorContraction
#SetConstStrideA:
#- [3, 1]
#SetConstStrideB:
#- [2, 0]
#- [3, 1]
UseBeta: false
UseInitialStridesAB: false
- BenchmarkCommonParameters:
- EdgeType: [ShiftPtr]
BenchmarkFinalParameters:
- ProblemSizes:
- Exact: [16, 16, 1, 8] # passes on source and asm
- Exact: [16, 32, 1, 8] # fails - multiple tiles.
- Exact: [32, 16, 1, 8] # fails - multiple tiles.
BenchmarkForkParameters: null
BenchmarkJoinParameters: null
ForkParameters:
- PrefetchGlobalRead: [0]
- KernelLanguage: [Source,Assembly]
- ThreadTile:
- [2, 2]
- WorkGroup:
- [8, 8, 1]
- DepthU: [8]
- GlobalReadVectorWidth: [1]
- VectorWidth: [1]
- FractionalLoad: [0]
InitialSolutionParameters: null
JoinParameters: null
GlobalParameters: {CMakeBuildType: Release, EnqueuesPerSync: 1, ForceRedoBenchmarkProblems: true,
ForceRedoLibraryClient: true, ForceRedoLibraryLogic: true, KernelTime: true, LibraryPrintDebug: false,
MergeFiles: true, MinimumRequiredVersion: 4.2.0, NumElementsToValidate: 1000,
ShortNames: false, SolutionSelectionAlg: 1, SyncsPerBenchmark: 1,
ValidationMaxToPrint: 4, ValidationPrintValids: false,
DataInitTypeAB: 1,
}
# Case has free index for A is 1 and for B is 0.
# So does interesting transpose in the output space.
# Bug appears to be in the store path with second work-group, set AB=1 still fails.
# Check usage of WorkGroup0/1 and consistency of output space assignment in reads and stores.
# store code takes WG1 and
#
# Check cstrides0/1 written by host code - seems ok, likely WG-related problem.
#
# Diff code with slightly different mapping