diff options
| author | Nick Kreeger <nick.kreeger@gmail.com> | 2022-04-23 20:14:48 -0500 |
|---|---|---|
| committer | Nick Kreeger <nick.kreeger@gmail.com> | 2022-04-23 20:14:48 -0500 |
| commit | 4620032ee304aae35a12b3e8927f0e27f527f4e1 (patch) | |
| tree | e172c9be943d8e2e941f62acca3a9845e3edac31 /mlir/benchmark | |
| parent | afa20aff6ef009889f9b75a2412fea09940eaf61 (diff) | |
| download | llvm-4620032ee304aae35a12b3e8927f0e27f527f4e1.tar.gz | |
Revert "[mlir][sparse] Expose SpareTensor passes as enums instead of opaque numbers for vectorization and parallelization options."
This reverts commit d59cf901cbae7991f7847eb038d825efff1221ad.
Build fails on NVIDIA Sparse tests:
https://lab.llvm.org/buildbot/#/builders/61/builds/25447
Diffstat (limited to 'mlir/benchmark')
| -rw-r--r-- | mlir/benchmark/python/common.py | 2 |
1 files changed, 1 insertions, 1 deletions
diff --git a/mlir/benchmark/python/common.py b/mlir/benchmark/python/common.py index 31875f16bfdc..da0ef20a1829 100644 --- a/mlir/benchmark/python/common.py +++ b/mlir/benchmark/python/common.py @@ -16,7 +16,7 @@ def setup_passes(mlir_module): """Setup pass pipeline parameters for benchmark functions. """ opt = ( - "parallelization-strategy=none" + "parallelization-strategy=0" " vectorization-strategy=0 vl=1 enable-simd-index32=False" ) pipeline = f"sparse-compiler{{{opt}}}" |