diff options
| author | Matthias Springer <me@m-sp.org> | 2023-07-31 15:16:28 +0200 |
|---|---|---|
| committer | Matthias Springer <me@m-sp.org> | 2023-07-31 15:20:00 +0200 |
| commit | aba0ef70597980d84e31f41e09cdbd00ea65d9fd (patch) | |
| tree | 2eb52c58e95deda9a49286864b22139e8a2f640d /mlir/lib/Conversion/VectorToGPU/VectorToGPU.cpp | |
| parent | 09156b36c65def7d1954e78b70408b4e743d417e (diff) | |
[mlir][bufferization] Support casts in EmptyTensorElimination
EmptyTensorElimination is a pre-bufferization transformation that replaces "tensor.empty" ops with "tensor.extract_slice" ops. This revision adds support for cases where the input IR contains "tensor.cast" ops.
Differential Revision: https://reviews.llvm.org/D156167
Diffstat (limited to 'mlir/lib/Conversion/VectorToGPU/VectorToGPU.cpp')
0 files changed, 0 insertions, 0 deletions