diff options
| author | Kunwar Grover <groverkss@gmail.com> | 2024-10-22 15:50:16 +0100 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2024-10-22 15:50:16 +0100 |
| commit | 1004865f1ca41a9581da8747f34b29862d3ebc3d (patch) | |
| tree | 6339111e0135a61bb93ec0fd219f89c334afbba1 /clang/lib/Basic/Module.cpp | |
| parent | 4c697f7037b719b9ed1fa3bcaa68c4a4219c2fc5 (diff) | |
| download | llvm-1004865f1ca41a9581da8747f34b29862d3ebc3d.zip llvm-1004865f1ca41a9581da8747f34b29862d3ebc3d.tar.gz llvm-1004865f1ca41a9581da8747f34b29862d3ebc3d.tar.bz2 | |
[mlir][Vector] Support 0-d vectors natively in TransferOpReduceRank (#112907)
Since
https://github.com/llvm/llvm-project/commit/ddf2d62c7dddf1e4a9012d96819ff1ed005fbb05
, 0-d vectors are supported in VectorType. This patch removes 0-d vector
handling with scalars for the TransferOpReduceRank pattern. This pattern
specifically introduces tensor.extract_slice during vectorization,
causing vectorization to not fold transfer_read/transfer_write slices
properly. The changes in vectorization test files reflect this.
There are other places where lowering patterns are still side-stepping
from handling 0-d vectors properly, by turning them into scalars, but
this patch only focuses on the vector.transfer_x patterns.
Diffstat (limited to 'clang/lib/Basic/Module.cpp')
0 files changed, 0 insertions, 0 deletions