diff options
| author | Kojo Acquah <KoolJBlack@users.noreply.github.com> | 2024-03-19 10:09:33 -0700 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2024-03-19 13:09:33 -0400 |
| commit | fe84369cc6759194e006f3f624a064bce13c84d4 (patch) | |
| tree | 7b3c2cd4511a83862860db403f2bda113d5e4ef1 /llvm/lib/CodeGen | |
| parent | ab76052fa9331f418d7911cafefabd4dd0c1941e (diff) | |
| download | llvm-fe84369cc6759194e006f3f624a064bce13c84d4.zip llvm-fe84369cc6759194e006f3f624a064bce13c84d4.tar.gz llvm-fe84369cc6759194e006f3f624a064bce13c84d4.tar.bz2 | |
[mlir][ArmNeon] Implements unrolling patterns for LowerContractionToSMMLAPattern (#84848)
This patch updates `LowerContractionToSMMLAPattern` to unroll larger vector contracts into multiple smmla instructions.
Now accepts up to [8,8,8] tiles (previously only [2,2,8]). The N/M dimensions must be powers of 2. `vector.extract_strided_slice`/`vector.insert_strided_slice` divides the contract into tiles to be processed in a row.
Diffstat (limited to 'llvm/lib/CodeGen')
0 files changed, 0 insertions, 0 deletions