diff options
author | MaheshRavishankar <1663364+MaheshRavishankar@users.noreply.github.com> | 2025-04-15 14:10:18 -0700 |
---|---|---|
committer | GitHub <noreply@github.com> | 2025-04-15 14:10:18 -0700 |
commit | 0f3e460e06e03ce37445546457a16d6f1eee1e21 (patch) | |
tree | e9bf2ebb992bb23a8264374d997598b18098b2ce /clang/lib/Analysis/ThreadSafety.cpp | |
parent | ddb12674300eb1af5e6945b5447e7bff7cff4cd8 (diff) | |
download | llvm-0f3e460e06e03ce37445546457a16d6f1eee1e21.zip llvm-0f3e460e06e03ce37445546457a16d6f1eee1e21.tar.gz llvm-0f3e460e06e03ce37445546457a16d6f1eee1e21.tar.bz2 |
[mlir][Tensor] Generalize the pattern to swap `tensor.collapse_shape` -> `tensor.expand_shape`. (#133819)
The current patterns compared the reassocation indices for the two ops
and failed if neither of them were of size 1. This patch relaxes this
restriction by handling a new case where the reassociation indices might
be of the same size.
Also generalizes to cases where when generating the swapped
`tensor.expand_shape` -> `tensor.collapse_shape` if one of them is
degenerate, those are not generated.
Signed-off-by: MaheshRavishankar <mahesh.ravishankar@gmail.com>
Diffstat (limited to 'clang/lib/Analysis/ThreadSafety.cpp')
0 files changed, 0 insertions, 0 deletions