diff options
| author | Christopher Bate <cbate@nvidia.com> | 2025-03-12 22:19:01 -0600 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2025-03-12 22:19:01 -0600 |
| commit | 3438dfc7ff8863bdd8c34e41d0cade5ca4581891 (patch) | |
| tree | 1208f973ebc0b13da9c9a0db1bf08dbdeffb16be /llvm/lib/CodeGen/DFAPacketizer.cpp | |
| parent | 376e3b62cd36cabf4235e085cd13df05c2bd754b (diff) | |
| download | llvm-3438dfc7ff8863bdd8c34e41d0cade5ca4581891.zip llvm-3438dfc7ff8863bdd8c34e41d0cade5ca4581891.tar.gz llvm-3438dfc7ff8863bdd8c34e41d0cade5ca4581891.tar.bz2 | |
[mlir][tensor] Fix bufferization interface for 'tensor.reshape' (#128590)
Previously, the BufferizableOpInterface implementation for
'tensor.reshape'
listed the 'shape' operand as an alias for the result tensor, causing
unnecessary conflicts with ops that "write" to the shape operand.
Diffstat (limited to 'llvm/lib/CodeGen/DFAPacketizer.cpp')
0 files changed, 0 insertions, 0 deletions