diff options
| author | Matthias Springer <springerm@google.com> | 2023-02-13 16:35:47 +0100 |
|---|---|---|
| committer | Matthias Springer <springerm@google.com> | 2023-02-13 16:52:26 +0100 |
| commit | 00a5ae12448e6f33e40c38afd640eafdb7dab212 (patch) | |
| tree | f74a487a17de11f3a06dde21dc6e95f447f8ed6b /llvm/lib/Target/RISCV/Disassembler/RISCVDisassembler.cpp | |
| parent | 95526930da6c00f6f12816d1f99bdf99980c387f (diff) | |
| download | llvm-00a5ae12448e6f33e40c38afd640eafdb7dab212.zip llvm-00a5ae12448e6f33e40c38afd640eafdb7dab212.tar.gz llvm-00a5ae12448e6f33e40c38afd640eafdb7dab212.tar.bz2 | |
[mlir][bufferization] Better propagation of bufferizesToMemoryWrite through regions
`bufferizesToMemoryWrite(OpResult)` looks for OpOperands that bufferize to memory writes inside the region of the defining op (if it has one). Currently, if the reverse use-def chain stops at any value inside of the region, the OpResult is considered to bufferize to a memory write.
It is always safe to have false positives among `bufferizesToMemoryWrite`, so the previous implementation is also correct. However, it can lead to additional buffer copies.
Differential Revision: https://reviews.llvm.org/D142223
Diffstat (limited to 'llvm/lib/Target/RISCV/Disassembler/RISCVDisassembler.cpp')
0 files changed, 0 insertions, 0 deletions