diff options
| author | Matthias Springer <springerm@google.com> | 2022-06-09 21:49:37 +0200 |
|---|---|---|
| committer | Matthias Springer <springerm@google.com> | 2022-06-09 21:55:52 +0200 |
| commit | 3b2004e16b30e60ab1e3eaca3398e303270cb666 (patch) | |
| tree | a7c94b9d3321e385338f9100f7e6bcca59befdde /llvm/lib/Object/COFFObjectFile.cpp | |
| parent | 6d890a0fb8b1962cf7b58e9e16ff4545f1f2b84f (diff) | |
| download | llvm-3b2004e16b30e60ab1e3eaca3398e303270cb666.zip llvm-3b2004e16b30e60ab1e3eaca3398e303270cb666.tar.gz llvm-3b2004e16b30e60ab1e3eaca3398e303270cb666.tar.bz2 | |
[mlir][bufferization] Add TensorCopyInsertion pass
This pass runs the One-Shot Analysis to find out which tensor OpOperands must bufferize out-of-place. It then rewrites those tensor OpOperands to explicit allocations with a copy in the form of `bufferization.alloc_tensor`. The resulting IR can then be bufferized without having to care about read-after-write conflicts.
This change makes it possible to connect One-Shot Analysis to other bufferizations such as the sparse compiler.
Differential Revision: https://reviews.llvm.org/D126573
Diffstat (limited to 'llvm/lib/Object/COFFObjectFile.cpp')
0 files changed, 0 insertions, 0 deletions