diff options
| author | Matthias Springer <me@m-sp.org> | 2023-08-25 08:31:58 +0200 |
|---|---|---|
| committer | Matthias Springer <me@m-sp.org> | 2023-08-25 08:34:05 +0200 |
| commit | 79ff70fda223f22cf409301b0f0c2bf451dbb6b3 (patch) | |
| tree | b52efa80fb22033802d5e6bd37dbc048da75290d /llvm/lib/Transforms/Utils/BasicBlockUtils.cpp | |
| parent | 45d20338281e4fd17a773c067f28f839db0f9b8e (diff) | |
| download | llvm-79ff70fda223f22cf409301b0f0c2bf451dbb6b3.zip llvm-79ff70fda223f22cf409301b0f0c2bf451dbb6b3.tar.gz llvm-79ff70fda223f22cf409301b0f0c2bf451dbb6b3.tar.bz2 | |
[mlir][sparse] Better error handling when bufferizing sparse_tensor ops
sparse_tensor ops cannot be bufferized with One-Shot Bufferize. (They can only be analyzed.) The sparse compiler does the actual lowering to memref. Produce a proper error message instead of crashing.
This fixes #61311.
Differential Revision: https://reviews.llvm.org/D158728
Diffstat (limited to 'llvm/lib/Transforms/Utils/BasicBlockUtils.cpp')
0 files changed, 0 insertions, 0 deletions