diff options
| author | Nicolas Vasilache <nicolas.vasilache@gmail.com> | 2020-10-13 12:30:08 +0000 |
|---|---|---|
| committer | Nicolas Vasilache <nicolas.vasilache@gmail.com> | 2020-10-13 16:36:56 +0000 |
| commit | 6121117484ddd7c5a03b40004a8bba58506ce9d0 (patch) | |
| tree | 8d3ac6c79bd56becfc23224a013bf08bab133820 /clang/lib/Frontend/CompilerInvocation.cpp | |
| parent | ab55897817cc09113a9729d4ed907e13aa0386ff (diff) | |
| download | llvm-6121117484ddd7c5a03b40004a8bba58506ce9d0.zip llvm-6121117484ddd7c5a03b40004a8bba58506ce9d0.tar.gz llvm-6121117484ddd7c5a03b40004a8bba58506ce9d0.tar.bz2 | |
[mlir][Linalg] Fix TensorConstantOp bufferization in Linalg.
TensorConstantOp bufferization currently uses the vector dialect to store constant data into memory.
Due to natural vector size and alignment properties, this is problematic with n>1-D vectors whose most minor dimension is not naturally aligned.
Instead, this revision linearizes the constant and introduces a linalg.reshape to go back to the desired shape.
Still this is still to be considered a workaround and a better longer term solution will probably involve `llvm.global`.
Differential Revision: https://reviews.llvm.org/D89311
Diffstat (limited to 'clang/lib/Frontend/CompilerInvocation.cpp')
0 files changed, 0 insertions, 0 deletions