diff options
| author | Nicolas Vasilache <ntv@google.com> | 2020-03-13 16:32:27 -0400 |
|---|---|---|
| committer | Nicolas Vasilache <ntv@google.com> | 2020-03-13 16:33:23 -0400 |
| commit | bbf3ef85411660e2cebef8d1b633c35d9b179948 (patch) | |
| tree | 4db992600e5300fe8049beda17a15de75c1647b2 /llvm/tools/llvm-objdump/llvm-objdump.cpp | |
| parent | 015b640be4c6ce35969be5c38d628feeadb48634 (diff) | |
| download | llvm-bbf3ef85411660e2cebef8d1b633c35d9b179948.zip llvm-bbf3ef85411660e2cebef8d1b633c35d9b179948.tar.gz llvm-bbf3ef85411660e2cebef8d1b633c35d9b179948.tar.bz2 | |
[mlir][Vector]Lower vector.contract to llvm.intr.matrix_multiply
Summary:
This revision adds lowering of vector.contract to llvm.intr.matrix_multiply.
Note that there is currently a mismatch between the MLIR vector dialect which
expects row-major layout and the LLVM matrix intrinsics which expect column
major layout.
As a consequence, we currently only match a vector.contract with indexing maps
that express column-major matrix multiplication.
Other cases would require additional transposes and it is better to wait for
LLVM intrinsics to provide a per-operation attribute that would specify which
layout is expected.
A separate integration test, not submitted to MLIR core, has independently
verified that correct execution occurs on a 2x2x2 matrix multiplication.
Differential Revision: https://reviews.llvm.org/D76014
Diffstat (limited to 'llvm/tools/llvm-objdump/llvm-objdump.cpp')
0 files changed, 0 insertions, 0 deletions