diff options
| author | Stephan Herhut <herhut@google.com> | 2021-05-18 15:16:08 +0200 |
|---|---|---|
| committer | Stephan Herhut <herhut@google.com> | 2021-05-21 15:23:28 +0200 |
| commit | 884a6291f0b995579d2cd203bfdc5b6aa427be31 (patch) | |
| tree | 368cac87178b31f48659d168cf30fc718ff6cb8b /llvm/lib/CodeGen/MachineFunctionPass.cpp | |
| parent | 28844212fe4054784549a1f552b78fe675fe4ebf (diff) | |
| download | llvm-884a6291f0b995579d2cd203bfdc5b6aa427be31.zip llvm-884a6291f0b995579d2cd203bfdc5b6aa427be31.tar.gz llvm-884a6291f0b995579d2cd203bfdc5b6aa427be31.tar.bz2 | |
[mlir][linalg] Add scalar operands inlining pattern
This pattern inlines operands to a linalg.generic operation that use a constant
index and hence are loop-invariant scalars. This reduces the number of
linalg.generic operands and unlocks some canonicalizations that rely on seeing
an explicit tensor.extract.
Differential Revision: https://reviews.llvm.org/D102682
Diffstat (limited to 'llvm/lib/CodeGen/MachineFunctionPass.cpp')
0 files changed, 0 insertions, 0 deletions