diff options
| author | Philip Reames <preames@rivosinc.com> | 2022-07-08 10:09:49 -0700 |
|---|---|---|
| committer | Philip Reames <listmail@philipreames.com> | 2022-07-08 10:18:21 -0700 |
| commit | 264018d764e6b23690df900680b83df93951beb3 (patch) | |
| tree | afa0b534b6971c09eb9550cb1c3eff1182788cdc /llvm/lib/ProfileData/Coverage/CoverageMappingReader.cpp | |
| parent | a84e1e6c0d5d742db47d89ff6bdab19c3ccff779 (diff) | |
| download | llvm-264018d764e6b23690df900680b83df93951beb3.zip llvm-264018d764e6b23690df900680b83df93951beb3.tar.gz llvm-264018d764e6b23690df900680b83df93951beb3.tar.bz2 | |
[RISCV] Mark vsadd(u)_vl as commutable
This allows fixed length vectors involving splats on the LHS to commute into the _vx form of the instruction. Oddly, the generic canonicalization rules appear to catch the scalable vector cases. I haven't fully dug in to understand why, but I suspect it's because of a difference in how we represent splats (splat_vector vs build_vector).
Differential Revision: https://reviews.llvm.org/D129302
Diffstat (limited to 'llvm/lib/ProfileData/Coverage/CoverageMappingReader.cpp')
0 files changed, 0 insertions, 0 deletions