diff options
| author | Vikram Hegde <115221833+vikramRH@users.noreply.github.com> | 2025-01-17 11:09:39 +0530 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2025-01-17 11:09:39 +0530 |
| commit | 225fc4f3562002cc77e68340c7077442ca6d4d20 (patch) | |
| tree | 66ed11d91fb7c99ca6b9b86ebe74e8aebf02c6fd /llvm/lib/ProfileData/Coverage/CoverageMapping.cpp | |
| parent | f999b11e68c6377f718d0f05988af9852ca386ba (diff) | |
| download | llvm-225fc4f3562002cc77e68340c7077442ca6d4d20.zip llvm-225fc4f3562002cc77e68340c7077442ca6d4d20.tar.gz llvm-225fc4f3562002cc77e68340c7077442ca6d4d20.tar.bz2 | |
[AMDGPU][SDAG] Try folding "lshr i64 + mad" to "mad_u64_u32" (#119218)
The intention is to use a "copy" instead of a "sub" to handle the high
parts of 64-bit multiply for this specific case.
This unlocks copy prop use cases where the copy can be reused by later
multiply+add sequences if possible.
Fixes: SWDEV-487672, SWDEV-487669
Diffstat (limited to 'llvm/lib/ProfileData/Coverage/CoverageMapping.cpp')
0 files changed, 0 insertions, 0 deletions