diff options
| author | Mikhail R. Gadelha <mikhail@igalia.com> | 2025-02-05 09:33:24 -0300 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2025-02-05 09:33:24 -0300 |
| commit | e78be316394509a665796a325603fe773346fbba (patch) | |
| tree | 59d341af4e43fca5b065519b172534a5b3d7739b /clang/lib/Analysis/ProgramPoint.cpp | |
| parent | f77f777f35c4d60573c75701eda8ddbaee070c21 (diff) | |
| download | llvm-e78be316394509a665796a325603fe773346fbba.zip llvm-e78be316394509a665796a325603fe773346fbba.tar.gz llvm-e78be316394509a665796a325603fe773346fbba.tar.bz2 | |
[RISCV] Added cost model for fmuladd (#125683)
This patch updates the cost model for fmuladd on vector types to scale with LMUL. This was found when analyzing a hot loop in 519.lbm_r that was unprofitably vectorized, but doesn't directly impact that case and is split off so it doesn't get forgotten.
Unlike other FP arithmetic ops, it's not scaled by 2 because the scalar cost isn't scaled by 2.
Diffstat (limited to 'clang/lib/Analysis/ProgramPoint.cpp')
0 files changed, 0 insertions, 0 deletions