diff options
| author | Jay Foad <jay.foad@amd.com> | 2022-02-18 17:24:50 +0000 |
|---|---|---|
| committer | Jay Foad <jay.foad@amd.com> | 2022-05-16 15:15:23 +0100 |
| commit | 27fa41583fdee54d40ae680408f697e6d8201a8c (patch) | |
| tree | a7860942b3b3cede92eb597b3e833709227a354e /llvm/lib/Transforms/Utils/LoopUtils.cpp | |
| parent | 8ab819ad90d647b96bb4b6842a742d2552ba9e9c (diff) | |
| download | llvm-27fa41583fdee54d40ae680408f697e6d8201a8c.zip llvm-27fa41583fdee54d40ae680408f697e6d8201a8c.tar.gz llvm-27fa41583fdee54d40ae680408f697e6d8201a8c.tar.bz2 | |
[AMDGPU] Shrink MAD/FMA to MADAK/MADMK/FMAAK/FMAMK on GFX10
On GFX10 VOP3 instructions can have a literal operand, so the conversion
from VOP3 MAD/FMA to VOP2 MADAK/MADMK/FMAAK/FMAMK will not happen in
SIFoldOperands. The only benefit of the VOP2 form is code size, so do it
in SIShrinkInstructions instead.
Differential Revision: https://reviews.llvm.org/D125567
Diffstat (limited to 'llvm/lib/Transforms/Utils/LoopUtils.cpp')
0 files changed, 0 insertions, 0 deletions