diff options
| author | Amara Emerson <amara@apple.com> | 2021-03-05 10:10:42 -0800 |
|---|---|---|
| committer | Amara Emerson <amara@apple.com> | 2021-03-09 11:36:26 -0800 |
| commit | 45a9dca0150ec16e6365dfb9c270f11469337623 (patch) | |
| tree | 55aa3b0b10cbe1afca3b8bc87543984304b36733 /clang/lib/Frontend/CompilerInvocation.cpp | |
| parent | 55e760769b72eafa08e9e3f1aeb5a1ea8235baff (diff) | |
| download | llvm-45a9dca0150ec16e6365dfb9c270f11469337623.zip llvm-45a9dca0150ec16e6365dfb9c270f11469337623.tar.gz llvm-45a9dca0150ec16e6365dfb9c270f11469337623.tar.bz2 | |
[AArch64][GlobalISel] Form G_DUPLANE32 for <2 x s32> shufflevectors in lowering.
For <2 x s32>, we can use G_DUPLANE32, but with a <4 x s32> source. To make it
work, we can just widen the original source with a concat_vectors.
Doing this allows <2 x float> indexed fmul instruction selection patterns to
fire, which gives a nice 0.3% code size saving on Bullet with -Os.
Differential Revision: https://reviews.llvm.org/D98059
Diffstat (limited to 'clang/lib/Frontend/CompilerInvocation.cpp')
0 files changed, 0 insertions, 0 deletions