diff options
| author | Simon Pilgrim <llvm-dev@redking.me.uk> | 2019-05-02 14:00:55 +0000 |
|---|---|---|
| committer | Simon Pilgrim <llvm-dev@redking.me.uk> | 2019-05-02 14:00:55 +0000 |
| commit | df8daf0ef4d1d00436ea1040355bb08974c5fd66 (patch) | |
| tree | 53f06514438dc635f39cb3e3ce062c0a7c01c0d7 /clang/test/Modules/Inputs/ModuleMapLocations/Module_ModuleMap/a.h | |
| parent | a4939d35070f569d4ad3e6161ea382d348d0e72a (diff) | |
| download | bcm5719-llvm-df8daf0ef4d1d00436ea1040355bb08974c5fd66.tar.gz bcm5719-llvm-df8daf0ef4d1d00436ea1040355bb08974c5fd66.zip | |
[X86][SSE] lowerAddSubToHorizontalOp - enable ymm extraction+fold
Limiting scalar hadd/hsub generation to the lowest xmm looks to be unnecessary - we will be extracting one upper xmm whatever, and we can remove a shuffle by using the hop which is inline with what shouldUseHorizontalOp expects to happen anyway.
Testing on btver2 (the main target for fast-hops) shows this is beneficial even for float ops where we have a 'shuffle' to extract the float result:
https://godbolt.org/z/0R-U-K
Differential Revision: https://reviews.llvm.org/D61426
llvm-svn: 359786
Diffstat (limited to 'clang/test/Modules/Inputs/ModuleMapLocations/Module_ModuleMap/a.h')
0 files changed, 0 insertions, 0 deletions
