diff options
| author | Nikita Popov <nikita.ppv@gmail.com> | 2019-01-15 18:43:41 +0000 |
|---|---|---|
| committer | Nikita Popov <nikita.ppv@gmail.com> | 2019-01-15 18:43:41 +0000 |
| commit | d3b86b79fa99d7c9253cc2911aeda0655be9f7c0 (patch) | |
| tree | 49b9b61bf30aab82b74abf7ccb06d91558d786bd /openmp/runtime | |
| parent | 6f9d49cdde65898c3fbd74a7a98e7438216b0ba5 (diff) | |
| download | bcm5719-llvm-d3b86b79fa99d7c9253cc2911aeda0655be9f7c0.tar.gz bcm5719-llvm-d3b86b79fa99d7c9253cc2911aeda0655be9f7c0.zip | |
Reapply "[CodeGen][X86] Expand USUBSAT to UMAX+SUB, also for vectors"
Related to https://bugs.llvm.org/show_bug.cgi?id=40123.
Rather than scalarizing, expand a vector USUBSAT into UMAX+SUB,
which produces much better code for X86.
Reapplying with updated SLPVectorizer tests.
Differential Revision: https://reviews.llvm.org/D56636
llvm-svn: 351219
Diffstat (limited to 'openmp/runtime')
0 files changed, 0 insertions, 0 deletions
