diff options
| author | Craig Topper <craig.topper@intel.com> | 2018-11-30 18:43:15 +0000 |
|---|---|---|
| committer | Craig Topper <craig.topper@intel.com> | 2018-11-30 18:43:15 +0000 |
| commit | 8191307d0987ad1c18ae1cf391a43c4b54c2e41e (patch) | |
| tree | 3e8301f710bbfb8d18666dc07139acd278787909 /clang/lib/StaticAnalyzer/Core/RetainSummaryManager.cpp | |
| parent | 4b5b0c0025c3238f7a8894ba1ac28b6f2394286a (diff) | |
| download | bcm5719-llvm-8191307d0987ad1c18ae1cf391a43c4b54c2e41e.tar.gz bcm5719-llvm-8191307d0987ad1c18ae1cf391a43c4b54c2e41e.zip | |
[X86] Prefer lowerVectorShuffleAsBitMask over using a avx512 masked operation when avx512bw/avx512vl is enabled.
This does require a constant pool load instead of loading an immediate into a gpr, moving to a k register and masking. But its less instructions and more consistent with previous ISAs. It probably opens up more combine opportunities as one of the test cases demonstrates.
llvm-svn: 348018
Diffstat (limited to 'clang/lib/StaticAnalyzer/Core/RetainSummaryManager.cpp')
0 files changed, 0 insertions, 0 deletions
