diff options
| author | Simon Pilgrim <llvm-dev@redking.me.uk> | 2022-01-20 15:15:46 +0000 |
|---|---|---|
| committer | Simon Pilgrim <llvm-dev@redking.me.uk> | 2022-01-20 15:16:05 +0000 |
| commit | 866311e71c8f1f3724754d006eb50299424d5b1b (patch) | |
| tree | 57f9f5f7b6afb982c88f48d8b8f28b30ef25f33a /clang/lib/CodeGen/CodeGenFunction.cpp | |
| parent | f29256a64ac11cf59cea878c8d1ba9537db4f523 (diff) | |
| download | llvm-866311e71c8f1f3724754d006eb50299424d5b1b.zip llvm-866311e71c8f1f3724754d006eb50299424d5b1b.tar.gz llvm-866311e71c8f1f3724754d006eb50299424d5b1b.tar.bz2 | |
[X86] lowerToAddSubOrFMAddSub - lower 512-bit ADDSUB patterns to blend(fsub,fadd)
AVX512 doesn't provide a ADDSUB instruction, but if we've built this from a build vector of scalar fsub/fadd elements we can still lower to blend(fsub,fadd)
Diffstat (limited to 'clang/lib/CodeGen/CodeGenFunction.cpp')
0 files changed, 0 insertions, 0 deletions