diff options
| author | Nikita Popov <nikita.ppv@gmail.com> | 2019-02-10 19:06:38 +0000 |
|---|---|---|
| committer | Nikita Popov <nikita.ppv@gmail.com> | 2019-02-10 19:06:38 +0000 |
| commit | a0e96bd56d99d6313b15af0900859a8cb3ad73df (patch) | |
| tree | 61dc104e97810fed9563a231dfd8c1b6409c5b0c /llvm/lib/Target/WebAssembly/WebAssemblyFixFunctionBitcasts.cpp | |
| parent | e8adbae00a3e78795a653dadb58425cb89050e4c (diff) | |
| download | llvm-a0e96bd56d99d6313b15af0900859a8cb3ad73df.zip llvm-a0e96bd56d99d6313b15af0900859a8cb3ad73df.tar.gz llvm-a0e96bd56d99d6313b15af0900859a8cb3ad73df.tar.bz2 | |
[CodeGen][X86] Don't scalarize vector saturating add/sub
Now that we have vector support for [US](ADD|SUB)O we no longer
need to scalarize when expanding [US](ADD|SUB)SAT.
This matches what the cost model already does.
Differential Revision: https://reviews.llvm.org/D57348
llvm-svn: 353651
Diffstat (limited to 'llvm/lib/Target/WebAssembly/WebAssemblyFixFunctionBitcasts.cpp')
0 files changed, 0 insertions, 0 deletions