[all-commits] [llvm/llvm-project] a8f13d: [InstCombine] fold shuffle of fabs
Sanjay Patel via All-commits
all-commits at lists.llvm.org
Fri Feb 3 11:27:24 PST 2023
Branch: refs/heads/main
Home: https://github.com/llvm/llvm-project
Commit: a8f13dbdeb31be37ee15b5febb7cc2137bbece67
https://github.com/llvm/llvm-project/commit/a8f13dbdeb31be37ee15b5febb7cc2137bbece67
Author: Sanjay Patel <spatel at rotateright.com>
Date: 2023-02-03 (Fri, 03 Feb 2023)
Changed paths:
M llvm/lib/Transforms/InstCombine/InstCombineVectorOps.cpp
M llvm/test/Transforms/InstCombine/vec_shuffle.ll
Log Message:
-----------
[InstCombine] fold shuffle of fabs
shuffle (fabs X), Mask --> fabs (shuffle X, Mask)
shuffle (fabs X), (fabs Y), Mask --> fabs (shuf X, Y, Mask)
https://alive2.llvm.org/ce/z/JH2nkf
This generalizes the existing fneg transforms to also work with fabs.
A likely follow-up would generalize this further to move any unary
intrinsic op.
More information about the All-commits
mailing list