[PATCH] D93305: [AMDGPU][GlobalISel] Transform (fadd (fmul x, y), z) -> (fma x, y, z)
Mirko Brkusanin via Phabricator via llvm-commits
llvm-commits at lists.llvm.org
Wed Nov 3 10:49:09 PDT 2021
mbrkusanin accepted this revision.
mbrkusanin added a comment.
LGTM
================
Comment at: llvm/include/llvm/Target/GlobalISel/Combine.td:768
truncstore_merge, div_rem_to_divrem, funnel_shift_combines,
- form_bitfield_extract, constant_fold]>;
+ form_bitfield_extract, constant_fold, combine_fadd_fmul_to_fmad_or_fma]>;
----------------
Might be useful to make a new combine group for this and other fma combines.
CHANGES SINCE LAST ACTION
https://reviews.llvm.org/D93305/new/
https://reviews.llvm.org/D93305
More information about the llvm-commits
mailing list