[PATCH] D37616: [X86] PR34149 Suboptimal codegen for fast minnum and maxnum.
Alina Sbirlea via Phabricator via llvm-commits
llvm-commits at lists.llvm.org
Tue Sep 12 14:39:12 PDT 2017
asbirlea added a comment.
FWIW, we've seen a similar case of min/maxnum being generated in the IR and leading to suboptimal codegen.
The solution was replacing the IR generated with fcmp+select (coupled with https://reviews.llvm.org/D27846). Seems like the right approach to avoid adding complexity to the backend.
https://reviews.llvm.org/D37616
More information about the llvm-commits
mailing list