[llvm] AMDGPU: Don't canonicalize fminnum/fmaxnum if targets support IEEE fminimum(maximum)_num (PR #127711)
Stanislav Mekhanoshin via llvm-commits
llvm-commits at lists.llvm.org
Wed Feb 19 10:55:59 PST 2025
https://github.com/rampitec approved this pull request.
https://github.com/llvm/llvm-project/pull/127711
More information about the llvm-commits
mailing list