[PATCH] D74832: AMDGPU: Use default operand for VOP3P clamp
Stanislav Mekhanoshin via Phabricator via llvm-commits
llvm-commits at lists.llvm.org
Wed Feb 19 09:32:00 PST 2020
rampitec accepted this revision.
rampitec added inline comments.
This revision is now accepted and ready to land.
================
Comment at: llvm/lib/Target/AMDGPU/VOP3PInstructions.td:34
+ // FIXME: clampmod0 misbehaves with the non-default vdst_in
+ // following it. For now workaround thiss by requiring clamp
+ // in tied patterns. This should use undef_tied_input, but it
----------------
Typo: thiss
CHANGES SINCE LAST ACTION
https://reviews.llvm.org/D74832/new/
https://reviews.llvm.org/D74832
More information about the llvm-commits
mailing list