This is an archive of the discontinued LLVM Phabricator instance.

AMDGPU: Fix incorrect commute with sub when folding immediates
ClosedPublic

Authored by arsenm on May 2 2019, 3:50 AM.

Details

Reviewers
rampitec
Summary

When a fold of an immediate into a sub/subrev required shrinking the
instruction, the wrong VOP2 opcode was used. This was using the VOP2
equivalent of the original instruction, not the commuted instruction
with the inverted opcode.

Diff Detail

Event Timeline

arsenm created this revision.May 2 2019, 3:50 AM
This revision is now accepted and ready to land.May 2 2019, 11:48 AM
arsenm closed this revision.May 3 2019, 6:40 AM

r359883