[PATCH] D33802: [AMDGPU] Preserve operand order in SIFoldOperands

[Matt Arsenault via Phabricator via llvm-commits]

arsenm accepted this revision.
arsenm added a comment.
This revision is now accepted and ready to land.

LGTM



================
Comment at: lib/Target/AMDGPU/SIFoldOperands.cpp:715
+    } else if (Fold.isCommuted()) {
+      TII->commuteInstruction(*Fold.UseMI, false);
     }
----------------
Should add a comment that this is undoing the commute if the fold failed to restore the instruction to its original order


Repository:
  rL LLVM

https://reviews.llvm.org/D33802