[llvm] [AMDGPU] Switch V_CNDMASK operands to shrink it into VOP2 (PR #135162)

Matt Arsenault via llvm-commits llvm-commits at lists.llvm.org
Sun Apr 13 01:54:25 PDT 2025


================
@@ -831,6 +836,109 @@ bool SIShrinkInstructions::tryReplaceDeadSDST(MachineInstr &MI) const {
   return true;
 }
 
+unsigned SIShrinkInstructions::getInverseCompareOpcode(MachineInstr &MI) const {
+  switch (MI.getOpcode()) {
+  // unsigned 32
----------------
arsenm wrote:

Yes, be comprehensive 

https://github.com/llvm/llvm-project/pull/135162


More information about the llvm-commits mailing list