[llvm] [AMDGPU][True16] si-fold-operand selecting srcidx for v_mov_b16_t16_e64 (PR #162101)

Umang Yadav via llvm-commits llvm-commits at lists.llvm.org
Wed Oct 8 09:28:09 PDT 2025


================
@@ -932,7 +932,8 @@ static MachineOperand *lookUpCopyChain(const SIInstrInfo &TII,
   for (MachineInstr *SubDef = MRI.getVRegDef(SrcReg);
        SubDef && TII.isFoldableCopy(*SubDef);
        SubDef = MRI.getVRegDef(Sub->getReg())) {
-    unsigned SrcIdx = TII.getFoldableCopySrcIdx(*SubDef);
+    const int SrcIdx =
----------------
umangyadav wrote:

Can we add some unit-tests to make sure this is working as expected ? 

https://github.com/llvm/llvm-project/pull/162101


More information about the llvm-commits mailing list