[llvm] [AMDGPU][True16][CodeGen] S_PACK_XX_B32_B16 lowering for true16 mode (PR #162389)
Stanislav Mekhanoshin via llvm-commits
llvm-commits at lists.llvm.org
Thu Oct 9 11:09:38 PDT 2025
================
@@ -9115,6 +9115,63 @@ void SIInstrInfo::movePackToVALU(SIInstrWorklist &Worklist,
MachineOperand &Src1 = Inst.getOperand(2);
const DebugLoc &DL = Inst.getDebugLoc();
+ if (ST.useRealTrue16Insts()) {
+ Register SrcReg0 = Src0.getReg();
+ Register SrcReg1 = Src1.getReg();
+
+ if (!RI.isVGPR(MRI, SrcReg0)) {
----------------
rampitec wrote:
This is a scalar instruction, how could the operand be VGPR?
https://github.com/llvm/llvm-project/pull/162389
More information about the llvm-commits
mailing list