AMDGPU/SI: Set the kill flag on temp VGPRs used to restore SGPRs from scratch

[• tstellarAMD]

Summary

When we restore an SGPR value from scratch, we first load it into a
temporary VGPR and then use v_readlane_b32 to copy the value from the
VGPR back into an SGPR.

We weren't setting the kill flag on the VGPR in the v_readlane_b32
instruction, so the register scavenger wasn't able to re-use this
temp value later.

I wasn't able to create a lit test for this.

[arsenm]

LGTM

llvm/trunk/lib/Target/AMDGPU/SIRegisterInfo.cpp

case AMDGPU::SI_SPILL_S32_RESTORE: {
           BuildMI(*MBB, MI, DL, TII->get(AMDGPU::SI_SPILL_V32_RESTORE), TmpReg)
                   .addFrameIndex(Index)                   // frame_idx
                   .addReg(MFI->getScratchRSrcReg())       // scratch_rsrc
                   .addReg(MFI->getScratchWaveOffsetReg()) // scratch_offset
                   .addImm(i * 4)                          // offset
                   .addMemOperand(MMO);
           BuildMI(*MBB, MI, DL,
                   TII->getMCOpcodeFromPseudo(AMDGPU::V_READLANE_B32), SubReg)
-                  .addReg(TmpReg)
+                  .addReg(TmpReg, RegState::Kill)
                   .addImm(0)
                   .addReg(MI->getOperand(0).getReg(), RegState::ImplicitDefine);
         }
       }
 
       MI->eraseFromParent();
       break;
     }