[AMDGPU] Fix to 'Fold readlane from copy of SGPR or imm'

[tpr]

Summary

That change (r363670) could leave a copy from vgpr to sgpr. Fixed.

Change-Id: I00c3fe6fda2e8e1e36f53195b881b1449c777ea4

[arsenm]

LGTM

lib/Target/AMDGPU/SIFoldOperands.cpp

if (UseOpc == AMDGPU::V_READFIRSTLANE_B32 ||
                                        *UseMI))
           return;
 
         // %vgpr = COPY %sgpr0
         // %sgpr1 = V_READFIRSTLANE_B32 %vgpr
         // =>
         // %sgpr1 = COPY %sgpr0
         UseMI->setDesc(TII->get(AMDGPU::COPY));
+        UseMI->getOperand(1).setReg(OpToFold.getReg());
+        UseMI->getOperand(1).setSubReg(OpToFold.getSubReg());
+        UseMI->getOperand(1).setIsKill(false);
         UseMI->RemoveOperand(2); // Remove exec read (or src1 for readlane)
         return;
       }
     }
 
     const MCInstrDesc &UseDesc = UseMI->getDesc();
 
     // Don't fold into target independent nodes.  Target independent opcodes

test/CodeGen/AMDGPU/fold-readlane.mir

bb.0:
     %0:vgpr_32 = V_MOV_B32_e32 123, implicit $exec
     %1:sreg_32_xm0 = V_READFIRSTLANE_B32 %0, implicit $exec
 ...
 
 # GCN-LABEL: name: fold-imm-readfirstlane-readfirstlane{{$}}
 # GCN: %0:vgpr_32 = V_MOV_B32_e32 123, implicit $exec
 # GCN: %1:sreg_32_xm0 = S_MOV_B32 123
 # GCN: %2:vgpr_32 = V_MOV_B32_e32 123, implicit $exec
-# GCN: %3:sreg_32_xm0 = S_MOV_B32 123
+# GCN: %3:sreg_32_xm0 = COPY %1
 
 ---
 name: fold-imm-readfirstlane-readfirstlane
 tracksRegLiveness: true
 body:             |
   bb.0:
     %0:vgpr_32 = V_MOV_B32_e32 123, implicit $exec
     %1:sreg_32_xm0 = V_READFIRSTLANE_B32 %0, implicit $exec
     %2:vgpr_32 = COPY %1
     %3:sreg_32_xm0 = V_READFIRSTLANE_B32 %2, implicit $exec
 
 ...
 
 
 # GCN-LABEL: name: fold-copy-readfirstlane{{$}}
 # GCN: %0:sreg_32_xm0 = COPY $sgpr10
 # GCN: %1:vgpr_32 = COPY %0
-# GCN: %2:sreg_32_xm0 = COPY %1
+# GCN: %2:sreg_32_xm0 = COPY %0
 ---
 name: fold-copy-readfirstlane
 tracksRegLiveness: true
 body:             |
   bb.0:
     liveins: $sgpr10
     %0:sreg_32_xm0 = COPY $sgpr10
     %1:vgpr_32 = COPY %0