Restore SGPR_LO16 handling

Author: arsenm

llvm/lib/Target/AMDGPU/SIFoldOperands.cpp

@@ -1260,6 +1260,13 @@ void SIFoldOperandsImpl::foldOperand(
       return;
 
     const TargetRegisterClass *DestRC = TRI->getRegClassForReg(*MRI, DestReg);
+    // Allow immediates COPYd into sgpr_lo16 to be further folded while
+    // still being legal if not further folded
+    if (DestRC == &AMDGPU::SGPR_LO16RegClass) {
+      assert(ST->useRealTrue16Insts());
+      MRI->setRegClass(DestReg, &AMDGPU::SGPR_32RegClass);
+      DestRC = &AMDGPU::SGPR_32RegClass;
+    }
 
     // In order to fold immediates into copies, we need to change the copy to a
     // MOV. Find a compatible mov instruction with the value.
@@ -1298,14 +1305,6 @@ void SIFoldOperandsImpl::foldOperand(
       UseMI->setDesc(MovDesc);
 
       if (MovOp == AMDGPU::V_MOV_B16_t16_e64) {
-        // Allow immediates COPYd into sgpr_lo16 to be further folded while
-        // still being legal if not further folded
-        if (DestRC == &AMDGPU::SGPR_LO16RegClass) {
-          assert(ST->useRealTrue16Insts());
-          MRI->setRegClass(DestReg, &AMDGPU::SGPR_32RegClass);
-          DestRC = &AMDGPU::SGPR_32RegClass;
-        }
-
         const auto &SrcOp = UseMI->getOperand(UseOpIdx);
         MachineOperand NewSrcOp(SrcOp);
         MachineFunction *MF = UseMI->getParent()->getParent();