AMDGPU/SI: Attempt to fix inst-select-load-smrd.mir on some builds

[• tstellarAMD]

Summary

For some reason instructiosn are being inserted in the wrong order with some
builds. I'm not sure why this is happening.

lib/Target/AMDGPU/AMDGPUInstructionSelector.cpp

bool AMDGPUInstructionSelector::selectG_ADD(MachineInstr &I) const {
   unsigned DstLo = MRI.createVirtualRegister(&AMDGPU::SReg_32RegClass);
   unsigned DstHi = MRI.createVirtualRegister(&AMDGPU::SReg_32RegClass);
 
   if (Size != 64)
     return false;
 
   DebugLoc DL = I.getDebugLoc();
 
+  MachineOperand Lo1(getSubOperand64(I.getOperand(1), AMDGPU::sub0));
+  MachineOperand Lo2(getSubOperand64(I.getOperand(2), AMDGPU::sub0));
+
   BuildMI(*BB, &I, DL, TII.get(AMDGPU::S_ADD_U32), DstLo)
-          .add(getSubOperand64(I.getOperand(1), AMDGPU::sub0))
-          .add(getSubOperand64(I.getOperand(2), AMDGPU::sub0));
+          .add(Lo1)
+          .add(Lo2);
+
+  MachineOperand Hi1(getSubOperand64(I.getOperand(1), AMDGPU::sub1));
+  MachineOperand Hi2(getSubOperand64(I.getOperand(2), AMDGPU::sub1));
 
   BuildMI(*BB, &I, DL, TII.get(AMDGPU::S_ADDC_U32), DstHi)
-          .add(getSubOperand64(I.getOperand(1), AMDGPU::sub1))
-          .add(getSubOperand64(I.getOperand(2), AMDGPU::sub1));
+          .add(Hi1)
+          .add(Hi2);
 
   BuildMI(*BB, &I, DL, TII.get(AMDGPU::REG_SEQUENCE), I.getOperand(0).getReg())
           .addReg(DstLo)
           .addImm(AMDGPU::sub0)
           .addReg(DstHi)
           .addImm(AMDGPU::sub1);
 
   for (MachineOperand &MO : I.explicit_operands()) {

test/CodeGen/AMDGPU/GlobalISel/inst-select-load-smrd.mir

 # SIVI: [[K1048576:%[0-9]+]] = S_MOV_B32 1048576
 # SIVI: S_LOAD_DWORD_SGPR [[PTR]], [[K1048576]], 0
 # CI: S_LOAD_DWORD_IMM_ci [[PTR]], 262144, 0
 
 # Max immediate for CI
 # SIVI: [[K_LO:%[0-9]+]] = S_MOV_B32 4294967292
 # SIVI: [[K_HI:%[0-9]+]] = S_MOV_B32 3
 # SIVI: [[K:%[0-9]+]] = REG_SEQUENCE [[K_LO]], 1, [[K_HI]], 2
-# SIVI: [[K_SUB0:%[0-9]+]] = COPY [[K]].sub0
-# SIVI: [[PTR_LO:%[0-9]+]] = COPY [[PTR]].sub0
+# SIVI-DAG: [[K_SUB0:%[0-9]+]] = COPY [[K]].sub0
+# SIVI-DAG: [[PTR_LO:%[0-9]+]] = COPY [[PTR]].sub0
 # SIVI: [[ADD_PTR_LO:%[0-9]+]] = S_ADD_U32 [[PTR_LO]], [[K_SUB0]]
-# SIVI: [[K_SUB1:%[0-9]+]] = COPY [[K]].sub1
-# SIVI: [[PTR_HI:%[0-9]+]] = COPY [[PTR]].sub1
+# SIVI-DAG: [[K_SUB1:%[0-9]+]] = COPY [[K]].sub1
+# SIVI-DAG: [[PTR_HI:%[0-9]+]] = COPY [[PTR]].sub1
 # SIVI: [[ADD_PTR_HI:%[0-9]+]] = S_ADDC_U32 [[PTR_HI]], [[K_SUB1]]
 # SIVI: [[ADD_PTR:%[0-9]+]] = REG_SEQUENCE [[ADD_PTR_LO]], 1, [[ADD_PTR_HI]], 2
 # SIVI: S_LOAD_DWORD_IMM [[ADD_PTR]], 0, 0
 # CI: S_LOAD_DWORD_IMM_ci [[PTR]], 4294967295, 0
 
 # Immediate overflow for CI
 # GCN: [[K_LO:%[0-9]+]] = S_MOV_B32 0
 # GCN: [[K_HI:%[0-9]+]] = S_MOV_B32 4
 # GCN: [[K:%[0-9]+]] = REG_SEQUENCE [[K_LO]], 1, [[K_HI]], 2
-# GCN: [[K_SUB0:%[0-9]+]] = COPY [[K]].sub0
-# GCN: [[PTR_LO:%[0-9]+]] = COPY [[PTR]].sub0
+# GCN-DAG: [[K_SUB0:%[0-9]+]] = COPY [[K]].sub0
+# GCN-DAG: [[PTR_LO:%[0-9]+]] = COPY [[PTR]].sub0
 # GCN: [[ADD_PTR_LO:%[0-9]+]] = S_ADD_U32 [[PTR_LO]], [[K_SUB0]]
-# GCN: [[K_SUB1:%[0-9]+]] = COPY [[K]].sub1
-# GCN: [[PTR_HI:%[0-9]+]] = COPY [[PTR]].sub1
+# GCN-DAG: [[K_SUB1:%[0-9]+]] = COPY [[K]].sub1
+# GCN-DAG: [[PTR_HI:%[0-9]+]] = COPY [[PTR]].sub1
 # GCN: [[ADD_PTR_HI:%[0-9]+]] = S_ADDC_U32 [[PTR_HI]], [[K_SUB1]]
 # GCN: [[ADD_PTR:%[0-9]+]] = REG_SEQUENCE [[ADD_PTR_LO]], 1, [[ADD_PTR_HI]], 2
 # GCN: S_LOAD_DWORD_IMM [[ADD_PTR]], 0, 0
 
 # Max 32-bit byte offset
 # FIXME: The immediate gets selected twice, once into the
 # S_LOAD_DWORD instruction and once just as a normal constat.
 # SIVI: S_MOV_B32 4294967292
 # SIVI: [[K4294967292:%[0-9]+]] = S_MOV_B32 4294967292
 # SIVI: S_LOAD_DWORD_SGPR [[PTR]], [[K4294967292]], 0
 # CI: S_LOAD_DWORD_IMM_ci [[PTR]], 1073741823, 0
 
 # Overflow 32-bit byte offset
 # SIVI: [[K_LO:%[0-9]+]] = S_MOV_B32 0
 # SIVI: [[K_HI:%[0-9]+]] = S_MOV_B32 1
 # SIVI: [[K:%[0-9]+]] = REG_SEQUENCE [[K_LO]], 1, [[K_HI]], 2
-# SIVI: [[K_SUB0:%[0-9]+]] = COPY [[K]].sub0
-# SIVI: [[PTR_LO:%[0-9]+]] = COPY [[PTR]].sub0
+# SIVI-DAG: [[K_SUB0:%[0-9]+]] = COPY [[K]].sub0
+# SIVI-DAG: [[PTR_LO:%[0-9]+]] = COPY [[PTR]].sub0
 # SIVI: [[ADD_PTR_LO:%[0-9]+]] = S_ADD_U32 [[PTR_LO]], [[K_SUB0]]
-# SIVI: [[K_SUB1:%[0-9]+]] = COPY [[K]].sub1
-# SIVI: [[PTR_HI:%[0-9]+]] = COPY [[PTR]].sub1
+# SIVI-DAG: [[K_SUB1:%[0-9]+]] = COPY [[K]].sub1
+# SIVI-DAG: [[PTR_HI:%[0-9]+]] = COPY [[PTR]].sub1
 # SIVI: [[ADD_PTR_HI:%[0-9]+]] = S_ADDC_U32 [[PTR_HI]], [[K_SUB1]]
 # SIVI: [[ADD_PTR:%[0-9]+]] = REG_SEQUENCE [[ADD_PTR_LO]], 1, [[ADD_PTR_HI]], 2
 # SIVI: S_LOAD_DWORD_IMM [[ADD_PTR]], 0, 0
 # CI: S_LOAD_DWORD_IMM_ci [[PTR]], 1073741824, 0
 
 body: |
   bb.0:
     liveins: %sgpr0_sgpr1