[AMDGPU][GlobalISel] Fix issue with copy_scc_vcc on gfx7

When selecting for G_AMDGPU_COPY_SCC_VCC, we use S_CMP_LG_U64 or S_CMP_LG_U32
for wave64 and wave32 respectively. However, on gfx7 we do not have the
S_CMP_LG_U64 instruction. Work around this issue by using S_OR_B64 instead.

Author: vangthao95

llvm/lib/Target/AMDGPU/AMDGPUInstructionSelector.cpp

@@ -221,12 +221,23 @@ bool AMDGPUInstructionSelector::selectCOPY(MachineInstr &I) const {
 bool AMDGPUInstructionSelector::selectCOPY_SCC_VCC(MachineInstr &I) const {
   const DebugLoc &DL = I.getDebugLoc();
   MachineBasicBlock *BB = I.getParent();
+  Register VCCReg = I.getOperand(1).getReg();
+  MachineInstr *Cmp;
+
+  if (STI.getGeneration() >= AMDGPUSubtarget::VOLCANIC_ISLANDS) {
+    unsigned CmpOpc = STI.isWave64() ? AMDGPU::S_CMP_LG_U64 : AMDGPU::S_CMP_LG_U32;
+    Cmp = BuildMI(*BB, &I, DL, TII.get(CmpOpc))
+              .addReg(VCCReg)
+              .addImm(0);
+  } else {
+    // For gfx7 and earlier, S_CMP_LG_U64 doesn't exist, so we use S_OR_B64
+    // which sets SCC as a side effect.
+    Register DeadDst = MRI->createVirtualRegister(&AMDGPU::SReg_64RegClass);
+    Cmp = BuildMI(*BB, &I, DL, TII.get(AMDGPU::S_OR_B64), DeadDst)
+              .addReg(VCCReg)
+              .addReg(VCCReg);
+  }
 
-  unsigned CmpOpc =
-      STI.isWave64() ? AMDGPU::S_CMP_LG_U64 : AMDGPU::S_CMP_LG_U32;
-  MachineInstr *Cmp = BuildMI(*BB, &I, DL, TII.get(CmpOpc))
-                          .addReg(I.getOperand(1).getReg())
-                          .addImm(0);
   if (!constrainSelectedInstRegOperands(*Cmp, TII, TRI, RBI))
     return false;
 

llvm/test/CodeGen/AMDGPU/GlobalISel/inst-select-copy-scc-vcc.mir

@@ -0,0 +1,38 @@
+# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py
+# RUN: llc -mtriple=amdgcn -mcpu=gfx700 -run-pass=instruction-select -verify-machineinstrs %s -o - | FileCheck -check-prefix=GFX7 %s
+# RUN: llc -mtriple=amdgcn -mcpu=gfx803 -run-pass=instruction-select -verify-machineinstrs %s -o - | FileCheck -check-prefix=GFX8 %s
+# RUN: llc -mtriple=amdgcn -mcpu=gfx1100 -run-pass=instruction-select -verify-machineinstrs %s -o - | FileCheck -check-prefix=GFX11 %s
+
+---
+name: test_copy_scc_vcc
+legalized: true
+regBankSelected: true
+tracksRegLiveness: true
+body: |
+  bb.0:
+
+    ; GFX7-LABEL: name: test_copy_scc_vcc
+    ; GFX7: [[DEF:%[0-9]+]]:sreg_64_xexec = IMPLICIT_DEF
+    ; GFX7-NEXT: [[S_OR_B64_:%[0-9]+]]:sreg_64 = S_OR_B64 [[DEF]], [[DEF]], implicit-def $scc
+    ; GFX7-NEXT: [[COPY:%[0-9]+]]:sreg_32 = COPY $scc
+    ; GFX7-NEXT: $sgpr0 = COPY [[COPY]]
+    ; GFX7-NEXT: S_ENDPGM 0, implicit $sgpr0
+    ;
+    ; GFX8-LABEL: name: test_copy_scc_vcc
+    ; GFX8: [[DEF:%[0-9]+]]:sreg_64_xexec = IMPLICIT_DEF
+    ; GFX8-NEXT: S_CMP_LG_U64 [[DEF]], 0, implicit-def $scc
+    ; GFX8-NEXT: [[COPY:%[0-9]+]]:sreg_32 = COPY $scc
+    ; GFX8-NEXT: $sgpr0 = COPY [[COPY]]
+    ; GFX8-NEXT: S_ENDPGM 0, implicit $sgpr0
+    ;
+    ; GFX11-LABEL: name: test_copy_scc_vcc
+    ; GFX11: [[DEF:%[0-9]+]]:sreg_32_xm0_xexec = IMPLICIT_DEF
+    ; GFX11-NEXT: S_CMP_LG_U32 [[DEF]], 0, implicit-def $scc
+    ; GFX11-NEXT: [[COPY:%[0-9]+]]:sreg_32 = COPY $scc
+    ; GFX11-NEXT: $sgpr0 = COPY [[COPY]]
+    ; GFX11-NEXT: S_ENDPGM 0, implicit $sgpr0
+    %0:vcc(s1) = G_IMPLICIT_DEF
+    %1:sgpr(s32) = G_AMDGPU_COPY_SCC_VCC %0
+    $sgpr0 = COPY %1
+    S_ENDPGM 0, implicit $sgpr0
+...