MachineUniformityAnalysis: Improve isConstantOrUndefValuePhi

llvm/lib/CodeGen/MachineSSAContext.cpp

@@ -54,9 +54,34 @@ const MachineBasicBlock *MachineSSAContext::getDefBlock(Register value) const {
   return F->getRegInfo().getVRegDef(value)->getParent();
 }
 
+static bool isUndef(const MachineInstr &MI) {
+  return MI.getOpcode() == TargetOpcode::G_IMPLICIT_DEF ||
+         MI.getOpcode() == TargetOpcode::IMPLICIT_DEF;
+}
+
+/// MachineInstr equivalent of PHINode::hasConstantOrUndefValue() for G_PHI.
 template <>
 bool MachineSSAContext::isConstantOrUndefValuePhi(const MachineInstr &Phi) {
-  return Phi.isConstantValuePHI();
+  if (!Phi.isPHI())
+    return false;
+
+  // In later passes PHI may appear with an undef operand, getVRegDef can fail.
+  if (Phi.getOpcode() == TargetOpcode::PHI)
+    return Phi.isConstantValuePHI();
+
+  // For G_PHI we do equivalent of PHINode::hasConstantOrUndefValue().
+  const MachineRegisterInfo &MRI = Phi.getMF()->getRegInfo();
+  Register This = Phi.getOperand(0).getReg();
+  Register ConstantValue;
+  for (unsigned i = 1, e = Phi.getNumOperands(); i < e; i += 2) {
+    Register Incoming = Phi.getOperand(i).getReg();
+    if (Incoming != This && !isUndef(*MRI.getVRegDef(Incoming))) {
+      if (ConstantValue && ConstantValue != Incoming)
+        return false;
+      ConstantValue = Incoming;
+    }
+  }
+  return true;
 }
 
 template <>

llvm/test/Analysis/UniformityAnalysis/AMDGPU/MIR/hidden-diverge-gmir.mir

@@ -1,24 +1,24 @@
 # RUN: llc -mtriple=amdgcn-- -run-pass=print-machine-uniformity -o - %s 2>&1 | FileCheck %s
 # CHECK-LABEL: MachineUniformityInfo for function: hidden_diverge
 # CHECK-LABEL: BLOCK bb.0
-# CHECK: DIVERGENT: %{{[0-9]*}}: %{{[0-9]*}}:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.workitem.id.x)
-# CHECK: DIVERGENT: %{{[0-9]*}}: %{{[0-9]*}}:_(s1) = G_ICMP intpred(slt)
-# CHECK: DIVERGENT: %{{[0-9]*}}: %{{[0-9]*}}:_(s1) = G_XOR %{{[0-9]*}}:_, %{{[0-9]*}}:_
-# CHECK: DIVERGENT: %{{[0-9]*}}: %{{[0-9]*}}:_(s1), %{{[0-9]*}}:_(s64) = G_INTRINSIC_W_SIDE_EFFECTS intrinsic(@llvm.amdgcn.if)
-# CHECK: DIVERGENT: %{{[0-9]*}}: %{{[0-9]*}}:_(s1), %{{[0-9]*}}:_(s64) = G_INTRINSIC_W_SIDE_EFFECTS intrinsic(@llvm.amdgcn.if)
-# CHECK: DIVERGENT: G_BRCOND %{{[0-9]*}}:_(s1), %bb.1
-# CHECK: DIVERGENT: G_BR %bb.2
+# CHECK:     DIVERGENT: %{{[0-9]*}}: %{{[0-9]*}}:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.workitem.id.x)
+# CHECK:     DIVERGENT: %{{[0-9]*}}: %{{[0-9]*}}:_(s1) = G_ICMP intpred(slt)
+# CHECK:     DIVERGENT: %{{[0-9]*}}: %{{[0-9]*}}:_(s1) = G_XOR %{{[0-9]*}}:_, %{{[0-9]*}}:_
+# CHECK:     DIVERGENT: %{{[0-9]*}}: %{{[0-9]*}}:_(s1), %{{[0-9]*}}:_(s64) = G_INTRINSIC_W_SIDE_EFFECTS intrinsic(@llvm.amdgcn.if)
+# CHECK:     DIVERGENT: %{{[0-9]*}}: %{{[0-9]*}}:_(s1), %{{[0-9]*}}:_(s64) = G_INTRINSIC_W_SIDE_EFFECTS intrinsic(@llvm.amdgcn.if)
+# CHECK:     DIVERGENT: G_BRCOND %{{[0-9]*}}:_(s1), %bb.1
+# CHECK:     DIVERGENT: G_BR %bb.2
 # CHECK-LABEL: BLOCK bb.1
 # CHECK-LABEL: BLOCK bb.2
-# CHECK: DIVERGENT: %{{[0-9]*}}: %{{[0-9]*}}:_(s32) = G_PHI %{{[0-9]*}}:_(s32), %bb.1, %{{[0-9]*}}:_(s32), %bb.0
-# CHECK: DIVERGENT: %{{[0-9]*}}: %{{[0-9]*}}:_(s1) = G_PHI %{{[0-9]*}}:_(s1), %bb.1, %{{[0-9]*}}:_(s1), %bb.0
-# CHECK: DIVERGENT: %{{[0-9]*}}: %{{[0-9]*}}:_(s1), %{{[0-9]*}}:_(s64) = G_INTRINSIC_W_SIDE_EFFECTS intrinsic(@llvm.amdgcn.if)
-# CHECK: DIVERGENT: %{{[0-9]*}}: %{{[0-9]*}}:_(s1), %{{[0-9]*}}:_(s64) = G_INTRINSIC_W_SIDE_EFFECTS intrinsic(@llvm.amdgcn.if)
-# CHECK: DIVERGENT: G_BRCOND %{{[0-9]*}}:_(s1), %bb.3
-# CHECK: DIVERGENT: G_BR %bb.4
+# CHECK-NOT: DIVERGENT: %{{[0-9]*}}: %{{[0-9]*}}:_(s32) = G_PHI %{{[0-9]*}}:_(s32), %bb.1, %{{[0-9]*}}:_(s32), %bb.0
+# CHECK:     DIVERGENT: %{{[0-9]*}}: %{{[0-9]*}}:_(s1) = G_PHI %{{[0-9]*}}:_(s1), %bb.1, %{{[0-9]*}}:_(s1), %bb.0
+# CHECK:     DIVERGENT: %{{[0-9]*}}: %{{[0-9]*}}:_(s1), %{{[0-9]*}}:_(s64) = G_INTRINSIC_W_SIDE_EFFECTS intrinsic(@llvm.amdgcn.if)
+# CHECK:     DIVERGENT: %{{[0-9]*}}: %{{[0-9]*}}:_(s1), %{{[0-9]*}}:_(s64) = G_INTRINSIC_W_SIDE_EFFECTS intrinsic(@llvm.amdgcn.if)
+# CHECK:     DIVERGENT: G_BRCOND %{{[0-9]*}}:_(s1), %bb.3
+# CHECK:     DIVERGENT: G_BR %bb.4
 # CHECK-LABEL: BLOCK bb.3
 # CHECK-LABEL: BLOCK bb.4
-# CHECK: DIVERGENT: %{{[0-9]*}}: %{{[0-9]*}}:_(s32) = G_PHI %{{[0-9]*}}:_(s32), %bb.2, %{{[0-9]*}}:_(s32), %bb.3
+# CHECK:     DIVERGENT: %{{[0-9]*}}: %{{[0-9]*}}:_(s32) = G_PHI %{{[0-9]*}}:_(s32), %bb.2, %{{[0-9]*}}:_(s32), %bb.3
 
 ---
 name:            hidden_diverge

llvm/test/Analysis/UniformityAnalysis/AMDGPU/MIR/hidden-loop-diverge.mir

@@ -22,10 +22,10 @@
 # CHECK-NOT: DIVERGENT: G_BR %bb.5
 
 # CHECK-LABEL: BLOCK bb.4
-# CHECK: DIVERGENT: %{{[0-9]*}}: %{{[0-9]*}}:_(s32) = G_PHI %{{[0-9]*}}:_(s32), %bb.3, %{{[0-9]*}}:_(s32), %bb.2
+# CHECK-NOT: DIVERGENT: %{{[0-9]*}}: %{{[0-9]*}}:_(s32) = G_PHI %{{[0-9]*}}:_(s32), %bb.3, %{{[0-9]*}}:_(s32), %bb.2
 
 # CHECK-LABEL: BLOCK bb.5
-# CHECK: DIVERGENT: %{{[0-9]*}}: %{{[0-9]*}}:_(s32) = G_PHI %{{[0-9]*}}:_(s32), %bb.3, %{{[0-9]*}}:_(s32), %bb.4
+# CHECK-NOT: DIVERGENT: %{{[0-9]*}}: %{{[0-9]*}}:_(s32) = G_PHI %{{[0-9]*}}:_(s32), %bb.3, %{{[0-9]*}}:_(s32), %bb.4
 
 ---
 name:            hidden_loop_diverge

llvm/test/Analysis/UniformityAnalysis/AMDGPU/MIR/uses-value-from-cycle.mir

@@ -40,10 +40,10 @@ body:             |
 
   bb.5:
     successors: %bb.6(0x04000000), %bb.2(0x7c000000)
-    ; CHECK: DIVERGENT: %{{[0-9]}}: %{{[0-9]}}:_(s32) = G_PHI
-    ; CHECK: DIVERGENT: %{{[0-9]}}: %{{[0-9]}}:_(s32) = G_PHI
-    ; CHECK: DIVERGENT: %{{[0-9]}}: %{{[0-9]}}:_(s32) = G_PHI
-    ; CHECK-NOT: DIVERGENT: %{{[0-9]}}: %{{[0-9]}}:sreg_32_xm0_xexec(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.if.break)
+    ; CHECK-NOT: DIVERGENT: %{{[0-9]*}}: %{{[0-9]*}}:_(s32) = G_PHI
+    ; CHECK-NOT: DIVERGENT: %{{[0-9]*}}: %{{[0-9]*}}:_(s32) = G_PHI
+    ; CHECK:     DIVERGENT: %{{[0-9]*}}: %{{[0-9]*}}:_(s1) = G_PHI
+    ; CHECK-NOT: DIVERGENT: %{{[0-9]*}}: %{{[0-9]*}}:sreg_32_xm0_xexec(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.if.break)
     %19:_(s32) = G_PHI %18(s32), %bb.7, %25(s32), %bb.4
     %20:_(s32) = G_PHI %6(s32), %bb.7, %25(s32), %bb.4
     %21:_(s1) = G_PHI %34(s1), %bb.7, %33(s1), %bb.4

llvm/test/CodeGen/AMDGPU/GlobalISel/divergence-structurizer.mir

@@ -971,12 +971,10 @@ body: |
   ; GFX10-NEXT:   [[COPY5:%[0-9]+]]:_(s32) = COPY $vgpr5
   ; GFX10-NEXT:   [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 0
   ; GFX10-NEXT:   [[DEF:%[0-9]+]]:_(s1) = G_IMPLICIT_DEF
-  ; GFX10-NEXT:   [[COPY6:%[0-9]+]]:sreg_32(s1) = COPY [[DEF]](s1)
   ; GFX10-NEXT:   [[ICMP:%[0-9]+]]:_(s1) = G_ICMP intpred(sgt), [[COPY4]](s32), [[COPY1]]
   ; GFX10-NEXT:   [[DEF1:%[0-9]+]]:sreg_32(s1) = IMPLICIT_DEF
   ; GFX10-NEXT:   [[DEF2:%[0-9]+]]:sreg_32(s1) = IMPLICIT_DEF
-  ; GFX10-NEXT:   [[DEF3:%[0-9]+]]:sreg_32(s1) = IMPLICIT_DEF
-  ; GFX10-NEXT:   [[COPY7:%[0-9]+]]:sreg_32(s1) = COPY [[ICMP]](s1)
+  ; GFX10-NEXT:   [[COPY6:%[0-9]+]]:sreg_32(s1) = COPY [[ICMP]](s1)
   ; GFX10-NEXT:   G_BR %bb.7
   ; GFX10-NEXT: {{  $}}
   ; GFX10-NEXT: bb.1:
@@ -989,19 +987,18 @@ body: |
   ; GFX10-NEXT: bb.2:
   ; GFX10-NEXT:   successors: %bb.4(0x40000000), %bb.7(0x40000000)
   ; GFX10-NEXT: {{  $}}
-  ; GFX10-NEXT:   [[PHI:%[0-9]+]]:sreg_32_xm0_xexec(s1) = PHI %67(s1), %bb.6, %71(s1), %bb.7
-  ; GFX10-NEXT:   [[PHI1:%[0-9]+]]:sreg_32(s1) = PHI %49(s1), %bb.6, %48(s1), %bb.7
-  ; GFX10-NEXT:   [[PHI2:%[0-9]+]]:sreg_32(s1) = PHI %35(s1), %bb.6, %34(s1), %bb.7
+  ; GFX10-NEXT:   [[PHI:%[0-9]+]]:sreg_32_xm0_xexec(s1) = PHI %53(s1), %bb.6, %57(s1), %bb.7
+  ; GFX10-NEXT:   [[PHI1:%[0-9]+]]:sreg_32(s1) = PHI %35(s1), %bb.6, %34(s1), %bb.7
+  ; GFX10-NEXT:   [[PHI2:%[0-9]+]]:_(s1) = G_PHI %12(s1), %bb.6, [[DEF]](s1), %bb.7
+  ; GFX10-NEXT:   [[COPY7:%[0-9]+]]:sreg_32_xm0_xexec(s1) = COPY [[PHI2]](s1)
   ; GFX10-NEXT:   [[COPY8:%[0-9]+]]:sreg_32_xm0_xexec(s1) = COPY [[PHI]](s1)
   ; GFX10-NEXT:   [[COPY9:%[0-9]+]]:sreg_32(s1) = COPY [[PHI1]](s1)
-  ; GFX10-NEXT:   [[COPY10:%[0-9]+]]:sreg_32(s1) = COPY [[PHI2]](s1)
-  ; GFX10-NEXT:   [[COPY11:%[0-9]+]]:sreg_32_xm0_xexec(s1) = COPY [[COPY10]](s1)
   ; GFX10-NEXT:   G_INTRINSIC_W_SIDE_EFFECTS intrinsic(@llvm.amdgcn.end.cf), %15(s32)
   ; GFX10-NEXT:   [[INT:%[0-9]+]]:sreg_32_xm0_xexec(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.if.break), [[COPY9]](s1), %17(s32)
   ; GFX10-NEXT:   [[S_ANDN2_B32_:%[0-9]+]]:sreg_32_xm0_xexec(s1) = S_ANDN2_B32 [[COPY8]](s1), $exec_lo, implicit-def $scc
-  ; GFX10-NEXT:   [[S_AND_B32_:%[0-9]+]]:sreg_32_xm0_xexec(s1) = S_AND_B32 $exec_lo, [[COPY11]](s1), implicit-def $scc
+  ; GFX10-NEXT:   [[S_AND_B32_:%[0-9]+]]:sreg_32_xm0_xexec(s1) = S_AND_B32 $exec_lo, [[COPY7]](s1), implicit-def $scc
   ; GFX10-NEXT:   [[S_OR_B32_:%[0-9]+]]:sreg_32_xm0_xexec(s1) = S_OR_B32 [[S_ANDN2_B32_]](s1), [[S_AND_B32_]](s1), implicit-def $scc
-  ; GFX10-NEXT:   [[COPY12:%[0-9]+]]:sreg_32_xm0_xexec(s1) = COPY [[S_OR_B32_]](s1)
+  ; GFX10-NEXT:   [[COPY10:%[0-9]+]]:sreg_32_xm0_xexec(s1) = COPY [[S_OR_B32_]](s1)
   ; GFX10-NEXT:   SI_LOOP [[INT]](s32), %bb.7, implicit-def $exec, implicit-def $scc, implicit $exec
   ; GFX10-NEXT:   G_BR %bb.4
   ; GFX10-NEXT: {{  $}}
@@ -1018,28 +1015,27 @@ body: |
   ; GFX10-NEXT: {{  $}}
   ; GFX10-NEXT:   G_INTRINSIC_W_SIDE_EFFECTS intrinsic(@llvm.amdgcn.end.cf), [[INT]](s32)
   ; GFX10-NEXT:   [[ICMP2:%[0-9]+]]:_(s1) = G_ICMP intpred(sgt), [[COPY5]](s32), [[COPY]]
-  ; GFX10-NEXT:   [[COPY13:%[0-9]+]]:sreg_32(s1) = COPY [[ICMP2]](s1)
+  ; GFX10-NEXT:   [[COPY11:%[0-9]+]]:sreg_32(s1) = COPY [[ICMP2]](s1)
   ; GFX10-NEXT:   [[C2:%[0-9]+]]:_(s1) = G_CONSTANT i1 true
-  ; GFX10-NEXT:   [[COPY14:%[0-9]+]]:sreg_32_xm0_xexec(s1) = COPY [[C2]](s1)
+  ; GFX10-NEXT:   [[COPY12:%[0-9]+]]:sreg_32_xm0_xexec(s1) = COPY [[C2]](s1)
   ; GFX10-NEXT:   [[XOR:%[0-9]+]]:_(s1) = G_XOR [[ICMP]], [[C2]]
   ; GFX10-NEXT:   [[OR:%[0-9]+]]:_(s1) = G_OR [[ICMP2]], [[XOR]]
   ; GFX10-NEXT:   [[INT2:%[0-9]+]]:sreg_32_xm0_xexec(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.if.break), [[OR]](s1), %25(s32)
-  ; GFX10-NEXT:   [[DEF4:%[0-9]+]]:sreg_32(s1) = IMPLICIT_DEF
-  ; GFX10-NEXT:   [[DEF5:%[0-9]+]]:sreg_32(s1) = IMPLICIT_DEF
-  ; GFX10-NEXT:   [[S_ANDN2_B32_1:%[0-9]+]]:sreg_32(s1) = S_ANDN2_B32 %63(s1), $exec_lo, implicit-def $scc
-  ; GFX10-NEXT:   [[S_AND_B32_1:%[0-9]+]]:sreg_32(s1) = S_AND_B32 $exec_lo, [[COPY13]](s1), implicit-def $scc
+  ; GFX10-NEXT:   [[DEF3:%[0-9]+]]:sreg_32(s1) = IMPLICIT_DEF
+  ; GFX10-NEXT:   [[S_ANDN2_B32_1:%[0-9]+]]:sreg_32(s1) = S_ANDN2_B32 %49(s1), $exec_lo, implicit-def $scc
+  ; GFX10-NEXT:   [[S_AND_B32_1:%[0-9]+]]:sreg_32(s1) = S_AND_B32 $exec_lo, [[COPY11]](s1), implicit-def $scc
   ; GFX10-NEXT:   [[S_OR_B32_1:%[0-9]+]]:sreg_32(s1) = S_OR_B32 [[S_ANDN2_B32_1]](s1), [[S_AND_B32_1]](s1), implicit-def $scc
-  ; GFX10-NEXT:   [[S_ANDN2_B32_2:%[0-9]+]]:sreg_32_xm0_xexec(s1) = S_ANDN2_B32 [[COPY12]](s1), $exec_lo, implicit-def $scc
-  ; GFX10-NEXT:   [[S_AND_B32_2:%[0-9]+]]:sreg_32_xm0_xexec(s1) = S_AND_B32 $exec_lo, [[COPY14]](s1), implicit-def $scc
+  ; GFX10-NEXT:   [[S_ANDN2_B32_2:%[0-9]+]]:sreg_32_xm0_xexec(s1) = S_ANDN2_B32 [[COPY10]](s1), $exec_lo, implicit-def $scc
+  ; GFX10-NEXT:   [[S_AND_B32_2:%[0-9]+]]:sreg_32_xm0_xexec(s1) = S_AND_B32 $exec_lo, [[COPY12]](s1), implicit-def $scc
   ; GFX10-NEXT:   [[S_OR_B32_2:%[0-9]+]]:sreg_32_xm0_xexec(s1) = S_OR_B32 [[S_ANDN2_B32_2]](s1), [[S_AND_B32_2]](s1), implicit-def $scc
   ; GFX10-NEXT:   SI_LOOP [[INT2]](s32), %bb.7, implicit-def $exec, implicit-def $scc, implicit $exec
   ; GFX10-NEXT:   G_BR %bb.5
   ; GFX10-NEXT: {{  $}}
   ; GFX10-NEXT: bb.5:
   ; GFX10-NEXT:   [[PHI4:%[0-9]+]]:_(s32) = G_PHI [[INT2]](s32), %bb.4
-  ; GFX10-NEXT:   [[COPY15:%[0-9]+]]:sreg_32(s1) = COPY [[S_OR_B32_1]](s1)
+  ; GFX10-NEXT:   [[COPY13:%[0-9]+]]:sreg_32(s1) = COPY [[S_OR_B32_1]](s1)
   ; GFX10-NEXT:   G_INTRINSIC_W_SIDE_EFFECTS intrinsic(@llvm.amdgcn.end.cf), [[PHI4]](s32)
-  ; GFX10-NEXT:   [[SELECT:%[0-9]+]]:_(s32) = G_SELECT [[COPY15]](s1), [[COPY3]], [[COPY2]]
+  ; GFX10-NEXT:   [[SELECT:%[0-9]+]]:_(s32) = G_SELECT [[COPY13]](s1), [[COPY3]], [[COPY2]]
   ; GFX10-NEXT:   [[INTRINSIC_CONVERGENT:%[0-9]+]]:_(s32) = G_INTRINSIC_CONVERGENT intrinsic(@llvm.amdgcn.readfirstlane), [[SELECT]](s32)
   ; GFX10-NEXT:   $sgpr0 = COPY [[INTRINSIC_CONVERGENT]](s32)
   ; GFX10-NEXT:   SI_RETURN_TO_EPILOG implicit $sgpr0
@@ -1049,42 +1045,32 @@ body: |
   ; GFX10-NEXT: {{  $}}
   ; GFX10-NEXT:   [[PHI5:%[0-9]+]]:_(s32) = G_PHI [[INT1]](s32), %bb.3
   ; GFX10-NEXT:   [[C3:%[0-9]+]]:_(s1) = G_CONSTANT i1 false
-  ; GFX10-NEXT:   [[COPY16:%[0-9]+]]:sreg_32(s1) = COPY [[C3]](s1)
-  ; GFX10-NEXT:   [[COPY17:%[0-9]+]]:sreg_32(s1) = COPY [[C3]](s1)
+  ; GFX10-NEXT:   [[COPY14:%[0-9]+]]:sreg_32(s1) = COPY [[C3]](s1)
   ; GFX10-NEXT:   G_INTRINSIC_W_SIDE_EFFECTS intrinsic(@llvm.amdgcn.end.cf), [[PHI5]](s32)
   ; GFX10-NEXT:   [[S_ANDN2_B32_3:%[0-9]+]]:sreg_32(s1) = S_ANDN2_B32 %42(s1), $exec_lo, implicit-def $scc
-  ; GFX10-NEXT:   [[S_AND_B32_3:%[0-9]+]]:sreg_32(s1) = S_AND_B32 $exec_lo, [[COPY17]](s1), implicit-def $scc
+  ; GFX10-NEXT:   [[S_AND_B32_3:%[0-9]+]]:sreg_32(s1) = S_AND_B32 $exec_lo, [[COPY14]](s1), implicit-def $scc
   ; GFX10-NEXT:   [[S_OR_B32_3:%[0-9]+]]:sreg_32(s1) = S_OR_B32 [[S_ANDN2_B32_3]](s1), [[S_AND_B32_3]](s1), implicit-def $scc
-  ; GFX10-NEXT:   [[S_ANDN2_B32_4:%[0-9]+]]:sreg_32(s1) = S_ANDN2_B32 %56(s1), $exec_lo, implicit-def $scc
-  ; GFX10-NEXT:   [[S_AND_B32_4:%[0-9]+]]:sreg_32(s1) = S_AND_B32 $exec_lo, [[COPY16]](s1), implicit-def $scc
-  ; GFX10-NEXT:   [[S_OR_B32_4:%[0-9]+]]:sreg_32(s1) = S_OR_B32 [[S_ANDN2_B32_4]](s1), [[S_AND_B32_4]](s1), implicit-def $scc
-  ; GFX10-NEXT:   [[DEF6:%[0-9]+]]:sreg_32_xm0_xexec(s1) = IMPLICIT_DEF
+  ; GFX10-NEXT:   [[DEF4:%[0-9]+]]:sreg_32_xm0_xexec(s1) = IMPLICIT_DEF
   ; GFX10-NEXT:   G_BR %bb.2
   ; GFX10-NEXT: {{  $}}
   ; GFX10-NEXT: bb.7:
   ; GFX10-NEXT:   successors: %bb.1(0x40000000), %bb.2(0x40000000)
   ; GFX10-NEXT: {{  $}}
-  ; GFX10-NEXT:   [[PHI6:%[0-9]+]]:sreg_32_xm0_xexec(s1) = PHI [[COPY7]](s1), %bb.0, [[S_OR_B32_]](s1), %bb.2, [[S_OR_B32_2]](s1), %bb.4
-  ; GFX10-NEXT:   [[PHI7:%[0-9]+]]:sreg_32(s1) = PHI [[DEF3]](s1), %bb.0, [[PHI7]](s1), %bb.2, [[S_OR_B32_1]](s1), %bb.4
-  ; GFX10-NEXT:   [[PHI8:%[0-9]+]]:sreg_32(s1) = PHI [[DEF2]](s1), %bb.0, [[PHI1]](s1), %bb.2, [[DEF5]](s1), %bb.4
-  ; GFX10-NEXT:   [[PHI9:%[0-9]+]]:sreg_32(s1) = PHI [[DEF1]](s1), %bb.0, [[PHI2]](s1), %bb.2, [[DEF4]](s1), %bb.4
-  ; GFX10-NEXT:   [[PHI10:%[0-9]+]]:_(s32) = G_PHI [[INT2]](s32), %bb.4, [[PHI10]](s32), %bb.2, [[C]](s32), %bb.0
-  ; GFX10-NEXT:   [[PHI11:%[0-9]+]]:_(s32) = G_PHI [[C]](s32), %bb.4, [[INT]](s32), %bb.2, [[C]](s32), %bb.0
-  ; GFX10-NEXT:   [[COPY18:%[0-9]+]]:sreg_32_xm0_xexec(s1) = COPY [[PHI6]](s1)
-  ; GFX10-NEXT:   [[COPY19:%[0-9]+]]:sreg_32(s1) = COPY [[PHI7]](s1)
-  ; GFX10-NEXT:   [[COPY20:%[0-9]+]]:sreg_32(s1) = COPY [[PHI8]](s1)
-  ; GFX10-NEXT:   [[COPY21:%[0-9]+]]:sreg_32(s1) = COPY [[PHI9]](s1)
+  ; GFX10-NEXT:   [[PHI6:%[0-9]+]]:sreg_32_xm0_xexec(s1) = PHI [[COPY6]](s1), %bb.0, [[S_OR_B32_]](s1), %bb.2, [[S_OR_B32_2]](s1), %bb.4
+  ; GFX10-NEXT:   [[PHI7:%[0-9]+]]:sreg_32(s1) = PHI [[DEF2]](s1), %bb.0, [[PHI7]](s1), %bb.2, [[S_OR_B32_1]](s1), %bb.4
+  ; GFX10-NEXT:   [[PHI8:%[0-9]+]]:sreg_32(s1) = PHI [[DEF1]](s1), %bb.0, [[PHI1]](s1), %bb.2, [[DEF3]](s1), %bb.4
+  ; GFX10-NEXT:   [[PHI9:%[0-9]+]]:_(s32) = G_PHI [[INT2]](s32), %bb.4, [[PHI9]](s32), %bb.2, [[C]](s32), %bb.0
+  ; GFX10-NEXT:   [[PHI10:%[0-9]+]]:_(s32) = G_PHI [[C]](s32), %bb.4, [[INT]](s32), %bb.2, [[C]](s32), %bb.0
+  ; GFX10-NEXT:   [[COPY15:%[0-9]+]]:sreg_32_xm0_xexec(s1) = COPY [[PHI6]](s1)
+  ; GFX10-NEXT:   [[COPY16:%[0-9]+]]:sreg_32(s1) = COPY [[PHI7]](s1)
+  ; GFX10-NEXT:   [[COPY17:%[0-9]+]]:sreg_32(s1) = COPY [[PHI8]](s1)
   ; GFX10-NEXT:   [[C4:%[0-9]+]]:_(s1) = G_CONSTANT i1 true
-  ; GFX10-NEXT:   [[COPY22:%[0-9]+]]:sreg_32(s1) = COPY [[C4]](s1)
-  ; GFX10-NEXT:   [[S_ANDN2_B32_5:%[0-9]+]]:sreg_32(s1) = S_ANDN2_B32 [[COPY21]](s1), $exec_lo, implicit-def $scc
-  ; GFX10-NEXT:   [[S_AND_B32_5:%[0-9]+]]:sreg_32(s1) = S_AND_B32 $exec_lo, [[COPY6]](s1), implicit-def $scc
-  ; GFX10-NEXT:   [[S_OR_B32_5:%[0-9]+]]:sreg_32(s1) = S_OR_B32 [[S_ANDN2_B32_5]](s1), [[S_AND_B32_5]](s1), implicit-def $scc
-  ; GFX10-NEXT:   [[COPY23:%[0-9]+]]:sreg_32(s1) = COPY [[S_OR_B32_5]](s1)
-  ; GFX10-NEXT:   [[S_ANDN2_B32_6:%[0-9]+]]:sreg_32(s1) = S_ANDN2_B32 [[COPY20]](s1), $exec_lo, implicit-def $scc
-  ; GFX10-NEXT:   [[S_AND_B32_6:%[0-9]+]]:sreg_32(s1) = S_AND_B32 $exec_lo, [[COPY22]](s1), implicit-def $scc
-  ; GFX10-NEXT:   [[S_OR_B32_6:%[0-9]+]]:sreg_32(s1) = S_OR_B32 [[S_ANDN2_B32_6]](s1), [[S_AND_B32_6]](s1), implicit-def $scc
-  ; GFX10-NEXT:   [[COPY24:%[0-9]+]]:sreg_32(s1) = COPY [[S_OR_B32_6]](s1)
-  ; GFX10-NEXT:   [[SI_IF:%[0-9]+]]:sreg_32_xm0_xexec(s32) = SI_IF [[COPY18]](s1), %bb.2, implicit-def $exec, implicit-def $scc, implicit $exec
+  ; GFX10-NEXT:   [[COPY18:%[0-9]+]]:sreg_32(s1) = COPY [[C4]](s1)
+  ; GFX10-NEXT:   [[S_ANDN2_B32_4:%[0-9]+]]:sreg_32(s1) = S_ANDN2_B32 [[COPY17]](s1), $exec_lo, implicit-def $scc
+  ; GFX10-NEXT:   [[S_AND_B32_4:%[0-9]+]]:sreg_32(s1) = S_AND_B32 $exec_lo, [[COPY18]](s1), implicit-def $scc
+  ; GFX10-NEXT:   [[S_OR_B32_4:%[0-9]+]]:sreg_32(s1) = S_OR_B32 [[S_ANDN2_B32_4]](s1), [[S_AND_B32_4]](s1), implicit-def $scc
+  ; GFX10-NEXT:   [[COPY19:%[0-9]+]]:sreg_32(s1) = COPY [[S_OR_B32_4]](s1)
+  ; GFX10-NEXT:   [[SI_IF:%[0-9]+]]:sreg_32_xm0_xexec(s32) = SI_IF [[COPY15]](s1), %bb.2, implicit-def $exec, implicit-def $scc, implicit $exec
   ; GFX10-NEXT:   G_BR %bb.1
   bb.0:
     successors: %bb.7(0x80000000)