Index: lib/CodeGen/MachineInstr.cpp
===================================================================
--- lib/CodeGen/MachineInstr.cpp
+++ lib/CodeGen/MachineInstr.cpp
@@ -935,7 +935,8 @@
       continue;
     if (MOReg == Reg || (TRI && TargetRegisterInfo::isPhysicalRegister(MOReg) &&
                          TargetRegisterInfo::isPhysicalRegister(Reg) &&
-                         TRI->isSubRegister(MOReg, Reg)))
+                         (TRI->isSubRegister(MOReg, Reg) ||
+                          TRI->isSubRegister(Reg, MOReg))))
       if (!isKill || MO.isKill())
         return i;
   }
Index: test/CodeGen/AMDGPU/optimize-if-exec-masking.mir
===================================================================
--- test/CodeGen/AMDGPU/optimize-if-exec-masking.mir
+++ test/CodeGen/AMDGPU/optimize-if-exec-masking.mir
@@ -131,6 +131,26 @@
     ret void
   }
 
+  define amdgpu_kernel void @if_and_xor_read_exec_copy_subreg(i32 %z, i32 %v) #0 {
+  main_body:
+    %id = call i32 @llvm.amdgcn.workitem.id.x()
+    %cc = icmp eq i32 %id, 0
+    %0 = call { i1, i64 } @llvm.amdgcn.if(i1 %cc)
+    %1 = extractvalue { i1, i64 } %0, 0
+    %2 = extractvalue { i1, i64 } %0, 1
+    br i1 %1, label %if, label %end
+
+  if:                                               ; preds = %main_body
+    %v.if = load volatile i32, i32 addrspace(1)* undef
+    br label %end
+
+  end:                                              ; preds = %if, %main_body
+    %r = phi i32 [ 4, %main_body ], [ %v.if, %if ]
+    call void @llvm.amdgcn.end.cf(i64 %2)
+    store i32 %r, i32 addrspace(1)* undef
+    ret void
+  }
+
   ; Function Attrs: nounwind readnone
   declare i32 @llvm.amdgcn.workitem.id.x() #1
 
@@ -731,3 +751,61 @@
     S_ENDPGM
 
 ...
+---
+# A read from exec copy subreg prevents optimization
+# CHECK-LABEL: name: if_and_xor_read_exec_copy_subreg{{$}}
+# CHECK: $sgpr0_sgpr1 = COPY $exec
+# CHECK-NEXT: $sgpr4 = S_MOV_B32 $sgpr1
+name:            if_and_xor_read_exec_copy_subreg
+alignment:       0
+exposesReturnsTwice: false
+legalized:       false
+regBankSelected: false
+selected:        false
+tracksRegLiveness: true
+liveins:
+  - { reg: '$vgpr0' }
+frameInfo:
+  isFrameAddressTaken: false
+  isReturnAddressTaken: false
+  hasStackMap:     false
+  hasPatchPoint:   false
+  stackSize:       0
+  offsetAdjustment: 0
+  maxAlignment:    0
+  adjustsStack:    false
+  hasCalls:        false
+  maxCallFrameSize: 0
+  hasOpaqueSPAdjustment: false
+  hasVAStart:      false
+  hasMustTailInVarArgFunc: false
+body:             |
+  bb.0.main_body:
+    liveins: $vgpr0
+
+    $sgpr0_sgpr1 = COPY $exec
+    $sgpr4 = S_MOV_B32 $sgpr1
+    $vcc = V_CMP_EQ_I32_e64 0, killed $vgpr0, implicit $exec
+    $vgpr0 = V_MOV_B32_e32 4, implicit $exec
+    $sgpr2_sgpr3 = S_AND_B64 $sgpr0_sgpr1, killed $vcc, implicit-def $scc
+    $sgpr0_sgpr1 = S_XOR_B64 $sgpr2_sgpr3, killed $sgpr0_sgpr1, implicit-def $scc
+    $exec = S_MOV_B64_term killed $sgpr2_sgpr3
+    SI_MASK_BRANCH %bb.2, implicit $exec
+    S_BRANCH %bb.1
+
+  bb.1.if:
+    liveins: $sgpr0_sgpr1
+
+    $sgpr7 = S_MOV_B32 61440
+    $sgpr6 = S_MOV_B32 -1
+    $vgpr0 = BUFFER_LOAD_DWORD_OFFSET $sgpr4_sgpr5_sgpr6_sgpr7, 0, 0, 0, 0, 0, implicit $exec :: (volatile load 4 from `i32 addrspace(1)* undef`)
+
+  bb.2.end:
+    liveins: $vgpr0, $sgpr0_sgpr1
+
+    $exec = S_OR_B64 $exec, killed $sgpr0_sgpr1, implicit-def $scc
+    $sgpr3 = S_MOV_B32 61440
+    $sgpr2 = S_MOV_B32 -1
+    BUFFER_STORE_DWORD_OFFSET killed $vgpr0, $sgpr0_sgpr1_sgpr2_sgpr3, 0, 0, 0, 0, 0, implicit $exec :: (store 4 into `i32 addrspace(1)* undef`)
+    S_ENDPGM
+...