diff --git a/llvm/lib/Target/AMDGPU/AMDGPUTargetMachine.cpp b/llvm/lib/Target/AMDGPU/AMDGPUTargetMachine.cpp
--- a/llvm/lib/Target/AMDGPU/AMDGPUTargetMachine.cpp
+++ b/llvm/lib/Target/AMDGPU/AMDGPUTargetMachine.cpp
@@ -1039,6 +1039,7 @@
   // FIXME: We need to run a pass to propagate the attributes when calls are
   // supported.
 
+  addPass(createSinkingPass());
   // Merge divergent exit nodes. StructurizeCFG won't recognize the multi-exit
   // regions formed by them.
   addPass(&AMDGPUUnifyDivergentExitNodesID);
@@ -1049,7 +1050,6 @@
     }
     addPass(createStructurizeCFGPass(false)); // true -> SkipUniformRegions
   }
-  addPass(createSinkingPass());
   addPass(createAMDGPUAnnotateUniformValues());
   if (!LateCFGStructurize) {
     addPass(createSIAnnotateControlFlowPass());
diff --git a/llvm/test/CodeGen/AMDGPU/loop_exit_with_xor.ll b/llvm/test/CodeGen/AMDGPU/loop_exit_with_xor.ll
--- a/llvm/test/CodeGen/AMDGPU/loop_exit_with_xor.ll
+++ b/llvm/test/CodeGen/AMDGPU/loop_exit_with_xor.ll
@@ -6,11 +6,11 @@
 ; with exec.
 
 ; GCN-LABEL: {{^}}needs_and:
-; GCN: s_xor_b64 [[REG1:[^ ,]*]], {{[^ ,]*, -1$}}
-; GCN: s_and_b64 [[REG2:[^ ,]*]], exec, [[REG1]]
-; GCN: s_or_b64 [[REG3:[^ ,]*]], [[REG2]],
-; GCN: s_andn2_b64 exec, exec, [[REG3]]
 
+; GCN: s_or_b64 exec, exec, [[REG1:[^ ,]*]]
+; GCN: s_andn2_b64 exec, exec, [[REG2:[^ ,]*]]
+; GCN: s_or_b64 [[REG2:[^ ,]*]], [[REG1:[^ ,]*]], [[REG2:[^ ,]*]]
+; GCN: s_or_b64 exec, exec, [[REG2:[^ ,]*]]
 define void @needs_and(i32 %arg) {
 entry:
   br label %loop
diff --git a/llvm/test/CodeGen/AMDGPU/multilevel-break.ll b/llvm/test/CodeGen/AMDGPU/multilevel-break.ll
--- a/llvm/test/CodeGen/AMDGPU/multilevel-break.ll
+++ b/llvm/test/CodeGen/AMDGPU/multilevel-break.ll
@@ -73,17 +73,16 @@
 ; GCN-NEXT:  BB0_4: ; %LOOP
 ; GCN-NEXT:    ; Parent Loop BB0_2 Depth=1
 ; GCN-NEXT:    ; => This Inner Loop Header: Depth=2
-; GCN-NEXT:    v_mov_b32_e32 v1, v0
-; GCN-NEXT:    v_add_i32_e32 v0, vcc, 1, v1
-; GCN-NEXT:    v_cmp_lt_i32_e32 vcc, v1, v4
+; GCN-NEXT:    v_cmp_lt_i32_e32 vcc, v0, v4
 ; GCN-NEXT:    s_or_b64 s[2:3], s[2:3], exec
 ; GCN-NEXT:    s_or_b64 s[6:7], s[6:7], exec
 ; GCN-NEXT:    s_and_saveexec_b64 s[8:9], vcc
 ; GCN-NEXT:    s_cbranch_execz BB0_3
 ; GCN-NEXT:  ; %bb.5: ; %ENDIF
 ; GCN-NEXT:    ; in Loop: Header=BB0_4 Depth=2
-; GCN-NEXT:    v_cmp_ne_u32_e32 vcc, v5, v0
+; GCN-NEXT:    v_add_i32_e32 v0, vcc, 1, v0
 ; GCN-NEXT:    s_andn2_b64 s[2:3], s[2:3], exec
+; GCN-NEXT:    v_cmp_ne_u32_e32 vcc, v5, v0
 ; GCN-NEXT:    s_andn2_b64 s[6:7], s[6:7], exec
 ; GCN-NEXT:    s_and_b64 s[10:11], vcc, exec
 ; GCN-NEXT:    s_or_b64 s[6:7], s[6:7], s[10:11]
@@ -196,7 +195,7 @@
 ; GCN-NEXT:    s_cbranch_execz BB1_9
 ; GCN-NEXT:  BB1_2: ; %bb1
 ; GCN-NEXT:    ; =>This Inner Loop Header: Depth=1
-; GCN-NEXT:    buffer_load_dword v1, off, s[0:3], 0
+; GCN-NEXT:    buffer_load_dword v1, off, s[0:3], 0 glc
 ; GCN-NEXT:    s_waitcnt vmcnt(0)
 ; GCN-NEXT:    v_cmp_gt_i32_e32 vcc, 1, v1
 ; GCN-NEXT:    s_mov_b64 s[6:7], -1
@@ -213,7 +212,7 @@
 ; GCN-NEXT:    s_cbranch_vccz BB1_5
 ; GCN-NEXT:  ; %bb.4: ; %case1
 ; GCN-NEXT:    ; in Loop: Header=BB1_2 Depth=1
-; GCN-NEXT:    buffer_load_dword v2, off, s[0:3], 0
+; GCN-NEXT:    buffer_load_dword v2, off, s[0:3], 0 glc
 ; GCN-NEXT:    s_waitcnt vmcnt(0)
 ; GCN-NEXT:    v_cmp_ge_i32_e32 vcc, v0, v2
 ; GCN-NEXT:    s_mov_b64 s[8:9], 0
@@ -233,7 +232,7 @@
 ; GCN-NEXT:    s_cbranch_vccz BB1_1
 ; GCN-NEXT:  ; %bb.8: ; %case0
 ; GCN-NEXT:    ; in Loop: Header=BB1_2 Depth=1
-; GCN-NEXT:    buffer_load_dword v1, off, s[0:3], 0
+; GCN-NEXT:    buffer_load_dword v1, off, s[0:3], 0 glc
 ; GCN-NEXT:    s_waitcnt vmcnt(0)
 ; GCN-NEXT:    s_mov_b64 s[8:9], 0
 ; GCN-NEXT:    v_cmp_ge_i32_e32 vcc, v0, v1