Index: lib/Target/AMDGPU/AMDGPUTargetMachine.cpp
===================================================================
--- lib/Target/AMDGPU/AMDGPUTargetMachine.cpp
+++ lib/Target/AMDGPU/AMDGPUTargetMachine.cpp
@@ -886,6 +886,9 @@
 }
 
 void GCNPassConfig::addPreEmitPass() {
+  addPass(createSIMemoryLegalizerPass());
+  addPass(createSIInsertWaitcntsPass());
+
   // The hazard recognizer that runs as part of the post-ra scheduler does not
   // guarantee to be able handle all hazards correctly. This is because if there
   // are multiple scheduling regions in a basic block, the regions are scheduled
@@ -896,8 +899,6 @@
   // cases.
   addPass(&PostRAHazardRecognizerID);
 
-  addPass(createSIMemoryLegalizerPass());
-  addPass(createSIInsertWaitcntsPass());
   addPass(createSIShrinkInstructionsPass());
   addPass(&SIInsertSkipsPassID);
   addPass(createSIDebuggerInsertNopsPass());
Index: lib/Target/AMDGPU/SIMemoryLegalizer.cpp
===================================================================
--- lib/Target/AMDGPU/SIMemoryLegalizer.cpp
+++ lib/Target/AMDGPU/SIMemoryLegalizer.cpp
@@ -737,7 +737,7 @@
     case SIAtomicScope::WAVEFRONT:
     case SIAtomicScope::SINGLETHREAD:
       // The L1 cache keeps all memory operations in order for
-      // wavesfronts in the same work-group.
+      // wavefronts in the same work-group.
       break;
     default:
       llvm_unreachable("Unsupported synchronization scope");
Index: test/CodeGen/AMDGPU/llvm.amdgcn.mov.dpp.ll
===================================================================
--- test/CodeGen/AMDGPU/llvm.amdgcn.mov.dpp.ll
+++ test/CodeGen/AMDGPU/llvm.amdgcn.mov.dpp.ll
@@ -35,7 +35,8 @@
 ; VI: ; %endif
 ; VI-OPT: s_mov_b32
 ; VI-OPT: s_mov_b32
-; VI-NOOPT: s_nop 1
+; VI-NOOPT: s_waitcnt
+; VI-NOOPT-NEXT: s_nop 0
 ; VI: v_mov_b32_dpp [[VGPR0:v[0-9]+]], v{{[0-9]+}} quad_perm:[1,0,0,0] row_mask:0x1 bank_mask:0x1 bound_ctrl:0
 ; VI: s_nop 1
 ; VI: v_mov_b32_dpp [[VGPR1:v[0-9]+]], [[VGPR0]] quad_perm:[1,0,0,0] row_mask:0x1 bank_mask:0x1 bound_ctrl:0
Index: test/CodeGen/AMDGPU/llvm.amdgcn.update.dpp.ll
===================================================================
--- test/CodeGen/AMDGPU/llvm.amdgcn.update.dpp.ll
+++ test/CodeGen/AMDGPU/llvm.amdgcn.update.dpp.ll
@@ -12,6 +12,32 @@
   ret void
 }
 
+; VI-LABEL: {{^}}dpp_test1:
+; VI-OPT: v_add_u32_e32 [[REG:v[0-9]+]], vcc, v{{[0-9]+}}, v{{[0-9]+}}
+; VI-NOOPT: v_mov_b32_e32 v{{[0-9]+}}, 0
+; VI-NOOPT: v_mov_b32_e32 [[REG:v[0-9]+]], v{{[0-9]+}}
+; VI-NEXT: s_nop 1
+; VI-NEXT: v_mov_b32_dpp v2, [[REG]] quad_perm:[1,0,3,2] row_mask:0xf bank_mask:0xf
+@0 = internal unnamed_addr addrspace(3) global [448 x i32] undef, align 4
+define weak_odr amdgpu_kernel void @dpp_test1(i32* %arg) local_unnamed_addr {
+bb:
+  %tmp = tail call i32 @llvm.amdgcn.workitem.id.x()
+  %tmp1 = zext i32 %tmp to i64
+  %tmp2 = getelementptr inbounds [448 x i32], [448 x i32] addrspace(3)* @0, i32 0, i32 %tmp
+  %tmp3 = load i32, i32 addrspace(3)* %tmp2, align 4
+  fence syncscope("workgroup") release
+  tail call void @llvm.amdgcn.s.barrier()
+  fence syncscope("workgroup") acquire
+  %tmp4 = add nsw i32 %tmp3, %tmp3
+  %tmp5 = tail call i32 @llvm.amdgcn.update.dpp.i32(i32 0, i32 %tmp4, i32 177, i32 15, i32 15, i1 zeroext false)
+  %tmp6 = add nsw i32 %tmp5, %tmp4
+  %tmp7 = getelementptr inbounds i32, i32* %arg, i64 %tmp1
+  store i32 %tmp6, i32* %tmp7, align 4
+  ret void
+}
+
+declare i32 @llvm.amdgcn.workitem.id.x()
+declare void @llvm.amdgcn.s.barrier()
 declare i32 @llvm.amdgcn.update.dpp.i32(i32, i32, i32, i32, i32, i1) #0
 
 attributes #0 = { nounwind readnone convergent }
Index: test/CodeGen/AMDGPU/memory_clause.ll
===================================================================
--- test/CodeGen/AMDGPU/memory_clause.ll
+++ test/CodeGen/AMDGPU/memory_clause.ll
@@ -105,8 +105,9 @@
 
 ; GCN-LABEL: {{^}}vector_clause_indirect:
 ; GCN: global_load_dwordx2 [[ADDR:v\[[0-9:]+\]]], v[{{[0-9:]+}}], off
-; GCN-NEXT: s_nop
+; GCN-NEXT: s_nop 0
 ; GCN-NEXT: s_waitcnt vmcnt(0)
+; GCN-NEXT: s_nop 0
 ; GCN-NEXT: global_load_dwordx4 v[{{[0-9:]+}}], [[ADDR]], off
 ; GCN-NEXT: global_load_dwordx4 v[{{[0-9:]+}}], [[ADDR]], off offset:16
 define amdgpu_kernel void @vector_clause_indirect(i64 addrspace(1)* noalias nocapture readonly %arg, <4 x i32> addrspace(1)* noalias nocapture readnone %arg1, <4 x i32> addrspace(1)* noalias nocapture %arg2) {