Index: lib/Target/AMDGPU/AMDGPURegisterInfo.h
===================================================================
--- lib/Target/AMDGPU/AMDGPURegisterInfo.h
+++ lib/Target/AMDGPU/AMDGPURegisterInfo.h
@@ -27,6 +27,8 @@
 struct AMDGPURegisterInfo : public AMDGPUGenRegisterInfo {
   AMDGPURegisterInfo();
 
+  bool enableMultipleCopyHints() const override { return true; }
+
   /// \returns the sub reg enum value for the given \p Channel
   /// (e.g. getSubRegFromChannel(0) -> AMDGPU::sub0)
   unsigned getSubRegFromChannel(unsigned Channel) const;
Index: test/CodeGen/AMDGPU/callee-special-input-sgprs.ll
===================================================================
--- test/CodeGen/AMDGPU/callee-special-input-sgprs.ll
+++ test/CodeGen/AMDGPU/callee-special-input-sgprs.ll
@@ -208,8 +208,8 @@
 ; GCN: enable_sgpr_workgroup_id_z = 0
 
 ; GCN: s_mov_b32 s33, s8
-; GCN: s_mov_b32 s4, s33
-; GCN: s_mov_b32 s6, s7
+; GCN-DAG: s_mov_b32 s4, s33
+; GCN-DAG: s_mov_b32 s6, s7
 ; GCN: s_mov_b32 s32, s33
 ; GCN: s_swappc_b64
 define amdgpu_kernel void @kern_indirect_use_workgroup_id_y() #1 {
@@ -223,8 +223,8 @@
 ; GCN: enable_sgpr_workgroup_id_z = 1
 
 ; GCN: s_mov_b32 s33, s8
-; GCN: s_mov_b32 s4, s33
-; GCN: s_mov_b32 s6, s7
+; GCN-DAG: s_mov_b32 s4, s33
+; GCN-DAG: s_mov_b32 s6, s7
 ; GCN: s_swappc_b64
 define amdgpu_kernel void @kern_indirect_use_workgroup_id_z() #1 {
   call void @use_workgroup_id_z()
@@ -396,7 +396,7 @@
 
 ; GCN-DAG: s_mov_b32 s33, s8
 ; GCN-DAG: v_mov_b32_e32 v0, 0x22b
-; GCN: s_mov_b32 s4, s33
+; GCN-DAG: s_mov_b32 s4, s33
 ; GCN-DAG: s_mov_b32 s6, s7
 ; GCN-DAG: s_mov_b32 s32, s33
 ; GCN: s_swappc_b64
@@ -412,7 +412,7 @@
 
 ; GCN: s_mov_b32 s33, s8
 ; GCN-DAG: v_mov_b32_e32 v0, 0x22b
-; GCN: s_mov_b32 s4, s33
+; GCN-DAG: s_mov_b32 s4, s33
 ; GCN-DAG: s_mov_b32 s6, s7
 
 ; GCN: s_mov_b32 s32, s33
Index: test/CodeGen/AMDGPU/callee-special-input-vgprs.ll
===================================================================
--- test/CodeGen/AMDGPU/callee-special-input-vgprs.ll
+++ test/CodeGen/AMDGPU/callee-special-input-vgprs.ll
@@ -220,8 +220,8 @@
 ; GCN-LABEL: {{^}}kern_indirect_other_arg_use_workitem_id_z:
 ; GCN: enable_vgpr_workitem_id = 2
 
-; GCN: v_mov_b32_e32 v0, 0x22b
-; GCN: v_mov_b32_e32 v1, v2
+; GCN-DAG: v_mov_b32_e32 v0, 0x22b
+; GCN-DAG: v_mov_b32_e32 v1, v2
 ; GCN: s_swappc_b64
 ; GCN-NOT: v0
 define amdgpu_kernel void @kern_indirect_other_arg_use_workitem_id_z() #1 {
Index: test/CodeGen/AMDGPU/ret.ll
===================================================================
--- test/CodeGen/AMDGPU/ret.ll
+++ test/CodeGen/AMDGPU/ret.ll
@@ -126,9 +126,9 @@
 ; GCN-LABEL: {{^}}vgpr_ps_addr119:
 ; GCN-DAG: v_mov_b32_e32 v0, v2
 ; GCN-DAG: v_mov_b32_e32 v1, v3
-; GCN: v_mov_b32_e32 v2, v6
-; GCN: v_mov_b32_e32 v3, v8
-; GCN: v_mov_b32_e32 v4, v12
+; GCN-DAG: v_mov_b32_e32 v2, v6
+; GCN-DAG: v_mov_b32_e32 v3, v8
+; GCN-DAG: v_mov_b32_e32 v4, v12
 ; GCN-NOT: s_endpgm
 define amdgpu_ps { float, float, float, float, float } @vgpr_ps_addr119([9 x <16 x i8>] addrspace(4)* byval %arg, i32 inreg %arg1, i32 inreg %arg2, <2 x i32> %arg3, <2 x i32> %arg4, <2 x i32> %arg5, <3 x i32> %arg6, <2 x i32> %arg7, <2 x i32> %arg8, <2 x i32> %arg9, float %arg10, float %arg11, float %arg12, float %arg13, float %arg14, float %arg15, float %arg16, float %arg17, float %arg18) #3 {
 bb:
@@ -178,8 +178,8 @@
 }
 
 ; GCN-LABEL: {{^}}sgpr:
-; GCN: s_add_i32 s0, s3, 2
-; GCN: s_mov_b32 s2, s3
+; GCN-DAG: s_add_i32 s0, s3, 2
+; GCN-DAG: s_mov_b32 s2, s3
 ; GCN-NOT: s_endpgm
 define amdgpu_vs { i32, i32, i32 } @sgpr([9 x <16 x i8>] addrspace(4)* byval %arg, i32 inreg %arg1, i32 inreg %arg2, float %arg3) #0 {
 bb: