diff --git a/lib/Target/R600/AMDGPUSubtarget.h b/lib/Target/R600/AMDGPUSubtarget.h
index 0c0145cb2b3..2f2a152519a 100644
--- a/lib/Target/R600/AMDGPUSubtarget.h
+++ b/lib/Target/R600/AMDGPUSubtarget.h
@@ -243,6 +243,10 @@ public:
     // FIXME: Not sure what this is for other subtagets.
     llvm_unreachable("do not know max waves per CU for this subtarget.");
   }
+
+  bool enableSubRegLiveness() const override {
+    return true;
+  }
 };
 
 } // End namespace llvm
diff --git a/test/CodeGen/R600/imm.ll b/test/CodeGen/R600/imm.ll
index 8a244776912..8577a7e5799 100644
--- a/test/CodeGen/R600/imm.ll
+++ b/test/CodeGen/R600/imm.ll
@@ -24,7 +24,7 @@ entry:
 
 ; CHECK-LABEL: {{^}}store_inline_imm_0.0_f32
 ; CHECK: v_mov_b32_e32 [[REG:v[0-9]+]], 0{{$}}
-; CHECK-NEXT: buffer_store_dword [[REG]]
+; CHECK: buffer_store_dword [[REG]]
 define void @store_inline_imm_0.0_f32(float addrspace(1)* %out) {
   store float 0.0, float addrspace(1)* %out
   ret void
@@ -32,7 +32,7 @@ define void @store_inline_imm_0.0_f32(float addrspace(1)* %out) {
 
 ; CHECK-LABEL: {{^}}store_imm_neg_0.0_f32
 ; CHECK: v_mov_b32_e32 [[REG:v[0-9]+]], 0x80000000
-; CHECK-NEXT: buffer_store_dword [[REG]]
+; CHECK: buffer_store_dword [[REG]]
 define void @store_imm_neg_0.0_f32(float addrspace(1)* %out) {
   store float -0.0, float addrspace(1)* %out
   ret void
@@ -40,7 +40,7 @@ define void @store_imm_neg_0.0_f32(float addrspace(1)* %out) {
 
 ; CHECK-LABEL: {{^}}store_inline_imm_0.5_f32
 ; CHECK: v_mov_b32_e32 [[REG:v[0-9]+]], 0.5{{$}}
-; CHECK-NEXT: buffer_store_dword [[REG]]
+; CHECK: buffer_store_dword [[REG]]
 define void @store_inline_imm_0.5_f32(float addrspace(1)* %out) {
   store float 0.5, float addrspace(1)* %out
   ret void
@@ -48,7 +48,7 @@ define void @store_inline_imm_0.5_f32(float addrspace(1)* %out) {
 
 ; CHECK-LABEL: {{^}}store_inline_imm_m_0.5_f32
 ; CHECK: v_mov_b32_e32 [[REG:v[0-9]+]], -0.5{{$}}
-; CHECK-NEXT: buffer_store_dword [[REG]]
+; CHECK: buffer_store_dword [[REG]]
 define void @store_inline_imm_m_0.5_f32(float addrspace(1)* %out) {
   store float -0.5, float addrspace(1)* %out
   ret void
@@ -56,7 +56,7 @@ define void @store_inline_imm_m_0.5_f32(float addrspace(1)* %out) {
 
 ; CHECK-LABEL: {{^}}store_inline_imm_1.0_f32
 ; CHECK: v_mov_b32_e32 [[REG:v[0-9]+]], 1.0{{$}}
-; CHECK-NEXT: buffer_store_dword [[REG]]
+; CHECK: buffer_store_dword [[REG]]
 define void @store_inline_imm_1.0_f32(float addrspace(1)* %out) {
   store float 1.0, float addrspace(1)* %out
   ret void
@@ -64,7 +64,7 @@ define void @store_inline_imm_1.0_f32(float addrspace(1)* %out) {
 
 ; CHECK-LABEL: {{^}}store_inline_imm_m_1.0_f32
 ; CHECK: v_mov_b32_e32 [[REG:v[0-9]+]], -1.0{{$}}
-; CHECK-NEXT: buffer_store_dword [[REG]]
+; CHECK: buffer_store_dword [[REG]]
 define void @store_inline_imm_m_1.0_f32(float addrspace(1)* %out) {
   store float -1.0, float addrspace(1)* %out
   ret void
@@ -72,7 +72,7 @@ define void @store_inline_imm_m_1.0_f32(float addrspace(1)* %out) {
 
 ; CHECK-LABEL: {{^}}store_inline_imm_2.0_f32
 ; CHECK: v_mov_b32_e32 [[REG:v[0-9]+]], 2.0{{$}}
-; CHECK-NEXT: buffer_store_dword [[REG]]
+; CHECK: buffer_store_dword [[REG]]
 define void @store_inline_imm_2.0_f32(float addrspace(1)* %out) {
   store float 2.0, float addrspace(1)* %out
   ret void
@@ -80,7 +80,7 @@ define void @store_inline_imm_2.0_f32(float addrspace(1)* %out) {
 
 ; CHECK-LABEL: {{^}}store_inline_imm_m_2.0_f32
 ; CHECK: v_mov_b32_e32 [[REG:v[0-9]+]], -2.0{{$}}
-; CHECK-NEXT: buffer_store_dword [[REG]]
+; CHECK: buffer_store_dword [[REG]]
 define void @store_inline_imm_m_2.0_f32(float addrspace(1)* %out) {
   store float -2.0, float addrspace(1)* %out
   ret void
@@ -88,7 +88,7 @@ define void @store_inline_imm_m_2.0_f32(float addrspace(1)* %out) {
 
 ; CHECK-LABEL: {{^}}store_inline_imm_4.0_f32
 ; CHECK: v_mov_b32_e32 [[REG:v[0-9]+]], 4.0{{$}}
-; CHECK-NEXT: buffer_store_dword [[REG]]
+; CHECK: buffer_store_dword [[REG]]
 define void @store_inline_imm_4.0_f32(float addrspace(1)* %out) {
   store float 4.0, float addrspace(1)* %out
   ret void
@@ -96,7 +96,7 @@ define void @store_inline_imm_4.0_f32(float addrspace(1)* %out) {
 
 ; CHECK-LABEL: {{^}}store_inline_imm_m_4.0_f32
 ; CHECK: v_mov_b32_e32 [[REG:v[0-9]+]], -4.0{{$}}
-; CHECK-NEXT: buffer_store_dword [[REG]]
+; CHECK: buffer_store_dword [[REG]]
 define void @store_inline_imm_m_4.0_f32(float addrspace(1)* %out) {
   store float -4.0, float addrspace(1)* %out
   ret void
@@ -104,7 +104,7 @@ define void @store_inline_imm_m_4.0_f32(float addrspace(1)* %out) {
 
 ; CHECK-LABEL: {{^}}store_literal_imm_f32:
 ; CHECK: v_mov_b32_e32 [[REG:v[0-9]+]], 0x45800000
-; CHECK-NEXT: buffer_store_dword [[REG]]
+; CHECK: buffer_store_dword [[REG]]
 define void @store_literal_imm_f32(float addrspace(1)* %out) {
   store float 4096.0, float addrspace(1)* %out
   ret void
@@ -113,7 +113,7 @@ define void @store_literal_imm_f32(float addrspace(1)* %out) {
 ; CHECK-LABEL: {{^}}add_inline_imm_0.0_f32
 ; CHECK: s_load_dword [[VAL:s[0-9]+]]
 ; CHECK: v_add_f32_e64 [[REG:v[0-9]+]], 0, [[VAL]]{{$}}
-; CHECK-NEXT: buffer_store_dword [[REG]]
+; CHECK: buffer_store_dword [[REG]]
 define void @add_inline_imm_0.0_f32(float addrspace(1)* %out, float %x) {
   %y = fadd float %x, 0.0
   store float %y, float addrspace(1)* %out
@@ -123,7 +123,7 @@ define void @add_inline_imm_0.0_f32(float addrspace(1)* %out, float %x) {
 ; CHECK-LABEL: {{^}}add_inline_imm_0.5_f32
 ; CHECK: s_load_dword [[VAL:s[0-9]+]]
 ; CHECK: v_add_f32_e64 [[REG:v[0-9]+]], 0.5, [[VAL]]{{$}}
-; CHECK-NEXT: buffer_store_dword [[REG]]
+; CHECK: buffer_store_dword [[REG]]
 define void @add_inline_imm_0.5_f32(float addrspace(1)* %out, float %x) {
   %y = fadd float %x, 0.5
   store float %y, float addrspace(1)* %out
@@ -133,7 +133,7 @@ define void @add_inline_imm_0.5_f32(float addrspace(1)* %out, float %x) {
 ; CHECK-LABEL: {{^}}add_inline_imm_neg_0.5_f32
 ; CHECK: s_load_dword [[VAL:s[0-9]+]]
 ; CHECK: v_add_f32_e64 [[REG:v[0-9]+]], -0.5, [[VAL]]{{$}}
-; CHECK-NEXT: buffer_store_dword [[REG]]
+; CHECK: buffer_store_dword [[REG]]
 define void @add_inline_imm_neg_0.5_f32(float addrspace(1)* %out, float %x) {
   %y = fadd float %x, -0.5
   store float %y, float addrspace(1)* %out
@@ -143,7 +143,7 @@ define void @add_inline_imm_neg_0.5_f32(float addrspace(1)* %out, float %x) {
 ; CHECK-LABEL: {{^}}add_inline_imm_1.0_f32
 ; CHECK: s_load_dword [[VAL:s[0-9]+]]
 ; CHECK: v_add_f32_e64 [[REG:v[0-9]+]], 1.0, [[VAL]]{{$}}
-; CHECK-NEXT: buffer_store_dword [[REG]]
+; CHECK: buffer_store_dword [[REG]]
 define void @add_inline_imm_1.0_f32(float addrspace(1)* %out, float %x) {
   %y = fadd float %x, 1.0
   store float %y, float addrspace(1)* %out
@@ -153,7 +153,7 @@ define void @add_inline_imm_1.0_f32(float addrspace(1)* %out, float %x) {
 ; CHECK-LABEL: {{^}}add_inline_imm_neg_1.0_f32
 ; CHECK: s_load_dword [[VAL:s[0-9]+]]
 ; CHECK: v_add_f32_e64 [[REG:v[0-9]+]], -1.0, [[VAL]]{{$}}
-; CHECK-NEXT: buffer_store_dword [[REG]]
+; CHECK: buffer_store_dword [[REG]]
 define void @add_inline_imm_neg_1.0_f32(float addrspace(1)* %out, float %x) {
   %y = fadd float %x, -1.0
   store float %y, float addrspace(1)* %out
@@ -163,7 +163,7 @@ define void @add_inline_imm_neg_1.0_f32(float addrspace(1)* %out, float %x) {
 ; CHECK-LABEL: {{^}}add_inline_imm_2.0_f32
 ; CHECK: s_load_dword [[VAL:s[0-9]+]]
 ; CHECK: v_add_f32_e64 [[REG:v[0-9]+]], 2.0, [[VAL]]{{$}}
-; CHECK-NEXT: buffer_store_dword [[REG]]
+; CHECK: buffer_store_dword [[REG]]
 define void @add_inline_imm_2.0_f32(float addrspace(1)* %out, float %x) {
   %y = fadd float %x, 2.0
   store float %y, float addrspace(1)* %out
@@ -173,7 +173,7 @@ define void @add_inline_imm_2.0_f32(float addrspace(1)* %out, float %x) {
 ; CHECK-LABEL: {{^}}add_inline_imm_neg_2.0_f32
 ; CHECK: s_load_dword [[VAL:s[0-9]+]]
 ; CHECK: v_add_f32_e64 [[REG:v[0-9]+]], -2.0, [[VAL]]{{$}}
-; CHECK-NEXT: buffer_store_dword [[REG]]
+; CHECK: buffer_store_dword [[REG]]
 define void @add_inline_imm_neg_2.0_f32(float addrspace(1)* %out, float %x) {
   %y = fadd float %x, -2.0
   store float %y, float addrspace(1)* %out
@@ -183,7 +183,7 @@ define void @add_inline_imm_neg_2.0_f32(float addrspace(1)* %out, float %x) {
 ; CHECK-LABEL: {{^}}add_inline_imm_4.0_f32
 ; CHECK: s_load_dword [[VAL:s[0-9]+]]
 ; CHECK: v_add_f32_e64 [[REG:v[0-9]+]], 4.0, [[VAL]]{{$}}
-; CHECK-NEXT: buffer_store_dword [[REG]]
+; CHECK: buffer_store_dword [[REG]]
 define void @add_inline_imm_4.0_f32(float addrspace(1)* %out, float %x) {
   %y = fadd float %x, 4.0
   store float %y, float addrspace(1)* %out
@@ -193,7 +193,7 @@ define void @add_inline_imm_4.0_f32(float addrspace(1)* %out, float %x) {
 ; CHECK-LABEL: {{^}}add_inline_imm_neg_4.0_f32
 ; CHECK: s_load_dword [[VAL:s[0-9]+]]
 ; CHECK: v_add_f32_e64 [[REG:v[0-9]+]], -4.0, [[VAL]]{{$}}
-; CHECK-NEXT: buffer_store_dword [[REG]]
+; CHECK: buffer_store_dword [[REG]]
 define void @add_inline_imm_neg_4.0_f32(float addrspace(1)* %out, float %x) {
   %y = fadd float %x, -4.0
   store float %y, float addrspace(1)* %out
@@ -203,7 +203,7 @@ define void @add_inline_imm_neg_4.0_f32(float addrspace(1)* %out, float %x) {
 ; CHECK-LABEL: @commute_add_inline_imm_0.5_f32
 ; CHECK: buffer_load_dword [[VAL:v[0-9]+]]
 ; CHECK: v_add_f32_e32 [[REG:v[0-9]+]], 0.5, [[VAL]]
-; CHECK-NEXT: buffer_store_dword [[REG]]
+; CHECK: buffer_store_dword [[REG]]
 define void @commute_add_inline_imm_0.5_f32(float addrspace(1)* %out, float addrspace(1)* %in) {
   %x = load float addrspace(1)* %in
   %y = fadd float %x, 0.5
@@ -214,7 +214,7 @@ define void @commute_add_inline_imm_0.5_f32(float addrspace(1)* %out, float addr
 ; CHECK-LABEL: @commute_add_literal_f32
 ; CHECK: buffer_load_dword [[VAL:v[0-9]+]]
 ; CHECK: v_add_f32_e32 [[REG:v[0-9]+]], 0x44800000, [[VAL]]
-; CHECK-NEXT: buffer_store_dword [[REG]]
+; CHECK: buffer_store_dword [[REG]]
 define void @commute_add_literal_f32(float addrspace(1)* %out, float addrspace(1)* %in) {
   %x = load float addrspace(1)* %in
   %y = fadd float %x, 1024.0
@@ -225,7 +225,7 @@ define void @commute_add_literal_f32(float addrspace(1)* %out, float addrspace(1
 ; CHECK-LABEL: {{^}}add_inline_imm_1_f32
 ; CHECK: s_load_dword [[VAL:s[0-9]+]]
 ; CHECK: v_add_f32_e64 [[REG:v[0-9]+]], 1, [[VAL]]{{$}}
-; CHECK-NEXT: buffer_store_dword [[REG]]
+; CHECK: buffer_store_dword [[REG]]
 define void @add_inline_imm_1_f32(float addrspace(1)* %out, float %x) {
   %y = fadd float %x, 0x36a0000000000000
   store float %y, float addrspace(1)* %out
@@ -235,7 +235,7 @@ define void @add_inline_imm_1_f32(float addrspace(1)* %out, float %x) {
 ; CHECK-LABEL: {{^}}add_inline_imm_2_f32
 ; CHECK: s_load_dword [[VAL:s[0-9]+]]
 ; CHECK: v_add_f32_e64 [[REG:v[0-9]+]], 2, [[VAL]]{{$}}
-; CHECK-NEXT: buffer_store_dword [[REG]]
+; CHECK: buffer_store_dword [[REG]]
 define void @add_inline_imm_2_f32(float addrspace(1)* %out, float %x) {
   %y = fadd float %x, 0x36b0000000000000
   store float %y, float addrspace(1)* %out
@@ -245,7 +245,7 @@ define void @add_inline_imm_2_f32(float addrspace(1)* %out, float %x) {
 ; CHECK-LABEL: {{^}}add_inline_imm_16_f32
 ; CHECK: s_load_dword [[VAL:s[0-9]+]]
 ; CHECK: v_add_f32_e64 [[REG:v[0-9]+]], 16, [[VAL]]
-; CHECK-NEXT: buffer_store_dword [[REG]]
+; CHECK: buffer_store_dword [[REG]]
 define void @add_inline_imm_16_f32(float addrspace(1)* %out, float %x) {
   %y = fadd float %x, 0x36e0000000000000
   store float %y, float addrspace(1)* %out
@@ -255,7 +255,7 @@ define void @add_inline_imm_16_f32(float addrspace(1)* %out, float %x) {
 ; CHECK-LABEL: {{^}}add_inline_imm_neg_1_f32
 ; CHECK: s_load_dword [[VAL:s[0-9]+]]
 ; CHECK: v_add_f32_e64 [[REG:v[0-9]+]], -1, [[VAL]]
-; CHECK-NEXT: buffer_store_dword [[REG]]
+; CHECK: buffer_store_dword [[REG]]
 define void @add_inline_imm_neg_1_f32(float addrspace(1)* %out, float %x) {
   %y = fadd float %x, 0xffffffffe0000000
   store float %y, float addrspace(1)* %out
@@ -265,7 +265,7 @@ define void @add_inline_imm_neg_1_f32(float addrspace(1)* %out, float %x) {
 ; CHECK-LABEL: {{^}}add_inline_imm_neg_2_f32
 ; CHECK: s_load_dword [[VAL:s[0-9]+]]
 ; CHECK: v_add_f32_e64 [[REG:v[0-9]+]], -2, [[VAL]]
-; CHECK-NEXT: buffer_store_dword [[REG]]
+; CHECK: buffer_store_dword [[REG]]
 define void @add_inline_imm_neg_2_f32(float addrspace(1)* %out, float %x) {
   %y = fadd float %x, 0xffffffffc0000000
   store float %y, float addrspace(1)* %out
@@ -275,7 +275,7 @@ define void @add_inline_imm_neg_2_f32(float addrspace(1)* %out, float %x) {
 ; CHECK-LABEL: {{^}}add_inline_imm_neg_16_f32
 ; CHECK: s_load_dword [[VAL:s[0-9]+]]
 ; CHECK: v_add_f32_e64 [[REG:v[0-9]+]], -16, [[VAL]]
-; CHECK-NEXT: buffer_store_dword [[REG]]
+; CHECK: buffer_store_dword [[REG]]
 define void @add_inline_imm_neg_16_f32(float addrspace(1)* %out, float %x) {
   %y = fadd float %x, 0xfffffffe00000000
   store float %y, float addrspace(1)* %out
@@ -285,7 +285,7 @@ define void @add_inline_imm_neg_16_f32(float addrspace(1)* %out, float %x) {
 ; CHECK-LABEL: {{^}}add_inline_imm_63_f32
 ; CHECK: s_load_dword [[VAL:s[0-9]+]]
 ; CHECK: v_add_f32_e64 [[REG:v[0-9]+]], 63, [[VAL]]
-; CHECK-NEXT: buffer_store_dword [[REG]]
+; CHECK: buffer_store_dword [[REG]]
 define void @add_inline_imm_63_f32(float addrspace(1)* %out, float %x) {
   %y = fadd float %x, 0x36ff800000000000
   store float %y, float addrspace(1)* %out
@@ -295,7 +295,7 @@ define void @add_inline_imm_63_f32(float addrspace(1)* %out, float %x) {
 ; CHECK-LABEL: {{^}}add_inline_imm_64_f32
 ; CHECK: s_load_dword [[VAL:s[0-9]+]]
 ; CHECK: v_add_f32_e64 [[REG:v[0-9]+]], 64, [[VAL]]
-; CHECK-NEXT: buffer_store_dword [[REG]]
+; CHECK: buffer_store_dword [[REG]]
 define void @add_inline_imm_64_f32(float addrspace(1)* %out, float %x) {
   %y = fadd float %x, 0x3700000000000000
   store float %y, float addrspace(1)* %out
diff --git a/test/CodeGen/R600/llvm.AMDGPU.class.ll b/test/CodeGen/R600/llvm.AMDGPU.class.ll
index 0bc7d4e6fb5..f111eb97c8b 100644
--- a/test/CodeGen/R600/llvm.AMDGPU.class.ll
+++ b/test/CodeGen/R600/llvm.AMDGPU.class.ll
@@ -472,7 +472,7 @@ define void @test_no_fold_or_class_f32_0(i32 addrspace(1)* %out, float addrspace
 ; SI-LABEL: {{^}}test_class_0_f32:
 ; SI-NOT: v_cmp_class
 ; SI: v_mov_b32_e32 [[RESULT:v[0-9]+]], 0{{$}}
-; SI-NEXT: buffer_store_dword [[RESULT]]
+; SI: buffer_store_dword [[RESULT]]
 ; SI: s_endpgm
 define void @test_class_0_f32(i32 addrspace(1)* %out, float %a) #0 {
   %result = call i1 @llvm.AMDGPU.class.f32(float %a, i32 0) #1
diff --git a/test/CodeGen/R600/setcc-opt.ll b/test/CodeGen/R600/setcc-opt.ll
index a44c89f72cf..5ccdd3e2ba7 100644
--- a/test/CodeGen/R600/setcc-opt.ll
+++ b/test/CodeGen/R600/setcc-opt.ll
@@ -199,7 +199,7 @@ define void @cmp_sext_k_neg1_i8_arg(i1 addrspace(1)* %out, i8 %b) nounwind {
 
 ; FUNC-LABEL: {{^}}cmp_zext_k_neg1:
 ; SI: v_mov_b32_e32 [[RESULT:v[0-9]+]], 1{{$}}
-; SI-NEXT: buffer_store_byte [[RESULT]]
+; SI: buffer_store_byte [[RESULT]]
 ; SI: s_endpgm
 define void @cmp_zext_k_neg1(i1 addrspace(1)* %out, i8 %b) nounwind {
   %b.ext = zext i8 %b to i32
@@ -210,7 +210,7 @@ define void @cmp_zext_k_neg1(i1 addrspace(1)* %out, i8 %b) nounwind {
 
 ; FUNC-LABEL: {{^}}zext_bool_icmp_ne_k:
 ; SI: v_mov_b32_e32 [[RESULT:v[0-9]+]], 1{{$}}
-; SI-NEXT: buffer_store_byte [[RESULT]]
+; SI: buffer_store_byte [[RESULT]]
 ; SI-NEXT: s_endpgm
 define void @zext_bool_icmp_ne_k(i1 addrspace(1)* %out, i32 %a, i32 %b) nounwind {
   %icmp0 = icmp ne i32 %a, %b
@@ -222,7 +222,7 @@ define void @zext_bool_icmp_ne_k(i1 addrspace(1)* %out, i32 %a, i32 %b) nounwind
 
 ; FUNC-LABEL: {{^}}zext_bool_icmp_eq_k:
 ; SI: v_mov_b32_e32 [[RESULT:v[0-9]+]], 0{{$}}
-; SI-NEXT: buffer_store_byte [[RESULT]]
+; SI: buffer_store_byte [[RESULT]]
 ; SI-NEXT: s_endpgm
 define void @zext_bool_icmp_eq_k(i1 addrspace(1)* %out, i32 %a, i32 %b) nounwind {
   %icmp0 = icmp ne i32 %a, %b
diff --git a/test/CodeGen/R600/trunc-cmp-constant.ll b/test/CodeGen/R600/trunc-cmp-constant.ll
index 97af81d821d..a097ab0f537 100644
--- a/test/CodeGen/R600/trunc-cmp-constant.ll
+++ b/test/CodeGen/R600/trunc-cmp-constant.ll
@@ -34,7 +34,7 @@ define void @zextload_i1_to_i32_trunc_cmp_eq_0(i1 addrspace(1)* %out, i1 addrspa
 
 ; FUNC-LABEL: {{^}}sextload_i1_to_i32_trunc_cmp_eq_1:
 ; SI: v_mov_b32_e32 [[RESULT:v[0-9]+]], 0{{$}}
-; SI-NEXT: buffer_store_byte [[RESULT]]
+; SI: buffer_store_byte [[RESULT]]
 define void @sextload_i1_to_i32_trunc_cmp_eq_1(i1 addrspace(1)* %out, i1 addrspace(1)* %in) nounwind {
   %load = load i1 addrspace(1)* %in
   %ext = sext i1 %load to i32
@@ -69,7 +69,7 @@ define void @sextload_i1_to_i32_trunc_cmp_eq_neg1(i1 addrspace(1)* %out, i1 addr
 
 ; FUNC-LABEL: {{^}}zextload_i1_to_i32_trunc_cmp_eq_neg1:
 ; SI: v_mov_b32_e32 [[RESULT:v[0-9]+]], 0{{$}}
-; SI-NEXT: buffer_store_byte [[RESULT]]
+; SI: buffer_store_byte [[RESULT]]
 define void @zextload_i1_to_i32_trunc_cmp_eq_neg1(i1 addrspace(1)* %out, i1 addrspace(1)* %in) nounwind {
   %load = load i1 addrspace(1)* %in
   %ext = zext i1 %load to i32
@@ -105,7 +105,7 @@ define void @zextload_i1_to_i32_trunc_cmp_ne_0(i1 addrspace(1)* %out, i1 addrspa
 
 ; FUNC-LABEL: {{^}}sextload_i1_to_i32_trunc_cmp_ne_1:
 ; SI: v_mov_b32_e32 [[RESULT:v[0-9]+]], 1{{$}}
-; SI-NEXT: buffer_store_byte [[RESULT]]
+; SI: buffer_store_byte [[RESULT]]
 define void @sextload_i1_to_i32_trunc_cmp_ne_1(i1 addrspace(1)* %out, i1 addrspace(1)* %in) nounwind {
   %load = load i1 addrspace(1)* %in
   %ext = sext i1 %load to i32
@@ -146,7 +146,7 @@ define void @sextload_i1_to_i32_trunc_cmp_ne_neg1(i1 addrspace(1)* %out, i1 addr
 
 ; FUNC-LABEL: {{^}}zextload_i1_to_i32_trunc_cmp_ne_neg1:
 ; SI: v_mov_b32_e32 [[RESULT:v[0-9]+]], 1{{$}}
-; SI-NEXT: buffer_store_byte [[RESULT]]
+; SI: buffer_store_byte [[RESULT]]
 define void @zextload_i1_to_i32_trunc_cmp_ne_neg1(i1 addrspace(1)* %out, i1 addrspace(1)* %in) nounwind {
   %load = load i1 addrspace(1)* %in
   %ext = zext i1 %load to i32