vendor/llvm/llvm-trunk-r321017

1 files changed, 96 insertions, 96 deletions

diff --git a/test/CodeGen/AMDGPU/function-args.ll b/test/CodeGen/AMDGPU/function-args.ll
index 6b22cb0b7e28..ca36732540b2 100644
--- a/test/CodeGen/AMDGPU/function-args.ll
+++ b/test/CodeGen/AMDGPU/function-args.ll
@@ -1,6 +1,6 @@
-; RUN: llc -march=amdgcn -mcpu=hawaii -verify-machineinstrs < %s | FileCheck  -enable-var-scope -check-prefix=GCN -check-prefix=CI %s
-; RUN: llc -march=amdgcn -mcpu=fiji -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefix=GCN -check-prefix=VI %s
-; RUN: llc -march=amdgcn -mcpu=gfx900 -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefix=GCN -check-prefix=VI %s
+; RUN: llc -march=amdgcn -mcpu=hawaii -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,CI,CIVI %s
+; RUN: llc -march=amdgcn -mcpu=fiji -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,VI,CIVI,GFX89 %s
+; RUN: llc -march=amdgcn -mcpu=gfx900 -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,VI,GFX89 %s
 
 ; GCN-LABEL: {{^}}void_func_i1:
 ; GCN: v_and_b32_e32 v0, 1, v0
@@ -24,7 +24,7 @@ define void @void_func_i1_zeroext(i1 zeroext %arg0) #0 {
 
 ; GCN-LABEL: {{^}}void_func_i1_signext:
 ; GCN: s_waitcnt
-; GCN-NEXT: v_add_i32_e32 v0, vcc, 12, v0
+; GCN-NEXT: v_add_{{i|u}}32_e32 v0, {{(vcc, )?}}12, v0
 ; GCN-NOT: v0
 ; GCN: buffer_store_dword v0, off
 define void @void_func_i1_signext(i1 signext %arg0) #0 {
@@ -60,7 +60,7 @@ define void @void_func_i8(i8 %arg0) #0 {
 
 ; GCN-LABEL: {{^}}void_func_i8_zeroext:
 ; GCN-NOT: and_b32
-; GCN: v_add_i32_e32 v0, vcc, 12, v0
+; GCN: v_add_{{i|u}}32_e32 v0, {{(vcc, )?}}12, v0
 define void @void_func_i8_zeroext(i8 zeroext %arg0) #0 {
   %ext = zext i8 %arg0 to i32
   %add = add i32 %ext, 12
@@ -70,7 +70,7 @@ define void @void_func_i8_zeroext(i8 zeroext %arg0) #0 {
 
 ; GCN-LABEL: {{^}}void_func_i8_signext:
 ; GCN-NOT: v_bfe_i32
-; GCN: v_add_i32_e32 v0, vcc, 12, v0
+; GCN: v_add_{{i|u}}32_e32 v0, {{(vcc, )?}}12, v0
 define void @void_func_i8_signext(i8 signext %arg0) #0 {
   %ext = sext i8 %arg0 to i32
   %add = add i32 %ext, 12
@@ -87,7 +87,7 @@ define void @void_func_i16(i16 %arg0) #0 {
 
 ; GCN-LABEL: {{^}}void_func_i16_zeroext:
 ; GCN-NOT: v0
-; GCN: v_add_i32_e32 v0, vcc, 12, v0
+; GCN: v_add_{{i|u}}32_e32 v0, {{(vcc, )?}}12, v0
 define void @void_func_i16_zeroext(i16 zeroext %arg0) #0 {
   %ext = zext i16 %arg0 to i32
   %add = add i32 %ext, 12
@@ -97,7 +97,7 @@ define void @void_func_i16_zeroext(i16 zeroext %arg0) #0 {
 
 ; GCN-LABEL: {{^}}void_func_i16_signext:
 ; GCN-NOT: v0
-; GCN: v_add_i32_e32 v0, vcc, 12, v0
+; GCN: v_add_{{i|u}}32_e32 v0, {{(vcc, )?}}12, v0
 define void @void_func_i16_signext(i16 signext %arg0) #0 {
   %ext = sext i16 %arg0 to i32
   %add = add i32 %ext, 12
@@ -502,8 +502,8 @@ define void @void_func_struct_i8_i32({ i8, i32 } %arg0) #0 {
 }
 
 ; GCN-LABEL: {{^}}void_func_byval_struct_i8_i32:
-; GCN-DAG: buffer_load_ubyte v[[ELT0:[0-9]+]], off, s[0:3], s5{{$}}
-; GCN-DAG: buffer_load_dword v[[ELT1:[0-9]+]], off, s[0:3], s5 offset:4{{$}}
+; GCN-DAG: buffer_load_ubyte v[[ELT0:[0-9]+]], off, s[0:3], s5 offset:4{{$}}
+; GCN-DAG: buffer_load_dword v[[ELT1:[0-9]+]], off, s[0:3], s5 offset:8{{$}}
 ; GCN-DAG: buffer_store_dword v[[ELT1]]
 ; GCN-DAG: buffer_store_byte v[[ELT0]]
 define void @void_func_byval_struct_i8_i32({ i8, i32 }* byval %arg0) #0 {
@@ -513,10 +513,10 @@ define void @void_func_byval_struct_i8_i32({ i8, i32 }* byval %arg0) #0 {
 }
 
 ; GCN-LABEL: {{^}}void_func_byval_struct_i8_i32_x2:
-; GCN: buffer_load_ubyte v[[ELT0_0:[0-9]+]], off, s[0:3], s5{{$}}
-; GCN: buffer_load_dword v[[ELT1_0:[0-9]+]], off, s[0:3], s5 offset:4{{$}}
-; GCN: buffer_load_ubyte v[[ELT0_1:[0-9]+]], off, s[0:3], s5 offset:8{{$}}
-; GCN: buffer_load_dword v[[ELT1_1:[0-9]+]], off, s[0:3], s5 offset:12{{$}}
+; GCN: buffer_load_ubyte v[[ELT0_0:[0-9]+]], off, s[0:3], s5 offset:4{{$}}
+; GCN: buffer_load_dword v[[ELT1_0:[0-9]+]], off, s[0:3], s5 offset:8{{$}}
+; GCN: buffer_load_ubyte v[[ELT0_1:[0-9]+]], off, s[0:3], s5 offset:12{{$}}
+; GCN: buffer_load_dword v[[ELT1_1:[0-9]+]], off, s[0:3], s5 offset:16{{$}}
 
 ; GCN: ds_write_b32 v0, v0
 ; GCN: s_setpc_b64
@@ -530,7 +530,7 @@ define void @void_func_byval_struct_i8_i32_x2({ i8, i32 }* byval %arg0, { i8, i3
 }
 
 ; GCN-LABEL: {{^}}void_func_byval_i32_byval_i64:
-; GCN-DAG: buffer_load_dword v[[ARG0_LOAD:[0-9]+]], off, s[0:3], s5{{$}}
+; GCN-DAG: buffer_load_dword v[[ARG0_LOAD:[0-9]+]], off, s[0:3], s5 offset:4{{$}}
 ; GCN-DAG: buffer_load_dword v[[ARG1_LOAD0:[0-9]+]], off, s[0:3], s5 offset:8{{$}}
 ; GCN-DAG: buffer_load_dword v[[ARG1_LOAD1:[0-9]+]], off, s[0:3], s5 offset:12{{$}}
 ; GCN-DAG: buffer_store_dword v[[ARG0_LOAD]], off
@@ -552,9 +552,9 @@ define void @void_func_byval_i32_byval_i64(i32* byval %arg0, i64* byval %arg1) #
 ; GCN-DAG: buffer_store_dwordx4 v[20:23], off
 ; GCN-DAG: buffer_store_dwordx4 v[24:27], off
 ; GCN-DAG: buffer_store_dwordx4 v[28:31], off
-; GCN-DAG: buffer_load_dword v[[LOAD_ARG1:[0-9]+]], off, s[0:3], s5{{$}}
-; GCN-DAG: buffer_load_dword v[[LOAD_ARG2_0:[0-9]+]], off, s[0:3], s5 offset:4
-; GCN-DAG: buffer_load_dword v[[LOAD_ARG2_1:[0-9]+]], off, s[0:3], s5 offset:8
+; GCN-DAG: buffer_load_dword v[[LOAD_ARG1:[0-9]+]], off, s[0:3], s5 offset:4{{$}}
+; GCN-DAG: buffer_load_dword v[[LOAD_ARG2_0:[0-9]+]], off, s[0:3], s5 offset:8
+; GCN-DAG: buffer_load_dword v[[LOAD_ARG2_1:[0-9]+]], off, s[0:3], s5 offset:12
 
 ; GCN: buffer_store_dword v[[LOAD_ARG1]]
 ; GCN: buffer_store_dwordx2 v{{\[}}[[LOAD_ARG2_0]]:[[LOAD_ARG2_1]]{{\]}}, off
@@ -567,14 +567,14 @@ define void @void_func_v32i32_i32_i64(<32 x i32> %arg0, i32 %arg1, i64 %arg2) #0
 
 ; FIXME: Different ext load types on CI vs. VI
 ; GCN-LABEL: {{^}}void_func_v32i32_i1_i8_i16:
-; GCN-DAG: buffer_load_ubyte [[LOAD_ARG1:v[0-9]+]], off, s[0:3], s5{{$}}
-; VI-DAG: buffer_load_ushort [[LOAD_ARG2:v[0-9]+]], off, s[0:3], s5 offset:4{{$}}
-; VI-DAG: buffer_load_ushort [[LOAD_ARG3:v[0-9]+]], off, s[0:3], s5 offset:8{{$}}
-; VI-DAG: buffer_load_ushort [[LOAD_ARG4:v[0-9]+]], off, s[0:3], s5 offset:12{{$}}
+; GCN-DAG: buffer_load_ubyte [[LOAD_ARG1:v[0-9]+]], off, s[0:3], s5 offset:4{{$}}
+; VI-DAG: buffer_load_ushort [[LOAD_ARG2:v[0-9]+]], off, s[0:3], s5 offset:8{{$}}
+; VI-DAG: buffer_load_ushort [[LOAD_ARG3:v[0-9]+]], off, s[0:3], s5 offset:12{{$}}
+; VI-DAG: buffer_load_ushort [[LOAD_ARG4:v[0-9]+]], off, s[0:3], s5 offset:16{{$}}
 
-; CI-DAG: buffer_load_dword [[LOAD_ARG2:v[0-9]+]], off, s[0:3], s5 offset:4{{$}}
-; CI-DAG: buffer_load_dword [[LOAD_ARG3:v[0-9]+]], off, s[0:3], s5 offset:8{{$}}
-; CI-DAG: buffer_load_dword [[LOAD_ARG4:v[0-9]+]], off, s[0:3], s5 offset:12{{$}}
+; CI-DAG: buffer_load_dword [[LOAD_ARG2:v[0-9]+]], off, s[0:3], s5 offset:8{{$}}
+; CI-DAG: buffer_load_dword [[LOAD_ARG3:v[0-9]+]], off, s[0:3], s5 offset:12{{$}}
+; CI-DAG: buffer_load_dword [[LOAD_ARG4:v[0-9]+]], off, s[0:3], s5 offset:16{{$}}
 
 ; GCN-DAG: v_and_b32_e32 [[TRUNC_ARG1_I1:v[0-9]+]], 1, [[LOAD_ARG1]]
 ; CI-DAG: v_cvt_f16_f32_e32 [[CVT_ARG4:v[0-9]+]], [[LOAD_ARG4]]
@@ -582,7 +582,7 @@ define void @void_func_v32i32_i32_i64(<32 x i32> %arg0, i32 %arg1, i64 %arg2) #0
 ; GCN: buffer_store_byte [[TRUNC_ARG1_I1]], off
 ; GCN: buffer_store_byte [[LOAD_ARG2]], off
 ; GCN: buffer_store_short [[LOAD_ARG3]], off
-; VI: buffer_store_short [[LOAD_ARG4]], off
+; GFX89 buffer_store_short [[LOAD_ARG4]], off
 
 ; CI: buffer_store_short [[CVT_ARG4]], off
 define void @void_func_v32i32_i1_i8_i16(<32 x i32> %arg0, i1 %arg1, i8 %arg2, i16 %arg3, half %arg4) #0 {
@@ -595,10 +595,10 @@ define void @void_func_v32i32_i1_i8_i16(<32 x i32> %arg0, i1 %arg1, i8 %arg2, i1
 }
 
 ; GCN-LABEL: {{^}}void_func_v32i32_v2i32_v2f32:
-; GCN-DAG: buffer_load_dword v[[LOAD_ARG1_0:[0-9]+]], off, s[0:3], s5{{$}}
-; GCN-DAG: buffer_load_dword v[[LOAD_ARG1_1:[0-9]+]], off, s[0:3], s5 offset:4{{$}}
-; GCN-DAG: buffer_load_dword v[[LOAD_ARG2_0:[0-9]+]], off, s[0:3], s5 offset:8{{$}}
-; GCN-DAG: buffer_load_dword v[[LOAD_ARG2_1:[0-9]+]], off, s[0:3], s5 offset:12{{$}}
+; GCN-DAG: buffer_load_dword v[[LOAD_ARG1_0:[0-9]+]], off, s[0:3], s5 offset:4{{$}}
+; GCN-DAG: buffer_load_dword v[[LOAD_ARG1_1:[0-9]+]], off, s[0:3], s5 offset:8{{$}}
+; GCN-DAG: buffer_load_dword v[[LOAD_ARG2_0:[0-9]+]], off, s[0:3], s5 offset:12{{$}}
+; GCN-DAG: buffer_load_dword v[[LOAD_ARG2_1:[0-9]+]], off, s[0:3], s5 offset:16{{$}}
 
 ; GCN: buffer_store_dwordx2 v{{\[}}[[LOAD_ARG1_0]]:[[LOAD_ARG1_1]]{{\]}}, off
 ; GCN: buffer_store_dwordx2 v{{\[}}[[LOAD_ARG2_0]]:[[LOAD_ARG2_1]]{{\]}}, off
@@ -610,8 +610,8 @@ define void @void_func_v32i32_v2i32_v2f32(<32 x i32> %arg0, <2 x i32> %arg1, <2
 }
 
 ; GCN-LABEL: {{^}}void_func_v32i32_v2i16_v2f16:
-; GFX9-DAG: buffer_load_dword [[LOAD_ARG1:v[0-9]+]], off, s[0:3], s5{{$}}
-; GFX9-DAG: buffer_load_dword [[LOAD_ARG2:v[0-9]+]], off, s[0:3], s5 offset:4{{$}}
+; GFX9-DAG: buffer_load_dword [[LOAD_ARG1:v[0-9]+]], off, s[0:3], s5 offset:4{{$}}
+; GFX9-DAG: buffer_load_dword [[LOAD_ARG2:v[0-9]+]], off, s[0:3], s5 offset:8{{$}}
 ; GFX9: buffer_store_dword [[LOAD_ARG1]], off
 ; GFX9: buffer_store_short [[LOAD_ARG2]], off
 define void @void_func_v32i32_v2i16_v2f16(<32 x i32> %arg0, <2 x i16> %arg1, <2 x half> %arg2) #0 {
@@ -622,15 +622,15 @@ define void @void_func_v32i32_v2i16_v2f16(<32 x i32> %arg0, <2 x i16> %arg1, <2
 }
 
 ; GCN-LABEL: {{^}}void_func_v32i32_v2i64_v2f64:
-; GCN-DAG: buffer_load_dword v[[LOAD_ARG1_0:[0-9]+]], off, s[0:3], s5{{$}}
-; GCN-DAG: buffer_load_dword v[[LOAD_ARG1_1:[0-9]+]], off, s[0:3], s5 offset:4{{$}}
-; GCN-DAG: buffer_load_dword v[[LOAD_ARG1_2:[0-9]+]], off, s[0:3], s5 offset:8{{$}}
-; GCN-DAG: buffer_load_dword v[[LOAD_ARG1_3:[0-9]+]], off, s[0:3], s5 offset:12{{$}}
+; GCN-DAG: buffer_load_dword v[[LOAD_ARG1_0:[0-9]+]], off, s[0:3], s5 offset:4{{$}}
+; GCN-DAG: buffer_load_dword v[[LOAD_ARG1_1:[0-9]+]], off, s[0:3], s5 offset:8{{$}}
+; GCN-DAG: buffer_load_dword v[[LOAD_ARG1_2:[0-9]+]], off, s[0:3], s5 offset:12{{$}}
+; GCN-DAG: buffer_load_dword v[[LOAD_ARG1_3:[0-9]+]], off, s[0:3], s5 offset:16{{$}}
 
-; GCN-DAG: buffer_load_dword v[[LOAD_ARG2_0:[0-9]+]], off, s[0:3], s5 offset:16{{$}}
-; GCN-DAG: buffer_load_dword v[[LOAD_ARG2_1:[0-9]+]], off, s[0:3], s5 offset:20{{$}}
-; GCN-DAG: buffer_load_dword v[[LOAD_ARG2_2:[0-9]+]], off, s[0:3], s5 offset:24{{$}}
-; GCN-DAG: buffer_load_dword v[[LOAD_ARG2_3:[0-9]+]], off, s[0:3], s5 offset:28{{$}}
+; GCN-DAG: buffer_load_dword v[[LOAD_ARG2_0:[0-9]+]], off, s[0:3], s5 offset:20{{$}}
+; GCN-DAG: buffer_load_dword v[[LOAD_ARG2_1:[0-9]+]], off, s[0:3], s5 offset:24{{$}}
+; GCN-DAG: buffer_load_dword v[[LOAD_ARG2_2:[0-9]+]], off, s[0:3], s5 offset:28{{$}}
+; GCN-DAG: buffer_load_dword v[[LOAD_ARG2_3:[0-9]+]], off, s[0:3], s5 offset:32{{$}}
 
 ; GCN: buffer_store_dwordx4 v{{\[}}[[LOAD_ARG1_0]]:[[LOAD_ARG1_3]]{{\]}}, off
 ; GCN: buffer_store_dwordx4 v{{\[}}[[LOAD_ARG2_0]]:[[LOAD_ARG2_3]]{{\]}}, off
@@ -642,15 +642,15 @@ define void @void_func_v32i32_v2i64_v2f64(<32 x i32> %arg0, <2 x i64> %arg1, <2
 }
 
 ; GCN-LABEL: {{^}}void_func_v32i32_v4i32_v4f32:
-; GCN-DAG: buffer_load_dword v[[LOAD_ARG1_0:[0-9]+]], off, s[0:3], s5{{$}}
-; GCN-DAG: buffer_load_dword v[[LOAD_ARG1_1:[0-9]+]], off, s[0:3], s5 offset:4{{$}}
-; GCN-DAG: buffer_load_dword v[[LOAD_ARG1_2:[0-9]+]], off, s[0:3], s5 offset:8{{$}}
-; GCN-DAG: buffer_load_dword v[[LOAD_ARG1_3:[0-9]+]], off, s[0:3], s5 offset:12{{$}}
+; GCN-DAG: buffer_load_dword v[[LOAD_ARG1_0:[0-9]+]], off, s[0:3], s5 offset:4{{$}}
+; GCN-DAG: buffer_load_dword v[[LOAD_ARG1_1:[0-9]+]], off, s[0:3], s5 offset:8{{$}}
+; GCN-DAG: buffer_load_dword v[[LOAD_ARG1_2:[0-9]+]], off, s[0:3], s5 offset:12{{$}}
+; GCN-DAG: buffer_load_dword v[[LOAD_ARG1_3:[0-9]+]], off, s[0:3], s5 offset:16{{$}}
 
-; GCN-DAG: buffer_load_dword v[[LOAD_ARG2_0:[0-9]+]], off, s[0:3], s5 offset:16{{$}}
-; GCN-DAG: buffer_load_dword v[[LOAD_ARG2_1:[0-9]+]], off, s[0:3], s5 offset:20{{$}}
-; GCN-DAG: buffer_load_dword v[[LOAD_ARG2_2:[0-9]+]], off, s[0:3], s5 offset:24{{$}}
-; GCN-DAG: buffer_load_dword v[[LOAD_ARG2_3:[0-9]+]], off, s[0:3], s5 offset:28{{$}}
+; GCN-DAG: buffer_load_dword v[[LOAD_ARG2_0:[0-9]+]], off, s[0:3], s5 offset:20{{$}}
+; GCN-DAG: buffer_load_dword v[[LOAD_ARG2_1:[0-9]+]], off, s[0:3], s5 offset:24{{$}}
+; GCN-DAG: buffer_load_dword v[[LOAD_ARG2_2:[0-9]+]], off, s[0:3], s5 offset:28{{$}}
+; GCN-DAG: buffer_load_dword v[[LOAD_ARG2_3:[0-9]+]], off, s[0:3], s5 offset:32{{$}}
 
 ; GCN: buffer_store_dwordx4 v{{\[}}[[LOAD_ARG1_0]]:[[LOAD_ARG1_3]]{{\]}}, off
 ; GCN: buffer_store_dwordx4 v{{\[}}[[LOAD_ARG2_0]]:[[LOAD_ARG2_3]]{{\]}}, off
@@ -662,23 +662,23 @@ define void @void_func_v32i32_v4i32_v4f32(<32 x i32> %arg0, <4 x i32> %arg1, <4
 }
 
 ; GCN-LABEL: {{^}}void_func_v32i32_v8i32_v8f32:
-; GCN-DAG: buffer_load_dword v[[LOAD_ARG1_0:[0-9]+]], off, s[0:3], s5{{$}}
-; GCN-DAG: buffer_load_dword v[[LOAD_ARG1_1:[0-9]+]], off, s[0:3], s5 offset:4{{$}}
-; GCN-DAG: buffer_load_dword v[[LOAD_ARG1_2:[0-9]+]], off, s[0:3], s5 offset:8{{$}}
-; GCN-DAG: buffer_load_dword v[[LOAD_ARG1_3:[0-9]+]], off, s[0:3], s5 offset:12{{$}}
-; GCN-DAG: buffer_load_dword v[[LOAD_ARG1_4:[0-9]+]], off, s[0:3], s5 offset:16{{$}}
-; GCN-DAG: buffer_load_dword v[[LOAD_ARG1_5:[0-9]+]], off, s[0:3], s5 offset:20{{$}}
-; GCN-DAG: buffer_load_dword v[[LOAD_ARG1_6:[0-9]+]], off, s[0:3], s5 offset:24{{$}}
-; GCN-DAG: buffer_load_dword v[[LOAD_ARG1_7:[0-9]+]], off, s[0:3], s5 offset:28{{$}}
+; GCN-DAG: buffer_load_dword v[[LOAD_ARG1_0:[0-9]+]], off, s[0:3], s5 offset:4{{$}}
+; GCN-DAG: buffer_load_dword v[[LOAD_ARG1_1:[0-9]+]], off, s[0:3], s5 offset:8{{$}}
+; GCN-DAG: buffer_load_dword v[[LOAD_ARG1_2:[0-9]+]], off, s[0:3], s5 offset:12{{$}}
+; GCN-DAG: buffer_load_dword v[[LOAD_ARG1_3:[0-9]+]], off, s[0:3], s5 offset:16{{$}}
+; GCN-DAG: buffer_load_dword v[[LOAD_ARG1_4:[0-9]+]], off, s[0:3], s5 offset:20{{$}}
+; GCN-DAG: buffer_load_dword v[[LOAD_ARG1_5:[0-9]+]], off, s[0:3], s5 offset:24{{$}}
+; GCN-DAG: buffer_load_dword v[[LOAD_ARG1_6:[0-9]+]], off, s[0:3], s5 offset:28{{$}}
+; GCN-DAG: buffer_load_dword v[[LOAD_ARG1_7:[0-9]+]], off, s[0:3], s5 offset:32{{$}}
 
-; GCN-DAG: buffer_load_dword v[[LOAD_ARG2_0:[0-9]+]], off, s[0:3], s5 offset:32{{$}}
-; GCN-DAG: buffer_load_dword v[[LOAD_ARG2_1:[0-9]+]], off, s[0:3], s5 offset:36{{$}}
-; GCN-DAG: buffer_load_dword v[[LOAD_ARG2_2:[0-9]+]], off, s[0:3], s5 offset:40{{$}}
-; GCN-DAG: buffer_load_dword v[[LOAD_ARG2_3:[0-9]+]], off, s[0:3], s5 offset:44{{$}}
-; GCN-DAG: buffer_load_dword v[[LOAD_ARG2_4:[0-9]+]], off, s[0:3], s5 offset:48{{$}}
-; GCN-DAG: buffer_load_dword v[[LOAD_ARG2_5:[0-9]+]], off, s[0:3], s5 offset:52{{$}}
-; GCN-DAG: buffer_load_dword v[[LOAD_ARG2_6:[0-9]+]], off, s[0:3], s5 offset:56{{$}}
-; GCN-DAG: buffer_load_dword v[[LOAD_ARG2_7:[0-9]+]], off, s[0:3], s5 offset:60{{$}}
+; GCN-DAG: buffer_load_dword v[[LOAD_ARG2_0:[0-9]+]], off, s[0:3], s5 offset:36{{$}}
+; GCN-DAG: buffer_load_dword v[[LOAD_ARG2_1:[0-9]+]], off, s[0:3], s5 offset:40{{$}}
+; GCN-DAG: buffer_load_dword v[[LOAD_ARG2_2:[0-9]+]], off, s[0:3], s5 offset:44{{$}}
+; GCN-DAG: buffer_load_dword v[[LOAD_ARG2_3:[0-9]+]], off, s[0:3], s5 offset:48{{$}}
+; GCN-DAG: buffer_load_dword v[[LOAD_ARG2_4:[0-9]+]], off, s[0:3], s5 offset:52{{$}}
+; GCN-DAG: buffer_load_dword v[[LOAD_ARG2_5:[0-9]+]], off, s[0:3], s5 offset:56{{$}}
+; GCN-DAG: buffer_load_dword v[[LOAD_ARG2_6:[0-9]+]], off, s[0:3], s5 offset:60{{$}}
+; GCN-DAG: buffer_load_dword v[[LOAD_ARG2_7:[0-9]+]], off, s[0:3], s5 offset:64{{$}}
 
 ; GCN: buffer_store_dwordx4 v{{\[}}[[LOAD_ARG1_4]]:[[LOAD_ARG1_7]]{{\]}}, off
 ; GCN: buffer_store_dwordx4 v{{\[}}[[LOAD_ARG1_0]]:[[LOAD_ARG1_3]]{{\]}}, off
@@ -692,39 +692,39 @@ define void @void_func_v32i32_v8i32_v8f32(<32 x i32> %arg0, <8 x i32> %arg1, <8
 }
 
 ; GCN-LABEL: {{^}}void_func_v32i32_v16i32_v16f32:
-; GCN-DAG: buffer_load_dword v[[LOAD_ARG1_0:[0-9]+]], off, s[0:3], s5{{$}}
-; GCN-DAG: buffer_load_dword v[[LOAD_ARG1_1:[0-9]+]], off, s[0:3], s5 offset:4{{$}}
-; GCN-DAG: buffer_load_dword v[[LOAD_ARG1_2:[0-9]+]], off, s[0:3], s5 offset:8{{$}}
-; GCN-DAG: buffer_load_dword v[[LOAD_ARG1_3:[0-9]+]], off, s[0:3], s5 offset:12{{$}}
-; GCN-DAG: buffer_load_dword v[[LOAD_ARG1_4:[0-9]+]], off, s[0:3], s5 offset:16{{$}}
-; GCN-DAG: buffer_load_dword v[[LOAD_ARG1_5:[0-9]+]], off, s[0:3], s5 offset:20{{$}}
-; GCN-DAG: buffer_load_dword v[[LOAD_ARG1_6:[0-9]+]], off, s[0:3], s5 offset:24{{$}}
-; GCN-DAG: buffer_load_dword v[[LOAD_ARG1_7:[0-9]+]], off, s[0:3], s5 offset:28{{$}}
-; GCN-DAG: buffer_load_dword v[[LOAD_ARG1_8:[0-9]+]], off, s[0:3], s5 offset:32{{$}}
-; GCN-DAG: buffer_load_dword v[[LOAD_ARG1_9:[0-9]+]], off, s[0:3], s5 offset:36{{$}}
-; GCN-DAG: buffer_load_dword v[[LOAD_ARG1_10:[0-9]+]], off, s[0:3], s5 offset:40{{$}}
-; GCN-DAG: buffer_load_dword v[[LOAD_ARG1_11:[0-9]+]], off, s[0:3], s5 offset:44{{$}}
-; GCN-DAG: buffer_load_dword v[[LOAD_ARG1_12:[0-9]+]], off, s[0:3], s5 offset:48{{$}}
-; GCN-DAG: buffer_load_dword v[[LOAD_ARG1_13:[0-9]+]], off, s[0:3], s5 offset:52{{$}}
-; GCN-DAG: buffer_load_dword v[[LOAD_ARG1_14:[0-9]+]], off, s[0:3], s5 offset:56{{$}}
-; GCN-DAG: buffer_load_dword v[[LOAD_ARG1_15:[0-9]+]], off, s[0:3], s5 offset:60{{$}}
+; GCN-DAG: buffer_load_dword v[[LOAD_ARG1_0:[0-9]+]], off, s[0:3], s5 offset:4{{$}}
+; GCN-DAG: buffer_load_dword v[[LOAD_ARG1_1:[0-9]+]], off, s[0:3], s5 offset:8{{$}}
+; GCN-DAG: buffer_load_dword v[[LOAD_ARG1_2:[0-9]+]], off, s[0:3], s5 offset:12{{$}}
+; GCN-DAG: buffer_load_dword v[[LOAD_ARG1_:[0-9]+]], off, s[0:3], s5 offset:16{{$}}
+; GCN-DAG: buffer_load_dword v[[LOAD_ARG1_4:[0-9]+]], off, s[0:3], s5 offset:20{{$}}
+; GCN-DAG: buffer_load_dword v[[LOAD_ARG1_5:[0-9]+]], off, s[0:3], s5 offset:24{{$}}
+; GCN-DAG: buffer_load_dword v[[LOAD_ARG1_6:[0-9]+]], off, s[0:3], s5 offset:28{{$}}
+; GCN-DAG: buffer_load_dword v[[LOAD_ARG1_7:[0-9]+]], off, s[0:3], s5 offset:32{{$}}
+; GCN-DAG: buffer_load_dword v[[LOAD_ARG1_8:[0-9]+]], off, s[0:3], s5 offset:36{{$}}
+; GCN-DAG: buffer_load_dword v[[LOAD_ARG1_9:[0-9]+]], off, s[0:3], s5 offset:40{{$}}
+; GCN-DAG: buffer_load_dword v[[LOAD_ARG1_10:[0-9]+]], off, s[0:3], s5 offset:44{{$}}
+; GCN-DAG: buffer_load_dword v[[LOAD_ARG1_11:[0-9]+]], off, s[0:3], s5 offset:48{{$}}
+; GCN-DAG: buffer_load_dword v[[LOAD_ARG1_12:[0-9]+]], off, s[0:3], s5 offset:52{{$}}
+; GCN-DAG: buffer_load_dword v[[LOAD_ARG1_13:[0-9]+]], off, s[0:3], s5 offset:56{{$}}
+; GCN-DAG: buffer_load_dword v[[LOAD_ARG1_14:[0-9]+]], off, s[0:3], s5 offset:60{{$}}
+; GCN-DAG: buffer_load_dword v[[LOAD_ARG2_15:[0-9]+]], off, s[0:3], s5 offset:64{{$}}
 
-; GCN-DAG: buffer_load_dword v[[LOAD_ARG2_0:[0-9]+]], off, s[0:3], s5 offset:64{{$}}
-; GCN-DAG: buffer_load_dword v[[LOAD_ARG2_1:[0-9]+]], off, s[0:3], s5 offset:68{{$}}
-; GCN-DAG: buffer_load_dword v[[LOAD_ARG2_2:[0-9]+]], off, s[0:3], s5 offset:72{{$}}
-; GCN-DAG: buffer_load_dword v[[LOAD_ARG2_3:[0-9]+]], off, s[0:3], s5 offset:76{{$}}
-; GCN-DAG: buffer_load_dword v[[LOAD_ARG2_4:[0-9]+]], off, s[0:3], s5 offset:80{{$}}
-; GCN-DAG: buffer_load_dword v[[LOAD_ARG2_5:[0-9]+]], off, s[0:3], s5 offset:84{{$}}
-; GCN-DAG: buffer_load_dword v[[LOAD_ARG2_6:[0-9]+]], off, s[0:3], s5 offset:88{{$}}
-; GCN-DAG: buffer_load_dword v[[LOAD_ARG2_7:[0-9]+]], off, s[0:3], s5 offset:92{{$}}
-; GCN-DAG: buffer_load_dword v[[LOAD_ARG2_8:[0-9]+]], off, s[0:3], s5 offset:96{{$}}
-; GCN-DAG: buffer_load_dword v[[LOAD_ARG2_9:[0-9]+]], off, s[0:3], s5 offset:100{{$}}
-; GCN-DAG: buffer_load_dword v[[LOAD_ARG2_10:[0-9]+]], off, s[0:3], s5 offset:104{{$}}
-; GCN-DAG: buffer_load_dword v[[LOAD_ARG2_11:[0-9]+]], off, s[0:3], s5 offset:108{{$}}
-; GCN-DAG: buffer_load_dword v[[LOAD_ARG2_12:[0-9]+]], off, s[0:3], s5 offset:112{{$}}
-; GCN-DAG: buffer_load_dword v[[LOAD_ARG2_13:[0-9]+]], off, s[0:3], s5 offset:116{{$}}
-; GCN-DAG: buffer_load_dword v[[LOAD_ARG2_14:[0-9]+]], off, s[0:3], s5 offset:120{{$}}
-; GCN-DAG: buffer_load_dword v[[LOAD_ARG2_15:[0-9]+]], off, s[0:3], s5 offset:124{{$}}
+; GCN-DAG: buffer_load_dword v[[LOAD_ARG2_0:[0-9]+]], off, s[0:3], s5 offset:68{{$}}
+; GCN-DAG: buffer_load_dword v[[LOAD_ARG2_1:[0-9]+]], off, s[0:3], s5 offset:72{{$}}
+; GCN-DAG: buffer_load_dword v[[LOAD_ARG2_2:[0-9]+]], off, s[0:3], s5 offset:76{{$}}
+; GCN-DAG: buffer_load_dword v[[LOAD_ARG2_3:[0-9]+]], off, s[0:3], s5 offset:80{{$}}
+; GCN-DAG: buffer_load_dword v[[LOAD_ARG2_4:[0-9]+]], off, s[0:3], s5 offset:84{{$}}
+; GCN-DAG: buffer_load_dword v[[LOAD_ARG2_5:[0-9]+]], off, s[0:3], s5 offset:88{{$}}
+; GCN-DAG: buffer_load_dword v[[LOAD_ARG2_6:[0-9]+]], off, s[0:3], s5 offset:92{{$}}
+; GCN-DAG: buffer_load_dword v[[LOAD_ARG2_7:[0-9]+]], off, s[0:3], s5 offset:96{{$}}
+; GCN-DAG: buffer_load_dword v[[LOAD_ARG2_8:[0-9]+]], off, s[0:3], s5 offset:100{{$}}
+; GCN-DAG: buffer_load_dword v[[LOAD_ARG2_9:[0-9]+]], off, s[0:3], s5 offset:104{{$}}
+; GCN-DAG: buffer_load_dword v[[LOAD_ARG2_10:[0-9]+]], off, s[0:3], s5 offset:108{{$}}
+; GCN-DAG: buffer_load_dword v[[LOAD_ARG2_11:[0-9]+]], off, s[0:3], s5 offset:112{{$}}
+; GCN-DAG: buffer_load_dword v[[LOAD_ARG2_12:[0-9]+]], off, s[0:3], s5 offset:116{{$}}
+; GCN-DAG: buffer_load_dword v[[LOAD_ARG2_13:[0-9]+]], off, s[0:3], s5 offset:120{{$}}
+; GCN-DAG: buffer_load_dword v[[LOAD_ARG2_14:[0-9]+]], off, s[0:3], s5 offset:124{{$}}
+; GCN-DAG: buffer_load_dword v[[LOAD_ARG2_15:[0-9]+]], off, s[0:3], s5 offset:128{{$}}
 define void @void_func_v32i32_v16i32_v16f32(<32 x i32> %arg0, <16 x i32> %arg1, <16 x float> %arg2) #0 {
   store volatile <32 x i32> %arg0, <32 x i32> addrspace(1)* undef
   store volatile <16 x i32> %arg1, <16 x i32> addrspace(1)* undef