diff test/CodeGen/AMDGPU/function-args.ll @ 147:c2174574ed3a

LLVM 10
author Shinji KONO <kono@ie.u-ryukyu.ac.jp>
date Wed, 14 Aug 2019 16:55:33 +0900
parents 3a76565eade5
children
line wrap: on
line diff
--- a/test/CodeGen/AMDGPU/function-args.ll	Sat Feb 17 09:57:20 2018 +0900
+++ b/test/CodeGen/AMDGPU/function-args.ll	Wed Aug 14 16:55:33 2019 +0900
@@ -161,8 +161,7 @@
 }
 
 ; GCN-LABEL: {{^}}void_func_v3i32:
-; GCN-DAG: buffer_store_dword v2, off
-; GCN-DAG: buffer_store_dwordx2 v[0:1], off
+; GCN-DAG: buffer_store_dwordx3 v[0:2], off
 define void @void_func_v3i32(<3 x i32> %arg0) #0 {
   store <3 x i32> %arg0, <3 x i32> addrspace(1)* undef
   ret void
@@ -221,7 +220,7 @@
 ; GCN-DAG: buffer_store_dwordx4 v[4:7], off
 ; GCN-DAG: buffer_store_dwordx4 v[8:11], off
 ; GCN-DAG: buffer_store_dwordx4 v[12:15], off
-; GCN-DAG: buffer_load_dword [[STACKLOAD:v[0-9]+]], off, s[0:3], s5
+; GCN-DAG: buffer_load_dword [[STACKLOAD:v[0-9]+]], off, s[0:3], s32
 ; GCN-DAG: buffer_store_dwordx4 v[16:19], off
 ; GCN-DAG: buffer_store_dwordx4 v[20:23], off
 ; GCN-DAG: buffer_store_dwordx4 v[24:27], off
@@ -297,8 +296,8 @@
 }
 
 ; GCN-LABEL: {{^}}void_func_v3i16:
-; GCN-DAG: buffer_store_dword v0, off
-; GCN-DAG: buffer_store_short v2, off
+; GCN-DAG: buffer_store_dword v{{[0-9]+}}, off
+; GCN-DAG: buffer_store_short v{{[0-9]+}}, off
 define void @void_func_v3i16(<3 x i16> %arg0) #0 {
   store <3 x i16> %arg0, <3 x i16> addrspace(1)* undef
   ret void
@@ -314,8 +313,17 @@
 }
 
 ; GCN-LABEL: {{^}}void_func_v5i16:
-; GCN-DAG: buffer_store_short v4, off,
-; GCN-DAG: buffer_store_dwordx2 v[1:2], off
+; CI: v_lshlrev_b32
+; CI: v_and_b32
+; CI: v_lshlrev_b32
+; CI: v_or_b32
+; CI: v_or_b32
+; CI-DAG: buffer_store_short v
+; CI-DAG: buffer_store_dwordx2 v
+
+; GFX89-DAG: buffer_store_short v2, off,
+; GFX89-DAG: buffer_store_dwordx2 v[0:1], off
+
 define void @void_func_v5i16(<5 x i16> %arg0) #0 {
   store <5 x i16> %arg0, <5 x i16> addrspace(1)* undef
   ret void
@@ -347,8 +355,7 @@
 }
 
 ; GCN-LABEL: {{^}}void_func_v3f32:
-; GCN-DAG: buffer_store_dword v2, off
-; GCN-DAG: buffer_store_dwordx2 v[0:1], off
+; GCN-DAG: buffer_store_dwordx3 v[0:2], off
 define void @void_func_v3f32(<3 x float> %arg0) #0 {
   store <3 x float> %arg0, <3 x float> addrspace(1)* undef
   ret void
@@ -434,10 +441,17 @@
   ret void
 }
 
+; FIXME: Different abi if f16 legal
 ; GCN-LABEL: {{^}}void_func_v3f16:
-; GFX9-NOT: v0
-; GCN-DAG: buffer_store_dword v0, off
-; GCN-DAG: buffer_store_short v2, off
+; CI-DAG: v_cvt_f16_f32_e32 v{{[0-9]+}}, v0
+; CI-DAG: v_cvt_f16_f32_e32 v{{[0-9]+}}, v1
+; CI-DAG: v_cvt_f16_f32_e32 v{{[0-9]+}}, v2
+
+; GFX89-DAG: v0
+; GFX89-DAG: v1
+
+; GCN-DAG: buffer_store_short
+; GCN-DAG: buffer_store_dword
 define void @void_func_v3f16(<3 x half> %arg0) #0 {
   store <3 x half> %arg0, <3 x half> addrspace(1)* undef
   ret void
@@ -502,8 +516,8 @@
 }
 
 ; GCN-LABEL: {{^}}void_func_byval_struct_i8_i32:
-; 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_load_ubyte v[[ELT0:[0-9]+]], off, s[0:3], s32{{$}}
+; GCN-DAG: buffer_load_dword v[[ELT1:[0-9]+]], off, s[0:3], s32 offset:4{{$}}
 ; GCN-DAG: buffer_store_dword v[[ELT1]]
 ; GCN-DAG: buffer_store_byte v[[ELT0]]
 define void @void_func_byval_struct_i8_i32({ i8, i32 } addrspace(5)* byval %arg0) #0 {
@@ -513,10 +527,10 @@
 }
 
 ; GCN-LABEL: {{^}}void_func_byval_struct_i8_i32_x2:
-; 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: buffer_load_ubyte v[[ELT0_0:[0-9]+]], off, s[0:3], s32{{$}}
+; GCN: buffer_load_dword v[[ELT1_0:[0-9]+]], off, s[0:3], s32 offset:4{{$}}
+; GCN: buffer_load_ubyte v[[ELT0_1:[0-9]+]], off, s[0:3], s32 offset:8{{$}}
+; GCN: buffer_load_dword v[[ELT1_1:[0-9]+]], off, s[0:3], s32 offset:12{{$}}
 
 ; GCN: ds_write_b32 v0, v0
 ; GCN: s_setpc_b64
@@ -530,9 +544,9 @@
 }
 
 ; GCN-LABEL: {{^}}void_func_byval_i32_byval_i64:
-; 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{{$}}
+; GCN-DAG: buffer_load_dword v[[ARG0_LOAD:[0-9]+]], off, s[0:3], s32{{$}}
+; GCN-DAG: buffer_load_dword v[[ARG1_LOAD0:[0-9]+]], off, s[0:3], s32 offset:8{{$}}
+; GCN-DAG: buffer_load_dword v[[ARG1_LOAD1:[0-9]+]], off, s[0:3], s32 offset:12{{$}}
 ; GCN-DAG: buffer_store_dword v[[ARG0_LOAD]], off
 ; GCN-DAG: buffer_store_dwordx2 v{{\[}}[[ARG1_LOAD0]]:[[ARG1_LOAD1]]{{\]}}, off
 define void @void_func_byval_i32_byval_i64(i32 addrspace(5)* byval %arg0, i64 addrspace(5)* byval %arg1) #0 {
@@ -552,9 +566,9 @@
 ; 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 offset:4{{$}}
-; GCN-DAG: buffer_load_dword v[[LOAD_ARG2_0:[0-9]+]], off, s[0:3], s5 offset:8
-; GCN-DAG: buffer_load_dword v[[LOAD_ARG2_1:[0-9]+]], off, s[0:3], s5 offset:12
+; GCN-DAG: buffer_load_dword v[[LOAD_ARG1:[0-9]+]], off, s[0:3], s32{{$}}
+; GCN-DAG: buffer_load_dword v[[LOAD_ARG2_0:[0-9]+]], off, s[0:3], s32 offset:4
+; GCN-DAG: buffer_load_dword v[[LOAD_ARG2_1:[0-9]+]], off, s[0:3], s32 offset:8
 
 ; GCN: buffer_store_dword v[[LOAD_ARG1]]
 ; GCN: buffer_store_dwordx2 v{{\[}}[[LOAD_ARG2_0]]:[[LOAD_ARG2_1]]{{\]}}, off
@@ -567,14 +581,14 @@
 
 ; 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 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{{$}}
-; VI-DAG: buffer_load_ushort [[LOAD_ARG4:v[0-9]+]], off, s[0:3], s5 offset:16{{$}}
+; GCN-DAG: buffer_load_ubyte [[LOAD_ARG1:v[0-9]+]], off, s[0:3], s32{{$}}
+; VI-DAG: buffer_load_ushort [[LOAD_ARG2:v[0-9]+]], off, s[0:3], s32 offset:4{{$}}
+; VI-DAG: buffer_load_ushort [[LOAD_ARG3:v[0-9]+]], off, s[0:3], s32 offset:8{{$}}
+; VI-DAG: buffer_load_ushort [[LOAD_ARG4:v[0-9]+]], off, s[0:3], s32 offset:12{{$}}
 
-; 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{{$}}
+; CI-DAG: buffer_load_dword [[LOAD_ARG2:v[0-9]+]], off, s[0:3], s32 offset:4{{$}}
+; CI-DAG: buffer_load_dword [[LOAD_ARG3:v[0-9]+]], off, s[0:3], s32 offset:8{{$}}
+; CI-DAG: buffer_load_dword [[LOAD_ARG4:v[0-9]+]], off, s[0:3], s32 offset:12{{$}}
 
 ; 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]]
@@ -595,10 +609,10 @@
 }
 
 ; GCN-LABEL: {{^}}void_func_v32i32_v2i32_v2f32:
-; 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-DAG: buffer_load_dword v[[LOAD_ARG1_0:[0-9]+]], off, s[0:3], s32{{$}}
+; GCN-DAG: buffer_load_dword v[[LOAD_ARG1_1:[0-9]+]], off, s[0:3], s32 offset:4{{$}}
+; GCN-DAG: buffer_load_dword v[[LOAD_ARG2_0:[0-9]+]], off, s[0:3], s32 offset:8{{$}}
+; GCN-DAG: buffer_load_dword v[[LOAD_ARG2_1:[0-9]+]], off, s[0:3], s32 offset:12{{$}}
 
 ; 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 +624,8 @@
 }
 
 ; GCN-LABEL: {{^}}void_func_v32i32_v2i16_v2f16:
-; 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-DAG: buffer_load_dword [[LOAD_ARG1:v[0-9]+]], off, s[0:3], s32 offset:4{{$}}
+; GFX9-DAG: buffer_load_dword [[LOAD_ARG2:v[0-9]+]], off, s[0:3], s32 offset:8{{$}}
 ; 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 +636,15 @@
 }
 
 ; GCN-LABEL: {{^}}void_func_v32i32_v2i64_v2f64:
-; 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_0:[0-9]+]], off, s[0:3], s32{{$}}
+; GCN-DAG: buffer_load_dword v[[LOAD_ARG1_1:[0-9]+]], off, s[0:3], s32 offset:4{{$}}
+; GCN-DAG: buffer_load_dword v[[LOAD_ARG1_2:[0-9]+]], off, s[0:3], s32 offset:8{{$}}
+; GCN-DAG: buffer_load_dword v[[LOAD_ARG1_3:[0-9]+]], off, s[0:3], s32 offset:12{{$}}
 
-; 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-DAG: buffer_load_dword v[[LOAD_ARG2_0:[0-9]+]], off, s[0:3], s32 offset:16{{$}}
+; GCN-DAG: buffer_load_dword v[[LOAD_ARG2_1:[0-9]+]], off, s[0:3], s32 offset:20{{$}}
+; GCN-DAG: buffer_load_dword v[[LOAD_ARG2_2:[0-9]+]], off, s[0:3], s32 offset:24{{$}}
+; GCN-DAG: buffer_load_dword v[[LOAD_ARG2_3:[0-9]+]], off, s[0:3], s32 offset:28{{$}}
 
 ; 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 +656,15 @@
 }
 
 ; GCN-LABEL: {{^}}void_func_v32i32_v4i32_v4f32:
-; 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_0:[0-9]+]], off, s[0:3], s32{{$}}
+; GCN-DAG: buffer_load_dword v[[LOAD_ARG1_1:[0-9]+]], off, s[0:3], s32 offset:4{{$}}
+; GCN-DAG: buffer_load_dword v[[LOAD_ARG1_2:[0-9]+]], off, s[0:3], s32 offset:8{{$}}
+; GCN-DAG: buffer_load_dword v[[LOAD_ARG1_3:[0-9]+]], off, s[0:3], s32 offset:12{{$}}
 
-; 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-DAG: buffer_load_dword v[[LOAD_ARG2_0:[0-9]+]], off, s[0:3], s32 offset:16{{$}}
+; GCN-DAG: buffer_load_dword v[[LOAD_ARG2_1:[0-9]+]], off, s[0:3], s32 offset:20{{$}}
+; GCN-DAG: buffer_load_dword v[[LOAD_ARG2_2:[0-9]+]], off, s[0:3], s32 offset:24{{$}}
+; GCN-DAG: buffer_load_dword v[[LOAD_ARG2_3:[0-9]+]], off, s[0:3], s32 offset:28{{$}}
 
 ; 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 +676,23 @@
 }
 
 ; GCN-LABEL: {{^}}void_func_v32i32_v8i32_v8f32:
-; 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_ARG1_0:[0-9]+]], off, s[0:3], s32{{$}}
+; GCN-DAG: buffer_load_dword v[[LOAD_ARG1_1:[0-9]+]], off, s[0:3], s32 offset:4{{$}}
+; GCN-DAG: buffer_load_dword v[[LOAD_ARG1_2:[0-9]+]], off, s[0:3], s32 offset:8{{$}}
+; GCN-DAG: buffer_load_dword v[[LOAD_ARG1_3:[0-9]+]], off, s[0:3], s32 offset:12{{$}}
+; GCN-DAG: buffer_load_dword v[[LOAD_ARG1_4:[0-9]+]], off, s[0:3], s32 offset:16{{$}}
+; GCN-DAG: buffer_load_dword v[[LOAD_ARG1_5:[0-9]+]], off, s[0:3], s32 offset:20{{$}}
+; GCN-DAG: buffer_load_dword v[[LOAD_ARG1_6:[0-9]+]], off, s[0:3], s32 offset:24{{$}}
+; GCN-DAG: buffer_load_dword v[[LOAD_ARG1_7:[0-9]+]], off, s[0:3], s32 offset:28{{$}}
 
-; 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-DAG: buffer_load_dword v[[LOAD_ARG2_0:[0-9]+]], off, s[0:3], s32 offset:32{{$}}
+; GCN-DAG: buffer_load_dword v[[LOAD_ARG2_1:[0-9]+]], off, s[0:3], s32 offset:36{{$}}
+; GCN-DAG: buffer_load_dword v[[LOAD_ARG2_2:[0-9]+]], off, s[0:3], s32 offset:40{{$}}
+; GCN-DAG: buffer_load_dword v[[LOAD_ARG2_3:[0-9]+]], off, s[0:3], s32 offset:44{{$}}
+; GCN-DAG: buffer_load_dword v[[LOAD_ARG2_4:[0-9]+]], off, s[0:3], s32 offset:48{{$}}
+; GCN-DAG: buffer_load_dword v[[LOAD_ARG2_5:[0-9]+]], off, s[0:3], s32 offset:52{{$}}
+; GCN-DAG: buffer_load_dword v[[LOAD_ARG2_6:[0-9]+]], off, s[0:3], s32 offset:56{{$}}
+; GCN-DAG: buffer_load_dword v[[LOAD_ARG2_7:[0-9]+]], off, s[0:3], s32 offset:60{{$}}
 
 ; 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 +706,39 @@
 }
 
 ; GCN-LABEL: {{^}}void_func_v32i32_v16i32_v16f32:
-; 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_ARG1_0:[0-9]+]], off, s[0:3], s32{{$}}
+; GCN-DAG: buffer_load_dword v[[LOAD_ARG1_1:[0-9]+]], off, s[0:3], s32 offset:4{{$}}
+; GCN-DAG: buffer_load_dword v[[LOAD_ARG1_2:[0-9]+]], off, s[0:3], s32 offset:8{{$}}
+; GCN-DAG: buffer_load_dword v[[LOAD_ARG1_:[0-9]+]], off, s[0:3], s32 offset:12{{$}}
+; GCN-DAG: buffer_load_dword v[[LOAD_ARG1_4:[0-9]+]], off, s[0:3], s32 offset:16{{$}}
+; GCN-DAG: buffer_load_dword v[[LOAD_ARG1_5:[0-9]+]], off, s[0:3], s32 offset:20{{$}}
+; GCN-DAG: buffer_load_dword v[[LOAD_ARG1_6:[0-9]+]], off, s[0:3], s32 offset:24{{$}}
+; GCN-DAG: buffer_load_dword v[[LOAD_ARG1_7:[0-9]+]], off, s[0:3], s32 offset:28{{$}}
+; GCN-DAG: buffer_load_dword v[[LOAD_ARG1_8:[0-9]+]], off, s[0:3], s32 offset:32{{$}}
+; GCN-DAG: buffer_load_dword v[[LOAD_ARG1_9:[0-9]+]], off, s[0:3], s32 offset:36{{$}}
+; GCN-DAG: buffer_load_dword v[[LOAD_ARG1_10:[0-9]+]], off, s[0:3], s32 offset:40{{$}}
+; GCN-DAG: buffer_load_dword v[[LOAD_ARG1_11:[0-9]+]], off, s[0:3], s32 offset:44{{$}}
+; GCN-DAG: buffer_load_dword v[[LOAD_ARG1_12:[0-9]+]], off, s[0:3], s32 offset:48{{$}}
+; GCN-DAG: buffer_load_dword v[[LOAD_ARG1_13:[0-9]+]], off, s[0:3], s32 offset:52{{$}}
+; GCN-DAG: buffer_load_dword v[[LOAD_ARG1_14:[0-9]+]], off, s[0:3], s32 offset:56{{$}}
+; GCN-DAG: buffer_load_dword v[[LOAD_ARG2_15:[0-9]+]], off, s[0:3], s32 offset:60{{$}}
 
-; 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{{$}}
-; GCN-DAG: buffer_load_dword v[[LOAD_ARG2_15:[0-9]+]], off, s[0:3], s5 offset:128{{$}}
+; GCN-DAG: buffer_load_dword v[[LOAD_ARG2_0:[0-9]+]], off, s[0:3], s32 offset:64{{$}}
+; GCN-DAG: buffer_load_dword v[[LOAD_ARG2_1:[0-9]+]], off, s[0:3], s32 offset:68{{$}}
+; GCN-DAG: buffer_load_dword v[[LOAD_ARG2_2:[0-9]+]], off, s[0:3], s32 offset:72{{$}}
+; GCN-DAG: buffer_load_dword v[[LOAD_ARG2_3:[0-9]+]], off, s[0:3], s32 offset:76{{$}}
+; GCN-DAG: buffer_load_dword v[[LOAD_ARG2_4:[0-9]+]], off, s[0:3], s32 offset:80{{$}}
+; GCN-DAG: buffer_load_dword v[[LOAD_ARG2_5:[0-9]+]], off, s[0:3], s32 offset:84{{$}}
+; GCN-DAG: buffer_load_dword v[[LOAD_ARG2_6:[0-9]+]], off, s[0:3], s32 offset:88{{$}}
+; GCN-DAG: buffer_load_dword v[[LOAD_ARG2_7:[0-9]+]], off, s[0:3], s32 offset:92{{$}}
+; GCN-DAG: buffer_load_dword v[[LOAD_ARG2_8:[0-9]+]], off, s[0:3], s32 offset:96{{$}}
+; GCN-DAG: buffer_load_dword v[[LOAD_ARG2_9:[0-9]+]], off, s[0:3], s32 offset:100{{$}}
+; GCN-DAG: buffer_load_dword v[[LOAD_ARG2_10:[0-9]+]], off, s[0:3], s32 offset:104{{$}}
+; GCN-DAG: buffer_load_dword v[[LOAD_ARG2_11:[0-9]+]], off, s[0:3], s32 offset:108{{$}}
+; GCN-DAG: buffer_load_dword v[[LOAD_ARG2_12:[0-9]+]], off, s[0:3], s32 offset:112{{$}}
+; GCN-DAG: buffer_load_dword v[[LOAD_ARG2_13:[0-9]+]], off, s[0:3], s32 offset:116{{$}}
+; GCN-DAG: buffer_load_dword v[[LOAD_ARG2_14:[0-9]+]], off, s[0:3], s32 offset:120{{$}}
+; GCN-DAG: buffer_load_dword v[[LOAD_ARG2_15:[0-9]+]], off, s[0:3], s32 offset:124{{$}}
 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
@@ -732,6 +746,45 @@
   ret void
 }
 
+; Make sure v3 isn't a wasted register because of v3 types being promoted to v4
+; GCN-LABEL: {{^}}void_func_v3f32_wasted_reg:
+; GCN: s_waitcnt
+; GCN: ds_write_b32 v{{[0-9]+}}, v0
+; GCN-NEXT: ds_write_b32 v{{[0-9]+}}, v1
+; GCN-NEXT: ds_write_b32 v{{[0-9]+}}, v2
+; GCN-NEXT: ds_write_b32 v{{[0-9]+}}, v3
+; GCN-NEXT: s_waitcnt
+; GCN-NEXT: s_setpc_b64
+define void @void_func_v3f32_wasted_reg(<3 x float> %arg0, i32 %arg1) #0 {
+  %arg0.0 = extractelement <3 x float> %arg0, i32 0
+  %arg0.1 = extractelement <3 x float> %arg0, i32 1
+  %arg0.2 = extractelement <3 x float> %arg0, i32 2
+  store volatile float %arg0.0, float addrspace(3)* undef
+  store volatile float %arg0.1, float addrspace(3)* undef
+  store volatile float %arg0.2, float addrspace(3)* undef
+  store volatile i32 %arg1, i32 addrspace(3)* undef
+  ret void
+}
+
+; GCN-LABEL: {{^}}void_func_v3i32_wasted_reg:
+; GCN: s_waitcnt
+; GCN: ds_write_b32 v{{[0-9]+}}, v0
+; GCN-NEXT: ds_write_b32 v{{[0-9]+}}, v1
+; GCN-NEXT: ds_write_b32 v{{[0-9]+}}, v2
+; GCN-NEXT: ds_write_b32 v{{[0-9]+}}, v3
+; GCN-NEXT: s_waitcnt
+; GCN-NEXT: s_setpc_b64
+define void @void_func_v3i32_wasted_reg(<3 x i32> %arg0, i32 %arg1) #0 {
+  %arg0.0 = extractelement <3 x i32> %arg0, i32 0
+  %arg0.1 = extractelement <3 x i32> %arg0, i32 1
+  %arg0.2 = extractelement <3 x i32> %arg0, i32 2
+  store volatile i32 %arg0.0, i32 addrspace(3)* undef
+  store volatile i32 %arg0.1, i32 addrspace(3)* undef
+  store volatile i32 %arg0.2, i32 addrspace(3)* undef
+  store volatile i32 %arg1, i32 addrspace(3)* undef
+  ret void
+}
+
 ; Check there is no crash.
 ; GCN-LABEL: {{^}}void_func_v16i8:
 define void @void_func_v16i8(<16 x i8> %arg0) #0 {