1
0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-10-25 05:52:53 +02:00
llvm-mirror/test/CodeGen/AMDGPU/load-global-i32.ll
Tom Stellard d773f533b9 AMDGPU/SI: Implement a custom MachineSchedStrategy
Summary:
GCNSchedStrategy re-uses most of GenericScheduler, it's just uses
a different method to compute the excess and critical register
pressure limits.

It's not enabled by default, to enable it you need to pass -misched=gcn
to llc.

Shader DB stats:

32464 shaders in 17874 tests
Totals:
SGPRS: 1542846 -> 1643125 (6.50 %)
VGPRS: 1005595 -> 904653 (-10.04 %)
Spilled SGPRs: 29929 -> 27745 (-7.30 %)
Spilled VGPRs: 334 -> 352 (5.39 %)
Scratch VGPRs: 1612 -> 1624 (0.74 %) dwords per thread
Code Size: 36688188 -> 37034900 (0.95 %) bytes
LDS: 1913 -> 1913 (0.00 %) blocks
Max Waves: 254101 -> 265125 (4.34 %)
Wait states: 0 -> 0 (0.00 %)

Totals from affected shaders:
SGPRS: 1338220 -> 1438499 (7.49 %)
VGPRS: 886221 -> 785279 (-11.39 %)
Spilled SGPRs: 29869 -> 27685 (-7.31 %)
Spilled VGPRs: 334 -> 352 (5.39 %)
Scratch VGPRs: 1612 -> 1624 (0.74 %) dwords per thread
Code Size: 34315716 -> 34662428 (1.01 %) bytes
LDS: 1551 -> 1551 (0.00 %) blocks
Max Waves: 188127 -> 199151 (5.86 %)
Wait states: 0 -> 0 (0.00 %)

Reviewers: arsenm, mareko, nhaehnle, MatzeB, atrick

Subscribers: arsenm, kzhuravl, llvm-commits

Differential Revision: https://reviews.llvm.org/D23688

llvm-svn: 279995
2016-08-29 19:42:52 +00:00

522 lines
16 KiB
LLVM

; RUN: llc -march=amdgcn -verify-machineinstrs < %s | FileCheck -check-prefix=GCN -check-prefix=GCN-NOHSA -check-prefix=FUNC %s
; RUN: llc -mtriple=amdgcn--amdhsa -mcpu=kaveri -verify-machineinstrs < %s | FileCheck -check-prefix=GCN -check-prefix=GCN-HSA -check-prefix=FUNC %s
; RUN: llc -march=amdgcn -mcpu=tonga -verify-machineinstrs < %s | FileCheck -check-prefix=GCN -check-prefix=GCN-NOHSA -check-prefix=FUNC %s
; RUN: llc -march=r600 -mcpu=redwood < %s | FileCheck -check-prefix=EG -check-prefix=FUNC %s
; FUNC-LABEL: {{^}}global_load_i32:
; GCN-NOHSA: buffer_load_dword v{{[0-9]+}}
; GCN-HSA: flat_load_dword
; EG: VTX_READ_32 T{{[0-9]+}}.X, T{{[0-9]+}}.X, 0
define void @global_load_i32(i32 addrspace(1)* %out, i32 addrspace(1)* %in) #0 {
entry:
%ld = load i32, i32 addrspace(1)* %in
store i32 %ld, i32 addrspace(1)* %out
ret void
}
; FUNC-LABEL: {{^}}global_load_v2i32:
; GCN-NOHSA: buffer_load_dwordx2
; GCN-HSA: flat_load_dwordx2
; EG: VTX_READ_64
define void @global_load_v2i32(<2 x i32> addrspace(1)* %out, <2 x i32> addrspace(1)* %in) #0 {
entry:
%ld = load <2 x i32>, <2 x i32> addrspace(1)* %in
store <2 x i32> %ld, <2 x i32> addrspace(1)* %out
ret void
}
; FUNC-LABEL: {{^}}global_load_v3i32:
; GCN-NOHSA: buffer_load_dwordx4
; GCN-HSA: flat_load_dwordx4
; EG: VTX_READ_128
define void @global_load_v3i32(<3 x i32> addrspace(1)* %out, <3 x i32> addrspace(1)* %in) #0 {
entry:
%ld = load <3 x i32>, <3 x i32> addrspace(1)* %in
store <3 x i32> %ld, <3 x i32> addrspace(1)* %out
ret void
}
; FUNC-LABEL: {{^}}global_load_v4i32:
; GCN-NOHSA: buffer_load_dwordx4
; GCN-HSA: flat_load_dwordx4
; EG: VTX_READ_128
define void @global_load_v4i32(<4 x i32> addrspace(1)* %out, <4 x i32> addrspace(1)* %in) #0 {
entry:
%ld = load <4 x i32>, <4 x i32> addrspace(1)* %in
store <4 x i32> %ld, <4 x i32> addrspace(1)* %out
ret void
}
; FUNC-LABEL: {{^}}global_load_v8i32:
; GCN-NOHSA: buffer_load_dwordx4
; GCN-NOHSA: buffer_load_dwordx4
; GCN-HSA: flat_load_dwordx4
; GCN-HSA: flat_load_dwordx4
; EG: VTX_READ_128
; EG: VTX_READ_128
define void @global_load_v8i32(<8 x i32> addrspace(1)* %out, <8 x i32> addrspace(1)* %in) #0 {
entry:
%ld = load <8 x i32>, <8 x i32> addrspace(1)* %in
store <8 x i32> %ld, <8 x i32> addrspace(1)* %out
ret void
}
; FUNC-LABEL: {{^}}global_load_v16i32:
; GCN-NOHSA: buffer_load_dwordx4
; GCN-NOHSA: buffer_load_dwordx4
; GCN-NOHSA: buffer_load_dwordx4
; GCN-NOHSA: buffer_load_dwordx4
; GCN-HSA: flat_load_dwordx4
; GCN-HSA: flat_load_dwordx4
; GCN-HSA: flat_load_dwordx4
; GCN-HSA: flat_load_dwordx4
; EG: VTX_READ_128
; EG: VTX_READ_128
; EG: VTX_READ_128
; EG: VTX_READ_128
define void @global_load_v16i32(<16 x i32> addrspace(1)* %out, <16 x i32> addrspace(1)* %in) #0 {
entry:
%ld = load <16 x i32>, <16 x i32> addrspace(1)* %in
store <16 x i32> %ld, <16 x i32> addrspace(1)* %out
ret void
}
; FUNC-LABEL: {{^}}global_zextload_i32_to_i64:
; GCN-NOHSA-DAG: buffer_load_dword v[[LO:[0-9]+]],
; GCN-HSA-DAG: flat_load_dword v[[LO:[0-9]+]],
; GCN-DAG: v_mov_b32_e32 v[[HI:[0-9]+]], 0{{$}}
; GCN-NOHSA: buffer_store_dwordx2 v{{\[}}[[LO]]:[[HI]]]
; GCN-HSA: flat_store_dwordx2 v{{\[[0-9]+:[0-9]+\]}}, v{{\[}}[[LO]]:[[HI]]]
; EG: MEM_RAT_CACHELESS STORE_RAW T{{[0-9]+}}.XY
define void @global_zextload_i32_to_i64(i64 addrspace(1)* %out, i32 addrspace(1)* %in) #0 {
%ld = load i32, i32 addrspace(1)* %in
%ext = zext i32 %ld to i64
store i64 %ext, i64 addrspace(1)* %out
ret void
}
; FUNC-LABEL: {{^}}global_sextload_i32_to_i64:
; GCN-NOHSA: buffer_load_dword v[[LO:[0-9]+]]
; GCN-HSA: flat_load_dword v[[LO:[0-9]+]]
; GCN: v_ashrrev_i32_e32 v[[HI:[0-9]+]], 31, v[[LO]]
; GCN-NOHSA: buffer_store_dwordx2 v{{\[}}[[LO]]:[[HI]]{{\]}}
; GCN-HSA: flat_store_dwordx2 v{{\[[0-9]+:[0-9]+\]}}, v{{\[}}[[LO]]:[[HI]]{{\]}}
; EG: MEM_RAT
; EG: VTX_READ_32
; EG: ASHR {{[* ]*}}T{{[0-9]\.[XYZW]}}, T{{[0-9]\.[XYZW]}}, literal.
; EG: 31
define void @global_sextload_i32_to_i64(i64 addrspace(1)* %out, i32 addrspace(1)* %in) #0 {
%ld = load i32, i32 addrspace(1)* %in
%ext = sext i32 %ld to i64
store i64 %ext, i64 addrspace(1)* %out
ret void
}
; FUNC-LABEL: {{^}}global_zextload_v1i32_to_v1i64:
; GCN-NOHSA: buffer_load_dword
; GCN-NOHSA: buffer_store_dwordx2
; GCN-HSA: flat_load_dword
; GCN-HSA: flat_store_dwordx2
define void @global_zextload_v1i32_to_v1i64(<1 x i64> addrspace(1)* %out, <1 x i32> addrspace(1)* %in) #0 {
%ld = load <1 x i32>, <1 x i32> addrspace(1)* %in
%ext = zext <1 x i32> %ld to <1 x i64>
store <1 x i64> %ext, <1 x i64> addrspace(1)* %out
ret void
}
; FUNC-LABEL: {{^}}global_sextload_v1i32_to_v1i64:
; GCN-NOHSA: buffer_load_dword v[[LO:[0-9]+]]
; GCN-HSA: flat_load_dword v[[LO:[0-9]+]]
; GCN: v_ashrrev_i32_e32 v[[HI:[0-9]+]], 31, v[[LO]]
; GCN-NOHSA: buffer_store_dwordx2 v{{\[}}[[LO]]:[[HI]]{{\]}}
; GCN-HSA: flat_store_dwordx2 v{{\[[0-9]+:[0-9]+\]}}, v{{\[}}[[LO]]:[[HI]]{{\]}}
define void @global_sextload_v1i32_to_v1i64(<1 x i64> addrspace(1)* %out, <1 x i32> addrspace(1)* %in) #0 {
%ld = load <1 x i32>, <1 x i32> addrspace(1)* %in
%ext = sext <1 x i32> %ld to <1 x i64>
store <1 x i64> %ext, <1 x i64> addrspace(1)* %out
ret void
}
; FUNC-LABEL: {{^}}global_zextload_v2i32_to_v2i64:
; GCN-NOHSA: buffer_load_dwordx2
; GCN-NOHSA: buffer_store_dwordx4
; GCN-HSA: flat_load_dwordx2
; GCN-HSA: flat_store_dwordx4
define void @global_zextload_v2i32_to_v2i64(<2 x i64> addrspace(1)* %out, <2 x i32> addrspace(1)* %in) #0 {
%ld = load <2 x i32>, <2 x i32> addrspace(1)* %in
%ext = zext <2 x i32> %ld to <2 x i64>
store <2 x i64> %ext, <2 x i64> addrspace(1)* %out
ret void
}
; FUNC-LABEL: {{^}}global_sextload_v2i32_to_v2i64:
; GCN-NOHSA: buffer_load_dwordx2
; GCN-HSA: flat_load_dwordx2
; GCN-DAG: v_ashrrev_i32
; GCN-DAG: v_ashrrev_i32
; GCN-NOHSA-DAG: buffer_store_dwordx4
; GCN-HSA-DAG: flat_store_dwordx4
define void @global_sextload_v2i32_to_v2i64(<2 x i64> addrspace(1)* %out, <2 x i32> addrspace(1)* %in) #0 {
%ld = load <2 x i32>, <2 x i32> addrspace(1)* %in
%ext = sext <2 x i32> %ld to <2 x i64>
store <2 x i64> %ext, <2 x i64> addrspace(1)* %out
ret void
}
; FUNC-LABEL: {{^}}global_zextload_v4i32_to_v4i64:
; GCN-NOHSA: buffer_load_dwordx4
; GCN-NOHSA: buffer_store_dwordx4
; GCN-NOHSA: buffer_store_dwordx4
; GCN-HSA: flat_load_dwordx4
; GCN-HSA: flat_store_dwordx4
; GCN-HSA: flat_store_dwordx4
define void @global_zextload_v4i32_to_v4i64(<4 x i64> addrspace(1)* %out, <4 x i32> addrspace(1)* %in) #0 {
%ld = load <4 x i32>, <4 x i32> addrspace(1)* %in
%ext = zext <4 x i32> %ld to <4 x i64>
store <4 x i64> %ext, <4 x i64> addrspace(1)* %out
ret void
}
; FUNC-LABEL: {{^}}global_sextload_v4i32_to_v4i64:
; GCN-NOHSA: buffer_load_dwordx4
; GCN-HSA: flat_load_dwordx4
; GCN-DAG: v_ashrrev_i32
; GCN-DAG: v_ashrrev_i32
; GCN-DAG: v_ashrrev_i32
; GCN-DAG: v_ashrrev_i32
; GCN-NOHSA-DAG: buffer_store_dwordx4
; GCN-NOHSA-DAG: buffer_store_dwordx4
; GCN-HSA-DAG: flat_store_dwordx4
; GCN-HSA-DAG: flat_store_dwordx4
define void @global_sextload_v4i32_to_v4i64(<4 x i64> addrspace(1)* %out, <4 x i32> addrspace(1)* %in) #0 {
%ld = load <4 x i32>, <4 x i32> addrspace(1)* %in
%ext = sext <4 x i32> %ld to <4 x i64>
store <4 x i64> %ext, <4 x i64> addrspace(1)* %out
ret void
}
; FUNC-LABEL: {{^}}global_zextload_v8i32_to_v8i64:
; GCN-NOHSA: buffer_load_dwordx4
; GCN-NOHSA: buffer_load_dwordx4
; GCN-HSA: flat_load_dwordx4
; GCN-HSA: flat_load_dwordx4
; GCN-NOHSA-DAG: buffer_store_dwordx4
; GCN-NOHSA-DAG: buffer_store_dwordx4
; GCN-NOHSA-DAG: buffer_store_dwordx4
; GCN-NOHSA-DAG: buffer_store_dwordx4
; GCN-HSA-DAG: flat_store_dwordx4
; GCN-HSA-DAG: flat_store_dwordx4
; GCN-SA-DAG: flat_store_dwordx4
; GCN-HSA-DAG: flat_store_dwordx4
define void @global_zextload_v8i32_to_v8i64(<8 x i64> addrspace(1)* %out, <8 x i32> addrspace(1)* %in) #0 {
%ld = load <8 x i32>, <8 x i32> addrspace(1)* %in
%ext = zext <8 x i32> %ld to <8 x i64>
store <8 x i64> %ext, <8 x i64> addrspace(1)* %out
ret void
}
; FUNC-LABEL: {{^}}global_sextload_v8i32_to_v8i64:
; GCN-NOHSA: buffer_load_dwordx4
; GCN-NOHSA: buffer_load_dwordx4
; GCN-HSA: flat_load_dwordx4
; GCN-HSA: flat_load_dwordx4
; GCN-DAG: v_ashrrev_i32
; GCN-DAG: v_ashrrev_i32
; GCN-DAG: v_ashrrev_i32
; GCN-DAG: v_ashrrev_i32
; GCN-DAG: v_ashrrev_i32
; GCN-DAG: v_ashrrev_i32
; GCN-DAG: v_ashrrev_i32
; GCN-DAG: v_ashrrev_i32
; GCN-NOHSA-DAG: buffer_store_dwordx4
; GCN-NOHSA-DAG: buffer_store_dwordx4
; GCN-NOHSA-DAG: buffer_store_dwordx4
; GCN-NOHSA-DAG: buffer_store_dwordx4
; GCN-HSA-DAG: flat_store_dwordx4
; GCN-HSA-DAG: flat_store_dwordx4
; GCN-HSA-DAG: flat_store_dwordx4
; GCN-HSA-DAG: flat_store_dwordx4
define void @global_sextload_v8i32_to_v8i64(<8 x i64> addrspace(1)* %out, <8 x i32> addrspace(1)* %in) #0 {
%ld = load <8 x i32>, <8 x i32> addrspace(1)* %in
%ext = sext <8 x i32> %ld to <8 x i64>
store <8 x i64> %ext, <8 x i64> addrspace(1)* %out
ret void
}
; FUNC-LABEL: {{^}}global_sextload_v16i32_to_v16i64:
; GCN-NOHSA: buffer_load_dwordx4
; GCN-NOHSA: buffer_load_dwordx4
; GCN-NOHSA: buffer_load_dwordx4
; GCN-NOHSA: buffer_load_dwordx4
; GCN-HSA: flat_load_dwordx4
; GCN-HSA: flat_load_dwordx4
; GCN-HSA: flat_load_dwordx4
; GCN-HSA: flat_load_dwordx4
; GCN-DAG: v_ashrrev_i32
; GCN-DAG: v_ashrrev_i32
; GCN-DAG: v_ashrrev_i32
; GCN-DAG: v_ashrrev_i32
; GCN-NOHSA-DAG: buffer_store_dwordx4
; GCN-HSA-DAG: flat_store_dwordx4
; GCN-DAG: v_ashrrev_i32
; GCN-DAG: v_ashrrev_i32
; GCN-DAG: v_ashrrev_i32
; GCN-DAG: v_ashrrev_i32
; GCN-NOHSA-DAG: buffer_store_dwordx4
; GCN-HSA-DAG: flat_store_dwordx4
; GCN-DAG: v_ashrrev_i32
; GCN-DAG: v_ashrrev_i32
; GCN-DAG: v_ashrrev_i32
; GCN-DAG: v_ashrrev_i32
; GCN-NOHSA-DAG: buffer_store_dwordx4
; GCN-HSA-DAG: flat_store_dwordx4
; GCN-DAG: v_ashrrev_i32
; GCN-DAG: v_ashrrev_i32
; GCN-DAG: v_ashrrev_i32
; GCN-DAG: v_ashrrev_i32
; GCN-NOHSA-DAG: buffer_store_dwordx4
; GCN-HSA-DAG: flat_store_dwordx4
define void @global_sextload_v16i32_to_v16i64(<16 x i64> addrspace(1)* %out, <16 x i32> addrspace(1)* %in) #0 {
%ld = load <16 x i32>, <16 x i32> addrspace(1)* %in
%ext = sext <16 x i32> %ld to <16 x i64>
store <16 x i64> %ext, <16 x i64> addrspace(1)* %out
ret void
}
; FUNC-LABEL: {{^}}global_zextload_v16i32_to_v16i64
; GCN-NOHSA: buffer_load_dwordx4
; GCN-NOHSA: buffer_load_dwordx4
; GCN-NOHSA: buffer_load_dwordx4
; GCN-NOHSA: buffer_load_dwordx4
; GCN-HSA: flat_load_dwordx4
; GCN-HSA: flat_load_dwordx4
; GCN-HSA: flat_load_dwordx4
; GCN-HSA: flat_load_dwordx4
; GCN-NOHSA: buffer_store_dwordx4
; GCN-NOHSA: buffer_store_dwordx4
; GCN-NOHSA: buffer_store_dwordx4
; GCN-NOHSA: buffer_store_dwordx4
; GCN-NOHSA: buffer_store_dwordx4
; GCN-NOHSA: buffer_store_dwordx4
; GCN-NOHSA: buffer_store_dwordx4
; GCN-NOHSA: buffer_store_dwordx4
; GCN-HSA: flat_store_dwordx4
; GCN-HSA: flat_store_dwordx4
; GCN-HSA: flat_store_dwordx4
; GCN-HSA: flat_store_dwordx4
; GCN-HSA: flat_store_dwordx4
; GCN-HSA: flat_store_dwordx4
; GCN-HSA: flat_store_dwordx4
; GCN-HSA: flat_store_dwordx4
define void @global_zextload_v16i32_to_v16i64(<16 x i64> addrspace(1)* %out, <16 x i32> addrspace(1)* %in) #0 {
%ld = load <16 x i32>, <16 x i32> addrspace(1)* %in
%ext = zext <16 x i32> %ld to <16 x i64>
store <16 x i64> %ext, <16 x i64> addrspace(1)* %out
ret void
}
; FUNC-LABEL: {{^}}global_sextload_v32i32_to_v32i64:
; GCN-NOHSA: buffer_load_dwordx4
; GCN-NOHSA: buffer_load_dwordx4
; GCN-NOHSA: buffer_load_dwordx4
; GCN-NOHSA: buffer_load_dwordx4
; GCN-NOHSA: buffer_load_dwordx4
; GCN-NOHSA: buffer_load_dwordx4
; GCN-NOHSA: buffer_load_dwordx4
; GCN-NOHSA-DAG: buffer_load_dwordx4
; GCN-HSA: flat_load_dwordx4
; GCN-HSA: flat_load_dwordx4
; GCN-HSA: flat_load_dwordx4
; GCN-HSA: flat_load_dwordx4
; GCN-HSA: flat_load_dwordx4
; GCN-HSA: flat_load_dwordx4
; GCN-HSA: flat_load_dwordx4
; GCN-HSA: flat_load_dwordx4
; GCN-DAG: v_ashrrev_i32
; GCN-DAG: v_ashrrev_i32
; GCN-DAG: v_ashrrev_i32
; GCN-DAG: v_ashrrev_i32
; GCN-DAG: v_ashrrev_i32
; GCN-DAG: v_ashrrev_i32
; GCN-DAG: v_ashrrev_i32
; GCN-DAG: v_ashrrev_i32
; GCN-DAG: v_ashrrev_i32
; GCN-DAG: v_ashrrev_i32
; GCN-DAG: v_ashrrev_i32
; GCN-DAG: v_ashrrev_i32
; GCN-DAG: v_ashrrev_i32
; GCN-DAG: v_ashrrev_i32
; GCN-DAG: v_ashrrev_i32
; GCN-DAG: v_ashrrev_i32
; GCN-DAG: v_ashrrev_i32
; GCN-DAG: v_ashrrev_i32
; GCN-DAG: v_ashrrev_i32
; GCN-DAG: v_ashrrev_i32
; GCN-DAG: v_ashrrev_i32
; GCN-DAG: v_ashrrev_i32
; GCN-DAG: v_ashrrev_i32
; GCN-DAG: v_ashrrev_i32
; GCN-DAG: v_ashrrev_i32
; GCN-DAG: v_ashrrev_i32
; GCN-DAG: v_ashrrev_i32
; GCN-DAG: v_ashrrev_i32
; GCN-DAG: v_ashrrev_i32
; GCN-DAG: v_ashrrev_i32
; GCN-DAG: v_ashrrev_i32
; GCN-DAG: v_ashrrev_i32
; GCN-NOHSA: buffer_store_dwordx4
; GCN-NOHSA: buffer_store_dwordx4
; GCN-NOHSA: buffer_store_dwordx4
; GCN-NOHSA: buffer_store_dwordx4
; GCN-NOHSA: buffer_store_dwordx4
; GCN-NOHSA: buffer_store_dwordx4
; GCN-NOHSA: buffer_store_dwordx4
; GCN-NOHSA: buffer_store_dwordx4
; GCN-NOHSA: buffer_store_dwordx4
; GCN-NOHSA: buffer_store_dwordx4
; GCN-NOHSA: buffer_store_dwordx4
; GCN-NOHSA: buffer_store_dwordx4
; GCN-NOHSA: buffer_store_dwordx4
; GCN-NOHSA: buffer_store_dwordx4
; GCN-NOHSA: buffer_store_dwordx4
; GCN-NOHSA: buffer_store_dwordx4
; GCN-HSA: flat_store_dwordx4
; GCN-HSA: flat_store_dwordx4
; GCN-HSA: flat_store_dwordx4
; GCN-HSA: flat_store_dwordx4
; GCN-HSA: flat_store_dwordx4
; GCN-HSA: flat_store_dwordx4
; GCN-HSA: flat_store_dwordx4
; GCN-HSA: flat_store_dwordx4
; GCN-HSA: flat_store_dwordx4
; GCN-HSA: flat_store_dwordx4
; GCN-HSA: flat_store_dwordx4
; GCN-HSA: flat_store_dwordx4
; GCN-HSA: flat_store_dwordx4
; GCN-HSA: flat_store_dwordx4
; GCN-HSA: flat_store_dwordx4
; GCN-HSA: flat_store_dwordx4
define void @global_sextload_v32i32_to_v32i64(<32 x i64> addrspace(1)* %out, <32 x i32> addrspace(1)* %in) #0 {
%ld = load <32 x i32>, <32 x i32> addrspace(1)* %in
%ext = sext <32 x i32> %ld to <32 x i64>
store <32 x i64> %ext, <32 x i64> addrspace(1)* %out
ret void
}
; FUNC-LABEL: {{^}}global_zextload_v32i32_to_v32i64:
; GCN-NOHSA: buffer_load_dwordx4
; GCN-NOHSA: buffer_load_dwordx4
; GCN-NOHSA: buffer_load_dwordx4
; GCN-NOHSA: buffer_load_dwordx4
; GCN-NOHSA: buffer_load_dwordx4
; GCN-NOHSA: buffer_load_dwordx4
; GCN-NOHSA: buffer_load_dwordx4
; GCN-NOHSA: buffer_load_dwordx4
; GCN-HSA: flat_load_dwordx4
; GCN-HSA: flat_load_dwordx4
; GCN-HSA: flat_load_dwordx4
; GCN-HSA: flat_load_dwordx4
; GCN-HSA: flat_load_dwordx4
; GCN-HSA: flat_load_dwordx4
; GCN-HSA: flat_load_dwordx4
; GCN-HSA: flat_load_dwordx4
; GCN-NOHSA-DAG: buffer_store_dwordx4
; GCN-NOHSA-DAG: buffer_store_dwordx4
; GCN-NOHSA-DAG: buffer_store_dwordx4
; GCN-NOHSA-DAG: buffer_store_dwordx4
; GCN-NOHSA-DAG: buffer_store_dwordx4
; GCN-NOHSA-DAG: buffer_store_dwordx4
; GCN-NOHSA-DAG: buffer_store_dwordx4
; GCN-NOHSA-DAG: buffer_store_dwordx4
; GCN-NOHSA-DAG: buffer_store_dwordx4
; GCN-NOHSA-DAG: buffer_store_dwordx4
; GCN-NOHSA-DAG: buffer_store_dwordx4
; GCN-NOHSA-DAG: buffer_store_dwordx4
; GCN-NOHSA-DAG: buffer_store_dwordx4
; GCN-NOHSA-DAG: buffer_store_dwordx4
; GCN-NOHSA-DAG: buffer_store_dwordx4
; GCN-NOHSA-DAG: buffer_store_dwordx4
; GCN-HSA-DAG: flat_store_dwordx4
; GCN-HSA-DAG: flat_store_dwordx4
; GCN-HSA-DAG: flat_store_dwordx4
; GCN-HSA-DAG: flat_store_dwordx4
; GCN-HSA-DAG: flat_store_dwordx4
; GCN-HSA-DAG: flat_store_dwordx4
; GCN-HSA-DAG: flat_store_dwordx4
; GCN-HSA-DAG: flat_store_dwordx4
; GCN-HSA-DAG: flat_store_dwordx4
; GCN-HSA-DAG: flat_store_dwordx4
; GCN-HSA-DAG: flat_store_dwordx4
; GCN-HSA-DAG: flat_store_dwordx4
; GCN-HSA-DAG: flat_store_dwordx4
; GCN-HSA-DAG: flat_store_dwordx4
; GCN-HSA-DAG: flat_store_dwordx4
; GCN-HSA-DAG: flat_store_dwordx4
define void @global_zextload_v32i32_to_v32i64(<32 x i64> addrspace(1)* %out, <32 x i32> addrspace(1)* %in) #0 {
%ld = load <32 x i32>, <32 x i32> addrspace(1)* %in
%ext = zext <32 x i32> %ld to <32 x i64>
store <32 x i64> %ext, <32 x i64> addrspace(1)* %out
ret void
}
attributes #0 = { nounwind }