1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
|
; RUN: llc -global-isel -march=amdgcn -mcpu=gfx1010 -verify-machineinstrs < %s | FileCheck -check-prefixes=GCN,ALIGNED,ALIGNED-WGP %s
; RUN: llc -global-isel -march=amdgcn -mcpu=gfx1011 -verify-machineinstrs < %s | FileCheck -check-prefixes=GCN,ALIGNED,ALIGNED-WGP %s
; RUN: llc -global-isel -march=amdgcn -mcpu=gfx1012 -verify-machineinstrs < %s | FileCheck -check-prefixes=GCN,ALIGNED,ALIGNED-WGP %s
; RUN: llc -global-isel -march=amdgcn -mcpu=gfx1010 -verify-machineinstrs -mattr=+cumode < %s | FileCheck -check-prefixes=GCN,ALIGNED,ALIGNED-CU %s
; RUN: llc -global-isel -march=amdgcn -mcpu=gfx1010 -verify-machineinstrs -mattr=+cumode,+unaligned-access-mode < %s | FileCheck -check-prefixes=GCN,UNALIGNED %s
; RUN: llc -global-isel -march=amdgcn -mcpu=gfx1100 -verify-machineinstrs < %s | FileCheck -check-prefixes=GCN,ALIGNED,ALIGNED-CU %s
; RUN: llc -global-isel -march=amdgcn -mcpu=gfx1100 -verify-machineinstrs -mattr=+cumode < %s | FileCheck -check-prefixes=GCN,ALIGNED,ALIGNED-CU %s
; RUN: llc -global-isel -march=amdgcn -mcpu=gfx1100 -verify-machineinstrs -mattr=+cumode,+unaligned-access-mode < %s | FileCheck -check-prefixes=GCN,UNALIGNED %s
; GCN-LABEL: test_local_misaligned_v2:
; GCN-DAG: ds_{{read2|load_2addr}}_b32
; GCN-DAG: ds_{{write2|store_2addr}}_b32
define amdgpu_kernel void @test_local_misaligned_v2(ptr addrspace(3) %arg) {
bb:
%lid = tail call i32 @llvm.amdgcn.workitem.id.x()
%gep = getelementptr inbounds i32, ptr addrspace(3) %arg, i32 %lid
%load = load <2 x i32>, ptr addrspace(3) %gep, align 4
%v1 = extractelement <2 x i32> %load, i32 0
%v2 = extractelement <2 x i32> %load, i32 1
%v3 = insertelement <2 x i32> undef, i32 %v2, i32 0
%v4 = insertelement <2 x i32> %v3, i32 %v1, i32 1
store <2 x i32> %v4, ptr addrspace(3) %gep, align 4
ret void
}
; GCN-LABEL: test_local_misaligned_v4:
; ALIGNED-DAG: ds_{{read2|load_2addr}}_b32
; ALIGNED-DAG: ds_{{read2|load_2addr}}_b32
; ALIGNED-DAG: ds_{{write2|store_2addr}}_b32
; ALIGNED-DAG: ds_{{write2|store_2addr}}_b32
; UNALIGNED-DAG: ds_{{read2|load_2addr}}_b64
; UNALIGNED-DAG: ds_{{write2|store_2addr}}_b64
define amdgpu_kernel void @test_local_misaligned_v4(ptr addrspace(3) %arg) {
bb:
%lid = tail call i32 @llvm.amdgcn.workitem.id.x()
%gep = getelementptr inbounds i32, ptr addrspace(3) %arg, i32 %lid
%load = load <4 x i32>, ptr addrspace(3) %gep, align 4
%v1 = extractelement <4 x i32> %load, i32 0
%v2 = extractelement <4 x i32> %load, i32 1
%v3 = extractelement <4 x i32> %load, i32 2
%v4 = extractelement <4 x i32> %load, i32 3
%v5 = insertelement <4 x i32> undef, i32 %v4, i32 0
%v6 = insertelement <4 x i32> %v5, i32 %v3, i32 1
%v7 = insertelement <4 x i32> %v6, i32 %v2, i32 2
%v8 = insertelement <4 x i32> %v7, i32 %v1, i32 3
store <4 x i32> %v8, ptr addrspace(3) %gep, align 4
ret void
}
; GCN-LABEL: test_local_misaligned_v3:
; ALIGNED-DAG: ds_{{read2|load_2addr}}_b32
; ALIGNED-DAG: ds_{{read|load}}_b32
; ALIGNED-DAG: ds_{{write2|store_2addr}}_b32
; ALIGNED-DAG: ds_{{write|store}}_b32
; UNALIGNED-DAG: ds_{{read|load}}_b96
; UNALIGNED-DAG: ds_{{write|store}}_b96
define amdgpu_kernel void @test_local_misaligned_v3(ptr addrspace(3) %arg) {
bb:
%lid = tail call i32 @llvm.amdgcn.workitem.id.x()
%gep = getelementptr inbounds i32, ptr addrspace(3) %arg, i32 %lid
%load = load <3 x i32>, ptr addrspace(3) %gep, align 4
%v1 = extractelement <3 x i32> %load, i32 0
%v2 = extractelement <3 x i32> %load, i32 1
%v3 = extractelement <3 x i32> %load, i32 2
%v5 = insertelement <3 x i32> undef, i32 %v3, i32 0
%v6 = insertelement <3 x i32> %v5, i32 %v1, i32 1
%v7 = insertelement <3 x i32> %v6, i32 %v2, i32 2
store <3 x i32> %v7, ptr addrspace(3) %gep, align 4
ret void
}
; GCN-LABEL: test_local_aligned_v2:
; GCN-DAG: ds_{{read|load}}_b64
; GCN-DAG: ds_{{write|store}}_b64
define amdgpu_kernel void @test_local_aligned_v2(ptr addrspace(3) %arg) {
bb:
%lid = tail call i32 @llvm.amdgcn.workitem.id.x()
%gep = getelementptr inbounds i32, ptr addrspace(3) %arg, i32 %lid
%load = load <2 x i32>, ptr addrspace(3) %gep, align 8
%v1 = extractelement <2 x i32> %load, i32 0
%v2 = extractelement <2 x i32> %load, i32 1
%v3 = insertelement <2 x i32> undef, i32 %v2, i32 0
%v4 = insertelement <2 x i32> %v3, i32 %v1, i32 1
store <2 x i32> %v4, ptr addrspace(3) %gep, align 8
ret void
}
; GCN-LABEL: test_local_aligned_v3:
; GCN-DAG: ds_{{read|load}}_b96
; GCN-DAG: ds_{{write|store}}_b96
define amdgpu_kernel void @test_local_aligned_v3(ptr addrspace(3) %arg) {
bb:
%lid = tail call i32 @llvm.amdgcn.workitem.id.x()
%gep = getelementptr inbounds i32, ptr addrspace(3) %arg, i32 %lid
%load = load <3 x i32>, ptr addrspace(3) %gep, align 16
%v1 = extractelement <3 x i32> %load, i32 0
%v2 = extractelement <3 x i32> %load, i32 1
%v3 = extractelement <3 x i32> %load, i32 2
%v5 = insertelement <3 x i32> undef, i32 %v3, i32 0
%v6 = insertelement <3 x i32> %v5, i32 %v1, i32 1
%v7 = insertelement <3 x i32> %v6, i32 %v2, i32 2
store <3 x i32> %v7, ptr addrspace(3) %gep, align 16
ret void
}
; GCN-LABEL: test_local_v4_aligned8:
; ALIGNED-WGP-DAG: ds_{{read2|load_2addr}}_b32
; ALIGNED-WGP-DAG: ds_{{read2|load_2addr}}_b32
; ALIGNED-WGP-DAG: ds_{{write2|store_2addr}}_b32
; ALIGNED-WGP-DAG: ds_{{write2|store_2addr}}_b32
; ALIGNED-CU-DAG: ds_{{read2|load_2addr}}_b64
; ALIGNED-CU-DAG: ds_{{write2|store_2addr}}_b64
; UNALIGNED-DAG: ds_{{read2|load_2addr}}_b64
; UNALIGNED-DAG: ds_{{write2|store_2addr}}_b64
define amdgpu_kernel void @test_local_v4_aligned8(ptr addrspace(3) %arg) {
bb:
%lid = tail call i32 @llvm.amdgcn.workitem.id.x()
%gep = getelementptr inbounds i32, ptr addrspace(3) %arg, i32 %lid
%load = load <4 x i32>, ptr addrspace(3) %gep, align 8
%v1 = extractelement <4 x i32> %load, i32 0
%v2 = extractelement <4 x i32> %load, i32 1
%v3 = extractelement <4 x i32> %load, i32 2
%v4 = extractelement <4 x i32> %load, i32 3
%v5 = insertelement <4 x i32> undef, i32 %v4, i32 0
%v6 = insertelement <4 x i32> %v5, i32 %v3, i32 1
%v7 = insertelement <4 x i32> %v6, i32 %v2, i32 2
%v8 = insertelement <4 x i32> %v7, i32 %v1, i32 3
store <4 x i32> %v8, ptr addrspace(3) %gep, align 8
ret void
}
declare i32 @llvm.amdgcn.workitem.id.x()
|
