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
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
|
; RUN: llc -mtriple=amdgcn -mcpu=gfx1010 -verify-machineinstrs < %s | FileCheck --check-prefixes=GCN,W32 --enable-var-scope %s
; RUN: llc -mtriple=amdgcn -mcpu=gfx1010 -mattr=+wavefrontsize64 -verify-machineinstrs < %s | FileCheck --check-prefixes=GCN,W64 --enable-var-scope %s
; RUN: opt -mtriple=amdgcn-amd-amdhsa -mcpu=gfx1010 -S -amdgpu-annotate-uniform < %s | FileCheck --check-prefixes=OPT,OPT-W32 --enable-var-scope %s
; RUN: opt -mtriple=amdgcn-amd-amdhsa -mcpu=gfx1010 -mattr=+wavefrontsize64 -S -amdgpu-annotate-uniform < %s | FileCheck --check-prefixes=OPT,OPT-W64 --enable-var-scope %s
; GCN-LABEL: {{^}}lshr_threadid:
; W64: global_load_dword
; W32: v_readfirstlane_b32 [[OFFSET:s[0-9]+]], v0
; W32: s_load_dword s{{[0-9]+}}, s[{{[0-9:]+}}], [[OFFSET]]
; OPT-LABEL: @lshr_threadid
; OPT-W64: %arrayidx = getelementptr inbounds i32, ptr addrspace(1) %in, i64 %div4{{$}}
; OPT-W32: %arrayidx = getelementptr inbounds i32, ptr addrspace(1) %in, i64 %div4, !amdgpu.uniform
define amdgpu_kernel void @lshr_threadid(ptr addrspace(1) align 4 %in, ptr addrspace(1) align 4 %out) !reqd_work_group_size !0 {
entry:
%lid = tail call i32 @llvm.amdgcn.workitem.id.x()
%div = lshr i32 %lid, 5
%div4 = zext i32 %div to i64
%arrayidx = getelementptr inbounds i32, ptr addrspace(1) %in, i64 %div4
%load = load i32, ptr addrspace(1) %arrayidx, align 4
%arrayidx2 = getelementptr inbounds i32, ptr addrspace(1) %out, i64 %div4
store i32 %load, ptr addrspace(1) %arrayidx2, align 4
ret void
}
; GCN-LABEL: {{^}}ashr_threadid:
; W64: global_load_dword
; W32: v_readfirstlane_b32 [[OFFSET:s[0-9]+]], v0
; W32: s_load_dword s{{[0-9]+}}, s[{{[0-9:]+}}], [[OFFSET]]
; OPT-LABEL: @ashr_threadid
; OPT-W64: %arrayidx = getelementptr inbounds i32, ptr addrspace(1) %in, i64 %div4{{$}}
; OPT-W32: %arrayidx = getelementptr inbounds i32, ptr addrspace(1) %in, i64 %div4, !amdgpu.uniform
define amdgpu_kernel void @ashr_threadid(ptr addrspace(1) align 4 %in, ptr addrspace(1) align 4 %out) !reqd_work_group_size !0 {
entry:
%lid = tail call i32 @llvm.amdgcn.workitem.id.x()
%div = ashr i32 %lid, 5
%div4 = zext i32 %div to i64
%arrayidx = getelementptr inbounds i32, ptr addrspace(1) %in, i64 %div4
%load = load i32, ptr addrspace(1) %arrayidx, align 4
%arrayidx2 = getelementptr inbounds i32, ptr addrspace(1) %out, i64 %div4
store i32 %load, ptr addrspace(1) %arrayidx2, align 4
ret void
}
; GCN-LABEL: {{^}}and_threadid:
; W64: global_load_dword
; W32: v_readfirstlane_b32 [[OFFSET:s[0-9]+]], v0
; W32: s_load_dword s{{[0-9]+}}, s[{{[0-9:]+}}], [[OFFSET]]
; OPT-LABEL: @and_threadid
; OPT-W64: %arrayidx = getelementptr inbounds i32, ptr addrspace(1) %in, i64 %div4{{$}}
; OPT-W32: %arrayidx = getelementptr inbounds i32, ptr addrspace(1) %in, i64 %div4, !amdgpu.uniform
define amdgpu_kernel void @and_threadid(ptr addrspace(1) align 4 %in, ptr addrspace(1) align 4 %out) !reqd_work_group_size !0 {
entry:
%lid = tail call i32 @llvm.amdgcn.workitem.id.x()
%and = and i32 %lid, -32
%div4 = zext i32 %and to i64
%arrayidx = getelementptr inbounds i32, ptr addrspace(1) %in, i64 %div4
%load = load i32, ptr addrspace(1) %arrayidx, align 4
%arrayidx2 = getelementptr inbounds i32, ptr addrspace(1) %out, i64 %div4
store i32 %load, ptr addrspace(1) %arrayidx2, align 4
ret void
}
; GCN-LABEL: {{^}}lshr_threadid_no_dim_info:
; GCN: global_load_dword
; OPT-LABEL: @lshr_threadid_no_dim_info
; OPT: %arrayidx = getelementptr inbounds i32, ptr addrspace(1) %in, i64 %div4{{$}}
define amdgpu_kernel void @lshr_threadid_no_dim_info(ptr addrspace(1) align 4 %in, ptr addrspace(1) align 4 %out) {
entry:
%lid = tail call i32 @llvm.amdgcn.workitem.id.x()
%div = lshr i32 %lid, 5
%div4 = zext i32 %div to i64
%arrayidx = getelementptr inbounds i32, ptr addrspace(1) %in, i64 %div4
%load = load i32, ptr addrspace(1) %arrayidx, align 4
%arrayidx2 = getelementptr inbounds i32, ptr addrspace(1) %out, i64 %div4
store i32 %load, ptr addrspace(1) %arrayidx2, align 4
ret void
}
; GCN-LABEL: {{^}}lshr_threadid_2d:
; GCN: global_load_dword
; OPT-LABEL: @lshr_threadid_2d
; OPT: %arrayidx = getelementptr inbounds i32, ptr addrspace(1) %in, i64 %div4{{$}}
define amdgpu_kernel void @lshr_threadid_2d(ptr addrspace(1) align 4 %in, ptr addrspace(1) align 4 %out) !reqd_work_group_size !1 {
entry:
%lid = tail call i32 @llvm.amdgcn.workitem.id.x()
%div = lshr i32 %lid, 5
%div4 = zext i32 %div to i64
%arrayidx = getelementptr inbounds i32, ptr addrspace(1) %in, i64 %div4
%load = load i32, ptr addrspace(1) %arrayidx, align 4
%arrayidx2 = getelementptr inbounds i32, ptr addrspace(1) %out, i64 %div4
store i32 %load, ptr addrspace(1) %arrayidx2, align 4
ret void
}
; GCN-LABEL: {{^}}lshr_threadid_3d:
; GCN: global_load_dword
; OPT-LABEL: @lshr_threadid_3d
; OPT: %arrayidx = getelementptr inbounds i32, ptr addrspace(1) %in, i64 %div4{{$}}
define amdgpu_kernel void @lshr_threadid_3d(ptr addrspace(1) align 4 %in, ptr addrspace(1) align 4 %out) !reqd_work_group_size !2 {
entry:
%lid = tail call i32 @llvm.amdgcn.workitem.id.x()
%div = lshr i32 %lid, 5
%div4 = zext i32 %div to i64
%arrayidx = getelementptr inbounds i32, ptr addrspace(1) %in, i64 %div4
%load = load i32, ptr addrspace(1) %arrayidx, align 4
%arrayidx2 = getelementptr inbounds i32, ptr addrspace(1) %out, i64 %div4
store i32 %load, ptr addrspace(1) %arrayidx2, align 4
ret void
}
; GCN-LABEL: {{^}}lshr_threadid_1d_uneven:
; W64: global_load_dword
; W32: v_readfirstlane_b32 [[OFFSET:s[0-9]+]], v0
; W32: s_load_dword s{{[0-9]+}}, s[{{[0-9:]+}}], [[OFFSET]]
; OPT-LABEL: @lshr_threadid_1d_uneven
; OPT-W64: %arrayidx = getelementptr inbounds i32, ptr addrspace(1) %in, i64 %div4{{$}}
; OPT-W32: %arrayidx = getelementptr inbounds i32, ptr addrspace(1) %in, i64 %div4, !amdgpu.uniform
define amdgpu_kernel void @lshr_threadid_1d_uneven(ptr addrspace(1) align 4 %in, ptr addrspace(1) align 4 %out) !reqd_work_group_size !3 {
entry:
%lid = tail call i32 @llvm.amdgcn.workitem.id.x()
%div = lshr i32 %lid, 5
%div4 = zext i32 %div to i64
%arrayidx = getelementptr inbounds i32, ptr addrspace(1) %in, i64 %div4
%load = load i32, ptr addrspace(1) %arrayidx, align 4
%arrayidx2 = getelementptr inbounds i32, ptr addrspace(1) %out, i64 %div4
store i32 %load, ptr addrspace(1) %arrayidx2, align 4
ret void
}
; GCN-LABEL: {{^}}and_threadid_2d:
; GCN: global_load_dword
; OPT-LABEL: @and_threadid_2d
; OPT: %arrayidx = getelementptr inbounds i32, ptr addrspace(1) %in, i64 %div4{{$}}
define amdgpu_kernel void @and_threadid_2d(ptr addrspace(1) align 4 %in, ptr addrspace(1) align 4 %out) !reqd_work_group_size !1 {
entry:
%lid = tail call i32 @llvm.amdgcn.workitem.id.x()
%and = and i32 %lid, -32
%div4 = zext i32 %and to i64
%arrayidx = getelementptr inbounds i32, ptr addrspace(1) %in, i64 %div4
%load = load i32, ptr addrspace(1) %arrayidx, align 4
%arrayidx2 = getelementptr inbounds i32, ptr addrspace(1) %out, i64 %div4
store i32 %load, ptr addrspace(1) %arrayidx2, align 4
ret void
}
declare i32 @llvm.amdgcn.workitem.id.x()
!0 = !{i32 64, i32 1, i32 1}
!1 = !{i32 65, i32 2, i32 1}
!2 = !{i32 64, i32 1, i32 2}
!3 = !{i32 65, i32 1, i32 1}
|
