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
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
|
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: opt -mtriple=amdgcn-amd-amdhsa -S -passes=amdgpu-lower-kernel-attributes,instcombine %s | FileCheck -enable-var-scope -check-prefix=GCN %s
; Function Attrs: mustprogress nofree norecurse nosync nounwind readnone willreturn
define amdgpu_kernel void @get_local_size_x(ptr addrspace(1) %out) #0 {
; GCN-LABEL: @get_local_size_x(
; GCN-NEXT: [[IMPLICITARG_PTR:%.*]] = tail call ptr addrspace(4) @llvm.amdgcn.implicitarg.ptr()
; GCN-NEXT: [[GEP_LOCAL_SIZE:%.*]] = getelementptr inbounds i8, ptr addrspace(4) [[IMPLICITARG_PTR]], i64 12
; GCN-NEXT: [[LOCAL_SIZE:%.*]] = load i16, ptr addrspace(4) [[GEP_LOCAL_SIZE]], align 4
; GCN-NEXT: store i16 [[LOCAL_SIZE]], ptr addrspace(1) [[OUT:%.*]], align 2
; GCN-NEXT: ret void
;
%group.id = tail call i32 @llvm.amdgcn.workgroup.id.x()
%implicitarg.ptr = tail call ptr addrspace(4) @llvm.amdgcn.implicitarg.ptr()
%block.count.x = load i32, ptr addrspace(4) %implicitarg.ptr, align 4
%cmp.id.count = icmp ult i32 %group.id, %block.count.x
%local.size.offset = select i1 %cmp.id.count, i64 12, i64 18
%gep.local.size = getelementptr inbounds i8, ptr addrspace(4) %implicitarg.ptr, i64 %local.size.offset
%local.size = load i16, ptr addrspace(4) %gep.local.size, align 2
store i16 %local.size, ptr addrspace(1) %out
ret void
}
; Function Attrs: mustprogress nofree norecurse nosync nounwind readnone willreturn
define amdgpu_kernel void @get_local_size_y(ptr addrspace(1) %out) #0 {
; GCN-LABEL: @get_local_size_y(
; GCN-NEXT: [[IMPLICITARG_PTR:%.*]] = tail call ptr addrspace(4) @llvm.amdgcn.implicitarg.ptr()
; GCN-NEXT: [[GEP_LOCAL_SIZE:%.*]] = getelementptr inbounds i8, ptr addrspace(4) [[IMPLICITARG_PTR]], i64 14
; GCN-NEXT: [[LOCAL_SIZE:%.*]] = load i16, ptr addrspace(4) [[GEP_LOCAL_SIZE]], align 2
; GCN-NEXT: store i16 [[LOCAL_SIZE]], ptr addrspace(1) [[OUT:%.*]], align 2
; GCN-NEXT: ret void
;
%group.id = tail call i32 @llvm.amdgcn.workgroup.id.y()
%implicitarg.ptr = tail call ptr addrspace(4) @llvm.amdgcn.implicitarg.ptr()
%gep.block.count.y = getelementptr inbounds i8, ptr addrspace(4) %implicitarg.ptr, i64 4
%block.count.y = load i32, ptr addrspace(4) %gep.block.count.y, align 4
%cmp.id.count = icmp ult i32 %group.id, %block.count.y
%local.size.offset = select i1 %cmp.id.count, i64 14, i64 20
%gep.local.size = getelementptr inbounds i8, ptr addrspace(4) %implicitarg.ptr, i64 %local.size.offset
%local.size = load i16, ptr addrspace(4) %gep.local.size, align 2
store i16 %local.size, ptr addrspace(1) %out
ret void
}
; Function Attrs: mustprogress nofree norecurse nosync nounwind readnone willreturn
define amdgpu_kernel void @get_local_size_z(ptr addrspace(1) %out) #0 {
; GCN-LABEL: @get_local_size_z(
; GCN-NEXT: [[IMPLICITARG_PTR:%.*]] = tail call ptr addrspace(4) @llvm.amdgcn.implicitarg.ptr()
; GCN-NEXT: [[GEP_LOCAL_SIZE:%.*]] = getelementptr inbounds i8, ptr addrspace(4) [[IMPLICITARG_PTR]], i64 16
; GCN-NEXT: [[LOCAL_SIZE:%.*]] = load i16, ptr addrspace(4) [[GEP_LOCAL_SIZE]], align 4
; GCN-NEXT: store i16 [[LOCAL_SIZE]], ptr addrspace(1) [[OUT:%.*]], align 2
; GCN-NEXT: ret void
;
%group.id = tail call i32 @llvm.amdgcn.workgroup.id.z()
%implicitarg.ptr = tail call ptr addrspace(4) @llvm.amdgcn.implicitarg.ptr()
%gep.block.count.z = getelementptr inbounds i8, ptr addrspace(4) %implicitarg.ptr, i64 8
%block.count.z = load i32, ptr addrspace(4) %gep.block.count.z, align 4
%cmp.id.count = icmp ult i32 %group.id, %block.count.z
%local.size.offset = select i1 %cmp.id.count, i64 16, i64 22
%gep.local.size = getelementptr inbounds i8, ptr addrspace(4) %implicitarg.ptr, i64 %local.size.offset
%local.size = load i16, ptr addrspace(4) %gep.local.size, align 2
store i16 %local.size, ptr addrspace(1) %out
ret void
}
; Function Attrs: mustprogress nofree norecurse nosync nounwind readnone willreturn
define amdgpu_kernel void @get_remainder_x(ptr addrspace(1) %out) #0 {
; GCN-LABEL: @get_remainder_x(
; GCN-NEXT: store i16 0, ptr addrspace(1) [[OUT:%.*]], align 2
; GCN-NEXT: ret void
;
%implicitarg.ptr = tail call ptr addrspace(4) @llvm.amdgcn.implicitarg.ptr()
%gep.x = getelementptr inbounds i8, ptr addrspace(4) %implicitarg.ptr, i64 18
%remainder.x = load i16, ptr addrspace(4) %gep.x, align 2
store i16 %remainder.x, ptr addrspace(1) %out
ret void
}
; Function Attrs: mustprogress nofree norecurse nosync nounwind readnone willreturn
define amdgpu_kernel void @get_remainder_y(ptr addrspace(1) %out) #0 {
; GCN-LABEL: @get_remainder_y(
; GCN-NEXT: store i16 0, ptr addrspace(1) [[OUT:%.*]], align 2
; GCN-NEXT: ret void
;
%implicitarg.ptr = tail call ptr addrspace(4) @llvm.amdgcn.implicitarg.ptr()
%gep.y = getelementptr inbounds i8, ptr addrspace(4) %implicitarg.ptr, i64 18
%remainder.y = load i16, ptr addrspace(4) %gep.y, align 2
store i16 %remainder.y, ptr addrspace(1) %out
ret void
}
; Function Attrs: mustprogress nofree norecurse nosync nounwind readnone willreturn
define amdgpu_kernel void @get_remainder_z(ptr addrspace(1) %out) #0 {
; GCN-LABEL: @get_remainder_z(
; GCN-NEXT: store i16 0, ptr addrspace(1) [[OUT:%.*]], align 2
; GCN-NEXT: ret void
;
%implicitarg.ptr = tail call ptr addrspace(4) @llvm.amdgcn.implicitarg.ptr()
%gep.z = getelementptr inbounds i8, ptr addrspace(4) %implicitarg.ptr, i64 18
%remainder.z = load i16, ptr addrspace(4) %gep.z, align 2
store i16 %remainder.z, ptr addrspace(1) %out
ret void
}
; Function Attrs: mustprogress nofree norecurse nosync nounwind readnone willreturn
define amdgpu_kernel void @get_work_group_size_x(ptr addrspace(1) %out) #0 {
; GCN-LABEL: @get_work_group_size_x(
; GCN-NEXT: [[IMPLICITARG_PTR:%.*]] = tail call ptr addrspace(4) @llvm.amdgcn.implicitarg.ptr()
; GCN-NEXT: [[GEP_X:%.*]] = getelementptr inbounds i8, ptr addrspace(4) [[IMPLICITARG_PTR]], i64 12
; GCN-NEXT: [[GROUP_SIZE_X:%.*]] = load i16, ptr addrspace(4) [[GEP_X]], align 4
; GCN-NEXT: store i16 [[GROUP_SIZE_X]], ptr addrspace(1) [[OUT:%.*]], align 2
; GCN-NEXT: ret void
;
%implicitarg.ptr = tail call ptr addrspace(4) @llvm.amdgcn.implicitarg.ptr()
%gep.x = getelementptr inbounds i8, ptr addrspace(4) %implicitarg.ptr, i64 12
%group.size.x = load i16, ptr addrspace(4) %gep.x, align 2
store i16 %group.size.x, ptr addrspace(1) %out
ret void
}
; Function Attrs: mustprogress nofree norecurse nosync nounwind readnone willreturn
define amdgpu_kernel void @get_work_group_size_y(ptr addrspace(1) %out) #0 {
; GCN-LABEL: @get_work_group_size_y(
; GCN-NEXT: [[IMPLICITARG_PTR:%.*]] = tail call ptr addrspace(4) @llvm.amdgcn.implicitarg.ptr()
; GCN-NEXT: [[GEP_Y:%.*]] = getelementptr inbounds i8, ptr addrspace(4) [[IMPLICITARG_PTR]], i64 14
; GCN-NEXT: [[GROUP_SIZE_Y:%.*]] = load i16, ptr addrspace(4) [[GEP_Y]], align 2
; GCN-NEXT: store i16 [[GROUP_SIZE_Y]], ptr addrspace(1) [[OUT:%.*]], align 2
; GCN-NEXT: ret void
;
%implicitarg.ptr = tail call ptr addrspace(4) @llvm.amdgcn.implicitarg.ptr()
%gep.y = getelementptr inbounds i8, ptr addrspace(4) %implicitarg.ptr, i64 14
%group.size.y = load i16, ptr addrspace(4) %gep.y, align 2
store i16 %group.size.y, ptr addrspace(1) %out
ret void
}
; Function Attrs: mustprogress nofree norecurse nosync nounwind readnone willreturn
define amdgpu_kernel void @get_work_group_size_z(ptr addrspace(1) %out) #0 {
; GCN-LABEL: @get_work_group_size_z(
; GCN-NEXT: [[IMPLICITARG_PTR:%.*]] = tail call ptr addrspace(4) @llvm.amdgcn.implicitarg.ptr()
; GCN-NEXT: [[GEP_Z:%.*]] = getelementptr inbounds i8, ptr addrspace(4) [[IMPLICITARG_PTR]], i64 16
; GCN-NEXT: [[GROUP_SIZE_Z:%.*]] = load i16, ptr addrspace(4) [[GEP_Z]], align 4
; GCN-NEXT: store i16 [[GROUP_SIZE_Z]], ptr addrspace(1) [[OUT:%.*]], align 2
; GCN-NEXT: ret void
;
%implicitarg.ptr = tail call ptr addrspace(4) @llvm.amdgcn.implicitarg.ptr()
%gep.z = getelementptr inbounds i8, ptr addrspace(4) %implicitarg.ptr, i64 16
%group.size.z = load i16, ptr addrspace(4) %gep.z, align 2
store i16 %group.size.z, ptr addrspace(1) %out
ret void
}
; Function Attrs: mustprogress nofree norecurse nosync nounwind readnone willreturn
define amdgpu_kernel void @get_work_group_size_x_reqd(ptr addrspace(1) %out) #0 !reqd_work_group_size !0 {
; GCN-LABEL: @get_work_group_size_x_reqd(
; GCN-NEXT: store i16 8, ptr addrspace(1) [[OUT:%.*]], align 2
; GCN-NEXT: ret void
;
%implicitarg.ptr = tail call ptr addrspace(4) @llvm.amdgcn.implicitarg.ptr()
%gep.x = getelementptr inbounds i8, ptr addrspace(4) %implicitarg.ptr, i64 12
%group.size.x = load i16, ptr addrspace(4) %gep.x, align 2
store i16 %group.size.x, ptr addrspace(1) %out
ret void
}
; Function Attrs: mustprogress nofree norecurse nosync nounwind readnone willreturn
define amdgpu_kernel void @get_work_group_size_y_reqd(ptr addrspace(1) %out) #0 !reqd_work_group_size !0 {
; GCN-LABEL: @get_work_group_size_y_reqd(
; GCN-NEXT: store i16 16, ptr addrspace(1) [[OUT:%.*]], align 2
; GCN-NEXT: ret void
;
%implicitarg.ptr = tail call ptr addrspace(4) @llvm.amdgcn.implicitarg.ptr()
%gep.y = getelementptr inbounds i8, ptr addrspace(4) %implicitarg.ptr, i64 14
%group.size.y = load i16, ptr addrspace(4) %gep.y, align 2
store i16 %group.size.y, ptr addrspace(1) %out
ret void
}
; Function Attrs: mustprogress nofree norecurse nosync nounwind readnone willreturn
define amdgpu_kernel void @get_work_group_size_z_reqd(ptr addrspace(1) %out) #0 !reqd_work_group_size !0 {
; GCN-LABEL: @get_work_group_size_z_reqd(
; GCN-NEXT: store i16 2, ptr addrspace(1) [[OUT:%.*]], align 2
; GCN-NEXT: ret void
;
%implicitarg.ptr = tail call ptr addrspace(4) @llvm.amdgcn.implicitarg.ptr()
%gep.z = getelementptr inbounds i8, ptr addrspace(4) %implicitarg.ptr, i64 16
%group.size.z = load i16, ptr addrspace(4) %gep.z, align 2
store i16 %group.size.z, ptr addrspace(1) %out
ret void
}
declare ptr addrspace(4) @llvm.amdgcn.implicitarg.ptr() #1
declare i32 @llvm.amdgcn.workgroup.id.x() #1
declare i32 @llvm.amdgcn.workgroup.id.y() #1
declare i32 @llvm.amdgcn.workgroup.id.z() #1
!llvm.module.flags = !{!1}
attributes #0 = { nounwind "uniform-work-group-size"="true" }
attributes #1 = { nounwind readnone speculatable }
!0 = !{i32 8, i32 16, i32 2}
!1 = !{i32 1, !"amdgpu_code_object_version", i32 500}
|
