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
| ; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: opt -mtriple=amdgcn-- -S -o - -structurizecfg -structurizecfg-skip-uniform-regions -structurizecfg-relaxed-uniform-regions < %s | FileCheck %s
define amdgpu_cs void @uniform(i32 inreg %v) {
; CHECK-LABEL: @uniform(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[CC:%.*]] = icmp eq i32 [[V:%.*]], 0
; CHECK-NEXT: br i1 [[CC]], label [[IF:%.*]], label [[END:%.*]], !structurizecfg.uniform !0
; CHECK: if:
; CHECK-NEXT: br label [[END]], !structurizecfg.uniform !0
; CHECK: end:
; CHECK-NEXT: ret void
;
entry:
%cc = icmp eq i32 %v, 0
br i1 %cc, label %if, label %end
if:
br label %end
end:
ret void
}
define amdgpu_cs void @nonuniform(i32 addrspace(4)* %ptr) {
; CHECK-LABEL: @nonuniform(
; CHECK-NEXT: entry:
; CHECK-NEXT: br label [[FOR_BODY:%.*]]
; CHECK: for.body:
; CHECK-NEXT: [[I:%.*]] = phi i32 [ 0, [[ENTRY:%.*]] ], [ [[TMP0:%.*]], [[FLOW:%.*]] ]
; CHECK-NEXT: [[CC:%.*]] = icmp ult i32 [[I]], 4
; CHECK-NEXT: br i1 [[CC]], label [[MID_LOOP:%.*]], label [[FLOW]]
; CHECK: mid.loop:
; CHECK-NEXT: [[V:%.*]] = call i32 @llvm.amdgcn.workitem.id.x()
; CHECK-NEXT: [[CC2:%.*]] = icmp eq i32 [[V]], 0
; CHECK-NEXT: br i1 [[CC2]], label [[END_LOOP:%.*]], label [[FLOW1:%.*]]
; CHECK: Flow:
; CHECK-NEXT: [[TMP0]] = phi i32 [ [[TMP2:%.*]], [[FLOW1]] ], [ undef, [[FOR_BODY]] ]
; CHECK-NEXT: [[TMP1:%.*]] = phi i1 [ [[TMP3:%.*]], [[FLOW1]] ], [ true, [[FOR_BODY]] ]
; CHECK-NEXT: br i1 [[TMP1]], label [[FOR_END:%.*]], label [[FOR_BODY]]
; CHECK: end.loop:
; CHECK-NEXT: [[I_INC:%.*]] = add i32 [[I]], 1
; CHECK-NEXT: br label [[FLOW1]]
; CHECK: Flow1:
; CHECK-NEXT: [[TMP2]] = phi i32 [ [[I_INC]], [[END_LOOP]] ], [ undef, [[MID_LOOP]] ]
; CHECK-NEXT: [[TMP3]] = phi i1 [ false, [[END_LOOP]] ], [ true, [[MID_LOOP]] ]
; CHECK-NEXT: br label [[FLOW]]
; CHECK: for.end:
; CHECK-NEXT: br i1 [[CC]], label [[IF:%.*]], label [[END:%.*]]
; CHECK: if:
; CHECK-NEXT: br label [[END]]
; CHECK: end:
; CHECK-NEXT: ret void
;
entry:
br label %for.body
for.body:
%i = phi i32 [0, %entry], [%i.inc, %end.loop]
%cc = icmp ult i32 %i, 4
br i1 %cc, label %mid.loop, label %for.end
mid.loop:
%v = call i32 @llvm.amdgcn.workitem.id.x()
%cc2 = icmp eq i32 %v, 0
br i1 %cc2, label %end.loop, label %for.end
end.loop:
%i.inc = add i32 %i, 1
br label %for.body
for.end:
br i1 %cc, label %if, label %end
if:
br label %end
end:
ret void
}
define amdgpu_cs void @uniform_branch_to_nonuniform_subregions(i32 addrspace(4)* %ptr, i32 inreg %data) {
; CHECK-LABEL: @uniform_branch_to_nonuniform_subregions(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[C:%.*]] = icmp eq i32 [[DATA:%.*]], 42
; CHECK-NEXT: br i1 [[C]], label [[UNIFORM_FOR_BODY:%.*]], label [[FOR_BODY:%.*]], !structurizecfg.uniform !0
; CHECK: for.body:
; CHECK-NEXT: [[I:%.*]] = phi i32 [ 0, [[ENTRY:%.*]] ], [ [[TMP0:%.*]], [[FLOW1:%.*]] ]
; CHECK-NEXT: [[CC:%.*]] = icmp ult i32 [[I]], 4
; CHECK-NEXT: br i1 [[CC]], label [[MID_LOOP:%.*]], label [[FLOW1]]
; CHECK: mid.loop:
; CHECK-NEXT: [[V:%.*]] = call i32 @llvm.amdgcn.workitem.id.x()
; CHECK-NEXT: [[CC2:%.*]] = icmp eq i32 [[V]], 0
; CHECK-NEXT: br i1 [[CC2]], label [[END_LOOP:%.*]], label [[FLOW2:%.*]]
; CHECK: Flow1:
; CHECK-NEXT: [[TMP0]] = phi i32 [ [[TMP2:%.*]], [[FLOW2]] ], [ undef, [[FOR_BODY]] ]
; CHECK-NEXT: [[TMP1:%.*]] = phi i1 [ [[TMP3:%.*]], [[FLOW2]] ], [ true, [[FOR_BODY]] ]
; CHECK-NEXT: br i1 [[TMP1]], label [[FOR_END:%.*]], label [[FOR_BODY]]
; CHECK: end.loop:
; CHECK-NEXT: [[I_INC:%.*]] = add i32 [[I]], 1
; CHECK-NEXT: br label [[FLOW2]]
; CHECK: Flow2:
; CHECK-NEXT: [[TMP2]] = phi i32 [ [[I_INC]], [[END_LOOP]] ], [ undef, [[MID_LOOP]] ]
; CHECK-NEXT: [[TMP3]] = phi i1 [ false, [[END_LOOP]] ], [ true, [[MID_LOOP]] ]
; CHECK-NEXT: br label [[FLOW1]]
; CHECK: for.end:
; CHECK-NEXT: br i1 [[CC]], label [[IF:%.*]], label [[FLOW:%.*]]
; CHECK: if:
; CHECK-NEXT: br label [[FLOW]]
; CHECK: uniform.for.body:
; CHECK-NEXT: [[UNIFORM_I:%.*]] = phi i32 [ 0, [[ENTRY]] ], [ [[TMP4:%.*]], [[FLOW4:%.*]] ]
; CHECK-NEXT: [[UNIFORM_CC:%.*]] = icmp ult i32 [[UNIFORM_I]], 4
; CHECK-NEXT: br i1 [[UNIFORM_CC]], label [[UNIFORM_MID_LOOP:%.*]], label [[FLOW4]]
; CHECK: uniform.mid.loop:
; CHECK-NEXT: [[UNIFORM_V:%.*]] = call i32 @llvm.amdgcn.workitem.id.x()
; CHECK-NEXT: [[UNIFORM_CC2:%.*]] = icmp eq i32 [[UNIFORM_V]], 0
; CHECK-NEXT: br i1 [[UNIFORM_CC2]], label [[UNIFORM_END_LOOP:%.*]], label [[FLOW5:%.*]]
; CHECK: Flow4:
; CHECK-NEXT: [[TMP4]] = phi i32 [ [[TMP6:%.*]], [[FLOW5]] ], [ undef, [[UNIFORM_FOR_BODY]] ]
; CHECK-NEXT: [[TMP5:%.*]] = phi i1 [ [[TMP7:%.*]], [[FLOW5]] ], [ true, [[UNIFORM_FOR_BODY]] ]
; CHECK-NEXT: br i1 [[TMP5]], label [[UNIFORM_FOR_END:%.*]], label [[UNIFORM_FOR_BODY]]
; CHECK: uniform.end.loop:
; CHECK-NEXT: [[UNIFORM_I_INC:%.*]] = add i32 [[UNIFORM_I]], 1
; CHECK-NEXT: br label [[FLOW5]]
; CHECK: Flow5:
; CHECK-NEXT: [[TMP6]] = phi i32 [ [[UNIFORM_I_INC]], [[UNIFORM_END_LOOP]] ], [ undef, [[UNIFORM_MID_LOOP]] ]
; CHECK-NEXT: [[TMP7]] = phi i1 [ false, [[UNIFORM_END_LOOP]] ], [ true, [[UNIFORM_MID_LOOP]] ]
; CHECK-NEXT: br label [[FLOW4]]
; CHECK: uniform.for.end:
; CHECK-NEXT: br i1 [[UNIFORM_CC]], label [[UNIFORM_IF:%.*]], label [[FLOW3:%.*]]
; CHECK: uniform.if:
; CHECK-NEXT: br label [[FLOW3]]
; CHECK: Flow:
; CHECK-NEXT: br label [[END:%.*]]
; CHECK: Flow3:
; CHECK-NEXT: br label [[END]]
; CHECK: end:
; CHECK-NEXT: ret void
;
entry:
%c = icmp eq i32 %data, 42
br i1 %c, label %uniform.for.body, label %for.body
for.body:
%i = phi i32 [0, %entry], [%i.inc, %end.loop]
%cc = icmp ult i32 %i, 4
br i1 %cc, label %mid.loop, label %for.end
mid.loop:
%v = call i32 @llvm.amdgcn.workitem.id.x()
%cc2 = icmp eq i32 %v, 0
br i1 %cc2, label %end.loop, label %for.end
end.loop:
%i.inc = add i32 %i, 1
br label %for.body
for.end:
br i1 %cc, label %if, label %end
if:
br label %end
uniform.for.body:
%uniform.i = phi i32 [0, %entry], [%uniform.i.inc, %uniform.end.loop]
%uniform.cc = icmp ult i32 %uniform.i, 4
br i1 %uniform.cc, label %uniform.mid.loop, label %uniform.for.end
uniform.mid.loop:
%uniform.v = call i32 @llvm.amdgcn.workitem.id.x()
%uniform.cc2 = icmp eq i32 %uniform.v, 0
br i1 %uniform.cc2, label %uniform.end.loop, label %uniform.for.end
uniform.end.loop:
%uniform.i.inc = add i32 %uniform.i, 1
br label %uniform.for.body
uniform.for.end:
br i1 %uniform.cc, label %uniform.if, label %end
uniform.if:
br label %end
end:
ret void
}
declare i32 @llvm.amdgcn.workitem.id.x()
|