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
204
205
206
207
208
209
210
211
|
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: llc -mtriple=amdgcn -verify-machineinstrs -simplifycfg-require-and-preserve-domtree=1 < %s | FileCheck -check-prefix=SI %s
; RUN: opt -mtriple=amdgcn-- -S -amdgpu-unify-divergent-exit-nodes -verify -simplifycfg-require-and-preserve-domtree=1 %s | FileCheck -check-prefix=IR %s
define amdgpu_kernel void @infinite_loop(ptr addrspace(1) %out) {
; SI-LABEL: infinite_loop:
; SI: ; %bb.0: ; %entry
; SI-NEXT: s_load_dwordx2 s[0:1], s[2:3], 0x9
; SI-NEXT: s_mov_b32 s3, 0xf000
; SI-NEXT: s_mov_b32 s2, -1
; SI-NEXT: v_mov_b32_e32 v0, 0x3e7
; SI-NEXT: s_and_b64 vcc, exec, -1
; SI-NEXT: .LBB0_1: ; %loop
; SI-NEXT: ; =>This Inner Loop Header: Depth=1
; SI-NEXT: s_waitcnt lgkmcnt(0)
; SI-NEXT: buffer_store_dword v0, off, s[0:3], 0
; SI-NEXT: s_waitcnt vmcnt(0)
; SI-NEXT: s_mov_b64 vcc, vcc
; SI-NEXT: s_cbranch_vccnz .LBB0_1
; SI-NEXT: ; %bb.2: ; %DummyReturnBlock
; SI-NEXT: s_endpgm
; IR-LABEL: @infinite_loop(
; IR-NEXT: entry:
; IR-NEXT: br label [[LOOP:%.*]]
; IR: loop:
; IR-NEXT: store volatile i32 999, ptr addrspace(1) [[OUT:%.*]], align 4
; IR-NEXT: br i1 true, label [[LOOP]], label [[DUMMYRETURNBLOCK:%.*]]
; IR: DummyReturnBlock:
; IR-NEXT: ret void
entry:
br label %loop
loop:
store volatile i32 999, ptr addrspace(1) %out, align 4
br label %loop
}
define amdgpu_kernel void @infinite_loop_ret(ptr addrspace(1) %out) {
; SI-LABEL: infinite_loop_ret:
; SI: ; %bb.0: ; %entry
; SI-NEXT: v_cmp_eq_u32_e32 vcc, 1, v0
; SI-NEXT: s_and_saveexec_b64 s[0:1], vcc
; SI-NEXT: s_cbranch_execz .LBB1_3
; SI-NEXT: ; %bb.1: ; %loop.preheader
; SI-NEXT: s_load_dwordx2 s[0:1], s[2:3], 0x9
; SI-NEXT: s_mov_b32 s3, 0xf000
; SI-NEXT: s_mov_b32 s2, -1
; SI-NEXT: v_mov_b32_e32 v0, 0x3e7
; SI-NEXT: s_and_b64 vcc, exec, -1
; SI-NEXT: .LBB1_2: ; %loop
; SI-NEXT: ; =>This Inner Loop Header: Depth=1
; SI-NEXT: s_waitcnt lgkmcnt(0)
; SI-NEXT: buffer_store_dword v0, off, s[0:3], 0
; SI-NEXT: s_waitcnt vmcnt(0)
; SI-NEXT: s_mov_b64 vcc, vcc
; SI-NEXT: s_cbranch_vccnz .LBB1_2
; SI-NEXT: .LBB1_3: ; %UnifiedReturnBlock
; SI-NEXT: s_endpgm
; IR-LABEL: @infinite_loop_ret(
; IR-NEXT: entry:
; IR-NEXT: [[TMP:%.*]] = tail call i32 @llvm.amdgcn.workitem.id.x()
; IR-NEXT: [[COND:%.*]] = icmp eq i32 [[TMP]], 1
; IR-NEXT: br i1 [[COND]], label [[LOOP:%.*]], label [[UNIFIEDRETURNBLOCK:%.*]]
; IR: loop:
; IR-NEXT: store volatile i32 999, ptr addrspace(1) [[OUT:%.*]], align 4
; IR-NEXT: br i1 true, label [[LOOP]], label [[UNIFIEDRETURNBLOCK]]
; IR: UnifiedReturnBlock:
; IR-NEXT: ret void
entry:
%tmp = tail call i32 @llvm.amdgcn.workitem.id.x()
%cond = icmp eq i32 %tmp, 1
br i1 %cond, label %loop, label %return
loop:
store volatile i32 999, ptr addrspace(1) %out, align 4
br label %loop
return:
ret void
}
define amdgpu_kernel void @infinite_loops(ptr addrspace(1) %out) {
; SI-LABEL: infinite_loops:
; SI: ; %bb.0: ; %entry
; SI-NEXT: s_load_dwordx2 s[0:1], s[2:3], 0x9
; SI-NEXT: s_mov_b64 s[2:3], -1
; SI-NEXT: s_cbranch_scc1 .LBB2_4
; SI-NEXT: ; %bb.1:
; SI-NEXT: s_mov_b32 s3, 0xf000
; SI-NEXT: s_mov_b32 s2, -1
; SI-NEXT: v_mov_b32_e32 v0, 0x378
; SI-NEXT: s_and_b64 vcc, exec, -1
; SI-NEXT: .LBB2_2: ; %loop2
; SI-NEXT: ; =>This Inner Loop Header: Depth=1
; SI-NEXT: s_waitcnt lgkmcnt(0)
; SI-NEXT: buffer_store_dword v0, off, s[0:3], 0
; SI-NEXT: s_waitcnt vmcnt(0)
; SI-NEXT: s_mov_b64 vcc, vcc
; SI-NEXT: s_cbranch_vccnz .LBB2_2
; SI-NEXT: ; %bb.3: ; %Flow
; SI-NEXT: s_mov_b64 s[2:3], 0
; SI-NEXT: .LBB2_4: ; %Flow2
; SI-NEXT: s_and_b64 vcc, exec, s[2:3]
; SI-NEXT: s_waitcnt lgkmcnt(0)
; SI-NEXT: s_mov_b64 vcc, vcc
; SI-NEXT: s_cbranch_vccz .LBB2_7
; SI-NEXT: ; %bb.5:
; SI-NEXT: s_mov_b32 s3, 0xf000
; SI-NEXT: s_mov_b32 s2, -1
; SI-NEXT: s_waitcnt expcnt(0)
; SI-NEXT: v_mov_b32_e32 v0, 0x3e7
; SI-NEXT: s_and_b64 vcc, exec, 0
; SI-NEXT: .LBB2_6: ; %loop1
; SI-NEXT: ; =>This Inner Loop Header: Depth=1
; SI-NEXT: buffer_store_dword v0, off, s[0:3], 0
; SI-NEXT: s_waitcnt vmcnt(0)
; SI-NEXT: s_mov_b64 vcc, vcc
; SI-NEXT: s_cbranch_vccz .LBB2_6
; SI-NEXT: .LBB2_7: ; %DummyReturnBlock
; SI-NEXT: s_endpgm
; IR-LABEL: @infinite_loops(
; IR-NEXT: entry:
; IR-NEXT: br i1 undef, label [[LOOP1:%.*]], label [[LOOP2:%.*]]
; IR: loop1:
; IR-NEXT: store volatile i32 999, ptr addrspace(1) [[OUT:%.*]], align 4
; IR-NEXT: br i1 true, label [[LOOP1]], label [[DUMMYRETURNBLOCK:%.*]]
; IR: loop2:
; IR-NEXT: store volatile i32 888, ptr addrspace(1) [[OUT]], align 4
; IR-NEXT: br i1 true, label [[LOOP2]], label [[DUMMYRETURNBLOCK]]
; IR: DummyReturnBlock:
; IR-NEXT: ret void
entry:
br i1 undef, label %loop1, label %loop2
loop1:
store volatile i32 999, ptr addrspace(1) %out, align 4
br label %loop1
loop2:
store volatile i32 888, ptr addrspace(1) %out, align 4
br label %loop2
}
define amdgpu_kernel void @infinite_loop_nest_ret(ptr addrspace(1) %out) {
; SI-LABEL: infinite_loop_nest_ret:
; SI: ; %bb.0: ; %entry
; SI-NEXT: v_cmp_ne_u32_e32 vcc, 1, v0
; SI-NEXT: s_and_saveexec_b64 s[0:1], vcc
; SI-NEXT: s_cbranch_execz .LBB3_5
; SI-NEXT: ; %bb.1: ; %outer_loop.preheader
; SI-NEXT: s_load_dwordx2 s[4:5], s[2:3], 0x9
; SI-NEXT: v_cmp_ne_u32_e64 s[0:1], 3, v0
; SI-NEXT: s_mov_b32 s7, 0xf000
; SI-NEXT: s_mov_b32 s6, -1
; SI-NEXT: v_mov_b32_e32 v0, 0x3e7
; SI-NEXT: .LBB3_2: ; %outer_loop
; SI-NEXT: ; =>This Loop Header: Depth=1
; SI-NEXT: ; Child Loop BB3_3 Depth 2
; SI-NEXT: s_mov_b64 s[2:3], 0
; SI-NEXT: .LBB3_3: ; %inner_loop
; SI-NEXT: ; Parent Loop BB3_2 Depth=1
; SI-NEXT: ; => This Inner Loop Header: Depth=2
; SI-NEXT: s_and_b64 s[8:9], exec, s[0:1]
; SI-NEXT: s_or_b64 s[2:3], s[8:9], s[2:3]
; SI-NEXT: s_waitcnt lgkmcnt(0)
; SI-NEXT: buffer_store_dword v0, off, s[4:7], 0
; SI-NEXT: s_waitcnt vmcnt(0)
; SI-NEXT: s_andn2_b64 exec, exec, s[2:3]
; SI-NEXT: s_cbranch_execnz .LBB3_3
; SI-NEXT: ; %bb.4: ; %loop.exit.guard
; SI-NEXT: ; in Loop: Header=BB3_2 Depth=1
; SI-NEXT: s_or_b64 exec, exec, s[2:3]
; SI-NEXT: s_mov_b64 vcc, 0
; SI-NEXT: s_branch .LBB3_2
; SI-NEXT: .LBB3_5: ; %UnifiedReturnBlock
; SI-NEXT: s_endpgm
; IR-LABEL: @infinite_loop_nest_ret(
; IR-NEXT: entry:
; IR-NEXT: [[TMP:%.*]] = tail call i32 @llvm.amdgcn.workitem.id.x()
; IR-NEXT: [[COND1:%.*]] = icmp ne i32 [[TMP]], 1
; IR-NEXT: br i1 [[COND1]], label [[OUTER_LOOP:%.*]], label [[UNIFIEDRETURNBLOCK:%.*]]
; IR: outer_loop:
; IR-NEXT: br label [[INNER_LOOP:%.*]]
; IR: inner_loop:
; IR-NEXT: store volatile i32 999, ptr addrspace(1) [[OUT:%.*]], align 4
; IR-NEXT: [[COND3:%.*]] = icmp eq i32 [[TMP]], 3
; IR-NEXT: br i1 true, label [[TRANSITIONBLOCK:%.*]], label [[UNIFIEDRETURNBLOCK]]
; IR: TransitionBlock:
; IR-NEXT: br i1 [[COND3]], label [[INNER_LOOP]], label [[OUTER_LOOP]]
; IR: UnifiedReturnBlock:
; IR-NEXT: ret void
entry:
%tmp = tail call i32 @llvm.amdgcn.workitem.id.x()
%cond1 = icmp ne i32 %tmp, 1 ; avoid following BB optimizing away through the domination
br i1 %cond1, label %outer_loop, label %return
outer_loop:
; %cond2 = icmp eq i32 %tmp, 2
; br i1 %cond2, label %outer_loop, label %inner_loop
br label %inner_loop
inner_loop: ; preds = %LeafBlock, %LeafBlock1
store volatile i32 999, ptr addrspace(1) %out, align 4
%cond3 = icmp eq i32 %tmp, 3
br i1 %cond3, label %inner_loop, label %outer_loop
return:
ret void
}
declare i32 @llvm.amdgcn.workitem.id.x()
|
