collapse-endcf.ll
10.3 KB
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
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
; RUN: llc -march=amdgcn -mcpu=tahiti -verify-machineinstrs -amdgpu-remove-redundant-endcf < %s | FileCheck -enable-var-scope -check-prefix=GCN %s
; GCN-LABEL: {{^}}simple_nested_if:
; GCN: s_and_saveexec_b64 [[SAVEEXEC:s\[[0-9:]+\]]]
; GCN-NEXT: s_cbranch_execz [[ENDIF:BB[0-9_]+]]
; GCN: s_and_b64 exec, exec, vcc
; GCN-NEXT: s_cbranch_execz [[ENDIF]]
; GCN-NEXT: ; %bb.{{[0-9]+}}:
; GCN: store_dword
; GCN-NEXT: {{^}}[[ENDIF]]:
; GCN-NEXT: s_or_b64 exec, exec, [[SAVEEXEC]]
; GCN: ds_write_b32
; GCN: s_endpgm
define amdgpu_kernel void @simple_nested_if(i32 addrspace(1)* nocapture %arg) {
bb:
%tmp = tail call i32 @llvm.amdgcn.workitem.id.x()
%tmp1 = icmp ugt i32 %tmp, 1
br i1 %tmp1, label %bb.outer.then, label %bb.outer.end
bb.outer.then: ; preds = %bb
%tmp4 = getelementptr inbounds i32, i32 addrspace(1)* %arg, i32 %tmp
store i32 0, i32 addrspace(1)* %tmp4, align 4
%tmp5 = icmp eq i32 %tmp, 2
br i1 %tmp5, label %bb.outer.end, label %bb.inner.then
bb.inner.then: ; preds = %bb.outer.then
%tmp7 = add i32 %tmp, 1
%tmp9 = getelementptr inbounds i32, i32 addrspace(1)* %arg, i32 %tmp7
store i32 1, i32 addrspace(1)* %tmp9, align 4
br label %bb.outer.end
bb.outer.end: ; preds = %bb.outer.then, %bb.inner.then, %bb
store i32 3, i32 addrspace(3)* null
ret void
}
; GCN-LABEL: {{^}}uncollapsable_nested_if:
; GCN: s_and_saveexec_b64 [[SAVEEXEC_OUTER:s\[[0-9:]+\]]]
; GCN-NEXT: s_cbranch_execz [[ENDIF_OUTER:BB[0-9_]+]]
; GCN: s_and_saveexec_b64 [[SAVEEXEC_INNER:s\[[0-9:]+\]]]
; GCN-NEXT: s_cbranch_execz [[ENDIF_INNER:BB[0-9_]+]]
; GCN-NEXT: ; %bb.{{[0-9]+}}:
; GCN: store_dword
; GCN-NEXT: {{^}}[[ENDIF_INNER]]:
; GCN-NEXT: s_or_b64 exec, exec, [[SAVEEXEC_INNER]]
; GCN: store_dword
; GCN-NEXT: {{^}}[[ENDIF_OUTER]]:
; GCN-NEXT: s_or_b64 exec, exec, [[SAVEEXEC_OUTER]]
; GCN: ds_write_b32
; GCN: s_endpgm
define amdgpu_kernel void @uncollapsable_nested_if(i32 addrspace(1)* nocapture %arg) {
bb:
%tmp = tail call i32 @llvm.amdgcn.workitem.id.x()
%tmp1 = icmp ugt i32 %tmp, 1
br i1 %tmp1, label %bb.outer.then, label %bb.outer.end
bb.outer.then: ; preds = %bb
%tmp4 = getelementptr inbounds i32, i32 addrspace(1)* %arg, i32 %tmp
store i32 0, i32 addrspace(1)* %tmp4, align 4
%tmp5 = icmp eq i32 %tmp, 2
br i1 %tmp5, label %bb.inner.end, label %bb.inner.then
bb.inner.then: ; preds = %bb.outer.then
%tmp7 = add i32 %tmp, 1
%tmp8 = getelementptr inbounds i32, i32 addrspace(1)* %arg, i32 %tmp7
store i32 1, i32 addrspace(1)* %tmp8, align 4
br label %bb.inner.end
bb.inner.end: ; preds = %bb.inner.then, %bb.outer.then
%tmp9 = add i32 %tmp, 2
%tmp10 = getelementptr inbounds i32, i32 addrspace(1)* %arg, i32 %tmp9
store i32 2, i32 addrspace(1)* %tmp10, align 4
br label %bb.outer.end
bb.outer.end: ; preds = %bb.inner.then, %bb
store i32 3, i32 addrspace(3)* null
ret void
}
; GCN-LABEL: {{^}}nested_if_if_else:
; GCN: s_and_saveexec_b64 [[SAVEEXEC_OUTER:s\[[0-9:]+\]]]
; GCN-NEXT: s_cbranch_execz [[ENDIF_OUTER:BB[0-9_]+]]
; GCN: s_and_saveexec_b64 [[SAVEEXEC_INNER:s\[[0-9:]+\]]]
; GCN-NEXT: s_xor_b64 [[SAVEEXEC_INNER2:s\[[0-9:]+\]]], exec, [[SAVEEXEC_INNER]]
; GCN-NEXT: s_cbranch_execz [[THEN_INNER:BB[0-9_]+]]
; GCN-NEXT: ; %bb.{{[0-9]+}}:
; GCN: store_dword
; GCN-NEXT: {{^}}[[THEN_INNER]]:
; GCN-NEXT: s_or_saveexec_b64 [[SAVEEXEC_INNER3:s\[[0-9:]+\]]], [[SAVEEXEC_INNER2]]
; GCN-NEXT: s_xor_b64 exec, exec, [[SAVEEXEC_INNER3]]
; GCN-NEXT: s_cbranch_execz [[ENDIF_OUTER]]
; GCN: store_dword
; GCN-NEXT: {{^}}[[ENDIF_OUTER]]:
; GCN-NEXT: s_or_b64 exec, exec, [[SAVEEXEC_OUTER]]
; GCN: ds_write_b32
; GCN: s_endpgm
define amdgpu_kernel void @nested_if_if_else(i32 addrspace(1)* nocapture %arg) {
bb:
%tmp = tail call i32 @llvm.amdgcn.workitem.id.x()
%tmp1 = getelementptr inbounds i32, i32 addrspace(1)* %arg, i32 %tmp
store i32 0, i32 addrspace(1)* %tmp1, align 4
%tmp2 = icmp ugt i32 %tmp, 1
br i1 %tmp2, label %bb.outer.then, label %bb.outer.end
bb.outer.then: ; preds = %bb
%tmp5 = icmp eq i32 %tmp, 2
br i1 %tmp5, label %bb.then, label %bb.else
bb.then: ; preds = %bb.outer.then
%tmp3 = add i32 %tmp, 1
%tmp4 = getelementptr inbounds i32, i32 addrspace(1)* %arg, i32 %tmp3
store i32 1, i32 addrspace(1)* %tmp4, align 4
br label %bb.outer.end
bb.else: ; preds = %bb.outer.then
%tmp7 = add i32 %tmp, 2
%tmp9 = getelementptr inbounds i32, i32 addrspace(1)* %arg, i32 %tmp7
store i32 2, i32 addrspace(1)* %tmp9, align 4
br label %bb.outer.end
bb.outer.end: ; preds = %bb, %bb.then, %bb.else
store i32 3, i32 addrspace(3)* null
ret void
}
; GCN-LABEL: {{^}}nested_if_else_if:
; GCN: s_and_saveexec_b64 [[SAVEEXEC_OUTER:s\[[0-9:]+\]]]
; GCN-NEXT: s_xor_b64 [[SAVEEXEC_OUTER2:s\[[0-9:]+\]]], exec, [[SAVEEXEC_OUTER]]
; GCN-NEXT: s_cbranch_execz [[THEN_OUTER:BB[0-9_]+]]
; GCN-NEXT: ; %bb.{{[0-9]+}}:
; GCN: store_dword
; GCN-NEXT: s_and_saveexec_b64 [[SAVEEXEC_INNER_IF_OUTER_ELSE:s\[[0-9:]+\]]]
; GCN-NEXT: s_cbranch_execz [[THEN_OUTER_FLOW:BB[0-9_]+]]
; GCN-NEXT: ; %bb.{{[0-9]+}}:
; GCN: store_dword
; GCN-NEXT: {{^}}[[THEN_OUTER_FLOW]]:
; GCN-NEXT: s_or_b64 exec, exec, [[SAVEEXEC_INNER_IF_OUTER_ELSE]]
; GCN-NEXT: {{^}}[[THEN_OUTER]]:
; GCN-NEXT: s_or_saveexec_b64 [[SAVEEXEC_OUTER3:s\[[0-9:]+\]]], [[SAVEEXEC_OUTER2]]
; GCN-NEXT: s_xor_b64 exec, exec, [[SAVEEXEC_OUTER3]]
; GCN-NEXT: s_cbranch_execz [[ENDIF_OUTER:BB[0-9_]+]]
; GCN-NEXT: ; %bb.{{[0-9]+}}:
; GCN: store_dword
; GCN-NEXT: s_and_saveexec_b64 [[SAVEEXEC_ELSE:s\[[0-9:]+\]]],
; GCN-NEXT: s_cbranch_execz [[FLOW1:BB[0-9_]+]]
; GCN-NEXT: ; %bb.{{[0-9]+}}:
; GCN: store_dword
; GCN-NEXT: [[FLOW1]]:
; GCN-NEXT: s_or_b64 exec, exec, [[SAVEEXEC_ELSE]]
; GCN: s_or_b64 exec, exec, [[SAVEEXEC_OUTER3]]
; GCN: ds_write_b32
; GCN: s_endpgm
define amdgpu_kernel void @nested_if_else_if(i32 addrspace(1)* nocapture %arg) {
bb:
%tmp = tail call i32 @llvm.amdgcn.workitem.id.x()
%tmp1 = getelementptr inbounds i32, i32 addrspace(1)* %arg, i32 %tmp
store i32 0, i32 addrspace(1)* %tmp1, align 4
%cc1 = icmp ugt i32 %tmp, 1
br i1 %cc1, label %bb.outer.then, label %bb.outer.else
bb.outer.then:
%tmp2 = getelementptr inbounds i32, i32 addrspace(1)* %tmp1, i32 1
store i32 1, i32 addrspace(1)* %tmp2, align 4
%cc2 = icmp eq i32 %tmp, 2
br i1 %cc2, label %bb.inner.then, label %bb.outer.end
bb.inner.then:
%tmp3 = getelementptr inbounds i32, i32 addrspace(1)* %tmp1, i32 2
store i32 2, i32 addrspace(1)* %tmp3, align 4
br label %bb.outer.end
bb.outer.else:
%tmp4 = getelementptr inbounds i32, i32 addrspace(1)* %tmp1, i32 3
store i32 3, i32 addrspace(1)* %tmp4, align 4
%cc3 = icmp eq i32 %tmp, 2
br i1 %cc3, label %bb.inner.then2, label %bb.outer.end
bb.inner.then2:
%tmp5 = getelementptr inbounds i32, i32 addrspace(1)* %tmp1, i32 4
store i32 4, i32 addrspace(1)* %tmp5, align 4
br label %bb.outer.end
bb.outer.end:
store i32 3, i32 addrspace(3)* null
ret void
}
; GCN-LABEL: {{^}}s_endpgm_unsafe_barrier:
; GCN: s_and_saveexec_b64 [[SAVEEXEC:s\[[0-9:]+\]]]
; GCN-NEXT: s_cbranch_execz [[ENDIF:BB[0-9_]+]]
; GCN-NEXT: ; %bb.{{[0-9]+}}:
; GCN: store_dword
; GCN-NEXT: {{^}}[[ENDIF]]:
; GCN-NEXT: s_or_b64 exec, exec, [[SAVEEXEC]]
; GCN: s_barrier
; GCN-NEXT: s_endpgm
define amdgpu_kernel void @s_endpgm_unsafe_barrier(i32 addrspace(1)* nocapture %arg) {
bb:
%tmp = tail call i32 @llvm.amdgcn.workitem.id.x()
%tmp1 = icmp ugt i32 %tmp, 1
br i1 %tmp1, label %bb.then, label %bb.end
bb.then: ; preds = %bb
%tmp4 = getelementptr inbounds i32, i32 addrspace(1)* %arg, i32 %tmp
store i32 0, i32 addrspace(1)* %tmp4, align 4
br label %bb.end
bb.end: ; preds = %bb.then, %bb
call void @llvm.amdgcn.s.barrier()
ret void
}
; GCN-LABEL: {{^}}scc_liveness:
; GCN: [[BB1_OUTER_LOOP:BB[0-9]+_[0-9]+]]:
; GCN: s_or_b64 exec, exec, [[SAVEEXEC_OUTER:s\[[0-9:]+\]]]
;
; GCN: [[BB1_INNER_LOOP:BB[0-9]+_[0-9]+]]:
; GCN: s_or_b64 exec, exec, s{{\[[0-9]+:[0-9]+\]}}
; GCN: s_andn2_b64
; GCN-NEXT: s_cbranch_execz
; GCN: [[BB1_LOOP:BB[0-9]+_[0-9]+]]:
; GCN: s_andn2_b64 exec, exec,
; GCN-NEXT: s_cbranch_execnz [[BB1_LOOP]]
; GCN: buffer_load_dword v{{[0-9]+}}, v{{[0-9]+}}, s{{\[[0-9]+:[0-9]+\]}}, 0 offen
; GCN: s_and_saveexec_b64 [[SAVEEXEC_OUTER]], {{vcc|s\[[0-9:]+\]}}
; GCN-NEXT: s_cbranch_execz [[BB1_OUTER_LOOP]]
; GCN-NOT: s_or_b64 exec, exec
; GCN: s_or_b64 exec, exec, s{{\[[0-9]+:[0-9]+\]}}
; GCN: buffer_store_dword
; GCN: buffer_store_dword
; GCN: buffer_store_dword
; GCN: buffer_store_dword
; GCN: s_setpc_b64
define void @scc_liveness(i32 %arg) local_unnamed_addr #0 {
bb:
br label %bb1
bb1: ; preds = %Flow1, %bb1, %bb
%tmp = icmp slt i32 %arg, 519
br i1 %tmp, label %bb2, label %bb1
bb2: ; preds = %bb1
%tmp3 = icmp eq i32 %arg, 0
br i1 %tmp3, label %bb4, label %bb10
bb4: ; preds = %bb2
%tmp6 = load float, float addrspace(5)* undef
%tmp7 = fcmp olt float %tmp6, 0.0
br i1 %tmp7, label %bb8, label %Flow
bb8: ; preds = %bb4
%tmp9 = insertelement <4 x float> undef, float 0.0, i32 1
br label %Flow
Flow: ; preds = %bb8, %bb4
%tmp8 = phi <4 x float> [ %tmp9, %bb8 ], [ zeroinitializer, %bb4 ]
br label %bb10
bb10: ; preds = %Flow, %bb2
%tmp11 = phi <4 x float> [ zeroinitializer, %bb2 ], [ %tmp8, %Flow ]
br i1 %tmp3, label %bb12, label %Flow1
Flow1: ; preds = %bb10
br label %bb1
bb12: ; preds = %bb10
store volatile <4 x float> %tmp11, <4 x float> addrspace(5)* undef, align 16
ret void
}
declare i32 @llvm.amdgcn.workitem.id.x() #0
declare void @llvm.amdgcn.s.barrier() #1
attributes #0 = { nounwind readnone speculatable }
attributes #1 = { nounwind convergent }
attributes #2 = { nounwind }