merge-cond-stores.ll
11.7 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
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: opt -simplifycfg -instcombine < %s -simplifycfg-merge-cond-stores=true -simplifycfg-merge-cond-stores-aggressively=false -phi-node-folding-threshold=2 -S | FileCheck %s
; This test should succeed and end up if-converted.
define void @test_simple(i32* %p, i32 %a, i32 %b) {
; CHECK-LABEL: @test_simple(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[X1:%.*]] = icmp ne i32 [[A:%.*]], 0
; CHECK-NEXT: [[X2:%.*]] = icmp eq i32 [[B:%.*]], 0
; CHECK-NEXT: [[TMP0:%.*]] = xor i1 [[X2]], true
; CHECK-NEXT: [[TMP1:%.*]] = or i1 [[X1]], [[TMP0]]
; CHECK-NEXT: br i1 [[TMP1]], label [[TMP2:%.*]], label [[TMP3:%.*]]
; CHECK: 2:
; CHECK-NEXT: [[NOT_X2:%.*]] = xor i1 [[X2]], true
; CHECK-NEXT: [[SPEC_SELECT:%.*]] = zext i1 [[NOT_X2]] to i32
; CHECK-NEXT: store i32 [[SPEC_SELECT]], i32* [[P:%.*]], align 4
; CHECK-NEXT: br label [[TMP3]]
; CHECK: 3:
; CHECK-NEXT: ret void
;
entry:
%x1 = icmp eq i32 %a, 0
br i1 %x1, label %fallthrough, label %yes1
yes1:
store i32 0, i32* %p
br label %fallthrough
fallthrough:
%x2 = icmp eq i32 %b, 0
br i1 %x2, label %end, label %yes2
yes2:
store i32 1, i32* %p
br label %end
end:
ret void
}
; This is the same as test_simple, but the branch target order has been swapped
define void @test_simple_commuted(i32* %p, i32 %a, i32 %b) {
; CHECK-LABEL: @test_simple_commuted(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[X1:%.*]] = icmp eq i32 [[A:%.*]], 0
; CHECK-NEXT: [[X2:%.*]] = icmp eq i32 [[B:%.*]], 0
; CHECK-NEXT: [[TMP0:%.*]] = or i1 [[X1]], [[X2]]
; CHECK-NEXT: br i1 [[TMP0]], label [[TMP1:%.*]], label [[TMP2:%.*]]
; CHECK: 1:
; CHECK-NEXT: [[SPEC_SELECT:%.*]] = zext i1 [[X2]] to i32
; CHECK-NEXT: store i32 [[SPEC_SELECT]], i32* [[P:%.*]], align 4
; CHECK-NEXT: br label [[TMP2]]
; CHECK: 2:
; CHECK-NEXT: ret void
;
entry:
%x1 = icmp eq i32 %a, 0
br i1 %x1, label %yes1, label %fallthrough
yes1:
store i32 0, i32* %p
br label %fallthrough
fallthrough:
%x2 = icmp eq i32 %b, 0
br i1 %x2, label %yes2, label %end
yes2:
store i32 1, i32* %p
br label %end
end:
ret void
}
; This test should entirely fold away, leaving one large basic block.
define void @test_recursive(i32* %p, i32 %a, i32 %b, i32 %c, i32 %d) {
; CHECK-LABEL: @test_recursive(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[TMP0:%.*]] = or i32 [[B:%.*]], [[A:%.*]]
; CHECK-NEXT: [[X4:%.*]] = icmp eq i32 [[D:%.*]], 0
; CHECK-NEXT: [[TMP1:%.*]] = or i32 [[TMP0]], [[C:%.*]]
; CHECK-NEXT: [[TMP2:%.*]] = icmp ne i32 [[TMP1]], 0
; CHECK-NEXT: [[TMP3:%.*]] = xor i1 [[X4]], true
; CHECK-NEXT: [[TMP4:%.*]] = or i1 [[TMP2]], [[TMP3]]
; CHECK-NEXT: br i1 [[TMP4]], label [[TMP5:%.*]], label [[TMP6:%.*]]
; CHECK: 5:
; CHECK-NEXT: [[X3:%.*]] = icmp eq i32 [[C]], 0
; CHECK-NEXT: [[X2:%.*]] = icmp ne i32 [[B]], 0
; CHECK-NEXT: [[SPEC_SELECT:%.*]] = zext i1 [[X2]] to i32
; CHECK-NEXT: [[SPEC_SELECT1:%.*]] = select i1 [[X3]], i32 [[SPEC_SELECT]], i32 2
; CHECK-NEXT: [[SPEC_SELECT2:%.*]] = select i1 [[X4]], i32 [[SPEC_SELECT1]], i32 3
; CHECK-NEXT: store i32 [[SPEC_SELECT2]], i32* [[P:%.*]], align 4
; CHECK-NEXT: br label [[TMP6]]
; CHECK: 6:
; CHECK-NEXT: ret void
;
entry:
%x1 = icmp eq i32 %a, 0
br i1 %x1, label %fallthrough, label %yes1
yes1:
store i32 0, i32* %p
br label %fallthrough
fallthrough:
%x2 = icmp eq i32 %b, 0
br i1 %x2, label %next, label %yes2
yes2:
store i32 1, i32* %p
br label %next
next:
%x3 = icmp eq i32 %c, 0
br i1 %x3, label %fallthrough2, label %yes3
yes3:
store i32 2, i32* %p
br label %fallthrough2
fallthrough2:
%x4 = icmp eq i32 %d, 0
br i1 %x4, label %end, label %yes4
yes4:
store i32 3, i32* %p
br label %end
end:
ret void
}
; The code in each diamond is too large - it won't be if-converted so our
; heuristics should say no.
define void @test_not_ifconverted(i32* %p, i32 %a, i32 %b) {
; CHECK-LABEL: @test_not_ifconverted(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[X1:%.*]] = icmp eq i32 [[A:%.*]], 0
; CHECK-NEXT: br i1 [[X1]], label [[FALLTHROUGH:%.*]], label [[YES1:%.*]]
; CHECK: yes1:
; CHECK-NEXT: [[Y1:%.*]] = or i32 [[B:%.*]], 55
; CHECK-NEXT: [[Y2:%.*]] = add i32 [[Y1]], 24
; CHECK-NEXT: [[Y3:%.*]] = and i32 [[Y2]], 67
; CHECK-NEXT: store i32 [[Y3]], i32* [[P:%.*]], align 4
; CHECK-NEXT: br label [[FALLTHROUGH]]
; CHECK: fallthrough:
; CHECK-NEXT: [[X2:%.*]] = icmp eq i32 [[B]], 0
; CHECK-NEXT: br i1 [[X2]], label [[END:%.*]], label [[YES2:%.*]]
; CHECK: yes2:
; CHECK-NEXT: [[Z1:%.*]] = or i32 [[A]], 55
; CHECK-NEXT: [[Z2:%.*]] = add i32 [[Z1]], 24
; CHECK-NEXT: [[Z3:%.*]] = and i32 [[Z2]], 67
; CHECK-NEXT: store i32 [[Z3]], i32* [[P]], align 4
; CHECK-NEXT: br label [[END]]
; CHECK: end:
; CHECK-NEXT: ret void
;
entry:
%x1 = icmp eq i32 %a, 0
br i1 %x1, label %fallthrough, label %yes1
yes1:
%y1 = or i32 %b, 55
%y2 = add i32 %y1, 24
%y3 = and i32 %y2, 67
store i32 %y3, i32* %p
br label %fallthrough
fallthrough:
%x2 = icmp eq i32 %b, 0
br i1 %x2, label %end, label %yes2
yes2:
%z1 = or i32 %a, 55
%z2 = add i32 %z1, 24
%z3 = and i32 %z2, 67
store i32 %z3, i32* %p
br label %end
end:
ret void
}
; The store to %p clobbers the previous store, so if-converting this would
; be illegal.
define void @test_aliasing1(i32* %p, i32 %a, i32 %b) {
; CHECK-LABEL: @test_aliasing1(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[X1:%.*]] = icmp eq i32 [[A:%.*]], 0
; CHECK-NEXT: br i1 [[X1]], label [[FALLTHROUGH:%.*]], label [[YES1:%.*]]
; CHECK: yes1:
; CHECK-NEXT: store i32 0, i32* [[P:%.*]], align 4
; CHECK-NEXT: br label [[FALLTHROUGH]]
; CHECK: fallthrough:
; CHECK-NEXT: [[Y1:%.*]] = load i32, i32* [[P]], align 4
; CHECK-NEXT: [[X2:%.*]] = icmp eq i32 [[Y1]], 0
; CHECK-NEXT: br i1 [[X2]], label [[END:%.*]], label [[YES2:%.*]]
; CHECK: yes2:
; CHECK-NEXT: store i32 1, i32* [[P]], align 4
; CHECK-NEXT: br label [[END]]
; CHECK: end:
; CHECK-NEXT: ret void
;
entry:
%x1 = icmp eq i32 %a, 0
br i1 %x1, label %fallthrough, label %yes1
yes1:
store i32 0, i32* %p
br label %fallthrough
fallthrough:
%y1 = load i32, i32* %p
%x2 = icmp eq i32 %y1, 0
br i1 %x2, label %end, label %yes2
yes2:
store i32 1, i32* %p
br label %end
end:
ret void
}
; The load from %q aliases with %p, so if-converting this would be illegal.
define void @test_aliasing2(i32* %p, i32* %q, i32 %a, i32 %b) {
; CHECK-LABEL: @test_aliasing2(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[X1:%.*]] = icmp eq i32 [[A:%.*]], 0
; CHECK-NEXT: br i1 [[X1]], label [[FALLTHROUGH:%.*]], label [[YES1:%.*]]
; CHECK: yes1:
; CHECK-NEXT: store i32 0, i32* [[P:%.*]], align 4
; CHECK-NEXT: br label [[FALLTHROUGH]]
; CHECK: fallthrough:
; CHECK-NEXT: [[Y1:%.*]] = load i32, i32* [[Q:%.*]], align 4
; CHECK-NEXT: [[X2:%.*]] = icmp eq i32 [[Y1]], 0
; CHECK-NEXT: br i1 [[X2]], label [[END:%.*]], label [[YES2:%.*]]
; CHECK: yes2:
; CHECK-NEXT: store i32 1, i32* [[P]], align 4
; CHECK-NEXT: br label [[END]]
; CHECK: end:
; CHECK-NEXT: ret void
;
entry:
%x1 = icmp eq i32 %a, 0
br i1 %x1, label %fallthrough, label %yes1
yes1:
store i32 0, i32* %p
br label %fallthrough
fallthrough:
%y1 = load i32, i32* %q
%x2 = icmp eq i32 %y1, 0
br i1 %x2, label %end, label %yes2
yes2:
store i32 1, i32* %p
br label %end
end:
ret void
}
declare void @f()
; This should get if-converted.
define i32 @test_diamond_simple(i32* %p, i32* %q, i32 %a, i32 %b) {
; CHECK-LABEL: @test_diamond_simple(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[X1:%.*]] = icmp eq i32 [[A:%.*]], 0
; CHECK-NEXT: [[Z2:%.*]] = select i1 [[X1]], i32 [[B:%.*]], i32 0
; CHECK-NEXT: [[X2:%.*]] = icmp eq i32 [[B]], 0
; CHECK-NEXT: [[Z4:%.*]] = select i1 [[X2]], i32 [[Z2]], i32 3
; CHECK-NEXT: [[TMP0:%.*]] = or i32 [[A]], [[B]]
; CHECK-NEXT: [[TMP1:%.*]] = icmp eq i32 [[TMP0]], 0
; CHECK-NEXT: br i1 [[TMP1]], label [[TMP3:%.*]], label [[TMP2:%.*]]
; CHECK: 2:
; CHECK-NEXT: [[SIMPLIFYCFG_MERGE:%.*]] = select i1 [[X2]], i32 [[Z2]], i32 1
; CHECK-NEXT: store i32 [[SIMPLIFYCFG_MERGE]], i32* [[P:%.*]], align 4
; CHECK-NEXT: br label [[TMP3]]
; CHECK: 3:
; CHECK-NEXT: ret i32 [[Z4]]
;
entry:
%x1 = icmp eq i32 %a, 0
br i1 %x1, label %no1, label %yes1
yes1:
store i32 0, i32* %p
br label %fallthrough
no1:
%z1 = add i32 %a, %b
br label %fallthrough
fallthrough:
%z2 = phi i32 [ %z1, %no1 ], [ 0, %yes1 ]
%x2 = icmp eq i32 %b, 0
br i1 %x2, label %no2, label %yes2
yes2:
store i32 1, i32* %p
br label %end
no2:
%z3 = sub i32 %z2, %b
br label %end
end:
%z4 = phi i32 [ %z3, %no2 ], [ 3, %yes2 ]
ret i32 %z4
}
; Now there is a call to f() in the bottom branch. The store in the first
; branch would now be reordered with respect to the call if we if-converted,
; so we must not.
define i32 @test_diamond_alias3(i32* %p, i32* %q, i32 %a, i32 %b) {
; CHECK-LABEL: @test_diamond_alias3(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[X1:%.*]] = icmp eq i32 [[A:%.*]], 0
; CHECK-NEXT: br i1 [[X1]], label [[NO1:%.*]], label [[YES1:%.*]]
; CHECK: yes1:
; CHECK-NEXT: store i32 0, i32* [[P:%.*]], align 4
; CHECK-NEXT: br label [[FALLTHROUGH:%.*]]
; CHECK: no1:
; CHECK-NEXT: call void @f()
; CHECK-NEXT: [[Z1:%.*]] = add i32 [[A]], [[B:%.*]]
; CHECK-NEXT: br label [[FALLTHROUGH]]
; CHECK: fallthrough:
; CHECK-NEXT: [[Z2:%.*]] = phi i32 [ [[Z1]], [[NO1]] ], [ 0, [[YES1]] ]
; CHECK-NEXT: [[X2:%.*]] = icmp eq i32 [[B]], 0
; CHECK-NEXT: br i1 [[X2]], label [[NO2:%.*]], label [[YES2:%.*]]
; CHECK: yes2:
; CHECK-NEXT: store i32 1, i32* [[P]], align 4
; CHECK-NEXT: br label [[END:%.*]]
; CHECK: no2:
; CHECK-NEXT: call void @f()
; CHECK-NEXT: [[Z3:%.*]] = sub i32 [[Z2]], [[B]]
; CHECK-NEXT: br label [[END]]
; CHECK: end:
; CHECK-NEXT: [[Z4:%.*]] = phi i32 [ [[Z3]], [[NO2]] ], [ 3, [[YES2]] ]
; CHECK-NEXT: ret i32 [[Z4]]
;
entry:
%x1 = icmp eq i32 %a, 0
br i1 %x1, label %no1, label %yes1
yes1:
store i32 0, i32* %p
br label %fallthrough
no1:
call void @f()
%z1 = add i32 %a, %b
br label %fallthrough
fallthrough:
%z2 = phi i32 [ %z1, %no1 ], [ 0, %yes1 ]
%x2 = icmp eq i32 %b, 0
br i1 %x2, label %no2, label %yes2
yes2:
store i32 1, i32* %p
br label %end
no2:
call void @f()
%z3 = sub i32 %z2, %b
br label %end
end:
%z4 = phi i32 [ %z3, %no2 ], [ 3, %yes2 ]
ret i32 %z4
}
; This test has an outer if over the two triangles. This requires creating a new BB to hold the store.
define void @test_outer_if(i32* %p, i32 %a, i32 %b, i32 %c) {
; CHECK-LABEL: @test_outer_if(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[X3:%.*]] = icmp eq i32 [[C:%.*]], 0
; CHECK-NEXT: br i1 [[X3]], label [[END:%.*]], label [[CONTINUE:%.*]]
; CHECK: continue:
; CHECK-NEXT: [[X1:%.*]] = icmp ne i32 [[A:%.*]], 0
; CHECK-NEXT: [[X2:%.*]] = icmp eq i32 [[B:%.*]], 0
; CHECK-NEXT: [[TMP0:%.*]] = xor i1 [[X2]], true
; CHECK-NEXT: [[TMP1:%.*]] = or i1 [[X1]], [[TMP0]]
; CHECK-NEXT: br i1 [[TMP1]], label [[TMP2:%.*]], label [[END]]
; CHECK: 2:
; CHECK-NEXT: [[NOT_X2:%.*]] = xor i1 [[X2]], true
; CHECK-NEXT: [[SPEC_SELECT:%.*]] = zext i1 [[NOT_X2]] to i32
; CHECK-NEXT: store i32 [[SPEC_SELECT]], i32* [[P:%.*]], align 4
; CHECK-NEXT: br label [[END]]
; CHECK: end:
; CHECK-NEXT: ret void
;
entry:
%x3 = icmp eq i32 %c, 0
br i1 %x3, label %end, label %continue
continue:
%x1 = icmp eq i32 %a, 0
br i1 %x1, label %fallthrough, label %yes1
yes1:
store i32 0, i32* %p
br label %fallthrough
fallthrough:
%x2 = icmp eq i32 %b, 0
br i1 %x2, label %end, label %yes2
yes2:
store i32 1, i32* %p
br label %end
end:
ret void
}