llvm.org GIT mirror llvm / release_60 test / CodeGen / X86 / tail-opts.ll
release_60

Tree @release_60 (Download .tar.gz)

tail-opts.ll @release_60raw · history · blame

  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
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
; RUN: llc < %s -mtriple=x86_64-unknown-linux-gnu -asm-verbose=false -post-RA-scheduler=true | FileCheck %s

declare void @bar(i32)
declare void @car(i32)
declare void @dar(i32)
declare void @ear(i32)
declare void @far(i32)
declare i1 @qux()

@GHJK = global i32 0
@HABC = global i32 0

; BranchFolding should tail-merge the stores since they all precede
; direct branches to the same place.

; CHECK-LABEL: tail_merge_me:
; CHECK-NOT:  GHJK
; CHECK:      movl $0, GHJK(%rip)
; CHECK-NEXT: movl $1, HABC(%rip)
; CHECK-NOT:  GHJK

define void @tail_merge_me() nounwind {
entry:
  %a = call i1 @qux()
  br i1 %a, label %A, label %next
next:
  %b = call i1 @qux()
  br i1 %b, label %B, label %C

A:
  call void @bar(i32 0)
  store i32 0, i32* @GHJK
  br label %M

B:
  call void @car(i32 1)
  store i32 0, i32* @GHJK
  br label %M

C:
  call void @dar(i32 2)
  store i32 0, i32* @GHJK
  br label %M

M:
  store i32 1, i32* @HABC
  %c = call i1 @qux()
  br i1 %c, label %return, label %altret

return:
  call void @ear(i32 1000)
  ret void
altret:
  call void @far(i32 1001)
  ret void
}

declare i8* @choose(i8*, i8*)

; BranchFolding should tail-duplicate the indirect jump to avoid
; redundant branching.

; CHECK-LABEL: tail_duplicate_me:
; CHECK:      movl $0, GHJK(%rip)
; CHECK-NEXT: jmpq *%r
; CHECK:      movl $0, GHJK(%rip)
; CHECK-NEXT: jmpq *%r
; CHECK:      movl $0, GHJK(%rip)
; CHECK-NEXT: jmpq *%r

define void @tail_duplicate_me() nounwind {
entry:
  %a = call i1 @qux()
  %c = call i8* @choose(i8* blockaddress(@tail_duplicate_me, %return),
                        i8* blockaddress(@tail_duplicate_me, %altret))
  br i1 %a, label %A, label %next
next:
  %b = call i1 @qux()
  br i1 %b, label %B, label %C

A:
  call void @bar(i32 0)
  store i32 0, i32* @GHJK
  br label %M

B:
  call void @car(i32 1)
  store i32 0, i32* @GHJK
  br label %M

C:
  call void @dar(i32 2)
  store i32 0, i32* @GHJK
  br label %M

M:
  indirectbr i8* %c, [label %return, label %altret]

return:
  call void @ear(i32 1000)
  ret void
altret:
  call void @far(i32 1001)
  ret void
}

; BranchFolding shouldn't try to merge the tails of two blocks
; with only a branch in common, regardless of the fallthrough situation.

; CHECK-LABEL: dont_merge_oddly:
; CHECK-NOT:   ret
; CHECK:        ucomiss %xmm{{[0-2]}}, %xmm{{[0-2]}}
; CHECK-NEXT:   jbe .LBB2_3
; CHECK-NEXT:   ucomiss %xmm{{[0-2]}}, %xmm{{[0-2]}}
; CHECK-NEXT:   ja .LBB2_4
; CHECK-NEXT: .LBB2_2:
; CHECK-NEXT:   movb $1, %al
; CHECK-NEXT:   ret
; CHECK-NEXT: .LBB2_3:
; CHECK-NEXT:   ucomiss %xmm{{[0-2]}}, %xmm{{[0-2]}}
; CHECK-NEXT:   jbe .LBB2_2
; CHECK-NEXT: .LBB2_4:
; CHECK-NEXT:   xorl %eax, %eax
; CHECK-NEXT:   ret

define i1 @dont_merge_oddly(float* %result) nounwind {
entry:
  %tmp4 = getelementptr float, float* %result, i32 2
  %tmp5 = load float, float* %tmp4, align 4
  %tmp7 = getelementptr float, float* %result, i32 4
  %tmp8 = load float, float* %tmp7, align 4
  %tmp10 = getelementptr float, float* %result, i32 6
  %tmp11 = load float, float* %tmp10, align 4
  %tmp12 = fcmp olt float %tmp8, %tmp11
  br i1 %tmp12, label %bb, label %bb21

bb:
  %tmp23469 = fcmp olt float %tmp5, %tmp8
  br i1 %tmp23469, label %bb26, label %bb30

bb21:
  %tmp23 = fcmp olt float %tmp5, %tmp11
  br i1 %tmp23, label %bb26, label %bb30

bb26:
  ret i1 0

bb30:
  ret i1 1
}

; Do any-size tail-merging when two candidate blocks will both require
; an unconditional jump to complete a two-way conditional branch.

; CHECK-LABEL: c_expand_expr_stmt:
;
; This test only works when register allocation happens to use %rax for both
; load addresses.
;
; CHE:        jmp .LBB3_11
; CHE-NEXT: .LBB3_9:
; CHE-NEXT:   movq 8(%rax), %rax
; CHE-NEXT:   xorl %edx, %edx
; CHE-NEXT:   movb 16(%rax), %al
; CHE-NEXT:   cmpb $16, %al
; CHE-NEXT:   je .LBB3_11
; CHE-NEXT:   cmpb $23, %al
; CHE-NEXT:   jne .LBB3_14
; CHE-NEXT: .LBB3_11:

%0 = type { %struct.rtx_def* }
%struct.lang_decl = type opaque
%struct.rtx_def = type { i16, i8, i8, [1 x %union.rtunion] }
%struct.tree_decl = type { [24 x i8], i8*, i32, %union.tree_node*, i32, i8, i8, i8, i8, %union.tree_node*, %union.tree_node*, %union.tree_node*, %union.tree_node*, %union.tree_node*, %union.tree_node*, %union.tree_node*, %union.tree_node*, %union.tree_node*, %struct.rtx_def*, %union..2anon, %0, %union.tree_node*, %struct.lang_decl* }
%union..2anon = type { i32 }
%union.rtunion = type { i8* }
%union.tree_node = type { %struct.tree_decl }

define fastcc void @c_expand_expr_stmt(%union.tree_node* %expr) nounwind {
entry:
  %tmp4 = load i8, i8* null, align 8                  ; <i8> [#uses=3]
  switch i8 %tmp4, label %bb3 [
    i8 18, label %bb
  ]

bb:                                               ; preds = %entry
  switch i32 undef, label %bb1 [
    i32 0, label %bb2.i
    i32 37, label %bb.i
  ]

bb.i:                                             ; preds = %bb
  switch i32 undef, label %bb1 [
    i32 0, label %lvalue_p.exit
  ]

bb2.i:                                            ; preds = %bb
  br label %bb3

lvalue_p.exit:                                    ; preds = %bb.i
  %tmp21 = load %union.tree_node*, %union.tree_node** null, align 8  ; <%union.tree_node*> [#uses=3]
  %tmp22 = getelementptr inbounds %union.tree_node, %union.tree_node* %tmp21, i64 0, i32 0, i32 0, i64 0 ; <i8*> [#uses=1]
  %tmp23 = load i8, i8* %tmp22, align 8               ; <i8> [#uses=1]
  %tmp24 = zext i8 %tmp23 to i32                  ; <i32> [#uses=1]
  switch i32 %tmp24, label %lvalue_p.exit4 [
    i32 0, label %bb2.i3
    i32 2, label %bb.i1
  ]

bb.i1:                                            ; preds = %lvalue_p.exit
  %tmp25 = getelementptr inbounds %union.tree_node, %union.tree_node* %tmp21, i64 0, i32 0, i32 2 ; <i32*> [#uses=1]
  %tmp26 = bitcast i32* %tmp25 to %union.tree_node** ; <%union.tree_node**> [#uses=1]
  %tmp27 = load %union.tree_node*, %union.tree_node** %tmp26, align 8 ; <%union.tree_node*> [#uses=2]
  %tmp28 = getelementptr inbounds %union.tree_node, %union.tree_node* %tmp27, i64 0, i32 0, i32 0, i64 16 ; <i8*> [#uses=1]
  %tmp29 = load i8, i8* %tmp28, align 8               ; <i8> [#uses=1]
  %tmp30 = zext i8 %tmp29 to i32                  ; <i32> [#uses=1]
  switch i32 %tmp30, label %lvalue_p.exit4 [
    i32 0, label %bb2.i.i2
    i32 2, label %bb.i.i
  ]

bb.i.i:                                           ; preds = %bb.i1
  %tmp34 = tail call fastcc i32 @lvalue_p(%union.tree_node* null) nounwind ; <i32> [#uses=1]
  %phitmp = icmp ne i32 %tmp34, 0                 ; <i1> [#uses=1]
  br label %lvalue_p.exit4

bb2.i.i2:                                         ; preds = %bb.i1
  %tmp35 = getelementptr inbounds %union.tree_node, %union.tree_node* %tmp27, i64 0, i32 0, i32 0, i64 8 ; <i8*> [#uses=1]
  %tmp36 = bitcast i8* %tmp35 to %union.tree_node** ; <%union.tree_node**> [#uses=1]
  %tmp37 = load %union.tree_node*, %union.tree_node** %tmp36, align 8 ; <%union.tree_node*> [#uses=1]
  %tmp38 = getelementptr inbounds %union.tree_node, %union.tree_node* %tmp37, i64 0, i32 0, i32 0, i64 16 ; <i8*> [#uses=1]
  %tmp39 = load i8, i8* %tmp38, align 8               ; <i8> [#uses=1]
  switch i8 %tmp39, label %bb2 [
    i8 16, label %lvalue_p.exit4
    i8 23, label %lvalue_p.exit4
  ]

bb2.i3:                                           ; preds = %lvalue_p.exit
  %tmp40 = getelementptr inbounds %union.tree_node, %union.tree_node* %tmp21, i64 0, i32 0, i32 0, i64 8 ; <i8*> [#uses=1]
  %tmp41 = bitcast i8* %tmp40 to %union.tree_node** ; <%union.tree_node**> [#uses=1]
  %tmp42 = load %union.tree_node*, %union.tree_node** %tmp41, align 8 ; <%union.tree_node*> [#uses=1]
  %tmp43 = getelementptr inbounds %union.tree_node, %union.tree_node* %tmp42, i64 0, i32 0, i32 0, i64 16 ; <i8*> [#uses=1]
  %tmp44 = load i8, i8* %tmp43, align 8               ; <i8> [#uses=1]
  switch i8 %tmp44, label %bb2 [
    i8 16, label %lvalue_p.exit4
    i8 23, label %lvalue_p.exit4
  ]

lvalue_p.exit4:                                   ; preds = %bb2.i3, %bb2.i3, %bb2.i.i2, %bb2.i.i2, %bb.i.i, %bb.i1, %lvalue_p.exit
  %tmp45 = phi i1 [ %phitmp, %bb.i.i ], [ false, %bb2.i.i2 ], [ false, %bb2.i.i2 ], [ false, %bb.i1 ], [ false, %bb2.i3 ], [ false, %bb2.i3 ], [ false, %lvalue_p.exit ] ; <i1> [#uses=1]
  %tmp46 = icmp eq i8 %tmp4, 0                    ; <i1> [#uses=1]
  %or.cond = or i1 %tmp45, %tmp46                 ; <i1> [#uses=1]
  br i1 %or.cond, label %bb2, label %bb3

bb1:                                              ; preds = %bb2.i.i, %bb.i, %bb
  %.old = icmp eq i8 %tmp4, 23                    ; <i1> [#uses=1]
  br i1 %.old, label %bb2, label %bb3

bb2:                                              ; preds = %bb1, %lvalue_p.exit4, %bb2.i3, %bb2.i.i2
  br label %bb3

bb3:                                              ; preds = %bb2, %bb1, %lvalue_p.exit4, %bb2.i, %entry
  %expr_addr.0 = phi %union.tree_node* [ null, %bb2 ], [ %expr, %bb2.i ], [ %expr, %entry ], [ %expr, %bb1 ], [ %expr, %lvalue_p.exit4 ] ; <%union.tree_node*> [#uses=0]
  unreachable
}

declare fastcc i32 @lvalue_p(%union.tree_node* nocapture) nounwind readonly

declare fastcc %union.tree_node* @default_conversion(%union.tree_node*) nounwind


; If one tail merging candidate falls through into the other,
; tail merging is likely profitable regardless of how few
; instructions are involved. This function should have only
; one ret instruction.

; CHECK-LABEL: foo:
; CHECK:        callq func
; CHECK-NEXT:   popq
; CHECK-NEXT: .LBB4_2:
; CHECK-NEXT:   ret

define void @foo(i1* %V) nounwind {
entry:
  %t0 = icmp eq i1* %V, null
  br i1 %t0, label %return, label %bb

bb:
  call void @func()
  ret void

return:
  ret void
}

declare void @func()

; one - One instruction may be tail-duplicated even with optsize.

; CHECK-LABEL: one:
; CHECK: j{{.*}} tail_call_me
; CHECK: j{{.*}} tail_call_me

@XYZ = external global i32

declare void @tail_call_me()

define void @one(i32 %v) nounwind optsize {
entry:
  %0 = icmp eq i32 %v, 0
  br i1 %0, label %bbx, label %bby

bby:
  switch i32 %v, label %bb7 [
    i32 16, label %return
  ]

bb7:
  tail call void @tail_call_me()
  ret void

bbx:
  switch i32 %v, label %bb12 [
    i32 128, label %return
  ]

bb12:
  tail call void @tail_call_me()
  ret void

return:
  ret void
}

; two - Same as one, but with two instructions in the common
; tail instead of one. This is too much to be merged, given
; the optsize attribute.

; CHECK-LABEL: two:
; CHECK-NOT: XYZ
; CHECK: ret
; CHECK: movl $0, XYZ(%rip)
; CHECK: movl $1, XYZ(%rip)
; CHECK-NOT: XYZ

define void @two() nounwind optsize {
entry:
  %0 = icmp eq i32 undef, 0
  br i1 %0, label %bbx, label %bby

bby:
  switch i32 undef, label %bb7 [
    i32 16, label %return
  ]

bb7:
  store volatile i32 0, i32* @XYZ
  store volatile i32 1, i32* @XYZ
  unreachable

bbx:
  switch i32 undef, label %bb12 [
    i32 128, label %return
  ]

bb12:
  store volatile i32 0, i32* @XYZ
  store volatile i32 1, i32* @XYZ
  unreachable

return:
  ret void
}

; two_minsize - Same as two, but with minsize instead of optsize.

; CHECK-LABEL: two_minsize:
; CHECK-NOT: XYZ
; CHECK: ret
; CHECK: andl $0, XYZ(%rip)
; CHECK: movl $1, XYZ(%rip)
; CHECK-NOT: XYZ

define void @two_minsize() nounwind minsize {
entry:
  %0 = icmp eq i32 undef, 0
  br i1 %0, label %bbx, label %bby

bby:
  switch i32 undef, label %bb7 [
    i32 16, label %return
  ]

bb7:
  store volatile i32 0, i32* @XYZ
  store volatile i32 1, i32* @XYZ
  unreachable

bbx:
  switch i32 undef, label %bb12 [
    i32 128, label %return
  ]

bb12:
  store volatile i32 0, i32* @XYZ
  store volatile i32 1, i32* @XYZ
  unreachable

return:
  ret void
}

; two_nosize - Same as two, but without the optsize attribute.
; Now two instructions are enough to be tail-duplicated.

; CHECK-LABEL: two_nosize:
; CHECK: movl $0, XYZ(%rip)
; CHECK: jmp tail_call_me
; CHECK: movl $0, XYZ(%rip)
; CHECK: jmp tail_call_me

define void @two_nosize() nounwind {
entry:
  %0 = icmp eq i32 undef, 0
  br i1 %0, label %bbx, label %bby

bby:
  switch i32 undef, label %bb7 [
    i32 16, label %return
  ]

bb7:
  store volatile i32 0, i32* @XYZ
  tail call void @tail_call_me()
  ret void

bbx:
  switch i32 undef, label %bb12 [
    i32 128, label %return
  ]

bb12:
  store volatile i32 0, i32* @XYZ
  tail call void @tail_call_me()
  ret void

return:
  ret void
}

; Tail-merging should merge the two ret instructions since one side
; can fall-through into the ret and the other side has to branch anyway.

; CHECK-LABEL: TESTE:
; CHECK: ret
; CHECK-NOT: ret
; CHECK: size TESTE

define i64 @TESTE(i64 %parami, i64 %paraml) nounwind readnone {
entry:
  %cmp = icmp slt i64 %parami, 1                  ; <i1> [#uses=1]
  %varx.0 = select i1 %cmp, i64 1, i64 %parami    ; <i64> [#uses=1]
  %cmp410 = icmp slt i64 %paraml, 1               ; <i1> [#uses=1]
  br i1 %cmp410, label %for.end, label %bb.nph

bb.nph:                                           ; preds = %entry
  %tmp15 = mul i64 %paraml, %parami                   ; <i64> [#uses=1]
  ret i64 %tmp15

for.end:                                          ; preds = %entry
  ret i64 %varx.0
}

; We should tail merge small blocks that don't end in a tail call or return
; instruction. Those blocks are typically unreachable and will be placed
; out-of-line after the main return, so we should try to eliminate as many of
; them as possible.

; CHECK-LABEL: merge_aborts:
; CHECK-NOT: callq abort
; CHECK: ret
; CHECK: callq abort
; CHECK-NOT: callq abort
; CHECK: .Lfunc_end{{.*}}:

declare void @abort()
define void @merge_aborts() {
entry:
  %c1 = call i1 @qux()
  br i1 %c1, label %cont1, label %abort1
abort1:
  call void @abort()
  unreachable
cont1:
  %c2 = call i1 @qux()
  br i1 %c2, label %cont2, label %abort2
abort2:
  call void @abort()
  unreachable
cont2:
  %c3 = call i1 @qux()
  br i1 %c3, label %cont3, label %abort3
abort3:
  call void @abort()
  unreachable
cont3:
  %c4 = call i1 @qux()
  br i1 %c4, label %cont4, label %abort4
abort4:
  call void @abort()
  unreachable
cont4:
  ret void
}

; Use alternating abort functions so that the blocks we wish to merge are not
; layout successors during branch folding.

; CHECK-LABEL: merge_alternating_aborts:
; CHECK-NOT: callq abort
; CHECK: ret
; CHECK: callq abort
; CHECK: callq alt_abort
; CHECK-NOT: callq abort
; CHECK-NOT: callq alt_abort
; CHECK: .Lfunc_end{{.*}}:

declare void @alt_abort()

define void @merge_alternating_aborts() {
entry:
  %c1 = call i1 @qux()
  br i1 %c1, label %cont1, label %abort1
abort1:
  call void @abort()
  unreachable
cont1:
  %c2 = call i1 @qux()
  br i1 %c2, label %cont2, label %abort2
abort2:
  call void @alt_abort()
  unreachable
cont2:
  %c3 = call i1 @qux()
  br i1 %c3, label %cont3, label %abort3
abort3:
  call void @abort()
  unreachable
cont3:
  %c4 = call i1 @qux()
  br i1 %c4, label %cont4, label %abort4
abort4:
  call void @alt_abort()
  unreachable
cont4:
  ret void
}