llvm.org GIT mirror llvm / release_38 test / CodeGen / AArch64 / aarch64-dynamic-stack-layout.ll
release_38

Tree @release_38 (Download .tar.gz)

aarch64-dynamic-stack-layout.ll @release_38raw · 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
; RUN: llc -verify-machineinstrs -mtriple=aarch64-none-linux-gnu -disable-post-ra < %s | FileCheck %s

; This test aims to check basic correctness of frame layout &
; frame access code. There are 8 functions in this test file,
; each function implements one element in the cartesian product
; of:
; . a function having a VLA/noVLA
; . a function with dynamic stack realignment/no dynamic stack realignment.
; . a function needing a frame pionter/no frame pointer,
; since the presence/absence of these has influence on the frame
; layout and which pointer to use to access various part of the
; frame (bp,sp,fp).
;
; Furthermore: in every test function:
; . there is always one integer and 1 floating point argument to be able
;   to check those are accessed correctly.
; . there is always one local variable to check that is accessed
;   correctly
;
; The LLVM-IR below was produced by clang on the following C++ code:
;extern "C" int g();
;extern "C" int novla_nodynamicrealign_call(int i1, int i2, int i3, int i4, int i5, int i6, int i7, int i8, int i9, int i10,
;                                             double d1, double d2, double d3, double d4, double d5, double d6, double d7, double d8, double d9, double d10)
;{
;  // use an argument passed on the stack.
;  volatile int l1;
;  return i10 + (int)d10 + l1 + g();
;}
;extern "C" int novla_nodynamicrealign_nocall(int i1, int i2, int i3, int i4, int i5, int i6, int i7, int i8, int i9, int i10,
;                                             double d1, double d2, double d3, double d4, double d5, double d6, double d7, double d8, double d9, double d10)
;{
;  // use an argument passed on the stack.
;  volatile int l1;
;  return i10 + (int)d10 + l1;
;}
;extern "C" int novla_dynamicrealign_call(int i1, int i2, int i3, int i4, int i5, int i6, int i7, int i8, int i9, int i10,
;                                         double d1, double d2, double d3, double d4, double d5, double d6, double d7, double d8, double d9, double d10)
;{
;  // use an argument passed on the stack.
;  alignas(128) volatile int l1;
;  return i10 + (int)d10 + l1 + g();
;}
;extern "C" int novla_dynamicrealign_nocall(int i1, int i2, int i3, int i4, int i5, int i6, int i7, int i8, int i9, int i10,
;                                           double d1, double d2, double d3, double d4, double d5, double d6, double d7, double d8, double d9, double d10)
;{
;  // use an argument passed on the stack.
;  alignas(128) volatile int l1;
;  return i10 + (int)d10 + l1;
;}
;
;extern "C" int vla_nodynamicrealign_call(int i1, int i2, int i3, int i4, int i5, int i6, int i7, int i8, int i9, int i10,
;                                         double d1, double d2, double d3, double d4, double d5, double d6, double d7, double d8, double d9, double d10)
;{
;  // use an argument passed on the stack.
;  volatile int l1;
;  volatile int vla[i1];
;  return i10 + (int)d10 + l1 + g() + vla[0];
;}
;extern "C" int vla_nodynamicrealign_nocall(int i1, int i2, int i3, int i4, int i5, int i6, int i7, int i8, int i9, int i10,
;                                           double d1, double d2, double d3, double d4, double d5, double d6, double d7, double d8, double d9, double d10)
;{
;  // use an argument passed on the stack.
;  volatile int l1;
;  volatile int vla[i1];
;  return i10 + (int)d10 + l1 + vla[0];
;}
;extern "C" int vla_dynamicrealign_call(int i1, int i2, int i3, int i4, int i5, int i6, int i7, int i8, int i9, int i10,
;                                       double d1, double d2, double d3, double d4, double d5, double d6, double d7, double d8, double d9, double d10)
;{
;  // use an argument passed on the stack.
;  alignas(128) volatile int l1;
;  volatile int vla[i1];
;  return i10 + (int)d10 + l1 + g() + vla[0];
;}
;extern "C" int vla_dynamicrealign_nocall(int i1, int i2, int i3, int i4, int i5, int i6, int i7, int i8, int i9, int i10,
;                                         double d1, double d2, double d3, double d4, double d5, double d6, double d7, double d8, double d9, double d10)
;{
;  // use an argument passed on the stack.
;  alignas(128) volatile int l1;
;  volatile int vla[i1];
;  return i10 + (int)d10 + l1 + vla[0];
;}



define i32 @novla_nodynamicrealign_call(i32 %i1, i32 %i2, i32 %i3, i32 %i4, i32 %i5, i32 %i6, i32 %i7, i32 %i8, i32 %i9, i32 %i10, double %d1, double %d2, double %d3, double %d4, double %d5, double %d6, double %d7, double %d8, double %d9, double %d10) #0 {
entry:
  %l1 = alloca i32, align 4
  %conv = fptosi double %d10 to i32
  %add = add nsw i32 %conv, %i10
  %l1.0.l1.0. = load volatile i32, i32* %l1, align 4
  %add1 = add nsw i32 %add, %l1.0.l1.0.
  %call = tail call i32 @g()
  %add2 = add nsw i32 %add1, %call
  ret i32 %add2
}
; CHECK-LABEL: novla_nodynamicrealign_call
; CHECK: .cfi_startproc
;   Check that used callee-saved registers are saved
; CHECK: stp	x20, x19, [sp, #-32]!
;   Check that the frame pointer is created:
; CHECK: stp	x29, x30, [sp, #16]
; CHECK: add	x29, sp, #16
;   Check correctness of cfi pseudo-instructions
; CHECK: .cfi_def_cfa w29, 16
; CHECK: .cfi_offset w30, -8
; CHECK: .cfi_offset w29, -16
; CHECK: .cfi_offset w19, -24
; CHECK: .cfi_offset w20, -32
;   Check correct access to arguments passed on the stack, through frame pointer
; CHECK: ldr	d[[DARG:[0-9]+]], [x29, #40]
; CHECK: ldr	w[[IARG:[0-9]+]], [x29, #24]
;   Check correct access to local variable on the stack, through stack pointer
; CHECK: ldr	w[[ILOC:[0-9]+]], [sp, #12]
;   Check epilogue:
; CHECK: ldp	x29, x30, [sp, #16]
; CHECK: ldp	x20, x19, [sp], #32
; CHECK: ret
; CHECK: .cfi_endproc


declare i32 @g() #0

; Function Attrs: nounwind
define i32 @novla_nodynamicrealign_nocall(i32 %i1, i32 %i2, i32 %i3, i32 %i4, i32 %i5, i32 %i6, i32 %i7, i32 %i8, i32 %i9, i32 %i10, double %d1, double %d2, double %d3, double %d4, double %d5, double %d6, double %d7, double %d8, double %d9, double %d10) #1 {
entry:
  %l1 = alloca i32, align 4
  %conv = fptosi double %d10 to i32
  %add = add nsw i32 %conv, %i10
  %l1.0.l1.0. = load volatile i32, i32* %l1, align 4
  %add1 = add nsw i32 %add, %l1.0.l1.0.
  ret i32 %add1
}
; CHECK-LABEL: novla_nodynamicrealign_nocall
;   Check that space is reserved for one local variable on the stack.
; CHECK:	sub	sp, sp, #16             // =16
;   Check correct access to arguments passed on the stack, through stack pointer
; CHECK: ldr	d[[DARG:[0-9]+]], [sp, #40]
; CHECK: ldr	w[[IARG:[0-9]+]], [sp, #24]
;   Check correct access to local variable on the stack, through stack pointer
; CHECK: ldr	w[[ILOC:[0-9]+]], [sp, #12]
;   Check epilogue:
; CHECK: add	sp, sp, #16             // =16
; CHECK: ret


define i32 @novla_dynamicrealign_call(i32 %i1, i32 %i2, i32 %i3, i32 %i4, i32 %i5, i32 %i6, i32 %i7, i32 %i8, i32 %i9, i32 %i10, double %d1, double %d2, double %d3, double %d4, double %d5, double %d6, double %d7, double %d8, double %d9, double %d10) #0 {
entry:
  %l1 = alloca i32, align 128
  %conv = fptosi double %d10 to i32
  %add = add nsw i32 %conv, %i10
  %l1.0.l1.0. = load volatile i32, i32* %l1, align 128
  %add1 = add nsw i32 %add, %l1.0.l1.0.
  %call = tail call i32 @g()
  %add2 = add nsw i32 %add1, %call
  ret i32 %add2
}

; CHECK-LABEL: novla_dynamicrealign_call
; CHECK: .cfi_startproc
;   Check that used callee-saved registers are saved
; CHECK: stp	x20, x19, [sp, #-32]!
;   Check that the frame pointer is created:
; CHECK: stp	x29, x30, [sp, #16]
; CHECK: add	x29, sp, #16
;   Check the dynamic realignment of the stack pointer to a 128-byte boundary
; CHECK: sub	x9, sp, #96
; CHECK: and	sp, x9, #0xffffffffffffff80
;   Check correctness of cfi pseudo-instructions
; CHECK: .cfi_def_cfa w29, 16
; CHECK: .cfi_offset w30, -8
; CHECK: .cfi_offset w29, -16
; CHECK: .cfi_offset w19, -24
; CHECK: .cfi_offset w20, -32
;   Check correct access to arguments passed on the stack, through frame pointer
; CHECK: ldr	d[[DARG:[0-9]+]], [x29, #40]
; CHECK: ldr	w[[IARG:[0-9]+]], [x29, #24]
;   Check correct access to local variable on the stack, through re-aligned stack pointer
; CHECK: ldr	w[[ILOC:[0-9]+]], [sp]
;   Check epilogue:
;     Check that stack pointer get restored from frame pointer.
; CHECK: sub	sp, x29, #16            // =16
; CHECK: ldp	x29, x30, [sp, #16]
; CHECK: ldp	x20, x19, [sp], #32
; CHECK: ret
; CHECK: .cfi_endproc


; Function Attrs: nounwind
define i32 @novla_dynamicrealign_nocall(i32 %i1, i32 %i2, i32 %i3, i32 %i4, i32 %i5, i32 %i6, i32 %i7, i32 %i8, i32 %i9, i32 %i10, double %d1, double %d2, double %d3, double %d4, double %d5, double %d6, double %d7, double %d8, double %d9, double %d10) #1 {
entry:
  %l1 = alloca i32, align 128
  %conv = fptosi double %d10 to i32
  %add = add nsw i32 %conv, %i10
  %l1.0.l1.0. = load volatile i32, i32* %l1, align 128
  %add1 = add nsw i32 %add, %l1.0.l1.0.
  ret i32 %add1
}

; CHECK-LABEL: novla_dynamicrealign_nocall
;   Check that the frame pointer is created:
; CHECK: stp	x29, x30, [sp, #-16]!
; CHECK: mov	x29, sp
;   Check the dynamic realignment of the stack pointer to a 128-byte boundary
; CHECK: sub	x9, sp, #112
; CHECK: and	sp, x9, #0xffffffffffffff80
;   Check correct access to arguments passed on the stack, through frame pointer
; CHECK: ldr	d[[DARG:[0-9]+]], [x29, #40]
; CHECK: ldr	w[[IARG:[0-9]+]], [x29, #24]
;   Check correct access to local variable on the stack, through re-aligned stack pointer
; CHECK: ldr	w[[ILOC:[0-9]+]], [sp]
;   Check epilogue:
;     Check that stack pointer get restored from frame pointer.
; CHECK: mov	sp, x29
; CHECK: ldp	x29, x30, [sp], #16
; CHECK: ret


define i32 @vla_nodynamicrealign_call(i32 %i1, i32 %i2, i32 %i3, i32 %i4, i32 %i5, i32 %i6, i32 %i7, i32 %i8, i32 %i9, i32 %i10, double %d1, double %d2, double %d3, double %d4, double %d5, double %d6, double %d7, double %d8, double %d9, double %d10) #0 {
entry:
  %l1 = alloca i32, align 4
  %0 = zext i32 %i1 to i64
  %vla = alloca i32, i64 %0, align 4
  %conv = fptosi double %d10 to i32
  %add = add nsw i32 %conv, %i10
  %l1.0.l1.0. = load volatile i32, i32* %l1, align 4
  %add1 = add nsw i32 %add, %l1.0.l1.0.
  %call = tail call i32 @g()
  %add2 = add nsw i32 %add1, %call
  %1 = load volatile i32, i32* %vla, align 4, !tbaa !1
  %add3 = add nsw i32 %add2, %1
  ret i32 %add3
}

; CHECK-LABEL: vla_nodynamicrealign_call
; CHECK: .cfi_startproc
;   Check that used callee-saved registers are saved
; CHECK: stp	x20, x19, [sp, #-32]!
;   Check that the frame pointer is created:
; CHECK: stp	x29, x30, [sp, #16]
; CHECK: add	x29, sp, #16
;   Check that space is reserved on the stack for the local variable,
;   rounded up to a multiple of 16 to keep the stack pointer 16-byte aligned.
; CHECK: sub	sp, sp, #16
;   Check correctness of cfi pseudo-instructions
; CHECK: .cfi_def_cfa w29, 16
; CHECK: .cfi_offset w30, -8
; CHECK: .cfi_offset w29, -16
; CHECK: .cfi_offset w19, -24
; CHECK: .cfi_offset w20, -32
;   Check correct access to arguments passed on the stack, through frame pointer
; CHECK: ldr	w[[IARG:[0-9]+]], [x29, #24]
; CHECK: ldr	d[[DARG:[0-9]+]], [x29, #40]
;   Check correct reservation of 16-byte aligned VLA (size in w0) on stack
; CHECK: mov	w9, w0
; CHECK: mov	 x10, sp
; CHECK: lsl	x9, x9, #2
; CHECK: add	x9, x9, #15
; CHECK: and	x9, x9, #0x7fffffff0
; CHECK: sub	 x[[VLASPTMP:[0-9]+]], x10, x9
; CHECK: mov	 sp, x[[VLASPTMP]]
;   Check correct access to local variable, through frame pointer
; CHECK: ldur	w[[ILOC:[0-9]+]], [x29, #-20]
;   Check correct accessing of the VLA variable through the base pointer
; CHECK: ldr	w[[VLA:[0-9]+]], [x[[VLASPTMP]]]
;   Check epilogue:
;     Check that stack pointer get restored from frame pointer.
; CHECK: sub	sp, x29, #16            // =16
; CHECK: ldp	x29, x30, [sp, #16]
; CHECK: ldp	x20, x19, [sp], #32
; CHECK: ret
; CHECK: .cfi_endproc


; Function Attrs: nounwind
define i32 @vla_nodynamicrealign_nocall(i32 %i1, i32 %i2, i32 %i3, i32 %i4, i32 %i5, i32 %i6, i32 %i7, i32 %i8, i32 %i9, i32 %i10, double %d1, double %d2, double %d3, double %d4, double %d5, double %d6, double %d7, double %d8, double %d9, double %d10) #1 {
entry:
  %l1 = alloca i32, align 4
  %0 = zext i32 %i1 to i64
  %vla = alloca i32, i64 %0, align 4
  %conv = fptosi double %d10 to i32
  %add = add nsw i32 %conv, %i10
  %l1.0.l1.0. = load volatile i32, i32* %l1, align 4
  %add1 = add nsw i32 %add, %l1.0.l1.0.
  %1 = load volatile i32, i32* %vla, align 4, !tbaa !1
  %add2 = add nsw i32 %add1, %1
  ret i32 %add2
}

; CHECK-LABEL: vla_nodynamicrealign_nocall
;   Check that the frame pointer is created:
; CHECK: stp	x29, x30, [sp, #-16]!
; CHECK: mov	x29, sp
;   Check that space is reserved on the stack for the local variable,
;   rounded up to a multiple of 16 to keep the stack pointer 16-byte aligned.
; CHECK: sub	sp, sp, #16
;   Check correctness of cfi pseudo-instructions
;   Check correct access to arguments passed on the stack, through frame pointer
; CHECK: ldr	w[[IARG:[0-9]+]], [x29, #24]
; CHECK: ldr	d[[DARG:[0-9]+]], [x29, #40]
;   Check correct reservation of 16-byte aligned VLA (size in w0) on stack
; CHECK: mov	w9, w0
; CHECK: mov	 x10, sp
; CHECK: lsl	x9, x9, #2
; CHECK: add	x9, x9, #15
; CHECK: and	x9, x9, #0x7fffffff0
; CHECK: sub	 x[[VLASPTMP:[0-9]+]], x10, x9
; CHECK: mov	 sp, x[[VLASPTMP]]
;   Check correct access to local variable, through frame pointer
; CHECK: ldur	w[[ILOC:[0-9]+]], [x29, #-4]
;   Check correct accessing of the VLA variable through the base pointer
; CHECK: ldr	w[[VLA:[0-9]+]], [x[[VLASPTMP]]]
;   Check epilogue:
;     Check that stack pointer get restored from frame pointer.
; CHECK: mov    sp, x29
; CHECK: ldp	x29, x30, [sp], #16
; CHECK: ret


define i32 @vla_dynamicrealign_call(i32 %i1, i32 %i2, i32 %i3, i32 %i4, i32 %i5, i32 %i6, i32 %i7, i32 %i8, i32 %i9, i32 %i10, double %d1, double %d2, double %d3, double %d4, double %d5, double %d6, double %d7, double %d8, double %d9, double %d10) #0 {
entry:
  %l1 = alloca i32, align 128
  %0 = zext i32 %i1 to i64
  %vla = alloca i32, i64 %0, align 4
  %conv = fptosi double %d10 to i32
  %add = add nsw i32 %conv, %i10
  %l1.0.l1.0. = load volatile i32, i32* %l1, align 128
  %add1 = add nsw i32 %add, %l1.0.l1.0.
  %call = tail call i32 @g()
  %add2 = add nsw i32 %add1, %call
  %1 = load volatile i32, i32* %vla, align 4, !tbaa !1
  %add3 = add nsw i32 %add2, %1
  ret i32 %add3
}

; CHECK-LABEL: vla_dynamicrealign_call
; CHECK: .cfi_startproc
;   Check that used callee-saved registers are saved
; CHECK: stp	x22, x21, [sp, #-48]!
; CHECK: stp	x20, x19, [sp, #16]
;   Check that the frame pointer is created:
; CHECK: stp	x29, x30, [sp, #32]
; CHECK: add	x29, sp, #32
;   Check that the stack pointer gets re-aligned to 128
;   bytes & the base pointer (x19) gets initialized to
;   this 128-byte aligned area for local variables &
;   spill slots
; CHECK: sub	x9, sp, #80            // =80
; CHECK: and	sp, x9, #0xffffffffffffff80
; CHECK: mov    x19, sp
;   Check correctness of cfi pseudo-instructions
; CHECK: .cfi_def_cfa w29, 16
; CHECK: .cfi_offset w30, -8
; CHECK: .cfi_offset w29, -16
; CHECK: .cfi_offset w19, -24
; CHECK: .cfi_offset w20, -32
; CHECK: .cfi_offset w21, -40
; CHECK: .cfi_offset w22, -48
;   Check correct access to arguments passed on the stack, through frame pointer
; CHECK: ldr	w[[IARG:[0-9]+]], [x29, #24]
; CHECK: ldr	d[[DARG:[0-9]+]], [x29, #40]
;   Check correct reservation of 16-byte aligned VLA (size in w0) on stack
;   and set-up of base pointer (x19).
; CHECK: mov	w9, w0
; CHECK: mov	 x10, sp
; CHECK: lsl	x9, x9, #2
; CHECK: add	x9, x9, #15
; CHECK: and	x9, x9, #0x7fffffff0
; CHECK: sub	 x[[VLASPTMP:[0-9]+]], x10, x9
; CHECK: mov	 sp, x[[VLASPTMP]]
;   Check correct access to local variable, through base pointer
; CHECK: ldr	w[[ILOC:[0-9]+]], [x19]
; CHECK: ldr	 w[[VLA:[0-9]+]], [x[[VLASPTMP]]]
;   Check epilogue:
;     Check that stack pointer get restored from frame pointer.
; CHECK: sub	sp, x29, #32
; CHECK: ldp	x29, x30, [sp, #32]
; CHECK: ldp	x20, x19, [sp, #16]
; CHECK: ldp	x22, x21, [sp], #48
; CHECK: ret
; CHECK: .cfi_endproc


; Function Attrs: nounwind
define i32 @vla_dynamicrealign_nocall(i32 %i1, i32 %i2, i32 %i3, i32 %i4, i32 %i5, i32 %i6, i32 %i7, i32 %i8, i32 %i9, i32 %i10, double %d1, double %d2, double %d3, double %d4, double %d5, double %d6, double %d7, double %d8, double %d9, double %d10) #1 {
entry:
  %l1 = alloca i32, align 128
  %0 = zext i32 %i1 to i64
  %vla = alloca i32, i64 %0, align 4
  %conv = fptosi double %d10 to i32
  %add = add nsw i32 %conv, %i10
  %l1.0.l1.0. = load volatile i32, i32* %l1, align 128
  %add1 = add nsw i32 %add, %l1.0.l1.0.
  %1 = load volatile i32, i32* %vla, align 4, !tbaa !1
  %add2 = add nsw i32 %add1, %1
  ret i32 %add2
}

; CHECK-LABEL: vla_dynamicrealign_nocall
;   Check that used callee-saved registers are saved
; CHECK: stp	x20, x19, [sp, #-32]!
;   Check that the frame pointer is created:
; CHECK: stp	x29, x30, [sp, #16]
; CHECK: add	x29, sp, #16
;   Check that the stack pointer gets re-aligned to 128
;   bytes & the base pointer (x19) gets initialized to
;   this 128-byte aligned area for local variables &
;   spill slots
; CHECK: sub	x9, sp, #96
; CHECK: and	sp, x9, #0xffffffffffffff80
; CHECK: mov    x19, sp
;   Check correct access to arguments passed on the stack, through frame pointer
; CHECK: ldr	w[[IARG:[0-9]+]], [x29, #24]
; CHECK: ldr	d[[DARG:[0-9]+]], [x29, #40]
;   Check correct reservation of 16-byte aligned VLA (size in w0) on stack
;   and set-up of base pointer (x19).
; CHECK: mov	w9, w0
; CHECK: mov	 x10, sp
; CHECK: lsl	x9, x9, #2
; CHECK: add	x9, x9, #15
; CHECK: and	x9, x9, #0x7fffffff0
; CHECK: sub	 x[[VLASPTMP:[0-9]+]], x10, x9
; CHECK: mov	 sp, x[[VLASPTMP]]
;   Check correct access to local variable, through base pointer
; CHECK: ldr	w[[ILOC:[0-9]+]], [x19]
; CHECK: ldr	 w[[VLA:[0-9]+]], [x[[VLASPTMP]]]
;   Check epilogue:
;     Check that stack pointer get restored from frame pointer.
; CHECK: sub	sp, x29, #16
; CHECK: ldp	x29, x30, [sp, #16]
; CHECK: ldp	x20, x19, [sp], #32
; CHECK: ret


; Function Attrs: nounwind
define i32 @vla_dynamicrealign_nocall_large_align(i32 %i1, i32 %i2, i32 %i3, i32 %i4, i32 %i5, i32 %i6, i32 %i7, i32 %i8, i32 %i9, i32 %i10, double %d1, double %d2, double %d3, double %d4, double %d5, double %d6, double %d7, double %d8, double %d9, double %d10) #1 {
entry:
  %l1 = alloca i32, align 32768
  %0 = zext i32 %i1 to i64
  %vla = alloca i32, i64 %0, align 4
  %conv = fptosi double %d10 to i32
  %add = add nsw i32 %conv, %i10
  %l1.0.l1.0. = load volatile i32, i32* %l1, align 32768
  %add1 = add nsw i32 %add, %l1.0.l1.0.
  %1 = load volatile i32, i32* %vla, align 4, !tbaa !1
  %add2 = add nsw i32 %add1, %1
  ret i32 %add2
}

; CHECK-LABEL: vla_dynamicrealign_nocall_large_align
;   Check that used callee-saved registers are saved
; CHECK: stp	x20, x19, [sp, #-32]!
;   Check that the frame pointer is created:
; CHECK: stp	x29, x30, [sp, #16]
; CHECK: add	x29, sp, #16
;   Check that the stack pointer gets re-aligned to 128
;   bytes & the base pointer (x19) gets initialized to
;   this 128-byte aligned area for local variables &
;   spill slots
; CHECK: sub	x9, sp, #7, lsl #12
; CHECK: and	sp, x9, #0xffffffffffff8000
; CHECK: mov    x19, sp
;   Check correct access to arguments passed on the stack, through frame pointer
; CHECK: ldr	w[[IARG:[0-9]+]], [x29, #24]
; CHECK: ldr	d[[DARG:[0-9]+]], [x29, #40]
;   Check correct reservation of 16-byte aligned VLA (size in w0) on stack
;   and set-up of base pointer (x19).
; CHECK: mov	w9, w0
; CHECK: mov	 x10, sp
; CHECK: lsl	x9, x9, #2
; CHECK: add	x9, x9, #15
; CHECK: and	x9, x9, #0x7fffffff0
; CHECK: sub	 x[[VLASPTMP:[0-9]+]], x10, x9
; CHECK: mov	 sp, x[[VLASPTMP]]
;   Check correct access to local variable, through base pointer
; CHECK: ldr	w[[ILOC:[0-9]+]], [x19]
; CHECK: ldr	 w[[VLA:[0-9]+]], [x[[VLASPTMP]]]
;   Check epilogue:
;     Check that stack pointer get restored from frame pointer.
; CHECK: sub	sp, x29, #16
; CHECK: ldp	x29, x30, [sp, #16]
; CHECK: ldp	x20, x19, [sp], #32
; CHECK: ret


define void @realign_conditional(i1 %b) {
entry:
  br i1 %b, label %bb0, label %bb1

bb0:
  %MyAlloca = alloca i8, i64 64, align 32
  br label %bb1

bb1:
  ret void
}

; CHECK-LABEL: realign_conditional
; No realignment in the prologue.
; CHECK-NOT:  and
; CHECK-NOT:  0xffffffffffffffe0
; CHECK:  tbz  {{.*}} .[[LABEL:.*]]
; Stack is realigned in a non-entry BB.
; CHECK:  sub  [[REG:x[01-9]+]], sp, #64
; CHECK:  and  sp, [[REG]], #0xffffffffffffffe0
; CHECK:  .[[LABEL]]:
; CHECK:  ret


define void @realign_conditional2(i1 %b) {
entry:
  %tmp = alloca i8, i32 4
  br i1 %b, label %bb0, label %bb1

bb0:
  %MyAlloca = alloca i8, i64 64, align 32
  br label %bb1

bb1:
  ret void
}

; CHECK-LABEL: realign_conditional2
; Extra realignment in the prologue (performance issue).
; CHECK:  sub  x9, sp, #32            // =32
; CHECK:  and  sp, x9, #0xffffffffffffffe0
; CHECK:  mov   x19, sp
; CHECK:  tbz  {{.*}} .[[LABEL:.*]]
; Stack is realigned in a non-entry BB.
; CHECK:  sub  [[REG:x[01-9]+]], sp, #64
; CHECK:  and  sp, [[REG]], #0xffffffffffffffe0
; CHECK:  .[[LABEL]]:
; CHECK:  ret

attributes #0 = { "less-precise-fpmad"="false" "no-frame-pointer-elim"="true" "no-frame-pointer-elim-non-leaf" "no-infs-fp-math"="false" "no-nans-fp-math"="false" "stack-protector-buffer-size"="8" "unsafe-fp-math"="false" "use-soft-float"="false" }
attributes #1 = { nounwind "less-precise-fpmad"="false" "no-frame-pointer-elim"="true" "no-frame-pointer-elim-non-leaf" "no-infs-fp-math"="false" "no-nans-fp-math"="false" "stack-protector-buffer-size"="8" "unsafe-fp-math"="false" "use-soft-float"="false" }

!1 = !{!2, !2, i64 0}
!2 = !{!"int", !3, i64 0}
!3 = !{!"omnipotent char", !4, i64 0}
!4 = !{!"Simple C/C++ TBAA"}