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
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
|
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --function-signature --check-globals
; RUN: opt -S -passes=openmp-opt < %s | FileCheck %s
;; void unknown(void);
;; void spmd_amenable(void) __attribute__((assume("ompx_spmd_amenable")));
;;
;; void sequential_loop() {
;; #pragma omp target teams
;; {
;; for (int i = 0; i < 100; ++i) {
;; #pragma omp parallel
;; {
;; unknown();
;; }
;; }
;; spmd_amenable();
;; }
;; }
;;
;; void use(__attribute__((noescape)) int *) __attribute__((assume("ompx_spmd_amenable")));
;;
;; void sequential_loop_to_stack_var() {
;; #pragma omp target teams
;; {
;; int x;
;; use(&x);
;; for (int i = 0; i < 100; ++i) {
;; #pragma omp parallel
;; {
;; unknown();
;; }
;; }
;; spmd_amenable();
;; }
;; }
;;
;; void sequential_loop_to_shared_var() {
;; #pragma omp target teams
;; {
;; int x;
;; for (int i = 0; i < 100; ++i) {
;; #pragma omp parallel
;; {
;; x++;
;; unknown();
;; }
;; }
;; spmd_amenable();
;; }
;; }
target triple = "nvptx64"
%struct.ident_t = type { i32, i32, i32, i32, i8* }
@0 = private unnamed_addr constant [23 x i8] c";unknown;unknown;0;0;;\00", align 1
@1 = private unnamed_addr constant %struct.ident_t { i32 0, i32 2, i32 0, i32 0, i8* getelementptr inbounds ([23 x i8], [23 x i8]* @0, i32 0, i32 0) }, align 8
@__omp_offloading_14_5896c35_sequential_loop_l5_exec_mode = weak constant i8 1
@__omp_offloading_14_5896c35_sequential_loop_to_stack_var_l20_exec_mode = weak constant i8 1
@__omp_offloading_14_5896c35_sequential_loop_to_shared_var_l35_exec_mode = weak constant i8 1
@llvm.compiler.used = appending global [3 x i8*] [i8* @__omp_offloading_14_5896c35_sequential_loop_l5_exec_mode, i8* @__omp_offloading_14_5896c35_sequential_loop_to_stack_var_l20_exec_mode, i8* @__omp_offloading_14_5896c35_sequential_loop_to_shared_var_l35_exec_mode], section "llvm.metadata"
;.
; CHECK: @[[GLOB0:[0-9]+]] = private unnamed_addr constant [23 x i8] c"
; CHECK: @[[GLOB1:[0-9]+]] = private unnamed_addr constant [[STRUCT_IDENT_T:%.*]] { i32 0, i32 2, i32 0, i32 0, i8* getelementptr inbounds ([23 x i8], [23 x i8]* @[[GLOB0]], i32 0, i32 0) }, align 8
; CHECK: @[[__OMP_OFFLOADING_14_5896C35_SEQUENTIAL_LOOP_L5_EXEC_MODE:[a-zA-Z0-9_$"\\.-]+]] = weak constant i8 2
; CHECK: @[[__OMP_OFFLOADING_14_5896C35_SEQUENTIAL_LOOP_TO_STACK_VAR_L20_EXEC_MODE:[a-zA-Z0-9_$"\\.-]+]] = weak constant i8 2
; CHECK: @[[__OMP_OFFLOADING_14_5896C35_SEQUENTIAL_LOOP_TO_SHARED_VAR_L35_EXEC_MODE:[a-zA-Z0-9_$"\\.-]+]] = weak constant i8 2
; CHECK: @[[LLVM_COMPILER_USED:[a-zA-Z0-9_$"\\.-]+]] = appending global [3 x i8*] [i8* @__omp_offloading_14_5896c35_sequential_loop_l5_exec_mode, i8* @__omp_offloading_14_5896c35_sequential_loop_to_stack_var_l20_exec_mode, i8* @__omp_offloading_14_5896c35_sequential_loop_to_shared_var_l35_exec_mode], section "llvm.metadata"
; CHECK: @[[X:[a-zA-Z0-9_$"\\.-]+]] = internal addrspace(3) global [4 x i8] undef, align 32
;.
define weak void @__omp_offloading_14_5896c35_sequential_loop_l5() #0 {
; CHECK-LABEL: define {{[^@]+}}@__omp_offloading_14_5896c35_sequential_loop_l5
; CHECK-SAME: () #[[ATTR0:[0-9]+]] {
; CHECK-NEXT: entry:
; CHECK-NEXT: [[DOTZERO_ADDR:%.*]] = alloca i32, align 4
; CHECK-NEXT: [[DOTTHREADID_TEMP_:%.*]] = alloca i32, align 4
; CHECK-NEXT: [[TMP0:%.*]] = call i32 @__kmpc_target_init(%struct.ident_t* @[[GLOB1]], i1 true, i1 false, i1 false)
; CHECK-NEXT: [[EXEC_USER_CODE:%.*]] = icmp eq i32 [[TMP0]], -1
; CHECK-NEXT: br i1 [[EXEC_USER_CODE]], label [[USER_CODE_ENTRY:%.*]], label [[WORKER_EXIT:%.*]]
; CHECK: user_code.entry:
; CHECK-NEXT: [[TMP1:%.*]] = call i32 @__kmpc_global_thread_num(%struct.ident_t* @[[GLOB1]]) #[[ATTR3:[0-9]+]]
; CHECK-NEXT: store i32 [[TMP1]], i32* [[DOTTHREADID_TEMP_]], align 4
; CHECK-NEXT: call void @__omp_outlined__(i32* noalias nocapture noundef nonnull readonly align 4 dereferenceable(4) [[DOTTHREADID_TEMP_]], i32* noalias nocapture noundef nonnull readnone align 4 dereferenceable(4) [[DOTZERO_ADDR]]) #[[ATTR3]]
; CHECK-NEXT: call void @__kmpc_target_deinit(%struct.ident_t* @[[GLOB1]], i1 true, i1 false)
; CHECK-NEXT: ret void
; CHECK: worker.exit:
; CHECK-NEXT: ret void
;
entry:
%.zero.addr = alloca i32, align 4
%.threadid_temp. = alloca i32, align 4
store i32 0, i32* %.zero.addr, align 4
%0 = call i32 @__kmpc_target_init(%struct.ident_t* @1, i1 false, i1 true, i1 true)
%exec_user_code = icmp eq i32 %0, -1
br i1 %exec_user_code, label %user_code.entry, label %worker.exit
user_code.entry: ; preds = %entry
%1 = call i32 @__kmpc_global_thread_num(%struct.ident_t* @1)
store i32 %1, i32* %.threadid_temp., align 4
call void @__omp_outlined__(i32* %.threadid_temp., i32* %.zero.addr) #3
call void @__kmpc_target_deinit(%struct.ident_t* @1, i1 false, i1 true)
ret void
worker.exit: ; preds = %entry
ret void
}
declare i32 @__kmpc_target_init(%struct.ident_t*, i1, i1, i1)
define internal void @__omp_outlined__(i32* noalias %.global_tid., i32* noalias %.bound_tid.) #0 {
; CHECK-LABEL: define {{[^@]+}}@__omp_outlined__
; CHECK-SAME: (i32* noalias nocapture nofree noundef nonnull readonly align 4 dereferenceable(4) [[DOTGLOBAL_TID_:%.*]], i32* noalias nocapture nofree nonnull readnone align 4 dereferenceable(4) [[DOTBOUND_TID_:%.*]]) #[[ATTR0]] {
; CHECK-NEXT: entry:
; CHECK-NEXT: [[DOTGLOBAL_TID__ADDR:%.*]] = alloca i32*, align 8
; CHECK-NEXT: [[DOTBOUND_TID__ADDR:%.*]] = alloca i32*, align 8
; CHECK-NEXT: [[I:%.*]] = alloca i32, align 4
; CHECK-NEXT: [[CAPTURED_VARS_ADDRS:%.*]] = alloca [0 x i8*], align 8
; CHECK-NEXT: store i32* [[DOTGLOBAL_TID_]], i32** [[DOTGLOBAL_TID__ADDR]], align 8
; CHECK-NEXT: store i32 0, i32* [[I]], align 4
; CHECK-NEXT: br label [[FOR_COND:%.*]]
; CHECK: for.cond:
; CHECK-NEXT: [[TMP0:%.*]] = load i32, i32* [[I]], align 4
; CHECK-NEXT: [[CMP:%.*]] = icmp slt i32 [[TMP0]], 100
; CHECK-NEXT: br i1 [[CMP]], label [[FOR_BODY:%.*]], label [[FOR_END:%.*]]
; CHECK: for.body:
; CHECK-NEXT: [[TMP1:%.*]] = load i32, i32* [[DOTGLOBAL_TID_]], align 4
; CHECK-NEXT: [[TMP2:%.*]] = bitcast [0 x i8*]* [[CAPTURED_VARS_ADDRS]] to i8**
; CHECK-NEXT: call void @__kmpc_parallel_51(%struct.ident_t* noundef @[[GLOB1]], i32 [[TMP1]], i32 noundef 1, i32 noundef -1, i32 noundef -1, i8* noundef bitcast (void (i32*, i32*)* @__omp_outlined__1 to i8*), i8* noundef bitcast (void (i16, i32)* @__omp_outlined__1_wrapper to i8*), i8** noundef [[TMP2]], i64 noundef 0)
; CHECK-NEXT: br label [[FOR_INC:%.*]]
; CHECK: for.inc:
; CHECK-NEXT: [[TMP3:%.*]] = load i32, i32* [[I]], align 4
; CHECK-NEXT: [[INC:%.*]] = add nsw i32 [[TMP3]], 1
; CHECK-NEXT: store i32 [[INC]], i32* [[I]], align 4
; CHECK-NEXT: br label [[FOR_COND]], !llvm.loop [[LOOP9:![0-9]+]]
; CHECK: for.end:
; CHECK-NEXT: call void @spmd_amenable() #[[ATTR4:[0-9]+]]
; CHECK-NEXT: ret void
;
entry:
%.global_tid..addr = alloca i32*, align 8
%.bound_tid..addr = alloca i32*, align 8
%i = alloca i32, align 4
%captured_vars_addrs = alloca [0 x i8*], align 8
store i32* %.global_tid., i32** %.global_tid..addr, align 8
store i32* %.bound_tid., i32** %.bound_tid..addr, align 8
store i32 0, i32* %i, align 4
br label %for.cond
for.cond: ; preds = %for.inc, %entry
%0 = load i32, i32* %i, align 4
%cmp = icmp slt i32 %0, 100
br i1 %cmp, label %for.body, label %for.end
for.body: ; preds = %for.cond
%1 = load i32*, i32** %.global_tid..addr, align 8
%2 = load i32, i32* %1, align 4
%3 = bitcast [0 x i8*]* %captured_vars_addrs to i8**
call void @__kmpc_parallel_51(%struct.ident_t* @1, i32 %2, i32 1, i32 -1, i32 -1, i8* bitcast (void (i32*, i32*)* @__omp_outlined__1 to i8*), i8* bitcast (void (i16, i32)* @__omp_outlined__1_wrapper to i8*), i8** %3, i64 0)
br label %for.inc
for.inc: ; preds = %for.body
%4 = load i32, i32* %i, align 4
%inc = add nsw i32 %4, 1
store i32 %inc, i32* %i, align 4
br label %for.cond, !llvm.loop !9
for.end: ; preds = %for.cond
call void @spmd_amenable() #4
ret void
}
define internal void @__omp_outlined__1(i32* noalias %.global_tid., i32* noalias %.bound_tid.) #0 {
; CHECK-LABEL: define {{[^@]+}}@__omp_outlined__1
; CHECK-SAME: (i32* noalias nocapture nofree readnone [[DOTGLOBAL_TID_:%.*]], i32* noalias nocapture nofree readnone [[DOTBOUND_TID_:%.*]]) #[[ATTR0]] {
; CHECK-NEXT: entry:
; CHECK-NEXT: [[DOTGLOBAL_TID__ADDR:%.*]] = alloca i32*, align 8
; CHECK-NEXT: [[DOTBOUND_TID__ADDR:%.*]] = alloca i32*, align 8
; CHECK-NEXT: call void @unknown() #[[ATTR5:[0-9]+]]
; CHECK-NEXT: ret void
;
entry:
%.global_tid..addr = alloca i32*, align 8
%.bound_tid..addr = alloca i32*, align 8
store i32* %.global_tid., i32** %.global_tid..addr, align 8
store i32* %.bound_tid., i32** %.bound_tid..addr, align 8
call void @unknown() #5
ret void
}
declare void @unknown() #1
define internal void @__omp_outlined__1_wrapper(i16 zeroext %0, i32 %1) #0 {
; CHECK-LABEL: define {{[^@]+}}@__omp_outlined__1_wrapper
; CHECK-SAME: (i16 zeroext [[TMP0:%.*]], i32 [[TMP1:%.*]]) #[[ATTR0]] {
; CHECK-NEXT: entry:
; CHECK-NEXT: [[DOTADDR:%.*]] = alloca i16, align 2
; CHECK-NEXT: [[DOTADDR1:%.*]] = alloca i32, align 4
; CHECK-NEXT: [[DOTZERO_ADDR:%.*]] = alloca i32, align 4
; CHECK-NEXT: [[GLOBAL_ARGS:%.*]] = alloca i8**, align 8
; CHECK-NEXT: store i32 0, i32* [[DOTZERO_ADDR]], align 4
; CHECK-NEXT: store i16 [[TMP0]], i16* [[DOTADDR]], align 2
; CHECK-NEXT: store i32 [[TMP1]], i32* [[DOTADDR1]], align 4
; CHECK-NEXT: call void @__kmpc_get_shared_variables(i8*** [[GLOBAL_ARGS]])
; CHECK-NEXT: call void @__omp_outlined__1(i32* [[DOTADDR1]], i32* [[DOTZERO_ADDR]]) #[[ATTR3]]
; CHECK-NEXT: ret void
;
entry:
%.addr = alloca i16, align 2
%.addr1 = alloca i32, align 4
%.zero.addr = alloca i32, align 4
%global_args = alloca i8**, align 8
store i32 0, i32* %.zero.addr, align 4
store i16 %0, i16* %.addr, align 2
store i32 %1, i32* %.addr1, align 4
call void @__kmpc_get_shared_variables(i8*** %global_args)
call void @__omp_outlined__1(i32* %.addr1, i32* %.zero.addr) #3
ret void
}
declare void @__kmpc_get_shared_variables(i8***)
declare void @__kmpc_parallel_51(%struct.ident_t*, i32, i32, i32, i32, i8*, i8*, i8**, i64)
declare void @spmd_amenable() #2
declare i32 @__kmpc_global_thread_num(%struct.ident_t*) #3
declare void @__kmpc_target_deinit(%struct.ident_t*, i1, i1)
define weak void @__omp_offloading_14_5896c35_sequential_loop_to_stack_var_l20() #0 {
; CHECK-LABEL: define {{[^@]+}}@__omp_offloading_14_5896c35_sequential_loop_to_stack_var_l20
; CHECK-SAME: () #[[ATTR0]] {
; CHECK-NEXT: entry:
; CHECK-NEXT: [[DOTZERO_ADDR:%.*]] = alloca i32, align 4
; CHECK-NEXT: [[DOTTHREADID_TEMP_:%.*]] = alloca i32, align 4
; CHECK-NEXT: [[TMP0:%.*]] = call i32 @__kmpc_target_init(%struct.ident_t* @[[GLOB1]], i1 true, i1 false, i1 false)
; CHECK-NEXT: [[EXEC_USER_CODE:%.*]] = icmp eq i32 [[TMP0]], -1
; CHECK-NEXT: br i1 [[EXEC_USER_CODE]], label [[USER_CODE_ENTRY:%.*]], label [[WORKER_EXIT:%.*]]
; CHECK: user_code.entry:
; CHECK-NEXT: [[TMP1:%.*]] = call i32 @__kmpc_global_thread_num(%struct.ident_t* @[[GLOB1]]) #[[ATTR3]]
; CHECK-NEXT: store i32 [[TMP1]], i32* [[DOTTHREADID_TEMP_]], align 4
; CHECK-NEXT: call void @__omp_outlined__2(i32* noalias nocapture noundef nonnull readonly align 4 dereferenceable(4) [[DOTTHREADID_TEMP_]], i32* noalias nocapture noundef nonnull readnone align 4 dereferenceable(4) [[DOTZERO_ADDR]]) #[[ATTR3]]
; CHECK-NEXT: call void @__kmpc_target_deinit(%struct.ident_t* @[[GLOB1]], i1 true, i1 false)
; CHECK-NEXT: ret void
; CHECK: worker.exit:
; CHECK-NEXT: ret void
;
entry:
%.zero.addr = alloca i32, align 4
%.threadid_temp. = alloca i32, align 4
store i32 0, i32* %.zero.addr, align 4
%0 = call i32 @__kmpc_target_init(%struct.ident_t* @1, i1 false, i1 true, i1 true)
%exec_user_code = icmp eq i32 %0, -1
br i1 %exec_user_code, label %user_code.entry, label %worker.exit
user_code.entry: ; preds = %entry
%1 = call i32 @__kmpc_global_thread_num(%struct.ident_t* @1)
store i32 %1, i32* %.threadid_temp., align 4
call void @__omp_outlined__2(i32* %.threadid_temp., i32* %.zero.addr) #3
call void @__kmpc_target_deinit(%struct.ident_t* @1, i1 false, i1 true)
ret void
worker.exit: ; preds = %entry
ret void
}
define internal void @__omp_outlined__2(i32* noalias %.global_tid., i32* noalias %.bound_tid.) #0 {
; CHECK-LABEL: define {{[^@]+}}@__omp_outlined__2
; CHECK-SAME: (i32* noalias nocapture nofree noundef nonnull readonly align 4 dereferenceable(4) [[DOTGLOBAL_TID_:%.*]], i32* noalias nocapture nofree nonnull readnone align 4 dereferenceable(4) [[DOTBOUND_TID_:%.*]]) #[[ATTR0]] {
; CHECK-NEXT: entry:
; CHECK-NEXT: [[DOTGLOBAL_TID__ADDR:%.*]] = alloca i32*, align 8
; CHECK-NEXT: [[DOTBOUND_TID__ADDR:%.*]] = alloca i32*, align 8
; CHECK-NEXT: [[I:%.*]] = alloca i32, align 4
; CHECK-NEXT: [[CAPTURED_VARS_ADDRS:%.*]] = alloca [0 x i8*], align 8
; CHECK-NEXT: store i32* [[DOTGLOBAL_TID_]], i32** [[DOTGLOBAL_TID__ADDR]], align 8
; CHECK-NEXT: [[TMP0:%.*]] = alloca i8, i64 4, align 1
; CHECK-NEXT: [[X_ON_STACK:%.*]] = bitcast i8* [[TMP0]] to i32*
; CHECK-NEXT: call void @use(i32* nocapture [[X_ON_STACK]]) #[[ATTR4]]
; CHECK-NEXT: store i32 0, i32* [[I]], align 4
; CHECK-NEXT: br label [[FOR_COND:%.*]]
; CHECK: for.cond:
; CHECK-NEXT: [[TMP1:%.*]] = load i32, i32* [[I]], align 4
; CHECK-NEXT: [[CMP:%.*]] = icmp slt i32 [[TMP1]], 100
; CHECK-NEXT: br i1 [[CMP]], label [[FOR_BODY:%.*]], label [[FOR_END:%.*]]
; CHECK: for.body:
; CHECK-NEXT: [[TMP2:%.*]] = load i32, i32* [[DOTGLOBAL_TID_]], align 4
; CHECK-NEXT: [[TMP3:%.*]] = bitcast [0 x i8*]* [[CAPTURED_VARS_ADDRS]] to i8**
; CHECK-NEXT: call void @__kmpc_parallel_51(%struct.ident_t* noundef @[[GLOB1]], i32 [[TMP2]], i32 noundef 1, i32 noundef -1, i32 noundef -1, i8* noundef bitcast (void (i32*, i32*)* @__omp_outlined__3 to i8*), i8* noundef bitcast (void (i16, i32)* @__omp_outlined__3_wrapper to i8*), i8** noundef [[TMP3]], i64 noundef 0)
; CHECK-NEXT: br label [[FOR_INC:%.*]]
; CHECK: for.inc:
; CHECK-NEXT: [[TMP4:%.*]] = load i32, i32* [[I]], align 4
; CHECK-NEXT: [[INC:%.*]] = add nsw i32 [[TMP4]], 1
; CHECK-NEXT: store i32 [[INC]], i32* [[I]], align 4
; CHECK-NEXT: br label [[FOR_COND]], !llvm.loop [[LOOP11:![0-9]+]]
; CHECK: for.end:
; CHECK-NEXT: call void @spmd_amenable() #[[ATTR4]]
; CHECK-NEXT: ret void
;
entry:
%.global_tid..addr = alloca i32*, align 8
%.bound_tid..addr = alloca i32*, align 8
%i = alloca i32, align 4
%captured_vars_addrs = alloca [0 x i8*], align 8
store i32* %.global_tid., i32** %.global_tid..addr, align 8
store i32* %.bound_tid., i32** %.bound_tid..addr, align 8
%x = call i8* @__kmpc_alloc_shared(i64 4)
%x_on_stack = bitcast i8* %x to i32*
call void @use(i32* nocapture %x_on_stack) #4
store i32 0, i32* %i, align 4
br label %for.cond
for.cond: ; preds = %for.inc, %entry
%0 = load i32, i32* %i, align 4
%cmp = icmp slt i32 %0, 100
br i1 %cmp, label %for.body, label %for.end
for.body: ; preds = %for.cond
%1 = load i32*, i32** %.global_tid..addr, align 8
%2 = load i32, i32* %1, align 4
%3 = bitcast [0 x i8*]* %captured_vars_addrs to i8**
call void @__kmpc_parallel_51(%struct.ident_t* @1, i32 %2, i32 1, i32 -1, i32 -1, i8* bitcast (void (i32*, i32*)* @__omp_outlined__3 to i8*), i8* bitcast (void (i16, i32)* @__omp_outlined__3_wrapper to i8*), i8** %3, i64 0)
br label %for.inc
for.inc: ; preds = %for.body
%4 = load i32, i32* %i, align 4
%inc = add nsw i32 %4, 1
store i32 %inc, i32* %i, align 4
br label %for.cond, !llvm.loop !11
for.end: ; preds = %for.cond
call void @spmd_amenable() #4
call void @__kmpc_free_shared(i8* %x, i64 4)
ret void
}
declare i8* @__kmpc_alloc_shared(i64) #3
declare void @use(i32* nocapture) #2
define internal void @__omp_outlined__3(i32* noalias %.global_tid., i32* noalias %.bound_tid.) #0 {
; CHECK-LABEL: define {{[^@]+}}@__omp_outlined__3
; CHECK-SAME: (i32* noalias nocapture nofree readnone [[DOTGLOBAL_TID_:%.*]], i32* noalias nocapture nofree readnone [[DOTBOUND_TID_:%.*]]) #[[ATTR0]] {
; CHECK-NEXT: entry:
; CHECK-NEXT: [[DOTGLOBAL_TID__ADDR:%.*]] = alloca i32*, align 8
; CHECK-NEXT: [[DOTBOUND_TID__ADDR:%.*]] = alloca i32*, align 8
; CHECK-NEXT: call void @unknown() #[[ATTR5]]
; CHECK-NEXT: ret void
;
entry:
%.global_tid..addr = alloca i32*, align 8
%.bound_tid..addr = alloca i32*, align 8
store i32* %.global_tid., i32** %.global_tid..addr, align 8
store i32* %.bound_tid., i32** %.bound_tid..addr, align 8
call void @unknown() #5
ret void
}
define internal void @__omp_outlined__3_wrapper(i16 zeroext %0, i32 %1) #0 {
; CHECK-LABEL: define {{[^@]+}}@__omp_outlined__3_wrapper
; CHECK-SAME: (i16 zeroext [[TMP0:%.*]], i32 [[TMP1:%.*]]) #[[ATTR0]] {
; CHECK-NEXT: entry:
; CHECK-NEXT: [[DOTADDR:%.*]] = alloca i16, align 2
; CHECK-NEXT: [[DOTADDR1:%.*]] = alloca i32, align 4
; CHECK-NEXT: [[DOTZERO_ADDR:%.*]] = alloca i32, align 4
; CHECK-NEXT: [[GLOBAL_ARGS:%.*]] = alloca i8**, align 8
; CHECK-NEXT: store i32 0, i32* [[DOTZERO_ADDR]], align 4
; CHECK-NEXT: store i16 [[TMP0]], i16* [[DOTADDR]], align 2
; CHECK-NEXT: store i32 [[TMP1]], i32* [[DOTADDR1]], align 4
; CHECK-NEXT: call void @__kmpc_get_shared_variables(i8*** [[GLOBAL_ARGS]])
; CHECK-NEXT: call void @__omp_outlined__3(i32* [[DOTADDR1]], i32* [[DOTZERO_ADDR]]) #[[ATTR3]]
; CHECK-NEXT: ret void
;
entry:
%.addr = alloca i16, align 2
%.addr1 = alloca i32, align 4
%.zero.addr = alloca i32, align 4
%global_args = alloca i8**, align 8
store i32 0, i32* %.zero.addr, align 4
store i16 %0, i16* %.addr, align 2
store i32 %1, i32* %.addr1, align 4
call void @__kmpc_get_shared_variables(i8*** %global_args)
call void @__omp_outlined__3(i32* %.addr1, i32* %.zero.addr) #3
ret void
}
declare void @__kmpc_free_shared(i8* nocapture, i64) #3
define weak void @__omp_offloading_14_5896c35_sequential_loop_to_shared_var_l35() #0 {
; CHECK-LABEL: define {{[^@]+}}@__omp_offloading_14_5896c35_sequential_loop_to_shared_var_l35
; CHECK-SAME: () #[[ATTR0]] {
; CHECK-NEXT: entry:
; CHECK-NEXT: [[DOTZERO_ADDR:%.*]] = alloca i32, align 4
; CHECK-NEXT: [[DOTTHREADID_TEMP_:%.*]] = alloca i32, align 4
; CHECK-NEXT: [[TMP0:%.*]] = call i32 @__kmpc_target_init(%struct.ident_t* @[[GLOB1]], i1 true, i1 false, i1 false)
; CHECK-NEXT: [[EXEC_USER_CODE:%.*]] = icmp eq i32 [[TMP0]], -1
; CHECK-NEXT: br i1 [[EXEC_USER_CODE]], label [[USER_CODE_ENTRY:%.*]], label [[WORKER_EXIT:%.*]]
; CHECK: user_code.entry:
; CHECK-NEXT: [[TMP1:%.*]] = call i32 @__kmpc_global_thread_num(%struct.ident_t* @[[GLOB1]]) #[[ATTR3]]
; CHECK-NEXT: store i32 [[TMP1]], i32* [[DOTTHREADID_TEMP_]], align 4
; CHECK-NEXT: call void @__omp_outlined__4(i32* noalias nocapture noundef nonnull readonly align 4 dereferenceable(4) [[DOTTHREADID_TEMP_]], i32* noalias nocapture noundef nonnull readnone align 4 dereferenceable(4) [[DOTZERO_ADDR]]) #[[ATTR3]]
; CHECK-NEXT: call void @__kmpc_target_deinit(%struct.ident_t* @[[GLOB1]], i1 true, i1 false)
; CHECK-NEXT: ret void
; CHECK: worker.exit:
; CHECK-NEXT: ret void
;
entry:
%.zero.addr = alloca i32, align 4
%.threadid_temp. = alloca i32, align 4
store i32 0, i32* %.zero.addr, align 4
%0 = call i32 @__kmpc_target_init(%struct.ident_t* @1, i1 false, i1 true, i1 true)
%exec_user_code = icmp eq i32 %0, -1
br i1 %exec_user_code, label %user_code.entry, label %worker.exit
user_code.entry: ; preds = %entry
%1 = call i32 @__kmpc_global_thread_num(%struct.ident_t* @1)
store i32 %1, i32* %.threadid_temp., align 4
call void @__omp_outlined__4(i32* %.threadid_temp., i32* %.zero.addr) #3
call void @__kmpc_target_deinit(%struct.ident_t* @1, i1 false, i1 true)
ret void
worker.exit: ; preds = %entry
ret void
}
define internal void @__omp_outlined__4(i32* noalias %.global_tid., i32* noalias %.bound_tid.) #0 {
; CHECK-LABEL: define {{[^@]+}}@__omp_outlined__4
; CHECK-SAME: (i32* noalias nocapture nofree noundef nonnull readonly align 4 dereferenceable(4) [[DOTGLOBAL_TID_:%.*]], i32* noalias nocapture nofree nonnull readnone align 4 dereferenceable(4) [[DOTBOUND_TID_:%.*]]) #[[ATTR0]] {
; CHECK-NEXT: entry:
; CHECK-NEXT: [[DOTGLOBAL_TID__ADDR:%.*]] = alloca i32*, align 8
; CHECK-NEXT: [[DOTBOUND_TID__ADDR:%.*]] = alloca i32*, align 8
; CHECK-NEXT: [[I:%.*]] = alloca i32, align 4
; CHECK-NEXT: [[CAPTURED_VARS_ADDRS:%.*]] = alloca [1 x i8*], align 8
; CHECK-NEXT: store i32* [[DOTGLOBAL_TID_]], i32** [[DOTGLOBAL_TID__ADDR]], align 8
; CHECK-NEXT: store i32 0, i32* [[I]], align 4
; CHECK-NEXT: br label [[FOR_COND:%.*]]
; CHECK: for.cond:
; CHECK-NEXT: [[TMP0:%.*]] = load i32, i32* [[I]], align 4
; CHECK-NEXT: [[CMP:%.*]] = icmp slt i32 [[TMP0]], 100
; CHECK-NEXT: br i1 [[CMP]], label [[FOR_BODY:%.*]], label [[FOR_END:%.*]]
; CHECK: for.body:
; CHECK-NEXT: [[TMP1:%.*]] = getelementptr inbounds [1 x i8*], [1 x i8*]* [[CAPTURED_VARS_ADDRS]], i64 0, i64 0
; CHECK-NEXT: store i8* addrspacecast (i8 addrspace(3)* getelementptr inbounds ([4 x i8], [4 x i8] addrspace(3)* @x, i32 0, i32 0) to i8*), i8** [[TMP1]], align 8
; CHECK-NEXT: [[TMP2:%.*]] = load i32, i32* [[DOTGLOBAL_TID_]], align 4
; CHECK-NEXT: [[TMP3:%.*]] = bitcast [1 x i8*]* [[CAPTURED_VARS_ADDRS]] to i8**
; CHECK-NEXT: call void @__kmpc_parallel_51(%struct.ident_t* noundef @[[GLOB1]], i32 [[TMP2]], i32 noundef 1, i32 noundef -1, i32 noundef -1, i8* noundef bitcast (void (i32*, i32*, i32*)* @__omp_outlined__5 to i8*), i8* noundef bitcast (void (i16, i32)* @__omp_outlined__5_wrapper to i8*), i8** noundef [[TMP3]], i64 noundef 1)
; CHECK-NEXT: br label [[FOR_INC:%.*]]
; CHECK: for.inc:
; CHECK-NEXT: [[TMP4:%.*]] = load i32, i32* [[I]], align 4
; CHECK-NEXT: [[INC:%.*]] = add nsw i32 [[TMP4]], 1
; CHECK-NEXT: store i32 [[INC]], i32* [[I]], align 4
; CHECK-NEXT: br label [[FOR_COND]], !llvm.loop [[LOOP12:![0-9]+]]
; CHECK: for.end:
; CHECK-NEXT: call void @spmd_amenable() #[[ATTR4]]
; CHECK-NEXT: ret void
;
entry:
%.global_tid..addr = alloca i32*, align 8
%.bound_tid..addr = alloca i32*, align 8
%i = alloca i32, align 4
%captured_vars_addrs = alloca [1 x i8*], align 8
store i32* %.global_tid., i32** %.global_tid..addr, align 8
store i32* %.bound_tid., i32** %.bound_tid..addr, align 8
%x = call i8* @__kmpc_alloc_shared(i64 4)
%x_on_stack = bitcast i8* %x to i32*
store i32 0, i32* %i, align 4
br label %for.cond
for.cond: ; preds = %for.inc, %entry
%0 = load i32, i32* %i, align 4
%cmp = icmp slt i32 %0, 100
br i1 %cmp, label %for.body, label %for.end
for.body: ; preds = %for.cond
%1 = getelementptr inbounds [1 x i8*], [1 x i8*]* %captured_vars_addrs, i64 0, i64 0
%2 = bitcast i32* %x_on_stack to i8*
store i8* %2, i8** %1, align 8
%3 = load i32*, i32** %.global_tid..addr, align 8
%4 = load i32, i32* %3, align 4
%5 = bitcast [1 x i8*]* %captured_vars_addrs to i8**
call void @__kmpc_parallel_51(%struct.ident_t* @1, i32 %4, i32 1, i32 -1, i32 -1, i8* bitcast (void (i32*, i32*, i32*)* @__omp_outlined__5 to i8*), i8* bitcast (void (i16, i32)* @__omp_outlined__5_wrapper to i8*), i8** %5, i64 1)
br label %for.inc
for.inc: ; preds = %for.body
%6 = load i32, i32* %i, align 4
%inc = add nsw i32 %6, 1
store i32 %inc, i32* %i, align 4
br label %for.cond, !llvm.loop !12
for.end: ; preds = %for.cond
call void @spmd_amenable() #4
call void @__kmpc_free_shared(i8* %x, i64 4)
ret void
}
define internal void @__omp_outlined__5(i32* noalias %.global_tid., i32* noalias %.bound_tid., i32* nonnull align 4 dereferenceable(4) %x) #0 {
; CHECK-LABEL: define {{[^@]+}}@__omp_outlined__5
; CHECK-SAME: (i32* noalias nocapture nofree readnone [[DOTGLOBAL_TID_:%.*]], i32* noalias nocapture nofree readnone [[DOTBOUND_TID_:%.*]], i32* nocapture nofree nonnull align 4 dereferenceable(4) [[X:%.*]]) #[[ATTR0]] {
; CHECK-NEXT: entry:
; CHECK-NEXT: [[DOTGLOBAL_TID__ADDR:%.*]] = alloca i32*, align 8
; CHECK-NEXT: [[DOTBOUND_TID__ADDR:%.*]] = alloca i32*, align 8
; CHECK-NEXT: [[X_ADDR:%.*]] = alloca i32*, align 8
; CHECK-NEXT: store i32* [[X]], i32** [[X_ADDR]], align 8
; CHECK-NEXT: [[TMP0:%.*]] = load i32, i32* [[X]], align 4
; CHECK-NEXT: [[INC:%.*]] = add nsw i32 [[TMP0]], 1
; CHECK-NEXT: store i32 [[INC]], i32* [[X]], align 4
; CHECK-NEXT: call void @unknown() #[[ATTR5]]
; CHECK-NEXT: ret void
;
entry:
%.global_tid..addr = alloca i32*, align 8
%.bound_tid..addr = alloca i32*, align 8
%x.addr = alloca i32*, align 8
store i32* %.global_tid., i32** %.global_tid..addr, align 8
store i32* %.bound_tid., i32** %.bound_tid..addr, align 8
store i32* %x, i32** %x.addr, align 8
%0 = load i32*, i32** %x.addr, align 8
%1 = load i32, i32* %0, align 4
%inc = add nsw i32 %1, 1
store i32 %inc, i32* %0, align 4
call void @unknown() #5
ret void
}
define internal void @__omp_outlined__5_wrapper(i16 zeroext %0, i32 %1) #0 {
; CHECK-LABEL: define {{[^@]+}}@__omp_outlined__5_wrapper
; CHECK-SAME: (i16 zeroext [[TMP0:%.*]], i32 [[TMP1:%.*]]) #[[ATTR0]] {
; CHECK-NEXT: entry:
; CHECK-NEXT: [[DOTADDR:%.*]] = alloca i16, align 2
; CHECK-NEXT: [[DOTADDR1:%.*]] = alloca i32, align 4
; CHECK-NEXT: [[DOTZERO_ADDR:%.*]] = alloca i32, align 4
; CHECK-NEXT: [[GLOBAL_ARGS:%.*]] = alloca i8**, align 8
; CHECK-NEXT: store i32 0, i32* [[DOTZERO_ADDR]], align 4
; CHECK-NEXT: store i16 [[TMP0]], i16* [[DOTADDR]], align 2
; CHECK-NEXT: store i32 [[TMP1]], i32* [[DOTADDR1]], align 4
; CHECK-NEXT: call void @__kmpc_get_shared_variables(i8*** [[GLOBAL_ARGS]])
; CHECK-NEXT: [[TMP2:%.*]] = load i8**, i8*** [[GLOBAL_ARGS]], align 8
; CHECK-NEXT: [[TMP3:%.*]] = getelementptr inbounds i8*, i8** [[TMP2]], i64 0
; CHECK-NEXT: [[TMP4:%.*]] = bitcast i8** [[TMP3]] to i32**
; CHECK-NEXT: [[TMP5:%.*]] = load i32*, i32** [[TMP4]], align 8
; CHECK-NEXT: call void @__omp_outlined__5(i32* [[DOTADDR1]], i32* [[DOTZERO_ADDR]], i32* [[TMP5]]) #[[ATTR3]]
; CHECK-NEXT: ret void
;
entry:
%.addr = alloca i16, align 2
%.addr1 = alloca i32, align 4
%.zero.addr = alloca i32, align 4
%global_args = alloca i8**, align 8
store i32 0, i32* %.zero.addr, align 4
store i16 %0, i16* %.addr, align 2
store i32 %1, i32* %.addr1, align 4
call void @__kmpc_get_shared_variables(i8*** %global_args)
%2 = load i8**, i8*** %global_args, align 8
%3 = getelementptr inbounds i8*, i8** %2, i64 0
%4 = bitcast i8** %3 to i32**
%5 = load i32*, i32** %4, align 8
call void @__omp_outlined__5(i32* %.addr1, i32* %.zero.addr, i32* %5) #3
ret void
}
attributes #0 = { convergent noinline norecurse nounwind "frame-pointer"="none" "min-legal-vector-width"="0" "no-trapping-math"="true" "stack-protector-buffer-size"="8" "target-features"="+ptx32,+sm_20" }
attributes #1 = { convergent "frame-pointer"="none" "no-trapping-math"="true" "stack-protector-buffer-size"="8" "target-features"="+ptx32,+sm_20" }
attributes #2 = { convergent "frame-pointer"="none" "llvm.assume"="ompx_spmd_amenable" "no-trapping-math"="true" "stack-protector-buffer-size"="8" "target-features"="+ptx32,+sm_20" }
attributes #3 = { nounwind }
attributes #4 = { convergent "llvm.assume"="ompx_spmd_amenable" }
attributes #5 = { convergent }
!omp_offload.info = !{!0, !1, !2}
!nvvm.annotations = !{!3, !4, !5}
!llvm.module.flags = !{!6, !7, !8}
!0 = !{i32 0, i32 20, i32 92892213, !"sequential_loop_to_stack_var", i32 20, i32 1}
!1 = !{i32 0, i32 20, i32 92892213, !"sequential_loop", i32 5, i32 0}
!2 = !{i32 0, i32 20, i32 92892213, !"sequential_loop_to_shared_var", i32 35, i32 2}
!3 = !{void ()* @__omp_offloading_14_5896c35_sequential_loop_l5, !"kernel", i32 1}
!4 = !{void ()* @__omp_offloading_14_5896c35_sequential_loop_to_stack_var_l20, !"kernel", i32 1}
!5 = !{void ()* @__omp_offloading_14_5896c35_sequential_loop_to_shared_var_l35, !"kernel", i32 1}
!6 = !{i32 1, !"wchar_size", i32 4}
!7 = !{i32 7, !"openmp", i32 50}
!8 = !{i32 7, !"openmp-device", i32 50}
!9 = distinct !{!9, !10}
!10 = !{!"llvm.loop.mustprogress"}
!11 = distinct !{!11, !10}
!12 = distinct !{!12, !10}
;.
; CHECK: attributes #[[ATTR0]] = { convergent noinline norecurse nounwind "frame-pointer"="none" "min-legal-vector-width"="0" "no-trapping-math"="true" "stack-protector-buffer-size"="8" "target-features"="+ptx32,+sm_20" }
; CHECK: attributes #[[ATTR1:[0-9]+]] = { convergent "frame-pointer"="none" "no-trapping-math"="true" "stack-protector-buffer-size"="8" "target-features"="+ptx32,+sm_20" }
; CHECK: attributes #[[ATTR2:[0-9]+]] = { convergent "frame-pointer"="none" "llvm.assume"="ompx_spmd_amenable" "no-trapping-math"="true" "stack-protector-buffer-size"="8" "target-features"="+ptx32,+sm_20" }
; CHECK: attributes #[[ATTR3]] = { nounwind }
; CHECK: attributes #[[ATTR4]] = { convergent "llvm.assume"="ompx_spmd_amenable" }
; CHECK: attributes #[[ATTR5]] = { convergent }
;.
; CHECK: [[META0:![0-9]+]] = !{i32 0, i32 20, i32 92892213, !"sequential_loop_to_stack_var", i32 20, i32 1}
; CHECK: [[META1:![0-9]+]] = !{i32 0, i32 20, i32 92892213, !"sequential_loop", i32 5, i32 0}
; CHECK: [[META2:![0-9]+]] = !{i32 0, i32 20, i32 92892213, !"sequential_loop_to_shared_var", i32 35, i32 2}
; CHECK: [[META3:![0-9]+]] = !{void ()* @__omp_offloading_14_5896c35_sequential_loop_l5, !"kernel", i32 1}
; CHECK: [[META4:![0-9]+]] = !{void ()* @__omp_offloading_14_5896c35_sequential_loop_to_stack_var_l20, !"kernel", i32 1}
; CHECK: [[META5:![0-9]+]] = !{void ()* @__omp_offloading_14_5896c35_sequential_loop_to_shared_var_l35, !"kernel", i32 1}
; CHECK: [[META6:![0-9]+]] = !{i32 1, !"wchar_size", i32 4}
; CHECK: [[META7:![0-9]+]] = !{i32 7, !"openmp", i32 50}
; CHECK: [[META8:![0-9]+]] = !{i32 7, !"openmp-device", i32 50}
; CHECK: [[LOOP9]] = distinct !{!9, !10}
; CHECK: [[META10:![0-9]+]] = !{!"llvm.loop.mustprogress"}
; CHECK: [[LOOP11]] = distinct !{!11, !10}
; CHECK: [[LOOP12]] = distinct !{!12, !10}
;.
|
