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
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
|
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -mtriple=riscv32 -verify-machineinstrs < %s \
; RUN: | FileCheck -check-prefix=RV32I %s
; As well as calling convention details, we check that ra and fp are
; consistently stored to fp-4 and fp-8.
; Check that on RV32, i64 and double are passed in a pair of registers. Unlike
; the convention for varargs, this need not be an aligned pair.
define i32 @callee_scalars(i32 %a, i64 %b, i32 %c, i32 %d, double %e) nounwind {
; RV32I-LABEL: callee_scalars:
; RV32I: # %bb.0:
; RV32I-NEXT: addi sp, sp, -32
; RV32I-NEXT: sw ra, 28(sp)
; RV32I-NEXT: sw s0, 24(sp)
; RV32I-NEXT: sw s1, 20(sp)
; RV32I-NEXT: sw s2, 16(sp)
; RV32I-NEXT: sw s3, 12(sp)
; RV32I-NEXT: sw s4, 8(sp)
; RV32I-NEXT: addi s0, sp, 32
; RV32I-NEXT: mv s1, a4
; RV32I-NEXT: mv s2, a3
; RV32I-NEXT: mv s3, a1
; RV32I-NEXT: mv s4, a0
; RV32I-NEXT: lui a0, %hi(__fixdfsi)
; RV32I-NEXT: addi a2, a0, %lo(__fixdfsi)
; RV32I-NEXT: mv a0, a5
; RV32I-NEXT: mv a1, a6
; RV32I-NEXT: jalr a2
; RV32I-NEXT: add a1, s4, s3
; RV32I-NEXT: add a1, a1, s2
; RV32I-NEXT: add a1, a1, s1
; RV32I-NEXT: add a0, a1, a0
; RV32I-NEXT: lw s4, 8(sp)
; RV32I-NEXT: lw s3, 12(sp)
; RV32I-NEXT: lw s2, 16(sp)
; RV32I-NEXT: lw s1, 20(sp)
; RV32I-NEXT: lw s0, 24(sp)
; RV32I-NEXT: lw ra, 28(sp)
; RV32I-NEXT: addi sp, sp, 32
; RV32I-NEXT: ret
%b_trunc = trunc i64 %b to i32
%e_fptosi = fptosi double %e to i32
%1 = add i32 %a, %b_trunc
%2 = add i32 %1, %c
%3 = add i32 %2, %d
%4 = add i32 %3, %e_fptosi
ret i32 %4
}
define i32 @caller_scalars() nounwind {
; RV32I-LABEL: caller_scalars:
; RV32I: # %bb.0:
; RV32I-NEXT: addi sp, sp, -16
; RV32I-NEXT: sw ra, 12(sp)
; RV32I-NEXT: sw s0, 8(sp)
; RV32I-NEXT: addi s0, sp, 16
; RV32I-NEXT: lui a0, 262464
; RV32I-NEXT: mv a6, a0
; RV32I-NEXT: lui a0, %hi(callee_scalars)
; RV32I-NEXT: addi a7, a0, %lo(callee_scalars)
; RV32I-NEXT: addi a0, zero, 1
; RV32I-NEXT: addi a1, zero, 2
; RV32I-NEXT: addi a3, zero, 3
; RV32I-NEXT: addi a4, zero, 4
; RV32I-NEXT: mv a2, zero
; RV32I-NEXT: mv a5, zero
; RV32I-NEXT: jalr a7
; RV32I-NEXT: lw s0, 8(sp)
; RV32I-NEXT: lw ra, 12(sp)
; RV32I-NEXT: addi sp, sp, 16
; RV32I-NEXT: ret
%1 = call i32 @callee_scalars(i32 1, i64 2, i32 3, i32 4, double 5.000000e+00)
ret i32 %1
}
; Check that i128 and fp128 are passed indirectly
define i32 @callee_large_scalars(i128 %a, fp128 %b) nounwind {
; RV32I-LABEL: callee_large_scalars:
; RV32I: # %bb.0:
; RV32I-NEXT: addi sp, sp, -16
; RV32I-NEXT: sw ra, 12(sp)
; RV32I-NEXT: sw s0, 8(sp)
; RV32I-NEXT: addi s0, sp, 16
; RV32I-NEXT: lw a2, 12(a1)
; RV32I-NEXT: lw a3, 12(a0)
; RV32I-NEXT: xor a2, a3, a2
; RV32I-NEXT: lw a3, 4(a1)
; RV32I-NEXT: lw a4, 4(a0)
; RV32I-NEXT: xor a3, a4, a3
; RV32I-NEXT: or a2, a3, a2
; RV32I-NEXT: lw a3, 8(a1)
; RV32I-NEXT: lw a4, 8(a0)
; RV32I-NEXT: xor a3, a4, a3
; RV32I-NEXT: lw a1, 0(a1)
; RV32I-NEXT: lw a0, 0(a0)
; RV32I-NEXT: xor a0, a0, a1
; RV32I-NEXT: or a0, a0, a3
; RV32I-NEXT: or a0, a0, a2
; RV32I-NEXT: xor a0, a0, zero
; RV32I-NEXT: seqz a0, a0
; RV32I-NEXT: lw s0, 8(sp)
; RV32I-NEXT: lw ra, 12(sp)
; RV32I-NEXT: addi sp, sp, 16
; RV32I-NEXT: ret
%b_bitcast = bitcast fp128 %b to i128
%1 = icmp eq i128 %a, %b_bitcast
%2 = zext i1 %1 to i32
ret i32 %2
}
define i32 @caller_large_scalars() nounwind {
; RV32I-LABEL: caller_large_scalars:
; RV32I: # %bb.0:
; RV32I-NEXT: addi sp, sp, -48
; RV32I-NEXT: sw ra, 44(sp)
; RV32I-NEXT: sw s0, 40(sp)
; RV32I-NEXT: addi s0, sp, 48
; RV32I-NEXT: sw zero, -40(s0)
; RV32I-NEXT: sw zero, -44(s0)
; RV32I-NEXT: sw zero, -48(s0)
; RV32I-NEXT: sw zero, -12(s0)
; RV32I-NEXT: sw zero, -16(s0)
; RV32I-NEXT: sw zero, -20(s0)
; RV32I-NEXT: addi a0, zero, 1
; RV32I-NEXT: sw a0, -24(s0)
; RV32I-NEXT: lui a0, 524272
; RV32I-NEXT: mv a0, a0
; RV32I-NEXT: sw a0, -36(s0)
; RV32I-NEXT: lui a0, %hi(callee_large_scalars)
; RV32I-NEXT: addi a2, a0, %lo(callee_large_scalars)
; RV32I-NEXT: addi a0, s0, -24
; RV32I-NEXT: addi a1, s0, -48
; RV32I-NEXT: jalr a2
; RV32I-NEXT: lw s0, 40(sp)
; RV32I-NEXT: lw ra, 44(sp)
; RV32I-NEXT: addi sp, sp, 48
; RV32I-NEXT: ret
%1 = call i32 @callee_large_scalars(i128 1, fp128 0xL00000000000000007FFF000000000000)
ret i32 %1
}
; Must keep define on a single line due to an update_llc_test_checks.py limitation
define i32 @callee_large_scalars_exhausted_regs(i32 %a, i32 %b, i32 %c, i32 %d, i32 %e, i32 %f, i32 %g, i128 %h, i32 %i, fp128 %j) nounwind {
; Check that arguments larger than 2*xlen are handled correctly when their
; address is passed on the stack rather than in memory
; RV32I-LABEL: callee_large_scalars_exhausted_regs:
; RV32I: # %bb.0:
; RV32I-NEXT: addi sp, sp, -16
; RV32I-NEXT: sw ra, 12(sp)
; RV32I-NEXT: sw s0, 8(sp)
; RV32I-NEXT: addi s0, sp, 16
; RV32I-NEXT: lw a0, 4(s0)
; RV32I-NEXT: lw a1, 12(a0)
; RV32I-NEXT: lw a2, 12(a7)
; RV32I-NEXT: xor a1, a2, a1
; RV32I-NEXT: lw a2, 4(a0)
; RV32I-NEXT: lw a3, 4(a7)
; RV32I-NEXT: xor a2, a3, a2
; RV32I-NEXT: or a1, a2, a1
; RV32I-NEXT: lw a2, 8(a0)
; RV32I-NEXT: lw a3, 8(a7)
; RV32I-NEXT: xor a2, a3, a2
; RV32I-NEXT: lw a0, 0(a0)
; RV32I-NEXT: lw a3, 0(a7)
; RV32I-NEXT: xor a0, a3, a0
; RV32I-NEXT: or a0, a0, a2
; RV32I-NEXT: or a0, a0, a1
; RV32I-NEXT: xor a0, a0, zero
; RV32I-NEXT: seqz a0, a0
; RV32I-NEXT: lw s0, 8(sp)
; RV32I-NEXT: lw ra, 12(sp)
; RV32I-NEXT: addi sp, sp, 16
; RV32I-NEXT: ret
%j_bitcast = bitcast fp128 %j to i128
%1 = icmp eq i128 %h, %j_bitcast
%2 = zext i1 %1 to i32
ret i32 %2
}
define i32 @caller_large_scalars_exhausted_regs() nounwind {
; RV32I-LABEL: caller_large_scalars_exhausted_regs:
; RV32I: # %bb.0:
; RV32I-NEXT: addi sp, sp, -64
; RV32I-NEXT: sw ra, 60(sp)
; RV32I-NEXT: sw s0, 56(sp)
; RV32I-NEXT: addi s0, sp, 64
; RV32I-NEXT: addi a0, s0, -48
; RV32I-NEXT: sw a0, 4(sp)
; RV32I-NEXT: addi a0, zero, 9
; RV32I-NEXT: sw a0, 0(sp)
; RV32I-NEXT: sw zero, -40(s0)
; RV32I-NEXT: sw zero, -44(s0)
; RV32I-NEXT: sw zero, -48(s0)
; RV32I-NEXT: sw zero, -12(s0)
; RV32I-NEXT: sw zero, -16(s0)
; RV32I-NEXT: sw zero, -20(s0)
; RV32I-NEXT: addi a0, zero, 8
; RV32I-NEXT: sw a0, -24(s0)
; RV32I-NEXT: lui a0, 524272
; RV32I-NEXT: mv a0, a0
; RV32I-NEXT: sw a0, -36(s0)
; RV32I-NEXT: lui a0, %hi(callee_large_scalars_exhausted_regs)
; RV32I-NEXT: addi t0, a0, %lo(callee_large_scalars_exhausted_regs)
; RV32I-NEXT: addi a0, zero, 1
; RV32I-NEXT: addi a1, zero, 2
; RV32I-NEXT: addi a2, zero, 3
; RV32I-NEXT: addi a3, zero, 4
; RV32I-NEXT: addi a4, zero, 5
; RV32I-NEXT: addi a5, zero, 6
; RV32I-NEXT: addi a6, zero, 7
; RV32I-NEXT: addi a7, s0, -24
; RV32I-NEXT: jalr t0
; RV32I-NEXT: lw s0, 56(sp)
; RV32I-NEXT: lw ra, 60(sp)
; RV32I-NEXT: addi sp, sp, 64
; RV32I-NEXT: ret
%1 = call i32 @callee_large_scalars_exhausted_regs(
i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i128 8, i32 9,
fp128 0xL00000000000000007FFF000000000000)
ret i32 %1
}
; Ensure that libcalls generated in the middle-end obey the calling convention
define i32 @caller_mixed_scalar_libcalls(i64 %a) nounwind {
; RV32I-LABEL: caller_mixed_scalar_libcalls:
; RV32I: # %bb.0:
; RV32I-NEXT: addi sp, sp, -32
; RV32I-NEXT: sw ra, 28(sp)
; RV32I-NEXT: sw s0, 24(sp)
; RV32I-NEXT: addi s0, sp, 32
; RV32I-NEXT: mv a2, a1
; RV32I-NEXT: mv a1, a0
; RV32I-NEXT: lui a0, %hi(__floatditf)
; RV32I-NEXT: addi a3, a0, %lo(__floatditf)
; RV32I-NEXT: addi a0, s0, -24
; RV32I-NEXT: jalr a3
; RV32I-NEXT: lw a0, -24(s0)
; RV32I-NEXT: lw s0, 24(sp)
; RV32I-NEXT: lw ra, 28(sp)
; RV32I-NEXT: addi sp, sp, 32
; RV32I-NEXT: ret
%1 = sitofp i64 %a to fp128
%2 = bitcast fp128 %1 to i128
%3 = trunc i128 %2 to i32
ret i32 %3
}
; Check that the stack is used once the GPRs are exhausted
define i32 @callee_many_scalars(i8 %a, i16 %b, i32 %c, i64 %d, i32 %e, i32 %f, i64 %g, i32 %h) nounwind {
; RV32I-LABEL: callee_many_scalars:
; RV32I: # %bb.0:
; RV32I-NEXT: addi sp, sp, -16
; RV32I-NEXT: sw ra, 12(sp)
; RV32I-NEXT: sw s0, 8(sp)
; RV32I-NEXT: addi s0, sp, 16
; RV32I-NEXT: lw t0, 0(s0)
; RV32I-NEXT: xor a4, a4, t0
; RV32I-NEXT: xor a3, a3, a7
; RV32I-NEXT: or a3, a3, a4
; RV32I-NEXT: xor a3, a3, zero
; RV32I-NEXT: lui a4, 16
; RV32I-NEXT: addi a4, a4, -1
; RV32I-NEXT: and a1, a1, a4
; RV32I-NEXT: andi a0, a0, 255
; RV32I-NEXT: add a0, a0, a1
; RV32I-NEXT: add a0, a0, a2
; RV32I-NEXT: seqz a1, a3
; RV32I-NEXT: add a0, a1, a0
; RV32I-NEXT: add a0, a0, a5
; RV32I-NEXT: add a0, a0, a6
; RV32I-NEXT: lw a1, 4(s0)
; RV32I-NEXT: add a0, a0, a1
; RV32I-NEXT: lw s0, 8(sp)
; RV32I-NEXT: lw ra, 12(sp)
; RV32I-NEXT: addi sp, sp, 16
; RV32I-NEXT: ret
%a_ext = zext i8 %a to i32
%b_ext = zext i16 %b to i32
%1 = add i32 %a_ext, %b_ext
%2 = add i32 %1, %c
%3 = icmp eq i64 %d, %g
%4 = zext i1 %3 to i32
%5 = add i32 %4, %2
%6 = add i32 %5, %e
%7 = add i32 %6, %f
%8 = add i32 %7, %h
ret i32 %8
}
define i32 @caller_many_scalars() nounwind {
; RV32I-LABEL: caller_many_scalars:
; RV32I: # %bb.0:
; RV32I-NEXT: addi sp, sp, -32
; RV32I-NEXT: sw ra, 28(sp)
; RV32I-NEXT: sw s0, 24(sp)
; RV32I-NEXT: addi s0, sp, 32
; RV32I-NEXT: addi a0, zero, 8
; RV32I-NEXT: sw a0, 4(sp)
; RV32I-NEXT: sw zero, 0(sp)
; RV32I-NEXT: lui a0, %hi(callee_many_scalars)
; RV32I-NEXT: addi t0, a0, %lo(callee_many_scalars)
; RV32I-NEXT: addi a0, zero, 1
; RV32I-NEXT: addi a1, zero, 2
; RV32I-NEXT: addi a2, zero, 3
; RV32I-NEXT: addi a3, zero, 4
; RV32I-NEXT: addi a5, zero, 5
; RV32I-NEXT: addi a6, zero, 6
; RV32I-NEXT: addi a7, zero, 7
; RV32I-NEXT: mv a4, zero
; RV32I-NEXT: jalr t0
; RV32I-NEXT: lw s0, 24(sp)
; RV32I-NEXT: lw ra, 28(sp)
; RV32I-NEXT: addi sp, sp, 32
; RV32I-NEXT: ret
%1 = call i32 @callee_many_scalars(i8 1, i16 2, i32 3, i64 4, i32 5, i32 6, i64 7, i32 8)
ret i32 %1
}
; Check passing of coerced integer arrays
%struct.small = type { i32, i32* }
define i32 @callee_small_coerced_struct([2 x i32] %a.coerce) nounwind {
; RV32I-LABEL: callee_small_coerced_struct:
; RV32I: # %bb.0:
; RV32I-NEXT: addi sp, sp, -16
; RV32I-NEXT: sw ra, 12(sp)
; RV32I-NEXT: sw s0, 8(sp)
; RV32I-NEXT: addi s0, sp, 16
; RV32I-NEXT: xor a0, a0, a1
; RV32I-NEXT: seqz a0, a0
; RV32I-NEXT: lw s0, 8(sp)
; RV32I-NEXT: lw ra, 12(sp)
; RV32I-NEXT: addi sp, sp, 16
; RV32I-NEXT: ret
%1 = extractvalue [2 x i32] %a.coerce, 0
%2 = extractvalue [2 x i32] %a.coerce, 1
%3 = icmp eq i32 %1, %2
%4 = zext i1 %3 to i32
ret i32 %4
}
define i32 @caller_small_coerced_struct() nounwind {
; RV32I-LABEL: caller_small_coerced_struct:
; RV32I: # %bb.0:
; RV32I-NEXT: addi sp, sp, -16
; RV32I-NEXT: sw ra, 12(sp)
; RV32I-NEXT: sw s0, 8(sp)
; RV32I-NEXT: addi s0, sp, 16
; RV32I-NEXT: lui a0, %hi(callee_small_coerced_struct)
; RV32I-NEXT: addi a2, a0, %lo(callee_small_coerced_struct)
; RV32I-NEXT: addi a0, zero, 1
; RV32I-NEXT: addi a1, zero, 2
; RV32I-NEXT: jalr a2
; RV32I-NEXT: lw s0, 8(sp)
; RV32I-NEXT: lw ra, 12(sp)
; RV32I-NEXT: addi sp, sp, 16
; RV32I-NEXT: ret
%1 = call i32 @callee_small_coerced_struct([2 x i32] [i32 1, i32 2])
ret i32 %1
}
; Check large struct arguments, which are passed byval
%struct.large = type { i32, i32, i32, i32 }
define i32 @callee_large_struct(%struct.large* byval align 4 %a) nounwind {
; RV32I-LABEL: callee_large_struct:
; RV32I: # %bb.0:
; RV32I-NEXT: addi sp, sp, -16
; RV32I-NEXT: sw ra, 12(sp)
; RV32I-NEXT: sw s0, 8(sp)
; RV32I-NEXT: addi s0, sp, 16
; RV32I-NEXT: lw a1, 12(a0)
; RV32I-NEXT: lw a0, 0(a0)
; RV32I-NEXT: add a0, a0, a1
; RV32I-NEXT: lw s0, 8(sp)
; RV32I-NEXT: lw ra, 12(sp)
; RV32I-NEXT: addi sp, sp, 16
; RV32I-NEXT: ret
%1 = getelementptr inbounds %struct.large, %struct.large* %a, i32 0, i32 0
%2 = getelementptr inbounds %struct.large, %struct.large* %a, i32 0, i32 3
%3 = load i32, i32* %1
%4 = load i32, i32* %2
%5 = add i32 %3, %4
ret i32 %5
}
define i32 @caller_large_struct() nounwind {
; RV32I-LABEL: caller_large_struct:
; RV32I: # %bb.0:
; RV32I-NEXT: addi sp, sp, -48
; RV32I-NEXT: sw ra, 44(sp)
; RV32I-NEXT: sw s0, 40(sp)
; RV32I-NEXT: addi s0, sp, 48
; RV32I-NEXT: addi a0, zero, 1
; RV32I-NEXT: sw a0, -24(s0)
; RV32I-NEXT: sw a0, -40(s0)
; RV32I-NEXT: addi a0, zero, 2
; RV32I-NEXT: sw a0, -20(s0)
; RV32I-NEXT: sw a0, -36(s0)
; RV32I-NEXT: addi a0, zero, 3
; RV32I-NEXT: sw a0, -16(s0)
; RV32I-NEXT: sw a0, -32(s0)
; RV32I-NEXT: addi a0, zero, 4
; RV32I-NEXT: sw a0, -12(s0)
; RV32I-NEXT: sw a0, -28(s0)
; RV32I-NEXT: lui a0, %hi(callee_large_struct)
; RV32I-NEXT: addi a1, a0, %lo(callee_large_struct)
; RV32I-NEXT: addi a0, s0, -40
; RV32I-NEXT: jalr a1
; RV32I-NEXT: lw s0, 40(sp)
; RV32I-NEXT: lw ra, 44(sp)
; RV32I-NEXT: addi sp, sp, 48
; RV32I-NEXT: ret
%ls = alloca %struct.large, align 4
%1 = bitcast %struct.large* %ls to i8*
%a = getelementptr inbounds %struct.large, %struct.large* %ls, i32 0, i32 0
store i32 1, i32* %a
%b = getelementptr inbounds %struct.large, %struct.large* %ls, i32 0, i32 1
store i32 2, i32* %b
%c = getelementptr inbounds %struct.large, %struct.large* %ls, i32 0, i32 2
store i32 3, i32* %c
%d = getelementptr inbounds %struct.large, %struct.large* %ls, i32 0, i32 3
store i32 4, i32* %d
%2 = call i32 @callee_large_struct(%struct.large* byval align 4 %ls)
ret i32 %2
}
; Check 2x*xlen values are aligned appropriately when passed on the stack
; Must keep define on a single line due to an update_llc_test_checks.py limitation
define i32 @callee_aligned_stack(i32 %a, i32 %b, fp128 %c, i32 %d, i32 %e, i64 %f, i32 %g, i32 %h, double %i, i32 %j, [2 x i32] %k) nounwind {
; The double should be 8-byte aligned on the stack, but the two-element array
; should only be 4-byte aligned
; RV32I-LABEL: callee_aligned_stack:
; RV32I: # %bb.0:
; RV32I-NEXT: addi sp, sp, -16
; RV32I-NEXT: sw ra, 12(sp)
; RV32I-NEXT: sw s0, 8(sp)
; RV32I-NEXT: addi s0, sp, 16
; RV32I-NEXT: lw a0, 0(a2)
; RV32I-NEXT: add a0, a0, a7
; RV32I-NEXT: lw a1, 0(s0)
; RV32I-NEXT: add a0, a0, a1
; RV32I-NEXT: lw a1, 8(s0)
; RV32I-NEXT: add a0, a0, a1
; RV32I-NEXT: lw a1, 16(s0)
; RV32I-NEXT: add a0, a0, a1
; RV32I-NEXT: lw a1, 20(s0)
; RV32I-NEXT: add a0, a0, a1
; RV32I-NEXT: lw s0, 8(sp)
; RV32I-NEXT: lw ra, 12(sp)
; RV32I-NEXT: addi sp, sp, 16
; RV32I-NEXT: ret
%1 = bitcast fp128 %c to i128
%2 = trunc i128 %1 to i32
%3 = add i32 %2, %g
%4 = add i32 %3, %h
%5 = bitcast double %i to i64
%6 = trunc i64 %5 to i32
%7 = add i32 %4, %6
%8 = add i32 %7, %j
%9 = extractvalue [2 x i32] %k, 0
%10 = add i32 %8, %9
ret i32 %10
}
define void @caller_aligned_stack() nounwind {
; The double should be 8-byte aligned on the stack, but the two-element array
; should only be 4-byte aligned
; RV32I-LABEL: caller_aligned_stack:
; RV32I: # %bb.0:
; RV32I-NEXT: addi sp, sp, -64
; RV32I-NEXT: sw ra, 60(sp)
; RV32I-NEXT: sw s0, 56(sp)
; RV32I-NEXT: addi s0, sp, 64
; RV32I-NEXT: addi a0, zero, 18
; RV32I-NEXT: sw a0, 24(sp)
; RV32I-NEXT: addi a0, zero, 17
; RV32I-NEXT: sw a0, 20(sp)
; RV32I-NEXT: addi a0, zero, 16
; RV32I-NEXT: sw a0, 16(sp)
; RV32I-NEXT: lui a0, 262236
; RV32I-NEXT: addi a0, a0, 655
; RV32I-NEXT: sw a0, 12(sp)
; RV32I-NEXT: lui a0, 377487
; RV32I-NEXT: addi a0, a0, 1475
; RV32I-NEXT: sw a0, 8(sp)
; RV32I-NEXT: addi a0, zero, 15
; RV32I-NEXT: sw a0, 0(sp)
; RV32I-NEXT: lui a0, 262153
; RV32I-NEXT: addi a0, a0, 491
; RV32I-NEXT: sw a0, -20(s0)
; RV32I-NEXT: lui a0, 545260
; RV32I-NEXT: addi a0, a0, -1967
; RV32I-NEXT: sw a0, -24(s0)
; RV32I-NEXT: lui a0, 964690
; RV32I-NEXT: addi a0, a0, -328
; RV32I-NEXT: sw a0, -28(s0)
; RV32I-NEXT: lui a0, 335544
; RV32I-NEXT: addi a0, a0, 1311
; RV32I-NEXT: sw a0, -32(s0)
; RV32I-NEXT: lui a0, 688509
; RV32I-NEXT: addi a5, a0, -2048
; RV32I-NEXT: lui a0, %hi(callee_aligned_stack)
; RV32I-NEXT: addi t0, a0, %lo(callee_aligned_stack)
; RV32I-NEXT: addi a0, zero, 1
; RV32I-NEXT: addi a1, zero, 11
; RV32I-NEXT: addi a2, s0, -32
; RV32I-NEXT: addi a3, zero, 12
; RV32I-NEXT: addi a4, zero, 13
; RV32I-NEXT: addi a6, zero, 4
; RV32I-NEXT: addi a7, zero, 14
; RV32I-NEXT: jalr t0
; RV32I-NEXT: lw s0, 56(sp)
; RV32I-NEXT: lw ra, 60(sp)
; RV32I-NEXT: addi sp, sp, 64
; RV32I-NEXT: ret
%1 = call i32 @callee_aligned_stack(i32 1, i32 11,
fp128 0xLEB851EB851EB851F400091EB851EB851, i32 12, i32 13,
i64 20000000000, i32 14, i32 15, double 2.720000e+00, i32 16,
[2 x i32] [i32 17, i32 18])
ret void
}
; Check return of 2x xlen scalars
define i64 @callee_small_scalar_ret() nounwind {
; RV32I-LABEL: callee_small_scalar_ret:
; RV32I: # %bb.0:
; RV32I-NEXT: addi sp, sp, -16
; RV32I-NEXT: sw ra, 12(sp)
; RV32I-NEXT: sw s0, 8(sp)
; RV32I-NEXT: addi s0, sp, 16
; RV32I-NEXT: lui a0, 466866
; RV32I-NEXT: addi a0, a0, 1677
; RV32I-NEXT: addi a1, zero, 287
; RV32I-NEXT: lw s0, 8(sp)
; RV32I-NEXT: lw ra, 12(sp)
; RV32I-NEXT: addi sp, sp, 16
; RV32I-NEXT: ret
ret i64 1234567898765
}
define i32 @caller_small_scalar_ret() nounwind {
; RV32I-LABEL: caller_small_scalar_ret:
; RV32I: # %bb.0:
; RV32I-NEXT: addi sp, sp, -16
; RV32I-NEXT: sw ra, 12(sp)
; RV32I-NEXT: sw s0, 8(sp)
; RV32I-NEXT: addi s0, sp, 16
; RV32I-NEXT: lui a0, %hi(callee_small_scalar_ret)
; RV32I-NEXT: addi a0, a0, %lo(callee_small_scalar_ret)
; RV32I-NEXT: jalr a0
; RV32I-NEXT: lui a2, 56
; RV32I-NEXT: addi a2, a2, 580
; RV32I-NEXT: xor a1, a1, a2
; RV32I-NEXT: lui a2, 200614
; RV32I-NEXT: addi a2, a2, 647
; RV32I-NEXT: xor a0, a0, a2
; RV32I-NEXT: or a0, a0, a1
; RV32I-NEXT: xor a0, a0, zero
; RV32I-NEXT: seqz a0, a0
; RV32I-NEXT: lw s0, 8(sp)
; RV32I-NEXT: lw ra, 12(sp)
; RV32I-NEXT: addi sp, sp, 16
; RV32I-NEXT: ret
%1 = call i64 @callee_small_scalar_ret()
%2 = icmp eq i64 987654321234567, %1
%3 = zext i1 %2 to i32
ret i32 %3
}
; Check return of 2x xlen structs
define %struct.small @callee_small_struct_ret() nounwind {
; RV32I-LABEL: callee_small_struct_ret:
; RV32I: # %bb.0:
; RV32I-NEXT: addi sp, sp, -16
; RV32I-NEXT: sw ra, 12(sp)
; RV32I-NEXT: sw s0, 8(sp)
; RV32I-NEXT: addi s0, sp, 16
; RV32I-NEXT: addi a0, zero, 1
; RV32I-NEXT: mv a1, zero
; RV32I-NEXT: lw s0, 8(sp)
; RV32I-NEXT: lw ra, 12(sp)
; RV32I-NEXT: addi sp, sp, 16
; RV32I-NEXT: ret
ret %struct.small { i32 1, i32* null }
}
define i32 @caller_small_struct_ret() nounwind {
; RV32I-LABEL: caller_small_struct_ret:
; RV32I: # %bb.0:
; RV32I-NEXT: addi sp, sp, -16
; RV32I-NEXT: sw ra, 12(sp)
; RV32I-NEXT: sw s0, 8(sp)
; RV32I-NEXT: addi s0, sp, 16
; RV32I-NEXT: lui a0, %hi(callee_small_struct_ret)
; RV32I-NEXT: addi a0, a0, %lo(callee_small_struct_ret)
; RV32I-NEXT: jalr a0
; RV32I-NEXT: add a0, a0, a1
; RV32I-NEXT: lw s0, 8(sp)
; RV32I-NEXT: lw ra, 12(sp)
; RV32I-NEXT: addi sp, sp, 16
; RV32I-NEXT: ret
%1 = call %struct.small @callee_small_struct_ret()
%2 = extractvalue %struct.small %1, 0
%3 = extractvalue %struct.small %1, 1
%4 = ptrtoint i32* %3 to i32
%5 = add i32 %2, %4
ret i32 %5
}
; Check return of >2x xlen scalars
define fp128 @callee_large_scalar_ret() nounwind {
; RV32I-LABEL: callee_large_scalar_ret:
; RV32I: # %bb.0:
; RV32I-NEXT: addi sp, sp, -16
; RV32I-NEXT: sw ra, 12(sp)
; RV32I-NEXT: sw s0, 8(sp)
; RV32I-NEXT: addi s0, sp, 16
; RV32I-NEXT: lui a1, 524272
; RV32I-NEXT: mv a1, a1
; RV32I-NEXT: sw a1, 12(a0)
; RV32I-NEXT: sw zero, 8(a0)
; RV32I-NEXT: sw zero, 4(a0)
; RV32I-NEXT: sw zero, 0(a0)
; RV32I-NEXT: lw s0, 8(sp)
; RV32I-NEXT: lw ra, 12(sp)
; RV32I-NEXT: addi sp, sp, 16
; RV32I-NEXT: ret
ret fp128 0xL00000000000000007FFF000000000000
}
define void @caller_large_scalar_ret() nounwind {
; RV32I-LABEL: caller_large_scalar_ret:
; RV32I: # %bb.0:
; RV32I-NEXT: addi sp, sp, -32
; RV32I-NEXT: sw ra, 28(sp)
; RV32I-NEXT: sw s0, 24(sp)
; RV32I-NEXT: addi s0, sp, 32
; RV32I-NEXT: lui a0, %hi(callee_large_scalar_ret)
; RV32I-NEXT: addi a1, a0, %lo(callee_large_scalar_ret)
; RV32I-NEXT: addi a0, s0, -32
; RV32I-NEXT: jalr a1
; RV32I-NEXT: lw s0, 24(sp)
; RV32I-NEXT: lw ra, 28(sp)
; RV32I-NEXT: addi sp, sp, 32
; RV32I-NEXT: ret
%1 = call fp128 @callee_large_scalar_ret()
ret void
}
; Check return of >2x xlen structs
define void @callee_large_struct_ret(%struct.large* noalias sret %agg.result) nounwind {
; RV32I-LABEL: callee_large_struct_ret:
; RV32I: # %bb.0:
; RV32I-NEXT: addi sp, sp, -16
; RV32I-NEXT: sw ra, 12(sp)
; RV32I-NEXT: sw s0, 8(sp)
; RV32I-NEXT: addi s0, sp, 16
; RV32I-NEXT: addi a1, zero, 2
; RV32I-NEXT: sw a1, 4(a0)
; RV32I-NEXT: addi a1, zero, 1
; RV32I-NEXT: sw a1, 0(a0)
; RV32I-NEXT: addi a1, zero, 3
; RV32I-NEXT: sw a1, 8(a0)
; RV32I-NEXT: addi a1, zero, 4
; RV32I-NEXT: sw a1, 12(a0)
; RV32I-NEXT: lw s0, 8(sp)
; RV32I-NEXT: lw ra, 12(sp)
; RV32I-NEXT: addi sp, sp, 16
; RV32I-NEXT: ret
%a = getelementptr inbounds %struct.large, %struct.large* %agg.result, i32 0, i32 0
store i32 1, i32* %a, align 4
%b = getelementptr inbounds %struct.large, %struct.large* %agg.result, i32 0, i32 1
store i32 2, i32* %b, align 4
%c = getelementptr inbounds %struct.large, %struct.large* %agg.result, i32 0, i32 2
store i32 3, i32* %c, align 4
%d = getelementptr inbounds %struct.large, %struct.large* %agg.result, i32 0, i32 3
store i32 4, i32* %d, align 4
ret void
}
define i32 @caller_large_struct_ret() nounwind {
; RV32I-LABEL: caller_large_struct_ret:
; RV32I: # %bb.0:
; RV32I-NEXT: addi sp, sp, -32
; RV32I-NEXT: sw ra, 28(sp)
; RV32I-NEXT: sw s0, 24(sp)
; RV32I-NEXT: addi s0, sp, 32
; RV32I-NEXT: lui a0, %hi(callee_large_struct_ret)
; RV32I-NEXT: addi a1, a0, %lo(callee_large_struct_ret)
; RV32I-NEXT: addi a0, s0, -24
; RV32I-NEXT: jalr a1
; RV32I-NEXT: lw a0, -12(s0)
; RV32I-NEXT: lw a1, -24(s0)
; RV32I-NEXT: add a0, a1, a0
; RV32I-NEXT: lw s0, 24(sp)
; RV32I-NEXT: lw ra, 28(sp)
; RV32I-NEXT: addi sp, sp, 32
; RV32I-NEXT: ret
%1 = alloca %struct.large
call void @callee_large_struct_ret(%struct.large* sret %1)
%2 = getelementptr inbounds %struct.large, %struct.large* %1, i32 0, i32 0
%3 = load i32, i32* %2
%4 = getelementptr inbounds %struct.large, %struct.large* %1, i32 0, i32 3
%5 = load i32, i32* %4
%6 = add i32 %3, %5
ret i32 %6
}
|
