/
common-chain.ll
1269 lines (1240 loc) · 48.9 KB
/
common-chain.ll
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
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -ppc-asm-full-reg-names -verify-machineinstrs \
; RUN: -mtriple=powerpc64le-unknown-linux-gnu -mcpu=pwr9 < %s | FileCheck %s
; addresses:
; 1: base1 + offset
; 2: + offset
; 3: + offset
; 4: + offset
;
; chains:
; 1: base: base1 + offset, offsets: (0, offset)
; 2: base: base1 + 3*offset, offsets: (0, offset)
;
; long long two_chain_same_offset_succ(char *p, long long offset, long long base1, long long n) {
; long long o1 = base1 + offset;
; long long o2 = base1 + 2 * offset;
; long long o3 = base1 + 3 * offset;
; long long o4 = base1 + 4 * offset;
; char *p1 = p + o1;
; char *p2 = p + o2;
; char *p3 = p + o3;
; char *p4 = p + o4;
; long long sum = 0;
; for (long long i = 0; i < n; ++i) {
; unsigned long x1 = *(unsigned long *)(p1 + i);
; unsigned long x2 = *(unsigned long *)(p2 + i);
; unsigned long x3 = *(unsigned long *)(p3 + i);
; unsigned long x4 = *(unsigned long *)(p4 + i);
; sum += x1 * x2 * x3 * x4;
; }
; return sum;
; }
;
define i64 @two_chain_same_offset_succ(i8* %p, i64 %offset, i64 %base1, i64 %n) {
; CHECK-LABEL: two_chain_same_offset_succ:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: cmpdi r6, 1
; CHECK-NEXT: blt cr0, .LBB0_4
; CHECK-NEXT: # %bb.1: # %for.body.preheader
; CHECK-NEXT: sldi r8, r4, 1
; CHECK-NEXT: mtctr r6
; CHECK-NEXT: add r5, r3, r5
; CHECK-NEXT: li r3, 0
; CHECK-NEXT: sldi r7, r4, 2
; CHECK-NEXT: add r9, r4, r8
; CHECK-NEXT: .p2align 4
; CHECK-NEXT: .LBB0_2: # %for.body
; CHECK-NEXT: #
; CHECK-NEXT: ldx r6, r5, r4
; CHECK-NEXT: ldx r10, r5, r8
; CHECK-NEXT: ldx r11, r5, r9
; CHECK-NEXT: ldx r12, r5, r7
; CHECK-NEXT: addi r5, r5, 1
; CHECK-NEXT: mulld r6, r10, r6
; CHECK-NEXT: mulld r6, r6, r11
; CHECK-NEXT: maddld r3, r6, r12, r3
; CHECK-NEXT: bdnz .LBB0_2
; CHECK-NEXT: # %bb.3: # %for.cond.cleanup
; CHECK-NEXT: blr
; CHECK-NEXT: .LBB0_4:
; CHECK-NEXT: li r3, 0
; CHECK-NEXT: blr
entry:
%mul = shl nsw i64 %offset, 1
%mul2 = mul nsw i64 %offset, 3
%mul4 = shl nsw i64 %offset, 2
%cmp46 = icmp sgt i64 %n, 0
br i1 %cmp46, label %for.body, label %for.cond.cleanup
for.cond.cleanup: ; preds = %for.body, %entry
%sum.0.lcssa = phi i64 [ 0, %entry ], [ %add16, %for.body ]
ret i64 %sum.0.lcssa
for.body: ; preds = %entry, %for.body
%sum.048 = phi i64 [ %add16, %for.body ], [ 0, %entry ]
%i.047 = phi i64 [ %inc, %for.body ], [ 0, %entry ]
%add = add i64 %i.047, %base1
%add.ptr9.idx = add i64 %add, %offset
%add.ptr9 = getelementptr inbounds i8, i8* %p, i64 %add.ptr9.idx
%0 = bitcast i8* %add.ptr9 to i64*
%1 = load i64, i64* %0, align 8
%add.ptr10.idx = add i64 %add, %mul
%add.ptr10 = getelementptr inbounds i8, i8* %p, i64 %add.ptr10.idx
%2 = bitcast i8* %add.ptr10 to i64*
%3 = load i64, i64* %2, align 8
%add.ptr11.idx = add i64 %add, %mul2
%add.ptr11 = getelementptr inbounds i8, i8* %p, i64 %add.ptr11.idx
%4 = bitcast i8* %add.ptr11 to i64*
%5 = load i64, i64* %4, align 8
%add.ptr12.idx = add i64 %add, %mul4
%add.ptr12 = getelementptr inbounds i8, i8* %p, i64 %add.ptr12.idx
%6 = bitcast i8* %add.ptr12 to i64*
%7 = load i64, i64* %6, align 8
%mul13 = mul i64 %3, %1
%mul14 = mul i64 %mul13, %5
%mul15 = mul i64 %mul14, %7
%add16 = add i64 %mul15, %sum.048
%inc = add nuw nsw i64 %i.047, 1
%exitcond.not = icmp eq i64 %inc, %n
br i1 %exitcond.not, label %for.cond.cleanup, label %for.body
}
; addresses:
; 1: base1 + offset
; 2: + offset
; 3: + offset
; 4: + offset
; 5: + offset
;
; It can not be commoned to chains because we will need a chain for a single address,
; which can not make the commoning be profitable.
;
; long long not_perfect_chain_all_same_offset_fail(char *p, long long offset, long long base1, long long n) {
; long long o1 = base1 + offset;
; long long o2 = base1 + 2 * offset;
; long long o3 = base1 + 3 * offset;
; long long o4 = base1 + 4 * offset;
; long long o5 = base1 + 5 * offset;
; char *p1 = p + o1;
; char *p2 = p + o2;
; char *p3 = p + o3;
; char *p4 = p + o4;
; char *p5 = p + o5;
; long long sum = 0;
; for (long long i = 0; i < n; ++i) {
; unsigned long x1 = *(unsigned long *)(p1 + i);
; unsigned long x2 = *(unsigned long *)(p2 + i);
; unsigned long x3 = *(unsigned long *)(p3 + i);
; unsigned long x4 = *(unsigned long *)(p4 + i);
; unsigned long x5 = *(unsigned long *)(p5 + i);
; sum += x1 * x2 * x3 * x4 * x5;
; }
; return sum;
; }
;
define i64 @not_perfect_chain_all_same_offset_fail(i8* %p, i64 %offset, i64 %base1, i64 %n) {
; CHECK-LABEL: not_perfect_chain_all_same_offset_fail:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: cmpdi r6, 1
; CHECK-NEXT: std r30, -16(r1) # 8-byte Folded Spill
; CHECK-NEXT: blt cr0, .LBB1_4
; CHECK-NEXT: # %bb.1: # %for.body.preheader
; CHECK-NEXT: sldi r7, r4, 2
; CHECK-NEXT: sldi r9, r4, 1
; CHECK-NEXT: add r5, r3, r5
; CHECK-NEXT: li r3, 0
; CHECK-NEXT: add r8, r4, r7
; CHECK-NEXT: mtctr r6
; CHECK-NEXT: add r10, r4, r9
; CHECK-NEXT: .p2align 4
; CHECK-NEXT: .LBB1_2: # %for.body
; CHECK-NEXT: #
; CHECK-NEXT: ldx r6, r5, r4
; CHECK-NEXT: ldx r11, r5, r9
; CHECK-NEXT: ldx r12, r5, r10
; CHECK-NEXT: ldx r0, r5, r7
; CHECK-NEXT: mulld r6, r11, r6
; CHECK-NEXT: ldx r30, r5, r8
; CHECK-NEXT: addi r5, r5, 1
; CHECK-NEXT: mulld r6, r6, r12
; CHECK-NEXT: mulld r6, r6, r0
; CHECK-NEXT: maddld r3, r6, r30, r3
; CHECK-NEXT: bdnz .LBB1_2
; CHECK-NEXT: # %bb.3: # %for.cond.cleanup
; CHECK-NEXT: ld r30, -16(r1) # 8-byte Folded Reload
; CHECK-NEXT: blr
; CHECK-NEXT: .LBB1_4:
; CHECK-NEXT: li r3, 0
; CHECK-NEXT: ld r30, -16(r1) # 8-byte Folded Reload
; CHECK-NEXT: blr
entry:
%mul = shl nsw i64 %offset, 1
%mul2 = mul nsw i64 %offset, 3
%mul4 = shl nsw i64 %offset, 2
%mul6 = mul nsw i64 %offset, 5
%cmp58 = icmp sgt i64 %n, 0
br i1 %cmp58, label %for.body, label %for.cond.cleanup
for.cond.cleanup: ; preds = %for.body, %entry
%sum.0.lcssa = phi i64 [ 0, %entry ], [ %add21, %for.body ]
ret i64 %sum.0.lcssa
for.body: ; preds = %entry, %for.body
%sum.060 = phi i64 [ %add21, %for.body ], [ 0, %entry ]
%i.059 = phi i64 [ %inc, %for.body ], [ 0, %entry ]
%add = add i64 %i.059, %base1
%add.ptr12.idx = add i64 %add, %offset
%add.ptr12 = getelementptr inbounds i8, i8* %p, i64 %add.ptr12.idx
%0 = bitcast i8* %add.ptr12 to i64*
%1 = load i64, i64* %0, align 8
%add.ptr13.idx = add i64 %add, %mul
%add.ptr13 = getelementptr inbounds i8, i8* %p, i64 %add.ptr13.idx
%2 = bitcast i8* %add.ptr13 to i64*
%3 = load i64, i64* %2, align 8
%add.ptr14.idx = add i64 %add, %mul2
%add.ptr14 = getelementptr inbounds i8, i8* %p, i64 %add.ptr14.idx
%4 = bitcast i8* %add.ptr14 to i64*
%5 = load i64, i64* %4, align 8
%add.ptr15.idx = add i64 %add, %mul4
%add.ptr15 = getelementptr inbounds i8, i8* %p, i64 %add.ptr15.idx
%6 = bitcast i8* %add.ptr15 to i64*
%7 = load i64, i64* %6, align 8
%add.ptr16.idx = add i64 %add, %mul6
%add.ptr16 = getelementptr inbounds i8, i8* %p, i64 %add.ptr16.idx
%8 = bitcast i8* %add.ptr16 to i64*
%9 = load i64, i64* %8, align 8
%mul17 = mul i64 %3, %1
%mul18 = mul i64 %mul17, %5
%mul19 = mul i64 %mul18, %7
%mul20 = mul i64 %mul19, %9
%add21 = add i64 %mul20, %sum.060
%inc = add nuw nsw i64 %i.059, 1
%exitcond.not = icmp eq i64 %inc, %n
br i1 %exitcond.not, label %for.cond.cleanup, label %for.body
}
; addresses:
; 1: base1
; 2: + 2*offset
; 3: + offset
;
; We need at least 4 addresses to common 2 chains to reuse at least 1 offset.
;
; long long no_enough_elements_fail(char *p, long long offset, long long base1, long long n) {
; long long o1 = base1;
; long long o2 = base1 + 2 * offset;
; long long o3 = base1 + 3 * offset;
; char *p1 = p + o1;
; char *p2 = p + o2;
; char *p3 = p + o3;
; long long sum = 0;
; for (long long i = 0; i < n; ++i) {
; unsigned long x1 = *(unsigned long *)(p1 + i);
; unsigned long x2 = *(unsigned long *)(p2 + i);
; unsigned long x3 = *(unsigned long *)(p3 + i);
; sum += x1 * x2 * x3;
; }
; return sum;
; }
;
define i64 @no_enough_elements_fail(i8* %p, i64 %offset, i64 %base1, i64 %n) {
; CHECK-LABEL: no_enough_elements_fail:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: cmpdi r6, 1
; CHECK-NEXT: blt cr0, .LBB2_4
; CHECK-NEXT: # %bb.1: # %for.body.preheader
; CHECK-NEXT: sldi r7, r4, 1
; CHECK-NEXT: mtctr r6
; CHECK-NEXT: add r5, r3, r5
; CHECK-NEXT: li r3, 0
; CHECK-NEXT: add r4, r4, r7
; CHECK-NEXT: .p2align 5
; CHECK-NEXT: .LBB2_2: # %for.body
; CHECK-NEXT: #
; CHECK-NEXT: ld r6, 0(r5)
; CHECK-NEXT: ldx r8, r5, r7
; CHECK-NEXT: ldx r9, r5, r4
; CHECK-NEXT: addi r5, r5, 1
; CHECK-NEXT: mulld r6, r8, r6
; CHECK-NEXT: maddld r3, r6, r9, r3
; CHECK-NEXT: bdnz .LBB2_2
; CHECK-NEXT: # %bb.3: # %for.cond.cleanup
; CHECK-NEXT: blr
; CHECK-NEXT: .LBB2_4:
; CHECK-NEXT: li r3, 0
; CHECK-NEXT: blr
entry:
%mul = shl nsw i64 %offset, 1
%mul1 = mul nsw i64 %offset, 3
%cmp32 = icmp sgt i64 %n, 0
br i1 %cmp32, label %for.body, label %for.cond.cleanup
for.cond.cleanup: ; preds = %for.body, %entry
%sum.0.lcssa = phi i64 [ 0, %entry ], [ %add10, %for.body ]
ret i64 %sum.0.lcssa
for.body: ; preds = %entry, %for.body
%sum.034 = phi i64 [ %add10, %for.body ], [ 0, %entry ]
%i.033 = phi i64 [ %inc, %for.body ], [ 0, %entry ]
%add.ptr5.idx = add i64 %i.033, %base1
%add.ptr5 = getelementptr inbounds i8, i8* %p, i64 %add.ptr5.idx
%0 = bitcast i8* %add.ptr5 to i64*
%1 = load i64, i64* %0, align 8
%add.ptr6.idx = add i64 %add.ptr5.idx, %mul
%add.ptr6 = getelementptr inbounds i8, i8* %p, i64 %add.ptr6.idx
%2 = bitcast i8* %add.ptr6 to i64*
%3 = load i64, i64* %2, align 8
%add.ptr7.idx = add i64 %add.ptr5.idx, %mul1
%add.ptr7 = getelementptr inbounds i8, i8* %p, i64 %add.ptr7.idx
%4 = bitcast i8* %add.ptr7 to i64*
%5 = load i64, i64* %4, align 8
%mul8 = mul i64 %3, %1
%mul9 = mul i64 %mul8, %5
%add10 = add i64 %mul9, %sum.034
%inc = add nuw nsw i64 %i.033, 1
%exitcond.not = icmp eq i64 %inc, %n
br i1 %exitcond.not, label %for.cond.cleanup, label %for.body
}
; addresses:
; 1: base1
; 2: + 2*offset
; 3: + 2*offset
; 4: + 3*offset
;
; The diff between address 2 and address 1 is offset, and this offset is not reused among other addresses,
; so we can not common any chains.
;
; long long no_reuseable_offset_fail(char *p, long long offset, long long base1, long long n) {
; long long o1 = base1;
; long long o2 = base1 + 2 * offset;
; long long o3 = base1 + 4 * offset;
; long long o4 = base1 + 7 * offset;
; char *p1 = p + o1;
; char *p2 = p + o2;
; char *p3 = p + o3;
; char *p4 = p + o4;
; long long sum = 0;
; for (long long i = 0; i < n; ++i) {
; unsigned long x1 = *(unsigned long *)(p1 + i);
; unsigned long x2 = *(unsigned long *)(p2 + i);
; unsigned long x3 = *(unsigned long *)(p3 + i);
; unsigned long x4 = *(unsigned long *)(p4 + i);
; sum += x1 * x2 * x3 * x4;
; }
; return sum;
; }
;
define i64 @no_reuseable_offset_fail(i8* %p, i64 %offset, i64 %base1, i64 %n) {
; CHECK-LABEL: no_reuseable_offset_fail:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: cmpdi r6, 1
; CHECK-NEXT: blt cr0, .LBB3_4
; CHECK-NEXT: # %bb.1: # %for.body.preheader
; CHECK-NEXT: sldi r7, r4, 3
; CHECK-NEXT: mtctr r6
; CHECK-NEXT: add r5, r3, r5
; CHECK-NEXT: li r3, 0
; CHECK-NEXT: sldi r8, r4, 2
; CHECK-NEXT: sub r7, r7, r4
; CHECK-NEXT: sldi r4, r4, 1
; CHECK-NEXT: .p2align 4
; CHECK-NEXT: .LBB3_2: # %for.body
; CHECK-NEXT: #
; CHECK-NEXT: ld r6, 0(r5)
; CHECK-NEXT: ldx r9, r5, r4
; CHECK-NEXT: ldx r10, r5, r8
; CHECK-NEXT: ldx r11, r5, r7
; CHECK-NEXT: addi r5, r5, 1
; CHECK-NEXT: mulld r6, r9, r6
; CHECK-NEXT: mulld r6, r6, r10
; CHECK-NEXT: maddld r3, r6, r11, r3
; CHECK-NEXT: bdnz .LBB3_2
; CHECK-NEXT: # %bb.3: # %for.cond.cleanup
; CHECK-NEXT: blr
; CHECK-NEXT: .LBB3_4:
; CHECK-NEXT: li r3, 0
; CHECK-NEXT: blr
entry:
%mul = shl nsw i64 %offset, 1
%mul1 = shl nsw i64 %offset, 2
%mul3 = mul nsw i64 %offset, 7
%cmp44 = icmp sgt i64 %n, 0
br i1 %cmp44, label %for.body, label %for.cond.cleanup
for.cond.cleanup: ; preds = %for.body, %entry
%sum.0.lcssa = phi i64 [ 0, %entry ], [ %add15, %for.body ]
ret i64 %sum.0.lcssa
for.body: ; preds = %entry, %for.body
%sum.046 = phi i64 [ %add15, %for.body ], [ 0, %entry ]
%i.045 = phi i64 [ %inc, %for.body ], [ 0, %entry ]
%add.ptr8.idx = add i64 %i.045, %base1
%add.ptr8 = getelementptr inbounds i8, i8* %p, i64 %add.ptr8.idx
%0 = bitcast i8* %add.ptr8 to i64*
%1 = load i64, i64* %0, align 8
%add.ptr9.idx = add i64 %add.ptr8.idx, %mul
%add.ptr9 = getelementptr inbounds i8, i8* %p, i64 %add.ptr9.idx
%2 = bitcast i8* %add.ptr9 to i64*
%3 = load i64, i64* %2, align 8
%add.ptr10.idx = add i64 %add.ptr8.idx, %mul1
%add.ptr10 = getelementptr inbounds i8, i8* %p, i64 %add.ptr10.idx
%4 = bitcast i8* %add.ptr10 to i64*
%5 = load i64, i64* %4, align 8
%add.ptr11.idx = add i64 %add.ptr8.idx, %mul3
%add.ptr11 = getelementptr inbounds i8, i8* %p, i64 %add.ptr11.idx
%6 = bitcast i8* %add.ptr11 to i64*
%7 = load i64, i64* %6, align 8
%mul12 = mul i64 %3, %1
%mul13 = mul i64 %mul12, %5
%mul14 = mul i64 %mul13, %7
%add15 = add i64 %mul14, %sum.046
%inc = add nuw nsw i64 %i.045, 1
%exitcond.not = icmp eq i64 %inc, %n
br i1 %exitcond.not, label %for.cond.cleanup, label %for.body
}
; addresses:
; 1: base1 + offset
; 2: + offset
; 3: + 3*offset
; 4: + 2*offset
; 5: + 1*offset
; 6: + 2*offset
;
; The diff between address 2 and address 1 is offset, and this offset is reused between address 4 and address 5.
; but the diff between address 3 and address 2 (3*offset) is not the same with the diff between address 6
; and address 5(2*offset), so we can not common chains for these addresses.
;
; long long not_same_offset_fail(char *p, long long offset, long long base1, long long n) {
; long long o1 = base1 + offset;
; long long o2 = base1 + 2 * offset;
; long long o3 = base1 + 5 * offset;
; long long o4 = base1 + 7 * offset;
; long long o5 = base1 + 8 * offset;
; long long o6 = base1 + 10 * offset;
; char *p1 = p + o1;
; char *p2 = p + o2;
; char *p3 = p + o3;
; char *p4 = p + o4;
; char *p5 = p + o5;
; char *p6 = p + o6;
; long long sum = 0;
; for (long long i = 0; i < n; ++i) {
; unsigned long x1 = *(unsigned long *)(p1 + i);
; unsigned long x2 = *(unsigned long *)(p2 + i);
; unsigned long x3 = *(unsigned long *)(p3 + i);
; unsigned long x4 = *(unsigned long *)(p4 + i);
; unsigned long x5 = *(unsigned long *)(p5 + i);
; unsigned long x6 = *(unsigned long *)(p6 + i);
; sum += x1 * x2 * x3 * x4 * x5 * x6;
; }
; return sum;
; }
;
define i64 @not_same_offset_fail(i8* %p, i64 %offset, i64 %base1, i64 %n) {
; CHECK-LABEL: not_same_offset_fail:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: cmpdi r6, 1
; CHECK-NEXT: std r28, -32(r1) # 8-byte Folded Spill
; CHECK-NEXT: std r29, -24(r1) # 8-byte Folded Spill
; CHECK-NEXT: std r30, -16(r1) # 8-byte Folded Spill
; CHECK-NEXT: blt cr0, .LBB4_3
; CHECK-NEXT: # %bb.1: # %for.body.preheader
; CHECK-NEXT: mulli r7, r4, 10
; CHECK-NEXT: add r5, r3, r5
; CHECK-NEXT: sldi r8, r4, 3
; CHECK-NEXT: sub r9, r8, r4
; CHECK-NEXT: sldi r3, r4, 2
; CHECK-NEXT: mtctr r6
; CHECK-NEXT: add r10, r4, r3
; CHECK-NEXT: sldi r11, r4, 1
; CHECK-NEXT: li r3, 0
; CHECK-NEXT: .p2align 4
; CHECK-NEXT: .LBB4_2: # %for.body
; CHECK-NEXT: #
; CHECK-NEXT: ldx r6, r5, r4
; CHECK-NEXT: ldx r12, r5, r11
; CHECK-NEXT: ldx r0, r5, r10
; CHECK-NEXT: ldx r30, r5, r9
; CHECK-NEXT: mulld r6, r12, r6
; CHECK-NEXT: ldx r29, r5, r8
; CHECK-NEXT: ldx r28, r5, r7
; CHECK-NEXT: addi r5, r5, 1
; CHECK-NEXT: mulld r6, r6, r0
; CHECK-NEXT: mulld r6, r6, r30
; CHECK-NEXT: mulld r6, r6, r29
; CHECK-NEXT: maddld r3, r6, r28, r3
; CHECK-NEXT: bdnz .LBB4_2
; CHECK-NEXT: b .LBB4_4
; CHECK-NEXT: .LBB4_3:
; CHECK-NEXT: li r3, 0
; CHECK-NEXT: .LBB4_4: # %for.cond.cleanup
; CHECK-NEXT: ld r30, -16(r1) # 8-byte Folded Reload
; CHECK-NEXT: ld r29, -24(r1) # 8-byte Folded Reload
; CHECK-NEXT: ld r28, -32(r1) # 8-byte Folded Reload
; CHECK-NEXT: blr
entry:
%mul = shl nsw i64 %offset, 1
%mul2 = mul nsw i64 %offset, 5
%mul4 = mul nsw i64 %offset, 7
%mul6 = shl nsw i64 %offset, 3
%mul8 = mul nsw i64 %offset, 10
%cmp70 = icmp sgt i64 %n, 0
br i1 %cmp70, label %for.body, label %for.cond.cleanup
for.cond.cleanup: ; preds = %for.body, %entry
%sum.0.lcssa = phi i64 [ 0, %entry ], [ %add26, %for.body ]
ret i64 %sum.0.lcssa
for.body: ; preds = %entry, %for.body
%sum.072 = phi i64 [ %add26, %for.body ], [ 0, %entry ]
%i.071 = phi i64 [ %inc, %for.body ], [ 0, %entry ]
%add = add i64 %i.071, %base1
%add.ptr15.idx = add i64 %add, %offset
%add.ptr15 = getelementptr inbounds i8, i8* %p, i64 %add.ptr15.idx
%0 = bitcast i8* %add.ptr15 to i64*
%1 = load i64, i64* %0, align 8
%add.ptr16.idx = add i64 %add, %mul
%add.ptr16 = getelementptr inbounds i8, i8* %p, i64 %add.ptr16.idx
%2 = bitcast i8* %add.ptr16 to i64*
%3 = load i64, i64* %2, align 8
%add.ptr17.idx = add i64 %add, %mul2
%add.ptr17 = getelementptr inbounds i8, i8* %p, i64 %add.ptr17.idx
%4 = bitcast i8* %add.ptr17 to i64*
%5 = load i64, i64* %4, align 8
%add.ptr18.idx = add i64 %add, %mul4
%add.ptr18 = getelementptr inbounds i8, i8* %p, i64 %add.ptr18.idx
%6 = bitcast i8* %add.ptr18 to i64*
%7 = load i64, i64* %6, align 8
%add.ptr19.idx = add i64 %add, %mul6
%add.ptr19 = getelementptr inbounds i8, i8* %p, i64 %add.ptr19.idx
%8 = bitcast i8* %add.ptr19 to i64*
%9 = load i64, i64* %8, align 8
%add.ptr20.idx = add i64 %add, %mul8
%add.ptr20 = getelementptr inbounds i8, i8* %p, i64 %add.ptr20.idx
%10 = bitcast i8* %add.ptr20 to i64*
%11 = load i64, i64* %10, align 8
%mul21 = mul i64 %3, %1
%mul22 = mul i64 %mul21, %5
%mul23 = mul i64 %mul22, %7
%mul24 = mul i64 %mul23, %9
%mul25 = mul i64 %mul24, %11
%add26 = add i64 %mul25, %sum.072
%inc = add nuw nsw i64 %i.071, 1
%exitcond.not = icmp eq i64 %inc, %n
br i1 %exitcond.not, label %for.cond.cleanup, label %for.body
}
; addresses:
; 1: base1 + offset
; 2: + offset
; 3: + 3*offset
; 4: + 2*offset
;
; chains:
; 1: base1 + offset, offsets: (0, 2*offset)
; 2: base1 + 4*offset, offsets: (0, 2*offset)
;
; long long two_chain_different_offsets_succ(char *p, long long offset, long long base1, long long n) {
; long long o1 = base1 + offset;
; long long o2 = base1 + 3 * offset;
; long long o3 = base1 + 4 * offset;
; long long o4 = base1 + 6 * offset;
; char *p1 = p + o1;
; char *p2 = p + o2;
; char *p3 = p + o3;
; char *p4 = p + o4;
; long long sum = 0;
; for (long long i = 0; i < n; ++i) {
; unsigned long x1 = *(unsigned long *)(p1 + i);
; unsigned long x2 = *(unsigned long *)(p2 + i);
; unsigned long x3 = *(unsigned long *)(p3 + i);
; unsigned long x4 = *(unsigned long *)(p4 + i);
; sum += x1 * x2 * x3 * x4;
; }
; return sum;
; }
;
define i64 @two_chain_different_offsets_succ(i8* %p, i64 %offset, i64 %base1, i64 %n) {
; CHECK-LABEL: two_chain_different_offsets_succ:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: cmpdi r6, 1
; CHECK-NEXT: blt cr0, .LBB5_4
; CHECK-NEXT: # %bb.1: # %for.body.preheader
; CHECK-NEXT: mulli r7, r4, 6
; CHECK-NEXT: add r5, r3, r5
; CHECK-NEXT: sldi r3, r4, 1
; CHECK-NEXT: add r9, r4, r3
; CHECK-NEXT: mtctr r6
; CHECK-NEXT: sldi r8, r4, 2
; CHECK-NEXT: li r3, 0
; CHECK-NEXT: .p2align 4
; CHECK-NEXT: .LBB5_2: # %for.body
; CHECK-NEXT: #
; CHECK-NEXT: ldx r6, r5, r4
; CHECK-NEXT: ldx r10, r5, r9
; CHECK-NEXT: ldx r11, r5, r8
; CHECK-NEXT: ldx r12, r5, r7
; CHECK-NEXT: addi r5, r5, 1
; CHECK-NEXT: mulld r6, r10, r6
; CHECK-NEXT: mulld r6, r6, r11
; CHECK-NEXT: maddld r3, r6, r12, r3
; CHECK-NEXT: bdnz .LBB5_2
; CHECK-NEXT: # %bb.3: # %for.cond.cleanup
; CHECK-NEXT: blr
; CHECK-NEXT: .LBB5_4:
; CHECK-NEXT: li r3, 0
; CHECK-NEXT: blr
entry:
%mul = mul nsw i64 %offset, 3
%mul2 = shl nsw i64 %offset, 2
%mul4 = mul nsw i64 %offset, 6
%cmp46 = icmp sgt i64 %n, 0
br i1 %cmp46, label %for.body, label %for.cond.cleanup
for.cond.cleanup: ; preds = %for.body, %entry
%sum.0.lcssa = phi i64 [ 0, %entry ], [ %add16, %for.body ]
ret i64 %sum.0.lcssa
for.body: ; preds = %entry, %for.body
%sum.048 = phi i64 [ %add16, %for.body ], [ 0, %entry ]
%i.047 = phi i64 [ %inc, %for.body ], [ 0, %entry ]
%add = add i64 %i.047, %base1
%add.ptr9.idx = add i64 %add, %offset
%add.ptr9 = getelementptr inbounds i8, i8* %p, i64 %add.ptr9.idx
%0 = bitcast i8* %add.ptr9 to i64*
%1 = load i64, i64* %0, align 8
%add.ptr10.idx = add i64 %add, %mul
%add.ptr10 = getelementptr inbounds i8, i8* %p, i64 %add.ptr10.idx
%2 = bitcast i8* %add.ptr10 to i64*
%3 = load i64, i64* %2, align 8
%add.ptr11.idx = add i64 %add, %mul2
%add.ptr11 = getelementptr inbounds i8, i8* %p, i64 %add.ptr11.idx
%4 = bitcast i8* %add.ptr11 to i64*
%5 = load i64, i64* %4, align 8
%add.ptr12.idx = add i64 %add, %mul4
%add.ptr12 = getelementptr inbounds i8, i8* %p, i64 %add.ptr12.idx
%6 = bitcast i8* %add.ptr12 to i64*
%7 = load i64, i64* %6, align 8
%mul13 = mul i64 %3, %1
%mul14 = mul i64 %mul13, %5
%mul15 = mul i64 %mul14, %7
%add16 = add i64 %mul15, %sum.048
%inc = add nuw nsw i64 %i.047, 1
%exitcond.not = icmp eq i64 %inc, %n
br i1 %exitcond.not, label %for.cond.cleanup, label %for.body
}
; addresses:
; 1: base1 + offset
; 2: + 2*offset
; 3: + base2 - base1 - 2*offset
; 4: + 2*offset
;
; chains:
; 1: base1 + offset, offsets: (0, 2*offset)
; 2: base2 + offset, offsets: (0, 2*offset)
;
; long long two_chain_two_bases_succ(char *p, long long offset, long long base1, long long base2, long long n) {
; long long o1 = base1 + offset;
; long long o2 = base1 + 3 * offset;
; long long o3 = base2 + offset;
; long long o4 = base2 + 3 * offset;
; char *p1 = p + o1;
; char *p2 = p + o2;
; char *p3 = p + o3;
; char *p4 = p + o4;
; long long sum = 0;
; for (long long i = 0; i < n; ++i) {
; unsigned long x1 = *(unsigned long *)(p1 + i);
; unsigned long x2 = *(unsigned long *)(p2 + i);
; unsigned long x3 = *(unsigned long *)(p3 + i);
; unsigned long x4 = *(unsigned long *)(p4 + i);
; sum += x1 * x2 * x3 * x4;
; }
; return sum;
; }
;
define i64 @two_chain_two_bases_succ(i8* %p, i64 %offset, i64 %base1, i64 %base2, i64 %n) {
; CHECK-LABEL: two_chain_two_bases_succ:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: cmpdi r7, 1
; CHECK-NEXT: blt cr0, .LBB6_4
; CHECK-NEXT: # %bb.1: # %for.body.preheader
; CHECK-NEXT: sldi r8, r4, 1
; CHECK-NEXT: mtctr r7
; CHECK-NEXT: add r9, r4, r8
; CHECK-NEXT: add r8, r6, r9
; CHECK-NEXT: add r6, r6, r4
; CHECK-NEXT: add r9, r5, r9
; CHECK-NEXT: add r5, r5, r4
; CHECK-NEXT: li r4, 0
; CHECK-NEXT: .p2align 4
; CHECK-NEXT: .LBB6_2: # %for.body
; CHECK-NEXT: #
; CHECK-NEXT: ldx r7, r3, r5
; CHECK-NEXT: ldx r10, r3, r9
; CHECK-NEXT: ldx r11, r3, r6
; CHECK-NEXT: ldx r12, r3, r8
; CHECK-NEXT: addi r3, r3, 1
; CHECK-NEXT: mulld r7, r10, r7
; CHECK-NEXT: mulld r7, r7, r11
; CHECK-NEXT: maddld r4, r7, r12, r4
; CHECK-NEXT: bdnz .LBB6_2
; CHECK-NEXT: # %bb.3: # %for.cond.cleanup
; CHECK-NEXT: mr r3, r4
; CHECK-NEXT: blr
; CHECK-NEXT: .LBB6_4:
; CHECK-NEXT: li r4, 0
; CHECK-NEXT: mr r3, r4
; CHECK-NEXT: blr
entry:
%mul = mul nsw i64 %offset, 3
%cmp44 = icmp sgt i64 %n, 0
br i1 %cmp44, label %for.body, label %for.cond.cleanup
for.cond.cleanup: ; preds = %for.body, %entry
%sum.0.lcssa = phi i64 [ 0, %entry ], [ %add15, %for.body ]
ret i64 %sum.0.lcssa
for.body: ; preds = %entry, %for.body
%sum.046 = phi i64 [ %add15, %for.body ], [ 0, %entry ]
%i.045 = phi i64 [ %inc, %for.body ], [ 0, %entry ]
%add = add i64 %i.045, %base1
%add.ptr8.idx = add i64 %add, %offset
%add.ptr8 = getelementptr inbounds i8, i8* %p, i64 %add.ptr8.idx
%0 = bitcast i8* %add.ptr8 to i64*
%1 = load i64, i64* %0, align 8
%add1 = add i64 %i.045, %mul
%add.ptr9.idx = add i64 %add1, %base1
%add.ptr9 = getelementptr inbounds i8, i8* %p, i64 %add.ptr9.idx
%2 = bitcast i8* %add.ptr9 to i64*
%3 = load i64, i64* %2, align 8
%add2 = add i64 %i.045, %base2
%add.ptr10.idx = add i64 %add2, %offset
%add.ptr10 = getelementptr inbounds i8, i8* %p, i64 %add.ptr10.idx
%4 = bitcast i8* %add.ptr10 to i64*
%5 = load i64, i64* %4, align 8
%add.ptr11.idx = add i64 %add2, %mul
%add.ptr11 = getelementptr inbounds i8, i8* %p, i64 %add.ptr11.idx
%6 = bitcast i8* %add.ptr11 to i64*
%7 = load i64, i64* %6, align 8
%mul12 = mul i64 %3, %1
%mul13 = mul i64 %mul12, %5
%mul14 = mul i64 %mul13, %7
%add15 = add i64 %mul14, %sum.046
%inc = add nuw nsw i64 %i.045, 1
%exitcond.not = icmp eq i64 %inc, %n
br i1 %exitcond.not, label %for.cond.cleanup, label %for.body
}
;
; Check chain commoning can reduce register pressure to save register spill/reload.
;
; int spill_reduce_succ(double *input1, double *input2, double *output, long long m, long long inc1, long long inc2, long long inc3, long long inc4, long long inc) {
; inc = inc4;
; #pragma unroll 4
; for (long long i = 0; i < 4 * m; i++) {
; output[inc + inc1] += input1[inc + inc1] * input2[inc + inc1];
; output[inc + inc2] += input1[inc + inc2] * input2[inc + inc2];
; output[inc + inc3] += input1[inc + inc3] * input2[inc + inc3];
; inc = inc + inc4;
; }
; return 0;
; }
;
define signext i32 @spill_reduce_succ(double* %input1, double* %input2, double* %output, i64 %m, i64 %inc1, i64 %inc2, i64 %inc3, i64 %inc4, i64 %inc) {
; CHECK-LABEL: spill_reduce_succ:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: stdu r1, -336(r1)
; CHECK-NEXT: .cfi_def_cfa_offset 336
; CHECK-NEXT: .cfi_offset r14, -144
; CHECK-NEXT: .cfi_offset r15, -136
; CHECK-NEXT: .cfi_offset r16, -128
; CHECK-NEXT: .cfi_offset r17, -120
; CHECK-NEXT: .cfi_offset r18, -112
; CHECK-NEXT: .cfi_offset r19, -104
; CHECK-NEXT: .cfi_offset r20, -96
; CHECK-NEXT: .cfi_offset r21, -88
; CHECK-NEXT: .cfi_offset r22, -80
; CHECK-NEXT: .cfi_offset r23, -72
; CHECK-NEXT: .cfi_offset r24, -64
; CHECK-NEXT: .cfi_offset r25, -56
; CHECK-NEXT: .cfi_offset r26, -48
; CHECK-NEXT: .cfi_offset r27, -40
; CHECK-NEXT: .cfi_offset r28, -32
; CHECK-NEXT: .cfi_offset r29, -24
; CHECK-NEXT: .cfi_offset r30, -16
; CHECK-NEXT: .cfi_offset r31, -8
; CHECK-NEXT: .cfi_offset r2, -152
; CHECK-NEXT: cmpdi r6, 1
; CHECK-NEXT: std r14, 192(r1) # 8-byte Folded Spill
; CHECK-NEXT: std r15, 200(r1) # 8-byte Folded Spill
; CHECK-NEXT: std r16, 208(r1) # 8-byte Folded Spill
; CHECK-NEXT: std r17, 216(r1) # 8-byte Folded Spill
; CHECK-NEXT: std r18, 224(r1) # 8-byte Folded Spill
; CHECK-NEXT: std r19, 232(r1) # 8-byte Folded Spill
; CHECK-NEXT: std r20, 240(r1) # 8-byte Folded Spill
; CHECK-NEXT: std r21, 248(r1) # 8-byte Folded Spill
; CHECK-NEXT: std r22, 256(r1) # 8-byte Folded Spill
; CHECK-NEXT: std r23, 264(r1) # 8-byte Folded Spill
; CHECK-NEXT: std r24, 272(r1) # 8-byte Folded Spill
; CHECK-NEXT: std r25, 280(r1) # 8-byte Folded Spill
; CHECK-NEXT: std r26, 288(r1) # 8-byte Folded Spill
; CHECK-NEXT: std r27, 296(r1) # 8-byte Folded Spill
; CHECK-NEXT: std r28, 304(r1) # 8-byte Folded Spill
; CHECK-NEXT: std r29, 312(r1) # 8-byte Folded Spill
; CHECK-NEXT: std r30, 320(r1) # 8-byte Folded Spill
; CHECK-NEXT: std r31, 328(r1) # 8-byte Folded Spill
; CHECK-NEXT: std r2, 184(r1) # 8-byte Folded Spill
; CHECK-NEXT: std r9, 40(r1) # 8-byte Folded Spill
; CHECK-NEXT: std r8, 48(r1) # 8-byte Folded Spill
; CHECK-NEXT: std r7, 64(r1) # 8-byte Folded Spill
; CHECK-NEXT: std r5, 80(r1) # 8-byte Folded Spill
; CHECK-NEXT: std r4, 72(r1) # 8-byte Folded Spill
; CHECK-NEXT: std r3, 56(r1) # 8-byte Folded Spill
; CHECK-NEXT: blt cr0, .LBB7_7
; CHECK-NEXT: # %bb.1: # %for.body.preheader
; CHECK-NEXT: sldi r3, r6, 2
; CHECK-NEXT: li r4, 1
; CHECK-NEXT: mr r16, r10
; CHECK-NEXT: cmpdi r3, 1
; CHECK-NEXT: iselgt r3, r3, r4
; CHECK-NEXT: addi r4, r3, -1
; CHECK-NEXT: clrldi r6, r3, 63
; CHECK-NEXT: cmpldi r4, 3
; CHECK-NEXT: blt cr0, .LBB7_4
; CHECK-NEXT: # %bb.2: # %for.body.preheader.new
; CHECK-NEXT: ld r30, 40(r1) # 8-byte Folded Reload
; CHECK-NEXT: sldi r4, r16, 2
; CHECK-NEXT: ld r19, 80(r1) # 8-byte Folded Reload
; CHECK-NEXT: ld r21, 72(r1) # 8-byte Folded Reload
; CHECK-NEXT: ld r22, 56(r1) # 8-byte Folded Reload
; CHECK-NEXT: ld r27, 48(r1) # 8-byte Folded Reload
; CHECK-NEXT: ld r18, 64(r1) # 8-byte Folded Reload
; CHECK-NEXT: add r5, r30, r4
; CHECK-NEXT: rldicl r0, r3, 62, 2
; CHECK-NEXT: sldi r5, r5, 3
; CHECK-NEXT: add r11, r19, r5
; CHECK-NEXT: add r7, r21, r5
; CHECK-NEXT: add r5, r22, r5
; CHECK-NEXT: std r5, 168(r1) # 8-byte Folded Spill
; CHECK-NEXT: add r5, r27, r4
; CHECK-NEXT: add r4, r18, r4
; CHECK-NEXT: std r7, 176(r1) # 8-byte Folded Spill
; CHECK-NEXT: sldi r5, r5, 3
; CHECK-NEXT: sldi r4, r4, 3
; CHECK-NEXT: add r29, r19, r5
; CHECK-NEXT: add r7, r21, r5
; CHECK-NEXT: add r5, r22, r5
; CHECK-NEXT: add r26, r19, r4
; CHECK-NEXT: std r5, 152(r1) # 8-byte Folded Spill
; CHECK-NEXT: add r5, r21, r4
; CHECK-NEXT: add r4, r22, r4
; CHECK-NEXT: std r7, 160(r1) # 8-byte Folded Spill
; CHECK-NEXT: std r4, 136(r1) # 8-byte Folded Spill
; CHECK-NEXT: sldi r4, r16, 1
; CHECK-NEXT: std r5, 144(r1) # 8-byte Folded Spill
; CHECK-NEXT: add r10, r16, r4
; CHECK-NEXT: add r3, r18, r4
; CHECK-NEXT: add r5, r30, r10
; CHECK-NEXT: sldi r3, r3, 3
; CHECK-NEXT: sldi r5, r5, 3
; CHECK-NEXT: add r23, r19, r5
; CHECK-NEXT: add r7, r21, r5
; CHECK-NEXT: add r5, r22, r5
; CHECK-NEXT: std r5, 120(r1) # 8-byte Folded Spill
; CHECK-NEXT: add r5, r27, r10
; CHECK-NEXT: std r7, 128(r1) # 8-byte Folded Spill
; CHECK-NEXT: sldi r5, r5, 3
; CHECK-NEXT: add r20, r19, r5
; CHECK-NEXT: add r7, r21, r5
; CHECK-NEXT: add r5, r22, r5
; CHECK-NEXT: std r5, 104(r1) # 8-byte Folded Spill
; CHECK-NEXT: add r5, r18, r10
; CHECK-NEXT: std r7, 112(r1) # 8-byte Folded Spill
; CHECK-NEXT: sub r10, r18, r10
; CHECK-NEXT: sldi r5, r5, 3
; CHECK-NEXT: sldi r10, r10, 3
; CHECK-NEXT: add r17, r19, r5
; CHECK-NEXT: add r7, r21, r5
; CHECK-NEXT: add r5, r22, r5
; CHECK-NEXT: std r5, 88(r1) # 8-byte Folded Spill
; CHECK-NEXT: add r5, r30, r4
; CHECK-NEXT: std r7, 96(r1) # 8-byte Folded Spill
; CHECK-NEXT: add r7, r19, r3
; CHECK-NEXT: sldi r5, r5, 3
; CHECK-NEXT: add r14, r19, r5
; CHECK-NEXT: add r31, r21, r5
; CHECK-NEXT: add r2, r22, r5
; CHECK-NEXT: add r5, r27, r4
; CHECK-NEXT: add r4, r22, r3
; CHECK-NEXT: sldi r5, r5, 3
; CHECK-NEXT: add r12, r19, r5
; CHECK-NEXT: add r8, r21, r5
; CHECK-NEXT: add r9, r22, r5
; CHECK-NEXT: add r5, r21, r3
; CHECK-NEXT: add r3, r16, r30
; CHECK-NEXT: rldicl r30, r0, 2, 1
; CHECK-NEXT: addi r0, r30, -4
; CHECK-NEXT: sldi r28, r3, 3
; CHECK-NEXT: rldicl r30, r0, 62, 2
; CHECK-NEXT: add r3, r19, r28
; CHECK-NEXT: addi r0, r30, 1
; CHECK-NEXT: add r30, r21, r28
; CHECK-NEXT: add r28, r22, r28
; CHECK-NEXT: mtctr r0
; CHECK-NEXT: add r0, r16, r27
; CHECK-NEXT: sldi r0, r0, 3
; CHECK-NEXT: add r25, r21, r0
; CHECK-NEXT: add r24, r22, r0
; CHECK-NEXT: add r22, r22, r10
; CHECK-NEXT: add r21, r21, r10
; CHECK-NEXT: add r10, r16, r18
; CHECK-NEXT: add r27, r19, r0
; CHECK-NEXT: li r0, 0
; CHECK-NEXT: sldi r18, r16, 5
; CHECK-NEXT: sldi r10, r10, 3
; CHECK-NEXT: add r19, r19, r10
; CHECK-NEXT: mr r10, r16
; CHECK-NEXT: .p2align 4
; CHECK-NEXT: .LBB7_3: # %for.body
; CHECK-NEXT: #
; CHECK-NEXT: lfdux f0, r21, r18
; CHECK-NEXT: lfdux f1, r22, r18
; CHECK-NEXT: ld r15, 88(r1) # 8-byte Folded Reload
; CHECK-NEXT: add r10, r10, r16
; CHECK-NEXT: add r10, r10, r16
; CHECK-NEXT: xsmuldp f0, f1, f0
; CHECK-NEXT: lfd f1, 0(r19)
; CHECK-NEXT: add r10, r10, r16
; CHECK-NEXT: add r10, r10, r16
; CHECK-NEXT: xsadddp f0, f1, f0
; CHECK-NEXT: stfd f0, 0(r19)
; CHECK-NEXT: add r19, r19, r18
; CHECK-NEXT: lfdx f0, r24, r0
; CHECK-NEXT: lfdx f1, r25, r0
; CHECK-NEXT: xsmuldp f0, f0, f1
; CHECK-NEXT: lfdx f1, r27, r0
; CHECK-NEXT: xsadddp f0, f1, f0
; CHECK-NEXT: stfdx f0, r27, r0
; CHECK-NEXT: lfdx f0, r28, r0
; CHECK-NEXT: lfdx f1, r30, r0
; CHECK-NEXT: xsmuldp f0, f0, f1
; CHECK-NEXT: lfdx f1, r3, r0
; CHECK-NEXT: xsadddp f0, f1, f0
; CHECK-NEXT: stfdx f0, r3, r0
; CHECK-NEXT: lfdx f0, r4, r0
; CHECK-NEXT: lfdx f1, r5, r0
; CHECK-NEXT: xsmuldp f0, f0, f1
; CHECK-NEXT: lfdx f1, r7, r0
; CHECK-NEXT: xsadddp f0, f1, f0
; CHECK-NEXT: stfdx f0, r7, r0
; CHECK-NEXT: lfdx f0, r9, r0
; CHECK-NEXT: lfdx f1, r8, r0
; CHECK-NEXT: xsmuldp f0, f0, f1
; CHECK-NEXT: lfdx f1, r12, r0
; CHECK-NEXT: xsadddp f0, f1, f0
; CHECK-NEXT: stfdx f0, r12, r0
; CHECK-NEXT: lfdx f0, r2, r0
; CHECK-NEXT: lfdx f1, r31, r0
; CHECK-NEXT: xsmuldp f0, f0, f1
; CHECK-NEXT: lfdx f1, r14, r0
; CHECK-NEXT: xsadddp f0, f1, f0
; CHECK-NEXT: stfdx f0, r14, r0
; CHECK-NEXT: lfdx f0, r15, r0
; CHECK-NEXT: ld r15, 96(r1) # 8-byte Folded Reload
; CHECK-NEXT: lfdx f1, r15, r0
; CHECK-NEXT: ld r15, 104(r1) # 8-byte Folded Reload
; CHECK-NEXT: xsmuldp f0, f0, f1
; CHECK-NEXT: lfdx f1, r17, r0
; CHECK-NEXT: xsadddp f0, f1, f0
; CHECK-NEXT: stfdx f0, r17, r0
; CHECK-NEXT: lfdx f0, r15, r0
; CHECK-NEXT: ld r15, 112(r1) # 8-byte Folded Reload
; CHECK-NEXT: lfdx f1, r15, r0
; CHECK-NEXT: ld r15, 120(r1) # 8-byte Folded Reload
; CHECK-NEXT: xsmuldp f0, f0, f1
; CHECK-NEXT: lfdx f1, r20, r0
; CHECK-NEXT: xsadddp f0, f1, f0
; CHECK-NEXT: stfdx f0, r20, r0
; CHECK-NEXT: lfdx f0, r15, r0
; CHECK-NEXT: ld r15, 128(r1) # 8-byte Folded Reload
; CHECK-NEXT: lfdx f1, r15, r0
; CHECK-NEXT: ld r15, 136(r1) # 8-byte Folded Reload
; CHECK-NEXT: xsmuldp f0, f0, f1
; CHECK-NEXT: lfdx f1, r23, r0
; CHECK-NEXT: xsadddp f0, f1, f0
; CHECK-NEXT: stfdx f0, r23, r0
; CHECK-NEXT: lfdx f0, r15, r0
; CHECK-NEXT: ld r15, 144(r1) # 8-byte Folded Reload
; CHECK-NEXT: lfdx f1, r15, r0
; CHECK-NEXT: ld r15, 152(r1) # 8-byte Folded Reload
; CHECK-NEXT: xsmuldp f0, f0, f1
; CHECK-NEXT: lfdx f1, r26, r0
; CHECK-NEXT: xsadddp f0, f1, f0
; CHECK-NEXT: stfdx f0, r26, r0
; CHECK-NEXT: lfdx f0, r15, r0
; CHECK-NEXT: ld r15, 160(r1) # 8-byte Folded Reload
; CHECK-NEXT: lfdx f1, r15, r0
; CHECK-NEXT: ld r15, 168(r1) # 8-byte Folded Reload
; CHECK-NEXT: xsmuldp f0, f0, f1
; CHECK-NEXT: lfdx f1, r29, r0
; CHECK-NEXT: xsadddp f0, f1, f0
; CHECK-NEXT: stfdx f0, r29, r0
; CHECK-NEXT: lfdx f0, r15, r0
; CHECK-NEXT: ld r15, 176(r1) # 8-byte Folded Reload
; CHECK-NEXT: lfdx f1, r15, r0
; CHECK-NEXT: xsmuldp f0, f0, f1
; CHECK-NEXT: lfdx f1, r11, r0
; CHECK-NEXT: xsadddp f0, f1, f0
; CHECK-NEXT: stfdx f0, r11, r0
; CHECK-NEXT: add r0, r0, r18
; CHECK-NEXT: bdnz .LBB7_3
; CHECK-NEXT: .LBB7_4: # %for.cond.cleanup.loopexit.unr-lcssa
; CHECK-NEXT: cmpldi r6, 0
; CHECK-NEXT: beq cr0, .LBB7_7
; CHECK-NEXT: # %bb.5: # %for.body.epil.preheader
; CHECK-NEXT: ld r12, 64(r1) # 8-byte Folded Reload