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
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
|
/* longlong.h -- definitions for mixed size 32/64 bit arithmetic.
Copyright (C) 1991, 1992, 1993 Free Software Foundation, Inc.
This definition file is free software; you can redistribute it
and/or modify it under the terms of the GNU General Public
License as published by the Free Software Foundation; either
version 2, or (at your option) any later version.
This definition file is distributed in the hope that it will be
useful, but WITHOUT ANY WARRANTY; without even the implied
warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
See the GNU General Public License for more details.
You should have received a copy of the GNU General Public License
along with this program; if not, write to the Free Software
Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. */
#ifndef LONG_TYPE_SIZE
#ifdef BITS_PER_LONGINT
#define LONG_TYPE_SIZE BITS_PER_LONGINT
#else
#define LONG_TYPE_SIZE 32
#endif
#endif
#define __BITS4 (LONG_TYPE_SIZE / 4)
#define __ll_B (1L << (LONG_TYPE_SIZE / 2))
#define __ll_lowpart(t) ((unsigned long int) (t) % __ll_B)
#define __ll_highpart(t) ((unsigned long int) (t) / __ll_B)
/* Define auxiliary asm macros.
1) umul_ppmm(high_prod, low_prod, multipler, multiplicand)
multiplies two unsigned long integers MULTIPLER and MULTIPLICAND,
and generates a two unsigned word product in HIGH_PROD and
LOW_PROD.
2) __umulsidi3(a,b) multiplies two unsigned long integers A and B,
and returns a long long product. This is just a variant of umul_ppmm.
3) udiv_qrnnd(quotient, remainder, high_numerator, low_numerator,
denominator) divides a two-word unsigned integer, composed by the
integers HIGH_NUMERATOR and LOW_NUMERATOR, by DENOMINATOR and
places the quotient in QUOTIENT and the remainder in REMAINDER.
HIGH_NUMERATOR must be less than DENOMINATOR for correct operation.
If, in addition, the most significant bit of DENOMINATOR must be 1,
then the pre-processor symbol UDIV_NEEDS_NORMALIZATION is defined to 1.
4) sdiv_qrnnd(quotient, remainder, high_numerator, low_numerator,
denominator). Like udiv_qrnnd but the numbers are signed. The
quotient is rounded towards 0.
5) count_leading_zeros(count, x) counts the number of zero-bits from
the msb to the first non-zero bit. This is the number of steps X
needs to be shifted left to set the msb. Undefined for X == 0.
6) add_ssaaaa(high_sum, low_sum, high_addend_1, low_addend_1,
high_addend_2, low_addend_2) adds two two-word unsigned integers,
composed by HIGH_ADDEND_1 and LOW_ADDEND_1, and HIGH_ADDEND_2 and
LOW_ADDEND_2 respectively. The result is placed in HIGH_SUM and
LOW_SUM. Overflow (i.e. carry out) is not stored anywhere, and is
lost.
7) sub_ddmmss(high_difference, low_difference, high_minuend,
low_minuend, high_subtrahend, low_subtrahend) subtracts two
two-word unsigned integers, composed by HIGH_MINUEND_1 and
LOW_MINUEND_1, and HIGH_SUBTRAHEND_2 and LOW_SUBTRAHEND_2
respectively. The result is placed in HIGH_DIFFERENCE and
LOW_DIFFERENCE. Overflow (i.e. carry out) is not stored anywhere,
and is lost.
If any of these macros are left undefined for a particular CPU,
C macros are used. */
/* The CPUs come in alphabetical order below.
Please add support for more CPUs here, or improve the current support
for the CPUs below! */
#if defined (__GNUC__) && !defined (NO_ASM)
/* We sometimes need to clobber "cc" with gcc2, but that would not be
understood by gcc1. Use cpp to avoid major code duplication. */
#if __GNUC__ < 2
#define __CLOBBER_CC
#define __AND_CLOBBER_CC
#else /* __GNUC__ >= 2 */
#define __CLOBBER_CC : "cc"
#define __AND_CLOBBER_CC , "cc"
#endif /* __GNUC__ < 2 */
#if defined (__a29k__) || defined (___AM29K__)
#define add_ssaaaa(sh, sl, ah, al, bh, bl) \
__asm__ ("add %1,%4,%5
addc %0,%2,%3" \
: "=r" ((unsigned long int)(sh)), \
"=&r" ((unsigned long int)(sl)) \
: "%r" ((unsigned long int)(ah)), \
"rI" ((unsigned long int)(bh)), \
"%r" ((unsigned long int)(al)), \
"rI" ((unsigned long int)(bl)))
#define sub_ddmmss(sh, sl, ah, al, bh, bl) \
__asm__ ("sub %1,%4,%5
subc %0,%2,%3" \
: "=r" ((unsigned long int)(sh)), \
"=&r" ((unsigned long int)(sl)) \
: "r" ((unsigned long int)(ah)), \
"rI" ((unsigned long int)(bh)), \
"r" ((unsigned long int)(al)), \
"rI" ((unsigned long int)(bl)))
#define umul_ppmm(xh, xl, m0, m1) \
do { \
unsigned long int __m0 = (m0), __m1 = (m1); \
__asm__ ("multiplu %0,%1,%2" \
: "=r" ((unsigned long int)(xl)) \
: "r" (__m0), \
"r" (__m1)); \
__asm__ ("multmu %0,%1,%2" \
: "=r" ((unsigned long int)(xh)) \
: "r" (__m0), \
"r" (__m1)); \
} while (0)
#define udiv_qrnnd(q, r, n1, n0, d) \
__asm__ ("dividu %0,%3,%4" \
: "=r" ((unsigned long int)(q)), \
"=q" ((unsigned long int)(r)) \
: "1" ((unsigned long int)(n1)), \
"r" ((unsigned long int)(n0)), \
"r" ((unsigned long int)(d)))
#define count_leading_zeros(count, x) \
__asm__ ("clz %0,%1" \
: "=r" ((unsigned long int)(count)) \
: "r" ((unsigned long int)(x)))
#endif /* __a29k__ */
#if defined (__alpha__)
#define umul_ppmm(ph, pl, m0, m1) \
do { \
unsigned long int __m0 = (m0), __m1 = (m1); \
__asm__ ("umulh %r1,%2,%0" \
: "=r" ((unsigned long int) ph) \
: "%rJ" (__m0), \
"rI" (__m1)); \
(pl) = (unsigned long int) (__m0) * (unsigned long int) (__m1); \
} while (0)
#define UMUL_TIME 46
#define UDIV_TIME 500
#endif
#if defined (__arm__)
#define add_ssaaaa(sh, sl, ah, al, bh, bl) \
__asm__ ("adds %1,%4,%5
adc %0,%2,%3" \
: "=r" ((unsigned long int)(sh)), \
"=&r" ((unsigned long int)(sl)) \
: "%r" ((unsigned long int)(ah)), \
"rI" ((unsigned long int)(bh)), \
"%r" ((unsigned long int)(al)), \
"rI" ((unsigned long int)(bl)))
#define sub_ddmmss(sh, sl, ah, al, bh, bl) \
__asm__ ("subs %1,%4,%5
sbc %0,%2,%3" \
: "=r" ((unsigned long int)(sh)), \
"=&r" ((unsigned long int)(sl)) \
: "r" ((unsigned long int)(ah)), \
"rI" ((unsigned long int)(bh)), \
"r" ((unsigned long int)(al)), \
"rI" ((unsigned long int)(bl)))
#endif /* __arm__ */
#if defined (__gmicro__)
#define add_ssaaaa(sh, sl, ah, al, bh, bl) \
__asm__ ("add.w %5,%1
addx %3,%0" \
: "=g" ((unsigned long int)(sh)), \
"=&g" ((unsigned long int)(sl)) \
: "%0" ((unsigned long int)(ah)), \
"g" ((unsigned long int)(bh)), \
"%1" ((unsigned long int)(al)), \
"g" ((unsigned long int)(bl)))
#define sub_ddmmss(sh, sl, ah, al, bh, bl) \
__asm__ ("sub.w %5,%1
subx %3,%0" \
: "=g" ((unsigned long int)(sh)), \
"=&g" ((unsigned long int)(sl)) \
: "0" ((unsigned long int)(ah)), \
"g" ((unsigned long int)(bh)), \
"1" ((unsigned long int)(al)), \
"g" ((unsigned long int)(bl)))
#define umul_ppmm(ph, pl, m0, m1) \
__asm__ ("mulx %3,%0,%1" \
: "=g" ((unsigned long int)(ph)), \
"=r" ((unsigned long int)(pl)) \
: "%0" ((unsigned long int)(m0)), \
"g" ((unsigned long int)(m1)))
#define udiv_qrnnd(q, r, nh, nl, d) \
__asm__ ("divx %4,%0,%1" \
: "=g" ((unsigned long int)(q)), \
"=r" ((unsigned long int)(r)) \
: "1" ((unsigned long int)(nh)), \
"0" ((unsigned long int)(nl)), \
"g" ((unsigned long int)(d)))
#define count_leading_zeros(count, x) \
__asm__ ("bsch/1 %1,%0" \
: "=g" (count) \
: "g" ((unsigned long int)(x)), \
"0" (0UL))
#endif
#if defined (__hppa)
#define add_ssaaaa(sh, sl, ah, al, bh, bl) \
__asm__ ("add %4,%5,%1
addc %2,%3,%0" \
: "=r" ((unsigned long int)(sh)), \
"=&r" ((unsigned long int)(sl)) \
: "%rM" ((unsigned long int)(ah)), \
"rM" ((unsigned long int)(bh)), \
"%rM" ((unsigned long int)(al)), \
"rM" ((unsigned long int)(bl)))
#define sub_ddmmss(sh, sl, ah, al, bh, bl) \
__asm__ ("sub %4,%5,%1
subb %2,%3,%0" \
: "=r" ((unsigned long int)(sh)), \
"=&r" ((unsigned long int)(sl)) \
: "rM" ((unsigned long int)(ah)), \
"rM" ((unsigned long int)(bh)), \
"rM" ((unsigned long int)(al)), \
"rM" ((unsigned long int)(bl)))
#if defined (_PA_RISC1_1)
#define umul_ppmm(wh, wl, u, v) \
do { \
union {long long int __ll; \
struct {unsigned long int __h, __l;} __i; \
} __xx; \
__asm__ ("xmpyu %1,%2,%0" \
: "=x" (__xx.__ll) \
: "x" ((unsigned long int)(u)), \
"x" ((unsigned long int)(v))); \
(wh) = __xx.__i.__h; \
(wl) = __xx.__i.__l; \
} while (0)
#define UMUL_TIME 8
#define UDIV_TIME 60
#else
#define UMUL_TIME 40
#define UDIV_TIME 80
#endif
#define count_leading_zeros(count, x) \
do { \
unsigned long int __tmp; \
__asm__ ( \
"ldi 1,%0
extru,= %1,15,16,%%r0 ; Bits 31..16 zero?
extru,tr %1,15,16,%1 ; No. Shift down, skip add.
ldo 16(%0),%0 ; Yes. Perform add.
extru,= %1,23,8,%%r0 ; Bits 15..8 zero?
extru,tr %1,23,8,%1 ; No. Shift down, skip add.
ldo 8(%0),%0 ; Yes. Perform add.
extru,= %1,27,4,%%r0 ; Bits 7..4 zero?
extru,tr %1,27,4,%1 ; No. Shift down, skip add.
ldo 4(%0),%0 ; Yes. Perform add.
extru,= %1,29,2,%%r0 ; Bits 3..2 zero?
extru,tr %1,29,2,%1 ; No. Shift down, skip add.
ldo 2(%0),%0 ; Yes. Perform add.
extru %1,30,1,%1 ; Extract bit 1.
sub %0,%1,%0 ; Subtract it.
" : "=r" (count), "=r" (__tmp) : "1" (x)); \
} while (0)
#endif
#if defined (__i386__) || defined (__i486__)
#define add_ssaaaa(sh, sl, ah, al, bh, bl) \
__asm__ ("addl %5,%1
adcl %3,%0" \
: "=r" ((unsigned long int)(sh)), \
"=&r" ((unsigned long int)(sl)) \
: "%0" ((unsigned long int)(ah)), \
"g" ((unsigned long int)(bh)), \
"%1" ((unsigned long int)(al)), \
"g" ((unsigned long int)(bl)))
#define sub_ddmmss(sh, sl, ah, al, bh, bl) \
__asm__ ("subl %5,%1
sbbl %3,%0" \
: "=r" ((unsigned long int)(sh)), \
"=&r" ((unsigned long int)(sl)) \
: "0" ((unsigned long int)(ah)), \
"g" ((unsigned long int)(bh)), \
"1" ((unsigned long int)(al)), \
"g" ((unsigned long int)(bl)))
#define umul_ppmm(w1, w0, u, v) \
__asm__ ("mull %3" \
: "=a" ((unsigned long int)(w0)), \
"=d" ((unsigned long int)(w1)) \
: "%0" ((unsigned long int)(u)), \
"rm" ((unsigned long int)(v)))
#define udiv_qrnnd(q, r, n1, n0, d) \
__asm__ ("divl %4" \
: "=a" ((unsigned long int)(q)), \
"=d" ((unsigned long int)(r)) \
: "0" ((unsigned long int)(n0)), \
"1" ((unsigned long int)(n1)), \
"rm" ((unsigned long int)(d)))
#define count_leading_zeros(count, x) \
do { \
unsigned long int __cbtmp; \
__asm__ ("bsrl %1,%0" \
: "=r" (__cbtmp) : "rm" ((unsigned long int)(x))); \
(count) = __cbtmp ^ 31; \
} while (0)
#define UMUL_TIME 40
#define UDIV_TIME 40
#endif /* 80x86 */
#if defined (__i860__)
#if 0
/* Make sure these patterns really improve the code before
switching them on. */
#define add_ssaaaa(sh, sl, ah, al, bh, bl) \
do { \
union \
{ \
long long int ll; \
struct {unsigned long int l, h;} i; \
} __a, __b, __s; \
__a.i.l = (al); __a.i.h = (ah); \
__b.i.l = (bl); __b.i.h = (bh); \
__asm__ ("fiadd.dd %1,%2,%0" \
: "=f" (__s.ll) \
: "%f" (__a.ll), "f" (__b.ll)); \
(sh) = __s.i.h; (sl) = __s.i.l; \
} while (0)
#define sub_ddmmss(sh, sl, ah, al, bh, bl) \
do { \
union \
{ \
long long int ll; \
struct {unsigned long int l, h;} i; \
} __a, __b, __s; \
__a.i.l = (al); __a.i.h = (ah); \
__b.i.l = (bl); __b.i.h = (bh); \
__asm__ ("fisub.dd %1,%2,%0" \
: "=f" (__s.ll) \
: "%f" (__a.ll), "f" (__b.ll)); \
(sh) = __s.i.h; (sl) = __s.i.l; \
} while (0)
#endif
#endif /* __i860__ */
#if defined (__i960__)
#define umul_ppmm(w1, w0, u, v) \
({union {long long int __ll; \
struct {unsigned long int __l, __h;} __i; \
} __xx; \
__asm__ ("emul %2,%1,%0" \
: "=d" (__xx.__ll) \
: "%dI" ((unsigned long int)(u)), \
"dI" ((unsigned long int)(v))); \
(w1) = __xx.__i.__h; (w0) = __xx.__i.__l;})
#define __umulsidi3(u, v) \
({long long int __w; \
__asm__ ("emul %2,%1,%0" \
: "=d" (__w) \
: "%dI" ((unsigned long int)(u)), \
"dI" ((unsigned long int)(v))); \
__w; })
#endif /* __i960__ */
#if defined (___IBMR2__) /* IBM RS6000 */
#define add_ssaaaa(sh, sl, ah, al, bh, bl) \
__asm__ ("a%I5 %1,%4,%5
ae %0,%2,%3" \
: "=r" ((unsigned long int)(sh)), \
"=&r" ((unsigned long int)(sl)) \
: "%r" ((unsigned long int)(ah)), \
"r" ((unsigned long int)(bh)), \
"%r" ((unsigned long int)(al)), \
"rI" ((unsigned long int)(bl)))
#define sub_ddmmss(sh, sl, ah, al, bh, bl) \
__asm__ ("sf%I4 %1,%5,%4
sfe %0,%3,%2" \
: "=r" ((unsigned long int)(sh)), \
"=&r" ((unsigned long int)(sl)) \
: "r" ((unsigned long int)(ah)), \
"r" ((unsigned long int)(bh)), \
"rI" ((unsigned long int)(al)), \
"r" ((unsigned long int)(bl)))
#define umul_ppmm(xh, xl, m0, m1) \
do { \
unsigned long int __m0 = (m0), __m1 = (m1); \
__asm__ ("mul %0,%2,%3" \
: "=r" ((unsigned long int)(xh)), \
"=q" ((unsigned long int)(xl)) \
: "r" (__m0), \
"r" (__m1)); \
(xh) += ((((signed long int) __m0 >> 31) & __m1) \
+ (((signed long int) __m1 >> 31) & __m0)); \
} while (0)
#define smul_ppmm(xh, xl, m0, m1) \
__asm__ ("mul %0,%2,%3" \
: "=r" ((unsigned long int)(xh)), \
"=q" ((unsigned long int)(xl)) \
: "r" (m0), \
"r" (m1))
#define UMUL_TIME 8
#define sdiv_qrnnd(q, r, nh, nl, d) \
__asm__ ("div %0,%2,%4" \
: "=r" (q), "=q" (r) \
: "r" (nh), "1" (nl), "r" (d))
#define UDIV_TIME 100
#define count_leading_zeros(count, x) \
__asm__ ("cntlz %0,%1" \
: "=r" ((unsigned long int)(count)) \
: "r" ((unsigned long int)(x)))
#endif /* ___IBMR2__ */
#if defined (__mc68000__)
#define add_ssaaaa(sh, sl, ah, al, bh, bl) \
__asm__ ("add%.l %5,%1
addx%.l %3,%0" \
: "=d" ((unsigned long int)(sh)), \
"=&d" ((unsigned long int)(sl)) \
: "%0" ((unsigned long int)(ah)), \
"d" ((unsigned long int)(bh)), \
"%1" ((unsigned long int)(al)), \
"g" ((unsigned long int)(bl)))
#define sub_ddmmss(sh, sl, ah, al, bh, bl) \
__asm__ ("sub%.l %5,%1
subx%.l %3,%0" \
: "=d" ((unsigned long int)(sh)), \
"=&d" ((unsigned long int)(sl)) \
: "0" ((unsigned long int)(ah)), \
"d" ((unsigned long int)(bh)), \
"1" ((unsigned long int)(al)), \
"g" ((unsigned long int)(bl)))
#if defined (__mc68020__) || defined (__NeXT__) || defined(mc68020)
#define umul_ppmm(w1, w0, u, v) \
__asm__ ("mulu%.l %3,%1:%0" \
: "=d" ((unsigned long int)(w0)), \
"=d" ((unsigned long int)(w1)) \
: "%0" ((unsigned long int)(u)), \
"dmi" ((unsigned long int)(v)))
#define UMUL_TIME 45
#define udiv_qrnnd(q, r, n1, n0, d) \
__asm__ ("divu%.l %4,%1:%0" \
: "=d" ((unsigned long int)(q)), \
"=d" ((unsigned long int)(r)) \
: "0" ((unsigned long int)(n0)), \
"1" ((unsigned long int)(n1)), \
"dmi" ((unsigned long int)(d)))
#define UDIV_TIME 90
#define sdiv_qrnnd(q, r, n1, n0, d) \
__asm__ ("divs%.l %4,%1:%0" \
: "=d" ((unsigned long int)(q)), \
"=d" ((unsigned long int)(r)) \
: "0" ((unsigned long int)(n0)), \
"1" ((unsigned long int)(n1)), \
"dmi" ((unsigned long int)(d)))
#define count_leading_zeros(count, x) \
__asm__ ("bfffo %1{%b2:%b2},%0" \
: "=d" ((unsigned long int)(count)) \
: "od" ((unsigned long int)(x)), "n" (0))
#else /* not mc68020 */
/* This ought to be improved by relying on reload to move inputs and
outputs to their positions. */
#define umul_ppmm(xh, xl, a, b) \
__asm__ ("| Inlined umul_ppmm
movel %2,d0
movel %3,d1
movel d0,d2
swap d0
movel d1,d3
swap d1
movew d2,d4
mulu d3,d4
mulu d1,d2
mulu d0,d3
mulu d0,d1
movel d4,d0
eorw d0,d0
swap d0
addl d0,d2
addl d3,d2
jcc 1f
addl #65536,d1
1: swap d2
moveq #0,d0
movew d2,d0
movew d4,d2
movel d2,%1
addl d1,d0
movel d0,%0" \
: "=g" ((unsigned long int)(xh)), \
"=g" ((unsigned long int)(xl)) \
: "g" ((unsigned long int)(a)), \
"g" ((unsigned long int)(b)) \
: "d0", "d1", "d2", "d3", "d4")
#define UMUL_TIME 100
#define UDIV_TIME 400
#endif /* not mc68020 */
#endif /* mc68000 */
#if defined (__m88000__)
#define add_ssaaaa(sh, sl, ah, al, bh, bl) \
__asm__ ("addu.co %1,%r4,%r5
addu.ci %0,%r2,%r3" \
: "=r" ((unsigned long int)(sh)), \
"=&r" ((unsigned long int)(sl)) \
: "%rJ" ((unsigned long int)(ah)), \
"rJ" ((unsigned long int)(bh)), \
"%rJ" ((unsigned long int)(al)), \
"rJ" ((unsigned long int)(bl)))
#define sub_ddmmss(sh, sl, ah, al, bh, bl) \
__asm__ ("subu.co %1,%r4,%r5
subu.ci %0,%r2,%r3" \
: "=r" ((unsigned long int)(sh)), \
"=&r" ((unsigned long int)(sl)) \
: "rJ" ((unsigned long int)(ah)), \
"rJ" ((unsigned long int)(bh)), \
"rJ" ((unsigned long int)(al)), \
"rJ" ((unsigned long int)(bl)))
#define UMUL_TIME 17
#define UDIV_TIME 150
#define count_leading_zeros(count, x) \
do { \
unsigned long int __cbtmp; \
__asm__ ("ff1 %0,%1" \
: "=r" (__cbtmp) \
: "r" ((unsigned long int)(x))); \
(count) = __cbtmp ^ 31; \
} while (0)
#if defined (__mc88110__)
#define umul_ppmm(wh, wl, u, v) \
do { \
union {long long int __ll; \
struct {unsigned long int __h, __l;} __i; \
} __xx; \
__asm__ ("mulu.d %0,%1,%2" \
: "=r" (__xx.__ll) \
: "r" ((unsigned long int)(u)), \
"r" ((unsigned long int)(v))); \
(wh) = __xx.__i.__h; \
(wl) = __xx.__i.__l; \
} while (0)
#define udiv_qrnnd(q, r, n1, n0, d) \
__asm__ ("or r10,%2,0
or r11,%3,0
divu.d r10,r10,%4
mulu %1,%4,r11
subu %1,%3,%1
or %0,r11,0" \
: "=r" (q), \
"=&r" (r) \
: "r" (n1), \
"r" (n0), \
"r" (d) \
: "r10", "r11")
#endif
#endif /* __m88000__ */
#if defined (__mips__)
/* The LO and HI registers are fixed in gcc/mips.h, for some reason. */
#if 0 && __GNUC__ >= 2
#define umul_ppmm(w1, w0, u, v) \
__asm__ ("multu %2,%3" \
: "=l" ((unsigned long int)(w0)), \
"=h" ((unsigned long int)(w1)) \
: "d" ((unsigned long int)(u)), \
"d" ((unsigned long int)(v)))
#else
#define umul_ppmm(w1, w0, u, v) \
__asm__ ("multu %2,%3
mflo %0
mfhi %1" \
: "=d" ((unsigned long int)(w0)), \
"=d" ((unsigned long int)(w1)) \
: "d" ((unsigned long int)(u)), \
"d" ((unsigned long int)(v)))
#endif
#define UMUL_TIME 10
#define UDIV_TIME 100
#endif /* __mips__ */
#if defined (__ns32000__)
#define umul_ppmm(w1, w0, u, v) \
({union {long long int __ll; \
struct {unsigned long int __l, __h;} __i; \
} __xx; \
__asm__ ("meid %2,%0" \
: "=g" (__xx.__ll) \
: "%0" ((unsigned long int)(u)), \
"g" ((unsigned long int)(v))); \
(w1) = __xx.__i.__h; (w0) = __xx.__i.__l;})
#define __umulsidi3(u, v) \
({long long int __w; \
__asm__ ("meid %2,%0" \
: "=g" (__w) \
: "%0" ((unsigned long int)(u)), \
"g" ((unsigned long int)(v))); \
__w; })
#define udiv_qrnnd(q, r, n1, n0, d) \
__asm__ ("movd %2,r0
movd %3,r1
deid %4,r0
movd r1,%0
movd r0,%1" \
: "=g" ((unsigned long int)(q)), \
"=g" ((unsigned long int)(r)) \
: "g" ((unsigned long int)(n0)), \
"g" ((unsigned long int)(n1)), \
"g" ((unsigned long int)(d)) \
: "r0", "r1")
#endif /* __ns32000__ */
#if defined (__pyr__)
#define add_ssaaaa(sh, sl, ah, al, bh, bl) \
__asm__ ("addw %5,%1
addwc %3,%0" \
: "=r" ((unsigned long int)(sh)), \
"=&r" ((unsigned long int)(sl)) \
: "%0" ((unsigned long int)(ah)), \
"g" ((unsigned long int)(bh)), \
"%1" ((unsigned long int)(al)), \
"g" ((unsigned long int)(bl)))
#define sub_ddmmss(sh, sl, ah, al, bh, bl) \
__asm__ ("subw %5,%1
subwb %3,%0" \
: "=r" ((unsigned long int)(sh)), \
"=&r" ((unsigned long int)(sl)) \
: "0" ((unsigned long int)(ah)), \
"g" ((unsigned long int)(bh)), \
"1" ((unsigned long int)(al)), \
"g" ((unsigned long int)(bl)))
/* This insn doesn't work on ancient pyramids. */
#define umul_ppmm(w1, w0, u, v) \
({union {long long int __ll; \
struct {unsigned long int __h, __l;} __i; \
} __xx; \
__xx.__i.__l = u; \
__asm__ ("uemul %3,%0" \
: "=r" (__xx.__i.__h), \
"=r" (__xx.__i.__l) \
: "1" (__xx.__i.__l), \
"g" (v)); \
(w1) = __xx.__i.__h; (w0) = __xx.__i.__l;})
#endif /* __pyr__ */
#if defined (__ibm032__) /* RT/ROMP */
#define add_ssaaaa(sh, sl, ah, al, bh, bl) \
__asm__ ("a %1,%5
ae %0,%3" \
: "=r" ((unsigned long int)(sh)), \
"=&r" ((unsigned long int)(sl)) \
: "%0" ((unsigned long int)(ah)), \
"r" ((unsigned long int)(bh)), \
"%1" ((unsigned long int)(al)), \
"r" ((unsigned long int)(bl)))
#define sub_ddmmss(sh, sl, ah, al, bh, bl) \
__asm__ ("s %1,%5
se %0,%3" \
: "=r" ((unsigned long int)(sh)), \
"=&r" ((unsigned long int)(sl)) \
: "0" ((unsigned long int)(ah)), \
"r" ((unsigned long int)(bh)), \
"1" ((unsigned long int)(al)), \
"r" ((unsigned long int)(bl)))
#define umul_ppmm(ph, pl, m0, m1) \
do { \
unsigned long int __m0 = (m0), __m1 = (m1); \
__asm__ ( \
"s r2,r2
mts r10,%2
m r2,%3
m r2,%3
m r2,%3
m r2,%3
m r2,%3
m r2,%3
m r2,%3
m r2,%3
m r2,%3
m r2,%3
m r2,%3
m r2,%3
m r2,%3
m r2,%3
m r2,%3
m r2,%3
cas %0,r2,r0
mfs r10,%1" \
: "=r" ((unsigned long int)(ph)), \
"=r" ((unsigned long int)(pl)) \
: "%r" (__m0), \
"r" (__m1) \
: "r2"); \
(ph) += ((((signed long int) __m0 >> 31) & __m1) \
+ (((signed long int) __m1 >> 31) & __m0)); \
} while (0)
#define UMUL_TIME 20
#define UDIV_TIME 200
#define count_leading_zeros(count, x) \
do { \
if ((x) >= 0x10000) \
__asm__ ("clz %0,%1" \
: "=r" ((unsigned long int)(count)) \
: "r" ((unsigned long int)(x) >> 16)); \
else \
{ \
__asm__ ("clz %0,%1" \
: "=r" ((unsigned long int)(count)) \
: "r" ((unsigned long int)(x))); \
(count) += 16; \
} \
} while (0)
#endif
#if defined (__sparc__)
#define add_ssaaaa(sh, sl, ah, al, bh, bl) \
__asm__ ("addcc %4,%5,%1
addx %2,%3,%0" \
: "=r" ((unsigned long int)(sh)), \
"=&r" ((unsigned long int)(sl)) \
: "%r" ((unsigned long int)(ah)), \
"rI" ((unsigned long int)(bh)), \
"%r" ((unsigned long int)(al)), \
"rI" ((unsigned long int)(bl)) \
__CLOBBER_CC)
#define sub_ddmmss(sh, sl, ah, al, bh, bl) \
__asm__ ("subcc %4,%5,%1
subx %2,%3,%0" \
: "=r" ((unsigned long int)(sh)), \
"=&r" ((unsigned long int)(sl)) \
: "r" ((unsigned long int)(ah)), \
"rI" ((unsigned long int)(bh)), \
"r" ((unsigned long int)(al)), \
"rI" ((unsigned long int)(bl)) \
__CLOBBER_CC)
#if defined (__sparc_v8__)
#define umul_ppmm(w1, w0, u, v) \
__asm__ ("umul %2,%3,%1;rd %%y,%0" \
: "=r" ((unsigned long int)(w1)), \
"=r" ((unsigned long int)(w0)) \
: "r" ((unsigned long int)(u)), \
"r" ((unsigned long int)(v)))
/* We might want to leave this undefined for `SuperSPARC (tm)' since
its implementation is crippled and often traps. */
#define udiv_qrnnd(q, r, n1, n0, d) \
__asm__ ("mov %2,%%y;nop;nop;nop;udiv %3,%4,%0;umul %0,%4,%1;sub %3,%1,%1"\
: "=&r" ((unsigned long int)(q)), \
"=&r" ((unsigned long int)(r)) \
: "r" ((unsigned long int)(n1)), \
"r" ((unsigned long int)(n0)), \
"r" ((unsigned long int)(d)))
#define UMUL_TIME 6
#define UDIV_TIME 25
#else
/* SPARC without integer multiplication and divide instructions.
(i.e. at least Sun4/20,40,60,65,75,110,260,280,330,360,380,470,490) */
#define umul_ppmm(w1, w0, u, v) \
__asm__ ("! Inlined umul_ppmm
wr %%g0,%2,%%y ! SPARC has 0-3 delay insn after a wr
sra %3,31,%%g2 ! Don't move this insn
and %2,%%g2,%%g2 ! Don't move this insn
andcc %%g0,0,%%g1 ! Don't move this insn
mulscc %%g1,%3,%%g1
mulscc %%g1,%3,%%g1
mulscc %%g1,%3,%%g1
mulscc %%g1,%3,%%g1
mulscc %%g1,%3,%%g1
mulscc %%g1,%3,%%g1
mulscc %%g1,%3,%%g1
mulscc %%g1,%3,%%g1
mulscc %%g1,%3,%%g1
mulscc %%g1,%3,%%g1
mulscc %%g1,%3,%%g1
mulscc %%g1,%3,%%g1
mulscc %%g1,%3,%%g1
mulscc %%g1,%3,%%g1
mulscc %%g1,%3,%%g1
mulscc %%g1,%3,%%g1
mulscc %%g1,%3,%%g1
mulscc %%g1,%3,%%g1
mulscc %%g1,%3,%%g1
mulscc %%g1,%3,%%g1
mulscc %%g1,%3,%%g1
mulscc %%g1,%3,%%g1
mulscc %%g1,%3,%%g1
mulscc %%g1,%3,%%g1
mulscc %%g1,%3,%%g1
mulscc %%g1,%3,%%g1
mulscc %%g1,%3,%%g1
mulscc %%g1,%3,%%g1
mulscc %%g1,%3,%%g1
mulscc %%g1,%3,%%g1
mulscc %%g1,%3,%%g1
mulscc %%g1,%3,%%g1
mulscc %%g1,0,%%g1
add %%g1,%%g2,%0
rd %%y,%1" \
: "=r" ((unsigned long int)(w1)), \
"=r" ((unsigned long int)(w0)) \
: "%rI" ((unsigned long int)(u)), \
"r" ((unsigned long int)(v)) \
: "%g1", "%g2" __AND_CLOBBER_CC)
#define UMUL_TIME 39 /* 39 instructions */
/* It's quite necessary to add this much assembler for the sparc.
The default udiv_qrnnd (in C) is more than 10 times slower! */
#define udiv_qrnnd(q, r, n1, n0, d) \
__asm__ ("! Inlined udiv_qrnnd
mov 32,%%g1
subcc %1,%2,%%g0
1: bcs 5f
addxcc %0,%0,%0 ! shift n1n0 and a q-bit in lsb
sub %1,%2,%1 ! this kills msb of n
addx %1,%1,%1 ! so this can't give carry
subcc %%g1,1,%%g1
2: bne 1b
subcc %1,%2,%%g0
bcs 3f
addxcc %0,%0,%0 ! shift n1n0 and a q-bit in lsb
b 3f
sub %1,%2,%1 ! this kills msb of n
4: sub %1,%2,%1
5: addxcc %1,%1,%1
bcc 2b
subcc %%g1,1,%%g1
! Got carry from n. Subtract next step to cancel this carry.
bne 4b
addcc %0,%0,%0 ! shift n1n0 and a 0-bit in lsb
sub %1,%2,%1
3: xnor %0,0,%0
! End of inline udiv_qrnnd" \
: "=&r" ((unsigned long int)(q)), \
"=&r" ((unsigned long int)(r)) \
: "r" ((unsigned long int)(d)), \
"1" ((unsigned long int)(n1)), \
"0" ((unsigned long int)(n0)) : "%g1" __AND_CLOBBER_CC)
#define UDIV_TIME (3+7*32) /* 7 instructions/iteration. 32 iterations. */
#endif /* __sparc8__ */
#endif /* __sparc__ */
#if defined (__vax__)
#define add_ssaaaa(sh, sl, ah, al, bh, bl) \
__asm__ ("addl2 %5,%1
adwc %3,%0" \
: "=g" ((unsigned long int)(sh)), \
"=&g" ((unsigned long int)(sl)) \
: "%0" ((unsigned long int)(ah)), \
"g" ((unsigned long int)(bh)), \
"%1" ((unsigned long int)(al)), \
"g" ((unsigned long int)(bl)))
#define sub_ddmmss(sh, sl, ah, al, bh, bl) \
__asm__ ("subl2 %5,%1
sbwc %3,%0" \
: "=g" ((unsigned long int)(sh)), \
"=&g" ((unsigned long int)(sl)) \
: "0" ((unsigned long int)(ah)), \
"g" ((unsigned long int)(bh)), \
"1" ((unsigned long int)(al)), \
"g" ((unsigned long int)(bl)))
#define umul_ppmm(xh, xl, m0, m1) \
do { \
union {long long int __ll; \
struct {unsigned long int __l, __h;} __i; \
} __xx; \
unsigned long int __m0 = (m0), __m1 = (m1); \
__asm__ ("emul %1,%2,$0,%0" \
: "=g" (__xx.__ll) \
: "g" (__m0), \
"g" (__m1)); \
(xh) = __xx.__i.__h; (xl) = __xx.__i.__l; \
(xh) += ((((signed long int) __m0 >> 31) & __m1) \
+ (((signed long int) __m1 >> 31) & __m0)); \
} while (0)
#define sdiv_qrnnd(q, r, n1, n0, d) \
do { \
union {long long int __ll; \
struct {unsigned long int __l, __h;} __i; \
} __xx; \
__xx.__i.__h = n1; __xx.__i.__l = n0; \
__asm__ ("ediv %3,%2,%0,%1" \
: "=g" (q), "=g" (r) \
: "g" (__n1n0.ll), "g" (d)); \
} while (0)
#endif /* __vax__ */
#endif /* __GNUC__ */
#if !defined (umul_ppmm) && defined (__umulsidi3)
#define umul_ppmm(ph, pl, m0, m1) \
{ \
unsigned long long int __ll = __umulsidi3 (m0, m1); \
ph = (unsigned long int) (__ll >> LONG_TYPE_SIZE); \
pl = (unsigned long int) __ll; \
}
#endif
#if !defined (__umulsidi3)
#define __umulsidi3(u, v) \
({long __hi, __lo; \
umul_ppmm (__hi, __lo, u, v); \
((unsigned long long) __hi << LONG_TYPE_SIZE) | __lo; })
#endif
/* If this machine has no inline assembler, use C macros. */
#if !defined (add_ssaaaa)
#define add_ssaaaa(sh, sl, ah, al, bh, bl) \
do { \
unsigned long int __x; \
__x = (al) + (bl); \
(sh) = (ah) + (bh) + (__x < (al)); \
(sl) = __x; \
} while (0)
#endif
#if !defined (sub_ddmmss)
#define sub_ddmmss(sh, sl, ah, al, bh, bl) \
do { \
unsigned long int __x; \
__x = (al) - (bl); \
(sh) = (ah) - (bh) - (__x > (al)); \
(sl) = __x; \
} while (0)
#endif
#if !defined (umul_ppmm)
#define umul_ppmm(w1, w0, u, v) \
do { \
unsigned long int __x0, __x1, __x2, __x3; \
unsigned int __ul, __vl, __uh, __vh; \
\
__ul = __ll_lowpart (u); \
__uh = __ll_highpart (u); \
__vl = __ll_lowpart (v); \
__vh = __ll_highpart (v); \
\
__x0 = (unsigned long int) __ul * __vl; \
__x1 = (unsigned long int) __ul * __vh; \
__x2 = (unsigned long int) __uh * __vl; \
__x3 = (unsigned long int) __uh * __vh; \
\
__x1 += __ll_highpart (__x0);/* this can't give carry */ \
__x1 += __x2; /* but this indeed can */ \
if (__x1 < __x2) /* did we get it? */ \
__x3 += __ll_B; /* yes, add it in the proper pos. */ \
\
(w1) = __x3 + __ll_highpart (__x1); \
(w0) = __ll_lowpart (__x1) * __ll_B + __ll_lowpart (__x0); \
} while (0)
#endif
/* Define this unconditionally, so it can be used for debugging. */
#define __udiv_qrnnd_c(q, r, n1, n0, d) \
do { \
unsigned long int __d1, __d0, __q1, __q0, __r1, __r0, __m; \
__d1 = __ll_highpart (d); \
__d0 = __ll_lowpart (d); \
\
__r1 = (n1) % __d1; \
__q1 = (n1) / __d1; \
__m = (unsigned long int) __q1 * __d0; \
__r1 = __r1 * __ll_B | __ll_highpart (n0); \
if (__r1 < __m) \
{ \
__q1--, __r1 += (d); \
if (__r1 >= (d)) /* i.e. we didn't get carry when adding to __r1 */\
if (__r1 < __m) \
__q1--, __r1 += (d); \
} \
__r1 -= __m; \
\
__r0 = __r1 % __d1; \
__q0 = __r1 / __d1; \
__m = (unsigned long int) __q0 * __d0; \
__r0 = __r0 * __ll_B | __ll_lowpart (n0); \
if (__r0 < __m) \
{ \
__q0--, __r0 += (d); \
if (__r0 >= (d)) \
if (__r0 < __m) \
__q0--, __r0 += (d); \
} \
__r0 -= __m; \
\
(q) = (unsigned long int) __q1 * __ll_B | __q0; \
(r) = __r0; \
} while (0)
/* If udiv_qrnnd was not defined for this processor, use __udiv_qrnnd_c. */
#if !defined (udiv_qrnnd)
#define UDIV_NEEDS_NORMALIZATION 1
#define udiv_qrnnd __udiv_qrnnd_c
#endif
#if !defined (count_leading_zeros)
extern
#ifdef __STDC__
const
#endif
unsigned char __clz_tab[];
#define count_leading_zeros(count, x) \
do { \
unsigned long int __xr = (x); \
unsigned int __a; \
\
if (LONG_TYPE_SIZE <= 32) \
{ \
__a = __xr < (1<<2*__BITS4) \
? (__xr < (1<<__BITS4) ? 0 : __BITS4) \
: (__xr < (1<<3*__BITS4) ? 2*__BITS4 : 3*__BITS4); \
} \
else \
{ \
for (__a = LONG_TYPE_SIZE - 8; __a > 0; __a -= 8) \
if (((__xr >> __a) & 0xff) != 0) \
break; \
} \
\
(count) = LONG_TYPE_SIZE - (__clz_tab[__xr >> __a] + __a); \
} while (0)
#endif
#ifndef UDIV_NEEDS_NORMALIZATION
#define UDIV_NEEDS_NORMALIZATION 0
#endif
|
