summaryrefslogtreecommitdiff
path: root/include/fpu/softfloat.h
blob: fa4fae224fd3a40f18a029a43e246060bdebe476 (plain)
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
/*
 * QEMU float support
 *
 * The code in this source file is derived from release 2a of the SoftFloat
 * IEC/IEEE Floating-point Arithmetic Package. Those parts of the code (and
 * some later contributions) are provided under that license, as detailed below.
 * It has subsequently been modified by contributors to the QEMU Project,
 * so some portions are provided under:
 *  the SoftFloat-2a license
 *  the BSD license
 *  GPL-v2-or-later
 *
 * Any future contributions to this file after December 1st 2014 will be
 * taken to be licensed under the Softfloat-2a license unless specifically
 * indicated otherwise.
 */

/*
===============================================================================
This C header file is part of the SoftFloat IEC/IEEE Floating-point
Arithmetic Package, Release 2a.

Written by John R. Hauser.  This work was made possible in part by the
International Computer Science Institute, located at Suite 600, 1947 Center
Street, Berkeley, California 94704.  Funding was partially provided by the
National Science Foundation under grant MIP-9311980.  The original version
of this code was written as part of a project to build a fixed-point vector
processor in collaboration with the University of California at Berkeley,
overseen by Profs. Nelson Morgan and John Wawrzynek.  More information
is available through the Web page `http://HTTP.CS.Berkeley.EDU/~jhauser/
arithmetic/SoftFloat.html'.

THIS SOFTWARE IS DISTRIBUTED AS IS, FOR FREE.  Although reasonable effort
has been made to avoid it, THIS SOFTWARE MAY CONTAIN FAULTS THAT WILL AT
TIMES RESULT IN INCORRECT BEHAVIOR.  USE OF THIS SOFTWARE IS RESTRICTED TO
PERSONS AND ORGANIZATIONS WHO CAN AND WILL TAKE FULL RESPONSIBILITY FOR ANY
AND ALL LOSSES, COSTS, OR OTHER PROBLEMS ARISING FROM ITS USE.

Derivative works are acceptable, even for commercial purposes, so long as
(1) they include prominent notice that the work is derivative, and (2) they
include prominent notice akin to these four paragraphs for those parts of
this code that are retained.

===============================================================================
*/

/* BSD licensing:
 * Copyright (c) 2006, Fabrice Bellard
 * All rights reserved.
 *
 * Redistribution and use in source and binary forms, with or without
 * modification, are permitted provided that the following conditions are met:
 *
 * 1. Redistributions of source code must retain the above copyright notice,
 * this list of conditions and the following disclaimer.
 *
 * 2. Redistributions in binary form must reproduce the above copyright notice,
 * this list of conditions and the following disclaimer in the documentation
 * and/or other materials provided with the distribution.
 *
 * 3. Neither the name of the copyright holder nor the names of its contributors
 * may be used to endorse or promote products derived from this software without
 * specific prior written permission.
 *
 * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
 * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
 * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE
 * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
 * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
 * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
 * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
 * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
 * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF
 * THE POSSIBILITY OF SUCH DAMAGE.
 */

/* Portions of this work are licensed under the terms of the GNU GPL,
 * version 2 or later. See the COPYING file in the top-level directory.
 */

#ifndef SOFTFLOAT_H
#define SOFTFLOAT_H

#define LIT64( a ) a##LL

/*----------------------------------------------------------------------------
| Software IEC/IEEE floating-point ordering relations
*----------------------------------------------------------------------------*/
enum {
    float_relation_less      = -1,
    float_relation_equal     =  0,
    float_relation_greater   =  1,
    float_relation_unordered =  2
};

#include "fpu/softfloat-types.h"

static inline void set_float_detect_tininess(int val, float_status *status)
{
    status->float_detect_tininess = val;
}
static inline void set_float_rounding_mode(int val, float_status *status)
{
    status->float_rounding_mode = val;
}
static inline void set_float_exception_flags(int val, float_status *status)
{
    status->float_exception_flags = val;
}
static inline void set_floatx80_rounding_precision(int val,
                                                   float_status *status)
{
    status->floatx80_rounding_precision = val;
}
static inline void set_flush_to_zero(flag val, float_status *status)
{
    status->flush_to_zero = val;
}
static inline void set_flush_inputs_to_zero(flag val, float_status *status)
{
    status->flush_inputs_to_zero = val;
}
static inline void set_default_nan_mode(flag val, float_status *status)
{
    status->default_nan_mode = val;
}
static inline void set_snan_bit_is_one(flag val, float_status *status)
{
    status->snan_bit_is_one = val;
}
static inline int get_float_detect_tininess(float_status *status)
{
    return status->float_detect_tininess;
}
static inline int get_float_rounding_mode(float_status *status)
{
    return status->float_rounding_mode;
}
static inline int get_float_exception_flags(float_status *status)
{
    return status->float_exception_flags;
}
static inline int get_floatx80_rounding_precision(float_status *status)
{
    return status->floatx80_rounding_precision;
}
static inline flag get_flush_to_zero(float_status *status)
{
    return status->flush_to_zero;
}
static inline flag get_flush_inputs_to_zero(float_status *status)
{
    return status->flush_inputs_to_zero;
}
static inline flag get_default_nan_mode(float_status *status)
{
    return status->default_nan_mode;
}

/*----------------------------------------------------------------------------
| Routine to raise any or all of the software IEC/IEEE floating-point
| exception flags.
*----------------------------------------------------------------------------*/
void float_raise(uint8_t flags, float_status *status);

/*----------------------------------------------------------------------------
| If `a' is denormal and we are in flush-to-zero mode then set the
| input-denormal exception and return zero. Otherwise just return the value.
*----------------------------------------------------------------------------*/
float16 float16_squash_input_denormal(float16 a, float_status *status);
float32 float32_squash_input_denormal(float32 a, float_status *status);
float64 float64_squash_input_denormal(float64 a, float_status *status);

/*----------------------------------------------------------------------------
| Options to indicate which negations to perform in float*_muladd()
| Using these differs from negating an input or output before calling
| the muladd function in that this means that a NaN doesn't have its
| sign bit inverted before it is propagated.
| We also support halving the result before rounding, as a special
| case to support the ARM fused-sqrt-step instruction FRSQRTS.
*----------------------------------------------------------------------------*/
enum {
    float_muladd_negate_c = 1,
    float_muladd_negate_product = 2,
    float_muladd_negate_result = 4,
    float_muladd_halve_result = 8,
};

/*----------------------------------------------------------------------------
| Software IEC/IEEE integer-to-floating-point conversion routines.
*----------------------------------------------------------------------------*/
float32 int16_to_float32(int16_t, float_status *status);
float32 int32_to_float32(int32_t, float_status *status);
float64 int16_to_float64(int16_t, float_status *status);
float64 int32_to_float64(int32_t, float_status *status);
float32 uint16_to_float32(uint16_t, float_status *status);
float32 uint32_to_float32(uint32_t, float_status *status);
float64 uint16_to_float64(uint16_t, float_status *status);
float64 uint32_to_float64(uint32_t, float_status *status);
floatx80 int32_to_floatx80(int32_t, float_status *status);
float128 int32_to_float128(int32_t, float_status *status);
float32 int64_to_float32(int64_t, float_status *status);
float64 int64_to_float64(int64_t, float_status *status);
floatx80 int64_to_floatx80(int64_t, float_status *status);
float128 int64_to_float128(int64_t, float_status *status);
float32 uint64_to_float32(uint64_t, float_status *status);
float64 uint64_to_float64(uint64_t, float_status *status);
float128 uint64_to_float128(uint64_t, float_status *status);

/*----------------------------------------------------------------------------
| Software half-precision conversion routines.
*----------------------------------------------------------------------------*/
float16 float32_to_float16(float32, flag, float_status *status);
float32 float16_to_float32(float16, flag, float_status *status);
float16 float64_to_float16(float64 a, flag ieee, float_status *status);
float64 float16_to_float64(float16 a, flag ieee, float_status *status);
int16_t float16_to_int16(float16, float_status *status);
uint16_t float16_to_uint16(float16 a, float_status *status);
int16_t float16_to_int16_round_to_zero(float16, float_status *status);
uint16_t float16_to_uint16_round_to_zero(float16 a, float_status *status);
int32_t float16_to_int32(float16, float_status *status);
uint32_t float16_to_uint32(float16 a, float_status *status);
int32_t float16_to_int32_round_to_zero(float16, float_status *status);
uint32_t float16_to_uint32_round_to_zero(float16 a, float_status *status);
int64_t float16_to_int64(float16, float_status *status);
uint64_t float16_to_uint64(float16 a, float_status *status);
int64_t float16_to_int64_round_to_zero(float16, float_status *status);
uint64_t float16_to_uint64_round_to_zero(float16 a, float_status *status);
float16 int16_to_float16(int16_t a, float_status *status);
float16 int32_to_float16(int32_t a, float_status *status);
float16 int64_to_float16(int64_t a, float_status *status);
float16 uint16_to_float16(uint16_t a, float_status *status);
float16 uint32_to_float16(uint32_t a, float_status *status);
float16 uint64_to_float16(uint64_t a, float_status *status);

/*----------------------------------------------------------------------------
| Software half-precision operations.
*----------------------------------------------------------------------------*/

float16 float16_round_to_int(float16, float_status *status);
float16 float16_add(float16, float16, float_status *status);
float16 float16_sub(float16, float16, float_status *status);
float16 float16_mul(float16, float16, float_status *status);
float16 float16_muladd(float16, float16, float16, int, float_status *status);
float16 float16_div(float16, float16, float_status *status);
float16 float16_scalbn(float16, int, float_status *status);
float16 float16_min(float16, float16, float_status *status);
float16 float16_max(float16, float16, float_status *status);
float16 float16_minnum(float16, float16, float_status *status);
float16 float16_maxnum(float16, float16, float_status *status);
float16 float16_minnummag(float16, float16, float_status *status);
float16 float16_maxnummag(float16, float16, float_status *status);
float16 float16_sqrt(float16, float_status *status);
int float16_compare(float16, float16, float_status *status);
int float16_compare_quiet(float16, float16, float_status *status);

int float16_is_quiet_nan(float16, float_status *status);
int float16_is_signaling_nan(float16, float_status *status);
float16 float16_maybe_silence_nan(float16, float_status *status);

static inline int float16_is_any_nan(float16 a)
{
    return ((float16_val(a) & ~0x8000) > 0x7c00);
}

static inline int float16_is_neg(float16 a)
{
    return float16_val(a) >> 15;
}

static inline int float16_is_infinity(float16 a)
{
    return (float16_val(a) & 0x7fff) == 0x7c00;
}

static inline int float16_is_zero(float16 a)
{
    return (float16_val(a) & 0x7fff) == 0;
}

static inline int float16_is_zero_or_denormal(float16 a)
{
    return (float16_val(a) & 0x7c00) == 0;
}

static inline float16 float16_abs(float16 a)
{
    /* Note that abs does *not* handle NaN specially, nor does
     * it flush denormal inputs to zero.
     */
    return make_float16(float16_val(a) & 0x7fff);
}

static inline float16 float16_chs(float16 a)
{
    /* Note that chs does *not* handle NaN specially, nor does
     * it flush denormal inputs to zero.
     */
    return make_float16(float16_val(a) ^ 0x8000);
}

static inline float16 float16_set_sign(float16 a, int sign)
{
    return make_float16((float16_val(a) & 0x7fff) | (sign << 15));
}

#define float16_zero make_float16(0)
#define float16_half make_float16(0x3800)
#define float16_one make_float16(0x3c00)
#define float16_one_point_five make_float16(0x3e00)
#define float16_two make_float16(0x4000)
#define float16_three make_float16(0x4200)
#define float16_infinity make_float16(0x7c00)

/*----------------------------------------------------------------------------
| The pattern for a default generated half-precision NaN.
*----------------------------------------------------------------------------*/
float16 float16_default_nan(float_status *status);

/*----------------------------------------------------------------------------
| Software IEC/IEEE single-precision conversion routines.
*----------------------------------------------------------------------------*/
int16_t float32_to_int16(float32, float_status *status);
uint16_t float32_to_uint16(float32, float_status *status);
int16_t float32_to_int16_round_to_zero(float32, float_status *status);
uint16_t float32_to_uint16_round_to_zero(float32, float_status *status);
int32_t float32_to_int32(float32, float_status *status);
int32_t float32_to_int32_round_to_zero(float32, float_status *status);
uint32_t float32_to_uint32(float32, float_status *status);
uint32_t float32_to_uint32_round_to_zero(float32, float_status *status);
int64_t float32_to_int64(float32, float_status *status);
uint64_t float32_to_uint64(float32, float_status *status);
uint64_t float32_to_uint64_round_to_zero(float32, float_status *status);
int64_t float32_to_int64_round_to_zero(float32, float_status *status);
float64 float32_to_float64(float32, float_status *status);
floatx80 float32_to_floatx80(float32, float_status *status);
float128 float32_to_float128(float32, float_status *status);

/*----------------------------------------------------------------------------
| Software IEC/IEEE single-precision operations.
*----------------------------------------------------------------------------*/
float32 float32_round_to_int(float32, float_status *status);
float32 float32_add(float32, float32, float_status *status);
float32 float32_sub(float32, float32, float_status *status);
float32 float32_mul(float32, float32, float_status *status);
float32 float32_div(float32, float32, float_status *status);
float32 float32_rem(float32, float32, float_status *status);
float32 float32_muladd(float32, float32, float32, int, float_status *status);
float32 float32_sqrt(float32, float_status *status);
float32 float32_exp2(float32, float_status *status);
float32 float32_log2(float32, float_status *status);
int float32_eq(float32, float32, float_status *status);
int float32_le(float32, float32, float_status *status);
int float32_lt(float32, float32, float_status *status);
int float32_unordered(float32, float32, float_status *status);
int float32_eq_quiet(float32, float32, float_status *status);
int float32_le_quiet(float32, float32, float_status *status);
int float32_lt_quiet(float32, float32, float_status *status);
int float32_unordered_quiet(float32, float32, float_status *status);
int float32_compare(float32, float32, float_status *status);
int float32_compare_quiet(float32, float32, float_status *status);
float32 float32_min(float32, float32, float_status *status);
float32 float32_max(float32, float32, float_status *status);
float32 float32_minnum(float32, float32, float_status *status);
float32 float32_maxnum(float32, float32, float_status *status);
float32 float32_minnummag(float32, float32, float_status *status);
float32 float32_maxnummag(float32, float32, float_status *status);
int float32_is_quiet_nan(float32, float_status *status);
int float32_is_signaling_nan(float32, float_status *status);
float32 float32_maybe_silence_nan(float32, float_status *status);
float32 float32_scalbn(float32, int, float_status *status);

static inline float32 float32_abs(float32 a)
{
    /* Note that abs does *not* handle NaN specially, nor does
     * it flush denormal inputs to zero.
     */
    return make_float32(float32_val(a) & 0x7fffffff);
}

static inline float32 float32_chs(float32 a)
{
    /* Note that chs does *not* handle NaN specially, nor does
     * it flush denormal inputs to zero.
     */
    return make_float32(float32_val(a) ^ 0x80000000);
}

static inline int float32_is_infinity(float32 a)
{
    return (float32_val(a) & 0x7fffffff) == 0x7f800000;
}

static inline int float32_is_neg(float32 a)
{
    return float32_val(a) >> 31;
}

static inline int float32_is_zero(float32 a)
{
    return (float32_val(a) & 0x7fffffff) == 0;
}

static inline int float32_is_any_nan(float32 a)
{
    return ((float32_val(a) & ~(1 << 31)) > 0x7f800000UL);
}

static inline int float32_is_zero_or_denormal(float32 a)
{
    return (float32_val(a) & 0x7f800000) == 0;
}

static inline float32 float32_set_sign(float32 a, int sign)
{
    return make_float32((float32_val(a) & 0x7fffffff) | (sign << 31));
}

#define float32_zero make_float32(0)
#define float32_half make_float32(0x3f000000)
#define float32_one make_float32(0x3f800000)
#define float32_one_point_five make_float32(0x3fc00000)
#define float32_two make_float32(0x40000000)
#define float32_three make_float32(0x40400000)
#define float32_infinity make_float32(0x7f800000)

/*----------------------------------------------------------------------------
| Packs the sign `zSign', exponent `zExp', and significand `zSig' into a
| single-precision floating-point value, returning the result.  After being
| shifted into the proper positions, the three fields are simply added
| together to form the result.  This means that any integer portion of `zSig'
| will be added into the exponent.  Since a properly normalized significand
| will have an integer portion equal to 1, the `zExp' input should be 1 less
| than the desired result exponent whenever `zSig' is a complete, normalized
| significand.
*----------------------------------------------------------------------------*/

static inline float32 packFloat32(flag zSign, int zExp, uint32_t zSig)
{
    return make_float32(
          (((uint32_t)zSign) << 31) + (((uint32_t)zExp) << 23) + zSig);
}

/*----------------------------------------------------------------------------
| The pattern for a default generated single-precision NaN.
*----------------------------------------------------------------------------*/
float32 float32_default_nan(float_status *status);

/*----------------------------------------------------------------------------
| Software IEC/IEEE double-precision conversion routines.
*----------------------------------------------------------------------------*/
int16_t float64_to_int16(float64, float_status *status);
uint16_t float64_to_uint16(float64, float_status *status);
int16_t float64_to_int16_round_to_zero(float64, float_status *status);
uint16_t float64_to_uint16_round_to_zero(float64, float_status *status);
int32_t float64_to_int32(float64, float_status *status);
int32_t float64_to_int32_round_to_zero(float64, float_status *status);
uint32_t float64_to_uint32(float64, float_status *status);
uint32_t float64_to_uint32_round_to_zero(float64, float_status *status);
int64_t float64_to_int64(float64, float_status *status);
int64_t float64_to_int64_round_to_zero(float64, float_status *status);
uint64_t float64_to_uint64(float64 a, float_status *status);
uint64_t float64_to_uint64_round_to_zero(float64 a, float_status *status);
float32 float64_to_float32(float64, float_status *status);
floatx80 float64_to_floatx80(float64, float_status *status);
float128 float64_to_float128(float64, float_status *status);

/*----------------------------------------------------------------------------
| Software IEC/IEEE double-precision operations.
*----------------------------------------------------------------------------*/
float64 float64_round_to_int(float64, float_status *status);
float64 float64_trunc_to_int(float64, float_status *status);
float64 float64_add(float64, float64, float_status *status);
float64 float64_sub(float64, float64, float_status *status);
float64 float64_mul(float64, float64, float_status *status);
float64 float64_div(float64, float64, float_status *status);
float64 float64_rem(float64, float64, float_status *status);
float64 float64_muladd(float64, float64, float64, int, float_status *status);
float64 float64_sqrt(float64, float_status *status);
float64 float64_log2(float64, float_status *status);
int float64_eq(float64, float64, float_status *status);
int float64_le(float64, float64, float_status *status);
int float64_lt(float64, float64, float_status *status);
int float64_unordered(float64, float64, float_status *status);
int float64_eq_quiet(float64, float64, float_status *status);
int float64_le_quiet(float64, float64, float_status *status);
int float64_lt_quiet(float64, float64, float_status *status);
int float64_unordered_quiet(float64, float64, float_status *status);
int float64_compare(float64, float64, float_status *status);
int float64_compare_quiet(float64, float64, float_status *status);
float64 float64_min(float64, float64, float_status *status);
float64 float64_max(float64, float64, float_status *status);
float64 float64_minnum(float64, float64, float_status *status);
float64 float64_maxnum(float64, float64, float_status *status);
float64 float64_minnummag(float64, float64, float_status *status);
float64 float64_maxnummag(float64, float64, float_status *status);
int float64_is_quiet_nan(float64 a, float_status *status);
int float64_is_signaling_nan(float64, float_status *status);
float64 float64_maybe_silence_nan(float64, float_status *status);
float64 float64_scalbn(float64, int, float_status *status);

static inline float64 float64_abs(float64 a)
{
    /* Note that abs does *not* handle NaN specially, nor does
     * it flush denormal inputs to zero.
     */
    return make_float64(float64_val(a) & 0x7fffffffffffffffLL);
}

static inline float64 float64_chs(float64 a)
{
    /* Note that chs does *not* handle NaN specially, nor does
     * it flush denormal inputs to zero.
     */
    return make_float64(float64_val(a) ^ 0x8000000000000000LL);
}

static inline int float64_is_infinity(float64 a)
{
    return (float64_val(a) & 0x7fffffffffffffffLL ) == 0x7ff0000000000000LL;
}

static inline int float64_is_neg(float64 a)
{
    return float64_val(a) >> 63;
}

static inline int float64_is_zero(float64 a)
{
    return (float64_val(a) & 0x7fffffffffffffffLL) == 0;
}

static inline int float64_is_any_nan(float64 a)
{
    return ((float64_val(a) & ~(1ULL << 63)) > 0x7ff0000000000000ULL);
}

static inline int float64_is_zero_or_denormal(float64 a)
{
    return (float64_val(a) & 0x7ff0000000000000LL) == 0;
}

static inline float64 float64_set_sign(float64 a, int sign)
{
    return make_float64((float64_val(a) & 0x7fffffffffffffffULL)
                        | ((int64_t)sign << 63));
}

#define float64_zero make_float64(0)
#define float64_half make_float64(0x3fe0000000000000LL)
#define float64_one make_float64(0x3ff0000000000000LL)
#define float64_one_point_five make_float64(0x3FF8000000000000ULL)
#define float64_two make_float64(0x4000000000000000ULL)
#define float64_three make_float64(0x4008000000000000ULL)
#define float64_ln2 make_float64(0x3fe62e42fefa39efLL)
#define float64_infinity make_float64(0x7ff0000000000000LL)

/*----------------------------------------------------------------------------
| The pattern for a default generated double-precision NaN.
*----------------------------------------------------------------------------*/
float64 float64_default_nan(float_status *status);

/*----------------------------------------------------------------------------
| Software IEC/IEEE extended double-precision conversion routines.
*----------------------------------------------------------------------------*/
int32_t floatx80_to_int32(floatx80, float_status *status);
int32_t floatx80_to_int32_round_to_zero(floatx80, float_status *status);
int64_t floatx80_to_int64(floatx80, float_status *status);
int64_t floatx80_to_int64_round_to_zero(floatx80, float_status *status);
float32 floatx80_to_float32(floatx80, float_status *status);
float64 floatx80_to_float64(floatx80, float_status *status);
float128 floatx80_to_float128(floatx80, float_status *status);

/*----------------------------------------------------------------------------
| Software IEC/IEEE extended double-precision operations.
*----------------------------------------------------------------------------*/
floatx80 floatx80_round(floatx80 a, float_status *status);
floatx80 floatx80_round_to_int(floatx80, float_status *status);
floatx80 floatx80_add(floatx80, floatx80, float_status *status);
floatx80 floatx80_sub(floatx80, floatx80, float_status *status);
floatx80 floatx80_mul(floatx80, floatx80, float_status *status);
floatx80 floatx80_div(floatx80, floatx80, float_status *status);
floatx80 floatx80_rem(floatx80, floatx80, float_status *status);
floatx80 floatx80_sqrt(floatx80, float_status *status);
int floatx80_eq(floatx80, floatx80, float_status *status);
int floatx80_le(floatx80, floatx80, float_status *status);
int floatx80_lt(floatx80, floatx80, float_status *status);
int floatx80_unordered(floatx80, floatx80, float_status *status);
int floatx80_eq_quiet(floatx80, floatx80, float_status *status);
int floatx80_le_quiet(floatx80, floatx80, float_status *status);
int floatx80_lt_quiet(floatx80, floatx80, float_status *status);
int floatx80_unordered_quiet(floatx80, floatx80, float_status *status);
int floatx80_compare(floatx80, floatx80, float_status *status);
int floatx80_compare_quiet(floatx80, floatx80, float_status *status);
int floatx80_is_quiet_nan(floatx80, float_status *status);
int floatx80_is_signaling_nan(floatx80, float_status *status);
floatx80 floatx80_maybe_silence_nan(floatx80, float_status *status);
floatx80 floatx80_scalbn(floatx80, int, float_status *status);

static inline floatx80 floatx80_abs(floatx80 a)
{
    a.high &= 0x7fff;
    return a;
}

static inline floatx80 floatx80_chs(floatx80 a)
{
    a.high ^= 0x8000;
    return a;
}

static inline int floatx80_is_infinity(floatx80 a)
{
    return (a.high & 0x7fff) == 0x7fff && a.low == 0x8000000000000000LL;
}

static inline int floatx80_is_neg(floatx80 a)
{
    return a.high >> 15;
}

static inline int floatx80_is_zero(floatx80 a)
{
    return (a.high & 0x7fff) == 0 && a.low == 0;
}

static inline int floatx80_is_zero_or_denormal(floatx80 a)
{
    return (a.high & 0x7fff) == 0;
}

static inline int floatx80_is_any_nan(floatx80 a)
{
    return ((a.high & 0x7fff) == 0x7fff) && (a.low<<1);
}

/*----------------------------------------------------------------------------
| Return whether the given value is an invalid floatx80 encoding.
| Invalid floatx80 encodings arise when the integer bit is not set, but
| the exponent is not zero. The only times the integer bit is permitted to
| be zero is in subnormal numbers and the value zero.
| This includes what the Intel software developer's manual calls pseudo-NaNs,
| pseudo-infinities and un-normal numbers. It does not include
| pseudo-denormals, which must still be correctly handled as inputs even
| if they are never generated as outputs.
*----------------------------------------------------------------------------*/
static inline bool floatx80_invalid_encoding(floatx80 a)
{
    return (a.low & (1ULL << 63)) == 0 && (a.high & 0x7FFF) != 0;
}

#define floatx80_zero make_floatx80(0x0000, 0x0000000000000000LL)
#define floatx80_one make_floatx80(0x3fff, 0x8000000000000000LL)
#define floatx80_ln2 make_floatx80(0x3ffe, 0xb17217f7d1cf79acLL)
#define floatx80_pi make_floatx80(0x4000, 0xc90fdaa22168c235LL)
#define floatx80_half make_floatx80(0x3ffe, 0x8000000000000000LL)
#define floatx80_infinity make_floatx80(0x7fff, 0x8000000000000000LL)

/*----------------------------------------------------------------------------
| Returns the fraction bits of the extended double-precision floating-point
| value `a'.
*----------------------------------------------------------------------------*/

static inline uint64_t extractFloatx80Frac(floatx80 a)
{
    return a.low;
}

/*----------------------------------------------------------------------------
| Returns the exponent bits of the extended double-precision floating-point
| value `a'.
*----------------------------------------------------------------------------*/

static inline int32_t extractFloatx80Exp(floatx80 a)
{
    return a.high & 0x7FFF;
}

/*----------------------------------------------------------------------------
| Returns the sign bit of the extended double-precision floating-point value
| `a'.
*----------------------------------------------------------------------------*/

static inline flag extractFloatx80Sign(floatx80 a)
{
    return a.high >> 15;
}

/*----------------------------------------------------------------------------
| Packs the sign `zSign', exponent `zExp', and significand `zSig' into an
| extended double-precision floating-point value, returning the result.
*----------------------------------------------------------------------------*/

static inline floatx80 packFloatx80(flag zSign, int32_t zExp, uint64_t zSig)
{
    floatx80 z;

    z.low = zSig;
    z.high = (((uint16_t)zSign) << 15) + zExp;
    return z;
}

/*----------------------------------------------------------------------------
| Normalizes the subnormal extended double-precision floating-point value
| represented by the denormalized significand `aSig'.  The normalized exponent
| and significand are stored at the locations pointed to by `zExpPtr' and
| `zSigPtr', respectively.
*----------------------------------------------------------------------------*/

void normalizeFloatx80Subnormal(uint64_t aSig, int32_t *zExpPtr,
                                uint64_t *zSigPtr);

/*----------------------------------------------------------------------------
| Takes two extended double-precision floating-point values `a' and `b', one
| of which is a NaN, and returns the appropriate NaN result.  If either `a' or
| `b' is a signaling NaN, the invalid exception is raised.
*----------------------------------------------------------------------------*/

floatx80 propagateFloatx80NaN(floatx80 a, floatx80 b, float_status *status);

/*----------------------------------------------------------------------------
| Takes an abstract floating-point value having sign `zSign', exponent `zExp',
| and extended significand formed by the concatenation of `zSig0' and `zSig1',
| and returns the proper extended double-precision floating-point value
| corresponding to the abstract input.  Ordinarily, the abstract value is
| rounded and packed into the extended double-precision format, with the
| inexact exception raised if the abstract input cannot be represented
| exactly.  However, if the abstract value is too large, the overflow and
| inexact exceptions are raised and an infinity or maximal finite value is
| returned.  If the abstract value is too small, the input value is rounded to
| a subnormal number, and the underflow and inexact exceptions are raised if
| the abstract input cannot be represented exactly as a subnormal extended
| double-precision floating-point number.
|     If `roundingPrecision' is 32 or 64, the result is rounded to the same
| number of bits as single or double precision, respectively.  Otherwise, the
| result is rounded to the full precision of the extended double-precision
| format.
|     The input significand must be normalized or smaller.  If the input
| significand is not normalized, `zExp' must be 0; in that case, the result
| returned is a subnormal number, and it must not require rounding.  The
| handling of underflow and overflow follows the IEC/IEEE Standard for Binary
| Floating-Point Arithmetic.
*----------------------------------------------------------------------------*/

floatx80 roundAndPackFloatx80(int8_t roundingPrecision, flag zSign,
                              int32_t zExp, uint64_t zSig0, uint64_t zSig1,
                              float_status *status);

/*----------------------------------------------------------------------------
| Takes an abstract floating-point value having sign `zSign', exponent
| `zExp', and significand formed by the concatenation of `zSig0' and `zSig1',
| and returns the proper extended double-precision floating-point value
| corresponding to the abstract input.  This routine is just like
| `roundAndPackFloatx80' except that the input significand does not have to be
| normalized.
*----------------------------------------------------------------------------*/

floatx80 normalizeRoundAndPackFloatx80(int8_t roundingPrecision,
                                       flag zSign, int32_t zExp,
                                       uint64_t zSig0, uint64_t zSig1,
                                       float_status *status);

/*----------------------------------------------------------------------------
| The pattern for a default generated extended double-precision NaN.
*----------------------------------------------------------------------------*/
floatx80 floatx80_default_nan(float_status *status);

/*----------------------------------------------------------------------------
| Software IEC/IEEE quadruple-precision conversion routines.
*----------------------------------------------------------------------------*/
int32_t float128_to_int32(float128, float_status *status);
int32_t float128_to_int32_round_to_zero(float128, float_status *status);
int64_t float128_to_int64(float128, float_status *status);
int64_t float128_to_int64_round_to_zero(float128, float_status *status);
uint64_t float128_to_uint64(float128, float_status *status);
uint64_t float128_to_uint64_round_to_zero(float128, float_status *status);
uint32_t float128_to_uint32_round_to_zero(float128, float_status *status);
float32 float128_to_float32(float128, float_status *status);
float64 float128_to_float64(float128, float_status *status);
floatx80 float128_to_floatx80(float128, float_status *status);

/*----------------------------------------------------------------------------
| Software IEC/IEEE quadruple-precision operations.
*----------------------------------------------------------------------------*/
float128 float128_round_to_int(float128, float_status *status);
float128 float128_add(float128, float128, float_status *status);
float128 float128_sub(float128, float128, float_status *status);
float128 float128_mul(float128, float128, float_status *status);
float128 float128_div(float128, float128, float_status *status);
float128 float128_rem(float128, float128, float_status *status);
float128 float128_sqrt(float128, float_status *status);
int float128_eq(float128, float128, float_status *status);
int float128_le(float128, float128, float_status *status);
int float128_lt(float128, float128, float_status *status);
int float128_unordered(float128, float128, float_status *status);
int float128_eq_quiet(float128, float128, float_status *status);
int float128_le_quiet(float128, float128, float_status *status);
int float128_lt_quiet(float128, float128, float_status *status);
int float128_unordered_quiet(float128, float128, float_status *status);
int float128_compare(float128, float128, float_status *status);
int float128_compare_quiet(float128, float128, float_status *status);
int float128_is_quiet_nan(float128, float_status *status);
int float128_is_signaling_nan(float128, float_status *status);
float128 float128_maybe_silence_nan(float128, float_status *status);
float128 float128_scalbn(float128, int, float_status *status);

static inline float128 float128_abs(float128 a)
{
    a.high &= 0x7fffffffffffffffLL;
    return a;
}

static inline float128 float128_chs(float128 a)
{
    a.high ^= 0x8000000000000000LL;
    return a;
}

static inline int float128_is_infinity(float128 a)
{
    return (a.high & 0x7fffffffffffffffLL) == 0x7fff000000000000LL && a.low == 0;
}

static inline int float128_is_neg(float128 a)
{
    return a.high >> 63;
}

static inline int float128_is_zero(float128 a)
{
    return (a.high & 0x7fffffffffffffffLL) == 0 && a.low == 0;
}

static inline int float128_is_zero_or_denormal(float128 a)
{
    return (a.high & 0x7fff000000000000LL) == 0;
}

static inline int float128_is_any_nan(float128 a)
{
    return ((a.high >> 48) & 0x7fff) == 0x7fff &&
        ((a.low != 0) || ((a.high & 0xffffffffffffLL) != 0));
}

#define float128_zero make_float128(0, 0)

/*----------------------------------------------------------------------------
| The pattern for a default generated quadruple-precision NaN.
*----------------------------------------------------------------------------*/
float128 float128_default_nan(float_status *status);

#endif /* SOFTFLOAT_H */