File: softfloat-specialize.h

package info (click to toggle)
fs-uae 3.0.5%2Bdfsg-1
  • links: PTS, VCS
  • area: main
  • in suites: bullseye
  • size: 86,408 kB
  • sloc: cpp: 264,626; python: 139,849; ansic: 110,926; sh: 4,686; makefile: 2,317; asm: 275; xml: 10
file content (793 lines) | stat: -rw-r--r-- 31,930 bytes parent folder | download | duplicates (10)
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
/*============================================================================
This C source fragment is part of the SoftFloat IEC/IEEE Floating-point
Arithmetic Package, Release 2b.

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://www.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 ALL LOSSES,
COSTS, OR OTHER PROBLEMS THEY INCUR DUE TO THE SOFTWARE, AND WHO FURTHERMORE
EFFECTIVELY INDEMNIFY JOHN HAUSER AND THE INTERNATIONAL COMPUTER SCIENCE
INSTITUTE (possibly via similar legal warning) AGAINST ALL LOSSES, COSTS, OR
OTHER PROBLEMS INCURRED BY THEIR CUSTOMERS AND CLIENTS DUE TO THE SOFTWARE.

Derivative works are acceptable, even for commercial purposes, so long as
(1) the source code for the derivative work includes prominent notice that
the work is derivative, and (2) the source code includes prominent notice with
these four paragraphs for those parts of this code that are retained.
=============================================================================*/

#ifndef _SOFTFLOAT_SPECIALIZE_H_
#define _SOFTFLOAT_SPECIALIZE_H_

#include "softfloat.h"

/*============================================================================
 * Adapted for Bochs (x86 achitecture simulator) by
 *            Stanislav Shwartsman [sshwarts at sourceforge net]
 * ==========================================================================*/

#define int16_indefinite ((Bit16s)0x8000)
#define int32_indefinite ((Bit32s)0x80000000)
#define int64_indefinite BX_CONST64(0x8000000000000000)

#define uint16_indefinite (0xffff)
#define uint32_indefinite (0xffffffff)
#define uint64_indefinite BX_CONST64(0xffffffffffffffff)

/*----------------------------------------------------------------------------
| Internal canonical NaN format.
*----------------------------------------------------------------------------*/

typedef struct {
    int sign;
    Bit64u hi, lo;
} commonNaNT;

#ifdef FLOAT16

/*----------------------------------------------------------------------------
| The pattern for a default generated half-precision NaN.
*----------------------------------------------------------------------------*/
const float16 float16_default_nan = 0xFE00;

#define float16_fraction extractFloat16Frac
#define float16_exp extractFloat16Exp
#define float16_sign extractFloat16Sign

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

BX_CPP_INLINE Bit16u extractFloat16Frac(float16 a)
{
    return a & 0x3FF;
}

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

BX_CPP_INLINE Bit16s extractFloat16Exp(float16 a)
{
    return (a>>10) & 0x1F;
}

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

BX_CPP_INLINE int extractFloat16Sign(float16 a)
{
    return a>>15;
}

/*----------------------------------------------------------------------------
| 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.
*----------------------------------------------------------------------------*/

BX_CPP_INLINE float16 packFloat16(int zSign, int zExp, Bit16u zSig)
{
    return (((Bit16u) zSign)<<15) + (((Bit16u) zExp)<<10) + zSig;
}

/*----------------------------------------------------------------------------
| Returns 1 if the half-precision floating-point value `a' is a NaN;
| otherwise returns 0.
*----------------------------------------------------------------------------*/

BX_CPP_INLINE int float16_is_nan(float16 a)
{
    return (0xF800 < (Bit16u) (a<<1));
}

/*----------------------------------------------------------------------------
| Returns 1 if the half-precision floating-point value `a' is a signaling
| NaN; otherwise returns 0.
*----------------------------------------------------------------------------*/

BX_CPP_INLINE int float16_is_signaling_nan(float16 a)
{
    return (((a>>9) & 0x3F) == 0x3E) && (a & 0x1FF);
}

/*----------------------------------------------------------------------------
| Returns 1 if the half-precision floating-point value `a' is denormal;
| otherwise returns 0.
*----------------------------------------------------------------------------*/

BX_CPP_INLINE int float16_is_denormal(float16 a)
{
   return (extractFloat16Exp(a) == 0) && (extractFloat16Frac(a) != 0);
}

/*----------------------------------------------------------------------------
| Convert float16 denormals to zero.
*----------------------------------------------------------------------------*/

BX_CPP_INLINE float16 float16_denormal_to_zero(float16 a)
{
  if (float16_is_denormal(a)) a &= 0x8000;
  return a;
}

/*----------------------------------------------------------------------------
| Returns the result of converting the half-precision floating-point NaN
| `a' to the canonical NaN format. If `a' is a signaling NaN, the invalid
| exception is raised.
*----------------------------------------------------------------------------*/

BX_CPP_INLINE commonNaNT float16ToCommonNaN(float16 a, float_status_t &status)
{
    commonNaNT z;
    if (float16_is_signaling_nan(a)) float_raise(status, float_flag_invalid);
    z.sign = a>>15;
    z.lo = 0;
    z.hi = ((Bit64u) a)<<54;
    return z;
}

/*----------------------------------------------------------------------------
| Returns the result of converting the canonical NaN `a' to the half-
| precision floating-point format.
*----------------------------------------------------------------------------*/

BX_CPP_INLINE float16 commonNaNToFloat16(commonNaNT a)
{
    return (((Bit16u) a.sign)<<15) | 0x7E00 | (Bit16u)(a.hi>>54);
}

#endif

/*----------------------------------------------------------------------------
| Commonly used single-precision floating point constants
*----------------------------------------------------------------------------*/
const float32 float32_negative_inf  = 0xff800000;
const float32 float32_positive_inf  = 0x7f800000;
const float32 float32_negative_zero = 0x80000000;
const float32 float32_positive_zero = 0x00000000;
const float32 float32_negative_one  = 0xbf800000;
const float32 float32_positive_one  = 0x3f800000;
const float32 float32_max_float     = 0x7f7fffff;
const float32 float32_min_float     = 0xff7fffff;

/*----------------------------------------------------------------------------
| The pattern for a default generated single-precision NaN.
*----------------------------------------------------------------------------*/
const float32 float32_default_nan   = 0xffc00000;

#define float32_fraction extractFloat32Frac
#define float32_exp extractFloat32Exp
#define float32_sign extractFloat32Sign

#define FLOAT32_EXP_BIAS 0x7F

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

BX_CPP_INLINE Bit32u extractFloat32Frac(float32 a)
{
    return a & 0x007FFFFF;
}

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

BX_CPP_INLINE Bit16s extractFloat32Exp(float32 a)
{
    return (a>>23) & 0xFF;
}

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

BX_CPP_INLINE int extractFloat32Sign(float32 a)
{
    return a>>31;
}

/*----------------------------------------------------------------------------
| 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.
*----------------------------------------------------------------------------*/

BX_CPP_INLINE float32 packFloat32(int zSign, Bit16s zExp, Bit32u zSig)
{
    return (((Bit32u) zSign)<<31) + (((Bit32u) zExp)<<23) + zSig;
}

/*----------------------------------------------------------------------------
| Returns 1 if the single-precision floating-point value `a' is a NaN;
| otherwise returns 0.
*----------------------------------------------------------------------------*/

BX_CPP_INLINE int float32_is_nan(float32 a)
{
    return (0xFF000000 < (Bit32u) (a<<1));
}

/*----------------------------------------------------------------------------
| Returns 1 if the single-precision floating-point value `a' is a signaling
| NaN; otherwise returns 0.
*----------------------------------------------------------------------------*/

BX_CPP_INLINE int float32_is_signaling_nan(float32 a)
{
    return (((a>>22) & 0x1FF) == 0x1FE) && (a & 0x003FFFFF);
}

/*----------------------------------------------------------------------------
| Returns 1 if the single-precision floating-point value `a' is denormal;
| otherwise returns 0.
*----------------------------------------------------------------------------*/

BX_CPP_INLINE int float32_is_denormal(float32 a)
{
   return (extractFloat32Exp(a) == 0) && (extractFloat32Frac(a) != 0);
}

/*----------------------------------------------------------------------------
| Convert float32 denormals to zero.
*----------------------------------------------------------------------------*/

BX_CPP_INLINE float32 float32_denormal_to_zero(float32 a)
{
  if (float32_is_denormal(a)) a &= 0x80000000;
  return a;
}

/*----------------------------------------------------------------------------
| Returns the result of converting the single-precision floating-point NaN
| `a' to the canonical NaN format.  If `a' is a signaling NaN, the invalid
| exception is raised.
*----------------------------------------------------------------------------*/

BX_CPP_INLINE commonNaNT float32ToCommonNaN(float32 a, float_status_t &status)
{
    commonNaNT z;
    if (float32_is_signaling_nan(a)) float_raise(status, float_flag_invalid);
    z.sign = a>>31;
    z.lo = 0;
    z.hi = ((Bit64u) a)<<41;
    return z;
}

/*----------------------------------------------------------------------------
| Returns the result of converting the canonical NaN `a' to the single-
| precision floating-point format.
*----------------------------------------------------------------------------*/

BX_CPP_INLINE float32 commonNaNToFloat32(commonNaNT a)
{
    return (((Bit32u) a.sign)<<31) | 0x7FC00000 | (Bit32u)(a.hi>>41);
}

/*----------------------------------------------------------------------------
| Takes two single-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.
*----------------------------------------------------------------------------*/

float32 propagateFloat32NaN(float32 a, float32 b, float_status_t &status);

/*----------------------------------------------------------------------------
| Takes single-precision floating-point NaN `a' and returns the appropriate
| NaN result.  If `a' is a signaling NaN, the invalid exception is raised.
*----------------------------------------------------------------------------*/

BX_CPP_INLINE float32 propagateFloat32NaN(float32 a, float_status_t &status)
{
    if (float32_is_signaling_nan(a))
        float_raise(status, float_flag_invalid);

    return a | 0x00400000;
}

/*----------------------------------------------------------------------------
| Commonly used single-precision floating point constants
*----------------------------------------------------------------------------*/
const float64 float64_negative_inf  = BX_CONST64(0xfff0000000000000);
const float64 float64_positive_inf  = BX_CONST64(0x7ff0000000000000);
const float64 float64_negative_zero = BX_CONST64(0x8000000000000000);
const float64 float64_positive_zero = BX_CONST64(0x0000000000000000);
const float64 float64_negative_one  = BX_CONST64(0xbff0000000000000);
const float64 float64_positive_one  = BX_CONST64(0x3ff0000000000000);
const float64 float64_max_float     = BX_CONST64(0x7fefffffffffffff);
const float64 float64_min_float     = BX_CONST64(0xffefffffffffffff);

/*----------------------------------------------------------------------------
| The pattern for a default generated double-precision NaN.
*----------------------------------------------------------------------------*/
const float64 float64_default_nan = BX_CONST64(0xFFF8000000000000);

#define float64_fraction extractFloat64Frac
#define float64_exp extractFloat64Exp
#define float64_sign extractFloat64Sign

#define FLOAT64_EXP_BIAS 0x3FF

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

BX_CPP_INLINE Bit64u extractFloat64Frac(float64 a)
{
    return a & BX_CONST64(0x000FFFFFFFFFFFFF);
}

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

BX_CPP_INLINE Bit16s extractFloat64Exp(float64 a)
{
    return (Bit16s)(a>>52) & 0x7FF;
}

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

BX_CPP_INLINE int extractFloat64Sign(float64 a)
{
    return (int)(a>>63);
}

/*----------------------------------------------------------------------------
| Packs the sign `zSign', exponent `zExp', and significand `zSig' into a
| double-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.
*----------------------------------------------------------------------------*/

BX_CPP_INLINE float64 packFloat64(int zSign, Bit16s zExp, Bit64u zSig)
{
    return (((Bit64u) zSign)<<63) + (((Bit64u) zExp)<<52) + zSig;
}

/*----------------------------------------------------------------------------
| Returns 1 if the double-precision floating-point value `a' is a NaN;
| otherwise returns 0.
*----------------------------------------------------------------------------*/

BX_CPP_INLINE int float64_is_nan(float64 a)
{
    return (BX_CONST64(0xFFE0000000000000) < (Bit64u) (a<<1));
}

/*----------------------------------------------------------------------------
| Returns 1 if the double-precision floating-point value `a' is a signaling
| NaN; otherwise returns 0.
*----------------------------------------------------------------------------*/

BX_CPP_INLINE int float64_is_signaling_nan(float64 a)
{
    return (((a>>51) & 0xFFF) == 0xFFE) && (a & BX_CONST64(0x0007FFFFFFFFFFFF));
}

/*----------------------------------------------------------------------------
| Returns 1 if the double-precision floating-point value `a' is denormal;
| otherwise returns 0.
*----------------------------------------------------------------------------*/

BX_CPP_INLINE int float64_is_denormal(float64 a)
{
   return (extractFloat64Exp(a) == 0) && (extractFloat64Frac(a) != 0);
}

/*----------------------------------------------------------------------------
| Convert float64 denormals to zero.
*----------------------------------------------------------------------------*/

BX_CPP_INLINE float64 float64_denormal_to_zero(float64 a)
{
  if (float64_is_denormal(a)) a &= ((Bit64u)(1) << 63);
  return a;
}

/*----------------------------------------------------------------------------
| Returns the result of converting the double-precision floating-point NaN
| `a' to the canonical NaN format.  If `a' is a signaling NaN, the invalid
| exception is raised.
*----------------------------------------------------------------------------*/

BX_CPP_INLINE commonNaNT float64ToCommonNaN(float64 a, float_status_t &status)
{
    commonNaNT z;
    if (float64_is_signaling_nan(a)) float_raise(status, float_flag_invalid);
    z.sign = (int)(a>>63);
    z.lo = 0;
    z.hi = a<<12;
    return z;
}

/*----------------------------------------------------------------------------
| Returns the result of converting the canonical NaN `a' to the double-
| precision floating-point format.
*----------------------------------------------------------------------------*/

BX_CPP_INLINE float64 commonNaNToFloat64(commonNaNT a)
{
    return (((Bit64u) a.sign)<<63) | BX_CONST64(0x7FF8000000000000) | (a.hi>>12);
}

/*----------------------------------------------------------------------------
| Takes two 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.
*----------------------------------------------------------------------------*/

float64 propagateFloat64NaN(float64 a, float64 b, float_status_t &status);

/*----------------------------------------------------------------------------
| Takes double-precision floating-point NaN `a' and returns the appropriate
| NaN result.  If `a' is a signaling NaN, the invalid exception is raised.
*----------------------------------------------------------------------------*/

BX_CPP_INLINE float64 propagateFloat64NaN(float64 a, float_status_t &status)
{
    if (float64_is_signaling_nan(a))
        float_raise(status, float_flag_invalid);

    return a | BX_CONST64(0x0008000000000000);
}

#ifdef FLOATX80

/*----------------------------------------------------------------------------
| The pattern for a default generated extended double-precision NaN.  The
| `high' and `low' values hold the most- and least-significant bits,
| respectively.
*----------------------------------------------------------------------------*/
#define floatx80_default_nan_exp 0xFFFF
#define floatx80_default_nan_fraction BX_CONST64(0xC000000000000000)

#define floatx80_fraction extractFloatx80Frac
#define floatx80_exp extractFloatx80Exp
#define floatx80_sign extractFloatx80Sign

#define FLOATX80_EXP_BIAS 0x3FFF

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

BX_CPP_INLINE Bit64u extractFloatx80Frac(floatx80 a)
{
    return a.fraction;
}

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

BX_CPP_INLINE Bit32s extractFloatx80Exp(floatx80 a)
{
    return a.exp & 0x7FFF;
}

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

BX_CPP_INLINE int extractFloatx80Sign(floatx80 a)
{
    return a.exp>>15;
}

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

BX_CPP_INLINE floatx80 packFloatx80(int zSign, Bit32s zExp, Bit64u zSig)
{
    floatx80 z;
    z.fraction = zSig;
    z.exp = (zSign << 15) + zExp;
    return z;
}

/*----------------------------------------------------------------------------
| Returns 1 if the extended double-precision floating-point value `a' is a
| NaN; otherwise returns 0.
*----------------------------------------------------------------------------*/

BX_CPP_INLINE int floatx80_is_nan(floatx80 a)
{
    return ((a.exp & 0x7FFF) == 0x7FFF) && (Bit64s) (a.fraction<<1);
}

/*----------------------------------------------------------------------------
| Returns 1 if the extended double-precision floating-point value `a' is a
| signaling NaN; otherwise returns 0.
*----------------------------------------------------------------------------*/

BX_CPP_INLINE int floatx80_is_signaling_nan(floatx80 a)
{
    Bit64u aLow = a.fraction & ~BX_CONST64(0x4000000000000000);
    return ((a.exp & 0x7FFF) == 0x7FFF) &&
            ((Bit64u) (aLow<<1)) && (a.fraction == aLow);
}

/*----------------------------------------------------------------------------
| Returns 1 if the extended double-precision floating-point value `a' is an
| unsupported; otherwise returns 0.
*----------------------------------------------------------------------------*/

BX_CPP_INLINE int floatx80_is_unsupported(floatx80 a)
{
    return ((a.exp & 0x7FFF) && !(a.fraction & BX_CONST64(0x8000000000000000)));
}

/*----------------------------------------------------------------------------
| Returns the result of converting the extended double-precision floating-
| point NaN `a' to the canonical NaN format. If `a' is a signaling NaN, the
| invalid exception is raised.
*----------------------------------------------------------------------------*/

BX_CPP_INLINE commonNaNT floatx80ToCommonNaN(floatx80 a, float_status_t &status)
{
    commonNaNT z;
    if (floatx80_is_signaling_nan(a)) float_raise(status, float_flag_invalid);
    z.sign = a.exp >> 15;
    z.lo = 0;
    z.hi = a.fraction << 1;
    return z;
}

/*----------------------------------------------------------------------------
| Returns the result of converting the canonical NaN `a' to the extended
| double-precision floating-point format.
*----------------------------------------------------------------------------*/

BX_CPP_INLINE floatx80 commonNaNToFloatx80(commonNaNT a)
{
    floatx80 z;
    z.fraction = BX_CONST64(0xC000000000000000) | (a.hi>>1);
    z.exp = (((Bit16u) a.sign)<<15) | 0x7FFF;
    return z;
}

/*----------------------------------------------------------------------------
| 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_t &status);

/*----------------------------------------------------------------------------
| Takes extended double-precision floating-point  NaN  `a' and returns the
| appropriate NaN result. If `a' is a signaling NaN, the invalid exception
| is raised.
*----------------------------------------------------------------------------*/

BX_CPP_INLINE floatx80 propagateFloatx80NaN(floatx80 a, float_status_t &status)
{
    if (floatx80_is_signaling_nan(a))
        float_raise(status, float_flag_invalid);

    a.fraction |= BX_CONST64(0xC000000000000000);

    return a;
}

/*----------------------------------------------------------------------------
| The pattern for a default generated extended double-precision NaN.
*----------------------------------------------------------------------------*/
extern const floatx80 floatx80_default_nan;

#endif /* FLOATX80 */

#ifdef FLOAT128

#include "softfloat-macros.h"

/*----------------------------------------------------------------------------
| The pattern for a default generated quadruple-precision NaN. The `high' and
| `low' values hold the most- and least-significant bits, respectively.
*----------------------------------------------------------------------------*/
#define float128_default_nan_hi BX_CONST64(0xFFFF800000000000)
#define float128_default_nan_lo BX_CONST64(0x0000000000000000)

#define float128_exp extractFloat128Exp

/*----------------------------------------------------------------------------
| Returns the least-significant 64 fraction bits of the quadruple-precision
| floating-point value `a'.
*----------------------------------------------------------------------------*/

BX_CPP_INLINE Bit64u extractFloat128Frac1(float128 a)
{
    return a.lo;
}

/*----------------------------------------------------------------------------
| Returns the most-significant 48 fraction bits of the quadruple-precision
| floating-point value `a'.
*----------------------------------------------------------------------------*/

BX_CPP_INLINE Bit64u extractFloat128Frac0(float128 a)
{
    return a.hi & BX_CONST64(0x0000FFFFFFFFFFFF);
}

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

BX_CPP_INLINE Bit32s extractFloat128Exp(float128 a)
{
    return ((Bit32s)(a.hi>>48)) & 0x7FFF;
}

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

BX_CPP_INLINE int extractFloat128Sign(float128 a)
{
    return (int)(a.hi >> 63);
}

/*----------------------------------------------------------------------------
| Packs the sign `zSign', the exponent `zExp', and the significand formed
| by the concatenation of `zSig0' and `zSig1' into a quadruple-precision
| floating-point value, returning the result.  After being shifted into the
| proper positions, the three fields `zSign', `zExp', and `zSig0' are simply
| added together to form the most significant 32 bits of the result.  This
| means that any integer portion of `zSig0' 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 `zSig0' and `zSig1' concatenated form a complete, normalized
| significand.
*----------------------------------------------------------------------------*/

BX_CPP_INLINE float128 packFloat128(int zSign, Bit32s zExp, Bit64u zSig0, Bit64u zSig1)
{
    float128 z;
    z.lo = zSig1;
    z.hi = (((Bit64u) zSign)<<63) + (((Bit64u) zExp)<<48) + zSig0;
    return z;
}

/*----------------------------------------------------------------------------
| Packs two 64-bit precision integers into into the quadruple-precision
| floating-point value, returning the result.
*----------------------------------------------------------------------------*/

BX_CPP_INLINE float128 packFloat128(Bit64u zHi, Bit64u zLo)
{
    float128 z;
    z.lo = zLo;
    z.hi = zHi;
    return z;
}

#ifdef _MSC_VER
#define PACK_FLOAT_128(hi,lo) { lo, hi }
#else
#define PACK_FLOAT_128(hi,lo) packFloat128(BX_CONST64(hi),BX_CONST64(lo))
#endif

/*----------------------------------------------------------------------------
| Returns 1 if the quadruple-precision floating-point value `a' is a NaN;
| otherwise returns 0.
*----------------------------------------------------------------------------*/

BX_CPP_INLINE int float128_is_nan(float128 a)
{
    return (BX_CONST64(0xFFFE000000000000) <= (Bit64u) (a.hi<<1))
        && (a.lo || (a.hi & BX_CONST64(0x0000FFFFFFFFFFFF)));
}

/*----------------------------------------------------------------------------
| Returns 1 if the quadruple-precision floating-point value `a' is a
| signaling NaN; otherwise returns 0.
*----------------------------------------------------------------------------*/

BX_CPP_INLINE int float128_is_signaling_nan(float128 a)
{
    return (((a.hi>>47) & 0xFFFF) == 0xFFFE)
        && (a.lo || (a.hi & BX_CONST64(0x00007FFFFFFFFFFF)));
}

/*----------------------------------------------------------------------------
| Returns the result of converting the quadruple-precision floating-point NaN
| `a' to the canonical NaN format.  If `a' is a signaling NaN, the invalid
| exception is raised.
*----------------------------------------------------------------------------*/

BX_CPP_INLINE commonNaNT float128ToCommonNaN(float128 a, float_status_t &status)
{
    commonNaNT z;
    if (float128_is_signaling_nan(a)) float_raise(status, float_flag_invalid);
    z.sign = (int)(a.hi>>63);
    shortShift128Left(a.hi, a.lo, 16, &z.hi, &z.lo);
    return z;
}

/*----------------------------------------------------------------------------
| Returns the result of converting the canonical NaN `a' to the quadruple-
| precision floating-point format.
*----------------------------------------------------------------------------*/

BX_CPP_INLINE float128 commonNaNToFloat128(commonNaNT a)
{
    float128 z;
    shift128Right(a.hi, a.lo, 16, &z.hi, &z.lo);
    z.hi |= (((Bit64u) a.sign)<<63) | BX_CONST64(0x7FFF800000000000);
    return z;
}

/*----------------------------------------------------------------------------
| Takes two quadruple-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.
*----------------------------------------------------------------------------*/

float128 propagateFloat128NaN(float128 a, float128 b, float_status_t &status);

/*----------------------------------------------------------------------------
| The pattern for a default generated quadruple-precision NaN.
*----------------------------------------------------------------------------*/
extern const float128 float128_default_nan;

#endif /* FLOAT128 */

#endif