aboutsummaryrefslogtreecommitdiff
path: root/fpu/softfloat-specialize.h
blob: f9b6f0cbc64837093b007fd7ed2bb2e095e3b588 (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

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

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.

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

/*----------------------------------------------------------------------------
| Underflow tininess-detection mode, statically initialized to default value.
| (The declaration in `softfloat.h' must match the `int8' type here.)
*----------------------------------------------------------------------------*/
int8 float_detect_tininess = float_tininess_after_rounding;

/*----------------------------------------------------------------------------
| Raises the exceptions specified by `flags'.  Floating-point traps can be
| defined here if desired.  It is currently not possible for such a trap
| to substitute a result value.  If traps are not implemented, this routine
| should be simply `float_exception_flags |= flags;'.
*----------------------------------------------------------------------------*/

void float_raise( int8 flags STATUS_PARAM )
{

    STATUS(float_exception_flags) |= flags;

}

/*----------------------------------------------------------------------------
| Internal canonical NaN format.
*----------------------------------------------------------------------------*/
typedef struct {
    flag sign;
    bits64 high, low;
} commonNaNT;

/*----------------------------------------------------------------------------
| The pattern for a default generated single-precision NaN.
*----------------------------------------------------------------------------*/
#define float32_default_nan 0xFFC00000

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

int float32_is_nan( float32 a )
{

    return ( 0xFF000000 < (bits32) ( a<<1 ) );

}

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

int float32_is_signaling_nan( float32 a )
{

    return ( ( ( a>>22 ) & 0x1FF ) == 0x1FE ) && ( a & 0x003FFFFF );

}

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

static commonNaNT float32ToCommonNaN( float32 a STATUS_PARAM )
{
    commonNaNT z;

    if ( float32_is_signaling_nan( a ) ) float_raise( float_flag_invalid STATUS_VAR );
    z.sign = a>>31;
    z.low = 0;
    z.high = ( (bits64) a )<<41;
    return z;

}

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

static float32 commonNaNToFloat32( commonNaNT a )
{

    return ( ( (bits32) a.sign )<<31 ) | 0x7FC00000 | ( a.high>>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.
*----------------------------------------------------------------------------*/

static float32 propagateFloat32NaN( float32 a, float32 b STATUS_PARAM)
{
    flag aIsNaN, aIsSignalingNaN, bIsNaN, bIsSignalingNaN;

    aIsNaN = float32_is_nan( a );
    aIsSignalingNaN = float32_is_signaling_nan( a );
    bIsNaN = float32_is_nan( b );
    bIsSignalingNaN = float32_is_signaling_nan( b );
    a |= 0x00400000;
    b |= 0x00400000;
    if ( aIsSignalingNaN | bIsSignalingNaN ) float_raise( float_flag_invalid STATUS_VAR);
    if ( aIsSignalingNaN ) {
        if ( bIsSignalingNaN ) goto returnLargerSignificand;
        return bIsNaN ? b : a;
    }
    else if ( aIsNaN ) {
        if ( bIsSignalingNaN | ! bIsNaN ) return a;
 returnLargerSignificand:
        if ( (bits32) ( a<<1 ) < (bits32) ( b<<1 ) ) return b;
        if ( (bits32) ( b<<1 ) < (bits32) ( a<<1 ) ) return a;
        return ( a < b ) ? a : b;
    }
    else {
        return b;
    }

}

/*----------------------------------------------------------------------------
| The pattern for a default generated double-precision NaN.
*----------------------------------------------------------------------------*/
#define float64_default_nan LIT64( 0xFFF8000000000000 )

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

int float64_is_nan( float64 a )
{

    return ( LIT64( 0xFFE0000000000000 ) < (bits64) ( a<<1 ) );

}

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

int float64_is_signaling_nan( float64 a )
{

    return
           ( ( ( a>>51 ) & 0xFFF ) == 0xFFE )
        && ( a & LIT64( 0x0007FFFFFFFFFFFF ) );

}

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

static commonNaNT float64ToCommonNaN( float64 a STATUS_PARAM)
{
    commonNaNT z;

    if ( float64_is_signaling_nan( a ) ) float_raise( float_flag_invalid STATUS_VAR);
    z.sign = a>>63;
    z.low = 0;
    z.high = a<<12;
    return z;

}

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

static float64 commonNaNToFloat64( commonNaNT a )
{

    return
          ( ( (bits64) a.sign )<<63 )
        | LIT64( 0x7FF8000000000000 )
        | ( a.high>>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.
*----------------------------------------------------------------------------*/

static float64 propagateFloat64NaN( float64 a, float64 b STATUS_PARAM)
{
    flag aIsNaN, aIsSignalingNaN, bIsNaN, bIsSignalingNaN;

    aIsNaN = float64_is_nan( a );
    aIsSignalingNaN = float64_is_signaling_nan( a );
    bIsNaN = float64_is_nan( b );
    bIsSignalingNaN = float64_is_signaling_nan( b );
    a |= LIT64( 0x0008000000000000 );
    b |= LIT64( 0x0008000000000000 );
    if ( aIsSignalingNaN | bIsSignalingNaN ) float_raise( float_flag_invalid STATUS_VAR);
    if ( aIsSignalingNaN ) {
        if ( bIsSignalingNaN ) goto returnLargerSignificand;
        return bIsNaN ? b : a;
    }
    else if ( aIsNaN ) {
        if ( bIsSignalingNaN | ! bIsNaN ) return a;
 returnLargerSignificand:
        if ( (bits64) ( a<<1 ) < (bits64) ( b<<1 ) ) return b;
        if ( (bits64) ( b<<1 ) < (bits64) ( a<<1 ) ) return a;
        return ( a < b ) ? a : b;
    }
    else {
        return b;
    }

}

#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_high 0xFFFF
#define floatx80_default_nan_low  LIT64( 0xC000000000000000 )

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

int floatx80_is_nan( floatx80 a )
{

    return ( ( a.high & 0x7FFF ) == 0x7FFF ) && (bits64) ( a.low<<1 );

}

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

int floatx80_is_signaling_nan( floatx80 a )
{
    bits64 aLow;

    aLow = a.low & ~ LIT64( 0x4000000000000000 );
    return
           ( ( a.high & 0x7FFF ) == 0x7FFF )
        && (bits64) ( aLow<<1 )
        && ( a.low == aLow );

}

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

static commonNaNT floatx80ToCommonNaN( floatx80 a STATUS_PARAM)
{
    commonNaNT z;

    if ( floatx80_is_signaling_nan( a ) ) float_raise( float_flag_invalid STATUS_VAR);
    z.sign = a.high>>15;
    z.low = 0;
    z.high = a.low<<1;
    return z;

}

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

static floatx80 commonNaNToFloatx80( commonNaNT a )
{
    floatx80 z;

    z.low = LIT64( 0xC000000000000000 ) | ( a.high>>1 );
    z.high = ( ( (bits16) 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.
*----------------------------------------------------------------------------*/

static floatx80 propagateFloatx80NaN( floatx80 a, floatx80 b STATUS_PARAM)
{
    flag aIsNaN, aIsSignalingNaN, bIsNaN, bIsSignalingNaN;

    aIsNaN = floatx80_is_nan( a );
    aIsSignalingNaN = floatx80_is_signaling_nan( a );
    bIsNaN = floatx80_is_nan( b );
    bIsSignalingNaN = floatx80_is_signaling_nan( b );
    a.low |= LIT64( 0xC000000000000000 );
    b.low |= LIT64( 0xC000000000000000 );
    if ( aIsSignalingNaN | bIsSignalingNaN ) float_raise( float_flag_invalid STATUS_VAR);
    if ( aIsSignalingNaN ) {
        if ( bIsSignalingNaN ) goto returnLargerSignificand;
        return bIsNaN ? b : a;
    }
    else if ( aIsNaN ) {
        if ( bIsSignalingNaN | ! bIsNaN ) return a;
 returnLargerSignificand:
        if ( a.low < b.low ) return b;
        if ( b.low < a.low ) return a;
        return ( a.high < b.high ) ? a : b;
    }
    else {
        return b;
    }

}

#endif

#ifdef FLOAT128

/*----------------------------------------------------------------------------
| 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_high LIT64( 0xFFFF800000000000 )
#define float128_default_nan_low  LIT64( 0x0000000000000000 )

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

int float128_is_nan( float128 a )
{

    return
           ( LIT64( 0xFFFE000000000000 ) <= (bits64) ( a.high<<1 ) )
        && ( a.low || ( a.high & LIT64( 0x0000FFFFFFFFFFFF ) ) );

}

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

int float128_is_signaling_nan( float128 a )
{

    return
           ( ( ( a.high>>47 ) & 0xFFFF ) == 0xFFFE )
        && ( a.low || ( a.high & LIT64( 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.
*----------------------------------------------------------------------------*/

static commonNaNT float128ToCommonNaN( float128 a STATUS_PARAM)
{
    commonNaNT z;

    if ( float128_is_signaling_nan( a ) ) float_raise( float_flag_invalid STATUS_VAR);
    z.sign = a.high>>63;
    shortShift128Left( a.high, a.low, 16, &z.high, &z.low );
    return z;

}

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

static float128 commonNaNToFloat128( commonNaNT a )
{
    float128 z;

    shift128Right( a.high, a.low, 16, &z.high, &z.low );
    z.high |= ( ( (bits64) a.sign )<<63 ) | LIT64( 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.
*----------------------------------------------------------------------------*/

static float128 propagateFloat128NaN( float128 a, float128 b STATUS_PARAM)
{
    flag aIsNaN, aIsSignalingNaN, bIsNaN, bIsSignalingNaN;

    aIsNaN = float128_is_nan( a );
    aIsSignalingNaN = float128_is_signaling_nan( a );
    bIsNaN = float128_is_nan( b );
    bIsSignalingNaN = float128_is_signaling_nan( b );
    a.high |= LIT64( 0x0000800000000000 );
    b.high |= LIT64( 0x0000800000000000 );
    if ( aIsSignalingNaN | bIsSignalingNaN ) float_raise( float_flag_invalid STATUS_VAR);
    if ( aIsSignalingNaN ) {
        if ( bIsSignalingNaN ) goto returnLargerSignificand;
        return bIsNaN ? b : a;
    }
    else if ( aIsNaN ) {
        if ( bIsSignalingNaN | ! bIsNaN ) return a;
 returnLargerSignificand:
        if ( lt128( a.high<<1, a.low, b.high<<1, b.low ) ) return b;
        if ( lt128( b.high<<1, b.low, a.high<<1, a.low ) ) return a;
        return ( a.high < b.high ) ? a : b;
    }
    else {
        return b;
    }

}

#endif