about summary refs log tree commit diff
path: root/sysdeps/ieee754/ldbl-128/e_jnl.c
blob: 540b95ca5893bae33b2d60f0139b8e0f1f82bfa4 (plain) (blame)
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
/*
 * ====================================================
 * Copyright (C) 1993 by Sun Microsystems, Inc. All rights reserved.
 *
 * Developed at SunPro, a Sun Microsystems, Inc. business.
 * Permission to use, copy, modify, and distribute this
 * software is freely granted, provided that this notice
 * is preserved.
 * ====================================================
 */

/* Modifications for 128-bit long double are
   Copyright (C) 2001 Stephen L. Moshier <moshier@na-net.ornl.gov>
   and are incorporated herein by permission of the author.  The author
   reserves the right to distribute this material elsewhere under different
   copying permissions.  These modifications are distributed here under
   the following terms:

    This library is free software; you can redistribute it and/or
    modify it under the terms of the GNU Lesser General Public
    License as published by the Free Software Foundation; either
    version 2.1 of the License, or (at your option) any later version.

    This library is distributed in the hope that it will be useful,
    but WITHOUT ANY WARRANTY; without even the implied warranty of
    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
    Lesser General Public License for more details.

    You should have received a copy of the GNU Lesser General Public
    License along with this library; if not, see
    <http://www.gnu.org/licenses/>.  */

/*
 * __ieee754_jn(n, x), __ieee754_yn(n, x)
 * floating point Bessel's function of the 1st and 2nd kind
 * of order n
 *
 * Special cases:
 *	y0(0)=y1(0)=yn(n,0) = -inf with division by zero signal;
 *	y0(-ve)=y1(-ve)=yn(n,-ve) are NaN with invalid signal.
 * Note 2. About jn(n,x), yn(n,x)
 *	For n=0, j0(x) is called,
 *	for n=1, j1(x) is called,
 *	for n<x, forward recursion us used starting
 *	from values of j0(x) and j1(x).
 *	for n>x, a continued fraction approximation to
 *	j(n,x)/j(n-1,x) is evaluated and then backward
 *	recursion is used starting from a supposed value
 *	for j(n,x). The resulting value of j(0,x) is
 *	compared with the actual value to correct the
 *	supposed value of j(n,x).
 *
 *	yn(n,x) is similar in all respects, except
 *	that forward recursion is used for all
 *	values of n>1.
 *
 */

#include <errno.h>
#include <float.h>
#include <math.h>
#include <math_private.h>
#include <fenv_private.h>
#include <math-underflow.h>

static const _Float128
  invsqrtpi = L(5.6418958354775628694807945156077258584405E-1),
  two = 2,
  one = 1,
  zero = 0;


_Float128
__ieee754_jnl (int n, _Float128 x)
{
  uint32_t se;
  int32_t i, ix, sgn;
  _Float128 a, b, temp, di, ret;
  _Float128 z, w;
  ieee854_long_double_shape_type u;


  /* J(-n,x) = (-1)^n * J(n, x), J(n, -x) = (-1)^n * J(n, x)
   * Thus, J(-n,x) = J(n,-x)
   */

  u.value = x;
  se = u.parts32.w0;
  ix = se & 0x7fffffff;

  /* if J(n,NaN) is NaN */
  if (ix >= 0x7fff0000)
    {
      if ((u.parts32.w0 & 0xffff) | u.parts32.w1 | u.parts32.w2 | u.parts32.w3)
	return x + x;
    }

  if (n < 0)
    {
      n = -n;
      x = -x;
      se ^= 0x80000000;
    }
  if (n == 0)
    return (__ieee754_j0l (x));
  if (n == 1)
    return (__ieee754_j1l (x));
  sgn = (n & 1) & (se >> 31);	/* even n -- 0, odd n -- sign(x) */
  x = fabsl (x);

  {
    SET_RESTORE_ROUNDL (FE_TONEAREST);
    if (x == 0 || ix >= 0x7fff0000)	/* if x is 0 or inf */
      return sgn == 1 ? -zero : zero;
    else if ((_Float128) n <= x)
      {
	/* Safe to use J(n+1,x)=2n/x *J(n,x)-J(n-1,x) */
	if (ix >= 0x412D0000)
	  {			/* x > 2**302 */

	    /* ??? Could use an expansion for large x here.  */

	    /* (x >> n**2)
	     *      Jn(x) = cos(x-(2n+1)*pi/4)*sqrt(2/x*pi)
	     *      Yn(x) = sin(x-(2n+1)*pi/4)*sqrt(2/x*pi)
	     *      Let s=sin(x), c=cos(x),
	     *          xn=x-(2n+1)*pi/4, sqt2 = sqrt(2),then
	     *
	     *             n    sin(xn)*sqt2    cos(xn)*sqt2
	     *          ----------------------------------
	     *             0     s-c             c+s
	     *             1    -s-c            -c+s
	     *             2    -s+c            -c-s
	     *             3     s+c             c-s
	     */
	    _Float128 s;
	    _Float128 c;
	    __sincosl (x, &s, &c);
	    switch (n & 3)
	      {
	      case 0:
		temp = c + s;
		break;
	      case 1:
		temp = -c + s;
		break;
	      case 2:
		temp = -c - s;
		break;
	      case 3:
		temp = c - s;
		break;
	      }
	    b = invsqrtpi * temp / sqrtl (x);
	  }
	else
	  {
	    a = __ieee754_j0l (x);
	    b = __ieee754_j1l (x);
	    for (i = 1; i < n; i++)
	      {
		temp = b;
		b = b * ((_Float128) (i + i) / x) - a;	/* avoid underflow */
		a = temp;
	      }
	  }
      }
    else
      {
	if (ix < 0x3fc60000)
	  {			/* x < 2**-57 */
	    /* x is tiny, return the first Taylor expansion of J(n,x)
	     * J(n,x) = 1/n!*(x/2)^n  - ...
	     */
	    if (n >= 400)		/* underflow, result < 10^-4952 */
	      b = zero;
	    else
	      {
		temp = x * 0.5;
		b = temp;
		for (a = one, i = 2; i <= n; i++)
		  {
		    a *= (_Float128) i;	/* a = n! */
		    b *= temp;	/* b = (x/2)^n */
		  }
		b = b / a;
	      }
	  }
	else
	  {
	    /* use backward recurrence */
	    /*                      x      x^2      x^2
	     *  J(n,x)/J(n-1,x) =  ----   ------   ------   .....
	     *                      2n  - 2(n+1) - 2(n+2)
	     *
	     *                      1      1        1
	     *  (for large x)   =  ----  ------   ------   .....
	     *                      2n   2(n+1)   2(n+2)
	     *                      -- - ------ - ------ -
	     *                       x     x         x
	     *
	     * Let w = 2n/x and h=2/x, then the above quotient
	     * is equal to the continued fraction:
	     *                  1
	     *      = -----------------------
	     *                     1
	     *         w - -----------------
	     *                        1
	     *              w+h - ---------
	     *                     w+2h - ...
	     *
	     * To determine how many terms needed, let
	     * Q(0) = w, Q(1) = w(w+h) - 1,
	     * Q(k) = (w+k*h)*Q(k-1) - Q(k-2),
	     * When Q(k) > 1e4      good for single
	     * When Q(k) > 1e9      good for double
	     * When Q(k) > 1e17     good for quadruple
	     */
	    /* determine k */
	    _Float128 t, v;
	    _Float128 q0, q1, h, tmp;
	    int32_t k, m;
	    w = (n + n) / (_Float128) x;
	    h = 2 / (_Float128) x;
	    q0 = w;
	    z = w + h;
	    q1 = w * z - 1;
	    k = 1;
	    while (q1 < L(1.0e17))
	      {
		k += 1;
		z += h;
		tmp = z * q1 - q0;
		q0 = q1;
		q1 = tmp;
	      }
	    m = n + n;
	    for (t = zero, i = 2 * (n + k); i >= m; i -= 2)
	      t = one / (i / x - t);
	    a = t;
	    b = one;
	    /*  estimate log((2/x)^n*n!) = n*log(2/x)+n*ln(n)
	     *  Hence, if n*(log(2n/x)) > ...
	     *  single 8.8722839355e+01
	     *  double 7.09782712893383973096e+02
	     *  long double 1.1356523406294143949491931077970765006170e+04
	     *  then recurrent value may overflow and the result is
	     *  likely underflow to zero
	     */
	    tmp = n;
	    v = two / x;
	    tmp = tmp * __ieee754_logl (fabsl (v * tmp));

	    if (tmp < L(1.1356523406294143949491931077970765006170e+04))
	      {
		for (i = n - 1, di = (_Float128) (i + i); i > 0; i--)
		  {
		    temp = b;
		    b *= di;
		    b = b / x - a;
		    a = temp;
		    di -= two;
		  }
	      }
	    else
	      {
		for (i = n - 1, di = (_Float128) (i + i); i > 0; i--)
		  {
		    temp = b;
		    b *= di;
		    b = b / x - a;
		    a = temp;
		    di -= two;
		    /* scale b to avoid spurious overflow */
		    if (b > L(1e100))
		      {
			a /= b;
			t /= b;
			b = one;
		      }
		  }
	      }
	    /* j0() and j1() suffer enormous loss of precision at and
	     * near zero; however, we know that their zero points never
	     * coincide, so just choose the one further away from zero.
	     */
	    z = __ieee754_j0l (x);
	    w = __ieee754_j1l (x);
	    if (fabsl (z) >= fabsl (w))
	      b = (t * z / b);
	    else
	      b = (t * w / a);
	  }
      }
    if (sgn == 1)
      ret = -b;
    else
      ret = b;
  }
  if (ret == 0)
    {
      ret = __copysignl (LDBL_MIN, ret) * LDBL_MIN;
      __set_errno (ERANGE);
    }
  else
    math_check_force_underflow (ret);
  return ret;
}
strong_alias (__ieee754_jnl, __jnl_finite)

_Float128
__ieee754_ynl (int n, _Float128 x)
{
  uint32_t se;
  int32_t i, ix;
  int32_t sign;
  _Float128 a, b, temp, ret;
  ieee854_long_double_shape_type u;

  u.value = x;
  se = u.parts32.w0;
  ix = se & 0x7fffffff;

  /* if Y(n,NaN) is NaN */
  if (ix >= 0x7fff0000)
    {
      if ((u.parts32.w0 & 0xffff) | u.parts32.w1 | u.parts32.w2 | u.parts32.w3)
	return x + x;
    }
  if (x <= 0)
    {
      if (x == 0)
	return ((n < 0 && (n & 1) != 0) ? 1 : -1) / L(0.0);
      if (se & 0x80000000)
	return zero / (zero * x);
    }
  sign = 1;
  if (n < 0)
    {
      n = -n;
      sign = 1 - ((n & 1) << 1);
    }
  if (n == 0)
    return (__ieee754_y0l (x));
  {
    SET_RESTORE_ROUNDL (FE_TONEAREST);
    if (n == 1)
      {
	ret = sign * __ieee754_y1l (x);
	goto out;
      }
    if (ix >= 0x7fff0000)
      return zero;
    if (ix >= 0x412D0000)
      {				/* x > 2**302 */

	/* ??? See comment above on the possible futility of this.  */

	/* (x >> n**2)
	 *      Jn(x) = cos(x-(2n+1)*pi/4)*sqrt(2/x*pi)
	 *      Yn(x) = sin(x-(2n+1)*pi/4)*sqrt(2/x*pi)
	 *      Let s=sin(x), c=cos(x),
	 *          xn=x-(2n+1)*pi/4, sqt2 = sqrt(2),then
	 *
	 *             n    sin(xn)*sqt2    cos(xn)*sqt2
	 *          ----------------------------------
	 *             0     s-c             c+s
	 *             1    -s-c            -c+s
	 *             2    -s+c            -c-s
	 *             3     s+c             c-s
	 */
	_Float128 s;
	_Float128 c;
	__sincosl (x, &s, &c);
	switch (n & 3)
	  {
	  case 0:
	    temp = s - c;
	    break;
	  case 1:
	    temp = -s - c;
	    break;
	  case 2:
	    temp = -s + c;
	    break;
	  case 3:
	    temp = s + c;
	    break;
	  }
	b = invsqrtpi * temp / sqrtl (x);
      }
    else
      {
	a = __ieee754_y0l (x);
	b = __ieee754_y1l (x);
	/* quit if b is -inf */
	u.value = b;
	se = u.parts32.w0 & 0xffff0000;
	for (i = 1; i < n && se != 0xffff0000; i++)
	  {
	    temp = b;
	    b = ((_Float128) (i + i) / x) * b - a;
	    u.value = b;
	    se = u.parts32.w0 & 0xffff0000;
	    a = temp;
	  }
      }
    /* If B is +-Inf, set up errno accordingly.  */
    if (! isfinite (b))
      __set_errno (ERANGE);
    if (sign > 0)
      ret = b;
    else
      ret = -b;
  }
 out:
  if (isinf (ret))
    ret = __copysignl (LDBL_MAX, ret) * LDBL_MAX;
  return ret;
}
strong_alias (__ieee754_ynl, __ynl_finite)