File: machar.c

package info (click to toggle)
octave 2.0.13-4
  • links: PTS
  • area: main
  • in suites: hamm
  • size: 23,828 kB
  • ctags: 13,172
  • sloc: cpp: 66,241; fortran: 37,245; ansic: 26,548; sh: 7,269; makefile: 3,808; lex: 1,943; yacc: 1,844; perl: 1,676; lisp: 1,662; exp: 123
file content (380 lines) | stat: -rw-r--r-- 9,908 bytes parent folder | download | duplicates (6)
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
#ifdef HAVE_CONFIG_H
#include <config.h>
#endif

#include "f77-fcn.h"

/*

This file combines the single and double precision versions of machar,
selected by cc -DSP or cc -DDP.  This feature provided by D. G. Hough,
August 3, 1988.

*/

#ifdef SP
#define REAL float
#define ZERO 0.0
#define ONE 1.0
#define PREC "Single "
#define REALSIZE 1
#endif

#ifdef DP
#define REAL double
#define ZERO 0.0e0
#define ONE 1.0e0
#define PREC "Double "
#define REALSIZE 2
#endif

#include <math.h>
#include <stdio.h>

#define ABS(xxx) ((xxx>ZERO)?(xxx):(-xxx))

void
rmachar(ibeta,it,irnd,ngrd,machep,negep,iexp,minexp,
        maxexp,eps,epsneg,xmin,xmax)

      int *ibeta,*iexp,*irnd,*it,*machep,*maxexp,*minexp,*negep,*ngrd;
      REAL *eps,*epsneg,*xmax,*xmin;

/*

   This subroutine is intended to determine the parameters of the
    floating-point arithmetic system specified below.  The
    determination of the first three uses an extension of an algorithm
    due to M. Malcolm, CACM 15 (1972), pp. 949-951, incorporating some,
    but not all, of the improvements suggested by M. Gentleman and S.
    Marovich, CACM 17 (1974), pp. 276-277.  An earlier version of this
    program was published in the book Software Manual for the
    Elementary Functions by W. J. Cody and W. Waite, Prentice-Hall,
    Englewood Cliffs, NJ, 1980.  The present program is a
    translation of the Fortran 77 program in W. J. Cody, "MACHAR:
    A subroutine to dynamically determine machine parameters".
    TOMS (14), 1988.

   Parameter values reported are as follows:

        ibeta   - the radix for the floating-point representation
        it      - the number of base ibeta digits in the floating-point
                  significand
        irnd    - 0 if floating-point addition chops
                  1 if floating-point addition rounds, but not in the
                    IEEE style
                  2 if floating-point addition rounds in the IEEE style
                  3 if floating-point addition chops, and there is
                    partial underflow
                  4 if floating-point addition rounds, but not in the
                    IEEE style, and there is partial underflow
                  5 if floating-point addition rounds in the IEEE style,
                    and there is partial underflow
        ngrd    - the number of guard digits for multiplication with
                  truncating arithmetic.  It is
                  0 if floating-point arithmetic rounds, or if it
                    truncates and only  it  base  ibeta digits
                    participate in the post-normalization shift of the
                    floating-point significand in multiplication;
                  1 if floating-point arithmetic truncates and more
                    than  it  base  ibeta  digits participate in the
                    post-normalization shift of the floating-point
                    significand in multiplication.
        machep  - the largest negative integer such that
                  1.0+FLOAT(ibeta)**machep .NE. 1.0, except that
                  machep is bounded below by  -(it+3)
        negeps  - the largest negative integer such that
                  1.0-FLOAT(ibeta)**negeps .NE. 1.0, except that
                  negeps is bounded below by  -(it+3)
        iexp    - the number of bits (decimal places if ibeta = 10)
                  reserved for the representation of the exponent
                  (including the bias or sign) of a floating-point
                  number
        minexp  - the largest in magnitude negative integer such that
                  FLOAT(ibeta)**minexp is positive and normalized
        maxexp  - the smallest positive power of  BETA  that overflows
        eps     - the smallest positive floating-point number such
                  that  1.0+eps .NE. 1.0. In particular, if either
                  ibeta = 2  or  IRND = 0, eps = FLOAT(ibeta)**machep.
                  Otherwise,  eps = (FLOAT(ibeta)**machep)/2
        epsneg  - A small positive floating-point number such that
                  1.0-epsneg .NE. 1.0. In particular, if ibeta = 2
                  or  IRND = 0, epsneg = FLOAT(ibeta)**negeps.
                  Otherwise,  epsneg = (ibeta**negeps)/2.  Because
                  negeps is bounded below by -(it+3), epsneg may not
                  be the smallest number that can alter 1.0 by
                  subtraction.
        xmin    - the smallest non-vanishing normalized floating-point
                  power of the radix, i.e.,  xmin = FLOAT(ibeta)**minexp
        xmax    - the largest finite floating-point number.  In
                  particular  xmax = (1.0-epsneg)*FLOAT(ibeta)**maxexp
                  Note - on some machines  xmax  will be only the
                  second, or perhaps third, largest number, being
                  too small by 1 or 2 units in the last digit of
                  the significand.

      Latest revision - August 4, 1988

      Author - W. J. Cody
               Argonne National Laboratory

*/

{
      int i,iz,j,k;
      int mx,itmp,nxres;
      REAL a,b,beta,betain,one,y,z,zero;
      REAL betah,t,tmp,tmpa,tmp1,two;

      (*irnd) = 1;
      one = (REAL)(*irnd);
      two = one + one;
      a = two;
      b = a;
      zero = 0.0e0;

/*
  determine ibeta,beta ala malcolm
*/

      tmp = ((a+one)-a)-one;

      while (tmp == zero) {
         a = a+a;
         tmp = a+one;
         tmp1 = tmp-a;
         tmp = tmp1-one;
      }

      tmp = a+b;
      itmp = (int)(tmp-a);
      while (itmp == 0) {
         b = b+b;
         tmp = a+b;
         itmp = (int)(tmp-a);
      }

      *ibeta = itmp;
      beta = (REAL)(*ibeta);

/*
  determine irnd, it
*/

      (*it) = 0;
      b = one;
      tmp = ((b+one)-b)-one;

      while (tmp == zero) {
         *it = *it+1;
         b = b*beta;
         tmp = b+one;
         tmp1 = tmp-b;
         tmp = tmp1-one;
      }

      *irnd = 0;
      betah = beta/two;
      tmp = a+betah;
      tmp1 = tmp-a;
      if (tmp1 != zero) *irnd = 1;
      tmpa = a+beta;
      tmp = tmpa+betah;
      if ((*irnd == 0) && (tmp-tmpa != zero)) *irnd = 2;

/*
  determine negep, epsneg
*/

      (*negep) = (*it) + 3;
      betain = one / beta;
      a = one;

      for (i = 1; i<=(*negep); i++) {
         a = a * betain;
      }

      b = a;
      tmp = (one-a);
      tmp = tmp-one;

      while (tmp == zero) {
         a = a*beta;
         *negep = *negep-1;
         tmp1 = one-a;
         tmp = tmp1-one;
      }

      (*negep) = -(*negep);
      (*epsneg) = a;

/*
  determine machep, eps
*/

      (*machep) = -(*it) - 3;
      a = b;
      tmp = one+a;

      while (tmp-one == zero) {
         a = a*beta;
         *machep = *machep+1;
         tmp = one+a;
      }

      *eps = a;

/*
  determine ngrd
*/

      (*ngrd) = 0;
      tmp = one+*eps;
      tmp = tmp*one;
      if (((*irnd) == 0) && (tmp-one) != zero) (*ngrd) = 1;

/*
  determine iexp, minexp, xmin

  loop to determine largest i such that
         (1/beta) ** (2**(i))
    does not underflow.
    exit from loop is signaled by an underflow.
*/

      i = 0;
      k = 1;
      z = betain;
      t = one+*eps;
      nxres = 0;

      for (;;) {
         y = z;
         z = y * y;

/*
  check for underflow
*/

         a = z * one;
         tmp = z*t;
         if ((a+a == zero) || (ABS(z) > y)) break;
         tmp1 = tmp*betain;
         if (tmp1*beta == z) break;
         i = i + 1;
         k = k+k;
      }

/*
  determine k such that (1/beta)**k does not underflow
    first set  k = 2 ** i
*/

      (*iexp) = i + 1;
      mx = k + k;
      if (*ibeta == 10) {

/*
  for decimal machines only
*/

         (*iexp) = 2;
         iz = *ibeta;
         while (k >= iz) {
            iz = iz * (*ibeta);
            (*iexp) = (*iexp) + 1;
         }
         mx = iz + iz - 1;
      }

/*
  loop to determine minexp, xmin.
    exit from loop is signaled by an underflow.
*/

      for (;;) {
         (*xmin) = y;
         y = y * betain;
         a = y * one;
         tmp = y*t;
         tmp1 = a+a;
         if ((tmp1 == zero) || (ABS(y) >= (*xmin))) break;
         k = k + 1;
         tmp1 = tmp*betain;
         tmp1 = tmp1*beta;

         if ((tmp1 == y) && (tmp != y)) {
            nxres = 3;
            *xmin = y;
            break;
         }

      }

      (*minexp) = -k;

/*
  determine maxexp, xmax
*/

      if ((mx <= k+k-3) && ((*ibeta) != 10)) {
         mx = mx + mx;
         (*iexp) = (*iexp) + 1;
      }

      (*maxexp) = mx + (*minexp);

/*
  Adjust *irnd to reflect partial underflow.
*/

      (*irnd) = (*irnd)+nxres;

/*
  Adjust for IEEE style machines.
*/

      if ((*irnd) >= 2) (*maxexp) = (*maxexp)-2;

/*
  adjust for machines with implicit leading bit in binary
    significand and machines with radix point at extreme
    right of significand.
*/

      i = (*maxexp) + (*minexp);
      if (((*ibeta) == 2) && (i == 0)) (*maxexp) = (*maxexp) - 1;
      if (i > 20) (*maxexp) = (*maxexp) - 1;
      if (a != y) (*maxexp) = (*maxexp) - 2;
      (*xmax) = one - (*epsneg);
      tmp = (*xmax)*one;
      if (tmp != (*xmax)) (*xmax) = one - beta * (*epsneg);
      (*xmax) = (*xmax) / (beta * beta * beta * (*xmin));
      i = (*maxexp) + (*minexp) + 3;
      if (i > 0) {

         for (j = 1; j<=i; j++ ) {
             if ((*ibeta) == 2) (*xmax) = (*xmax) + (*xmax);
             if ((*ibeta) != 2) (*xmax) = (*xmax) * beta;
         }

      }

    return;

}

void
#if defined (F77_APPEND_UNDERSCORE)
machar_ (REAL *xmin, REAL *xmax, REAL *epsneg, REAL *eps, REAL *log10_ibeta)
#else
machar (REAL *xmin, REAL *xmax, REAL *epsneg, REAL *eps, REAL *log10_ibeta)
#endif
{
  int ibeta, iexp, irnd, it, machep, maxexp, minexp, negep, ngrd;

  rmachar (&ibeta, &it, &irnd, &ngrd, &machep, &negep, &iexp, &minexp,
	   &maxexp, eps, epsneg, xmin, xmax);

  *log10_ibeta = log10 ((REAL) ibeta);
}