aboutsummaryrefslogtreecommitdiff
path: root/libgcc/config/rs6000/_divkc3.c
blob: b08e47c8af4ded2951f8e066c1221e45a6976b31 (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
/* Copyright (C) 1989-2024 Free Software Foundation, Inc.

This file is part of GCC.

GCC is free software; you can redistribute it and/or modify it under
the terms of the GNU General Public License as published by the Free
Software Foundation; either version 3, or (at your option) any later
version.

GCC 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 General Public License
for more details.

Under Section 7 of GPL version 3, you are granted additional
permissions described in the GCC Runtime Library Exception, version
3.1, as published by the Free Software Foundation.

You should have received a copy of the GNU General Public License and
a copy of the GCC Runtime Library Exception along with this program;
see the files COPYING3 and COPYING.RUNTIME respectively.  If not, see
<http://www.gnu.org/licenses/>.  */

/* This is a temporary specialization of code from libgcc/libgcc2.c.  */

#include "soft-fp.h"
#include "quad-float128.h"

/* Use the correct built-in function based on whether TFmode is _Float128 or
   long double.  See quad-float128.h for more details.  */
#ifndef __LONG_DOUBLE_IEEE128__
#define COPYSIGN(x,y) __builtin_copysignf128 (x, y)
#define INFINITY __builtin_inff128 ()
#define FABS __builtin_fabsf128

#else
#define COPYSIGN(x,y) __builtin_copysignl (x, y)
#define INFINITY __builtin_infl ()
#define FABS __builtin_fabsl
#endif

#define isnan __builtin_isnan
#define isinf __builtin_isinf
#define isfinite __builtin_isfinite

#if defined(FLOAT128_HW_INSNS) && !defined(__divkc3)
#define __divkc3 __divkc3_sw
#endif

#ifndef __LONG_DOUBLE_IEEE128__
#define RBIG   (__LIBGCC_KF_MAX__ / 2)
#define RMIN   (__LIBGCC_KF_MIN__)
#define RMIN2  (__LIBGCC_KF_EPSILON__)
#define RMINSCAL (1 / __LIBGCC_KF_EPSILON__)
#define RMAX2  (RBIG * RMIN2)
#else
#define RBIG   (__LIBGCC_TF_MAX__ / 2)
#define RMIN   (__LIBGCC_TF_MIN__)
#define RMIN2  (__LIBGCC_TF_EPSILON__)
#define RMINSCAL (1 / __LIBGCC_TF_EPSILON__)
#define RMAX2  (RBIG * RMIN2)
#endif

TCtype
__divkc3 (TFtype a, TFtype b, TFtype c, TFtype d)
{
  TFtype denom, ratio, x, y;
  TCtype res;

  /* long double has significant potential underflow/overflow errors that
     can be greatly reduced with a limited number of tests and adjustments.
  */

  /* Scale by max(c,d) to reduce chances of denominator overflowing.  */
  if (FABS (c) < FABS (d))
    {
      /* Prevent underflow when denominator is near max representable.  */
      if (FABS (d) >= RBIG)
	{
	  a = a / 2;
	  b = b / 2;
	  c = c / 2;
	  d = d / 2;
	}
      /* Avoid overflow/underflow issues when c and d are small.
	 Scaling up helps avoid some underflows.
	 No new overflow possible since c&d < RMIN2.  */
      if (FABS (d) < RMIN2)
	{
	  a = a * RMINSCAL;
	  b = b * RMINSCAL;
	  c = c * RMINSCAL;
	  d = d * RMINSCAL;
	}
      else
	{
	  if (((FABS (a) < RMIN) && (FABS (b) < RMAX2) && (FABS (d) < RMAX2))
	      || ((FABS (b) < RMIN) && (FABS (a) < RMAX2)
		  && (FABS (d) < RMAX2)))
	    {
	      a = a * RMINSCAL;
	      b = b * RMINSCAL;
	      c = c * RMINSCAL;
	      d = d * RMINSCAL;
	    }
	}
      ratio = c / d;
      denom = (c * ratio) + d;
      /* Choose alternate order of computation if ratio is subnormal.  */
      if (FABS (ratio) > RMIN)
	{
	  x = ((a * ratio) + b) / denom;
	  y = ((b * ratio) - a) / denom;
	}
      else
	{
	  x = ((c * (a / d)) + b) / denom;
	  y = ((c * (b / d)) - a) / denom;
	}
    }
  else
    {
      /* Prevent underflow when denominator is near max representable.  */
      if (FABS (c) >= RBIG)
	{
	  a = a / 2;
	  b = b / 2;
	  c = c / 2;
	  d = d / 2;
	}
      /* Avoid overflow/underflow issues when both c and d are small.
	 Scaling up helps avoid some underflows.
	 No new overflow possible since both c&d are less than RMIN2.  */
      if (FABS (c) < RMIN2)
	{
	  a = a * RMINSCAL;
	  b = b * RMINSCAL;
	  c = c * RMINSCAL;
	  d = d * RMINSCAL;
	}
      else
	{
	  if (((FABS (a) < RMIN) && (FABS (b) < RMAX2) && (FABS (c) < RMAX2))
	      || ((FABS (b) < RMIN) && (FABS (a) < RMAX2)
		  && (FABS (c) < RMAX2)))
	    {
	      a = a * RMINSCAL;
	      b = b * RMINSCAL;
	      c = c * RMINSCAL;
	      d = d * RMINSCAL;
	    }
	}
      ratio = d / c;
      denom = (d * ratio) + c;
      /* Choose alternate order of computation if ratio is subnormal.  */
      if (FABS (ratio) > RMIN)
	{
	  x = ((b * ratio) + a) / denom;
	  y = (b - (a * ratio)) / denom;
	}
      else
	{
	  x = (a + (d * (b / c))) / denom;
	  y = (b - (d * (a / c))) / denom;
	}
    }

  /* Recover infinities and zeros that computed as NaN+iNaN; the only cases
     are nonzero/zero, infinite/finite, and finite/infinite.  */
  if (isnan (x) && isnan (y))
    {
      if (c == 0.0 && d == 0.0 && (!isnan (a) || !isnan (b)))
	{
	  x = COPYSIGN (INFINITY, c) * a;
	  y = COPYSIGN (INFINITY, c) * b;
	}
      else if ((isinf (a) || isinf (b)) && isfinite (c) && isfinite (d))
	{
	  a = COPYSIGN (isinf (a) ? 1 : 0, a);
	  b = COPYSIGN (isinf (b) ? 1 : 0, b);
	  x = INFINITY * (a * c + b * d);
	  y = INFINITY * (b * c - a * d);
	}
      else if ((isinf (c) || isinf (d)) && isfinite (a) && isfinite (b))
	{
	  c = COPYSIGN (isinf (c) ? 1 : 0, c);
	  d = COPYSIGN (isinf (d) ? 1 : 0, d);
	  x = 0.0 * (a * c + b * d);
	  y = 0.0 * (b * c - a * d);
	}
    }

  __real__ res = x;
  __imag__ res = y;
  return res;
}