summary refs log tree commit diff
path: root/sysdeps/powerpc/fpu/e_hypot.c
blob: 58352c0e54c6111b8097d38801dd408d4c255833 (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
/* Pythagorean addition using doubles
   Copyright (C) 2011-2018 Free Software Foundation, Inc.
   This file is part of the GNU C Library
   Contributed by Adhemerval Zanella <azanella@br.ibm.com>, 2011

   The GNU C Library is free software; you can redistribute it and/or
   modify it under the terms of the GNU Library General Public License as
   published by the Free Software Foundation; either version 2 of the
   License, or (at your option) any later version.

   The GNU C 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
   Library General Public License for more details.

   You should have received a copy of the GNU Library General Public
   License along with the GNU C Library; see the file COPYING.LIB.  If
   not, see <http://www.gnu.org/licenses/>.  */

#include <math.h>
#include <math_private.h>
#include <stdint.h>

static const double two60   = 1.152921504606847e+18;
static const double two500  = 3.2733906078961419e+150;
static const double two600  = 4.149515568880993e+180;
static const double two1022 = 4.49423283715579e+307;
static const double twoM500 = 3.054936363499605e-151;
static const double twoM600 = 2.4099198651028841e-181;
static const double two60factor = 1.5592502418239997e+290;
static const double pdnum   = 2.225073858507201e-308;

/* __ieee754_hypot(x,y)
 *
 * This a FP only version without any FP->INT conversion.
 * It is similar to default C version, making appropriates
 * overflow and underflows checks as well scaling when it
 * is needed.
 */

#ifdef _ARCH_PWR7
/* POWER7 isinf and isnan optimization are fast. */
# define TEST_INF_NAN(x, y)                                       \
   if ((isinf(x) || isinf(y))					  \
       && !issignaling (x) && !issignaling (y))			  \
       return INFINITY;                                           \
   if (isnan(x) || isnan(y))                                      \
       return x + y;
# else
/* For POWER6 and below isinf/isnan triggers LHS and PLT calls are
 * costly (especially for POWER6). */
# define GET_TW0_HIGH_WORD(d1,d2,i1,i2)                           \
 do {                                                             \
   ieee_double_shape_type gh_u1;                                  \
   ieee_double_shape_type gh_u2;                                  \
   gh_u1.value = (d1);                                            \
   gh_u2.value = (d2);                                            \
   (i1) = gh_u1.parts.msw & 0x7fffffff;                           \
   (i2) = gh_u2.parts.msw & 0x7fffffff;                           \
 } while (0)

# define TEST_INF_NAN(x, y)                                      \
 do {                                                            \
   uint32_t hx, hy;                                              \
   GET_TW0_HIGH_WORD(x, y, hx, hy);                              \
   if (hy > hx) {                                                \
     uint32_t ht = hx; hx = hy; hy = ht;                         \
   }                                                             \
   if (hx >= 0x7ff00000) {                                       \
     if ((hx == 0x7ff00000 || hy == 0x7ff00000)			 \
	 && !issignaling (x) && !issignaling (y))		 \
       return INFINITY;                                          \
     return x + y;						 \
   }                                                             \
 } while (0)

#endif


double
__ieee754_hypot (double x, double y)
{
  x = fabs (x);
  y = fabs (y);

  TEST_INF_NAN (x, y);

  if (y > x)
    {
      double t = x;
      x = y;
      y = t;
    }
  if (y == 0.0)
    return x;
  /* if y is higher enough, y * 2^60 might overflow. The tests if
     y >= 1.7976931348623157e+308/2^60 (two60factor) and uses the
     appropriate check to avoid the overflow exception generation.  */
  if (y > two60factor)
    {
      if ((x / y) > two60)
	return x + y;
    }
  else
    {
      if (x > (y * two60))
	return x + y;
    }
  if (x > two500)
    {
      x *= twoM600;
      y *= twoM600;
      return sqrt (x * x + y * y) / twoM600;
    }
  if (y < twoM500)
    {
      if (y <= pdnum)
	{
	  x *= two1022;
	  y *= two1022;
	  double ret = sqrt (x * x + y * y) / two1022;
	  math_check_force_underflow_nonneg (ret);
	  return ret;
	}
      else
	{
	  x *= two600;
	  y *= two600;
	  return sqrt (x * x + y * y) / two600;
	}
    }
  return sqrt (x * x + y * y);
}
strong_alias (__ieee754_hypot, __hypot_finite)