mirror of
https://github.com/freebsd/freebsd-src
synced 2024-07-21 18:27:22 +00:00
2d3b0a687b
patch to fix half-cycle trigonometric functions
Paul Zimmermann, a MPFR developer, contacted me about large errors in
the half-cycle trigonometric functions. I've have investigated these
issues and developed the attached patch. The float, double, and ld80
(long double) changes have been tested.
Caveat emptor: The ld128 changes have not been compiled. The ld128
changes have not been tested. I do not have access to a system that
uses ld128 floating point.
Here is an itemized list of changes:
* lib/msun/src/math_private.h:
. Add fast floor macros to compute the integer part of |x| for
0 <= |x| 01xp(N-1), where N is the precision of the type of x.
These macros are used in the half-cycle trigonometric functions
(e.g., sinpi(x)).
. The FFLOOR80 macros is used with the Intel 80-bit extended double
functions. This macors corrects an off-by-one error, which led to
enormous error for |x| > 0x1p32.
* lib/msun/src/s_cospif.c:
* lib/msun/src/s_cospi.c:
* lib/msun/ld80/s_cospil.c:
. Update Copyright years.
. Use FFLOOR*() macro to get integer part of |x|.
. Correct handle the range 0x1p(N-1) <= |x| < 0x1pN. Here, one needs
to determine if the integral value of |x| is even or odd to choose
+1 or -1. If |x| >= 0x1pN, always return +1.
* lib/msun/src/s_sinpif.c:
* lib/msun/src/s_sinpi.c:
* lib/msun/ld80/s_sinpil.c:
. Update Copyright years.
. Use FFLOOR*() macro to get integer part of |x|.
* lib/msun/src/s_tanpif.c:
* lib/msun/src/s_tanpi.c:
* lib/msun/ld80/s_tanpil.c:
. Update Copyright years.
. For +-0.5, return +-inf. Previously, tanpi[fl]() returned an NaN.
. Use FFLOOR*() to get integer part of |x|. Need to determine if the
integer part is even or odd. This is used to set +-0 for |x|
integral
and +-inf for (n+1/2).
. For 0x1p(N-1) <= |x| < 0x1pN need to determine if x is an even or
odd
integer to select +0 or -0. For |x| >= 0x1pN, it is always an even
integer, select 0.
. Note, tanpi[fl](x) is an odd function, so one needs to consider
tanpi[fl](-|x|) = - tanpi[fl](|x|).
* lib/msun/ld128/s_cospil.c:
* lib/msun/ld128/s_sinpil.c:
* lib/msun/ld128/s_tanpil.c:
. Update Copyright years.
. These routines use an FFLOOR128 macros, which likely should be
replaced by a bit twiddling algorithm.
. The same considerations above are applied to 0x1p112 <= |x| <
0x1p113,
and |x| >= 0x1p113 cases.
. Note, even and odd determination used fmodl(x,2.), which is likely
slow.
PR: 272742
MFC after: 1 week
123 lines
3.3 KiB
C
123 lines
3.3 KiB
C
/*-
|
|
* Copyright (c) 2017-2023 Steven G. Kargl
|
|
* All rights reserved.
|
|
*
|
|
* Redistribution and use in source and binary forms, with or without
|
|
* modification, are permitted provided that the following conditions
|
|
* are met:
|
|
* 1. Redistributions of source code must retain the above copyright
|
|
* notice unmodified, this list of conditions, and the following
|
|
* disclaimer.
|
|
* 2. Redistributions in binary form must reproduce the above copyright
|
|
* notice, this list of conditions and the following disclaimer in the
|
|
* documentation and/or other materials provided with the distribution.
|
|
*
|
|
* THIS SOFTWARE IS PROVIDED BY THE AUTHOR ``AS IS'' AND ANY EXPRESS OR
|
|
* IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES
|
|
* OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED.
|
|
* IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR ANY DIRECT, INDIRECT,
|
|
* INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT
|
|
* NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
|
|
* DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
|
|
* THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
|
|
* (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF
|
|
* THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
|
|
*/
|
|
|
|
/*
|
|
* See ../src/s_tanpi.c for implementation details.
|
|
*/
|
|
|
|
#include "fpmath.h"
|
|
#include "math.h"
|
|
#include "math_private.h"
|
|
|
|
/*
|
|
* pi_hi contains the leading 56 bits of a 169 bit approximation for pi.
|
|
*/
|
|
static const long double
|
|
pi_hi = 3.14159265358979322702026593105983920e+00L,
|
|
pi_lo = 1.14423774522196636802434264184180742e-17L;
|
|
|
|
static inline long double
|
|
__kernel_tanpil(long double x)
|
|
{
|
|
long double hi, lo, t;
|
|
|
|
if (x < 0.25) {
|
|
hi = (double)x;
|
|
lo = x - hi;
|
|
lo = lo * (pi_lo + pi_hi) + hi * pi_lo;
|
|
hi *= pi_hi;
|
|
_2sumF(hi, lo);
|
|
t = __kernel_tanl(hi, lo, -1);
|
|
} else if (x > 0.25) {
|
|
x = 0.5 - x;
|
|
hi = (double)x;
|
|
lo = x - hi;
|
|
lo = lo * (pi_lo + pi_hi) + hi * pi_lo;
|
|
hi *= pi_hi;
|
|
_2sumF(hi, lo);
|
|
t = - __kernel_tanl(hi, lo, 1);
|
|
} else
|
|
t = 1;
|
|
|
|
return (t);
|
|
}
|
|
|
|
volatile static const double vzero = 0;
|
|
|
|
long double
|
|
tanpil(long double x)
|
|
{
|
|
long double ai, ar, ax, hi, lo, t;
|
|
double odd;
|
|
|
|
ax = fabsl(x);
|
|
|
|
if (ax < 1) {
|
|
if (ax < 0.5) {
|
|
if (ax < 0x1p-60) {
|
|
if (x == 0)
|
|
return (x);
|
|
hi = (double)x;
|
|
hi *= 0x1p113L;
|
|
lo = x * 0x1p113L - hi;
|
|
t = (pi_lo + pi_hi) * lo + pi_lo * lo +
|
|
pi_hi * hi;
|
|
return (t * 0x1p-113L);
|
|
}
|
|
t = __kernel_tanpil(ax);
|
|
} else if (ax == 0.5)
|
|
t = 1 / vzero;
|
|
else
|
|
t = -__kernel_tanpil(1 - ax);
|
|
return (x < 0 ? -t : t);
|
|
}
|
|
|
|
if (ax < 0x1p112) {
|
|
/* Split ax = ai + ar with 0 <= ar < 1. */
|
|
FFLOORL128(ax, ai, ar);
|
|
odd = fmodl(ai, 2.L) == 0 ? 1 : -1;
|
|
if (ar < 0.5)
|
|
t = ar == 0 ? copysign(0., odd) : __kernel_tanpil(ar);
|
|
else if (ar == 0.5)
|
|
t = odd / vzero;
|
|
else
|
|
t = -__kernel_tanpil(1 - ar);
|
|
return (x < 0 ? -t : t);
|
|
}
|
|
|
|
/* x = +-inf or nan. */
|
|
if (isinf(x) || isnan(x))
|
|
return (vzero / vzero);
|
|
|
|
/*
|
|
* For 0x1p112 <= |x| < 0x1p113 need to determine if x is an even
|
|
* or odd integer to set t = +0 or -0.
|
|
* For |x| >= 0x1p113, it is always an even integer, so t = 0.
|
|
*/
|
|
t = fmodl(ax,2.L) == 0 ? 0 : copysign(0., -1.);
|
|
return (copysignl(t, x));
|
|
}
|