mirror of
https://sourceware.org/git/glibc.git
synced 2024-11-27 07:20:11 +00:00
aaee3cd88e
This patch continues cleaning up the math_private.h header, which contains lots of different definitions many of which are only needed by a limited subset of files using that header (and some of which are overridden by architectures that only want to override selected parts of the header), by moving the math_narrow_eval macro out to a separate math-narrow-eval.h header, only included by those files that need it. That header is placed in include/ (since it's used in stdlib/, not just files built in math/, but no sysdeps variants are needed at present). Tested for x86_64, and with build-many-glibcs.py. (Installed stripped shared libraries change because of line numbers in assertions in strtod_l.c.) * include/math-narrow-eval.h: New file. Contents moved from .... * sysdeps/generic/math_private.h: ... here. (math_narrow_eval): Remove macro. Moved to math-narrow-eval.h. [FLT_EVAL_METHOD != 0] (excess_precision): Likewise. * math/s_fdim_template.c: Include <math-narrow-eval.h>. * stdlib/strtod_l.c: Likewise. * sysdeps/i386/fpu/s_f32xaddf64.c: Likewise. * sysdeps/i386/fpu/s_f32xsubf64.c: Likewise. * sysdeps/i386/fpu/s_fdim.c: Likewise. * sysdeps/ieee754/dbl-64/e_cosh.c: Likewise. * sysdeps/ieee754/dbl-64/e_gamma_r.c: Likewise. * sysdeps/ieee754/dbl-64/e_j1.c: Likewise. * sysdeps/ieee754/dbl-64/e_jn.c: Likewise. * sysdeps/ieee754/dbl-64/e_lgamma_r.c: Likewise. * sysdeps/ieee754/dbl-64/e_sinh.c: Likewise. * sysdeps/ieee754/dbl-64/gamma_productf.c: Likewise. * sysdeps/ieee754/dbl-64/k_rem_pio2.c: Likewise. * sysdeps/ieee754/dbl-64/lgamma_neg.c: Likewise. * sysdeps/ieee754/dbl-64/s_erf.c: Likewise. * sysdeps/ieee754/dbl-64/s_llrint.c: Likewise. * sysdeps/ieee754/dbl-64/s_lrint.c: Likewise. * sysdeps/ieee754/flt-32/e_coshf.c: Likewise. * sysdeps/ieee754/flt-32/e_exp2f.c: Likewise. * sysdeps/ieee754/flt-32/e_expf.c: Likewise. * sysdeps/ieee754/flt-32/e_gammaf_r.c: Likewise. * sysdeps/ieee754/flt-32/e_j1f.c: Likewise. * sysdeps/ieee754/flt-32/e_jnf.c: Likewise. * sysdeps/ieee754/flt-32/e_lgammaf_r.c: Likewise. * sysdeps/ieee754/flt-32/e_sinhf.c: Likewise. * sysdeps/ieee754/flt-32/k_rem_pio2f.c: Likewise. * sysdeps/ieee754/flt-32/lgamma_negf.c: Likewise. * sysdeps/ieee754/flt-32/s_erff.c: Likewise. * sysdeps/ieee754/flt-32/s_llrintf.c: Likewise. * sysdeps/ieee754/flt-32/s_lrintf.c: Likewise. * sysdeps/ieee754/ldbl-96/gamma_product.c: Likewise.
118 lines
3.2 KiB
C
118 lines
3.2 KiB
C
/* Single-precision e^x function.
|
|
Copyright (C) 2017-2018 Free Software Foundation, Inc.
|
|
This file is part of the GNU C Library.
|
|
|
|
The GNU C 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.
|
|
|
|
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
|
|
Lesser General Public License for more details.
|
|
|
|
You should have received a copy of the GNU Lesser General Public
|
|
License along with the GNU C Library; if not, see
|
|
<http://www.gnu.org/licenses/>. */
|
|
|
|
#ifdef __expf
|
|
# undef libm_hidden_proto
|
|
# define libm_hidden_proto(ignored)
|
|
#endif
|
|
|
|
#include <math.h>
|
|
#include <math-narrow-eval.h>
|
|
#include <stdint.h>
|
|
#include <shlib-compat.h>
|
|
#include <libm-alias-float.h>
|
|
#include "math_config.h"
|
|
|
|
/*
|
|
EXP2F_TABLE_BITS = 5
|
|
EXP2F_POLY_ORDER = 3
|
|
|
|
ULP error: 0.502 (nearest rounding.)
|
|
Relative error: 1.69 * 2^-34 in [-ln2/64, ln2/64] (before rounding.)
|
|
Wrong count: 170635 (all nearest rounding wrong results with fma.)
|
|
Non-nearest ULP error: 1 (rounded ULP error)
|
|
*/
|
|
|
|
#define N (1 << EXP2F_TABLE_BITS)
|
|
#define InvLn2N __exp2f_data.invln2_scaled
|
|
#define T __exp2f_data.tab
|
|
#define C __exp2f_data.poly_scaled
|
|
|
|
static inline uint32_t
|
|
top12 (float x)
|
|
{
|
|
return asuint (x) >> 20;
|
|
}
|
|
|
|
float
|
|
__expf (float x)
|
|
{
|
|
uint32_t abstop;
|
|
uint64_t ki, t;
|
|
/* double_t for better performance on targets with FLT_EVAL_METHOD==2. */
|
|
double_t kd, xd, z, r, r2, y, s;
|
|
|
|
xd = (double_t) x;
|
|
abstop = top12 (x) & 0x7ff;
|
|
if (__glibc_unlikely (abstop >= top12 (88.0f)))
|
|
{
|
|
/* |x| >= 88 or x is nan. */
|
|
if (asuint (x) == asuint (-INFINITY))
|
|
return 0.0f;
|
|
if (abstop >= top12 (INFINITY))
|
|
return x + x;
|
|
if (x > 0x1.62e42ep6f) /* x > log(0x1p128) ~= 88.72 */
|
|
return __math_oflowf (0);
|
|
if (x < -0x1.9fe368p6f) /* x < log(0x1p-150) ~= -103.97 */
|
|
return __math_uflowf (0);
|
|
#if WANT_ERRNO_UFLOW
|
|
if (x < -0x1.9d1d9ep6f) /* x < log(0x1p-149) ~= -103.28 */
|
|
return __math_may_uflowf (0);
|
|
#endif
|
|
}
|
|
|
|
/* x*N/Ln2 = k + r with r in [-1/2, 1/2] and int k. */
|
|
z = InvLn2N * xd;
|
|
|
|
/* Round and convert z to int, the result is in [-150*N, 128*N] and
|
|
ideally ties-to-even rule is used, otherwise the magnitude of r
|
|
can be bigger which gives larger approximation error. */
|
|
#if TOINT_INTRINSICS
|
|
kd = roundtoint (z);
|
|
ki = converttoint (z);
|
|
#elif TOINT_RINT
|
|
kd = rint (z);
|
|
ki = (long) kd;
|
|
#elif TOINT_SHIFT
|
|
# define SHIFT __exp2f_data.shift
|
|
kd = math_narrow_eval ((double) (z + SHIFT)); /* Needs to be double. */
|
|
ki = asuint64 (kd);
|
|
kd -= SHIFT;
|
|
#endif
|
|
r = z - kd;
|
|
|
|
/* exp(x) = 2^(k/N) * 2^(r/N) ~= s * (C0*r^3 + C1*r^2 + C2*r + 1) */
|
|
t = T[ki % N];
|
|
t += ki << (52 - EXP2F_TABLE_BITS);
|
|
s = asdouble (t);
|
|
z = C[0] * r + C[1];
|
|
r2 = r * r;
|
|
y = C[2] * r + 1;
|
|
y = z * r2 + y;
|
|
y = y * s;
|
|
return (float) y;
|
|
}
|
|
|
|
#ifndef __expf
|
|
hidden_def (__expf)
|
|
strong_alias (__expf, __ieee754_expf)
|
|
strong_alias (__expf, __expf_finite)
|
|
versioned_symbol (libm, __expf, expf, GLIBC_2_27);
|
|
libm_alias_float_other (__exp, exp)
|
|
#endif
|