mirror of
https://sourceware.org/git/glibc.git
synced 2024-11-30 00:31:08 +00:00
e44acb2063
Similar to the changes that were made to call sqrt functions directly in glibc, instead of __ieee754_sqrt variants, so that the compiler could inline them automatically without needing special inline definitions in lots of math_private.h headers, this patch makes libm code call floor functions directly instead of __floor variants, removing the inlines / macros for x86_64 (SSE4.1) and powerpc (POWER5). The redirection used to ensure that __ieee754_sqrt does still get called when the compiler doesn't inline a built-in function expansion is refactored so it can be applied to other functions; the refactoring is arranged so it's not limited to unary functions either (it would be reasonable to use this mechanism for copysign - removing the inline in math_private_calls.h but also eliminating unnecessary local PLT entry use in the cases (powerpc soft-float and e500v1, for IBM long double) where copysign calls don't get inlined). The point of this change is that more architectures can get floor calls inlined where they weren't previously (AArch64, for example), without needing special inline definitions in their math_private.h, and existing such definitions in math_private.h headers can be removed. Note that it's possible that in some cases an inline may be used where an IFUNC call was previously used - this is the case on x86_64, for example. I think the direct calls to floor are still appropriate; if there's any significant performance cost from inline SSE2 floor instead of an IFUNC call ending up with SSE4.1 floor, that indicates that either the function should be doing something else that's faster than using floor at all, or it should itself have IFUNC variants, or that the compiler choice of inlining for generic tuning should change to allow for the possibility that, by not inlining, an SSE4.1 IFUNC might be called at runtime - but not that glibc should avoid calling floor internally. (After all, all the same considerations would apply to any user program calling floor, where it might either be inlined or left as an out-of-line call allowing for a possible IFUNC.) Tested for x86_64, and with build-many-glibcs.py. * include/math.h [!_ISOMAC && !(__FINITE_MATH_ONLY__ && __FINITE_MATH_ONLY__ > 0) && !NO_MATH_REDIRECT] (MATH_REDIRECT): New macro. [!_ISOMAC && !(__FINITE_MATH_ONLY__ && __FINITE_MATH_ONLY__ > 0) && !NO_MATH_REDIRECT] (MATH_REDIRECT_LDBL): Likewise. [!_ISOMAC && !(__FINITE_MATH_ONLY__ && __FINITE_MATH_ONLY__ > 0) && !NO_MATH_REDIRECT] (MATH_REDIRECT_F128): Likewise. [!_ISOMAC && !(__FINITE_MATH_ONLY__ && __FINITE_MATH_ONLY__ > 0) && !NO_MATH_REDIRECT] (MATH_REDIRECT_UNARY_ARGS): Likewise. [!_ISOMAC && !(__FINITE_MATH_ONLY__ && __FINITE_MATH_ONLY__ > 0) && !NO_MATH_REDIRECT] (sqrt): Redirect using MATH_REDIRECT. [!_ISOMAC && !(__FINITE_MATH_ONLY__ && __FINITE_MATH_ONLY__ > 0) && !NO_MATH_REDIRECT] (floor): Likewise. * sysdeps/aarch64/fpu/s_floor.c: Define NO_MATH_REDIRECT before header inclusion. * sysdeps/aarch64/fpu/s_floorf.c: Likewise. * sysdeps/ieee754/dbl-64/s_floor.c: Likewise. * sysdeps/ieee754/dbl-64/wordsize-64/s_floor.c: Likewise. * sysdeps/ieee754/float128/s_floorf128.c: Likewise. * sysdeps/ieee754/flt-32/s_floorf.c: Likewise. * sysdeps/ieee754/ldbl-128/s_floorl.c: Likewise. * sysdeps/ieee754/ldbl-128ibm/s_floorl.c: Likewise. * sysdeps/m68k/m680x0/fpu/s_floor_template.c: Likewise. * sysdeps/powerpc/powerpc32/power4/fpu/multiarch/s_floor.c: Likewise. * sysdeps/powerpc/powerpc32/power4/fpu/multiarch/s_floorf.c: Likewise. * sysdeps/powerpc/powerpc64/fpu/multiarch/s_floor.c: Likewise. * sysdeps/powerpc/powerpc64/fpu/multiarch/s_floorf.c: Likewise. * sysdeps/riscv/rv64/rvd/s_floor.c: Likewise. * sysdeps/riscv/rvf/s_floorf.c: Likewise. * sysdeps/sparc/sparc64/fpu/multiarch/s_floor.c: Likewise. * sysdeps/sparc/sparc64/fpu/multiarch/s_floorf.c: Likewise. * sysdeps/x86_64/fpu/multiarch/s_floor.c: Likewise. * sysdeps/x86_64/fpu/multiarch/s_floorf.c: Likewise. * sysdeps/powerpc/fpu/math_private.h [_ARCH_PWR5X] (__floor): Remove macro. [_ARCH_PWR5X] (__floorf): Likewise. * sysdeps/x86_64/fpu/math_private.h [__SSE4_1__] (__floor): Remove inline function. [__SSE4_1__] (__floorf): Likewise. * math/w_lgamma_main.c (LGFUNC (__lgamma)): Use floor functions instead of __floor variants. * math/w_lgamma_r_compat.c (__lgamma_r): Likewise. * math/w_lgammaf_main.c (LGFUNC (__lgammaf)): Likewise. * math/w_lgammaf_r_compat.c (__lgammaf_r): Likewise. * math/w_lgammal_main.c (LGFUNC (__lgammal)): Likewise. * math/w_lgammal_r_compat.c (__lgammal_r): Likewise. * math/w_tgamma_compat.c (__tgamma): Likewise. * math/w_tgamma_template.c (M_DECL_FUNC (__tgamma)): Likewise. * math/w_tgammaf_compat.c (__tgammaf): Likewise. * math/w_tgammal_compat.c (__tgammal): Likewise. * sysdeps/ieee754/dbl-64/e_lgamma_r.c (sin_pi): Likewise. * sysdeps/ieee754/dbl-64/k_rem_pio2.c (__kernel_rem_pio2): Likewise. * sysdeps/ieee754/dbl-64/lgamma_neg.c (__lgamma_neg): Likewise. * sysdeps/ieee754/flt-32/e_lgammaf_r.c (sin_pif): Likewise. * sysdeps/ieee754/flt-32/lgamma_negf.c (__lgamma_negf): Likewise. * sysdeps/ieee754/ldbl-128/e_lgammal_r.c (__ieee754_lgammal_r): Likewise. * sysdeps/ieee754/ldbl-128/e_powl.c (__ieee754_powl): Likewise. * sysdeps/ieee754/ldbl-128/lgamma_negl.c (__lgamma_negl): Likewise. * sysdeps/ieee754/ldbl-128/s_expm1l.c (__expm1l): Likewise. * sysdeps/ieee754/ldbl-128ibm/e_lgammal_r.c (__ieee754_lgammal_r): Likewise. * sysdeps/ieee754/ldbl-128ibm/e_powl.c (__ieee754_powl): Likewise. * sysdeps/ieee754/ldbl-128ibm/lgamma_negl.c (__lgamma_negl): Likewise. * sysdeps/ieee754/ldbl-128ibm/s_expm1l.c (__expm1l): Likewise. * sysdeps/ieee754/ldbl-128ibm/s_truncl.c (__truncl): Likewise. * sysdeps/ieee754/ldbl-96/e_lgammal_r.c (sin_pi): Likewise. * sysdeps/ieee754/ldbl-96/lgamma_negl.c (__lgamma_negl): Likewise. * sysdeps/powerpc/power5+/fpu/s_modf.c (__modf): Likewise. * sysdeps/powerpc/power5+/fpu/s_modff.c (__modff): Likewise.
153 lines
4.2 KiB
C
153 lines
4.2 KiB
C
/* expm1l.c
|
|
*
|
|
* Exponential function, minus 1
|
|
* 128-bit long double precision
|
|
*
|
|
*
|
|
*
|
|
* SYNOPSIS:
|
|
*
|
|
* long double x, y, expm1l();
|
|
*
|
|
* y = expm1l( x );
|
|
*
|
|
*
|
|
*
|
|
* DESCRIPTION:
|
|
*
|
|
* Returns e (2.71828...) raised to the x power, minus one.
|
|
*
|
|
* Range reduction is accomplished by separating the argument
|
|
* into an integer k and fraction f such that
|
|
*
|
|
* x k f
|
|
* e = 2 e.
|
|
*
|
|
* An expansion x + .5 x^2 + x^3 R(x) approximates exp(f) - 1
|
|
* in the basic range [-0.5 ln 2, 0.5 ln 2].
|
|
*
|
|
*
|
|
* ACCURACY:
|
|
*
|
|
* Relative error:
|
|
* arithmetic domain # trials peak rms
|
|
* IEEE -79,+MAXLOG 100,000 1.7e-34 4.5e-35
|
|
*
|
|
*/
|
|
|
|
/* Copyright 2001 by Stephen L. Moshier
|
|
|
|
This 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.
|
|
|
|
This 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 this library; if not, see
|
|
<http://www.gnu.org/licenses/>. */
|
|
|
|
#include <errno.h>
|
|
#include <math.h>
|
|
#include <math_private.h>
|
|
#include <math_ldbl_opt.h>
|
|
|
|
/* exp(x) - 1 = x + 0.5 x^2 + x^3 P(x)/Q(x)
|
|
-.5 ln 2 < x < .5 ln 2
|
|
Theoretical peak relative error = 8.1e-36 */
|
|
|
|
static const long double
|
|
P0 = 2.943520915569954073888921213330863757240E8L,
|
|
P1 = -5.722847283900608941516165725053359168840E7L,
|
|
P2 = 8.944630806357575461578107295909719817253E6L,
|
|
P3 = -7.212432713558031519943281748462837065308E5L,
|
|
P4 = 4.578962475841642634225390068461943438441E4L,
|
|
P5 = -1.716772506388927649032068540558788106762E3L,
|
|
P6 = 4.401308817383362136048032038528753151144E1L,
|
|
P7 = -4.888737542888633647784737721812546636240E-1L,
|
|
Q0 = 1.766112549341972444333352727998584753865E9L,
|
|
Q1 = -7.848989743695296475743081255027098295771E8L,
|
|
Q2 = 1.615869009634292424463780387327037251069E8L,
|
|
Q3 = -2.019684072836541751428967854947019415698E7L,
|
|
Q4 = 1.682912729190313538934190635536631941751E6L,
|
|
Q5 = -9.615511549171441430850103489315371768998E4L,
|
|
Q6 = 3.697714952261803935521187272204485251835E3L,
|
|
Q7 = -8.802340681794263968892934703309274564037E1L,
|
|
/* Q8 = 1.000000000000000000000000000000000000000E0 */
|
|
/* C1 + C2 = ln 2 */
|
|
|
|
C1 = 6.93145751953125E-1L,
|
|
C2 = 1.428606820309417232121458176568075500134E-6L,
|
|
/* ln 2^-114 */
|
|
minarg = -7.9018778583833765273564461846232128760607E1L, big = 1e290L;
|
|
|
|
|
|
long double
|
|
__expm1l (long double x)
|
|
{
|
|
long double px, qx, xx;
|
|
int32_t ix, lx, sign;
|
|
int k;
|
|
double xhi;
|
|
|
|
/* Detect infinity and NaN. */
|
|
xhi = ldbl_high (x);
|
|
EXTRACT_WORDS (ix, lx, xhi);
|
|
sign = ix & 0x80000000;
|
|
ix &= 0x7fffffff;
|
|
if (!sign && ix >= 0x40600000)
|
|
return __expl (x);
|
|
if (ix >= 0x7ff00000)
|
|
{
|
|
/* Infinity (which must be negative infinity). */
|
|
if (((ix - 0x7ff00000) | lx) == 0)
|
|
return -1.0L;
|
|
/* NaN. Invalid exception if signaling. */
|
|
return x + x;
|
|
}
|
|
|
|
/* expm1(+- 0) = +- 0. */
|
|
if ((ix | lx) == 0)
|
|
return x;
|
|
|
|
/* Minimum value. */
|
|
if (x < minarg)
|
|
return (4.0/big - 1.0L);
|
|
|
|
/* Express x = ln 2 (k + remainder), remainder not exceeding 1/2. */
|
|
xx = C1 + C2; /* ln 2. */
|
|
px = floorl (0.5 + x / xx);
|
|
k = px;
|
|
/* remainder times ln 2 */
|
|
x -= px * C1;
|
|
x -= px * C2;
|
|
|
|
/* Approximate exp(remainder ln 2). */
|
|
px = (((((((P7 * x
|
|
+ P6) * x
|
|
+ P5) * x + P4) * x + P3) * x + P2) * x + P1) * x + P0) * x;
|
|
|
|
qx = (((((((x
|
|
+ Q7) * x
|
|
+ Q6) * x + Q5) * x + Q4) * x + Q3) * x + Q2) * x + Q1) * x + Q0;
|
|
|
|
xx = x * x;
|
|
qx = x + (0.5 * xx + xx * px / qx);
|
|
|
|
/* exp(x) = exp(k ln 2) exp(remainder ln 2) = 2^k exp(remainder ln 2).
|
|
|
|
We have qx = exp(remainder ln 2) - 1, so
|
|
exp(x) - 1 = 2^k (qx + 1) - 1
|
|
= 2^k qx + 2^k - 1. */
|
|
|
|
px = __ldexpl (1.0L, k);
|
|
x = px * qx + (px - 1.0);
|
|
return x;
|
|
}
|
|
libm_hidden_def (__expm1l)
|
|
long_double_symbol (libm, __expm1l, expm1l);
|