mirror of
https://sourceware.org/git/glibc.git
synced 2024-12-02 09:40:13 +00:00
4b6574a6f6
include/math.h has a mechanism to redirect internal calls to various libm functions, that can often be inlined by the compiler, to call non-exported __* names for those functions in the case when the calls aren't inlined, with the redirection being disabled when NO_MATH_REDIRECT. Add fma to the functions to which this mechanism is applied. At present, libm-internal fma calls (generally to __builtin_fma* functions) are only done when it's known the call will be inlined, with alternative code not relying on an fma operation being used in the caller otherwise. This patch is in preparation for adding the TS 18661 / C2X narrowing fma functions to glibc; it will be natural for the narrowing function implementations to call the underlying fma functions unconditionally, with this either being inlined or resulting in an __fma* call. (Using two levels of round-to-odd computation like that, in the case where there isn't an fma hardware instruction, isn't optimal but is certainly a lot simpler for the initial implementation than writing different narrowing fma implementations for all the various pairs of formats.) Tested with build-many-glibcs.py that installed stripped shared libraries are unchanged by the patch (using <https://sourceware.org/pipermail/libc-alpha/2021-September/130991.html> to fix installed library stripping in build-many-glibcs.py). Also tested for x86_64.
73 lines
2.3 KiB
C
73 lines
2.3 KiB
C
/* Compute x * y + z as ternary operation.
|
|
Copyright (C) 2010-2021 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
|
|
<https://www.gnu.org/licenses/>. */
|
|
|
|
#define NO_MATH_REDIRECT
|
|
#include <math.h>
|
|
#include <fenv.h>
|
|
#include <ieee754.h>
|
|
#include <math-barriers.h>
|
|
#include <fenv_private.h>
|
|
#include <libm-alias-float.h>
|
|
#include <math-use-builtins.h>
|
|
|
|
/* This implementation relies on double being more than twice as
|
|
precise as float and uses rounding to odd in order to avoid problems
|
|
with double rounding.
|
|
See a paper by Boldo and Melquiond:
|
|
http://www.lri.fr/~melquion/doc/08-tc.pdf */
|
|
|
|
float
|
|
__fmaf (float x, float y, float z)
|
|
{
|
|
#if USE_FMAF_BUILTIN
|
|
return __builtin_fmaf (x, y, z);
|
|
#else
|
|
/* Use generic implementation. */
|
|
fenv_t env;
|
|
|
|
/* Multiplication is always exact. */
|
|
double temp = (double) x * (double) y;
|
|
|
|
/* Ensure correct sign of an exact zero result by performing the
|
|
addition in the original rounding mode in that case. */
|
|
if (temp == -z)
|
|
return (float) temp + z;
|
|
|
|
union ieee754_double u;
|
|
|
|
libc_feholdexcept_setround (&env, FE_TOWARDZERO);
|
|
|
|
/* Perform addition with round to odd. */
|
|
u.d = temp + (double) z;
|
|
/* Ensure the addition is not scheduled after fetestexcept call. */
|
|
math_force_eval (u.d);
|
|
|
|
/* Reset rounding mode and test for inexact simultaneously. */
|
|
int j = libc_feupdateenv_test (&env, FE_INEXACT) != 0;
|
|
|
|
if ((u.ieee.mantissa1 & 1) == 0 && u.ieee.exponent != 0x7ff)
|
|
u.ieee.mantissa1 |= j;
|
|
|
|
/* And finally truncation with round to nearest. */
|
|
return (float) u.d;
|
|
#endif /* ! USE_FMAF_BUILTIN */
|
|
}
|
|
#ifndef __fmaf
|
|
libm_alias_float (__fma, fma)
|
|
#endif
|