mirror of
https://sourceware.org/git/glibc.git
synced 2024-11-28 15:51:07 +00:00
d8742dd82f
This patch adds the narrowing add functions from TS 18661-1 to glibc's libm: fadd, faddl, daddl, f32addf64, f32addf32x, f32xaddf64 for all configurations; f32addf64x, f32addf128, f64addf64x, f64addf128, f32xaddf64x, f32xaddf128, f64xaddf128 for configurations with _Float64x and _Float128; __nldbl_daddl for ldbl-opt. As discussed for the build infrastructure patch, tgmath.h support is deliberately deferred, and FP_FAST_* macros are not applicable without optimized function implementations. Function implementations are added for all relevant pairs of formats (including certain cases of a format and itself where more than one type has that format). The main implementations use round-to-odd, or a trivial computation in the case where both formats are the same or where the wider format is IBM long double (in which case we don't attempt to be correctly rounding). The sysdeps/ieee754/soft-fp implementations use soft-fp, and are used automatically for configurations without exceptions and rounding modes by virtue of existing Implies files. As previously discussed, optimized versions for particular architectures are possible, but not included. i386 gets a special version of f32xaddf64 to avoid problems with double rounding (similar to the existing fdim version), since this function must round just once without an intermediate rounding to long double. (No such special version is needed for any other function, because the nontrivial functions use round-to-odd, which does the intermediate computation with the rounding mode set to round-to-zero, and double rounding is OK except in round-to-nearest mode, so is OK for that intermediate round-to-zero computation.) mul and div will need slightly different special versions for i386 (using round-to-odd on long double instead of precision control) because of the possibility of inexact intermediate results in the subnormal range for double. To reduce duplication among the different function implementations, math-narrow.h gets macros CHECK_NARROW_ADD, NARROW_ADD_ROUND_TO_ODD and NARROW_ADD_TRIVIAL. In the trivial cases and for any architecture-specific optimized implementations, the overhead of the errno setting might be significant, but I think that's best handled through compiler built-in functions rather than providing separate no-errno versions in glibc (and likewise there are no __*_finite entry points for these function provided, __*_finite effectively being no-errno versions at present in most cases). Tested for x86_64 and x86, with both GCC 6 and GCC 7. Tested for mips64 (all three ABIs, both hard and soft float) and powerpc with GCC 7. Tested with build-many-glibcs.py with both GCC 6 and GCC 7. * math/Makefile (libm-narrow-fns): Add add. (libm-test-funcs-narrow): Likewise. * math/Versions (GLIBC_2.28): Add narrowing add functions. * math/bits/mathcalls-narrow.h (add): Use __MATHCALL_NARROW . * math/gen-auto-libm-tests.c (test_functions): Add add. * math/math-narrow.h (CHECK_NARROW_ADD): New macro. (NARROW_ADD_ROUND_TO_ODD): Likewise. (NARROW_ADD_TRIVIAL): Likewise. * sysdeps/ieee754/float128/float128_private.h (__faddl): New macro. (__daddl): Likewise. * sysdeps/ieee754/ldbl-opt/Makefile (libnldbl-calls): Add fadd and dadd. (CFLAGS-nldbl-dadd.c): New variable. (CFLAGS-nldbl-fadd.c): Likewise. * sysdeps/ieee754/ldbl-opt/Versions (GLIBC_2.28): Add __nldbl_daddl. * sysdeps/ieee754/ldbl-opt/nldbl-compat.h (__nldbl_daddl): New prototype. * manual/arith.texi (Misc FP Arithmetic): Document fadd, faddl, daddl, fMaddfN, fMaddfNx, fMxaddfN and fMxaddfNx. * math/auto-libm-test-in: Add tests of add. * math/auto-libm-test-out-narrow-add: New generated file. * math/libm-test-narrow-add.inc: New file. * sysdeps/i386/fpu/s_f32xaddf64.c: Likewise. * sysdeps/ieee754/dbl-64/s_f32xaddf64.c: Likewise. * sysdeps/ieee754/dbl-64/s_fadd.c: Likewise. * sysdeps/ieee754/float128/s_f32addf128.c: Likewise. * sysdeps/ieee754/float128/s_f64addf128.c: Likewise. * sysdeps/ieee754/float128/s_f64xaddf128.c: Likewise. * sysdeps/ieee754/ldbl-128/s_daddl.c: Likewise. * sysdeps/ieee754/ldbl-128/s_f64xaddf128.c: Likewise. * sysdeps/ieee754/ldbl-128/s_faddl.c: Likewise. * sysdeps/ieee754/ldbl-128ibm/s_daddl.c: Likewise. * sysdeps/ieee754/ldbl-128ibm/s_faddl.c: Likewise. * sysdeps/ieee754/ldbl-96/s_daddl.c: Likewise. * sysdeps/ieee754/ldbl-96/s_faddl.c: Likewise. * sysdeps/ieee754/ldbl-opt/nldbl-dadd.c: Likewise. * sysdeps/ieee754/ldbl-opt/nldbl-fadd.c: Likewise. * sysdeps/ieee754/soft-fp/s_daddl.c: Likewise. * sysdeps/ieee754/soft-fp/s_fadd.c: Likewise. * sysdeps/ieee754/soft-fp/s_faddl.c: Likewise. * sysdeps/powerpc/fpu/libm-test-ulps: Update. * sysdeps/mach/hurd/i386/libm.abilist: Likewise. * sysdeps/unix/sysv/linux/aarch64/libm.abilist: Likewise. * sysdeps/unix/sysv/linux/alpha/libm.abilist: Likewise. * sysdeps/unix/sysv/linux/arm/libm.abilist: Likewise. * sysdeps/unix/sysv/linux/hppa/libm.abilist: Likewise. * sysdeps/unix/sysv/linux/i386/libm.abilist: Likewise. * sysdeps/unix/sysv/linux/ia64/libm.abilist: Likewise. * sysdeps/unix/sysv/linux/m68k/coldfire/libm.abilist: Likewise. * sysdeps/unix/sysv/linux/m68k/m680x0/libm.abilist: Likewise. * sysdeps/unix/sysv/linux/microblaze/libm.abilist: Likewise. * sysdeps/unix/sysv/linux/mips/mips32/libm.abilist: Likewise. * sysdeps/unix/sysv/linux/mips/mips64/libm.abilist: Likewise. * sysdeps/unix/sysv/linux/nios2/libm.abilist: Likewise. * sysdeps/unix/sysv/linux/powerpc/powerpc32/fpu/libm.abilist: Likewise. * sysdeps/unix/sysv/linux/powerpc/powerpc32/nofpu/libm.abilist: Likewise. * sysdeps/unix/sysv/linux/powerpc/powerpc64/libm-le.abilist: Likewise. * sysdeps/unix/sysv/linux/powerpc/powerpc64/libm.abilist: Likewise. * sysdeps/unix/sysv/linux/riscv/rv64/libm.abilist: Likewise. * sysdeps/unix/sysv/linux/s390/s390-32/libm.abilist: Likewise. * sysdeps/unix/sysv/linux/s390/s390-64/libm.abilist: Likewise. * sysdeps/unix/sysv/linux/sh/libm.abilist: Likewise. * sysdeps/unix/sysv/linux/sparc/sparc32/libm.abilist: Likewise. * sysdeps/unix/sysv/linux/sparc/sparc64/libm.abilist: Likewise. * sysdeps/unix/sysv/linux/tile/tilegx32/libm.abilist: Likewise. * sysdeps/unix/sysv/linux/tile/tilegx64/libm.abilist: Likewise. * sysdeps/unix/sysv/linux/x86_64/64/libm.abilist: Likewise. * sysdeps/unix/sysv/linux/x86_64/x32/libm.abilist: Likewise.
205 lines
7.1 KiB
C
205 lines
7.1 KiB
C
/* Helper macros for functions returning a narrower type.
|
|
Copyright (C) 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/>. */
|
|
|
|
#ifndef _MATH_NARROW_H
|
|
#define _MATH_NARROW_H 1
|
|
|
|
#include <bits/floatn.h>
|
|
#include <bits/long-double.h>
|
|
#include <errno.h>
|
|
#include <fenv.h>
|
|
#include <ieee754.h>
|
|
#include <math_private.h>
|
|
|
|
/* Carry out a computation using round-to-odd. The computation is
|
|
EXPR; the union type in which to store the result is UNION and the
|
|
subfield of the "ieee" field of that union with the low part of the
|
|
mantissa is MANTISSA; SUFFIX is the suffix for the libc_fe* macros
|
|
to ensure that the correct rounding mode is used, for platforms
|
|
with multiple rounding modes where those macros set only the
|
|
relevant mode. This macro does not work correctly if the sign of
|
|
an exact zero result depends on the rounding mode, so that case
|
|
must be checked for separately. */
|
|
#define ROUND_TO_ODD(EXPR, UNION, SUFFIX, MANTISSA) \
|
|
({ \
|
|
fenv_t env; \
|
|
UNION u; \
|
|
\
|
|
libc_feholdexcept_setround ## SUFFIX (&env, FE_TOWARDZERO); \
|
|
u.d = (EXPR); \
|
|
math_force_eval (u.d); \
|
|
u.ieee.MANTISSA \
|
|
|= libc_feupdateenv_test ## SUFFIX (&env, FE_INEXACT) != 0; \
|
|
\
|
|
u.d; \
|
|
})
|
|
|
|
/* Check for error conditions from a narrowing add function returning
|
|
RET with arguments X and Y and set errno as needed. Overflow and
|
|
underflow can occur for finite arguments and a domain error for
|
|
infinite ones. */
|
|
#define CHECK_NARROW_ADD(RET, X, Y) \
|
|
do \
|
|
{ \
|
|
if (!isfinite (RET)) \
|
|
{ \
|
|
if (isnan (RET)) \
|
|
{ \
|
|
if (!isnan (X) && !isnan (Y)) \
|
|
__set_errno (EDOM); \
|
|
} \
|
|
else if (isfinite (X) && isfinite (Y)) \
|
|
__set_errno (ERANGE); \
|
|
} \
|
|
else if ((RET) == 0 && (X) != -(Y)) \
|
|
__set_errno (ERANGE); \
|
|
} \
|
|
while (0)
|
|
|
|
/* Implement narrowing add using round-to-odd. The arguments are X
|
|
and Y, the return type is TYPE and UNION, MANTISSA and SUFFIX are
|
|
as for ROUND_TO_ODD. */
|
|
#define NARROW_ADD_ROUND_TO_ODD(X, Y, TYPE, UNION, SUFFIX, MANTISSA) \
|
|
do \
|
|
{ \
|
|
TYPE ret; \
|
|
\
|
|
/* Ensure a zero result is computed in the original rounding \
|
|
mode. */ \
|
|
if ((X) == -(Y)) \
|
|
ret = (TYPE) ((X) + (Y)); \
|
|
else \
|
|
ret = (TYPE) ROUND_TO_ODD (math_opt_barrier (X) + (Y), \
|
|
UNION, SUFFIX, MANTISSA); \
|
|
\
|
|
CHECK_NARROW_ADD (ret, (X), (Y)); \
|
|
return ret; \
|
|
} \
|
|
while (0)
|
|
|
|
/* Implement a narrowing add function that is not actually narrowing
|
|
or where no attempt is made to be correctly rounding (the latter
|
|
only applies to IBM long double). The arguments are X and Y and
|
|
the return type is TYPE. */
|
|
#define NARROW_ADD_TRIVIAL(X, Y, TYPE) \
|
|
do \
|
|
{ \
|
|
TYPE ret; \
|
|
\
|
|
ret = (TYPE) ((X) + (Y)); \
|
|
CHECK_NARROW_ADD (ret, (X), (Y)); \
|
|
return ret; \
|
|
} \
|
|
while (0)
|
|
|
|
/* The following macros declare aliases for a narrowing function. The
|
|
sole argument is the base name of a family of functions, such as
|
|
"add". If any platform changes long double format after the
|
|
introduction of narrowing functions, in a way requiring symbol
|
|
versioning compatibility, additional variants of these macros will
|
|
be needed. */
|
|
|
|
#define libm_alias_float_double_main(func) \
|
|
weak_alias (__f ## func, f ## func) \
|
|
weak_alias (__f ## func, f32 ## func ## f64) \
|
|
weak_alias (__f ## func, f32 ## func ## f32x)
|
|
|
|
#ifdef NO_LONG_DOUBLE
|
|
# define libm_alias_float_double(func) \
|
|
libm_alias_float_double_main (func) \
|
|
weak_alias (__f ## func, f ## func ## l)
|
|
#else
|
|
# define libm_alias_float_double(func) \
|
|
libm_alias_float_double_main (func)
|
|
#endif
|
|
|
|
#define libm_alias_float32x_float64_main(func) \
|
|
weak_alias (__f32x ## func ## f64, f32x ## func ## f64)
|
|
|
|
#ifdef NO_LONG_DOUBLE
|
|
# define libm_alias_float32x_float64(func) \
|
|
libm_alias_float32x_float64_main (func) \
|
|
weak_alias (__f32x ## func ## f64, d ## func ## l)
|
|
#elif defined __LONG_DOUBLE_MATH_OPTIONAL
|
|
# define libm_alias_float32x_float64(func) \
|
|
libm_alias_float32x_float64_main (func) \
|
|
weak_alias (__f32x ## func ## f64, __nldbl_d ## func ## l)
|
|
#else
|
|
# define libm_alias_float32x_float64(func) \
|
|
libm_alias_float32x_float64_main (func)
|
|
#endif
|
|
|
|
#if __HAVE_FLOAT128 && !__HAVE_DISTINCT_FLOAT128
|
|
# define libm_alias_float_ldouble_f128(func) \
|
|
weak_alias (__f ## func ## l, f32 ## func ## f128)
|
|
# define libm_alias_double_ldouble_f128(func) \
|
|
weak_alias (__d ## func ## l, f32x ## func ## f128) \
|
|
weak_alias (__d ## func ## l, f64 ## func ## f128)
|
|
#else
|
|
# define libm_alias_float_ldouble_f128(func)
|
|
# define libm_alias_double_ldouble_f128(func)
|
|
#endif
|
|
|
|
#if __HAVE_FLOAT64X_LONG_DOUBLE
|
|
# define libm_alias_float_ldouble_f64x(func) \
|
|
weak_alias (__f ## func ## l, f32 ## func ## f64x)
|
|
# define libm_alias_double_ldouble_f64x(func) \
|
|
weak_alias (__d ## func ## l, f32x ## func ## f64x) \
|
|
weak_alias (__d ## func ## l, f64 ## func ## f64x)
|
|
#else
|
|
# define libm_alias_float_ldouble_f64x(func)
|
|
# define libm_alias_double_ldouble_f64x(func)
|
|
#endif
|
|
|
|
#define libm_alias_float_ldouble(func) \
|
|
weak_alias (__f ## func ## l, f ## func ## l) \
|
|
libm_alias_float_ldouble_f128 (func) \
|
|
libm_alias_float_ldouble_f64x (func)
|
|
|
|
#define libm_alias_double_ldouble(func) \
|
|
weak_alias (__d ## func ## l, d ## func ## l) \
|
|
libm_alias_double_ldouble_f128 (func) \
|
|
libm_alias_double_ldouble_f64x (func)
|
|
|
|
#define libm_alias_float64x_float128(func) \
|
|
weak_alias (__f64x ## func ## f128, f64x ## func ## f128)
|
|
|
|
#define libm_alias_float32_float128_main(func) \
|
|
weak_alias (__f32 ## func ## f128, f32 ## func ## f128)
|
|
|
|
#define libm_alias_float64_float128_main(func) \
|
|
weak_alias (__f64 ## func ## f128, f64 ## func ## f128) \
|
|
weak_alias (__f64 ## func ## f128, f32x ## func ## f128)
|
|
|
|
#if __HAVE_FLOAT64X_LONG_DOUBLE
|
|
# define libm_alias_float32_float128(func) \
|
|
libm_alias_float32_float128_main (func)
|
|
# define libm_alias_float64_float128(func) \
|
|
libm_alias_float64_float128_main (func)
|
|
#else
|
|
# define libm_alias_float32_float128(func) \
|
|
libm_alias_float32_float128_main (func) \
|
|
weak_alias (__f32 ## func ## f128, f32 ## func ## f64x)
|
|
# define libm_alias_float64_float128(func) \
|
|
libm_alias_float64_float128_main (func) \
|
|
weak_alias (__f64 ## func ## f128, f64 ## func ## f64x) \
|
|
weak_alias (__f64 ## func ## f128, f32x ## func ## f64x)
|
|
#endif
|
|
|
|
#endif /* math-narrow.h. */
|