diff options
author | Joseph Myers <joseph@codesourcery.com> | 2018-02-10 02:08:43 +0000 |
---|---|---|
committer | Joseph Myers <joseph@codesourcery.com> | 2018-02-10 02:08:43 +0000 |
commit | d8742dd82f6a00601155c69bad3012e905591e1f (patch) | |
tree | d37836d2d6af8b428dc3092466bea93c2624469f /sysdeps/ieee754/ldbl-opt | |
parent | a85b70dbd2efb84123dcfb7a2131b2de81b59b6a (diff) | |
download | glibc-d8742dd82f6a00601155c69bad3012e905591e1f.tar.gz glibc-d8742dd82f6a00601155c69bad3012e905591e1f.tar.xz glibc-d8742dd82f6a00601155c69bad3012e905591e1f.zip |
Add narrowing add functions.
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.
Diffstat (limited to 'sysdeps/ieee754/ldbl-opt')
-rw-r--r-- | sysdeps/ieee754/ldbl-opt/Makefile | 4 | ||||
-rw-r--r-- | sysdeps/ieee754/ldbl-opt/Versions | 6 | ||||
-rw-r--r-- | sysdeps/ieee754/ldbl-opt/nldbl-compat.h | 3 | ||||
-rw-r--r-- | sysdeps/ieee754/ldbl-opt/nldbl-dadd.c | 28 | ||||
-rw-r--r-- | sysdeps/ieee754/ldbl-opt/nldbl-fadd.c | 28 |
5 files changed, 68 insertions, 1 deletions
diff --git a/sysdeps/ieee754/ldbl-opt/Makefile b/sysdeps/ieee754/ldbl-opt/Makefile index 38afe38ab8..2340e4ce29 100644 --- a/sysdeps/ieee754/ldbl-opt/Makefile +++ b/sysdeps/ieee754/ldbl-opt/Makefile @@ -44,7 +44,7 @@ libnldbl-calls = asprintf dprintf fprintf fscanf fwprintf fwscanf iovfscanf \ isoc99_vwscanf isoc99_vfwscanf isoc99_vswscanf \ nextup nextdown totalorder totalordermag getpayload \ canonicalize setpayload setpayloadsig llogb fmaxmag fminmag \ - roundeven fromfp ufromfp fromfpx ufromfpx + roundeven fromfp ufromfp fromfpx ufromfpx fadd dadd libnldbl-routines = $(libnldbl-calls:%=nldbl-%) libnldbl-inhibit-o = $(object-suffixes) libnldbl-static-only-routines = $(libnldbl-routines) @@ -86,6 +86,7 @@ CFLAGS-nldbl-csinh.c = -fno-builtin-csinhl CFLAGS-nldbl-csqrt.c = -fno-builtin-csqrtl CFLAGS-nldbl-ctan.c = -fno-builtin-ctanl CFLAGS-nldbl-ctanh.c = -fno-builtin-ctanhl +CFLAGS-nldbl-dadd.c = -fno-builtin-daddl CFLAGS-nldbl-erf.c = -fno-builtin-erfl CFLAGS-nldbl-erfc.c = -fno-builtin-erfcl CFLAGS-nldbl-exp.c = -fno-builtin-expl @@ -93,6 +94,7 @@ CFLAGS-nldbl-exp10.c = -fno-builtin-exp10l CFLAGS-nldbl-exp2.c = -fno-builtin-exp2l CFLAGS-nldbl-expm1.c = -fno-builtin-expm1l CFLAGS-nldbl-fabs.c = -fno-builtin-fabsl +CFLAGS-nldbl-fadd.c = -fno-builtin-faddl CFLAGS-nldbl-fdim.c = -fno-builtin-fdiml CFLAGS-nldbl-finite.c = -fno-builtin-finitel CFLAGS-nldbl-floor.c = -fno-builtin-floorl diff --git a/sysdeps/ieee754/ldbl-opt/Versions b/sysdeps/ieee754/ldbl-opt/Versions index d3f0beaef2..e50efa3520 100644 --- a/sysdeps/ieee754/ldbl-opt/Versions +++ b/sysdeps/ieee754/ldbl-opt/Versions @@ -97,4 +97,10 @@ libm { sincosl; tanl; tanhl; truncl; expl; __finitel; __signbitl; __fpclassifyl; nexttowardf; nexttoward; __nldbl_nexttowardf; } + GLIBC_2.28 { + # Functions taking long double = double argument and rounding + # result to double (same as f32x*f64 functions, but those names + # are not reserved in TS 18661-1). + __nldbl_daddl; + } } diff --git a/sysdeps/ieee754/ldbl-opt/nldbl-compat.h b/sysdeps/ieee754/ldbl-opt/nldbl-compat.h index d61fbb2f64..74f0e459fa 100644 --- a/sysdeps/ieee754/ldbl-opt/nldbl-compat.h +++ b/sysdeps/ieee754/ldbl-opt/nldbl-compat.h @@ -101,5 +101,8 @@ extern int __nldbl___obstack_vprintf_chk (struct obstack *, int, const char *, __gnuc_va_list) __THROW; extern void __nldbl___vsyslog_chk (int, int, const char *, va_list); +/* The original declarations of these were hidden by the including + file. */ +extern double __nldbl_daddl (double, double) __THROW; #endif /* __NLDBL_COMPAT_H */ diff --git a/sysdeps/ieee754/ldbl-opt/nldbl-dadd.c b/sysdeps/ieee754/ldbl-opt/nldbl-dadd.c new file mode 100644 index 0000000000..acbcb3ff75 --- /dev/null +++ b/sysdeps/ieee754/ldbl-opt/nldbl-dadd.c @@ -0,0 +1,28 @@ +/* Compatibility routine for IEEE double as long double for dadd. + 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/>. */ + +#define daddl __hide_daddl +#include "nldbl-compat.h" +#undef daddl + +double +attribute_hidden +daddl (double x, double y) +{ + return __nldbl_daddl (x, y); +} diff --git a/sysdeps/ieee754/ldbl-opt/nldbl-fadd.c b/sysdeps/ieee754/ldbl-opt/nldbl-fadd.c new file mode 100644 index 0000000000..c31a6db475 --- /dev/null +++ b/sysdeps/ieee754/ldbl-opt/nldbl-fadd.c @@ -0,0 +1,28 @@ +/* Compatibility routine for IEEE double as long double for fadd. + 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/>. */ + +#define faddl __hide_faddl +#include "nldbl-compat.h" +#undef faddl + +float +attribute_hidden +faddl (double x, double y) +{ + return fadd (x, y); +} |