glibc/sysdeps/powerpc/fpu/s_modff.c

56 lines
1.6 KiB
C
Raw Normal View History

/* Copyright (C) 2013-2020 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 Library General Public License as
published by the Free Software Foundation; either version 2 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
Library General Public License for more details.
You should have received a copy of the GNU Library General Public
License along with the GNU C Library; see the file COPYING.LIB. If
Prefer https to http for gnu.org and fsf.org URLs Also, change sources.redhat.com to sourceware.org. This patch was automatically generated by running the following shell script, which uses GNU sed, and which avoids modifying files imported from upstream: sed -ri ' s,(http|ftp)(://(.*\.)?(gnu|fsf|sourceware)\.org($|[^.]|\.[^a-z])),https\2,g s,(http|ftp)(://(.*\.)?)sources\.redhat\.com($|[^.]|\.[^a-z]),https\2sourceware.org\4,g ' \ $(find $(git ls-files) -prune -type f \ ! -name '*.po' \ ! -name 'ChangeLog*' \ ! -path COPYING ! -path COPYING.LIB \ ! -path manual/fdl-1.3.texi ! -path manual/lgpl-2.1.texi \ ! -path manual/texinfo.tex ! -path scripts/config.guess \ ! -path scripts/config.sub ! -path scripts/install-sh \ ! -path scripts/mkinstalldirs ! -path scripts/move-if-change \ ! -path INSTALL ! -path locale/programs/charmap-kw.h \ ! -path po/libc.pot ! -path sysdeps/gnu/errlist.c \ ! '(' -name configure \ -execdir test -f configure.ac -o -f configure.in ';' ')' \ ! '(' -name preconfigure \ -execdir test -f preconfigure.ac ';' ')' \ -print) and then by running 'make dist-prepare' to regenerate files built from the altered files, and then executing the following to cleanup: chmod a+x sysdeps/unix/sysv/linux/riscv/configure # Omit irrelevant whitespace and comment-only changes, # perhaps from a slightly-different Autoconf version. git checkout -f \ sysdeps/csky/configure \ sysdeps/hppa/configure \ sysdeps/riscv/configure \ sysdeps/unix/sysv/linux/csky/configure # Omit changes that caused a pre-commit check to fail like this: # remote: *** error: sysdeps/powerpc/powerpc64/ppc-mcount.S: trailing lines git checkout -f \ sysdeps/powerpc/powerpc64/ppc-mcount.S \ sysdeps/unix/sysv/linux/s390/s390-64/syscall.S # Omit change that caused a pre-commit check to fail like this: # remote: *** error: sysdeps/sparc/sparc64/multiarch/memcpy-ultra3.S: last line does not end in newline git checkout -f sysdeps/sparc/sparc64/multiarch/memcpy-ultra3.S
2019-09-07 05:40:42 +00:00
not, see <https://www.gnu.org/licenses/>. */
powerpc: Refactor modf{f} The modf{f} optimization is not an optimization for ISA 2.07+. This patch move the IFUNC for powerpc64 only, move the power5+ to generic location, and include the generic implementation for ISA 2.07+. The performance changes are based on modf benchtests: * POWER9 - ppc64 "modf": { "": { "duration": 4.97057e+09, "iterations": 1.00688e+09, "max": 28.76, "min": 4.912, "mean": 4.9366 } } * POWER9 - power5+ "modf": { "": { "duration": 4.98291e+09, "iterations": 9.32818e+08, "max": 15.058, "min": 5.107, "mean": 5.34178 } } * POWER8 - ppc64 "modf": { "": { "duration": 5.05329e+09, "iterations": 8.38814e+08, "max": 518.051, "min": 5.79, "mean": 6.02433 } } * POWER8 - power5+ "modf": { "": { "duration": 5.05573e+09, "iterations": 8.35254e+08, "max": 63.141, "min": 5.873, "mean": 6.05293 } } * POWER7 - ppc64 "modf": { "": { "duration": 4.89818e+09, "iterations": 1.08408e+09, "max": 57.556, "min": 3.953, "mean": 4.51827 } } * POWER7 - power5+ "modf": { "": { "duration": 4.83789e+09, "iterations": 1.33409e+09, "max": 46.608, "min": 2.224, "mean": 3.62636 } } Checked on powerpc-linux-gnu (built without --with-cpu, with --with-cpu=power4 and with --with-cpu=power5+ and --disable-multi-arch), powerpc64-linux-gnu (built without --with-cp and with --with-cpu=power5+ and --disable-multi-arch). * sysdeps/powerpc/power5+/fpu/s_modf.c: Move to ... * sysdeps/powerpc/fpu/s_modf.c: ... here. Add ISA 2.07 optimization. * sysdeps/powerpc/power5+/fpu/s_modff.c: Move to ... * sysdeps/powerpc/fpu/s_modff.c: ... here. Add ISA 2.07 optimization. * sysdeps/powerpc/powerpc32/power4/fpu/multiarch/s_modf-power5+.c: Adjust include. * sysdeps/powerpc/powerpc32/power4/fpu/multiarch/s_modff-power5+.c: Likewise. * sysdeps/powerpc/powerpc64/be/fpu/multiarch/Makefile (sysdep_calls, sysdep_routines): Add s_modf* objects. (CFLAGS-s_modf-power5+.c, CFLAGS-s_modff-power5+.c, CFLAGS-s_modf-ppc64.c, CFLAGS-s_modff-ppc64.c): New rule. * sysdeps/powerpc/powerpc64/fpu/multiarch/s_modf-power5+.c: Move to ... * sysdeps/powerpc/powerpc64/be/fpu/multiarch/s_modf-power5+.c: ... here. * sysdeps/powerpc/powerpc64/fpu/multiarch/s_modf-power5+.c: Movo to ... * sysdeps/powerpc/powerpc64/be/fpu/multiarch/s_modf-power5+.c: Move ... here. * sysdeps/powerpc/powerpc64/fpu/multiarch/s_modf.c: Move to ... * sysdeps/powerpc/powerpc64/be/fpu/multiarch/s_modf.c: ... here. * sysdeps/powerpc/powerpc64/fpu/multiarch/s_modff-power5+.c: Move to ... * sysdeps/powerpc/powerpc64/be/fpu/multiarch/s_modff-power5+.c: ... here. * sysdeps/powerpc/powerpc64/fpu/multiarch/s_modff-ppc64.c: Move to ... * sysdeps/powerpc/powerpc64/be/fpu/multiarch/s_modff-ppc64.c: ... here. * sysdeps/powerpc/powerpc64/fpu/multiarch/s_modff.c: Move to ... * sysdeps/powerpc/powerpc64/be/fpu/multiarch/s_modff.c: ... here. Reviewed-by: Gabriel F. T. Gomes <gabrielftg@linux.ibm.com>
2019-03-18 20:18:49 +00:00
/* ISA 2.07 provides fast GPR to FP instruction (mfvsr{d,wz}) which make
generic implementation faster. Also disables for old ISAs that do not
have ceil/floor instructions. */
#if defined(_ARCH_PWR8) || !defined(_ARCH_PWR5X)
# include <sysdeps/ieee754/flt-32/s_modff.c>
#else
# include <math.h>
# include <libm-alias-float.h>
float
__modff (float x, float *iptr)
{
if (__builtin_isinff (x))
{
*iptr = x;
Use copysign functions not __copysign functions in glibc libm. Continuing the move to use, within libm, public names for libm functions that can be inlined as built-in functions on many architectures, this patch moves calls to __copysign functions to call the corresponding copysign names instead, with asm redirection to __copysign when the calls are not inlined (all cases are inlined except for IBM long double for powerpc soft-float / e500v1). This eliminates the need for an inline function defining __copysign in terms of __builtin_copysign. 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_BINARY_ARGS): New macro. [!_ISOMAC && !(__FINITE_MATH_ONLY__ && __FINITE_MATH_ONLY__ > 0) && !NO_MATH_REDIRECT] (copysign): Redirect using MATH_REDIRECT. * sysdeps/alpha/fpu/s_copysign.c: Define NO_MATH_REDIRECT before header inclusion. * sysdeps/alpha/fpu/s_copysignf.c: Likewise. * sysdeps/ieee754/dbl-64/s_copysign.c: Likewise. * sysdeps/ieee754/float128/s_copysignf128.c: Likewise. * sysdeps/ieee754/flt-32/s_copysignf.c: Likewise. * sysdeps/ieee754/ldbl-128/s_copysignl.c: Likewise. * sysdeps/ieee754/ldbl-128ibm/s_copysignl.c: Likewise. * sysdeps/ieee754/ldbl-96/s_copysignl.c: Likewise. * sysdeps/powerpc/powerpc32/power4/fpu/multiarch/s_copysign.c: Likewise. * sysdeps/powerpc/powerpc32/power4/fpu/multiarch/s_copysignf.c: Likewise. * sysdeps/powerpc/powerpc64/fpu/multiarch/s_copysign.c: Likewise. * sysdeps/powerpc/powerpc64/fpu/multiarch/s_copysignf.c: Likewise. * sysdeps/riscv/rvd/s_copysign.c: Likewise. * sysdeps/riscv/rvf/s_copysignf.c: Likewise. * sysdeps/sparc/sparc32/sparcv9/fpu/multiarch/s_copysign.c: Likewise. * sysdeps/sparc/sparc32/sparcv9/fpu/multiarch/s_copysignf.c: Likewise. * sysdeps/generic/math_private_calls.h [!__MATH_DECLARING_LONG_DOUBLE || !NO_LONG_DOUBLE] (__copysign): Do not declare and define as an inline function. * math/divtc3.c (__divtc3): Use copysign functions instead of __copysign variants. * math/multc3.c (__multc3): Likewise. * sysdeps/generic/math-type-macros.h (M_COPYSIGN): Likewise. * sysdeps/ieee754/dbl-64/e_atan2.c (signArctan2): Likewise. * sysdeps/ieee754/dbl-64/e_atanh.c (__ieee754_atanh): Likewise. * sysdeps/ieee754/dbl-64/e_gamma_r.c (__ieee754_gamma_r): Likewise. * sysdeps/ieee754/dbl-64/e_jn.c (__ieee754_jn): Likewise. (__ieee754_yn): Likewise. * sysdeps/ieee754/dbl-64/s_asinh.c (__asinh): Likewise. * sysdeps/ieee754/dbl-64/s_atan.c (__signArctan): Likewise. * sysdeps/ieee754/dbl-64/s_scalbln.c (__scalbln): Likewise. * sysdeps/ieee754/dbl-64/s_scalbn.c (__scalbn): Likewise. * sysdeps/ieee754/dbl-64/s_sin.c (do_sin): Likewise. (__sin): Likewise. * sysdeps/ieee754/dbl-64/s_sincos.c (__sincos): Likewise. * sysdeps/ieee754/dbl-64/wordsize-64/s_nearbyint.c (__nearbyint): Likewise. * sysdeps/ieee754/dbl-64/wordsize-64/s_scalbln.c (__scalbln): Likewise. * sysdeps/ieee754/dbl-64/wordsize-64/s_scalbn.c (__scalbn): Likewise. * sysdeps/ieee754/flt-32/e_atanhf.c (__ieee754_atanhf): Likewise. * sysdeps/ieee754/flt-32/e_gammaf_r.c (__ieee754_gammaf_r): Likewise. * sysdeps/ieee754/flt-32/e_jnf.c (__ieee754_jnf): Likewise. (__ieee754_ynf): Likewise. * sysdeps/ieee754/flt-32/s_asinhf.c (__asinhf): Likewise. * sysdeps/ieee754/flt-32/s_scalbnf.c (__scalbnf): Likewise. * sysdeps/ieee754/k_standard.c (__kernel_standard): Likewise. * sysdeps/ieee754/ldbl-128/e_gammal_r.c (__ieee754_gammal_r): Likewise. * sysdeps/ieee754/ldbl-128/e_jnl.c (__ieee754_jnl): Likewise. (__ieee754_ynl): Likewise. * sysdeps/ieee754/ldbl-128/s_scalblnl.c (__scalblnl): Likewise. * sysdeps/ieee754/ldbl-128/s_scalbnl.c (__scalbnl): Likewise. * sysdeps/ieee754/ldbl-128ibm/e_gammal_r.c (__ieee754_gammal_r): Likewise. * sysdeps/ieee754/ldbl-128ibm/e_jnl.c (__ieee754_jnl): Likewise. (__ieee754_ynl): Likewise. * sysdeps/ieee754/ldbl-128ibm/s_fmal.c (__fmal): Likewise. * sysdeps/ieee754/ldbl-128ibm/s_scalblnl.c (__scalblnl): Likewise. * sysdeps/ieee754/ldbl-128ibm/s_scalbnl.c (__scalbnl): Likewise. * sysdeps/ieee754/ldbl-96/e_gammal_r.c (__ieee754_gammal_r): Likewise. * sysdeps/ieee754/ldbl-96/e_jnl.c (__ieee754_jnl): Likewise. (__ieee754_ynl) * sysdeps/ieee754/ldbl-96/s_asinhl.c (__asinhl): Likewise. * sysdeps/ieee754/ldbl-96/s_scalblnl.c (__scalblnl): Likewise. * sysdeps/ieee754/ldbl-opt/nldbl-copysign.c (copysignl): Likewise. * sysdeps/powerpc/power5+/fpu/s_modf.c (__modf): Likewise. * sysdeps/powerpc/power5+/fpu/s_modff.c (__modff): Likewise.
2018-09-27 20:04:48 +00:00
return copysignf (0.0, x);
}
else if (__builtin_isnanf (x))
{
*iptr = NAN;
return NAN;
}
if (x >= 0.0)
{
Use floor functions not __floor functions in glibc libm. 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.
2018-09-14 13:09:01 +00:00
*iptr = floorf (x);
Use copysign functions not __copysign functions in glibc libm. Continuing the move to use, within libm, public names for libm functions that can be inlined as built-in functions on many architectures, this patch moves calls to __copysign functions to call the corresponding copysign names instead, with asm redirection to __copysign when the calls are not inlined (all cases are inlined except for IBM long double for powerpc soft-float / e500v1). This eliminates the need for an inline function defining __copysign in terms of __builtin_copysign. 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_BINARY_ARGS): New macro. [!_ISOMAC && !(__FINITE_MATH_ONLY__ && __FINITE_MATH_ONLY__ > 0) && !NO_MATH_REDIRECT] (copysign): Redirect using MATH_REDIRECT. * sysdeps/alpha/fpu/s_copysign.c: Define NO_MATH_REDIRECT before header inclusion. * sysdeps/alpha/fpu/s_copysignf.c: Likewise. * sysdeps/ieee754/dbl-64/s_copysign.c: Likewise. * sysdeps/ieee754/float128/s_copysignf128.c: Likewise. * sysdeps/ieee754/flt-32/s_copysignf.c: Likewise. * sysdeps/ieee754/ldbl-128/s_copysignl.c: Likewise. * sysdeps/ieee754/ldbl-128ibm/s_copysignl.c: Likewise. * sysdeps/ieee754/ldbl-96/s_copysignl.c: Likewise. * sysdeps/powerpc/powerpc32/power4/fpu/multiarch/s_copysign.c: Likewise. * sysdeps/powerpc/powerpc32/power4/fpu/multiarch/s_copysignf.c: Likewise. * sysdeps/powerpc/powerpc64/fpu/multiarch/s_copysign.c: Likewise. * sysdeps/powerpc/powerpc64/fpu/multiarch/s_copysignf.c: Likewise. * sysdeps/riscv/rvd/s_copysign.c: Likewise. * sysdeps/riscv/rvf/s_copysignf.c: Likewise. * sysdeps/sparc/sparc32/sparcv9/fpu/multiarch/s_copysign.c: Likewise. * sysdeps/sparc/sparc32/sparcv9/fpu/multiarch/s_copysignf.c: Likewise. * sysdeps/generic/math_private_calls.h [!__MATH_DECLARING_LONG_DOUBLE || !NO_LONG_DOUBLE] (__copysign): Do not declare and define as an inline function. * math/divtc3.c (__divtc3): Use copysign functions instead of __copysign variants. * math/multc3.c (__multc3): Likewise. * sysdeps/generic/math-type-macros.h (M_COPYSIGN): Likewise. * sysdeps/ieee754/dbl-64/e_atan2.c (signArctan2): Likewise. * sysdeps/ieee754/dbl-64/e_atanh.c (__ieee754_atanh): Likewise. * sysdeps/ieee754/dbl-64/e_gamma_r.c (__ieee754_gamma_r): Likewise. * sysdeps/ieee754/dbl-64/e_jn.c (__ieee754_jn): Likewise. (__ieee754_yn): Likewise. * sysdeps/ieee754/dbl-64/s_asinh.c (__asinh): Likewise. * sysdeps/ieee754/dbl-64/s_atan.c (__signArctan): Likewise. * sysdeps/ieee754/dbl-64/s_scalbln.c (__scalbln): Likewise. * sysdeps/ieee754/dbl-64/s_scalbn.c (__scalbn): Likewise. * sysdeps/ieee754/dbl-64/s_sin.c (do_sin): Likewise. (__sin): Likewise. * sysdeps/ieee754/dbl-64/s_sincos.c (__sincos): Likewise. * sysdeps/ieee754/dbl-64/wordsize-64/s_nearbyint.c (__nearbyint): Likewise. * sysdeps/ieee754/dbl-64/wordsize-64/s_scalbln.c (__scalbln): Likewise. * sysdeps/ieee754/dbl-64/wordsize-64/s_scalbn.c (__scalbn): Likewise. * sysdeps/ieee754/flt-32/e_atanhf.c (__ieee754_atanhf): Likewise. * sysdeps/ieee754/flt-32/e_gammaf_r.c (__ieee754_gammaf_r): Likewise. * sysdeps/ieee754/flt-32/e_jnf.c (__ieee754_jnf): Likewise. (__ieee754_ynf): Likewise. * sysdeps/ieee754/flt-32/s_asinhf.c (__asinhf): Likewise. * sysdeps/ieee754/flt-32/s_scalbnf.c (__scalbnf): Likewise. * sysdeps/ieee754/k_standard.c (__kernel_standard): Likewise. * sysdeps/ieee754/ldbl-128/e_gammal_r.c (__ieee754_gammal_r): Likewise. * sysdeps/ieee754/ldbl-128/e_jnl.c (__ieee754_jnl): Likewise. (__ieee754_ynl): Likewise. * sysdeps/ieee754/ldbl-128/s_scalblnl.c (__scalblnl): Likewise. * sysdeps/ieee754/ldbl-128/s_scalbnl.c (__scalbnl): Likewise. * sysdeps/ieee754/ldbl-128ibm/e_gammal_r.c (__ieee754_gammal_r): Likewise. * sysdeps/ieee754/ldbl-128ibm/e_jnl.c (__ieee754_jnl): Likewise. (__ieee754_ynl): Likewise. * sysdeps/ieee754/ldbl-128ibm/s_fmal.c (__fmal): Likewise. * sysdeps/ieee754/ldbl-128ibm/s_scalblnl.c (__scalblnl): Likewise. * sysdeps/ieee754/ldbl-128ibm/s_scalbnl.c (__scalbnl): Likewise. * sysdeps/ieee754/ldbl-96/e_gammal_r.c (__ieee754_gammal_r): Likewise. * sysdeps/ieee754/ldbl-96/e_jnl.c (__ieee754_jnl): Likewise. (__ieee754_ynl) * sysdeps/ieee754/ldbl-96/s_asinhl.c (__asinhl): Likewise. * sysdeps/ieee754/ldbl-96/s_scalblnl.c (__scalblnl): Likewise. * sysdeps/ieee754/ldbl-opt/nldbl-copysign.c (copysignl): Likewise. * sysdeps/powerpc/power5+/fpu/s_modf.c (__modf): Likewise. * sysdeps/powerpc/power5+/fpu/s_modff.c (__modff): Likewise.
2018-09-27 20:04:48 +00:00
return copysignf (x - *iptr, x);
}
else
{
Use ceil functions not __ceil functions in glibc libm. Continuing the move to use, within libm, public names for libm functions that can be inlined as built-in functions on many architectures, this patch moves calls to __ceil functions to call the corresponding ceil names instead, with asm redirection to __ceil when the calls are not inlined. Tested for x86_64, and with build-many-glibcs.py. * include/math.h [!_ISOMAC && !(__FINITE_MATH_ONLY__ && __FINITE_MATH_ONLY__ > 0) && !NO_MATH_REDIRECT] (ceil): Redirect using MATH_REDIRECT. * sysdeps/aarch64/fpu/s_ceil.c: Define NO_MATH_REDIRECT before header inclusion. * sysdeps/aarch64/fpu/s_ceilf.c: Likewise. * sysdeps/ieee754/dbl-64/s_ceil.c: Likewise. * sysdeps/ieee754/dbl-64/wordsize-64/s_ceil.c: Likewise. * sysdeps/ieee754/float128/s_ceilf128.c: Likewise. * sysdeps/ieee754/flt-32/s_ceilf.c: Likewise. * sysdeps/ieee754/ldbl-128/s_ceill.c: Likewise. * sysdeps/ieee754/ldbl-128ibm/s_ceill.c: Likewise. * sysdeps/m68k/m680x0/fpu/s_ceil_template.c: Likewise. * sysdeps/powerpc/powerpc32/power4/fpu/multiarch/s_ceil.c: Likewise. * sysdeps/powerpc/powerpc32/power4/fpu/multiarch/s_ceilf.c: Likewise. * sysdeps/powerpc/powerpc64/fpu/multiarch/s_ceil.c: Likewise. * sysdeps/powerpc/powerpc64/fpu/multiarch/s_ceilf.c: Likewise. * sysdeps/riscv/rv64/rvd/s_ceil.c: Likewise. * sysdeps/riscv/rvf/s_ceilf.c: Likewise. * sysdeps/sparc/sparc64/fpu/multiarch/s_ceil.c: Likewise. * sysdeps/sparc/sparc64/fpu/multiarch/s_ceilf.c: Likewise. * sysdeps/x86_64/fpu/multiarch/s_ceil.c: Likewise. * sysdeps/x86_64/fpu/multiarch/s_ceilf.c: Likewise. * sysdeps/powerpc/fpu/math_private.h [_ARCH_PWR5X] (__ceil): Remove macro. * sysdeps/ieee754/dbl-64/e_gamma_r.c (gamma_positive): Use ceil functions instead of __ceil variants. * sysdeps/ieee754/flt-32/e_gammaf_r.c (gammaf_positive): Likewise. * sysdeps/ieee754/ldbl-128/e_gammal_r.c (gammal_positive): Likewise. * sysdeps/ieee754/ldbl-128ibm/e_gammal_r.c (gammal_positive): Likewise. * sysdeps/ieee754/ldbl-128ibm/s_truncl.c (__truncl): Likewise. * sysdeps/ieee754/ldbl-96/e_gammal_r.c (gammal_positive): Likewise. * sysdeps/powerpc/power5+/fpu/s_modf.c (__modf): Likewise. * sysdeps/powerpc/power5+/fpu/s_modff.c (__modff): Likewise.
2018-09-17 20:42:06 +00:00
*iptr = ceilf (x);
Use copysign functions not __copysign functions in glibc libm. Continuing the move to use, within libm, public names for libm functions that can be inlined as built-in functions on many architectures, this patch moves calls to __copysign functions to call the corresponding copysign names instead, with asm redirection to __copysign when the calls are not inlined (all cases are inlined except for IBM long double for powerpc soft-float / e500v1). This eliminates the need for an inline function defining __copysign in terms of __builtin_copysign. 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_BINARY_ARGS): New macro. [!_ISOMAC && !(__FINITE_MATH_ONLY__ && __FINITE_MATH_ONLY__ > 0) && !NO_MATH_REDIRECT] (copysign): Redirect using MATH_REDIRECT. * sysdeps/alpha/fpu/s_copysign.c: Define NO_MATH_REDIRECT before header inclusion. * sysdeps/alpha/fpu/s_copysignf.c: Likewise. * sysdeps/ieee754/dbl-64/s_copysign.c: Likewise. * sysdeps/ieee754/float128/s_copysignf128.c: Likewise. * sysdeps/ieee754/flt-32/s_copysignf.c: Likewise. * sysdeps/ieee754/ldbl-128/s_copysignl.c: Likewise. * sysdeps/ieee754/ldbl-128ibm/s_copysignl.c: Likewise. * sysdeps/ieee754/ldbl-96/s_copysignl.c: Likewise. * sysdeps/powerpc/powerpc32/power4/fpu/multiarch/s_copysign.c: Likewise. * sysdeps/powerpc/powerpc32/power4/fpu/multiarch/s_copysignf.c: Likewise. * sysdeps/powerpc/powerpc64/fpu/multiarch/s_copysign.c: Likewise. * sysdeps/powerpc/powerpc64/fpu/multiarch/s_copysignf.c: Likewise. * sysdeps/riscv/rvd/s_copysign.c: Likewise. * sysdeps/riscv/rvf/s_copysignf.c: Likewise. * sysdeps/sparc/sparc32/sparcv9/fpu/multiarch/s_copysign.c: Likewise. * sysdeps/sparc/sparc32/sparcv9/fpu/multiarch/s_copysignf.c: Likewise. * sysdeps/generic/math_private_calls.h [!__MATH_DECLARING_LONG_DOUBLE || !NO_LONG_DOUBLE] (__copysign): Do not declare and define as an inline function. * math/divtc3.c (__divtc3): Use copysign functions instead of __copysign variants. * math/multc3.c (__multc3): Likewise. * sysdeps/generic/math-type-macros.h (M_COPYSIGN): Likewise. * sysdeps/ieee754/dbl-64/e_atan2.c (signArctan2): Likewise. * sysdeps/ieee754/dbl-64/e_atanh.c (__ieee754_atanh): Likewise. * sysdeps/ieee754/dbl-64/e_gamma_r.c (__ieee754_gamma_r): Likewise. * sysdeps/ieee754/dbl-64/e_jn.c (__ieee754_jn): Likewise. (__ieee754_yn): Likewise. * sysdeps/ieee754/dbl-64/s_asinh.c (__asinh): Likewise. * sysdeps/ieee754/dbl-64/s_atan.c (__signArctan): Likewise. * sysdeps/ieee754/dbl-64/s_scalbln.c (__scalbln): Likewise. * sysdeps/ieee754/dbl-64/s_scalbn.c (__scalbn): Likewise. * sysdeps/ieee754/dbl-64/s_sin.c (do_sin): Likewise. (__sin): Likewise. * sysdeps/ieee754/dbl-64/s_sincos.c (__sincos): Likewise. * sysdeps/ieee754/dbl-64/wordsize-64/s_nearbyint.c (__nearbyint): Likewise. * sysdeps/ieee754/dbl-64/wordsize-64/s_scalbln.c (__scalbln): Likewise. * sysdeps/ieee754/dbl-64/wordsize-64/s_scalbn.c (__scalbn): Likewise. * sysdeps/ieee754/flt-32/e_atanhf.c (__ieee754_atanhf): Likewise. * sysdeps/ieee754/flt-32/e_gammaf_r.c (__ieee754_gammaf_r): Likewise. * sysdeps/ieee754/flt-32/e_jnf.c (__ieee754_jnf): Likewise. (__ieee754_ynf): Likewise. * sysdeps/ieee754/flt-32/s_asinhf.c (__asinhf): Likewise. * sysdeps/ieee754/flt-32/s_scalbnf.c (__scalbnf): Likewise. * sysdeps/ieee754/k_standard.c (__kernel_standard): Likewise. * sysdeps/ieee754/ldbl-128/e_gammal_r.c (__ieee754_gammal_r): Likewise. * sysdeps/ieee754/ldbl-128/e_jnl.c (__ieee754_jnl): Likewise. (__ieee754_ynl): Likewise. * sysdeps/ieee754/ldbl-128/s_scalblnl.c (__scalblnl): Likewise. * sysdeps/ieee754/ldbl-128/s_scalbnl.c (__scalbnl): Likewise. * sysdeps/ieee754/ldbl-128ibm/e_gammal_r.c (__ieee754_gammal_r): Likewise. * sysdeps/ieee754/ldbl-128ibm/e_jnl.c (__ieee754_jnl): Likewise. (__ieee754_ynl): Likewise. * sysdeps/ieee754/ldbl-128ibm/s_fmal.c (__fmal): Likewise. * sysdeps/ieee754/ldbl-128ibm/s_scalblnl.c (__scalblnl): Likewise. * sysdeps/ieee754/ldbl-128ibm/s_scalbnl.c (__scalbnl): Likewise. * sysdeps/ieee754/ldbl-96/e_gammal_r.c (__ieee754_gammal_r): Likewise. * sysdeps/ieee754/ldbl-96/e_jnl.c (__ieee754_jnl): Likewise. (__ieee754_ynl) * sysdeps/ieee754/ldbl-96/s_asinhl.c (__asinhl): Likewise. * sysdeps/ieee754/ldbl-96/s_scalblnl.c (__scalblnl): Likewise. * sysdeps/ieee754/ldbl-opt/nldbl-copysign.c (copysignl): Likewise. * sysdeps/powerpc/power5+/fpu/s_modf.c (__modf): Likewise. * sysdeps/powerpc/power5+/fpu/s_modff.c (__modff): Likewise.
2018-09-27 20:04:48 +00:00
return copysignf (x - *iptr, x);
}
}
powerpc: Refactor modf{f} The modf{f} optimization is not an optimization for ISA 2.07+. This patch move the IFUNC for powerpc64 only, move the power5+ to generic location, and include the generic implementation for ISA 2.07+. The performance changes are based on modf benchtests: * POWER9 - ppc64 "modf": { "": { "duration": 4.97057e+09, "iterations": 1.00688e+09, "max": 28.76, "min": 4.912, "mean": 4.9366 } } * POWER9 - power5+ "modf": { "": { "duration": 4.98291e+09, "iterations": 9.32818e+08, "max": 15.058, "min": 5.107, "mean": 5.34178 } } * POWER8 - ppc64 "modf": { "": { "duration": 5.05329e+09, "iterations": 8.38814e+08, "max": 518.051, "min": 5.79, "mean": 6.02433 } } * POWER8 - power5+ "modf": { "": { "duration": 5.05573e+09, "iterations": 8.35254e+08, "max": 63.141, "min": 5.873, "mean": 6.05293 } } * POWER7 - ppc64 "modf": { "": { "duration": 4.89818e+09, "iterations": 1.08408e+09, "max": 57.556, "min": 3.953, "mean": 4.51827 } } * POWER7 - power5+ "modf": { "": { "duration": 4.83789e+09, "iterations": 1.33409e+09, "max": 46.608, "min": 2.224, "mean": 3.62636 } } Checked on powerpc-linux-gnu (built without --with-cpu, with --with-cpu=power4 and with --with-cpu=power5+ and --disable-multi-arch), powerpc64-linux-gnu (built without --with-cp and with --with-cpu=power5+ and --disable-multi-arch). * sysdeps/powerpc/power5+/fpu/s_modf.c: Move to ... * sysdeps/powerpc/fpu/s_modf.c: ... here. Add ISA 2.07 optimization. * sysdeps/powerpc/power5+/fpu/s_modff.c: Move to ... * sysdeps/powerpc/fpu/s_modff.c: ... here. Add ISA 2.07 optimization. * sysdeps/powerpc/powerpc32/power4/fpu/multiarch/s_modf-power5+.c: Adjust include. * sysdeps/powerpc/powerpc32/power4/fpu/multiarch/s_modff-power5+.c: Likewise. * sysdeps/powerpc/powerpc64/be/fpu/multiarch/Makefile (sysdep_calls, sysdep_routines): Add s_modf* objects. (CFLAGS-s_modf-power5+.c, CFLAGS-s_modff-power5+.c, CFLAGS-s_modf-ppc64.c, CFLAGS-s_modff-ppc64.c): New rule. * sysdeps/powerpc/powerpc64/fpu/multiarch/s_modf-power5+.c: Move to ... * sysdeps/powerpc/powerpc64/be/fpu/multiarch/s_modf-power5+.c: ... here. * sysdeps/powerpc/powerpc64/fpu/multiarch/s_modf-power5+.c: Movo to ... * sysdeps/powerpc/powerpc64/be/fpu/multiarch/s_modf-power5+.c: Move ... here. * sysdeps/powerpc/powerpc64/fpu/multiarch/s_modf.c: Move to ... * sysdeps/powerpc/powerpc64/be/fpu/multiarch/s_modf.c: ... here. * sysdeps/powerpc/powerpc64/fpu/multiarch/s_modff-power5+.c: Move to ... * sysdeps/powerpc/powerpc64/be/fpu/multiarch/s_modff-power5+.c: ... here. * sysdeps/powerpc/powerpc64/fpu/multiarch/s_modff-ppc64.c: Move to ... * sysdeps/powerpc/powerpc64/be/fpu/multiarch/s_modff-ppc64.c: ... here. * sysdeps/powerpc/powerpc64/fpu/multiarch/s_modff.c: Move to ... * sysdeps/powerpc/powerpc64/be/fpu/multiarch/s_modff.c: ... here. Reviewed-by: Gabriel F. T. Gomes <gabrielftg@linux.ibm.com>
2019-03-18 20:18:49 +00:00
# ifndef __modff
Use libm_alias_float for powerpc. Continuing the preparation for additional _FloatN / _FloatNx function aliases, this patch makes powerpc libm function implementations use libm_alias_float to define function aliases. Tested with build-many-glibcs.py that installed stripped shared libraries are unchanged for all its hard-float powerpc configurations. * sysdeps/powerpc/fpu/s_cosf.c: Include <libm-alias-float.h>. (cosf): Define using libm_alias_float. * sysdeps/powerpc/fpu/s_fabs.S: Include <libm-alias-float.h>. (fabsf): Define using libm_alias_float. * sysdeps/powerpc/fpu/s_fmaf.S: Include <libm-alias-float.h>. (fmaf): Define using libm_alias_float. * sysdeps/powerpc/fpu/s_rintf.c: Include <libm-alias-float.h>. (rintf): Define using libm_alias_float. * sysdeps/powerpc/fpu/s_sinf.c: Include <libm-alias-float.h>. (sinf): Define using libm_alias_float. * sysdeps/powerpc/power5+/fpu/s_modff.c: Include <libm-alias-float.h>. (modff): Define using libm_alias_float. * sysdeps/powerpc/power7/fpu/s_logbf.c: Include <libm-alias-float.h>. (logbf): Define using libm_alias_float. * sysdeps/powerpc/powerpc32/fpu/s_ceilf.S: Include <libm-alias-float.h>. (ceilf): Define using libm_alias_float. * sysdeps/powerpc/powerpc32/fpu/s_copysign.S: Include <libm-alias-float.h>. (copysignf): Define using libm_alias_float. * sysdeps/powerpc/powerpc32/fpu/s_floorf.S: Include <libm-alias-float.h>. (floorf): Define using libm_alias_float. * sysdeps/powerpc/powerpc32/fpu/s_llrintf.c: Include <libm-alias-float.h>. (llrintf): Define using libm_alias_float. * sysdeps/powerpc/powerpc32/fpu/s_llroundf.c: Include <libm-alias-float.h>. (llroundf): Define using libm_alias_float. * sysdeps/powerpc/powerpc32/fpu/s_lrint.S: Include <libm-alias-float.h>. (lrintf): Define using libm_alias_float. * sysdeps/powerpc/powerpc32/fpu/s_lround.S: Include <libm-alias-float.h>. (lroundf): Define using libm_alias_float. * sysdeps/powerpc/powerpc32/fpu/s_nearbyintf.S: Include <libm-alias-float.h>. (nearbyintf): Define using libm_alias_float. * sysdeps/powerpc/powerpc32/fpu/s_rintf.S: Include <libm-alias-float.h>. (rintf): Define using libm_alias_float. * sysdeps/powerpc/powerpc32/fpu/s_roundf.S: Include <libm-alias-float.h>. (roundf): Define using libm_alias_float. * sysdeps/powerpc/powerpc32/fpu/s_truncf.S: Include <libm-alias-float.h>. (truncf): Define using libm_alias_float. * sysdeps/powerpc/powerpc32/power4/fpu/multiarch/s_ceilf.c: Include <libm-alias-float.h>. (ceilf): Define using libm_alias_float. * sysdeps/powerpc/powerpc32/power4/fpu/multiarch/s_copysignf.c: Include <libm-alias-float.h>. (copysignf): Define using libm_alias_float. * sysdeps/powerpc/powerpc32/power4/fpu/multiarch/s_floorf.c: Include <libm-alias-float.h>. (floorf): Define using libm_alias_float. * sysdeps/powerpc/powerpc32/power4/fpu/multiarch/s_llrintf.c: Include <libm-alias-float.h>. (llrintf): Define using libm_alias_float. * sysdeps/powerpc/powerpc32/power4/fpu/multiarch/s_llroundf.c: Include <libm-alias-float.h>. (llroundf): Define using libm_alias_float. * sysdeps/powerpc/powerpc32/power4/fpu/multiarch/s_logbf.c: Include <libm-alias-float.h>. (logbf): Define using libm_alias_float. * sysdeps/powerpc/powerpc32/power4/fpu/multiarch/s_lrintf.c: Include <libm-alias-float.h>. (lrintf): Define using libm_alias_float. * sysdeps/powerpc/powerpc32/power4/fpu/multiarch/s_lroundf.c: Include <libm-alias-float.h>. (lroundf): Define using libm_alias_float. * sysdeps/powerpc/powerpc32/power4/fpu/multiarch/s_modff.c: Include <libm-alias-float.h>. (modff): Define using libm_alias_float. * sysdeps/powerpc/powerpc32/power4/fpu/multiarch/s_roundf.c: Include <libm-alias-float.h>. (roundf): Define using libm_alias_float. * sysdeps/powerpc/powerpc32/power4/fpu/multiarch/s_truncf.c: Include <libm-alias-float.h>. (truncf): Define using libm_alias_float. * sysdeps/powerpc/powerpc32/power4/fpu/s_llrintf.S: Include <libm-alias-float.h>. (llrintf): Define using libm_alias_float. * sysdeps/powerpc/powerpc32/power4/fpu/s_llround.S: Include <libm-alias-float.h>. (llroundf): Define using libm_alias_float. * sysdeps/powerpc/powerpc32/power5+/fpu/s_ceilf.S: Include <libm-alias-float.h>. (ceilf): Define using libm_alias_float. * sysdeps/powerpc/powerpc32/power5+/fpu/s_floorf.S: Include <libm-alias-float.h>. (floorf): Define using libm_alias_float. * sysdeps/powerpc/powerpc32/power5+/fpu/s_llround.S: Include <libm-alias-float.h>. (llroundf): Define using libm_alias_float. * sysdeps/powerpc/powerpc32/power5+/fpu/s_lround.S: Include <libm-alias-float.h>. (lroundf): Define using libm_alias_float. * sysdeps/powerpc/powerpc32/power5+/fpu/s_roundf.S: Include <libm-alias-float.h>. (roundf): Define using libm_alias_float. * sysdeps/powerpc/powerpc32/power5+/fpu/s_truncf.S: Include <libm-alias-float.h>. (truncf): Define using libm_alias_float. * sysdeps/powerpc/powerpc32/power6/fpu/s_copysign.S: Include <libm-alias-float.h>. (copysignf): Define using libm_alias_float. * sysdeps/powerpc/powerpc32/power6/fpu/s_llrintf.S: Include <libm-alias-float.h>. (llrintf): Define using libm_alias_float. * sysdeps/powerpc/powerpc32/power6/fpu/s_llround.S: Include <libm-alias-float.h>. (llroundf): Define using libm_alias_float. * sysdeps/powerpc/powerpc32/power6x/fpu/s_lrint.S: Include <libm-alias-float.h>. (lrintf): Define using libm_alias_float. * sysdeps/powerpc/powerpc32/power6x/fpu/s_lround.S: Include <libm-alias-float.h>. (lroundf): Define using libm_alias_float. * sysdeps/powerpc/powerpc64/fpu/multiarch/s_ceilf.c: Include <libm-alias-float.h>. (ceilf): Define using libm_alias_float. * sysdeps/powerpc/powerpc64/fpu/multiarch/s_copysignf.c: Include <libm-alias-float.h>. (copysignf): Define using libm_alias_float. * sysdeps/powerpc/powerpc64/fpu/multiarch/s_cosf.c: Include <libm-alias-float.h>. (cosf): Define using libm_alias_float. * sysdeps/powerpc/powerpc64/fpu/multiarch/s_floorf.c: Include <libm-alias-float.h>. (floorf): Define using libm_alias_float. * sysdeps/powerpc/powerpc64/fpu/multiarch/s_llrintf.c: Include <libm-alias-float.h>. (llrintf): Define using libm_alias_float. * sysdeps/powerpc/powerpc64/fpu/multiarch/s_llroundf.c: Include <libm-alias-float.h>. (llroundf): Define using libm_alias_float. * sysdeps/powerpc/powerpc64/fpu/multiarch/s_logbf.c: Include <libm-alias-float.h>. (logbf): Define using libm_alias_float. * sysdeps/powerpc/powerpc64/fpu/multiarch/s_modff.c: Include <libm-alias-float.h>. (modff): Define using libm_alias_float. * sysdeps/powerpc/powerpc64/fpu/multiarch/s_roundf.c: Include <libm-alias-float.h>. (roundf): Define using libm_alias_float. * sysdeps/powerpc/powerpc64/fpu/multiarch/s_sinf.c: Include <libm-alias-float.h>. (sinf): Define using libm_alias_float. * sysdeps/powerpc/powerpc64/fpu/multiarch/s_truncf.c: Include <libm-alias-float.h>. (truncf): Define using libm_alias_float. * sysdeps/powerpc/powerpc64/fpu/s_ceilf.S: Include <libm-alias-float.h>. (ceilf): Define using libm_alias_float. * sysdeps/powerpc/powerpc64/fpu/s_copysign.S: Include <libm-alias-float.h>. (copysignf): Define using libm_alias_float. * sysdeps/powerpc/powerpc64/fpu/s_floorf.S: Include <libm-alias-float.h>. (floorf): Define using libm_alias_float. * sysdeps/powerpc/powerpc64/fpu/s_llrint.S: Include <libm-alias-float.h>. (llrintf): Define using libm_alias_float. * sysdeps/powerpc/powerpc64/fpu/s_llroundf.S: Include <libm-alias-float.h>. (llroundf): Define using libm_alias_float. * sysdeps/powerpc/powerpc64/fpu/s_nearbyintf.S: Include <libm-alias-float.h>. (nearbyintf): Define using libm_alias_float. * sysdeps/powerpc/powerpc64/fpu/s_rintf.S: Include <libm-alias-float.h>. (rintf): Define using libm_alias_float. * sysdeps/powerpc/powerpc64/fpu/s_roundf.S: Include <libm-alias-float.h>. (roundf): Define using libm_alias_float. * sysdeps/powerpc/powerpc64/fpu/s_truncf.S: Include <libm-alias-float.h>. (truncf): Define using libm_alias_float. * sysdeps/powerpc/powerpc64/power5+/fpu/s_ceilf.S: Include <libm-alias-float.h>. (ceilf): Define using libm_alias_float. * sysdeps/powerpc/powerpc64/power5+/fpu/s_floorf.S: Include <libm-alias-float.h>. (floorf): Define using libm_alias_float. * sysdeps/powerpc/powerpc64/power5+/fpu/s_llround.S: Include <libm-alias-float.h>. (llroundf): Define using libm_alias_float. * sysdeps/powerpc/powerpc64/power5+/fpu/s_roundf.S: Include <libm-alias-float.h>. (roundf): Define using libm_alias_float. * sysdeps/powerpc/powerpc64/power5+/fpu/s_truncf.S: Include <libm-alias-float.h>. (truncf): Define using libm_alias_float. * sysdeps/powerpc/powerpc64/power6/fpu/s_copysign.S: Include <libm-alias-float.h>. (copysignf): Define using libm_alias_float. * sysdeps/powerpc/powerpc64/power6x/fpu/s_llrint.S: Include <libm-alias-float.h>. (llrintf): Define using libm_alias_float. * sysdeps/powerpc/powerpc64/power6x/fpu/s_llround.S: Include <libm-alias-float.h>. (llroundf): Define using libm_alias_float. * sysdeps/powerpc/powerpc64/power8/fpu/s_cosf.S: Include <libm-alias-float.h>. (cosf): Define using libm_alias_float. * sysdeps/powerpc/powerpc64/power8/fpu/s_llrint.S: Include <libm-alias-float.h>. (llrintf): Define using libm_alias_float. * sysdeps/powerpc/powerpc64/power8/fpu/s_llround.S: Include <libm-alias-float.h>. (llroundf): Define using libm_alias_float. * sysdeps/powerpc/powerpc64/power8/fpu/s_sinf.S: Include <libm-alias-float.h>. (sinf): Define using libm_alias_float.
2017-12-05 00:26:26 +00:00
libm_alias_float (__modf, modf)
powerpc: Refactor modf{f} The modf{f} optimization is not an optimization for ISA 2.07+. This patch move the IFUNC for powerpc64 only, move the power5+ to generic location, and include the generic implementation for ISA 2.07+. The performance changes are based on modf benchtests: * POWER9 - ppc64 "modf": { "": { "duration": 4.97057e+09, "iterations": 1.00688e+09, "max": 28.76, "min": 4.912, "mean": 4.9366 } } * POWER9 - power5+ "modf": { "": { "duration": 4.98291e+09, "iterations": 9.32818e+08, "max": 15.058, "min": 5.107, "mean": 5.34178 } } * POWER8 - ppc64 "modf": { "": { "duration": 5.05329e+09, "iterations": 8.38814e+08, "max": 518.051, "min": 5.79, "mean": 6.02433 } } * POWER8 - power5+ "modf": { "": { "duration": 5.05573e+09, "iterations": 8.35254e+08, "max": 63.141, "min": 5.873, "mean": 6.05293 } } * POWER7 - ppc64 "modf": { "": { "duration": 4.89818e+09, "iterations": 1.08408e+09, "max": 57.556, "min": 3.953, "mean": 4.51827 } } * POWER7 - power5+ "modf": { "": { "duration": 4.83789e+09, "iterations": 1.33409e+09, "max": 46.608, "min": 2.224, "mean": 3.62636 } } Checked on powerpc-linux-gnu (built without --with-cpu, with --with-cpu=power4 and with --with-cpu=power5+ and --disable-multi-arch), powerpc64-linux-gnu (built without --with-cp and with --with-cpu=power5+ and --disable-multi-arch). * sysdeps/powerpc/power5+/fpu/s_modf.c: Move to ... * sysdeps/powerpc/fpu/s_modf.c: ... here. Add ISA 2.07 optimization. * sysdeps/powerpc/power5+/fpu/s_modff.c: Move to ... * sysdeps/powerpc/fpu/s_modff.c: ... here. Add ISA 2.07 optimization. * sysdeps/powerpc/powerpc32/power4/fpu/multiarch/s_modf-power5+.c: Adjust include. * sysdeps/powerpc/powerpc32/power4/fpu/multiarch/s_modff-power5+.c: Likewise. * sysdeps/powerpc/powerpc64/be/fpu/multiarch/Makefile (sysdep_calls, sysdep_routines): Add s_modf* objects. (CFLAGS-s_modf-power5+.c, CFLAGS-s_modff-power5+.c, CFLAGS-s_modf-ppc64.c, CFLAGS-s_modff-ppc64.c): New rule. * sysdeps/powerpc/powerpc64/fpu/multiarch/s_modf-power5+.c: Move to ... * sysdeps/powerpc/powerpc64/be/fpu/multiarch/s_modf-power5+.c: ... here. * sysdeps/powerpc/powerpc64/fpu/multiarch/s_modf-power5+.c: Movo to ... * sysdeps/powerpc/powerpc64/be/fpu/multiarch/s_modf-power5+.c: Move ... here. * sysdeps/powerpc/powerpc64/fpu/multiarch/s_modf.c: Move to ... * sysdeps/powerpc/powerpc64/be/fpu/multiarch/s_modf.c: ... here. * sysdeps/powerpc/powerpc64/fpu/multiarch/s_modff-power5+.c: Move to ... * sysdeps/powerpc/powerpc64/be/fpu/multiarch/s_modff-power5+.c: ... here. * sysdeps/powerpc/powerpc64/fpu/multiarch/s_modff-ppc64.c: Move to ... * sysdeps/powerpc/powerpc64/be/fpu/multiarch/s_modff-ppc64.c: ... here. * sysdeps/powerpc/powerpc64/fpu/multiarch/s_modff.c: Move to ... * sysdeps/powerpc/powerpc64/be/fpu/multiarch/s_modff.c: ... here. Reviewed-by: Gabriel F. T. Gomes <gabrielftg@linux.ibm.com>
2019-03-18 20:18:49 +00:00
# endif
#endif