glibc/sysdeps/aarch64/fpu/math_private.h

345 lines
9.2 KiB
C
Raw Normal View History

/* Private floating point rounding and exceptions handling. AArch64 version.
Copyright (C) 2014-2017 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 AARCH64_MATH_PRIVATE_H
#define AARCH64_MATH_PRIVATE_H 1
#include <fenv.h>
#include <fpu_control.h>
#define math_opt_barrier(x) \
({ __typeof (x) __x = (x); __asm ("" : "+w" (__x)); __x; })
#define math_force_eval(x) \
({ __typeof (x) __x = (x); __asm __volatile__ ("" : : "w" (__x)); })
extern __always_inline double
__ieee754_sqrt (double d)
{
double res;
asm __volatile__ ("fsqrt %d0, %d1" : "=w" (res) : "w" (d));
return res;
}
extern __always_inline float
__ieee754_sqrtf (float s)
{
float res;
asm __volatile__ ("fsqrt %s0, %s1" : "=w" (res) : "w" (s));
return res;
}
static __always_inline void
libc_feholdexcept_aarch64 (fenv_t *envp)
{
fpu_control_t fpcr;
fpu_control_t new_fpcr;
fpu_fpsr_t fpsr;
fpu_fpsr_t new_fpsr;
_FPU_GETCW (fpcr);
_FPU_GETFPSR (fpsr);
envp->__fpcr = fpcr;
envp->__fpsr = fpsr;
/* Clear exception flags and set all exceptions to non-stop. */
new_fpcr = fpcr & ~(FE_ALL_EXCEPT << FE_EXCEPT_SHIFT);
new_fpsr = fpsr & ~FE_ALL_EXCEPT;
if (__glibc_unlikely (new_fpcr != fpcr))
_FPU_SETCW (new_fpcr);
if (new_fpsr != fpsr)
_FPU_SETFPSR (new_fpsr);
}
#define libc_feholdexcept libc_feholdexcept_aarch64
#define libc_feholdexceptf libc_feholdexcept_aarch64
#define libc_feholdexceptl libc_feholdexcept_aarch64
static __always_inline void
libc_fesetround_aarch64 (int round)
{
fpu_control_t fpcr;
_FPU_GETCW (fpcr);
/* Check whether rounding modes are different. */
round = (fpcr ^ round) & _FPU_FPCR_RM_MASK;
/* Set new rounding mode if different. */
if (__glibc_unlikely (round != 0))
_FPU_SETCW (fpcr ^ round);
}
#define libc_fesetround libc_fesetround_aarch64
#define libc_fesetroundf libc_fesetround_aarch64
#define libc_fesetroundl libc_fesetround_aarch64
static __always_inline void
libc_feholdexcept_setround_aarch64 (fenv_t *envp, int round)
{
fpu_control_t fpcr;
fpu_control_t new_fpcr;
fpu_fpsr_t fpsr;
fpu_fpsr_t new_fpsr;
_FPU_GETCW (fpcr);
_FPU_GETFPSR (fpsr);
envp->__fpcr = fpcr;
envp->__fpsr = fpsr;
/* Clear exception flags, set all exceptions to non-stop,
and set new rounding mode. */
new_fpcr = fpcr & ~((FE_ALL_EXCEPT << FE_EXCEPT_SHIFT) | _FPU_FPCR_RM_MASK);
new_fpcr |= round;
new_fpsr = fpsr & ~FE_ALL_EXCEPT;
if (__glibc_unlikely (new_fpcr != fpcr))
_FPU_SETCW (new_fpcr);
if (new_fpsr != fpsr)
_FPU_SETFPSR (new_fpsr);
}
#define libc_feholdexcept_setround libc_feholdexcept_setround_aarch64
#define libc_feholdexcept_setroundf libc_feholdexcept_setround_aarch64
#define libc_feholdexcept_setroundl libc_feholdexcept_setround_aarch64
static __always_inline int
libc_fetestexcept_aarch64 (int ex)
{
fpu_fpsr_t fpsr;
_FPU_GETFPSR (fpsr);
return fpsr & ex & FE_ALL_EXCEPT;
}
#define libc_fetestexcept libc_fetestexcept_aarch64
#define libc_fetestexceptf libc_fetestexcept_aarch64
#define libc_fetestexceptl libc_fetestexcept_aarch64
static __always_inline void
libc_fesetenv_aarch64 (const fenv_t *envp)
{
fpu_control_t fpcr;
fpu_control_t new_fpcr;
_FPU_GETCW (fpcr);
new_fpcr = envp->__fpcr;
if (__glibc_unlikely (fpcr != new_fpcr))
_FPU_SETCW (new_fpcr);
_FPU_SETFPSR (envp->__fpsr);
}
#define libc_fesetenv libc_fesetenv_aarch64
#define libc_fesetenvf libc_fesetenv_aarch64
#define libc_fesetenvl libc_fesetenv_aarch64
#define libc_feresetround_noex libc_fesetenv_aarch64
#define libc_feresetround_noexf libc_fesetenv_aarch64
#define libc_feresetround_noexl libc_fesetenv_aarch64
static __always_inline int
libc_feupdateenv_test_aarch64 (const fenv_t *envp, int ex)
{
fpu_control_t fpcr;
fpu_control_t new_fpcr;
fpu_fpsr_t fpsr;
fpu_fpsr_t new_fpsr;
int excepts;
_FPU_GETCW (fpcr);
_FPU_GETFPSR (fpsr);
/* Merge current exception flags with the saved fenv. */
excepts = fpsr & FE_ALL_EXCEPT;
new_fpcr = envp->__fpcr;
new_fpsr = envp->__fpsr | excepts;
if (__glibc_unlikely (fpcr != new_fpcr))
_FPU_SETCW (new_fpcr);
if (fpsr != new_fpsr)
_FPU_SETFPSR (new_fpsr);
/* Raise the exceptions if enabled in the new FP state. */
if (__glibc_unlikely (excepts & (new_fpcr >> FE_EXCEPT_SHIFT)))
Fix libm feraiseexcept namespace (bug 17723). Various C90 and UNIX98 libm functions call feraiseexcept, which is not in those standards. This causes linknamespace test failures - except on x86 / x86_64, where feraiseexcept is inline (for the relevant constant arguments) in bits/fenv.h. This patch fixes this by making those functions call __feraiseexcept instead. All changes are applied to all architectures rather than considering the possibility that some might not be needed in some cases (e.g. x86) as it seems most maintainable to keep architectures consistent. Where __feraiseexcept does not exist, it is added, with feraiseexcept made a weak alias; where it is a strong alias, it is made weak. libm_hidden_def / libm_hidden_proto are used with __feraiseexcept (this might in some cases improve code generation for existing calls to __feraiseexcept in some code on some architectures). Where there are dummy feraiseexcept macros (on architectures without floating-point exceptions support, to avoid compile errors from references to undefined FE_* macros), corresponding dummy __feraiseexcept macros are added. And on x86, to ensure __feraiseexcept calls still get inlined, the inline function in bits/fenv.h is refactored so that most of it can be reused in an inline __feraiseexcept in a separate include/bits/fenv.h. Calls are changed in C90/UNIX98 functions, but generally not in functions missing from those standards. They are also changed in libc_fe* functions (on the basis that those might be used in any libm function), and in feupdateenv (on the same basis - may be used, via default libc_*, in any libm function - of course feupdateenv will need changing to __feupdateenv in a subsequent patch to make that fully namespace-clean). No __feraiseexcept is added corresponding to the feraiseexcept in powerpc bits/fenvinline.h, because that macro definition is conditional on !defined __NO_MATH_INLINES, and glibc libm is built with -D__NO_MATH_INLINES, so changing internal calls to use __feraiseexcept should make no difference. Tested for x86_64 (testsuite; the only change in disassembly of installed shared libraries is a slight code reordering in clog10, of no apparent significance). Also tested for MIPS, where (in the configuration tested) it eliminates math.h linknamespace failures for n32 and n64 (some for o32 remain because of other issues). [BZ #17723] * include/fenv.h (__feraiseexcept): Use libm_hidden_proto. * math/fraiseexcpt.c (__feraiseexcept): Use libm_hidden_def. * sysdeps/aarch64/fpu/fraiseexcpt.c (feraiseexcept): Rename to __feraiseexcept and define as weak alias of __feraiseexcept. Use libm_hidden_weak. * sysdeps/arm/fraiseexcpt.c (feraiseexcept): Likewise. * sysdeps/hppa/fpu/fraiseexcpt.c (feraiseexcept): Likewise. * sysdeps/i386/fpu/fraiseexcpt.c (__feraiseexcept): Use libm_hidden_def. * sysdeps/ia64/fpu/fraiseexcpt.c (feraiseexcept): Rename to __feraiseexcept and define as weak alias of __feraiseexcept. Use libm_hidden_weak. * sysdeps/m68k/coldfire/fpu/fraiseexcpt.c (feraiseexcept): Likewise. * sysdeps/microblaze/math_private.h (__feraiseexcept): New macro. * sysdeps/mips/fpu/fraiseexcpt.c (feraiseexcept): Rename to __feraiseexcept and define as weak alias of __feraiseexcept. Use libm_hidden_weak. * sysdeps/powerpc/fpu/fraiseexcpt.c (__feraiseexcept): Use libm_hidden_def. * sysdeps/powerpc/nofpu/fraiseexcpt.c (__feraiseexcept): Likewise. * sysdeps/powerpc/powerpc32/e500/nofpu/fraiseexcpt.c (__feraiseexcept): Likewise. * sysdeps/s390/fpu/fraiseexcpt.c (feraiseexcept): Rename to __feraiseexcept and define as weak alias of __feraiseexcept. Use libm_hidden_weak. * sysdeps/sh/sh4/fpu/fraiseexcpt.c (feraiseexcept): Likewise. * sysdeps/sparc/fpu/fraiseexcpt.c (__feraiseexcept): Use libm_hidden_def. * sysdeps/tile/math_private.h (__feraiseexcept): New macro. * sysdeps/unix/sysv/linux/alpha/fraiseexcpt.S (__feraiseexcept): Use libm_hidden_def. * sysdeps/x86_64/fpu/fraiseexcpt.c (__feraiseexcept): Use libm_hidden_def. (feraiseexcept): Define as weak not strong alias. Use libm_hidden_weak. * sysdeps/x86/fpu/bits/fenv.h (__feraiseexcept_invalid_divbyzero): New inline function. Factored out of ... (feraiseexcept): ... here. Use __feraiseexcept_invalid_divbyzero. * sysdeps/x86/fpu/include/bits/fenv.h: New file. * math/e_scalb.c (invalid_fn): Call __feraiseexcept instead of feraiseexcept. * math/w_acos.c (__acos): Likewise. * math/w_asin.c (__asin): Likewise. * math/w_ilogb.c (__ilogb): Likewise. * math/w_j0.c (y0): Likewise. * math/w_j1.c (y1): Likewise. * math/w_jn.c (yn): Likewise. * math/w_log.c (__log): Likewise. * math/w_log10.c (__log10): Likewise. * sysdeps/aarch64/fpu/feupdateenv.c (feupdateenv): Likewise. * sysdeps/aarch64/fpu/math_private.h (libc_feupdateenv_test_aarch64): Likewise. * sysdeps/alpha/fpu/feupdateenv.c (__feupdateenv): Likewise. * sysdeps/arm/fenv_private.h (libc_feupdateenv_test_vfp): Likewise. * sysdeps/arm/feupdateenv.c (feupdateenv): Likewise. * sysdeps/ia64/fpu/feupdateenv.c (feupdateenv): Likewise. * sysdeps/m68k/fpu/feupdateenv.c (__feupdateenv): Likewise. * sysdeps/mips/fpu/feupdateenv.c (feupdateenv): Likewise. * sysdeps/powerpc/fpu/e_sqrt.c (__slow_ieee754_sqrt): Likewise. * sysdeps/s390/fpu/feupdateenv.c (feupdateenv): Likewise. * sysdeps/sh/sh4/fpu/feupdateenv.c (feupdateenv): Likewise. * sysdeps/sparc/fpu/feupdateenv.c (__feupdateenv): Likewise.
2014-12-30 18:08:09 +01:00
__feraiseexcept (excepts);
return excepts & ex;
}
#define libc_feupdateenv_test libc_feupdateenv_test_aarch64
#define libc_feupdateenv_testf libc_feupdateenv_test_aarch64
#define libc_feupdateenv_testl libc_feupdateenv_test_aarch64
static __always_inline void
libc_feupdateenv_aarch64 (const fenv_t *envp)
{
libc_feupdateenv_test_aarch64 (envp, 0);
}
#define libc_feupdateenv libc_feupdateenv_aarch64
#define libc_feupdateenvf libc_feupdateenv_aarch64
#define libc_feupdateenvl libc_feupdateenv_aarch64
static __always_inline void
libc_feholdsetround_aarch64 (fenv_t *envp, int round)
{
fpu_control_t fpcr;
fpu_fpsr_t fpsr;
_FPU_GETCW (fpcr);
_FPU_GETFPSR (fpsr);
envp->__fpcr = fpcr;
envp->__fpsr = fpsr;
/* Check whether rounding modes are different. */
round = (fpcr ^ round) & _FPU_FPCR_RM_MASK;
/* Set new rounding mode if different. */
if (__glibc_unlikely (round != 0))
_FPU_SETCW (fpcr ^ round);
}
#define libc_feholdsetround libc_feholdsetround_aarch64
#define libc_feholdsetroundf libc_feholdsetround_aarch64
#define libc_feholdsetroundl libc_feholdsetround_aarch64
static __always_inline void
libc_feresetround_aarch64 (fenv_t *envp)
{
fpu_control_t fpcr;
int round;
_FPU_GETCW (fpcr);
/* Check whether rounding modes are different. */
round = (envp->__fpcr ^ fpcr) & _FPU_FPCR_RM_MASK;
/* Restore the rounding mode if it was changed. */
if (__glibc_unlikely (round != 0))
_FPU_SETCW (fpcr ^ round);
}
#define libc_feresetround libc_feresetround_aarch64
#define libc_feresetroundf libc_feresetround_aarch64
#define libc_feresetroundl libc_feresetround_aarch64
/* We have support for rounding mode context. */
#define HAVE_RM_CTX 1
static __always_inline void
libc_feholdsetround_aarch64_ctx (struct rm_ctx *ctx, int r)
{
fpu_control_t fpcr;
int round;
_FPU_GETCW (fpcr);
ctx->env.__fpcr = fpcr;
/* Check whether rounding modes are different. */
round = (fpcr ^ r) & _FPU_FPCR_RM_MASK;
ctx->updated_status = round != 0;
/* Set the rounding mode if changed. */
if (__glibc_unlikely (round != 0))
_FPU_SETCW (fpcr ^ round);
}
#define libc_feholdsetround_ctx libc_feholdsetround_aarch64_ctx
#define libc_feholdsetroundf_ctx libc_feholdsetround_aarch64_ctx
#define libc_feholdsetroundl_ctx libc_feholdsetround_aarch64_ctx
static __always_inline void
libc_feresetround_aarch64_ctx (struct rm_ctx *ctx)
{
/* Restore the rounding mode if updated. */
if (__glibc_unlikely (ctx->updated_status))
_FPU_SETCW (ctx->env.__fpcr);
}
#define libc_feresetround_ctx libc_feresetround_aarch64_ctx
#define libc_feresetroundf_ctx libc_feresetround_aarch64_ctx
#define libc_feresetroundl_ctx libc_feresetround_aarch64_ctx
static __always_inline void
libc_feholdsetround_noex_aarch64_ctx (struct rm_ctx *ctx, int r)
{
fpu_control_t fpcr;
fpu_fpsr_t fpsr;
int round;
_FPU_GETCW (fpcr);
_FPU_GETFPSR (fpsr);
ctx->env.__fpcr = fpcr;
ctx->env.__fpsr = fpsr;
/* Check whether rounding modes are different. */
round = (fpcr ^ r) & _FPU_FPCR_RM_MASK;
ctx->updated_status = round != 0;
/* Set the rounding mode if changed. */
if (__glibc_unlikely (round != 0))
_FPU_SETCW (fpcr ^ round);
}
#define libc_feholdsetround_noex_ctx libc_feholdsetround_noex_aarch64_ctx
#define libc_feholdsetround_noexf_ctx libc_feholdsetround_noex_aarch64_ctx
#define libc_feholdsetround_noexl_ctx libc_feholdsetround_noex_aarch64_ctx
static __always_inline void
libc_feresetround_noex_aarch64_ctx (struct rm_ctx *ctx)
{
/* Restore the rounding mode if updated. */
if (__glibc_unlikely (ctx->updated_status))
_FPU_SETCW (ctx->env.__fpcr);
/* Write new FPSR to restore exception flags. */
_FPU_SETFPSR (ctx->env.__fpsr);
}
#define libc_feresetround_noex_ctx libc_feresetround_noex_aarch64_ctx
#define libc_feresetround_noexf_ctx libc_feresetround_noex_aarch64_ctx
#define libc_feresetround_noexl_ctx libc_feresetround_noex_aarch64_ctx
Optimized generic expf and exp2f with wrappers Based on new expf and exp2f code from https://github.com/ARM-software/optimized-routines/ with wrapper on aarch64: expf reciprocal-throughput: 2.3x faster expf latency: 1.7x faster without wrapper on aarch64: expf reciprocal-throughput: 3.3x faster expf latency: 1.7x faster without wrapper on aarch64: exp2f reciprocal-throughput: 2.8x faster exp2f latency: 1.3x faster libm.so size on aarch64: .text size: -152 bytes .rodata size: -1740 bytes expf/exp2f worst case nearest rounding error: 0.502 ulp worst case non-nearest rounding error: 1 ulp Error checks are inline and errno setting is in separate tail called functions, but the wrappers are kept in this patch to handle the _LIB_VERSION==_SVID_ case. (So e.g. errno is set twice for expf calls and once for __expf_finite calls on targets where the new code is used.) Double precision arithmetics is used which is expected to be faster on most targets (including soft-float) than using single precision and it is easier to get good precision result with it. Const data is kept in a separate translation unit which complicates maintenance a bit, but is expected to give good code for literal loads on most targets and allows sharing data across expf, exp2f and powf. (This data is disabled on i386, m68k and ia64 which have their own expf, exp2f and powf code.) Some details may need target specific tweaks: - best convert and round to int operation in the arg reduction may be different across targets. - code was optimized on fma target, optimal polynomial eval may be different without fma. - gcc does not always generate good code for fp bit representation access via unions or it may be inherently slow on some targets. The libm-test-ulps will need adjustment because.. - The argument reduction ideally uses nearest rounded rint, but that is not efficient on most targets, so the polynomial can get evaluated on a wider interval in non-nearest rounding mode making 1 ulp errors common in that case. - The polynomial is evaluated such that it may have 1 ulp error on negative tiny inputs with upward rounding. * math/Makefile (type-float-routines): Add math_errf and e_exp2f_data. * sysdeps/aarch64/fpu/math_private.h (TOINT_INTRINSICS): Define. (roundtoint, converttoint): Likewise. * sysdeps/ieee754/flt-32/e_expf.c: New implementation. * sysdeps/ieee754/flt-32/e_exp2f.c: New implementation. * sysdeps/ieee754/flt-32/e_exp2f_data.c: New file. * sysdeps/ieee754/flt-32/math_config.h: New file. * sysdeps/ieee754/flt-32/math_errf.c: New file. * sysdeps/ieee754/flt-32/t_exp2f.h: Remove. * sysdeps/i386/fpu/e_exp2f_data.c: New file. * sysdeps/i386/fpu/math_errf.c: New file. * sysdeps/ia64/fpu/e_exp2f_data.c: New file. * sysdeps/ia64/fpu/math_errf.c: New file. * sysdeps/m68k/m680x0/fpu/e_exp2f_data.c: New file. * sysdeps/m68k/m680x0/fpu/math_errf.c: New file.
2017-09-06 18:42:00 +02:00
/* Hack: only include the large arm_neon.h when needed. */
#ifdef _MATH_CONFIG_H
# include <arm_neon.h>
/* ACLE intrinsics for frintn and fcvtns instructions. */
# define TOINT_INTRINSICS 1
static inline double_t
roundtoint (double_t x)
{
return vget_lane_f64 (vrndn_f64 (vld1_f64 (&x)), 0);
}
static inline uint64_t
converttoint (double_t x)
{
return vcvtnd_s64_f64 (x);
}
#endif
#include_next <math_private.h>
#endif