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.
This commit is contained in:
Joseph Myers
parent
221e4babca
commit
e44acb2063
76
ChangeLog
76
ChangeLog
|
|
@ -1,3 +1,79 @@
|
|||
2018-09-14 Joseph Myers <joseph@codesourcery.com>
|
||||
|
||||
* 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.
|
||||
|
||||
2018-09-12 Joseph Myers <joseph@codesourcery.com>
|
||||
|
||||
* elf/Makefile (modules-names-tests): New variable.
|
||||
|
|
|
|||
|
|
@ -79,16 +79,29 @@ fabsf128 (_Float128 x)
|
|||
|
||||
# if !(defined __FINITE_MATH_ONLY__ && __FINITE_MATH_ONLY__ > 0)
|
||||
# ifndef NO_MATH_REDIRECT
|
||||
/* Declare sqrt for use within GLIBC. Compilers typically inline sqrt as a
|
||||
single instruction. Use an asm to avoid use of PLTs if it doesn't. */
|
||||
float (sqrtf) (float) asm ("__ieee754_sqrtf");
|
||||
double (sqrt) (double) asm ("__ieee754_sqrt");
|
||||
# ifndef __NO_LONG_DOUBLE_MATH
|
||||
long double (sqrtl) (long double) asm ("__ieee754_sqrtl");
|
||||
/* Declare some functions for use within GLIBC. Compilers typically
|
||||
inline those functions as a single instruction. Use an asm to
|
||||
avoid use of PLTs if it doesn't. */
|
||||
# define MATH_REDIRECT(FUNC, PREFIX, ARGS) \
|
||||
float (FUNC ## f) (ARGS (float)) asm (PREFIX #FUNC "f"); \
|
||||
double (FUNC) (ARGS (double)) asm (PREFIX #FUNC ); \
|
||||
MATH_REDIRECT_LDBL (FUNC, PREFIX, ARGS) \
|
||||
MATH_REDIRECT_F128 (FUNC, PREFIX, ARGS)
|
||||
# ifdef __NO_LONG_DOUBLE_MATH
|
||||
# define MATH_REDIRECT_LDBL(FUNC, PREFIX, ARGS)
|
||||
# else
|
||||
# define MATH_REDIRECT_LDBL(FUNC, PREFIX, ARGS) \
|
||||
long double (FUNC ## l) (ARGS (long double)) asm (PREFIX #FUNC "l");
|
||||
# endif
|
||||
# if __HAVE_DISTINCT_FLOAT128 > 0
|
||||
_Float128 (sqrtf128) (_Float128) asm ("__ieee754_sqrtf128");
|
||||
# if __HAVE_DISTINCT_FLOAT128
|
||||
# define MATH_REDIRECT_F128(FUNC, PREFIX, ARGS) \
|
||||
_Float128 (FUNC ## f128) (ARGS (_Float128)) asm (PREFIX #FUNC "f128");
|
||||
# else
|
||||
# define MATH_REDIRECT_F128(FUNC, PREFIX, ARGS)
|
||||
# endif
|
||||
# define MATH_REDIRECT_UNARY_ARGS(TYPE) TYPE
|
||||
MATH_REDIRECT (sqrt, "__ieee754_", MATH_REDIRECT_UNARY_ARGS)
|
||||
MATH_REDIRECT (floor, "__", MATH_REDIRECT_UNARY_ARGS)
|
||||
# endif
|
||||
# endif
|
||||
|
||||
|
|
|
|||
|
|
@ -31,7 +31,7 @@ LGFUNC (__lgamma) (double x)
|
|||
if(__builtin_expect(!isfinite(y), 0)
|
||||
&& isfinite(x) && _LIB_VERSION != _IEEE_)
|
||||
return __kernel_standard(x, x,
|
||||
__floor(x)==x&&x<=0.0
|
||||
floor(x)==x&&x<=0.0
|
||||
? 15 /* lgamma pole */
|
||||
: 14); /* lgamma overflow */
|
||||
|
||||
|
|
|
|||
|
|
@ -28,7 +28,7 @@ __lgamma_r(double x, int *signgamp)
|
|||
if(__builtin_expect(!isfinite(y), 0)
|
||||
&& isfinite(x) && _LIB_VERSION != _IEEE_)
|
||||
return __kernel_standard(x, x,
|
||||
__floor(x)==x&&x<=0.0
|
||||
floor(x)==x&&x<=0.0
|
||||
? 15 /* lgamma pole */
|
||||
: 14); /* lgamma overflow */
|
||||
|
||||
|
|
|
|||
|
|
@ -28,7 +28,7 @@ LGFUNC (__lgammaf) (float x)
|
|||
if(__builtin_expect(!isfinite(y), 0)
|
||||
&& isfinite(x) && _LIB_VERSION != _IEEE_)
|
||||
return __kernel_standard_f(x, x,
|
||||
__floorf(x)==x&&x<=0.0f
|
||||
floorf(x)==x&&x<=0.0f
|
||||
? 115 /* lgamma pole */
|
||||
: 114); /* lgamma overflow */
|
||||
|
||||
|
|
|
|||
|
|
@ -31,7 +31,7 @@ __lgammaf_r(float x, int *signgamp)
|
|||
if(__builtin_expect(!isfinite(y), 0)
|
||||
&& isfinite(x) && _LIB_VERSION != _IEEE_)
|
||||
return __kernel_standard_f(x, x,
|
||||
__floorf(x)==x&&x<=0.0f
|
||||
floorf(x)==x&&x<=0.0f
|
||||
? 115 /* lgamma pole */
|
||||
: 114); /* lgamma overflow */
|
||||
|
||||
|
|
|
|||
|
|
@ -35,7 +35,7 @@ LGFUNC (__lgammal) (long double x)
|
|||
if(__builtin_expect(!isfinite(y), 0)
|
||||
&& isfinite(x) && _LIB_VERSION != _IEEE_)
|
||||
return __kernel_standard_l(x, x,
|
||||
__floorl(x)==x&&x<=0.0L
|
||||
floorl(x)==x&&x<=0.0L
|
||||
? 215 /* lgamma pole */
|
||||
: 214); /* lgamma overflow */
|
||||
|
||||
|
|
|
|||
|
|
@ -32,7 +32,7 @@ __lgammal_r(long double x, int *signgamp)
|
|||
if(__builtin_expect(!isfinite(y), 0)
|
||||
&& isfinite(x) && _LIB_VERSION != _IEEE_)
|
||||
return __kernel_standard(x, x,
|
||||
__floorl(x)==x&&x<=0.0
|
||||
floorl(x)==x&&x<=0.0
|
||||
? 215 /* lgamma pole */
|
||||
: 214); /* lgamma overflow */
|
||||
|
||||
|
|
|
|||
|
|
@ -33,7 +33,7 @@ __tgamma(double x)
|
|||
&& _LIB_VERSION != _IEEE_) {
|
||||
if (x == 0.0)
|
||||
return __kernel_standard(x,x,50); /* tgamma pole */
|
||||
else if(__floor(x)==x&&x<0.0)
|
||||
else if(floor(x)==x&&x<0.0)
|
||||
return __kernel_standard(x,x,41); /* tgamma domain */
|
||||
else if (y == 0)
|
||||
__set_errno (ERANGE); /* tgamma underflow */
|
||||
|
|
|
|||
|
|
@ -41,7 +41,7 @@ M_DECL_FUNC (__tgamma) (FLOAT x)
|
|||
if (x == 0)
|
||||
/* Pole error: tgamma(x=0). */
|
||||
__set_errno (ERANGE);
|
||||
else if (M_SUF (__floor) (x) == x && x < 0)
|
||||
else if (M_SUF (floor) (x) == x && x < 0)
|
||||
/* Domain error: tgamma(integer x<0). */
|
||||
__set_errno (EDOM);
|
||||
else
|
||||
|
|
|
|||
|
|
@ -32,7 +32,7 @@ __tgammaf(float x)
|
|||
if (x == (float)0.0)
|
||||
/* tgammaf pole */
|
||||
return __kernel_standard_f(x, x, 150);
|
||||
else if(__floorf(x)==x&&x<0.0f)
|
||||
else if(floorf(x)==x&&x<0.0f)
|
||||
/* tgammaf domain */
|
||||
return __kernel_standard_f(x, x, 141);
|
||||
else if (y == 0)
|
||||
|
|
|
|||
|
|
@ -36,7 +36,7 @@ __tgammal(long double x)
|
|||
&& _LIB_VERSION != _IEEE_) {
|
||||
if(x==0.0)
|
||||
return __kernel_standard_l(x,x,250); /* tgamma pole */
|
||||
else if(__floorl(x)==x&&x<0.0L)
|
||||
else if(floorl(x)==x&&x<0.0L)
|
||||
return __kernel_standard_l(x,x,241); /* tgamma domain */
|
||||
else if (y == 0)
|
||||
__set_errno (ERANGE); /* tgamma underflow */
|
||||
|
|
|
|||
|
|
@ -16,6 +16,7 @@
|
|||
License along with the GNU C Library; if not, see
|
||||
<http://www.gnu.org/licenses/>. */
|
||||
|
||||
#define NO_MATH_REDIRECT
|
||||
#include <math.h>
|
||||
#include <libm-alias-double.h>
|
||||
|
||||
|
|
|
|||
|
|
@ -16,6 +16,7 @@
|
|||
License along with the GNU C Library; if not, see
|
||||
<http://www.gnu.org/licenses/>. */
|
||||
|
||||
#define NO_MATH_REDIRECT
|
||||
#include <math.h>
|
||||
#include <libm-alias-float.h>
|
||||
|
||||
|
|
|
|||
|
|
@ -168,10 +168,10 @@ sin_pi(double x)
|
|||
* argument reduction, make sure inexact flag not raised if input
|
||||
* is an integer
|
||||
*/
|
||||
z = __floor(y);
|
||||
z = floor(y);
|
||||
if(z!=y) { /* inexact anyway */
|
||||
y *= 0.5;
|
||||
y = 2.0*(y - __floor(y)); /* y = |x| mod 2.0 */
|
||||
y = 2.0*(y - floor(y)); /* y = |x| mod 2.0 */
|
||||
n = (int) (y*4.0);
|
||||
} else {
|
||||
if(ix>=0x43400000) {
|
||||
|
|
|
|||
|
|
@ -196,7 +196,7 @@ recompute:
|
|||
|
||||
/* compute n */
|
||||
z = __scalbn (z, q0); /* actual value of z */
|
||||
z -= 8.0 * __floor (z * 0.125); /* trim off integer >= 8 */
|
||||
z -= 8.0 * floor (z * 0.125); /* trim off integer >= 8 */
|
||||
n = (int32_t) z;
|
||||
z -= (double) n;
|
||||
ih = 0;
|
||||
|
|
|
|||
|
|
@ -282,7 +282,7 @@ __lgamma_neg (double x, int *signgamp)
|
|||
{
|
||||
/* Determine the half-integer region X lies in, handle exact
|
||||
integers and determine the sign of the result. */
|
||||
int i = __floor (-2 * x);
|
||||
int i = floor (-2 * x);
|
||||
if ((i & 1) == 0 && i == -2 * x)
|
||||
return 1.0 / 0.0;
|
||||
double xn = ((i & 1) == 0 ? -i / 2 : (-i - 1) / 2);
|
||||
|
|
@ -299,7 +299,7 @@ __lgamma_neg (double x, int *signgamp)
|
|||
approximations to an adjusted version of the gamma function. */
|
||||
if (i < 2)
|
||||
{
|
||||
int j = __floor (-8 * x) - 16;
|
||||
int j = floor (-8 * x) - 16;
|
||||
double xm = (-33 - 2 * j) * 0.0625;
|
||||
double x_adj = x - xm;
|
||||
size_t deg = poly_deg[j];
|
||||
|
|
|
|||
|
|
@ -17,6 +17,7 @@
|
|||
* Bit twiddling.
|
||||
*/
|
||||
|
||||
#define NO_MATH_REDIRECT
|
||||
#include <math.h>
|
||||
#include <math_private.h>
|
||||
#include <libm-alias-double.h>
|
||||
|
|
|
|||
|
|
@ -30,6 +30,7 @@
|
|||
* ====================================================
|
||||
*/
|
||||
|
||||
#define NO_MATH_REDIRECT
|
||||
#include <math.h>
|
||||
#include <math_private.h>
|
||||
#include <stdint.h>
|
||||
|
|
|
|||
|
|
@ -1,2 +1,3 @@
|
|||
#define NO_MATH_REDIRECT
|
||||
#include <float128_private.h>
|
||||
#include "../ldbl-128/s_floorl.c"
|
||||
|
|
|
|||
|
|
@ -104,10 +104,10 @@ sin_pif(float x)
|
|||
* argument reduction, make sure inexact flag not raised if input
|
||||
* is an integer
|
||||
*/
|
||||
z = __floorf(y);
|
||||
z = floorf(y);
|
||||
if(z!=y) { /* inexact anyway */
|
||||
y *= (float)0.5;
|
||||
y = (float)2.0*(y - __floorf(y)); /* y = |x| mod 2.0 */
|
||||
y = (float)2.0*(y - floorf(y)); /* y = |x| mod 2.0 */
|
||||
n = (int) (y*(float)4.0);
|
||||
} else {
|
||||
if(ix>=0x4b800000) {
|
||||
|
|
|
|||
|
|
@ -197,7 +197,7 @@ __lgamma_negf (float x, int *signgamp)
|
|||
{
|
||||
/* Determine the half-integer region X lies in, handle exact
|
||||
integers and determine the sign of the result. */
|
||||
int i = __floorf (-2 * x);
|
||||
int i = floorf (-2 * x);
|
||||
if ((i & 1) == 0 && i == -2 * x)
|
||||
return 1.0f / 0.0f;
|
||||
float xn = ((i & 1) == 0 ? -i / 2 : (-i - 1) / 2);
|
||||
|
|
@ -214,7 +214,7 @@ __lgamma_negf (float x, int *signgamp)
|
|||
approximations to an adjusted version of the gamma function. */
|
||||
if (i < 2)
|
||||
{
|
||||
int j = __floorf (-8 * x) - 16;
|
||||
int j = floorf (-8 * x) - 16;
|
||||
float xm = (-33 - 2 * j) * 0.0625f;
|
||||
float x_adj = x - xm;
|
||||
size_t deg = poly_deg[j];
|
||||
|
|
|
|||
|
|
@ -20,6 +20,7 @@
|
|||
* Bit twiddling.
|
||||
*/
|
||||
|
||||
#define NO_MATH_REDIRECT
|
||||
#include <math.h>
|
||||
#include <math_private.h>
|
||||
#include <libm-alias-float.h>
|
||||
|
|
|
|||
|
|
@ -776,11 +776,11 @@ __ieee754_lgammal_r (_Float128 x, int *signgamp)
|
|||
if (x < -2 && x > -50)
|
||||
return __lgamma_negl (x, signgamp);
|
||||
q = -x;
|
||||
p = __floorl (q);
|
||||
p = floorl (q);
|
||||
if (p == q)
|
||||
return (one / fabsl (p - p));
|
||||
_Float128 halfp = p * L(0.5);
|
||||
if (halfp == __floorl (halfp))
|
||||
if (halfp == floorl (halfp))
|
||||
*signgamp = -1;
|
||||
else
|
||||
*signgamp = 1;
|
||||
|
|
@ -801,7 +801,7 @@ __ieee754_lgammal_r (_Float128 x, int *signgamp)
|
|||
if (x < L(13.5))
|
||||
{
|
||||
p = 0;
|
||||
nx = __floorl (x + L(0.5));
|
||||
nx = floorl (x + L(0.5));
|
||||
nn = nx;
|
||||
switch (nn)
|
||||
{
|
||||
|
|
|
|||
|
|
@ -198,10 +198,10 @@ __ieee754_powl (_Float128 x, _Float128 y)
|
|||
yisint = 2; /* even integer y */
|
||||
else if (iy >= 0x3fff0000) /* 1.0 */
|
||||
{
|
||||
if (__floorl (y) == y)
|
||||
if (floorl (y) == y)
|
||||
{
|
||||
z = 0.5 * y;
|
||||
if (__floorl (z) == z)
|
||||
if (floorl (z) == z)
|
||||
yisint = 2;
|
||||
else
|
||||
yisint = 1;
|
||||
|
|
@ -413,7 +413,7 @@ __ieee754_powl (_Float128 x, _Float128 y)
|
|||
n = 0;
|
||||
if (i > 0x3ffe0000)
|
||||
{ /* if |z| > 0.5, set n = [z+0.5] */
|
||||
n = __floorl (z + L(0.5));
|
||||
n = floorl (z + L(0.5));
|
||||
t = n;
|
||||
p_h -= t;
|
||||
}
|
||||
|
|
|
|||
|
|
@ -449,7 +449,7 @@ __lgamma_negl (_Float128 x, int *signgamp)
|
|||
{
|
||||
/* Determine the half-integer region X lies in, handle exact
|
||||
integers and determine the sign of the result. */
|
||||
int i = __floorl (-2 * x);
|
||||
int i = floorl (-2 * x);
|
||||
if ((i & 1) == 0 && i == -2 * x)
|
||||
return L(1.0) / L(0.0);
|
||||
_Float128 xn = ((i & 1) == 0 ? -i / 2 : (-i - 1) / 2);
|
||||
|
|
@ -466,7 +466,7 @@ __lgamma_negl (_Float128 x, int *signgamp)
|
|||
approximations to an adjusted version of the gamma function. */
|
||||
if (i < 2)
|
||||
{
|
||||
int j = __floorl (-8 * x) - 16;
|
||||
int j = floorl (-8 * x) - 16;
|
||||
_Float128 xm = (-33 - 2 * j) * L(0.0625);
|
||||
_Float128 x_adj = x - xm;
|
||||
size_t deg = poly_deg[j];
|
||||
|
|
|
|||
|
|
@ -136,7 +136,7 @@ __expm1l (_Float128 x)
|
|||
|
||||
/* Express x = ln 2 (k + remainder), remainder not exceeding 1/2. */
|
||||
xx = C1 + C2; /* ln 2. */
|
||||
px = __floorl (0.5 + x / xx);
|
||||
px = floorl (0.5 + x / xx);
|
||||
k = px;
|
||||
/* remainder times ln 2 */
|
||||
x -= px * C1;
|
||||
|
|
|
|||
|
|
@ -24,6 +24,7 @@ static char rcsid[] = "$NetBSD: $";
|
|||
* Bit twiddling.
|
||||
*/
|
||||
|
||||
#define NO_MATH_REDIRECT
|
||||
#include <math.h>
|
||||
#include <math_private.h>
|
||||
#include <libm-alias-ldouble.h>
|
||||
|
|
|
|||
|
|
@ -726,11 +726,11 @@ __ieee754_lgammal_r (long double x, int *signgamp)
|
|||
if (x < -2 && x > -48)
|
||||
return __lgamma_negl (x, signgamp);
|
||||
q = -x;
|
||||
p = __floorl (q);
|
||||
p = floorl (q);
|
||||
if (p == q)
|
||||
return (one / fabsl (p - p));
|
||||
long double halfp = p * 0.5L;
|
||||
if (halfp == __floorl (halfp))
|
||||
if (halfp == floorl (halfp))
|
||||
*signgamp = -1;
|
||||
else
|
||||
*signgamp = 1;
|
||||
|
|
@ -751,7 +751,7 @@ __ieee754_lgammal_r (long double x, int *signgamp)
|
|||
if (x < 13.5L)
|
||||
{
|
||||
p = 0;
|
||||
nx = __floorl (x + 0.5L);
|
||||
nx = floorl (x + 0.5L);
|
||||
nn = nx;
|
||||
switch (nn)
|
||||
{
|
||||
|
|
|
|||
|
|
@ -195,10 +195,10 @@ __ieee754_powl (long double x, long double y)
|
|||
yisint = 2; /* even integer y */
|
||||
else if (iy >= 0x3ff00000) /* 1.0 */
|
||||
{
|
||||
if (__floorl (y) == y)
|
||||
if (floorl (y) == y)
|
||||
{
|
||||
z = 0.5 * y;
|
||||
if (__floorl (z) == z)
|
||||
if (floorl (z) == z)
|
||||
yisint = 2;
|
||||
else
|
||||
yisint = 1;
|
||||
|
|
@ -392,7 +392,7 @@ __ieee754_powl (long double x, long double y)
|
|||
n = 0;
|
||||
if (i > 0x3fe00000)
|
||||
{ /* if |z| > 0.5, set n = [z+0.5] */
|
||||
n = __floorl (z + 0.5L);
|
||||
n = floorl (z + 0.5L);
|
||||
t = n;
|
||||
p_h -= t;
|
||||
}
|
||||
|
|
|
|||
|
|
@ -430,7 +430,7 @@ __lgamma_negl (long double x, int *signgamp)
|
|||
{
|
||||
/* Determine the half-integer region X lies in, handle exact
|
||||
integers and determine the sign of the result. */
|
||||
int i = __floorl (-2 * x);
|
||||
int i = floorl (-2 * x);
|
||||
if ((i & 1) == 0 && i == -2 * x)
|
||||
return 1.0L / 0.0L;
|
||||
long double xn = ((i & 1) == 0 ? -i / 2 : (-i - 1) / 2);
|
||||
|
|
@ -447,7 +447,7 @@ __lgamma_negl (long double x, int *signgamp)
|
|||
approximations to an adjusted version of the gamma function. */
|
||||
if (i < 2)
|
||||
{
|
||||
int j = __floorl (-8 * x) - 16;
|
||||
int j = floorl (-8 * x) - 16;
|
||||
long double xm = (-33 - 2 * j) * 0.0625L;
|
||||
long double x_adj = x - xm;
|
||||
size_t deg = poly_deg[j];
|
||||
|
|
|
|||
|
|
@ -120,7 +120,7 @@ __expm1l (long double x)
|
|||
|
||||
/* Express x = ln 2 (k + remainder), remainder not exceeding 1/2. */
|
||||
xx = C1 + C2; /* ln 2. */
|
||||
px = __floorl (0.5 + x / xx);
|
||||
px = floorl (0.5 + x / xx);
|
||||
k = px;
|
||||
/* remainder times ln 2 */
|
||||
x -= px * C1;
|
||||
|
|
|
|||
|
|
@ -17,6 +17,7 @@
|
|||
License along with the GNU C Library; if not, see
|
||||
<http://www.gnu.org/licenses/>. */
|
||||
|
||||
#define NO_MATH_REDIRECT
|
||||
#include <math.h>
|
||||
#include <math_private.h>
|
||||
#include <math_ldbl_opt.h>
|
||||
|
|
|
|||
|
|
@ -47,7 +47,7 @@ __truncl (long double x)
|
|||
else
|
||||
{
|
||||
/* The high part is a nonzero integer. */
|
||||
lo = xh > 0 ? __floor (xl) : __ceil (xl);
|
||||
lo = xh > 0 ? floor (xl) : __ceil (xl);
|
||||
xh = hi;
|
||||
xl = lo;
|
||||
ldbl_canonicalize_int (&xh, &xl);
|
||||
|
|
|
|||
|
|
@ -221,11 +221,11 @@ sin_pi (long double x)
|
|||
* argument reduction, make sure inexact flag not raised if input
|
||||
* is an integer
|
||||
*/
|
||||
z = __floorl (y);
|
||||
z = floorl (y);
|
||||
if (z != y)
|
||||
{ /* inexact anyway */
|
||||
y *= 0.5;
|
||||
y = 2.0*(y - __floorl(y)); /* y = |x| mod 2.0 */
|
||||
y = 2.0*(y - floorl(y)); /* y = |x| mod 2.0 */
|
||||
n = (int) (y*4.0);
|
||||
}
|
||||
else
|
||||
|
|
|
|||
|
|
@ -316,7 +316,7 @@ __lgamma_negl (long double x, int *signgamp)
|
|||
{
|
||||
/* Determine the half-integer region X lies in, handle exact
|
||||
integers and determine the sign of the result. */
|
||||
int i = __floorl (-2 * x);
|
||||
int i = floorl (-2 * x);
|
||||
if ((i & 1) == 0 && i == -2 * x)
|
||||
return 1.0L / 0.0L;
|
||||
long double xn = ((i & 1) == 0 ? -i / 2 : (-i - 1) / 2);
|
||||
|
|
@ -333,7 +333,7 @@ __lgamma_negl (long double x, int *signgamp)
|
|||
approximations to an adjusted version of the gamma function. */
|
||||
if (i < 2)
|
||||
{
|
||||
int j = __floorl (-8 * x) - 16;
|
||||
int j = floorl (-8 * x) - 16;
|
||||
long double xm = (-33 - 2 * j) * 0.0625L;
|
||||
long double x_adj = x - xm;
|
||||
size_t deg = poly_deg[j];
|
||||
|
|
|
|||
|
|
@ -16,6 +16,7 @@
|
|||
License along with the GNU C Library. If not, see
|
||||
<http://www.gnu.org/licenses/>. */
|
||||
|
||||
#define NO_MATH_REDIRECT
|
||||
#include <math.h>
|
||||
|
||||
FLOAT
|
||||
|
|
|
|||
|
|
@ -97,26 +97,6 @@ __ieee754_sqrtf128 (_Float128 __x)
|
|||
__z; })
|
||||
# endif
|
||||
|
||||
# ifndef __floor
|
||||
# define __floor(x) \
|
||||
({ double __z; \
|
||||
__asm __volatile ( \
|
||||
" frim %0,%1\n" \
|
||||
: "=f" (__z) \
|
||||
: "f" (x)); \
|
||||
__z; })
|
||||
# endif
|
||||
# ifndef __floorf
|
||||
# define __floorf(x) \
|
||||
({ float __z; \
|
||||
__asm __volatile ( \
|
||||
" frim %0,%1\n" \
|
||||
" frsp %0,%0\n" \
|
||||
: "=f" (__z) \
|
||||
: "f" (x)); \
|
||||
__z; })
|
||||
# endif
|
||||
|
||||
#endif /* defined _ARCH_PWR5X */
|
||||
|
||||
#endif /* _PPC_MATH_PRIVATE_H_ */
|
||||
|
|
|
|||
|
|
@ -36,7 +36,7 @@ __modf (double x, double *iptr)
|
|||
|
||||
if (x >= 0.0)
|
||||
{
|
||||
*iptr = __floor (x);
|
||||
*iptr = floor (x);
|
||||
return __copysign (x - *iptr, x);
|
||||
}
|
||||
else
|
||||
|
|
|
|||
|
|
@ -35,7 +35,7 @@ __modff (float x, float *iptr)
|
|||
|
||||
if (x >= 0.0)
|
||||
{
|
||||
*iptr = __floorf (x);
|
||||
*iptr = floorf (x);
|
||||
return __copysignf (x - *iptr, x);
|
||||
}
|
||||
else
|
||||
|
|
|
|||
|
|
@ -16,6 +16,7 @@
|
|||
License along with the GNU C Library; if not, see
|
||||
<http://www.gnu.org/licenses/>. */
|
||||
|
||||
#define NO_MATH_REDIRECT
|
||||
#include <math.h>
|
||||
#include <math_ldbl_opt.h>
|
||||
#include <shlib-compat.h>
|
||||
|
|
|
|||
|
|
@ -16,6 +16,7 @@
|
|||
License along with the GNU C Library; if not, see
|
||||
<http://www.gnu.org/licenses/>. */
|
||||
|
||||
#define NO_MATH_REDIRECT
|
||||
#include <math.h>
|
||||
#include <math_ldbl_opt.h>
|
||||
#include <shlib-compat.h>
|
||||
|
|
|
|||
|
|
@ -16,6 +16,7 @@
|
|||
License along with the GNU C Library; if not, see
|
||||
<http://www.gnu.org/licenses/>. */
|
||||
|
||||
#define NO_MATH_REDIRECT
|
||||
#include <math.h>
|
||||
#include <math_ldbl_opt.h>
|
||||
#include <shlib-compat.h>
|
||||
|
|
|
|||
|
|
@ -16,6 +16,7 @@
|
|||
License along with the GNU C Library; if not, see
|
||||
<http://www.gnu.org/licenses/>. */
|
||||
|
||||
#define NO_MATH_REDIRECT
|
||||
#include <math.h>
|
||||
#include <math_ldbl_opt.h>
|
||||
#include <shlib-compat.h>
|
||||
|
|
|
|||
|
|
@ -16,6 +16,7 @@
|
|||
License along with the GNU C Library. If not, see
|
||||
<http://www.gnu.org/licenses/>. */
|
||||
|
||||
#define NO_MATH_REDIRECT
|
||||
#include <math.h>
|
||||
#include <math_private.h>
|
||||
#include <fenv_private.h>
|
||||
|
|
|
|||
|
|
@ -16,6 +16,7 @@
|
|||
License along with the GNU C Library. If not, see
|
||||
<http://www.gnu.org/licenses/>. */
|
||||
|
||||
#define NO_MATH_REDIRECT
|
||||
#include <math.h>
|
||||
#include <math_private.h>
|
||||
#include <fenv_private.h>
|
||||
|
|
|
|||
|
|
@ -16,6 +16,7 @@
|
|||
License along with the GNU C Library; if not, see
|
||||
<http://www.gnu.org/licenses/>. */
|
||||
|
||||
#define NO_MATH_REDIRECT
|
||||
#include <sparc-ifunc.h>
|
||||
#include <math.h>
|
||||
#include <libm-alias-double.h>
|
||||
|
|
|
|||
|
|
@ -16,6 +16,7 @@
|
|||
License along with the GNU C Library; if not, see
|
||||
<http://www.gnu.org/licenses/>. */
|
||||
|
||||
#define NO_MATH_REDIRECT
|
||||
#include <sparc-ifunc.h>
|
||||
#include <math.h>
|
||||
#include <libm-alias-float.h>
|
||||
|
|
|
|||
|
|
@ -27,30 +27,6 @@ __rintf (float d)
|
|||
# endif
|
||||
return res;
|
||||
}
|
||||
|
||||
extern __always_inline double
|
||||
__floor (double d)
|
||||
{
|
||||
double res;
|
||||
# if defined __AVX__ || defined SSE2AVX
|
||||
asm ("vroundsd $1, %1, %0, %0" : "=x" (res) : "xm" (d));
|
||||
# else
|
||||
asm ("roundsd $1, %1, %0" : "=x" (res) : "xm" (d));
|
||||
# endif
|
||||
return res;
|
||||
}
|
||||
|
||||
extern __always_inline float
|
||||
__floorf (float d)
|
||||
{
|
||||
float res;
|
||||
# if defined __AVX__ || defined SSE2AVX
|
||||
asm ("vroundss $1, %1, %0, %0" : "=x" (res) : "xm" (d));
|
||||
# else
|
||||
asm ("roundss $1, %1, %0" : "=x" (res) : "xm" (d));
|
||||
# endif
|
||||
return res;
|
||||
}
|
||||
#endif /* __SSE4_1__ */
|
||||
|
||||
#endif /* X86_64_MATH_PRIVATE_H */
|
||||
|
|
|
|||
|
|
@ -16,6 +16,7 @@
|
|||
License along with the GNU C Library; if not, see
|
||||
<http://www.gnu.org/licenses/>. */
|
||||
|
||||
#define NO_MATH_REDIRECT
|
||||
#include <libm-alias-double.h>
|
||||
|
||||
#define floor __redirect_floor
|
||||
|
|
|
|||
|
|
@ -16,6 +16,7 @@
|
|||
License along with the GNU C Library; if not, see
|
||||
<http://www.gnu.org/licenses/>. */
|
||||
|
||||
#define NO_MATH_REDIRECT
|
||||
#include <libm-alias-float.h>
|
||||
|
||||
#define floorf __redirect_floorf
|
||||
|
|
|
|||
Loading…
Reference in New Issue