mirror of
https://sourceware.org/git/glibc.git
synced 2025-01-09 19:00:08 +00:00
[PATCH 5/7] sin/cos slow paths: remove unused slowpath functions
Remove all unused slowpath functions. * sysdeps/ieee754/dbl-64/s_sin.c (TAYLOR_SLOW): Remove. (do_cos_slow): Likewise. (do_sin_slow): Likewise. (reduce_and_compute): Likewise. (slow): Likewise. (slow1): Likewise. (slow2): Likewise. (sloww): Likewise. (sloww1): Likewise. (sloww2): Likewise. (bslow): Likewise. (bslow1): Likewise. (bslow2): Likewise. (cslow2): Likewise.
This commit is contained in:
Wilco Dijkstra
parent
649095838b
commit
72f6e9a3e3
17
ChangeLog
17
ChangeLog
@ -1,3 +1,20 @@
|
||||
2018-04-03 Wilco Dijkstra <wdijkstr@arm.com>
|
||||
|
||||
* sysdeps/ieee754/dbl-64/s_sin.c (TAYLOR_SLOW): Remove.
|
||||
(do_cos_slow): Likewise.
|
||||
(do_sin_slow): Likewise.
|
||||
(reduce_and_compute): Likewise.
|
||||
(slow): Likewise.
|
||||
(slow1): Likewise.
|
||||
(slow2): Likewise.
|
||||
(sloww): Likewise.
|
||||
(sloww1): Likewise.
|
||||
(sloww2): Likewise.
|
||||
(bslow): Likewise.
|
||||
(bslow1): Likewise.
|
||||
(bslow2): Likewise.
|
||||
(cslow2): Likewise.
|
||||
|
||||
2018-04-03 Wilco Dijkstra <wdijkstr@arm.com>
|
||||
|
||||
* sysdeps/ieee754/dbl-64/s_sin.c (TAYLOR_SIN): Remove cor parameter.
|
||||
|
||||
@ -22,22 +22,11 @@
|
||||
/* */
|
||||
/* FUNCTIONS: usin */
|
||||
/* ucos */
|
||||
/* slow */
|
||||
/* slow1 */
|
||||
/* slow2 */
|
||||
/* sloww */
|
||||
/* sloww1 */
|
||||
/* sloww2 */
|
||||
/* bsloww */
|
||||
/* bsloww1 */
|
||||
/* bsloww2 */
|
||||
/* cslow2 */
|
||||
/* FILES NEEDED: dla.h endian.h mpa.h mydefs.h usncs.h */
|
||||
/* branred.c sincos32.c dosincos.c mpa.c */
|
||||
/* sincos.tbl */
|
||||
/* branred.c sincos.tbl */
|
||||
/* */
|
||||
/* An ultimate sin and routine. Given an IEEE double machine number x */
|
||||
/* it computes the correctly rounded (to nearest) value of sin(x) or cos(x) */
|
||||
/* An ultimate sin and cos routine. Given an IEEE double machine number x */
|
||||
/* it computes sin(x) or cos(x) with ~0.55 ULP. */
|
||||
/* Assumption: Machine arithmetic operations are performed in */
|
||||
/* round to nearest mode of IEEE 754 standard. */
|
||||
/* */
|
||||
@ -74,29 +63,6 @@
|
||||
res; \
|
||||
})
|
||||
|
||||
/* This is again a variation of the Taylor series expansion with the term
|
||||
x^3/3! expanded into the following for better accuracy:
|
||||
|
||||
bb * x ^ 3 + 3 * aa * x * x1 * x2 + aa * x1 ^ 3 + aa * x2 ^ 3
|
||||
|
||||
The correction term is dx and bb + aa = -1/3!
|
||||
*/
|
||||
#define TAYLOR_SLOW(x0, dx, cor) \
|
||||
({ \
|
||||
static const double th2_36 = 206158430208.0; /* 1.5*2**37 */ \
|
||||
double xx = (x0) * (x0); \
|
||||
double x1 = ((x0) + th2_36) - th2_36; \
|
||||
double y = aa * x1 * x1 * x1; \
|
||||
double r = (x0) + y; \
|
||||
double x2 = ((x0) - x1) + (dx); \
|
||||
double t = (((POLYNOMIAL2 (xx) + bb) * xx + 3.0 * aa * x1 * x2) \
|
||||
* (x0) + aa * x2 * x2 * x2 + (dx)); \
|
||||
t = (((x0) - r) + y) + t; \
|
||||
double res = r + t; \
|
||||
(cor) = (r - res) + t; \
|
||||
res; \
|
||||
})
|
||||
|
||||
#define SINCOS_TABLE_LOOKUP(u, sn, ssn, cs, ccs) \
|
||||
({ \
|
||||
int4 k = u.i[LOW_HALF] << 2; \
|
||||
@ -123,23 +89,7 @@ static const double
|
||||
cs4 = -4.16666666666664434524222570944589E-02,
|
||||
cs6 = 1.38888874007937613028114285595617E-03;
|
||||
|
||||
static const double t22 = 0x1.8p22;
|
||||
|
||||
void __dubsin (double x, double dx, double w[]);
|
||||
void __docos (double x, double dx, double w[]);
|
||||
double __mpsin (double x, double dx, bool reduce_range);
|
||||
double __mpcos (double x, double dx, bool reduce_range);
|
||||
static double slow (double x);
|
||||
static double slow1 (double x);
|
||||
static double slow2 (double x);
|
||||
static double sloww (double x, double dx, double orig, bool shift_quadrant);
|
||||
static double sloww1 (double x, double dx, double orig, bool shift_quadrant);
|
||||
static double sloww2 (double x, double dx, double orig, int n);
|
||||
static double bsloww (double x, double dx, double orig, int n);
|
||||
static double bsloww1 (double x, double dx, double orig, int n);
|
||||
static double bsloww2 (double x, double dx, double orig, int n);
|
||||
int __branred (double x, double *a, double *aa);
|
||||
static double cslow2 (double x);
|
||||
|
||||
/* Given a number partitioned into X and DX, this function computes the cosine
|
||||
of the number by combining the sin and cos of X (as computed by a variation
|
||||
@ -166,40 +116,6 @@ do_cos (double x, double dx)
|
||||
return cs + cor;
|
||||
}
|
||||
|
||||
/* A more precise variant of DO_COS. EPS is the adjustment to the correction
|
||||
COR. */
|
||||
static inline double
|
||||
__always_inline
|
||||
do_cos_slow (double x, double dx, double eps, double *corp)
|
||||
{
|
||||
mynumber u;
|
||||
|
||||
if (x <= 0)
|
||||
dx = -dx;
|
||||
|
||||
u.x = big + fabs (x);
|
||||
x = fabs (x) - (u.x - big);
|
||||
|
||||
double xx, y, x1, x2, e1, e2, res, cor;
|
||||
double s, sn, ssn, c, cs, ccs;
|
||||
xx = x * x;
|
||||
s = x * xx * (sn3 + xx * sn5);
|
||||
c = x * dx + xx * (cs2 + xx * (cs4 + xx * cs6));
|
||||
SINCOS_TABLE_LOOKUP (u, sn, ssn, cs, ccs);
|
||||
x1 = (x + t22) - t22;
|
||||
x2 = (x - x1) + dx;
|
||||
e1 = (sn + t22) - t22;
|
||||
e2 = (sn - e1) + ssn;
|
||||
cor = (ccs - cs * c - e1 * x2 - e2 * x) - sn * s;
|
||||
y = cs - e1 * x1;
|
||||
cor = cor + ((cs - y) - e1 * x1);
|
||||
res = y + cor;
|
||||
cor = (y - res) + cor;
|
||||
cor = 1.0005 * cor + __copysign (eps, cor);
|
||||
*corp = cor;
|
||||
return res;
|
||||
}
|
||||
|
||||
/* Given a number partitioned into X and DX, this function computes the sine of
|
||||
the number by combining the sin and cos of X (as computed by a variation of
|
||||
the Taylor series) with the values looked up from the sin/cos table to get
|
||||
@ -224,70 +140,6 @@ do_sin (double x, double dx)
|
||||
return sn + cor;
|
||||
}
|
||||
|
||||
/* A more precise variant of DO_SIN. EPS is the adjustment to the correction
|
||||
COR. */
|
||||
static inline double
|
||||
__always_inline
|
||||
do_sin_slow (double x, double dx, double eps, double *corp)
|
||||
{
|
||||
mynumber u;
|
||||
|
||||
if (x <= 0)
|
||||
dx = -dx;
|
||||
u.x = big + fabs (x);
|
||||
x = fabs (x) - (u.x - big);
|
||||
|
||||
double xx, y, x1, x2, c1, c2, res, cor;
|
||||
double s, sn, ssn, c, cs, ccs;
|
||||
xx = x * x;
|
||||
s = x * xx * (sn3 + xx * sn5);
|
||||
c = xx * (cs2 + xx * (cs4 + xx * cs6));
|
||||
SINCOS_TABLE_LOOKUP (u, sn, ssn, cs, ccs);
|
||||
x1 = (x + t22) - t22;
|
||||
x2 = (x - x1) + dx;
|
||||
c1 = (cs + t22) - t22;
|
||||
c2 = (cs - c1) + ccs;
|
||||
cor = (ssn + s * ccs + cs * s + c2 * x + c1 * x2 - sn * x * dx) - sn * c;
|
||||
y = sn + c1 * x1;
|
||||
cor = cor + ((sn - y) + c1 * x1);
|
||||
res = y + cor;
|
||||
cor = (y - res) + cor;
|
||||
cor = 1.0005 * cor + __copysign (eps, cor);
|
||||
*corp = cor;
|
||||
return res;
|
||||
}
|
||||
|
||||
/* Reduce range of X and compute sin of a + da. When SHIFT_QUADRANT is true,
|
||||
the routine returns the cosine of a + da by rotating the quadrant once and
|
||||
computing the sine of the result. */
|
||||
static inline double
|
||||
__always_inline
|
||||
reduce_and_compute (double x, bool shift_quadrant)
|
||||
{
|
||||
double retval = 0, a, da;
|
||||
unsigned int n = __branred (x, &a, &da);
|
||||
int4 k = (n + shift_quadrant) % 4;
|
||||
switch (k)
|
||||
{
|
||||
case 2:
|
||||
a = -a;
|
||||
da = -da;
|
||||
/* Fall through. */
|
||||
case 0:
|
||||
if (a * a < 0.01588)
|
||||
retval = bsloww (a, da, x, n);
|
||||
else
|
||||
retval = bsloww1 (a, da, x, n);
|
||||
break;
|
||||
|
||||
case 1:
|
||||
case 3:
|
||||
retval = bsloww2 (a, da, x, n);
|
||||
break;
|
||||
}
|
||||
return retval;
|
||||
}
|
||||
|
||||
/* Reduce range of x to within PI/2 with abs (x) < 105414350. The high part
|
||||
is written to *a, the low part to *da. Range reduction is accurate to 136
|
||||
bits so that when x is large and *a very close to zero, all 53 bits of *a
|
||||
@ -508,299 +360,6 @@ __cos (double x)
|
||||
return retval;
|
||||
}
|
||||
|
||||
/************************************************************************/
|
||||
/* Routine compute sin(x) for 2^-26 < |x|< 0.25 by Taylor with more */
|
||||
/* precision and if still doesn't accurate enough by mpsin or dubsin */
|
||||
/************************************************************************/
|
||||
|
||||
static inline double
|
||||
__always_inline
|
||||
slow (double x)
|
||||
{
|
||||
double res, cor, w[2];
|
||||
res = TAYLOR_SLOW (x, 0, cor);
|
||||
if (res == res + 1.0007 * cor)
|
||||
return res;
|
||||
|
||||
__dubsin (fabs (x), 0, w);
|
||||
if (w[0] == w[0] + 1.000000001 * w[1])
|
||||
return __copysign (w[0], x);
|
||||
|
||||
return __copysign (__mpsin (fabs (x), 0, false), x);
|
||||
}
|
||||
|
||||
/*******************************************************************************/
|
||||
/* Routine compute sin(x) for 0.25<|x|< 0.855469 by __sincostab.tbl and Taylor */
|
||||
/* and if result still doesn't accurate enough by mpsin or dubsin */
|
||||
/*******************************************************************************/
|
||||
|
||||
static inline double
|
||||
__always_inline
|
||||
slow1 (double x)
|
||||
{
|
||||
double w[2], cor, res;
|
||||
|
||||
res = do_sin_slow (x, 0, 0, &cor);
|
||||
if (res == res + cor)
|
||||
return res;
|
||||
|
||||
__dubsin (fabs (x), 0, w);
|
||||
if (w[0] == w[0] + 1.000000005 * w[1])
|
||||
return w[0];
|
||||
|
||||
return __mpsin (fabs (x), 0, false);
|
||||
}
|
||||
|
||||
/**************************************************************************/
|
||||
/* Routine compute sin(x) for 0.855469 <|x|<2.426265 by __sincostab.tbl */
|
||||
/* and if result still doesn't accurate enough by mpsin or dubsin */
|
||||
/**************************************************************************/
|
||||
static inline double
|
||||
__always_inline
|
||||
slow2 (double x)
|
||||
{
|
||||
double w[2], y, y1, y2, cor, res;
|
||||
|
||||
double t = hp0 - fabs (x);
|
||||
res = do_cos_slow (t, hp1, 0, &cor);
|
||||
if (res == res + cor)
|
||||
return res;
|
||||
|
||||
y = fabs (x) - hp0;
|
||||
y1 = y - hp1;
|
||||
y2 = (y - y1) - hp1;
|
||||
__docos (y1, y2, w);
|
||||
if (w[0] == w[0] + 1.000000005 * w[1])
|
||||
return w[0];
|
||||
|
||||
return __mpsin (fabs (x), 0, false);
|
||||
}
|
||||
|
||||
/* Compute sin(x + dx) where X is small enough to use Taylor series around zero
|
||||
and (x + dx) in the first or third quarter of the unit circle. ORIG is the
|
||||
original value of X for computing error of the result. If the result is not
|
||||
accurate enough, the routine calls mpsin or dubsin. SHIFT_QUADRANT rotates
|
||||
the unit circle by 1 to compute the cosine instead of sine. */
|
||||
static inline double
|
||||
__always_inline
|
||||
sloww (double x, double dx, double orig, bool shift_quadrant)
|
||||
{
|
||||
double y, t, res, cor, w[2], a, da, xn;
|
||||
mynumber v;
|
||||
int4 n;
|
||||
res = TAYLOR_SLOW (x, dx, cor);
|
||||
|
||||
double eps = fabs (orig) * 3.1e-30;
|
||||
|
||||
cor = 1.0005 * cor + __copysign (eps, cor);
|
||||
|
||||
if (res == res + cor)
|
||||
return res;
|
||||
|
||||
a = fabs (x);
|
||||
da = (x > 0) ? dx : -dx;
|
||||
__dubsin (a, da, w);
|
||||
eps = fabs (orig) * 1.1e-30;
|
||||
cor = 1.000000001 * w[1] + __copysign (eps, w[1]);
|
||||
|
||||
if (w[0] == w[0] + cor)
|
||||
return __copysign (w[0], x);
|
||||
|
||||
t = (orig * hpinv + toint);
|
||||
xn = t - toint;
|
||||
v.x = t;
|
||||
y = (orig - xn * mp1) - xn * mp2;
|
||||
n = (v.i[LOW_HALF] + shift_quadrant) & 3;
|
||||
da = xn * pp3;
|
||||
t = y - da;
|
||||
da = (y - t) - da;
|
||||
y = xn * pp4;
|
||||
a = t - y;
|
||||
da = ((t - a) - y) + da;
|
||||
|
||||
if (n & 2)
|
||||
{
|
||||
a = -a;
|
||||
da = -da;
|
||||
}
|
||||
x = fabs (a);
|
||||
dx = (a > 0) ? da : -da;
|
||||
__dubsin (x, dx, w);
|
||||
eps = fabs (orig) * 1.1e-40;
|
||||
cor = 1.000000001 * w[1] + __copysign (eps, w[1]);
|
||||
|
||||
if (w[0] == w[0] + cor)
|
||||
return __copysign (w[0], a);
|
||||
|
||||
return shift_quadrant ? __mpcos (orig, 0, true) : __mpsin (orig, 0, true);
|
||||
}
|
||||
|
||||
/* Compute sin(x + dx) where X is in the first or third quarter of the unit
|
||||
circle. ORIG is the original value of X for computing error of the result.
|
||||
If the result is not accurate enough, the routine calls mpsin or dubsin.
|
||||
SHIFT_QUADRANT rotates the unit circle by 1 to compute the cosine instead of
|
||||
sine. */
|
||||
static inline double
|
||||
__always_inline
|
||||
sloww1 (double x, double dx, double orig, bool shift_quadrant)
|
||||
{
|
||||
double w[2], cor, res;
|
||||
|
||||
res = do_sin_slow (x, dx, 3.1e-30 * fabs (orig), &cor);
|
||||
|
||||
if (res == res + cor)
|
||||
return __copysign (res, x);
|
||||
|
||||
dx = (x > 0 ? dx : -dx);
|
||||
__dubsin (fabs (x), dx, w);
|
||||
|
||||
double eps = 1.1e-30 * fabs (orig);
|
||||
cor = 1.000000005 * w[1] + __copysign (eps, w[1]);
|
||||
|
||||
if (w[0] == w[0] + cor)
|
||||
return __copysign (w[0], x);
|
||||
|
||||
return shift_quadrant ? __mpcos (orig, 0, true) : __mpsin (orig, 0, true);
|
||||
}
|
||||
|
||||
/***************************************************************************/
|
||||
/* Routine compute sin(x+dx) (Double-Length number) where x in second or */
|
||||
/* fourth quarter of unit circle.Routine receive also the original value */
|
||||
/* and quarter(n= 1or 3)of x for computing error of result.And if result not*/
|
||||
/* accurate enough routine calls mpsin1 or dubsin */
|
||||
/***************************************************************************/
|
||||
|
||||
static inline double
|
||||
__always_inline
|
||||
sloww2 (double x, double dx, double orig, int n)
|
||||
{
|
||||
double w[2], cor, res;
|
||||
|
||||
res = do_cos_slow (x, dx, 3.1e-30 * fabs (orig), &cor);
|
||||
|
||||
if (res == res + cor)
|
||||
return (n & 2) ? -res : res;
|
||||
|
||||
dx = x > 0 ? dx : -dx;
|
||||
__docos (fabs (x), dx, w);
|
||||
|
||||
double eps = 1.1e-30 * fabs (orig);
|
||||
cor = 1.000000005 * w[1] + __copysign (eps, w[1]);
|
||||
|
||||
if (w[0] == w[0] + cor)
|
||||
return (n & 2) ? -w[0] : w[0];
|
||||
|
||||
return (n & 1) ? __mpsin (orig, 0, true) : __mpcos (orig, 0, true);
|
||||
}
|
||||
|
||||
/***************************************************************************/
|
||||
/* Routine compute sin(x+dx) or cos(x+dx) (Double-Length number) where x */
|
||||
/* is small enough to use Taylor series around zero and (x+dx) */
|
||||
/* in first or third quarter of unit circle.Routine receive also */
|
||||
/* (right argument) the original value of x for computing error of */
|
||||
/* result.And if result not accurate enough routine calls other routines */
|
||||
/***************************************************************************/
|
||||
|
||||
static inline double
|
||||
__always_inline
|
||||
bsloww (double x, double dx, double orig, int n)
|
||||
{
|
||||
double res, cor, w[2], a, da;
|
||||
|
||||
res = TAYLOR_SLOW (x, dx, cor);
|
||||
cor = 1.0005 * cor + __copysign (1.1e-24, cor);
|
||||
if (res == res + cor)
|
||||
return res;
|
||||
|
||||
a = fabs (x);
|
||||
da = (x > 0) ? dx : -dx;
|
||||
__dubsin (a, da, w);
|
||||
cor = 1.000000001 * w[1] + __copysign (1.1e-24, w[1]);
|
||||
|
||||
if (w[0] == w[0] + cor)
|
||||
return __copysign (w[0], x);
|
||||
|
||||
return (n & 1) ? __mpcos (orig, 0, true) : __mpsin (orig, 0, true);
|
||||
}
|
||||
|
||||
/***************************************************************************/
|
||||
/* Routine compute sin(x+dx) or cos(x+dx) (Double-Length number) where x */
|
||||
/* in first or third quarter of unit circle.Routine receive also */
|
||||
/* (right argument) the original value of x for computing error of result.*/
|
||||
/* And if result not accurate enough routine calls other routines */
|
||||
/***************************************************************************/
|
||||
|
||||
static inline double
|
||||
__always_inline
|
||||
bsloww1 (double x, double dx, double orig, int n)
|
||||
{
|
||||
double w[2], cor, res;
|
||||
|
||||
res = do_sin_slow (x, dx, 1.1e-24, &cor);
|
||||
if (res == res + cor)
|
||||
return (x > 0) ? res : -res;
|
||||
|
||||
dx = (x > 0) ? dx : -dx;
|
||||
__dubsin (fabs (x), dx, w);
|
||||
|
||||
cor = 1.000000005 * w[1] + __copysign (1.1e-24, w[1]);
|
||||
|
||||
if (w[0] == w[0] + cor)
|
||||
return __copysign (w[0], x);
|
||||
|
||||
return (n & 1) ? __mpcos (orig, 0, true) : __mpsin (orig, 0, true);
|
||||
}
|
||||
|
||||
/***************************************************************************/
|
||||
/* Routine compute sin(x+dx) or cos(x+dx) (Double-Length number) where x */
|
||||
/* in second or fourth quarter of unit circle.Routine receive also the */
|
||||
/* original value and quarter(n= 1or 3)of x for computing error of result. */
|
||||
/* And if result not accurate enough routine calls other routines */
|
||||
/***************************************************************************/
|
||||
|
||||
static inline double
|
||||
__always_inline
|
||||
bsloww2 (double x, double dx, double orig, int n)
|
||||
{
|
||||
double w[2], cor, res;
|
||||
|
||||
res = do_cos_slow (x, dx, 1.1e-24, &cor);
|
||||
if (res == res + cor)
|
||||
return (n & 2) ? -res : res;
|
||||
|
||||
dx = (x > 0) ? dx : -dx;
|
||||
__docos (fabs (x), dx, w);
|
||||
|
||||
cor = 1.000000005 * w[1] + __copysign (1.1e-24, w[1]);
|
||||
|
||||
if (w[0] == w[0] + cor)
|
||||
return (n & 2) ? -w[0] : w[0];
|
||||
|
||||
return (n & 1) ? __mpsin (orig, 0, true) : __mpcos (orig, 0, true);
|
||||
}
|
||||
|
||||
/************************************************************************/
|
||||
/* Routine compute cos(x) for 2^-27 < |x|< 0.25 by Taylor with more */
|
||||
/* precision and if still doesn't accurate enough by mpcos or docos */
|
||||
/************************************************************************/
|
||||
|
||||
static inline double
|
||||
__always_inline
|
||||
cslow2 (double x)
|
||||
{
|
||||
double w[2], cor, res;
|
||||
|
||||
res = do_cos_slow (x, 0, 0, &cor);
|
||||
if (res == res + cor)
|
||||
return res;
|
||||
|
||||
__docos (fabs (x), 0, w);
|
||||
if (w[0] == w[0] + 1.000000005 * w[1])
|
||||
return w[0];
|
||||
|
||||
return __mpcos (x, 0, false);
|
||||
}
|
||||
|
||||
#ifndef __cos
|
||||
libm_alias_double (__cos, cos)
|
||||
#endif
|
||||
|
||||
Loading…
Reference in New Issue
Block a user