Rearrange the polynomial evaluation for better parallelism. This

saves an average of about 8 cycles or 5% on A64 (amd64 and i386 --
more in cycles but about the same percentage on i386, and more with
old versions of gcc) with good CFLAGS and some parallelism in the
caller.  As usual, it takes a couple more multiplications so it will
be slower on old machines.

Convert to __FBSDID().
This commit is contained in:
bde 2008-02-19 12:54:14 +00:00
parent 2aa5a61fd3
commit e508bf1279
2 changed files with 9 additions and 9 deletions

View File

@ -11,9 +11,8 @@
* ====================================================
*/
#ifndef lint
static char rcsid[] = "$FreeBSD$";
#endif
#include <sys/cdefs.h>
__FBSDID("$FreeBSD$");
/*
* __kernel_cos( x, y )
@ -72,7 +71,8 @@ __kernel_cos(double x, double y)
double hz,z,r,w;
z = x*x;
r = z*(C1+z*(C2+z*(C3+z*(C4+z*(C5+z*C6)))));
w = z*z;
r = z*(C1+z*(C2+z*C3)) + w*w*(C4+z*(C5+z*C6));
hz = 0.5*z;
w = one-hz;
return w + (((one-w)-hz) + (z*r-x*y));

View File

@ -11,9 +11,8 @@
* ====================================================
*/
#ifndef lint
static char rcsid[] = "$FreeBSD$";
#endif
#include <sys/cdefs.h>
__FBSDID("$FreeBSD$");
/* __kernel_sin( x, y, iy)
* kernel sin function on ~[-pi/4, pi/4] (except on -0), pi/4 ~ 0.7854
@ -60,11 +59,12 @@ S6 = 1.58969099521155010221e-10; /* 0x3DE5D93A, 0x5ACFD57C */
double
__kernel_sin(double x, double y, int iy)
{
double z,r,v;
double z,r,v,w;
z = x*x;
w = z*z;
r = S2+z*(S3+z*S4) + z*w*(S5+z*S6);
v = z*x;
r = S2+z*(S3+z*(S4+z*(S5+z*S6)));
if(iy==0) return x+v*(S1+z*r);
else return x-((z*(half*y-v*r)-y)-v*S1);
}