d/freebsd-dev
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Use STRICT_ASSIGN() for exp2f() and exp2() instead of a volatile

Browse Source 
variable hack for exp2f() only.

The volatile variable had a surprisingly large cost for exp2f() -- 19
cycles or 15% on i386 in the worst case observed.  This is only partly
explained by there being several references to the variable, only one
of which benefited from it being volatile.  Arches that have working
assignment are likely to benefit even more from not having any volatile
variable.

exp2() now has a chance of working with extra precision on i386.

exp2() has even more references to the variable, so it would have been
pessimized more by simply declaring the variable as volatile.  Even
the temporary volatile variable for STRICT_ASSIGN costs 5-10% on i386,
(A64) so I will change STRICT_ASSIGN() to do an ordinary assignment
until i386 defaults to extra precision.
This commit is contained in:
Bruce Evans 2008-01-19 21:37:14 +00:00
parent fa7fdac725
commit 684217d889
Notes: svn2git 2020-12-20 02:59:44 +00:00 
svn path=/head/; revision=175501
2 changed files with 5 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
lib/msun/src/s_exp2.c
View File

@ -364,7 +364,7 @@ exp2(double x)
}
/* Reduce x, computing z, i0, and k. */
t = x + redux;
STRICT_ASSIGN(double, t, x + redux);
GET_LOW_WORD(i0, t);
i0 += TBLSIZE / 2;
k = (i0 >> TBLBITS) << 20;

7
lib/msun/src/s_exp2f.c
View File

@ -27,6 +27,8 @@
#include <sys/cdefs.h>
__FBSDID("$FreeBSD$");
#include <float.h>
#include "math.h"
#include "math_private.h"
@ -91,8 +93,7 @@ float
exp2f(float x)
{
double tv;
float r, z;
volatile float t; /* prevent gcc from using too much precision */
float r, t, z;
uint32_t hx, hr, ix, i0;
int32_t k;
@ -115,7 +116,7 @@ exp2f(float x)
}
/* Reduce x, computing z, i0, and k. */
t = x + redux;
STRICT_ASSIGN(float, t, x + redux);
GET_FLOAT_WORD(i0, t);
i0 += TBLSIZE / 2;
k = (i0 >> TBLBITS) << 23;