Rearrange the inner loop of scanc() to get better code on i*86's
(on an i486, 10 cycles (+ cache misses) instead of 15). The change should be a no-op if the compiler is any good. The best possible i*86 code for the same algorithm is only 1 more cycle faster on i486's so I don't want to bother implementing an assembler version. scanc() is a bottleneck for OPOST processing. It is naturally about 4 times as slow as bcopy() on 32-bit systems.
This commit is contained in:
parent
d800e06858
commit
5182dcbec2
Notes:
svn2git
2020-12-20 02:59:44 +00:00
svn path=/head/; revision=9485
@ -32,7 +32,7 @@
|
||||
*
|
||||
* @(#)scanc.c 8.1 (Berkeley) 6/10/93
|
||||
*
|
||||
* $Id: scanc.c,v 1.2 1994/08/02 07:44:27 davidg Exp $
|
||||
* $Id: scanc.c,v 1.3 1995/03/17 06:15:39 phk Exp $
|
||||
*/
|
||||
|
||||
#include <sys/libkern.h>
|
||||
@ -47,6 +47,14 @@ scanc(size, cp, table, mask0)
|
||||
register u_char mask;
|
||||
|
||||
mask = mask0;
|
||||
for (end = &cp[size]; cp < end && (table[*cp] & mask) == 0; ++cp);
|
||||
for (end = &cp[size]; cp < end; ++cp) {
|
||||
/*
|
||||
* gcc-2.6.3 generates poor (un)sign extension code on i386's.
|
||||
* The cast to volatile should have no effect, but in fact it
|
||||
* improves the code on i386's.
|
||||
*/
|
||||
if (table[*(volatile u_char *)cp] & mask)
|
||||
break;
|
||||
}
|
||||
return (end - cp);
|
||||
}
|
||||
|
Loading…
Reference in New Issue
Block a user