Compiler optimization (was: 8086 (was Re: more talking to the press.))

From: Hans Franke <Hans.Franke_at_mch20.sbs.de>
Date: Fri Nov 14 14:46:45 2003

Am 14 Nov 2003 21:39 meinte Fred N. van Kempen:

> On Fri, 14 Nov 2003, Hans Franke wrote:
> > Would be great, I still haven't seen one like that.
> > And just let me guess, it'll replace it by a REP STOSB,
> > and not use STOSW or try to allign the REP to 16 Bit borders...
> Yeah, I've seen them translate to STOSB, probably ebcause the
> C code was using a 'char *'... never tried using that with a
> 'short *', now I come to think of it.

It almost doubles the speed, of course, if it's an odd
number of bytes, you need one additional STOSB before
(or after, depending if the initial address was even or
odd). I'm getting courious about the optimizations your
compiler does. I loved the string operations, since
they are the closest stuff to caracter operations on a
mainframe, and I know most compilers had a real problem
using them.

Gruss
H.
--
VCF Europa 5.0 am 01./02. Mai 2004 in Muenchen
http://www.vcfe.org/
Received on Fri Nov 14 2003 - 14:46:45 GMT

This archive was generated by hypermail 2.3.0 : Fri Oct 10 2014 - 23:36:19 BST