From:	"Alexei A. Frounze" <alex DOT fru AT mtu-net DOT ru>
Newsgroups:	comp.os.msdos.djgpp
Subject:	Re: inefficiency of GCC output code & -O problem
Date:	Wed, 19 Apr 2000 19:57:48 +0400
Organization:	MTU-Intel ISP
Lines:	32
Message-ID:	<38FDD77C.34F9E065@mtu-net.ru>
References:	<Pine DOT SUN DOT 3 DOT 91 DOT 1000419094240 DOT 10023G-100000 AT is>
NNTP-Posting-Host:	ppp103-64.dialup.mtu-net.ru
Mime-Version:	1.0
X-Trace:	gavrilo.mtu.ru 956163956 29012 212.188.103.64 (19 Apr 2000 17:05:56 GMT)
X-Complaints-To:	usenet-abuse AT mtu DOT ru
NNTP-Posting-Date:	19 Apr 2000 17:05:56 GMT
X-Mailer:	Mozilla 4.72 [en] (Win95; I)
X-Accept-Language:	en,ru
To:	djgpp AT delorie DOT com
DJ-Gateway:	from newsgroup comp.os.msdos.djgpp
Reply-To:	djgpp AT delorie DOT com

Eli Zaretskii wrote:
> 
> On Tue, 18 Apr 2000, Alexei A. Frounze wrote:
> 
> > Cyrix 6x86.
> > Originally it was P266, but something burnt out and now it doesn't work on
> > frequencies higher than 133MHz anymore. IMHO a good CPU
> 
> It's not a question of ``good'' or ``bad''.  Cyrix is different from
> K6.  In particular, K6 is known to write to memory very fast, but read
> much slower (or the other way around, I don't remember).  It's also
> much more sensitive to alignment of data and code.

I simply told that in order to mention that it's not a Ciryx 6x86 P266 and Cyrix
P133. It's something new now. :)

> Since you asked what might be the cause of different behavior of the
> same code, I was suggesting that one of the differences between
> processors is the reason for the different effects of changes in code
> on performance.

So then the division trick is better for most of the CPUs, since the inline ASM
with this division doesn't make the code noticable slow. It makes it faster. My
computer/CPU is the example.

bye.
Alexei A. Frounze
-----------------------------------------
Homepage: http://alexfru.chat.ru
Mirror:   http://members.xoom.com/alexfru

- Raw text -