From:	Robert Hoehne <Robert DOT Hoehne AT Mathematik DOT tu-chemnitz DOT de>
Newsgroups:	comp.os.msdos.djgpp
Subject:	Re: Interesting benchmark results
Date:	Mon, 10 Mar 1997 11:19:18 +0100
Organization:	TU Chemnitz-Zwickau
Lines:	34
Message-ID:	<3323E026.6C0B@Mathematik.tu-chemnitz.de>
References:	<Pine DOT SUN DOT 3 DOT 91 DOT 970309180414 DOT 26812U-100000 AT is>
NNTP-Posting-Host:	daemon.hrz.tu-chemnitz.de
Mime-Version:	1.0
To:	djgpp AT delorie DOT com
DJ-Gateway:	from newsgroup comp.os.msdos.djgpp

OK, I will write here also some remarks from me
about the optimizations and benchmarks.

In my opinion, benchmarks are in most cases can be
compared with games, just for fun. If you want
to see the results of different optimization levels
you shoud use a real program for testing the
speed (not checking somly some loops or so on).

For instance for me I saw the following:

The editor of RHIDE can be build also as an
standalone editor and has there an option, to
profile itself (it scrolls automaticaly an
opened editor from the beginning to the end and
stops the time for it).

I have tested mostly everything with all the
optimization switches and found, that the best
speed is reached with simply '-O2' and nothing
else.

I have tried also '-m486' which blowed up 
the exe size and slowed down the excution
time.

Robert
-- 
*****************************************************************
* Robert Hoehne, Fakultaet fuer Mathematik, TU-Chemnitz-Zwickau *
* Post:    Am Berg 3, D-09573 Dittmannsdorf                     *
* e-Mail:  Robert DOT Hoehne AT Mathematik DOT TU-Chemnitz DOT DE              *
* WWW:     http://www.tu-chemnitz.de/~rho                       *
*****************************************************************

- Raw text -