Date: Sun, 31 Dec 2000 12:31:52 +0200
From: "Eli Zaretskii" <eliz AT is DOT elta DOT co DOT il>
Sender: halo1 AT zahav DOT net DOT il
To: "Tom ST Denis" <tstdenis3160 AT home DOT com>
Message-Id: <7704-Sun31Dec2000123152+0200-eliz@is.elta.co.il>
X-Mailer: Emacs 20.6 (via feedmail 8.3.emacs20_6 I) and Blat ver 1.8.6
CC: djgpp AT delorie DOT com
In-reply-to: <f_v36.53630$59.14770834@news3.rdc1.on.home.com>
	(tstdenis3160 AT home DOT com)
Subject: Re: Support for higher end cpus
References:  <f_v36.53630$59 DOT 14770834 AT news3 DOT rdc1 DOT on DOT home DOT com>
Reply-To: djgpp AT delorie DOT com
Errors-To: nobody AT delorie DOT com
X-Mailing-List: djgpp AT delorie DOT com
X-Unsubscribes-To: listserv AT delorie DOT com
Precedence: bulk

> From: "Tom ST Denis" <tstdenis3160 AT home DOT com>
> Newsgroups: comp.os.msdos.djgpp
> Date: Sun, 31 Dec 2000 01:29:47 GMT
> 
> I know (from my earlier post) that DJGPP can understand switches such
> as -march=k6 or -march=i686 but the code it produces doesn't seem to be any
> faster (substantially anyways) then -march=i486.  The output code *is*
> different just not improved.

I think you need to take up this issue with the GCC developers.  DJGPP
simply uses the latest GCC version, there are now DJGPP-specific
optimization switches.

> My basis for this judgement is my compilation of Allegro and my updated
> Plush lib.  I get about the same FPS in my Plush examples when I use
> march=k6 (on my Athlon) then I do with march=i486.

I don't know how well can you test compiler optimizations with
graphics libraries.  It's possible that some hardware-related code is
eating most of the cycles.