cvs.gedasymbols.org/archives/browse.cgi   search  
Mail Archives: djgpp/1997/06/12/18:49:47

From: leathm AT solwarra DOT gbrmpa DOT gov DOT au (Leath Muller)
Message-Id: <199706122247.IAA03169@solwarra.gbrmpa.gov.au>
Subject: Re: Weird Results Tesitng Allegro's Performance
To: bryan DOT murphy AT hcst DOT com (Bryan Murphy)
Date: Fri, 13 Jun 1997 08:47:36 +1000 (EST)
Cc: djgpp AT delorie DOT com
In-Reply-To: <c=US%a=_%p=Hassler_Communic%l=DAISY-970612132431Z-180@daisy.hcst.com> from "Bryan Murphy" at Jun 12, 97 09:24:31 am

> Yeah, the VGA was standard 320x200, the rest was 640x480.  
> What I don't understand is why the Linear Frame Buffer is slower
> than the Banked Mode!  What's up with that?  You don't need to
> change the banks when using the LFB, so it technically should
> be quicker.  Weird...

Maybe the card runs faster when you are moving data to the DOS address
space due to some hardware mods... Its been a while since I did much
DOS programming but isn't the linear frame-buffer allocated somewhere in
the 4Gb address space under VBE 2.0 and the banked modes the 64k block
in the DOS memory area?

If the card is optimised for DOS access then it seems likely the LFB will
run slower (although, this would be _really_ stupid... :)

Leathal.

- Raw text -


  webmaster     delorie software   privacy  
  Copyright © 2019   by DJ Delorie     Updated Jul 2019