*BSD News Article 8986


Return to BSD News archive

Xref: sserve comp.unix.pc-clone.32bit:753 comp.unix.sysv386:26366 comp.unix.bsd:9043 comp.os.linux:19463
Newsgroups: comp.unix.pc-clone.32bit,comp.unix.sysv386,comp.unix.bsd,comp.os.linux
Path: sserve!manuel.anu.edu.au!munnari.oz.au!news.hawaii.edu!ames!agate!spool.mu.edu!umn.edu!math.fu-berlin.de!informatik.tu-muenchen.de!roell
From: roell@informatik.tu-muenchen.de (Thomas Roell)
Subject: Re: ET4000/W32 and VESA VL-Bus
In-Reply-To: turbo@cse.uta.edu's message of Thu, 17 Dec 1992 19:05:42 GMT
References: <BzBEI1.CH@aeon.in-berlin.de> <1992Dec17.080653.4328@Informatik.TU-Muenchen.DE>
	<1992Dec17.190542.2662@utagraph.uta.edu>
Sender: news@Informatik.TU-Muenchen.DE (USENET Newssystem)
Organization: Inst. fuer Informatik, Technische Univ. Muenchen, Germany
Date: Fri, 18 Dec 1992 09:59:06 GMT
Message-ID: <1992Dec18.095906.3950@Informatik.TU-Muenchen.DE>
Lines: 47

>I thought that since EGA boards have been using double ported DRAM to
>avoid this?  Or are you saying 100MBs is for both ports?  I have noticed
>some ads saying their S3 board uses double ported DRAM so are we to
>assume that most are not?  If so then as you say this will instantly
>destroy any speed a coprocessor can give as the only thing that matters
>then is faster DRAM.  I am no expert (as is obvius to the experts by
>now) but I am just trying to get this picture.  If ram access has always
>got this refresh overhead (assuming a single port) then any board will
>simply be limited by DRAM bandwidth.

Yes, you are right, partially. Of course the serious graphics boards
use all VRAM, which are dual ported RAMs specifically for graphics
boards. They have a internal shift register for the screen refresh
data and a random access port for the graphics engine. And of course
those allow you to use the 100MB/sec (which was again just a sample
number which seems to be realistic for the WD90C31) exclusively for
the drawing operations. But the point was that somebody asked about
the ET4000/W32, which is a DRAM based (and not VRAM based) solution.
In my eyes, nothing justifies the usage of DRAMs for a graphics board if
you want to use it for a GUI. The price difference is rather minor
in those days.

Also there are quite a number of S3 chips, which use EITHER VRAM or
DRAM:

	86C911		VRAM
	86C924		VRAM
	86C801		DRAM
	86C805		DRAM
	86C928		VRAM


What I am saying is that for 1028x768 in 70Hz and 1280x1024 you should
generally forget the DRAM based solutions. Even if they look good at
benchmarks; most of these benchmarks used a 640x480 resolution,
where the screen refresh only takes 25MB/sec, and the available
bandwidth for graphics operations is quite the same as for VRAM based
solutions. But if you use the DRAM based boards at 1024x768, 70Hz,
you'll see the difference.

- Thomas

--
-------------------------------------------------------------------------------
Das Reh springt hoch, 				e-mail: roell@sgcs.com
das Reh springt weit,				#include <sys/pizza.h>
was soll es tun, es hat ja Zeit ...