*BSD News Article 9378


Return to BSD News archive

Received: by minnie.vk1xwt.ampr.org with NNTP
	id AA5668 ; Fri, 01 Jan 93 01:52:19 EST
Xref: sserve comp.unix.bsd:9435 comp.os.linux:20726 comp.unix.pc-clone.32bit:841
Path: sserve!manuel.anu.edu.au!munnari.oz.au!spool.mu.edu!olivea!apple!netcomsv!netcom.com!hasty
From: hasty@netcom.com (Amancio Hasty Jr)
Newsgroups: comp.unix.bsd,comp.os.linux,comp.unix.pc-clone.32bit
Subject: Re: ET4000/W32 and VESA VL-Bus
Message-ID: <1992Dec28.223727.3569@netcom.com>
Date: 28 Dec 92 22:37:27 GMT
References: <1hloneINNfnn@cbl.umd.edu> <1992Dec28.103211.12677@diomedes.robots.ox.ac.uk> <1992Dec28.190316.22747@Informatik.TU-Muenchen.DE>
Organization: Netcom Online Communications Services (408-241-9760 login: guest)
Lines: 70

In article <1992Dec28.190316.22747@Informatik.TU-Muenchen.DE> roell@informatik.tu-muenchen.de (Thomas Roell) writes:
>>The 801 is indeed DRAM based (60ns DRAM), For the 911 and 801 boards both
>>for 71Hz refresh at 1024x768 on a 13MHz ISA bus I get:

Setting the tone again, normally I wouldn't respond to your posting but Jon
is out in vacation so allow me to expand on behalf of Jon Tombs:

Both Jon and I ran xbench  using the Actix GraphicEngine32 (801) and we both
got 64k xstones.  However,  I ran xbench at 1024x768 45MHz interlace. 

Jon's cpu is a 486/33Mhz 256k cache mine was a 486/33Mhz 64k cache.
He runs Linux and I run 386bsd. In the course of working on XS3 we
usually match each others xbench results.

What we are trying to compare here is the effect of running a DRAM based
card at lets say 71MHz vs. 45 MHz interlace which you have stated in your
previous posting that running at a high dot clock rate the performace of a
DRAM based will be significant worse.

Last but not least, Jon ran out of time before he had a chance to complete
the test round.

>
>Sorry, but this way of comparing things is quite rediculuts, if not
>even dumb (sorry folks , but I lack a better word of stating that somebody is
>not the brightest mind if he/she does things like that ;-)). 
>
>The issue here is that you have to compare two things that appeared at the
>market at about the same time. For example 86C911 vs. WD90C31
>would make sence (ca 55k xstones vs. 45k xstones). Also 86C801/86C805
>vs. mach32 (Ultra Pro) gives some sence: 100k vs. 64k. Or if you want

Can you be kind to post your Utra Pro benchmark results?

Also, is 64k xstones is that what your are getting? 
Because I am getting 83k xstones with my 801 on my new 486/50Mhz VLB.




>to stay in the domain S3, 801 vs 928. But what you do is comparing a
>chip that's ONE year old, and which in fact was one of the very first
>so called Windows accelerators. The 801/805/928 are simply the next
>generation, and hence much faster than the last generation. Other uneaqual
>comparisons wouldn't help you in comparing DRAM vs. VRAM at all.
>
>You are right if you compare the price/performance ratio of the 911 and
>a 801 based board today. But the 928 bases boards are just around the corner

According to a couple of vga manufacturers they expect the 928 to start
rolling out in less than 4 weeks.

>and will not cost much more than 801 based boards. That's the scenario where
>my comments apply. Then we have the same chips design as base and can compare
>a VRAM and a DRAM implementation with the same graphics engine ...
>

According to ACTIX's Director of Marketing the S3 928 is going to list for
about $350. The ACTIX GraphicEngine32 is listing for $199.
It will be interesting to find out from different manufacturers what are
they planning to sell the 928 for :-)


Amancio


-- 
Amancio Hasty           |  
Home: (415) 495-3046    |  ftp-site depository of all my work:
e-mail hasty@netcom.com	|  sunvis.rtpnc.epa.gov:/pub/386bsd/incoming