Path: utzoo!utgpu!news-server.csri.toronto.edu!bonnie.concordia.ca!uunet!sequent!talon.UCS.ORST.EDU!cs.umn.edu!kksys!edgar!orac!bret
From: bret@orac.UUCP (Bret Indrelee)
Newsgroups: comp.sys.amiga.advocacy
Subject: Re: (Video) Hardware Idiots ?
Summary: Speed of VGA
Message-ID: <375@orac.UUCP>
Date: 13 Jun 91 01:34:15 GMT
References: <1991Jun9.151244.8883@cunixf.cc.columbia.edu> <1991Jun9.184849.4299@neon.Stanford.EDU> <1991Jun10.043321.21692@cunixf.cc.columbia.edu>
Organization: Technix Inc., Saint Paul MN, USA
Lines: 33

In article <1991Jun10.043321.21692@cunixf.cc.columbia.edu> es1@cunixb.cc.columbia.edu (Ethan Solomita) writes:
>	However there are uses for everything and if it weren't
>slower I'd want it. However, I don't consider the additional cost
>of that board reasonable. Also, after seeing the speed of windows
>I'd be afraid of anything more than 16 colors. The speed of VGA
>boards ain't so great either.
>	-- Ethan

VGA lives on the ATbus (now sometimes called the ISA bus).  This bus
is slow.  It is difficult to get any kind of random access runnings at
greater than about 2Mbytes/sec (possible, just difficult) assuming the
CLK is running 8 1/3 MHz.  Run it any faster and you better be ready
for an unreliable system, or invent a logic family that can work in
about -5nSec ;-)

The time of signal propagation doesn't allow enough time for a board
to assert *READY to insert wait states if you run your ATbus at greater
than 8 1/3 MHz, and not every piece of hardware can run zero-wait states.
At 10 MHz, you have to be able to respond before the signals have settled
(thus requiring negative time) to meet the ATbus spec.


On Microchannel, it should be possible to create a graphics board that
can really cook.  I don't know if anyone has yet...I'm just saying that
the bandwidth is available.

-Bret


-- 
------------------------------------------------------------------------------
Bret Indrelee		|	Our mail is still somewhat unreliable.  Sorry.
uunet.uu.net!cs.umn.edu!kksys!edgar!orac!bret		-And still trying