Path: utzoo!attcan!uunet!lll-winken!lll-tis!ames!amdahl!pyramid!prls!philabs!sbcs!root
From: root@sbcs.sunysb.edu (root)
Newsgroups: comp.sys.amiga
Subject: Re: Studebakers
Summary: Hires screens
Message-ID: <1327@sbcs.sunysb.edu>
Date: 11 Jun 88 17:26:18 GMT
References: <4400@gryphon.CTS.COM> <56089@sun.uucp> <4429@killer.UUCP>
Organization: State University of New York at Stony Brook
Lines: 38

In article <4429@killer.UUCP>, elg@killer.UUCP (Eric Green) writes:
> In message <56089@sun.uucp>, cmcmanis%pepper@Sun.COM (Chuck McManis) says:
> Amiga bus, which means goodbye low-cost DRAMs and cycle-multiplexed
> bus interface, hello lots of trickery and kludges and expensive fast
> RAMs. However, this resolution would allow the Amiga to move into
> areas such as low-cost image processing that the current display

	If we change the model of low level graphics accesses from
	allowing direct CPU access to screen bits to just
	primitives, eg lines, polygons, etc the issue of how the
	frame buffer is implemented goes away nicely.  Getting
	people to write programs that don't expect to access
	screen bits directly also has a side benefit that the
	programs are more easily moved into network window systems,
	eg X, NeWS, etc. 

	The hardware issues in high resolutions displays boil down
	to the simple fact that you cannot supply the display
	controller with 10-100+ mBytes/sec at the same time that you are
	supplying 4-5 mBytes/sec (or 50 mBytes+ to a 68030) to the 
	CPU + whatever disk DMA, network DMA, etc are consuming.
	High res ==> clock rates ==> video rams.  Or you build your 
	entire memory system from 15 nS SRAM :-)

> simply is too limited to adequately support (at least in a manner
> acceptable to the current state-of-the-art in image processing, which
> is either RGB 24-bit or 8-bit grey-scale).

	Agreed.  But are we building home/low end machines or SGI
	killers?  

> 
> --
> Eric Lee Green    ..!{ames,att,decwrl,ihnp4,mit-eddie,osu-cis}!killer!elg
>           Snail Mail P.O. Box 92191 Lafayette, LA 70509              
> "Is a dream a lie if it don't come true, or is it something worse?"

						Rick Spanbauer
						SUNY/Stony Brook