Path: utzoo!utgpu!news-server.csri.toronto.edu!rpi!zaphod.mps.ohio-state.edu!uwm.edu!lll-winken!sun-barr!newstop!sun!amdcad!brahms!phil
From: phil@brahms.amd.com (Phil Ngai)
Newsgroups: comp.sys.ibm.pc.hardware
Subject: Re: Caching and VGA (was: Comparing 486 to 386 Systems)
Message-ID: <1991Apr21.041928.8258@amd.com>
Date: 21 Apr 91 04:19:28 GMT
References: <1991Apr6.045408.15395@agate.berkeley.edu>  <1991Apr18.192814.21504@amd.com> <1991Apr20.224804.6066@cc.helsinki.fi>
Sender: usenet@amd.com (NNTP Posting)
Organization: Advanced Micro Devices, Inc.
Lines: 24

osmoviita@cc.helsinki.fi writes:
>Have You experienced real problems or is this theoretical thinking? I have

You asked how it (could) suffer. I posted one way. If you don't like
it, don't take it.

>I wouldn't mind not to write same value to same
>pixel if it is already there.

Sorry, but caches don't work that way.

Caches also work real poorly with paged memory, which the VGA frame
buffer is. Just how do you think they fit 256 Kbytes of RAM into
the 64 Kbyte segment starting at A000?

>But do You mean that if same places of
>different pages are written after each other the cache won't let the data
>through? Or what??

Could be. There are many different types of caches, your description is
one popular way.

--
	It doesn't have to be perfect to be useful.