Newsgroups: comp.sys.amiga.advocacy
Path: utzoo!utgpu!news-server.csri.toronto.edu!rpi!zaphod.mps.ohio-state.edu!wuarchive!psuvax1!news
From: melling@cs.psu.edu (Michael D Mellinger)
Subject: Re: NeXT-bashing party (hit "n" if you're not interested :-))
In-Reply-To: tinyguy@cs.mcgill.ca's message of 29 Mar 91 19:29:48 GMT
Message-ID: <6u9Gmncc1@cs.psu.edu>
Sender: news@cs.psu.edu (Usenet)
Nntp-Posting-Host: sunws6.sys.cs.psu.edu
Organization: Penn State Computer Science
References: <1991Mar26.043648.17656@NCoast.ORG>
	<1991Mar26.222344.16190@news.iastate.edu> <20202@cbmvax.commodore.com>
	<1991Mar29.192948.1914@cs.mcgill.ca>
Date: Sat, 30 Mar 91 03:39:40 GMT
Lines: 18


In article <1991Mar29.192948.1914@cs.mcgill.ca> tinyguy@cs.mcgill.ca (Yeo-Hoon BAE) writes:


   Is it really worth having external cache with 040 chip?
   I read from somewhere which compared the performance of
   486 with 128k cache and without one. In general, the 
   presence of cache only makes 20% difference or so, according
   to them. I remember them stating that the internal 4 way
   assositive 8k cache is 'equivalent' to 32k external,
   assuming no clever cache contoller is used.

   Any comments ?

20% of 15 mips is 3 more mips.  Anyone care for an extra 3 mips?

-Mike

