home *** CD-ROM | disk | FTP | other *** search
- Newsgroups: comp.sys.ibm.pc.hardware
- Path: sparky!uunet!munnari.oz.au!spool.mu.edu!uwm.edu!rpi!utcsri!newsflash.concordia.ca!sifon!homer.cs.mcgill.ca!storm
- From: storm@cs.mcgill.ca (Marc WANDSCHNEIDER)
- Subject: Re: Advantage of 256Kb over 64Kb Cache with 386?
- Message-ID: <C0p3Az.ArH@cs.mcgill.ca>
- Sender: news@cs.mcgill.ca (Netnews Administrator)
- Organization: SOCS - McGill University, Montreal, Canada
- References: <C0nGtz.Mry@dutiws.twi.tudelft.nl>
- Date: Mon, 11 Jan 1993 15:06:34 GMT
- Lines: 25
-
- In article <C0nGtz.Mry@dutiws.twi.tudelft.nl> zonnevel@dutiws.twi.tudelft.nl (B.J.Zonneveld.tel-015-622622) writes:
- >Hi, I want to know what the improvement is of using 256kb cache in
- >stead of 64kb on my 384/40'er. Is it a noticeable speed improvement?
- >If anyone has any experience or read something could you please
- >email me personally.
-
- Chances are, little.
-
- Most 64k cache systems are going to have some 4 way set associative
- caching scheme, for which 64k will be adequate, and 256k will only give you
- a 2% improvement or so.
-
- Many systems that come with 256k caches are direct mapped, which
- is a REALLY sucky caching policy, but gives you similar performance to the
- 64k 4way sa cache just because it's 4 times bigger.
-
- In other words, don't bother.
-
- Toodlepip!
- Marc 'em.
- --
- storm@cs.mcgill.ca McGill University "-- Attack ships on
- Marc Wandschneider Montreal, CANADA fire "
- Any opinions expressed are not mine, but those of the Demon Lord
- Yeegeheeegenogohugu who possessed me whilst I munched on Raisin Bran.
-