Path: utzoo!attcan!utgpu!jarvis.csri.toronto.edu!mailrus!iuvax!rutgers!uwvax!astroatc!ttl
From: ttl@astroatc.UUCP (Tony Laundrie)
Newsgroups: comp.arch
Subject: Re: How Caches Work
Message-ID: <2803@astroatc.UUCP>
Date: 11 Sep 89 15:30:20 GMT
References: <21936@cup.portal.com> <1082@cernvax.UUCP> <16306@watdragon.waterloo.edu> <RANG.89Sep10184900@derby.cs.wisc.edu> <31224@ucbvax.BERKELEY.EDU>
Reply-To: ttl@astroatc.UUCP (Tony Laundrie)
Organization: Astronautics Technology Cntr, Madison, WI
Lines: 13

In article <31224@ucbvax.BERKELEY.EDU> elm@chilli.Berkeley.EDU (ethan miller) writes:
>In article <RANG.89Sep10184900@derby.cs.wisc.edu> rang@cs.wisc.edu (Anton Rang) writes:
>%  The problem is that caching something is not without cost.  Loading
>%128 words into the cache from main memory is generally just as
>%expensive as fetching 128 words from main memory directly.  The cache
>
>It is often faster to load 128 words sequentially than it is to have
>to fetch those words from memory.  If you can use static column mode on
>

Loading 128 words into the cache from memory is much faster than loading them
one at a time because the path between cache and memory is usually many
words wide (like 16).