Author: Robert Hyatt
Date: 19:30:42 06/24/02
Go up one level in this thread
On June 24, 2002 at 13:05:09, Gian-Carlo Pascutto wrote: >On June 24, 2002 at 10:30:26, Robert Henry Durrett wrote: > >>This addresses half the problem. What if the microprocessor wishes to WRITE >>something. Why not write it directly to a huge cache and bypass RAM entirely? >>If you had extremely large caches, couldn't RAM be dispensed with entirely? > >Writing to a cache is somewhat different. I believe most caches >work by writing both to the cache and to the RAM. Remember that when >writing, you don't actually need to wait until the data is written >out before you can do anything else, so there is no 'delay' in >writing to the actual RAM. That is "write through". It isn't used much today. Most caches use "copy back" where a line is not written back to memory until it needs to be replaced in cache and has been modified. > >However it's usually good to assume that something that was just >written may be read in again soon, so it makes sense to already >have a copy in the cache handy. > >-- >GCP
This page took 0 seconds to execute
Last modified: Thu, 15 Apr 21 08:11:13 -0700
Current Computer Chess Club Forums at Talkchess. This site by Sean Mintz.