Author: Robert Hyatt
Date: 19:00:51 04/30/04
Go up one level in this thread
On April 30, 2004 at 16:57:19, Vincent Diepeveen wrote: >On April 30, 2004 at 16:51:50, Robert Hyatt wrote: > >>On April 30, 2004 at 16:28:53, Peter Skinner wrote: >> >>>On April 30, 2004 at 16:25:29, Eugene Nalimov wrote: >>> >>> >>>>>Current egtb cache caches compressed blocks. So this is a moot point. >>>> >>>>Unfortunately no. That is in my "TODO" list. >>>> >>>>Thanks, >>>>Eugene >>>> >>>>>Decompression is _not_ the bottleneck. From actual testing rather than >>>>>guessing... >>> >>>I would have to figure the biggest bottleneck would be the hard drive speed, and >>>cpu speed. >>> >>>I know when I switched to 10,000 rpm drives I noticed quite an improvement over >>>the 7200 rpm. When I got my 15k rpm drive it was even better. >>> >>>Peter >> >>For 10K to 15K all you see is reduced average rotational latency.. Max transfer >>speed doesn't change. Of course the drives are not as "dense" either, usually >>being 1/4 (or worse) the size of the biggest 10K drives. > >There is 3.4 ms SCSI drives. Hard to beat :) that's 15K drives. But, as I said, they have lower rotational latency, hence lower overall average access times, but no higher bandwidth. As a result they are less dense and smaller. When I bought my 36 gig 15K drives I also bought 3 146 gig 10K drives. That's a good comparison on density vs average access time.
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.