Author: Robert Hyatt
Date: 18:53:55 08/24/03
Go up one level in this thread
On August 22, 2003 at 16:24:08, Sune Fischer wrote: >On August 21, 2003 at 11:31:08, Robert Hyatt wrote: > >>>I was thinking more about how silly it is to copy the empty bitboards for each >>>ply. If you update the boards that are active, they will stay in the cache. >>>Those that are not used might drop out, unless they are copied once every micro >>>second. >>> >> >>That is a reasonable rate for a program that searches 1M nodes per second. I'm >>going at 2.4M so make that about once every 400 nanoseconds. :) Suddenly it >>begins to add up in a big way. :) >> > >Ehh, if you search 2.4 Mnodes on a dual that's 1.2 nodes on a single (one every >800 ns), I'd say not very far from 1M. I assume you will also have _two_ chips >to do the copying :) _no_. You have exactly _one_ bus connecting _both_ processors to memory. That's a problem... > >It's still faster to unmake in your case I think, you also have the [64] piece >array which would need copying, I got a ~10% increase in make/unmake over >make/uncopy myself. >But IMO, the real benefit of unmaking is that you don't have to be so cheap in >adding arrays since only one entry needs handling at a move. > >-S.
This page took 0.1 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.