Author: Dan Newman
Date: 02:27:16 04/25/00
Go up one level in this thread
On April 25, 2000 at 01:20:11, Bas Hamstra wrote: >I have some evidence that an unrotated bb approach can be as fast or faster than >a rotated one. > >- my fastest ever version did it unrotated. I thereafter thought rotated would >be even faster, but never got that speed again. (until hopefully now) > >- Dan Newman reaches almost 600k nps with little eval on a PIII/500, unrotated. >While I thought the limit (based on what I see around) for rotated on this >hardware is about 500k doing only material! > I'm down to 480 knps now :) >- On this board I saw someone gen moves pretty fast unrotated. > >Pro unrotated: > >- you can gen moves in LVA/MVV order right away. You can not do that while >rotating, at least not the way Crafty does it. Saves a sort afterwards. Don't >know how big a factor this is. > >- You don't need the expensive 64 bit shifts doing movegeneration (and eval), >which saves a lot of overhead. > >- Your make() is much faster without the 4 Occupied maps. > >Contra: > >- You have to scan for blocks, while rotated doesn't need to. However using a >int__64 blockmask[From][To] can do this pretty quick (though some say scanning >the board is even faster). > I've changed my mind on this one. Lately I've found the blockmask's to be faster than scanning--sometimes I do have to scan though... >The big question is: is the extra overhead of rotated bb's justifyable? Could it >be non-rotated is faster overall? > I think this is really difficult to figure out. If you work a long time on one scheme, you might well find it faster than another that you spent a shorter time on. It could be you just overlooked something, some trick that really would have sped it up. But my gut feeling is that non-rotated is a bit faster (given equal programming effort) on the latest Intel machines. (OTOH, it could be I'm just avoiding all that work implementing rotated bitboards. :)) -Dan. >(Currently I myself have started all over trying to make a really fast rotated >BB program. Looks promising so far: make/unmake=2M/sec and movegeneration=12M >moves/sec on a Celeron 466)
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.