Author: Sune Fischer
Date: 01:07:51 09/17/02
Go up one level in this thread
On September 16, 2002 at 18:47:35, Gerd Isenberg wrote: > >Yes, may be, specially if you inline them. > >But otherwise an indirect function call via a 64 pointer array is not as bad. >Specially with diagonals, it may save a few cycles. The diagonal code is >shlightly larger than the straight one, and there are a lot of squares happy >with less than seven iterations: > >7 6 5 4 4 5 6 7 >6 5 4 4 4 4 5 6 >5 4 4 4 4 4 4 5 >4 4 4 4 4 4 4 4 >4 4 4 4 4 4 4 4 >5 4 4 4 4 4 4 5 >6 5 4 4 4 4 5 6 >7 6 5 4 4 5 6 7 So you can save max 3/7 of the job, but instead you need a lookup into a 64 pointer table? What if that table isn't in L1 10% of the time? Even so, isn't there some latency in getting data from L1 into the registers? Running inside registers, completely, is fast, you can afford a little extra work, I think :) Forget MMX (or rather live with it for now), but think Hammer for pete's sake ;D >Cheers, BitBoards forever! To bitboard or not to bitboard... is a stupid question :) -S. >Gerd > >>>An interesting feature of this routines may be looking for all squares >>>attackable after all possible moves by the sliders. You only need two >>>consecutive calls. >> >>Yes, that is true, so you can get rid of your 'taxi-distance' table too, just >>count the iterations here! >> >>-S. >> >>>Cheers, >>>Gerd
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.