Author: Gerd Isenberg
Date: 07:34:26 10/17/03
Go up one level in this thread
On October 17, 2003 at 09:48:00, Vladimir Medvedev wrote: > >Thank you, Gerd! > >>i had a quick look to your Bitboards.cpp file. >>My collection of BitScan (LSB) routines exceeds further on. >>I fear your switch case with single isolated LS1B is not optimizable as a jump >>table, but works like 64 nested "if then elses". Not sure about how the branch >>prediction works here, but i guess the squares on the "black" side are a bit >>handicapped ;-) > >Can't compiler optimize it to log2(64) = 6 "if-then=elses" ? >If not, I can do it manually... Yes, of course that could (and should) be done by the compiler (have to inspect assembler). > >But I don't want to use assembler, it's not my native language... > >Could you write some direct links to threads on LSB topic in this Forum? >This search engine does not work for me :((( some archive links on the fly (searched by Author "Walter Faxon") http://www.chess-archive.com/ccc.php?art_id=265635 http://www.chess-archive.com/ccc.php?art_id=268531 http://www.chess-archive.com/ccc.php?art_id=269112 http://www.chess-archive.com/ccc.php?art_id=272174 http://www.chess-archive.com/ccc.php?art_id=273932 http://www.chess-archive.com/ccc.php?art_id=275154 http://www.chess-archive.com/ccc.php?art_id=305907 http://www.chess-archive.com/ccc.php?art_id=305916 http://www.chess-archive.com/ccc.php?art_id=306363 and this one about Matt's de Bruijn multiplication: http://www.chess-archive.com/ccc.php?art_id=306211 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.