Author: Jeremiah Penery
Date: 16:09:20 10/14/02
Go up one level in this thread
On October 14, 2002 at 06:34:43, Vincent Diepeveen wrote: >On October 14, 2002 at 04:29:41, Daniel Clausen wrote: > >>On October 13, 2002 at 22:48:10, Jeremiah Penery wrote: >> >>>On October 13, 2002 at 21:40:42, Robert Hyatt wrote: >>> >>><snip> >>> >>>>You are _totally_ wasting your breath... >>> >>>I don't mind too much wasting my breath, as long as some decent discussion comes >>>from it. :) >> >>As if that ever happened on this board when the subject was related to DB. ;) >> >>Sargon > >the marketing hype created by IBM is so big that we'll never end >talking about it, like they talked for well over 100 years about >The Turk automata that won from Napoleon. > >it's pretty weird to see people argument that the thing searched 18 >ply fullwidth based upon some mainlines, despite statements and >theoretical impossibilities to do so :) But here you are claiming that it searched less plies because of shorter mainlines in some cases. >Amazingly no one ever talks about shredder here. Shredder always shows >longer mainlines. Some years ago i had a selective search in diep which >checked the principal variation of diep further. > >In the end i threw it out. What does that have to do with anything? >Now suppose you have 480 processors idling, i'm so amazed no one can >understand that in order to get more nodes a second, the only >important thing, even the chat yesterday Hsu was only talking >about nodes a second NOT about search depths, it is important to >give them jobs. In the Hsu chat, there is exactly one statement about nodes/sec. He says it would be possible to build a single chip today doing a billion n/s, and a machine that would do a trillion. That is the ONLY mention of nodes/sec, and that only because someone directly asked about how fast DB would be in NPS today if it was updated. The only mentions of search depth are in relation to questions about 12(6). >So splitting a position at the end of the pv 1 deeper is not so stupid >here. The rest is from hashtable and extensions. > >The only interesting question this Jeremiah Penery guy should ask himself >is: "WHAT WAS IBM BUSY DOING?" > >Answer: getting as many nodes a second as possible against kasparov Wrong. _IBM_ was busy MARKETING. Some of those marketing people probably wouldn't know a node searched from a pawn, so you can't say they only cared about nodes/sec. They cared only about making money. Telling people it can beat Kasparov is enough, since 99% of people don't know a thing about nodes either. >Now how do you get as many as possible CPUs to work in order to >get more nodes a second, with just a small search depth? Making them search MTD style on the same search with different bounds, to converge on the true score, is one way. They sometimes did that. >All we know is that even at 11 ply search depths they didn't manage >to get the full potential of the cpu's. In fact 126 MLN nodes a second >is a lot less than 480 x 2.25 MLN nodes a second = 1.08 BLN > >126 MLN nodes a second is 11.7% from that. > >That's basically based upon the last seconds of the 3 minute search. > >the first few seconds not many processors had a job out of 480. > >So what i do then is to already let them split mainline second ply >after root. I put a bunch of processors there, despite possibly >getting a different alfabeta score. > >For a 2 processor setup that's horrible for the speedup (gives a >very bad speedup). For 480 processors it's great, getting them >busy is very important! You say they were 88% idle, but that they only cared about getting them un-idle. I think if they were REALLY that concerned about idling processors that they could find a way to make them busy somehow. That the processors were not continually busy shows you that they were NOT only concerned about NPS. >In fact we see from the deepblue paper in 2001 that it was already >taking processors from a search job if it took a bit too long to >search it! Then it resplitted and added more cpu's. That automatically >means that you get a longer PV. Only if that line manages to get backed up to the PV, which is probably uncommon.
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.