Author: Slater Wold
Date: 08:52:09 11/21/01
Go up one level in this thread
On November 21, 2001 at 11:19:08, Robert Hyatt wrote: >On November 21, 2001 at 11:05:00, Slater Wold wrote: > >> >>As I have found positions where the NPS search is 2.5x faster, but it solves the >>solution in 4x faster than a single cpu. >> >>Dann and I had this "super" linear discussion before. >> >>Seems like it would even out, eventually. But like I said, I believe you. And >>I'll do it to solution now. (But of course, I'll still look at the NPS!) :) >> > > >First, two cpus is going to have a _hard_ time searching 2.5x the raw >nodes per second. I have no idea how that might happen, unless there is a >bug in the node-counting that sometimes counts nodes twice. Sorry. I've seen positions where it will search 1.8x the NPS and solve it 4x faster. I was just reversing your comment. >Second, "super-linear" can happen on occasional positions. But as you said, >it will average out over multiple positions so that the speedup simply can not >be >2.0 for two processors on average. I was in the middle of the super-linear >speedup discussion. I hope it stays "at rest" now. :) I've seen it happen a time or two. I've found a solution one go, and can never get it again. (Happened more than once with DJ7.) >I have seen several cases of spectacular speedups, but then I have also seen >an equal number of horrible speedups. Bruce once sent me one that produced >a particularly ugly result on Crafty, But I can't seem to locate the thing >at present... I think I've only seen 1 or 2. But I have seen a LOT that are greater than the speedup of the NPS speedup. In other words, it takes the SMP less nodes to find the solutions, that the 1 CPU. >In any case, NPS is kind of like engine RPM. It should increase linearly with >the number of processors, assuming the parallel algorithm is good at keeping >both cpus busy all the time and doesn't have one (or more) sitting around >waiting excessively. But RPM has nothing to do with vehicle speed, because >of losses along the drive train. The MPH value (time to solution) is the thing >that wins races (or games). HUM. Now you're picking a subject I am _very_ familiar with. RPM's and and MPH aren't _DIRECTLY_ related. IE: If you have a car that has a 4.11 gear ratio with 351c.i. motor, that is getting 400 HP at 5750RPM, it SHOULD go 12's in the 1/4 mile. (Depending on weight.) Let's just say, it goes 12.5 @ 119MPH. Now, let's say you install an aluminum driveshaft. Your RPM's are going to increase. Same setup, same everything, it will probably get 400HP at 5900 RPM. And if you run the 1/4 mile again, I would guarantee 12.3's at the SAME MPH. Maybe, you'll get 1 or 2 more MPH. You're going .2 seconds faster, but the MPH isn't changing. RPM doesn't = MPH, but the faster you can rev, the faster you can get to that top MPH. Unless your gears are wacky.
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.