Author: Robert Hyatt
Date: 09:48:32 09/04/02
Go up one level in this thread
On September 04, 2002 at 11:47:39, Tony Werten wrote: >On September 04, 2002 at 10:33:41, Robert Hyatt wrote: > >>On September 04, 2002 at 03:31:19, Tony Werten wrote: >> >>>On September 03, 2002 at 18:03:14, Gian-Carlo Pascutto wrote: >>> >>>>However reasonable your explanations may be, the gist of your DTS article >>>>and the most important thing for comparison were the speedup numbers. After >>>>what we discovered and what you just posted, it is clear that they are >>>>based on very shaky foundations. >>> >>>I must be missing something. The only thing I see wrong with the speedup numbers >>>is the way they are calculated. >>> >>>Since time was measured in miliseconds ie 3 significant numbers after the dot, >>>the speedup should have been given in 3 significant numbers behind the dot as >>>well. >> >> >> >>Just a note. I am not sure where this "millisecond" stuff comes from. But in >>Cray Blitz, we only kept time to the nearest second, as produced by the Cray >>library system call. > >So the speedup was calculated a different way and from that speedup the >solutiontime was calculated. Unfortunately the solutiontime was in >milliseconds,suggesting a high precision and the speedup factor only in tenths >giving the strang looking "precision" of 2.000 or 1.900 for anyone calculating >it the normal way from the tables. > >OK at least I understand what it's all about now. Not sure if I care though. I'm lost now. Where are you seeing "milliseconds in the DTS article"??? Perhaps you are making a bad assumption because the one processor numbers are so big? those are _seconds_. Which is why I mentioned in the paper that this was a _huge_ computational project to complete. :) But so far as I recall, all times were in seconds. that is all Cray Blitz ever displayed. I always rounded speedups to .x because that was simply the way everyone else reported the same sort of data. And with the variance in times between runs on the same position, even that .1 is a bit silly... It would probably be "saner" to use three fractions and leave it at that, 1/4, 1/2 and 3/4, as that comes closer to covering the "jitter" in the speedup data. Hope that helps clear things up. If I said milliseconds somewhere in the article, I hope it was in the context of overhead or something, and not related to raw search times. Otherwise I certainly misstated something. I did notice a microsecond reference but it was in relation to memory conflicts or something, and there the hardware performance monitor I used did give time down to the nanosecond (actually in terms of clock cycles) level... But not for any search times or speedups... > >Tony >
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.