Author: Tony Werten
Date: 10:27:30 09/04/02
Go up one level in this thread
On September 04, 2002 at 12:48:32, Robert Hyatt wrote: >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"??? Sorry, my mistake. In Holland ( and prabably more countries ) a "," is used as a decimal separator, and a "." for thousands. I used them correct a few lines above but when reading the table I went wrong. ( I already thought the table was sloppy since you forgot the 0, in a few places :) Tony > >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.