Computer Chess Club Archives


Search

Terms

Messages

Subject: Re: Table statement

Author: Robert Hyatt

Date: 10:29:05 09/05/02

Go up one level in this thread


On September 05, 2002 at 10:53:22, Vincent Diepeveen wrote:

>On September 04, 2002 at 14:29:05, Robert Hyatt wrote:
>
>you get even with fast memory on your quad only a 2.8 speedup
>on average at 30 positions.


I got a 3.0 speedup on the positions you wanted me to run.  You have
the data, you _know_ that is correct.  But only for that one run.  GCP
got 2.8 on a different machine (quad 550 of mine compared to my quad 700)
and I'd expect that if it were to be run again it would produce a different
result also.


>
>that's a lot more than a run on 1 position.

You can say that all you want.  Doesn't make it true.  My SMP test
results have _always_ been with respect to many positions when I talk
about average speedup and the formula I generally provide.

Only an idiot would use _one_ position for anything other than as a
counter example if some know-it-all says "you can't get more than a 1.4X
speedup".  Because _then_ one exception is enough.  But for speedup
results, I use test _sets_.  Ask Bruce.  He and I used to exchange results
all the time as we were working on our respective parallel searches.  And
we _both_ used test suites of positions, not single positions.

So this is simply more "disinformation" for which you are becoming quite
infamous...





>
>>On September 04, 2002 at 14:02:54, Vincent Diepeveen wrote:
>>
>>>On September 04, 2002 at 12:43:37, Robert Hyatt wrote:
>>>
>>>Please run crafty at 16 processors. Fine with me.
>>>Even though it's a different program. I have no problems
>>>with it.
>>
>>And what would be the point?  I might give you some 16 processor
>>numbers on a NUMA machine before long.  I _might_.
>>
>>
>>>
>>>But rewrite also the article then that it's not a DTS thing,
>>>but a smp_lock thing that doesn't scale above 8 cpu's.
>>
>>
>>Vincent, the smp_lock thing doesn't hurt me thru 16 cpus as I already
>>know.  I don't understand why you don't follow this, but in a typical
>>3 minute search, I see numbers like this:
>>
>>              time=3:29  cpu=399%  mat=0  n=303284136  fh=89%  nps=1450k
>>              ext-> chk=4663926 cap=1175890 pp=230533 1rep=74539 mate=3299
>>              predicted=2  nodes=303284136  evals=99342268
>>              endgame tablebase-> probes done=0  successful=0
>>              SMP->  split=774  stop=133  data=14/64  cpu=13:55  elap=3:29
>>
>>That is from a real game played on ICC.
>>
>>Note it only did 774 splits.  that is 774 smp_locks.  Do you _really_ think
>>that hurts performance?  _really_?
>>
>>If so, I have this bridge I need to get rid of...
>>
>>You can say smp_lock is a problem all you want.  You can say that it killed
>>you on a NUMA machine all you want.  But that doesn't mean it kills _me_
>>on 8 or 16 processors...
>>
>>
>>BTW I would hate to publish 16 cpu crafty numbers, because that would probably
>>give you _another_ problem to overcome with your "sponsors".  :)



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.