Computer Chess Club Archives


Search

Terms

Messages

Subject: Re: parallel scaling

Author: Robert Hyatt

Date: 20:25:04 10/28/03

Go up one level in this thread


On October 28, 2003 at 16:04:46, Matthew Hull wrote:

>On October 28, 2003 at 09:48:52, Robert Hyatt wrote:
>
>>On October 27, 2003 at 21:23:13, Vincent Diepeveen wrote:
>>
>>>On October 27, 2003 at 20:09:55, Eugene Nalimov wrote:
>>>
>>>>On October 27, 2003 at 20:00:54, Robert Hyatt wrote:
>>>>
>>>>>On October 27, 2003 at 19:57:12, Eugene Nalimov wrote:
>>>>>
>>>>>>On October 27, 2003 at 19:24:10, Peter Skinner wrote:
>>>>>>
>>>>>>>On October 27, 2003 at 19:06:51, Eugene Nalimov wrote:
>>>>>>>
>>>>>>>>
>>>>>>>>I don't think you should be afraid. 500 CPUs is not enough -- you need
>>>>>>>>reasonable good program to run on them.
>>>>>>>>
>>>>>>>>Thanks,
>>>>>>>>Eugene
>>>>>>>
>>>>>>>I would bet on Crafty with 500 processors. That is for sure. I know it is quite
>>>>>>>a capable program :)
>>>>>>>
>>>>>>>Peter.
>>>>>>
>>>>>>Efficiently utilizing 500 CPUs is *very* non-trivial task. I believe Bob can do
>>>>>>it, but it will be nor quick nor easy.
>>>>>>
>>>>>>Thanks,
>>>>>>Eugene
>>>>>
>>>>>
>>>>>If the NUMA stuff doesn't swamp me.  And if your continual updates to the
>>>>>endgame tables doesn't swamp me.  We _might_ see some progress here.  :)
>>>>>
>>>>>If I can just figure out how to malloc() the hash tables reasonably on your
>>>>>NUMA platform, without wrecking everything, that will be a step...
>>>>
>>>>Ok, just call the memory allocation function exactly where you are calling it
>>>>now, and then let the user issue "mt" command before "hash" and "hashp" if (s)he
>>>>want good scaling.
>>>>
>>>>Thanks,
>>>>Eugene
>>>
>>>That's why i'm multiprocessing. All problems solved at once :)
>>
>>
>>And several added.  Duplicate code.  Duplicate LRU egtb buffers.  Threads
>>are not necessarily bad here.  We're hitting 6.75M+ nodes per second on a quad
>>opteron at 1.8ghz.  That's not bad.  I'll post some output when everything is
>>cleaned up and finalized, particularly allocating the hash tables.
>
>
>Is that with the SMP version or with NUMA version?
>
>MH


It is a hybrid.  The new SMP version will support NUMA.  Eugene has already
written windows NUMA support and it will automatically work if you use a
NUMA platform with windows.  I'll do this on Linux once I have a NUMA box
with a Linux kernel to play with.  Version 19.5 will have these changes.  You
won't see any external differences.  I just now allocate things like the
tree block on a local processor for efficiency.  We are working on distributing
the Hash table across all processors.  Eugene has written something there
although I am not sure we are done with it yet...

More as it develops.  As I had mentioned, I had already done most of this
once, already, for the NUMA alpha project I worked on last year.  It wasn't
very hard to do it a second time, it took a couple of hours.

Note that it was not a complete re-write, as I had mentioned previously,
in spite of what some thought was required.  It isn't _that_ big a deal.




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.