ChessUSA.com TalkChess.com
Hosted by Your Move Chess & Games
 
 FAQFAQ   SearchSearch   MemberlistMemberlist   UsergroupsUsergroups   RegisterRegister 
 ProfileProfile   Log in to check your private messagesLog in to check your private messages   Log inLog in 

info about zappa on 512 cores ?
Post new topic    TalkChess.com Forum Index -> Computer Chess Club: Programming and Technical Discussions Flat
View previous topic :: View next topic  
Author Message
Robert Hyatt



Joined: 27 Feb 2006
Posts: 15816
Location: Birmingham, AL
PostPost subject: Re: numa scaling    Posted: Mon Jun 25, 2012 9:17 pm Reply to topic Reply with quote
Daniel Shawul wrote:
Quote:

The times are pretty variable. And there is some tuning that can be done inside Crafty as it really expects bus-level speeds, not infiniband latency, which would likely be somewhat better with different internal settings...

No they are not. Have you seen the example given in the test code that I mentioned?
Code:

Memory allocated on cpu 0
0: time = 7.95079 seconds
1: time = 7.93437 seconds
2: time = 10.2906 seconds
3: time = 10.3224 seconds

This has a 7 sec to 10 sec difference between accessing a far/near memory.
Quote:

Those times don't really say much about how a CHESS program like Crafty will scale. The locks will be important and at infiniband latencies, they will likely hurt significantly..

Like I have mentioned before, I don't think inifiniband is involved here. That is used only for connecting "nodes" with 32 cores each. The cluster have thousands of cores where each node an HP Prolient G5 servers 8sockets X AMD optern quad-core. So each cpu is connected to the other through the HyperTransport interface Machine spec

Here is the other machine with 2socketX 12 core AMD



You don't consider 50% as a significant variance??? I did look at the "test code" to see what it is doing, and it is purely a bandwidth measure. There is latency and there is bandwidth. Infiniband can provide bandwidth, but it is very slow in terms of latency when compared to a normal local memory access...

The AMD approach, if you REALLY have 8 chips, is a large ring. And for each hop, the access time goes way up. With 4 chips, you have one local, two 1-hops, and one 2-hop access. With 8, it is 1 local, 2 1-hops, 2 2-hops, 2 3-hops and 1 4-hop, which gets sticky.

Crafty was tuned on a 4 chip AMD box... I have not done any sort of tuning (yet) for the newer AMD and/or Intel boxes where everyone is using NUMA now.


We have 3 clusters here that use infiniband, and while it looks great compared to other network topologies, it does not look great compared to actual memory over the bus..
Back to top
View user's profile Send private message
Display posts from previous:   
Subject Author Date/Time
info about zappa on 512 cores ? Daniel Shawul Sat Jun 23, 2012 2:05 pm
      numa scaling Daniel Shawul Sun Jun 24, 2012 10:20 am
            Re: numa scaling Robert Hyatt Sun Jun 24, 2012 5:01 pm
                  Re: numa scaling Daniel Shawul Sun Jun 24, 2012 5:41 pm
                        Re: numa scaling Robert Hyatt Mon Jun 25, 2012 12:37 am
                              Re: numa scaling Daniel Shawul Mon Jun 25, 2012 1:23 am
                                    Re: numa scaling Robert Hyatt Mon Jun 25, 2012 10:05 am
                                          Re: numa scaling Daniel Shawul Mon Jun 25, 2012 4:00 pm
                                                Re: numa scaling Daniel Shawul Mon Jun 25, 2012 5:21 pm
                                                Re: numa scaling Daniel Shawul Mon Jun 25, 2012 8:09 pm
                                                      Re: numa scaling Robert Hyatt Mon Jun 25, 2012 8:38 pm
                                                            Re: numa scaling Daniel Shawul Mon Jun 25, 2012 8:53 pm
                                                                  Re: numa scaling Robert Hyatt Mon Jun 25, 2012 9:17 pm
                                                                        Re: numa scaling Daniel Shawul Mon Jun 25, 2012 9:46 pm
                                                                              Re: numa scaling Robert Hyatt Tue Jun 26, 2012 3:34 am
                                                                                    Re: numa scaling Daniel Shawul Tue Jun 26, 2012 11:06 am
                                                      Re: numa scaling Daniel Shawul Tue Jun 26, 2012 12:55 am
            transposition tables Daniel Shawul Sun Jun 24, 2012 5:53 pm
                  Re: transposition tables Daniel Shawul Wed Jun 27, 2012 11:17 pm
                        Re: transposition tables Ronald de Man Fri Jun 29, 2012 11:47 pm
                              Re: transposition tables Daniel Shawul Sat Jun 30, 2012 12:40 am
      Re: info about zappa on 512 cores ? Vincent Diepeveen Fri Jun 29, 2012 11:07 pm
            Re: info about zappa on 512 cores ? Daniel Shawul Sat Jun 30, 2012 12:32 am
                  Re: info about zappa on 512 cores ? Daniel Shawul Sat Jun 30, 2012 10:50 am
Post new topic    TalkChess.com Forum Index -> Computer Chess Club: Programming and Technical Discussions

 
Jump to:  
You cannot post new topics in this forum
You cannot reply to topics in this forum
You cannot edit your posts in this forum
You cannot delete your posts in this forum
You cannot vote in polls in this forum




Powered by phpBB © 2001, 2005 phpBB Group
Enhanced with Moby Threads