Author: Vincent Diepeveen
Date: 14:52:33 09/02/03
Go up one level in this thread
On September 01, 2003 at 09:39:55, Jeremiah Penery wrote: >On September 01, 2003 at 06:09:48, Mridul Muralidharan wrote: > >>Hi Jeremiah, >> >> If you want crafty to get to work with a decent speedup on a 16 or 32 CPU >>cc-numa where you have say 2 - 4 processors per node with a significant >>inter-node latency (like most higher cpu numa boxes ?!) , you will have to >>ensure that the way you split , memory usage , etc is optimal - you dont want to >>access a hash entry in proc 0 from proc 32 when the latency wil be in >>milliseconds !!! > >The specific discussion was about Opteron machines up to 8 CPUs, which will all >be contained in one node and have extremely low non-local memory latency. > >Any large (multi-node) SMP machine will have the same problem as NUMA with >respect to inter-node latency. SMP doesn't magically make node-to-node >communication any faster. > >But in reality, almost nobody uses a machine that big, especially for chess. >For any but the most extremely scalable architectures, there is significant >diminishing returns when adding processors for chess playing. I'd say that a >very scalable 8-way SMP or NUMA (Opteron) machine will not be very much slower >than even a 64-way Alpha/Itanium/xxx machine for chess. calculating nps: 8 way opteron: 8 * 200k nps = 1.6 MLN - 2GB hashtable 64 way SGI altix 3000 (latency 2-3 us to 50% of processors): 64 * 100k nps = 6.4 MLN - 128GB hashtable Give me the 64 way itanium in that case :)
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.