[CHiPPS] Fwd: Questions on Blis
alessandro.tiberi at gmail.com
Mon Mar 16 05:24:58 EDT 2009
>> We are running Blis (mpi built) on a single machine with 16Gb Ram and
>> two quadcore (opteron), so that's a total
>> of eight cores. We tried several degrees of parallelism (# of process),
>> from 2 to 8. The bottom line seems to be
>> that the more processes we use, the sooner it runs out of memory.
> That makes sense, given that CHiPPS is currently architected for a
> distributed environment. When Ted says that more processes can
> alleviate the memory issue, he is thinking of distributing the processes
> among different nodes in a cluster or grid, each with its own memory.
Yes, that was clear enough.
>> However, from Alp's log, it appears that relatively few nodes are
>> queued (about 13K nodes with 2 processes running and 7K with 6.)
>> (btw, I have been told that famous commercial software has no problem
>> with these instances even if running on much lower profile platforms
>> although I did not personally try
> Well, CHiPPS is a development code at this point, so there are bound to
> be lots of opportunities to improve it!
Just to be clear, I think that the work done with CHiPPS is great, the
comparison was just to
say that our instaces are not (in some sense) too demanding.
>> I do not have a very strong feeling about this (On the one hand even if
>> vectors are sparse they eventually are just a sequence of numbers, and
>> hopefully they are far enough from being uniformly distributed, so we
>> should gain something from compression...).
> That's likely to be an empirical question, but probably worth a try.
> Writing idle subtrees to disk is also definitely worth a try.
Well, I guess I will eventually try to do both.
More information about the CHiPPS