[Beowulf] Definition of HPC

[Hearns, John]

-----Original Message-----
From: beowulf-bounces at beowulf.org [mailto:beowulf-bounces at beowulf.org] On Behalf Of Mark Hahn
Sent: 22 April 2013 18:41
To: Craig Tierney - NOAA Affiliate
Cc: Beowulf List
Subject: Re: [Beowulf] Definition of HPC

>> understood, but how did you decide that was actually a good thing?
>>
> Mark,
>
> Because it stopped the random out of memory conditions that we were having.

aha, so basically "rebooting windows resolves my performance problems" ;)

>> I'm guessing this may have been a much bigger deal on strongly NUMA
>> machines of a certain era (high-memory ia64 SGI, older kernels).

and the situation you're referring to was actually on Altix, right?
(therefore not necessarily a good idea with current machines and kernels.)



Mark, I don't understand your forcefulness here.

All modern compute nodes are essentially NUMA machines (I am assuming all are dual or more socket machines).
If caches are a large fraction of memory then you have increased memory requests from the foreign node.
Surely for HPC workloads resetting the system so that you get deterministic run times is a good thing?

Has anyone seen any studies on run times for HPC codes where caches are dropped before each job versus not?
It would be good to see if there really is a big spread in run time - as I think there should be.

(I am hoping someone will chip in here - you know who you are!)

The contents of this email are confidential and for the exclusive use of the intended recipient.  If you receive this email in error you should not copy it, retransmit it, use it or disclose its contents but should return it to the sender immediately and delete your copy.