Re: [AMBER-Developers] incompatible processor requirements in parallel tests

From: Volodymyr Babin <>
Date: Thu, 18 Feb 2010 22:35:27 -0500 (EST)

On Thu, February 18, 2010 17:20, Lachele Foley wrote:
> As fond as I am of the AMBER_NTHREADS idea, for the purpose of testing I
> think having several sets is perfectly acceptable. It just needs to be
> documented.

Thank you. On the other hand, similar effect can be easily achieved
using Jason's rules and a short script that sets -np and invokes
'make tests.NPcpus' for them.

> Another question: is there a preferred numprocs range for tests? That
> way, the docs can say something like "most parallel tests can be run using
> anywhere between 2 and 32 threads, but a few (see instructions below) have
> special requirements."

There is probably no single rule; I would run at least 2 threads
per sander communicator.



AMBER-Developers mailing list
Received on Thu Feb 18 2010 - 20:00:02 PST
Custom Search