[RegCNET] RegCM & MPI performance

[James Ciarlo`]

Dear RegCNET,

I would like to be more efficient with RegCM simulations, while we haven't
yet done a study of how the RegCM performs on our cluster I was wondering
if anyone has done any studies on model performance with MPI.

Details such as changing the number of processors with the same experiment,
how the MPI splits the domain, how a change of domain effects the process
of the experiments.

Thanks and regards,
James
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <https://lists.ictp.it/pipermail/regcnet/attachments/20160701/1f78c805/attachment.html>