Re: updating mpi-defaults (decommissioning lam)
- To: firstname.lastname@example.org
- Subject: Re: updating mpi-defaults (decommissioning lam)
- From: Manuel Prinz <email@example.com>
- Date: Thu, 19 May 2011 22:31:34 +0200
- Message-id: <[🔎] 20110519203134.GC9329@woodstock>
- In-reply-to: <1302452423.30269.90.camel@workhorse>
- References: <1302152322.5206.17.camel@pug> <20110407142531.GO6199@onerussian.com> <20110407181423.GA1845@xanadu.blop.info> <1302224087.7214.4.camel@pug> <20110409121240.GA6273@woodstock> <1302419585.4651.20.camel@pug> <1302452423.30269.90.camel@workhorse>
On Sun, Apr 10, 2011 at 12:20:23PM -0400, Adam C Powell IV wrote:
> FWIW, my "vote" would be to go ahead and replace LAM with MPICH2 on the
> non-OpenMPI arches now, and remove LAM and MPICH1 from the archive. Or
> if we decide MPICH2 is better than OpenMPI, default to that everywhere.
> Either way, let's get rid of LAM and MPICH1, and switch mpi-defaults,
> sooner rather than later.
This seems reasonable and we should go that route. The proposed plan (as
I understand it) would be:
- Update mpi-defaults to use MPICH2 (in progress). binNMU all packages
and remove LAM from the archive.
Open MPI arch support:
- Update openmpi to build on all arches. (Progressing, but slowly.)
- Once we have full arch support, decide what to do with mpi-defaults.
So these are basically two orthogonal changes, and the new mpi-defaults
helps the LAM removal. I will upload a fixed mpi-defaults soon so that
the LAM removal can take place ASAP. I'm sorry for the inconvenience that
was caused by my quasi-MIA! Though times…