[Date Prev][Date Next] [Thread Prev][Thread Next] [Date Index] [Thread Index]

Re: MPICH 1.2 performance



In 02 Aug 2000 12:06:27 -0400 Camm Maguire <camm@enhanced.com> cum veritate scripsit :

> Greetings!

Hi!


> > I haven't yet looked into LAM.
> > Does it work as expected, including update-alternatives ? 
> > # i.e. should mpich provide "mpi" ?
> Yes, it should.  Mark and I originally spent some considerable effort
> trying to make the mpi on Debian as implementation independent as
> possible.  If anyone has occasion to do so in the course of their
> work, I encourage them to test the mpi switching on Debian and report
> back problems here.  Of course, LAM and MPICH are source, not binary,
> compatible, alas, so a recompile is required.

I've tried doing it with potato lam, and custom-built mpich 1.2.0-3, 
and I had problems with update-alternatives.
I'll need to look at it. Basically, lam is the default, and
using update-alternatives to set "mpi" to mpich (which should be enough?)
does not seem to work as expected. 
I had to remove "lam2-dev" to make mpich work. 

I haven't looked into it very closely yet. It might be because it's a potato.



regards,
	junichi

--
University: ti0113@mail4.doshisha.ac.jp    Netfort: dancer@netfort.gr.jp
dancer, a.k.a. Junichi Uekawa   http://www.netfort.gr.jp/~dancer
 Dept. of Knowledge Engineering and Computer Science, Doshisha University.
... Long Live Free Software, LIBERTAS OMNI VINCIT.



Reply to: