I am puzzled by your question.
The big achievement of LAM is to support heterogeneous clusters. I
currently mix executables compiled in 64-bit mode using 64-bit LAM on a
pwr3 ibm and executables compiled on 32-bit Linux PCs using the 32-bit
LAM.
I have already included comments about heterogeneous clusters in the
repository of our DIRCCR12 code (have a look at the manual on
http://www-laog.obs.ujf-grenoble.fr/~valiron/ccr12/index.html )
I am afraid you make a confusion between 32/64 bit addressing (which is
related to the platform and usually cannot be changed) and the default
integer size which is a compiler option.
You should pay attention to several points:
1) use THE SAME LAM version
2) have COMPATIBLE INTEGER and FLOATING formats. You can't mix a non-IEEE
machine with an IEEE one. You can't mix a LAM compiled with default 32 bit
integers with a LAM compiled with default 64 bit integers. But you can mix
a LAM compiled on a big endian machine with 64 bit address space with a
LAM compiled on a little endian machine with 32 bit address space.
And you can benefit of the large address space on the 64 bit machine. This
sometimes helps...
Just make sure the compiler options for building LAM provide the same
default size for integers on both platforms.
3) manage your PATH in such a way that you pick the relevant executables
on each machine (using a schema file is very handy).
Best.
Pierre.
On Thu, 12 Aug 2004, William Boatin wrote:
> I have four machines on which i have installed lam 7.0.6
> two of these macines are 64 bit machines, and so lam went ahead and
> compiled/built 64 bit versions of itself on those machines
> for reasons mentioned in the archives, 64 and 32 bit versions of lam are not
> compatible.
> i have searched in the documentation and the archives but i cant find
> anything that tells me how to compile lam in 32 bit mode on a 64 bit
> machine.
> what flags do i have to set and at what point?
> thanks
>
> _________________________________________________________________
> Don’t just search. Find. Check out the new MSN Search!
> http://search.msn.click-url.com/go/onm00200636ave/direct/01/
>
> _______________________________________________
> This list is archived at http://www.lam-mpi.org/MailArchives/lam/
>
--
Soutenez le mouvement SAUVONS LA RECHERCHE :
au national : http://recherche-en-danger.apinc.org/
sur Grenoble : http://recherchegrenoble.free.fr et http://etatsg.free.fr
_/_/_/_/ _/ _/ Dr. Pierre VALIRON
_/ _/ _/ _/ Laboratoire d'Astrophysique (UMR 5571 CNRS)
_/ _/ _/ _/ Observatoire de Grenoble / U. Joseph Fourier
_/_/_/_/ _/ _/ BP 53 F-38041 Grenoble Cedex 9 (France)
_/ _/ _/
_/ _/ _/ http://www-laog.obs.ujf-grenoble.fr
_/ _/ _/ mailto:Pierre.Valiron_at_[hidden]
_/ _/_/ Phone / Fax: +33 (0)4 76.51.47.87 / (0)4 76.44.88.21
|
