[Top][All Lists]
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
Re: Fortran libraries on the Blue Gene with mpi
From: |
Christian Rössel |
Subject: |
Re: Fortran libraries on the Blue Gene with mpi |
Date: |
Fri, 17 Apr 2009 12:35:05 +0200 |
User-agent: |
Thunderbird 1.5.0.14 (X11/20060911) |
John R. Cary wrote:
> Hi Ralf,
>
> Ralf Wildenhues wrote:
>> Hello John,
>>
>>
>>
>> OK. That's fairly easy to support in Libtool then: the only thing we
>> need to get right is to turn off shared library support completely for
>> BG/L.
>>
>
> I gave the wrong impression. This is a BG/P. My previous reference to the
> compilers was because the BG/L compilers (I thought) are the same.
>
>> Can we assume bg* produces code for the compute nodes only? Let's turn
>> the question around: how can we reliably detect that code is being
>> compiled for the compute nodes?
>>
>
> I don't know for sure, but the experiments at the end of this indicate that
> bg compiled code works on the login nodes.
Hi Ralf and John,
Code compiled with bg* compiler wrappers is supposed to run on the
compute nodes. That is the purpose of the bg* wrappers. This also
applies to the mpi* compiler wrappers. Code compiled with the "normal"
compilers (e.g. xlc) does not run on the compute nodes.
Cheers,
Christian
- Fortran libraries on the Blue Gene with mpi, John R. Cary, 2009/04/13
- Re: Fortran libraries on the Blue Gene with mpi, Ralf Wildenhues, 2009/04/14
- Re: Fortran libraries on the Blue Gene with mpi, John R. Cary, 2009/04/16
- Re: Fortran libraries on the Blue Gene with mpi,
Christian Rössel <=
- Re: Fortran libraries on the Blue Gene with mpi, Ralf Wildenhues, 2009/04/18
- Re: Fortran libraries on the Blue Gene with mpi, John R. Cary, 2009/04/18
- Re: Fortran libraries on the Blue Gene with mpi, Ralf Wildenhues, 2009/04/19