During my PhD I performed all my calculation using fortran (90 and
on). I also learned and implemented openmp and MPI in some of my
codes. However the queue system of the computing machines I had at
that time makes impossible to take advantage of the parallelization,
since the delay introduced to get a slot with 4 processors was
equivalent to the sequential run.
Later I have tried to parallelize some codes with MPI in an IBM
PowerSeries running AIX, but the administrator had a lot of problems
to successfully install MPI.
Recently I have been exploring the possibility to use a GRID for
running parallel jobs, but after reading some reports it seems that
the implementation of MPI into a grid is quite difficult. Therefore I
am still coding in a sequential way.
The first time I heard about co-arrays was in the Alexanders post. I
should admit that I am quite excited about the idea. Mostly because
of co-arrays can guarantee to have a "standard" MPI-like environment
and may be provide an easy solution to some of the problems I had in
the past. Moreover, I would be glad to do some test if someone knows a
beta testing project.
I hope this information could be of some help.
Best regards.
Jose M. Llorens
> I'm currently updating our Fortran Resource file
> and wanted to get a feel for how many people were
> involved in parallel programming in Fortran.
>
> the current file can be found at
>
> http://www.kcl.ac.uk/fortran/pdfs/fortran_resources.pdf
>
> In that file we identify the following types
> of parallel programming
>
> automatic
> co-array fortran
> hpf
> mpi
> openmp
> posix threads
>
> So could you take the time to answer the following questions.
>
> do you do parallel programming?
>
> if so which method do you use?
>
> if you currently are doing parallel programming
> would you move to co-arrays if they were
> available?
>
> would you move to another hardware platform and operating
> system to be able to use co-arrays?
>
> Cheers
>
> Ian Chivers
>
>
|