Thank you for your reply.
I understand your current plan. However, the feature is realy usefull
for some applications that requires parallel I/O transactions in high
performance. (i.e. highest-level parallelism in MPI-IO functionality)
Thus it is very nice to hear its support in the near future.
Regards,
> Hi,
>
> I am extremely sorry for the delayed response. We do not plan to
> support this in the near future, but we would like to support this
> someday in the future.
>
> Thanks.
> --
> Shashwat Srivastav
> LAM / MPI Developer (http://www.lam-mpi.org)
> Indiana University
> http://www.cs.indiana.edu/~ssrivast
>
>
> On Dec 1, 2003, Masahiro TATSUMI wrote:
>
> > Hi, all.
> >
> > I tried to migrate from mpich, but I found the
> > MPI_TYPE_CREATE_INDEXED_BLOCK is not supported by
> > LAM/MPI 7.0.3.
> >
> > Is there any future plan to support it?
> >
> > Regards.
> >
> > ---
> > Masahiro TATSUMI, Ph.D. <tatsumi_at_[hidden]>
> > Fuel Eng and Dev. Dpt., Nuclear Fuel Industries, Ltd.
> > ---
> > [External email from NFI]
> >
> > _______________________________________________
> > This list is archived at http://www.lam-mpi.org/MailArchives/lam/
>
> _______________________________________________
> This list is archived at http://www.lam-mpi.org/MailArchives/lam/
Masahiro TATSUMI, Ph.D. <tatsumi_at_[hidden]>
Fuel Eng and Dev. Dpt., Nuclear Fuel Industries, Ltd.
|
