I have reported as long ago as 1.4.5rc2 (see
http://www.open-mpi.org/community/lists/devel/2012/01/10256.php ) that Open
MPI does not build with the Intel compilers (versions 9.1 and 10.0 tested)
on IA64.

This is still true with 1.6.2rc2, and I doubt anybody plans to fix this
soon, if ever.
HOWEVER, the following still appears in OMPI's README and suggests to the
casual reader that ICC 9.1 and 1.0 on IA64 should probably work:

> - The Intel 9.0 v20051201 compiler on IA64 platforms seems to have a
>   problem with optimizing the ptmalloc2 memory manager component (the
>   generated code will segv).  As such, the ptmalloc2 component will
>   automatically disable itself if it detects that it is on this
>   platform/compiler combination.  The only effect that this should
>   have is that the MCA parameter mpi_leave_pinned will be inoperative.

There is no other mention of IA64 in the README and the other Intel
compiler issues are not related.

So, I think the README could use an update with respect to IA64 and ICC.
Note that I can build w/ gcc just fine on IA64, but I'd not exactly break
down in tears if OMPI dropped support for IA64 entirely.

-Paul

On Tue, Sep 11, 2012 at 7:10 AM, Jeff Squyres <jsquy...@cisco.com> wrote:

> 1.6.2rc2 is out -- please test:
>
>     http://www.open-mpi.org/software/ompi/v1.6/
>
> Changes since rc1:
>
> - VT compile fix on Solaris
> - rmaps segv fix
>
> --
> Jeff Squyres
> jsquy...@cisco.com
> For corporate legal information go to:
> http://www.cisco.com/web/about/doing_business/legal/cri/
>
>
> _______________________________________________
> devel mailing list
> de...@open-mpi.org
> http://www.open-mpi.org/mailman/listinfo.cgi/devel
>



-- 
Paul H. Hargrove                          phhargr...@lbl.gov
Future Technologies Group
Computer and Data Sciences Department     Tel: +1-510-495-2352
Lawrence Berkeley National Laboratory     Fax: +1-510-486-6900

Reply via email to