[OMPI devel] 1.4.2rc1 available for test

2010-04-13 Thread Ralph Castain
Hi folks I rolled the 1.4.2 release candidate 1 tarball today. It is available on the web site: http://www.open-mpi.org/software/ompi/v1.4/ There is no rpm version available - just tarballs. Please give it a whirl and let us know of any problems. Thanks Ralph

Re: [OMPI devel] inquiring about openmpi

2010-04-13 Thread Jeff Squyres
Yikes! I totally mis-read your email as an inquiry about LAM/MPI. Looking at it closer, I see that you are asking about Open MPI, but using LAM as a reference. Sorry about that! You probably want to look in ompi/proc/proc.h. On Apr 13, 2010, at 10:23 AM, luyang dong wrote: > dear teachers

Re: [OMPI devel] inquiring about openmpi

2010-04-13 Thread Jeff Squyres
This is the list for Open MPI developers, not LAM/MPI. We ex-LAM/MPI developers are on this list, but we're not inclined to answer LAM questions on this list. :-) Heck, we're not inclined to answer LAM questions at all, if we can avoid it. :-) :-) :-) Specifically: LAM is pretty dead. We h

[OMPI devel] inquiring about openmpi

2010-04-13 Thread luyang dong
dear teachers:     LAM/MPI constructs communication channel via process location identified by  type struct _gps in LAM universe. struct _gps{  int4 gps_node;  int4 gps_pid;  int4 gps_idx;  int4 gps_granks; }. In order to know of other proces

Re: [OMPI devel] problem when binding to socket on a singlesocket node

2010-04-13 Thread Jeff Squyres
On Apr 13, 2010, at 3:27 AM, Ralph Castain wrote: > I actually went back/forth on that as well - I personally think it might be > better to just have warn and quiet, with warn being the default. The warning > could be generated with orte_show_help so the messages would be consolidated > across

Re: [OMPI devel] problem when binding to socket on a single socket node

2010-04-13 Thread Nadia Derbey
On Tue, 2010-04-13 at 01:27 -0600, Ralph Castain wrote: > On Apr 13, 2010, at 1:02 AM, Nadia Derbey wrote: > > > On Mon, 2010-04-12 at 10:07 -0600, Ralph Castain wrote: > >> By definition, if you bind to all available cpus in the OS, you are > >> bound to nothing (i.e., "unbound") as your process

Re: [OMPI devel] problem when binding to socket on a single socket node

2010-04-13 Thread Ralph Castain
On Apr 13, 2010, at 1:02 AM, Nadia Derbey wrote: > On Mon, 2010-04-12 at 10:07 -0600, Ralph Castain wrote: >> By definition, if you bind to all available cpus in the OS, you are >> bound to nothing (i.e., "unbound") as your process runs on any >> available cpu. >> >> >> PLPA doesn't care, and I

Re: [OMPI devel] problem when binding to socket on a single socket node

2010-04-13 Thread Nadia Derbey
On Mon, 2010-04-12 at 10:07 -0600, Ralph Castain wrote: > By definition, if you bind to all available cpus in the OS, you are > bound to nothing (i.e., "unbound") as your process runs on any > available cpu. > > > PLPA doesn't care, and I personally don't care. I was just explaining > why it gene