Re: [OMPI devel] PathScale 3.0 problems with Open MPI 1.2.[34]

2007-10-24 Thread Bogdan Costescu 

On Tue, 23 Oct 2007, Brian Barrett wrote:


  --without-memory-manager --enable-mca-static=btl-mx,mtl-mx


From what I understand from the FAQ, the above --enable-mca-static 
option would include statically linked MX support in libmpi. But I was 
building all support in (--enable-static --disable-shared) for other 
reasons anyway, so I guess that it wouldn't make any difference. I've 
already tried to build all shared (the 'configure' default) and this 
made no difference; --without-memory-manager is the only option which 
makes a difference.


Given that both Patrick and Brian recommend using 
"--without-memory-manager", I won't feel bad about doing it :-)


Thanks a lot !

--
Bogdan Costescu

IWR - Interdisziplinaeres Zentrum fuer Wissenschaftliches Rechnen
Universitaet Heidelberg, INF 368, D-69120 Heidelberg, GERMANY
Telephone: +49 6221 54 8869, Telefax: +49 6221 54 8868
E-mail: bogdan.coste...@iwr.uni-heidelberg.de

[OMPI devel] RFC: Add "connect" field to openib BTL INI file

2007-10-24 Thread Jeff Squyres 
WHAT: Add a "connect" field to the openib BTL INI file to specify  
which connect pseudo-component(s) (CPCs) can be used for wireup of a  
given device.


WHY: 2 new CPCs are being written (by different parties); certain  
devices can only use certain CPCs.


WHERE: Mainly in btl_openib_ini.*, but probably also touch a few  
other btl_openib_* files.


WHEN: Sometime in the near future; no specific time set.

TIMEOUT: Friday, 2 Nov 2007



In addition to the already-existing "oob" connect pseudo-component  
(CPC), two more are in the works:


- XRC: Pasha/Mellanox is working on a new XRC CPC for ConnectX HCAs.

- RDMA CM: Welcome to Jon Mason from Open Grid Computing (for  
Chelsio) who will be doing iWARP-related work in the udapl and/or  
openib BTLs.  Either he or I will be implementing the RDMA CM-based CPC.


My proposal is that the "connect" field can be added to the INI file  
and take a comma-delimited list of values of acceptable CPCs for a  
given device.  For example, the ConnectX HCA can take the following  
value:


connect = xrc, rdma_cm, oob

Meaning:

- first, try the XRC CPC to try to make the connection
- if that fails, try the RDMA CM CPC
- if that fails, try the OOB CPC
- if that fails, fail the connection

iWARP-based NICs can use the following value:

connect = rdma_cm

If no "connect" value is specified, then default value of "oob,  
rdma_cm" can be assumed (possibly someday changing to "rdma_cm, oob").


I mention this here on the devel list because disparate groups are  
working on different CPC's; coordination will be required to  
implement this arbitration mechanism.


Comments?

--
Jeff Squyres
Cisco Systems

Re: [OMPI devel] PML cm and heterogeneous support

2007-10-24 Thread Jeff Squyres 

George / Patrick / Rich / Christian --

Any idea why that's there?  Is that because portals, MX, and PSM all  
require homogeneous environments?



On Oct 18, 2007, at 3:59 PM, Sajjad Tabib wrote:



Hi,

I am tried to run an MPI program in a heterogeneous environment  
using the pml cm component. However, open mpi returned with an  
error message indicating that PML add procs returned "Not  
supported". I dived into the cm code to see what was wrong and I  
came upon the code below, which basically shows that if the  
processes are running on different architectures, then return "not  
supported". Now, I'm wondering whether my interpretation is correct  
or not. Is it true that the cm component does not support a  
heterogeneous environment? If so, will the developers support this  
in the future? How could I get around this while still using the cm  
component? What will happen if I rebuilt openmpi without these  
statements?


I would appreciate your help.

 Code:

mca_pml_cm_add_procs(){

#if OMPI_ENABLE_HETEROGENEOUS_SUPPORT
107 for (i = 0 ; i < nprocs ; ++i) {
108 if (procs[i]->proc_arch != ompi_proc_local()->proc_arch) {
109 return OMPI_ERR_NOT_SUPPORTED;
110 }
111 }
112 #endif
.
.
.
}

Sajjad Tabib
___
devel mailing list
de...@open-mpi.org
http://www.open-mpi.org/mailman/listinfo.cgi/devel



--
Jeff Squyres
Cisco Systems

Re: [OMPI devel] PML cm and heterogeneous support

2007-10-24 Thread Brian Barrett 
No, it's because the CM PML was never designed to be used in a  
heterogeneous environment :).  While the MX BTL does support  
heterogeneous operations (at one point, I believe I even had it  
working), none of the MTLs have ever been tested in heterogeneous  
environments and it's known the datatype usage in the CM PML won't  
support heterogeneous operation.


Brian

On Oct 24, 2007, at 6:21 PM, Jeff Squyres wrote:


George / Patrick / Rich / Christian --

Any idea why that's there?  Is that because portals, MX, and PSM all
require homogeneous environments?


On Oct 18, 2007, at 3:59 PM, Sajjad Tabib wrote:



Hi,

I am tried to run an MPI program in a heterogeneous environment
using the pml cm component. However, open mpi returned with an
error message indicating that PML add procs returned "Not
supported". I dived into the cm code to see what was wrong and I
came upon the code below, which basically shows that if the
processes are running on different architectures, then return "not
supported". Now, I'm wondering whether my interpretation is correct
or not. Is it true that the cm component does not support a
heterogeneous environment? If so, will the developers support this
in the future? How could I get around this while still using the cm
component? What will happen if I rebuilt openmpi without these
statements?

I would appreciate your help.

 Code:

mca_pml_cm_add_procs(){

#if OMPI_ENABLE_HETEROGENEOUS_SUPPORT
107 for (i = 0 ; i < nprocs ; ++i) {
108 if (procs[i]->proc_arch != ompi_proc_local()- 
>proc_arch) {

109 return OMPI_ERR_NOT_SUPPORTED;
110 }
111 }
112 #endif
.
.
.
}

Sajjad Tabib
___
devel mailing list
de...@open-mpi.org
http://www.open-mpi.org/mailman/listinfo.cgi/devel



--
Jeff Squyres
Cisco Systems

___
devel mailing list
de...@open-mpi.org
http://www.open-mpi.org/mailman/listinfo.cgi/devel