Re: [OMPI users] problem starting a ompi job in a mix BE/LE cluster

On 6/2/2015 10:46 AM, Gilles Gouaillardet wrote: Steve, MCA_BTL_OPENIB_MODEX_MSG_{HTON,NTOH} do not convert all the fields of the mca_btl_openib_modex_message_t struct. I would start here ... Thanks. Cheers, Gilles On Wednesday, June 3, 2015, Jeff Squyres (jsquyres) mailto:jsquy...@

Re: [OMPI users] problem starting a ompi job in a mix BE/LE cluster

That's fine. But any pointers on where to start would be helpful and appreciated. On 6/2/2015 10:15 AM, Jeff Squyres (jsquyres) wrote: Steve -- I think that this falls directly in your prevue since you volunteered to maintain the openib BTL (this HCA ID thing is part of the openib BTL boots

Re: [OMPI users] problem starting a ompi job in a mix BE/LE cluster

In the master, the code is in opal/mca/btl/openib/btl_openib_component.c In the 1.8/1.10 series, the code is in the same file, but located under the ompi/mca/btl/openib directory > On Jun 2, 2015, at 8:14 AM, Steve Wise wrote: > > On 6/2/2015 10:04 AM, Ralph Castain wrote: >> >>> On Jun 2, 20

Re: [OMPI users] problem starting a ompi job in a mix BE/LE cluster

Steve, MCA_BTL_OPENIB_MODEX_MSG_{HTON,NTOH} do not convert all the fields of the mca_btl_openib_modex_message_t struct. I would start here ... Cheers, Gilles On Wednesday, June 3, 2015, Jeff Squyres (jsquyres) wrote: > Steve -- > > I think that this falls directly in your prevue since you v

Re: [OMPI users] problem starting a ompi job in a mix BE/LE cluster

Steve -- I think that this falls directly in your prevue since you volunteered to maintain the openib BTL (this HCA ID thing is part of the openib BTL bootstrapping). :-) > On Jun 2, 2015, at 10:04 AM, Ralph Castain wrote: > > >> On Jun 2, 2015, at 7:10 AM, Steve Wise wrote: >> >> On 6/1

Re: [OMPI users] problem starting a ompi job in a mix BE/LE cluster

On 6/2/2015 10:04 AM, Ralph Castain wrote: On Jun 2, 2015, at 7:10 AM, Steve Wise > wrote: On 6/1/2015 9:51 PM, Ralph Castain wrote: I’m wondering if it is also possible that the error message is simply printing that ID incorrectly. Looking at the code, it

Re: [OMPI users] problem starting a ompi job in a mix BE/LE cluster

> On Jun 2, 2015, at 7:10 AM, Steve Wise wrote: > > On 6/1/2015 9:51 PM, Ralph Castain wrote: >> I’m wondering if it is also possible that the error message is simply >> printing that ID incorrectly. Looking at the code, it appears that we do >> perform the network byte translation correctly w

Re: [OMPI users] problem starting a ompi job in a mix BE/LE cluster

On 6/1/2015 9:51 PM, Ralph Castain wrote: I’m wondering if it is also possible that the error message is simply printing that ID incorrectly. Looking at the code, it appears that we do perform the network byte translation correctly when we setup the data for transmission between the processes.

Re: [OMPI users] Fwd[2]: OMPI yalla vs impi

Hi, Mike! I have impi v 4.1.2 (- impi) I build ompi 1.8.5 with MXM and hcoll (- ompi_yalla) I build ompi 1.8.5 without MXM and hcoll (- ompi_clear) I start osu p2p: osu_mbr_mr test with this MPIs. You can find the result of benchmark in attached file(mvs10p_mpi.xls: list osu_mbr_mr) On 64 nodes

Re: [OMPI users] Memory usage for MPI program

Dear Nathan, After some initial debugging procedure, I found that the problem is with the CGNS (v 2.5) file which I am reading by each processor. The CGNS file which has 3-levels of userdefined data of descriptors/arrays is just read by each processor only for getting some texts, which in turn tak