Re: [OMPI users] Windows: MPI_Allreduce() crashes when using MPI_DOUBLE_PRECISION

Did you tried these test programs? Or any suggestion to overcome this bug??? Thank you. -Hiral On Fri, May 13, 2011 at 11:20 AM, hi wrote: > Hi Rainer, > >> Does REAL work for You? > No. > I am observing same errors (see below) even with INTEGER; please find > the

Re: [OMPI users] TotalView Memory debugging and OpenMPI

Can you send your diff in unified form? On May 11, 2011, at 4:05 PM, Peter Thompson wrote: > We've gotten a few reports of problems with memory debugging when using > OpenMPI under TotalView. Usually, TotalView will attach tot he processes > started after an MPI_Init. However in the case

Re: [OMPI users] btl_openib_cpc_include rdmacm questions

Thanks, I though of looking at ompi_info after I sent that note sigh. SEND_INPLACE appears to help performance of larger messages in my synthetic benchmarks over regular SEND. Also it appears that SEND_INPLACE still allows our code to run. We working on getting devs access to our system and

Re: [OMPI users] btl_openib_cpc_include rdmacm questions

Sorry typo 314 not 313, Brock Palen www.umich.edu/~brockp Center for Advanced Computing bro...@umich.edu (734)936-1985 On May 17, 2011, at 2:02 PM, Brock Palen wrote: > Thanks, I though of looking at ompi_info after I sent that note sigh. > > SEND_INPLACE appears to help performance of

Re: [OMPI users] Scheduling dynamically spawned processes

Thanks for pointing this out - it's an error in our man page. I've fixed it on our devel trunk and will get it push'd to the release. On May 16, 2011, at 1:14 PM, Thatyene Louise Alves de Souza Ramos wrote: > Ralph, thank you the reply. > > I just try what you said and it works! I didn't

Re: [OMPI users] Scheduling dynamically spawned processes

Hi Thatyene and Ralph. Now I got the solution and it worked fine. I did not try spawn_multiple because I've read the same documentation Thanks so much! On Tue, May 17, 2011 at 5:13 PM, Ralph Castain wrote: > Thanks for pointing this out - it's an error in our man page.