Re: [OMPI users] MPI_AllReduce() deadlock on IB

2011-03-25 Thread Brock Palen
Running with rdmacm the problem does seam to resolve its self, The code is large and complicated, but the problem does appear to arise regularly when ran. Just FYI, can I collect extra information to help find a fix? Brock Palen www.umich.edu/~brockp Center for Advanced Computing bro...@umich.ed

Re: [OMPI users] Is there an mca parameter equivalent to -bind-to-core?

2011-03-25 Thread Jeff Squyres
On Mar 24, 2011, at 9:38 PM, Gus Correa wrote: > Hence, the two contradictory values of mpi_paffinity_alone (1 and 0) reported > by 'ompi_info -all', really seem to have been nothing but a cheap plot by > Jeff to emulate the conspiracy against my sanity long held by the cosmogenic > flipping bi

Re: [OMPI users] Is there an mca parameter equivalent to -bind-to-core?

2011-03-25 Thread Gus Correa
Jeff Squyres wrote: On Mar 24, 2011, at 9:38 PM, Gus Correa wrote: Hence, the two contradictory values of mpi_paffinity_alone (1 and 0) reported by 'ompi_info -all', really seem to have been nothing but a cheap plot by Jeff to emulate the conspiracy against my sanity long held by the cosmogen