[OMPI users] Compilation errors: Unexpected EOF while looking for matching `'' on 1.4.5

2012-03-08 Thread Robert Collyer
The libtool that is constructed for the configuration I'm using (below) has bug when it is constructing compiler_lib_search_path in both the CXX and FC sections, as follows compiler_lib_search_path="-L/lib -L/usr/lib -L/usr/local/lib' ..." where the ellipses is just more directories. The error

Re: [OMPI users] compilation error with pgcc Unknown switch

2012-03-08 Thread Abhinav Sarje
Thanks Jeff, and all; I will stick to the GNU compilers for now. On Fri, Mar 9, 2012 at 7:05 AM, Jeffrey Squyres wrote: > I talked to Brian about this, and he agrees with Nathan: don't use PGI on the > Cray (I'm acting as an intermediary here -- I don't care about the Cray > platform at all :-)

Re: [OMPI users] compilation error with pgcc Unknown switch

2012-03-08 Thread George Bosilca
The opal_atomic_swap_64 function is always supposed to be inlined or not be present at all. However, if not present then it shouldn't be used (as no atomic on 64 bits data are supported by the architecture). george. On Mar 6, 2012, at 12:39 , Nathan Hjelm wrote: > I think the problem is that

Re: [OMPI users] compilation error with pgcc Unknown switch

2012-03-08 Thread Jeffrey Squyres
I talked to Brian about this, and he agrees with Nathan: don't use PGI on the Cray (I'm acting as an intermediary here -- I don't care about the Cray platform at all :-) ). They have always used GNU and it works fine. That being said, there may well be something broken with our non-inlined ass

Re: [OMPI users] Illegal Instruction on Checkpoint with BLCR

2012-03-08 Thread Reuti
Hi, Am 08.03.2012 um 19:02 schrieb Linton, Tom: > We have a legacy application that runs fine on our cluster using Intel MPI. > We ported it to OpenMPI so that we could use BLCR and it runs fine but > checkpointing is not working properly: > > 1. when we checkpoint with more than 1 core, it e

[OMPI users] Illegal Instruction on Checkpoint with BLCR

2012-03-08 Thread Linton, Tom
We have a legacy application that runs fine on our cluster using Intel MPI. We ported it to OpenMPI so that we could use BLCR and it runs fine but checkpointing is not working properly: 1. when we checkpoint with more than 1 core, it executes with the error: mpirun noticed that proces

Re: [OMPI users] InfiniBand path migration not working

2012-03-08 Thread Shamis, Pavel
Jeremy, Finally I had a chance to look at log file. Initially all qps are created on port 1, and in the same time alternative path loaded (ports 2, lids 4 and 2 ). I guess in some point you switch off port 1, APM even is reported because the alternative path is active now, and from some reason