[OMPI users] Limitation of MPI_BCAST

Hi, I am using openmpi 1.6 and when I tried to send a large array through MPI_BCAST in fortran. The number of count is larger than 3 billions. Although I compiled openmpi and my code with the option to declare my fortran integer as 64 bit long in linux. I found out that fortran pbcast_f.c will c

[OMPI users] [SPAM:## 71%] checkpoint --term core dump

Hi, I encountered a core dump when using ompi-checkpoint --term pid. Here is the trace: [genova:01808] *** Process received signal *** [genova:01808] Signal: Segmentation fault (11) [genova:01808] Signal code: Address not mapped (1) [genova:01808] Failing at address: 0x90 [genova:01808] [ 0] /

[OMPI users] Question on MPI_Reduce_scatter limit

Dear all, I am using openmpi 1.6 on linux. I have a question on MPI_Reduce_scatter. I try to see how large the data can push through MPI_Reduce_scatter using the following code. size = (long) 1024*1024*1024*4; for(k=1;k<=16;++k) { bufsize = k*size/16; for(i=0;i) at epoll.c:215 #2 0x

[OMPI users] hanging in ioctl in solaris 5.10 openmpi 1.6

Hi, My simple test case hangs in solaris 5.10 in openmpi 1.6. It does not have problem in linux. Also, if multiple processes run on the same machine, it does not have problem too. I used debugger to see where it hanged, it appear to be at 242 res = ioctl(devpollop->dpfd, DP_POLL, &dvp

[OMPI users] fortran program with integer kind=8 using openmpi‏

Dear all, Thank you for all responses. There is another problem using -fdefault-integer-8. I am using 1.6.. For the i8: configure:44650: checking for the value of MPI_STATUS_SIZE configure:44674: result: 3 Fortran INTEGERs configure:44866: checking if Fortran compiler works configure:44895: /u

Re: [OMPI users] fortran program with integer kind=8 using openmpi

My concern is how do the C side know fortran integer using 8 bytes? My valgrind check show something like: ==8482== Invalid read of size 8 ==8482==at 0x5F4A50E: ompi_op_base_minloc_2integer (op_base_functions.c:631) ==8482==by 0xBF70DD1: ompi_coll_tuned_allreduce_intra_recursivedoubling

[OMPI users] fortran program with integer kind=8 using openmpi

Hi, I try to compile my fortran program in linux with gfortran44 using option -fdefault-integer-8, then all my integer will of kind=8. My question is what should I do with openmpi? I am using 1.6, should I compile openmpi with the same options? Will it get the correct size of MPI_INTEGER and

[OMPI users] hang in mpi_allreduce in single linux machine‏

Hi, When I ran multiple processes in a single machine, the programs are hanging in mpi_allreduce in different points during different runs. I am using 1.3.4. When I used different machines to run the processes, it is OK. Also, when I recompiled open mpi in debug mode, the problem goes away.