Questions tagged [mvapich2]

MVAPICH2 is a high performance MPI 2.2 implementation for OpenFabrics and other high speed network interconnects. It is based on MPICH2 and MVICH and is provided as open source under BSD license.

33 questions
4
votes
1 answer

Toy program Fails using OpenMPI 1.6 but works with Mvapich2

I am trying to figure out why my version of OpenMPI 1.6 does not work. I am using gcc-4.7.2 on CentOS 6.6. Given a toy program (i.e. hello.c) #include #include #include int main(int argc, char * argv[]) { int…
irritable_phd_syndrome
  • 4,631
  • 3
  • 32
  • 60
4
votes
1 answer

How to tell MVAPICH2 to use tcp?

My application produces wrong results, if I use infiniband for the communication between two nodes (using MVAPICH2 as the MPI-implementation). OpenMPI offers the possibility to specify the network with $ mpirun --mca btl tcp,self ... is there…
4
votes
3 answers

MVAPICH hangs on MPI_Send for message larger than eager threshold

There is a simple program in c++ / mpi (mvapich), which sends an array of type float. When i use MPI_Send,MPI_Ssend,MPI_Rsend ,if the size of the data is more than the eager threshold(64k in my program), then during the call MPI_Send my program…
hgz
  • 41
  • 2
2
votes
1 answer

Mvapich2 (with IB) strange info after computing

I'm running example programs (hello-world & pi) with mvapich2 2.2. After computing I see info that looks like debug (in error thread). output thread Process 2 of 5 is on 37eff7e817ee Process 0 of 5 is on cb1479885879 Process 4 of 5 is on…
Ivister
  • 29
  • 3
2
votes
1 answer

MVAPICH2 RDMA-based communication without explicit PUT/GET use?

My cluster utilizes MVAPICH2 over Infiniband FDR and and I am considering the use of RDMA for my simulations. I am aware of the MPI_Put and MPI_Get calls for explicitly invoking RDMA operations, however I would like to know if this is the only way…
Tokth
  • 31
  • 4
2
votes
1 answer

Check if my MVAPICH has multi-threading enabled

I wonder if there is any command to show the enabled features of an MVAPICH installation similar to the one that we can find for OpenMPI: ompi_info Especially, I am interested in knowing if multi-thread support is enabled.
Bub Espinja
  • 4,029
  • 2
  • 29
  • 46
2
votes
1 answer

What does "Got unknown event 17 ... continuing ..." mean with MPI

I am running an MPI job and am getting this warning message: [comet-05-08.sdsc.edu:mpi_rank_10][async_thread] Got unknown event 17 ... continuing ... I am compiling with icc (ICC) 15.0.2 20150121 using MVAPICH 2.1. What does the message mean? Is it…
Richard
  • 56,349
  • 34
  • 180
  • 251
2
votes
1 answer

Infiniband vs. Gigabit ethernet, how do I control which is used by an MPI program

I have an MPI program that runs on a computer cluster that has both ethernet and Infiniband connectivity. When I compile with mpavich2's mpicc, it automatically links to the Infiniband libraries. Is there a way to control which network is used…
irritable_phd_syndrome
  • 4,631
  • 3
  • 32
  • 60
2
votes
1 answer

Comparing CPU utilization during MPI thread deadlock using mvapich2 vs. openmpi

I noticed that when I have a deadlocked MPI program, e.g. wait.c #include #include int main(int argc, char * argv[]) { int taskID = -1; int NTasks = -1; int a = 11; int b = 22; MPI_Status Stat; /* MPI…
irritable_phd_syndrome
  • 4,631
  • 3
  • 32
  • 60
2
votes
1 answer

Not enough locked memory (rdma_setup_startup_ring: cannot create cq)

I have an issue with the quantity of available memory in page locked on CentOS 7. After allocating nodes with slurm, when I launch a job with MPI (mvapich), I encounter the following error: Fatal error in MPI_Init: Other MPI error, error…
jyvet
  • 2,021
  • 15
  • 22
2
votes
0 answers

MPI + CUDA AWARE, concurrents kernels and MPI_Sendrecv

During my work, I've found a little problem. Now I'm using MVAPICH-GDR-2.05 and Open MPI 1.7.4 with CUDA 6.0. I'm working on the exchange of non contiguous elements between GPUs (like the columns of a matrix), and I'm trying to run two kernel's (one…
2
votes
1 answer

Mvapich MPI_Init_thread(mutiple_thread support) failed

I am using mvapich in a supercomputing cluster(PSB environment). I need to enable MPI_THREAD_MULTIPLE support to run my program. But the output of my program suggestes that MPI_Init_thread failed to enable MPI_THREAD_MULTIPLE. PBS scripts is…
user3392320
  • 67
  • 1
  • 8
1
vote
1 answer

Binding MPI processes on the second CPU socket with MVAPICH2.2

I'm using NUMA compute nodes where the network (Mellanox InfiniBand HCA) is connected to the second CPU socket (and NUMA node). Is there any environment variable to simply bind all MPI processes to the second CPU socket with MVAPICH2.2? The…
jyvet
  • 2,021
  • 15
  • 22
1
vote
0 answers

Precise definition of "MPI_THREAD_SERIALIZED"

Since MPI_THREAD_MULTIPLE is not as perform and stable as MPI_THREAD_SERIALIZED, I am trying to convert my MPI application to serialized. However, the exact definition of MPI_THREAD_SERIALIZED is not clear to me. Does it mean: Start and the end of…
xldrx
  • 21
  • 1
1
vote
1 answer

MVAPICH2-GDR has segmentation fault error

I am trying to use MVAPICH2-GDR for the simple hello world program. Although it can compile the code successfully, it has segmentation fault error in runtime. My platform has Redhat 6.5 and CUDA 7.5. So I downloaded the rpm file…
silence_lamb
  • 377
  • 1
  • 3
  • 12
1
2 3