topic Re: SEGFAULT on repeated MPI_Comm_connect|MPI_Comm_accept/MPI_Comm_disconnect in Intel® oneAPI Math Kernel Library

SEGFAULT on repeated MPI_Comm_connect|MPI_Comm_accept/MPI_Comm_disconnect

menno — Mon, 21 Jun 2021 09:26:36 GMT

A simulation package I'm working on uses repeated communications between participants by connecting, sending data, then disconnecting. This is not something I can change.

When I run this on Intel MPI (I tried versions 2020 Update 1 and 2), this gives a segmentation fault after several connect/send/disconnect cycles. The exact number varies from several tens to a few thousand.

I have created a simple reproduction program (see attached).

This works fine if I use OpenMPI 4.0.2 compiled with GCC 8.3.0 and compile the program with the mpicc from OpenMPI, but segfaults with Intel compiler and MPI.

It would be nice if this can be corroborated. And if so, how to solve the problem.

Re: SEGFAULT on repeated MPI_Comm_connect|MPI_Comm_accept/MPI_Comm_disconnect

Gennady_F_Intel — Mon, 21 Jun 2021 11:50:31 GMT

Menno,

I see your example makes the MPI calls only, therefore I would recommend you to ask this question to the MPI forum instead of MKL ones.

Re: SEGFAULT on repeated MPI_Comm_connect|MPI_Comm_accept/MPI_Comm_disconnect

menno — Mon, 21 Jun 2021 12:52:42 GMT

If you can redirect me to the MPI forum? I couldn't find any MPI-specific fora in the forum lists, and I saw other MPI-related questions being asked here, so I posted here. I'd be happy to use a more suitable forum.

Found it.

Re: SEGFAULT on repeated MPI_Comm_connect|MPI_Comm_accept/MPI_Comm_disconnect

menno — Mon, 21 Jun 2021 12:52:03 GMT

Re-posted to correct category https://community.intel.com/t5/Intel-oneAPI-HPC-Toolkit/SEGFAULT-on-repeated-MPI-Comm-connect-MPI-Comm-accept-MPI-Comm/m-p/1291702/highlight/true#M8479

Re:SEGFAULT on repeated MPI_Comm_connect|MPI_Comm_accept/MPI_Comm_disconnect

MRajesh_intel — Tue, 22 Jun 2021 06:51:44 GMT

Hi,

Thanks for posting your query. We are closing this thread as you have moved the thread to another forum. We will no longer respond to this thread and if you require any additional assistance from Intel, please start a new thread.

Any further interaction in this thread will be considered community only.

Have a Good day.

Regards

Rajesh.