Hi,
I am using Altair Feko 2022.3 and try to run a parallel computation across 2 of my Windows PC.
I had comfirmed that 2 hosts can reach to each other, but when executing the runfeko using
Intel(R) MPI Library, Version 2021.2 Build 20210318
I got the following error message:
Abort(343488527) on node 0 (rank 0 in comm 0): Fatal error in PMPI_Comm_dup: Other MPI error, error stack: PMPI_Comm_dup(168)..................: MPI_Comm_dup(MPI_COMM_WORLD, new_comm=00007FF670778EE0) failed PMPI_Comm_dup(153)..................: MPIR_Comm_dup_impl(51)..............: MPII_Comm_copy_with_info(686).......: MPIR_Get_contextid_sparse_group(490): MPIR_Allreduce_intra_auto_safe(241).: MPIR_Bcast_intra_auto(233)..........: MPIR_Bcast_intra_binomial(192)......: Failure during collective
After enable the debug message, I found it seems had some gathering issuse with the error message:
Incorrect Gather result in I_MPI_Pinning_printing
at the bottom of output.
With littel info to work with, I have no idea for now to resolve this problem. Can anyone help me, Thanks a lot.
Ps: Full debug output is in the attached text file.
連結已複製
Hello,
Thank you for reaching out to the Intel communities.
We have noticed that you are currently utilizing an unsupported version of Intel MPI. In order to resolve this issue, we kindly ask that you upgrade to the latest version of Intel MPI and execute your code once again.
To check which versions of Intel MPI are supported, please refer to the following link: https://www.intel.com/content/www/us/en/developer/articles/release-notes/intel-parallel-studio-xe-supported-and-unsupported-product-versions.html
If the problem persists even after upgrading to the latest Intel MPI 2021.9, please provide us with a sample reproducer code and the specifications of the hardware and operating system that you are currently using.
Thank you and best regards,
Aishwarya
