QuantumATK Forum
QuantumATK => General Questions and Answers => Topic started by: Ambika kumari on July 18, 2022, 15:36
-
Dear Admin
I am getting this error. What does it mean.
Calculating Eigenvalues : cn113:UCM:22f42:cd0b2700: 686464132 us(686464132 us!!!): dapl async_event CQ (0x1de4450) ERR 0
cn113:UCM:22f42:cd0b2700: 686464166 us(34 us): -- dapl_evd_cq_async_error_callback (0x1d85f40, 0x1829490, 0x2b2acd0b1d30, 0x1de4450)
cn113:UCM:22f42:cd0b2700: 686464308 us(142 us): dapl async_event QP (0x1f2d5a0) Event 1
Kindly reply
-
Dear Admin
please answer this query . I am not able to proceed.
-
It looks like a bug in Intel MPI, see e.g.: https://community.intel.com/t5/Intel-oneAPI-HPC-Toolkit/Intel-MPI-2018-4-error/td-p/1137805
Here are some suggestions on what you can try:
- Try changing the parallelization scheme: try with either more/fewer OpenMP threads, more processes per k-points, etc
- Try setting I_MPI_FABRICS=shm:dapl in the submission script as suggested in the Intel Forum thread
- Try using a newer Intel MPI installation if available on the cluster (you don't have to use the one shipped with QuantumATK). You will need to specify the mpiexec path in the machine settings in the job manager
There is not really much we can do as the error is likely not in the QuantumATK program. Try to consult your compute cluster admin or ask for help on the Intel MPI support forum.