--------------------------------------------------------------------------
By default, for Open MPI 4.0 and later, infiniband ports on a device
are not used by default.  The intent is to use UCX for these devices.
You can override this policy by setting the btl_openib_allow_ib MCA parameter
to true.

  Local host:              c003
  Local adapter:           mlx5_0
  Local port:              1

--------------------------------------------------------------------------
--------------------------------------------------------------------------
WARNING: There was an error initializing an OpenFabrics device.

  Local host:   c003
  Local device: mlx5_0
--------------------------------------------------------------------------
[c003:747877] *** Process received signal ***
[c003:747877] Signal: Segmentation fault (11)
[c003:747877] Signal code: Address not mapped (1)
[c003:747877] Failing at address: 0x40
[c003:747877] [ 0] /lib/x86_64-linux-gnu/libc.so.6(+0x43090)[0x7faa33833090]
[c003:747877] [ 1] /usr/local/lib/libtorch_cpu.so(+0x46b846e)[0x7faa0742346e]
[c003:747877] [ 2] /usr/local/lib/libtorch_cpu.so(+0x46b9b70)[0x7faa07424b70]
[c003:747877] [ 3] /usr/local/lib/libtorch_cpu.so(+0x46c71fb)[0x7faa074321fb]
[c003:747877] [ 4] /usr/local/lib/libtorch_cpu.so(_ZN5torch3jit16InterpreterState3runERSt6vectorIN3c106IValueESaIS4_EE+0x52)[0x7faa0741f212]
[c003:747877] [ 5] /usr/local/lib/libtorch_cpu.so(+0x46a71a6)[0x7faa074121a6]
[c003:747877] [ 6] /usr/local/lib/libtorch_cpu.so(_ZNK5torch3jit6MethodclESt6vectorIN3c106IValueESaIS4_EERKSt13unordered_mapINSt7__cxx1112basic_stringIcSt11char_traitsIcESaIcEEES4_St4hashISD_ESt8equal_toISD_ESaISt4pairIKSD_S4_EEE+0x180)[0x7faa07095170]
[c003:747877] [ 7] /mmfs1/scratch/bwaters2/bwaters/job-cfca52f2-4dcc-4beb-8315-a45e5599fdf0-007-bae777c4-4aae-4853-8f91-e37e3139033e/TE_759177527743_003-and-MO_781946209112_000-1711746738/staged_job_files/repository/md/TorchML__MD_173118614730_000/libkim-api-model-driver.so(_ZN12PytorchModel3RunERN3c106IValueE+0x381)[0x7faa296f0fb1]
[c003:747877] [ 8] /mmfs1/scratch/bwaters2/bwaters/job-cfca52f2-4dcc-4beb-8315-a45e5599fdf0-007-bae777c4-4aae-4853-8f91-e37e3139033e/TE_759177527743_003-and-MO_781946209112_000-1711746738/staged_job_files/repository/md/TorchML__MD_173118614730_000/libkim-api-model-driver.so(_ZN32TorchMLModelDriverImplementation3RunEPKN3KIM21ModelComputeArgumentsE+0x5c)[0x7faa296eed7c]
[c003:747877] [ 9] /mmfs1/scratch/bwaters2/bwaters/job-cfca52f2-4dcc-4beb-8315-a45e5599fdf0-007-bae777c4-4aae-4853-8f91-e37e3139033e/TE_759177527743_003-and-MO_781946209112_000-1711746738/staged_job_files/repository/md/TorchML__MD_173118614730_000/libkim-api-model-driver.so(_ZN32TorchMLModelDriverImplementation7ComputeEPKN3KIM21ModelComputeArgumentsE+0xd)[0x7faa296eee3d]
[c003:747877] [10] /mmfs1/scratch/bwaters2/bwaters/job-cfca52f2-4dcc-4beb-8315-a45e5599fdf0-007-bae777c4-4aae-4853-8f91-e37e3139033e/TE_759177527743_003-and-MO_781946209112_000-1711746738/staged_job_files/repository/md/TorchML__MD_173118614730_000/libkim-api-model-driver.so(_ZN18TorchMLModelDriver7ComputeEPKN3KIM12ModelComputeEPKNS0_21ModelComputeArgumentsE+0x33)[0x7faa296e68e3]
[c003:747877] [11] /usr/local/lib/libkim-api.so.2(_ZNK3KIM19ModelImplementation12ModelComputeEPKNS_16ComputeArgumentsE+0x4a0)[0x7faa33177900]
[c003:747877] [12] /usr/local/lib/libkim-api.so.2(_ZNK3KIM19ModelImplementation7ComputeEPKNS_16ComputeArgumentsE+0x667)[0x7faa33185e67]
[c003:747877] [13] /usr/local/lib/liblammps.so.0(_ZN9LAMMPS_NS7PairKIM7computeEii+0x20d)[0x7faa344bcc2d]
[c003:747877] [14] /usr/local/lib/liblammps.so.0(_ZN9LAMMPS_NS6Verlet5setupEi+0x3a2)[0x7faa34402982]
[c003:747877] [15] /usr/local/lib/liblammps.so.0(_ZN9LAMMPS_NS3Run7commandEiPPc+0xc7e)[0x7faa34397b8e]
[c003:747877] [16] /usr/local/lib/liblammps.so.0(_ZN9LAMMPS_NS5Input15execute_commandEv+0xc0f)[0x7faa3420f96f]
[c003:747877] [17] /usr/local/lib/liblammps.so.0(_ZN9LAMMPS_NS5Input4fileEv+0x175)[0x7faa3420fc25]
[c003:747877] [18] lammps(+0x13fe)[0x55bb666873fe]
[c003:747877] [19] /lib/x86_64-linux-gnu/libc.so.6(__libc_start_main+0xf3)[0x7faa33814083]
[c003:747877] [20] lammps(+0x148e)[0x55bb6668748e]
[c003:747877] *** End of error message ***
Traceback (most recent call last):
  File "../../td/ClusterEnergyAndForces__TD_000043093022_003/runner", line 46, in run_lammps
    lammps_process = subprocess.check_call(
  File "/usr/lib/python3.8/subprocess.py", line 364, in check_call
    raise CalledProcessError(retcode, cmd)
subprocess.CalledProcessError: Command '['lammps', '-in', 'isolated_atom.lammps.Si.in']' died with <Signals.SIGSEGV: 11>.

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "../../td/ClusterEnergyAndForces__TD_000043093022_003/runner", line 217, in <module>
    isolated_atom_energies[symbol] = get_isolated_atom_energy(
  File "../../td/ClusterEnergyAndForces__TD_000043093022_003/runner", line 72, in get_isolated_atom_energy
    run_lammps(templated_input, lammps_output)
  File "../../td/ClusterEnergyAndForces__TD_000043093022_003/runner", line 56, in run_lammps
    raise Exception("LAMMPS did not exit properly:\n" + extrainfo)
Exception: LAMMPS did not exit properly:
LAMMPS (2 Aug 2023 - Update 1)

Command exited with non-zero status 1

{"realtime":4.34,"usertime":2.71,"systime":4.12,"memmax":322104,"memavg":0}