Thanks! Now, the partitioning works.
For parallel computing, I’ve install gcc 13.1.0 and the latest version of “libxsmm”.
path also included as PYFR_XSMM_LIBRARY_PATH=/path/to/libxsmm.so
But for the same example case, I got the following error after command for parallel computing.
mpiexec -n 2 pyfr -p run -b cuda euler-vortex.pyfrm euler-vortex.ini
Please let me know how I can fix this…
Thanks!
Traceback (most recent call last):
File "/home/yongsu/Research/CFD/PyFR/libxsmm/pyfr-venv/bin/pyfr", line 8, in <module>
sys.exit(main())
^^^^^^
File "/home/yongsu/Research/CFD/PyFR/libxsmm/pyfr-venv/lib/python3.11/site-packages/pyfr/__main__.py", line 124, in main
args.process(args)
File "/home/yongsu/Research/CFD/PyFR/libxsmm/pyfr-venv/lib/python3.11/site-packages/pyfr/__main__.py", line 258, in process_run
_process_common(
File "/home/yongsu/Research/CFD/PyFR/libxsmm/pyfr-venv/lib/python3.11/site-packages/pyfr/__main__.py", line 240, in _process_common
rallocs = get_rank_allocation(mesh, cfg)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/yongsu/Research/CFD/PyFR/libxsmm/pyfr-venv/lib/python3.11/site-packages/pyfr/rank_allocator.py", line 12, in get_rank_allocation
return subclass_where(BaseRankAllocator, name=name)(mesh, cfg)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/yongsu/Research/CFD/PyFR/libxsmm/pyfr-venv/lib/python3.11/site-packages/pyfr/rank_allocator.py", line 29, in __init__
raise RuntimeError(f'Mesh has {nparts} partitions but running '
RuntimeError: Mesh has 2 partitions but running with 1 MPI ranks
Traceback (most recent call last):
File "/home/yongsu/Research/CFD/PyFR/libxsmm/pyfr-venv/bin/pyfr", line 8, in <module>
sys.exit(main())
^^^^^^
File "/home/yongsu/Research/CFD/PyFR/libxsmm/pyfr-venv/lib/python3.11/site-packages/pyfr/__main__.py", line 124, in main
args.process(args)
File "/home/yongsu/Research/CFD/PyFR/libxsmm/pyfr-venv/lib/python3.11/site-packages/pyfr/__main__.py", line 258, in process_run
_process_common(
File "/home/yongsu/Research/CFD/PyFR/libxsmm/pyfr-venv/lib/python3.11/site-packages/pyfr/__main__.py", line 240, in _process_common
rallocs = get_rank_allocation(mesh, cfg)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/yongsu/Research/CFD/PyFR/libxsmm/pyfr-venv/lib/python3.11/site-packages/pyfr/rank_allocator.py", line 12, in get_rank_allocation
return subclass_where(BaseRankAllocator, name=name)(mesh, cfg)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/yongsu/Research/CFD/PyFR/libxsmm/pyfr-venv/lib/python3.11/site-packages/pyfr/rank_allocator.py", line 29, in __init__
raise RuntimeError(f'Mesh has {nparts} partitions but running '