Versions Compared

Key

  • This line was added.
  • This line was removed.
  • Formatting was changed.

...

Specifying the number of Dask workers and threads enables the user to adjust the memory capability and parallelisation per Dask worker. It will help to address the potential stability and performance issues of Dask cluster.

Multiple GPU nodes

You can also specify flag "-G" together with "-D" when running jupyter.ini.sh to set up a Dask cluster by using Gadi GPU devices. As default, the number of Dask workers equals the number of GPU devices requested in the PBS job and each worker has 1 thread. 

...