Time Zone: UTC

20 May 01:30 – 20 May 02:00 in Tutorials / Workshops 2

Making the most of your schedule: From HPC to Local Cluster

Nick Mortimer, Paul Branson

Audience level:
Intermediate

Description

Dask offers a level of simplicity that makes distributed computing accessible to a broad scientific community. Because of this simplicity users often overlook some key features of the various Dask schedulers. We will present an outline of the types of schedulers and their uses. We will then focus on AARNet's SWAN environment, which provides a user with a single large node with 36 cores with 256 Gb

Abstract

Dask offers a level of simplicity that makes distributed computing accessible to a broad scientific community. Because of this simplicity users often overlook some key features of the various Dask schedulers. We will present an outline of the types of schedulers and their uses. We will then focus on AARNet's SWAN environment, which provides a user with a single large node with 36 cores with 256 Gb of ram. AARNet's shareholders are 38 Australian universities and the Commonwealth Scientific and Industrial Research Organisation (CSIRO), every student and researcher at these institutions has access to the Swan environment making it a great place for the introduction of Dask in a centrally managed cloud computing environment. In time this may drive the uptake of additional Dask components (Dask-Gateway and Jupyter integration) within the SWAN environment.