Python for High Performance and Scientific Computing

Authors: William Scullin (University of Rochester, Laboratory for Laser Energetics), Neelofer Banglawala (Edinburgh Parallel Computing Centre)

Abstract: The Python for High Performance and Scientific Computing BoF is intended to provide current and potential Python users and tool providers in the high performance and scientific computing communities a forum to talk about their current projects; ask questions of experts; explore methodologies including interactive supercomputing, data science, and machine learning; delve into issues with the language, modules, tools, and libraries; build community; and discuss the path forward. In the absence of a PyHPC workshop this year, this BoF provides a much needed platform for continued discussion and interaction amongst those in the Python and HPC space.

Long Description: The Python for High Performance and Scientific Computing BOF is intended to provide current and potential Python users and tool providers in the high performance and scientific computing communities: a forum to talk about their current projects; ask questions of experts and leading vendors; explore methodologies; delve into issues with the language, modules, tools, and libraries; build community; discuss the concerns of the community with advocates and active developers present; and help continue the path forward.

This BOF is a different space from other community workshops, tutorials, and meetings. Meeting during SC allows a focus specifically on the use of Python in HPC. The duration and the open admission to BOFs has allowed just enough time to present a wide array of material to an audience that is generally more diverse than found in other SC spaces. Attendance since SC09 has remained reliably between 30 and 60 attendees, even when other Python events have been scheduled. This year, the BoF fills the place of a successful series of workshops, which will resume in future years.

The format in past years has been 75% of the time dedicated to pre-selected presenters in academia, industry, and government presenting with question and answers periods and 25% of the time left open to moderated discussion. While vendors have been invited to present, presentations have been focused on how a new or innovative tool has further enabled the use of Python in the HPC space.



Back to Birds of a Feather Archive Listing