Green software use on HPC

Location:

This course will take place face-to-face at The Alan Turing Institute, British Library, London,

This course will not be streamed online and a recording will not be made.

Overview

This lesson introduces environmental sustainability principles in the context of high performance computing (HPC) systems. Understanding the scale of emissions from different sources is critical to being able to make changes to work in a more environmentally sustainable way. This lesson will give you the ability to understand emissions arising from use of HPC system and how to quantify them. We will use practical examples and real data from an existing HPC facility to illustrate the concepts. By the end of this lesson you should:

• Be able to understand the concept of carbon efficiency and how it relates to energy efficiency including cases where energy efficiency can be at odds with carbon efficiency
• Know about how HPC systems potentially reduce emissions
• Understand carbon intensity of electricity generation and the implications for carbon aware use of HPC
• Appreciate the embodied emissions associated with HPC hardware and how they impact carbon aware use of HPC
• Be aware of the frameworks used to measure and report on carbon emissions and how the terms used in these frameworks map onto HPC
• Gain practical advice on how you can measure and improve the carbon efficiency of your use of HPC

We use the UK National Supercomputing Service, ARCHER2 as an example throughout this lesson but the principles and learning should be applicable to any HPC system.

Target Audience:

This lesson is aimed at all stakeholders in HPC use (e.g. researchers, RSEs, funders). No knowledge of environmental sustainability principles is assumed.

Requirements:

Participants are required to abide by the ARCHER2 Code of Conduct.

Timetable:

Registration