Performance optimisation and productivity centre of excellence

Abstract

INDUSTRIAL EXTENDED ABSTRACTAs machines get larger and scientific applications advance, it is more and more imperative to fully utilize high performance computing (HPC) capability. The complexity and changing landscape of parallel computers may lead to users being unable or unsure how to achieve optimal performance from their applications and fully utilize their HPC resources.The Performance Optimisation and Productivity Centre of Excellence in Computing Applications (POP) has received funding from the European Commission as part of the Horizon 2020 programme to help alleviate these issues. It aims to uncover inefficiencies and their causes in existing parallel HPC applications that will lead to an improvement in the productivity and competitiveness of European organizations, in academia, government and industry. The POP project will drive efforts to highlight the need for and best practices in performance optimization through performance audits on codes along with training events to improve knowledge in this area. The aim is to help developers target their code development and refactoring in the most efficient direction and provide a return on investment from the savings due to the performance improvement.The POP project combines the expertise and experience of Barcelona Supercomputing Center (BSC), High Performance Computing Center Stuttgart, Jülich Supercomputing Centre (JSC), Numerical Algorithms Group Ltd (NAG), RWTH Aachen and TERATEC. This combination provides longstanding and well respected resources in the academic and commercial realms. The POP members have come together to create a coherent and consistent methodology to give a clear, precise and useful overview of the performance of each HPC application.The services of the POP project are free of charge to organizations with in the EU to analyze and advise on any parallel code in academic, government or industrial organizations of any domain. I. METHODS USEDEspecially when aiming for very large scale HPC, efficiency of the application should be a major objective in program development. There is a broad need for detailed quantitative understanding of the actual cause of any inefficiencies and the complex interplay of effects as systems scale. This is a key need in development and refactoring of applications, especially as we work toward exascale machines.There are two main performance analysis tools used during POP performance analysis. The Scalasca [1] environment has been developed at JSC and gives a highly scalable providing a call-path view. It can detect the root cause of many communication performance issues and provides a rich environment within which to investigate performance issues. The latest version of Scalasca is built upon Score-P [2] which is a community-developed parallel performance instrumentation and measurement system. It has an open format which allows the data to be used in conjunction with a range of tools. The second set of performance analysis tools have been developed by BSC are based around the Paraver [3] visualizer and Extr...

The Advanced Computing Hub at BSC: improving fusion codes following modern software engineering standards

“…• POP standard metrics [12] is a methodology for analyzing parallel codes to provide a quantitative way of measuring the relative impact of the different factors inherent in parallelization. This methodology was defined by the Performance Optimisation and Productivity Center of Excellence in HPC (POP CoE) [13].…”