Publication in Conference Proceedings.
High Performance Computing (HPC) and High Performance Data Analytics (HPDA) opens up the opportunity to solve a wide variety of questions and challenges. The number and complexity of challenges that HPC and HPDA can help with are limited by the performance of computer software and hardware. Increasingly, performance is now limited by how fast data can be moved within the memory and storage of the hardware. So far, little work has been done to improve data movement.
How will Maestro help? Maestro will develop a new framework to improve the performance of data movement in HPC and HPDA, helping to improve the performance of software, and therefore the energy consumption and CPU hours used by software; and to encourage the uptake of HPC by new communities by lowering the memory performance barrier.
Maestro will consider two key components:
- Data movement awareness: Moving data in computer memory had not always been a performance bottleneck. Great improvements have been made in computational performance, but the software for memory has not changed during this time. Maestro will develop a better understanding of the performance barriers of data movement.
- Memory awareness: As memory becomes more complex, software performance is limited by data movement across the layers of memory. To improve software performance it is now important that software has an ‘awareness’ of memory and how to optimise data movement. Maestro has the potential to influence a broad range of human discovery and knowledge, as every computational application relies on data movement.
Publication Type: Project Poster
Conference: ISC High Performance 2020 (ISC20)
Year of Publication: 2020
Authors: Dr. Manuel Arenaz (Appentra), Prof. Dirk Pleiter (Jülich Supercomputing Centre), Prof. Adrian Tate (Cray)
Publisher: International Workshop on OpenPOWER for HPC (IWOPH’19)
Keywords: Exascale Systems, HPC workflows, System Software & Runtime Systems
Link to the publication: https://2020.isc-program.com/presentation/?id=proj113&sess=sess326
PDF of the publication: https://linklings-public.s3.amazonaws.com/isc_hpc/2020/posters/proj113.pdf