Abstract
The next generation of supercomputers will break the exascale barrier. Soon we will have systems capable of at least one quintillion (billion billion) floating-point operations per second (1018 FLOPS). Tremendous amounts of work have been invested into identifying and overcoming the challenges of the exascale era. In this work, we present an overview of these efforts and provide insight into the important trends, developments, and exciting research opportunities in exascale computing. We use a three-stage approach in which we (1) discuss various exascale landmark studies, (2) use data-driven techniques to analyze the large collection of related literature, and (3) discuss eight research areas in depth based on influential articles. Overall, we observe that great advancements have been made in tackling the two primary exascale challenges: energy efficiency and fault tolerance. However, as we look forward, we still foresee two major concerns: the lack of suitable programming tools and the growing gap between processor performance and data bandwidth (i.e., memory, storage, networks). Although we will certainly reach exascale soon, without additional research, these issues could potentially limit the applicability of exascale computing.
| Original language | English |
|---|---|
| Article number | 23 |
| Pages (from-to) | 1-43 |
| Number of pages | 43 |
| Journal | ACM Computing Surveys |
| Volume | 53 |
| Issue number | 2 |
| DOIs | |
| Publication status | Published - Mar 2020 |
Funding
This work has received funding from the European Union’s Horizon 2020 research and innovation programme under grant agreement No 777533 (PROCESS) and No 823988 (ESiWACE2), and the Netherlands eScience Center under file number 027.016.G06. Authors’ addresses: S. Heldens, Netherlands eScience Center, Science Park 140, 1098 XG, Amsterdam, University of Amsterdam, Science Park 904, 1098 XH, Amsterdam; email: [email protected]; P. Hijma, Vrije Universiteit Amsterdam, De Boelelaan 1111, 1081 HV, Amsterdam, University of Amsterdam, Science Park 904, 1098 XH, Amsterdam; email: [email protected]; B. van Werkhoven and J. Maassen, Netherlands eScience Center, Science Park 140, 1098 XG, Amsterdam; emails: {b.vanwerkhoven, j.maassen}@esciencecenter.nl; A. S. Z. Belloum, University of Amsterdam, Amsterdam, Science Park 904, 1098 XH; email: [email protected]; R. V. van Nieuwpoort, Netherlands eScience Center, Amsterdam, Science Park 140, 1098 XG, University of Amsterdam, Amsterdam, Science Park 904, 1098 XH; email: [email protected]. U.S. The project is a collaboration between six US-based computing laboratories and is funded by the U.S. National Nuclear Security Administration and the US DOE Office of Science. The project is organized into four focus areas: “application development”, “software technology”, “hardware technology”, and “exascale systems”. Additionally, the project includes training of scientists on software engineering and programming tools. Overall, the project emphasizes “co-design and integration of activities to ensure that the result is a robust exascale ecosystem” [126, p. 65].
| Funders | Funder number |
|---|---|
| Office of Science | |
| National Nuclear Security Administration | |
| Horizon 2020 Framework Programme | ESiWACE2, 777533, 027.016, 823988, G06 |
Keywords
- data-driven analysis
- Exascale computing
- extreme-scale computing
- high-performance computing
- literature review
