Eurolab-4-HPC publishes long-term vision on HPC from 2022 to 2030

29 Sep 2017 Barcelona - The Eurolab-4-HPC has published a long-term vision on HPC from 2022 to 2030. It includes proposals for future European Research directions and funding routes. The objective of the Eurolab-4-HPC vision is to provide a long-term roadmap from 2023 to 2030 for HPC. The document starts with an assessment of future computing technologies that could influence HPC hardware and software. The proposal on research topics is derived from the report and discussions within the road mapping expert group. Eurolab-4-HPC prefers the term "vision" over "roadmap" because timings are hard to predict in the long-term.

Three trends are changing the HPC landscape. The first trend is the emergence of data analytics complementing simulation in scientific discovery. While simulation still remains a major pillar for science, there are massive volumes of scientific data that are now gathered by sensors augmenting data from simulation available for analysis. High-Performance Data Analysis (HPDA) will complement simulation in future HPC applications.

The second trend the authors see is the emergence of cloud computing and warehouse-scale computers in data centres. Data centres consist of low-cost volume processing, networking and storage servers, aiming at cost-effective data manipulation at unprecedented scales. The scale at which they host and manipulate data has led to fundamental breakthroughs in data analytics.

Large data centres are fundamentally different from traditional supercomputers in their design, operation and software structures. Particularly, big data applications in data centres and cloud computing centres require different algorithms and differ significantly from traditional HPC applications such that they may not require the same computer structures.

The third trend the document describes are Deep Neural Networks (DNN) for back propagation learning of complex patterns, which emerged as new technique penetrating different application areas. DNN learning requires high performance and is often run on supercomputers. Recent GPU accelerators are seen as very effective for DNN computing by their enhancements, e.g. support for 16-bit floating-point and tensor processing units. It is widely assumed that it will be applied in future autonomous cars thus opening a very large market segment for embedded HPC. DNNs will also be applied in engineering simulations traditionally running on HPC supercomputers, the authors predict.

Power and thermal management is considered as highly important and will continue its preference in future. Post-Exascale computers will target more than 1 Exaflops with less than 30 MW power consumption requiring processors with a much better performance per Watt than available today.

Because of the foreseeable end of CMOS scaling, new technologies are under development, such as, for example, Die Stacking and 3D Chip Technologies, Non-volatile Memory (NVM) Technologies, Photonics, Re- sistive Computing, Neuromorphic Computing, Quantum Computing, Nanotubes, Graphene, and diamond- based transistors. Since it is uncertain if/when some of the technologies will mature, it is hard to predict which ones will prevail.

The report sees that an opportunity for Europe may be development of competitive new hardware/software technologies based on upcoming new technologies to advantageously position European industry for the future. Target areas could be High-Performance Computing and Embedded High-Performance devices. The drawback could be that the chosen base technology may not be prevailing but be replaced by a different technology.

The Eurolab4HPC vision recommends the following funding opportunities for topics beyond Horizon 2020 (ICT):

  • Convergence of HPC and HPDA;
  • Impact of new NVMs;
  • Programmability;
  • Green ICT and Energy.
Ad Emmen