Exascale computing

Exascale computing refers to computing systems capable of calculating at least 1018 floating point operations per second (1 exaFLOPS). The terminology generally refers to the performance of supercomputer systems and no single machine has reached this goal. As of June 2020 there are systems being designed to reach the milestone of one exaFLOPS. In April 2020 the distributed Folding@home computer network attained one exaFLOPS of computing performance.[1][2][3][4]

Definition
Further information: FLOPS

Floating point operations per second (FLOPS) are a measure of computer performance. FLOPS can be recorded in different measures of precision, however the standard measure used by the TOP500 supercomputer list ranks computers by 64 bit (double-precision floating-point format) operations per second using the LINPACK benchmark.[5]

History

The first petascale computer that came into operation in 2008.[6]

At a supercomputing conference in 2009, Computerworld projected exascale implementation by 2018.[7] Although the exascale wall for FLOPS was not broken in 2019, the Oak Ridge National Laboratory performed a 1.8×1018 operation calculation per second (which is not the same as 1.8×1018 FLOPS) on the Summit OLCF-4 Supercomputer while analyzing genomic information in 2018.[8] They were Gordon Bell Award winners at Supercomputing 2018.

The exaFLOPS barrier was first broken in March of 2020 by the Folding@home project, used to fold proteins for medical research.[9][10]

Exascale computing would be a significant achievement in computer engineering, as an exascale computer would have processing power on the order of the estimated processing power of the human brain at the neural level[11] (although the functional power required to simulate a human brain might be lower). The Human Brain Project targets exascale computing capability.

Development

China

As of June 2020, China has two of the four fastest supercomputers in the world.[12] China's first exascale supercomputer will enter service after mid-2020 according to the head of the school of computing at the National University of Defense Technology (NUDT). According to the national plan for the next generation of high performance computers, China will develop an exascale computer during the 13th Five-Year-Plan period (2016–2020). The government of Tianjin Binhai New Area, NUDT and the National Supercomputing Center in Tianjin are working on the project. After Tianhe-1 and Tianhe-2, the exascale successor is planned to be named Tianhe-3.[13]

United States

In 2008, two United States of America governmental organisations within the US Department of Energy, the Office of Science and the National Nuclear Security Administration, provided funding to the Institute for Advanced Architectures for the development of an exascale supercomputer; Sandia National Laboratory and the Oak Ridge National Laboratory were also to collaborate on exascale designs.[14] The technology was expected to be applied in various computation-intensive research areas, including basic research, engineering, earth science, biology, materials science, energy issues, and national security.[15]

In January 2012, Intel purchased the InfiniBand product line from QLogic for US $125 million in order to fulfill its promise of developing exascale technology by 2018.[16]

By 2012, the United States had allotted $126 million for exascale computing development.[17]

In February 2013,[18] the Intelligence Advanced Research Projects Activity started Cryogenic Computer Complexity (C3) program which envisions a new generation of superconducting supercomputers that operate at exascale speeds based on superconducting logic. In December 2014 it announced a multi-year contract with International Business Machines, Raytheon BBN Technologies and Northrop Grumman to develop the technologies for C3 program.[19]

On 29 July 2015, President Obama signed an executive order creating a National Strategic Computing Initiative calling for the accelerated development of an exascale system and funding research into post-semiconductor computing.[20] The Exascale Computing Project hopes to build an exascale computer by 2021.[21]

On 18 March 2019, the United States Department of Energy and Intel announced the first exaFLOPS supercomputer would be operational at Argonne National Laboratory by the end of 2021. The computer, named "Aurora" is to be delivered to Argonne by Intel and Cray (now Hewlett Packard Enterprise), and is expected to use Intel Xe GPGPUs alongside a future Xeon Scalable CPU, and cost US$600 Million. [22]

On 7 May 2019, The U.S. Department of Energy announced a contract with Cray Inc. (now Hewlett Packard Enterprise) to build the Frontier supercomputer at Oak Ridge National Laboratory. Frontier is anticipated to be operational in 2021 and, with a performance of greater than 1.5 exaFLOPS, should then be the world’s most powerful computer.[23]

On 4 March, 2020, The U.S. Department of Energy (DOE) announced a contract with Hewlett Packard Enterprise and AMD, to build the El Capitan supercomputer at a cost of US$600 Million, to be installed at the Lawrence Livermore National Laboratory (LLNL). It is expected to be used primarily (but not exclusively) for nuclear weapons modeling. It was first announced in August 2019, when the DOE and LLNL announced the purchase of a Shasta supercomputer from Cray. It should be operational in early 2023 and have a performance of 2 exaFLOPS. It will use AMD CPUs and GPUs, with 4 Radeon Instinct GPUs per EPYC Zen 4 CPU, to speed up Artificial Intelligence tasks. It should consume around 40 MW of electric power. [24][25]

Taiwan

In June 2017, Taiwan's National Center for High-Performance Computing initiated the effort towards designing and building the first Taiwanese exascale supercomputer by funding construction of a new intermediary supercomputer based on a full technology transfer from Fujitsu corporation of Japan, which is currently building the fastest and most powerful A.I. based supercomputer in Japan.[26][27][28][29][30] Additionally, numerous other independent Taiwanese efforts have been made in Taiwan with the focus on the rapid development of exascale supercomputing technology, such as the Taiwanese Foxconn Corporation which recently designed and built the largest and fastest supercomputer in all of Taiwan. This new Foxconn supercomputer is designed to serve as a stepping stone in research and development towards the design and building of a state of the art Taiwanese exascale supercomputer.[31][32][33][34]

European Union
See also Supercomputing in Europe

In 2011, several projects aiming at developing technologies and software for exascale computing were started in the EU. The CRESTA project (Collaborative Research into Exascale Systemware, Tools and Applications),[35] the DEEP project (Dynamical ExaScale Entry Platform),[36] and the project Mont-Blanc.[37] A major European project based on exascale transition is the MaX (Materials at the Exascale) project.[38] The Energy oriented Centre of Excellence (EoCoE) exploits exascale technologies to support carbon-free energy research and applications.[39]

In 2015, the Scalable, Energy-Efficient, Resilient and Transparent Software Adaptation (SERT) project, a major research project between the University of Manchester and the STFC Daresbury Laboratory in Cheshire, was awarded c. £1million from the UK’s Engineering and Physical Sciences Research Council. The SERT project was due to start in March 2015. It will be funded by EPSRC under the Software for the Future II programme, and the project will partner with the Numerical Analysis Group (NAG), Cluster Vision and the Science and Technology Facilities Council (STFC).[40]

On 28 September 2018, the European High-Performance Computing Joint Undertaking (EuroHPC JU) was formally established by the EU. The EuroHPC JU aims to build an exascale supercomputer by 2022/2023. The EuroHPC JU will be jointly funded by its public members with a budget of around €1 billion. The EU's financial contribution is €486 million.[41][42]

Japan

In Japan, in 2013, the RIKEN Advanced Institute for Computational Science began planning an exascale system for 2020, intended to consume less than 30 megawatts.[43] In 2014, Fujitsu was awarded a contract by RIKEN to develop a next-generation supercomputer to succeed the K computer. The successor is called Fugaku, and aims to have a performance of at least 1 exaFLOPS, and be fully operational in 2021. It was partially put into operation in June 2020.[44] In 2015, Fujitsu announced at the International Supercomputing Conference that this supercomputer will use processors implementing the ARMv8 architecture with extensions it was co-designing with ARM Limited.[45]

India

In 2012, the Indian Government has proposed to commit US$2.5 billion to supercomputing research during the 12th five-year plan period (2012–2017). The project will be handled by Indian Institute of Science (IISc), Bangalore.[46][47] Additionally, it was later revealed that India plans to develop a supercomputer with processing power in the exaFLOPS range.[48] It will be developed by C-DAC within the subsequent five years of approval.[49]

Technological challenges

It has been recognized that enabling applications to fully exploit capabilities of Exascale computing systems is not straightforward.[50] In June 2014, the stagnation of the Top500 supercomputer list had observers question the possibility of exascale systems by 2020.[51] Developing data-intensive applications over exascale platforms requires the availability of new and effective programming paradigms and runtimes systems. [52] The Folding@home project, the first to break this barrier, relied on a network of servers sending pieces of work to hundreds of thousands of clients using a Client–server model network architecture.[53][10]

See also

References
  1. "Folding@Home Active CPUs & GPUs by OS". www.foldingathome.org. Retrieved 2020-04-08.
  2. Folding@home (2020-03-25). "Thanks to our AMAZING community, we've crossed the exaFLOP barrier! That's over a 1,000,000,000,000,000,000 operations per second, making us ~10x faster than the IBM Summit!pic.twitter.com/mPMnb4xdH3". @foldingathome. Retrieved 2020-04-04.
  3. "Folding@Home Crushes Exascale Barrier, Now Faster Than Dozens of Supercomputers - ExtremeTech". www.extremetech.com. Retrieved 2020-04-04.
  4. "Folding@Home exceeds 1.5 ExaFLOPS in the battle against Covid-19". TechSpot. Retrieved 2020-04-04.
  5. "FREQUENTLY ASKED QUESTIONS". www.top500.org. Retrieved 23 June 2020.
  6. National Research Council (U.S.) (2008). The potential impact of high-end capability computing on four illustrative fields of science and engineering. The National Academies. p. 11. ISBN 978-0-309-12485-0.
  7. "Scientists, IT community await exascale computers". Computerworld. 2009-12-07. Retrieved 2009-12-18.
  8. Hines, Jonathan (June 8, 2018). "Genomics Code Exceeds Exaops on Summit Supercomputer". Oak Ridge Leadership Computing Facility.
  9. Folding@home (2020-03-25). "Thanks to our AMAZING community, we've crossed the exaFLOP barrier! That's over a 1,000,000,000,000,000,000 operations per second, making us ~10x faster than the IBM Summit!pic.twitter.com/mPMnb4xdH3". @foldingathome. Retrieved 2020-03-26.
  10. March 2020, Paul Alcorn 25. "Folding@Home Network Breaks the ExaFLOP Barrier In Fight Against Coronavirus". Tom's Hardware. Retrieved 2020-03-26.
  11. "Brain performance in FLOPS – AI Impacts". aiimpacts.org. 2015-07-26. Retrieved 2017-12-27.
  12. "TOP500 List - June 2018". TOP500. Retrieved 20 July 2018.
  13. "China's Exascale Supercomputer Operational by 2020---Chinese Academy of Sciences". english.cas.cn.
  14. Johnson, R. Colin (4 May 2008), "U.S. launches exaflop supercomputer initiative", www.eetimes.com
  15. "Science Prospects and Benefits with Exascale Computing" (PDF). Oak Ridge National Laboratory. Archived from the original (PDF) on 2012-05-04. Retrieved 2009-12-18.
  16. "Intel Snaps Up InfiniBand Technology, Product Line from QLogic". 2012-01-23.
  17. "Obama Budget Includes $126 Million for Exascale Computing". Archived from the original on 2011-02-24.
  18. "Proposers' Day Announcement for the IARPA Cryogenic Computing Complexity (C3) Program - IARPA-BAA-13-05(pd) (Archived)". Federal Business Opportunities. February 11, 2013. Retrieved 11 October 2015.
  19. "US intel agency aims to develop superconducting computer". Reuters. December 3, 2014. Retrieved December 3, 2014.
  20. "Executive Order Creating a National Strategic Computing Initiative". The White House Office of the Press Secretary. July 29, 2015. Retrieved 11 October 2015.
  21. "U.S. Bumps Exascale Timeline, Focuses on Novel Architectures for 2021". The Next Platform. 2016-12-08. Retrieved 2016-12-13.
  22. "U.S. Department of Energy and Intel to deliver first exascale supercomputer". Argonne National Laboratory. 2019-03-18. Retrieved 2019-03-27.
  23. "U.S. Department of Energy and Cray to Deliver Record-Setting Frontier Supercomputer at ORNL". Oak Ridge National Laboratory. 2019-05-08. Retrieved 2019-05-08.
  24. "HPE, AMD win deal for U.S. supercomputer to model nuclear weapons". March 5, 2020 – via www.reuters.com.
  25. Smith, Ryan. "El Capitan Supercomputer Detailed: AMD CPUs & GPUs To Drive 2 Exaflops of Compute". www.anandtech.com.
  26. "Fujitsu to build world-class AI supercomputer".
  27. "Fujitsu to Build Japan's Fastest Supercomputer | TOP500 Supercomputer Sites".
  28. "Fujitsu to Build 3-PFLOPS Supercomputer for Taiwan NCHC".
  29. "Asetek Receives Order from Fujitsu to Cool Japan's Fastest AI Supercomputer System - Asetek".
  30. "Fujitsu Receives Order for Japan's Fastest Supercomputer System for AI Applications - Fujitsu Global".
  31. "Foxconn Builds Taiwan's Largest Supercomputer | TOP500 Supercomputer Sites".
  32. "Taiwan-based firm reveals supercomputer".
  33. "Hon Hai unveils Taiwan's fastest superc".
  34. "Hon Hai unveils supercomputer system | Tech | FOCUS TAIWAN - CNA ENGLISH NEWS".
  35. "Europe Gears Up for the Exascale Software Challenge with the 8.3M Euro CRESTA project". Project consortium. 14 November 2011. Retrieved 10 December 2011.
  36. "Booster for Next-Generation Supercomputers Kick-off for the European exascale project DEEP". FZ Jülich. 15 November 2011. Retrieved 10 December 2011.
  37. "Mont-Blanc project sets Exascale aims". Project consortium. 2011-10-31. Archived from the original on 5 December 2011. Retrieved 10 December 2011.
  38. "MaX website". project consortium. 25 November 2016. Retrieved 25 November 2016.
  39. "EoCoE website". Project consortium. 29 April 2020. Retrieved 29 April 2020.
  40. "Developing Simulation Software to Combat Humanity's Biggest Issues". Scientific Computuing. 25 February 2015. Archived from the original on 14 April 2015. Retrieved 8 April 2015.
  41. "EuroHPC - Europe's journey to exascale HPC". Retrieved 2019-02-09.
  42. "The European High-Performance Computing Joint Undertaking - EuroHPC". 11 January 2018. Retrieved 2019-02-09.
  43. Thibodeau, Patrick (November 22, 2013). "Why the U.S. may lose the race to exascale". Computerworld.
  44. "RIKEN selects contractor for basic design of post-K supercomputer", www.aics.riken.jp, 1 Oct 2014, archived from the original on 13 January 2017, retrieved 22 June 2016
  45. "Fujitsu picks 64-bit ARM for Japan's monster 1,000-PFLOPS super", www.theregister.co.uk, 20 June 2016
  46. "Making up lost ground: India pitches for $1bn leap in supercomputers". Daily Mail. 23 January 2012. Retrieved 29 January 2012.
  47. "India Aims to Double R&D Spending for Science". HPC Wire. 4 January 2012. Retrieved 29 January 2012.
  48. "C-DAC and Supercomputers in India". Archived from the original on 2016-03-03. Retrieved 2016-01-06.
  49. "India plans 61 times faster supercomputer by 2017". Times of India. 27 September 2012. Retrieved 9 October 2012.
  50. Abraham, Erika; Bekas, Costas; Brandic, Ivona; Genaim, Samir; Broch Johnsen, Einar; Kondov, Ivan; Pllana, Sabri; Streit, Achim (2015-03-24), Preparing HPC Applications for Exascale: Challenges and Recommendations, arXiv:1503.06974, Bibcode:2015arXiv150306974A
  51. Anthony, Sebastian (June 24, 2014). "Supercomputer stagnation: New list of the world's fastest computers casts shadow over exascale by 2020". Extremetech.com.
  52. Da Costa, Georges; et, al. (2015), "Exascale Machines Require New Programming Paradigms and Runtimes", Supercomputing Frontiers and Innovations, 2 (2): 6–27, doi:10.14529/jsfi150201
  53. "About – Folding@home". Retrieved 2020-03-26.

Sources
  • Gropp, William (2009). MPI at Exascale: Challenges for Data Structures and Algorithms. Recent Advances in Parallel Virtual Machine and Message Passing Interface, Lecture Notes in Computer Science. Lecture Notes in Computer Science. 5759. Berlin: Springer. p. 3. Bibcode:2009LNCS.5759....3G. doi:10.1007/978-3-642-03770-2_3. ISBN 978-3-642-03769-6.
  • Kirkley, John (November 22, 2011). "The Road to Exascale: Can Nanophotonics Help?". enterprisetech.com. Retrieved 11 October 2015.
This article is issued from Wikipedia. The text is licensed under Creative Commons - Attribution - Sharealike. Additional terms may apply for the media files.