Fugaku (supercomputer)

Fugaku (Japanese: 富岳)  named after an alternative name for Mount Fuji  is a claimed exascale supercomputer[4][5] (while only at petascale for mainstream benchmark), at the RIKEN Center for Computational Science in Kobe, Japan. It started development in 2014 as the successor to the K computer, and is officially scheduled to start operating in 2021.[6][7] Fugaku made its debut in 2020,[8] and became the fastest supercomputer in the world in the June 2020 TOP500 list,[9] as well as becoming the first ARM architecture-based computer to achieve this. As of January 2021, Fugaku is still the fastest supercomputer in the world.[10]

Fugaku
ActiveFrom 2021
SponsorsMEXT
OperatorsRIKEN
LocationRIKEN Center for Computational Science (R-CCS)
Architecture
Operating systemCustom Linux-based kernel
MemoryHBM2 32 GiB/node
Storage
  • 1.6 TB NVMe SSD/16 nodes (L1)
  • 150 PB shared Lustre FS (L2)[1]
  • Cloud storage services (L3)
Speed442 PFLOPS (per TOP500 Rmax), after upgrade; higher 2.0 EFLOPS on a different mixed-precision benchmark
CostUS$1 billion (total programme cost)[2][3]
RankingTOP500: 1, June 2020
Web sitewww.r-ccs.riken.jp/en/fugaku
SourcesFugaku System Configuration
PRIMEHPC FX1000 (Fugaku node) at SC19

Hardware

The supercomputer is built with the Fujitsu A64FX microprocessor. This CPU is based on the ARM version 8.2A processor architecture, and adopts the Scalable Vector Extensions for supercomputers.[11] Fugaku was aimed to be about 100 times more powerful than the K computer (i.e. a performance target of 1 exaFLOPS) and have a high level of practicability in the world.[12][13]

The initial (June 2020) configuration of Fugaku used 158,976 A64FX CPUs joined together using Fujitsu's proprietary torus fusion interconnect.[9] An upgrade in November 2020 increased the number of processors.[14]

Software

Fugaku will use a "light-weight multi-kernel operating system" named IHK/McKernel. The operating system uses both Linux and the McKernel light-weight kernel operating simultaneously and side by side. The infrastructure that both kernels run on is termed the Interface for Heterogeneous Kernels (IHK). The high-performance simulations are run on McKernel, with Linux available for all other POSIX-compatible services.[15][16][17]

Besides the system software, the supercomputer has run many kinds of applications, including several benchmarks. Running the mainstream HPL benchmark, used by TOP500, Fugaku is at petascale and almost halfway to exascale. Additionally, Fugaku has set world records on at least three other benchmarks, including HPL-AI; at 2.0 exaflops, the system has exceeded the exascale threshold for the benchmark.[18] A description of that benchmark is as follows:

The solver method of choice is a combination of LU factorization and iterative refinement performed afterwards to bring the solution back to 64-bit accuracy. The innovation of HPL-AI lies in dropping the requirement of 64-bit computation throughout the entire solution process and instead opting for low-precision (likely 16-bit) accuracy for LU, and a sophisticated iteration to recover the accuracy lost in factorization.[19]

Performance

The reported initial performance of Fugaku was a Rmax of 416 petaFLOPS in the FP64 high performance LINPACK benchmark used by the TOP500.[9] After the November 2020 upgrade in the number of processors, Fugaku's performance increased to a Rmax of 442 petaFLOPS.[14]

Fugaku also attained top spots in other rankings that test computers on different workloads, including Graph 500, HPL-AI, and HPCG. No previous supercomputer has ever led all four rankings at once.[20]

After a small hardware upgrade, as of November 2020, "Fugaku increased its performance on the new mixed precision HPC-AI benchmark to 2.0 exaflops, besting its 1.4 exaflops mark recorded six months ago. These represent the first benchmark measurements above one exaflop for any precision on any type of hardware." (a 42% increase)[21] Interestingly, the Arm A64FX core-count was only increased by 4.5%, to 7,630,848, but the measured performance rose much more on that benchmark (and the computer doesn't use other compute capabilities, such as GPUs), and a little more on TOP500, or by 6.4%, to 442 petaflops, a new world record[22] and widening the gap to the next computer by that much. For the High-Performance Conjugate Gradient (HPCG) benchmark it's over 5.4x as fast, at 16.0 HPCG-petaflops, as the numer two system, Summit,[23] that happens to also be second on TOP500.

Fugaku's performance surpasses the combined performance of the next 4 supercomputers on the top500 list (almost next 5) and surpasses by 45% margin all the other top-10 computers on HPCG benchmark.[24]

History

On May 23, 2019, RIKEN announced that the supercomputer was to be named Fugaku.[25] In August 2019, the logo for Fugaku was unveiled; it depicts Mount Fuji, symbolising "Fugaku's high performance" and "the wide range of its users".[7][26] In November 2019, the prototype of Fugaku won first place in the Green500 list.[27][28] Shipment of the equipment racks to the RIKEN facility began on December 2, 2019,[29] and was completed on May 13, 2020.[30] In June 2020, Fugaku became the fastest supercomputer in the world in the TOP500 list, displacing the IBM Summit.[9]

Fugaku has been used for research on masks related to COVID-19 pandemic.[31][32]

Cost

In 2018, Nikkei reported the programme would cost ¥130 billion (c. US$1 billion).[3][6]

Comparison

Performance and cost comparison chart against computers ranked #1 in TOP500
Name Start year End year Performance
PFLOPS)[note 1]
Cost
(million USD)

(not inflation adjusted)

TOP500 ranking CPU/GPU vendor CPU OS
Fugaku2020-4151213[3][note 2]June 2020 1stFujitsuA64FXCustom Linux-based kernel
Summit2018-148300[33]June 2018 to November 2019 1st IBM, NVIDIAPOWER9, TeslaLinux (RedHat)
Sierra2018-94November 2018 to November 2019 2nd
Sunway TaihuLight2016-93280[34]June 2016 to November 2017 1st NRCPCSunway SW26010Linux (Raise)
K20112019101045[35]June 2011 – November 2011 1stFujitsuSPARC64 VIIIfxLinux
  1. This is based on the TOP500 Rmax measurement using the LINPACK benchmark at FP64 precision.
  2. This is the total programme cost involving the creation of the technologies, rather than just for the machine.

See also

References

  1. "Post-K (Fugaku) Information". Fujitsu. Retrieved 2020-06-23.
  2. Clark, Don (22 June 2020). "Japanese Supercomputer Is Crowned World's Speediest". The New York Times. Retrieved 26 June 2020.
  3. Takei, Tomohisa (14 September 2018). "お値段1300億円のポスト「京」、IT業界は今度こそ生かせるか". 日経クロステック(xTECH) (in Japanese). Nikkei. Retrieved 28 June 2020.
  4. "Japan's Fugaku gains title as world's fastest supercomputer". www.riken.jp (Press release). Retrieved 2020-12-07.
  5. Dorrier, Jason (2020-06-25). "The World's New Fastest Supercomputer Is an Exascale Machine for AI". Singularity Hub. Retrieved 2020-12-07.
  6. Tsukimori, Osamu (7 January 2021). "Japan's Fugaku supercomputer is tackling some of the world's biggest problems". The Japan Times. Retrieved 26 January 2021.
  7. "スーパーコンピュータ「富岳」プロジェクト" (in Japanese). 理化学研究所. Retrieved 2019-05-25.
  8. "Supercomputer Fugaku, named after Mt. Fuji, makes its debut". The Asahi Shimbun. 2020-06-16. Retrieved 2020-06-23.
  9. Cutress, Dr Ian (22 June 2020). "New #1 Supercomputer: Fujitsu's Fugaku and A64FX take Arm to the Top with 415 PetaFLOPs". www.anandtech.com. Retrieved 22 June 2020.
  10. "Fugaku Retains Title as World's Fastest Supercomputer". HPC Wire. 17 November 2020. Retrieved 27 November 2020.
  11. "ポスト「京」のCPUの仕様を公表" (in Japanese). 富士通. 2018-08-22. Retrieved 2019-05-25.
  12. "スパコン「京」後継機は「富岳」 計算性能100倍、21年稼働". 毎日新聞 (in Japanese). 2019-05-23. Retrieved 2019-05-30.
  13. "Fugaku Remakes Exascale Computing In Its Own Image". 2019-12-09. Retrieved 2020-06-22.
  14. "November 2020 summary - TOP500". www.top500.org. Retrieved 7 December 2020.
  15. "Outline of the Development of the Supercomputer Fugaku". RIKEN Center for Computational Science. Retrieved 2020-06-23.
  16. "McKernel". RIKEN. Retrieved 2020-06-23.
  17. mckernel on GitHub
  18. "Fugaku Retains Title as World's Fastest Supercomputer". HPC Wire. 17 November 2020. Retrieved 27 November 2020.
  19. "HPL-AI Mixed-Precision Benchmark — HPL-AI 0.0.2 documentation". icl.bitbucket.io. Retrieved 2020-11-18.
  20. Byford, Sam (2020-06-23). "ARM-based Japanese supercomputer is now the fastest in the world". The Verge. Retrieved 2020-06-23.
  21. "November 2020 | TOP500". www.top500.org. Retrieved 2020-11-18.
  22. "Supercomputer Fugaku - Supercomputer Fugaku, A64FX 48C 2.2GHz, Tofu interconnect D | TOP500". www.top500.org. Retrieved 2020-11-18.
  23. "HPCG - November 2020 | TOP500". www.top500.org. Retrieved 2020-11-18.
  24. "HPCG - November 2020 | TOP500". www.top500.org. Retrieved 2020-12-01.
  25. "ポスト「京」の名称 「富岳(ふがく)」に決定" (in Japanese). 理化学研究所. 2019-05-23. Retrieved 2019-05-25.
  26. "R-CCS announced the Fugaku logo | RIKEN Center for Computational Science RIKEN Website". www.r-ccs.riken.jp. RIKEN Center for Computational Science. Retrieved 23 June 2020.
  27. "November 2019". TOP500.org. Retrieved 2019-11-20.
  28. "Fugaku prototype named greenest supercomputer". RIKEN. 2019-11-18. Retrieved 2019-11-20.
  29. "Fujitsu Begins Shipping Supercomputer Fugaku". Fujitsu. 2019-12-02. Retrieved 2020-06-23.
  30. "Delivery of the Supercomputer Fugaku has been Completed". RIKEN Center for Computational Science. 2020-05-13. Retrieved 2020-06-23.
  31. McCurry, Justin (26 August 2020). "Non-woven masks better to stop Covid-19, says Japanese supercomputer". The Guardian. Retrieved 22 September 2020.
  32. McCurry, Justin (22 September 2020). "Face shields ineffective at trapping aerosols, says Japanese supercomputer". The Guardian. Retrieved 22 September 2020.
  33. Shankland, Stephen (2018-06-26). "スパコン「TOP500」、IBM製「Summit」で米が中国を抜き首位に返り咲き" (in Japanese). ZDNet Japan. Retrieved 2020-10-28.
  34. 伊本貴士 (2020-06-24). "頂上極めた「富岳」の次の挑戦、日本が強い分野の開発に生かせるか" (in Japanese). 日経クロステック. Retrieved 2020-10-28.
  35. 田中誠士 (2019-08-05). "「2位じゃダメ」のスパコン京、見納め 6年超す長寿で" (in Japanese). 朝日新聞デジタル. Retrieved 2020-10-28.
Records
Preceded by
IBM Summit
World's most powerful supercomputer
June 2020 -
Incumbent
This article is issued from Wikipedia. The text is licensed under Creative Commons - Attribution - Sharealike. Additional terms may apply for the media files.