K computer

Quality 0.50 · 2 views · Updated 2 months ago

Supercomputer in Kobe, Japan

title: "K computer" type: doc version: 1 created: 2026-02-28 author: "Wikipedia contributors" status: active scope: public tags: ["2011-in-science", "fujitsu-supercomputers", "one-of-a-kind-computers", "petascale-computers", "riken", "sparc-microprocessor-products", "supercomputing-in-japan", "64-bit-computers"] description: "Supercomputer in Kobe, Japan" topic_path: "technology/computing" source: "https://en.wikipedia.org/wiki/K_computer" license: "CC BY-SA 4.0" wikipedia_page_id: 0 wikipedia_revision_id: 0

::summary Supercomputer in Kobe, Japan ::

::data[format=table title="Infobox custom computer"]

FieldValue
Image京コンピュータ (32588659510).jpg
DatesJune 2011 – August 2019
LocationRiken Advanced Institute for Computational Science
SponsorsMEXT, Japan Japan
OperatorsFujitsu
Architecture88,128 SPARC64 VIIIfx processors, Tofu interconnect
Speed10.51 petaflops (Rmax)
OSLinux
Power12.6 MW
ChartNameTOP500
ChartPosition18th
ChartDate
::

| Image = 京コンピュータ (32588659510).jpg | Caption = | Website = | Dates = June 2011 – August 2019 | Location = Riken Advanced Institute for Computational Science | Sponsors = MEXT, Japan Japan | Operators = Fujitsu | Architecture = 88,128 SPARC64 VIIIfx processors, Tofu interconnect | Memory = | Storage = | Speed = 10.51 petaflops (Rmax) | OS = Linux | Power = 12.6 MW | Space = | Cost = | ChartName = TOP500 | ChartPosition = 18th | ChartDate = | Purpose = | Legacy = | Emulators = | Sources =

::figure[src="https://upload.wikimedia.org/wikipedia/commons/f/fd/RIKEN_AICS_20120810-001.jpg" caption="Riken Advanced Institute for Computational Science (AICS) in Kobe, which housed the K computer"] ::

The K computer named for the Japanese word/numeral "kei", meaning 10 quadrillion (1016) was a supercomputer manufactured by Fujitsu, installed at the Riken Advanced Institute for Computational Science campus in Kobe, Hyōgo Prefecture, Japan. The K computer was based on a distributed memory architecture with over 80,000 compute nodes.{{cite conference|title=The K computer: Japanese next-generation supercomputer development project |conference=IEEE/ACM International Symposium on Low Power Electronics and Design |publisher=IEEE |date=1-3 August 2011 |pages=371–372 |first1=Mitsuo |last1=Yokokawa |first2=Fumiyoshi |last2=Shoji |first3=Atsuya |last3=Uno |first4=Motoyoshi |last4=Kurokawa |first5=Tadashi |last5=Watanabe |doi=10.1109/ISLPED.2011.5993668}} It was used for a variety of applications, including climate research, disaster prevention and medical research.

In June 2011, TOP500 ranked K the world's fastest supercomputer, with a computation speed of over 8 petaflops, and in November 2011, K became the first computer to top 10 petaflops.

, the K computer held third place for the HPCG benchmark. It held the first place until June 2018, when it was superseded by Summit and Sierra.

The K supercomputer was decommissioned on 30 August 2019. In Japan, the K computer was succeeded by the Fugaku supercomputer, in 2020, which took the top spot on the June 2020 TOP500 list, at that time nearly three times faster than second most powerful supercomputer.

Performance

On 20 June 2011, the TOP500 Project Committee announced that K had set a LINPACK record with a performance of 8.162 petaflops, making it the fastest supercomputer in the world at the time; K received top ranking in all four performance benchmarks at the 2011 HPC Challenge Awards.

On 18 June 2012, the TOP500 Project Committee announced that the California-based IBM Sequoia supercomputer replaced K as the world's fastest supercomputer, with a LINPACK performance of 16.325 petaflops. Sequoia is 55% faster than K, using 123% more CPU processors, but is also 150% more energy efficient.

On the TOP500 list, it became first in June 2011, falling down through time to lower positions, to eighteenth in November 2018.

K computer held third place in the HPCG benchmark test proposed by Jack Dongarra, with 0.6027 HPCG PFLOPS in November 2018.

Specifications

Node architecture

The K computer comprised 88,128 2.0 GHz eight-core SPARC64 VIIIfx processors contained in 864 cabinets, for a total of 705,024 cores, manufactured by Fujitsu with 45 nm CMOS technology.{{Cite conference |author=Takumi Maruyama |date=25 August 2009 |title=SPARC64(TM) VIIIfx: Fujitsu's New Generation Octo Core Processor for PETA Scale computing |conference=Proceedings of Hot Chips 21 |url=http://img.jp.fujitsu.com/downloads/jp/jhpc/090825HotChips21.pdf |publisher=IEEE Computer Society |access-date=24 February 2013 |archive-date=18 May 2012 |archive-url=https://web.archive.org/web/20120518034759/http://img.jp.fujitsu.com/downloads/jp/jhpc/090825HotChips21.pdf |url-status=live

Network

The nodes were connected by Fujitsu's proprietary torus fusion (Tofu) interconnect.{{cite web | url=http://www.fujitsu.com/downloads/TC/sc10/programming-on-k-computer.pdf | publisher=Fujitsu | title=Programming on K computer | access-date=24 June 2011 | archive-date=2 July 2020 | archive-url=https://web.archive.org/web/20200702201411/https://www.fujitsu.com/downloads/TC/sc10/programming-on-k-computer.pdf | url-status=live | url=http://blogs.cisco.com/performance/open-mpi-powers-8-petaflops/ | publisher=Cisco Systems | title=Open MPI powers 8 petaflops | access-date=24 June 2011 | archive-url=https://web.archive.org/web/20110628064742/http://blogs.cisco.com/performance/open-mpi-powers-8-petaflops/ | archive-date=28 June 2011 | url-status=dead |author=Yuichiro Ajima|s2cid=2049404 |year=2009 |title=Tofu: A 6D Mesh/Torus Interconnect for Exascale Computers |journal=Computer |volume=42 |issue=11 |pages=36–40 |publisher=IEEE Computer Society |doi=10.1109/MC.2009.370 |display-authors=etal |bibcode=2009Compr..42k..36A

File system

The system adopted a two-level local/global file system with parallel/distributed functions, and provided users with an automatic staging function for moving files between global and local file systems. Fujitsu developed an optimized parallel file system based on Lustre, called the Fujitsu Exabyte File System (FEFS), which is scalable to several hundred petabytes.{{cite web | url=http://www.olcf.ornl.gov/wp-content/events/lug2011/4-12-2011/230-300_Shinji_Sumimoto_LUG2011-FJ-20110407-pub.pdf | publisher=Fujitsu | title=An Overview of Fujitsu's Lustre Based File System | access-date=24 June 2011 | archive-date=20 March 2012 | archive-url=https://web.archive.org/web/20120320062356/http://www.olcf.ornl.gov/wp-content/events/lug2011/4-12-2011/230-300_Shinji_Sumimoto_LUG2011-FJ-20110407-pub.pdf | url-status=live

Power consumption

Although the K computer reported the highest total power consumption (9.89 MW the equivalent of almost 10,000 suburban homes) on the June 2011 TOP500 list, it is relatively efficient, achieving 824.6 GFlop/kW. This is 29.8% more efficient than China's NUDT TH MPP (ranked #2 in 2011), and 225.8% more efficient than Oak Ridge's Jaguar-Cray XT5-HE (ranked #3 in 2011). However, K's power efficiency still fell far short of the 2097.2 GFlops/kWatt supercomputer record set by IBM's NNSA/SC Blue Gene/Q Prototype 2. For comparison, the average power consumption of a TOP 10 system in 2011 was 4.3 MW, and the average efficiency was 463.7 GFlop/kW.

According to TOP500 compiler Jack Dongarra, professor of electrical engineering and computer science at the University of Tennessee, the K computer's performance equaled "one million linked desktop computers". The computer's annual running costs were estimated at US$10 million.

K Computer Mae rapid transit station

On 1 July 2011, Kobe's Port Island Line rapid transit system renamed one of its stations from "Port Island Minami" to "K Computer Mae" (meaning "In front of K Computer") denoting its vicinity. In June 2021, after the decommissioning of K computer, the station was renamed as Keisan Kagaku Center Station.

Notes

References

References

  1. "K computer, SPARC64 VIIIfs 2.0GHz, Tofu interconnect".
  2. Moroo, Jun. (2012). "Operation System for the K computer". Fujitsu Sci. Tech. J..
  3. (November 2018). "TOP500 List - November 2018".
  4. Japanese numbers]]
  5. (20 June 2011). "Japanese 'K' Computer Is Ranked Most Powerful". The New York Times.
  6. (20 June 2011). "Japanese supercomputer 'K' is world's fastest". The Telegraph.
  7. "Supercomputer "K computer" Takes First Place in World". Fujitsu.
  8. Moroo. (2012). "Operating System for the K computer". Fujitsu.
  9. "June 2011 TOP500 Supercomputer Sites".
  10. Kottoor, Naveena. (18 June 2012). "IBM supercomputer overtakes Fujitsu as world's fastest". BBC.
  11. "HPCG - November 2018 {{!}} TOP500 Supercomputer Sites".
  12. (16 August 2019). "Japan pulls plug on K, once the world's fastest supercomputer, after seven-year run".
  13. (23 June 2020). "Japan's Fugaku gains title as world's fastest supercomputer".
  14. (17 November 2011). ""K computer" No. 1 in Four Benchmarks at HPC Challenge Awards". Riken.
  15. "TOP500 - K computer, SPARC64 VIIIfx 2.0GHz, Tofu interconnect".
  16. (June 2017). "June 2017 HPCG Results". HPCG Benchmark.
  17. ""SPARC64™ VIIIfx": A Fast, Reliable, Low-power CPU". Fujitsu Global.
  18. "Riken Advanced Institute for Computational Science". Riken.
  19. (January 2012). "Japan's K Supercomputer". Trends in Japan.
  20. (17 November 2020). ""K Computer Mae" on the Port Liner will change its station name in June 2021 - [WTM] Railway & Travel News".

::callout[type=info title="Wikipedia Source"] This article was imported from Wikipedia and is available under the Creative Commons Attribution-ShareAlike 4.0 License. Content has been adapted to SurfDoc format. Original contributors can be found on the article history page. ::

2011-in-sciencefujitsu-supercomputersone-of-a-kind-computerspetascale-computersrikensparc-microprocessor-productssupercomputing-in-japan64-bit-computers