K computer
From Wikipedia the free encyclopedia
Active | June 2011 – August 2019 |
---|---|
Sponsors | MEXT, Japan |
Operators | Fujitsu |
Location | Riken Advanced Institute for Computational Science |
Architecture | 88,128 SPARC64 VIIIfx processors, Tofu interconnect |
Power | 12.6 MW |
Operating system | Linux[1][2] |
Speed | 10.51 petaflops (Rmax) |
Ranking | TOP500: 18th, as of November 2018[update][3] |
The K computer – named for the Japanese word/numeral "kei" (京), meaning 10 quadrillion (1016)[4][Note 1] – was a supercomputer manufactured by Fujitsu, installed at the Riken Advanced Institute for Computational Science campus in Kobe, Hyōgo Prefecture, Japan.[4][5][6] The K computer was based on a distributed memory architecture with over 80,000 compute nodes.[7] It was used for a variety of applications, including climate research, disaster prevention and medical research.[6] The K computer's operating system was based on the Linux kernel, with additional drivers designed to make use of the computer's hardware.[8]
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computer to top 10 petaflops.[9][10] It had originally been slated for completion in June 2012.[10] In June 2012, K was superseded as the world's fastest supercomputer by the American IBM Sequoia.[11]
As of November 2018[ref], 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 It held the first place until June 2018, when it was superseded by Summit and Sierra.[12][13]
The K supercomputer was decommissioned on 30 August 2019.[14] 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.[15]
Performance
[edit]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;[4][6][9] it achieved this performance with a computing efficiency ratio of 93.0%. The previous record holder was the Chinese National University of Defense Technology's Tianhe-1A, which performed at 2.507 petaflops.[5] The TOP500 list is revised semiannually, and the rankings change frequently, indicating the speed at which computing power is increasing.[4] In November 2011, Riken reported that K had become the first supercomputer to exceed 10 petaflops, achieving a LINPACK performance of 10.51 quadrillion computations per second with a computing efficiency ratio of 93.2%.[10] K received top ranking in all four performance benchmarks at the 2011 HPC Challenge Awards.[16]
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.[11]
On the TOP500 list, it became first in June 2011, falling down through time to lower positions, to eighteenth in November 2018.[12]
K computer held third place in the HPCG benchmark test proposed by Jack Dongarra, with 0.6027 HPCG PFLOPS in November 2018.[17]
Specifications
[edit]Node architecture
[edit]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,[1][18] manufactured by Fujitsu with 45 nm CMOS technology.[19] Each cabinet contained 96 computing nodes, in addition to six I/O nodes. Each computing node contained a single processor and 16 GB of memory. The computer's water cooling system was designed to minimize failure rate and power consumption.[20]
Network
[edit]The nodes were connected by Fujitsu's proprietary torus fusion (Tofu) interconnect.[20][21][22][23]
File system
[edit]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.[20][24]
Power consumption
[edit]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.[9]
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".[5] The computer's annual running costs were estimated at US$10 million.[5]
K Computer Mae rapid transit station
[edit]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.[25] In June 2021, after the decommissioning of K computer, the station was renamed as Keisan Kagaku Center Station.[26]
See also
[edit]Notes
[edit]- ^ See Japanese numbers
References
[edit]- ^ a b K computer, SPARC64 VIIIfs 2.0GHz, Tofu interconnect
- ^ Moroo, Jun; et al. (2012). "Operation System for the K computer" (PDF). Fujitsu Sci. Tech. J. 48 (3): 295–301. Archived from the original (PDF) on 28 December 2013. Retrieved 23 May 2013.
- ^ "TOP500 List - November 2018". www.top500.org. November 2018. Retrieved 16 November 2018.
- ^ a b c d "Japanese 'K' Computer Is Ranked Most Powerful". The New York Times. 20 June 2011. Retrieved 20 June 2011.
- ^ a b c d "Japanese supercomputer 'K' is world's fastest". The Telegraph. 20 June 2011. Retrieved 20 June 2011.
- ^ a b c "Supercomputer "K computer" Takes First Place in World". Fujitsu. Retrieved 20 June 2011.
- ^ Yokokawa, Mitsuo; Shoji, Fumiyoshi; Uno, Atsuya; Kurokawa, Motoyoshi; Watanabe, Tadashi (1–3 August 2011). The K computer: Japanese next-generation supercomputer development project. IEEE/ACM International Symposium on Low Power Electronics and Design. IEEE. pp. 371–372. doi:10.1109/ISLPED.2011.5993668. Retrieved 30 January 2013.
- ^ Moroo; et al. (2012). "Operating System for the K computer" (PDF). Fujitsu. Retrieved 18 June 2013.
- ^ a b c June 2011 TOP500 Supercomputer Sites
- ^ a b c "K computer" Achieves Goal of 10 Petaflops". Fujitsu. 2 November 2011. Retrieved 10 November. 2011.
- ^ a b Kottoor, Naveena (18 June 2012). "IBM supercomputer overtakes Fujitsu as world's fastest". BBC.
- ^ a b "TOP500 - K computer, SPARC64 VIIIfx 2.0GHz, Tofu interconnect". Retrieved 15 November 2017.
- ^ "HPCG - November 2018 | TOP500 Supercomputer Sites". www.top500.org. Retrieved 16 November 2018.
- ^ "Japan pulls plug on K, once the world's fastest supercomputer, after seven-year run". www.japantimes.co.jp. 16 August 2019. Retrieved 30 August 2019.
- ^ "Japan's Fugaku gains title as world's fastest supercomputer". www.riken.jp. 23 June 2020. Retrieved 13 April 2024.
- ^ ""K computer" No. 1 in Four Benchmarks at HPC Challenge Awards". Riken. 17 November 2011. Retrieved 17 November 2011.
- ^ "June 2017 HPCG Results". HPCG Benchmark. June 2017. Retrieved 29 September 2017.
- ^ ""SPARC64™ VIIIfx": A Fast, Reliable, Low-power CPU". Fujitsu Global. Retrieved 24 February 2013.
- ^ Takumi Maruyama (25 August 2009). SPARC64(TM) VIIIfx: Fujitsu's New Generation Octo Core Processor for PETA Scale computing (PDF). Proceedings of Hot Chips 21. IEEE Computer Society. Retrieved 24 February 2013.
- ^ a b c "Riken Advanced Institute for Computational Science" (PDF). Riken. Archived from the original (PDF) on 27 July 2011. Retrieved 20 June 2011.
- ^ "Programming on K computer" (PDF). Fujitsu. Retrieved 24 June 2011.
- ^ "Open MPI powers 8 petaflops". Cisco Systems. Archived from the original on 28 June 2011. Retrieved 24 June 2011.
- ^ Yuichiro Ajima; et al. (2009). "Tofu: A 6D Mesh/Torus Interconnect for Exascale Computers". Computer. 42 (11). IEEE Computer Society: 36–40. doi:10.1109/MC.2009.370. S2CID 2049404.
- ^ "An Overview of Fujitsu's Lustre Based File System" (PDF). Fujitsu. Retrieved 24 June 2011.
- ^ "Japan's K Supercomputer". Trends in Japan. January 2012. Retrieved 6 June 2012.
- ^ ""K Computer Mae" on the Port Liner will change its station name in June 2021 - [WTM] Railway & Travel News". 17 November 2020.
External links
[edit]- Riken Advanced Institute for Computational Science
- Riken Next-Generation Supercomputer R&D Center
- K computer: Fujitsu Global
- Fujitsu Scientific & Technical Journal, July 2012 (Vol. 48, No. 3, The K computer
- Special Interview: Taking on the Challenge of a 10-Petaflop Computer, Riken News, No. 298, April 2006.
- June 2017 Top 500