Fujitsu Limited has began shipping their very own Supercomputer Fugaku, which is jointly developed with Riken and promoted by the Ministry of Education, Culture, Sports, Science and Technology with the goal to start the operation somewhere between 2021 and 2022. The first machine to be shipped this time is one of the computer units of Fugaku, a supercomputer system comprised of over 150,000 high-performance CPUs connected together. Fujitsu will continue to deliver the units to RIKEN Center for Computational Science in Kobe, Japan, for installation and tuning.
By developing Fugaku, Fujitsu has accumulated various technologies and know-how, including cutting-edge development, system integration, simulation, and AI. Utilizing its supercomputing technologies, Fujitsu is contributing to resolve social issues, promote innovative research, apply such technologies in DX (Digital Transformation), and enhance its industrial competitiveness, including new drug development and the realization of a safe society through disaster prevention and mitigation.
The supercomputer Fugaku is a very large system, in which more than 150,000 high-performance CPUs A64FX(1) developed by Fujitsu based on the Arm instruction set architecture are connected by a high-speed network Tofu Interconnect D(2). In pursuit of superior performance and high reliability, Fujitsu has concentrated its advanced technologies and developed the supercomputer together with RIKEN.
Fugaku is manufactured by Fujitsu IT Products Ltd., and the units, to be shipped for the first time on December 2, will be delivered to RIKEN Center for Computational Science in Kobe, Japan.
Fugaku has been developed with the aim of achieving up to 100 times the application performance of the K computer with approximately 3 times the power consumption. With the highest energy-efficiency in the world, a prototype of the system received the No.1 position in Green500(3) at SC19, the International Conference for High-Performance Computing, Networking, Storage, and Analysis, held in Denver, U.S., from November 17 to November 22.
Fujitsu will continue to deliver computer units of Fugaku and carry out installation and tuning in preparation for the start of general operation between 2021 and 2022. At the same time, by globally providing the commercial Fujitsu Supercomputer PRIMEHPC FX1000 and PRIMEHPC FX700 that the company has developed by utilizing the technology of Fugaku, Fujitsu will promote solutions to social issues and cutting-edge research, such as in drug development and the realization of a safe society through disaster prevention and mitigation. Fujitsu will also provide these products to a wide range of customers in a variety of industries, thereby contributing to the application of these products to the DX field and strengthening corporate competitiveness.
(1) High-performance CPUs A64FX The world’s first CPU adopting Scalable Vector Extension (SVE) which is an extension of the Arm v8-A architecture for supercomputers. Developed by Fujitsu, A64FX has inherited the high performance and low power consumption CPU design the company has cultivated over the years. It realizes high performance per unit of power, high memory bandwidth by adopting HBM2 (High Bandwidth Memory), which is a high performance stacked memory. A64FX can also cope with the half-precision operation and integer dot product operation which are important in deep learning, etc., and are expected to expand its application in the field of AI.
(2) Tofu Interconnect D A network that connects nodes directly at low latency and high bandwidth (6.8 GB/s per link). Large-scale systems of up to about 390,000 nodes can be constructed by 6-dimensional mesh torus connection. It was developed by improving the function of Tofu Interconnect developed for K computer.
(3) Received the No.1 position in Green500 Presented at SC19 on November 18, the Green500 ranks the world’s top 500 fastest computing supercomputers by power consumption and efficiency among the TOP500 supercomputers. The performance measurement of the award-winning system demonstrated that Fugaku technologies have the world’s highest energy efficiency, achieving 1.9995 PFLOPS (petaflops) in calculation speed for simultaneous linear equations (LINPACK) against 2.3593 PFLOPS in a peak performance, and 16.876 GFLOPS/W (gigaflops per watt) in a performance per 1 watt of power consumption.
Archive
- October 2024(44)
- September 2024(94)
- August 2024(100)
- July 2024(99)
- June 2024(126)
- May 2024(155)
- April 2024(123)
- March 2024(112)
- February 2024(109)
- January 2024(95)
- December 2023(56)
- November 2023(86)
- October 2023(97)
- September 2023(89)
- August 2023(101)
- July 2023(104)
- June 2023(113)
- May 2023(103)
- April 2023(93)
- March 2023(129)
- February 2023(77)
- January 2023(91)
- December 2022(90)
- November 2022(125)
- October 2022(117)
- September 2022(137)
- August 2022(119)
- July 2022(99)
- June 2022(128)
- May 2022(112)
- April 2022(108)
- March 2022(121)
- February 2022(93)
- January 2022(110)
- December 2021(92)
- November 2021(107)
- October 2021(101)
- September 2021(81)
- August 2021(74)
- July 2021(78)
- June 2021(92)
- May 2021(67)
- April 2021(79)
- March 2021(79)
- February 2021(58)
- January 2021(55)
- December 2020(56)
- November 2020(59)
- October 2020(78)
- September 2020(72)
- August 2020(64)
- July 2020(71)
- June 2020(74)
- May 2020(50)
- April 2020(71)
- March 2020(71)
- February 2020(58)
- January 2020(62)
- December 2019(57)
- November 2019(64)
- October 2019(25)
- September 2019(24)
- August 2019(14)
- July 2019(23)
- June 2019(54)
- May 2019(82)
- April 2019(76)
- March 2019(71)
- February 2019(67)
- January 2019(75)
- December 2018(44)
- November 2018(47)
- October 2018(74)
- September 2018(54)
- August 2018(61)
- July 2018(72)
- June 2018(62)
- May 2018(62)
- April 2018(73)
- March 2018(76)
- February 2018(8)
- January 2018(7)
- December 2017(6)
- November 2017(8)
- October 2017(3)
- September 2017(4)
- August 2017(4)
- July 2017(2)
- June 2017(5)
- May 2017(6)
- April 2017(11)
- March 2017(8)
- February 2017(16)
- January 2017(10)
- December 2016(12)
- November 2016(20)
- October 2016(7)
- September 2016(102)
- August 2016(168)
- July 2016(141)
- June 2016(149)
- May 2016(117)
- April 2016(59)
- March 2016(85)
- February 2016(153)
- December 2015(150)