|
| Tuesday, 10 May 2016, 22:08 HKT/SGT | |
| |  | |
Source: Fujitsu Ltd | |
|
|
|
TOKYO, May 10, 2016 - (JCN Newswire) - Fujitsu today announced that it has received an order for a many-core large-scale supercomputer system from the University of Tokyo and the University of Tsukuba. The system will be deployed to the Joint Center for Advanced High-Performance Computing (JCAHPC), which the two universities jointly operate.
The new supercomputer will be an x86 cluster system consisting of 8,208 of the latest FUJITSU Server PRIMERGY x86 servers. These will run on the next-generation Intel(R) Xeon Phi(TM) processors (Intel development code name: Knights Landing), and achieve a theoretical aggregate performance of 25 petaflops (PFLOPS(1)).
The system is due to be completely operational starting December 2016, when it is expected to be Japan's highest-performance supercomputer.
Background
The University of Tokyo and the University of Tsukuba, along with Kyoto University, wrote their supercomputer system requirements as a common specification, the T2K Open Supercomputer, based on cutting-edge open technologies. Each university deployed its own x86 clusters based on the specification. In the case of the University of Tokyo and the University of Tsukuba, their respective systems operated from June 2008 to February 2014 (the University of Tsukuba) and March 2014 (the University of Tokyo).
In researching successor systems, the University of Tokyo and the University of Tsukuba established JCAHPC as Japan's first organization where universities would collaborate to build and operate a single supercomputer system. The universities made the decision to deploy Fujitsu's new supercomputer to this facility as their primary system.
About the System
This x86 cluster system is comprised of a combination of 8,208 of the latest PRIMERGY models as computation nodes, and an additional 51 PRIMERGY units, including 20 PRIMERGY RX2530 M2 models as login nodes. The computation nodes will use the latest PRIMERGY model optimally designed for the next-generation Intel(R) Xeon Phi(TM) processor (development code name: Knights Landing), giving the cluster a theoretical aggregate performance of 25 PFLOPS. Each computation node is to be connected with Intel(R) Omni-Path Architecture, the latest high-speed interconnect(2), for high-performance parallelization.
The high-density system is to have a compact physical footprint, with eight nodes fitting into a 2U rackmount chassis. Advanced "hot water" cooling technology(3) is used to supply cooling water to all the system's components, each of which have different optimum temperatures. In this way efficient cooling at low power is achieved.
Fujitsu will also supply an HPC middleware, the FUJITSU Software Technical Computing Suite, to ensure the efficient job scheduling and overall system management. The system will deliver maximum performance by utilizing Fujitsu and Fujitsu Laboratories' performance tuning technology.
Fujitsu is proud to be able to contribute to advances in computational science and simulation technologies by supplying large-scale, ultrafast mathematical processing performance.
[1] Petaflops: One quadrillion (1015) floating-point operations per second (peta = quadrillion). A measure of computing performance.
[2] Interconnect: The high-speed network connecting computation nodes.
[3] Hot water cooling technology: This technique allows for cooling with higher-temperature water than that of a conventional water cooling system, thus reducing the load on the hardware that provides cooled water. Furthermore, the heat radiated from the heated cooling water can be reused to further improve the system's energy efficiency.
Contact:
Fujitsu Limited
Public and Investor Relations
Tel: +81-3-3215-5259
URL: www.fujitsu.com/global/news/contacts/
Topic: Press release summary
Source: Fujitsu Ltd
Sectors: Cloud & Enterprise, IT Individual
http://www.acnnewswire.com
From the Asia Corporate News Network
Copyright © 2024 ACN Newswire. All rights reserved. A division of Asia Corporate News Network.
|
|
|
|
