It’s a good day to be Intel, Data Direct Networks (DDN), and Fujitsu. The Joint Center for Advanced High Performance Computing (JCAHPC) in Japan today released the details of its next generation supercomputer – Oakforest-PACS – which will deliver 25 PFLOPS, use Intel’s Xeon Phi (Knights Landing) manycore processors and Omni-Path Architecture, be built by Fujitsu, and be operational in December 2016.
When fired up, the Oakforest-PACS will be the fastest supercomputer system in Japan for the moment. Twenty-five PFLOPS would have taken the second spot on the TOP500 last November – ahead of Titan (DoE/Oak Ridge NL, 17.5 PFLOPS) but still short of Tianhe-2 (National Supercomputer Center, Guangzhou, 33.8 PFLOPS). There has been speculation that China will field two 100 PFLOPS machines this year, perhaps having one benchmarked in time for the June TOP500.
You may recall that JCAHPC was established in 2013 under agreement between the Center for Computational Sciences, University of Tsukuba (CCS) and the Information Technology Center, the University of Tokyo (ITC). JCAHPC consists of more than 20 faculty and staff members from both CCS and ITC. The primary mission of JCAHPC is designing, installing and operating the Post T2K System (Oakforest-PACS). CCS and ITC will cooperate for the procurement, installation and operation of the Oakforest-PACS under JCAHPC agreement.
The details of the system incude:
- “The Oakforest-PACS system has of 8,208 compute nodes, each of which consists of next-generation Intel Xeon Phi processor (code name: Knights Landing), and Intel Omni-Path Architecture (Intel OPA) as a high-performance interconnect, which is a brand-new fabric developed by Intel Corporation. This is the first large scale system with such a processor in Japan. The system is integrated by Fujitsu and its PRIMERGY server is employed as each of compute node. Additionally, the system employs the shared files system (capacity: 26 PB), and the fast file cache system (940 TB), both of which are provided by Data Direct Network (DDN).
- “Peak performance of the Oakforest-PACS is 25 PFLOPS and the total memory capacity is more than 900 TB. All compute nodes and servers of file systems are connected by fat-tree topology based on Intel OPA, which provides full bisection bandwidth. Therefore, flexible and efficient utilization and operation of compute nodes and file systems is available. Moreover, the fast file cache system is equipped with SSD’s and it is suitable for such applications that require higher file I/O performance.”
According to Robert Triendl, SVP at DDN, “The storage environment will consist of multiple shared file system, using DDN’s branch of the Intel Enterprise Edition of Lustre (IEEL) and DDN’s next generation ES14KX Lustre SSU, and providing up to 400 GB/sec of peak Lustre bandwidth. The shared file system will be enhanced by an NVMe-based distributed flash caching layer provided by 25 of DDN’s new IME14KX caching appliance with a total capacity of 940 TB and a peak performance of up to 1.4 TB/sec.”
Fujitsu has taken pains to conserve energy and space use. Oakforest-PACS will be a high-density system with a compact physical footprint, with eight nodes fitting into a 2U rackmount chassis. Advanced “hot water” cooling technology 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.
For Intel, the announcement is more evidence of traction for Omni-Path in the market place (see HPCwire article, Omni-Path Steadily Gaining Market Traction Says Intel) which is vying for sway with Mellanox’s Enhanced Data Rate (EDR) InfiniBand. (see HPCwire article, The Ultimate Debate – Interconnect Offloading) Versus Onloading).
“We’re pleased that the Universities of Tokyo and Tsukuba have chosen Fujitsu Primergy for their post-T2K leadership supercomputing system,” said Charles Wuischpard, vice president of the Data Center Group and general manager of High Performance Computing Platform Group at Intel Corporation. “Based on elements from the Intel Scalable System Framework, the system combines the highly parallel performance of next generation Intel Xeon Phi processors with the scalability of the Intel Omni-Path Architecture to deliver a highly efficient design. We look forward to the countless discoveries
When up and running, Oakforest-PACS will be available to researchers in Japan and their international collaborators through various types of programs operated by the High-Performance Computing Infrastructure, by MEXT’s Joint Usage/Research Centers, and by each of CCS and ITC under their original supercomputer resource sharing programs.
According to the release, the new supercomputer is expected to contribute to development of new frontiers in various domains including computational science and engineering (CSE). The Oakforest-PACS will be also utilized for education and training of students and young researchers in both of CSE and high-performance computing (HPC).
The Oakforest-PACS machine will be installed at the Kashiwa Research Complex II building in the Kashiwa-no-Ha (Oakleaf) campus, the University of Tokyo.