June 25, 2019 — For the ninth consecutive time, Japan’s K computer has taken the top spot on the Graph500 ranking, a benchmark which, in comparison to the better known Top500 ranking, gauges the ability of supercomputers on data-intensive loads rather than simple speed, with the goal of improving computing involving complex data problems in “big data” areas such as cybersecurity, medical informatics, data enrichment, social networks, symbolic networks, and modeling neuronal circuits in the brain. The benchmark is particularly important for efforts to realize an ultra-smart society such as that outlined in the Japanese government’s plan for Society 5.0, since the big data acquired by technologies such as IoT will need to be converted into graph data and processed at high speed to realize new business applications, with the aim both to create new industries and to contribute to the achievement of the United Nations Sustainable Development Goals, particularly goal 9 (Industry, innovation and infrastructure) and 11 (Sustainable cities and communities).
The top rank this time was won by a collaboration involving RIKEN, Kyushu University, Tokyo Institute of Technology, the Barcelona Supercomputing Center, Fujitsu, Fixstars Corporation, and the Japan Science and Technology Agency. The achievement was announced on June 19 at the ISC High Performance 2019 event in Frankfurt, Germany. In order to encourage the further development of such tools, the group has published the program as open source code on the GitHub repository. In addition, the group is working to develop new large-scale graph analysis algorithms and programs to operate on the supercomputer Fugaku, which is scheduled to succeed the K computer around 2021.
Two research projects funded by the Japan Science and Technology Agency (JST) CREST programs contributed to this achievement: “Advanced Computing and Optimization Infrastructure for Extremely Large-Scale Graphs on Post Peta-Scale Supercomputers” (PI: Prof. Katsuki Fujisawa of Kyushu University and Co-PI: Prof. Toyotaro Suzumura of Barcelona Supercomputing Center), which is a project in the research area of Development of System Software Technologies for Post-Peta Scale High Performance Computing (Research Supervisor: Prof. Mitsuhisa Sato of RIKEN), and “EBD: Extreme Big Data – Convergence of Big Data and HPC for Yottabyte Processing” (PI: Prof. Satoshi Matsuoka of Tokyo Institute of Technology), which is a project in the Advanced Core Technologies for Big Data Integration area (Research Supervisor: Prof. Masaru Kitsuregawa of the National Institute of Informatics).
About the Graph500
Data-intensive supercomputer applications are an increasingly important workload, but are ill-suited for platforms designed for 3D physics simulations. Application performance cannot be improved without a meaningful benchmark. Graphs are a core part of most analytics workloads. Backed by a steering committee of over 30 international HPC experts from academia, industry, and national laboratories, this specification establishes a large-scale benchmark for these applications. The Graph500 was announced at ISC2010 and the first list appeared at SC2010.
RIKEN is Japan’s largest comprehensive research institution renowned for high-quality research in a diverse range of scientific disciplines. Founded in 1917 as a private research foundation in Tokyo, RIKEN has grown rapidly in size and scope, today encompassing a network of world-class research centers and institutes across Japan.