Skip to main content



Archived content

NOTE: this is an archived page and the content is likely to be out of date.

Why Fujitsu

In 2006, the Japanese government defined supercomputing as a key technology of national importance. To advance research in this strategic area and maintain Japan's leading edge, the government also earmarked investment funds for large-scale promising projects. As part of the High-Performance Computing Infrastructure (HPCI) initiative led by the Japanese Ministry of Education, Culture, Sports, Science and Technology (MEXT), RIKEN – Japan's leading research institute – was entrusted with the task of developing a next-generation supercomputer.

To support it on this national strategic project, RIKEN needed a trustworthy, experienced partner. It turned to Fujitsu. Not only does Fujitsu have over 40 years of experience in the mainframe business, it has also gained invaluable insights pioneering the development of supercomputers over the past 30 years. Even more importantly, RIKEN valued Fujitsu's engineering spirit and unique approach to innovation. It was confident that Fujitsu would have the courage and vision to take a risk and try something totally new in order to break the existing speed and performance barriers. In addition, very few companies can match Fujitsu's technical depth and breadth, spanning core competencies in processor development, interconnect controller chips and system administration/management software for large-scale systems.

Both partners had been working on the K computer since 2006 with full operation and shared use scheduled for November 2012.

When we launched the K computer project, we knew we would need an exceptional partner at our side – a partner with the vision, determination and technical depth to accompany us into uncharted terrain and come out the other side with the world's fastest computer. Fujitsu was the obvious choice for us, bringing an invaluable combination of technical expertise and innovation to the table.

The possibilities

About K computer

Quick guide to supercomputing