The new system is a hybrid system consisting of three computational server systems, each intended for different purposes: large-scale parallel computation unit, application development unit for the next generation supercomputer, and SMP server (shared memory server). The company claims that new system has a speed of 186.1 teraflops.
The large-scale parallel computation unit, which forms the core of the new system, is able to deliver a parallel computing environment through the use of Fujitsu’s latest blade server, Primergy BX900, in a configuration of 2,134 nodes (4,268 CPUs, 17,072 cores) connected using InfiniBand QDR interconnect technology.
The code development unit uses a 300-node FX1 server cluster and the shared memory server uses a single-node SPARC Enterprise M9000 UNIX server. There is also a 36-unit Eternus DX80 disk array storage system.
All three server systems run Parallelnavi, Fujitsu’s middleware, which delivers a common development and execution environment and unified operations management, thereby ensuring a high level of operability.
