ARCHITECTURE OF A PARALLEL MACHINE - CENJU3

Cenju-3 is a parallel computer in which up to 256 processing elements (PEs) are connected by a highspeed multistage interconnection network. In designing the system, the architecture is tuned for up to a 256 pr ocessor system. A VR4400 with 1 MB of secondary cache memory is implem ented on a multi-chip-module to realize a compact and high-performance PE. The multistage network is implemented very compactly. The number of the cables is equal to the number of processors. The dedicated netw ork interface hardware designed for the system achieves low latency an d high throughput. This paper presents the machine architecture and it s evaluation.