Parallel Programming On Cenju - A Multiprocessor System For Modular Circuit Simulation

Cenju is an experimental multiprocessor system with a distributed shared memory scheme developed mainly for circuit simulation. The system is composed of 64 PEs (Processor Elements) which are divided into eight clusters. In each cluster, eight PEs are connected by a cluster bus. The cluster buses are in turn connected by a multistage network to form the whole system. Each PE consists of 32-bit microprocessor MC68020 (20 MHz), 4/8 MB of RAM and a floating-point processor WTL1167 (20 MHz). The system supports parallel programming using C and FORTRAN, in which parallel primitives are provided as subroutines to be embedded by the programmer. In this system, programmers must adhere to a Producer-Consumer model in which the producer of the data always writes the data to the consumer's memory. The simulation algorithm used in circuit simulation is hierarchical modular simulation in which the circuit to be simulated is divided subcircuits connected by an interconnection network. For the 64 multiprocessor system, a speedup of 15.8 compared to the one processor case was attained for a DRAM circuit. Furthermore, by parallelizing the serial bottleneck, a speedup of 25.8 could be realized. In this article, authors briefly describe the simulation algorithm and Cenju architecture, then dwell in some detail on the parallel programming aspects of Cenju.