ABSTRACT
SUMMARY In this paper, we propose a high performance highly modular ATM switch architecture known as Bodhi which is suitable for small, large, and very large size ATM switch implementations. Its basic configuration consists of two stages: an input stage and an output stage. The input stage consists of input group modules (IGMs) and output stage output group modules (OGMs). Each IGM-OGM pair is connected by multiple paths which carry cells from IGMs to OGMs. Excess cells at the IGMs are recycled to minimize the cell loss probability. Another module called recirculation module is used to couple several IGMs together to create additional routes for recirculating cells which gives this architecture robustness against nonuniform and directed traffic. Multicasting has been implemented by integrating copying and broadcasting techniques, and using some novel techniques to minimize the switch complexity. A shared buffer architecture is employed for OGMs such that it implements multiple priorities dynamically in a weighted manner, requires no speedup, and, can function in standalone mode as small switches. The performance of Bodhi has been evaluated by computer simulation to select design parameters for a 1k × 1k (k = 1024) switch fabric. It allows growability from 2.4 gigabit to 150 gigabit switch, and, expandability to 100+ Terrabit switch with the complexity increasing approximately linearly with size. Based on the study presented in this paper, it is seen that the Bodhi architecture offers a high degree of modularity, weighted dynamic priority control, robustness against nonuniform traffic conditions, low complexity, low latency, and, supports multicasting efficiently and without any limitation. Bodhi, therefore, has high potential for application in high speed broadband networks.
