An optical bus-based distributed dynamic barrier mechanism

Barrier synchronization is a useful parallel programming construct for ensu ring that all processors are at a particular location in the code before an y processor is allowed to continue. Barrier synchronization is integral to programming models such as the Bulk Synchronous Parallel model. Specialized hardware is often used to improve the performance of a barrier synchroniza tion operation. With continued improvement in processor performance, more e fficient synchronization mechanisms are required to counter the rising rela tive cost of synchronization operations. A high-speed, distributed barrier synchronization mechanism has been developed for broadcast-based optical in terconnection networks. This mechanism avoids multiple conversions between optical and electrical signals by having each processor locally decide whet her the barrier in which it is participating has been satisfied. It also al lows arbitrary sized partitions to be built dynamically during the executio n of a program. Simulations of the current hardware design estimate that th e barrier synchronization requires less than 300ns for a 128-processor syst em.