Efficient parallel algorithms on optically interconnected arrays of processors

Arrays of processors with pipelined optical buses are introduced for the efficient implementation of computationally intensive applications. Techniques for the concurrent transmission of messages over the optical bus to avoid collision of messages are shown. Convenient parallel data movement operations are derived for this architecture, which are then used in the design of parallel algorithms for solving systems of linear equations and finding the roots of nonlinear equations. It is suitable for the SIMD mode of operation because it can be easily synchronized and scaled to a massive number of processors. Their time complexities are shown to compare favorably with those implemented on processors connected with electronic buses or point-to-point links.