A parallel computer architecture for real-time control applications in grasping and manipulation

A scheduling algorithm is presented for multiprocessor architectures based on either complete or incomplete crossbar interconnection networks. The proposed algorithm takes into account the communication delays between processors and minimizes both the execution time and the communication cost. The algorithms are verified by experiments on an INMOS T800 transputer-based system. The system consists of eight nodes connected by bidirectional serial communication lines forming a 3-dimensional hypercube.<
>