Architecture and Implement at ion of Vulcan

IBM’s recently announced Scalable PO WERparallel‘ family of systems is based upon the Vulcan architecture, and the currently available 9076 SPI’ parallel system utilazes fundamental Vulcan technology. The ezperimental Vulcan parallel processor is designed to scale to many thousands of microprocessor-based nodes. To support a machine of this size, the nodes and network incorporate Q number of unusual features to scale aggregate bandwidth, enhance reliability, diagnose faults, and simplify cabling. The multistage Vulcan network is a unified data and service network driven by a single oscillator. The attempt as made to detect all network errors via CRC checking and component shadowing. Switching elements contain a dynamically allocated shared buffer for storing blocked packet flits from any input port. This paper describes key elements of Vulcan’s hardware architecture and implementation details of the Vulcan prototype.

[1]  Randall Rettberg,et al.  The Monarch parallel processor hardware design , 1990, Computer.

[2]  Michael D. Noakes,et al.  System design of the J-Machine , 1990 .

[3]  Charles E. Leiserson,et al.  Fat-trees: Universal networks for hardware-efficient supercomputing , 1985, IEEE Transactions on Computers.

[4]  William J. Dally,et al.  Deadlock-Free Message Routing in Multiprocessor Interconnection Networks , 1987, IEEE Transactions on Computers.

[5]  Duncan H. Lawrie,et al.  Access and Alignment of Data in an Array Processor , 1975, IEEE Transactions on Computers.

[6]  Yuval Tamir,et al.  Hardware Support for High-Priority Traffic in VLSI Communication Swithes , 1992, J. Parallel Distributed Comput..

[7]  Isaac D. Scherson,et al.  Least common ancestor networks , 1993, [1993] Proceedings Seventh International Parallel Processing Symposium.

[8]  William J. Dally.  Virtual-Channel Flow Control , 1992, IEEE Trans. Parallel Distributed Syst..

[9]  G. Jack Lipovski,et al.  Parallel computing - theory and comparisons , 1987 .

[10]  Leonard Kleinrock,et al.  Virtual Cut-Through: A New Computer Communication Switching Technique , 1979, Comput. Networks.

[11]  Leslie Lamport,et al.  Time, clocks, and the ordering of events in a distributed system , 1978, CACM.