An extensible architecture for data flow processing

In this research, we propose a general model for computer architectures. This model allows us to integrate some of the existing system architecture approaches for increasing computer capacity and indicates new possibilities for improving the cost/performance ratio of future computer systems. The model leads to the development of general purpose data flow machines and to different degrees of sophistication within these machines. Our fundamental approach is to separate the CPU into elementary components. This allows us to make a distinction between components for control and components for performing various processing functions, thus yielding a high degree of resource sharing.

[1]  Ellis S. Cohen Semantic Models for Parallel Systems , 1975 .

[2]  R.W. Keyes,et al.  Physical limits in digital electronics , 1975, Proceedings of the IEEE.

[3]  Jack B. Dennis,et al.  A preliminary architecture for a basic data-flow processor , 1974, ISCA '75.

[4]  Philip Enslow,et al.  Multiprocessor Organization—a Survey , 1977, CSUR.

[5]  Chak-Kuen Wong,et al.  Dynamic Memories with Faster Random and Sequential Access , 1977, IBM J. Res. Dev..

[6]  John Cocke,et al.  Configurable computers: a new class of general purpose machines , 1972, International Sympoisum on Theoretical Programming.

[7]  James E. Rumbaugh,et al.  A Data Flow Multiprocessor , 1977, IEEE Transactions on Computers.

[8]  Richard M. Russell,et al.  The CRAY-1 computer system , 1978, CACM.

[9]  Raymond E. Miller,et al.  A Comparison of Some Theoretical Models of Parallel Computation , 1973, IEEE Transactions on Computers.

[10]  Richard M. Brown,et al.  The ILLIAC IV Computer , 1968, IEEE Transactions on Computers.

[11]  Jack B. Dennis,et al.  First version of a data flow procedure language , 1974, Symposium on Programming.

[12]  Paul R. Kosinski A data flow language for operating systems programming , 1973 .