Communications of the ACM
Reduction languages for reduction machines
ISCA '75 Proceedings of the 2nd annual symposium on Computer architecture
A multi-processor reduction machine for user-defined reduction languages.
ISCA '80 Proceedings of the 7th annual symposium on Computer Architecture
A concurrent computer architecture and a ring based implementation
ISCA '79 Proceedings of the 6th annual symposium on Computer architecture
The architecture and system method of DDM1: A recursively structured Data Driven Machine
ISCA '78 Proceedings of the 5th annual symposium on Computer architecture
Evon: an extended von Neumann model for parallel processing
ACM '86 Proceedings of 1986 ACM Fall joint computer conference
Data-Driven and Demand-Driven Computer Architecture
ACM Computing Surveys (CSUR)
A recursive computer architecture for VLSI
ISCA '82 Proceedings of the 9th annual symposium on Computer Architecture
| Hi-index | 0.00 |
For a decentralized computing system of many computing elements (whether geographically distributed mainframe computers, or miniature computing elements within a single board or even chip), a naturally decentralized model is prerequisite for the organization of computation. This will allow a large number of computer elements to cooperate in the execution of a program. Computational models used in parallel computers (data flow, control flow, and reduction) help to identify the attributes of such a decentralized and general-purpose model. This paper examines data flow, control flow, and reduction models and presents a classification for their underlying concepts. In addition, it describes a computational model called recursive control flow, which is a synthesis of these concepts and which directly supports data flow, control flow, and reduction computation.