Annual review of computer science vol. 1, 1986
A report on the Sisal language project
Journal of Parallel and Distributed Computing - Special issue: data-flow processing
A multiprocessor DSP system using PADDI-2
DAC '98 Proceedings of the 35th annual Design Automation Conference
The VAL Language: Description and Analysis
ACM Transactions on Programming Languages and Systems (TOPLAS)
Advanced Topics in Dataflow Computing and Multithreading
Advanced Topics in Dataflow Computing and Multithreading
A preliminary architecture for a basic data-flow processor
ISCA '75 Proceedings of the 2nd annual symposium on Computer architecture
Hi-index | 0.00 |
Dataflow is a generic term characterizing algorithms or computers whose actions are determined by the availability of the data needed for these actions. Computations that are expressed and executed in dataflow terms are controlled by the arrival of data at operators (called actors). This is to be contrasted to control flow environments of conventional, so-called von Neumann machines, where the locus of execution is determined by an instruction pointer (or program counter-q.v.) that identifies the operation to be performed next. Dataflow algorithms can be represented as directed graphs in which the arcs are data paths and the nodes are operations to be performed on the data tokens arriving on the incoming arcs. The graph shown in Fig. 1 is a dataflow procedure. Multiple paths through such a graph represent parts of a computation that can be executed in parallel.