Program Partitioning for a Control/Data Driven Computer

Jurij Šilc, Borut Robič


The paper examines the problem of dataflow graph partitioning aiming to improve the efficiency of macro-dataflow computing on a hybrid control/data driven architecture. The partitioning consists of dataflow graph synchronization and scheduling of the synchronous graph. A new scheduling algorithm, called Global Arc Minimization (GAM), is introduced. The performance of the GAM algorithm is evaluated relative to some other known heuristic methods for static scheduling. When interprocessor communication delays are taken into account, the GAM algorithm achieves better performance on the simulated hybrid architecture.

Full Text:


Creative Commons License
This work is licensed under a Creative Commons Attribution-NoDerivatives 4.0 International License.

Crossref Similarity Check logo

Crossref logologo_doaj

 Hrvatski arhiv weba logo