hrcak mascot   Srce   HID

Journal of computing and information technology, Vol. 1 No. 1, 1993.

Izvorni znanstveni članak

Program Partitioning for a Control/Data Driven Computer

Jurij Šilc ; Jožef Stefan Institute, Ljubljana, Slovenia
Borut Robič ; Jožef Stefan Institute, Ljubljana, Slovenia

Puni tekst: engleski, pdf (4 MB) str. 47-55 preuzimanja: 57* citiraj
APA 6th Edition
Šilc, J. i Robič, B. (1993). Program Partitioning for a Control/Data Driven Computer. Journal of computing and information technology, 1 (1), 47-55. Preuzeto s https://hrcak.srce.hr/150516
MLA 8th Edition
Šilc, Jurij i Borut Robič. "Program Partitioning for a Control/Data Driven Computer." Journal of computing and information technology, vol. 1, br. 1, 1993, str. 47-55. https://hrcak.srce.hr/150516. Citirano 27.02.2021.
Chicago 17th Edition
Šilc, Jurij i Borut Robič. "Program Partitioning for a Control/Data Driven Computer." Journal of computing and information technology 1, br. 1 (1993): 47-55. https://hrcak.srce.hr/150516
Harvard
Šilc, J., i Robič, B. (1993). 'Program Partitioning for a Control/Data Driven Computer', Journal of computing and information technology, 1(1), str. 47-55. Preuzeto s: https://hrcak.srce.hr/150516 (Datum pristupa: 27.02.2021.)
Vancouver
Šilc J, Robič B. Program Partitioning for a Control/Data Driven Computer. Journal of computing and information technology [Internet]. 1993 [pristupljeno 27.02.2021.];1(1):47-55. Dostupno na: https://hrcak.srce.hr/150516
IEEE
J. Šilc i B. Robič, "Program Partitioning for a Control/Data Driven Computer", Journal of computing and information technology, vol.1, br. 1, str. 47-55, 1993. [Online]. Dostupno na: https://hrcak.srce.hr/150516. [Citirano: 27.02.2021.]

Sažetak
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.

Hrčak ID: 150516

URI
https://hrcak.srce.hr/150516

Posjeta: 104 *