Serialization of input and output data transfers in parallel structures

• Autorzy: Piech H. , Styś M.
• Języki publikacji: EN

Abstrakty

EN

We propose the new interpretation of feature named "serialization" as a characteristic of scheduling algorithms. In our interpretation serialization would be the property of algorithm referring to accumulating date in processes as well as to summary procedure of sending date to chosen place (processor or process) directly before their utilization. We want to practically prove that serialization can help us to enlargement the effectiveness of scheduling procedures.

Słowa kluczowe

EN

data transfer; parallel structures; serialization of input and output

• Wydawca: Wydawnictwo Politechniki Częstochowskiej
• Czasopismo: Prace Naukowe Instytutu Matematyki i Informatyki Politechniki Częstochowskiej
• Rocznik: 2007
• Tom: Vol. 6, nr 1
• Strony: 241--252
• Opis fizyczny: Bibliogr. 6 poz., rys., tab.

Twórcy

autor

Piech H.

autor

Styś M.

• Institute of Mathematics and Computer Science, Czestochowa University of Technology, Poland,

Bibliografia

• [1] Flynn M.J., Some computer organizations and their effectiveness, IEEE Trans. on Computers 1992, C21.
• [2] Raghavan P., A statistical adversary for online algorithms, Discrete Mathematics and Theoretical Computer Science, Springer-Verlag 1991.
• [3] Sait S.M., Youssef H., VLSI Design Automation: Theory and Practice, McGrow-Hill Book Co., Europe 1995.
• [4] Georges-Schleuter M., Explicit parallelism of genetic algorithms through population structures, Problem Solving from Nature, Springer-Verlag, New York 1991.
• [5] Valduriez P., Parallel Processing and Data Management, Chapman & Hall 1992.
• [6] Aarts E.H., Bont F.M., Habers E.H.,Van Laarhoven P.J., Parallel implementation of the statistical cooling algorithm, Integration, the VLSI Journal, 1986.