DocumentCode :
2407371
Title :
Using randomized rounding to satisfy timing constraints of real-time preemptive tasks
Author :
Datta, Anupam ; Choudhury, Sidharth ; Basu, Anupam
Author_Institution :
Dept. of Comput. Sci., Stanford Univ., CA, USA
fYear :
2002
fDate :
2002
Firstpage :
705
Lastpage :
710
Abstract :
In preemptive real-time systems, a tighter estimate of the Worst Case Response Time (WCRT) of the tasks can be obtained if the layout of the tasks in memory is included in the estimation procedure. This is because the Cache Related Preemption Delay (CRPD) depends on the inter-task interference in the cache. We develop a response time analysis framework which takes the layout of the tasks into account. We present an ILP formulation which generates a layout of the tasks such that all timing constraints are satisfied. To overcome the issue of non-scalability associated with an ILP solution, we also present a linear programming relaxation of the ILP formulation, which offers an approximate solution. The performance of the proposed formulation is demonstrated
Keywords :
cache storage; constraint theory; integer programming; linear programming; real-time systems; timing; cache related preemption delay; integer linear programming; linear programming relaxation; memory task layout; randomized rounding; real-time preemptive system; timing constraint satisfaction; worst case response time; Computer science; Delay effects; Dynamic programming; Integer linear programming; Interference constraints; Linear programming; Polynomials; Real time systems; Resumes; Timing;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Design Automation Conference, 2002. Proceedings of ASP-DAC 2002. 7th Asia and South Pacific and the 15th International Conference on VLSI Design. Proceedings.
Conference_Location :
Bangalore
Print_ISBN :
0-7695-1441-3
Type :
conf
DOI :
10.1109/ASPDAC.2002.995017
Filename :
995017
Link To Document :
بازگشت