Compilers: principles, techniques, and tools
Compilers: principles, techniques, and tools
The program dependence graph and its use in optimization
ACM Transactions on Programming Languages and Systems (TOPLAS)
Introduction to algorithms
Designing distributed applications with mobile code paradigms
ICSE '97 Proceedings of the 19th international conference on Software engineering
Advanced compiler design and implementation
Advanced compiler design and implementation
StratOSphere: mobile processing of distributed objects in Java
MobiCom '98 Proceedings of the 4th annual ACM/IEEE international conference on Mobile computing and networking
Automatic node selection for high performance applications on networks
Proceedings of the seventh ACM SIGPLAN symposium on Principles and practice of parallel programming
Ajents: towards an environment for parallel, distributed and mobile Java applications
JAVA '99 Proceedings of the ACM 1999 conference on Java Grande
Compiler optimizations for Java aglets in distributed data intensive applications
Proceedings of the 2002 ACM symposium on Applied computing
TRAVELER: A Mobile Agent Based Infrastructure for Wide Area Parallel Computing
ASAMA '99 Proceedings of the First International Symposium on Agent Systems and Applications Third International Symposium on Mobile Agents
Stochastic modeling and analysis of hybrid mobility in reconfigurable distributed virtual machines
Journal of Parallel and Distributed Computing
| Hi-index | 0.00 |
Mobile code carried by a mobile agent canautomatically travel to several data sources in order tocomplete a designated program. Traditionally, most mobileagent systems [7][8][13] need explicit involvement of theprogrammer to designate migration and computationschedule of the agent. In this paper, we study the compiler-supportedagent scheduling to optimize either the number ofthe migrations or the amount of data transfer. Twoapproaches are proposed and evaluated in our experiments,i.e. the static and dynamic scheduling algorithms. The firstalgorithm works totally offline. After converting the programcontrol flow graph (CFG) to program dependency graph(PDG), the schedule is worked out. On the other hand, inorder to dynamically schedule the agent when it reachespredicate (control flow) nodes, our dynamic schedulingalgorithm generates the motion schedule incrementally.Finally, our results show good improvement overunoptimized agent code both in terms of data transfer sizesand number of agent migrations.