C++ programming with CORBA
An Application-Level Dependable Technique for Farmer-Worker Parallel Programs
HPCN Europe '97 Proceedings of the International Conference and Exhibition on High-Performance Computing and Networking
System structure for software fault tolerance
Proceedings of the international conference on Reliable software
Computer Architecture: A Quantitative Approach
Computer Architecture: A Quantitative Approach
The N-Version Approach to Fault-Tolerant Software
IEEE Transactions on Software Engineering
PSIP: Program & System Information Protocol
PSIP: Program & System Information Protocol
Hierarchical master-worker skeletons
PADL'08 Proceedings of the 10th international conference on Practical aspects of declarative languages
| Hi-index | 0.00 |
This paper describes an algorithm for dynamically assigning tasks to processing entities in a world where each task has a set of resource or service requirements and each processing entity a set of resources or service capabilities. A task needs to be assigned to a node that offers all required services and the set of tasks is finished within a minimal execution time frame. Dependability and adaptability are inherent to the algorithm so that it accounts for the varying execution time of each task or the failure of a processing node. The algorithm is based on a dependable technique for farmer-worker parallel programs and is enhanced for modeling the time constraints in combination with the required configuration set in a multidimensional resources model. This paper describes how the algorithm is used for dynamically load balancing and parallelizing the nightly tests of a digital television content-processing embedded device.