SUBOPTIMAL APPROACHES TO SCHEDULING MALLEABLE TASKS
Błażewicz Jacek
Machowiak M., Mounie G., Trystram D.
In the paper, the problem of scheduling a set of n malleable tasks on m parallel computers is considered. The tasks may be executed by several processors simultaneously and the processing speed of a task is a function of the number of processors alloted. The problem is motivated by real-life applications of parallel computer systems in scientific computing of highly parallelizable tasks. Starting from the continuous version of the problem (i. e. where the tasks may require a fractional part of the resources), we propose a general approximation algorithm with a performance guarantee equal to 2. Then, some improvements are derived that lead to a very good average behavior of the scheduling algorithm.
Poznań
OWN
artykuł
application/pdf
eng
This publication is unavailable to your account. If you have more privileged account please try to use it or contact with the institution connected to this digital library.