A Dynamic Task Distribution and Engine Allocation Strategy for Distributed Execution of Logic Programs

Distributed execution of logic programs on heterogeneous pro cessors requires e cient task distribution and engine synchronization to exploit the potential for performance This paper presents a task driven scheduling technique to distribute tasks to engines e ectively It consists of a dynamic hierarchy of distributed scheduling components able to adapt to program characteristics and the platform con guration and to control the considerable communication costs while exploiting good degrees of parallelism It also incorporates an abort failure mechanism to reduce speculative work and keep engines as busy as possible Several experimen tal results illustrate the performance of the model