Abstract
Although automatic parallelization of conventional language programs is now widely accepted, relatively little emphasis has been placed on automatic parallelization of database query programs (sometimes referred to as “multiple queries” ). In this paper, we discuss the unique problems associated with automatic parallelization of database programs. From this discussion, we derive a complete approach to automatic parallelization of database programs. Beside integrating a number of existing techniques, our approach relies heavily on several new concepts, including the concepts of “algorithm-level” analysis and hybrid static/dynamic scheduling.
Date of this Version
1-1-1990
COinS