Combining Interprocedural Compile-Time and Run-Time Parallelization

摘要

This report describes the final results of a project revolving around an integrated allelization system that combines high quality interprocedural compile time analysis with flexible run time support. This research builds on our previous extensive work on interprocedural compile time analysis for parallelization, sponsored by DARPA through contracts at Rice University and Stanford University. The system is designed to address three core issues: (1) improving the effectiveness of compile time parallelization analysis; (2) integration of compile time analysis with efficient run time parallelization tests; and (3) managing an efficient mapping of parallel contracts to a contracts to a target architecture.