Direct parallelization of call statements

• Main Authors: Triolet, Rémi, Irigoin, Francois, Feautrier, Paul
• Format: Conference Proceeding
• Language: English
• Subjects: Computing methodologies > Artificial intelligence > Computer vision > Computer vision problems > Interest point and salient region detections; Computing methodologies > Machine learning; Computing methodologies > Machine learning > Learning paradigms > Supervised learning > Supervised learning by classification; Computing methodologies > Machine learning > Machine learning algorithms > Feature selection; Computing methodologies > Machine learning > Machine learning approaches > Classification and regression trees; Computing methodologies > Modeling and simulation > Model development and analysis; Computing methodologies > Modeling and simulation > Model development and analysis > Model verification and validation; Computing methodologies > Parallel computing methodologies > Parallel algorithms; Software and its engineering > Software notations and tools > Compilers; Theory of computation > Design and analysis of algorithms > Parallel algorithms; Theory of computation > Formal languages and automata theory > Formalisms > Rewrite systems
• ISSN: 0362-1340
• DOI: 10.1145/12276.13329

Asynchronous CALL statements are necessary in order to use more than one processor in current multiprocessors. Detecting CALL statements that may be executed in parallel is one way to fill this need. This approach requires accurate approximations of called procedure effects. This is achieved by using new objects called Region and Execution Context. An algorithm to find asynchronous CALL statements is given. It involves a new dependence test to compute data dependence graphs, which provides better results than previous ones even when no CALL statements are involved. This method has been implemented in Parafrase and preliminary results are encouraging.