Global optimization techniques for automatic parallelization of hybrid applications

• Authors: Dhruva R. Chakrabarti;Prithviraj Banerjee
• Venue: ICS '01 Proceedings of the 15th international conference on Supercomputing
• Year: 2001

This paper presents a novel technique to perform global optimization of communication and preprocessing calls in the presence of array accesses with arbitrary subscripts. Our scheme is presented in the context of automatic parallelization of sequential programs to produce message passing programs for execution on distributed machines. We use the static single assignment (SSA) form for message passing programs as the intermediate representation and then present techniques to perform global optimizations even in the presence of array accesses with arbitrary subscripts. The focus of this paper is in showing that, using a uniform compilation method both at compile-time and at run-time, our framework is able to determine the earliest and the latest legal communication point for a certain distributed array reference even in the presence of arbitrary array addressing functions. Our scheme then heuristically determines the final communication point after considering the interaction between the relevant communication schedules. Owing to combined static and dynamic analysis, a quasi-dynamic method of code generation is implemented. We describe the need for proper interaction between the compiler and the run-time routines for efficient implementation of optimizations as well as for compatible code generation. All of the analyses is initiated at compile-time, static analyses of the program is done as much as possible, and then the run-time routines take over the analyses while building on the data structures initiated at compile time. This scheme has been incorporated in our compiler framework which can use uniform methods to compile, parallelize, and optimize a sequential program irrespective of the subscripts used in array addressing functions. Experimental results for a number of benchmarks on an IBM SP-2 show up to around 10-25% reduction in total run-times in our globally-optimized schemes compared to other state-of-the-art schemes on 16 processors.