Parallelization Techniques for Sparse Matrix Applications

Sparse matrix problems are diicult to parallelize eeciently on distributed memory machines since data is often accessed indirectly. Inspector/executor strategies, which are typically used to parallelize loops with indirect references, incur substantial run-time preprocessing overheads when references with multiple levels of indirection are encountered | a frequent occurrence in sparse matrix algorithms. The sparse array rolling (SAR) technique, introduced in 15], signiicantly reduces these preprocessing overheads. This paper outlines the SAR approach and describes its runtime support accompanied by a detailed performance evaluation. The results demonstrate that SAR yields signiicant reduction in preprocessing overheads compared to standard inspector/executor techniques.