A practical approach to DOACROSS parallelization

Loops with cross-iteration dependences (doacross loops) often contain significant amounts of parallelism that can potentially be exploited on modern manycore processors. However, most production-strength compilers focus their automatic parallelization efforts on doall loops, and consider doacross parallelism to be impractical due to the space inefficiencies and the synchronization overheads of past approaches. This paper presents a novel and practical approach to automatically parallelizing doacross loops for execution on manycore-SMP systems. We introduce a compiler-and-runtime optimization called dependence folding that bounds the number of synchronization variables allocated per worker thread (processor core) to be at most the maximum depth of a loop nest being considered for automatic parallelization. Our approach has been implemented in a development version of the IBM XL Fortran V13.1 commercial parallelizing compiler and runtime system. For four benchmarks where automatic doall parallelization was largely ineffective (speedups of under 2×), our implementation delivered speedups of 6.5×, 9.0×, 17.3×, and 17.5× on a 32-core IBM Power7 SMP system, thereby showing that doacross parallelization can be a valuable technique to complement doall parallelization.