Data-Parallel Language Features for Sparse Codes: A Survey and Contributions

This paper proposes a new approach to improve data-parallel languages in the context of sparse and irregular computation. We analyze the capabilities of High Performance Fortran (HPF) and Vienna Fortran, and identify a set of problems leading to suboptimal parallel code generation for such computations on distributedmemory machines. Finally, we propose extensions to the data distribution facilities in Vienna Fortran which address these issues and provide a powerful mechanism for efficiently expressing sparse algorithms