Batched Generation of Incomplete Sparse Approximate Inverses on GPUs

TitleBatched Generation of Incomplete Sparse Approximate Inverses on GPUs
Publication TypeConference Proceedings
Year of Publication2016
AuthorsAnzt, H., E. Chow, T. Huckle, and J. Dongarra
Conference NameProceedings of the 7th Workshop on Latest Advances in Scalable Algorithms for Large-Scale Systems
Series TitleScalA '16
Pagination49–56
Date Published11-2016
ISBN Number978-1-5090-5222-6
AbstractIncomplete Sparse Approximate Inverses (ISAI) have recently been shown to be an attractive alternative to exact sparse triangular solves in the context of incomplete factorization preconditioning. In this paper we propose a batched GPU-kernel for the efficient generation of ISAI matrices. Utilizing only thread-local memory allows for computing the ISAI matrix with very small memory footprint. We demonstrate that this strategy is faster than the existing strategy for generating ISAI matrices, and use a large number of test matrices to assess the algorithm's efficiency in an iterative solver setting.
DOI10.1109/ScalA.2016.11