@inproceedings{a3870839ee2448029273e0fee0361ac0,
title = "Batched generation of incomplete sparse approximate inverses on GPUs",
abstract = "Incomplete 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.",
keywords = "Batched routines, GPU, Incomplete Sparse Approximate Inverses, Preconditioning",
author = "Hartwig Anzt and Edmond Chow and Thomas Huckle and Jack Dongarra",
note = "Publisher Copyright: {\textcopyright} 2016 IEEE.; 7th Workshop on Latest Advances in Scalable Algorithms for Large-Scale Systems, ScalA 2016 ; Conference date: 13-11-2016 Through 18-11-2016",
year = "2017",
month = jan,
day = "30",
doi = "10.1109/ScalA.2016.011",
language = "English",
series = "Proceedings of ScalA 2016: 7th Workshop on Latest Advances in Scalable Algorithms for Large-Scale Systems - Held in conjunction with SC16: The International Conference for High Performance Computing, Networking, Storage and Analysis",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "49--56",
booktitle = "Proceedings of ScalA 2016",
}