@inproceedings{95ee6a0e5d0546f4987a0ce1840834f7,
title = "GPU-accelerated co-design of induced dimension reduction: Algorithmic fusion and kernel overlap",
abstract = "In this paper we present an optimized GPU co-design of the Induced Dimension Reduction (IDR) algorithm for solving linear systems. Starting from a baseline implementation based on the generic BLAS routines from the MAGMA software library, we apply optimizations that are based on kernel fusion and kernel overlap. Runtime experiments are used to investigate the benefit of the distinct optimization techniques for different variants of the IDR algorithm. A comparison to the reference implementation reveals that the interplay between them can succeed in cutting the overall runtime by up to about one third.",
keywords = "Co-design, GPU, Induced Dimension Reduction (IDR), Kernel fusion, Kernel overlap",
author = "Hartwig Anzt and Eduardo Ponce and Peterson, {Gregory D.} and Jack Dongarra",
note = "Publisher Copyright: Copyright {\textcopyright} 2015 ACM.; 2nd International Workshop on Hardware-Software Co-Design for High Performance Computing, Co-HPC 2015 ; Conference date: 15-11-2015",
year = "2015",
month = nov,
day = "15",
doi = "10.1145/2834899.2834907",
language = "English",
series = "Proceedings of Co-HPC 2015: 2nd International Workshop on Hardware-Software Co-Design for High Performance Computing - Held in conjunction with SC 2015: The International Conference for High Performance Computing, Networking, Storage and Analysis",
publisher = "Association for Computing Machinery, Inc",
booktitle = "Proceedings of Co-HPC 2015",
}