GPU-accelerated Co-design of Induced Dimension Reduction: Algorithmic Fusion and Kernel Overlap

TitleGPU-accelerated Co-design of Induced Dimension Reduction: Algorithmic Fusion and Kernel Overlap
Publication TypeConference Paper
Year of Publication2015
AuthorsAnzt, H., E. Ponce, G. D. Peterson, and J. Dongarra
Conference Name2nd International Workshop on Hardware-Software Co-Design for High Performance Computing
Date Published11-2015
PublisherACM
Conference LocationAustin, TX
AbstractIn 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.
Project Tags: