Scalable Dense Linear Algebra on Heterogeneous Hardware
Innovative Computing Laboratory – The University of Tennessee Knoxville
Chapter in book HPC: Transition Towards Exascale Processing, in the series Advances in Parallel Computing, IOS Press, 2013
@article{bosilca2013scalable,
title={Scalable Dense Linear Algebra on Heterogeneous Hardware},
author={Bosilca, George and Bouteiller, Aurelien and Danalis, Anthony and Herault, Thomas and Kurzak, Jakub and Luszczek, Piotr and Tomov, Stanimire and Dongarra, Jack J},
year={2013}
}
Design of systems exceeding 1 Pflop/s and the push toward 1 Eflop/s, forced a dramatic shift in hardware design. Various physical and engineering constraints resulted in introduction of massive parallelism and functional hybridization with the use of accelerator units. This paradigm change brings about a serious challenge for application developers, as the management of multicore proliferation and heterogeneity rests on software. And it is reasonable to expect, that this situation will not change in the foreseeable future. This chapter presents a methodology of dealing with this issue in three common scenarios. In the context of shared-memory multicore installations, we show how high performance and scalability go hand in hand, when the well-known linear algebra algorithms are recast in terms of Direct Acyclic Graphs (DAGs), which are then transparently scheduled at runtime inside the Parallel Linear Algebra Software for Multicore Architectures (PLASMA) project. Similarly, Matrix Algebra on GPU and Multicore Architectures (MAGMA) schedules DAG-driven computations on multicore processors and accelerators. Finally, Distributed PLASMA (DPLASMA), takes the approach to distributed-memory machines with the use of automatic dependence analysis and the Direct Acyclic Graph Engine (DAGuE) to deliver high performance at the scale of many thousands of cores.
July 30, 2013 by hgpu
