Search Results for author: Hars Vardhan

Found 1 papers, 0 papers with code

dMath: Distributed Linear Algebra for DL

no code implementations19 Nov 2016 Steven Eliuk, Cameron Upright, Hars Vardhan, Stephen Walsh, Trevor Gale

The paper presents a parallel math library, dMath, that demonstrates leading scaling when using intranode, internode, and hybrid-parallelism for deep learning (DL).

Management Math

Cannot find the paper you are looking for? You can Submit a new open access paper.