Structure-aware Linear Solver for Realtime Convex Optimization for Embedded Systems

Ichitaro Yamazaki, Saeid Nooshabadi, Stanimire Tomov, Jack Dongarra

Research output: Contribution to journalArticlepeer-review

177 Downloads (Pure)

Abstract

With the increasing sophistication in the use of optimization algorithms such as deep learning on embedded systems, the convex optimization solvers on embedded systems have found widespread use. This letter presents a novel linear solver technique to reduce the run-time of convex optimization solver by using the property that some parameters are fixed during the solution iterations of a solve instance. Our experimental results show that the run-time can be reduced by two orders of magnitude.
Original languageEnglish
JournalIEEE Embedded Systems Letters
Early online date2 May 2017
DOIs
Publication statusPublished - 2017

Fingerprint

Dive into the research topics of 'Structure-aware Linear Solver for Realtime Convex Optimization for Embedded Systems'. Together they form a unique fingerprint.

Cite this