Skip to main content Skip to main navigation

Publication

Reconfigurable Hardware-Based Acceleration for Machine Learning and Signal Processing

Hendrik Wöhrle; Frank Kirchner
In: Formal Modeling and Verification of Cyber-Physical Systems: 1st International Summer School on Methods and Tools for the Design of Digital Systems. Graduate School System Design (SyDe-2015), September 9-11, Bremen, Germany, Pages 311-313, Lecture Notes in Computer Science (LNCS), Springer Fachmedien Wiesbaden, Wiesbaden, 9/2015.

Abstract

Certain application areas of signal processing and machine learning, such as robotics, impose technical limitations on the computing hardware, which make the use of generic processors unfeasible. In this paper we propose a framework for the development of data ow accelerators as a possible solution. The approach is based on model based development and code generation to allow a rapid development of the accelerators and perform a functional verification of the overall system.

Projekte

Weitere Links