quapona technologies

In this work a novel approach to automatically generate hardware is introduced that allows accelerated simulation of artificial neural networks (ANN) on field-programming gate arrays (FPGAs). A compiler architecture has been designed that primarily aims at reducing the development effort for non-hardware developers. This is done by implementing automatic generation of accordingly adjusted hardware processors. Deduced from high-level OpenCL source code, the processors are able to spatially map ANNs in a massive parallel fashion.

Autoren: Jörn Hoffmann, Frank Güttler, and M. Bogdan

Quelle: DATE 2011, Grenoble, 2011

date2011.pdf[Design of Electronic Systems by Dynamic Instruction Sets for Reconfigurable Hardware using High-Level OpenCL-C]78 kB

Beitrag teilen