Conference Proceedings

Heterogeneous computing system platform for high-performance pattern recognition applications

MA Mirzaei, V Voisin, A Annovi, G Baulieu, M Beretta, G Calderini, S Citraro, F Crescioli, G Galbit, V Liberali, SR Shojaii, A Stabile, W Tromeur, S Viret

2017 6th International Conference on Modern Circuits and Systems Technologies Mocast 2017 | IEEE | Published : 2017

Abstract

we present a system architecture made of a motherboard with a Xilinx Zynq System on Chip (SoC) and a mezzanine board equipped with an Associative Memory chip (AM). The proposed architecture is designed to serve as an accelerator of general purpose algorithms based on pipeline processing and pattern recognition. We present the open source software and firmware developed to fully exploit the available communication channels between the ARM CPU and the FPGA using Direct Memory Access (DMA) technique and the AM using Multi-Gigabit Transceivers (MGT). We report the measured performances and discuss potential applications and future developments. The proposed architecture is compact, portable and ..

View full abstract

University of Melbourne Researchers

Grants

Awarded by French ANR project FastTrack


Funding Acknowledgements

The project received founding from the French ANR project FastTrack (ANR-13-BS05-0011-01). The authors would like to be extremely grateful for their generosity, contribution and financial support. Many thanks to AM chip design team, LPNHE and IPNL for their technical support and precious help.