NeuroCGRA: A CGRA with support for neural networks
2014 (English)In: Proceedings of the 2014 International Conference on High Performance Computing and Simulation, HPCS 2014, IEEE , 2014, 506-511 p.Conference paper (Refereed)
Today, Coarse Grained Reconfigurable Architectures (CGRAs) are becoming an increasingly popular implementation platform. In real world applications, the CGRAs are required to simultaneously host processing (e.g. Audio/video acquisition) and estimation (e.g. audio/video/image recognition) tasks. For estimation problems, neural networks, promise a higher efficiency than conventional processing. However, most of the existing CGRAs provide no support for neural networks. To realize realize both neural networks and conventional processing on the same platform, this paper presents NeuroCGRA. NeuroCGRA allows the processing elements and the network to dynamically morph into either conventional CGRA or a neural network, depending on the hosted application. We have chosen the DRRA as a vehicle to study the feasibility and overheads of our approach. Synthesis results reveal that the proposed enhancements incur negligible overheads (4.4% area and 9.1% power) compared to the original DRRA cell.
Place, publisher, year, edition, pages
IEEE , 2014. 506-511 p.
IdentifiersURN: urn:nbn:se:kth:diva-160503DOI: 10.1109/HPCSim.2014.6903727ISI: 000361141700065ScopusID: 2-s2.0-84908631976ISBN: 9781479953127OAI: oai:DiVA.org:kth-160503DiVA: diva2:789966
2014 International Conference on High Performance Computing and Simulation, HPCS 2014; Bologna; Italy; 21 July 2014 through 25 July 2014
QC 201504172015-02-212015-02-212016-04-13Bibliographically approved