MW-scale parallel accelerators are a promising target for application domains such as the Internet of Thing (IoT), which require a strong compliance with a limited power budget combined with high performance capabilities. An important use case is given by smart sensing devices featuring increasingly sophisticated vision capabilities, at the cost of an increasing amount of near-sensor computation power. OpenVX is an emerging standard for the embedded vision, and provides a C-based application programming interface and a runtime environment. OpenVX is designed to maximize functional and performance portability across diverse hardware platforms. However, state-of-the-art implementations rely on memory-hungry data structures, which cannot be supported in constrained devices. In this paper we propose an alternative and novel approach to provide OpenVX support in mW-scale parallel accelerators. Our main contributions are: (i) an extension to the original OpenVX model to support static management of application graphs in the form of binary files; (ii) the definition of a companion runtime environment providing a lightweight support to execute binary graphs in a resource-constrained environment. Our approach achieves 68% memory footprint reduction and 3× execution speed-up compared to a baseline implementation. At the same time, data memory bandwidth is reduced by 10% and energy efficiency is improved by 2×.
|Data di pubblicazione:||2016|
|Titolo:||Enabling OpenVX support in mW-scale parallel accelerators|
|Autore/i:||Tagliavini, G; Haugou, G; Marongiu, A; Benini, L|
|Digital Object Identifier (DOI):||10.1145/2968455.2968518|
|Nome del convegno:||2016 International Conference on Compilers, Architectures and Synthesis for Embedded Systems|
|Luogo del convegno:||Pittsburgh Marriott City Center, usa|
|Data del convegno:||2016|
|Citazione:||Enabling OpenVX support in mW-scale parallel accelerators / Tagliavini, G; Haugou, G; Marongiu, A; Benini, L. - STAMPA. - (2016), pp. 1-10. ((Intervento presentato al convegno 2016 International Conference on Compilers, Architectures and Synthesis for Embedded Systems tenutosi a Pittsburgh Marriott City Center, usa nel 2016.|
|Tipologia||Relazione in Atti di Convegno|
File in questo prodotto:
I documenti presenti in Iris Unimore sono rilasciati con licenza Creative Commons Attribuzione - Non commerciale - Non opere derivate 3.0 Italia, salvo diversa indicazione.
In caso di violazione di copyright, contattare Supporto Iris