A Heterogeneous Cluster with Reconfigurable Accelerator for Energy Efficient Near-Sensor Data Analytics

Satyajit Das 1, 2 Kevin Martin 1 Philippe Coussy 1 Davide Rossi 2
Lab-STICC - Laboratoire des sciences et techniques de l'information, de la communication et de la connaissance
Abstract : IoT end-nodes require high performance and extreme energy efficiency to cope with complex near-sensor data analytics algorithms. Processing on multiple programmable processors operating in near-threshold is emerging as a promising solution to exploit the energy boost given by low-voltage operation, while recovering the related frequency degradation with parallelism. In this work, we present a heterogeneous cluster architecture extending a traditional parallel processor cluster with a reconfigurable Integrated Programmable Array (IPA) accelerator. While programmable processors guarantee programming legacy to easily manage peripherals, radio software stacks as well as the global program flow, offloading data-intensive and control-intensive kernels to the IPA leads to much higher system level performance and energy-efficiency. Experimental results show that the proposed heterogeneous cluster outperforms an 8-core homogeneous architecture by up to 4.8x in performance and 4.5x in energy efficiency when executing a mix of control-intensive and data-intensive kernels typical of near-sensor data analytics applications.
Liste complète des métadonnées

Cited literature [11 references]  Display  Hide  Download

Contributor : Kevin Martin <>
Submitted on : Monday, July 2, 2018 - 12:00:48 PM
Last modification on : Monday, February 25, 2019 - 3:14:12 PM
Document(s) archivé(s) le : Monday, October 1, 2018 - 7:50:23 AM


Files produced by the author(s)


  • HAL Id : hal-01827425, version 1


Satyajit Das, Kevin Martin, Philippe Coussy, Davide Rossi. A Heterogeneous Cluster with Reconfigurable Accelerator for Energy Efficient Near-Sensor Data Analytics. International Symposium on Circuits and Systems (ISCAS), May 2018, Florence, Italy. ⟨hal-01827425⟩



Record views


Files downloads