Energy-Efficient Near-Threshold Parallel Computing: The PULPv2 Cluster
- Rossi, Davide
- Pullini, Antonio
- Loi, Igor
- Gautschi, Michael
- Gurkaynak, Frank Kagan
- Teman, Adam
- Constantin, Jeremy
- Burg, Andreas
- Miro-Panades, Ivan
- Beigne, Edith
- Clermidy, Fabien
- Flatresse, Philippe
- Benini, Luca
Publication date
November 2017
DOI Publisher
Institute of Electrical and Electronics Engineers (IEEE) ISSN
0272-1732Abstract
This article presents an ultra-low-power parallel computing platform and its system-on-chip (SoC) embodiment, targeting a wide range of emerging near-sensor processing tasks for Internet of Things (IoT) applications. The proposed SoC achieves 193 million operations per second (MOPS) per mW at 162 MOPS (32 bits), improving the first-generation Parallel Ultra-Low-Power (PULP) architecture by 6.4 and 3.2 times in performance and energy efficiency, respectively
Add to ORKG