Title
Energy-Efficient Near-Threshold Parallel Computing: The PULPv2 Cluster.
Abstract
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...
Year
DOI
Venue
2017
10.1109/MM.2017.3711645
IEEE Micro
Keywords
Field
DocType
Random access memory,Energy efficiency,Memory management,System-on-chip,Low power electronics,Reduced instruction set computing,Power system management
Power management,System on a chip,Efficient energy use,Computer science,Internet of Things,Parallel computing,Parallel processing,Reduced instruction set computing,Memory management,Computer hardware,Low-power electronics
Journal
Volume
Issue
ISSN
37
5
0272-1732
Citations 
PageRank 
References 
5
0.55
0
Authors
13
Name
Order
Citations
PageRank
Davide Rossi141647.47
Antonio Pullini239028.27
Igor Loi344530.66
Michael Gautschi411310.19
Frank K. Gurkaynak5697.91
Adam Teman612919.12
Jeremy Constantin7404.86
A. Burg81426126.54
Ivan Miro-Panades9866.16
Edith Beigne1053652.54
Fabien Clermidy1179761.56
Philippe Flatresse129715.35
Luca Benini13131161188.49