Energy-Efficient Near-Threshold Parallel Computing: The PULPv2 Cluster

By Lori Cameron
Published 12/12/2017
Share this on:

Smart home automation icon on motherboard, future technology home remote control concept.

In the article “Energy-Efficient Near-Threshold Parallel Computing: The PULPv2 Cluster,” (login may be required for full text) which appears in the September/October 2017 issue of IEEE Micro, the authors present 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.



About Lori Cameron

Lori Cameron is a Senior Writer for the IEEE Computer Society and currently writes regular features for Computer magazine, Computing Edge, and the Computing Now and Magazine Roundup websites. Contact her at Follow her on LinkedIn.