Edge computing is a popular target for accelerating machine learning algorithms supporting mobile devices without requiring the communication latencies to handle them in the cloud. Edge deployments of machine learning primarily consider traditional concerns such as SWaP constraints (Size, Weight, and Power) for their installations. However, such metrics are not entirely sufficient to consider environmental impacts from computing given the significant contributions from embodied energy and carbon. In this paper we explore the tradeoffs of convolutional neural network acceleration engines for both inference and on-line training. In particular, we explore the use of processing-in-memory (PIM) approaches, mobile GPU accelerators, and recently released FPGAs, and compare them with novel Racetrack memory PIM. Replacing PIM-enabled DDR3 with Racetrack memory PIM can recover its embodied energy as quickly as 1 year. For high activity ratios, mobile GPUs can be more sustainable but have higher embodied energy to overcome compared to PIM-enabled Racetrack memory.
@article{arxiv.2207.01209,
title = {Sustainable AI Processing at the Edge},
author = {Sébastien Ollivier and Sheng Li and Yue Tang and Chayanika Chaudhuri and Peipei Zhou and Xulong Tang and Jingtong Hu and Alex K. Jones},
journal= {arXiv preprint arXiv:2207.01209},
year = {2024}
}
Comments
This work has been submitted to the IEEE for possible publication