# Sustainable AI Processing at the Edge

arXiv: https://arxiv.org/abs/2207.01209 · HTML: https://mlsanity.com/paper/2207.01209/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 2 of its 31 references that are in the map.
- First posted on arXiv 4 Jul 2022.

## Builds on (most cited first, 2 of 2)

- [EF-Train: Enable Efficient On-device CNN Training on FPGA Through Data Reshaping for Online Adaptation or Personalization](https://mlsanity.com/paper/2202.10935/) (2022)
- [FPIRM: Floating-point Processing in Racetrack Memories](https://mlsanity.com/paper/2204.13788/) (2022)

## Built on by (most cited first, 4 of 4)

- [Edge-Cloud Collaborative Computing on Distributed Intelligence and Model Optimization: A Survey](https://mlsanity.com/paper/2505.01821/) (2025)
- [Measuring What Matters: Connecting AI Ethics Evaluations to System Attributes, Hazards, and Harms](https://mlsanity.com/paper/2510.10339/) (2025)
- [A Survey on Video Analytics in Cloud-Edge-Terminal Collaborative Systems](https://mlsanity.com/paper/2502.06581/) (2025)
- [CORDIC Is All You Need](https://mlsanity.com/paper/2503.11685/) (2025)

## Abstract (arXiv)

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.