iOS as Acceleration

TL;DR

This paper demonstrates how underutilized iOS mobile devices can be harnessed through distributed pipeline parallelism to enhance local machine learning tasks, addressing privacy and cost concerns.

Contribution

It introduces a novel system leveraging iOS devices for distributed ML acceleration, showcasing practical applications and discussing limitations and future directions.

Findings

Significant acceleration in modest model training and inference.

Effective utilization of iOS devices for ML tasks.

Potential to reduce reliance on cloud computing for sensitive or costly applications.

Abstract

Practical utilization of large-scale machine learning requires a powerful compute setup, a necessity which poses a significant barrier to engagement with such artificial intelligence in more restricted system environments. While cloud computing offers a solution to weaker local environments, certain situations like training involving private or sensitive data, physical environments not available through the cloud, or higher anticipated usage costs, necessitate computing locally. We explore the potential to improve weaker local compute systems at zero additional cost by taking advantage of ubiquitous yet underutilized resources: mobile phones. Specifically, recent iOS phones are equipped with surprisingly powerful processors, but they also face limitations like memory constraints, thermal throttling, and OS sandboxing. We present a proof-of-concept system demonstrating a novel approach to harness an iOS device via distributed pipeline parallelism, achieving significant benefits in a lesser compute environment by accelerating modest model training, batch inference, and agentic LRM tool-usage. We discuss practical use-cases, limitations, and directions for future work. The findings of this paper highlight the potential for the improving commonplace mobile devices to provide greater contributions to machine learning.