CheckMate: LLM-Powered Approximate Intermittent Computing

TL;DR

CheckMate is an automated framework that uses large language models and Bayesian optimization to enable energy-efficient approximate computing in batteryless IoT systems, reducing power consumption with minimal accuracy loss.

Contribution

It introduces an automated, LLM-powered approach for context-aware code approximation and validation, eliminating manual effort and outperforming existing semi-automated tools.

Findings

Reduces power cycles by up to 60% in IoT applications

Achieves only 8% accuracy loss with improved speed

Outperforms semi-automated tools like ACCEPT

Abstract

Batteryless IoT systems face energy constraints exacerbated by checkpointing overhead. Approximate computing offers solutions but demands manual expertise, limiting scalability. This paper presents CheckMate, an automated framework leveraging LLMs for context-aware code approximations. CheckMate integrates validation of LLM-generated approximations to ensure correct execution and employs Bayesian optimization to fine-tune approximation parameters autonomously, eliminating the need for developer input. Tested across six IoT applications, it reduces power cycles by up to 60% with an accuracy loss of just 8%, outperforming semi-automated tools like ACCEPT in speedup and accuracy. CheckMate's results establish it as a robust, user-friendly tool and a foundational step toward automated approximation frameworks for intermittent computing.