CheckMate: LLM-Powered Approximate Intermittent Computing

2024-11-22

AI Summary

Batteryless IoT systems face two critical bottlenecks in intermittent computing: excessive energy overhead from frequent checkpointing, and poor scalability of manual parameter tuning in approximate computing. Method: This paper proposes the first LLM-driven automated framework for approximation in intermittent execution, integrating context-aware LLM-based code generation, lightweight runtime functional verification, and Bayesian optimization to enable end-to-end automatic synthesis and joint energy-efficiency–accuracy optimization of approximation strategies. Results: Evaluated across six IoT applications, our approach reduces power-cycle counts by up to 60% with only 8% accuracy degradation; it significantly outperforms the semi-automatic tool ACCEPT in both speedup and accuracy. The core contribution lies in the first deep integration of LLMs into the intermittent-computing approximation modeling and optimization loop—ensuring functional correctness and energy–accuracy trade-off without human intervention.

Technology Category

• Search and Optimization: Learning to Search
• Machine Learning: Large Multimodal Models (LMMs)
• Constraint Satisfaction and Optimization: Satisfiability Modulo Theories

Application Category

• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation

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.

Problem

• Automates code approximations using LLMs
• Reduces checkpointing overhead in IoT systems
• Ensures accuracy with autonomous parameter tuning

Innovation

• LLM-powered code approximations
• Bayesian optimization parameters
• Automated intermittent computing framework