Optimas: An Intelligent Analytics-Informed Generative AI Framework for Performance Optimization

TL;DR

Optimas is an automated AI framework that leverages large language models to translate performance diagnostics into effective code optimizations, significantly enhancing performance across diverse benchmarks.

Contribution

It introduces a fully automated, multi-agent AI system that maps diagnostics to code transformations, bridging the gap between performance analysis and code optimization.

Findings

Achieves 100% correct code generation in experiments.

Improves performance in over 98.82% of cases.

Gains range from 8.02% to 79.09% on NVIDIA GPUs.

Abstract

Large language models (LLMs) show promise for automated code optimization. However, without performance context, they struggle to produce correct and effective code transformations. Existing performance tools can identify bottlenecks but stop short of generating actionable code changes. Consequently, performance optimization continues to be a time-intensive and manual endeavor, typically undertaken only by experts with detailed architectural understanding. To bridge this gap, we introduce Optimas, a modular, fully automated, end-to-end generative AI framework built on a multi-agent workflow. Optimas uses LLMs to map performance diagnostics from multiple reports to established, literature-backed code transformations, while unifying insight extraction, code generation, execution, and validation within a single pipeline. Across 3,410 real-world experiments on 10 benchmarks and two HPC mini-applications, Optimas generates 100% correct code and improves performance in over 98.82% of those experiments, achieving average gains of 8.02%-79.09% on NVIDIA GPUs.