[2512.14018] PerfCoder: Large Language Models for Interpretable Code Performance Optimization

Computer Science > Software Engineering arXiv:2512.14018 (cs) [Submitted on 16 Dec 2025 (v1), last revised 8 May 2026 (this version, v2)] Title:PerfCoder: Large Language Models for Interpretable Code Performance Optimization Authors:Jiuding Yang, Shengyao Lu, Hongxuan Liu, Shayan Shirahmad Gale Bagi, Zahra Fazel, Tomasz Czajkowski, Di Niu View a PDF of the paper titled PerfCoder: Large Language Models for Interpretable Code Performance Optimization, by Jiuding Yang and 5 other authors View PDF HTML (experimental) Abstract:Large language models (LLMs) have achieved remarkable progress in automatic code generation, yet their ability to produce high-performance code remains limited--a critical requirement in real-world software systems. We argue that current LLMs struggle not only due to data scarcity but, more importantly, because they lack supervision that guides interpretable and effective performance improvements. In this work, we introduce PerfCoder, a family of LLMs specifically designed to generate performance-enhanced code from source code via interpretable, customized optimizations. PerfCoder is fine-tuned on a curated collection of real-world optimization trajectories with human-readable annotations, and preference-aligned by reinforcement fine-tuning using runtime measurements, enabling it to propose input-specific improvement strategies and apply them directly without relying on iterative refinement. On the PIE code performance benchmark, PerfCoder surpasses all e...