Leveraging Large Language Models to Detect Missed Peephole Optimizations

• URL: http://arxiv.org/abs/2508.16125v1
• Date: Fri, 22 Aug 2025 06:36:42 GMT
• Title: Leveraging Large Language Models to Detect Missed Peephole Optimizations
• Authors: Zhenyang Xu, Hongxu Xu, Yongqiang Tian, Xintong Zhou, Chengnian Sun,
• Abstract summary: peephole optimization is a critical class of compiler optimizations.<n>Previous methods either do not scale well or can only capture a limited subset of peephole optimizations.<n>We propose Lampo, a novel framework that combines the creative but unreliable code optimization ability of LLMs with rigorous correctness verification.
• Score: 7.48961433936748
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: By replacing small, suboptimal instruction sequences within programs with a more efficient equivalent, peephole optimization can not only directly optimize code size and performance, but also potentially enables further transformations in the subsequent optimization pipeline. Although peephole optimization is a critical class of compiler optimizations, discovering new and effective peephole optimizations is challenging as the instruction sets can be extremely complex and diverse. Previous methods either do not scale well or can only capture a limited subset of peephole optimizations. In this work, we leverage Large Language Models (LLMs) to detect missed peephole optimizations. We propose Lampo, a novel automated framework that synergistically combines the creative but unreliable code optimization ability of LLMs with rigorous correctness verification performed by translation validation tools, integrated in a feedback-driven iterative process. Through a comprehensive evaluation within LLVM ecosystems, we show that Lampo can successfully detect up to 17 out of 25 previously reported missed optimizations in LLVM on average, and that 22 out of 25 can potentially be found by Lampo with different LLMs. For comparison, the state-of-the-art superoptimizer for LLVM, Souper, identified 15 of them. Moreover, within seven months of development and intermittent experiments, Lampo found 26 missed peephole optimizations, 15 of which have been confirmed and 6 already fixed. These results demonstrate Lampo's strong potential in continuously detecting missed peephole optimizations.

Related papers

• LOOPRAG: Enhancing Loop Transformation Optimization with Retrieval-Augmented Large Language Models [23.6344001089164]
  LOOPRAG is a retrieval-augmented generation framework designed to guide Large Language Models (LLMs) in performing effective loop optimization.<n>We introduce a parameter-driven method to harness loop properties, which trigger various loop transformations, and generate diverse yet legal example codes.<n>To enhance correct and efficient code generation, we introduce a feedback-based iterative mechanism that incorporates compilation, testing and performance results.
  arXiv  Detail & Related papers  (2025-12-12T11:09:48Z)
• Targeted Testing of Compiler Optimizations via Grammar-Level Composition Styles [8.598686284546773]
  Existing fuzzers struggle to test compiler optimizations effectively.<n>We propose targeted fuzzing of individual optimizations to complement pipeline-based testing.<n>Our evaluation on LLVM and MLIR shows that TargetFuzz improves coverage by 8% and 11%.
  arXiv  Detail & Related papers  (2025-12-04T00:13:25Z)
• SemOpt: LLM-Driven Code Optimization via Rule-Based Analysis [7.451702651736553]
  SemOpt is a framework that leverages static program analysis to precisely identify optimizable code segments, retrieve the corresponding optimization strategies, and generate the optimized results.<n>On our benchmark containing 151 optimization tasks, SemOpt demonstrates its effectiveness under different LLMs by increasing the number of successful optimizations by 1.38 to 28 times compared to the baseline.
  arXiv  Detail & Related papers  (2025-10-18T07:44:18Z)
• Make Optimization Once and for All with Fine-grained Guidance [78.14885351827232]
  Learning to Optimize (L2O) enhances optimization efficiency with integrated neural networks.<n>L2O paradigms achieve great outcomes, e.g., refitting, generating unseen solutions iteratively or directly.<n>Our analyses explore general framework for learning optimization, called Diff-L2O, focusing on augmenting solutions from a wider view.
  arXiv  Detail & Related papers  (2025-03-14T14:48:12Z)
• Large Scale Multi-Task Bayesian Optimization with Large Language Models [29.12351845364205]
  We introduce a novel approach leveraging large language models (LLMs) to learn from, and improve upon, previous optimization trajectories.<n>We evaluate our method on two distinct domains: database query optimization and antimicrobial peptide design.
  arXiv  Detail & Related papers  (2025-03-11T07:46:19Z)
• A Problem-Oriented Perspective and Anchor Verification for Code Optimization [43.28045750932116]
  Large language models (LLMs) have shown remarkable capabilities in solving various programming tasks.<n>This paper investigates the capabilities of LLMs in optimizing code for minimal execution time.
  arXiv  Detail & Related papers  (2024-06-17T16:10:10Z)
• Discovering Preference Optimization Algorithms with and for Large Language Models [50.843710797024805]
  offline preference optimization is a key method for enhancing and controlling the quality of Large Language Model (LLM) outputs. We perform objective discovery to automatically discover new state-of-the-art preference optimization algorithms without (expert) human intervention. Experiments demonstrate the state-of-the-art performance of DiscoPOP, a novel algorithm that adaptively blends logistic and exponential losses.
  arXiv  Detail & Related papers  (2024-06-12T16:58:41Z)
• LLM as a Complementary Optimizer to Gradient Descent: A Case Study in Prompt Tuning [69.95292905263393]
  We show that gradient-based and high-level LLMs can effectively collaborate a combined optimization framework.<n>In this paper, we show that these complementary to each other and can effectively collaborate a combined optimization framework.
  arXiv  Detail & Related papers  (2024-05-30T06:24:14Z)
• Large Language Models as Optimizers [106.52386531624532]
  We propose Optimization by PROmpting (OPRO), a simple and effective approach to leverage large language models (LLMs) as prompts. In each optimization step, the LLM generates new solutions from the prompt that contains previously generated solutions with their values. We demonstrate that the best prompts optimized by OPRO outperform human-designed prompts by up to 8% on GSM8K, and by up to 50% on Big-Bench Hard tasks.
  arXiv  Detail & Related papers  (2023-09-07T00:07:15Z)
• M-L2O: Towards Generalizable Learning-to-Optimize by Test-Time Fast Self-Adaptation [145.7321032755538]
  Learning to Optimize (L2O) has drawn increasing attention as it often remarkably accelerates the optimization procedure of complex tasks. This paper investigates a potential solution to this open challenge by meta-training an L2O that can perform fast test-time self-adaptation to an out-of-distribution task.
  arXiv  Detail & Related papers  (2023-02-28T19:23:20Z)
• An Empirical Evaluation of Zeroth-Order Optimization Methods on AI-driven Molecule Optimization [78.36413169647408]
  We study the effectiveness of various ZO optimization methods for optimizing molecular objectives. We show the advantages of ZO sign-based gradient descent (ZO-signGD) We demonstrate the potential effectiveness of ZO optimization methods on widely used benchmark tasks from the Guacamol suite.
  arXiv  Detail & Related papers  (2022-10-27T01:58:10Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.