Supercompiler Code Optimization with Zero-Shot Reinforcement Learning

• URL: http://arxiv.org/abs/2404.16077v1
• Date: Wed, 24 Apr 2024 09:20:33 GMT
• Title: Supercompiler Code Optimization with Zero-Shot Reinforcement Learning
• Authors: Jialong Wu, Chaoyi Deng, Jianmin Wang, Mingsheng Long,
• Abstract summary: We present CodeZero, an artificial intelligence agent trained extensively on large data to produce effective optimization strategies instantly for each program in a single trial of the agent. Our methodology kindles the great potential of artificial intelligence for engineering and paves the way for scaling machine learning techniques in the realm of code optimization.
• Score: 63.164423329052404
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Effective code optimization in compilers plays a central role in computer and software engineering. While compilers can be made to automatically search the optimization space without the need for user interventions, this is not a standard practice since the search is slow and cumbersome. Here we present CodeZero, an artificial intelligence agent trained extensively on large data to produce effective optimization strategies instantly for each program in a single trial of the agent. To overcome the huge range of possible test programs, we prepare a large dataset of training programs that emphasize quality, naturalness, and diversity. To tackle the vast space of possible optimizations, we adapt deep reinforcement learning to train the agent in a sample-efficient manner through interacting with a world model of the compiler environment. Evaluation on both benchmark suites and production-level code optimization problems demonstrates our agent's supercompiler performances and zero-shot generalization abilities, outperforming built-in optimization options designed by compiler experts. Our methodology kindles the great potential of artificial intelligence for engineering and paves the way for scaling machine learning techniques in the realm of code optimization.

Related papers

• CodeDPO: Aligning Code Models with Self Generated and Verified Source Code [52.70310361822519]
  We propose CodeDPO, a framework that integrates preference learning into code generation to improve two key code preference factors: code correctness and efficiency. CodeDPO employs a novel dataset construction method, utilizing a self-generation-and-validation mechanism that simultaneously generates and evaluates code and test cases.
  arXiv  Detail & Related papers  (2024-10-08T01:36:15Z)
• Meta Large Language Model Compiler: Foundation Models of Compiler Optimization [21.161784011956126]
  Large Language Models (LLMs) have demonstrated remarkable capabilities across a variety of software engineering and coding tasks. However, their application in the domain of code and compiler optimization remains underexplored. We introduce Meta Large Language Model Compiler (LLM Compiler), a suite of robust, openly available, pre-trained models for code optimization tasks.
  arXiv  Detail & Related papers  (2024-06-27T21:47:48Z)
• Should AI Optimize Your Code? A Comparative Study of Current Large Language Models Versus Classical Optimizing Compilers [0.0]
  Large Language Models (LLMs) raise intriguing questions about the potential for AI-driven approaches to revolutionize code optimization methodologies. This paper presents a comparative analysis between two state-of-the-art Large Language Models, GPT-4.0 and CodeLlama-70B, and traditional optimizing compilers.
  arXiv  Detail & Related papers  (2024-06-17T23:26:41Z)
• Iterative or Innovative? A Problem-Oriented Perspective for Code Optimization [81.88668100203913]
  Large language models (LLMs) have demonstrated strong capabilities in solving a wide range of programming tasks. In this paper, we explore code optimization with a focus on performance enhancement, specifically aiming to optimize code for minimal execution time.
  arXiv  Detail & Related papers  (2024-06-17T16:10:10Z)
• Two Optimizers Are Better Than One: LLM Catalyst Empowers Gradient-Based Optimization for Prompt Tuning [69.95292905263393]
  We show that gradient-based optimization and large language models (MsLL) are complementary to each other, suggesting a collaborative optimization approach. Our code is released at https://www.guozix.com/guozix/LLM-catalyst.
  arXiv  Detail & Related papers  (2024-05-30T06:24:14Z)
• Large Language Models for Compiler Optimization [22.52765975286403]
  We present a transformer model trained from scratch to optimize LLVM assembly for code size. We ask the model to predict the instruction counts before and after optimization, and the optimized code itself. Our approach achieves a 3.0% improvement in reducing instruction counts over the compiler.
  arXiv  Detail & Related papers  (2023-09-11T22:11:46Z)
• 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)
• Learning to Superoptimize Real-world Programs [79.4140991035247]
  We propose a framework to learn to superoptimize real-world programs by using neural sequence-to-sequence models. We introduce the Big Assembly benchmark, a dataset consisting of over 25K real-world functions mined from open-source projects in x86-64 assembly.
  arXiv  Detail & Related papers  (2021-09-28T05:33:21Z)
• Learning to Optimize: A Primer and A Benchmark [94.29436694770953]
  Learning to optimize (L2O) is an emerging approach that leverages machine learning to develop optimization methods. This article is poised to be the first comprehensive survey and benchmark of L2O for continuous optimization.
  arXiv  Detail & Related papers  (2021-03-23T20:46:20Z)
• Static Neural Compiler Optimization via Deep Reinforcement Learning [1.458855293397494]
  In this paper, we employ a deep reinforcement learning approach to the phase-ordering problem. Provided with sub-sequences constituting LLVM's O3 sequence, our agent learns to outperform the O3 sequence on the set of source codes used for training. We believe that the models trained using our approach can be integrated into modern compilers as neural optimization agents.
  arXiv  Detail & Related papers  (2020-08-20T13:16:29Z)

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.