ReChisel: Effective Automatic Chisel Code Generation by LLM with Reflection

• URL: http://arxiv.org/abs/2505.19734v1
• Date: Mon, 26 May 2025 09:20:07 GMT
• Title: ReChisel: Effective Automatic Chisel Code Generation by LLM with Reflection
• Authors: Juxin Niu, Xiangfeng Liu, Dan Niu, Xi Wang, Zhe Jiang, Nan Guan,
• Abstract summary: ReChisel is an agentic system designed to enhance the effectiveness of Chisel code generation.<n> Experiments demonstrate that ReChisel significantly improves the success rate of Chisel code generation.
• Score: 10.897328608123772
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Coding with hardware description languages (HDLs) such as Verilog is a time-intensive and laborious task. With the rapid advancement of large language models (LLMs), there is increasing interest in applying LLMs to assist with HDL coding. Recent efforts have demonstrated the potential of LLMs in translating natural language to traditional HDL Verilog. Chisel, a next-generation HDL based on Scala, introduces higher-level abstractions, facilitating more concise, maintainable, and scalable hardware designs. However, the potential of using LLMs for Chisel code generation remains largely unexplored. This work proposes ReChisel, an LLM-based agentic system designed to enhance the effectiveness of Chisel code generation. ReChisel incorporates a reflection mechanism to iteratively refine the quality of generated code using feedback from compilation and simulation processes, and introduces an escape mechanism to break free from non-progress loops. Experiments demonstrate that ReChisel significantly improves the success rate of Chisel code generation, achieving performance comparable to state-of-the-art LLM-based agentic systems for Verilog code generation.

Related papers

• HDLCoRe: A Training-Free Framework for Mitigating Hallucinations in LLM-Generated HDL [8.078194378107936]
  HDLCoRe is a training-free framework that enhances large language models' HDL generation capabilities.<n>Our framework achieves superior performance on the RTLLM2.0 benchmark.
  arXiv  Detail & Related papers  (2025-03-18T07:09:39Z)
• Exploring Code Language Models for Automated HLS-based Hardware Generation: Benchmark, Infrastructure and Analysis [14.458529723566379]
  Large language models (LLMs) can be employed for programming languages such as Python and C++.<n>This paper explores leveraging LLMs to generate High-Level Synthesis (HLS)-based hardware design.
  arXiv  Detail & Related papers  (2025-02-19T17:53:59Z)
• HADES: Hardware Accelerated Decoding for Efficient Speculation in Large Language Models [1.2180334969164464]
  Large Language Models (LLMs) have revolutionized natural language processing by understanding and generating human-like text.<n>This paper introduces Hardware Accelerated Decoding (HADES), a novel approach to enhance the performance and energy efficiency of LLMs.
  arXiv  Detail & Related papers  (2024-12-27T21:19:01Z)
• HiVeGen -- Hierarchical LLM-based Verilog Generation for Scalable Chip Design [55.54477725000291]
  HiVeGen is a hierarchical Verilog generation framework that decomposes generation tasks into hierarchical submodules.<n> automatic Design Space Exploration (DSE) into hierarchy-aware prompt generation, introducing weight-based retrieval to enhance code reuse.<n>Real-time human-computer interaction to lower error-correction cost, significantly improving the quality of generated designs.
  arXiv  Detail & Related papers  (2024-12-06T19:37:53Z)
• Case2Code: Scalable Synthetic Data for Code Generation [105.89741089673575]
  Large Language Models (LLMs) have shown outstanding breakthroughs in code generation.<n>Recent work improves code LLMs by training on synthetic data generated by some powerful LLMs.<n>We propose a textbfCase2Code task by exploiting the expressiveness and correctness of programs.
  arXiv  Detail & Related papers  (2024-07-17T11:35:00Z)
• CodeV: Empowering LLMs with HDL Generation through Multi-Level Summarization [32.462699328256384]
  Traditional methods of adapting large language models for hardware design rely on synthetic HDL datasets.<n>We propose an efficient LLM fine-tuning pipeline for HDL generation that integrates a multi-level summarization data synthesis process with a novel Chat-FIM-Tag supervised fine-tuning method.
  arXiv  Detail & Related papers  (2024-07-15T03:57:20Z)
• Classification-Based Automatic HDL Code Generation Using LLMs [9.630310313347657]
  Large language models (LLMs) have demonstrated the ability to generate hardware description language (HDL) code for digital circuits. LLMs suffer from the hallucination problem, which leads to the generation of incorrect HDL code or misunderstanding of specifications. We introduce a human-expert-inspired method to mitigate the hallucination of LLMs and improve the performance in HDL code generation.
  arXiv  Detail & Related papers  (2024-07-04T09:00:13Z)
• Q*: Improving Multi-step Reasoning for LLMs with Deliberative Planning [53.6472920229013]
  Large Language Models (LLMs) have demonstrated impressive capability in many natural language tasks. LLMs are prone to produce errors, hallucinations and inconsistent statements when performing multi-step reasoning. We introduce Q*, a framework for guiding LLMs decoding process with deliberative planning.
  arXiv  Detail & Related papers  (2024-06-20T13:08:09Z)
• StepCoder: Improve Code Generation with Reinforcement Learning from Compiler Feedback [58.20547418182074]
  We introduce StepCoder, a novel framework for code generation, consisting of two main components. CCCS addresses the exploration challenge by breaking the long sequences code generation task into a Curriculum of Code Completion Subtasks. FGO only optimize the model by masking the unexecuted code segments to provide Fine-Grained Optimization. Our method improves the ability to explore the output space and outperforms state-of-the-art approaches in corresponding benchmarks.
  arXiv  Detail & Related papers  (2024-02-02T13:14:31Z)
• If LLM Is the Wizard, Then Code Is the Wand: A Survey on How Code Empowers Large Language Models to Serve as Intelligent Agents [81.60906807941188]
  Large language models (LLMs) are trained on a combination of natural language and formal language (code) Code translates high-level goals into executable steps, featuring standard syntax, logical consistency, abstraction, and modularity.
  arXiv  Detail & Related papers  (2024-01-01T16:51:20Z)
• CodeChain: Towards Modular Code Generation Through Chain of Self-revisions with Representative Sub-modules [51.82044734879657]
  We propose CodeChain, a novel framework for inference that elicits modularized code generation through a chain of self-revisions. We find that CodeChain can significantly boost both modularity as well as correctness of the generated solutions, achieving relative pass@1 improvements of 35% on APPS and 76% on CodeContests.
  arXiv  Detail & Related papers  (2023-10-13T10:17:48Z)

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.