Data is all you need: Finetuning LLMs for Chip Design via an Automated design-data augmentation framework

• URL: http://arxiv.org/abs/2403.11202v2
• Date: Wed, 10 Jul 2024 09:06:40 GMT
• Title: Data is all you need: Finetuning LLMs for Chip Design via an Automated design-data augmentation framework
• Authors: Kaiyan Chang, Kun Wang, Nan Yang, Ying Wang, Dantong Jin, Wenlong Zhu, Zhirong Chen, Cangyuan Li, Hao Yan, Yunhao Zhou, Zhuoliang Zhao, Yuan Cheng, Yudong Pan, Yiqi Liu, Mengdi Wang, Shengwen Liang, Yinhe Han, Huawei Li, Xiaowei Li,
• Abstract summary: This paper proposes an automated design-data augmentation framework, which generates high-volume and high-quality natural language aligned with Verilog and EDA scripts. The accuracy of Verilog generation surpasses that of the current state-of-the-art open-source Verilog generation model, increasing from 58.8% to 70.6% with the same benchmark.
• Score: 50.02710905062184
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recent advances in large language models have demonstrated their potential for automated generation of hardware description language (HDL) code from high-level prompts. Researchers have utilized fine-tuning to enhance the ability of these large language models (LLMs) in the field of Chip Design. However, the lack of Verilog data hinders further improvement in the quality of Verilog generation by LLMs. Additionally, the absence of a Verilog and Electronic Design Automation (EDA) script data augmentation framework significantly increases the time required to prepare the training dataset for LLM trainers. This paper proposes an automated design-data augmentation framework, which generates high-volume and high-quality natural language aligned with Verilog and EDA scripts. For Verilog generation, it translates Verilog files to an abstract syntax tree and then maps nodes to natural language with a predefined template. For Verilog repair, it uses predefined rules to generate the wrong verilog file and then pairs EDA Tool feedback with the right and wrong verilog file. For EDA Script generation, it uses existing LLM(GPT-3.5) to obtain the description of the Script. To evaluate the effectiveness of our data augmentation method, we finetune Llama2-13B and Llama2-7B models using the dataset generated by our augmentation framework. The results demonstrate a significant improvement in the Verilog generation tasks with LLMs. Moreover, the accuracy of Verilog generation surpasses that of the current state-of-the-art open-source Verilog generation model, increasing from 58.8% to 70.6% with the same benchmark. Our 13B model (ChipGPT-FT) has a pass rate improvement compared with GPT-3.5 in Verilog generation and outperforms in EDA script (i.e., SiliconCompiler) generation with only 200 EDA script data.

Related papers

• VerilogCoder: Autonomous Verilog Coding Agents with Graph-based Planning and Abstract Syntax Tree (AST)-based Waveform Tracing Tool [4.027984601764008]
  We propose VerilogCoder, a system of multiple Artificial Intelligence (AI) agents for Verilog code generation. The proposed methodology successfully generates 94.2% syntactically and functionally correct Verilog code.
  arXiv  Detail & Related papers  (2024-08-15T20:06:06Z)
• CodeV: Empowering LLMs for Verilog Generation through Multi-Level Summarization [37.4446786461791]
  This paper introduces CodeV, a series of open-source instruction-tuned Verilog generation LLMs. We show that CodeV relatively surpasses the previous open-source SOTA by 14.4% (BetterV in VerilogEval) and 11.3% (RTLCoder in RTLLM) respectively.
  arXiv  Detail & Related papers  (2024-07-15T03:57:20Z)
• DARG: Dynamic Evaluation of Large Language Models via Adaptive Reasoning Graph [70.79413606968814]
  We introduce Dynamic Evaluation of LLMs via Adaptive Reasoning Graph Evolvement (DARG) to dynamically extend current benchmarks with controlled complexity and diversity. Specifically, we first extract the reasoning graphs of data points in current benchmarks and then perturb the reasoning graphs to generate novel testing data. Such newly generated test samples can have different levels of complexity while maintaining linguistic diversity similar to the original benchmarks.
  arXiv  Detail & Related papers  (2024-06-25T04:27:53Z)
• A Multi-Expert Large Language Model Architecture for Verilog Code Generation [5.159745269633967]
  This paper introduces an innovative multi-expert LLM architecture for Verilog code generation (MEV-LLM) Our architecture uniquely integrates multiple LLMs, each specifically fine-tuned with a dataset that is categorized with respect to a distinct level of design complexity. Empirical evidence from experiments highlights notable improvements in terms of the percentage of generated Verilog outputs that are syntactically and functionally correct.
  arXiv  Detail & Related papers  (2024-04-11T16:58:29Z)
• CodecLM: Aligning Language Models with Tailored Synthetic Data [51.59223474427153]
  We introduce CodecLM, a framework for adaptively generating high-quality synthetic data for instruction-following abilities. We first encode seed instructions into metadata, which are concise keywords generated on-the-fly to capture the target instruction distribution. We also introduce Self-Rubrics and Contrastive Filtering during decoding to tailor data-efficient samples.
  arXiv  Detail & Related papers  (2024-04-08T21:15:36Z)
• BetterV: Controlled Verilog Generation with Discriminative Guidance [11.162807308782751]
  We propose a Verilog generation framework, BetterV, which fine-tunes the large language models (LLMs) on processed domain-specific runtime. BetterV has the ability to generate syntactically and functionally correct Verilog, which can outperform GPT-4 on the VerilogEval benchmark.
  arXiv  Detail & Related papers  (2024-02-03T08:00:12Z)
• LLM-Assisted Code Cleaning For Training Accurate Code Generators [53.087019724256606]
  We investigate data quality for code and find that making the code more structured and readable leads to improved code generation performance of the system. We build a novel data-cleaning pipeline that uses these principles to transform existing programs. We evaluate our approach on two challenging algorithmic code generation benchmarks and find that fine-tuning CodeLLaMa-7B improves the performance by up to 30% compared to fine-tuning on the original dataset.
  arXiv  Detail & Related papers  (2023-11-25T02:45:50Z)
• Benchmarking Large Language Models for Automated Verilog RTL Code Generation [21.747037230069854]
  We characterize the ability of large language models (LLMs) to generate useful Verilog. We construct an evaluation framework comprising test-benches for functional analysis and a flow to test the syntax of Verilog code. Our findings show that across our problem scenarios, the fine-tuning results in LLMs more capable of producing syntactically correct code.
  arXiv  Detail & Related papers  (2022-12-13T16:34:39Z)
• Fine-Grained Scene Graph Generation with Data Transfer [127.17675443137064]
  Scene graph generation (SGG) aims to extract (subject, predicate, object) triplets in images. Recent works have made a steady progress on SGG, and provide useful tools for high-level vision and language understanding. We propose a novel Internal and External Data Transfer (IETrans) method, which can be applied in a play-and-plug fashion and expanded to large SGG with 1,807 predicate classes.
  arXiv  Detail & Related papers  (2022-03-22T12:26:56Z)
• Self-Supervised Log Parsing [59.04636530383049]
  Large-scale software systems generate massive volumes of semi-structured log records. Existing approaches rely on log-specifics or manual rule extraction. We propose NuLog that utilizes a self-supervised learning model and formulates the parsing task as masked language modeling.
  arXiv  Detail & Related papers  (2020-03-17T19:25:25Z)

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.