Haoxing Ren

Haoxing Ren

Auto-generated profile, based on publicly available information

Haoxing Ren

NVIDIA Corporation, Austin, TX, USA

Research Focus & Metrics

Academic Career Length

20Years (2007-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
23 June 2024
Verified
Conference Paper
Open access
YTYunDa Tsai
YunDa Tsai
MLMingjie Liu
Mingjie Liu
HRHaoxing Ren
Haoxing Ren
This paper presents RTLFixer, a novel framework enabling automatic syntax errors fixing for Verilog code with Large Language Models (LLMs). Despite LLM's promising capabilities, our analysis indicates that approximately 55% of errors in LLM-generated Verilog are syntax-related, leading to compilation failures. To tackle this issue, we introduce a novel debugging framework that employs Retrieval-Augmented Generation (RAG) and ReAct prompting, enabling LLMs to act as autonomous agents in interactively debugging the code with feedback. This framework demonstrates exceptional proficiency in resolving syntax errors, successfully correcting about 98.5% of compilation errors in our debugging dataset, comprising 212 erroneous implementations derived from the VerilogEval benchmark. Our method leads to 32.3% and 10.1% increase in pass@1 success rates in the VerilogEval-Machine and VerilogEval-Human benchmarks, respectively. The source code and benchmark are available at https://github.com/NVlabs/RTLFixer.

11 April 2025 in Proceedings of the AAAI Conference on Artificial Intelligence
Verified
Journal Article
Open access
PDF file
CHChia-Tung Ho
Chia-Tung Ho
HRHaoxing Ren
Haoxing Ren
BKBrucek Khailany
Brucek Khailany
Due to the growing complexity of modern Integrated Circuits (ICs), automating hardware design can prevent a significant amount of human error from the engineering process and result in less errors. Verilog is a popular hardware description language for designing and modeling digital systems; thus, Verilog generation is one of the emerging areas of research to facilitate the design process. In this work, we propose VerilogCoder, a system of multiple Artificial Intelligence (AI) agents for Verilog code generation, to autonomously write Verilog code and fix syntax and functional errors using collaborative Verilog tools (i.e., syntax checker, simulator, and waveform tracer). Firstly, we propose a task planner that utilizes a novel Task and Circuit Relation Graph retrieval method to construct a holistic plan based on module descriptions. To debug and fix functional errors, we develop a novel and efficient abstract syntax tree (AST)-based waveform tracing tool, which is integrated within the autonomous Verilog completion flow. The proposed methodology successfully generates 94.2% syntactically and functionally correct Verilog code, surpassing the state-of-the-art methods by 33.9% on the VerilogEval-Human v2 benchmark.

24 September 2020 in IEEE Micro
Verified
Journal Article
Closed access
BKBrucek Khailany
Brucek Khailany
HRHaoxing Ren
Haoxing Ren
SDSteve Dai
Steve Dai
SGSaad Godil
Saad Godil
BKBen Keller
Ben Keller
WDWilliam J. Dally
William J. Dally
Recent advancements in machine learning provide an opportunity to transform chip design workflows. We review recent research applying techniques such as deep convolutional neural networks and graph-based neural networks in the areas of automatic design space exploration, power analysis, VLSI physical design, and analog design. We also present a future vision of an AI-assisted automated chip design workflow to aid designer productivity and automate optimization tasks.

26 March 2023
Verified
Conference Paper
Open access
AAAnthony Agnesina
Anthony Agnesina
PRPuranjay Rajvanshi
Puranjay Rajvanshi
TYTian Yang
Tian Yang
GPGeraldo Pradipta
Geraldo Pradipta
AJAustin Jiao
Austin Jiao
HRHaoxing Ren
Haoxing Ren

21 October 2025 in ACM Transactions on Design Automation of Electronic Systems
Verified
Journal Article
Open access
NPNathaniel Pinckney
Nathaniel Pinckney
CBChristopher Batten
Christopher Batten
MLMingjie Liu
Mingjie Liu
HRHaoxing Ren
Haoxing Ren
BKBrucek Khailany
Brucek Khailany
The application of large language models (LLMs) to digital hardware code generation is an emerging field, with most LLMs primarily trained on natural language and software code. Hardware code like Verilog constitutes a small portion of training data, and few hardware benchmarks exist. The open-source VerilogEval benchmark, released in November 2023, provided a consistent evaluation framework for LLMs on code completion tasks. Since then, both commercial and open models have seen significant development. In this work, we evaluate new commercial and open models since VerilogEval’s original release—including GPT-4o, GPT-4 Turbo, Llama3.1 (8B/70B/405B), Llama3 70B, Mistral Large, DeepSeek Coder (33B and 6.7B), CodeGemma 7B, and RTL-Coder—against an improved VerilogEval benchmark suite. We find measurable improvements in state-of-the-art models: GPT-4o achieves a 63% pass rate on specification-to-RTL tasks. The recently released and open Llama3.1 405B achieves a 58% pass rate, almost matching GPT-4o, while the smaller domain-specific RTL-Coder 6.7B models achieve an impressive 34% pass rate. Additionally, we enhance VerilogEval’s infrastructure by automatically classifying failures, introducing in-context learning support, and extending the tasks to specification-to-RTL translation. We find that prompt engineering remains crucial for achieving good pass rates and varies widely with model and task. A benchmark infrastructure that allows for prompt engineering and failure analysis is essential for continued model development and deployment.

10 July 2022
Verified
Conference Paper
Open access
HYHaoyu Yang
Haoyu Yang
ZLZongyi Li
Zongyi Li
KSKumara Sastry
Kumara Sastry
SMSaumyadip Mukhopadhyay
Saumyadip Mukhopadhyay
MKMark Kilgard
Mark Kilgard
HRHaoxing Ren
Haoxing Ren
Lithography simulation is a critical step in VLSI design and optimization for manufacturability. Existing solutions for highly accurate lithography simulation with rigorous models are computationally expensive and slow, even when equipped with various approximation techniques. Recently, machine learning has provided alternative solutions for lithography simulation tasks such as coarse-grained edge placement error regression and complete contour prediction. However, the impact of these learning-based methods has been limited due to restrictive usage scenarios or low simulation accuracy. To tackle these concerns, we introduce an dual-band optics-inspired neural network design that considers the optical physics underlying lithography. To the best of our knowledge, our approach yields the first published via/metal layer contour simulation at 1nm2/pixel resolution with any tile size. Compared to previous machine learning based solutions, we demonstrate that our framework can be trained much faster and offers a significant improvement on efficiency and image quality with 20× smaller model size. We also achieve 85× simulation speedup over traditional lithography simulator with ~ 1% accuracy loss.