1. [Publications](/publications)
2. CircuitOps: An ML Infrastructure Enabling Generative AI for VLSI Circuit Optimization
 
 # CircuitOps: An ML Infrastructure Enabling Generative AI for VLSI Circuit Optimization

  ![](/sites/default/files/styles/wide/public/publications/circuitops_overview.png?itok=c-lQwfja)

 An innovative ML infrastructure named CircuitOps is developed to streamline dataset generation and model inference for various generative AI (GAI)-based circuit optimization tasks. Addressing the challenges of the absence of a shared Intermediate Representation (IR), steep EDA learning curves, and AI-unfriendly data structures, we propose solutions that empower efficient data handling. Our contributions encompass the following: (1) labeled property graphs (LPGs) as IR for flexible netlist representation and efficient parallel processing; (2) tools-agnostic IR generation from standard EDA files; (3) customizable dataset generation facilitated through AI-friendly LPGs; (4) gRPC-based inference deployment. Compared with using Tcl interfaces of EDA design tools, CircuitOps achieves a significant 99x dataset generation speedup and 75K nets per second transfer throughput, validating its effectiveness in optimizing GAI tasks.



 ## Authors



[Rongjian Liang](/person/rongjian-liang)

Anthony Agnesina (NVIDIA)

Geraldo Pradipta (NVIDIA)

Vidya A. Chhabria (Arizona State University)

Mark Haoxing Ren (NVIDIA)

 

 

 ## Publication Date



Thursday, November 30, 2023

 

 ## Published in



[2023 IEEE/ACM International Conference on Computer Aided Design (ICCAD) ](https://2023.iccad.com/)

 

 ## Research Area



[Artificial Intelligence and Machine Learning ](/research-area/machine-learning-artificial-intelligence)

[Circuits and VLSI Design](/research-area/circuits)

 

 

 ## External Links



[GitHub repo](https://github.com/NVlabs/CircuitOps)

 

 

 ## Uploaded Files



[CircuitOps (1).pdf](https://d1qx31qr3h6wln.cloudfront.net/publications/CircuitOps%20%281%29.pdf "Open file in new window")10.22 MB

 

 

 ## Copyright



This material is posted here with permission of the IEEE. Internal or personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution must be obtained from the IEEE by writing to <pubs-permissions@ieee.org>.