Litcius/Paper detail

Invited Paper: CircuitOps: An ML Infrastructure Enabling Generative AI for VLSI Circuit Optimization

Rongjian Liang, Anthony Agnesina, Geraldo Pradipta, Vidya A. Chhabria, Haoxing Ren

202324 citationsDOI

Abstract

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 99× dataset generation speedup and 75K nets per second transfer throughput, validating its effectiveness in optimizing GAI tasks.

Topics & Concepts

Computer scienceInferenceNetlistSpeedupRepresentation (politics)ThroughputVery-large-scale integrationComputer engineeringSoftware deploymentComputer architectureArtificial intelligenceParallel computingMachine learningTheoretical computer scienceSoftware engineeringComputer hardwareEmbedded systemWirelessPoliticsTelecommunicationsLawPolitical scienceVLSI and FPGA Design TechniquesParallel Computing and Optimization TechniquesAdvanced Neural Network Applications
Invited Paper: CircuitOps: An ML Infrastructure Enabling Generative AI for VLSI Circuit Optimization | Litcius