DREAMPlace: Deep Learning Toolkit-Enabled GPU Acceleration for Modern VLSI Placement

Yibo Lin, Zixuan Jiang, Jiaqi Gu, Wuxi Li, Shounak Dhar, Haoxing Ren, Brucek Khailany, David Z. Pan

2020IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems163 citationsDOI

Abstract

Placement for very large-scale integrated (VLSI) circuits is one of the most important steps for design closure. We propose a novel GPU-accelerated placement framework DREAMPlace, by casting the analytical placement problem equivalently to training a neural network. Implemented on top of a widely adopted deep learning toolkit PyTorch, with customized key kernels for wirelength and density computations, DREAMPlace can achieve around 40× speedup in global placement without quality degradation compared to the state-of-the-art multithreaded placer RePlAce. We believe this work shall open up new directions for revisiting classical EDA problems with advancements in AI hardware and software.

Topics & Concepts

Computer scienceSpeedupVery-large-scale integrationComputer architectureComputationComputer engineeringDeep learningParallel computingKey (lock)AccelerationSoftwareArtificial neural networkComputational scienceArtificial intelligenceEmbedded systemAlgorithmProgramming languagePhysicsClassical mechanicsComputer securityVLSI and FPGA Design TechniquesVLSI and Analog Circuit TestingAdvancements in Photolithography Techniques