Paper

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

Volume Number:
40
Issue Number:
4
Pages:
Starting page
748
Ending page
761
Publication Date:
Publication Date
April 2021

paper Menu

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.

Affiliation
NVIDIA
IEEE Region
Region 05 (Southwestern U.S.)
Country
USA
Affiliation
University of Texas at Austin
IEEE Region
Region 05 (Southwestern U.S.)
Email