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

doi:10.1109/TCAD.2020.3003843

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

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\times $ 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.

Publication:

IEEE Transactions on Computer Aided Design

Pub Date:

2021

DOI:

10.1109/TCAD.2020.3003843

Bibcode:

2021ITCAD..40..748L

Keywords:

Deep learning;
GPU acceleration;
physical desgin;
VLSI placement

ADS

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

Abstract