Late Breaking Results: Parallelizing Net Routing with cGANs

Obstacle-avoiding multiterminal net routing approach is proposed. The approach is inspired by deep learning image processing. The key idea is based on training a conditional generative adversarial network (cGAN) to interpret a routing task as a graphical bitmap and consequently map it to an optimal...

Full description

Saved in:
Bibliographic Details
Published in:2021 58th ACM/IEEE Design Automation Conference (DAC) pp. 1372 - 1373
Main Authors: Utyamishev, Dmitry, Partin-Vaisband, Inna
Format: Conference Proceeding
Language:English
Published: IEEE 05.12.2021
Subjects:
Benchmark testing
cGAN
Deep learning
Design automation
generative models
GPU
Graphics processing units
Imaging
inpainting
multiterminal
Net routing
neural network
Training
Very large scale integration
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Obstacle-avoiding multiterminal net routing approach is proposed. The approach is inspired by deep learning image processing. The key idea is based on training a conditional generative adversarial network (cGAN) to interpret a routing task as a graphical bitmap and consequently map it to an optimal routing solution represented by another bitmap. The system is implemented in Python/Keras, trained on synthetically generated data, evaluated on typical high-resolution benchmarks, and compared with state-of-the-art traditional deterministic and deep learning solutions. The proposed system yields between 10.75x and 83.33x speedup over the traditional router without wirelength overhead due to effective parallelization on GPU hardware.
DOI:10.1109/DAC18074.2021.9586319