RegPlace: Regularity-Aware Placement for Full-System DNN Accelerator Designs
- 3 July 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems
- Vol. 45 (2) , 686-690
Abstract
The rise of deep neural network (DNN) accelerators demands physical design tools that recognize spatial regularity patterns. Traditional placers, unaware of the regularity of spatial arrays, produce suboptimal solutions. This work proposes RegPlace, a regularity-aware placement algorithm for full-system DNN accelerators that automatically identifies processing element using graph convolutional networks and employs a variance-based soft regularity loss to guide optimization. Compared to state-of-the-art methods, our approach achieves up to 6% wirelength reduction while maintaining comparable runtime, with post-placement metrics further confirming its effectiveness.Keywords
Funding Information
- Research Grants Council of Hong Kong SAR (CUHK14210723)
- Research Grants Council of Hong Kong SAR (CUHK14211824)
This publication has 15 references indexed in Scilit:
- DG-RePlAce: A Dataflow-Driven GPU-Accelerated Analytical Global Placement Framework for Machine Learning AcceleratorsIEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, 2024
- Stronger Mixed-Size Placement Backbone Considering Second-Order Information2023
- Gemmini: Enabling Systematic Deep-Learning Architecture Evaluation via Full-Stack Integration2021
- HybridDNN: A Framework for High-Performance Hybrid DNN Accelerator Design and Implementation2020
- MAGNet: A Modular Accelerator Generator for Neural Networks2019
- Structure-aware placement for datapath-intensive circuit designs2012
- PADE2012
- Keep it straight2012
- Regularity-constrained floorplanning for multi-core processors2011
- A data path layout assembler for high performance DSP circuits1990