作者
Mohamed Abdelfattah, Łukasz Dudziak, Thomas Chau, Royson Lee, Hyeji Kim, Nicholas Lane
发表日期
2020
研讨会论文
Design Automation Conference (DAC)
页码范围
https://arxiv.org/abs/2002.05022
简介
Neural architecture search (NAS) has been very successful at outperforming human-designed convolutional neural networks (CNN) in accuracy, and when hardware information is present, latency as well. However, NAS-designed CNNs typically have a complicated topology, therefore, it may be difficult to design a custom hardware (HW) accelerator for such CNNs. We automate HW-CNN codesign using NAS by including parameters from both the CNN model and the HW accelerator, and we jointly search for the best model-accelerator pair that boosts accuracy and efficiency. We call this Codesign-NAS. In this paper we focus on defining the Codesign-NAS multiobjective optimization problem, demonstrating its effectiveness, and exploring different ways of navigating the codesign search space. For CIFAR-10 image classification, we enumerate close to 4 billion model-accelerator pairs, and find the Pareto frontier …
引用总数
20202021202220232024328282110
学术搜索中的文章
MS Abdelfattah, Ł Dudziak, T Chau, R Lee, H Kim… - 2020 57th ACM/IEEE Design Automation Conference …, 2020