@article{Liu2022, 
author = {Lei Liu and Xiu Ma and Hua-Xiao Liu and Guang-Li Li and Lei Liu},
title = {FlexPDA: A Flexible Programming Framework for Deep Learning Accelerators},
year = {2022},
journal = {Journal of Computer Science and Technology},
volume = {37},
number = {5},
pages = {1200-1220},
keywords = {deep learning accelerator, programming framework, domain-specific language},
url = {https://www.sciopen.com/article/10.1007/s11390-021-1406-9},
doi = {10.1007/s11390-021-1406-9},
abstract = {There are a wide variety of intelligence accelerators with promising performance and energy efficiency, deployed in a broad range of applications such as computer vision and speech recognition. However, programming productivity hinders the deployment of deep learning accelerators. The low-level library invoked in the high-level deep learning framework which supports the end-to-end execution with a given model, is designed to reduce the programming burden on the intelligence accelerators. Unfortunately, it is inflexible for developers to build a network model for every deep learning application, which probably brings unnecessary repetitive implementation. In this paper, a flexible and efficient programming framework for deep learning accelerators, FlexPDA, is proposed, which provides more optimization opportunities than the low-level library and realizes quick transplantation of applications to intelligence accelerators for fast upgrades. We evaluate FlexPDA by using 10 representative operators selected from deep learning algorithms and an end-to-end network. The experimental results validate the effectiveness of FlexPDA, which achieves an end-to-end performance improvement of 1.620x over the low-level library.}
}