A high-performance dataflow-centric optimization framework for deep learning inference on the edge
Authors:
- Runhua ZhangRZRunhua Zhang
- Hongxu JiangHJHongxu Jiang
- Jinkun GengJinkun Geng
- Fangzheng TianFTFangzheng Tian
- Yuhang MaYMYuhang Ma
- Haojie WangHWHaojie Wang
- 20 May 2024
- journal article
- research article
- Published by Elsevier in Journal of Systems Architecture
- Vol. 152
Abstract
No abstract availableKeywords
Funding Information
- Academic Excellence Foundation of BUAA for PHD Students
- National Key Research and Development Program of China (2021ZD0110202)
This publication has 20 references indexed in Scilit:
- Edge-Cloud Polarization and Collaboration: A Comprehensive Survey for AIIEEE Transactions on Knowledge and Data Engineering, 2022
- Impact of Synchronization Topology on DML Performance: Both Logical Topology and Physical TopologyIEEE/ACM Transactions on Networking, 2021
- Adaptive parallel execution of deep neural networks on heterogeneous edge devices2019
- Automating IoT Data-Intensive Application Allocation in Clustered Edge ComputingIEEE Transactions on Knowledge and Data Engineering, 2019
- HAQ: Hardware-Aware Automated Quantization With Mixed Precision2019
- HiPS2018
- Deep Residual Learning for Image Recognition2016
- Pruning Incremental Linear Model Trees with Approximate LookaheadIEEE Transactions on Knowledge and Data Engineering, 2013
- Halide2013
- Bandwidth optimal all-reduce algorithms for clusters of workstationsJournal of Parallel and Distributed Computing, 2009