pommDNN: Performance optimal GPU memory management for deep neural network training
Authors:
- Weiduo ChenWCWeiduo Chen
- Xiaoshe DongXDXiaoshe Dong
- Xinhang ChenXCXinhang Chen
- Song LiuSLSong Liu
- Qin XiaQXQin Xia
- Qiang WangQWQiang Wang
- 1 November 2023
- journal article
- review article
- Published by Elsevier in Future Generation Computer Systems
- Vol. 152, 160-169
Abstract
No abstract availableKeywords
This publication has 5 references indexed in Scilit:
- An Intelligent Framework for Oversubscription Management in CPU-GPU Unified MemoryJournal of Grid Computing, 2023
- Deep learning based data prefetching in CPU-GPU unified virtual memoryJournal of Parallel and Distributed Computing, 2022
- Performance evaluation of convolutional neural network on Tianhe-3 prototypeThe Journal of Supercomputing, 2021
- moDNN: Memory Optimal Deep Neural Network Training on Graphics Processing UnitsIEEE Transactions on Parallel and Distributed Systems, 2018
- ImageNet classification with deep convolutional neural networksCommunications of the ACM, 2017