BlueConnect: Decomposing all-reduce for deep learning on heterogeneous network hierarchy
Authors:
- M. ChoMCM. Cho
- U. FinklerUFU. Finkler
- M. SerranoMSM. Serrano
- D. KungDKD. Kung
- H. HunterHHH. Hunter
- 1 November 2019
- journal article
- research article
- Published by IBM in IBM Journal of Research and Development
- Vol. 63 (6) , 1:1-1:11
Abstract
No abstract availableThis publication has 9 references indexed in Scilit:
- In-Datacenter Performance Analysis of a Tensor Processing Unit2017
- CNTK2016
- Deep Residual Learning for Image Recognition2016
- Application-Level Optimization of Big Data Transfers through Pipelining, Parallelism and ConcurrencyIEEE Transactions on Cloud Computing, 2015
- Caffe2014
- A scalable, commodity data center network architectureACM SIGCOMM Computer Communication Review, 2008
- Optimization of MPI collective communication on BlueGene/L systems2005
- Optimization of Collective Communication Operations in MPICHThe International Journal of High Performance Computing Applications, 2005
- PSockets: The Case for Application-level Network Striping for Data Intensive Applications using High Speed Wide Area Networks2000