CSpace

浏览/检索结果: 共6条,第1-6条 帮助

限定条件                
已选(0)清除 条数/页:   排序方式:
A Pattern-Based SpGEMM Library for Multi-Core and Many-Core Architectures 期刊论文
IEEE TRANSACTIONS ON PARALLEL AND DISTRIBUTED SYSTEMS, 2022, 卷号: 33, 期号: 1, 页码: 159-175
作者:  Xie, Zhen;  Tan, Guangming;  Liu, Weifeng;  Sun, Ninghui
收藏  |  浏览/下载:41/0  |  提交时间:2021/12/01
Libraries  Sparse matrices  Prediction algorithms  Neural networks  Predictive models  Memory management  Tuners  SpGEMM  spare BLAS  sparse format  auto-tuning  neural network  
Breaking the Interaction Wall: A DLPU-Centric Deep Learning Computing System 期刊论文
IEEE TRANSACTIONS ON COMPUTERS, 2022, 卷号: 71, 期号: 1, 页码: 209-222
作者:  Du, Zidong;  Guo, Qi;  Zhao, Yongwei;  Zeng, Xi;  Li, Ling;  Cheng, Limin;  Xu, Zhiwei;  Sun, Ninghui;  Chen, Yunji
收藏  |  浏览/下载:32/0  |  提交时间:2022/06/21
Deep learning  Central Processing Unit  Process control  Task analysis  Computational modeling  Pipelines  Runtime  Neural net accelerators  system architectures  interaction wall  
HyperFatTree: A Large-Scale Tree-Based Network with Low-Radix Switches 期刊论文
INTERNATIONAL JOURNAL OF PARALLEL PROGRAMMING, 2017, 卷号: 45, 期号: 1, 页码: 172-184
作者:  Su, Yong;  Wang, Zhan;  Fan, Zhiguo;  Cao, Zheng;  Liu, Xiaoli;  Shao, En;  An, Xuejun;  Sun, Ninghui
收藏  |  浏览/下载:69/0  |  提交时间:2019/12/12
High energy efficiency  Hierarchical topology  Low-radix switch  Large scale interconnecting network  
Graphine: Programming Graph-Parallel Computation of Large Natural Graphs for Multicore Clusters 期刊论文
IEEE TRANSACTIONS ON PARALLEL AND DISTRIBUTED SYSTEMS, 2016, 卷号: 27, 期号: 6, 页码: 1647-1659
作者:  Yan, Jie;  Tan, Guangming;  Mo, Zeyao;  Sun, Ninghui
收藏  |  浏览/下载:42/0  |  提交时间:2019/12/13
Graph-parallel  parallel framework  computational model  
Design and implementation of communication system of the Dawning 6000 supercomputer 期刊论文
FRONTIERS OF COMPUTER SCIENCE IN CHINA, 2010, 卷号: 4, 期号: 4, 页码: 466-474
作者:  Li, Qiang;  Li, Bo;  Huo, Zhigang;  Sun, Ninghui
收藏  |  浏览/下载:68/0  |  提交时间:2019/12/16
hyper parallel processing (HPP)  global address space (GAS)  virtualization  Dawning 6000  unified parallel C (UPC)  
Improving Performance of Dynamic Programming via Parallelism and Locality on Multicore Architectures 期刊论文
IEEE TRANSACTIONS ON PARALLEL AND DISTRIBUTED SYSTEMS, 2009, 卷号: 20, 期号: 2, 页码: 261-274
作者:  Tan, Guangming;  Sun, Ninghui;  Gao, Guang R.
收藏  |  浏览/下载:37/0  |  提交时间:2019/12/16
Dynamic programming  memory hierarchy  latency tolerant  percolation  multicore