CSpace

浏览/检索结果: 共5条,第1-5条 帮助

限定条件    
已选(0)清除 条数/页:   排序方式:
Accelerating Convolutional Neural Networks by Exploiting the Sparsity of Output Activation 期刊论文
IEEE TRANSACTIONS ON PARALLEL AND DISTRIBUTED SYSTEMS, 2023, 卷号: 34, 期号: 12, 页码: 3253-3265
作者:  Fan, Zhihua;  Li, Wenming;  Wang, Zhen;  Liu, Tianyu;  Wu, Haibin;  Liu, Yanhuan;  Wu, Meng;  Wu, Xinxin;  Ye, Xiaochun;  Fan, Dongrui;  Sun, Ninghui;  An, Xuejun
收藏  |  浏览/下载:2/0  |  提交时间:2024/05/20
Accelerator  output activation  prediction  sparse convolutional neural network  
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  
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  
Accelerating Irregular Computation in Massive Short Reads Mapping on FPGA Co-Processor 期刊论文
IEEE TRANSACTIONS ON PARALLEL AND DISTRIBUTED SYSTEMS, 2016, 卷号: 27, 期号: 5, 页码: 1253-1264
作者:  Tan, Guangming;  Zhang, Chunming;  Tang, Wen;  Zhang, Peiheng;  Sun, Ninghui
收藏  |  浏览/下载:38/0  |  提交时间:2019/12/13
Short read mapping  irregular computation  FPGA  multicore parallelism  
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