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:
CSCC: Convolution Split Compression Calculation Algorithm for Deep Neural Network 期刊论文
IEEE ACCESS, 2019, 卷号: 7, 页码: 71607-71615
作者:  Fan, Shengyu;  Yu, Hui;  Lu, Dianjie;  Jiao, Shuai;  Xu, Weizhi;  Liu, Fangai;  Liu, Zhiyong
收藏  |  浏览/下载:234/0  |  提交时间:2019/08/16
Convolutional neural network  sparse matrix vector multiplication  neural networks  convolution  sparse matrices  
Design and Implementation of Adaptive SpMV Library for Multicore and Many-Core Architecture 期刊论文
ACM TRANSACTIONS ON MATHEMATICAL SOFTWARE, 2018, 卷号: 44, 期号: 4, 页码: 25
作者:  Tan, Guangming;  Liu, Junhong;  Li, Jiajia
收藏  |  浏览/下载:56/0  |  提交时间:2019/12/10
Sparse matrix vector multiplication  auto-tuning  multicore  machine learning  
A multi-GPU parallel optimization model for the preconditioned conjugate gradient algorithm 期刊论文
PARALLEL COMPUTING, 2017, 卷号: 63, 页码: 1-16
作者:  Gao, Jiaquan;  Zhou, Yuanshen;  He, Guixia;  Xia, Yifei
收藏  |  浏览/下载:45/0  |  提交时间:2019/12/12
Optimization model  Preconditioned conjugate gradient algorithm  CUDA  Multiple GPUs  
A Cross-Platform SpMV Framework on Many-Core Architectures 期刊论文
ACM TRANSACTIONS ON ARCHITECTURE AND CODE OPTIMIZATION, 2016, 卷号: 13, 期号: 4, 页码: 25
作者:  Zhang, Yunquan;  Li, Shigang;  Yan, Shengen;  Zhou, Huiyang
收藏  |  浏览/下载:38/0  |  提交时间:2019/12/12
SpMV  segmented scan  BCCOO  OpenCL  CUDA  GPU  Intel MIC  parallel algorithms  
Automatic tuning of sparse matrix-vector multiplication on multicore clusters 期刊论文
SCIENCE CHINA-INFORMATION SCIENCES, 2015, 卷号: 58, 期号: 9, 页码: 14
作者:  Li ShiGang;  Hu ChangJun;  Zhang JunChao;  Zhang YunQuan
收藏  |  浏览/下载:50/0  |  提交时间:2019/12/13
SpMV  PGAS  hybridization  model-driven  multicore clusters  
Memory bandwidth optimization of SpMV on GPGPUs 期刊论文
FRONTIERS OF COMPUTER SCIENCE, 2015, 卷号: 9, 期号: 3, 页码: 431-441
作者:  Yan, Chenggang Clarence;  Yu, Hui;  Xu, Weizhi;  Zhang, Yingping;  Chen, Bochuan;  Tian, Zhu;  Wang, Yuxuan;  Yin, Jian
收藏  |  浏览/下载:56/0  |  提交时间:2019/12/13
GPGPU  performance tuning  SpMV  cache blocking  memory bandwidth