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:
Accelerating Data Transfer in Dataflow Architectures Through a Look-Ahead Acknowledgment Mechanism 期刊论文
JOURNAL OF COMPUTER SCIENCE AND TECHNOLOGY, 2022, 卷号: 37, 期号: 4, 页码: 942-959
作者:  Feng, Yu-Jing;  Li, De-Jian;  Tan, Xu;  Ye, Xiao-Chun;  Fan, Dong-Rui;  Li, Wen-Ming;  Wang, Da;  Zhang, Hao;  Tang, Zhi-Min
收藏  |  浏览/下载:25/0  |  提交时间:2022/12/07
dataflow model  control-ow model  high-performance computing application  data transfer  power efficiency  
Fast and accurate variable batch size convolution neural network training on large scale distributed systems 期刊论文
CONCURRENCY AND COMPUTATION-PRACTICE & EXPERIENCE, 2022, 页码: 26
作者:  Hu, Zhongzhe;  Xiao, Junmin;  Sun, Ninghui;  Tan, Guangming
收藏  |  浏览/下载:20/0  |  提交时间:2022/12/07
deep learning  distributed computing  ImageNet-1K  large-batch training  synchronous SGD  
Swallow: A Versatile Accelerator for Sparse Neural Networks 期刊论文
IEEE TRANSACTIONS ON COMPUTER-AIDED DESIGN OF INTEGRATED CIRCUITS AND SYSTEMS, 2020, 卷号: 39, 期号: 12, 页码: 4881-4893
作者:  Liu, Bosheng;  Chen, Xiaoming;  Han, Yinhe;  Xu, Haobo
收藏  |  浏览/下载:28/0  |  提交时间:2021/12/01
Accelerator  convolutional (Conv) layers  fully connected (FC) layers  sparse neural networks (SNNs)  
Self-Aware Neural Network Systems: A Survey and New Perspective 期刊论文
PROCEEDINGS OF THE IEEE, 2020, 卷号: 108, 期号: 7, 页码: 1047-1067
作者:  Du, Zidong;  Guo, Qi;  Zhao, Yongwei;  Chen, Yunji;  Xu, Zhiwei;  Zhi, Tian
收藏  |  浏览/下载:49/0  |  提交时间:2020/12/10
Artificial neural networks  Neurons  Self-aware  Monitoring  Sensors  Program processors  Logic gates  Self-aware neural network (NN) processors  
A Pipelining Loop Optimization Method for Dataflow Architecture 期刊论文
JOURNAL OF COMPUTER SCIENCE AND TECHNOLOGY, 2018, 卷号: 33, 期号: 1, 页码: 116-130
作者:  Tan, Xu;  Ye, Xiao-Chun;  Shen, Xiao-Wei;  Xu, Yuan-Chao;  Wang, Da;  Zhang, Lunkai;  Li, Wen-Ming;  Fan, Dong-Rui;  Tang, Zhi-Min
收藏  |  浏览/下载:74/0  |  提交时间:2019/12/10
dataflow model  control-flow model  loop optimization  exascale computing  scientific application  
Shangri-la: Achieving high performance from compiled network applications while enabling ease of programming 期刊论文
ACM SIGPLAN NOTICES, 2005, 卷号: 40, 期号: 6, 页码: 224-236
作者:  Chen, MK;  Li, XF;  Lian, RQ;  Lin, JH;  Liu, LX;  Liu, T;  Ju, R
收藏  |  浏览/下载:39/0  |  提交时间:2019/12/16
packet processing  network processors  chip multiprocessors  throughput-oriented computing  program partitioning  dataflow programming