CSpace

浏览/检索结果: 共2条,第1-2条 帮助

已选(0)清除 条数/页:   排序方式:
An Application-oblivious Memory Scheduling System for DNN Accelerators 期刊论文
ACM TRANSACTIONS ON ARCHITECTURE AND CODE OPTIMIZATION, 2022, 卷号: 19, 期号: 4, 页码: 26
作者:  Li, Jiansong;  Wang, Xueying;  Chen, Xiaobing;  Li, Guangli;  Dong, Xiao;  Zhao, Peng;  Yu, Xianzhi;  Yang, Yongxin;  Cao, Wei;  Liu, Lei;  Feng, Xiaobing
收藏  |  浏览/下载:22/0  |  提交时间:2023/07/12
Deep learning  memory scheduling  runtime system  DNN accelerators  
Optimizing the LINPACK Algorithm for Large-Scale PCIe-Based CPU-GPU Heterogeneous Systems 期刊论文
IEEE TRANSACTIONS ON PARALLEL AND DISTRIBUTED SYSTEMS, 2021, 卷号: 32, 期号: 9, 页码: 2367-2380
作者:  Tan, Guangming;  Shui, Chaoyang;  Wang, Yinshan;  Yu, Xianzhi;  Yan, Yujin
收藏  |  浏览/下载:47/0  |  提交时间:2021/12/01
Pipeline processing  Graphics processing units  Computer architecture  Supercomputers  Clustering algorithms  Programming  Optimization  LINPACK algorithm  software pipeline  performance model  heterogeneous computing  cluster