中文版 | English

在结果中检索

CSpace

浏览/检索结果: 共403条，第1-10条 帮助

已选(0)清除 条数/页：   排序方式：
CUTE: A scalable CPU-centric and Ultra-utilized Tensor Engine for convolutions 期刊论文
JOURNAL OF SYSTEMS ARCHITECTURE, 2024, 卷号: 149, 页码: 15
作者:  Li, Wenqing;  Ye, Jinpeng;  Zhang, Fuxin;  Liu, Tianyi;  Zhang, Tingting;  Wang, Jian
收藏  |  浏览/下载：2/0  |  提交时间：2024/05/20
Tensor engine  Convolution  Scalable architecture  CPU-centric  Utilization  
Distributed Multi-GPU Ab Initio Density Matrix Renormalization Group Algorithm with Applications to the P-Cluster of Nitrogenase 期刊论文
JOURNAL OF CHEMICAL THEORY AND COMPUTATION, 2024, 卷号: 20, 期号: 2, 页码: 775-786
作者:  Xiang, Chunyang;  Jia, Weile;  Fang, Wei-Hai;  Li, Zhendong
收藏  |  浏览/下载：2/0  |  提交时间：2024/05/20
Accelerating k-Shape Time Series Clustering Algorithm Using GPU 期刊论文
IEEE TRANSACTIONS ON PARALLEL AND DISTRIBUTED SYSTEMS, 2023, 卷号: 34, 期号: 10, 页码: 2718-2734
作者:  Wang, Xun;  Song, Ruibao;  Xiao, Junmin;  Li, Tong;  Li, Xueqi
收藏  |  浏览/下载：7/0  |  提交时间：2023/12/04
Data space  time series analysis  time series clustering  GPU architecture  k-shape algorithm  
ESA: An efficient sequence alignment algorithm for biological database search on Sunway TaihuLight 期刊论文
PARALLEL COMPUTING, 2023, 卷号: 117, 页码: 11
作者:  Zhang, Hao;  Huang, Zhiyi;  Chen, Yawen;  Liang, Jianguo;  Gao, Xiran
收藏  |  浏览/下载：7/0  |  提交时间：2023/12/04
Hybrid sequence alignment  Biological database search  Sunway TaihuLight  SW26010  Heterogeneous architecture  
Dadu-SV: Accelerate Stereo Vision Processing on NPU 期刊论文
IEEE EMBEDDED SYSTEMS LETTERS, 2022, 卷号: 14, 期号: 4, 页码: 191-194
作者:  Min, Feng;  Wang, Ying;  Xu, Haobo;  Huang, Junpei;  Wang, Yujie;  Zou, Xingqi;  Lu, Meixuan;  Han, Yinhe
收藏  |  浏览/下载：14/0  |  提交时间：2023/07/12
Hardware acceleration  neural computing  neural processing unit (NPU)  semiglobal matching (SGM)  stereo vision  
EAIS: Energy-aware adaptive scheduling for CNN inference on high-performance GPUs 期刊论文
FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE, 2022, 卷号: 130, 页码: 253-268
作者:  Yao, Chunrong;  Liu, Wantao;  Tang, Weiqing;  Hu, Songlin
收藏  |  浏览/下载：18/0  |  提交时间：2022/12/07
Energy-aware  Convolutional neural network (CNN) inference  High-performance GPUs  Workload scheduling  Service-Level-Objective (SLO)  
EnGN: A High-Throughput and Energy-Efficient Accelerator for Large Graph Neural Networks 期刊论文
IEEE TRANSACTIONS ON COMPUTERS, 2021, 卷号: 70, 期号: 9, 页码: 1511-1525
作者:  Liang, Shengwen;  Wang, Ying;  Liu, Cheng;  He, Lei;  Li, Huawei;  Xu, Dawen;  Li, Xiaowei
收藏  |  浏览/下载：37/0  |  提交时间：2021/12/01
Neural networks  Hardware  System-on-chip  Task analysis  Feature extraction  Memory management  Graph neural network  accelerator architecture  hardware acceleration  
A Chip-Level Optical Interconnect for CPU 期刊论文
IEEE PHOTONICS TECHNOLOGY LETTERS, 2021, 卷号: 33, 期号: 16, 页码: 852-855
作者:  Hao, Qinfen;  Qin, Mengyuan;  Qi, Nan;  Xue, Haiyun;  Han, Meng;  Li, Xiaolin;  Hao, Kai;  Niu, Xingmao;  Xiao, Limin;  Fan, Dongrui;  Kurata, Kazuhiko
收藏  |  浏览/下载：38/0  |  提交时间：2021/12/01
Integrated optics  Optical interconnections  Transceivers  Adaptive optics  Optical switches  Optical sensors  Power demand  Optical interconnections  digital integrated circuits  very high speed integrated circuits  chip scale packaging  system integration  
Improve the Resolution and Parallel Performance of the Three-Dimensional Refine Algorithm in RELION Using CUDA and MPI 期刊论文
IEEE-ACM TRANSACTIONS ON COMPUTATIONAL BIOLOGY AND BIOINFORMATICS, 2021, 卷号: 18, 期号: 2, 页码: 583-595
作者:  Zhang, Jingrong;  Wang, Zihao;  Liu, Zhiyong;  Zhang, Fa
收藏  |  浏览/下载：35/0  |  提交时间：2021/12/01
Memory management  Graphics processing units  Arrays  Statistical analysis  Three-dimensional displays  cryoEM  RELION  CUDA  statistical method  Top-k selection  
Evaluating and analyzing the energy efficiency of CNN inference on high-performance GPU 期刊论文
CONCURRENCY AND COMPUTATION-PRACTICE & EXPERIENCE, 2020, 页码: 26
作者:  Yao, Chunrong;  Liu, Wantao;  Tang, Weiqing;  Guo, Jinrong;  Hu, Songlin;  Lu, Yijun;  Jiang, Wei
收藏  |  浏览/下载：57/0  |  提交时间：2020/12/10
CNNs  energy efficiency  high-performance GPU  inference