中文版 | English

在结果中检索

CSpace

浏览/检索结果: 共19条，第1-10条 帮助

已选(0)清除 条数/页：   排序方式：
HiHGNN: Accelerating HGNNs Through Parallelism and Data Reusability Exploitation 期刊论文
IEEE TRANSACTIONS ON PARALLEL AND DISTRIBUTED SYSTEMS, 2024, 卷号: 35, 期号: 7, 页码: 1122-1138
作者:  Xue, Runzhen;  Han, Dengke;  Yan, Mingyu;  Zou, Mo;  Yang, Xiaocheng;  Wang, Duo;  Li, Wenming;  Tang, Zhimin;  Kim, John;  Ye, Xiaochun;  Fan, Dongrui
收藏  |  浏览/下载：1/0  |  提交时间：2024/12/06
Semantics  Parallel processing  Graph neural networks  Vectors  Graphics processing units  Fuses  Hardware  GNN  GNN accelerator  graph neural network  HGNN  HGNN accelerator  heterogeneous graph neural network  
MoDSE: A High-Accurate Multiobjective Design Space Exploration Framework for CPU Microarchitectures 期刊论文
IEEE TRANSACTIONS ON COMPUTER-AIDED DESIGN OF INTEGRATED CIRCUITS AND SYSTEMS, 2024, 卷号: 43, 期号: 5, 页码: 1525-1537
作者:  Wang, Duo;  Yan, Mingyu;  Teng, Yihan;  Han, Dengke;  Liu, Xin;  Li, Wenming;  Ye, Xiaochun;  Fan, Dongrui
收藏  |  浏览/下载：3/0  |  提交时间：2024/12/06
Pareto optimization  Predictive models  Measurement  Space exploration  Prediction algorithms  Central Processing Unit  Microarchitecture  CPU microarchitecture  design space exploration (DSE)  multiobjective exploration  Pareto hypervolume  prediction model  
Improving Utilization of Dataflow Unit for Multi-Batch Processing 期刊论文
ACM TRANSACTIONS ON ARCHITECTURE AND CODE OPTIMIZATION, 2024, 卷号: 21, 期号: 1, 页码: 26
作者:  Fan, Zhihua;  Li, Wenming;  Wang, Zhen;  Yang, Yu;  Ye, Xiaochun;  Fan, Dongrui;  Sun, Ninghui;  An, Xuejun
收藏  |  浏览/下载：12/0  |  提交时间：2024/05/20
Utilization  network-on-chip  decoupled architecture  batch processing  
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：11/0  |  提交时间：2024/05/20
Accelerator  output activation  prediction  sparse convolutional neural network  
Characterizing and Understanding Defense Methods for GNNs on GPUs 期刊论文
IEEE COMPUTER ARCHITECTURE LETTERS, 2023, 卷号: 22, 期号: 2, 页码: 137-140
作者:  Wu, Meng;  Yan, Mingyu;  Yang, Xiaocheng;  Li, Wenming;  Zhang, Zhimin;  Ye, Xiaochun;  Fan, Dongrui
收藏  |  浏览/下载：17/0  |  提交时间：2023/12/04
Kernel  Purification  Estimation  Graphics processing units  Perturbation methods  Electric breakdown  Training  Graph neural networks  defense  execution semantic  execution pattern  overhead  
Multi-Node Acceleration for Large-Scale GCNs 期刊论文
IEEE TRANSACTIONS ON COMPUTERS, 2022, 卷号: 71, 期号: 12, 页码: 3140-3152
作者:  Sun, Gongjian;  Yan, Mingyu;  Wang, Duo;  Li, Han;  Li, Wenming;  Ye, Xiaochun;  Fan, Dongrui;  Xie, Yuan
收藏  |  浏览/下载：36/0  |  提交时间：2023/07/12
Deep learning  graph neural network  hardware accelerator  multi-node system  communication optimization  
Characterizing and Understanding HGNNs on GPUs 期刊论文
IEEE COMPUTER ARCHITECTURE LETTERS, 2022, 卷号: 21, 期号: 2, 页码: 69-72
作者:  Yan, Mingyu;  Zou, Mo;  Yang, Xiaocheng;  Li, Wenming;  Ye, Xiaochun;  Fan, Dongrui;  Xie, Yuan
收藏  |  浏览/下载：35/0  |  提交时间：2022/12/07
Kernel  Semantics  Aggregates  Mercury (metals)  Motion pictures  Graphics processing units  Electric breakdown  Heterogeneous graph neural networks  GNNs  characterization  execution semantic  execution pattern  
An efficient scheduling algorithm for dataflow architecture using loop-pipelining 期刊论文
INFORMATION SCIENCES, 2021, 卷号: 547, 页码: 1136-1153
作者:  Li, Yi;  Wu, Meng;  Ye, Xiaochun;  Li, Wenming;  Xue, Rui;  Wang, Da;  Zhang, Hao;  Fan, Dongrui
收藏  |  浏览/下载：47/0  |  提交时间：2021/12/01
Dataflow architecture  Instruction scheduling  Multicast  Sharing path  Loop optimization  
Hardware Acceleration for GCNs via Bidirectional Fusion 期刊论文
IEEE COMPUTER ARCHITECTURE LETTERS, 2021, 卷号: 20, 期号: 1, 页码: 4
作者:  Li, Han;  Yan, Mingyu;  Yang, Xiaocheng;  Deng, Lei;  Li, Wenming;  Ye, Xiaochun;  Fan, Dongrui;  Xie, Yuan
收藏  |  浏览/下载：44/0  |  提交时间：2021/12/01
Random access memory  Computational modeling  Analytical models  Hardware  Engines  Computer architecture  Transforms  Graph convolutional neural networks  hardware accelerator  bidirectional execution  inter-phase fusion  
PIM-WEAVER: A High Energy-efficient, General-purpose Acceleration Architecture for String Operations in Big Data Processing 期刊论文
SUSTAINABLE COMPUTING-INFORMATICS & SYSTEMS, 2019, 卷号: 21, 页码: 129-142
作者:  Li, Wenming;  Ye, Xiaochun;  Wang, Da;  Zhang, Hao;  Tang, Zhimin;  Fan, Dongrui;  Sun, Ninghui
收藏  |  浏览/下载：147/0  |  提交时间：2019/08/16
PIM  String operations  Acceleration architecture  Big data  HMC