中文版 | English

在结果中检索

CSpace

浏览/检索结果: 共193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：3/0  |  提交时间：2024/05/20
Tensor engine  Convolution  Scalable architecture  CPU-centric  Utilization  
Mortar-FP8: Morphing the Existing FP32 Infrastructure for High-Performance Deep Learning Acceleration 期刊论文
IEEE TRANSACTIONS ON COMPUTER-AIDED DESIGN OF INTEGRATED CIRCUITS AND SYSTEMS, 2024, 卷号: 43, 期号: 3, 页码: 878-891
作者:  Li, Hongyan;  Lu, Hang;  Li, Xiaowei
收藏  |  浏览/下载：2/0  |  提交时间：2024/05/20
Deep learning accelerator  deep neural network (DNN)  fp8 format  
Real-Time Robust Video Object Detection System Against Physical-World Adversarial Attacks 期刊论文
IEEE TRANSACTIONS ON COMPUTER-AIDED DESIGN OF INTEGRATED CIRCUITS AND SYSTEMS, 2024, 卷号: 43, 期号: 1, 页码: 366-379
作者:  Han, Husheng;  Hu, Xing;  Hao, Yifan;  Xu, Kaidi;  Dang, Pucheng;  Wang, Ying;  Zhao, Yongwei;  Du, Zidong;  Guo, Qi;  Wang, Yanzhi;  Zhang, Xishan;  Chen, Tianshi
收藏  |  浏览/下载：3/0  |  提交时间：2024/05/20
Object detection  Streaming media  Optical flow  Feature extraction  Real-time systems  Task analysis  Detectors  Adversarial patch attack  deep learning security  domain-specific accelerator  hardware/software co-design  real time  
JANM-IK: Jacobian Argumented Nelder-Mead Algorithm for Inverse Kinematics and its Hardware Acceleration 期刊论文
IEEE COMPUTER ARCHITECTURE LETTERS, 2024, 卷号: 23, 期号: 1, 页码: 45-48
作者:  Yang, Yuxin;  Chen, Xiaoming;  Han, Yinhe
收藏  |  浏览/下载：2/0  |  提交时间：2024/05/20
Robotics  inverse kinematics  Jacobian  nelder-mead  software-hardware co-design  accelerator  
Mathematical Framework for Optimizing Crossbar Allocation for ReRAM-based CNN Accelerators 期刊论文
ACM TRANSACTIONS ON DESIGN AUTOMATION OF ELECTRONIC SYSTEMS, 2024, 卷号: 29, 期号: 1, 页码: 24
作者:  Li, Wanqian;  Han, Yinhe;  Chen, Xiaoming
收藏  |  浏览/下载：2/0  |  提交时间：2024/05/20
ReRAM crossbars  CNN accelerator  mathematical framework  crossbar allocation  
Frequency-Domain Inference Acceleration for Convolutional Neural Networks Using ReRAMs 期刊论文
IEEE TRANSACTIONS ON PARALLEL AND DISTRIBUTED SYSTEMS, 2023, 卷号: 34, 期号: 12, 页码: 3133-3146
作者:  Liu, Bosheng;  Jiang, Zhuoshen;  Wu, Yalan;  Wu, Jigang;  Chen, Xiaoming;  Liu, Peng;  Zhou, Qingguo;  Han, Yinhe
收藏  |  浏览/下载：8/0  |  提交时间：2023/12/04
Frequency-domain accelerator  energy efficiency  resistive random access memory  frequency-domain convolutions  
Poseidon-NDP: Practical Fully Homomorphic Encryption Accelerator Based on Near Data Processing Architecture 期刊论文
IEEE TRANSACTIONS ON COMPUTER-AIDED DESIGN OF INTEGRATED CIRCUITS AND SYSTEMS, 2023, 卷号: 42, 期号: 12, 页码: 4749-4762
作者:  Yang, Yinghao;  Lu, Hang;  Li, Xiaowei
收藏  |  浏览/下载：6/0  |  提交时间：2024/05/20
FPGA accelerator  fully homomorphic encryption (FHE)  near data processing (NDP)  privacy computing  
Hardware Acceleration for SLAM in Mobile Systems 期刊论文
JOURNAL OF COMPUTER SCIENCE AND TECHNOLOGY, 2023, 卷号: 38, 期号: 6, 页码: 1300-1322
作者:  Fan, Zhe;  Hao, Yi-Fan;  Zhi, Tian;  Guo, Qi;  Du, Zi-Dong
收藏  |  浏览/下载：2/0  |  提交时间：2024/05/20
hardware accelerator  instruction set  mobile system  simultaneous localization and mapping (SLAM) algorithm  
A Coordinated Model Pruning and Mapping Framework for RRAM-Based DNN Accelerators 期刊论文
IEEE TRANSACTIONS ON COMPUTER-AIDED DESIGN OF INTEGRATED CIRCUITS AND SYSTEMS, 2023, 卷号: 42, 期号: 7, 页码: 2364-2376
作者:  Qu, Songyun;  Li, Bing;  Zhao, Shixin;  Zhang, Lei;  Wang, Ying
收藏  |  浏览/下载：7/0  |  提交时间：2023/12/04
AutoML  bit-pruning  deep neural networks (DNNs)  resistive random access memory (RRAM)  
Accelerating Deformable Convolution Networks with Dynamic and Irregular Memory Accesses 期刊论文
ACM TRANSACTIONS ON DESIGN AUTOMATION OF ELECTRONIC SYSTEMS, 2023, 卷号: 28, 期号: 4, 页码: 23
作者:  Chu, Cheng;  Liu, Cheng;  Xu, Dawen;  Wang, Ying;  Luo, Tao;  Li, Huawei;  Li, Xiaowei
收藏  |  浏览/下载：7/0  |  提交时间：2023/12/04
Deformable convolution network  neural network accelerator  irregular memory access  runtime tile scheduling