中文版 | English

在结果中检索

CSpace

浏览/检索结果: 共15条，第1-10条 帮助

限定条件        
已选(0)清除 条数/页：   排序方式：
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  
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  
BitXpro: Regularity-Aware Hardware Runtime Pruning for Deep Neural Networks 期刊论文
IEEE TRANSACTIONS ON VERY LARGE SCALE INTEGRATION (VLSI) SYSTEMS, 2023, 卷号: 31, 期号: 1, 页码: 90-103
作者:  Li, Hongyan;  Lu, Hang;  Wang, Haoxuan;  Deng, Shengji;  Li, Xiaowei
收藏  |  浏览/下载：13/0  |  提交时间：2023/07/12
Deep learning accelerator  deep neural network (DNN)  hardware runtime pruning  
An Efficient Deep Learning Accelerator Architecture for Compressed Video Analysis 期刊论文
IEEE TRANSACTIONS ON COMPUTER-AIDED DESIGN OF INTEGRATED CIRCUITS AND SYSTEMS, 2022, 卷号: 41, 期号: 9, 页码: 2808-2820
作者:  Wang, Yongchen;  Wang, Ying;  Li, Huawei;  Li, Xiaowei
收藏  |  浏览/下载：31/0  |  提交时间：2022/12/07
Streaming media  Neural networks  Image coding  Decoding  Metadata  Deep learning  Hardware  Neural network acceleration  specialized accelerator  video analysis  
Saving Energy of RRAM-Based Neural Accelerator Through State-Aware Computing 期刊论文
IEEE TRANSACTIONS ON COMPUTER-AIDED DESIGN OF INTEGRATED CIRCUITS AND SYSTEMS, 2022, 卷号: 41, 期号: 7, 页码: 2115-2127
作者:  He, Yintao;  Wang, Ying;  Li, Huawei;  Li, Xiaowei
收藏  |  浏览/下载：28/0  |  提交时间：2022/12/07
Computer architecture  Microprocessors  Resistance  Power demand  Training  Biological neural networks  Optimization  Low power (LP)  neural networks  processing-in-memory  resistive random-access memory (RRAM)  
A Fast Precision Tuning Solution for Always-On DNN Accelerators 期刊论文
IEEE TRANSACTIONS ON COMPUTER-AIDED DESIGN OF INTEGRATED CIRCUITS AND SYSTEMS, 2022, 卷号: 41, 期号: 5, 页码: 1236-1248
作者:  Wang, Ying;  He, Yintao;  Cheng, Long;  Li, Huawei;  Li, Xiaowei
收藏  |  浏览/下载：25/0  |  提交时间：2022/12/07
Computer architecture  Neural networks  Computational modeling  Approximate computing  Tuning  Switches  Microprocessors  Always-on  CNN  computing-in-memory (CiM)  resistive RAM  
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：38/0  |  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  
An Edge 3D CNN Accelerator for Low-Power Activity Recognition 期刊论文
IEEE TRANSACTIONS ON COMPUTER-AIDED DESIGN OF INTEGRATED CIRCUITS AND SYSTEMS, 2021, 卷号: 40, 期号: 5, 页码: 918-930
作者:  Wang, Ying;  Wang, Yongchen;  Shi, Cong;  Cheng, Long;  Li, Huawei;  Li, Xiaowei
收藏  |  浏览/下载：37/0  |  提交时间：2021/12/01
Three-dimensional displays  Two dimensional displays  Arrays  Feature extraction  System-on-chip  Redundancy  3D CNN  activity analysis  CNN accelerator  network-on-chip  video  
Architecting Effectual Computation for Machine Learning Accelerators 期刊论文
IEEE TRANSACTIONS ON COMPUTER-AIDED DESIGN OF INTEGRATED CIRCUITS AND SYSTEMS, 2020, 卷号: 39, 期号: 10, 页码: 2654-2667
作者:  Lu, Hang;  Zhang, Mingzhe;  Han, Yinhe;  Wang, Qi;  Li, Huawei;  Li, Xiaowei
收藏  |  浏览/下载：88/0  |  提交时间：2020/12/10
Computational modeling  Throughput  Adders  Machine learning  Acceleration  Kernel  Computational efficiency  Accelerator architectures  neural network hardware  multiplying circuits  
Accelerating DNN-based 3D point cloud processing for mobile computing 期刊论文
SCIENCE CHINA-INFORMATION SCIENCES, 2019, 卷号: 62, 期号: 11, 页码: 11
作者:  Liu, Bosheng;  Chen, Xiaoming;  Han, Yinhe;  Li, Jiajun;  Xu, Haobo;  Li, Xiaowei
收藏  |  浏览/下载：225/0  |  提交时间：2019/12/10
deep neural network acceleration  point cloud data  neighbor point search  mobile robotics  hardware architecture