检索结果-内蒙古大学图书馆

Understanding co-run performance on CPU-GPU integrated processors： observations, insights, directions

Frontiers of computer science 2017年第1期11卷 130-146页

作者： Qi ZHU Bo WU Xipeng SHEN Kai SHEN Li SHEN Zhiying WANG National Key Laboratory of High Performance Computing National University of Defense Technology Changsha 410073 China Department of Computer Science North Carolina State University Raleigh NC 27695 USA Department of Electrical Engineering & Computer Science Colorado School of Mines Golden CO 80401 USA Department of Computer Science University of Rochester Rochester NY 14627 USA

Recent years have witnessed a processor develop- ment trend that integrates central processing unit （CPU） and graphic processing unit （GPU） into a single chip. The inte- gration helps to save some host-device data copying that a discrete GPU usually requires, but also introduces deep re- source sharing and possible interference between CPU and GPU. This work investigates the performance implications of independently co-running CPU and GPU programs on these platforms. First, we perform a comprehensive measurement that covers a wide variety of factors, including processor ar- chitectures, operating systems, benchmarks, timing mecha- nisms, inputs, and power management schemes. These mea- surements reveal a number of surprising observations. We an- alyze these observations and produce a list of novel insights, including the important roles of operating system （OS） con- text switching and power management in determining the program performance, and the subtle effect of CPU-GPU data copying. Finally, we confirm those insights through case studies, and point out some promising directions to mitigate anomalous performance degradation on integrated heteroge- neous processors.

关键词： performance analysis GPGPU co-run degrada-tion fused processor program transformation

来源：评论

学校读者我要写书评

暂无评论

Trusted dynamic level scheduling based on Bayes trust model

引用

science in China(Series F) 2007年第3期50卷 456-469页

作者： WANG Wei ZENG GuoSun Department of Computer Science and Engineering Tongji University Shanghai 201804 China Tongji Branch National Engineering & Technology Center of High Performance Computer Shanghai 201804 China

A kind of trust mechanism-based task scheduling model was presented. Referring to the trust relationship models of social persons, trust relationship is built among Grid nodes, and the trustworthiness of nodes is evaluated by utilizing the Bayes method. Integrating the trustworthiness of nodes into a Dynamic Level Scheduling （DLS） algorithm, the Trust-Dynamic Level Scheduling （Trust-DLS） algorithm is proposed. Theoretical analysis and simulations prove that the Trust-DLS algorithm can efficiently meet the requirement of Grid tasks in trust, sacrificing fewer time costs, and assuring the execution of tasks in a security way in Grid environment.

关键词： Grid computing trustworthy scheduling Bayes method trustworthiness evaluation Trust-DLS

来源：评论

学校读者我要写书评

暂无评论

A Real-time Relaxed Garbage Collection in DSM

引用

电子学报(英文版) 2007年第1期16卷 7-12页

作者： WU Junmin SONG Zhenhua Anhui Province Co-Key Laboratory of High Performance Computing and Application Department of Computer Science ＆ Technology University of Science ＆ Technology of China Hefei 230027 China

Garbage collection is a memory management mechanism for automatically reclaiming garbage objects in memory. It can effectively relieve the programmers' burden and optimize the design of programs. Currently many garbage collection methods for distributed systems have been put forth as the distributed systems are more and more popular. Relaxed consistency model is a very important kind of memory consistency model in distributed system, but it is inefficiently to perform garbage collection in the Distributed shared memory system (DSM) on relaxed memory model with traditional methods. This article proposes a trace-based garbage collection algorithm for DSM system based on relaxed memory model. Our algorithm notes the references among active objects of every node in DSM system, which makes the application process and the collection process able to execute concurrently. And it makes use of the relaxed consistency model's features to reduce communication cost and response delay. Furthermore, the use of two tables insures the algorithm correct and effective. This algorithm displays its advantages of real-time and incremental, and it is proved to be correct and effective.

关键词：垃圾回收算法分布式共享存储系统实时弱一致性模型 DSM

来源：评论

学校读者我要写书评

暂无评论

F2UE-NET: An Uncertainty-Driven Dynamic Expert Network for Long-Tail Retinal Disease Classification

F2UE-NET: An Uncertainty-Driven Dynamic Expert Network for L...

引用

IEEE International Symposium on Biomedical Imaging

作者： Junyong Zhao Tian Lin Meng Wang Liang Sun Haoyu Chen Daoqiang Zhang Huazhu Fu MOE Key Laboratory of Brain Computer Intelligence Technology College of Artificial Intelligence Nanjing University of Aeronautics and Astronautics Nanjing China Joint Shantou International Eye Center Shantou University and the Chinese University of Hong Kong Shantou Guangdong China Department of Ophthalmology Yong Loo Lin School of Medicine National University of Singapore Singapore Singapore Agency for Science Technology and Research (A*STAR) Institute of High Performance Computing (IHPC) Singapore Singapore

ISBN: (数字)9798331520526

ISBN: (纸本)9798331520533

The automatic diagnosis of retinal diseases presents a significant challenge in medical image analysis, primarily due to the long-tail distribution in existing retinal datasets. This imbalance creates substantial difficulties in model training and performance. To address this issue, we propose an uncertainty-driven dynamic expert network for long-tail retinal disease classification, called $\mathrm{F}^{2}\text{UE}$ -Net. Specifically, we apply Low-Rank Adaptation (LoRA) technology to fine-tune the foundation model, enhancing its feature extraction capabilities and overall performance. Additionally, we introduce an uncertainty-driven dynamic expert participation strategy, which assigns appropriate weights to different categories during training, ensuring high accuracy even for rare, tail-end diseases. Experimental results on a long-tail fundus disease dataset demonstrate that $\mathrm{F}^{2}$ UE outperforms state-of-the-art methods in long-tail retinal disease classification.

关键词： Training Heavily-tailed distribution Image analysis Foundation models Biological system modeling Tail Retina Feature extraction Medical diagnostic imaging Diseases

来源：评论

学校读者我要写书评

暂无评论

Parallel architecture and optimization for discrete-event simulation of spike neural networks

引用

science China(Technological sciences) 2013年第2期56卷 509-517页

作者： TANG YuHua ZHANG BaiDa WU JunJie HU TianJiang ZHOU Jing LIU FuDong Department of Computer Science and Technology School of ComputerNational University of Defense Technology State Key Laboratory of High Performance Computing National University of Defense Technology College of Mechatronic Engineering and Automation National University of Defense Technology

Spike neural networks are inspired by animal brains,and outperform traditional neural networks on complicated ***,spike neural networks are usually used on a large scale,and they cannot be computed on commercial,off-the-shelf computers.A parallel architecture is proposed and developed for discrete-event simulations of spike neural ***,mechanisms for both parallelism degree estimation and dynamic load balance are emphasized with theoretical and computational *** results show the effectiveness of the proposed parallelized spike neural network system and its corresponding support components.

关键词： spike neural network discrete event simulation intelligent parallelization framework

来源：评论

学校读者我要写书评

暂无评论

Protect You More Than Blank: Anti-Learning Sensitive User Information in the Social Networks

引用

Journal of computer science & Technology 2014年第5期29卷 762-776页

作者：袁明轩陈雷 Philip S. Yu 梅宏 Department of Computer Science and Engineering The Hong Kong University of Science and Technology Huawei Noah's Ark Laboratory Department of Computer Science University of Illinois at ChicagoChicago IL 60637 U.S.A. FellowACMIEEE Key Laboratory of High Confidence Software Technologies Ministry of Education Institute of Software School of Electronics Engineering and Computer Science Peking University Department of Computer Science and Engineering Shanghai Jiao Tong University

Social networks are getting more and more attention in recent years. People join social networks to share their information with others. However, due to the different cultures and backgrounds, people have different requirements on what kind of information should be published. Currently, when social network websites publish data, they just leave the information that a user feels sensitive blank. This is not enough due to the existence of the label-structure relationship. A group of analyzing algorithms can be used to learn the blank information with high accuracy. In this paper, we propose a personalized model to protect private information in social networks. Specifically, we break the label-structure association by slightly changing the edges in some users＇ neighborhoods. More importantly, in order to increase the usability of the published graph, we also preserve the influence value of each user during the privacy protection. We verify the effectiveness of our methods through extensive experiments. The results show that the proposed methods can protect sensitive labels against learning algorithms and at the same time, preserve certain graph utilities.

关键词： social network privacy protection

来源：评论

学校读者我要写书评

暂无评论

Multi-Agent Reinforcement Learning in Wireless Distributed Networks for 6G

arXiv

引用

arXiv 2025年

作者： Zhang, Jiayi Liu, Ziheng Zhu, Yiyang Shi, Enyu Xu, Bokai Yuen, Chau Niyato, Dusit Debbah, Mérouane Jin, Shi Ai, Bo Shen, Xuemin School of Electronic and Information Engineering The Frontiers Science Center for Smart High-Speed Railway System Beijing jiaotong University Beijing100044 China School of Electrical and Electronics Engineering Nanyang Technological University 639798 Singapore College of Computing and Data Science Nanyang Technological University 639798 Singapore KU 6G Research Center Department of Computer and Information Engineering Khalifa University Abu Dhabi127788 United Arab Emirates CentraleSupelec University Paris-Saclay Gif-sur-Yvette91192 France National Mobile Communications Research Laboratory Southeast University Nanjing210096 China Department of Electrical and Computer Engineering University of Waterloo WaterlooONN2L 3G1 Canada

The introduction of intelligent interconnectivity between the physical and human worlds has attracted great attention for future sixth-generation (6G) networks, emphasizing massive capacity, ultra-low latency, and unparalleled reliability. Wireless distributed networks and multi-agent reinforcement learning (MARL), both of which have evolved from centralized paradigms, are two promising solutions for the great attention. Given their distinct capabilities, such as decentralization and collaborative mechanisms, integrating these two paradigms holds great promise for unleashing the full power of 6G, attracting significant research and development attention. This paper provides a comprehensive study on MARL-assisted wireless distributed networks for 6G. In particular, we introduce the basic mathematical background and evolution of wireless distributed networks and MARL, as well as demonstrate their interrelationships. Subsequently, we analyze different structures of wireless distributed networks from the perspectives of homogeneous and heterogeneous. Furthermore, we introduce the basic concepts of MARL and discuss two typical categories, including model-based and model-free. We then present critical challenges faced by MARL-assisted wireless distributed networks, providing important guidance and insights for actual implementation. We also explore an interplay between MARL-assisted wireless distributed networks and emerging techniques, such as information bottleneck and mirror learning, delivering in-depth analyses and application scenarios. Finally, we outline several compelling research directions for future MARL-assisted wireless distributed networks. Copyright © 2025, The Authors. All rights reserved.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

AMPCliff: Quantitative definition and benchmarking of activity cliffs in antimicrobial peptides

引用

Journal of Advanced Research 2025年

作者： Li, Kewei Wu, Yuqian Li, Yinheng Guo, Yutong Kong, Yanwen Wang, Yan Liang, Yiyang Fan, Yusi Huang, Lan Zhang, Ruochi Zhou, Fengfeng College of Computer Science and Technology Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University Jilin Changchun 130012 China School of Software Jilin University Jilin Changchun 130012 China School of Life Sciences Jilin University Jilin Changchun 130012 China Department of Computer Science Columbia University 116th and Broadway New York City 10027 NY United States School of Artificial Intelligence Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University Jilin Changchun 130012 China School of Biology and Engineering Guizhou Medical University Guizhou Guiyang 550025 China School of Computer Engineering Changchun University of Engineering Jilin Changchun 130103 China Changchun Wenli High School Jilin Changchun 130062 China

Introduction: Activity cliff (AC) is a phenomenon that a pair of similar molecules differ by a small structural alternation but exhibit a large difference in their biochemical activities. This phenomenon affects various tasks ranging from virtual screening to lead optimization in drug development. The AC of small molecules has been extensively investigated but limited knowledge is accumulated about the AC phenomenon in pharmaceutical peptides with canonical amino acids. Objectives: This study introduces a quantitative definition and benchmarking framework AMPCliff for the AC phenomenon in antimicrobial peptides (AMPs) composed by canonical amino acids. Methods: This study establishes a benchmark dataset of paired AMPs in Staphylococcus aureus from the publicly available AMP dataset GRAMPA, and conducts a rigorous procedure to evaluate various AMP AC prediction models, including nine machine learning, four deep learning algorithms, four masked language models, and four generative language models. Results: A comprehensive analysis of the existing AMP dataset reveals a significant prevalence of AC within AMPs. AMPCliff quantifies the activities of AMPs by the metric minimum inhibitory concentration (MIC), and defines 0.9 as the minimum threshold for the normalized BLOSUM62 similarity score between a pair of aligned peptides with at least two-fold MIC changes. Our analysis reveals that these models are capable of detecting AMP AC events and the pre-trained protein language model ESM2 demonstrates superior performance across the evaluations. The predictive performance of AMP activity cliffs remains to be further improved, considering that ESM2 with 33 layers only achieves the Spearman correlation coefficient 0.4669 for the regression task of the −log(MIC) values on the benchmark dataset. Conclusion: Our findings highlight limitations in current deep learning-based representation models. To more accurately capture the properties of antimicrobial peptides (AMPs), it is ess

关键词： Activity cliff (AC) AMPCliff Antimicrobial peptide (AMP) Benchmark Minimum inhibitory concentration (MIC)

来源：评论

学校读者我要写书评

暂无评论

iMashup:a mashup-based framework for service composition

引用

science China(Information sciences) 2014年第1期57卷 5-24页

作者： LIU XuanZhe HUANG Gang ZHAO Qi MEI Hong BLAKE M.Brian Key Laboratory of High Confidence Software Technologies (Peking University) Ministry of Education School of Electronics Engineering and Computer Science Peking University Department of Computer Science and Engineering University of Notre Dame

The Web has undergone a tremendous change from a primarily publication platform towards a participatory and"programmable"platform,where a large number of heterogeneous Web-delivered services(including SOAP and RESTful Web services,RSS and Atom feeds)are *** results in the creation of Web mashup applications with rich user ***,the integration of Web-delivered services is still a challenging *** not only requires the developers’tedious eforts in understanding and coordinating heterogeneous service types,but also results in the time-consuming development of user *** this paper,we propose the iMashup composition framework to facilitate mashup development and *** provide a unified mashup component model for the common representation of heterogeneous Web-delivered service *** component model specifies necessary properties and behaviors at both business and user interface *** associate the component model with semantically meaningful tags,so that mashup developers can fast understand the service *** mashup developers can search and put the proper mashup components into the Web browser based composition environment,and connect them by data flows based on the tag-based *** an integration manner might prevent some low-level programming eforts and improve the composition efciency.A series of experimental study are conducted to evaluate our framework.

关键词： service composition mashup component model Web-delivered service

来源：评论

学校读者我要写书评

暂无评论

Integrated research of parallel computing:Status and future

引用

Chinese science Bulletin 2009年第11期54卷 1845-1853页

作者： CHEN GuoLiang SUN GuangZhong XU Yun LONG Bai Department of Computer Science and Technology University of Science and Technology of China National High PerformanceComputing Center Anhui Key Laboratory of High Performance Computing Hefei 230027 China

In the past twenty years, the research group in University of science and Technology of China has de-veloped an integrated research method for parallel computing, which is a combination of "Architecture-Algorithm-Programming-Application" . This method is also called the ecological environment of parallel computing research. In this paper, we survey the current status of integrated research method for par-allel computing and by combining the impact of multi-core systems, cloud computing and personal high performance computer, we present our outlook on the future development of parallel computing.

关键词：并行计算综合研究方法高性能计算机科学技术生态环境核系统编程算法

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：