检索结果-内蒙古大学图书馆

Proceedings of the 18th USENIX Conference on Operating systems Design and Implementation

作者： Hanze Zhang Ke Cheng Rong Chen Haibo Chen Institute of Parallel and Distributed Systems SEIEE Shanghai Jiao Tong University and Shanghai AI Laboratory and MoE Key Lab of Artificial Intelligence AI Institute Shanghai Jiao Tong University Institute of Parallel and Distributed Systems SEIEE Shanghai Jiao Tong University and Engineering Research Center for Domain-specific Operating Systems Ministry of Education China Institute of Parallel and Distributed Systems SEIEE Shanghai Jiao Tong University and Shanghai AI Laboratory and Engineering Research Center for Domain-specific Operating Systems Ministry of Education China Institute of Parallel and Distributed Systems SEIEE Shanghai Jiao Tong University and Engineering Research Center for Domain-specific Operating Systems Ministry of Education China and Key Laboratory of System Software (Chinese Academy of Sciences)

ISBN: (纸本)9781939133403

distributed lock services are extensively utilized in distributed systems to serialize concurrent accesses to shared resources. The need for fast and scalable lock services has become more pronounced with decreasing task execution times and expanding dataset scales. However, traditional lock managers, reliant on server CPUs to handle lock requests, experience significant queuing delays in lock grant latency. Advanced network hardware (e.g. programmable switches) presents an avenue to manage locks without queuing delays due to their high packet processing power. Nevertheless, their constrained memory capacity restricts the manageable lock scale, thereby limiting their effect in large-scale *** paper presents FISSLOCK, a fast and scalable distributed lock service that exploits the programmable switch to improve (tail) latency and peak throughput for millions of locks. The key idea behind FISSLOCK is the concept of lock fission, which decouples lock management into grant decision and participant maintenance. FISSLOCK leverages the programmable switch to decide lock grants synchronously and relies on servers to maintain participants (i.e., holders and waiters) asynchronously. By using the programmable switch for routing, FISSLOCK enables on-demand fine-grained lock migration, thereby reducing the lock grant and release delays. FISSLOCK carefully designs and implements grant decision procedure on the programmable switch, supporting over one million locks. Evaluation using various benchmarks and a real-world application shows the efficiency of FISSLOCK. Compared to the state-of-the-art switch-based approach (NetLock), FISSLOCK cuts up to 79.1% (from 43.0%) of median lock grant time in the microbenchmark and improves transaction throughput for TATP and TPC-C by 1.76× and 2.28×, respectively.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An End-to-End Classification Network Model Based on Hybrid Supervision for Industrial Surface Defect Detection

引用

International Journal of Pattern Recognition and Artificial Intelligence 2025年第5期39卷

作者： Qin, Runbing Chen, Ningjiang Gan, Shukun Guangxi University School of Computer Electronics and Information Nanning530004 China Education Department of Guangxi Zhuang Autonomous Region Key Laboratory of Parallel Distributed and Intelligent Computing Guangxi University Nanning530004 China Guangxi Intelligent Digital Services Research Center of Engineering Technology Nanning530004 China

Industrial part surface defect detection aims to precisely locate defects in images, which is crucial for quality control in manufacturing. The traditional method needs to be designed in advance, but it has shortcomings in terms of generalization ability. Deep neural network-based defect detection faces issues such as low resolution, data scarcity, labeling costs, and high computation. Therefore, an improved solution is necessary to enhance industrial product quality control efficiency and accuracy. A new method is proposed that utilizes end-to-end training of a two-stage neural network based on segmentation with an extended training process. The gradient flow from the classification to the segmentation network is adjusted to prevent unstable features from interfering with learning. To address the problem of image oversampling and undersampling during training, a frequency sampling scheme for negative samples is introduced. Additionally, positive pixels in the region-based segmentation mask are weighted using the distance transform algorithm so that regions with a high probability of defects can be detected without detailed annotation. Experiments are conducted across three distinct defect datasets by applying hybrid supervision encompassing diverse conditions. In the optimal case, the AP rate of the proposed model on the DAGM and KolektorSDD datasets reaches 100%, and the AP rate on the Severstal Steel dataset reaches 98.99%. The experiments’ results show that the detection accuracy has improved greatly, showing how well the proposed method works in the industry. © 2025 World Scientific Publishing Company.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Addressing Activation Outliers in LLMs: A Systematic Review of Post-Training Quantization Techniques

引用

IEEE Access 2025年 13卷 81917-81932页

作者： Patrik Czakó Gábor Kertész Sándor Szénási Doctoral School of Applied Informatics and Applied Mathematics Óbuda University Budapest Hungary John von Neumann Faculty of Informatics Óbuda University Budapest Hungary Laboratory of Parallel and Distributed Systems Institute for Computer Science and Control (SZTAKI) Hungarian Research Network (HUN-REN) Budapest Hungary Faculty of Economics and Informatics J. Selye University Komárno Slovakia

Large Language Models (LLMs) have transformed natural language processing, yet their deployment remains challenging due to substantial computational, memory, and energy demands. Post-training quantization has emerged as a key strategy for enabling efficient inference, particularly in resource-constrained settings. This systematic review focuses on weight-activation quantization, with a unique emphasis on the emergent outlier phenomenon in LLM activations. This work evaluates recent techniques that mitigate activation outliers and improve quantization efficiency, distinguishing itself from prior reviews. Using the PRISMA methodology, we examine 52 recent studies to uncover key trends and evaluate the effectiveness of different approaches. By synthesizing insights from these works, this review presents a diverse set of techniques and their implications for activation quantization, laying the groundwork for future research and practical advancements in LLM deployment.

关键词： Quantization (signal) Computational modeling Throughput Arithmetic Decoding Adaptation models Transformers Systematics Systematic literature review Large language models

来源：评论

学校读者我要写书评

暂无评论

ConvoyLLM: Dynamic Multi-Lane Convoy Control Using LLMs

arXiv

引用

arXiv 2025年

作者： Lu, Liping He, Zhican Chu, Duanfeng Wang, Rukang Peng, Saiqian Zhou, Pan School of Computer Science and Artificial Intelligence Wuhan University of Technology Wuhan430070 China Intelligent Transportation Systems Research Center Wuhan University of Technology Wuhan430070 China Hubei Key Laboratory of Distributed System Security School of Cyber Science and Engineering Huazhong University of Science and Technology Wuhan430074 China

This paper proposes a novel method for multi-lane convoy formation control that uses large language models (LLMs) to tackle coordination challenges in dynamic highway environments. Each connected and autonomous vehicle in the convoy uses a knowledge-driven approach to make real-time adaptive decisions based on various scenarios. Our method enables vehicles to dynamically perform tasks, including obstacle avoidance, convoy joining/leaving, and escort formation switching, all while maintaining the overall convoy structure. We design a Interlaced formation control strategy based on locally dynamic distributed graphs, ensuring the convoy remains stable and flexible. We conduct extensive experiments in the SUMO simulation platform across multiple traffic scenarios, and the results demonstrate that the proposed method is effective, robust, and adaptable to dynamic environments. The code is available at: https://***/chuduanfeng/ConvoyLLM . Copyright © 2025, The Authors. All rights reserved.

关键词： Autonomous vehicles

来源：评论

学校读者我要写书评

暂无评论

Virtual memory support for OR-parallel logic programming systems 3rd

引用

3rd International Conference on parallel Architectures and Languages Europe, PARLE 1991

作者： Véron, André Xu, Jiyang Delgado-Rannauro, S.A. Schuerman, K. Distributed and Parallel Systems Group European Computer-Industry Research Center Arabellastr. 17 München 81D-8000 Germany

ISBN: (纸本)9783540541523

Most previous parallel logic programming systems have been built on top of classical operating systems. The advances in the area of parallel operating systems have made it possible to explore new execution models that take advantage of their features. In this paper we propose a family of execution models (VM,VMBA,VMHW) that make use of the new virtual memory technologies such as copy-on-write, memory inheritance, and distributed shared memory. Preliminary results from our implementations and simulations are reported. © Springer-Verlag Berlin Heidelberg 1991.

关键词： computer circuits

来源：评论

学校读者我要写书评

暂无评论

PDRL-CM: An efficient cooperative caching management method for vehicular networks based on deep reinforcement learning

引用

Ad Hoc Networks 2025年 176卷

作者： Pingjie Ou Ningjiang Chen Long Yang School of Computer and Electronic Information Guangxi University Nanning 530004 Guangxi China Key Laboratory of Parallel Distributed and Intelligent Computing Education Department of Guangxi Zhuang Autonomous Region Nanning 530004 Guangxi China The Guangxi Intelligent Digital Services Research Center of Engineering Technology Nanning 530004 Guangxi China

In vehicular networks, onboard devices face the challenge of limited storage, and computational resources constrain their processing and storage capabilities. This limitation is particularly significant for applications that require complex computations and real-time responses. Additionally, limited storage capacity reduces the range of cacheable data, which can impact the immediate availability of data and the continuity of services. Therefore, improving cache utilization and meeting vehicles’ real-time data demands pose significant challenges. Deep reinforcement learning can optimize the issues arising from agents’ continuously changing state and action spaces due to increasing request demands. However, training the network may encounter instability and convergence difficulties in dynamic and complex environments or situations with sparse rewards. In response to these issues, this paper proposes a Priority-based Deep Reinforcement Learning Collaborative Cache Management method (PDRL-CM). PDRL-CM first designs a lightweight cache admission strategy that leverages data’s inherent and combined attributes. It then makes cache admission decisions Using Monte Carlo sampling and a max-value search strategy combined with a feedforward neural network. Secondly, the method considers minimizing system latency and reducing vehicle energy consumption as joint optimization problems. An improved deep reinforcement learning algorithm solves this problem and makes cache-sharding decisions. A prioritized experience replay mechanism is incorporated to adjust the network prediction model quickly and accelerate the convergence process. Experimental results indicate that, compared to existing DRL-based caching methods, PDRL-CM offers faster data processing efficiency and higher cache hit rates under varying vehicle density, storage capacity, and content volume conditions.

关键词： Cache memory

来源：评论

学校读者我要写书评

暂无评论

Personalized gesture interactions for cyber-physical smart-home environments

引用

Science China(Information Sciences) 2017年第7期60卷 144-158页

作者： Yihua LOU Wenjun WU Radu-Daniel VATAVU Wei-Tek TSAI State Key Laboratory of Software Development Environment Beihang University Mint Viz Research Lab Integrated Center for Research Developmentand Innovation in Advanced MaterialsNanotechnologies and Distributed Systems for Fabrication and Control (MANSiD) & Department of Computer Science University Stefan cel Mare of Suceava

A gesture-based interaction system for smart homes is a part of a complex cyber-physical environment, for which researchers and developers need to address major challenges in providing personalized gesture interactions. However, current research efforts have not tackled the problem of personalized gesture recognition that often involves user identification. To address this problem, we propose in this work a new event-driven service-oriented framework called gesture services for cyber-physical environments(GS-CPE) that extends the architecture of our previous work gesture profile for web services(GPWS). To provide user identification functionality, GS-CPE introduces a two-phase cascading gesture password recognition algorithm for gesture-based user identification using a two-phase cascading classifier with the hidden Markov model and the Golden Section Search, which achieves an accuracy rate of 96.2% with a small training dataset. To support personalized gesture interaction, an enhanced version of the Dynamic Time Warping algorithm with multiple gestural input sources and dynamic template adaptation support is implemented. Our experimental results demonstrate the performance of the algorithm can achieve an average accuracy rate of 98.5% in practical scenarios. Comparison results reveal that GS-CPE has faster response time and higher accuracy rate than other gesture interaction systems designed for smart-home environments.

关键词： gesture interaction personalization gesture recognition user identification event-driven architec ture

来源：评论

学校读者我要写书评

暂无评论

From parallel Plants to Smart Plants:Intelligent Control and Management for Plant Growth

引用

IEEE/CAA Journal of Automatica Sinica 2017年第2期4卷 161-166页

作者： Mengzhen Kang Fei-Yue Wang State Key Laboratory of Management and Control for Complex Systems Institute of AutomationChinese Academy of Sciences (SKL-MCCSCASIA) Qingdao Academy of Intelligent Industries Beijing Engineering Research Center of Intelligent Systems and Technology IEEE State Key Laboratory of Management and Control for Complex Systems (SKL-MCCS) Institute of AutomationChinese Academy of Sciences (CASIA) School of Computer and Control Engineering University of Chinese Academy of Sciences Research Center for Military Computational Experiments and Parallel Systems Technology National University of Defense Technology

Precision management of agricultural systems, aiming at optimizing profitability, productivity and sustainability, comprises a set of technologies including sensors, information systems, and informed management, etc. Expert systems are expected to aid farmers in plant management or environment control, but they are mostly based on the offline and static information, deviated from the actual situation. parallel management, achieved by virtual/artificial agricultural system, computational experiment and parallel execution, provides a generic framework of solution for online decision support. In this paper, we present the three steps toward the parallel management of plant: growth description U+0028 the crop model U+0029, prediction, and prescription. This approach can update the expert system by adding learning ability and the adaption of knowledge database according to the descriptive and predictive model. The possibilities of passing the knowledge of experienced farmers to younger generation, as well as the application to the parallel breeding of plant through such system, are discussed. © 2017 Chinese Association of Automation.

关键词： Agriculture Artificial intelligence Decision support systems Expert systems Sustainable development

来源：评论

学校读者我要写书评

暂无评论

A dynamic virtual fragmentation method for query recovery optimization

A dynamic virtual fragmentation method for query recovery op...

引用

computer Science Society (SCCC) International Conference Chilean FLAGGED

作者： J.A. Vazquez Parallel and Distributed Systems Laboratory Research Computer Center National Petroleum Institute of Mexico Mexico

The time consumed during the execution of queries in a parallel and distributed environment is highly affected by the form in which the tables comprising a database have been fragmented. The classical methods of fragmentation in a distributed database system helps, to a great extent, to make the information retrieval faster and with smaller calculation efforts. This is particularly true for applications where the specifications are well known in advance at the time of the creation of the tables that compose the database, which in some form or other influenced the design and the definition of the type of fragmentation and their distribution on different sites of processing. Nevertheless, the above characteristics cannot be used in applications where the distributed management cannot do inferences that help it to know in what sites the data with the characteristics the user is looking for are located. Under these conditions the time and amount of work used by the participants in the query solution can be highly increased. In this paper the dynamic virtual fragmentation method is presented. The method works as an alternative way that allows us to diminish response time consumed by queries using horizontal fragmented tables. The proposed method has been proven and implemented in a database parallel server running on a shared nothing supercomputer.

关键词： Optimization methods distributed databases Information retrieval Partitioning algorithms Laboratories Concurrent computing distributed computing Augmented virtuality Delay Supercomputers

来源：评论

学校读者我要写书评

暂无评论

Generative Adversarial Networks:Introduction and Outlook

引用

IEEE/CAA Journal of Automatica Sinica 2017年第4期4卷 588-598页

作者： Kunfeng Wang Chao Gou Yanjie Duan Yilun Lin Xinhu Zheng Fei-Yue Wang IEEE State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Qingdao Academy of Intelligent Industries State Key Laboratory of Management and Control for Complex Systems Institute of AutomationChinese Academy of Sciences University of Chinese Academy of Sciences Department of Computer Science and Engineering University of Minnesota Research Center for Computational Experiments and Parallel Systems Technology National University of Defense Technology

Recently, generative adversarial networks(GANs)have become a research focus of artificial intelligence. Inspired by two-player zero-sum game, GANs comprise a generator and a discriminator, both trained under the adversarial learning *** goal of GANs is to estimate the potential distribution of real data samples and generate new samples from that *** their initiation, GANs have been widely studied due to their enormous prospect for applications, including image and vision computing, speech and language processing, etc. In this review paper, we summarize the state of the art of GANs and look into the future. Firstly, we survey GANs' proposal background,theoretic and implementation models, and application ***, we discuss GANs' advantages and disadvantages, and their development trends. In particular, we investigate the relation between GANs and parallel intelligence,with the conclusion that GANs have a great potential in parallel systems research in terms of virtual-real interaction and integration. Clearly, GANs can provide substantial algorithmic support for parallel intelligence.

关键词： ACP approach adversarial learning generative adversarial networks(GANs) generative models parallel intelligence zero-sum game

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：