检索结果-内蒙古大学图书馆

29th international conference on parallel and distributed computing (Euro-Par)

作者： Li, Wenhai Cheng, Zhiling Chen, Yuan Li, Ao Deng, Lingfeng Wuhan Univ Wuhan Peoples R China

ISBN: (纸本)9783031396977;9783031396984

Concurrent hash tables are one of the fundamental building blocks for cloud computing. In this paper, we introduce lock-free modifications to in-memory bucketized cuckoo hashing. We present a novel concurrent strategy in designing a lock-free hash table, called LFBCH, that paves the way towards scalability and high space efficiency. To the best of our knowledge, this is the first attempt to incorporate lock-free technology into in-memory bucketized cuckoo hashing, while still providing worst-case constant-scale lookup time and extremely high load factor. All of the operations over LFBCH, such as get, put, "kick out" and rehash, are guaranteed to be lock-free, without introducing notorious problems like false miss and duplicated key. The experimental results indicate that under mixed workloads with up to 64 threads, the throughput of LFBCH is 14%-360% higher than other popular concurrent hash tables.

关键词： buckized cuckoo hashing lock-free data structure multicore parallel computing

来源：评论

学校读者我要写书评

暂无评论

Blockchain at the Edge: Harnessing distributed Ledger Technology in Edge and Cloud computing Environments 2

Blockchain at the Edge: Harnessing Distributed Ledger Techno...

引用

2nd IEEE international conference on Trends in Quantum computing and Emerging Business Technologies, TQCEBT 2024

作者： Prabakar, S. Sathish Kumar.r, Dr. Sasi, Archana Sowmya, P. Jawale, Vaishali Dharamvir, Prof. Dayananda Sagar University Bangalore School of Commerce and Management Studies Karnataka Bangalore India Jain University Faculty of Engineering and Technology Department of Aiml Kannagapura Rd Karnataka Bengaluru562112 India Presidency University Computer Science & Engineering Karnataka Bangalore India Karnataka Karkala India ASM's Institute of Business Management & Research Pune India The Oxford College of Engineering Department of Mca Bommanhalli Bengaluru560100 India

ISBN: (纸本)9798350384277

This study has investigated how blockchain-based technologies can be integrated at the boundary of computing environments in this research to revolutionize security, effectiveness, and transparent handling of information. Combining edge computing, Blockchain technology, and cloud-based solutions can be very beneficial to companies that depend on data-driven knowledge, because it always facilitates prompt decision-making. As Database trust and honesty issues have always been of trouble these problems are addressed by the decentralized ledger design's permanence and cryptographic safety features. Everyone makes use of edge techniques for consensus like Delegated Evidence of Stake and Practical Fault Tolerance of Byzantine Faults during the technical setup. Not only can deals at the boundary level improve the effectiveness of operations, but they also help save expenditures. There are many benefits and use situations that exist, such as enhanced data truthfulness, decreased delays, and ground-breaking uses for managing supply chains and cybersecurity. It is crucial to recognize that there remain issues with communication, optimizing resources, flexibility, safety precautions, and changing legislative landscapes. Considering these challenges, the study comes to the conclusion that there will be chances to improve privacy and automate processes in handling information in the coming years by integrating blockchain-based technologies at the edges. The goal of current research and cooperative projects is to address these kinds of problems as well as to understand the full capabilities of technological advances in computer-related settings. © 2024 IEEE.

关键词： distributed ledger

来源：评论

学校读者我要写书评

暂无评论

Optimizing Resource Utilization in Generative AI Ensembles for Edge computing 2

Optimizing Resource Utilization in Generative AI Ensembles f...

引用

2nd IEEE international conference on advances in Information Technology, ICAIT 2024

作者： Rao, N. Venkatesvara Swaminathan, Subbiah Kanimozhi, K.V. Manikandan, S.P. Seethalakshmi, K. Department of Computer Science and Engineering J.N.N.Institute of Engineering Ushaa Garden Kannigaipair Periyapalayam Highway Chennai India Department of Information Technology Rajalakshmi Engineering College Tamil Nadu Chennai India Department of Computer Science and Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Tamil Nadu Chennai India School of Engineering and Technology CMR UNIVERSITY Karnataka Bengaluru India Department of Computer Science and Engineering Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Tamil Nadu Chennai6000062 India

ISBN: (纸本)9798350383867

Edge computing in this period makes it difficult to deploy, AI ensemble on resource limited devices together flow the computation complexity and the system performs. The methods state below presents a comprehensive approach to the optimizing envelope of resources in generative AI sheaves for edge computing while characteristic adaptability, privacy and efficiency are minded. With improvement of model compression, hardware acceleration, and model optimization, computational cost can be reduced with high quality generated objects. Privately-oriented algorithms like federated learning and differential privacy provide entity safety of the data in the distributed and collaborative edge environments. Intelligent distribution resources management policies perform such actions instantaneously on-demand and automatically, hence improving performance. The experiments prove that the methodology is worthy to trusted adopting as it facilitates calculational efficiency, generates high quality results and also protects the information of the users. The ongoing evolution and sharing of new technologies including generative AI enhance edge intelligence and stimulate innovative breakthroughs in next generation devices while influencing society. ©2024 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Stable and quadratic-optimal parallel-distributed-compensation controller design for time-varying Takagi-Sugeno fuzzy model System: A complementary computational approach

引用

MEASUREMENT & CONTROL 2022年第3-4期55卷 119-125页

作者： Chou, Fu-, I Ho, Wen-Hsien Natl Kaohsiung Univ Sci & Technol Dept Elect Engn Kaohsiung Taiwan Kaohsiung Med Univ Dept Healthcare Adm & Med Informat 100 Shin Chuan 1st Rd Kaohsiung 807 Taiwan Kaohsiung Med Univ Hosp Dept Med Res Kaohsiung Taiwan Natl Pingtung Univ Sci & Technol Dept Mech Engn Pingtung Taiwan

A complementary computational approach is proposed for the time-varying Takagi-Sugeno fuzzy model system (TVTSFMS). The proposed approach integrates orthogonal-functional approach (OFA), hybrid Taguchi genetic algorithm (HTGA), and a stabilizability condition (SC) for use in designing stable and quadratic-optimal parallel-distributed-compensation (SQOPDC) controllers for optimal control problems. First, the SC was set according to linear matrix inequalities (LMIs). Next, OFA was used to derive an algorithm that only required algebraic computation to solve the TVTSFMS. Finally, The HTGA could be used to search the SQOPDC controller for the TVTSFMS. The SQOPDC controller obtained by the proposed complementary computational approach was evaluated in a case study of a vibratory pendulum design;the successful design verified the usability of the proposed hybrid intelligent computing method.

关键词： Takagi-Sugeno fuzzy model orthogonal-functional approach hybrid Taguchi-genetic algorithm time-varying parallel-distributed-compensation controller

来源：评论

学校读者我要写书评

暂无评论

A Performance Analysis of Leading Many-Core Technologies for Cellular Automata Execution

A Performance Analysis of Leading Many-Core Technologies for...

引用

29th international conference on parallel and distributed computing (Euro-Par)

作者： De Rango, Alessio D'Ambrosio, Donato Senatore, Alfonso Mendicino, Giuseppe Narasimhan, Kumudha Goli, Mehdi Burns, Rod Univ Calabria Dept Environm Engn Arcavacata Di Rende Italy Univ Calabria Dept Math & Comp Sci Arcavacata Di Rende Italy Codeplay Software Ltd Intel Co Edinburgh Midlothian Scotland

ISBN: (纸本)9783031506833;9783031506840

We extend the panorama of performance analyses of CUDA, OpenCL and SYCL for the execution of Cellular Automata. To this end, we apply the SciddicaT landslide model to a real event by considering two complex topographic surfaces of different granularity, thus resulting in two simulations of different computing loads. For each technology, we developed a global memory and two tiled implementations of SciddicaT by adopting the Nvidia nvcc compiler for CUDA, the Nvidia implementation of the OpenCL standard and the CUDA back-end of the Intel DPC++ compiler for SYCL. The experiments, performed on three Nvidia accelerators, point out from good to optimal performances of SYCL compared to CUDA according to the newer device's architecture. The carried-out Roofline analysis evidences high cache effects, pointing out greater advantages of tiled implementations for older architectures.

关键词： Cellular Automata Data-parallel Structured-Grid Fluid-Flow Simulation CUDA vs OpenCL vs SYCL Roofline

来源：评论

学校读者我要写书评

暂无评论

Thicket: Seeing the Performance Experiment Forest for the Individual Run Trees 23

Thicket: Seeing the Performance Experiment Forest for the In...

引用

32nd international Symposium on High-Performance parallel and distributed computing (HPDC) part of the ACM Federated computing Research conference (FCRC)

作者： Brink, Stephanie McKinsey, Michael Boehme, David Scully-Allison, Connor Lumsden, Ian Hawkins, Daryl Burgess, Treece Lama, Vanessa Luettgau, Jakob Isaacs, Katherine E. Taufer, Michela Pearce, Olga Lawrence Livermore Natl Lab Lawrence CA 94550 USA Texas A&M Univ College Stn TX USA Univ Utah Salt Lake City UT USA Univ Tennessee Knoxville TN USA

ISBN: (纸本)9798400701559

Thicket is an open-source Python toolkit for Exploratory Data Analysis (EDA) of multi-run performance experiments. It enables an understanding of optimal performance configuration for large-scale application codes. Most performance tools focus on a single execution (e.g., single platform, single measurement tool, single scale). Thicket bridges the gap to convenient analysis in multi-dimensional, multi-scale, multi-architecture, and multi-tool performance datasets by providing an interface for interacting with the performance data. Thicket has a modular structure composed of three components. The first component is a data structure for multi-dimensional performance data, which is composed automatically on the portable basis of call trees, and accommodates any subset of dimensions present in the dataset. The second is the metadata, enabling distinction and sub-selection of dimensions in performance data. The third is a dimensionality reduction mechanism, enabling analysis such as computing aggregated statistics on a given data dimension. Extensible mechanisms are available for applying analyses (e.g., top-down on Intel CPUs), data science techniques (e.g., K-means clustering from scikit-learn), modeling performance (e.g., Extra-P), and interactive visualization. We demonstrate the power and flexibility of Thicket through two case studies, first with the open-source RAJA Performance Suite on CPU and GPU clusters and another with a large physics simulation run on both a traditional HPC cluster and an AWS parallel Cluster instance.

关键词： HPC exploratory data analysis performance analysis parallel profile multi-dimensional

来源：评论

学校读者我要写书评

暂无评论

Enriching Big Data Intrusion Detection and Service Through Mapping and parallel Computation

Enriching Big Data Intrusion Detection and Service Through M...

引用

international conference on Artificial Intelligence: Theory and Applications (AITA)

作者： Roy, Koyel Deshmukh, Rushali JSPM Rajarshi Shahu Coll Engn Pune Maharashtra India

ISBN: (纸本)9789819984756;9789819984763

Large-scale analysis of data requires a significant amount of computing power and resources, so the vast and flexible interpreting, preservation, and remote servers that cloud computing companies provide are very attractive. MongoDB is a widely used database management system for big data that is known for its fast performance and ability to execute activities within the MapReduce framework. The notion of big data relies on the conceptualization of resource collaboration, where applications and related infrastructure are frequently distributed among multiple users or organizations through isolation techniques such as virtualization. Big data is vulnerable to various types of assaults owing to its collaborative assets and extensive system software. The lack of efficacy and utility in improving the efficiency and privacy of big data is a significant challenge. The mission of securing big data is of utmost importance, as any discrepancies in this regard can have significant detrimental effects. The complex and voluminous characteristics of big data pose significant challenges in the application of traditional security methodologies, thereby leading to potential issues. Therefore, this research approach utilizes effective big data query classification and partitioning along with mapping and parallel computation for improving efficiency, as well as a bilinear pairing, avalanche effect, and tamper detection for forensic analysis and report generation. The approach has been effectively tested and compared with conventional approaches to achieve improved outcomes.

关键词： Data mapping Avalanche effect Bilinear pairing parallel computation Big data

来源：评论

学校读者我要写书评

暂无评论

Hermes: Memory-Efficient Pipeline Inference for Large Models on Edge Devices 42

Hermes: Memory-Efficient Pipeline Inference for Large Models...

引用

42nd international conference on Computer Design

作者： Han, Xueyuan Cai, Zinuo Zhang, Yichu Fan, Chongxin Liu, Junhan Ma, Ruhui Buyya, Rajkumar Shanghai Jiao Tong Univ ParisTech Elite Inst Technol Shanghai Peoples R China Shanghai Jiao Tong Univ Sch Elect Informat & Elect Engn Shanghai Peoples R China Shanghai Jiao Tong Univ UM SJTU Joint Inst Shanghai Peoples R China Shanghai Aerosp Syst Engn Inst Shanghai Peoples R China Univ Melbourne Cloud Comp & Distributed Syst CLOUDS Lab Melbourne Vic Australia

ISBN: (纸本)9798350380415;9798350380408

The application of Transformer-based large models has achieved numerous success in recent years. However, the exponential growth in the parameters of large models introduces formidable memory challenge for edge deployment. Prior works to address this challenge mainly focus on optimizing the model structure and adopting memory swapping methods. However, the former reduces the inference accuracy, and the latter raises the inference latency. This paper introduces PIPELOAD, a novel memory-efficient pipeline execution mechanism. It reduces memory usage by incorporating dynamic memory management and minimizes inference latency by employing parallel model loading. Based on PIPELOAD mechanism, we present Hermes, a framework optimized for large model inference on edge devices. We evaluate Hermes on Transformer-based models of different sizes. Our experiments illustrate that Hermes achieves up to 4.24x increase in inference speed and 86.7% lower memory consumption than the state-of-the-art pipeline mechanism for BERT and ViT models, 2.58x increase in inference speed and 90.3% lower memory consumption for GPT-style models.

关键词： Edge computing Memory optimisation Large model inference Pipeline execution.

来源：评论

学校读者我要写书评

暂无评论

SA-DDQN: Self-Attention Mechanism Based DDQN for SFC Deployment in NFV/MEC-Enabled Networks 28

SA-DDQN: Self-Attention Mechanism Based DDQN for SFC Deploym...

引用

IEEE 28th international conference on parallel and distributed Systems (IEEE ICPADS)

作者： Wang, Ziheng Guo, Songtao Liu, Guiyan Chongqing Univ Coll Comp Sci Chongqing 400044 Peoples R China

ISBN: (纸本)9781665473156

Network function virtualization (NFV) is able to reduce the delay and improve the flexibility of network services in mobile edge computing (MEC) networks via deploying the service function chain (SFC) that consists of a sequence of ordered virtual network functions. However, it is still challenging to deploy SFC with delay guarantees and resource efficiency while taking into account the real-time network variations and dispersed edge server nodes in NFV/MEC-enabled networks. To address the issue, this paper proposes a self-attention mechanism-based double deep Q-network algorithm (SA-DDQN) for SFC deployment to jointly minimize the resource consumption on servers and bandwidth consumption on links within delay limits in dynamic NFV/MEC-enabled networks. In particular, we introduce the self-attention mechanism in the deep neural network structure, which enables the agent to pay its attention on more valuable physical nodes when making decisions, thus improving the efficiency of SFC deployment. Additionally, we utilize the Markov decision process (MDP) model to solve the problem of real-time network state variations. Finally, extensive simulation results show that our proposed SA-DDQN SFC deployment algorithm can reduce resource consumption by 25% and delay by 18.4% compared with the state-of-the-art algorithm.

关键词： Mobile edge computing network function virtualization SFC deployment deep reinforcement learning self-attention mechanism

来源：评论

学校读者我要写书评

暂无评论

A Float-Point Arithmetic Logic Unit for High Performance RISC-V Processor 6

A Float-Point Arithmetic Logic Unit for High Performance RIS...

引用

6th international conference on Frontier Technologies of Information and Computer, ICFTIC 2024

作者： Wei, Chunyuan Yuan, Chuan Qi, Yu Xu, Bangjian Niu, Xin College of Computer Science and Electronic Engineering Hunan University Changsha China College of Electrical and Information Engineering Hunan University Changsha China College of Computer National University of Defense Technology Science and Technology on Parallel and Distributed Laboratory Changsha China

ISBN: (纸本)9798331541750

With the rapid advancement of artificial intelligence, chips have become increasingly important. The emerging RISC-V instruction set gradually provides powerful computing support for this field. In this context, along with the computing requirements of deep learning, this paper presents the design of a high-performance floating-point arithmetic logic unit (FALU) that facilitates calculations with double-precision, single-precision, half-precision, and Bfloat16 precision data. This design is based on a single-channel algorithm with merged rounding. It improves and implements a composite adder that combines high and low bits. It also proposes a tree-like floating-point comparator based on the Kogge-Stone parallel prefix network. To ensure that the FALU components meet performance requirements, we undergo functional verification in the Vivado simulation environment. Operating at 1.47GHz under the 28nm CMOS process, the components achieve the predetermined performance indicators. © 2024 IEEE.

关键词： Computer circuits

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：