检索结果-内蒙古大学图书馆

International Conference on High Performance Computing

作者： Advik Raj Basani Siddharth Chaitra Vivek Advaith Krishna Arnab K. Paul Department of Computer Science and Information Systems DaSHLab BITS Pilani India

ISBN: (数字)9798331509095

ISBN: (纸本)9798331509101

distributed Machine Learning (DML) on resource-constrained edge devices holds immense potential for real-world applications. However, achieving fast convergence in DML in these heterogeneous environments remains a significant challenge. Traditional frameworks like Bulk Synchronous parallel (BSP) and Asynchronous Stochastic parallel (ASP) rely on frequent, small updates that incur substantial communication overhead and hinder convergence speed. Furthermore, these frameworks often employ static dataset sizes, neglecting the heterogeneity of edge devices and potentially leading to straggler nodes that slow down the entire training process. The straggler nodes, i.e., edge devices that take significantly longer to process their assigned data chunk - hinder the overall training speed. To address these limitations, this paper proposes Hermes, a novel probabilistic framework for efficient DML on edge devices. This framework leverages a dynamic threshold based on recent test loss behavior to identify statistically significant improvements in the model's generalization capability, hence transmitting updates only when major improvements are detected, thereby significantly reducing communication overhead. Additionally, Hermes employs dynamic dataset allocation to optimize resource utilization and prevents performance degradation caused by straggler nodes. Our evaluations on a real-world heterogeneous resource-constrained environment demonstrate that Hermes achieves faster convergence compared to state-of-the-art methods, resulting in a remarkable 13.22x reduction in training time and a 62.1% decrease in communication overhead.

关键词： Training Performance evaluation Accuracy Stochastic processes Machine learning Dynamic scheduling Propagation losses Probabilistic logic Resource management Convergence

来源：评论

学校读者我要写书评

暂无评论

D3-GNN: Dynamic distributed Dataflow for Streaming Graph Neural Networks

引用

PROCEEDINGS OF THE VLDB ENDOWMENT 2024年第11期17卷 2764-2777页

作者： Guliyev, Rustam Haldar, Aparajita Ferhatosmanoglu, Hakan Univ Warwick Coventry W Midlands England Fujitsu Res Europe Slough Berks England Amazon Web Serv Seattle WA USA

Graph Neural Network (GNN) models on streaming graphs entail algorithmic challenges to continuously capture its dynamic state, as well as systems challenges to optimize latency, memory, and throughput during both inference and training. We present D3-GNN, the first distributed, hybrid-parallel, streaming GNN system designed to handle real-time graph updates under online query setting. Our system addresses data management, algorithmic, and systems challenges, enabling continuous capturing of the dynamic state of the graph and updating node representations with fault-tolerance and optimal latency, load-balance, and throughput. D3-GNN utilizes streaming GNN aggregators and an unrolled, distributed computation graph architecture to handle cascading graph updates. To counteract data skew and neighborhood explosion issues, we introduce inter-layer and intra-layer windowed forward pass solutions. Experiments on large-scale graph streams demonstrate that D3-GNN achieves high efficiency and scalability. Compared to DGL, D3-GNN achieves a significant throughput improvement of about 76x for streaming workloads. The windowed enhancement further reduces running times by around 10x and message volumes by up to 15x at higher parallelism.

关键词：

来源：评论

学校读者我要写书评

暂无评论

parallel Optimisation and Implementation of a real-time Back Projection (BP) Algorithm for SAR Based on FPGA

引用

SENSORS 2022年第6期22卷 2292页

作者： Cao, Yue Guo, Shuchen Jiang, Shuai Zhou, Xuan Wang, Xiaobei Luo, Yunhua Yu, Zhongjun Zhang, Zhimin Deng, Yunkai Chinese Acad Sci Aerosp Informat Res Inst Beijing 100094 Peoples R China Univ Chinese Acad Sci Sch Elect Elect & Commun Engn Beijing 101408 Peoples R China

This study conducts an in-depth evaluation of imaging algorithms and software and hardware architectures to meet the capability requirements of real-time image acquisition systems, such as spaceborne and airborne synthetic aperture radar (SAR) systems. By analysing the principles and models of SAR imaging, this research creatively puts forward the fully parallel processing architecture for the back projection (BP) algorithm based on Field-Programmable Gate Array (FPGA). The processing time consumption has significant advantages compared with existing methods. This article describes the BP imaging algorithm, which stands out with its high processing accuracy and two-dimensional decoupling of distance and azimuth, and analyses the algorithmic flow, operation, and storage requirements. The algorithm is divided into five core operations: range pulse compression, upsampling, oblique distance calculation, data reading, and phase accumulation. The architecture and optimisation of the algorithm are presented, and the optimisation methods are described in detail from the perspective of algorithm flow, fixed-point operation, parallel processing, and distributed storage. Next, the maximum resource utilisation rate of the hardware platform in this study is found to be more than 80%, the system power consumption is 21.073 W, and the processing time efficiency is better than designs with other FPGA, DSP, GPU, and CPU. Finally, the correctness of the processing results is verified using actual data. The experimental results showed that 1.1 s were required to generate an image with a size of 900 x 900 pixels at a 200 MHz clock rate. This technology can solve the multi-mode, multi-resolution, and multi-geometry signal processing problems in an integrated manner, thus laying a foundation for the development of a new, high-performance, SAR system for real-time imaging processing.

关键词： synthetic aperture radar (SAR) back-projection algorithm (BP) real-time image processing field-programmable gate array (FPGA)

来源：评论

学校读者我要写书评

暂无评论

Web-Based Volunteer distributed Computing for Handling time-Critical Urgent Workloads

Web-Based Volunteer Distributed Computing for Handling Time-...

引用

Interactive Urgent Supercomputing (CIW-IUS), Combined International workshop on

作者： Nick Brown Simon Newby The Bayes Centre EPCC The University of Edinburgh Edinburgh UK

ISBN: (纸本)9781665463348

Urgent computing workloads are time critical, unpredictable, and highly dynamic. Whilst efforts are on-going to run these on traditional HPC machines, another option is to leverage the computing power donated by volunteers. Volunteer computing, where members of the public donate some of their CPU time to large scale projects has been popular for many years because it is a powerful way of delivering compute for specific problems, with the public often eager to contribute to a good cause with societal benefits. However, traditional volunteer computing has required user installation of specialist software which is a barrier to entry, and the development of the software itself by the projects, even on-top of existing frameworks, is nontrivial. As such, the number of users donating CPU time to these volunteer computing projects has decreased in recent years, and this comes at a time when the frequency of disasters, often driven by climate change, are rising fast. We believe that an alternative approach, where visitors to websites donate some of their CPU time whilst they are browsing, has the potential to address these issues. However, web-based distributed computing is an immature field and there are numerous questions that must be answered to fully understand the viability of leveraging the large scale parallelism that website visitors represent. In this paper we describe our web-based distributed computing framework, Panther, and perform in-depth performance experiments for two benchmarks using real world hardware and real world browsing habits for the first time. By exploring the performance characteristics of our approach we demonstrate that this is viable for urgent workloads, but there are numerous caveats, not least the most appropriate visitor patterns to a website, that must be considered.

关键词： Climate change distributed processing distributed computing time-frequency analysis parallel processing Benchmark testing

来源：评论

学校读者我要写书评

暂无评论

CVchain: A Cross-Voting-Based Low Latency parallel Chain System 23

CVchain: A Cross-Voting-Based Low Latency Parallel Chain Sys...

引用

23rd IEEE International Conference on Trust, Security and Privacy in Computing and Communications, TrustCom 2024

作者： Wang, Jianrong Ren, Yacong Hu, Dengcheng Li, Qi Li, Sen Li, Xuewei Liu, Xiulong Tianjin University College of Intelligence and Computing China Tianjin University School of Electrical and Information Engineering China Tianjin University School of Future Technology China

Despite existing parallel chain systems improving blockchain throughput by allowing concurrent blocks to be appended, challenges such as the excessive number of waiting blocks before confirmation and the inconsistency between block generation order and global confirmation sequence still persist. To address these challenges, we propose CVchain, a parallel chain system with a cross-voting mechanism. Blocks from other subchains are incorporated into the consistency determination of the main chain, reducing the probability of confirmation errors. Our global sorting mechanism leverages both real-time height information and the implicit temporal order contained in voting to improve the accuracy of block ordering. Furthermore, our voting mechanism randomly splits the mining power of the system, preventing targeted attacks on the specific subchain and defending against liveness attacks. We prove the safety and liveness properties of CVchain. We demonstrated its performance with a prototype implementation and large-scale experiments involving 200 nodes across 10 cloud servers in a distributed network environment. The results indicate that CVchain achieves a latency reduction of approximately 32.3% at a confirmation error probability of 0.01 while maintaining throughput levels comparable to OHIE. Additionally, it provides enhanced transaction ordering services. © 2024 IEEE.

关键词： Multiprocessing systems

来源：评论

学校读者我要写书评

暂无评论

parallel Physics-Informed Neural Networks & Giza Pyramid Construction Optimization Algorithm for FDIAs Detection in Industrial IoT:ML Based Techniques

Parallel Physics-Informed Neural Networks & Giza Pyramid Con...

引用

Sustainable Computing and Smart systems (ICSCSS), International Conference on

作者： Basi Reddy A R. Yogesh Rajkumar Dept. of CSE Bharath institute of higher education and research Chennai Tamilnadu India Dept. of IT Bharath institute of higher education and research Chennai Tamilnadu India

ISBN: (数字)9798350379990

ISBN: (纸本)9798350391558

The rapid evolution of IIoT (Industrial Internet of Things) in computing has brought about numerous security concerns, among which is the looming threat of False Data Injection (FDI) attacks. To address these attacks, a study introduces a novel approach called MLBT-FDIA-IIoT (Fault Data Injection Attack Detection in IIoT using parallel Physics-Informed Neural Networks with Giza Pyramid Construction Optimization algorithm). This method makes use of real-time sensor data for attack detection. The data is preprocessed using distributed Set-Membership Fusion Filtering (DSMFF) to remove noise. Then, it is fed into a neural network for classification. Specifically, parallel Physics-Informed Neural Networks (PPINN) are used to distinguish between normal operations and False Data Injection Attacks (FDIAs). However, PPINN lacks optimization methods for accurate detection. To address this, the study proposes the Giza Pyramid Construction Optimization algorithm (GPCOA). This algorithm optimizes the PPINN classifier to detect attacks with more precision. The proposed MLBT-FDIA-IIoT method is implemented using MATLAB and evaluates various metrics such as accuracy, recall, and precision. The results demonstrate significant improvements compared to existing techniques such as MLT-FDI-IIoT, FDIA-FDAS-IIoT, and DCDD-IIoT-FDIA.

关键词： Training Deep learning Support vector machines Correlation Accuracy Neural networks Data models

来源：评论

学校读者我要写书评

暂无评论

A Variable Sliding Window Algorithm Based on Concept Drift for Frequent Pattern Mining Over Data Streams*

A Variable Sliding Window Algorithm Based on Concept Drift f...

引用

International Conference on parallel and distributed systems (ICPADS)

作者： Yue Yin Peng Li Jing Chen School of Computer Science Nanjing University of Posts and Telecommunications Nanjing China Baotou Teachers’ College of Inner Mongolia University of Science and Technology Baotou China

Sliding window is a widely used model in the process of mining frequent patterns in data streams. In order to determine the exact size of the sliding window, it is necessary to know the time and scale of the change over data streams in advance. However, the prior knowledge is difficult to determine, and the fixed-size sliding window in the traditional algorithms obviously cannot adapt to this change, which have poor performance on the latest concepts of data streams. Based on the above shortcomings, this paper proposes a new frequent pattern mining algorithm based on concept drift using variable sliding window: VSWCDD (Variable Sliding Window-Concept Drift Detection), which is suitable for mining frequent patterns in changing data streams. The window size is dynamically determined by whether the concept drift occurs in the data stream. During the mining process, the mining result variables and the cause variables about the concept drift are monitored simultaneously. When the data stream is stable and there is no concept change, the window size keeps expansion. When the concept drift occurs, the window size changes according to the difference between detection nodes. Extensive experiments on both real and synthetic data show that the VSW-CDD algorithm proposed in this paper can timely detect the concept drift in the data stream and adapt to the new concepts by adjusting the window size. Finally, the latest frequent patterns in the data streams are mined and has a better effect for click data streams on e-commerce sites and medical data. Compared with other algorithms, the algorithm in this paper also has better performance in terms of recall and adaptation.

关键词： Heuristic algorithms distributed databases Data models Data mining Electronic commerce Biomedical monitoring Monitoring

来源：评论

学校读者我要写书评

暂无评论

Accelerating Gossip-Based Deep Learning in Heterogeneous Edge Computing Platforms

引用

IEEE TRANSACTIONS ON parallel AND distributed systems 2021年第7期32卷 1591-1602页

作者： Han, Rui Li, Shilin Wang, Xiangwei Liu, Chi Harold Xin, Gaofeng Chen, Lydia Y. Beijing Inst Technol Beijing 100811 Peoples R China Delft Univ Technol Mekelweg 5 NL-2628 CD Delft Netherlands

With the exponential growth of data created at the network edge, decentralized and Gossip-based training of deep learning (DL) models on edge computing (EC) gains tremendous research momentum, owing to its capability to learn from resource-strenuous edge nodes with limited network connectivity. Today's edge devices are extremely heterogeneous, e.g., hardware and software stacks, and result in high performance variation of training time and inducing extra delay to synchronize and converge. The large body of prior art accelerates DL, being data or model parallelization, via a centralized server, e.g., parameter server scheme, which may easily turn into the system bottleneck or single point of failure. In this artice, we propose EdgeGossip, a framework specifically designed to accelerate the training process of decentralized and Gossip-based DL training for heterogeneous EC platforms. EdgeGossip features on: (i) low performance variation among multiple EC platforms during iterative training, and (ii) accuracy-aware training to fastly obtain best possible model accuracy. We implement EdgeGossip based on popular Gossip algorithms and demonstrate its effectiveness using real-world DL workloads, i.e., considerably reducing model training time by an average of 2.70 times while only incurring accuracy losses of 0.78 percent.

关键词： Training Data models Computational modeling Peer-to-peer computing distributed databases Acceleration Servers Deep learning decentralized training gossip edge computing

来源：评论

学校读者我要写书评

暂无评论

parallel Implementation of real-time Object Detection using OpenMP

Parallel Implementation of Real-Time Object Detection using ...

引用

2021 International Conference on Information Science and Communications Technologies, ICISCT 2021

作者： Rakhimov, Mekhriddin Elov, Jamshid Khamdamov, Utkir Aminov, Shavkatjon Javliev, Shakhzod Tashkent University of Information Technologies Named after Muhammad Al-Khwarizmi Department of Artificial Intelligence Tashkent Uzbekistan Tashkent University of Information Technologies Named after Muhammad Al-Khwarizmi Department of Hardware and Software of Management Systems in Telecommunication Tashkent Uzbekistan Chonnam National University Department of Computer Engineering Gwangju Korea Republic of Tashkent University of Information Technologies Named after Muhammad Al-Khwarizmi Department of Computer System Tashkent Uzbekistan

ISBN: (纸本)9781665432580

One of the urgent problems of the modern world is the detection and recognition of objects on a video stream in real-time. To work with a video stream, you need to split it into frames that are more convenient for processing. There is a possibility of using multi-core processors for image processing. Typically, the operating system allows only one core of multi-core processors to execute a task. But there are such parallelization tools that allow parallelizing execution when processing data on multi-core processors. And OpenMP is one of them that can be used in real-time object detection processing procedures. But in this case, the main thing is to find that part of the algorithm that is suitable for parallelization. Using OpenMP simply does not give an efficient accelerated result. In this paper, we discuss the implementation of OpenMP technology in real-time object detection algorithms on multi-core processors. Experimental results show that the use of OpenMP technology significantly improves the processing speed for real-time object detection on multi-core processors, when there are no GPUs. © 2021 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

real-time High-Resolution Pedestrian Detection in Crowded Scenes via parallel Edge Offloading

arXiv

引用

arXiv 2023年

作者： Wang, Hao Bao, Hao Zeng, Liekang Luo, Ke Chen, Xu School of Computer Science and Engineering Sun Yat-sen University Guangzhou China

To identify dense and small-size pedestrians in surveillance systems, high-resolution cameras are widely deployed, where high-resolution images are captured and delivered to off-the-shelf pedestrian detection models. However, given the highly computation-intensive workload brought by the high resolution, the resource-constrained cameras fail to afford accurate inference in real time. To address that, we propose HODE, an offloaded video analytic framework that utilizes multiple edge nodes in proximity to expedite pedestrian detection with high-resolution inputs. Specifically, HODE can intelligently split high-resolution images into respective regions and then offload them to distributed edge nodes to perform pedestrian detection in parallel. A spatio-temporal flow filtering method is designed to enable context-aware region partitioning, as well as a DRL-based scheduling algorithm to allow accuracy-aware load balance among heterogeneous edge nodes. Extensive evaluation results using realistic prototypes show that HODE can achieve up to 2.01× speedup with very mild accuracy loss. Copyright © 2023, The Authors. All rights reserved.

关键词： Scheduling algorithms

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：