检索结果-内蒙古大学图书馆

FMCC-RT: a scalable and fine-grained all-reduce algorithm for large-scale SMP clusters

Science China(Information Sciences) 2025年第5期68卷 362-379页

作者： Jintao PENG Jie LIU Jianbin FANG Min XIE Yi DAI Zhiquan LAI Bo YANG Chunye GONG Xinjun MAO Guo MAO Jie REN School of Computer Science and Technology National University of Defense Technology Science and Technology on Parallel and Distributed Processing Laboratory National University of Defense Technology Laboratory of Digitizing Software for Frontier Equipment National University of Defense Technology National Supercomputer Center in Tianjin School of Computer Science Shaanxi Normal University

All-reduce is a widely used communication technique for distributed and parallel applications typically implemented using either a tree-based or ring-based scheme. Each of these approaches has its own limitations: tree-based schemes struggle with efficiently exchanging large messages, while ring-based solutions assume constant communication throughput,an unrealistic expectation in modern network communication infrastructures. We present FMCC-RT, an all-reduce approach that combines the advantages of tree-and ring-based implementations while mitigating their drawbacks. FMCC-RT dynamically switches between tree and ring-based implementations depending on the size of the message being processed. It utilizes an analytical model to assess the impact of message sizes on the achieved throughput, enabling the derivation of optimal work partitioning parameters. Furthermore, FMCC-RT is designed with an Open MPI-compatible API, requiring no modification to user code. We evaluated FMCC-RT through micro-benchmarks and real-world application tests. Experimental results show that FMCC-RT outperforms state-of-the-art tree-and ring-based methods, achieving speedups of up to 5.6×.

关键词： all-reduce collective communication MPI scalability

来源：评论

学校读者我要写书评

暂无评论

YFLM: An Improved Levenberg-Marquardt Algorithm for Global Bundle Adjustment 41st

YFLM: An Improved Levenberg-Marquardt Algorithm for Global ...

引用

41st computer Graphics International Conference, CGI 2024

作者： Peng, Jiaxin Li, Tao Jiang, Qin Liu, Jie Wang, Ruibo Laboratory of Software Engineering for Complex Systems School of Computer Science National University of Defense Technology Hunan Changsha410073 China Parallel and Distributed Processing Laboratory School of Computer Science National University of Defense Technology Hunan Changsha410073 China

ISBN: (纸本)9783031820205

The conventional Levenberg-Marquardt (LM) algorithm is a state-of-the-art trust-region optimization method for solving bundle adjustment problems in the Structure-from-Motion community, which not only takes advantage of the fast convergence of the Gauss-Newton method, but also the stability of the gradient descent method when approaching optimal solutions. However, the damping ratio of LM is simply provided by trial-and-error, which causes slow convergence rate for large-scale problems. This paper proposes the Yamashita-Fukushima LM (YFLM) algorithm to reduce the time complexity for global bundle adjustment, where the damping factor is determined by Yamashita and Fukushima’s method. YFLM dynamically calculates a more reasonable and optimal damping ratio according to the newest reprojection error. The experimental results show that the YFLM algorithm outperforms the conventional LM algorithm for most public bundle adjustment datasets. Besides this, the convergence of the YFLM algorithm is also evaluated with different σ∈(0,2]. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Damping

来源：评论

学校读者我要写书评

暂无评论

Optimizing Yinyang K-Means Algorithm on ARMv8 Many-Core CPUs 22nd

Optimizing Yinyang K-Means Algorithm on ARMv8 Many-Core CPU...

引用

22nd International Conference on Algorithms and Architectures for parallel processing, ICA3PP 2022

作者： Zhou, Tianyang Wang, Qinglin Yin, Shangfei Hao, Ruochen Liu, Jie Science and Technology on Parallel and Distributed Processing Laboratory National University of Defense Technology Changsha410073 China School of Computer Science National University of Defense Technology Changsha410073 China

ISBN: (纸本)9783031226762

K-Means algorithm is one of the most common clustering algorithms widely applied in various data analysis applications. Yinyang K-Means algorithm is a popular enhanced K-Means algorithm that avoids most unnecessary calculations using triangle inequality. However, Yinyang K-Means algorithm is time-consuming when the problem size is large. Due to the influence of performance and energy-efficiency, ARM CPUs have appeared in high performance computing. Therefore, it is very interesting to accelerate Yinyang K-Means algorithm on ARM CPUs. In this paper, we propose an efficient parallel implementation of Yinyang K-Means algorithm on ARMv8 many-core CPUs by means of vectorization, NUMA affinity memory optimization and data layout optimization. The experiment on two ARMv8 many-core CPUs has shown that our implementation can achieve up to 5.6 times faster than the open-source multi-threaded one of Yinyang K-Means algorithm. To the best of our knowledge, this is the first work that studies the optimization of Yinyang K-Means algorithms on ARMv8 CPUs. © 2023, Springer Nature Switzerland AG.

关键词： K-means clustering

来源：评论

学校读者我要写书评

暂无评论

CHIME: A Cache-Efficient and High-Performance Hybrid Index on Disaggregated Memory 24

CHIME: A Cache-Efficient and High-Performance Hybrid Index o...

引用

30th ACM Symposium on Operating Systems Principles, SOSP 2024

作者： Luo, Xuchuan Shen, Jiacheng Zuo, Pengfei Wang, Xin Lyu, Michael R. Zhou, Yangfan National Key Laboratory of Parallel and Distributed Computing Changsha China School of Computer Science Fudan University Shanghai China Duke Kunshan University Kunshan China Huawei Cloud Shenzhen China Shanghai Key Laboratory of Intelligent Information Processing Shanghai China The Chinese University of Hong Kong Hong Kong Hong Kong

ISBN: (纸本)9798400712517

Disaggregated memory (DM) is a widely discussed datacenter architecture in academia and industry. It decouples computing and memory resources from monolithic servers into two network-connected resource pools. Range indexes are widely adopted by storage systems on DM to efficiently locate and query remote data. However, existing range indexes on DM suffer from either high computing-side cache consumption or high memory-side read amplifications. In this paper, we propose CHIME, a hybrid index combining B+ trees with hopscotch hashing, to achieve low cache consumption and low read amplifications simultaneously. There are three challenges in constructing CHIME on DM, i.e., the complicated optimistic synchronization, the extra metadata access, and the read amplifications introduced by hopscotch hashing. CHIME leverages 1) a three-level optimistic synchronization scheme to synchronize read and write operations with various granularities, 2) an access-aggregated metadata management technique to eliminate extra metadata accesses by piggybacking and replicating metadata, and 3) an effective hotness-aware speculative read mechanism to mitigate the read amplifications of hopscotch hashing. Experimental results show that CHIME outperforms the state-of-the-art range indexes on DM by up to 5.1× with the same cache size and achieves similar performance with up to 8.7× lower cache consumption. © 2024 Copyright is held by the owner/author(s). Publication rights licensed to ACM.

关键词： Memory architecture

来源：评论

学校读者我要写书评

暂无评论

A Fast Adversarial Sample Detection Approach for Industrial Internet-of-Things Applications

A Fast Adversarial Sample Detection Approach for Industrial ...

引用

International Workshop on Quality of Service

作者： Shigeng Zhang Yudong Li Shuxin Chen Xuan Li Jian Zhang School of Computer Science and Engineering Central South University College of Computer Science and Electronic Engineering Hunan University The Science and Technology on Parallel and Distributed Processing Laboratory (PDL) China

Adversarial attacks reveal the inherent vulnerability of deep neural networks, which face serious security issues for their security. Among them, the attack against the Deep Neural Network (DNN) application used in the Industrial Internet of Things (IIoT) is a key area in adversarial attacks. Adversarial examples generated by attackers by adding human-undetectable interference to legitimate examples may cause models to make wrong decision results, resulting in serious accidents. Many detection technologies have been proposed to mitigate the harm of adversarial examples to neural networks, among which the methods based on the difference of feature attribution between normal examples and adversarial examples show state-of-the-art detection performance, but they suffer from detection efficiency. In this work, we focus on improving the detection efficiency of the feature-attribution-based detection methods. We observe that there is still a significant difference in the feature attribution distribution of a normal image and an adversarial image even only some pixels in the image are processed, which can be verified by utilizing the Kolmogorov-Smirnov test. Based on this observation, we first adopt a variety of strategies to sample partial pixels in an image and then utilize the selected pixels to train a feature-attribution-based detector for detecting adversarial examples. Extensive experiments conducted on four datasets (MNIST, CIFAR-10, SVHN, CIFAR-100) against various attacks proved that the detection efficiency of the accelerated detection method is improved (for example, the average execution time was increased by 8.7 times on CIFAR-10) while the detection performance maintains state-of-the-art.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Cooperative Air-Ground Instant Delivery by UAVs and Crowdsourced Taxis 40

Cooperative Air-Ground Instant Delivery by UAVs and Crowdsou...

引用

40th IEEE International Conference on Data engineering, ICDE 2024

作者： Gao, Junhui Wang, Qianru Zhang, Xin Shi, Juan Zhao, Xiang Han, Qingye Pan, Yan School of Computer Science Northwestern Polytechnical University China School of Computer Science and Technology Xidian University China Air Force Engineering University China National University of Defense Technology Laboratory for Big Data and Decision China School of Management Science and Real Estate Chongqing University China National University of Defense Technology National Key Laboratory of Information Systems Engineering China National University of Defense Technology National Key Laboratory of Parallel and Distributed Computing China

ISBN: (纸本)9798350317152

Instant delivery has become a fundamental service in people's daily lives. Different from the traditional express service, the instant delivery has a strict shipping time constraint after being ordered. However, the labor shortage makes it challenging to realize efficient instant delivery. To tackle the problem, researchers have studied to introduce vehicles (i.e., taxis) or Unmanned Aerial Vehicles (UAVs or drones) into instant delivery tasks. Unfortunately, the delivery detour of taxis and the limited battery of UAVs make it hard to meet the rapidly increasing instant delivery demands. Under this circumstance, this paper proposes an air-ground cooperative instant delivery paradigm to maximize the delivery performance and meanwhile minimize the negative effects on the taxi passengers. Specifically, a data-driven delivery potential-demands-aware cooperative strategy is designed to improve the overall delivery performance of both UAVs and taxis as well as the taxi passengers' experience. The experimental results show that the proposed method improves the delivery number by 30.1% and 114.5% compared to the taxi-based and UAV-based instant delivery respectively, and shortens the delivery time by 35.7% compared to the taxi-based instant delivery. © 2024 IEEE.

关键词： Unmanned aerial vehicles (UAV)

来源：评论

学校读者我要写书评

暂无评论

A survey of script learning

引用

Frontiers of Information Technology & Electronic engineering 2021年第3期22卷 341-373页

作者： Yi HAN Linbo QIAO Jianming ZHENG Hefeng WU Dongsheng LI Xiangke LIAO Science and Technology on Parallel and Distributed Processing Laboratory National University of Defense TechnologyChangsha 410000China Science and Technology on Information Systems Engineering Laboratory National University of Defense TechnologyChangsha 410000China School of Data and Computer Science Sun Yat-sen UniversityGuangzhou 510006China

Script is the structured knowledge representation of prototypical real-life event *** the commonsense knowledge inside the script can be helpful for machines in understanding natural language and drawing commonsensible *** learning is an interesting and promising research direction,in which a trained script learning system can process narrative texts to capture script knowledge and draw ***,there are currently no survey articles on script learning,so we are providing this comprehensive survey to deeply investigate the standard framework and the major research topics on script *** research field contains three main topics:event representations,script learning models,and evaluation *** each topic,we systematically summarize and categorize the existing script learning systems,and carefully analyze and compare the advantages and disadvantages of the representative *** also discuss the current state of the research and possible future directions.

关键词： Script learning Natural language processing Commonsense knowledge modeling Event reasoning

来源：评论

学校读者我要写书评

暂无评论

Differentially Private and Heterogeneity-Robust Federated Learning With Theoretical Guarantee

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第12期5卷 6369-6384页

作者： Wang, Xiuhua Wang, Shuai Li, Yiwei Fan, Fengrui Li, Shikang Lin, Xiaodong Huazhong University of Science and Technology Hubei Key Laboratory of Distributed System Security Hubei Engineering Research Center on Big Data Security School of Cyber Science and Engineering Wuhan430074 China University of Electronic Science and Technology of China National Key Laboratory of Wireless Communications Chengdu611731 China Xiamen University of Technology Fujian Key Laboratory of Communication Network and Information Processing Xiamen361024 China University of Guelph School of Computer Science GuelphONN1G 2W1 Canada

Federated learning (FL) is a popular distributed paradigm where enormous clients collaboratively train a machine learning (ML) model under the orchestration of a central server without knowing the clients' private raw data. The development of effective FL algorithms faces multiple practical challenges including data heterogeneity and clients' privacy protection. Despite that numerous attempts have been made to deal with data heterogeneity or rigorous privacy protection, none have effectively tackled both issues simultaneously. In this article, we propose a differentially private and heterogeneity-robust FL algorithm, named DP-FedCVR to mitigate the data heterogeneity by following the client-variance-reduction strategy. Besides, it adopts a sophisticated differential privacy (DP) mechanism where the privacy-amplified strategy is applied, to achieve a rigorous privacy protection guarantee. We show that the proposed DP-FedCVR algorithm maintains its heterogeneity-robustness though DP noises are incorporated, while achieving a sublinear convergence rate for a nonconvex FL problem. Numerical experiments based on image classification tasks are presented to demonstrate that DP-FedCVR provides superior performance over the benchmark algorithms in the presence of data heterogeneity and various DP privacy budgets. © 2020 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Feature and Performance Comparison of FaaS Platforms 14

Feature and Performance Comparison of FaaS Platforms

引用

14th IEEE International Conference on Software engineering and Service Science, ICSESS 2023

作者： Ma, Penghui Shi, Peichang Yi, Guodong College of Computer Science National University of Defense Technology National Key Laboratory of Parallel and Distributed Processing Changsha410073 China College of Computer Science National University of Defense Technology Key Laboratory of Software Engineering for Complex Systems Changsha410073 China Xiangjiang Lab Changsha410073 China School of Advanced Interdisciplinary Studies Hunan University of Technology and Business Changsha410073 China

ISBN: (纸本)9798350336269

With serverless computing offering more efficient and cost-effective application deployment, the diversity of serverless platforms presents challenges to users, including platform lock-in and costly migration. Moreover, due to the black box nature of function computing, traditional performance benchmarking methods are not applicable, necessitating new studies. This article presents a detailed comparison of six major public cloud function computing platforms and introduces a benchmarking framework for function computing performance. This framework aims to help users make comprehensive comparisons and select the most suitable platform for their specific needs. © 2023 IEEE.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

MPS: A Multiple Poisoned Samples Selection Strategy in Backdoor Attack

MPS: A Multiple Poisoned Samples Selection Strategy in Backd...

引用

IEEE International Conference on Trust, Security and Privacy in Computing and Communications (TrustCom)

作者： Weihong Zou Shigeng Zhang Weiping Wang Jian Zhang Xuan Liu Schoosl of Computer Science and Engineering Central South University Science and Technology on Parallel and Distributed Processing Laboratory (PDL) College of Computer Science and Electronic Engineering Hunan University

ISBN: (数字)9798350381993

ISBN: (纸本)9798350382006

Recently there has been many studies on backdoor attacks, which involve injecting poisoned samples into the training set in order to embed backdoors into the model. Existing multiple poisoned samples attacks usually randomly select a subset from clean samples to generate the poisoned samples. Filtering-and-Updating Strategy (FUS) has shown that the poisoning efficiency of each poisoned sample is inconsistent and random selection is not optimal. However, FUS does not fully considered the selection of multiple poisoned samples, there are still some issues with the selection of multiple poisoned samples. In this paper, we formulate the selection of multiple types of poisoned samples as a multi-objective optimization problem and proposed a Multiple Poisoned Samples Selection Strategy (MPS) to solve the issue. Unlike FUS, we consider the potential of clean samples that are not selected as to become efficient poisoned samples. Specifically, we use a weight-based contribution approach to calculate the contribution of each sample (clean sample and poisoned sample) during the training process from multiple dimensions. Finally, based on the greedy approach, we retain a subset of samples with the largest contribution in each dimension through iterations. We evaluate the effectiveness of MPS on various attack methods, including BadNet, Blended, ISSBA, and WaNet, as well as benchmark datasets. The experimental results on CIFAR-10 and GTSRB show that MPS can increase the attack strength by 1.45% to 18.34% compared to RSS and 0.43% to 10.84% compared to FUS in multiple poisoned samples attacks, thereby enhancing the stealthiness of the attack. Meanwhile, MPS is suitable for black-box settings, meaning that poisoned samples selected in one setting can be applied to other settings.

关键词： Training Data privacy Closed box Benchmark testing Security Protection Optimization

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：