检索结果-内蒙古大学图书馆

Detecting faults by tracing companion states in cloud computing systems

Jisuanji Xuebao/Chinese Journal of Computers 2012年第5期35卷 856-870页

作者： Rao, Xiang Wang, Huai-Min Chen, Zhen-Bang Zhou, Yang-Fan Cai, Hua Zhou, Qi Sun, Ting-Tao National Key Laboratory for Parallel and Distributed Processing National University of Defense Technology Changsha 410073 China Shenzhen Research Institute The Chinese University of Hong Kong Shenzhen China Department of Computing Platform Alibaba Cloud Computing Company Hangzhou 310011 China

A common way to construct a fault model is injecting the fault into the system and observing the subsequent symptoms, e. g. event logs. However, fault features would vary during the propagation period, and present different symptoms at different stage of the fault propagation process. The exiting detection window based feature extraction methods can only identify the early symptoms of a fault, but fail to detect the latter symptoms and cause false alarms. To solve the problem, we present a fault feature extraction method, called Companion State Tracer (CSTracer), which consists of 3 integrated steps: (1) pre-process logs to remove the unrelated logs;(2) construct a general identifier for the early symptoms of a fault;(3) construct a finite state machine model for the fault to trace the latter symptoms. CSTracer can persistently monitor a fault after the fault has been identified. We have justified the effectiveness of CSTracer in an enterprise cloud system. Compared with the existing, the results show that CSTracer has a better detection accuracy.

关键词： Fault detection

来源：评论

学校读者我要写书评

暂无评论

Topology-Aware Deployment of Scientific Applications in Cloud Computing

Topology-Aware Deployment of Scientific Applications in Clou...

引用

IEEE International Conference on Cloud Computing, CLOUD

作者： Pei Fan Zhenbang Chen Ji Wang Zibin Zheng Michael R. Lyu National Laboratory for Parallel & Distributed Processing National University of Defense Technology Changsha P.R.China Dept. of Computer Science & Engineering The Chinese University of Hong Kong Hong Kong China

Nowadays, more and more scientific applications are moving to cloud computing. The optimal deployment of scientific applications is critical for providing good services to users. Scientific applications are usually topology-aware applications. Therefore, considering the topology of a scientific application during the development will benefit the performance of the application. However, it is challenging to automatically discover and make use of the communication pattern of a scientific application while deploying the application on cloud. To attack this challenge, in this paper, we propose a framework to discover the communication topology of a scientific application by pre-execution and multi-scale graph clustering, based on which the deployment can be optimized. Comprehensive experiments are conducted by employing a well-known MPI benchmark and comparing the performance of our method with those of other methods. The experimental results show the effectiveness of our topology-aware deployment method.

关键词： Topology Clustering algorithms Benchmark testing Cloud computing Partitioning algorithms Clustering methods Throughput

来源：评论

学校读者我要写书评

暂无评论

Towards Vision Transformer Unrolling Fixed-Point Algorithm: a Case Study on Image Restoration

arXiv

引用

arXiv 2023年

作者： Qiao, Peng Liu, Sidun Sun, Tao Yang, Ke Dou, Yong The Science and Technology on Parallel and Distributed Laboratory School of Computer National University of Defense Technology Changsha China National Innovation Institute of Defense Technology Beijing China

The great success of Deep Neural Networks (DNNs) has inspired the algorithmic development of DNN-based Fixed-Point (DNN-FP) for computer vision tasks. DNN-FP methods, trained by Back-Propagation Through Time or computing the inaccurate inversion of the Jacobian, suffer from inferior representation ability. Motivated by the representation power of the Transformer, we propose a framework to unroll the FP and approximate each unrolled process via Transformer blocks, called FPformer. To reduce the high consumption of memory and computation, we come up with FPRformer by sharing parameters between the successive blocks. We further design a module to adapt Anderson acceleration to FPRformer to enlarge the unrolled iterations and improve the performance, called FPAformer. In order to fully exploit the capability of the Transformer, we apply the proposed model to image restoration, using self-supervised pre-training and supervised fine-tuning. 161 tasks from 4 categories of image restoration problems are used in the pre-training phase. Hereafter, the pre-trained FPformer, FPRformer, and FPAformer are further fine-tuned for the comparison scenarios. Using self-supervised pre-training and supervised fine-tuning, the proposed FPformer, FPRformer, and FPAformer achieve competitive performance with state-of-the-art image restoration methods and better training efficiency. FPAformer employs only 29.82% parameters used in SwinIR models, and provides superior performance after fine-tuning. To train these comparison models, it takes only 26.9% time used for training SwinIR models. It provides a promising way to introduce the Transformer in low-level vision tasks. © 2023, CC BY.

关键词： Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Audio Tagging by Cross Filtering Noisy Labels

arXiv

引用

arXiv 2020年

作者： Zhu, Boqing Xu, Kele Kong, Qiuqiang Wang, Huaimin Peng, Yuxing Science and Technology on Parallel and Distributed Laboratory National University of Defense Technology Changsha410073 China Centre for Vision Speech and Signal Processing University of Surrey GuildfordGU2 7XH United Kingdom

—High quality labeled datasets have allowed deep learning to achieve impressive results on many sound analysis tasks. Yet, it is labor-intensive to accurately annotate large amount of audio data, and the dataset may contain noisy labels in the practical settings. Meanwhile, the deep neural networks are susceptive to those incorrect labeled data because of their outstanding memorization ability. In this paper, we present a novel framework, named CrossFilter, to combat the noisy labels problem for audio tagging. Multiple representations (such as, Logmel and MFCC) are used as the input of our framework for providing more complementary information of the audio. Then, though the cooperation and interaction of two neural networks, we divide the dataset into curated and noisy subsets by incrementally pick out the possibly correctly labeled data from the noisy data. Moreover, our approach leverages the multitask learning on curated and noisy subsets with different loss function to fully utilize the entire dataset. The noisy-robust loss function is employed to alleviate the adverse effects of incorrect labels. On both the audio tagging datasets FSDKaggle2018 and FSDKaggle2019, empirical results demonstrate the performance improvement compared with other competing approaches. On FSDKaggle2018 dataset, our method achieves state-of-the-art performance and even surpasses the ensemble models. Copyright © 2020, The Authors. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

GNNRL-Smoothing: A Prior-Free Reinforcement Learning Model for Mesh Smoothing

arXiv

引用

arXiv 2024年

作者： Wang, Zhichao C. Chen, Xinhai C. Gong, Chunye Y. Yang, Bo Deng, Liang Sun, Yufei F. Pang, Yufei F. Liu, Jie National University of Defense Technology Science and Technology on Parallel and Distributed Processing Laboratory China National University of Defense Technology Laboratory of Digitizing Software for Frontier Equipment China China Aerodynamics Research and Development Center China Nankai University College of Software China

Mesh smoothing methods can enhance mesh quality by eliminating distorted elements, leading to improved convergence in simulations. To balance the efficiency and robustness of traditional mesh smoothing process, previous approaches have employed supervised learning and reinforcement learning to train intelligent smoothing models. However, these methods heavily rely on labeled dataset or prior knowledge to guide the models’ learning. Furthermore, their limited capacity to enhance mesh connectivity often restricts the effectiveness of smoothing. In this paper, we first systematically analyze the learning mechanisms of recent intelligent smoothing methods and propose a prior-free reinforcement learning model for intelligent mesh smoothing. Our proposed model integrates graph neural networks with reinforcement learning to implement an intelligent node smoothing agent and introduces, for the first time, a mesh connectivity improvement agent. We formalize mesh optimization as a Markov Decision Process and successfully train both agents using Twin Delayed Deep Deterministic Policy Gradient and Double Dueling Deep Q-Network in the absence of any prior data or knowledge. We verified the proposed model on both 2D and 3D meshes. Experimental results demonstrate that our model achieves feature-preserving smoothing on complex 3D surface meshes. It also achieves state-of-the-art results among intelligent smoothing methods on 2D meshes and is 7.16 times faster than traditional optimization-based smoothing methods. Moreover, the connectivity improvement agent can effectively enhance the quality distribution of the mesh. © 2024, CC BY.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Hierarchical diagnostic approach for performance problems in cloud computing platforms

引用

Tongxin Xuebao/Journal on Communications 2011年第7期32卷 114-124页

作者： Mi, Hai-Bo Wang, Huai-Min Cai, Hua Yin, Gang Zhou, Qi Sun, Ting-Tao Zhou, Yang-Fan National Laboratory for Parallel and Distributed Processing National University of Defense Technology Changsha 410073 China Computing Platform Alibaba Cloud Computing Company Hangzhou 310023 China Shenzhen Research Institute Chinese Univ. of Hong Kong Shenzhen 518057 China

A hierarchical diagnosis approach, namely Magnifier, was proposed, which models the execution path graph of a user request as component layer, module layer and function layer, and detects anomalies from higher layer to lower layer separately. Extensive experiments were conducted on the Alibaba cloud computing platform. The results indicate that, under the conditions of large volume of data and high complexity of execution paths, Magnifier can accurately and efficiently locate the prime causes of performance degradation.

关键词： Cloud computing

来源：评论

学校读者我要写书评

暂无评论

Single image defogging with single and multiple hybrid scattering model

Single image defogging with single and multiple hybrid scatt...

引用

International Conference on Security, Pattern Analysis, and Cybernetics (SPAC)

作者： Weijiang Feng Naiyang Guan Xiang Zhang Xuhui Huang Zhigang Luo Science and Technology on Parallel and Distributed Processing Laboratory College of Computer National University of Defense Technology Changsha Hunan P.R. China Department of Computer Science and Technology College of Computer National University of Defense Technology Changsha Hunan P.R. China

Image defogging (IDF) removes influences of fogs from an image to improve its quality. Since defogged images can significantly boost the performance of subsequent processing, IDF has attracted many attentions from the computer vision community. However, existing IDF algorithms are built on the assumption that light is scattered once by a grain. Since such assumption is violated if images are contaminated by dense haze or heavy fog, traditional IDF algorithms often fail in this situation. In this paper, we propose a hybrid image defogging (HIDF) algorithm to overcome this deficiency. In particular, HIDF applies the single scattering physics model (SSPM) to pixels dominated by single scattering of light, and applies the multiple scattering physics model (MSPM) to remaining pixels. To distinguish two types of pixels, HIDF utilizes the optical thickness of corresponding pixels. If optical thickness is smaller than a threshold that determines whether the single scattering or the multiple scattering dominates, HIDF applies the SSPM, and HIDF applies the MSPM otherwise. Experimental results on several popular foggy images demonstrate that HIDF competes with the state-of-the-art algorithms, and show the promise of HIDF for defogging heavily foggy images.

关键词： Meteorology Optical imaging Optical scattering Atmospheric modeling Image color analysis

来源：评论

学校读者我要写书评

暂无评论

Power and performance analysis of the Graph 500 benchmark on the Single-chip Cloud Computer

Power and performance analysis of the Graph 500 benchmark on...

引用

International Conference on Cloud Computing and Internet of Things (CCIOT)

作者： Zhiquan Lai King Tin Lam Cho-Li Wang Jinshu Su College of Computer National University of Defense Technology Changsha China Department of Computer Science The University of Hong Kong Hong Kong China National Key Laboratory of Parallel and Distributed Processing (PDL) Changsha China

ISBN: (纸本)9781479947638

The concerns of data-intensiveness and energy awareness are actively reshaping the design of high-performance computing (HPC) systems nowadays. The Graph500 is a widely adopted benchmark for evaluating the performance of computing systems for data-intensive workloads. In this paper, we introduce a data-parallel implementation of Graph500 on the Intel Single-chip Cloud Computer (SCC). The SCC features a non-coherent many-core architecture and multi-domain on-chip DVFS support for dynamic power management. With our custom-made shared virtual memory programming library, memory sharing among threads is done efficiently via the shared physical memory (SPM) while the library has taken care of the coherence. We conduct an in-depth study on the power and performance characteristics of the Graph500 workloads running on this system with varying system scales and power states. Our experimental results are insightful for the design of energy-efficient many-core systems for data-intensive applications.

关键词： Kernel Benchmark testing Computer architecture Programming Power measurement Computational modeling Runtime

来源：评论

学校读者我要写书评

暂无评论

Inverse dynamics of speech motor control 93

Inverse dynamics of speech motor control

引用

Proceedings of the 7th International Conference on Neural Information processing Systems

作者： Makoto Hirayama Eric Vatikiotis-Bateson Mitsuo Kawato ATR Human Information Processing Research Laboratories Kyoto Japan ATR Human Information Processing Research Laboratories Kyoto Japan and Laboratory of Parallel Distributed Processing Research Institute for Electronic Science Hokkaido University Sapporo Hokkaido Japan

Progress has been made in computational implementation of speech production based on physiological data. An inverse dynamics model of the speech articulator's musculo-skeletal system, which is the mapping from articulator trajectories to electromyographic (EMG) signals, was modeled using the acquired forward dynamics model and temporal (smoothness of EMG activation) and range constraints. This inverse dynamics model allows the use of a faster speech motor control scheme, which can be applied to phoneme-to-speech synthesis via musclo-skeletal system dynamics, or to future use in speech recognition. The forward acoustic model, which is the mapping from articulator trajectories to the acoustic parameters, was improved by adding velocity and voicing information inputs to distinguish acoustic parameter differences caused by changes in source characteristics.

关键词：

来源：评论

学校读者我要写书评

暂无评论

RAFlow: Read Ahead Accelerated I/O Flow through Multiple Virtual Layers

RAFlow: Read Ahead Accelerated I/O Flow through Multiple Vir...

引用

International Conference on Networking, Architecture, and Storage (NAS)

作者： Zhaoning Zhang Kui Wu Huiba Li Jinghua Feng Yuxing Peng Xicheng Lu National Key Laboratory for Parallel and Distributed Processing National University of Defense Technology China Computer Science Department University of Victoria B.C. Canada National Super Computing Center Tianjin China

Virtualization is the foundation for cloud computing, and the virtualization can not be achieved without software defined, elastic, flexible and scalable virtual layers. Unfortunately, if multiple virtual storage devices are chained together, the system may be subject to severe performance degradation. While the read-ahead (RA) mechanism in storage devices plays a very important role to improve I/O performance, RA may not be effective as expected for multiple virtualization layers, since it is originally designed for one layer only. When I/O requests are passed through a long I/O path, they may trigger a chain reaction and lead to unnecessary data transmission and thus bandwidth waste. In this paper, we study the dynamic behavior of RA through multiple I/O layers and demonstrate that if controlled well, RA can greatly accelerate I/O speed. We present RAFlow, a RA control mechanism, to effectively improve I/O performance by strategically expanding RA window at each layer. Our real-world experiments show that it can achieve 20% to 50% performance improvement in I/O paths with up to 8 virtualized storage devices.

关键词： Radio access networks Acceleration distributed databases Performance evaluation Synchronization Benchmark testing Degradation

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：