检索结果-内蒙古大学图书馆

IEEE International Conference on Computational Science and Engineering, CSE

作者： Yonggang Che Chuanfu Xu Zhenghua Wang Institute for Quantum Information & State Key Lab. of High Performance Computing College of Computer National University of Defense Technology Changsha China Science and Technology on Parallel and Distributed Processing Lab National University of Defense Technology Changsha China

ISBN: (数字)9781665403986

ISBN: (纸本)9781665403993

This paper presents a load balancing method for a multi-block grids-based CFD (Computational Fluid Dynamics) application on heterogeneous platform. This method includes an asymmetric task scheduling scheme and a load balancing model. The idea is to balance the computing speed between the CPU and the coprocessor by adjusting the workload and the numbers of threads on both sides. Optimal load balance parameters are empirically selected, guided by a performance model. performance evaluation is conducted on a computer server consists of two Intel Xeon E5-2670 v3 CPUs and two MIC coprocessors (Xeon Phi 5110P and Xeon Phi 7120P) for the simulation of turbulent combustion in a supersonic combustor. The results show that the performance is highly sensitive to the load balance parameters. With the optimal parameters, the heterogeneous computing achieves a maximum speedup of 2.30 × for a 6-block mesh, and a maximum speedup of 2.66 × for a 8-block mesh, over the CPU-only computing.

关键词： Computational modeling Computational fluid dynamics Load management Servers Task analysis Load modeling Coprocessors

来源：评论

学校读者我要写书评

暂无评论

Improving unsupervised domain adaptation by reducing bi-level feature redundancy

arXiv

引用

arXiv 2020年

作者： Wang, Mengzhu Zhang, Xiang Lan, Long Wang, Wei Tan, Huibin Luo, Zhigang Science and Technology on Parallel and Distributed Laboratory College of Computer National University of Defense Technology Changsha China Institute for Quantum State Key Laboratory of High Performance Computing National University of Defense Technology Changsha China DUT-RU International School of Information Science & Engineering Dalian University of Technology DalianLiaoning116000 China Department of Science and Technology on Parallel and Distributed Processing National University of Defense Technology Changsha China

Reducing feature redundancy has shown beneficial effects for improving the accuracy of deep learning models, thus it is also indispensable for the models of unsupervised domain adaptation (UDA). Nevertheless, most recent efforts in the field of UDA ignore this point. Moreover, main schemes realizing this in general independent of UDA purely involve a single domain, thus might not be effective for cross-domain tasks. In this paper, we emphasize the significance of reducing feature redundancy for improving UDA in a bi-level way. For the first level, we try to ensure compact domain-specific features with a transferable decorrelated normalization module, which preserves specific domain information whilst easing the side effect of feature redundancy on the sequel domain-invariance. In the second level, domain-invariant feature redundancy caused by domain-shared representation is further mitigated via an alternative brand orthogonality for better generalization. These two novel aspects can be easily plugged into any BN-based backbone neural networks. Specifically, simply applying them to ResNet50 has achieved competitive performance to the state-of-the-arts on five popular benchmarks. Our code will be available at https://***/dreamkily/gUDA. © 2020, CC BY.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

parallel computing for large-scale author name disambiguation in medline 21

Parallel computing for large-scale author name disambiguatio...

引用

21st IEEE International Conference on high performance Computing and Communications, 17th IEEE International Conference on Smart City and 5th IEEE International Conference on Data Science and systems, HPCC/SmartCity/DSS 2019

作者： Tang, Anyao Wu, Chengkun Liu, Jie Wang, Wei Yang, Xi Xing, Yuting Science and Technology on Parallel and Distributed Processing Laboratory Laboratory of Software Engineering for Complex Systems National University of Defense Technology Changsha410073 China State Key Laboratory of High Performance Computing College of Computer National University of Defense Technology Changsha410073 China College of Computer National University of Defense Technology Changsha 410073 China

ISBN: (纸本)9781728120584

Author name disambiguation (AND) is an important task in the field of scientific data mining. It has become a great challenge with the rapid growth of academic digital libraries. The task of AND for a large number of authors is computationally intensive. In particular, an author's name in MEDLINE is represented by full last name and initials, like 'Zhang S', which leads to a lot of identical strings that actually represent different names. In this paper, we proposed an efficient algorithm for parallel AND computation. The proposed algorithm mainly addresses the load balancing issue across many computing nodes. It involves the following strategies:(1) Author-based load balancing, which splits the computation load for each core by author name labels. (2) Matrix-based strategy, which calculates the pairwise similarity between publications and saves them in a matrix globally shared by all processes. Then group them by width-first search. We combine the above two strategies, the second of which is used to calculate authors with a large number of documents, and the other authors apply the first. We constructed a publications database written by Chinese authors from MEDLINE, the biggest public database for biomedical literature (abstracts). For benchmark testing, we experimented our algorithm with a dataset of 1 million publications on the Tianhe-2A supercomputer. Firstly, we trained an AND classifier that can achieve 98.1% of F1. The serial computation time is estimated to be approximately 246 hours, while the parallel execution time is approximately 66 hours in the case of four cores on a single node (with a speedup of 3.7x). Finally, we reduced the total parallel computing time of 1 million documents to about 2 hours and achieved 65.8% of parallelism efficiency using 200 cores on 90 nodes. © 2019 IEEE.

关键词： Matrix algebra

来源：评论

学校读者我要写书评

暂无评论

Density-Attentive Head Detector for Crowd Counting

Density-Attentive Head Detector for Crowd Counting

引用

International Conference on Data Science and Business Analytics (ICDSBA)

作者： Ziyu Zhao Xingyu Shen Long Lan Xiaoyao Yin Xiang Zhang Yonggang Che Zhigang Luo College of Computer National University of Defense Technology Changsha China Institute for Quantum Information & State Key Laboratory of High Performance Computing National University of Defense Technology Changsha China Science and Technology on Parallel and Distributed Processing National University of Defense Technology Changsha China

ISBN: (数字)9781728146447

ISBN: (纸本)9781728146454

In crowd counting, regression-based method shows better performance in extreme density scenes by introduces a density map. However, the regression-based method fails to locate the positions of each head, which significantly restricts its applications. Detection-based method counts each head with their accurate locations but works only in middle or low-level density scenes. In this paper, a joint learning method, named Density-attentive Head Detector (DAHD) is developed to overcome their respective shortcomings via a multi-task training procedure. Specifically, to guarantee the sensitivity of the detector to small or partially occluded heads, we carefully equip the detector with a density map which learned from regression module. Moreover, a novel Dilated Feature Pyramid Network (DFPN) is introduced to our method to enlarge the receptive field of convolutional kernel, bringing confirmative additional benefits to identify small heads. Experiments on the popular ShanghaiTech and Mall datasets confirm the improved performance of DAHD compared with the current detection-based approaches, and a comparable performance to regression-based approaches in term of counting.

关键词： Detectors Feature extraction Object detection Faces Kernel Training Task analysis

来源：评论

学校读者我要写书评

暂无评论

Phase Transition in Taxi Dynamics and Impact of Ridesharing

arXiv

引用

arXiv 2018年

作者： Yang, Bo Ren, Shen Legara, Erika Fille Li, Zengxiang Ong, Edward Y.X. Lin, Louis Monterola, Christopher Complex Systems Group Institute of High Performance Computing A-STAR 138632 Singapore Institute of High Performance Computing Distributed Computing A-STAR 138632 Singapore Land Transport Division Ministry of Transport 119903 Singapore Asian Institute of Management Technology and Entrepreneurship School of Innovation Manila Philippines

We develop a numerical model using both artificial and empirical inputs to analyze taxi dynamics in an urban setting. More specifically, we quantify how the supply and demand for taxi services, the underlying road network, and the public acceptance of taxi ridesharing (TRS) affect the optimal number of taxis for a particular city, as well as commuters' average waiting time and trip time. Results reveal certain universal features of the taxi dynamics with real-time taxi-booking|that there is a well-defined transition between the oversaturated phase when demand exceeds supply, and the undersaturated phase when supply exceeds demand. The boundary between the two phases gives the optimal number of taxis a city should accommodate, given the specific demand, road network and commuter habits. Adding or removing taxis may affect commuter experience very differently in the two phases revealed. In the oversaturated phase the average waiting time is affected exponentially, while in the undersaturated phase it is affected sub-linearly. We analyze various factors that can shift the phase boundary, and show that an increased level of acceptance for TRS universally shifts the phase boundary by reducing the number of taxis needed. We discuss some of the useful insights on the benefits and costs of TRS, especially how under certain situations TRS will not only have economic benefits for commuters, but can also save the overall travel time for the shared parties, by significantly reducing the time commuters spend on waiting for taxis. Our simulations also suggest that simple artificial taxi systems can capture most of the universal features of the taxi dynamics. The relevance of the assumptions and the overall methodology are also illustrated using the empirical road network and taxi demand in Singapore. Copyright © 2018, The Authors. All rights reserved.

关键词： Taxicabs

来源：评论

学校读者我要写书评

暂无评论

Towards Understanding Optimal Load-Balancing of Heterogeneous Short-Range Molecular Dynamics

Towards Understanding Optimal Load-Balancing of Heterogeneou...

引用

IEEE International Conference on high performance Computing Workshops (HiPCW)

作者： Steffen Hirschmann Dirk Pflüger Colin W. Glass Institute for Parallel and Distributed Systems University of Stuttgart Stuttgart Germany High Performance Computing Center Stuttgart University of Stuttgart Stuttgart Germany

ISBN: (纸本)9781509057740

For heterogeneous dynamic short-range molecular dynamics simulations it is critical to employ suitable load-balancing methods to minimize the time to solution. However, designing and parametrizing the optimal load-balancing method is a complex task, depending on detailed properties of the simulation *** main challenge in balancing the load of molecular dynamics simulations is the extreme difference in load density for scenarios with heterogeneous particle density, which can easily reach 4-6 orders of magnitude. Therefore, heterogeneity is deemed to be a relevant property and a suitable metric to reliably quantifying heterogeneity is formulated. This metric, which is based on binning particles and evaluating statistical moments, is then applied to example scenarios and correlated to the performance of five load balancing methodologies. Furthermore, how rapidly the load varies over time will determine how long the benefits of a specific partitioning are expected to last. We deem this to be another relevant property, the dynamics, and introduce corresponding metrics. The results indicate that these metric are useful to differentiate between scenarios and facilitate reasoning over the complex relationship between particle simulation scenarios and optimal load balancing methods. This work is a first step towards understanding this relationship, while introducing key concepts we regard as a crucial for this understanding.

关键词： Load modeling Computational modeling Measurement Dynamics Force Partitioning algorithms Load management

来源：评论

学校读者我要写书评

暂无评论

Policy-Driven Configuration Management for NoSQL

Policy-Driven Configuration Management for NoSQL

引用

IEEE International Conference on Cloud Computing, CLOUD

作者： Xianqiang Bao Ling Liu Nong Xiao Yang Zhou Qi Zhang State Key Laboratory of High Performance Computing National University of Defense Technology Hunan China Distributed Data Intensive Systems Lab Georgia Institute of Technology Atlanta Georgia USA

NoSQL systems have become the vital components to deliver big data services in the Cloud. However, existing NoSQL systems rely on experienced administrators to configure and tune the wide range of configurable parameters in order to achieve high performance. In this paper, we present a policy-driven configuration management system for NoSQL systems, called PCM. PCM can identify workload sensitive configuration parameters and capture the tuned parameters for different workloads as configuration policies. PCM also can be used to analyze the range of configuration parameters that may impact on the runtime performance of NoSQL systems in terms of read and write workloads. The configuration optimization recommended by PCM can enable NoSQL systems such as HBase to run much more efficiently than the default settings for both individual worker node and entire cluster in the Cloud. Our experimental results show that HBase under the PCM configuration outperforms the default configuration and some simple configurations on a range of workloads with offering significantly higher throughput.

关键词： Phase change materials Tuning Throughput Loading Compaction Optimization Monitoring

来源：评论

学校读者我要写书评

暂无评论

WPress: An Application-Driven performance Benchmark for Cloud-Based Virtual Machines

WPress: An Application-Driven Performance Benchmark for Clou...

引用

International Conference on Enterprise distributed Object Computing (EDOC)

作者： Amir Hossein Borhani Philipp Leitner Bu-Sung Lee Xiaorong Li Terence Hung Institute of High-Performance Computing (IHPC) Singapore s.e.a.l. software evolution & architecture lab University of Zurich Switzerland Parallel and Distributed Computing Center (PDCC) Nanyang Technological University Singapore

ISBN: (纸本)9781479954711

Approaching a comprehensive performance benchmark for on-line transaction processing (OLTP) applications in a cloud environment is a challenging task. Fundamental features of clouds, such as the pay-as-you-go pricing model and unknown underlying configuration of the system, are contrary to the basic assumptions of available benchmarks such as TPC-W or RUBiS. In this paper, we introduce a systematic performance benchmark approach for OLTP applications on public clouds that use virtual machines(VMs). We propose WPress benchmark, which is based on the widespread blogging software, WordPress, as a representative OLTP application and implement an open source workload generator. Furthermore, we utilize a CPU micro-benchmark to investigate CPU performance of cloud-based VMs in greater detail. Average response time and total VM cost are the performance metrics measured by WPress. We evaluate small and large instance types of three real-life cloud providers, Amazon EC2, Microsoft Azure and Rackspace cloud. Results imply that Rackspace cloud has better average response times and total VM cost on small instances. However, Microsoft Azure is preferable for large instance type.

关键词： Benchmark testing Cloud computing Time factors Servers Databases Blogs Publishing

来源：评论

学校读者我要写书评

暂无评论

TRANSDUCTIVE NONNEGATIVE MATRIX FACTORIZATION FOR SEMI-SUPERVISED high-performance SPEECH SEPARATION

TRANSDUCTIVE NONNEGATIVE MATRIX FACTORIZATION FOR SEMI-SUPER...

引用

IEEE International Conference on Acoustics, Speech and Signal Processing

作者： Naiyang Guan Long Lan Dacheng Tao Zhigang Luo Xuejun Yang Science and Technology on Parallel and Distributed Processing Laboratory School of Computer Science National University of Defense Technology Changsha Hunan 410073 China Centre for Quantum Computation and Intelligent Systems FEIT University of Technology Sydney Sydney NSW 2007 Australia State Key Laboratory of High Performance Computing National University of Defense Technology Changsha Hunan 410073 China

ISBN: (纸本)9781479928941

Regarding the non-negativity property of the magnitude spectrogram of speech signals, nonnegative matrix factorization (NMF) has obtained promising performance for speech separation by independently learning a dictionary on the speech signals of each known speaker. However, traditional NM-F fails to represent the mixture signals accurately because the dictionaries for speakers are learned in the absence of mixture signals. In this paper, we propose a new transductive NMF algorithm (TNMF) to jointly learn a dictionary on both speech signals of each speaker and the mixture signals to be separated. Since TNMF learns a more descriptive dictionary by encoding the mixture signals than that learned by NMF, it significantly boosts the separation performance. Experiments results on a popular TIMIT dataset show that the proposed TNMF-based methods outperform traditional NMF-based methods for separating the monophonic mixtures of speech signals of known speakers.

关键词： Speech Dictionaries as Topic Loudspeakers NMF protocol signals mixtures factorization high-performance

来源：评论

学校读者我要写书评

暂无评论

Encoder-free odometric system for autonomous microrobots

Encoder-free odometric system for autonomous microrobots

引用

作者： Kernbach, Serge Institute of Parallel and Distributed High-Performance Systems University of Stuttgart Universitaetsstr. 38 70569 Stuttgart Germany

This paper describes an odometric system for autonomous microrobots based on the optical properties of a motor-wheel transmission for motion feedback. We demonstrate that infra-red light, reflected from this mechanical system, shows distinctive periodic changes of amplitude, correlated with the motion of the robot. Real-time odometric signal processing, performed on a small embedded microcontroller, allows accurate movement detection for each wheel and is used for motion control, self-calibration, and calculation of differential and absolute velocity, displacement and rotation. We demonstrate some applications of this on-board odometric system in swarm robot experiments. This approach can also be applied to other industrial or academic mechatronic systems, where size or computational power are limiting factors. © 2012 Elsevier Ltd. All rights reserved.

关键词： Signal encoding

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：