检索结果-内蒙古大学图书馆

Data Science Session at the 5th International Conference on Information Technology and Nanotechnology, DS-ITNT 2019

作者： Zakharov, V.M. Shalagin, S.V. Eminov, B.F. Kazan National Research Technical University named after A.N. Tupolev Karl Marks 10 Kazan420111 Russia

The problem of processing images, i. e., two-dimensional data arrays, was solved through implementing two-dimensional fast Fourier transform (FFT) when using single-type hardware modules – IP-cores in the Virtex-6 FPGA architecture. We have shown the possibility of the parallel implementation of each stage in the two-dimensional FFT, based on four "butterfly"-type transforms (BTr) over four elements of the data array being processed. Estimations were obtained regarding time- and hardware complexity of the IP-core implementing BTrs and used in implementing the one-dimensional FFT. The results obtained can be used in estimating hardware and time consumption when performing a two-dimensional FFT over an array of the pre-defined dimensionality in using existing and forthcoming distributed programmable-architecture systems. © 2019 CEUR workshop Proceedings.

关键词： Intellectual property core

来源：评论

学校读者我要写书评

暂无评论

Event-based Cooperation of Functional Networking Components in distributed Technological systems

Event-based Cooperation of Functional Networking Components ...

引用

Moscow workshop on Electronic and Networking Technologies (MWENT)

作者： Valery A. Kokovin Alexander A. Evsikov Saygid U. Uvaysov Svetlana S. Uvaysova Department of Automation of Technological Processes State University "Dubna" branch "Protvino" Protvino Moscow reg. Russia Department of Design and Production of Radio-Electronic Means MIREA – Russian Technological University Moscow Russia School of Computer Engineering Higher School of Economics Moscow Russia

ISBN: (数字)9781728125725

ISBN: (纸本)9781728125732

The paper defines a new class of network devices Functional Networking Components (FNC). FNC can receive and process information (the presence of a computer with network ports), the FNC has a physical nature (mechanics), and it is able to affect the physical environment. The FNC mechanisms that allow processing input information from sensors and generate events and messages are examined, as well as the requirements for them are determined. The paper analyzes the advantages of using FNC computers based on a traditional microcontroller (ARM as an example) with the addition of a hardware accelerator on FPGA for processing fast processes. A simplified block diagram of the event's generator, messages and synchronization is given.

关键词： Field programmable gate arrays Synchronization Protocols IEC Standards Generators real-time systems Software

来源：评论

学校读者我要写书评

暂无评论

Using DCT-based Approximate Communication to Improve MPI Performance in parallel Clusters 38

Using DCT-based Approximate Communication to Improve MPI Per...

引用

IEEE 38th International Performance Computing and Communications Conference (IPCCC)

作者： Fan, Qianqian Lilja, David J. Sapatnekar, Sachin S. Univ Minnesota Dept Elect & Comp Engn Minneapolis MN 55455 USA

ISBN: (纸本)9781728110257

Communication overheads in distributed systems constitute a large fraction of the total execution time, and limit the scalability of applications running on these systems. We propose a DCT-based approximate communication scheme that takes advantage of the error resiliency of several widely-used applications, and improves communication efficiency by substantially reducing message lengths. Our scheme is implemented into the Message Passing Interface (MPI) library. When evaluated on several representative MPI applications on a real cluster system, it is seen that the fraction of total execution time devoted to communication reduces from 59% to 23%, even accounting for the computational overhead required for DCT encoding. For many communication-intensive applications, it is shown that our approximate communication scheme effectively speeds up the total execution time without much loss in quality of the result.

关键词： Message passing

来源：评论

学校读者我要写书评

暂无评论

Core-sets: An updated survey

引用

WILEY INTERDISCIPLINARY REVIEWS-DATA MINING AND KNOWLEDGE DISCOVERY 2020年第1期10卷

作者： Feldman, Dan Univ Haifa Comp Sci Dept IL-3498838 Haifa Israel

In optimization or machine learning problems we are given a set of items, usually points in some metric space, and the goal is to minimize or maximize an objective function over some space of candidate solutions. For example, in clustering problems, the input is a set of points in some metric space, and a common goal is to compute a set of centers in some other space (points, lines) that will minimize the sum of distances to these points. In database queries, we may need to compute such a some for a specific query set of k centers. However, traditional algorithms cannot handle modern systems that require parallel real-time computations of infinite distributed streams from sensors such as GPS, audio or video that arrive to a cloud, or networks of weaker devices such as smartphones or robots. Core-set is a "small data" summarization of the input "big data," where every possible query has approximately the same answer on both data sets. Generic techniques enable efficient coreset maintenance of streaming, distributed and dynamic data. Traditional algorithms can then be applied on these coresets to maintain the approximated optimal solutions. The challenge is to design coresets with provable tradeoff between their size and approximation error. This survey summarizes such constructions in a retrospective way, that aims to unified and simplify the state-of-the-art. This article is categorized under Algorithmic Development > Structure Discovery Fundamental Concepts of Data and Knowledge > Big Data Mining Technologies > Machine Learning Algorithmic Development > Scalable Statistical Methods

关键词： big data cloud coresets distributed computation streaming

来源：评论

学校读者我要写书评

暂无评论

GPU-based parallel real-time volt/var optimisation for distribution network considering distributed generators

引用

IET GENERATION TRANSMISSION & DISTRIBUTION 2018年第20期12卷 4472-4481页

作者： Huang, Shengjun Dinavahi, Venkata Univ Alberta Dept Elect & Comp Engn Edmonton AB T6G 2V4 Canada Natl Univ Def Technol Coll Informat Syst & Management Changsha 410073 Hunan Peoples R China

Although the wide integration of advanced metering infrastructure on distribution network facilitates the application of volt/var optimisation (VVO) in real-time circumstance, the contradiction between heavy computation load and low solution efficiency is still a big challenge, thus the system scales investigated in the literature are limited. In this study, the full AC real-time VVO is formulated based on particle swarm optimisation (PSO) framework and direct approach (DA) power flow method, where all components, such as distributed generator and on-load tap changer transformer, are formulated and integrated into the iterative DA process. Since both PSO and DA are suitable for parallel implementation, the graphics processing unit (GPU) is introduced for acceleration in order to achieve the possibility for real-time application. All the solution process is executed by GPU with the well-established data structure and thread organisation pattern, resulting in high efficiency by guaranteeing coalesced access within each warp. Case studies are conducted on four systems with sizes ranging from 136-bus to 1760-bus. Solution accuracy and convergence property are validated by the popular open source package Matpower. Based on the results from solution efficiency comparison between CPU sequential, CPU parallel, and GPU parallel programs, the promise of the proposed parallel implementation scheme for practical application is established.

关键词： distribution networks distributed power generation particle swarm optimisation graphics processing units parallel programming data structures load flow on load tap changers iterative methods public domain software software packages power engineering computing GPU-based parallel real-time volt-var optimisation distribution network distributed generators advanced metering infrastructure full AC real-time VVO particle swarm optimisation framework PSO framework direct approach power flow method DA power flow method distributed generator on-load tap changer transformer iterative DA process graphics processing unit data structure thread organisation pattern Matpower open source package CPU sequential program CPU parallel program GPU parallel program

来源：评论

学校读者我要写书评

暂无评论

A Simulation Workflow to Evaluate the Performance of Dynamic Load Balancing with Over-decomposition for Iterative parallel Applications

A Simulation Workflow to Evaluate the Performance of Dynamic...

引用

作者： Rafael Keller Tesser UNIVERSIDADE FEDERAL DO RIO GRANDE

学位级别：博士

In this thesis we present a novel simulation workflow to evaluate the performance of dynamic load balancing with over-decomposition applied to iterative parallel applications at low-cost. Its goals are to perform such evaluation with minimal application modification and at a low cost in terms of time and of resource requirements. Many parallel applications suffer from dynamic (temporal) load imbalance that can not be treated at the application level. It may be caused by intrinsic characteristics of the application or by external software and hardware factors. As demonstrated in this thesis, such dynamic imbalance can be found even in applications whose codes do not hint at any dynamism. Therefore, we need to rely on runtime dynamic load balancing mechanisms, such as dynamic load balancing based on over-decomposition. The problem is that evaluating and tuning the performance of such technique can be costly. This usually entails modifications to the application and a large number of executions to get statistically sound performance measurements with different load balancing parameter combinations. Moreover, useful and accurate measurements often require big resource allocations on a production cluster. Our simulation workflow, dubbed Simulated Adaptive MPI (SAMPI), employs a combined sequential emulation and trace-replay simulation approach to reduce the cost of such an evaluation. Both sequential emulation and trace-replay require a single computer node. Additionally, the trace-replay simulation lasts a small fraction of the real-life parallel execution time of the application. Besides the basic SAMPI simulation, we developed spatial aggregation and application- level rescaling techniques to speed-up the emulation process. To demonstrate the real-life performance benefits of dynamic load balance with over-decomposition, we evaluated the performance gains obtained by employing this technique on a iterative parallel geophysics application, called Ondes3D. Dynamic load

关键词： parallel computing high-performance computing performance evaluation dynamic load balancing over-decomposition simulation of distributed systems iterative applications SimGrid AMPI Charm++

来源：评论

学校读者我要写书评

暂无评论

Boosted Trees Model with Feature Engineering: An Approach for Post-Click Conversion Rate Prediction 19

Boosted Trees Model with Feature Engineering: An Approach fo...

引用

2nd International Conference on Big Data Technologies (ICBDT) / 3rd International Conference on Business Information systems workshop (ICBIS)

作者： Du, Guanglei Chen, Yang Wang, Xu Natl Univ Def Technol Sci & Technol Parallel & Distributed Lab Changsha Peoples R China

ISBN: (纸本)9781450371926

The post-click conversion rate (CVR) prediction is important for the sponsored search engine. The predicted CVR can guide people on how to choose the advertisements to display, and greatly affects the revenue of the electronic business platform and merchants who pay for the advertisement. In this paper, we describe a new approach to solve the CVR prediction problem in sponsored search. The approach is Boosted Trees Model with Feature Engineering (BTMFE), which incorporates the power of feature engineering as well as the boosted trees. We discuss different issues such as feature importance, feature interaction, historical information fusion and boosted trees algorithm. Finally, we compare BTMFE with other methods and present experimental results on real-world datasets.

关键词： Post-click conversion rate Boosted trees Feature engineering

来源：评论

学校读者我要写书评

暂无评论

Fast and Scalable Implementations of Influence Maximization Algorithms

Fast and Scalable Implementations of Influence Maximization ...

引用

IEEE International Conference on Cluster Computing (IEEE CLUSTER)

作者： Minutoli, Marco Halappanavar, Mahantesh Kalyanaraman, Ananth Sathanur, Arun Mcclure, Ryan McDermott, Jason Pacific Northwest Natl Lab Richland WA 99352 USA Washington State Univ Pullman WA 99164 USA

ISBN: (纸本)9781728147345

The Influence Maximization problem has been extensively studied in the past decade because of its practical applications in finding the key influencers in social networks. Due to the hardness of the underlying problem, existing algorithms have tried to trade off practical efficiency with approximation guarantees. Approximate solutions take several hours of compute time on modest sized real world inputs and there is a lack of effective parallel and distributed algorithms to solve this problem. In this paper, we present efficient parallel algorithms for multithreaded and distributed systems to solve the influence maximization with approximation guarantee. Our algorithms extend state-of-the-art sequential approach based on computing reverse reachability sets. We present a detailed experimental evaluation, and analyze their performance and their sensitivity to input parameters, using real world inputs. Our experimental results demonstrate significant speedup on parallel architectures. We further show a speedup of up to 586x relative to the state-of-the-art sequential baseline using 1024 nodes of a supercomputer at far greater accuracy and twice the seed set size. To the best of our knowledge, this is the first effort in parallelizing the influence maximization operation at scale.

关键词： Approximation algorithms Integrated circuit modeling Heuristic algorithms Scalability parallel algorithms Optimization Acceleration

来源：评论

学校读者我要写书评

暂无评论

Energy optimization of security-sensitive mixed-criticality applications for distributed real-time systems

引用

JOURNAL OF parallel AND distributed COMPUTING 2018年 117卷 115-126页

作者： Zhan, Jinyu Zhang, Xia Jiang, Wei Ma, Yue Jiang, Ke Univ Elect Sci & Technol China Sch Informat & Software Chengdu Sichuan Peoples R China Univ Texas Dallas Dept Comp Sci Richardson TX 75083 USA Univ Notre Dame Dept Comp Sci & Engn Notre Dame IN 46556 USA Linkoping Univ Dept Comp & Informat Sci Linkoping Sweden

Existing studies on mixed-criticality systems are usually safety-oriented, which seriously ignore the security and energy related requirements. In this paper we are interested in the design of security-sensitive mixed-criticality real-time systems. We first establish the system model to capture security-critical applications in mixed-criticality systems. Higher security-criticality protection always results in significant time and energy overhead in mixed-criticality systems. Thus, this paper proposes a system-level design framework for energy optimization of security-sensitive mixed-criticality system with hard real-time constraints. Since the time complexity of finding optimal solutions grows exponentially as problem size grows, a GA (Genetic Algorithm) based on efficient heuristic algorithm is devised to address the system-level optimization problem. Extensive experiments and a real-life case study have been conducted to show the efficiency of the proposed technique, which can obtain balanced minimal energy consumption while satisfying strict security and timing constraints. The proposed approach can save up to 28.9% energy consumption compared with other three candidates. (C) 2018 Elsevier Inc. All rights reserved.

关键词： distributed real-time system Mixed-criticality Security Energy Scheduling System design

来源：评论

学校读者我要写书评

暂无评论

Dlion: Decentralized distributed deep learning in micro-clouds 11

Dlion: Decentralized distributed deep learning in micro-clou...

引用

11th USENIX workshop on Hot Topics in Cloud Computing, HotCloud 2019

作者： Hong, Rankyung Chandra, Abhishek University of Minnesota United States

Deep learning is a popular technique for building models from large quantities of input data for applications in many domains. With the proliferation of edge devices such as sensor and mobile devices, large volumes of data are generated at rapid pace all over the world. Migrating large amounts of data into centralized data center(s) over WAN environments is often infeasible due to cost, performance or privacy reasons. Moreover, there is an increasing need for incremental or online deep learning over newly generated data in real-time. These trends require rethinking of the traditional training approach to deep learning. To handle the computation on distributed input data, micro-clouds—small-scale clouds deployed near edge devices in many different locations—provide an attractive alternative for data locality reasons. However, existing distributed deep learning systems do not support training in micro-clouds, due to the unique characteristics and challenges in this environment. In this paper, we examine the key challenges of deep learning in micro-clouds: computation and network resource heterogeneity at inter- and intra micro-cloud levels and their scale. We present DLion, a decentralized distributed deep learning system for such environments. It employs techniques specifically designed to address the above challenges to reduce training time, enhance model accuracy, and provide system scalability. We have implemented a prototype of DLion in TensorFlow and our preliminary experiments show promising results towards achieving accurate and efficient distributed deep learning in micro-clouds. © 2019 USENIX Association. All rights reserved.

关键词： Deep learning

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：