检索结果-内蒙古大学图书馆

PosDB: A distributed Column-Store Engine 1

11th International Andrei P. Ershov Informatics conference on Perspectives of System Informatics (PSI)

作者： Chernishev, George Galaktionov, Viacheslav Grigorev, Valentin Klyuchikov, Evgeniy Smirnov, Kirill St Petersburg State Univ St Petersburg Russia JetBrains Res St Petersburg Russia

ISBN: (数字)9783319743134

ISBN: (纸本)9783319743134;9783319743127

In this paper we present a novel disk-based distributed column-store, describe its architecture and discuss a number of technical solutions. Our system is essentially a query engine which was written completely from scratch. It is aimed for shared-nothing environments and supports different forms of parallel query processing. Query processing in PosDB is organized according to the classic Volcano pull-based model which is adapted for the column-store case. Currently, we support late materialization only, and therefore employ a join index data structure to represent positional information. In our system query plan can consist of both positional and value operators. PosDB has about a dozen of core operators among which several variants of selections and joins, aggregation. We also have several operators that ensure intra-query parallelism and operators for network interoperability. In its current state the system is fully capable of processing the Star Schema Benchmark in a local and distributed environment.

关键词： Query processing

来源：评论

学校读者我要写书评

暂无评论

Scalable Triangle Counting on distributed-Memory Systems

Scalable Triangle Counting on Distributed-Memory Systems

引用

IEEE conference on High Performance Extreme Computing (HPEC)

作者： Seher Acer Abdurrahman Yaşar Sivasankaran Rajamanickam Michael Wolf Ümit V. Catalyürek Center for Computing Research Sandia National Laboratories Albuquerque NM U.S.A. College of Computing Georgia Institute of Technology Atlanta GA U.S.A.

Triangle counting is a foundational graph-analysis kernel in network science. It has also been one of the challenge problems for the “Static Graph Challenge”. In this work, we propose a novel, hybrid, parallel triangle counting algorithm based on its linear algebra formulation. Our framework uses MPI and Cilk to exploit the benefits of distributed-memory and shared-memory parallelism, respectively. The problem is partitioned among MPI processes using a two-dimensional (2D) Cartesian block partitioning. One-dimensional (1D) rowwise partitioning is used within the Cartesian blocks for shared-memory parallelism using the Cilk programming model. Besides exhibiting very good strong scaling behavior in almost all tested graphs, our algorithm achieves the fastest time on the 1.4B edge real-world twitter graph, which is 3.217 seconds, on 1,092 cores. In comparison to past distributed-memory parallel winners of the graph challenge, we demonstrate a speed up of 2.7× on this twitter graph. This is also the fastest time reported for parallel triangle counting on the twitter graph when the graph is not replicated.

关键词： parallel processing Two dimensional displays Task analysis Computer architecture Message systems Kernel Partitioning algorithms

来源：评论

学校读者我要写书评

暂无评论

Resource Management Method of distributed parallel Database based on Directed Graph

引用

Journal of Physics: conference Series 2020年第1期1646卷

作者： Yingjie Shi Huayun Zhang Xiang Wang Yuchao Zhou Shusong Jiang China Realtime Database Co.Ltd. Building 6 big data Industrial Park No.180 software Avenue Yuhuatai District Nanjing China

A distributed parallel database resource management method based on directed graph is proposed. By using content distributor based on distributed unstructured P2P network association, the high performance and stability of distributed parallel database system in dynamic changing environment are guaranteed. The problem of network congestion caused by too many redundant messages and the 'barrel effect' caused by resource imbalance due to differential configuration is solved, through resource search algorithm based on directed graph lookahead, and the query node cached the resource information of two-level neighbor nodes. By adopting the Linux cgroups resource management mechanism, fully considering the multi tenant and multi factor based resource scheduling strategy, reduce resource fragments and better meet the problem of distributed parallel database storage or hot spot processing.

关键词：

来源：评论

学校读者我要写书评

暂无评论

parallel and Cloud-based Analysis of Omics Data: Modelling and Simulation in Medicine 25

Parallel and Cloud-based Analysis of Omics Data: Modelling a...

引用

25th euromicro International conference on parallel, distributed and network-based processing (PDP)

作者： Agapito, Giuseppe Calabrese, Barbara Guzzi, Pietro H. Fragomeni, Gionata Tradigo, Giuseppe Veltri, Pierangelo Cannataro, Mario Magna Graecia Univ Catanzaro Dept Med & Surg Sci Catanzaro Italy

ISBN: (纸本)9781509060580

High throughput experimental platforms and diagnostic equipments available in clinical settings and in research laboratories, such as magnetic resonance imaging, microarray, mass spectrometry and next-generation sequencing, are producing an increasing volume of clinical and omics data. Moreover, Electronic Patients Records (EPRs), eHealth systems, personal mobile sensors and Social networks are collecting an overwhelming volume of health and life style data that may be integrated with clinical data and more and more is used for the real-time monitoring of patient's health. This poses new issues in terms of secure data storage, effective models for data integration, efficient algorithms for data analysis, new models for health monitoring, that may be addressed, among the others, using high performance computing solutions. parallel computing and Cloud Computing may offer efficient and scalable solutions in an orthogonal way. In fact, parallel, bioinformatics software, that exploit off-the-shelf high performance computers, may be used to preprocess and analyze omics data at a lower layer, for instance to highlight genetic variation associated with complex diseases. On the other hand, Cloud Computing offers large scale data storage, data sharing services, on-demand anytime and anywhere access to resources and applications, for the realization of elastic and scalable applications and services. Motivated by the increasing use of parallel computing and cloud computing in life sciences, in this paper we survey both parallel bioinformatics algorithms for the parallel preprocessing and statistical and data mining analysis of omics data, as well as Cloud-based healthcare and biomedicine services and systems for large scale applications. Moreover, the paper underlines main issues and problems related to the use of such platforms for the storage and analysis of health data, with special focus to the security and privacy of patients data, that are particularly important in fields

关键词： Data visualization Bioinformatics Cloud computing Biological system modeling Proteins Genomics

来源：评论

学校读者我要写书评

暂无评论

Sequence Data Enhancement Method based on Knowledge Graph

Sequence Data Enhancement Method Based on Knowledge Graph

引用

IEEE International conference on Big Data and Cloud Computing (BdCloud)

作者： Huosheng Xie Wenda Chai Shufeng Lin College of Mathematics and Computer Science Fuzhou University Fuzhou China

ISBN: (数字)9781728143286

ISBN: (纸本)9781728143293

To solve the problem of low recommendation accuracy caused by too little user behavior information in the current behavior recommendation system, an algorithm based on end-to-end data enhancement was proposed. In this paper, knowledge graph is constructed by learning and integrating structured knowledge network. Moreover, the characteristics of users with high preference similarity can be propagated through the inter-entity relations mapped by the knowledge map to reconstruct the preference vector of users. Through comparative experiments on open data sets, the AUC of RNN model, CNN model, RNN attention model and ATRank were improved by 3.28%, 2.35%, 2.89% and 1.30%, respectively.

关键词： 6G mobile communication distributed processing Big Data Cloud computing Social computing Channel hot electron injection

来源：评论

学校读者我要写书评

暂无评论

DGCF: A distributed Greedy Clustering Framework for Large-scale Genomic Sequences

DGCF: A Distributed Greedy Clustering Framework for Large-sc...

引用

IEEE International conference on Bioinformatics and Biomedicine

作者： Zekun Yin Xiaoming Xu Kaichao Fan Ruilin Li Beifang Niu Weizhong Li Weiguo Liu School of Software Shandong University School of software Shandong University Computer Network Information Center Chinese Academy of Sciences University of Chinese Academy of Sciences J. Craig Venter Institute

ISBN: (纸本)9781728118680

Clustering is a very fundamental while time-consuming compute operation in biological sequence analysis. New sequencing technologies such as NGS and 3GS have dramatically increased both the dataset size and the length of a single read sequence. However, existing tools lack scalability for handling large-scale datasets as well as long sequences. A feasible solution to this problem is to use parallel and distributed systems. The efficient deployment of such systems, however, requires high parallelism in both software implementations as well as algorithmic optimizations. In this paper, we propose DGCF, a distributed Greedy Clustering Framework which is capable to handle large-scale datasets and long sequences. Our framework adopts a greedy clustering strategy which overlaps communication with computation among many distributed computing nodes. We also design and implement a sparse suffix array (SSA)-based alignment algorithm that can support long sequences. Experiments show that our framework achieves near-linear speedups on a distributed memory cluster.

关键词： greedy clustering sparse suffix array sequence analysis parallel computing Analyses, Sequence Frameworks parallel processing (COMPUTERS) greedy method Cluster Analysis Feasible Solution Dataset

来源：评论

学校读者我要写书评

暂无评论

CSSMT: Compiler based Software Simultaneous Multithreading (SMT)

CSSMT: Compiler based Software Simultaneous Multithreading (...

引用

euromicro International conference on parallel, distributed and network-based processing

作者： Yuanfang Chen Qingchuan Shi Xiaoming Li Electrical and Computer Engineering Department University of Delaware Advanced Micro Devices Inc Santa Clara CA US

Simultaneous multithreading (SMT) is a unique computer architecture feature to increase the pipeline utilization and therefore, increase the instruction throughput. It improves instruction level throughput by simultaneously filling both vertical and horizontal super-scalar pipeline slots that are left unfilled by native threads. So far SMT has been implemented in hardware. However, hardware SMT implementations have its limitations. First, it is complex and expensive to implement - only higher-end processors are equipped with it even though lower-end processors have same pipeline design as the higher-end variants and might also benefit from it. SMT also introduces great power/energy and area overheads. Moreover, being a hardware feature, SMT is limited by the range and depth of instruction analysis that it can afford at execution time, therefore it is unlikely to benefit from high-level software knowledge about instruction mix and might lose many improvement opportunities. In this paper, we address the limitation of the hardware-based SMT and introduce CSSMT: Compiler based Software Simultaneous Multithreading (SMT). The main contribution of CSSMT is that it exploits high-level program profiles to purposefully "re-mix" instructions from multiple programs to better fill vertical and horizontal super-scalar pipeline slots so that the overall throughput is improved. Furthermore, CSSMT is a software-transformation technique that enables SMT at software level during compilation time. Therefore, it can help overcome the limitation of the hardware-based SMT implementation and is more portable. We test CSSMT with programs from SPEC2006 and NAS benchmarks and achieve up to 12% speedup of execution time (30.7% improvement in terms of multi-program throughput).

关键词： Pipelines Standards Throughput Hardware Instruction sets Merging

来源：评论

学校读者我要写书评

暂无评论

Matching Cost Calculation Model based on Multi-Scale Convolutional Neural network

Matching Cost Calculation Model Based on Multi-Scale Convolu...

引用

IEEE International Symposium on parallel and distributed processing with Applications and IEEE International conference on Ubiquitous Computing and Communications (ISPA/IUCC)

作者： Tengna Wang Lin Ye Xian branch of China telecom co. LTD Xi’an China Shaanxi branch of China telecom co. LTD Xi’an China

The following topics are dealt with: learning (artificial intelligence); feature extraction; convolutional neural nets; Big Data; data mining; social networking (online); pattern clustering; telecommunication computin... 详细信息

ISBN: (纸本)9781728152103

关键词： convolutional neural nets feature extraction image matching stereo image processing Stereo image processing Computational modeling image matching Feature extraction multi-scale Neural network Costs

来源：评论

学校读者我要写书评

暂无评论

Copyright Protection Application based on Blockchain Technology

引用

IEEE International conference on Big Data and Cloud Computing (BdCloud)

作者： Yi Ouyang Xianghan Zheng Xiaoliang Lu Lin Xiaowei Shengyin Zhang Fujian Key Laboratory of Network Computing and Intelligent Information Processing Fuzhou University Fuzhou China MingByte Technology (Qingdao) Co. Ltd MingByte Technology Co. Ltd Qingdao China

ISBN: (数字)9781728143286

ISBN: (纸本)9781728143293

In the traditional copyright protection platform, there are problems such as copyright information security and high registration cost. With the rapid development of blockchain technology, blockchain technology, as a new technology architecture, has the characteristics of decentralization, nontamperability, traceability, openness and transparency, and has a natural combination with copyright protection, which is expected to solve the existence of traditional copyright protection. The pain point of this paper is to apply the blockchain technology to the copyright management platform. It is hoped that in this way, the problems of poor security, difficult rights, complicated transaction procedures, etc. in the traditional copyright management platform are solved. An attempt to combine chain technology with copyright protection.

关键词： Blockchain Peer-to-peer computing distributed databases Smart contracts Security Fabrics distributed ledger

来源：评论

学校读者我要写书评

暂无评论

CUDA Optimization Method for Activation Function in Convolution Operation

CUDA Optimization Method for Activation Function in Convolut...

引用

IEEE International conference on Big Data and Cloud Computing (BdCloud)

作者： Lubin Feng Dulei Zheng Jianzhi Yu College of Computer Science and Engineering Shandong University of Science and Technology Qingdao China

ISBN: (数字)9781728143286

ISBN: (纸本)9781728143293

Deep learning is an important field of computer research. Convolutional neural networks have received much attention in the field of image recognition because of their excellent recognition ability. The neural network contains a large number of parameters. For the training time-consuming problem of convolutional neural networks, how to effectively realize the computational acceleration in the training process is one of the hot topics in the field of deep learning research. In this paper, two parallel algorithms are designed based on single-thread block multi-thread and multi-thread block strategies. The former is a parallel algorithm between activation functions, and the latter is based on the former, and the parallelization algorithm inside the activation function. Finally, this paper designed a contrast experiment to verify the algorithm. The experimental results show that both algorithms have achieved a good acceleration effect, so that the GPU resources can be fully utilized to achieve the purpose of computational acceleration.

关键词： Instruction sets Graphics processing units Kernel Convolution Neurons Acceleration Training

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：