检索结果-内蒙古大学图书馆

5th international conference on Communication Systems and Network Technologies (CSNT)

作者： Sinha, Rashmi Sharan Singh, Satvir Singh, Sarabjeet Banga, Vijay Kumar SBSS Tech Campus Ferozepur 152004 India Amritsar Coll Engn & Tech Amritsar 143001 Punjab India

ISBN: (纸本)9781479917976

Genetic Algorithm (GA) is one of most popular swarm based evolutionary search algorithm that involves multiple data independent computations. Such computations can be made parallel on GPU cores using Compute Unified Design Architecture (CUDA) platform. In this paper, various operations of GA such as fitness evaluation, selection, crossover and mutation, etc. are implemented in parallel on GPU cores and then performance is compared with its serial implementation. the algorithm performance in serial and in parallel implementations are examined on a testbed of well-known benchmark optimization functions. the performances are analyzed with varying parameters viz. (i) population sizes, (ii) dimensional sizes, and (iii) problems of differing complexities. Results shows that the overall computational time can substantially be decreased by parallel implementation on GPU cores. the proposed implementations resulted in 1.18 to 4.15 times faster than the corresponding serial implementation on CPU.

关键词： Genetic Algorithm (GA) General Purpose Computing on Graphics processing Unit (GPGPU) Compute Unified Device Architecture(CUDA)

来源：评论

学校读者我要写书评

暂无评论

Proceedings of PyHPC 2015: 5th Workshop on Python for High-Performance and Scientific Computing - Held in conjunction with SC 2015: the international conference for High Performance Computing, Networking, Storage and Analysis

Proceedings of PyHPC 2015: 5th Workshop on Python for High-P...

引用

5th Workshop on Python for High-Performance and Scientific Computing, PyHPC 2015

ISBN: (纸本)9781450340106

the proceedings contain 6 papers. the topics discussed include: Python, performance and natural language processing;performance and productivity of parallel Python programming - a study with a CFD test case;PeachPy meets Opcodes: direct machine code generation from Python;PyTACC: HPC Python at the Texas advanced computing center;feature frequency profiles for automatic sample identification using PySpark;dispel4py: a Python framework for data-intensive eScience;and solving large numerical optimization problems in HPC with Python.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Quantum computer simulation on multi-GPU incorporating data locality 1

引用

15th international conference on algorithms and architectures for parallel processing, ICA3PP 2015

作者： Zhang, Pei Yuan, Jiabin Lu, Xiangwen College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics Nanjing211106 China

ISBN: (数字)9783319271194

ISBN: (纸本)9783319271187

Quantum computer simulation (QCS) provides an effective platform for the development and validation of quantum algorithms. the exponential runtime overhead limits the simulation scale on classical computers which makes advisable the use of Graphics processing Units. However, simulating quantum computers on multi-GPU has poor performance due to low data locality and frequent data transfer. Here, we propose a novel implemental scheme for QCS on multi-GPU. Our implementation addresses the aforementioned challenges by (i) an efficient data distribution method enhancing high data locality on each GPU global memory and (ii) an assignment function for the threads mapping to each GPU memory space achieving high bandwidth and data reuse for multiple quantum gates. Experimental results show that the simulation of 29-qubit Quantum Fourier Transform algorithm using four NVIDIA K20c GPUs gains a performance ratio of 358, compared to the sequential implementation of released libquantum, along with a parallel efficiency of 0. 92. © Springer international Publishing Switzerland 2015.

关键词： Graphics processing unit

来源：评论

学校读者我要写书评

暂无评论

iPLAR: Towards interactive programming with parallel linear algebra in R 15th

iPLAR: Towards interactive programming with parallel linear ...

引用

15th international conference on algorithms and architectures for parallel processing, ICA3PP 2015

作者： Wang, Zhaokang Fan, Shiqing Gu, Rong Yuan, Chunfeng Huang, Yihua National Key Laboratory for Novel Software Technology Collaborative Innovation Center of Novel Software Technology and Industrialization Nanjing University Nanjing210023 China

ISBN: (纸本)9783319271392

R is a widely-used statistical programming language in the data science community. However, in the big data era, R faces the challenges from large scale data analysis tasks. It lacks the ability of distributed linear algebra computation in its local interactive shell. In this paper, we propose iPLAR, a system that runs in the interactive R environment, wraps the high performance parallel linear algebra library, and provides a group of easy-to-use interfaces. iPLAR adopts the client-server model to uncouple the interactive shell from the ScaLAPACK/MPI distributed computing backend. In addition, it provides R users with a group of parallel-detail-transparent interfaces that are similar to the native R linear algebra interfaces. We evaluate the efficiency of iPLAR with representative basic matrix operations and two widely-used machine learning algorithms. Experimental results show that iPLAR achieves the near- linear data scalability and enhances the interactive processing capability of R to large problem scales. © 2015 Springer international Publishing Switzerland.

关键词： Big data

来源：评论

学校读者我要写书评

暂无评论

Auditory and visual cortex of primates: a comparison of two sensory systems

引用

EUROPEAN JOURNAL OF NEUROSCIENCE 2015年第5期41卷 579-585页

作者： Rauschecker, Josef P. Georgetown Univ Med Ctr Dept Neurosci Washington DC 20057 USA Tech Univ Munich Inst Adv Study Garching Germany

A comparative view of the brain, comparing related functions across species and sensory systems, offers a number of advantages. In particular, it allows separation of the formal purpose of a model structure from its implementation in specific brains. Models of auditory cortical processing can be conceived by analogy to the visual cortex, incorporating neural mechanisms that are found in both the visual and auditory systems. Examples of such canonical features at the columnar level are direction selectivity, size/bandwidth selectivity, and receptive fields with segregated vs. overlapping ON and OFF subregions. On a larger scale, parallel processing pathways have been envisioned that represent the two main facets of sensory perception: (i) identification of objects;and (ii) processing of space. Expanding this model in terms of sensorimotor integration and control offers an overarching view of cortical function independently of sensory modality.

关键词： hierarchical processing internal models sensorimotor integration simple and complex cells ventral and dorsal streams

来源：评论

学校读者我要写书评

暂无评论

UniDegree: A GPU-based graph representation for SSSP 15th

UniDegree: A GPU-based graph representation for SSSP

引用

15th international conference on algorithms and architectures for parallel processing, ICA3PP 2015

作者： Zhang, Changyou Wang, Feng Huang, Kun Liu, Zhiyou Chen, Yifeng Laboratory of Parallel Software and Computational Science Institute of Software Chinese Academy of Sciences Beijing100190 China HCST Key Lab School of EECS Peking University Beijing100085 China School of Computer Beijing Institute of Technology Beijing100081 China

ISBN: (纸本)9783319271217

GPU is the mainstream co-processor computers of heterogeneous architecture. parallel graph algorithms are fundamental for many data-driven applications to be solved on heterogeneous clusters. SSSP (Single Source Shortest Path) algorithm is one of the most important one. We proposed a graph representation structure with unified vertex’s degree. this method ensures the data block size consistency. And then, the transferring in memory on this representation makes the data reading in cohesion for CUDA thread blocks. thirdly, vertex renumbering optimizes the locality of graph vertices to make the relaxing operation more efficient. With data of New York road, we implemented SSSP algorithms of delta-stepping on Nvida Tesla K20x GPU device. the experimental results show that the best unified-degree is approximate to the mode of vertex-degree of the graph. For example of the New York road map, all degrees were unified into 4-degree that results to the biggest speed-up of SSSP algorithm. © Springer international Publishing Switzerland 2015.

关键词： Graphics processing unit

来源：评论

学校读者我要写书评

暂无评论

A parallel Framework for Object Detection and Recognition for Secure Vehicle Parking 17

A Parallel Framework for Object Detection and Recognition fo...

引用

2015 IEEE 17th international conference on High Performance Computing and Communications (HPCC)

作者： Mahmood, Zahid Khan, Muhammad Usman Shahid Jawad, Muhammad Khan, Samee U. Yang, Laurence T. North Dakota State Univ Dept Elect & Comp Engn Fargo ND 58102 USA St Francis Xavier Univ Dept Comp Sci Antigonish NS B2G 2W5 Canada

ISBN: (纸本)9781479989379

Image analytics, biometrics access control, security, and surveillance applications utilize complex machine learning and computer vision algorithms, such as face detection and recognition. Speedup and accuracy are two important factors that need to be addressed in all such complex applications. parallel computing breaks down the complex tasks into discrete fragments to be solved concurrently on multiple processors. the parallel computing procedure significantly reduces the execution time with improved speedup. this paper presents a parallel framework for object detection and recognition for a secure vehicle parking. the proposed framework is divided in to three steps: (1) vehicle detection at the parking entry junction, (2) driver's face detection, and (3) identification of driver's face from the huge database of stored facial images. On successful identification of authorized person, vehicle is allowed to enter in the parking-lot. the adaptive boosting algorithm is used for vehicle and face detection, while Eigenfaces based approach is employed for face recognition. Moreover, the scalability comparison of parallely executed driver face recognition algorithm indicates high speedup compared to serial execution. Furthermore, the results of the proposed framework reveal promising performance and encourage outcomes to be deployed in real-time at entrance/exits of the public/private vehicle parking areas.

关键词： Eigenfaces Face Recognition Haar Classifiers parallel processing

来源：评论

学校读者我要写书评

暂无评论

Towards an Automatic Prediction of Image processing algorithms Performances on Embedded Heterogeneous architectures

Towards an Automatic Prediction of Image Processing Algorith...

引用

international conference on parallel processing Workshops (ICPPW)

作者： Romain Saussard Boubker Bouzid Marius Vasiliu Roger Reynaud Renault S.A.S. Guyancourt France Universite Paris-Sud Orsay ÃŽle-de-France FR

Image processing algorithms are widely used in the automotive field for ADAS (Advanced Driver Assistance System) purposes. To embed these algorithms, semiconductor companies offer heterogeneous architectures which are composed of different processing units, often with massively parallel computing unit. However, embedding complex algorithms on these So Cs (System on Chip) remains a difficult task due to heterogeneity, it is not easy to decide how to allocate parts of a given algorithm on processing units of a given SoC. In order to help automotive industry in embedding algorithms on heterogeneous architectures, we propose a novel approach to predict performances of image processing algorithms on different computing units of a given heterogeneous SoC. Our methodology is able to predict a more or less wide interval of execution time with a degree of confidence using only high level description of algorithms to embed, and a few characteristics of computing units.

关键词： Kernel Computer architecture Image processing Graphics processing units parallel processing Prediction algorithms Instruction sets

来源：评论

学校读者我要写书评

暂无评论

Reducing overhead in the uintah framework to support short-lived tasks on GPU-heterogeneous architectures 5

Reducing overhead in the uintah framework to support short-l...

引用

5th international Workshop on Domain-Specific Languages and High-Level Frameworks for High Performance Computing, WOLFHPC 2015

作者： Peterson, Brad Dasari, Harish Humphrey, Alan Sutherland, James Saad, Tony Berzins, Martin Scientific Computing and Imaging Institute University of Utah Salt Lake CityUT84112 United States

ISBN: (纸本)9781450340168

the Uintah computational framework is used for the parallel solution of partial differential equations on adaptive mesh refinement grids using modern supercomputers. Uintah is structured with an application layer and a separate runtime system. the Uintah runtime system is based on a distributed directed acyclic graph (DAG) of computational tasks, with a task scheduler that efficiently schedules and execute these tasks on both CPU cores and on-node accelerators. the runtime system identifies task dependencies, creates a taskgraph prior to an iteration based on these dependencies, prepares data for tasks, automatically generates MPI message tags, and manages data after task computation. Managing tasks for accelerators pose significant challenges over their CPU task counterparts due to supporting more memory regions, API call latency, memory bandwidth concerns, and the added complexity of development. these challenges are greatest when tasks compute within a few milliseconds, especially those that have stencil based computations that involve halo data, have little reuse of data, and/or require many computational variables. Current and emerging heterogeneous architectures necessitate addressing these challenges within Uintah. this work is not designed to improve performance of existing tasks, but rather reduce runtime overhead to allow developers writing short-lived computational tasks to utilize Uintah in a heterogeneous environment. this work analyzes an initial approach for managing accelerator tasks alongside existing CPU tasks within Uintah. the principal contribution of this work is to identify and address inefficiencies that arise when mapping tasks onto the GPU, to implement new schemes to reduce runtime system overhead, to introduce new features that allow for more tasks to leverage on-node accelerators, and to show overhead reduction results from these improvements. © 2015 ACM.

关键词： Graphics processing unit

来源：评论

学校读者我要写书评

暂无评论

Beyond Data parallelism: Identifying parallel tasks in sequential programs 15th

Beyond Data Parallelism: Identifying parallel tasks in seque...

引用

15th international conference on algorithms and architectures for parallel processing, ICA3PP 2015

作者： Li, Zhen Zhao, Bo Jannesari, Ali Wolf, Felix Technische Universität Darmstadt Darmstadt64289 Germany Xi’an Jiaotong University Xi’an710049 China

ISBN: (纸本)9783319271392

Today, millions of legacy programs are awaiting their parallelization. For this reason, the automatic discovery of parallelism in sequential programs is now receiving considerable attention. However, past efforts mainly concentrated on data parallelism hidden inside loops. As programming models begin to support more irregular types of parallelism, centered around the notion of tasks in various forms, methods are needed to identify code sections that could potentially represent parallel tasks. In this paper, we present a novel approach to automatically finding parallel tasks in sequential programs. We first created a dynamic dependence graph, then isolated tasks, and finally produced a task graph according to the dependences we find. With the help of a source-to-source code translator, parallel code is automatically generated. We conducted a range of experiments to cover both tasks executing the same code and tasks executing different code. Results showed that our method achieved reasonable speedups on the test cases. © Springer international Publishing Switzerland 2015.

关键词： parallel programming

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：