检索结果-内蒙古大学图书馆

5th International Symposium on Computing and Networking (CANDAR)

作者： Funasaka, Shunji Nakano, Koji Ito, Yasuaki Hiroshima Univ Dept Informat Engn Kagamiyama 1-4-1 Higashihiroshima 7398527 Japan

ISBN: (纸本)9781538620878

A task array is a 2-dimensional array of tasks with dependency relations. Each task uses the resulting values of some tasks in the left columns, and so it can be started only after these left tasks are completed. Conventional CUDA implementations repeatedly perform a separated CUDA kernel call for each column from left to right to synchronize the computation for tasks. However, this conventional CUDA implementation has several drawbacks: a CUDA kernel call has a certain overhead, and the running time of a CUDA kernel is determined by a CUDA block that terminates lastly. Also, every task must write and preserve the resulting values in the global memory with low memory access performance for the following tasks. The main contribution of this paper is to introduce task arrays and to present Single Kernel Soft Synchronization (SKSS) technique that significantly reduces such overheads for task arrays. The SKSS performs only one CUDA kernel call and CUDA blocks assigned to each row of a task array using a global counter. To clarify the potentiality of our SKSS technique, we have implemented the dynamic programming for the 0-1 knapsack problem, the summed area table computation, and the error diffusion of a gray-scale image using our SKSS technique and compared with previously published best GPU implementations. Quite surprisingly, the experimental results using NVIDIA Titan X show that, our SKSS implementations are 1.29-2.11 times faster for the 0-1 knapsack problem, 1.08-1.56 times faster for the summed area table computation, and 1.61-2.11 times faster for the error diffusion.

关键词： Graphics processing units Task analysis Kernel parallel algorithms Synchronization Computer architecture Dynamic programming Error diffusion task analysis dynamic programming Computer Architecture Kernel parallel algorithms Seeds Graphics Processing Unit Religious Missions knapsack problems grayscale images global memory

来源：评论

学校读者我要写书评

暂无评论

A Functional Approach to parallelizing Data Mining algorithms in Java 14th

引用

14th International Conference on parallel Computing Technologies (PaCT)

作者： Kholod, Ivan Shorov, Andrey Gorlatch, Sergei St Petersburg Electrotech Univ LETI St Petersburg Russia Univ Munster Munster Germany

ISBN: (纸本)9783319629322;9783319629315

We describe a new approach to parallelizing data mining algorithms. We use the representation of an algorithm as a sequence of functions and we use higher-order functions to express parallel execution. Our approach generalizes the popular MapReduce programming model by enabling not only data-parallel, but also task-parallel implementation and a combination of both. We implement our approach as an extension of the industrial-strength library Xelopes, and we illustrate it by developing a multi-threaded Java program for the 1R classification algorithm, with experiments on a multi-core processor.

关键词： parallel algorithms Data mining parallel data mining Multithreads Multi-core processors MapReduce, homomorphisms

来源：评论

学校读者我要写书评

暂无评论

Optimized algorithms for Solving Structural Inverse Gravimetry and Magnetometry Problems on GPUs 11th

Optimized Algorithms for Solving Structural Inverse Gravimet...

引用

11th International Scientific Conference on parallel Computational Technologies (PCT)

作者： Akimova, Elena N. Misilov, Vladimir E. Tretyakov, Andrey I. RAS Krasovskii Inst Math & Mech Ural Branch 16 S Kovalevskaya St Ekaterinburg Russia Ural Fed Univ 19 Mira St Ekaterinburg Russia

ISBN: (纸本)9783319670355;9783319670348

In this article, we construct new variants of iteratively regularized linearized gradient-type methods for solving structural inverse gravimetry and magnetometry problems, namely the regularized conjugate gradient method, the modified regularized conjugate gradient method, and the hybrid regularized conjugate gradient method. The main idea of the modification is to calculate the Jacobian matrix of the integral operator at a fixed point, without updating it during the entire iteration process. We also developed memory-optimized and time-efficient parallel algorithms and programs on the basis of the constructed modified methods. The memory optimization uses the block-Toeplitz structure of the Jacobian matrix. The algorithms were implemented on GPUs using the NVIDIA CUDA technology. We performed an efficiency and speedup analysis, and solved a model problem with synthetic disturbed data.

关键词： Nonlinear gradient-type methods parallel algorithms Gravimetry and magnetometry problems Toeplitz matrix GPU

来源：评论

学校读者我要写书评

暂无评论

An algorithm for Gaussian Recursive Filters in a Multicore Architecture

An algorithm for Gaussian Recursive Filters in a Multicore A...

引用

Federated Conference on Computer Science and Information Systems (FedCSIS)

作者： Galletti, Ardelio Giunta, Giulio Marcellino, Livia Parlato, Diego Univ Naples Parthenope Dept Sci & Technol Isola C4 I-80143 Naples Italy

ISBN: (纸本)9788394625375

Recursive Filters (RFs) are a well-known way to approximate the Gaussian convolution and, due to their computational efficiency, are intensively used in several technical and scientific fields. The accuracy of the RFs can be improved by means of the repeated application of the filter, which gives rise to the so-called K-iterated Gaussian recursive filter. In this work we propose a parallel algorithm for the implementation of the K-iterated first-order Gaussian RF for multicore architectures. This algorithm is based on a domain decomposition with overlapping strategy. The presented implementation is tailored for multicore architectures and makes use of the Pthreads library. We will show through extensive numerical tests that our parallel implementation is very efficient for large one-dimensional signals and guarantees the same accuracy level of the sequential K-iterated first-order Gaussian RF.

关键词： Radio frequency Multicore processing Convolution parallel algorithms Signal processing algorithms Approximation algorithms parallel algorithms Signal processing algorithms radiofrequency Convolution Approximation algorithms recursive filters Multi-core processors Gauss ARCHITECTURE

来源：评论

学校读者我要写书评

暂无评论

Data-Driven Approach to Ensuring Fault Tolerance and Efficiency of Swarm Systems 5

Data-Driven Approach to Ensuring Fault Tolerance and Efficie...

引用

IEEE International Conference on Big Data (IEEE Big Data)

作者： Majd, Amin Troubitsyna, Elena Abo Akad Univ Dept Informat Technol Turku Finland

ISBN: (纸本)9781538627150

Swarms of drones are increasingly deployed to perform a variety of monitoring tasks. However, despite a growing popularity of swarm-based monitoring solutions, there is still a lack of approaches that allow the designers to ensure that a swarm configuration maximizes coverage of the monitored area and delivers the desired quality of the monitored data. A drone might fail or run out of energy and hence leave some blind spots in the monitored area. Moreover, an inefficient configuration resulting in the energy-greedy communication can quickly deplete the batteries of the drones and force a premature mission termination. We propose a novel data-driven integrated solution that combines learning and optimization over the streams of monitored data to ensure fault tolerance and efficiency of the swarm navigation. The benchmarking results demonstrate that the proposed approach allows us to significantly improve the coverage and energy efficiency characteristics.

关键词： swarm of drones reconfiguration learning evolutionary computing parallel algorithms

来源：评论

学校读者我要写书评

暂无评论

Why Is MPI So Slow? Analyzing the Fundamental Limits in Implementing MPI-3.1 17

Why Is MPI So Slow? Analyzing the Fundamental Limits in Impl...

引用

International Conference for High Performance Computing, Networking, Storage and Analysis (SC)

作者： Rafenetti, Ken Amer, Abdelhalim Oden, Lena Archer, Charles Bland, Wesley Fujita, Hajime Guo, Yanfei Janjusic, Tomislav Durnov, Dmitry Blocksome, Michael Si, Min Seo, Sangmin Langer, Akhil Zheng, Gengbin Takagi, Masamichi Cofman, Paul Jose, Jithin Sur, Sayantan Sannikov, Alexander Oblomov, Sergey Chuvelev, Michael Hatanaka, Masayuki Zhao, Xin Fischer, Paul Rathnayake, Thilina Otten, Matt Min, Misun Balaji, Pavan Argonne Natl Lab Argonne IL 60439 USA Intel Corp Santa Clara CA 95051 USA Mellanox Technol Sunnyvale CA USA RIKEN Adv Inst Computat Sci Kobe Hyogo Japan Univ Illinois Chicago IL 60680 USA Cornell Univ Ithaca NY 14853 USA

ISBN: (数字)9781450351140

ISBN: (纸本)9781450351140

This paper provides an in-depth analysis of the software overheads in the MPI performance-critical path and exposes mandatory performance overheads that are unavoidable based on the MPI-3.1 specification. We first present a highly optimized implementation of the MPI-3.1 standard in which the communication stack all the way from the application to the low-level network communication API takes only a few tens of instructions. We carefully study these instructions and analyze the root cause of the overheads based on specific requirements from the MPI standard that are unavoidable under the current MPI standard. We recommend potential changes to the MPI standard that can minimize these overheads. Our experimental results on a variety of network architectures and applications demonstrate significant benefits from our proposed changes.

关键词： High performance computing Network architecture Software parallel algorithms Standards

来源：评论

学校读者我要写书评

暂无评论

parallel Optimal Pairwise Biological Sequence Comparison: algorithms, Platforms, and Classification

引用

ACM COMPUTING SURVEYS 2016年第4期48卷 63-63页

作者： De Oliveira Sandes, Edans Flavius Boukerche, Azzedine Magalhaes Alves De Melo, Alba Cristina Univ Brasilia BR-70910900 Brasilia DF Brazil Univ Ottawa Sch Informat Technol & Engn SITE 800 King Edward Ave Ottawa ON K1N 6N5 Canada

Many bioinformatics applications, such as the optimal pairwise biological sequence comparison, demand a great quantity of computing resource, thus are excellent candidates to run in high-performance computing (HPC) platforms. In the last two decades, a large number of HPC-based solutions were proposed for this problem that run in different platforms, targeting different types of comparisons with slightly different algorithms and making the comparative analysis of these approaches very difficult. This article proposes a classification of parallel optimal pairwise sequence comparison solutions, in order to highlight their main characteristics in a unifiedway. We then discuss several HPC-based solutions, including clusters ofmulticores and accelerators such as Cell Broadband Engines (CellBEs), Field-Programmable Gate Arrays (FPGAs), Graphics Processing Units (GPUs) and Intel Xeon Phi, as well as hybrid solutions, which combine two or more platforms, providing the actual landscape of the main proposals in this area. Finally, we present open questions and perspectives in this research field.

关键词： algorithms Performance parallel algorithms biological sequence comparison FPGA GPU multicores CellBE Intel Phi

来源：评论

学校读者我要写书评

暂无评论

The Matching Problem in General Graphs is in Quasi-NC 58

The Matching Problem in General Graphs is in Quasi-NC

引用

58th IEEE Annual Symposium on Foundations of Computer Science (FOCS)

作者： Svensson, Ola Tarnawski, Jakub Ecole Polytech Fed Lausanne Lausanne Switzerland

ISBN: (纸本)9781538634646

We show that the perfect matching problem in general graphs is in quasi-NC. That is, we give a deterministic parallel algorithm which runs in O(log(3) n) time on n O(log(2) n) processors. The result is obtained by a derandomization of the Isolation Lemma for perfect matchings, which was introduced in the classic paper by Mulmuley, Vazirani and Vazirani [1987] to obtain a Randomized NC algorithm. Our proof extends the framework of Fenner, Gurjar and Thierauf [2016], who proved the analogous result in the special case of bipartite graphs. Compared to that setting, several new ingredients are needed due to the significantly more complex structure of perfect matchings in general graphs. In particular, our proof heavily relies on the laminar structure of the faces of the perfect matching polytope. This is an extended abstract. The full version of the paper, which includes all proofs, may be found at https: //***/abs/1704.01929.

关键词： Bipartite graph parallel algorithms Program processors Computer science Electronic mail Complexity theory Algorithm design and analysis

来源：评论

学校读者我要写书评

暂无评论

Hardware-In-The-Loop Testing of High Switching Frequency Power Electronics Converters

Hardware-In-The-Loop Testing of High Switching Frequency Pow...

引用

IEEE Electric Ship Technologies Symposium (ESTS)

作者： Difronzo, Michele Milton, Matthew Davidson, Matthew Benigni, Andrea Univ South Carolina Coll Engn & Comp Columbia SC 29208 USA

ISBN: (纸本)9781509049448

In this paper, we present the Hardware-In-The Loop (HIL) usage of a new simulation approach recently introduced by the authors and discuss the programmable logic interface required for the HIL simulation of high switching frequency power electronics converters. As a test case, we simulate a notional ship power system where one converter is externally controlled using the developed HIL simulation platform. The ship system is composed of eight converters all operating at 100kHz, the real-time simulation is performed using a FPGA-based platform and a 50 nanosecond simulation time step.

关键词： Circuit Simulation parallel algorithms Power electronics Real Time Systems Power System Simulation

来源：评论

学校读者我要写书评

暂无评论

parallelized Dimensional Decomposition for Large-Scale Dynamic Stochastic Economic Models 17

Parallelized Dimensional Decomposition for Large-Scale Dynam...

引用

Platform for Advanced Scientific Computing Conference (PASC)

作者： Eftekhari, Aryan Scheidegger, Simon Schenk, Olaf Univ Svizzera Italiana Inst Computat Sci Fac Informat Lugano Switzerland Univ Zurich Dept Banking & Finance Zurich Switzerland Stanford Univ Hoover Inst Stanford CA 94305 USA

ISBN: (纸本)9781450350624

We introduce and deploy a generic, highly scalable computational method to solve high-dimensional dynamic stochastic economic models on high-performance computing platforms. Within an MPI-TBB parallel, nonlinear time iteration framework, we approximate economic policy functions using an adaptive sparse grid algorithm with d-linear basis functions that is combined with a dimensional decomposition scheme. Numerical experiments on "Piz Daint" (Cray XC30) at the Swiss National Supercomputing Centre show that our framework scales nicely to at least 1, 000 compute nodes. As an economic application, we compute global solutions to international real business cycle models up to 200 continuous dimensions with significant speedup values over state-of-the-art techniques.

关键词： Generalized ANOVA Dimensional Decomposition High-Dimensional Model Representation parallel algorithms Adaptive Sparse Grids High-Performance Computing Heterogeneous Systems International Real Business Cycle

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：