检索结果-内蒙古大学图书馆

作者： Federico Tesser Universite Bordeaux

学位级别：博士

Adaptive discretizations are important in compressible/incompressible flow problems since it is often necessary to resolve details on multiple levels, allowing large regions of space to be modeled using a reduced number of degrees of freedom (reducing the computational time). There are a wide variety of methods for adaptively discretizing space, but Cartesian grids have often outperformed them even at high resolutions due to their simple and accurate numerical stencils and their superior parallel performances. Such performance and simplicity are in general obtained applying a finite-difference scheme for the resolution of the problems involved, but this discretization approach does not present, by contrast, an easy adapting path. In a finite-volume scheme, instead, we can incorporate different types of grids, more suitable for adaptive refinements, increasing the complexity on the stencils and getting a greater flexibility. The Laplace operator is an essential building block of the Navier-Stokes equations, a model that governs fluid flows, but it occurs also in differential equations that describe many other physical phenomena, such as electric and gravitational potentials, and quantum mechanics. So, it is a very important differential operator, and all the studies carried out on it, prove its relevance. In this work will be presented 2D finite-difference and finite-volume approaches to solve the Laplacian operator, applying patches of overlapping grids where a more fined level is needed, leaving coarser meshes in the rest of the computational domain. These overlapping grids will have generic quadrilateral shapes. Specifically, the topics covered will be: 1) introduction to the finite difference method, finite volume method, domain partitioning, solution approximation; 2) overview of different types of meshes to represent in a discrete way the geometry involved in a problem, with a focus on the octree data structure, presenting PABLO and PABLitO. The first one is an

关键词： Python Finite Differences Finite Volumes parallel programming Laplace Operator Adaptive Discretizations

来源：评论

学校读者我要写书评

暂无评论

Techniques for Enhancing the Efficiency of Transactional Memory Systems

Techniques for Enhancing the Efficiency of Transactional Mem...

引用

作者： SHADY ALAAELDIN MOHAMED ABDELKADER RABIE ISSA KTH Royal Institute of Technology

学位级别：博士

Transactional Memory (TM) is an emerging programming paradigm that drastically simplifies the development of concurrent applications by reliev- ing programmers from a major source of complexity: how to ensure correct, yet efficient, synchronization of concurrent accesses to shared memory. De- spite the large body of research devoted to this area, existing TM systems still suffer from severe limitations that hamper both their performance and energy efficiency. This dissertation tackles the problem of how to build efficient implemen- tations of the TM abstraction by introducing innovative techniques that ad- dress three crucial limitations of existing TM systems by: (i) extending the effective capacity of Hardware TM (HTM) implementations; (ii) reducing the synchronization overheads in Hybrid TM (HyTM) systems; (iii) enhanc- ing the efficiency of TM applications via energy-aware contention manage- ment schemes. The first contribution of this dissertation, named POWER8-TM (P8TM), addresses what is arguably one of the most compelling limita- tions of existing HTM implementations: the inability to process transac- tions whose footprint exceeds the capacity of the processor's cache. By leveraging, in an innovative way, two hardware features provided by IBM POWER8 processors, namely Rollback-only Transactions and Suspend/Re- sume, P8TM can achieve up to 7× performance gains in workloads that stress the capacity limitations of HTM. The second contribution is DMP-TM (Dynamic Memory Partitioning- TM), a novel Hybrid TM (HyTM) that offloads the cost of detecting con- flicts between HTM and Software TM (STM) to off-the-shelf operating sys- tem memory protection mechanisms. DMP-TM's design is agnostic to the STM algorithm and has the key advantage of allowing for integrating, in an efficient way, highly scalable STM implementations that would, otherwise, demand expensive instrumentation of the HTM path. This allows DMP-TM to achieve up to 20× speedups compared to state of the ar

关键词： Transactional Memory parallel programming Concurrency Control Self-tuning Energy Efficiency Data Partitioning Dynamic Frequency and Volt-age Scaling (DVFS) Hardware Transactional Memory (HTM)

来源：评论

学校读者我要写书评

暂无评论

A Portable Multidimensional Coarray for C++ 26

A Portable Multidimensional Coarray for C++

引用

26th Euromicro International Conference on parallel, Distributed, and Network-Based Processing, PDP 2018

作者： Mobbauer, Felix Kowalewski, Roger Fuchs, Tobias Furlinger, Karl Computer Science Department MNM Ludwig-Maximilians-Universitat Germany

ISBN: (纸本)9781538649756

Fortran Coarrays are a well known data structure in High Performance Computing (HPC) applications. There have been various attempts to port the concept to other programming languages that have a wider user base outside of scientific computing. While a popular implementation of the partitioned global address space (PGAS) model is Unified parallel C (UPC), there is currently no portable implementation of Coarrays for C++. In this paper a portable version is presented, which is closely based on the Coarray C++ implementation of the Cray Compiling Environment. In this work we focus on a common subset of all proposed features by Cray. Our implementation utilizes the distributed data structures provided by the DASH library, demonstrating their universal applicability. Finally, a performance evaluation shows that our proposed Coarray abstraction adds negligible overhead and even outperforms native Coarray Fortran. © 2018 IEEE.

关键词： parallel programming

来源：评论

学校读者我要写书评

暂无评论

IT-ecosystem of the hybrilit heterogeneous platform for high-performance computing and training of IT-specialists 8

IT-ecosystem of the hybrilit heterogeneous platform for high...

引用

Selected Papers of the 8th International Conference "Distributed Computing and Grid-Technologies in Science and Education", GRID 2018

作者： Adam, Gheorge Bashashin, Maxim Belyakov, Dmitry Kirakosyan, Margarit Matveev, Mikhail Podgainy, Dmitry Sapozhnikova, Tatiana Streltsova, Oksana Torosyan, Shushanik Vala, Martin Valova, Lucia Vorontsov, Alexei Zaikina, Tatiana Zemlyanaya, Elena Zuev, Maxim Laboratory of Information Technologies Joint Institute for Nuclear Research Dubna Moscow Region141980 Russia 30 Reactorului St. Magurele - Bucharest077125 Romania Dubna State University Dubna Moscow Region141980 Russia Plekhanov Russian University of Economics Moscow117997 Russia Moscow117198 Russia Institute of Experimental Physics SAS Košice040 01 Slovakia

HybriLIT heterogeneous platform that is a component of the Multifunctional Information and Computing Complex (MICC) of Joint Institute for Nuclear Research. HybriLIT includes GOVORUN supercomputer and education and testing polygon;its platform is based on the latest computation architectures (processors;co-processors;graphical accelerators), and also modern software such as Intel Cluster Studio, CUDA, MATLAB, etc;thus, allowing to carry out extra-massive computations and reach sufficient acceleration, and also to provide training courses on parallel programming technologies and work on HPC-platforms for students, PhD students and young scientists [1]. In order to increase the efficiency of work on the heterogeneous platform HybriLIT, there appears a need to develop an information-computing environment for work with parallel programming technologies that provides users with possibility to use the resources of the supercomputer for carrying out resource-intensive and massive parallel tasks, use the applied software packages adapted for hybrid architectures, and also develop and debug applications using modern IT solutions and frameworks such as machine learning approaches for accelerating experimental data analysis. Software and information environment are also a convenient tool for organization of tutorials. The developing software and information environment, together with a heterogeneous computing system and a components for providing computations using application packages with a developed graphical interface, form an IT-ecosystem that allows you not only to carry out effective HPC computations, but it is also a fruitful platform for training IT-specialists in the HPC-sphere. © 2018 Gheorge Adam, Maxim Bashashin, Dmitry Belyakov, Margarit Kirakosyan, Mikhail Matveev, Dmitry Podgainy, Tatiana Sapozhnikova, Oksana Streltsova, Shushanik Torosyan, Martin Vala, Lucia Valova, Alexei Vorontsov, Tatiana Zaikina, Elena Zemlyanaya, Maxim Zuev.

关键词： parallel programming

来源：评论

学校读者我要写书评

暂无评论

A comparison of five parallel programming models for C++

A comparison of five parallel programming models for C++

引用

Proceedings of the International Convention MIPRO

作者： Ensar Ajkunic Hana Fatkic Emina Omerovic Kristina Talic Novica Nosovic Faculty of Electrical Engineering University of Sarajevo Sarajevo Bosnia and Herzegovina

Multi-core processors offer a growing potential of parallelism but pose a challenge of program development for achieving high performance in applications. This pape r presents a comparison of the five parallel programming models for implementing parallel programs in C++ on multi -core computer systems. The models under consideration are Intel ® 's Thread Building Blocks (TBB), OpenMPI, Intel ® 's Cilk™ Plus, OpenMP and Pthreads. For demonstration purposes multiple parallel implementations of an algorithm for matrix multiplication suitable for parallelization were created. The main goal of this paper is a comprehensive comparison of chosen models with respect to the following criteria: performance and coding effort required.

关键词： Message systems Libraries parallel programming Program processors parallel processing Data models

来源：评论

学校读者我要写书评

暂无评论

Pipeline pattern for parallel MCTS 10

Pipeline pattern for parallel MCTS

引用

10th International Conference on Agents and Artificial Intelligence, ICAART 2018

作者： Mirsoleimani, S Ali den Herik, Jaap van Plaat, Aske Vermaseren, Jos Leiden Centre of Data Science Leiden University Niels Bohrweg 1 Leiden2333 CA Netherlands Nikhef Theory Group Nikhef Science Park 105 Amsterdam1098 XG Netherlands

ISBN: (纸本)9789897582752

In this paper, we present a new algorithm for parallel Monte Carlo tree search (MCTS). It is based on the pipeline pattern and allows flexible management of the control flow of the operations in parallel MCTS. The pipeline pattern provides for the first structured parallel programming approach to MCTS. The Pipeline Pattern for parallel MCTS algorithm (called 3PMCTS) scales very well to a higher number of cores when compared to the existing methods. The observed speedup is 21 on a 24-core machine. Copyright © 2018 by SCITEPRESS – Science and Technology Publications, Lda. All rights reserved

关键词： parallel programming

来源：评论

学校读者我要写书评

暂无评论

Consistent representation of Fortran programs in PARFOR compiler at different levels of abstraction 20

Consistent representation of Fortran programs in PARFOR comp...

引用

20th Conference Scientific Services and Internet, SSI 2018

作者： Kataev, N.A. Russia

PARFOR parallelizing compiler is the main part of SAPFOR (System For Automated parallelization). This compiler can be applied as a stand-alone tool to exploit implicit parallelism in traditional sequential languages Fortran and C. It was primarily designed to perform source-to-source transformation of a sequential program for execution on parallel architectures with distributed memory. Implicitly parallel programming assumes that programmers may describe the properties of the original sequential program in order to reduce the complexity of finding an optimal program specific sequence of transform passes. PARFOR focuses on parallel programming in DVMH model. CDVMH and Fortran-DVMH languages are used. PARFOR relies on LLVM (Low Level Virtual Machine) compiler infrastructure to examine a program. However, program transformations are based on a higher level program representation in the form of an abstract syntax tree (AST). In this paper, we consider an approach that allows us to consistently represent programs at two levels of abstraction: the source-level (AST) and the low-level level (LLVM IR). The considered questions involve the interpretation of information derived from LLVM IR to retain a user-friendly description of analysis results. In addition, the possibilities of analysis of the transformed LLVM IR are explored to improve the quality of the source program analysis. We also discuss the reasons which argue the choice of LLVM as a base for PARFOR development. © 2018 CEUR-WS. All rights reserved.

关键词： parallel programming

来源：评论

学校读者我要写书评

暂无评论

parallel programming for multimedia applications

引用

MULTIMEDIA TOOLS AND APPLICATIONS 2011年第2期51卷 801-818页

作者： Kalva, Hari Colic, Aleksandar Garcia, Adriana Furht, Borko Florida Atlantic Univ Dept Comp & Elect Engn & Comp Sci Boca Raton FL 33431 USA

Computing capabilities are continuing to increase with the availability of multi core and many core processors. The wide availability of multi core processors has made parallel programming possible for end user applications running on desktops, workstations, and mobile devices. While parallel hardware has become common, software that exploits parallel capabilities is just beginning to take hold. Multimedia applications, with their data parallel nature and large computing requirements will benefit significantly from parallel programming. In this paper an overview of parallel programming is presented and languages and tools for parallel programming such as OpenMP and CUDA are introduced within the scope of multimedia applications.

关键词： parallel programming OpenMP CUDA SIMD Multimedia programming

来源：评论

学校读者我要写书评

暂无评论

Evaluation of Dynamic Task Scheduling Algorithms in a Runtime System for Heterogeneous Architectures 31

Evaluation of Dynamic Task Scheduling Algorithms in a Runtim...

引用

31st GI/ITG International Conference on Architecture of Computing Systems, ARCS 2018

作者： Becker, Thomas Busse, Pablo Schuele, Tobias Karlsruhe Institute of Technology Karlsruhe76131 Germany Siemens AG Corporate Technology Munich81739 Germany

ISBN: (纸本)9783800745593

Heterogeneous parallel architectures present many challenges to application developers. One of the most important ones is the decision where to execute a specific task. As today's systems are often dynamic in nature, this cannot be solved at design time. A solution is offered by runtime systems that employ dynamic scheduling algorithms. Still, the question which algorithm to use remains. In this paper, we describe the integration of dynamic task scheduling algorithms well-known in the literature into EMB2, a library for parallel programming of embedded heterogeneous systems. Moreover, we evaluate these algorithms on a real system using different benchmarks. The evaluation covers different modes: In immediate mode, tasks are scheduled in the order they arrive in the system, whereas in batch mode, all ready-to-execute tasks are considered during the scheduling decision. Our experimental results show that batch mode heuristics generally obtain better results. An exception is the Minimum Completion Time heuristic, which achieves similar results at less overhead and algorithm complexity. © ARCS 2018.

关键词： parallel programming

来源：评论

学校读者我要写书评

暂无评论

Contextual graphical environment for spatial visualisation of numerical experiments in continuum mechanics 8

Contextual graphical environment for spatial visualisation o...

引用

Selected Papers of the 8th International Conference "Distributed Computing and Grid-Technologies in Science and Education", GRID 2018

作者： Khramushin, V.N. Saint Petersburg State University Russia

The usage of open-source and easy-to-modify programme code for spatial visualisation of fast-evolving physical phenomena directly in the course of supercomputer calculations becomes relevant in design, research, construction and subsequent analysis of the validity of the simulated processes in resource-intensive numerical experiments, which is especially important in the study of non-stationary processes in continuum mechanics. Such visualisation has to have minimal impact on computational processes and allow for setting rheological parameters of simulated physical environment and criteria for dynamic and hybrid restructuring of computational processes. Almost any computational platform have embedded graphical means for visualisation of spatial geometrical objects using multi-core processors, which may provide solution to the formulated problem in full measure for parallel visualisation of the current results without substantial impact on the core computational processes. In the present research work we study one possible version of software suite which is based on graphical programming environment OpenGL, surrounded by tools for working with time and interval timers, input devices and text data views at the lowest possible level of direct input/output and interrupt processing in Windows OS. © 2018 Vasily N. Khramushin.

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：