检索结果-内蒙古大学图书馆

MERIT: Tensor Transform for Memory-Efficient Vision Processing on parallel Architectures

IEEE TRANSACTIONS ON VERY LARGE SCALE INTEGRATION (VLSI) SYSTEMS 2020年第3期28卷 791-804页

作者： Lin, Yu-Sheng Chen, Wei-Chao Chien, Shao-Yi Natl Taiwan Univ Grad Inst Elect Engn Taipei 10617 Taiwan Skywatch Inc Taipei 10084 Taiwan Inventec Inc Taipei 11167 Taiwan

Computationally intensive deep neural networks (DNNs) are well- suited to run on GPUs, but newly developed algorithms usually require the heavily optimized DNN routines to work efficiently, and this problem could be even more difficult for specialized DNN architectures. In this article, we propose a mathematical formulation that can be useful for transferring the algorithm optimization knowledge across computing platforms. We discover that data movement and storage inside parallel processor architectures can be viewed as tensor transforms across memory hierarchies, making it possible to describe many memory optimization techniques mathematically. Such transform, which we call memory-efficient ranged inner-product tensor (MERIT) transform, can be applied to not only DNN tasks but also many traditional machine learning and computer vision computations. Moreover, the tensor transforms can be readily mapped to existing vector processor architectures. In this article, we demonstrate that many popular applications can be converted to a succinct MERIT notation on GPUs, speeding up GPU kernels up to 20 times while using only half as many code tokens. We also use the principle of the proposed transform to design a specialized hardware unit called MERIT-z processor. This processor can be applied to a variety of DNN tasks as well as other computer vision tasks while providing comparable area and power efficiency to dedicated DNN application-specific integrated circuits (ASICs).

关键词： Transforms Magneto electrical resistivity imaging technique Computer architecture Tensile stress Task analysis Graphics processing units Optimization Neural network hardware parallel programming vector processors

来源：评论

学校读者我要写书评

暂无评论

HDOT - An approach towards productive programming of hybrid applications

引用

JOURNAL OF parallel AND DISTRIBUTED COMPUTING 2020年第0期137卷 104-118页

作者： Ciesko, Jan Martinez-Ferrer, Pedro J. Penacoba Veigas, Raul Teruel, Xavier Beltran, Vicenc Barcelona Supercomp Ctr Barcelona Spain Barcelona Supercomp Ctr Grp Parallel Programming Models Barcelona Spain Barcelona Supercomp Ctr Parallel & Distributed Programming Models Barcelona Spain

A wealth of important scientific and engineering applications are configured for use on high performance computing architectures using functionality found in the MPI specification. This specification provides application developers with a straightforward means for implementing their ideas for execution on distributed-memory parallel processing computers. OpenMP directives provide a means for operating on shared-memory regions of those computers. With the advent of machines composed of many-core processors, the strict synchronisation required by the bulk synchronous parallel (BSP) communication model can hinder performance increases. This is due to the complexity to handle load imbalances, to reduce serialisation imposed by blocking communication patterns, to overlap communication with computation and, finally, to deal with increasing memory overheads. The MPI specification provides advanced features such as non-blocking calls or shared memory to mitigate some of these factors. However, applying these features efficiently usually requires significant changes on the application structure. Task parallel programming models are being developed as a means of mitigating the abovementioned issues but without requiring extensive changes on the application code. In this work, we present a methodology to develop hybrid applications based on tasks called hierarchical domain overdecomposition with tasking (HDOT). This methodology overcomes most of the issues found on MPI-only and traditional hybrid MPI+OpenMP applications. However, by emphasising the reuse of data partition schemes from process-level and applying them to task-level, it enables a natural coexistence between MPI and shared-memory programming models. The proposed methodology shows promising results in terms of programmability and performance measured on a set of applications. (C) 2019 Elsevier Inc. All rights reserved.

关键词： parallel programming Hybrid programming MPI OpenMP OmpSs-2

来源：评论

学校读者我要写书评

暂无评论

Distributed non-negative matrix factorization with determination of the number of latent features

引用

JOURNAL OF SUPERCOMPUTING 2020年第9期76卷 7458-7488页

作者： Chennupati, Gopinath Vangara, Raviteja Skau, Erik Djidjev, Hristo Alexandrov, Boian LANL Informat Sci CCS 3 Grp Los Alamos NM 87545 USA LANL Theoret Div T 1 Grp Los Alamos NM 87545 USA

The holistic analysis and understanding of the latent (that is, not directly observable) variables and patterns buried in large datasets is crucial for data-driven science, decision making and emergency response. Such exploratory analyses require devising unsupervised learning methods for data mining and extraction of the latent features, and non-negative matrix factorization (NMF) is one of the prominent such methods. NMF is based on compute-intense non-convex constrained minimization, which, for large datasets requires fast and distributed algorithms. However, current parallel implementations of NMF fail to estimate the number of latent features. In practice, identifying these features is both difficult and significant for pattern recognition and latent feature analysis, especially for large dense matrices. In this paper, we introduce a distributed NMF algorithm coupled with distributed custom clustering followed by a stability analysis on dense data, which we call DnMFk, to determine the number of latent variables. The results on synthetic data and the classical Swimmer data set demonstrate the accuracy of model determination while scaling nearly linearly across multiple processors for large data. Further, we employ DnMFk to determine the number of hidden features from a terabyte matrix.

关键词： NMF Latent features Distributed processing Clustering parallel programming Silhouette Big data

来源：评论

学校读者我要写书评

暂无评论

Performance Impact on Neural Network with Partitioned Convolution Implemented with GPU programming

Performance Impact on Neural Network with Partitioned Convol...

引用

作者： Lee, Bill McMaster University

学位级别：硕士

For input data of homogenous type, the standard form of convolutional neural network is normally constructed with universally applied filters to identify global patterns. However, for certain datasets, there are identifiable trends and patterns within subgroups of input data. This research proposes a convolutional neural network that deliberately partitions input data into groups to be processed with unique sets of convolutional layers, thus identifying the underlying features of individual data groups. Training and testing data are built from historical prices of stock market and preprocessed so that the generated datasets are suitable for both standard and the proposed convolutional neural network. The author of this research also developed a software framework that can construct neural networks to perform necessary testing. The calculation logic was implemented using parallel programming and executed on a Nvidia graphic processing unit, thus allowing tests to be executed without expensive hardware. Tests were executed for 134 sets of datasets to benchmark the performance between standard and the proposed convolutional neural network. Test results show that the partitioned convolution method is capable of performance that rivals its standard counterpart. Further analysis indicates that more sophisticated method of building datasets, larger sets of training data, or more training epochs can further improve the performance of the partitioned neural network. For suitable datasets, the proposed method could be a viable replacement or supplement to the standard convolutional neural network structure.

关键词： convolutional neural network parallel programming partitioned

来源：评论

学校读者我要写书评

暂无评论

GPU programming Productivity in Different Abstraction Paradigms: A Randomized Controlled Trial Comparing CUDA and Thrust

引用

ACM TRANSACTIONS ON COMPUTING EDUCATION 2020年第4期20卷 1–27页

作者： Daleiden, Patrick Stefik, Andreas Uesbeck, Philip Merlin Univ Nevada 4505 S Maryland Pkwy Las Vegas NV 89154 USA

Coprocessor architectures in High Performance Computing are prevalent in today's scientific computing clusters and require specialized knowledge for proper utilization. Various alternative paradigms for parallel and offload computation exist, but little is known about the human factors impacts of using the different paradigms. With computer science student participants from the University of Nevada, Las Vegas with no previous exposure to Graphics Processing Unit programming, our study compared NVIDIA CUDA C/C++ as a control group and the Thrust library. The designers of Thrust claim their higher level of abstraction enhances programmer productivity. The trial was conducted on 91 participants and was administered through our computerized testing platform. Although the study was narrowly focused on the basic steps of an offloaded computation problem and was not intended to be a comprehensive evaluation of the superiority of one approach or the other, we found evidence that although Thrust was designed for ease of use, the abstractions tended to be confusing to students and in several cases diminished productivity. Specifically, abstractions in Thrust for (i) memory allocation through a C++ Standard Template Library-style vector library call, (ii) memory transfers between the host and Graphics Processing Unit coprocessor through an overloaded assignment operator, and (iii) execution of an offloaded routine through a generic transform library call instead of a CUDA kernel routine all performed either equal to or worse than CUDA.

关键词： Computer science education parallel programming threads human factors evidence evaluation empirical studies GPU programming

来源：评论

学校读者我要写书评

暂无评论

Optimal Kernel Design for Finite-Element Numerical Integration on GPUs

引用

COMPUTING IN SCIENCE & ENGINEERING 2020年第6期22卷 61-74页

作者： Banas, Krzysztof Kruzel, Filip Bielanski, Jan AGH Univ Sci & Technol Krakow Poland Cracow Univ Technol Inst Comp Sci Krakow Poland

This article presents the design and optimization of the GPU kernels for numerical integration, as it is applied in the standard form in finite-element codes. The optimization process employs autotuning, with the main emphasis on the placement of variables in the shared memory or registers. OpenCL and the first order finite-element method (FEM) approximation are selected for code design, but the techniques are also applicable to the CUDA programming model and other types of finite-element discretizations (including discontinuous Galerkin and isogeometric). The autotuning optimization is performed for four example graphics processors and the obtained results are discussed.

关键词： Finite Element Analysis Galerkin Method Graphics Processing Units Integration Optimisation parallel Architectures parallel programming Shared Memory Systems Isogeometric Discretization Discontinuous Galerkin Discretization Open CL Graphics Processors First Order Finite Element Method Approximation Autotuning Optimization Finite Element Discretizations CUDA programming Model Code Design Shared Memory Finite Element Codes GPU Kernels Finite Element Numerical Integration Optimal Kernel Design Finite Element Analysis Graphics Processing Units Jacobian Matrices Solid Modeling Approximation Algorithms Optimization Computational Modeling

来源：评论

学校读者我要写书评

暂无评论

Simplifying and implementing service level objectives for stream parallelism

引用

JOURNAL OF SUPERCOMPUTING 2020年第6期76卷 4603-4628页

作者： Griebler, Dalvan Vogel, Adriano De Sensi, Daniele Danelutto, Marco Fernandes, Luiz G. Pontifical Catholic Univ Rio Grande Sul PUCRS Sch Technol Porto Alegre RS Brazil Univ Pisa UNIPI Dept Comp Sci Pisa Italy Tres de Maio Fac SETREM Lab Adv Res Cloud Comp LARCC Tres De Maio Brazil

An increasing attention has been given to provide service level objectives (SLOs) in stream processing applications due to the performance and energy requirements, and because of the need to impose limits in terms of resource usage while improving the system utilization. Since the current and next-generation computing systems are intrinsically offering parallel architectures, the software has to naturally exploit the architecture parallelism. Implement and meet SLOs on existing applications is not a trivial task for application programmers, since the software development process, besides the parallelism exploitation, requires the implementation of autonomic algorithms or strategies. This is a system-oriented programming approach and requires the management of multiple knobs and sensors (e.g., the number of threads to use, the clock frequency of the cores, etc.) so that the system can self-adapt at runtime. In this work, we introduce a new and simpler way to define SLO in the application's source code, by abstracting from the programmer all the details relative to self-adaptive system implementation. The application programmer specifies which parts of the code to parallelize and the related SLOs that should be enforced. To reach this goal, source-to-source code transformation rules are implemented in our compiler, which automatically generates self-adaptive strategies to enforce, at runtime, the user-expressed objectives. The experiments highlighted promising results with simpler, effective, and efficient SLO implementations for real-world applications.

关键词： parallel programming Stream processing Self-adaptive Domain-specific language Power-aware computing

来源：评论

学校读者我要写书评

暂无评论

Efficient parallelisation of the packet classification algorithms on multi-core central processing units using multi-threading application program interfaces

引用

IET COMPUTERS AND DIGITAL TECHNIQUES 2020年第6期14卷 313-321页

作者： Abbasi, Mahdi Rafiee, Milad Bu Ali Sina Univ Engn Fac Dept Comp Engn Hamadan Hamadan Iran

The categorisation of network packets according to multiple parameters such as sender and receiver addresses is called packet classification. Packet classification lies at the core of Software-Defined Networking (SDN)-based network applications. Due to the increasing speed of network traffic, there is an urgent need for packet classification at higher speeds. Although it is possible to accelerate packet classification algorithms through hardware implementation, this solution imposes high costs and offers limited development capacity. On the other hand, current software methods to solve this problem are relatively slow. A practical solution to this problem is to parallelise packet classification using multi-core processors. In this study, the Thread, parallel patterns library (PPL), open multi-processing (OpenMP), and threading building blocks (TBB) libraries are examined and implemented to parallelise three packet classification algorithms, i.e. tuple space search, tuple pruning search, and hierarchical tree. According to the results, the type of algorithm and rulesets may influence the performance of parallelisation libraries. In general, the TBB-based method shows the best performance among parallelisation libraries due to using a theft mechanism and can accelerate the classification process up to 8.3 times on a system with a quad-core processor.

关键词： multi-threading application program interfaces telecommunication traffic parallel programming software libraries pattern classification multiprocessing systems packet switching parallelisation libraries classification process packet classification algorithms multicore central processing units multithreading application program interfaces network packets SDN-based network applications multicore processors open multiprocessing

来源：评论

学校读者我要写书评

暂无评论

Performance Tradeoffs in Shared-memory Platform Portable Implementations of a Stencil Kernel

Performance Tradeoffs in Shared-memory Platform Portable Imp...

引用

21st Eurographics Symposium on parallel Graphics and Visualization, EGPGV 2021

作者： Bethel, E. Wes Heinemann, Colleen Perciano, Talita Lawrence Berkeley National Laboratory BerkeleyCA United States San Francisco State University San FranciscoCA United States University of Illinois Urbana-ChampaignIL United States

ISBN: (纸本)9783038681380

Building on a significant amount of current research that examines the idea of platform-portable parallel code across different types of processor families, this work focuses on two sets of related questions. First, using a performance analysis methodology that leverages multiple metrics including hardware performance counters and elapsed time on both CPU and GPU platforms, we examine the performance differences that arise when using two common platform portable parallel programming approaches, namely OpenMP and VTK-m, for a stencil-based computation, which serves as a proxy for many different types of computations in visualization and analytics. Second, we explore the performance differences that result when using coarser- and finer-grained parallelism approaches that are afforded by both OpenMP and VTK-m. © 2021 The Author(s).

关键词： parallel programming

来源：评论

学校读者我要写书评

暂无评论

Highly parallelized Contour Integral Method for Computing Resonant Modes of Lossy Cavities

引用

IEEE TRANSACTIONS ON MAGNETICS 2020年第1期56卷 1-4页

作者： Pham-Xuan, Vinh Ackermann, Wolfgang De Gersem, Herbert Tech Univ Darmstadt Inst Teilchenbeschleunigung & Elektromagnet Felde D-64289 Darmstadt Germany

In this article, we address an efficient solver of the Maxwell eigenvalue problem for lossy cavity resonators. The curlcurl equation for the electric field is discretized using curved tetrahedral incomplete quadratic finite elements, resulting in a nonlinear eigenvalue formulation. The eigenvalue problem is efficiently solved using a contour integral method (CIM). This method enables an accurate computation of all eigenvalues within a predefined region and is implemented in a highly parallelized framework to enhance the performance of the algorithm. Numerical results are presented to demonstrate the accuracy and efficiency of the proposed method.

关键词： Cavity resonators contour integral method (CIM) eigenvalues and eigenfunctions finite-element analysis Maxwell equations 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：