检索结果-内蒙古大学图书馆

International Conference on parallel and distributed Systems (ICPADS)

作者： Hao Jiang Feng Wang Kuan Li Canqun Yang Kejia Zhao Chun Huang College of Computer Science National University of Defense Technology Changsha China Science and Technology on Parallel and Distributed Processing Laboratory National University of Defense Technology Changsha China

ISBN: (纸本)9781467386692

This paper presents an implementation of an accurate and efficient compensated Double-precision General Matrix Multiplication (DGEMM) based on OpenBLAS for 64-bit ARMv8 multi-core processors. Due to cancellation phenomena in floating point arithmetic, the results of DGEMM may not be as accurate as expected. In order to increase the accuracy of DGEMM, we compensate the error introduced by its dot product kernel (GEBP) by applying an error-free transformation to rewrite the kernel in assembly language. We optimize the computations in the inner kernel through exploiting loop unrolling, instruction scheduling and software-implemented register rotation to exploit instruction level parallelism (ILP). We also conduct a priori error analysis of the derived CompDGEMM. Our compensated DGEMM is as accurate as the existing quadruple precision GEMM using MBLAS, but is up to 6.4x faster. Our parallel implementation achieves good performance and scalability under varying thread counts across a range of matrix sizes evaluated.

关键词： Multicore processing Kernel Registers Libraries Error analysis Algorithm design and analysis

来源：评论

学校读者我要写书评

暂无评论

Mirror image:newfangled cell-level layout technique for single-event transient mitigation

引用

Chinese Science Bulletin 2014年第23期59卷 2850-2858页

作者： Pengcheng Huang Shuming Chen Zhengfa Liang Jianjun Chen Chunmei Hu Yibai He Micro-electronics and Microprocessor Institute National University of Defense Technology National Laboratory for Parallel and Distributed Processing National University of Defense Technology

Recent years,the hardening of combinational circuits is becoming a common *** the transistor-level hardening technique,the cell-level hardening technique,a divide and conquer strategy,can substantially make use of some typical character in the cell-circuit module to mitigate single event transient(SET)*** mirror image(MI)technique proposed in this paper can adequately enhance the charge sharing in those cell-circuits with stage-by-stage inverter-like structure.3D TCAD mixed-mode simulation have been performed in 65 nm twinwell bulk CMOS process,the results indicate that the MI technique can almost reduce the SET pulse width from the anterior-stage PMOS over 25%,and can mitigate the SET pulse width from the posterior-stage PMOS about 10%.The MI technique,a represent of the cell-level technique,may be the future of the hardening of combinational circuits.

关键词：单事件技术细胞瞬态镜像组合逻辑电路次布 CMOS工艺

来源：评论

学校读者我要写书评

暂无评论

UniMESH: The light-weight unidirectional channel Network-on-Chip in 2D mesh topology

UniMESH: The light-weight unidirectional channel Network-on-...

引用

International Conference on Electronics, Communications and Computers (CONIELECOMP)

作者： Feng Wang Xiantuo Tang Zuocheng Xing Hengzhu Liu Science and Technology on Parallel and Distributed Processing Laboratory National University of Defense Technology Changsha Hunan China Institute of Microelectronics National University of Defense Technology Changsha Hunan China

ISBN: (纸本)9781479974375

Power consumption, design complexity and areacost are limiting constraints in the design of interconnect for scalable many-core systems. To tackle the power and area concerns, we propose a light-weight unidirectional channel network-on-chip in 2D mesh topology (UniMESH), which simplifies router architectures, uses only half amount of channel links to guarantee a fully connected topology, and adopts a novel routing algorithm and deadlock recovery mechanism. As a result, it can reduce both design complexity and area-cost, and decrease some unwanted power consumption. Evaluations show that the proposed light-weight UniMESH can reduce 57.4% router areas, and save 39.3% total power consumption and only add few extra latency when compared with conventional 2D mesh design in SPLASH application simulations.

关键词： Routing System recovery Ports (Computers) Topology Latches Network topology Nickel

来源：评论

学校读者我要写书评

暂无评论

Running mechanism and implementation technique of self-adaptive software in open environment

引用

Jisuanji Xuebao/Chinese Journal of Computers 2015年第9期38卷 1893-1906页

作者： Mao, Xin-Jun Dong, Meng-Gao Qi, Zhi-Chang Yin, Jun-Wen Department of Computer Science and Technology College of Computer National University of Defense Technology Changsha410073 China Science and Technology on Parallel and Distributed Processing Laboratory College of Computer National University of Defense Technology Changsha410073 China Laboratory of Science and Technology on Integrated Logistic Support National University of Defense Technology Changsha410073 China

Due to the uncertainty and unpredictability of environment changes, it is a great challenge to develop self-adaptive systems in open environment. First, it is difficult for developers to clearly predict various environment changes and precisely define self-adaptation requirements at design-time. Second, many of self-adaptation decisions should be made by system at run-time. In order to deal with the problems, the paper presents an approach that is based on software agent technology and organization metaphor to support the development and running of such systems. Our approach enables developer to describe self-adaptive systems and investigate self-adaptation according to the high-level organization abstractions. A self-adaptation mechanism called role dynamic binding is designed and on-line self-adaptation is achieved by introducing enforcement learning. The paper details the on-line self-adaptation decision algorithm that integrates dynamic binding mechanism with enforcement learning together. Especially, a general-purpose and systematics software engineering solution to developing such system is provided, including self-adaptive software model, implementation framework, structured process and supporting software environment SADE+. A case is studied to illustrate our approach and validate its effectiveness. ©, 2015, Jisuanji Xuebao/Chinese Journal of Computers. All right reserved.

关键词： Dynamics

来源：评论

学校读者我要写书评

暂无评论

A Novel Run-time Load Balancing Method for MapReduce

A Novel Run-time Load Balancing Method for MapReduce

引用

International Conference on Computer Science and Network Technology

作者： Zhihong Liu Yaping Liu Baosheng Wang Zhenghu Gong College of Computer National University of Defense Technology Changsha Hunan China Science and Technology on Parallel and Distributed Processing Laboratory National University of Defense Technology Changsha Hunan China

ISBN: (纸本)9781467381741

In recent years, many companies are embracing the Hadoop MapReduce system for large-data processing with completion time constrains. However, exiting Hadoop schedulers still suffer from the reducer load imbalancing problem. In this paper, we present a novel run-time load balancing method for MapReduce. Our approach predicts the workload of each reduce task at run-time, and assigns the reduce tasks to specified machines based on the estimated workload of reduce tasks dynamically. Therefore, our approach can achieve load balance among machines. The experimental results show that our approach achieves high accuracy while predicting the workload of reduce tasks, and improves the job completion time by up to 23.15%.

关键词： MapReduce load balancing task scheduling Load balancing TASK SCHEDULING Completion time Runtime Workload Religious Missions

来源：评论

学校读者我要写书评

暂无评论

MilkyWay-2 supercomputer： system and application

引用

Frontiers of Computer Science 2014年第3期8卷 345-356页

作者： Xiangke LIAO Liquan XIAO Canqun YANG Yutong LU Science and Technology on Parallel and Distributed Processing Laboratory National University of Defense Technology Changsha 410073 China College of Computer National University of Defense Technology Changsha 410073 China

On June 17, 2013, MilkyWay-2 （Tianhe-2） supercomputer was crowned as the fastest supercomputer in the world on the 41th TOP500 list. This paper provides an overview of the MilkyWay-2 project and describes the design of hardware and software systems. The key architecture features of MilkyWay-2 are highlighted, including neo-heterogeneous compute nodes integrating commodity- off-the-shelf processors and accelerators that share similar instruction set architecture, powerful networks that employ proprietary interconnection chips to support the massively parallel message-passing communications, proprietary 16- core processor designed for scientific computing, efficient software stacks that provide high performance file system, emerging programming model for heterogeneous systems, and intelligent system administration. We perform extensive evaluation with wide-ranging applications from LINPACK and Graph500 benchmarks to massively parallel software deployed in the system.

关键词： MilkyWay-2 supercomputer petaflops computing neo-heterogeneous architecture interconnect network heterogeneous programing model system management benchmark optimization performance evaluation

来源：评论

学校读者我要写书评

暂无评论

The TH Express high performance interconnect networks

引用

Frontiers of Computer Science 2014年第3期8卷 357-366页

作者： Zhengbin PANG Min XIE Jun ZHANG Yi ZHENG Guibin WANG Dezun DONG Guang SUO Science and Technology on Parallel and Distributed Processing Laboratory National University of Defense Technology Changsha 410073 China College of Computer National University of Defense Technology Changsha 410073 China

Interconnection network plays an important role in scalable high performance computer （HPC） systems. The TH Express-2 interconnect has been used in MilkyWay-2 system to provide high-bandwidth and low-latency interprocessot communications, and continuous efforts are devoted to the development of our proprietary interconnect. This paper describes the state-of-the-art of our proprietary interconnect, especially emphasizing on the design of network interface. Several key features are introduced, such as user-level communication, remote direct memory access, offload collective operation, and hardware reliable end-to-end communication, etc. The design of a low level message passing infrastructures and an upper message passing services are also proposed. The preliminary performance results demonstrate the efficiency of the TH interconnect interface.

关键词： HPC network interface chip （NIC） TH Express nterconnect offload collective operation

来源：评论

学校读者我要写书评

暂无评论

Fast image matching algorithm based on affine invariants

引用

Journal of Central South University 2014年第5期21卷 1907-1918页

作者：张毅卢凯高颖慧 National Laboratory for Parallel and Distributed Processing(National University of Defense Technology) College of Computer National University of Defense Technology College of Electronic Science and Engineering National University of Defense Technology

Feature-based image matching algorithms play an indispensable role in automatic target recognition （ATR）. In this work, a fast image matching algorithm （FIMA） is proposed which utilizes the geometry feature of extended centroid （EC） to build affine invariants. Based on at-fine invariants of the length ratio of two parallel line segments, FIMA overcomes the invalidation problem of the state-of-the-art algorithms based on affine geometry features, and increases the feature diversity of different targets, thus reducing misjudgment rate during recognizing targets. However, it is found that FIMA suffers from the parallelogram contour problem and the coincidence invalidation. An advanced FIMA is designed to cope with these problems. Experiments prove that the proposed algorithms have better robustness for Gaussian noise, gray-scale change, contrast change, illumination and small three-dimensional rotation. Compared with the latest fast image matching algorithms based on geometry features, FIMA reaches the speedup of approximate 1.75 times. Thus, FIMA would be more suitable for actual ATR applications.

关键词： affine invariants image matching extended centroid robustness performance

来源：评论

学校读者我要写书评

暂无评论

High-energy-density electron beam from interaction of two successive laser pulses with subcritical-density plasma

引用

Physical Review Accelerators and Beams 2016年第2期19卷 021301-021301页

作者： J. W. Wang W. Yu M. Y. Yu H. Xu J. J. Ju S. X. Luan M. Murakami M. Zepf S. Rykovanov Helmholtz Institute Jena Jena 07743 Germany State Key Laboratory of High Field Laser Physics Shanghai Institute of Optics and Fine Mechanics Chinese Academy of Sciences Shanghai 201800 China Institute for Fusion Theory and Simulation and the Department of Physics Zhejiang University Hangzhou 310027 China Institute for Theoretical Physics I Ruhr University Bochum D-44780 Germany National Laboratory for Parallel and Distributed Processing School of Computer Science National University of Defense Technology Changsha 410073 China Institute of Laser Engineering Osaka University Osaka 565-0871 Japan Centre for Plasma Physics School of Mathematics and Physics Queen’s University Belfast Belfast BT7 1NN United Kingdom

It is shown by particle-in-cell simulations that a narrow electron beam with high energy and charge density can be generated in a subcritical-density plasma by two consecutive laser pulses. Although the first laser pulse dissipates rapidly, the second pulse can propagate for a long distance in the thin wake channel created by the first pulse and can further accelerate the preaccelerated electrons therein. Given that the second pulse also self-focuses, the resulting electron beam has a narrow waist and high charge and energy densities. Such beams are useful for enhancing the target-back space-charge field in target normal sheath acceleration of ions and bremsstrahlung sources, among others.

关键词： Plasma acceleration & new acceleration techniques

来源：评论

学校读者我要写书评

暂无评论

MilkyWay-2： back to the world Top 1

引用

Frontiers of Computer Science 2014年第3期8卷 343-344页

作者： Xiangke LIAO Science and Technology on Parallel and Distributed Processing Laboratory National University of Defense Technology Changsha 410073 China College of Computer National University of Defense Technology Changsha 410073 China

On the 41st Top500 list announced in June 2013, the MilkyWay-2 system produced by national University of Defense Technology （NUDT） in China won the first place with a LINPACK test result of 33.86 PFLOPS. It has been one and a half year since its predecessor, MilkyWay-1 （TH-1）, reached the same place for the first time. On the newest Top500 list published in November 2013, MilkyWay-2 continued to win the champion.

关键词：

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：