检索结果-内蒙古大学图书馆

24th ACM International Conference on Supercomputing, ICS'10

作者： Dou, Yong Lei, Yuanwu Wu, Guiming Guo, Song Zhou, Jie Shen, Li National Laboratory for Parallel and Distributed Processing NUDT Changsha 410073 China

ISBN: (纸本)9781450300186

In this paper we explore the capability and flexibility of FPGA solutions in a sense to accelerate scientific computing applications which require very high precision arithmetic, based on 128-bit or even 256-bit floating-point number representation. This paper addresses the accuracy when performing LU decomposition on large-scale matrices. In future ExaScale computing environments, accuracy errors are expected to increase up to a level which leaves only 11 significant bits in the mantissa. This is caused by the required large amount of accumulation operations which are in the order of O(n 3). Using exact long fixed-point numbers instead of usual floatingpoint numbers in the accumulation process, leads to exact accumulation results with only one bit error, originated by the rounding in the last normalization step. We have developed two types of High Precision Multiplication and Accumulation (HP-MAC), for Double-Double (128 bits) and Quad-Double (256 bits) floating-point, respectively, and implemented them into FPGA devices. We propose a two-level RAM banks scheme to store and add long fixed-point numbers with minimized crucial data paths lengths. We also introduce a scheme of partial summation to enhance the pipeline throughput of MAC operations, by dividing the summation function into 4 partial operations, processed in 4 banks. To prove the concept, we prototyped six 128-bit HP-MAC units into a Xilinx Virtex-5 XC5VLX330 FPGA chip and performed LU decomposition. The experimental results show accuracy improvement of 10 to 24 bits, compared to a software approach with similar precision arithmetic. Moreover, our LU decomposition implementation, based on FPGA running at 133MHz, achieves 29X - 56X better performance and much lower power consumption compared to the use of a software-based library running on an Intel Core2 Quad Q8200 CPU at 2.33GHz. © 2010 ACM.

关键词： Field programmable gate arrays (FPGA)

来源：评论

学校读者我要写书评

暂无评论

Communication-aware task partition and voltage scaling for energy minimization on heterogeneous parallel systems

Communication-aware task partition and voltage scaling for e...

引用

2011 12th International Conference on parallel and distributed Computing, Applications and Technologies, PDCAT 2011

作者： Wang, Guibin Song, Wei National Laboratory for Parallel and Distributed Processing National University of Defense Technology China

ISBN: (纸本)9780769545646

Heterogeneous parallel systems have become popular in general purpose computing and even high performance computing fields. There are many studies focused on harnessing heterogeneous parallel processing for better performance. However the energy optimization for heterogeneous system has not been well studied. Owing to the differences in performance and energy consumption, the energy optimization technique for heterogeneous system is different from the existing methods designed for homogeneous system. Besides typical voltage scaling method, reasonable task partitioning is also an essential method for optimizing energy consumption on heterogeneous systems. Through partitioning a data parallel task and mapping sub-tasks onto several processors, one could achieve better performance and reduced energy consumption. As the computation cost reduces with specific accelerators, the communication overhead becomes more prominent. Therefore, the task partition optimization should holistically consider the computation improvement and communication overhead to achieve higher energy efficiency. Typically, task partition and voltage scaling are not orthogonal and influence the effect of each other in the energy optimization problem. In order to harness both two knobs efficiently, this paper proposes an integer linear programming (ILP) based energy-optimal solution designed for heterogeneous system. We present a case study of optimizing MGRID benchmark on a typical CPU-GPU heterogeneous system. The experimental results demonstrate that the proposed method could exploit the heterogeneity in different processors and achieve improved energy efficiency. © 2011 IEEE.

关键词： Energy efficiency

来源：评论

学校读者我要写书评

暂无评论

Adaptive Linearized Alternating Direction Method of Multipliers for Non-Convex Compositely Regularized Optimization Problems

引用

Tsinghua Science and Technology 2017年第3期22卷 328-341页

作者： Linbo Qiao Bofeng Zhang Xicheng Lu Jinshu Su College of Computer National University of Defense Technologyand National Laboratory for Parallel and Distributed ProcessingNational University of Defense TechnologyChangsha 410073China College of Computer National University of Defense TechnologyChangsha 410073China

We consider a wide range of non-convex regularized minimization problems, where the non-convex regularization term is composite with a linear function engaged in sparse learning. Recent theoretical investigations have demonstrated their superiority over their convex counterparts. The computational challenge lies in the fact that the proximal mapping associated with non-convex regularization is not easily obtained due to the imposed linear composition. Fortunately, the problem structure allows one to introduce an auxiliary variable and reformulate it as an optimization problem with linear constraints, which can be solved using the Linearized Alternating Direction Method of Multipliers （LADMM）. Despite the success of LADMM in practice, it remains unknown whether LADMM is convergent in solving such non-convex compositely regularized optimizations. In this research, we first present a detailed convergence analysis of the LADMM algorithm for solving a non-convex compositely regularized optimization problem with a large class of non-convex penalties. Furthermore, we propose an Adaptive LADMM （AdaLADMM） algorithm with a line-search criterion. Experimental results on different genres of datasets validate the efficacy of the proposed algorithm.

关键词： adaptive linearized alternating direction method of multipliers non-convex compositely regularizedoptimization cappled-ll regularized logistic regression

来源：评论

学校读者我要写书评

暂无评论

Weakly hard real-time scheduling algorithm for multimedia embedded system on multiprocessor platform

Weakly hard real-time scheduling algorithm for multimedia em...

引用

2008 the 1st IEEE International Conference on Ubi-Media Computing and Workshops, U-Media2008

作者： Wu, Tong Jin, Shiyao National Laboratory of Parallel and Distributed Processing NUDT Changsha Hunan China

ISBN: (纸本)9781424418657

Multiprocessor architectures are becoming more attractive for embedded systems, and also for multimedia embedded systems. In multimedia embedded systems, there exist both hard real-time tasks and multimedia stream with QoS guarantee. In this context, researched on integrated schedule of both hard real-time tasks and streams are urgent affairs. This paper analyzes the shortcomings of the current approach - multimedia server, and then based on the DBF algorithm, proposes an algorithm which also considers the resource constraint. According to the different budget schemes, greedy algorithm and optimistic algorithm are brought up. Results show the performance of the algorithms. © 2008 IEEE.

关键词： Embedded systems

来源：评论

学校读者我要写书评

暂无评论

A prototype of Web-based distributed simulation environment 4

A prototype of Web-based distributed simulation environment

引用

4th International Conference/Exhibition on High Performance Computing in the Asia-Pacific Region, HPC-Asia 2000

作者： Dang, Gang Wang, Xiaoqing Zhang, Wensong Jin, Shiyao National Laboratory of Parallel and Distributed Processing National University of Defense Technology China

ISBN: (纸本)0769505902

Nowadays, many simulation environments not only can not reuse existing simulation models and tools, but also depend on operating systems and hardware platforms, and even more they lack the capability to execute over the Internet and the Web. The paper addresses these disadvantages by putting forward a prototype of a distributed simulation environment based on the Web (DSEW). It introduces both the technology of software components and the technology of integration with Java and CORBA, which enables portability, scalability, reusability, interoperability and visualization of the simulation application, and can also shorten the development period and communicate efficiently. © 2000 IEEE.

关键词： Common object request broker architecture (CORBA)

来源：评论

学校读者我要写书评

暂无评论

Uml based statistical testing acceleration of distributed safety-critical software

引用

2nd International Symposium on parallel and distributed processing and Applications, ISPA 2004

作者： Yan, Jiong Wang, Ji Chen, Huo-Wang National Laboratory for Parallel and Distributed Processing Changsha China

ISBN: (纸本)9783540241287

It is necessary to assess the reliability of distributed safety-critical systems to a high degree of confidence before they are deployed in the field. However, distributed safety-critical software systems often include some rarely executed critical functions that are often inadequately tested in statistical testing based reliability estimation. This paper presents a method that can accelerate statistical testing of distributed safety-critical software. The method starts with the derivation of scenario usage diagram model (SUD) from UML diagrams annotated with usage related attributes and reliability attributes. Then the statistical testing accelerating method based on importance sampling is presented. When both the critical scenarios and the entire software are adequately tested, the method can still compute the unbiased software reliability from the test results with much less test cases. Thus, the statistical testing cost of distributed safety-critical software can be reduced effectively. © Springer-Verlag Berlin Heidelberg 2004.

关键词： Software reliability

来源：评论

学校读者我要写书评

暂无评论

Recent advances on trusted computing in China

引用

Chinese Science Bulletin 2012年第35期57卷 4529-4532页

作者： DONG Wei CHEN LiQian School of Computer National University of Defense TechnologyChangsha 410073China National Laboratory for Parallel and Distributed Processing Changsha 410073China

This article highlights some recent research advances on trusted computing in China,focusing mainly on the methodologies and technologies related to trusted computing module,trusted computing platform,trusted network ... 详细信息

关键词：可信计算平台中国计算模块网络连接软件

来源：评论

学校读者我要写书评

暂无评论

Chinese named rntity recognition with a hybrid-statistical model

Chinese named rntity recognition with a hybrid-statistical m...

引用

7th Asia-Pacific Web Conference on Web Technologies Research and Development - APWeb 2005

作者： Zhang, Xiaoyan Wang, Ting Tang, Jintao Zhou, Huiping Chen, Huowang National Laboratory for Parallel and Distributed Processing Changsha Hunan 410073 China

With the rapid growth of the available information on the Internet, it is more difficult for us to find the relevant information quickly on the Web. Named Entity Recognition (NER), one of the key techniques in some web information processing tools such as information retrieval and information extraction, has been paid more and more attention. In this paper we address the problem of Chinese NER using a hybrid-statistical model. This study is concentrated on entity names (personal names, location names and organization names), temporal expressions (dates and times) and number expressions. The method is characterized as follows: firstly, NER and Part-of-Speech tagging have been integrated into a unified framework;secondly, it combines Hidden Markov Model (HMM) with Maximum Entropy Model (MEM) by taking MEM as a sub-model invoked in Viterbi algorithm;thirdly, the Part-of-Speech information of the context has been used in MEM. The experiment shows that the hybrid-statistical model could achieve preferable results of Chinese NER, in which the F1 value ranges from 74% to 92% for all kinds of named entities on an open-test data. © Springer-Verlag Berlin Heidelberg 2005.

关键词： Pattern recognition

来源：评论

学校读者我要写书评

暂无评论

A Novel Multi-objective Neural Architecture Search Algorithm via Gaussian Progress Sampling 5

A Novel Multi-objective Neural Architecture Search Algorithm...

引用

5th IEEE International Conference on Artificial Intelligence and Big Data, ICAIBD 2022

作者： Chen, Xuehui Jiang, Jingfei Niu, Xin Pan, Hengyue Dong, Peijie Wei, Zimian National University of Defense Technology National Laboratory for Parallel and Distributed Processing Changsha China

ISBN: (纸本)9781665499132

Multi-objective neural architecture search (NAS) algorithms aim to automatically search the neural architecture suitable for different computing power platforms by using multi-objective optimization methods. The LEMONADE algorithm, which is a representative algorithm of multi-objective NAS algorithms, maintains a population of networks on an approximation of the Pareto front of the multiple objectives, such as predictive performance, number of parameters or FLOPs. To address the irrationality and repeatability of only sampling based on cheap objectives in LEMONADE, we propose a novel multi-objective neural architecture search algorithm via Gaussian Process sampling, dubbed GP-LEMONADE. Meanwhile, to make the sampling process more efficient, we design the online predictor based on Gaussian Process to predict expensive objectives, and sample candidate networks by combining cheap objectives and expensive objectives, so as to ensure the rationality and efficiency of sampling. Experiments show that the GP-LEMONADE algorithm evolves 100 generations and obtains the SOTA model with 3.98% test error. This process only takes 7.38 GPU days, which is 26.75 GPU days shorter than that of LEMONADE. Our methods have improved the performance of the LEMONADE algorithm and ensured the rationality and efficiency of sampling during the evolution, which effectively improving the search efficiency of multi-objective NAS algorithms. © 2022 IEEE.

关键词： Multiobjective optimization

来源：评论

学校读者我要写书评

暂无评论

A data communication scheduler for stream programs on CPU-GPU platform

A data communication scheduler for stream programs on CPU-GP...

引用

10th IEEE International Conference on Computer and Information Technology, CIT-2010, 7th IEEE International Conference on Embedded Software and Systems, ICESS-2010, 10th IEEE Int. Conf. Scalable Computing and Communications, ScalCom-2010

作者： Tang, Tao Xu, Xinhai Lin, Yisong National Laboratory for Parallel and Distributed Processing National University of Defense Technology Changsha China

ISBN: (纸本)9780769541082

In recent years, heterogeneous parallel system have become a focus research area in high performance computing field. Generally,in a heterogeneous parallel system, CPU provides the basic computing environment and special purpose accelerator (GPU in this paper) provides high computing performance. However, the overall performance of the system is prone to be limited by the data communication between the CPU and the GPU. Data communication is typically used to synchronize the array on the CPU and the stream (in AMD's terminology) on the GPU. In many cases, programmers just add data synchronization for each GPU invoking independently. It is easy to program in this manner but much redundant communication may be introduced, which will dramatically degrade the overall performance. To alleviate this problem, based on the stream programming model, we propose a heuristic data communication schedule approach in this paper. By analyzing the state transition of stream/array data pair, relaxing the synchronization strategy conditionally and considering optimization for branch and loop control structure, our approach can significantly reduce the redundant data communication in most cases. © 2010 IEEE.

关键词： Graphics processing unit

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：