检索结果-内蒙古大学图书馆

2010 2nd International Conference on MultiMedia and Information Technology, MMIT 2010

作者： Shao, Chenxi Wang, Lizhong Computer Science and Technology School of University of Science and Technology of China Hefei China Anhui Province Key Laboratory Software in Computing and Communication Hefei 230027 China MOE-Microsoft Key Laboratory Multimedia Computing and Communication University of Science and Technology of China Hefei China

ISBN: (纸本)9780769540085

In the process of supply chain (SC) management, time inventory management problem is extremely important. In terms of academic methods, quantitative methods are very popular as the researchers could calculate the inventory if they got the historic data of some SC. However, based on quantitative methods and the results cannot too be convincible. This paper considered a supply chain system includes several kinds of products. As to the historic suppliers' demand data of this SC system, firstly we applied a quantitative forecasting analysis method to it;secondly we made a qualitative analysis to improve the complex system's inventory management performance. According to the comparison between quantitative method and the method used in this paper, we find that the accuracy is more perfect. Not only the inventory cost is lower, also the forecasting accuracy is better. © 2010 IEEE.

关键词： Supply chain management

来源：评论

学校读者我要写书评

暂无评论

Stochastic prefix-based fault tolerant source routing algorithm for network on chip

Stochastic prefix-based fault tolerant source routing algori...

引用

2012 International Conference on Computer and Information Science, ICCIS 2012 - A Conference of World Engineering, Science and Technology Congress, ESTCON 2012

作者： Xu, Gengchun Ren, Kaixin Gu, Naijie Anhui Province Key Laboratory of Computing and Communication Software Hefei China USTC-SICT Joint Laboratory on Network and Communication Hefei China School of Computer Science and Technology University of Science and Technology of China Hefei China

ISBN: (纸本)9781467319386

In this paper, a novel fault-tolerant source routing algorithm for Network on Chip (NOC) called Stochastic Prefix-based Source Routing (SPSR) is proposed. Compared to non-source routing algorithms, it releases the intermediate node from complicated decision-making or routing table maintenance. Unlike the traditional source routing algorithms which use broadcast packets to record the YD of every intermediate node in Route Discovery, it predetermine prospective routes, which can greatly reduces the packets generated and forwarded in the Route Discovery phase, and therefore reduces the power consumption. The proposed routing algorithm is implemented on the open source simulator Nirgam [14], incorporating Orion [15] to estimate the power consumption. Experiment results show that the proposed algorithm can greatly reduce the power consumption in the route discovery and the latency of SPSR is comparable with that of the broadcasting mechanism. © 2012 IEEE.

关键词： Network-on-chip

来源：评论

学校读者我要写书评

暂无评论

Cache locking optimization in java virtual machine

Cache locking optimization in java virtual machine

引用

2013 IEEE Conference Anthology, ANTHOLOGY 2013

作者： Lin, Chuanwen Gu, Naijie Cai, Songsong School of Computer Science and Technology University of Science and Technology of China Anhui Province Key Laboratory of Computing and Communication Software Hefei China Institute of Computing Technology Chinese Academy of Sciences Beijing China

ISBN: (纸本)9781479916603

Cache plays an important role in multilevel storage system. It can greatly reduce the memory access latency. So the cache hit rate has a significant impact on the performance of the application. Many processors provide cache locking mechanism, which can lock the certain lines in cache. It enables an application to affect the cache replacement decisions under software control. This paper presents a novel method, which uses cache locking mechanism to reduce the run-time of java virtual machine (JVM). JVM often uses just-in-time compiler (JIT) to improve the performance. JIT compiles the method that has been invoked certain times, and then JVM executes the compiled method when invoking this method the next time. This paper analyzes the calling situation of the compiled method in JVM, and then proposes a heuristic approach to lock the compiled method in cache for an appropriate period. It can reduce cache miss rate when JVM executes the compiled method. The algorithm has been implemented in HotSpot based on Loongson-3A. Also, it can be implemented in other run-time systems. Experiment results show that the cache locking heuristic algorithm averagely reduces the cache miss rate by 8.5%, and improves the performance by 4% on the benchmark SPECjvm2008. © 2013 IEEE.

关键词： Application programs

来源：评论

学校读者我要写书评

暂无评论

Models of parallel computation :a survey and classification

引用

中国高等学校学术文摘·计算机科学 2007年第2期1卷 156-165页

作者： ZHANG Yunquan CHEN Guoliang SUN Guangzhong MIAO Qiankun Laboratory of Parallel Computing Institute of SoftwareChinese Academy of SciencesBeijing 100080China State Key Laboratory of Computer Science Institute of SoftwareChinese Academy of SciencesBeijing 100080China Anhui Province-MOST Key Co-Lab of High Performance Computing and Its Applications Department of Computer Science and TechnologyUniversity of Science and Technology of ChinaHefei 230027China

In this paper,the state-of-the-art parallel computational model research is *** will introduce various models that were developed during the past *** to their targeting architecture features,especially memory organization,we classify these parallel computational models into three *** models and their characteristics are discussed based on three generations *** believe that with the ever increasing speed gap between the CPU and memory systems,incorporating non-uniform memory hierarchy into computational models will become *** the emergence of multi-core CPUs,the parallelism hierarchy of current computing platforms becomes more and more *** this complicated parallelism hierarchy in future computational models becomes more and more important.A semi-automatic toolkit that can extract model parameters and their values on real computers can reduce the model analysis complexity,thus allowing more complicated models with more parameters to be *** memory and hierarchical parallelism will be two very important features that should be considered in future model design and research.

关键词： parallel computational models hierarchicalmemory hierarchical parallelism three generations memorymodel

来源：评论

学校读者我要写书评

暂无评论

IPRAR: A DFG-based approach to instruction clustering for multicluster VLIW DSP processor with SIMD structure

引用

Journal of Computational Information Systems 2014年第3期10卷 1257-1269页

作者： Yang, Yangzhao Gu, Naijie Zhao, Zeng Ren, Kaixin School of Computer Science and Technology University of Science and Technology of China Hefei 230027 China Anhui Province Key Laboratory of Computing and Communication Software Hefei 230027 China USTC and Loongson Technology Associated Laboratory Institute of Advanced Technology University of Science and Technology of China Hefei 230027 China

Modern Very Long Instruction (VLIW) DSP can improve performance by using instruction-level parallelism (ILP) and obtain better parallelism through instruction clustering. The essence of clustering is resource allocation. Traditional clustering method assumes that one instruction can only be assigned to a certain cluster, which is inapplicable to the architecture with SIMD structure. To address this issue, this paper presents IPRAR, a novel instruction clustering algorithm for the features of SIMD structure based on DFG. Due to considering the features of SIMD structure, IPRAR can be implemented on BWDSP100 with satisfactory. Besides, IPRAR can make the load of cluster more balanced and minimize the intercluster communication overload. Finally, numerous experiment results show that the IPRAR has an average of 7-10% performance improvement compared to the traditional methods. © 2014 Binary Information Press.

关键词： Clustering algorithms

来源：评论

学校读者我要写书评

暂无评论

Implicit interpolation of time vector series

Implicit interpolation of time vector series

引用

2011 7th International Conference on Natural Computation, ICNC 2011

作者： Li, Dao-Lun Zha, Wen-Shu Lu, De-Tang Department of Modern Mechanics University of Science and Technology of China China Key Laboratory of Software in Computing and Communication of Anhui Province University of Science and Technology of China Hefei 230027 China

ISBN: (纸本)9781424499533

Time vector series abound in many fields, which are different from time series. Based on mapping and implicit function interpolation, the method of implicit interpolation over time vector series is developed and studied. Time vector series are mapped into a sequence of closed curves or surfaces, which are seen as the interpolation data set. Based on the interpolation data set, the implicit interpolation function is constructed and from which an isoline is drawn. The inverse mapping of the isoline is the prediction of vector series at the new time. Based on the well logging data an application is given to predict the unknown isotope logging data of year 2004 with the known data of year 2003 and 2005 which shows the performance of the method. © 2011 IEEE.

关键词： Mapping

来源：评论

学校读者我要写书评

暂无评论

Precisely reconstruct porous media model based on synchrotron radiation slice images

Precisely reconstruct porous media model based on synchrotro...

引用

2009 International Conference on Computational Intelligence and software Engineering, CiSE 2009

作者： Song, Bo Dong, Lanfang Lu, Detang Anhui Province Key Lab of Software in Computing and Communication School of Computer Science and Technology USTC Hefei China Institute of Engineering and Science Software USTC Hefei China

ISBN: (纸本)9781424445073

In this paper a method for precisely reconstructing porous media three-dimensional model based on slice images is proposed. It first processes the original slice images, then uses 3D seed filling algorithm to find all pores based on the constructed spatial data, finally uses the modified marching cubes algorithm based on bounding box technology to render material skeletons and pores. Associating with the porous media flow specific application, a novel invalid pore removing method is proposed. The final reconstructed model shows that our method can precisely reconstruct the pore network and recover the pore shape. It also can identify the pores which meet spatial scale threshold conditions. Comparison of running time between the original marching cubes algorithm and the modified marching cubes algorithm is given. It shows that due to the bounding box technology the running time of modified marching cubes algorithm is shorten greatly when the pores are far away from each other. ©2009 IEEE.

关键词： Porous materials

来源：评论

学校读者我要写书评

暂无评论

Optimizing BLAS2 for a decoupled access/execute architecture processor

引用

Journal of Computational Information Systems 2014年第3期10卷 1231-1241页

作者： Zhao, Zeng Gu, Naijie Yang, Yangzhao Ren, Kaixin School of Computer Science and Technology University of Science and Technology of China Hefei 230027 China USTC and Loongson Technology Associated Laboratory Institute of Advanced Technology University of Science and Technology of China Hefei 230027 China Anhui Province Key Laboratory of Computing and Communication Software Hefei 230027 China

Basic Linear Algebra Subroutines (BLAS) is a widely used basic mathematical library for high-performance computing. It has a great impact on the performance of supercomputers. This paper focuses on memory accessing optimization for the level-2 library of BLAS (BLAS2) based on Godson-3B chips. The key contribution of this work is proposing several methods to make full use of the Godson-3B's hardware features, as well as to improve the performance of memory access. GEMV, the kernel function of BLAS2, is selected to demonstrate the optimization methods for Godson-3B. Using Single Instruction Multiple Data (SIMD) instructions, Direct Register Access (DRA) and Direct Cache Access (DCA) of Godson-3B, two optimization algorithms for GEMV are introduced in this paper. Experiments show that the best computing performance of the optimized GEMVs on Godson-3B is more than 1.8Gops, which is far superior to that of other versions. While the test scale of GEMVs is greater than the size of L2-cache, its average performance exceeds UBLAS and OpenBlas, the two most famous optimized BLAS libraries for GODSON, by more than 60% and 20% respectively. © 2014 Binary Information Press.

关键词： Supercomputers

来源：评论

学校读者我要写书评

暂无评论

SvdNPD: A negative data publication method based on the sensitive value distribution

SvdNPD: A negative data publication method based on the sens...

引用

International Workshop on Artificial Immune Systems, AIS 2015

作者： Wu, Linli Luo, Wenjian Zhao, Dongdong School of Computer Science and Technology University of Science and Technology of China Hefei Anhui230027 China Anhui Province Key Laboratory of Software Engineering in Computing and Communication University of Science and Technology of China Hefei Anhui230027 China

ISBN: (纸本)9781509002986

Existing data publication methods retain the relationship between the quasi-identifier attributes and sensitive attributes of published data. We call them "positive data publication". However, it will lead to potential risk that attackers could deduce the privacy of the corresponding individuals from the published data. Recently, by combining the negative representation with k-anonymity and l-diversity, (k, m)- anonNPD and (l, m)-divNPD algorithms have been proposed, which improve the degree of privacy because the sensitive value of each individual is transformed into a negative value randomly. However, to reduce the average error of the reconstructed distribution, the data published by (k, m)-anonNPD and (l, m)-divNPD are often much larger than the original data. In this paper, we take the Sensitive Value Distribution into consideration, and propose a novel Negative Data Publication approach (i.e. SvdNPD), which is based on l-diversity. According to the sensitive value distribution, the negative selection probability of the sensitive attribute in each record can be calculated. Then the data could be published by transforming the sensitive value to a negative one with this probability. Experimental results show that the effective usage of the individual sensitive value distribution could enhance the utility of published data. Meanwhile, compared with (l, 1)-divNPD, SvdNPD just sacrifices a tiny privacy degree which is acceptable. © 2015 IEEE.

关键词： Metadata

来源：评论

学校读者我要写书评

暂无评论

Directed differential evolution based on directional derivative for numerical optimization problems

Directed differential evolution based on directional derivat...

引用

2011 11th International Conference on Hybrid Intelligent Systems, HIS 2011

作者： Zhang, Jun Luo, Wenjian School of Computer Science and Technology University of Science and Technology of China Hefei 230027 Anhui China Anhui Province Key Laboratory of Software Engineering in Computing and Communication University of Science and Technology of China Hefei 230027 Anhui China

ISBN: (纸本)9781457721502

Differential Evolution is one kind of Evolutionary Algorithms, which has been successfully applied to solve many optimization problems. In this paper, a directed differential mutation (DDM), which utilizes the directional derivative to decide a suitable search direction and a proper mutation step size, is proposed. It is merged into the classical DE to form a new algorithm, named directed differential evolution (DDE). The performance of the DDE is tested on 23 classical problems for numerical optimization. The experimental results demonstrate that the performance of the DDE outperforms the classical DE on most functions. © 2011 IEEE.

关键词： Evolutionary algorithms

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：