检索结果-内蒙古大学图书馆

IEEE Annual Joint Conference: INFOCOM, IEEE Computer and Communications Societies

作者： P. Goyal H.M. Vin C. Shen P.J. Shenoy Distributed Multimedia Computing Laboratory Department of Computer Sciences UT Austin Austin TX USA Cambridge Research Center Mitsubishi Electric Research Laboratory Cambridge MA USA

We present an adaptive network layer protocol for VBR video transport. It: (1) minimizes the buffer requirement in the network while guaranteeing that packets of VBR encoded video flows will not be lost, and (2) minimizes the end-to-end delay and jitter of frames. To achieve the former objective, we utilize a receiver-oriented adaptive credit-based flow control algorithm, and derive the necessary and sufficient number of buffers that should be reserved for ensuring its reliability. To minimize the end-to-end delay and jitter for VBR encoded video streams, we: (1) present bandwidth estimation techniques which exploit the structure of the video traffic, and (2) define a new fairness criteria for buffer allocation and then present a fair buffer/bandwidth allocation algorithm. We experimentally evaluate this protocol for a wide range of parameters and many network configurations, and demonstrate its adaptability. We also compare the performance of the protocol with numerous other schemes and demonstrate its suitability for video transport.

关键词： Adaptive systems Transport protocols Jitter Delay estimation Programmable control Adaptive control Streaming media Bandwidth Communication system traffic control Channel allocation

来源：评论

学校读者我要写书评

暂无评论

Optimizing the placement of multimedia objects on disk arrays

Optimizing the placement of multimedia objects on disk array...

引用

IEEE International Conference on Multimedia computing and Systems (ICMCS)

作者： H.M. Vin S.S. Rao P. Goyal Distributed Multimedia Computing Laboratory Department of Computer Sciences University of Texas Austin Austin TX USA

The immensity of the data transfer requirements of multimedia objects will require multimedia servers to be founded on disk arrays. To effectively utilize a disk array and hence to maximize the number of clients that can be serviced simultaneously, a multimedia server must interleave the storage of each media stream among the disks in the array. We identify two placement policies for organizing storage of multimedia objects on disk arrays. We present methods for optimizing the performance of server for both the placement policies, and empirically validate and evaluate the methods through extensive trace driven simulation.

关键词： Streaming media network servers Throughput Multimedia computing Laboratories distributed computing Electronic mail Telephony Organizing Design optimization

来源：评论

学校读者我要写书评

暂无评论

PARALLEL AND distributed TLM COMPUTATION WITH SIGNAL-PROCESSING FOR ELECTROMAGNETIC-FIELD MODELING

引用

INTERNATIONAL JOURNAL OF NUMERICAL MODELLING-ELECTRONIC networkS DEVICES AND FIELDS 1995年第3-4期8卷 169-185页

作者： SO, PPM ESWARAPPA, C HOEFER, WJR NSERC/MPR Teltech Research Chair in RF Engineering Department of Electrical and Computer Engineering University of Victoria Victoria British Columbia V8W 3P6 Canada Poman So received his B.Sc. degree in computer science and physics from the University of Toronto Toronto Onatario Canada in 1985. He obtained his B.A. Sc. and M.A.Sc. degrees in electrical engineering (summa cum laude) from the University of Ottawa Ottawa Ontario Canada in 1987 and 1989 respectively. Mr So was a research engineer in the University of Ottawa from January 1989 to October 1991 his research interests included CAD techniques of microwave circuits and numerical methods for electromagnetic wave modelling. He specialized in the development of electromagnetic engineering CAD software and successfully implemented a number of electromagnetic wave simulators based on the two-dimensional and three-dimensional transmission-line matrix methods. From August 1990 to February 1991 he accompanied Professor W. J. R. Hoefer to Rome Italy and Sophia Antiopolas France. During that time he implemented a parallel version of the 3D-TLM simulator for the CM-2 Connection Machine using C-Star and X Windows Library. He is a research engineer and a Ph.D. student at the University of Victoria Victoria British Columbia Canada. He ported the 2D- and 3D-TLM simulators to DECmpp 1200 massively parallel computer using MPL C and C++. He also combined OSA90/hope a commercially available microwave CAD program with a 2D-TLM simulation module for geometry optimization using the Datapipe technique of OSA90/hope. Recently he has developed a distributed client-server computing technique for the TLM method this technique could accelerate the TLM simulation by more than an order of magnitude. Channabasappa Eswarappa received the M.Tech. degree in electrical engineering from the Indian Institute of Technology Kanpur India in 1983 and Ph. D. degree from the University of Ottawa Canada in 1990. He worked as an Assistant Executive Engineer and later as

This paper describes the implementation of transmission-line matrix (TLM) method algorithms on a massively parallel computer (DECmpp 12000), the technique of distributed computing in the UNIX environment, and the combination of TLM analysis with Prony's method as well as with autoregressive moving average (ARMA) digital signal processing for electromagnetic field modelling. By combining these advanced computation techniques, typical electromagnetic field modelling of microwave structures by TLM analysis can be accelerated by a few orders of magnitude.

关键词： Mathematical models

来源：评论

学校读者我要写书评

暂无评论

An infrastructure for application-specific customization 6

An infrastructure for application-specific customization

引用

6th ACM SIGOPS European Workshop on Matching Operating Systems to Application Needs, EW 1994

作者： Banerji, Arindam Conn, David L. Distributed Computing Research Laboratory Department of Computer Science and Engineering University of Notre Dame Notre DameIN United States

As application requirements diverge, it is becoming increasingly clear that the one size fits all operating system design strategy is obsolete. Customizable system services would allow application-specific optimizations, and various customization strategies have been proposed. These vary widely and, depending on the required level of application-developer involvement, can be categorized as parametric variation, interposition or synthesis methods. We present a common architectural infrastructure for operating system components which allows customization by any of diese approaches. Our ongoing implementation based on this framework is beginning to show mat support for application-specific customization can be incorporated into existing commercial operating systems.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Device driver issues in high-performance networking

Device driver issues in high-performance networking

引用

USENIX 1994 High-Speed networking Symposium

作者： Tracey, John Michael Banerji, Arindam Distributed Computing Research Laboratory Department of Computer Science and Engineering University of Notre Dame Notre DameIN46556-5637 United States

High-performance networking requires attention to operating system support at the device driver level. Existing driver models, such as those of Unix, are not necessarily well-suited to supporting high-speed network interfaces. In fact, current drivers may represent a significant obstacle between applications and the high-speed network adapters they seek to exploit. Yet existing models cannot simply be discarded. Certain trends in RISC processor design can also tend to make existing device driver implementations less efficient. Specifically, many drivers make extensive use of operations which are becoming relatively more costly as RISC architectures evolve. This paper describes an effort currently underway to develop device drivers specifically designed to support high-speed network interfaces on RISC architectures. We have analyzed the operation of some existing commercial device driver implementations and modified one using several techniques. Taken together, these techniques promise to produce network device drivers which deliver the high level of performance demanded by today's high speed networks. © USENIX *** right reserved.

关键词： HIgh speed networks

来源：评论

学校读者我要写书评

暂无评论

A Comparative Study of Star Graphs and Rotator Graphs

A Comparative Study of Star Graphs and Rotator Graphs

引用

International Conference on Parallel Processing (ICPP)

作者： Subburajan Ponnuswamy Vipin Chaudhary Parallel and Distributed Computing Laboratory Department of ECE Wayne State University Detroit MI USA

Star graph is an extensively studied Cayley graph, considered to be an attractive alternative to the popular binary cube. The rotator graphs are a set of directed Cayley graphs introduced recently. In this paper we compare the structural and algorithmic aspects of star graphs with that of rotator graphs. In the process we present some new results for star graphs and rotator graphs. We present a formula for the number of nodes at any distance from the identity permutation in star graphs. The minimum bisection width of star and rotator graphs is obtained. Partitioning and fault tolerant parameters for both star and rotator graphs are analyzed. The node disjoint parallel paths and hence the upper bound on the fault diameter of rotator graphs are presented. We compare the minimal path routing in star and rotator graphs using simulation results.

关键词： Routing Fault tolerance Tin Parallel processing distributed computing Laboratories Delay Computational modeling Upper bound Multiprocessing systems

来源：评论

学校读者我要写书评

暂无评论

The use of frameworks for scientific computation in a parallel distributed environment

The use of frameworks for scientific computation in a parall...

引用

International Symposium on High Performance distributed computing

作者： R. Armstrong J. Macfarlane Distributed Computing Department Sandia National Laboratories Livermore CA USA Information and Computing Sciences Lawrence Berkeley National Laboratory Berkeley CA USA

The purpose of the paper is to introduce a frame-based approach to scientific computing on distributed computing platforms. The objective of the effort is to introduce well-defined mappings between the representations of physical phenomena as mathematical structures and the computational algorithms for modeling that phenomena on high-performance parallel computing platforms. Using this approach, we identify representations that solve classes of scientific problems based on the computational structure required for solution on parallel processors. Thus, once the representation is defined for a particular problem, the mapping onto a parallel computing environment can be managed automatically in software. We demonstrate the benefits of this approach by application to a combustion modeling problem.< >

关键词： Concurrent computing Parallel processing Scientific computing distributed computing Physics computing Computational modeling Mathematical model Environmental management Application software Combustion

来源：评论

学校读者我要写书评

暂无评论

Embedding of cycles in rotator and incomplete rotator graphs

Embedding of cycles in rotator and incomplete rotator graphs

引用

International Symposium on Parallel and distributed Processing (IPDPS)

作者： S. Ponnuswamy V. Chaudhary Parallel and Distributed Computing Laboratory Department of Electrical and Computer Engineering Wayne State University Detroit MI USA

Symmetric directed Cayley graphs called rotator graphs have been proposed recently in the literature. In addition to a lower diameter and average distance compared to the star graph, hypercube, and k-ary n-cubes, these rotator graphs also have a rich cyclic structure. We identify a variety of disjoint cycles in rotator graphs. An efficient algorithm for Hamiltonian cycles in rotator graphs is presented. This algorithm uses a basic sequence of four generators repeatedly with generators of higher order in between, to obtain Hamiltonian cycle in any n-rotator graph. We study the embedding of undirected cycles and directed cycles in rotator graphs. We also prove that the incomplete rotator graph obtained from the rotator graph is Hamiltonian. The embedding of undirected rings in rotator graphs is shown to have a low average dilation.< >

关键词： Multiprocessor interconnection networks distributed computing Parallel processing Algorithm design and analysis Laboratories Concurrent computing Hypercubes Optical fiber communication Very large scale integration Protocols

来源：评论

学校读者我要写书评

暂无评论

Contention sensitive fault-tolerant routing algorithms for hypercubes

Contention sensitive fault-tolerant routing algorithms for h...

引用

International Symposium on Parallel Architectures, Algorithms and networks (ISPAN)

作者： R. Srinivasan V. Chaudhary S.M. Mahmud Parallel and Distributed Computing Laboratory Department of Electrical and Computer Engineering Wayne State University Detroit MI USA

We present two new fault tolerant routing algorithms for hypercubes. The first algorithm requires only local knowledge of the faults whereas the second algorithm requires global knowledge. Unlike previous fault tolerant routing algorithms, our algorithms take into consideration the dynamic conditions (link contention) of the network. We have shown that checking for dynamic conditions in fault tolerant algorithms is essential. Performance evaluation by extensive simulation of our algorithms and other fault tolerant routing algorithms show that ours are better than previous algorithms by as much as 50%; and 500%; in time and space, respectively. We also observed that global information about the location of faults does not give us additional benefit. This observation is true regardless of the consideration of the dynamic conditions in the network.< >

关键词： Fault tolerance Routing Hypercubes Telecommunication traffic distributed computing Laboratories network topology Scalability Hardware Adaptive algorithm

来源：评论

学校读者我要写书评

暂无评论

Minimum dependence distance tiling of nested loops with non-uniform dependences

Minimum dependence distance tiling of nested loops with non-...

引用

International Symposium on Parallel and distributed Processing (IPDPS)

作者： S. Punyamurtula V. Chaudhary Parallel and Distributed Computing Laboratory Department of Electrical and Computer Engineering Wayne State University Detroit MI USA Wayne State University

We address the problem of partitioning nested loops with non-uniform (irregular) dependence vectors. Although many methods exist for nested loop partitioning, most of these perform poorly when parallelizing nested loops with irregular dependencies. We apply the results of classical convex theory and principles of linear programming to iteration spaces and show the correspondence between minimum dependence distance computation and iteration space tiling. The cross-iteration dependencies are analyzed by forming an Integer Dependence Convex Hull (IDCH). A simple way to compute minimum dependence distances from the dependence distance vectors of the extreme points of the IDCH is presented. Using these minimum dependence distances the iteration space can be tiled. Iterations in a tile can be executed in parallel and the tiles can be executed with proper synchronization. We demonstrate that our technique gives much better speedup and extracts more parallelism than the existing techniques.< >

关键词： Tiles distributed computing Concurrent computing Vectors Linear programming Parallel processing Laboratories Sequential analysis Data analysis Data mining

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：