检索结果-内蒙古大学图书馆

Preprototyping SIMD coprocessors using virtual machine emulation and trace compilation

Performance Evaluation Review 1997年第1期25卷 88-99页

作者： Herbordt, Martin C. Kidwai, Owais Weems, Charles C. Univ of Houston Houston United States

The use of massively parallel SIMD array architectures is proliferating in the area of domain specific coprocessors. Even so, they have undergone few systematic empirical studies. The underlying problems include the size of the architecture space, the lack of portability of the test programs, and the inherent complexity of simulating up to hundreds of thousands of processing elements. We address the computational cost problem with a novel approach to trace-based simulation. Code is run on an abstract virtual machine to generate a coarse-grained trace, which is then refined through a series of transformations (a process we call trace compilation) wherein greater resolution is obtained with respect to the details of the target machine. We have found this technique to be one to two orders of magnitude faster than instruction-level simulation while still retaining much of the accuracy of the model. Furthermore, abstract machine traces must be regenerated for only a small fraction of the possible parameter combinations. Using virtual machine emulation and trace compilation also addresses program portability by allowing the user to code in a single data parallel language with a single compiler, regardless of the target architecture. This technique has already been used to generate significant results with respect to SIMD array architectures, a sample of which are presented here.

关键词： Parallel processing systems

来源：评论

学校读者我要写书评

暂无评论

Distributed route initialization algorithms for the Monash Secure RISC Multiprocessor

Distributed route initialization algorithms for the Monash S...

引用

Annual Hawaii international conference on System Sciences (HICSS)

作者： V.J. Fazio R.D. Pose Department of Computer Science Monash University Clayton VIC Australia Department of Computer Science Adonash University Clayton VIC Australia

The Monash Secure RISC Multiprocessor (SRMP) is a general-purpose large-scale multiprocessor with a capability-based distributed shared virtual memory. The physical design of the Monash SRMP consists of passive backplane bus sections and dual-ported processor-memory modules connected in an unusual topology. This paper details three algorithms used for route initialization. The first is a simplification of the flooding algorithms commonly used in distributed networks. The second algorithm uses a variation of the depth-first search algorithm, which has been used to route mesh and hypercube architectures. The final algorithm uses a theoretical solution to the gossiping (all-to-all broadcast) problem for mesh networks; this is the first known simulation of this algorithm. The algorithms are evaluated via simulations of the traffic flow over the multiprocessor network.

关键词： Reduced instruction set computing Routing Table lookup Circuit faults computer science Australia Large-scale systems Backplanes Computational modeling computer architecture

来源：评论

学校读者我要写书评

暂无评论

Efficient terrain data representation for 3D rendering using the generalized BFOS algorithm

Efficient terrain data representation for 3D rendering using...

引用

IEEE international conference on Image Processing

作者： S.P. Oswald K. Ramchandran T.S. Huang Beckman Institute and ECE Department University of Illinois Urbana-Champaign Urbana IL USA

Digital terrain data has widespread applications in areas such as the military, geographic information systems (GIS), and flight simulator video games. The combination of the abundance of terrain data with the limited rendering capabilities of computer graphics machines creates the necessity for algorithms which generate efficient representations of the data for rendering. This paper presents such an algorithm. Terrain data is tessellated using a regular triangular grid, and the regular grid is represented using a binary tree. The generalized BFOS algorithm, a well-known optimal tree-pruning method for regression and quantization trees, is used to prune the tree optimally, resulting in a far more efficient representation of this data than known in the literature. In addition to its optimal properties, the representation is also embedded, making it suitable for displays at multiple resolutions.

关键词： Rendering (computer graphics) Geographic Information systems Application software Military computing Computational modeling Aerospace simulation Games computer graphics Binary trees Tree graphs

来源：评论

学校读者我要写书评

暂无评论

modeling ATR applications for intelligent execution upon a heterogeneous computing platform

Modeling ATR applications for intelligent execution upon a h...

引用

IEEE international conference on systems, Man and Cybernetics

作者： J.R. Budenske R.S. Ramamujan K.J. Thurber H.J. Siegel Architecture Technology Corporation Minneapolis MN USA

The information processing tasks associated with real-time applications (e.g., automatic target recognition, intelligent robotics, information fusion) have very diverse computational requirements that result in different needs for different computing system capabilities. Heterogeneous parallel computing provides a variety of architectural capabilities, orchestrated to perform an application whose tasks have such diverse execution requirements. A key issue that must be addressed in embedding real-time applications on heterogeneous parallel computing architectures is the design of a high-level operating system for selecting algorithms, matching subtasks to processors, and scheduling subtask execution. Essentially, high-level descriptions of an application would be "intelligently executed" by such an operating system. This paper presents on-going research in the development of an Intelligent Operating System, specifically describing the mechanism for the selection of algorithms that functionally satisfy the processing needs of ATR subtasks. The methodology presented here can also be used for other application domains and classes of hardware platforms whose characteristics are similar to those of the applications and platform considered here.

关键词： Intelligent robots Operating systems Computational intelligence Real time systems Parallel processing Information processing Target recognition Robotics and automation computer architecture Algorithm design and analysis

来源：评论

学校读者我要写书评

暂无评论

Reliability analysis of electric utility SCADA systems

Reliability analysis of electric utility SCADA systems

引用

Power Industry computer Application conference (PICA)

作者： A.G. Bruce Trans Power New Zealand Limited New Zealand

Electric utility SCADA systems must be highly reliable given the potential for the SCADA system to directly contribute to load curtailment. This paper presents an analysis of SCADA system reliability in terms of its expected aggregate contribution to load curtailment on the power system. Expressing this aggregate in system minutes and applying an appropriate damage cost function then provides an annual cost measure of SCADA system reliability worth. A composite generation and transmission system reliability evaluation technique is used to perform the numerical analysis of the joint SCADA and power system model. This performs a Monte-Carlo simulation and includes an optimal power flow for enumerating grid load curtailment states and analysis of SCADA system component connectivity to determine availability of SCADA control. The application of this analysis is illustrated in a comparison of two alternative SCADA architectures. Trans Power has adopted a subtransmission SCADA architecture which utilises terminals operating off its national SCADA system. These terminals have replaced separate systems located in each area. The objective of the evaluation being to quantify the increased exposure to financial losses due to joint load curtailment.

关键词： Power industry SCADA systems Power system reliability Power system modeling Aggregates Power system analysis computing Power system measurements Cost function Power generation Performance evaluation

来源：评论

学校读者我要写书评

暂无评论

Multirate Kalman filtering approach for optimal two-dimensional signal reconstruction from noisy subband systems

Multirate Kalman filtering approach for optimal two-dimensio...

引用

IEEE international conference on Image Processing

作者： J.Q. Ni K.L. Ho K.W. Tse J.S. Ni M.H. Shen Department of Electrical and Electronic Engineering University of Hong Kong Hong Kong China Wuhan University of Hydraulic and Electrical Engineering Wuhan China

Conventional synthesis filters in subband systems lose their optimality when additive noise due, for example, to signal quantization, disturbs the subband components. The multichannel representation of the subband signal is combined with the statistical model of the input signal to derive the multirate state-space model for a filter bank system with additive noise. Thus the signal reconstruction problem in the subband system can be formulated as the process of optimal state estimation in the equivalent multirate state-space model. With the input signal embedded in the state vector, the multirate Kalman filtering provides the minimum-variance reconstruction of the input signal. Using the powerful Kronecker product notation, the results and derivations can then be extended to the 2-D cases. Incorporated with the vector dynamical model, the 2-D multirate state-space model for 2-D Kalman filtering is developed. computer simulation with the proposed 2-D multirate Kalman filter gives favorable results.

关键词： Kalman filters Filtering Filter bank Additive noise Signal synthesis Quantization Signal reconstruction State estimation Power system modeling computer simulation

来源：评论

学校读者我要写书评

暂无评论

Preprototyping SIMD coprocessors using virtual machine emulation and trace compilation 97

Preprototyping SIMD coprocessors using virtual machine emula...

引用

Proceedings of the 1997 ACM SIGMETRICS international conference on Measurement and modeling of computer systems

作者： Martin C. Herbordt Owais Kidwai Charles C. Weems Department of Electrical and Computer Engineering University of Houston Houston TX Department of Computer Science University of Massachusetts Amherst MA

ISBN: (纸本)9780897919098

关键词：

来源：评论

学校读者我要写书评

暂无评论

A performance evaluation of cluster architectures 97

A performance evaluation of cluster architectures

引用

Proceedings of the 1997 ACM SIGMETRICS international conference on Measurement and modeling of computer systems

作者： Xiaohan Qin Jean-Loup Baer Department of Computer Science and Engineering University of Washington Seattle WA

ISBN: (纸本)9780897919098

This paper investigates the performance of shared-memory cluster-based architectures where each cluster is a shared-bus multiprocessor augmented with a protocol processor maintaining cache coherence across clusters. For a given number of processors, sixteen in this study, we evaluate the performance of various cluster configurations. We also consider the impact of adding a remote shared cache in each cluster. We use Mean Value Analysis to estimate the cache miss latencies of various types and the overall execution time. The service demands of shared resources are characterized in detail by examining the sub-requests issued in resolving cache misses. In addition to the architectural system parameters and the service demands on resources, the analytical model needs parameters pertinent to applications. The latter, in particular cache miss profiles, are obtained by trace-driven simulation of three *** results show that without remote caches the performance of cluster-based architectures is mixed. In some configurations, the negative effects of the longer latency of inter-cluster misses and of the contention on the protocol processor are too large to counter-balance the lower contention on the data buses. For two out of the three applications best results are obtained when the system has clusters of size 2 or 4. The cluster-based architectures with remote caches consistently outperform the single bus system for all 3 applications. We also exercise the model with parameters reflecting the current trend in technology making the processor relatively faster than the bus and memory. Under these new conditions, our results show a clear performance advantage for the cluster-based architectures, with or without remote caches, over single bus systems.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Experiences with analysis of formal specifications in Astral

Experiences with analysis of formal specifications in Astral

引用

IEEE international conference on embedded and Real-Time Computing systems and Applications (RTCSA)

作者： K. Brink J. van Katwijk R.F. Lutje Spelberg W.J. Toetenel Department of Technical Mathematics and Computer Science Delft University of Technnology Delft Netherlands

An important issue in the design and implementation of real-time software is the verification of (temporal) properties. Our research of the past few years focused on requirements specification of real-time software and the use of tools in modeling and design. The development of a correct and complete requirements specification is difficult, and therefore tool support is considered important. Our development approach, builds upon requirements specifications constructed using the formal real-time specification language Astral. The development framework offers support for end-users in the construction of a software requirements specifications in Astral. Such end-risers are, for example, control engineers in the area of embedded, real-time control software. Support in the construction of an Astral specification through the use of analysis tools is important because it provides the user with (i) evidence concerning the correctness of the specification and (ii) feasibility of its implementation. This paper describes our development framework focusing on four approaches that have been employed in (timing) analysis of Astral specifications. The first two approaches, simulation and prototyping, are informal, while the latter two are formal, based on a translation into an extension of timed automata.

关键词： Formal specifications Specification languages Software quality Mathematics computer science Software tools Timing Software prototyping Virtual prototyping Automata

来源：评论

学校读者我要写书评

暂无评论

A model and design of a fully distributed computing environment for virtual reality

A model and design of a fully distributed computing environm...

引用

IEEE international conference on embedded and Real-Time Computing systems and Applications (RTCSA)

作者： Jiung-Yao Huang Chao-Tsong Fang-Tson Shuenn-Jyi Wang Wei-Chyuan Wang Multimedia and Virtual Reality Laboratory Institute of Computer Science and Information Engineering Tamkang University Tamsui Taiwan Avionics Development Center Institute for Information Industry Taipei Taiwan

ISBN: (纸本)0818680733

With the evolution of computing technologies, both PCs and workstations have increased computing power with less cost in the recent years. This paper presents a model and design of a fully distributed virtual reality system, called Multiple User Distributed simulation (MUDS) system, over a network of low-end computers. MUDS system is designed to provide a virtual environment for both a single user and multiple participants over a fully distributed environment. However, only the method and architecture of building a single user distributed virtual environment is presented in this paper. MUDS system adapts and modifies the concepts from High Level Architecture, which is designed by DoD of US to provide interoperability among distributed simulators. Compared to the other existing distributed systems, MUDS system provides a transparent interface among distributed tasks. The prototype of MUDS system has been successfully built in Institute of computer Science and Information Engineering, Tamkang University. An experiment of using MUDS system along with the experimental result will also be fully discussed in the paper.

关键词： Distributed computing Multiuser detection Power system modeling Computational modeling Virtual environment computer architecture Personal communication networks Workstations Costs Virtual reality

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：