Summary form only given. Dynamic structured adaptive mesh refinement (SAMR) techniques along with the emergence of the computational grid offer the potential for realistic scientific and engineering simulations of com...
详细信息
Summary form only given. Dynamic structured adaptive mesh refinement (SAMR) techniques along with the emergence of the computational grid offer the potential for realistic scientific and engineering simulations of complex physical phenomena. However, the inherent dynamic nature of SAMR applications coupled with the heterogeneity and dynamism of the underlying grid environment present significant research challenges. We present proactive runtime partitioning strategies based on performance prediction functions that are experimentally formulated in terms of system parameters such as CPU load and available memory. These proactive partitioning strategies form a part of the GridARM autonomic framework which enables self-managing, self-adapting, and self-optimizing SAMR applications on the grid. Experimental evaluation of the proactive schemes using the 3D Richtmyer-Meshkov compressible fluid dynamics kernel for different system configurations and workloads demonstrates the improvement in overall runtime performance.
The workload distribution approaches used by software distributed shared memory (DSM) clusters always distribute the working threads of applications according to the computational power of processors. However, in addi...
详细信息
ISBN:
(纸本)0769521355
The workload distribution approaches used by software distributed shared memory (DSM) clusters always distribute the working threads of applications according to the computational power of processors. However, in addition to computational cost, the cost of memory accesses is an important factor for determining program performance. Neglecting this cost will result in making wrong decisions in workload distribution and then degrading program performance. To address this problem, we propose a new approach with simultaneously considering the memory capability and the computational power of processors for workload distribution on software DSM clusters in this paper. We have implemented the proposed approach on a test bed. Our experimental results show that the proposed approach can provide more performance improvement for the applications compared to the others with considering only computational powers or memory capabilities.
Summary form only given. There is today an increasing diversity of parallel execution supports. Solving a target problem by using a single algorithm is not always efficient on any computational support. We present her...
详细信息
Summary form only given. There is today an increasing diversity of parallel execution supports. Solving a target problem by using a single algorithm is not always efficient on any computational support. We present here a polyalgorithmic approach for selecting the most suitable algorithm among various ones for given problem size and available resources. Our principal objective here is to illustrate such an approach on the well-known matrix multiplication problem which is one of the most important basic numerical kernels. More precisely, we propose a polyalgorithm which uses both advantages of standard and fast algorithms which is able to automatically choose the right and suitable algorithm for computing the matrix multiplication of any dimension on a particular parallel system. We target this approach on homogeneous clusters of PCs while providing some experiments.
This paper describes the background to a research project whose objective is to develop a Virtuality-based Understanding Scheme (VirUS) as a typecast of virtual teams. In response to rapidly changing environments and ...
详细信息
ISBN:
(纸本)1860584675
This paper describes the background to a research project whose objective is to develop a Virtuality-based Understanding Scheme (VirUS) as a typecast of virtual teams. In response to rapidly changing environments and developments in Information and Communication Technologies (ICT), organizations are increasingly using Virtual Teams (VTs). However, both managers and scientists have not yet agreed upon a common understanding of VTs. Classifications diverge as to what types of VTs exist and how degrees of virtualization in VTs can be identified. This creates difficulties for further research and managers striving to implement findings. Furthermore, research on management of VTs lacks attention to potential individual dysfunctions arising out of virtual working environments. According to Türk [51] mismanagement of these dysfunctions can enhance Overstabilisation, Overcomplexity and Overregulation as corporate pathologies and result in higher dominance, social and psychic cost. VirUS will serve as a basis for a projection of Turk's pathology concept. It involves an analysis of the relation between certain stages in VirUS and pathological states.
The following topics are dealt with: genomics; transcriptomes; proteomics; applied bioinformatics; data mining; ontology; comparative genomics; evolution and phylogenetics; functional genomics; high performance comput...
The following topics are dealt with: genomics; transcriptomes; proteomics; applied bioinformatics; data mining; ontology; comparative genomics; evolution and phylogenetics; functional genomics; high performance computing; pathways network systems biology; pattern recognition; promoter analysis; protein structure analysis; and sequence alignment.
This paper introduces the concept of rationality-based computing (RBC) and a preliminary design of middleware, GameMosix that implements the concept. Millions of computers and mobile devices over the Internet play rat...
详细信息
This paper introduces the concept of rationality-based computing (RBC) and a preliminary design of middleware, GameMosix that implements the concept. Millions of computers and mobile devices over the Internet play rationality-based games in sharing computational resources. Researchers in computer systems communities are becoming more interested in game theory and evolutionary computing. First, we discuss previous work on game theory and evolutionary game theory applied to computer systems. Then, we introduce the design of a preliminary version of RBC middleware architecture and some results from the simulation of the architecture.
This paper describes a learning scheme of a structural connectionist architecture based on a simple genetic approach to adaptive processing of tree-structures representation. Conventionally, one of the most popular su...
详细信息
ISBN:
(纸本)1932415335
This paper describes a learning scheme of a structural connectionist architecture based on a simple genetic approach to adaptive processing of tree-structures representation. Conventionally, one of the most popular supervised learning formulations of tree-structures processing is Backpropagation Through Structures (BPTS) [1]. The BPTS algorithm has been successfully applied to a number of learning tasks that involved complex symbolic structural patterns such as image semantic, internet behaviour, and chemical compound. However, this BPTS typed algorithm suffers from the long-term dependency problem in learning very deep tree structures. In this paper, we propose a simple genetic evolution approach for this processing. The idea of this algorithm is to tune the learning parameters by the genetic evolution with specified binary chromosome structures. Experimental results significantly support the capabilities of our proposed approach to classify and recognize structural patterns in terms of generalization capability.
This paper quantitatively describes and discusses the usefulness of texture analysis methods for the recognition of bark. Comparative studies of bark texture feature extraction are performed for the four texture analy...
详细信息
ISBN:
(纸本)0780386876
This paper quantitatively describes and discusses the usefulness of texture analysis methods for the recognition of bark. Comparative studies of bark texture feature extraction are performed for the four texture analysis methods such as the gray level run-length method (RLM), co-occurrence matrices method (COMM) and histogram method (HM) as well as auto-correlation method (acm). Specifically, we use three classifiers of nearest neighbor (l-NN), k-nearest neighbor (k-NN) and moving median centers (MMC) hypersphere classifiers to verify the validity of the extracted bark texture features. To gain good results we added to color information that proved very efficient. Moreover, the experimental results also demonstrate that from the viewpoint of the recognition accuracy and computational complexity, the COMM method is superior to the other three methods.
Grid and Web services are both hot topics today. In this paper, we present some ongoing work and planned future work at the Cambridge eScience Centre. After an introduction to these technologies in the context of grid...
详细信息
Grid and Web services are both hot topics today. In this paper, we present some ongoing work and planned future work at the Cambridge eScience Centre. After an introduction to these technologies in the context of grid applications development, we describe two use-cases: a database of results in computational fluid dynamics (CFD) and a small computational grid for aircraft engineering design. As grid services are moving towards Web services, we continue to make use of the Globus Toolkit v2.4 (GT2.4), without adopting the open grid services architecture (OGSA) wholesale. In our scenario, GT2.4 integrates distributed computing resources including HPC and clusters while Web services wrap the scientific code as a service.
We show a novel middleware approach for pervasive applications that communicate via an XML-based distributed virtual shared information space. This approach extends some common ideas on XML language binding frameworks...
详细信息
We show a novel middleware approach for pervasive applications that communicate via an XML-based distributed virtual shared information space. This approach extends some common ideas on XML language binding frameworks by a dedicated "merge logic" that lets pervasive devices share their information with low overhead.
暂无评论