Parallel and Distributed Computing Research Papers (original) (raw)

Frequent itemset mining is a classic problem in data mining. It is a non-supervised process which concerns in finding frequent patterns (or itemsets) hidden in large volumes of data in order to produce compact summaries or models of the database. These models are typically used to generate association rules, but recently they have also been used in far reaching domains like e-commerce and bio-informatics. Because databases are increasing in terms of both dimension (number of attributes) and size (number of records), one of the main issues in a frequent itemset mining algorithm is the ability to analyze very large databases. Sequential algorithms do not have this ability, especially in terms of run-time performance, for such very large databases. Therefore, we must rely on high performance parallel and distributed computing. We present new parallel algorithms for frequent itemset mining. Their efficiency is proven through a series of experiments on different parallel environments, that range from shared-memory multiprocessors machines to a set of SMP clusters connected together through a high speed network.

- by
- •
- Computer Science, Parallel Algorithms, Data Mining, Frequent Itemset Mining

The widespread use of digital images has led to a new challenge in digital image forensics. These images can be used in court as evidence of criminal cases. However, digital images are easily manipulated which brings up the need of a method to verify the authenticity of the image. One of the methods is by identifying the source camera. In spite of that, it takes a large amount of time to be completed by using traditional desktop computers. To tackle the problem, we aim to increase the performance of the process by implementing it in a distributed computing environment. We evaluate the camera identification process using conditional probability features and Apache Hadoop. The evaluation process used 6000 images from six different mobile phones of the different models and classified them using Apache Mahout, a scalable machine learning tool which runs on Hadoop. We ran the source camera identification process in a cluster of up to 19 computing nodes. The experimental results demonstrate exponential decrease in processing times and slight decrease in accuracies as the processes are distributed across the cluster. Our prediction accuracies are recorded between 85 to 95% across varying number of mappers.

Job Management Systems (JMSs) efficiently schedule and monitor jobs in parallel and distributed computing environments. Therefore, they are critical for improving the utilization of expensive resources in high-performance computing systems and centers, and an important component of grid software infrastructure. With many JMSs available commercially and in the public domain, it is difficult to choose an optimum JMS for a given computing environment.. In this paper, we present the results of the first empirical study of JMSs reported in the literature. Four commonly used systems, LSF, PBS Pro, Sun Grid Engine / CODINE, and Condor were considered. The study has revealed important strengths and weaknesses of these JMSs under different operational conditions. For example, LSF was shown to exhibit excellent throughput for a wide range of job types and submission rates. On the other hand, CODINE appeared to outperform other systems in terms of the average turnaround time for small jobs, and PBS appeared to excel in terms of turnaround time for relatively larger jobs.

- by Nikitas Alexandridis
- •
- Computer Science, Distributed Computing, Grid Computing, Public Domain

Performance is a key feature of large-scale computing systems. However, the achieved performance when a certain program is executed is significantly lower than the maximal theoretical performance of the large-scale computing system. The model-based performance evaluation may be used to support the performance-oriented program development for large-scale computing systems. In this paper we present a hybrid approach for performance modeling and prediction of parallel and distributed computing systems, which combines mathematical modeling and discrete-event simulation. We use mathematical modeling to develop parameterized performance models for components of the system. Thereafter, we use discreteevent simulation to describe the structure of system and the interaction among its components. As a result, we obtain a highlevel performance model, which combines the evaluation speed of mathematical models with the structure awareness and fidelity of the simulation model. We evaluate empirically our approach with a real-world material science program that comprises more than 15,000 lines of code.

- by Sabri Pllana
- •
- Distributed Computing, Parallel Computing, Materials Science, Computational Modeling
- by Kunihiko Kaneko
- •
- Computer Science, Science, Virtual Memory, Performance Evaluation
- by Dimitri Bertsekas
- •
- Numerical Method, Parallel and Distributed Computing

In this paper we have studied several works on direct network architectures which are well-built contestant for useful in many successful cost-effective, experimental massive parallel computers and well scale up shared memory of multiprocessors. The uniqueness of direct networks, as reflected by the communication latency and routing latency metrics are significant to the performance of such systems. A multiprocessor system can be used for the wormhole routing for the most capable switching method and has been adopted in several new massive parallel computers. This technique is unique technical challenges in routing and flow control in particular system, and avoid deadlock. The highly scale up network is a combination of topology and hypercube. Due to the being of concurrent multiple mesh and hypercubes, this network provides a great architectural support for parallel processing. The growth of the network is more efficient in terms of communication, interconnection network is scaled up the network and will be more reliable and also the unreliability of the interconnection network to get minimized. This is very desirable characteristic for the interconnection network as the network remains equipped for more failure of adjoining nodes or links in parallel computer architecture. Formulations to optimize the performance of throughput of networks through queuing theory M\M\1 concept.

The user has requested enhancement of the downloaded file.

- by John N. Tsitsiklis
- •
- Numerical Method, Parallel and Distributed Computing

a campus based private automatic branch exchange (PABX) network for federal university of technology owerri (FUTO) is designed and implemented in this work. the objective of the project is to set up voice communication between various schools or faculties in futo. the schools of interest are post graduate school and school of engineering technology (EEE dept). the connections between the two locations were established using the microwave radio PABX tie line. the connection facilitated efficient and fast voice communication between the two schools. the network architecture is designed using Edraw max version 7.8 which offers more flexibility when compared to other diagramming software.

Cloud Computing has recently emerged as a highly successful alternative information technology paradigm through on-demand resource provisioning and almost perfect reliability. In order to meet the customer demands, Cloud providers are deploying large-scale virtualized data centers consisting of thousands of servers across the world. These data centers require huge amount of electrical energy that incur very high operating cost and as a result, leave large carbon footprints. The reason behind the extremely high energy consumption is not just the amount of computing resources used, but also lies in inefficient use of these resources. Furthermore, with the recent proliferation of communication intensive applications, network resource demands are becoming one of the key areas of performance bottleneck. As a consequence, efficient utilization of data center resources and minimization of energy consumption are emerging as critical factors for the success of Cloud Computing. This thesis addresses the above mentioned resource and energy related issues by tackling through data center-level resource management, in particular, by efficient Virtual Machine (VM) placement and consolidation strategies. The problem of high resource wastage and energy consumption is dealt with an online consolidated VM cluster placement scheme, utilizing the Ant Colony Optimization (ACO) metaheuristic and a vector algebra-based multi-dimensional resource utilization model. In addition, optimization of network resource utilization is addressed by an online network-aware VM cluster placement strategy in order to localize data traffic among communicating VMs and reduce traffic load in data center interconnects that, in turn, reduces communication overhead in the upper layer network switches. Besides the online placement schemes that optimize the VM placement during the initial VM deployment phase, an offline decentralized dynamic VM consolidation framework and an associated algorithm leveraging VM live migration technique are presented to further optimize the run-time resource usage and energy consumption, along with migration overhead minimization. Such migration-aware dynamic VM consolidation strategy uses realistic VM migration parameters to estimate impacts of necessary VM migrations on data center and hosted applications. Simulation-based performance evaluation using representative workloads demonstrates that the proposed VM placement and consolidation strategies are capable of outperforming the state-of-the-art techniques, in the context of large data centers, by reducing energy consumption up to 29%, server resource wastage up to 85%, and network load up to 60%.

This tutorial gives an introduction to parallel and distributed simulation systems. Issues concerning the execution of discrete-event simulations on parallel and distributed computers either to reduce model execution time or to create geographically distributed virtual environments are covered. The emphasis of this tutorial is on the algorithms and techniques that are used in the underlying simulation executive to execute simulations on parallel and distributed computing platforms.

- by Richard Fujimoto
- •
- History, Distributed Computing, Computational Modeling, Telecommunications

Many cloud-based applications employ a data centre as a central server to process data that is generated by edge devices, such as smartphones, tablets and wearables. This model places ever increasing demands on communication and computational infrastructure with inevitable adverse effect on Quality-of-Service and Experience. The concept of Edge Computing is predicated on moving some of this computational load towards the edge of the network to harness computational capabilities that are currently untapped in edge nodes, such as base stations, routers and switches. This position paper considers the challenges and opportunities that arise out of this new direction in the computing landscape.

- by Blesson Varghese and +2
- •
- Computer Science, Distributed Computing, Parallel Computing, Network Security

Abstract A distributed estimation algorithm for sensor networks is proposed. A noisy time-varying signal is jointly tracked by a network of sensor nodes, in which each node computes its estimate as a weighted sum of its own and its neighbors&amp;amp;amp;amp;amp;amp;#x27; measurements and estimates. The weights are adaptively updated to minimize the variance of the estimation error. Both estimation and the parameter optimization is distributed; no central coordination of the nodes is required. An upper bound of the error variance in each node is derived. This ...

Abstract__ The addresses of Internet protocol (IP) are a vital resource for the Internet. In the network, IP address is assigned to every interface which connects to the Internet. The addresses are still assigned by using Internet Protocol version 4 (IPv4). IPv4 has demonstrated robust, compatibility with vast range of protocols, applications and easy implementation. IPv4 had been supposed to cover all the network interfaces, however with huge increase of the number of devices (computer, mobile, tablet, routers, server, etc) the reserve of assigned addresses is exhausted. IPv6 has been deployed for providing new services and for supporting the internet growth. This study compares the key specifications of IPv4 and IPv6, contrasts IPv4 and IPv6 header’s fields, the structure of headers, explains advantages of IPv6 and disadvantages of IPv4, and why we are running out of IPv4

- by Prof. (Dr.) Rafiqul Zaman Khan and +1
- •
- Gesture Recognition, Parallel and Distributed Computing

Models, architectures and languages for parallel computation have been of utmost research interest in computer science and engineering for several decades. A great variety of parallel computation models has been proposed and studied, and different parallel and distributed architectures designed as some possible ways of harnessing parallelism and improving performance of the general purpose computers.

- by P. T Tosic
- •
- Computer Science, Neural Networks, Cellular Automata, Distributed System

Notice of Violation of IEEE Publication Principles"A Dynamic Distributed Diagnosis Algorithm for an Arbitrary Network Topology with Unreliable Nodes and Links,"by Pabitra Mohan Khilar and Sudipta Mahapatra,in the Proceedings of the International Conference on Advanced Computing and Communications, 2007. ADCOM, Dec. 2007, pp. 125-130After careful and considered review of the content and authorship of this paper by a duly constituted expert committee, this paper has been found to be in violation of IEEE's Publication Principles.This paper contains significant portions of original text from the paper cited below. The original text was copied without attribution (including appropriate references to the original author(s) and/or paper title) and without permission.Due to the nature of this violation, reasonable effort should be made to remove all past references to this paper, and future references should be made to the following article:"A Distributed Network Connectivity Algorithm,"By E. Procopio Duarte Jr. and A.Weber,The Sixth International Symposium on Autonomous Decentralized Systems, 2003. ISADS 2003 April 2003, pp. 285-292This paper presents a distributed network diagnosis (DND) algorithm for an arbitrary network topology where every node needs to record the status of every other nodes and links assuming the nodes and links are subjected to crash and value faults in a dynamic fault environment (the node's or link's status may change during execution of algorithm). The algorithm operates correctly in each connected component if the network is partitioned due to a set of faulty links or faulty nodes. The worst-case bounds for diagnostic latency is at most O(td) rounds where t is the number of dissemination trees and d is the diameter of the network. The proposed approach uses non-broadcasting method of message dissemination that has similar diagnostic latency with flooding [4] and similar message co- mplexity with Chinese Agent [14] method of message dissemination respectively.

The quadratic assignment problem (QAP), one of the most difficult problems in the NP-hard class, models many applications in several areas such as operational research, parallel and distributed computing, and combinatorial data analysis. Other optimization combinatorial problems such as the traveling salesman problem, maximal clique, isomorphism and graph partitioning can be formulated as a QAP. In this paper, we survey some of the most important formulations available and classify them according to their mathematical sources. We also present a discussion on the theoretical resources used to define lower bounds for exact and heuristic algorithms, including those formulated according to metaheuristic strategies. Finally, we analyze the extension of the contributions brought about by the study of different approaches.

- by Tania Querido and +2
- •
- Combinatorial Optimization, Data Analysis, Integer Programming, Multidisciplinary

Abstract: The recent development of parallel and distributed computing software has introduced a variety of software tools that support several programming paradigms and languages. This variety of tools makes the selection of the best... more

Up coming generation need all sophisticated things done using smart technology. This intellectual devices makes a person life light,bright,stylish and relax. At present there are more number of security system available with work without the help of human action, which can be controlled by remote or voice. The system is designed such that the motion of the user will be detected from the IR sensor and after entering correct password only user will be able to unlock the door. The beneft of this system over the present system is that it is comfortable,affordable, can be set up easily where things are secured more.

- by Kotresh Marali and +1
- •
- Computer Architecture, Parallel and Distributed Computing

Comparisons of high-performance computers based on their peak floating point performance are common but seldom useful when comparing performance on real workloads. Factors that influence sustained performance extend beyond a system's floating-point units, and real applications exercise machines in complex and diverse ways. Even when it is possible to compare systems based on their performance, other considerations affect which machine is best for a given organization. These include the cost, the facilities requirements (power, floorspace, etc.), the programming model, the existing code base, and so on. This paper describes some of the important measures for evaluating high-performance computers. We present data for many of these metrics based on our experience at Lawrence Livermore National Laboratory (LLNL), and we compare them with published information on the Earth Simulator. We argue that evaluating systems involves far more than comparing benchmarks and acquisition costs. We show that evaluating systems often involves complex choices among a variety of factors that influence the value of a supercomputer to an organization, and that the high-end computing community should view cost/performance comparisons of different architectures with skepticism.

Aloe barbadensis (aloe-vera) also famous as a first aid plant is a valuable natural medicine. Its leaves have parallel venation that contains a soothing thick gel inside it and is useful for treatment and curing of wounds and diseases. In this paper, investigations were carried out to study the effect of dc and ac resistances of the aloe barbadensis leaves. The resistance of the leaf measured shows a proportional change with the change in the length of the leaf. The resistance of the leaf tissue increases with the increased distance between the electrodes due to circumvent current path. Both, fresh and the dry leaf of a aloe barbadensis plant was taken for the investigations. For fresh leaf, the dc resistance increases steeply along the length of a leaf while ac resistance comparatively shows a very slow increase in resistance, where as the results verified some fascinating changes in resistance as the leaf dried up.

Notice of Violation of IEEE Publication Principles"Towards a Unified Framework for Complexity Measurement in Aspect-Oriented Systems,"by A. Kumar, R. Kumar, P.S. Groverin the Proceedings of the 2008 International Conference on Computer Science and Software Engineering, vol.2, pp.98-103, Dec. 2008After careful and considered review of the content and authorship of this paper by a duly constituted expert committee, this paper has been found to be in violation of IEEE's Publication Principles.This paper contains significant portions of original text from the paper cited below. The original text was copied without attribution (including appropriate references to the original author(s) and/or paper title) and without permission.Due to the nature of this violation, reasonable effort should be made to remove all past references to this paper, and future references should be made to the following article:"Towards a Unified Coupling Framework for Measuring Aspect-oriented Programs"by T.T. Bartolomei, A. Garcia, C. Sant'Anna, C., E. Figueiredoin the Proceedings of the 3rd International Workshop on Software Quality Assurance (Portland, Oregon, November 06 - 06, 2006). SOQUA '06. ACMAspect-oriented programming (AOP) is an emerging technique that provides a mechanism to clearly encapsulate and implement concerns that crosscut other modules. It is claimed that this technique improves code modularization and therefore reduce complexity of object-oriented programs (OOP). Most of the proposed complexity measurement frameworks and metrics for AOP are for AspectJ programming language. In this paper we have defined a generic complexity measurement framework that takes into account three, the most well known families of available AOP languages, AspectJ, CaesarJ and Hyper/J. The proposed unified framework contributes to better understanding of complexity in AOP, which in turn help to (i) define new complexity metrics whic- h permit the analysis and comparison of Java, AspectJ, CaesarJ and Hyper/J implementations, and (ii) integrating different existing measures and examine same concepts in different ways.

Association Rule Mining (ARM) is one of the well know and most researched technique of data mining. There are so many ARM algorithms have been designed that their counting is a large number. In this paper we have surveyed the various ARM algorithms in four computing environments. The considered computing environments are sequential computing, parallel and distributed computing, grid computing and cloud computing. With the emergence of new computing paradigm, ARM algorithms have been designed by many researchers to improve the efficiency by utilizing the new paradigm. This paper represents the journey of ARM algorithms started from sequential algorithms, and through parallel and distributed, and grid based algorithms to the current state-of-the-art, along with the motives for adopting new machinery.

- by Sudhakar Singh and +1
- •
- Grid Computing, Data Mining, Cloud Computing, Association Rules Mining

Load balancing is one of the central issues and
challenges in cloud computing environments. In cloud computing
environments, the system should avoid wasting resources as a
result of under-utilization and avoid lengthy response times as a
result of over-utilization. In this paper, we propose a new load
balancing method, named Cloud Light Weight (CLW), which not
only balances the Virtual Machines'(VM) workload in cloud
computing datacenters, but it also assures QoS for users. It
reduces both the number of VM migration processes and the
migration time during applications execution. We validate our
algorithm using the CloudSim cloud system simulator.

Cloud Computing is an ever-growing paradigm shift in
computing allowing users commodity access to compute and storage
services. As such cloud computing is an emerging promising
approach for High Performance Computing (HPC) application
development. Automation of resource provision offered by Cloud
computing facilitates the eScience programmer usage of computing
and storage resources. Currently, there are many commercial services
for compute, storage, network and many others from big name
companies. However, these services typically do not have
performance guarantees associated with them. This results in
unexpected performance degradation of user’s applications that can
be somewhat random to the user. In order to overcome this, a user
must be well versed in the tools and technologies that drive Cloud
Computing. One of the state of the art cloud systems, Joyent
SmartDataCenter, is a cloud system that provides virtual machines
(and their processes) the ability to burst CPU capacity automatically
and thus is suitable for HPC applications. To help HPC developers,
we present a set of Hadoop MapReduce and MPI benchmarks for
FlexCloud (a SmartDataCenter installation). Our benchmarks show
that this cloud system offers scalable performance for HPC
environments.

Quadratic Assignment Problems model many applications in diverse areas such as operations research, parallel and distributed computing, and combinatorial data analysis. In this paper we survey some of the most important techniques, applications, and methods regarding the quadratic assignment problem. We focus our attention on recent developments. 1991 Mathematics Subject Classi cation. Primary 90B80, 90C20, 90C35, 90C27; Secondary 65H20, 65K05.

- by Sabri Pllana
- •
- Distributed Computing, Parallel Computing, Materials Science, Computational Modeling

Empathy is a concept central to psychiatry, psychotherapy and clinical psychology. The construct of empathy involves not only the affective experience of the other person's actual or inferred emotional state but also some minimal recognition and understanding of another's emotional state. It is proposed, in the light of multiple levels of analysis including social psychology, cognitive neuroscience and clinical neuropsychology, a model of empathy that involves both bottom-up and top-down information processing underpinned ...

- by Jean Decety
- •
- Psychology, Clinical Psychology, Cognitive Science, Social Psychology

1 A new and efficient mechanism to tolerate failures in interconnection networks for parallel and distributed computers, denoted as Immunet, is presented in this work. In the presence of failures, Immunet automatically reacts with a hardware reconfiguration of the surviving network resources. Immunet has four important advantages over previous fault-tolerant switching mechanisms. Its low hardware costs minimize the overhead that the network must support in absence of faults. As long as the network remains connected, Immunet can tolerate any number of failures regardless of their spatial and temporal combinations. The resulting communication infrastructure provides optimized adaptive minimal routing over the surviving topology. The system behavior under successive failures exhibits graceful performance degradation.

- by Fernando Vallejo
- •
- Distributed Computing, Computer Networks, Routing, Packet Switching

Software integration is a crucial aspect of collaborative software applications and systems. It enables a number of different software applications, created by different developers, using different programming languages, and even located at different places to work with each other collaboratively to achieve common goals. Nowadays, a number of techniques are available to enable software integration. Messaging is the most prominent technique in this respect. In this paper, two leading open-source messaging brokers, Apache ActiveMQ and Apache Apollo, have been experimentally compared with each other with regard to their messaging capabilities (message sending and receiving throughputs). Both brokers support exchanging messages between heterogeneous and distributed software applications using several messaging mechanisms including Java Message Service (henceforth JMS). A number of experimental test scenarios have been conducted to obtain the comparison results that indicate the one-to-one JMS messaging performance of each broker. Overall performance evaluation and analysis showed that Apache Apollo outperformed Apache ActiveMQ in all test scenarios regarding message sending throughputs. Whereas, Apache ActiveMQ outperformed Apache Apollo in most test scenarios regarding message receiving throughputs. Moreover, the evaluation methodology (test conditions, test scenarios, and test metrics) proposed in this paper has been carefully chosen to be adopted by software developers to evaluate other messaging brokers to determine the acceptable level of messaging capabilities in distributed environments of heterogeneous software applications.

This paper presents a neural network approach with successful implementation for the robot task-sequencing problem. The problem addresses the sequencing of tasks comprising loading and unloading of parts into and from the machines by a material-handling robot. The performance criterion is to minimize a weighted objective of the total robot travel time for a set of tasks and the tardiness of the tasks being sequenced. A three-phased parallel implementation of the neural network algorithm on Thinking Machine's CM-5 parallel computer is also presented which resulted in a dramatic increase in the speed of finding solutions. To evaluate the performance of the neural network approach, a branch-and-bound method and a heuristic procedure have been developed for the problem. The neural network method is shown to give good results and is especially useful for solving large problems on a parallel-computing platform. ᭧

Our energy production increasingly depends on renewable energy sources, which impose new challenges for distributed and decentralized systems. One problem is that the availability of renewable energy sources such as wind and solar is not continuous as it is affected by meteorological factors. The challenge is to develop forecast methods capable of determining the level of power generation (e.g., through solar power) in near real-time in order to control solar power plants for optimal energy production. Another scenario is the identification of optimal locations for * Funded by the German Federal Ministry of Education and Research (BMBF, http://www.bmbf.de) such power plants. In our collaborative project, these tasks are investigated in the domain of energy meteorology. For that purpose large data sources from many different sensors (e.g., satellites and ground stations) are the base for complex computations. The idea is to parallelize these computations in order to obtain significant speedup. This paper reports on an ongoing project employing Grid technologies in that context. Our approach to processing large data sets from a variety of heterogeneous data sources as well as ideas for parallel and distributed computing in energy meteorology are presented. Preliminary experience with several Grid middleware systems in our application scenario is discussed.

A new class of models, formalisms and mechanisms has recently evolved for describing concurrent and distributed computations based on the concept of "coordination". The purpose of a coordination model and associated language is to provide a means of integrating a number of possibly heterogeneous components together, by interfacing with each component in such a way that the collective set forms a single application that can execute on and take advantage of parallel and distributed systems. In this chapter we initially define and present in sufficient detail the fundamental concepts of what constitutes a coordination model or language. We then go on to classify these models and languages as either "data-driven" or "control-driven" (also called "process-" or "task-oriented"). In the process, the main existing coordination models and languages are described in sufficient detail to let the reader appreciate their features and put them into perspective with respect to each other. The chapter ends with a discussion comparing the various models and some conclusions.

- by Farhad Arbab
- •
- Distributed Computing, Computers, Parallel and Distributed Computing

Quadratic Assignment Problems model many applications in diverse areas such as operations research, parallel and distributed computing, and combinatorial data analysis. In this paper we survey some of the most important techniques, applications, and methods regarding the quadratic assignment problem. We focus our attention on recent developments. 1 This paper and a separate bibliography le (bib le) is available by anonymous ftp at orion.uwaterloo.ca in the directory pub/henry/qap.

Applications that explore, query, analyze, visualize, and, in general, process very large scale data sets are known as Data Intensive Applications. Large scale data intensive computing plays an increasingly important role in many scientific activities and commercial applications, whether it involves data mining of commercial transactions, experimental data analysis and visualization, or intensive simulation such as climate modeling. By combining high performance computation, very large data storage, high bandwidth access, and high-speed local and wide area networking, data intensive computing enhances the technical capabilities and usefulness of most systems. The integration of parallel and distributed computational environments will produce major improvements in performance for both computing intensive and data intensive applications in the future. The purpose of this introductory article is to provide an overview of the main issues in parallel data intensive computing in scientific and commercial applications and to encourage the reader to go into the more in-depth articles later in this special issue.

- by Mario Cannataro
- •
- Cognitive Science, Distributed Computing, Parallel Computing, Data Mining

The realization of truely heterogeneous database systems is hampered among others by two obstacles. One is the unsuitability of traditional transaction models, this has lead to the proposal of a new more flexible transaction model. Th.e second is the fact that none of the existing language and system support such a flexible model. This paper addresses these two issues by proposing a logic approach to the integration of database systems.

The University of Delaware, marking its 256th year as the only research university in the State of Delaware, is a state-assisted, privately governed institution with approximately 15,000 undergraduate students, 3,000 graduate students, 3,000 students enrolled in credit courses through Continuing Education, and 900 faculty members. The Department of Computer and Information Sciences (CIS) is one of 25 departments in the College of Arts and Sciences, and offers BA, BS, MS, and PhD degrees. There are 16 full-time tenuretrack or tenured faculty, 2 visiting faculty, and 5 research faculty in the department. There are 455 CIS undergraduate majors and 85 CIS graduate students. CIS courses are also taken by non-major students both as requirements in their degree programs and to earn a CIS minor. The Department of Electrical and Computer Engineering (ECE) is one of 6 departments in the College of Engineering, and offers a Bachelor of Electrical Engineering, Bachelor of Computer Engineering, MS and PhD degrees. There are 5 full-time tenure-track or tenured faculty in the Computer Engineering portion of ECE, and there are 110 undergraduate Computer Engineering majors, along with 20 Computer Engineering graduate students.

This paper presents several parallel algorithms for the construction of the Delaunay triangulation in E 2 and E 3 -one of the fundamental problems in computer graphics. The proposed algorithms are designed for parallel systems with shared memory and several processors. Such a hardware configuration (especially the case with two-processors) became widely spread in the last few years in the computer graphics area. Some of the proposed algorithms are easy to be implemented but not very efficient, while some of them prove opposite characteristics. Some of them are usable in E 2 only, other work in E 3 as well. The algorithms themselves were already published in computer graphics where the computer graphics criteria were highlighted. This paper concentrates on parallel and systematic point of view and gives detailed information about the parallelization of a computational geometry application to parallel and distributed computation oriented community.

- by Jiri Zara and +1
- •
- Cognitive Science, Distributed Computing, Parallel Computing, Computational Geometry

Dynamic scheduling algorithms have been successfully
used for parallel computations of nested loops in traditional
parallel computers and clusters. In this paper we propose a
new architecture, implementing a coarse grain dynamic loop
scheduling, suitable for reconfigurable hardware platforms. We
use an analytical model and a case study to evaluate the
performance of the proposed architecture. This approach makes
efficient memory and processing elements use and thus gives
better results than previous approaches.

- by Anthony T Chronopoulos
- •
- Computer Science, Compilers, Embedded Systems, Scheduling

Techniques to handle traffic bursts and out-of-order arrivals are of paramount importance to provide real-time sensor data analytics in domains like traffic surveillance, transportation management, healthcare and security applications. In these systems the amount of raw data coming from sensors must be analyzed by continuous queries that extract value-added information used to make informed decisions in real-time. To perform this task with timing constraints, parallelism must be exploited in the query execution in order to enable the real-time processing on parallel architectures. In this paper we focus on continuous preference queries, a representative class of continuous queries for decision making, and we propose a parallel query model targeting the efficient processing over out-of-order and bursty data streams. We study how to integrate punctuation mechanisms in order to enable out-of-order processing. Then, we present advanced scheduling strategies targeting scenarios with different burstiness levels, parameterized using the index of dispersion quantity. Extensive experiments have been performed using synthetic datasets and real-world data streams obtained from an existing real-time locating system. The experimental evaluation demonstrates the efficiency of our parallel solution and its effectiveness in handling the out-of-orderness degrees and burstiness levels of real-world applications.

- by Gabriele Mencagli and +1
- •
- Distributed Computing, Parallel Computing, Social Media, Data Streams

Cloud computing (CC) is a provision of providing on-demand, online services pay per use basis. Today cloud computing has been rising as new technology. Mainly cloud computing provides three computing resources to its users or clients; these are Infrastructure as a Service (IaaS), Platform as a Service (PaaS) and Software as a Service (PaaS). In other words cloud computing is a platform, environment, or an economic model to use various useful IT resources from anywhere in the world. It supports various issues like security, heterogeneity, parallelism, and data backup for internet users. As cloud computing is in its evolving stage today, there are various problems or issues to be discussed and solved. One of these issues is load distribution (LD) or load balancing (LB).

This paper presents a flexible and effective model for object-oriented parallel programming in both local and wide area contexts and its implementation as a Java package. Blending r emote evaluation and active messages, our model permits programmers to express asynchronous, complex interactions, so overcoming some of the limitations of the models based on message passing and RPC and reducing communication costs.