Anonymous remote computing: a paradigm for parallel programming on interconnected workstations

Joshi, Rushikesh K.; Ram, D. Janaki

doi:10.1109/32.748919

Cited by 17 publications

(5 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Carr (2003) posits that IT is becoming commoditised and should be used like a utility. Following this, Rappa (2004) asserts that cloud computing has the characteristics of a utility and the major business benefit in this is that the service is on-demand, the implication being that cloud consumers will pay the same for one server for a thousand hours as they would a thousand servers for one hour (Joshi & Ram 1999). This links with scalability as well to provide compelling reasons for using cloud computing.…”

Section: Literature Reviewmentioning

confidence: 99%

Cloud Computing: A Readiness Study among Small Financial Organisations

Gouweloos¹,

McArthur²

2019

Alternation

View full text Add to dashboard Cite

This article reports on the readiness for cloud computing in several financial services institutions from the Pietermaritzburg region. Cloud computing is viewed as being a disruptive technology, and there are real benefits for the adoption of this paradigm for service delivery. The study on which this article reports, investigated whether or not these small organisations are ready to take advantage of this technology. The researcher developed an initial framework for readiness, then interviewed three decision-makersone from each organisationand organised the data generated into a revised model for readiness. It has emerged that awareness and trust are key factors for these organisations. Counter-intuitively, cost saving has less of an influence than expected. There is limited literature in this specific context; this article therefore forms an initial basis for further research.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Cloud Computing: A Readiness Study among Small Financial Organisations

Gouweloos¹,

McArthur²

2019

Alternation

View full text Add to dashboard Cite

show abstract

“…The dynamic load on the participating systems and the hosts and link failures make the traditional cluster computing model unsuitable for parallel programming on MCC. These issues were effectively handled in [7], however the model does not address the mobile host participation in computation and the issues related to it. The Moset model is aimed to integrate the mobile hosts with the static hosts to form a mobile cluster, and to harness the idle computing power, of static and mobile hosts to utilize them for parallel computing.…”

Section: Moset Computation Modelmentioning

confidence: 99%

“…To incorporate this, each host is allocated an integer called Horse Power Factor (HPF) [7], which is a measure of the computing power of a machine, load on the machine and the network bandwidth of the communication channel. Machines in the network are normalized by a benchmark program to obtain a relative index of the machine, which is a static factor.…”

Section: Horse Power Factor and Dynamic Load Balancingmentioning

confidence: 99%

Communication and Computing Paradigm for Distributed Mobile Systems

Mohamed¹

2007

Int. Jour. Info. Sci. Comp.

View full text Add to dashboard Cite

The advancements in technology have enabled mobile devices to become information and service providers by complementing or replacing static hosts. This motivates the need for merging of mobile and grid technologies, leading to mobile grid paradigm. Computational mobile grid can also be viewed as a seamless integration of cluster of mobile clusters. Hence, as a first step in realizing a mobile grid, Anonymous Remote Mobile Cluster Computing (ARMCC) model is proposed. The main purpose of ARMCC is to utilize the idle computing power of both the static and mobile nodes, to provide parallel programming on a distributed mobile computing environment. The cluster model was extended to a mobile grid paradigm that integrates the computational, data and service grids. However, though the mobile grid is visualized as cluster of mobile clusters, the model of mobile cluster is not directly applicable to mobile grid. In addition to computational power other resources and services offered by the participating nodes are shared in case of mobile grid. Thus, all the participating mobile nodes in the mobile grid are represented using surrogate objects which reside on the static portion of the network. These surrogate objects are realized as a shared distributed object space. The constrained nature of the mobile devices participating in the mobile cluster requires an efficient communication primitive for exactly-once message delivery. Thus a novel communication paradigm, namely, Fault Tolerant Exactly Once Reliable Multicast Protocol (FTEORMP) for distributed mobile system is proposed. Key words: I. INTRODUCTIONHigh speed networks and the improved performance of processors in the recent years, has made network of workstations [1] an efficient paradigm for parallel and distributed computing. On the other hand, with rapid evolution of wireless communications, a huge number of communication devices and mobile devices have been developed. These devices provide high computing power and storage capabilities. At the same time, the cost for these high end mobile devices is decreasing and thus becoming affordable for everyone. Thus, computing is no longer restricted to desktop computers, and access to information, resources and data is made available anytime and anywhere [2]. This has led to a new era in computing, namely distributed mobile computing. It involves distributed mobile systems that are defined as a collection of processes where some processes are running on Mobile Hosts (MHs), in addition to some processes running on Static Hosts (SHs). These processes communicate with each other by exchanging messages. This paradigm provides the flexibility for the mobile users to roam around freely while maintaining connectivity with a wired computing infrastructure. Thus enabling mobile users to communicate/compute effortlessly, anywhere, anytime.This work specifically addresses problems arising out of integrating mobile devices into distributed systems. Applications with distributed systems are not suitable in distributed mobile sys...

show abstract

“…In anonymous remote computing (ARC) paradigm [9], a parallel program for NOW is written as a collection of several loosely coupled blocks called remote instruction blocks (RIB) within a single program entity. An RIB is a code fragment that can be migrated to a convenient anonymous remote node at runtime for execution.…”

Section: Arc Model Of Computationmentioning

confidence: 99%

Integrating task parallelism in data parallel languages for parallel programming on NOWs

Binu¹,

Ram²

2000

Concurrency: Pract. Exper.

View full text Add to dashboard Cite

SUMMARYA number of high-level parallel programming platforms for networks of workstations (NOWs) have been developed in recent times. Most of these platforms target the exploitation of data parallelism in applications. They do not allow expressibility of applications as a collection of tasks along with their precedence relationships. As a result, the control or task parallelism in an application cannot be expressed or exploited. The current work aims at integrating the notion of task parallelism and precedence relationships among constituting tasks to such high-level data parallel platforms for NOWs. Our model of integration provides for arbitrary nesting of data and task parallel modules. Also, the precedence relationships are clearly reflected from the program structure. The model relieves the programmer from the need to design applications for non-determinism in the order of completion of constituting tasks. The design of the runtime support as well as system-level book keeping is discussed. The model is general enough to be applied to a wide range of data parallel platforms. A specific case of integrating the model into anonymous remote computing (ARC), a data parallel programming platform, is presented. The performance related aspects are also discussed.

show abstract

Anonymous remote computing: a paradigm for parallel programming on interconnected workstations

Cited by 17 publications

References 40 publications

Cloud Computing: A Readiness Study among Small Financial Organisations

Cloud Computing: A Readiness Study among Small Financial Organisations

Communication and Computing Paradigm for Distributed Mobile Systems

Integrating task parallelism in data parallel languages for parallel programming on NOWs

Contact Info

Product

Resources

About