The continuous shift of hardware computing architectures, from single to many-core processors, as well as the blurring of the hardware - software interface, has made the introduction of parallel and distributed comput...
详细信息
ISBN:
(纸本)9783030105495;9783030105488
The continuous shift of hardware computing architectures, from single to many-core processors, as well as the blurring of the hardware - software interface, has made the introduction of parallel and distributedcomputing topics in the undergraduate curriculum an essential requirement for any quality computer science program. The University Politehnica of Bucharest offers a unique approach, employing a heterogeneous hardware and software teaching and computing infrastructure, to its over 450 students enrolled in undergraduate studies of Computer Science and Electrical Engineering. In this study we present two of the most important lectures covering PDC topics at the UPB.
Because of distributed nature, gridcomputing environments are easy targets for intruders looking for possible vulnerabilities to exploit [1]. By impersonating legitimate users, the intruders can use a service's a...
详细信息
grid is an emerging infrastructure which enables effective coordinate access to various distributedcomputing resources in order to serve the needs of collaborative research and work across the world. grid resource ma...
详细信息
ISBN:
(纸本)9783037850206
grid is an emerging infrastructure which enables effective coordinate access to various distributedcomputing resources in order to serve the needs of collaborative research and work across the world. grid resource management is always a key subject in the gridcomputing. We first analyze the resource management in the gridcomputing environment, then according to the load imbalance question in the ant colony optimization algorithm, propose an improved algorithm that suits to be used in the grid environment.
We investigate the problem of developing and optimizing a dynamic load. balancing scheduler for efficient execution of Logic and Constraint programs on Beowulf clusters. We experimentally evaluate alternative scheduli...
详细信息
ISBN:
(纸本)1880843528
We investigate the problem of developing and optimizing a dynamic load. balancing scheduler for efficient execution of Logic and Constraint programs on Beowulf clusters. We experimentally evaluate alternative scheduling strategies (centralized vs. distributed, top-most vs. bottommost, random vs. non-random) and use the results to implement and optimize the scheduler used in PALS-an efficient distributed implementation of Prolog.
gridcomputing extends the application domain to include interaction and collaboration, termed as interactive grid. Interactive grid enables various collaborative applications, in which activities involve geographical...
详细信息
ISBN:
(纸本)1424402115
gridcomputing extends the application domain to include interaction and collaboration, termed as interactive grid. Interactive grid enables various collaborative applications, in which activities involve geographically distributed and heterogeneous resources, to work together to achieve a common goal. Thus, software support to facilitate coordination among entities is needed. This paper introduces a session management framework for collaborative applications in interactive grid, and describes the mechanisms of session management in detail. Then, a scalable and flexible software architecture based on OGSA is presented, which adapt to the dynamism of grid resources. Finally, the performance evaluation is given.
Task scheduling algorithms are designed mostly with the sole goal of minimizing makespan (completion time). Almost all research works related to this kind of algorithms do not pay much attention to energy consumption....
详细信息
grid systems - A collection of distributed heterogeneous resources that are coupled together by computer networks - enabled the emergence of diverse types of innovative applications that have, in many cases, high-perf...
详细信息
grid systems - A collection of distributed heterogeneous resources that are coupled together by computer networks - enabled the emergence of diverse types of innovative applications that have, in many cases, high-performance orientation. Many scheduling heuristics aim to schedule high-performance applications represented by Directed Acyclic Graph (DAG)s. However, these heuristics are designed and tested for limited distributed architectures. Scheduling tasks in grid environments has new emerging requirements such as supporting heterogeneity and scalability. This paper presents modified versions of three heuristics. These modifications are necessary for the heuristics to meet the new grid requirements. Testing these heuristics is done through simulations using a grid simulation package. Finally, performance analysis of these heuristics and comparisons between them were also carried out as a part of work presented in this paper.
The technological and scientific advances in life sciences increase the demand on computing power and storage capacity. Such new requirements can be met by grid-computing, the collaboration of distributed resources ac...
详细信息
ISBN:
(纸本)9780889866485
The technological and scientific advances in life sciences increase the demand on computing power and storage capacity. Such new requirements can be met by grid-computing, the collaboration of distributed resources across institutional borders. This article focuses on the integration of DICOM as world-wide standard for medical imaging systems into a Globus grid environment. Globus is one of the most popular grid toolkits available today. A grid version of the DICOM implementation (grid-DICOM) is developed by adaption to the Globus grid security interface (GSI). Furthermore, the development of a grid-DICOM router enables a seamless integration of legacy DICOM devices like image archives (PACS) and other medical imaging systems. A web-based portal allows user-friendly access to these systems and other DICOM operations in the grid. A prototype of this DICOM image transfer service is installed and tested in Medigrid, the German grid network for life sciences. First runtime tests demonstrate the seamless integration, but reveal slightly higher transfer times compared to conventional DICOM transfer due to the additional security layer.
In this paper we present a novel approach for functional-style programming of distributed-memory clusters, targeting data-centric applications. The programming model proposed is purely sequential, SPMD-free and based ...
详细信息
ISBN:
(纸本)9781467387767
In this paper we present a novel approach for functional-style programming of distributed-memory clusters, targeting data-centric applications. The programming model proposed is purely sequential, SPMD-free and based on high-level functional features introduced since C++11 specification. Additionally, we propose a novel cluster-as-accelerator design principle. In this scheme, cluster nodes act as general interpreters of user-defined functional tasks over node-local portions of distributed data structures. We envision coupling a simple yet powerful programming model with a lightweight, locality aware distributed runtime as a promising step along the road towards high-performance data analytics, in particular under the perspective of the upcoming exascale era. We implemented the proposed approach in SkeDaTo, a prototyping C++ library of data-parallel skeletons exploiting cluster-as-accelerator at the bottom layer of the runtime software stack.
Self-stabilizing systems have in theory the unique and provable ability, to always return to a valid system state even in the face of failures. These properties are certainly desirable for domains like wireless ad-hoc...
详细信息
ISBN:
(纸本)9781509014590
Self-stabilizing systems have in theory the unique and provable ability, to always return to a valid system state even in the face of failures. These properties are certainly desirable for domains like wireless ad-hoc networks with numerous unpredictable faults. Unfortunately, the time in which the system returns to a valid state is not predictable and potentially unbound. The failure rate typically depends on physical phenomena and in self-stabilizing systems each node tries to react to failures in an inherently adaptive fashion by the cyclic observation of the states of its neighbors. When state changes are either too quick or too slow the system might never reach a state that is sufficiently stable for a specific task. In this paper, we investigate the influences of the error rate on the (stability) convergence time on the basis of topology information acquired in real network experiments. This allows us to asses the asymptotic behavior of relevant self-stabilizing algorithms in typical wireless networks.
暂无评论