Monitoring tools are necessary components in the support of distributed applications and can be used to provide dependability, debugging and testing, to enhance the performance and to make possible the run-time steeri...
详细信息
ISBN:
(纸本)0818680679
Monitoring tools are necessary components in the support of distributed applications and can be used to provide dependability, debugging and testing, to enhance the performance and to make possible the run-time steering of applications. These tools are needed to exploit in the best way all the available high performance computing resources of a heterogeneous environment. This paper describes HOLMES, an on-line monitoring system designed to support dynamic management of resources that requires run-time measurement. HOLMES identifies the evolving system state and provides the necessary information to any dynamic policy to assign resources by following application evolution. HOLMES makes possible to control and steer an application even distributed across heterogeneous architectures, from parallel machines to clusters of workstations and PCs.
In this paper we describe a task allocation method, that utilizes genetic programming to find a suitable solution in an adequate time for this NP-complete combinatorial optimization problem. The underlying distributed...
详细信息
ISBN:
(纸本)9780769530499
In this paper we describe a task allocation method, that utilizes genetic programming to find a suitable solution in an adequate time for this NP-complete combinatorial optimization problem. The underlying distributed embedded system is heterogenous, consisting of different processors with different properties such as core type, clock frequency, available memory, and I/O interfaces, interconnected with different communication media. In our applications, which are described as data flow graphs, the number of tasks to be placed is much larger than the number of processors available. We highlight the difficulties when applying genetic programming to this problem and present our solutions and enhancements, accompanied with some simulation results.
The growing demand for high-performance data processing stimulates the development of in-memory file systems, which exploit the advanced features of emerging non-volatile memory techniques for achieving high-speed fil...
详细信息
ISBN:
(纸本)9781509050819
The growing demand for high-performance data processing stimulates the development of in-memory file systems, which exploit the advanced features of emerging non-volatile memory techniques for achieving high-speed file accesses. Existing in-memory file systems, however, are all designed for the systems with uniformed memory accesses. Their performance is poor on Non-Uniform Memory Access (NUMA) machines as they do not consider the asymmetric memory access speed and the architecture of multiple nodes. In this paper, we propose a new design of NUMA-aware in-memory file systems. We propose a distributed file system layout for leveraging the loads of in-memory file accesses on different nodes, a thread-file binding algorithm and a buffer assignment technique for increasing local memory accesses during run-time. Based on the proposed techniques, we implement a functional NUMA-aware in-memory file system, HydraFS, in Linux kernel. Extensive experiments are conducted with the standard benchmark. The experimental results show that HydraFS significantly outperforms typical existing in-memory file systems, including EXT4-DAX, PMFS, and SIMFS.
Cloud computing is the latest evolution in the distributedcomputing paradigm and is being widely adopted by enterprises and organizations. The inherent benefits like instant scalability, pay for use, rapid elasticity...
详细信息
ISBN:
(纸本)9783642225765
Cloud computing is the latest evolution in the distributedcomputing paradigm and is being widely adopted by enterprises and organizations. The inherent benefits like instant scalability, pay for use, rapid elasticity, cost effectiveness, self-manageable service delivery and broader network access make cloud computing 'the preferred platform' for deploying applications and services. However, the technology being in nascent stage needs to be proven. The biggest challenge confronting service providers is effective provisioning and scheduling of cloud services to consumers leveraging the cost benefits of this computing paradigm. This paper attempts to investigate the key concerns for cloud resource management and explores possible alternatives that can be adapted from the existing grid technology.
Large-scale distributed systems are not always stable because the environments and the user requirements are changeable. The author has discussed the receptive platform to make distributed systems flexible and reliabl...
详细信息
ISBN:
(纸本)0818672676
Large-scale distributed systems are not always stable because the environments and the user requirements are changeable. The author has discussed the receptive platform to make distributed systems flexible and reliable. In order to achieve the receptive platform, it is essential to discuss how to update the distributed programs. Since conventional updating methods require that multiple processes be suspended simultaneously, the availability of the system becomes lower. A new method called the dynamic updating has been proposed. The key idea is that multiple versions of processes are allowed to co-exist temporarily while the old-version processes are not used anymore. If such protocol errors as the unspecified receptions and the dead-locks caused by the co-existence occurs, the suspended old-version processes are restarted from the consistent state. An algorithm, has been designed for treating the unspecified receptions. This paper proposes an extended group communication algorithm that can detect and resolve the deadlocks. By using the algorithm, the dynamic updating can be applied to more general distributed application programs.
There is a very serious problem plaguing people right now, and that is the shortage of blood banks around the world. This is because blood is at the heart of a major healthcare challenge, blood plays a vital role as t...
详细信息
ISBN:
(纸本)9798350391961;9798350391954
There is a very serious problem plaguing people right now, and that is the shortage of blood banks around the world. This is because blood is at the heart of a major healthcare challenge, blood plays a vital role as the body's energy source. To address this issue, this paper describes a post-donation blood quality testing system, as well as a cross-matching testing system for blood type suitability for patients, that utilizes the advanced security features of Amazon Web Services (AWS), rigorously stores all user data, including personal information and blood type, and adds a commitment to protecting the integrity and confidentiality of blood donor data. AWS's scalability ensures that the system can adapt to the growing demand for blood supply while maintaining performance and security, enhancing trust and transparency between donors, recipients, and healthcare providers. Blood is at the heart of a major healthcare challenge. Blood plays a vital role as the body's energy source. Hence, we propose a web-based application system that is integrated in real-time with hospital databases in various regions, especially in remote areas, enabling rapid identification of blood needs and effective distribution, greatly reducing emergency response time. Also, the system will effectively help people living in remote areas. This system not only solves today's blood supply management challenges but also sets a new standard for global healthcare equity and access in the future, ensuring that life-saving blood is available everywhere and to everyone who needs it.
Acknowledged as important factors for business environments operating as Virtual Organizations (VOs), trust and reputation are receiving attention also in grids devoted to scientific applications where problems of fin...
详细信息
ISBN:
(纸本)9781424428649
Acknowledged as important factors for business environments operating as Virtual Organizations (VOs), trust and reputation are receiving attention also in grids devoted to scientific applications where problems of finding suitable models and architectures for flexible security management of heterogeneous resources arise. Being these resources highly heterogeneous (from individual users to whole organizations or experiment tools and workflows), this paper presents a trust and reputation framework that integrates a number of information sources to produce a comprehensive evaluation of trust and reputation by clustering resources having similar capabilities of successfully executing a specific job. Here, trust and reputation are considered as Quality of Service (QoS) parameters, and are asserted on the operative context of resources, a concept expressing the resources capability of providing trusted services within collaborative scientific applications. Specifically, the framework exploits the use of distributed brokers that support interaction trust and the creation of VOs from existing scientific organizations. A broker is a distributed software module launched at some node of the grid that makes use of resources and communicates with other brokers to perform specific reputation services. In turn, each broker contributes to maintain a dynamic and adaptive reputation assessment within the grid in a collaborative and distributed fashion. The proposed framework is empirically implemented by adopting a SOA approach and results show its effectiveness and its possible integration in a scientific grid.
The edge-directed interpolation scheme is a noniterative, orientation-adaptive method to enhance image resolution with better visual effect than conventional interpolation methods. It interpolates the missing pixels b...
详细信息
ISBN:
(纸本)9780769545769
The edge-directed interpolation scheme is a noniterative, orientation-adaptive method to enhance image resolution with better visual effect than conventional interpolation methods. It interpolates the missing pixels based on the covariance of a high-resolution image estimated from the covariance of the low-resolution image. In spite of the impressive performance, the computational complexity of covariance-based adaptation is significantly higher than that of the conventional linear interpolation algorithms. In this paper, we propose a GPU-based massively parallel version of the edge-directed interpolation scheme. A speedup of 61.7x can be achieved with respect to its single-threaded CPU counterpart in the host computer.
With extensive use of Internet of Vehicle (IoV) technologies in vehicle traffic management, real-time analysis of vehicle behavior trajectories is of great significance to the assessment of traffic conditions and the ...
详细信息
ISBN:
(纸本)9781538637906
With extensive use of Internet of Vehicle (IoV) technologies in vehicle traffic management, real-time analysis of vehicle behavior trajectories is of great significance to the assessment of traffic conditions and the avoidance of abnormal conditions. This paper presents a solution which can efficiently deal with real-time streaming data of trajectory and excavate temporal and spatial abnormal information. In order to represent the local feature information of the trajectory and solve the problem of large loss of information in the feature point extraction algorithm, a trajectory partitioning strategy based on multi-motion feature and a similarity measure method based on trajectory structure are proposed. And based on the proposed strategy and method, a distributed clustering algorithm is designed for streaming trajectories to improve the efficiency of clustering algorithm. In order to solve the problem of massive calculation of distance and neighborhood density in trajectory anomaly detection algorithm, the data set is pruned by track clustering results, and the efficiency of the algorithm increases the real-time performance of abnormal trajectory detection.
ILCDIRAC is a complete distributedcomputing solution for the Linear Collider community. It's an extension of the DIRAC system and now used by all detector concepts of the LC community. ILCDIRAC provides a unified...
详细信息
ILCDIRAC is a complete distributedcomputing solution for the Linear Collider community. It's an extension of the DIRAC system and now used by all detector concepts of the LC community. ILCDIRAC provides a unified interface to the distributed resources for the ILC Virtual Organization and provides common interfaces to all ILC applications via a simplified API. It supports the overlay of beam-induced backgrounds with minimal impact on the Storage Elements by properly scheduling the jobs attempting to access the files. ILCDIRAC has been successfully used for the CLIC Conceptual Design Report and the ILC SiD Detailed Baseline Design, and is now adopted by the LC community as the official grid production tool. Members of the CALICE collaboration also use ILCDIRAC within their own Virtual Organization.
暂无评论