This paper focuses on the analytical performance analysis of P fault-prone processors that are running a job consisting of N independent tasks in parallel. All the tasks are assumed to have the same running time. We u...
详细信息
ISBN:
(纸本)1892512459
This paper focuses on the analytical performance analysis of P fault-prone processors that are running a job consisting of N independent tasks in parallel. All the tasks are assumed to have the same running time. We use a discrete Markov model for the analysis of the system. Assuming that there is no arrival process for tasks, the performance parameters that we calculate are conditioned on the job finishing successfully. We also assume that all the processors can fail but if the number of tasks is less than the number of processors, then the idle processors cannot fail. We will derive expressions for the mean execution time and the probability of success of a job. The results will be presented as probability distributions and graphs. Finally, we will compare our results with a similar system of processors running tasks having exponentially distributed times, as reported in [1].
Tool Gear is a software infrastructure for developing performance analysis and other tools. Unlike existing integrated toolkits, which focus on providing a suite of capabilities, Tool Gear is designed to help toot dev...
详细信息
ISBN:
(纸本)1892512459
Tool Gear is a software infrastructure for developing performance analysis and other tools. Unlike existing integrated toolkits, which focus on providing a suite of capabilities, Tool Gear is designed to help toot developers create new tools quickly. It combines dynamic instrumentation capabilities with an efficient database and a sophisticated and extensible graphical user interface. This paper describes the design of Tool Gear and presents examples of tools that have been built with it.
Considering a nonsingular mapping S : [0, 1] --> [0, 1] and the corresponding Frobenius-Perron operator, let P : L-1 (0, 1) --> L-1 (0, 1). In this paper we present the theoretic efficiency analysis of the two p...
详细信息
ISBN:
(纸本)1932415262
Considering a nonsingular mapping S : [0, 1] --> [0, 1] and the corresponding Frobenius-Perron operator, let P : L-1 (0, 1) --> L-1 (0, 1). In this paper we present the theoretic efficiency analysis of the two parallel algorithms to implement Ulam's method for the computation of a fixed density of P. The results are applied to the first-order digital phase locked loop (DPLL). Numerical results are presented and efficiency comparison of the two parallel algorithms is included.
The intrinsic goal of any operating system (OS) is to free the application level from tasks that are either repeating or hard to accomplish. In the 80s and 90s there have been strong efforts to develop distributed OS ...
详细信息
ISBN:
(纸本)1932415610
The intrinsic goal of any operating system (OS) is to free the application level from tasks that are either repeating or hard to accomplish. In the 80s and 90s there have been strong efforts to develop distributed OS providing fully location transparency. Although these projects delivered valuable results on certain aspects of distributed computing, satisfactory general purpose distributed resource management at the OS level could not be achieved. We argue that the performance gap between local and remote operation is the major obstacle for truly transparent distributed resource management. This performance gap can only be bridged with significantly increased flexibility at the OS level. At the same time constant overhead must be avoided.
As parallel and distributed computing environments, like the PC cluster or the GRID, become more popular, high performance parallel and distributed programs become increasingly more necessary. Within the family of suc...
详细信息
ISBN:
(纸本)1892512459
As parallel and distributed computing environments, like the PC cluster or the GRID, become more popular, high performance parallel and distributed programs become increasingly more necessary. Within the family of such programs, those that are based on message-passing are frequently characterized by unpredictable delays in message arrival times, which lead to significant differences in program performance. This paper reports the development of a simulator that measures program performance under parallel and distributed computing environments with variable parameters. Also, two types of numerical experiments are presented: one that was conducted on a program of matrix multiplication whose performance does not depend as much on communication delays and another experiment conducted on a program of branch and bound technique whose performance is more dependent on communication delays. Both experiments were performed in the simulator presented here, as well as in a real PC cluster environment. Through these numerical experiments, the effectiveness and problems of the simulator are discussed.
A significant disadvantage of fully homomorphic encryption is the long periods of time needed to process encrypted data, due to its complex and CPU-intensive arithmetic techniques. In this paper, a communication proto...
详细信息
ISBN:
(纸本)9781538637906
A significant disadvantage of fully homomorphic encryption is the long periods of time needed to process encrypted data, due to its complex and CPU-intensive arithmetic techniques. In this paper, a communication protocol is developed to ensure authenticity, integrity and privacy of measurement data across a distributed measuring system. The fully homomorphic encryption library LibScarab was extended by integer arithmetics, comparisons, decisions and multithreading to secure data processing. Furthermore, it enhances 32 and 64-bit arithmetic operations, improving them by a higher factor. This extension is integrated into a cloud computing architecture establishing privacy by design. The resulting parallelized algorithm solved the time constraint issues for smart meter gateway tariffs. Several tests were performed, fulfilling tariff specifications, where preserving privacy of accumulated data was necessary. It was concluded that this extension of the fully homomorphic encryption library meets the requirements of real world applications.
Today, more than ever, monitoring and surveillance systems play an important role in many aspects of our lives. Technology plays a vital role in our efforts to create, store and analyze vast amounts of data for both s...
详细信息
ISBN:
(纸本)1932415610
Today, more than ever, monitoring and surveillance systems play an important role in many aspects of our lives. Technology plays a vital role in our efforts to create, store and analyze vast amounts of data for both security and commercial purposes. In this paper, we propose an application which combines research performed in computer networks, multimedia databases and computer vision. We consider the problem where a number of networks are interconnected. Each of the individual nodes (networks) are collecting, processing and storing data from several sensors (cameras). Specifically, we emphasize on how the data (images) are processed by the individual nodes and how the information is transmitted, so that queries involving multiple nodes can be answered. During this process, we also identify several challenges related to sharing voluminous content provided by visual surveillance devices.
Cluster environment these days is gaining recognition in equivalence to complex parallel machines. This provides environment to utilize distributed resources in an efficient way. Complex applications can be run on clu...
详细信息
ISBN:
(纸本)1892512459
Cluster environment these days is gaining recognition in equivalence to complex parallel machines. This provides environment to utilize distributed resources in an efficient way. Complex applications can be run on clusters and at the same time have advantage of the power of high-end machines due to the availability of resources in multiples across the cluster. In order to provide transparency in data location we need some kind of interface, which would provide access to data that has been distributed across the nodes. parallel File System for Intel Networked Work-stations (PFSNIW) is one such parallel file system that has been developed by a team in Indian Institute of Technology, Bombay. In this paper we are discussing the effect of different network parameters on the performance of PFSNIW. We also discuss the results of the experiments that have been conducted to get optimal values for different parameters that influence the performance of the file system.
The ParaStation communication fabric provides a high-speed communication network with user-level access to enable efficient parallel computing on workstation clusters. The architecture, implemented on off-the-shelf wo...
详细信息
The ParaStation communication fabric provides a high-speed communication network with user-level access to enable efficient parallel computing on workstation clusters. The architecture, implemented on off-the-shelf workstations coupled by the ParaStation communication hardware, removes the kernel and common network protocols from the communication path while still providing full protection in a multiuser, multiprogramming environment. The programming interface presented by ParaStation consists of a UNIX socket emulation and widely used parallel programming environments such as PVM, P4, and MPI. This allows porting a wide range of client/server and parallelapplications to the ParaStation architecture. Implementations of ParaStation using various platforms, such as Digital's AlphaGeneration workstations and Linux PCs, achieve end-to-end (process-to-process) latencies as low as 2 mu s and a sustained bandwidth of up to 15 Mbyte/s per channel with small packets. Benchmarks using PVM on ParaStation demonstrate real application performance of 1 GFLOP on an 8-node cluster. (C) 1998 Elsevier Science Inc. All rights reserved.
distributed shared memory systems have become popular as a means of utilizing clusters of computers for solving large applications. We have developed a high-performance DSM at Wayne State University. To improve the pe...
详细信息
ISBN:
(纸本)1892512459
distributed shared memory systems have become popular as a means of utilizing clusters of computers for solving large applications. We have developed a high-performance DSM at Wayne State University. To improve the performance of our DSM, we have developed a memory hierarchy simulator that allows us to compare various techniques very quickly and with much less effort. This paper describes our simulator, DSMSim. We show that the simulator's Performance closely matches the real system and demonstrate potential performance gains of up to 60 percent after adding optimization features to the simulator. The simulator also accepts the same code as the Software distributed Shared Memory.
暂无评论