The processing time needed by some applications can be reduced if the work is shared between a network of processors rather than being implemented on a single processor. This principle has been applied to a software p...
详细信息
The processing time needed by some applications can be reduced if the work is shared between a network of processors rather than being implemented on a single processor. This principle has been applied to a software package developed to perform radiometric and geometric corrections of NOAA-AVHRR images, a parallel version has been developed and implemented on a ***, a computer made of 64 processors called 'transputers'. The result of this work is described.< >
The symposium materials contain 118 papers on new developments in parallelprocessing. Algorithms, architectures, mapping/scheduling, applications, special-purpose architectures, interconnection networks, software, an...
详细信息
ISBN:
(纸本)0818626720
The symposium materials contain 118 papers on new developments in parallelprocessing. Algorithms, architectures, mapping/scheduling, applications, special-purpose architectures, interconnection networks, software, and distributed systems are among the main topics covered.
Petri nets are a versatile tool for modeling and analyzing parallel and distributed computing systems. However, state explosion is a major impediment to their analysis and practical applications. To cope with this pro...
详细信息
ISBN:
(纸本)0818626720
Petri nets are a versatile tool for modeling and analyzing parallel and distributed computing systems. However, state explosion is a major impediment to their analysis and practical applications. To cope with this problem, this paper proposes a method for constructing hierarchically organized state space (HOSS) of a bounded Petri net. Using the HOSS, we obtain necessary and sufficient conditions for reachability and deadlock, and algorithms to test if a given state (marking) is reachable from the initial state and if there is a deadlock state (a state with no successor states).
Nonreplicated shared data of distributedapplications is optimally allocated to pre-specified multilevel memory partitions at the sites of a heterogeneous multicomputer network to minimize a weighted combination of sy...
详细信息
ISBN:
(纸本)0818626720
Nonreplicated shared data of distributedapplications is optimally allocated to pre-specified multilevel memory partitions at the sites of a heterogeneous multicomputer network to minimize a weighted combination of systemwide mean time delay performance and mean communication cost per access request. Greedy and fast optimization algorithms are presented for nonqueueing lightly-loaded as well as heavily-loaded multiqueue system models with channel, I/O, and memory hierarchy queues. Extensions to data exhibiting nonuniform access demand rates and distinct query and update statistics are presented.
Aroma simplifies the task of parallelizing large applications on multicomputers by providing applications with a shared object space. Aroma supports both traditional monolithic objects and aggregate object that can be...
详细信息
ISBN:
(纸本)0818626720
Aroma simplifies the task of parallelizing large applications on multicomputers by providing applications with a shared object space. Aroma supports both traditional monolithic objects and aggregate object that can be partitioned across multiple nodes. Aggregate objects support data parallelism efficiently. An Aroma program consists of tasks that operate on shared objects. Task typically execute on the node on which their input data is located, thus minimizing communication. Shared data objects have synchronization properties associated with them, making it possible to parallelize a large class of applications without using explicit locks and condition variables. In this paper, we present and justify the Aroma language features, and give examples of Aroma programs. Aroma has been implemented on the Nectar multicomputer and we give performance results for several applications.
We describe the implementation and performance of a three dimensional particle simulation distributed between a Thinking Machines CM-2 and a Cray Y-MP. These are connected by a combination of two high-speed networks;a...
详细信息
A method is described for remotely sensed image segmentation based on the integration of edge detection and region growing approaches. The method is designed for full exploitation of parallelprocessing. The initial e...
详细信息
This paper presents several methods for harmonizing a distributed operating system with parallel and distributedapplications. 'Harmonization' means that the system does not conflict with the parallel/distribu...
详细信息
This paper presents several methods for harmonizing a distributed operating system with parallel and distributedapplications. 'Harmonization' means that the system does not conflict with the parallel/distributedapplications and enables them to control mapping and scheduling for speedup and reliability. In conventional distributed operating systems, one of the most important goals is to achieve network transparency. However, parallel/distributedapplications have to bypass the facilities for network transparency because they require information on the locations and usage of system resources. Harmonization between the system and parallel/distributedapplications are realized by putting some parts of the system into the same position as the applications.< >
Throughout much of the parallelprocessing community there is the sense that writing software for distributed memory parallel processors is subject to a 'no pain-no gain' rule: that in order to reap the benefi...
详细信息
Throughout much of the parallelprocessing community there is the sense that writing software for distributed memory parallel processors is subject to a 'no pain-no gain' rule: that in order to reap the benefits of parallel computation one must first suffer the pain of converting the application to run on a parallel machine. The authors believe this is the result of inadequate programming tools and not a problem inherent to parallelprocessing. They show that one can parallelize real scientific applications and obtain good performance with little effort if the right tools are used. Their vehicle for this demonstration is a six-thousand line DNA and protein sequence comparison application that they have implemented in Mentat, an object-oriented parallelprocessing system for both parallel and distributed architectures. They briefly describe the application and present performance information for both the Mentat version and a hand-coded parallel version of the application.< >
Aroma simplifies the task of parallelizing large applications in multicomputers by providing applications with a shared object space. Aroma supports both traditional monolithic objects and aggregate objects that can b...
详细信息
Aroma simplifies the task of parallelizing large applications in multicomputers by providing applications with a shared object space. Aroma supports both traditional monolithic objects and aggregate objects that can be partitioned across multiple nodes. Aggregate objects support data parallelism efficiently. An Aroma program consists of tasks that operate on shared objects. Tasks typically execute on the node on which their input data is located, thus minimizing communication. Shared data objects have synchronization properties associated with them, making it possible to parallelize a large class of applications without using explicit, locks and condition variables. The authors present and justify the Aroma language features, and give examples of Aroma programs. Aroma has been implemented on the Nectar multicomputer. The authors give performance results for several applications.< >
暂无评论