This paper describes an implementation for Shared Memory Multiprocessor of a parallel algorithm to extract all cycles from a graph, using the cyclic conjunction operator. Validation of the parallel code was done using...
详细信息
The B-tree is a fundamental data structure that is used to access and update a large number of keys. In this paper we present a parallel algorithm on the EREW PRAM that deletes keys in a B-tree. Our algorithm runs in ...
详细信息
The paper describes a new stochastic heuristic algorithm for global optimization. The new optimization algorithm, called Intelligent-Particle Swarm Optimization (IPSO), offers more intelligence to particles by using c...
详细信息
The paper describes a new stochastic heuristic algorithm for global optimization. The new optimization algorithm, called Intelligent-Particle Swarm Optimization (IPSO), offers more intelligence to particles by using concepts such as: group experiences, unpleasant memories (tabu to be avoided), local landscape models based on virtual neighbors, and memetic replication of successful behavior parameters. The new individual complexity is amplified at the group level and consequently generates a more efficient optimization procedure. A simplified version of the IPSO algorithm was implemented and compared with the classical PSO algorithm for a simple test function and for the Loney's solenoid.
The main objective of this work is to highlight the advantages of coupling Java FDTD implementation with the mobile-agent computing paradigm, and to promote this approach as a flexible and valuable tool for the distri...
详细信息
The main objective of this work is to highlight the advantages of coupling Java FDTD implementation with the mobile-agent computing paradigm, and to promote this approach as a flexible and valuable tool for the distributed solution of complex and large-scale problems. Therefore, we present key issues related to the distributed implementation of a Finite-Difference Time-Domain (FDTD) code using Java mobile agents. The Java object-oriented FDTD code is described, and special agent communication and synchronization aspects related to FDTD are presented in detail.
A parallelised max-Log-MAP model (P-max-Log-MAP) that exploits the sub-word parallelism and very long instruction word architecture of a microprocessor or a digital signal processor (DSP) is presented. The proposed mo...
详细信息
A parallelised max-Log-MAP model (P-max-Log-MAP) that exploits the sub-word parallelism and very long instruction word architecture of a microprocessor or a digital signal processor (DSP) is presented. The proposed model reduces considerably the computational complexity of the max-Log-MAP algorithm;and therefore facilitates easy implementation.
The exponential increase in expressed sequence tag (EST) sequence data amplifies the computational cost of clustering sequences such that new algorithms are required to analyze data at a greater rate. We have pa-ralle...
详细信息
The exponential increase in expressed sequence tag (EST) sequence data amplifies the computational cost of clustering sequences such that new algorithms are required to analyze data at a greater rate. We have pa-rallelized d2-cluster on a SGI Origin 2000 multiprocessor and observed a speedup of approximately 100X on 126 processors when processing a 15,876 EST dataset. The parallelized d2-cluster code is obtainable from the SANBI website (http://w,A,***/CODES).
In order to understand details in the seismic wave field observed on regional and global scales on the Earth's surface accurate modeling of 3D wave propagation is necessary. While numerical techniques are now rout...
详细信息
In order to understand details in the seismic wave field observed on regional and global scales on the Earth's surface accurate modeling of 3D wave propagation is necessary. While numerical techniques are now routinely applied to local seismic wave propagation, only recently has the possibility of simulating wave propagation on larger scales in spherical geometry been investigated. We apply a high-order staggered-grid finite-difference scheme to the elastic wave equations in spherical coordinates [phi, theta, r]. Using regular grid spacing in a single domain the physical space is limited to spherical sections which do not include the axis theta = 0. While the staggering of the space-dependent fields improves the overall accuracy of the scheme, some of the tensor elements have to be interpolated to the required grid locations. By comparing with quasi-analytical solutions for layered Earth models we demonstrate the accuracy of the algorithm. Finally, the technique is used to study the effects of a source located in a simplified slab structure. The 3D technique will allow us to study the wave field due to laterally heterogeneous structures, such as subduction zones, plumes or oceanic ridges. (C) 2002 Elsevier Science B.V. All rights reserved.
Time optimal algorithms on an n-processor BSR PRAM for many n-size problems can be found in the literature. They outpace those on EREW, CREW or CRCW PRAM for the same problems. When only p (1 < p < n) processors...
详细信息
Time optimal algorithms on an n-processor BSR PRAM for many n-size problems can be found in the literature. They outpace those on EREW, CREW or CRCW PRAM for the same problems. When only p (1 < p < n) processors are available, efficient algorithms on a p-processor BSR for some n-size problems can not be obtained from those on an n-processor BSR, and they have to be reconsidered. In this paper, we discuss and give two algorithms on a p-processor BSR for the two n-size problems of matching parentheses and decoding a binary tree from its bit-string, respectively, and show that they are time optimal.
The paper analyzes the performance of parallel global optimization algorithm, which is used to optimize grillage-type foundations. The parallel algorithm is obtained by using the automatic parallelization tool. We des...
详细信息
The paper analyzes the performance of parallel global optimization algorithm, which is used to optimize grillage-type foundations. The parallel algorithm is obtained by using the automatic parallelization tool. We describe briefly the layer structure of the Master-Slave Template library and present a detailed mathematical formulation of the application problem. Experiments are done on the homogeneous computer cluster of 7 IBM machines RS6000. The results of experiments are presented.
A suite of scalable atomistic simulation programs has been developed for materials research based on space-time multiresolution algorithms. Design and analysis of parallel algorithms are presented for molecular dynami...
详细信息
A suite of scalable atomistic simulation programs has been developed for materials research based on space-time multiresolution algorithms. Design and analysis of parallel algorithms are presented for molecular dynamics (MD) simulations and quantum-mechanical (QM) calculations based on the density functional theory. Performance tests have been carried out on 1,088-processor Cray T3E and 1,280-processor IBM SP3 computers. The linear-scaling algorithms have enabled 6.44-billion-atom MD and 111,000-atom QM calculations on 1,024 SP3 processors with parallel efficiency well over 90%. The production-quality programs also feature wavelet-based computational-space decomposition for adaptive load balancing, spacefilling-curve-based adaptive data compression with user-defined error bound for scalable I/O, and octree-based fast visibility culling for immersive and interactive visualization of massive simulation data.
暂无评论