We discuss the efficient implementation of a collective operation called reduce-scatter, which is defined in the MPI standard. The reduce-scatter is equivalent to the combination of a reduction on vectors of length n ...
详细信息
We discuss the efficient implementation of a collective operation called reduce-scatter, which is defined in the MPI standard. The reduce-scatter is equivalent to the combination of a reduction on vectors of length n with a scatter of the resulting n-vector to all processors. We describe the implementation issues and the performance characterization of two recently proposed algorithms for the reduce-scatter that have been proven to be highly efficient in theory under the assumption of fully connected parallel system. A performance comparison with existing mainstream implementations of the operation is presented which confirms the practical advantage of the new algorithms. Experiments show that the two algorithms have different characteristics which make them complementary in providing a performance gain over standard algorithms. Our study has been carried out on two different platforms: an SP2 and a Myrinet interconnected cluster of Pentium PRO. However, most of the results reported here are not specific for either MPI or the platforms used, and they hold in general for any message passing programming system. (C) 2003 Elsevier B.V. All rights reserved.
The central contribution of this work is SAMBA (Single Application, Multiple Load Balancing), a framework for the development of parallel SPMD (single program, multiple data) applications with load balancing. This fra...
详细信息
The central contribution of this work is SAMBA (Single Application, Multiple Load Balancing), a framework for the development of parallel SPMD (single program, multiple data) applications with load balancing. This framework models the structure and the characteristics common to different SPMD applications and supports their development. SAMBA also contains a library of load balancing algorithms. This environment allows the developer to focus on the specific problem at hand. Special emphasis is given to the identification of appropriate load balancing strategies for each application. Three different case studies were used to validate the functionality of the framework: matrix multiplication, numerical integration, and a genetic algorithm. These applications illustrate its ease of use and the relevance of load balancing. Their choice was oriented by the different load imbalance factors they present and by their different task creation mechanisms. The computational experiments reported for these case studies made possible the validation of SAMBA and the comparison, without additional reprogramming costs, of different load balancing strategies for each of them. The numerical results and the elapsed times measurements show the importance of using an appropriate load balancing algorithm and the associated reductions that can be achieved in the elapsed times. They also illustrate that the most suitable load balancing strategy may vary with the type of application and with the number of available processors. Besides the support to the development of SPMD applications, the facilities offered by SAMBA in terms of load balancing play also an important role in terms of the development of efficient parallel implementations. (C) 2003 Elsevier Science B.V. All rights reserved.
An AB 2 operation is known as an efficient basic operation for public key cryptosystems over GF(2(m)), and various systolic arrays for performing AB(2) operations have already been proposed using a standard basis repr...
详细信息
An AB 2 operation is known as an efficient basic operation for public key cryptosystems over GF(2(m)), and various systolic arrays for performing AB(2) operations have already been proposed using a standard basis representation. However, these circuits have certain shortcomings for cryptographic application due to their high circuit complexity and long latency. Therefore, further research on an efficient AB(2) multiplication circuit is still needed. Accordingly, the authors present a new AB(2) algorithm and its systolic realisations in GF(2(m)). First, a new algorithm is proposed based on the MSB-first scheme using a standard basis representation. Thereafter, bitparallel and bit-serial systolic power multipliers are derived that exhibit a lower hardware complexity and smaller latency than conventional approaches. In addition, since the proposed architectures incorporate simplicity, regularity, modularity, and pipelinability, they are well suited to VLSI implementation and can be easily applied as a basic architecture for computing an inverse/ division operation and in crypto-processor chip design.
Data-parallel algorithms are presented for polygonizing a collection of line segments represented by a data-parallel bucket PMR quadtree, a data-parallel R-tree, and a data-parallel R+-tree. Such an operation is usefu...
详细信息
This paper solves the NP problem of DNA string matching using heuristics and parallelism. The current methods for approximate matching are merely different versions of dynamic programming. Dynamic programming is O(n2)...
详细信息
ISBN:
(纸本)1892512416
This paper solves the NP problem of DNA string matching using heuristics and parallelism. The current methods for approximate matching are merely different versions of dynamic programming. Dynamic programming is O(n2), and does not consider one of the most important areas in technology: parallelism. The proposed algorithm uses parallelism to solve approximate matching. It has a best-case time complexity of O(n), and has better performance in practice than dynamic programming.
in this article, we present a solution to the maximum clique problem using a gradient-ascent learning algorithm of the Hopfield neural network. This method provides a near-optimum parallel algorithm for finding a maxi...
详细信息
in this article, we present a solution to the maximum clique problem using a gradient-ascent learning algorithm of the Hopfield neural network. This method provides a near-optimum parallel algorithm for finding a maximum clique. To do this, we use the Hopfield neural network to generate a near-maximum clique and then modify weights in a gradient-ascent direction to allow the network to escape from the state of near-maximum clique to maximum clique or better. The proposed parallel algorithm is tested on two types of random graphs and some benchmark graphs from the Center for Discrete Mathematics and Theoretical Computer Science (DIMACS). The simulation results show that the proposed learning algorithm can find good solutions in reasonable computation time.
This paper describes a new parallel algorithm for solving multiphysics problems. These kind of problems are very demanding in terms of CPU time and memory space, which are typically not available on a single processor...
详细信息
For a positive integer c, a c-vertex-ranking of a graph G = (V,E) is a labeling of the vertices of G with integers such that, for any label i, deletion of all vertices with labels > i leaves connected components, e...
详细信息
Let G be a graph with n vertices and m edges. The problem of constructing a spanning tree is to find a connected subgraph of G with n vertices and n - 1 edges. In this paper, we propose an O(log n) time parallel algor...
详细信息
Let G be a graph with n vertices and m edges. The problem of constructing a spanning tree is to find a connected subgraph of G with n vertices and n - 1 edges. In this paper, we propose an O(log n) time parallel algorithm with O(n/log n) processors on an EREW PRAM for constructing a spanning tree on trapezoid graphs.
In this paper, we present a parallel algorithm for medial axis transformation, which is based on the parallel distance transformation presented in [1]. We first modify the parallel distance transformation as described...
详细信息
暂无评论