We consider technique for parallelization of computation with hypercomplex numbers in multidimensional space for signal processing purposes. In particular, parallel algorithms of the multidimensional hypercomplex disc...
详细信息
We consider technique for parallelization of computation with hypercomplex numbers in multidimensional space for signal processing purposes. In particular, parallel algorithms of the multidimensional hypercomplex discrete Fourier transform are developed. Results of their experimental research are shown.
Summary form only given. We evaluate two parallel algorithms for the codebook generation of the VQ compression: parallel LBG and aggressive PNN. parallel LBG is based on the LBG algorithm with the K-mean method. The c...
详细信息
Summary form only given. We evaluate two parallel algorithms for the codebook generation of the VQ compression: parallel LBG and aggressive PNN. parallel LBG is based on the LBG algorithm with the K-mean method. The cost of both latter algorithms mainly consists of: a) the computation part; b) the communication part; and c) the update part. Aggressive PNN is a parallelized version of the PNN (pairwise nearest neighbor) algorithm, whose cost mainly consists of: a) the computation part; b) the communication part; and c) the merge part. We measured the speedups and elapsed times of both algorithms on a PC cluster system. When the quality of images compressed by both algorithms is the same, the number of training vectors required by the aggressive PNN is much less than that by the parallel LBG, and the aggressive PNN is superior in terms of the elapsed time.
The shortest-paths problem is a fundamental problem in graph theory and finds diverse applications in various fields. This is why shortest path algorithms have been designed more thoroughly than any other algorithm in...
详细信息
The shortest-paths problem is a fundamental problem in graph theory and finds diverse applications in various fields. This is why shortest path algorithms have been designed more thoroughly than any other algorithm in graph theory. A large number of optimization problems are mathematically equivalent to the problem of finding shortest paths in a graph. The shortest-path between a pair of vertices is defined as the path with shortest length between the pair of vertices. The shortest path from one vertex to another often gives the best way to route a message between the vertices. This paper presents an O(n(2)) time sequential algorithm and an O(n(2)/p + log n) time parallel algorithm on EREW PRAM model for solving all pairs shortest paths problem on circular-arc graphs, where p and n represent respectively the number of processors and the number of vertices of the circular-arc graph.
We explore the possibility of using multiple processors to improve the encoding and decoding times of Lempel-Ziv schemes. A new layout of the processors, based on a full binary tree, is suggested and it is shown how L...
详细信息
We explore the possibility of using multiple processors to improve the encoding and decoding times of Lempel-Ziv schemes. A new layout of the processors, based on a full binary tree, is suggested and it is shown how LZSS and LZW can be adapted to take advantage of such parallel architectures. The layout is then generalized to higher order trees. Experimental results show an improvement in compression over the standard method of parallelization and an improvement in time over the sequential method. (C) 2004 Elsevier B.V. All rights reserved.
A sea change within the computing discipline occurred last year which is not widely recognized nor fully understood. Individual processor chips are not going to be faster in the future. The implications of this fact a...
详细信息
A sea change within the computing discipline occurred last year which is not widely recognized nor fully understood. Individual processor chips are not going to be faster in the future. The implications of this fact are discussed and changes to the undergraduate computing curriculum are proposed.
In this paper, we first demonstrate that the classical Purcell's vector method when combined with row pivoting yields a consistently small growth factor in comparison to the well-known Gauss elimination method, th...
详细信息
In this paper, we first demonstrate that the classical Purcell's vector method when combined with row pivoting yields a consistently small growth factor in comparison to the well-known Gauss elimination method, the Gauss-Jordan method and the Gauss-Huard method with partial pivoting. We then present six parallel algorithms of the Purcell method that may be used for direct solution of linear systems. The algorithms differ in ways of pivoting and load balancing. We recommend algorithms V and VI for their reliability and algorithms III and IV for good load balance if local pivoting is acceptable. Some numerical results are presented. (C) 2002 Elsevier Science B.V. All rights reserved.
One of the fundamental components of large-scale gene discovery projects is that of clustering of expressed sequence tags (ESTs) from complementary DNA (cDNA) clone libraries. Clustering is used to create non-redundan...
详细信息
One of the fundamental components of large-scale gene discovery projects is that of clustering of expressed sequence tags (ESTs) from complementary DNA (cDNA) clone libraries. Clustering is used to create non-redundant catalogs and indices of these sequences. In particular, clustering of ESTs is frequently used to estimate the number of genes derived from cDNA-based gene discovery efforts. This paper presents a novel parallel extension to an EST clustering program, UIcluster4, that incorporates alternative splicing information and a new parallelization strategy. The results are compared to other parallelized EST clustering systems in terms of overall processing time and in accuracy of the resulting clustering. (c) 2004 Published by Elsevier B.V.
A significant research effort has been devoted in recent years to the design of simple and efficient scheduling algorithms for input-queued packet switches. Among these algorithms, scheduling policies based on Maximum...
详细信息
ISBN:
(纸本)076952432X
A significant research effort has been devoted in recent years to the design of simple and efficient scheduling algorithms for input-queued packet switches. Among these algorithms, scheduling policies based on Maximum Weight Matching (MWM) were proved to achieve 100% throughput under any admissible traffic load. However, MWM is impractical for its high computational complexity O(N-3). In this paper, we propose a new approximate algorithm to MWM using local search technique. Notably we observe that: (a) Local search is well suitable for parallel computation. (b) Currently each line card of high performance router has at least one processor. Based on the two important observations, a randomized parallel scheduling algorithm is proposed It is proved to be rate stable and simulation results show that the proposed algorithm outperforms other randomized approximations to MWM.
Aligning long DNA sequences is a fundamental and common task in molecular biology. Though dynamic programniing algorithms have been developed to solve this problem, the space and time required by these algorithms are ...
详细信息
ISBN:
(纸本)3540287000
Aligning long DNA sequences is a fundamental and common task in molecular biology. Though dynamic programniing algorithms have been developed to solve this problem, the space and time required by these algorithms are still a challenge. In this paper we present the parallel Linear Space Alignment (PLSA) algorithm to compute the long sequence alignment to meet this challenge. Using this algorithm, the local start points and grid cache partition the whole sequence alignment problem into several smaller independent subproblems. A novel dynamic load balancing approach then efficiently solves these subproblems in parallel, which provides more parallelism in the trace-back phase. Furthermore, PLSA helps to find k near-optimal non-intersecting alignments. Our experiments show that this proposed algorithm scales well with the increasing number of processors, and it exhibits almost linear speedup for large-scale sequences.
This paper presents the Optimality Theorem in distributed parallel environment. Based on this theorem, a parallel algorithm using network-tree model is presented to compute shortest paths in large-scale networks. The ...
详细信息
ISBN:
(纸本)3540260447
This paper presents the Optimality Theorem in distributed parallel environment. Based on this theorem, a parallel algorithm using network-tree model is presented to compute shortest paths in large-scale networks. The correctness of this algorithm is proved theoretically and a series of computational test problems are performed on PC cluster. Factors such as network size and level of the network, which stake effect on the performance, are discussed in detail. Results of the experiments show that the proposed parallel algorithm is efficient in computing shortest paths in large-scale networks, especially when the network size is great.
暂无评论