|
1. |
A GENERALIZED MAPPING OF 2-D ARRAY PROCESSOR TO LINEAR ARRAY PROCESSOR AND ITS APPLICATIONS |
|
Parallel Algorithms and Applications,
Volume 6,
Issue 4,
1995,
Page 241-257
KUO-LIANG CHUNG,
R. C. T. LEE,
YU-CHIH LIN,
Preview
|
PDF (254KB)
|
|
摘要:
In a previous paper [14], Yang and Lee showed a mapping method which maps a 2-dimensional single-wavefront array processor to a linear array processor if there is only one wavefront propagating and never backtracks. In this paper, we shall discuss a more general case where the wavefront activates only a limited part of each diagonal. The mapping method which is more general than that given by Yang and Lee is presented here. We then show how this mapping can be applied to synthesize the stereo-matching algorithm on a linear array processor, where the number of processors depends upon the bandwidth of the wavefront.
ISSN:1063-7192
DOI:10.1080/10637199508915513
出版商:Taylor & Francis Group
年代:1995
数据来源: Taylor
|
2. |
A CONSTANT TIME ALGORITHM FOR THE CHANNEL ASSIGNMENT PROBLEM USING THE RECONFIGURABLE MESH |
|
Parallel Algorithms and Applications,
Volume 6,
Issue 4,
1995,
Page 259-271
MARKS. MERRY,
JOHNNIE BAKER,
Preview
|
PDF (249KB)
|
|
摘要:
A constant lime algorithm is given for the reconfigurable mesh which uses are-configurable mesh to solve the channel assignment problem involvingnintervals. To accomplish this, an algorithm is given which creates a linked list ofnitems in a reconfigurable mesh of size.
ISSN:1063-7192
DOI:10.1080/10637199508915514
出版商:Taylor & Francis Group
年代:1995
数据来源: Taylor
|
3. |
PARALLEL ALGORITHMS FOR FOURTH-ORDER PARABOLIC EQUATIONS |
|
Parallel Algorithms and Applications,
Volume 6,
Issue 4,
1995,
Page 273-286
M. A. ARIGU,
E. H. TWIZELL,
A. B. GUMEL,
Preview
|
PDF (192KB)
|
|
摘要:
Parallel numerical algorithms are presented for the solution of Fourth-order parabolic equations. The algorithms are tested on three problems with time-dependent and time-independent boundary conditions.
ISSN:1063-7192
DOI:10.1080/10637199508915515
出版商:Taylor & Francis Group
年代:1995
数据来源: Taylor
|
4. |
MONITORING THE CONVERGENCE OF THE LANCZOS ALGORITHM IN PARALLEL COMPUTING ENVIRONMENTS |
|
Parallel Algorithms and Applications,
Volume 6,
Issue 4,
1995,
Page 287-302
M. SZULARZ,
J. WESTON,
K. MURPHY,
M. CLINT,
Preview
|
PDF (287KB)
|
|
摘要:
The Lanczos algorithm is one of the most efficient methods for finding a small number of extreme eigenvalues and corresponding eigenvectors of large, sparse, symmetric matrices. In order to monitor its convergence the algorithm is usually supplemented with a routine which incorporates the computation of partial eigensolutions of the tridiagonal matrices generated successively by the method. In this paper a new convergence monitoring routine which avoids the computation of these partial eigensolutions is proposed. In this routine approximations to the required eigenvalues are computed at each stage, the accuracy of which increase as the Lanczos method progresses. This sequence of approximations converges onto the required eigenvalues with the added advantage that no eigensolution of the final matrix is required. The Lanczos algorithm with complete reorthogonalization and with the new convergence monitoring routine has been implemented on a shared memory Convex C3840 with two processors, and on a 16-node Intel iPSC/860 hypercube. The test results show that the new convergence monitor improves the performance of the Lanczos algorithm on a single processor substantially; that it can gainfully exploit the facilities of the shared memory machine; but does not improve significantly the performance of the Lanczos algorithm on the distributed memory machine.
ISSN:1063-7192
DOI:10.1080/10637199508915516
出版商:Taylor & Francis Group
年代:1995
数据来源: Taylor
|
5. |
A PARALLEL SCHEDULING ALGORITHM FOR PARALLEL APPLICATIONS |
|
Parallel Algorithms and Applications,
Volume 6,
Issue 4,
1995,
Page 303-316
MUSLIM BOZYIGIT,
AMINA. ABDULGHANI,
Preview
|
PDF (219KB)
|
|
摘要:
In this work, a parallel scheduling algorithm for scheduling a set ofnpartially ordered tasks on anm-processor parallel computing system is studied. The method is based on a conventional list scheduling, in particular, an earliest-task-first approach. Otherwise, the algorithm developed is an original algorithm. It is designed for a hypercube type system and is tested on a Transputer based environment, The time complexity of the algorithm isO(n(logn + logm)). The parallel scheduling algorithm produces the same schdules as its sequential counterpart whose complexity isO(mn2(logn + logm)), but in a shorter time.
ISSN:1063-7192
DOI:10.1080/10637199508915517
出版商:Taylor & Francis Group
年代:1995
数据来源: Taylor
|
|