Element-by-element vector and parallel computations. (English) Zbl 0638.73042
Vector and parallel algorithms for finite-element analysis using the element-by-element (EBE) data structure are developed. The algorithms are based on the EBE approach in conjunction with gradient-type iterative solution. The essential idea is to exploit the independent dense local- element matrix-vector calculations and reconfigure them to take advantage of vector or parallel processing capabilities. The ideas also are well suited to finite-element adaptive refinement computations. Specific algorithmic details related to the implementations are given, together with results of speed-up performance studies conducted on the vector and parallel architectures. The basic vector and parallel versions of the matrix-vector product for the EBE scheme are very straightforward modifications of the EBE algorithm, requiring little coding change.
MSC:
| 74S05 | Finite element methods applied to problems in solid mechanics |
| 74-04 | Software, source code, etc. for problems pertaining to mechanics of deformable solids |
| 65Y05 | Parallel numerical computation |
Keywords:
vector calculation; element-by-element (EBE) data structure; gradient- type iterative solution; independent dense local-element matrix-vector calculations; parallel processing; finite-element adaptive refinementReferences:
| [1] | and , Finite Elements: Computational Aspects, Prentice-Hall, Englewood Cliffs, 1984. · Zbl 0558.73064 |
| [2] | Hughes, Comp. Methods Appl. Mech. Eng. 36 pp 241– (1983) |
| [3] | Carey, Commun. appl. numer. methods 2 pp 145– (1986) |
| [4] | Hayes, Int. j. numer. methods eng. 23 pp 1043– (1986) |
| [5] | Jiang, Int. j. numer. methods eng. 24 pp 569– (1987) |
| [6] | Oden, Comp. Methods Appl. Mech. Eng. 59 pp 327– (1986) |
| [7] | and , ’Semiconductor device simulation using adaptive refinement and streamline upwinding’, Submitted to the I.E.E.E. Trans. on Computer Aided Design, 1988. |
| [8] | ’Advances and trends in element-by-element techniques’, In State-of-the-Art Surveys on Computational Mechanics, (Ed.), ASME Winter Annual Meeting, Anaheim, CA, 1986. |
| [9] | Winget, Comp. Methods Appl. Mech. Eng. 52 pp 711– (1985) |
| [10] | Carey, Commun. appl. numer. methods 2 pp 281– (1986) |
| [11] | Hestenes, J. Res. Natn. Bur. Stand. 49 pp 409– (1952) · Zbl 0048.09901 · doi:10.6028/jres.049.044 |
| [12] | and , Applied Iterative Methods, Academic Press, New York, 1981. · Zbl 0459.65014 |
| [13] | and , ’A refinement algorithm and dynamic data structure for finite element meshes’, Report TR-166, Center for Numerical Analysis, University of Texas at Austin, 1980. |
| [14] | Adams, Commun. appl. numer. methods 2 pp 263– (1986) |
| [15] | Babuska, SIAM J. Numer. Anal. 15 pp 736– (1978) |
| [16] | Courant, Bull. Am. Math. Soc. 49 pp 1– (1943) |
| [17] | Duff, Parallel Com. 3 pp 193– (1986) |
| [18] | ’Conjugate gradient methodss for indefinite systems’, In Lecture Notes in Mathematics, Vol. 506, Springer-Verlag, 1976, pp. 73-89. |
| [19] | Fox, Phys. Today 37 pp 50– (1984) |
| [20] | Gannon, IEEE Trans. Comp. C-33 pp 1180– (1984) |
| [21] | Glowinski, Comp. Method. Appl. Mech. Eng. 40 pp 27– (1983) |
| [22] | and . ’An element-by-element block iterative method for large nonlinear problems’, In Innovative Methods for Nonlinear Behaviour, ( et al., eds.), Pineridge Press, Swansea, 1985, pp. 51-62. |
| [23] | Kincaid, Commun. appl. numer. methods 2 pp 289– (1986) |
| [24] | McBryan, Commun. Pure Appl. Math. 28 pp 769– (1985) |
| [25] | Meier, Parallel Comp. 2 pp 33– (1985) |
| [26] | (Ed), Impact of New Computing Systems on Computational Mechanics, ASME, New York, 1983. |
| [27] | Rodrigue, Commun. appl. numer. methods 3 pp 245– (1986) |
| [28] | Seager, Commun. appl. numer. methods 2 pp 273– (1986) |
| [29] | ’Where are the parallel algorithms’, ICASE Report 85-2, NASA, Langley, 1985. |
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.
