{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,4]],"date-time":"2024-09-04T22:51:06Z","timestamp":1725490266128},"publisher-location":"Berlin, Heidelberg","reference-count":37,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783540656418"},{"type":"electronic","value":"9783540491644"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[1999]]},"DOI":"10.1007\/3-540-49164-3_13","type":"book-chapter","created":{"date-parts":[[2007,8,29]],"date-time":"2007-08-29T03:36:46Z","timestamp":1188358606000},"page":"127-139","source":"Crossref","is-referenced-by-count":0,"title":["Blocking Techniques in Numerical Software"],"prefix":"10.1007","author":[{"given":"Wilfried N.","family":"Gansterer","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dieter F.","family":"Kvasnicka","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Christoph W.","family":"Ueberhuber","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[1999,2,26]]},"reference":[{"key":"13_CR1","volume-title":"Lapack Users\u2019 Guide","author":"E. Anderson","year":"1995","unstructured":"E. Anderson et al., Lapack Users\u2019 Guide, 2nd ed., SIAM Press, Philadelphia, 1995.","edition":"2nd ed."},{"key":"13_CR2","doi-asserted-by":"publisher","first-page":"340","DOI":"10.1145\/263580.263662","volume-title":"Proceedings of the International Conference on Supercomputing","author":"J. Bilmes","year":"1997","unstructured":"J. Bilmes, K. Asanovic, C.-W. Chin, J. Demmel, Optimizing Matrix Multiply using PhiPac: a Portable, High-Performance, ANSI C Coding Methodology, Proceedings of the International Conference on Supercomputing, ACM, Vienna, Austria, 1997, pp. 340\u2013347."},{"key":"13_CR3","doi-asserted-by":"crossref","unstructured":"J. Bilmes, K. Asanovic, J. Demmel, D. Lam, C.-W. Chin, Optimizing Matrix Multiply using PhiPac: a Portable, High-Performance, ANSI C Coding Methodology, Technical report, Lapack Working Note 111, 1996.","DOI":"10.1145\/263580.263662"},{"key":"13_CR4","doi-asserted-by":"publisher","first-page":"23","DOI":"10.1109\/SHPCC.1994.296622","volume-title":"Proceedings of the Scalable High-Performance Computing Conference","author":"C.H. Bischof","year":"1994","unstructured":"C.H. Bischof, B. Lang, X. Sun, Parallel Tridiagonalization through Two-Step Band Reduction, Proceedings of the Scalable High-Performance Computing Conference, IEEE, Washington D. C., 1994, pp. 23\u201327."},{"key":"13_CR5","unstructured":"C.H. Bischof, B. Lang, X. Sun, A Framework for Symmetric Band Reduction, Technical report, Argonne Preprint ANL\/MCS-P586-0496, 1996."},{"key":"13_CR6","unstructured":"C.H. Bischof, B. Lang, X. Sun, The SBR Toolbox-Software for Successive Band Reduction, Technical report, Argonne Preprint ANL\/MCS-P587-0496, 1996."},{"key":"13_CR7","doi-asserted-by":"crossref","DOI":"10.1137\/1.9780898719642","volume-title":"ScaLapack Users\u2019 Guide","author":"L. S. Blackford","year":"1997","unstructured":"L. S. Blackford et al., ScaLapack Users\u2019 Guide, SIAM Press, Philadelphia, 1997."},{"key":"13_CR8","doi-asserted-by":"publisher","first-page":"336","DOI":"10.1145\/275323.275325","volume":"23","author":"S. Carr","year":"1997","unstructured":"S. Carr, R.B. Lehoucq, Compiler Blockability of Dense Matrix Factorizations, ACM Trans. Math. Software 23 (1997), pp. 336\u2013361.","journal-title":"ACM Trans. Math. Software"},{"key":"13_CR9","doi-asserted-by":"crossref","unstructured":"E. F. D\u2019Azevedo, J. J. Dongarra, Packed Storage Extension for ScaLapack, Technical report, Lapack Working Note 135, 1998.","DOI":"10.2172\/754353"},{"key":"13_CR10","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/77626.79170","volume":"16","author":"J. J. Dongarra","year":"1990","unstructured":"J. J. Dongarra, J. Du Croz, S. Hammarling, I. Duff, A Set of Level 3 Blas, ACM Trans. Math. Software 16 (1990), pp. 1\u201317.","journal-title":"ACM Trans. Math. Software"},{"key":"13_CR11","doi-asserted-by":"publisher","first-page":"18","DOI":"10.1145\/42288.42292","volume":"14","author":"J. J. Dongarra","year":"1988","unstructured":"J. J. Dongarra, J. Du Croz, S. Hammarling, R. J. Hanson, An Extended Set of Blas, ACM Trans. Math. Software 14 (1988), pp. 18\u201332.","journal-title":"ACM Trans. Math. Software"},{"key":"13_CR12","volume-title":"Linear Algebra and Matrix Theory","author":"J. J. Dongarra","year":"1998","unstructured":"J. J. Dongarra, I. S. Duff, D.C. Sorensen, H.A. van der Vorst, Linear Algebra and Matrix Theory, SIAM Press, Philadelphia, 1998."},{"key":"13_CR13","doi-asserted-by":"publisher","first-page":"215","DOI":"10.1016\/0377-0427(89)90367-1","volume":"27","author":"J. J. Dongarra","year":"1989","unstructured":"J. J. Dongarra, S. J. Hammarling, D. C. Sorensen, Block Reduction of Matrices to Condensed Forms for Eigenvalue Computations, J. Comput. Appl. Math. 27 (1989), pp. 215\u2013227.","journal-title":"J. Comput. Appl. Math."},{"key":"13_CR14","unstructured":"J. J. Dongarra, S. J. Hammarling, D. C. Sorensen, Block Reduction of Matrices to Condensed Forms for Eigenvalue Computations, Technical report, Lapack Working Note 2, 1987."},{"key":"13_CR15","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1006\/jcph.1994.1001","volume":"110","author":"C. C. Douglas","year":"1994","unstructured":"C. C. Douglas, M. Heroux, G. Slishman, R.M. Smith, GEMMW\u2014A Portable Level 3 Blas Winograd Variant of Strassen\u2019s Matrix-Matrix Multiply Algorithm, J. Computational Physics 110 (1994), pp. 1\u201310.","journal-title":"J. Computational Physics"},{"key":"13_CR16","unstructured":"W.N. Gansterer, D. F. Kvasnicka, High Performance Computing in Material Sciences. The Standard Eigenproblem-Concepts, Technical Report AURORA TR1998-18, Vienna University of Technology, 1998."},{"key":"13_CR17","unstructured":"W.N. Gansterer, D. F. Kvasnicka, High Performance Computing in Material Sciences. The Standard Eigenproblem-Experiments, Technical Report AURORA TR1998-19, Vienna University of Technology, 1998."},{"key":"13_CR18","doi-asserted-by":"crossref","DOI":"10.7551\/mitpress\/5712.001.0001","volume-title":"PVM: Parallel Virtual Machine\u2014A Users\u2019 Guide and Tutorial for Networked Parallel Computing","author":"A. Geist","year":"1994","unstructured":"A. Geist, A. Beguelin, J. J. Dongarra, W. Jiang, R. Manchek, V. Sunderam, PVM: Parallel Virtual Machine\u2014A Users\u2019 Guide and Tutorial for Networked Parallel Computing, MIT Press, Cambridge London, 1994."},{"key":"13_CR19","volume-title":"Matrix Computations","author":"G.H. Golub","year":"1996","unstructured":"G.H. Golub, C. F. Van Loan, Matrix Computations, 3rd ed., Johns Hopkins University Press, Baltimore, 1996.","edition":"3rd ed."},{"key":"13_CR20","volume-title":"Using MPI","author":"W. Gropp","year":"1994","unstructured":"W. Gropp, E. Lusk, A. Skjelum, Using MPI, MIT Press, Cambridge London, 1994."},{"key":"13_CR21","unstructured":"E. Haunschmid, D. F. Kvasnicka, High Performance Computing in Material Sciences. Maximizing Cache Utilization without Increasing Memory Requirements, Technical Report AURORA TR1998-17, Vienna University of Technology, 1998."},{"key":"13_CR22","unstructured":"High Performance Fortran Forum, High Performance Fortran Language Specification, Version 2.0, 1997."},{"key":"13_CR23","doi-asserted-by":"publisher","first-page":"352","DOI":"10.1145\/98267.98290","volume":"16","author":"N. J. Higham","year":"1990","unstructured":"N. J. Higham, Exploiting Fast Matrix Multiplication within the Level 3 Blas, ACM Trans. Math. Software 16 (1990), pp. 352\u2013368.","journal-title":"ACM Trans. Math. Software"},{"issue":"3","key":"13_CR24","doi-asserted-by":"publisher","first-page":"681","DOI":"10.1137\/0613043","volume":"13","author":"N. J. Higham","year":"1992","unstructured":"N. J. Higham, Stability of a Method for Multiplying Complex Matrices with Three Real Matrix Multiplications, SIAM J. Matrix Anal. Appl. 13(3) (1992), pp. 681\u2013687.","journal-title":"SIAM J. Matrix Anal. Appl."},{"key":"13_CR25","doi-asserted-by":"crossref","unstructured":"B. Kagstrom, P. Ling, C. Van Loan, GEMM-Based Level 3 Blas: High-Performance Model Implementations and Performance Evaluation Benchmark, ACM Trans. Math. Software 24 (1998).","DOI":"10.1145\/292395.292412"},{"key":"13_CR26","unstructured":"D. F. Kvasnicka, Parallel Packed Storage Scheme (P2S2) for Symmetric and Triangular Matrices, Technical Report to appear, Vienna University of Technology, 1998."},{"key":"13_CR27","first-page":"267","volume":"1","author":"D. F. Kvasnicka","year":"1998","unstructured":"D. F. Kvasnicka, W.N. Gansterer, C.W. Ueberhuber, A Level 3 Algorithm for the Symmetric Eigenproblem, Proceedings of the Third International Meeting on Vector and Parallel Processing (VECPAR\u201998), Vol. 1, 1998, pp. 267\u2013275.","journal-title":"Proceedings of the Third International Meeting on Vector and Parallel Processing (VECPAR\u201998)"},{"key":"13_CR28","unstructured":"J. Laderman, V. Pan, X.-H. Sha, On Practical Acceleration of Matrix Multiplication, Linear Algebra Appl.162-164 (1992), pp. 557\u2013588."},{"key":"13_CR29","doi-asserted-by":"publisher","first-page":"63","DOI":"10.1145\/165660.165673","volume":"21","author":"M. S. Lam","year":"1993","unstructured":"M. S. Lam, E. E. Rothberg, M. E. Wolf, The Cache Performance and Optimizations of Blocked Algorithms, Computer Architecture News 21 (1993), pp. 63\u201374.","journal-title":"Computer Architecture News"},{"key":"13_CR30","first-page":"63","volume":"5","author":"C. L. Lawson","year":"1979","unstructured":"C. L. Lawson, R. J. Hanson, D. Kincaid, F. T. Krogh, Blas for Fortran Usage, ACM Trans. Math. Software 5 (1979), pp. 63\u201374.","journal-title":"ACM Trans. Math. Software"},{"key":"13_CR31","doi-asserted-by":"publisher","first-page":"393","DOI":"10.1137\/1026076","volume":"26","author":"V. Pan","year":"1984","unstructured":"V. Pan, How Can We Speed Up Matrix Multiplication?, SIAM Rev. 26 (1984), pp. 393\u2013415.","journal-title":"SIAM Rev."},{"key":"13_CR32","unstructured":"R. Schreiber, J. J. Dongarra, Automatic Blocking of Nested Loops, Technical Report CS-90-108, University of Tennessee, 1990."},{"key":"13_CR33","doi-asserted-by":"publisher","first-page":"354","DOI":"10.1007\/BF02165411","volume":"13","author":"V. Strassen","year":"1969","unstructured":"V. Strassen, Gaussian Elimination Is not Optimal, Numer. Math. 13 (1969), pp. 354\u2013356.","journal-title":"Numer. Math."},{"key":"13_CR34","volume-title":"Numerical Computation","author":"C.W. Ueberhuber","year":"1997","unstructured":"C.W. Ueberhuber, Numerical Computation, Springer-Verlag, Heidelberg, 1997."},{"key":"13_CR35","unstructured":"R. van de Geijn, Using PLapack: Parallel Linear Algebra Package, MIT Press, 1997."},{"key":"13_CR36","doi-asserted-by":"crossref","unstructured":"R. C. Whaley, J. J. Dongarra, Automatically Tuned Linear Algebra Software, Technical report, Lapack Working Note131, 1997.","DOI":"10.1109\/SC.1998.10004"},{"key":"13_CR37","doi-asserted-by":"publisher","first-page":"381","DOI":"10.1016\/0024-3795(71)90009-7","volume":"4","author":"S. Winograd","year":"1971","unstructured":"S. Winograd, On Multiplication of 2\u00d72 Matrices, Linear Algebra Appl. 4 (1971), pp. 381\u2013388.","journal-title":"Linear Algebra Appl."}],"container-title":["Lecture Notes in Computer Science","Parallel Computation"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/3-540-49164-3_13","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,5,2]],"date-time":"2019-05-02T17:34:20Z","timestamp":1556818460000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/3-540-49164-3_13"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[1999]]},"ISBN":["9783540656418","9783540491644"],"references-count":37,"URL":"https:\/\/doi.org\/10.1007\/3-540-49164-3_13","relation":{},"ISSN":["0302-9743"],"issn-type":[{"type":"print","value":"0302-9743"}],"subject":[],"published":{"date-parts":[[1999]]}}}