{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,4]],"date-time":"2024-09-04T23:38:52Z","timestamp":1725493132710},"publisher-location":"Berlin, Heidelberg","reference-count":31,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783540401964"},{"type":"electronic","value":"9783540448631"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2003]]},"DOI":"10.1007\/3-540-44863-2_65","type":"book-chapter","created":{"date-parts":[[2007,10,20]],"date-time":"2007-10-20T13:45:55Z","timestamp":1192887955000},"page":"665-672","source":"Crossref","is-referenced-by-count":1,"title":["Self-Adapting Software for Numerical Linear Algebra Library Routines on Clusters"],"prefix":"10.1007","author":[{"given":"Zizhong","family":"Chen","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jack","family":"Dongarra","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Piotr","family":"Luszczek","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kenneth","family":"Roche","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2003,6,18]]},"reference":[{"key":"65_CR1","unstructured":"R. Agarwal, Fred Gustavson, and M. Zubair. A high-performacne algorithm using preprocessing for the sparse matrix-vector multiplication. In Proceedings of International Conference on Supercomputing, 1992."},{"key":"65_CR2","doi-asserted-by":"crossref","unstructured":"E. Anderson, Z. Bai, C. Bischof, Suzan L. Blackford, James W. Demmel, Jack J. Dongarra, J. Du Croz, A. Greenbaum, S. Hammarling, A. McKenney, and Danny C. Sorensen. LAPACK User\u2019s Guide. Society for Industrial and Applied Mathematics, Philadelphia, Third edition, 1999.","DOI":"10.1137\/1.9780898719604"},{"issue":"1\u20132","key":"65_CR3","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1016\/0377-0427(96)00019-2","volume":"74","author":"R. Barrett","year":"1996","unstructured":"Richard Barrett, Michael Berry, Jack Dongarra, Victor Eijkhout, and Charles Romine. Algorithmic bombardment for the iterative solution of linear systems: A poly-iterative approach. Journal of Computational and Applied Mathematics, 74(1\u20132):91\u2013109, 1996.","journal-title":"Journal of Computational and Applied Mathematics"},{"key":"65_CR4","doi-asserted-by":"publisher","first-page":"327","DOI":"10.1177\/109434200101500401","volume":"15","author":"F. Berman","year":"2001","unstructured":"F. Berman. The GrADS project: Software support for high level grid application development. International Journal of High Performance Computing Applications, 15:327\u2013344, 2001.","journal-title":"International Journal of High Performance Computing Applications"},{"key":"65_CR5","doi-asserted-by":"publisher","first-page":"14","DOI":"10.1006\/jpdc.1995.1141","volume":"31","author":"A. Bik","year":"1995","unstructured":"A. Bik and H. Wijshoff. Advanced compiler optimizations for sparse computations. Journal of Parallel and Distributing Computing, 31:14\u201324, 1995.","journal-title":"Journal of Parallel and Distributing Computing"},{"key":"65_CR6","doi-asserted-by":"crossref","unstructured":"J. Bilmes et al. Optimizing matrix multiply using PHiPAC: a portable, highperformance, ANSI C coding methodology. In Proceedings of International Conference on Supercomputing, Vienna, Austria, 1997. ACM SIGARC.","DOI":"10.1145\/263580.263662"},{"key":"65_CR7","doi-asserted-by":"crossref","unstructured":"Jack J. Dongarra, J. Du Croz, Iain S. Duff, and S. Hammarling. Algorithm 679: A set of Level 3 Basic Linear Algebra Subprograms. ACM Transactions on Mathematical Software, 16:1\u201317, March 1990.","DOI":"10.1145\/77626.79170"},{"key":"65_CR8","doi-asserted-by":"publisher","first-page":"18","DOI":"10.1145\/77626.77627","volume":"16","author":"J. J. Dongarra","year":"1990","unstructured":"Jack J. Dongarra, J. Du Croz, Iain S. Duff, and S. Hammarling. A set of Level 3 Basic Linear Algebra Subprograms. ACM Transactions on Mathematical Software, 16:18\u201328, March 1990.","journal-title":"ACM Transactions on Mathematical Software"},{"key":"65_CR9","doi-asserted-by":"publisher","first-page":"18","DOI":"10.1145\/42288.42292","volume":"14","author":"J. J. Dongarra","year":"1988","unstructured":"Jack J. Dongarra, J. Du Croz, S. Hammarling, and R. Hanson. Algorithm 656: An extended set of FORTRAN Basic Linear Algebra Subprograms. ACM Transactions on Mathematical Software, 14:18\u201332, March 1988.","journal-title":"ACM Transactions on Mathematical Software"},{"key":"65_CR10","doi-asserted-by":"crossref","unstructured":"Jack J. Dongarra, J. Du Croz, S. Hammarling, and R. Hanson. An extended set of FORTRAN Basic Linear Algebra Subprograms. ACM Transactions on Mathematical Software, 14:1\u201317, March 1988.","DOI":"10.1145\/42288.42291"},{"key":"65_CR11","unstructured":"Jack J. Dongarra and Victor Eijkhout. Self-adapting numerical software for next generation applications. Technical report, Innovative Computing Laboratory, University of Tennessee, August 2002. http:\/\/icl.cs.utk.edu\/iclprojects\/pages\/sans.html ."},{"key":"65_CR12","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1002\/cpe.728","volume":"15","author":"J. J. Dongarra","year":"2003","unstructured":"Jack J. Dongarra, Piotr Luszczek, and Antione Petitet. The LINPACK benchmark: Past, present, and future. Concurrency and Computation: Practice and Experience, 15:1\u201318, 2003.","journal-title":"Concurrency and Computation: Practice and Experience"},{"key":"65_CR13","unstructured":"Jack J. Dongarra and Clint R. Whaley. Automatically tuned linear algebra software (ATLAS). In Proceedings of SC\u201998 Conference. IEEE, 1998."},{"key":"65_CR14","unstructured":"Message Passing Interface Forum. MPI: A Message-Passing Interface Standard. The International Journal of Supercomputer Applications and High Performance Computing, 8, 1994."},{"key":"65_CR15","unstructured":"Message Passing Interface Forum. MPI: A Message-Passing Interface Standard (version 1.1), 1995. Available at: http:\/\/www.mpi-forum.org\/ ."},{"key":"65_CR16","unstructured":"Message Passing Interface Forum. MPI-2: Extensions to the Message-Passing Interface, 18 July 1997. Available at http:\/\/www.mpi-forum.org\/docs\/mpi-20.ps ."},{"key":"65_CR17","volume-title":"The Grid: Blueprint for a New Computing Infrastructure","author":"I. Foster","year":"1999","unstructured":"Ian Foster and Carl Kesselman. The Grid: Blueprint for a New Computing Infrastructure. Morgan Kaufmann, San Francisco, 1999."},{"key":"65_CR18","doi-asserted-by":"crossref","unstructured":"M. Frigo. A fast Fourier transform compiler. In Proceedings of ACM SIGPLAN Conference on Programming Language Design and Implementation, Atlanta, Georgia, USA, 1999.","DOI":"10.1145\/301618.301661"},{"key":"65_CR19","doi-asserted-by":"crossref","unstructured":"M. Frigo and S. G. Johnson. FFTW: An adaptive software architecture for the FFT. In Proceedings International Conference on Acoustics, Speech, and Signal Processing, Seattle, Washington, USA, 1998.","DOI":"10.1109\/ICASSP.1998.681704"},{"key":"65_CR20","volume-title":"Automatic optimization of sparse matrix-vector multiplication","author":"E.-J. Im","year":"2000","unstructured":"E.-J. Im. Automatic optimization of sparse matrix-vector multiplication. PhD thesis, University of California, Berkeley, California, 2000."},{"key":"65_CR21","unstructured":"E.-J. Im and Kathy Yelick. Optimizing sparse matrix-vector multiplication on SMPs. In Ninth SIAM Conference on Parallel Processing for Scientific Computing, San Antonio, Texas, 1999."},{"key":"65_CR22","doi-asserted-by":"crossref","unstructured":"Hans W. Meuer, Erik Strohmaier, Jack J. Dongarra, and Horst D. Simon. Top500 Supercomputer Sites, 20th edition edition, November 2002. (The report can be downloaded from http:\/\/www.netlib.org\/benchmark\/top500.html ).","DOI":"10.2172\/860748"},{"key":"65_CR23","doi-asserted-by":"crossref","unstructured":"D. Mirkovic and S. L. Johnsson. Automatic performance tuning in the UHFFT library. In 2001 International Conference on Computational Science, San Francisco, California, USA, 2001.","DOI":"10.1007\/3-540-45545-0_17"},{"key":"65_CR24","unstructured":"Jakob Ostergaard. OptimQR-A software package to create near-optimal solvers for sparse systems of linear equations. http:\/\/ostenfeld.dk\/~jakob\/OptimQR\/ ."},{"key":"65_CR25","doi-asserted-by":"publisher","first-page":"359","DOI":"10.1177\/109434200101500403","volume":"15","author":"A. Petitet","year":"2001","unstructured":"Antoine Petitet et al. Numerical libraries and the grid. International Journal of High Performance Computing Applications, 15:359\u2013374, 2001.","journal-title":"International Journal of High Performance Computing Applications"},{"key":"65_CR26","doi-asserted-by":"crossref","unstructured":"Ali Pinar and Michael T. Heath. Improving performance of sparse matrix-vector multiplication. In Proceddings of SC\u201999, 1999.","DOI":"10.1145\/331532.331562"},{"key":"65_CR27","doi-asserted-by":"crossref","unstructured":"J. R. Rice. On the construction of poly-algorithms for automatic numerical analysis. In M. Klerer and J. Reinfelds, editors, Interactive Systems for Experimental Applied Mathematics, pages 31\u2013313. Academic Press, 1968.","DOI":"10.1016\/B978-0-12-395608-8.50035-9"},{"key":"65_CR28","doi-asserted-by":"crossref","unstructured":"Sivan Toledo. Improving the memory-system performance of sparse matrix-vector multiplication. IBM Journal of Research and Development, 41(6), November 1997.","DOI":"10.1147\/rd.416.0711"},{"key":"65_CR29","unstructured":"Sathish Vadhiyar, Graham Fagg, and Jack J. Dongarra. Performance modeling for self adapting collective communications for MPI. In Los Alamos Computer Science Institute Symposium (LACSI 2001), Sante Fe, New Mexico, 2001."},{"key":"65_CR30","unstructured":"R. Weiss, H. Haefner, and W. Schoenauer. LINSOL (LINear SOLver)-Description and User\u2019s Guide for the Parallelized Version. University of Karlsruhe Computing Center, 1995."},{"issue":"1\u20132","key":"65_CR31","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1016\/S0167-8191(00)00087-9","volume":"27","author":"R. C. Whaley","year":"2001","unstructured":"R. Clint Whaley, Antoine Petitet, and Jack J. Dongarra. Automated empirical optimizations of software and the ATLAS project. Parallel Computing, 27(1\u20132):3\u201335, 2001.","journal-title":"Parallel Computing"}],"container-title":["Lecture Notes in Computer Science","Computational Science \u2014 ICCS 2003"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/3-540-44863-2_65","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,5,3]],"date-time":"2019-05-03T18:07:01Z","timestamp":1556906821000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/3-540-44863-2_65"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2003]]},"ISBN":["9783540401964","9783540448631"],"references-count":31,"URL":"https:\/\/doi.org\/10.1007\/3-540-44863-2_65","relation":{},"ISSN":["0302-9743"],"issn-type":[{"type":"print","value":"0302-9743"}],"subject":[],"published":{"date-parts":[[2003]]}}}