{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,4]],"date-time":"2024-09-04T16:09:30Z","timestamp":1725466170279},"publisher-location":"Berlin, Heidelberg","reference-count":20,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783642314636"},{"type":"electronic","value":"9783642314643"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2012]]},"DOI":"10.1007\/978-3-642-31464-3_7","type":"book-chapter","created":{"date-parts":[[2012,7,2]],"date-time":"2012-07-02T15:20:38Z","timestamp":1341242438000},"page":"60-69","source":"Crossref","is-referenced-by-count":0,"title":["New Level-3 BLAS Kernels for Cholesky Factorization"],"prefix":"10.1007","author":[{"given":"Fred G.","family":"Gustavson","sequence":"first","affiliation":[]},{"given":"Jerzy","family":"Wa\u015bniewski","sequence":"additional","affiliation":[]},{"given":"Jos\u00e9 R.","family":"Herrero","sequence":"additional","affiliation":[]}],"member":"297","reference":[{"issue":"2","key":"7_CR1","doi-asserted-by":"publisher","first-page":"214","DOI":"10.1145\/383738.383741","volume":"27","author":"B.S. Andersen","year":"2001","unstructured":"Andersen, B.S., Gustavson, F.G., Wa\u015bniewski, J.: A Recursive Formulation of Cholesky Factorization of a Matrix in Packed Storage. ACM TOMS\u00a027(2), 214\u2013244 (2001)","journal-title":"ACM TOMS"},{"issue":"2","key":"7_CR2","doi-asserted-by":"publisher","first-page":"201","DOI":"10.1145\/1067967.1067969","volume":"31","author":"B.S. Andersen","year":"2005","unstructured":"Andersen, B.S., Gunnels, J.A., Gustavson, F.G., Reid, J.K., Wa\u015bniewski, J.: A Fully Portable High Performance Minimal Storage Hybrid Cholesky Algorithm. ACM TOMS\u00a031(2), 201\u2013227 (2005)","journal-title":"ACM TOMS"},{"key":"7_CR3","doi-asserted-by":"publisher","DOI":"10.1137\/1.9780898719604","volume-title":"LAPACK Users\u2019 Guide Release 3.0","author":"E. Anderson","year":"1999","unstructured":"Anderson, E., et al.: LAPACK Users\u2019 Guide Release 3.0. SIAM, Philadelphia (1999)"},{"key":"7_CR4","doi-asserted-by":"crossref","unstructured":"D\u2019Azevedo, E., Dongarra, J.J.: Packed storage extension of ScaLAPACK. ORNL Report 6190, Oak Ridge National Laboratory, 13 pages (May 1998)","DOI":"10.2172\/754353"},{"issue":"1","key":"7_CR5","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/77626.79170","volume":"16","author":"J.J. Dongarra","year":"1990","unstructured":"Dongarra, J.J., Du Croz, J., Hammarling, S., Duff, I.: Set of Level 3 Basic Linear Algebra Subprograms. TOMS\u00a016(1), 1\u201317 (1990)","journal-title":"TOMS"},{"issue":"1","key":"7_CR6","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1137\/S0036144503428693","volume":"46","author":"E. Elmroth","year":"2004","unstructured":"Elmroth, E., Gustavson, F.G., Jonsson, I., K\u00e5gstr\u00f6m, B.: Recursive Blocked Algorithms and Hybrid Data Structures for Dense Matrix Library Software. SIAM Review\u00a046(1), 3\u201345 (2004)","journal-title":"SIAM Review"},{"key":"7_CR7","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"919","DOI":"10.1007\/978-3-540-75755-9_109","volume-title":"Applied Parallel Computing. State of the Art in Scientific Computing","author":"J.A. Gunnels","year":"2007","unstructured":"Gunnels, J.A., Gustavson, F.G., Pingali, K.K., Yotov, K.: Is Cache-Oblivious DGEMM Viable? In: K\u00e5gstr\u00f6m, B., Elmroth, E., Dongarra, J., Wa\u015bniewski, J. (eds.) PARA 2006. LNCS, vol.\u00a04699, pp. 919\u2013928. Springer, Heidelberg (2007)"},{"issue":"6","key":"7_CR8","doi-asserted-by":"publisher","first-page":"737","DOI":"10.1147\/rd.416.0737","volume":"41","author":"F.G. Gustavson","year":"1997","unstructured":"Gustavson, F.G.: Recursion Leads to Automatic Variable Blocking for Dense Linear-Algebra Algorithms. IBM J. R. & D\u00a041(6), 737\u2013755 (1997)","journal-title":"IBM J. R. & D"},{"issue":"6","key":"7_CR9","doi-asserted-by":"publisher","first-page":"823","DOI":"10.1147\/rd.446.0823","volume":"44","author":"F.G. Gustavson","year":"2000","unstructured":"Gustavson, F.G., Jonsson, I.: Minimal Storage High Performance Cholesky via Blocking and Recursion. IBM J. R. & D\u00a044(6), 823\u2013849 (2000)","journal-title":"IBM J. R. & D"},{"key":"7_CR10","doi-asserted-by":"crossref","unstructured":"Gustavson, F.G.: New Generalized Data Structures for Matrices Lead to a Variety of High-Performance Algorithms. In: Boisvert, R.F., Tang, P.T.P. (eds.) Proceedings of the IFIP WG 2.5 Working Group on The Architecture of Scientific Software, Ottawa, Canada, October 2-4, pp. 211\u2013234. Kluwer Academic Pub. (2000)","DOI":"10.1007\/978-0-387-35407-1_13"},{"issue":"1","key":"7_CR11","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1147\/rd.471.0031","volume":"47","author":"F.G. Gustavson","year":"2003","unstructured":"Gustavson, F.G.: High Performance Linear Algebra Algorithms using New Generalized Data Structures for Matrices. IBM J. R. & D\u00a047(1), 31\u201355 (2003)","journal-title":"IBM J. R. & D"},{"key":"7_CR12","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"540","DOI":"10.1007\/978-3-540-75755-9_66","volume-title":"Applied Parallel Computing. State of the Art in Scientific Computing","author":"F.G. Gustavson","year":"2007","unstructured":"Gustavson, F.G., Gunnels, J., Sexton, J.: Minimal Data Copy For Dense Linear Algebra Factorization. In: K\u00e5gstr\u00f6m, B., Elmroth, E., Dongarra, J., Wa\u015bniewski, J. (eds.) PARA 2006. LNCS, vol.\u00a04699, pp. 540\u2013549. Springer, Heidelberg (2007)"},{"issue":"1","key":"7_CR13","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1145\/1206040.1206048","volume":"33","author":"F.G. Gustavson","year":"2007","unstructured":"Gustavson, F.G., Reid, J.K., Wa\u015bniewski, J.: Algorithm 865: Fortran 95 Subroutines for Cholesky Factorization in Blocked Hybrid Format. ACM TOMS\u00a033(1), 5 pages (2007)","journal-title":"ACM TOMS"},{"key":"7_CR14","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"22","DOI":"10.1007\/978-3-642-28151-8_3","volume-title":"Applied Parallel and Scientific Computing","author":"F.G. Gustavson","year":"2012","unstructured":"Gustavson, F.G.: Cache Blocking. In: J\u00f3nasson, K. (ed.) PARA 2010, Part I. LNCS, vol.\u00a07133, pp. 22\u201332. Springer, Heidelberg (2012)"},{"key":"7_CR15","doi-asserted-by":"crossref","unstructured":"Gustavson, F.G., Karlsson, L., K\u00e5gstr\u00f6m, B.: Parallel and Cache-Efficient In-Place Matrix Storage Format Conversion. ACM TOMS, 34 pages (to appear, 2012)","DOI":"10.1145\/2168773.2168775"},{"key":"7_CR16","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"762","DOI":"10.1007\/11751649_84","volume-title":"Computational Science and Its Applications - ICCSA 2006","author":"J.R. Herrero","year":"2006","unstructured":"Herrero, J.R., Navarro, J.J.: Compiler-Optimized Kernels: An Efficient Alternative to Hand-Coded Inner Kernels. In: Gavrilova, M.L., Gervasi, O., Kumar, V., Tan, C.J.K., Taniar, D., Lagan\u00e1, A., Mun, Y., Choo, H. (eds.) ICCSA 2006. LNCS, vol.\u00a03984, pp. 762\u2013771. Springer, Heidelberg (2006)"},{"key":"7_CR17","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"659","DOI":"10.1007\/978-3-540-68111-3_69","volume-title":"Parallel Processing and Applied Mathematics","author":"J.R. Herrero","year":"2008","unstructured":"Herrero, J.R.: New Data Structures for Matrices and Specialized Inner Kernels: Low Overhead for High Performance. In: Wyrzykowski, R., Dongarra, J., Karczewski, K., Wasniewski, J. (eds.) PPAM 2007. LNCS, vol.\u00a04967, pp. 659\u2013667. Springer, Heidelberg (2008)"},{"key":"7_CR18","unstructured":"Knuth, D.: The Art of Computer Programming, 3rd edn., vol.\u00a01&2. Addison-Wesley"},{"issue":"9","key":"7_CR19","doi-asserted-by":"publisher","first-page":"1175","DOI":"10.1109\/TPDS.2007.70813","volume":"19","author":"J. Kurzak","year":"2008","unstructured":"Kurzak, J., Buttari, A., Dongarra, J.: Solving systems of Linear Equations on the Cell Processor using Cholesky Factorization. IEEE Trans. Parallel Distrib. Syst.\u00a019(9), 1175\u20131186 (2008)","journal-title":"IEEE Trans. Parallel Distrib. Syst."},{"key":"7_CR20","doi-asserted-by":"crossref","unstructured":"Whaley, C.: Empirically tuning LAPACK\u2019s blocking factor for increased performance. In: Proc. of the Conf. on Computer Aspects of Numerical Algs., 8 pages (2008)","DOI":"10.1109\/IMCSIT.2008.4747256"}],"container-title":["Lecture Notes in Computer Science","Parallel Processing and Applied Mathematics"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-31464-3_7.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,5,4]],"date-time":"2021-05-04T12:02:30Z","timestamp":1620129750000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-31464-3_7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2012]]},"ISBN":["9783642314636","9783642314643"],"references-count":20,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-31464-3_7","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2012]]}}}