{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T22:11:27Z","timestamp":1743027087046,"version":"3.40.3"},"publisher-location":"Berlin, Heidelberg","reference-count":18,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783642193279"},{"type":"electronic","value":"9783642193286"}],"license":[{"start":{"date-parts":[[2011,1,1]],"date-time":"2011-01-01T00:00:00Z","timestamp":1293840000000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2011]]},"DOI":"10.1007\/978-3-642-19328-6_7","type":"book-chapter","created":{"date-parts":[[2011,2,18]],"date-time":"2011-02-18T10:22:33Z","timestamp":1298024553000},"page":"45-57","source":"Crossref","is-referenced-by-count":3,"title":["Performance and Numerical Accuracy Evaluation of Heterogeneous Multicore Systems for Krylov Orthogonal Basis Computation"],"prefix":"10.1007","author":[{"given":"J\u00e9r\u00f4me","family":"Dubois","sequence":"first","affiliation":[]},{"given":"Christophe","family":"Calvin","sequence":"additional","affiliation":[]},{"given":"Serge","family":"Petiton","sequence":"additional","affiliation":[]}],"member":"297","reference":[{"issue":"2","key":"7_CR1","doi-asserted-by":"crossref","first-page":"135","DOI":"10.1145\/567806.567807","volume":"28","author":"L. Susan Blackford","year":"2002","unstructured":"An updated set of basic linear algebra subprograms (blas). ACM Trans. Math. Softw.\u00a028(2), 135\u2013151 (2002)","journal-title":"ACM Transactions on Mathematical Software"},{"key":"7_CR2","unstructured":"Arevalo, A., Matinata, R.M., (Raj)Pandian, M., Peri, E., Ruby, K., Thomas, F., Almond, C.: Architecture overview and its impact on programming. In: Programming the Cell Broadband Engine Architecture: Examples and Best Practices, ch. 4.61. IBM (2008)"},{"key":"7_CR3","volume-title":"SC 2009: Proceedings of the 2009 ACM\/IEEE Conference on Supercomputing","author":"N. Bell","year":"2009","unstructured":"Bell, N., Garland, M.: Implementing sparse matrix-vector multiplication on throughput-oriented processors. In: SC 2009: Proceedings of the 2009 ACM\/IEEE Conference on Supercomputing. ACM, New York (2009)"},{"issue":"1-3","key":"7_CR4","doi-asserted-by":"publisher","first-page":"307","DOI":"10.1016\/S0024-3795(99)00100-7","volume":"309","author":"T. Braconnier","year":"2000","unstructured":"Braconnier, T., Langlois, P., Rioual, J.C.: The influence of orthogonality on the arnoldi method. Linear Algebra and its Applications\u00a0309(1-3), 307\u2013323 (2000)","journal-title":"Linear Algebra and its Applications"},{"issue":"3","key":"7_CR5","doi-asserted-by":"publisher","first-page":"777","DOI":"10.1145\/1015706.1015800","volume":"23","author":"I. Buck","year":"2004","unstructured":"Buck, I., Foley, T., Horn, D., Sugerman, J., Fatahalian, K., Houston, M., Hanrahan, P.: Brook for gpus: stream computing on graphics hardware. ACM Trans. Graph.\u00a023(3), 777\u2013786 (2004)","journal-title":"ACM Trans. Graph."},{"key":"7_CR6","unstructured":"NVidia Corporation. Nvidia: Cublas library. Technical report. Whitepaper. Part of CUDA Toolkit"},{"issue":"1","key":"7_CR7","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/62038.62043","volume":"15","author":"I.S. Duff","year":"1989","unstructured":"Duff, I.S., Grimes, R.G., Lewis, J.G.: Sparse matrix test problems. ACM Trans. Math. Softw.\u00a015(1), 1\u201314 (1989)","journal-title":"ACM Trans. Math. Softw."},{"key":"7_CR8","unstructured":"Frigo, M., Johnson, S.G.: Fftw on the cell processor, \n                    \n                      http:\/\/www.fftw.org\/cell\/"},{"issue":"1","key":"7_CR9","doi-asserted-by":"publisher","first-page":"87","DOI":"10.1007\/s00211-005-0615-4","volume":"101","author":"L. Giraud","year":"2005","unstructured":"Giraud, L., Langou, J., Rozlo\u017en\u00edk, M., van den Eshof, J.: Rounding error analysis of the classical Gram-Schmidt orthogonalization process. Numerische Mathematik\u00a0101(1), 87\u2013100 (2005)","journal-title":"Numerische Mathematik"},{"key":"7_CR10","doi-asserted-by":"crossref","unstructured":"Goldberg, D.: What every computer scientist should know about floating-point arithmetic. ACM Computing Surveys (1991)","DOI":"10.1145\/103162.103163"},{"key":"7_CR11","volume-title":"Matrix Computations (Johns Hopkins Studies in Mathematical Sciences)","author":"G.H. Golub","year":"1996","unstructured":"Golub, G.H., Van Loan, C.F.: Matrix Computations (Johns Hopkins Studies in Mathematical Sciences). The Johns Hopkins University Press, Baltimore (1996)"},{"issue":"7-8","key":"7_CR12","doi-asserted-by":"publisher","first-page":"521","DOI":"10.1016\/j.parco.2007.04.004","volume":"33","author":"V. Hernandez","year":"2007","unstructured":"Hernandez, V., Roman, J.E., Tomas, A.: Parallel arnoldi eigensolvers with enhanced scalability via global communications rearrangement. Parallel Comput.\u00a033(7-8), 521\u2013540 (2007)","journal-title":"Parallel Comput."},{"issue":"2","key":"7_CR13","first-page":"9","volume":"22","author":"IEEE","year":"1985","unstructured":"IEEE: IEEE standard for binary floating-point arithmetic. ACM SIGPLAN Notices\u00a022(2), 9\u201325 (1985)","journal-title":"ACM SIGPLAN Notices"},{"key":"7_CR14","unstructured":"Meuer, H., Strohmaier, E., Dongarra, J., Simon, H.: Architecture share over time, \n                    \n                      http:\/\/www.top500.org\/overtime\/list\/32\/archtype"},{"key":"7_CR15","unstructured":"NVIDIA. NVIDIA CUDA Programming Guide 2.0 (2008)"},{"key":"7_CR16","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"409","DOI":"10.1007\/BFb0037424","volume-title":"SOFSEM \u201996: Theory and Practice of Informatics","author":"M. Rozlozn\u00edk","year":"1996","unstructured":"Rozlozn\u00edk, M., Strakos, Z., Tuma, M.: On the role of orthogonality in the gmres method. In: Kr\u00e1l, J., Bartosek, M., Jeffery, K. (eds.) SOFSEM 1996. LNCS, vol.\u00a01175, pp. 409\u2013416. Springer, Heidelberg (1996)"},{"key":"7_CR17","unstructured":"Takuya, Y., Daisuke, T., Taisuke, B., Mitsuhisa, S.: Parallel implementation of classical gram-schmidt orthogonalization using matrix multiplication. IPSJ SIG Technical Reports (63(HPC-106)), 31\u201336 (2006)"},{"key":"7_CR18","doi-asserted-by":"publisher","first-page":"2001","DOI":"10.1016\/S0167-8191(00)00087-9","volume":"27","author":"R. Clint Whaley","year":"2001","unstructured":"Clint Whaley, R., Petitet, A., Dongarra, J.J.: Automated empirical optimizations of software and the atlas project. Parallel Computing\u00a027, 2001 (2001)","journal-title":"Parallel Computing"}],"container-title":["Lecture Notes in Computer Science","High Performance Computing for Computational Science \u2013 VECPAR 2010"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-19328-6_7","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2018,10,8]],"date-time":"2018-10-08T21:36:42Z","timestamp":1539034602000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-19328-6_7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2011]]},"ISBN":["9783642193279","9783642193286"],"references-count":18,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-19328-6_7","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2011]]}}}