{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T06:03:15Z","timestamp":1774591395981,"version":"3.50.1"},"publisher-location":"Cham","reference-count":14,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783319460789","type":"print"},{"value":"9783319460796","type":"electronic"}],"license":[{"start":{"date-parts":[[2016,1,1]],"date-time":"2016-01-01T00:00:00Z","timestamp":1451606400000},"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":[[2016]]},"DOI":"10.1007\/978-3-319-46079-6_27","type":"book-chapter","created":{"date-parts":[[2016,10,5]],"date-time":"2016-10-05T12:01:40Z","timestamp":1475668900000},"page":"378-389","source":"Crossref","is-referenced-by-count":4,"title":["Optimization of the Sparse Matrix-Vector Products of an IDR Krylov Iterative Solver in EMGeo for the Intel KNL Manycore Processor"],"prefix":"10.1007","author":[{"given":"Tareq","family":"Malas","sequence":"first","affiliation":[]},{"given":"Thorsten","family":"Kurth","sequence":"additional","affiliation":[]},{"given":"Jack","family":"Deslippe","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2016,10,6]]},"reference":[{"key":"27_CR1","unstructured":"Datta, K.: Auto-tuning stencil codes for cache-based multicore platforms. Ph.D. thesis, EECS Department, University of California, Berkeley. http:\/\/www.eecs.berkeley.edu\/Pubs\/TechRpts\/2009\/EECS-2009-177.html"},{"key":"27_CR2","unstructured":"Gropp, W., Kaushik, D., Keyes, D., Smith, B.: Toward realistic performance bounds for implicit CFD codes. In: Proceedings of parallel CFD, vol. 99, pp. 233\u2013240. Citeseer (1999)"},{"key":"27_CR3","unstructured":"Kreutzer, M., Thies, J., R\u00f6hrig-Z\u00f6llner, M., Pieper, A., Shahzad, F., Galgon, M., Basermann, A., Fehske, H., Hager, G., Wellein, G.: GHOST: building blocks for high performance sparse linear algebra on heterogeneous systems abs\/1507.08101 (2015). http:\/\/arxiv.org\/abs\/1507.08101"},{"issue":"4","key":"27_CR4","doi-asserted-by":"publisher","first-page":"C439","DOI":"10.1137\/140991133","volume":"37","author":"T Malas","year":"2015","unstructured":"Malas, T., Hager, G., Ltaief, H., Stengel, H., Wellein, G., Keyes, D.: Multicore-optimized wavefront diamond blocking for optimizing stencil updates. SIAM J. Sci. Comput. 37(4), C439\u2013C464 (2015). doi: 10.1137\/140991133","journal-title":"SIAM J. Sci. Comput."},{"key":"27_CR5","unstructured":"Malas, T.M.: Tiling and asynchronous communication optimizations for stencil computations. Ph.D. thesis, King Abdullah University of Science and Technology, December 2015"},{"key":"27_CR6","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"111","DOI":"10.1007\/978-3-642-11515-8_10","volume-title":"High Performance Embedded Architectures and Compilers","author":"A Monakov","year":"2010","unstructured":"Monakov, A., Lokhmotov, A., Avetisyan, A.: Automatically tuning sparse matrix-vector multiplication for GPU architectures. In: Patt, Y.N., Foglia, P., Duesterwald, E., Faraboschi, P., Martorell, X. (eds.) HiPEAC 2010. LNCS, vol. 5952, pp. 111\u2013125. Springer, Heidelberg (2010). doi: 10.1007\/978-3-642-11515-8_10"},{"key":"27_CR7","unstructured":"NERSC: Measuring arithmetic intensity. https:\/\/www.nersc.gov\/users\/application-performance\/measuring-arithmetic-intensity"},{"issue":"3","key":"27_CR8","doi-asserted-by":"crossref","first-page":"1599","DOI":"10.1093\/gji\/ggu222","volume":"198","author":"PV Petrov","year":"2014","unstructured":"Petrov, P.V., Newman, G.A.: Three-dimensional inverse modelling of damped elastic wave propagation in the fourier domain. Geophys. J. Int. 198(3), 1599\u20131617 (2014)","journal-title":"Geophys. J. Int."},{"issue":"4","key":"27_CR9","doi-asserted-by":"publisher","first-page":"T137","DOI":"10.1190\/geo2011-0238.1","volume":"77","author":"PV Petrov","year":"2012","unstructured":"Petrov, P.V., Newman, G.A.: 3d finite-difference modeling of elastic wave propagation in the laplace-fourier domain. Geophysics 77(4), T137\u2013T155 (2012). doi: 10.1190\/geo2011-0238.1","journal-title":"Geophysics"},{"key":"27_CR10","doi-asserted-by":"crossref","unstructured":"Stengel, H., Treibig, J., Hager, G., Wellein, G.: Quantifying performance bottlenecks of stencil computations using the execution-cache-memory model. In: Proceedings of the 29th ACM on International Conference on Supercomputing, pp. 207\u2013216. ACM (2015)","DOI":"10.1145\/2751205.2751240"},{"key":"27_CR11","unstructured":"Tal, A.: Intel software development emulator. https:\/\/software.intel.com\/en-us\/articles\/intel-software-development-emulator"},{"key":"27_CR12","unstructured":"Williams, S.: Auto-tuning performance on multicore computers. Ph.D. thesis, EECS Department, University of California, Berkeley, December 2008"},{"issue":"4","key":"27_CR13","doi-asserted-by":"crossref","first-page":"65","DOI":"10.1145\/1498765.1498785","volume":"52","author":"S Williams","year":"2009","unstructured":"Williams, S., Watterman, A., Patterson, D.: Roofline: an insightful visual performance model for floating-point programs and multicore architectures. Commun. ACM. 52(4), 65\u201376 (2009)","journal-title":"Commun. ACM."},{"key":"27_CR14","unstructured":"Williams, S., Stralen, B.V., Ligocki, T., Oliker, L., Cordery, M., Lo, L.: Roofline performance model. http:\/\/crd.lbl.gov\/departments\/computer-science\/PAR\/research\/roofline\/"}],"container-title":["Lecture Notes in Computer Science","High Performance Computing"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-46079-6_27","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2017,6,24]],"date-time":"2017-06-24T20:25:24Z","timestamp":1498335924000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-46079-6_27"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016]]},"ISBN":["9783319460789","9783319460796"],"references-count":14,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-46079-6_27","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2016]]}}}