{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T00:50:44Z","timestamp":1740099044929,"version":"3.37.3"},"publisher-location":"Cham","reference-count":14,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319780238"},{"type":"electronic","value":"9783319780245"}],"license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018]]},"DOI":"10.1007\/978-3-319-78024-5_50","type":"book-chapter","created":{"date-parts":[[2018,3,22]],"date-time":"2018-03-22T08:28:25Z","timestamp":1521707305000},"page":"579-589","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["On the Tunability of a New Hessenberg Reduction Algorithm Using Parallel Cache Assignment"],"prefix":"10.1007","author":[{"given":"Mahmoud","family":"Eljammaly","sequence":"first","affiliation":[]},{"given":"Lars","family":"Karlsson","sequence":"additional","affiliation":[]},{"given":"Bo","family":"K\u00e5gstr\u00f6m","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2018,3,23]]},"reference":[{"issue":"4","key":"50_CR1","doi-asserted-by":"publisher","first-page":"929","DOI":"10.1137\/S0895479801384573","volume":"23","author":"K Braman","year":"2002","unstructured":"Braman, K., Byers, R., Mathias, R.: The multishift QR algorithm. Part I: maintaining well-focused shifts and level 3 performance. SIMAX 23(4), 929\u2013947 (2002). \nhttps:\/\/doi.org\/10.1137\/S0895479801384573","journal-title":"SIMAX"},{"issue":"4","key":"50_CR2","doi-asserted-by":"publisher","first-page":"948","DOI":"10.1137\/S0895479801384585","volume":"23","author":"K Braman","year":"2002","unstructured":"Braman, K., Byers, R., Mathias, R.: The multishift QR algorithm. Part II: aggressive early deflation. SIMAX 23(4), 948\u2013973 (2002). \nhttps:\/\/doi.org\/10.1137\/S0895479801384585","journal-title":"SIMAX"},{"issue":"1","key":"50_CR3","doi-asserted-by":"publisher","first-page":"38","DOI":"10.1016\/j.parco.2008.10.002","volume":"35","author":"A Buttari","year":"2009","unstructured":"Buttari, A., Langou, J., Kurzak, J., Dongarra, J.: A class of parallel tiled linear algebra algorithms for multicore architectures. Parallel Comput. 35(1), 38\u201353 (2009). \nhttps:\/\/doi.org\/10.1016\/j.parco.2008.10.002","journal-title":"Parallel Comput."},{"key":"50_CR4","doi-asserted-by":"publisher","unstructured":"Castaldo, A., Whaley, R.C.: Achieving scalable parallelization for the Hessenberg factorization. In: 2011 IEEE International Conference on Cluster Computing (CLUSTER), pp. 65\u201373. IEEE (2011). \nhttps:\/\/doi.org\/10.1109\/CLUSTER.2011.16","DOI":"10.1109\/CLUSTER.2011.16"},{"issue":"4","key":"50_CR5","doi-asserted-by":"publisher","first-page":"22","DOI":"10.1145\/2491491.2491493","volume":"39","author":"A Castaldo","year":"2013","unstructured":"Castaldo, A., Whaley, R.C., Samuel, S.: Scaling LAPACK panel operations using parallel cache assignment. ACM TOMS 39(4), 22 (2013). \nhttps:\/\/doi.org\/10.1145\/2491491.2491493","journal-title":"ACM TOMS"},{"key":"50_CR6","unstructured":"Eljammaly, M., Karlsson, L., K\u00e5gstr\u00f6m, B.: Evaluation of the tunability of a new NUMA-aware Hessenberg reduction algorithm. NLAFET Working Note 8, December 2016. Also as Report UMINF 16.22, Department of Computing Science, Ume\u00e5 University, SE-901 87 Ume\u00e5, Sweden"},{"issue":"4","key":"50_CR7","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/2699471","volume":"41","author":"R Granat","year":"2015","unstructured":"Granat, R., K\u00e5gstr\u00f6m, B., Kressner, D., Shao, M.: Algorithm 953: parallel library software for the multishift QR algorithm with aggressive early deflation. ACM Trans. Math. Softw. 41(4), 1\u201323 (2015). \nhttps:\/\/doi.org\/10.1145\/2699471\n\n. Article no. 29","journal-title":"ACM Trans. Math. Softw."},{"key":"50_CR8","doi-asserted-by":"publisher","unstructured":"Hasan, M.R., Whaley, R.C.: Effectively exploiting parallel scale for all problem sizes in LU factorization. In: 2014 IEEE 28th International Parallel and Distributed Processing Symposium, pp. 1039\u20131048. IEEE (2014). \nhttps:\/\/doi.org\/10.1109\/IPDPS.2014.109","DOI":"10.1109\/IPDPS.2014.109"},{"issue":"12","key":"50_CR9","doi-asserted-by":"publisher","first-page":"771","DOI":"10.1016\/j.parco.2011.05.001","volume":"37","author":"L Karlsson","year":"2011","unstructured":"Karlsson, L., K\u00e5gstr\u00f6m, B.: Parallel two-stage reduction to Hessenberg form using dynamic scheduling on shared-memory architectures. Parallel Comput. 37(12), 771\u2013782 (2011). \nhttps:\/\/doi.org\/10.1016\/j.parco.2011.05.001\n\n. 6th International Workshop on Parallel Matrix Algorithms and Applications (PMAA 2010)","journal-title":"Parallel Comput."},{"issue":"2","key":"50_CR10","doi-asserted-by":"publisher","first-page":"13:1","DOI":"10.1145\/2427023.2427030","volume":"39","author":"J Poulson","year":"2013","unstructured":"Poulson, J., Marker, B., van de Geijn, R.A., Hammond, J.R., Romero, N.A.: Elemental: a new framework for distributed memory dense matrix computations. ACM Trans. Math. Softw. 39(2), 13:1\u201313:24 (2013). \nhttps:\/\/doi.org\/10.1145\/2427023.2427030","journal-title":"ACM Trans. Math. Softw."},{"issue":"2","key":"50_CR11","doi-asserted-by":"publisher","first-page":"180","DOI":"10.1145\/1141885.1141887","volume":"32","author":"G Quintana-Ort\u00ed","year":"2006","unstructured":"Quintana-Ort\u00ed, G., van de Geijn, R.: Improving the performance of reduction to Hessenberg form. ACM TOMS 32(2), 180\u2013194 (2006). \nhttps:\/\/doi.org\/10.1145\/1141885.1141887","journal-title":"ACM TOMS"},{"key":"50_CR12","doi-asserted-by":"publisher","unstructured":"Schreiber, R., Loan, C.V.: A storage efficient WY representation for products of Householder transformations. Technical report, no. 1 (1989). \nhttps:\/\/doi.org\/10.1137\/0910005","DOI":"10.1137\/0910005"},{"key":"50_CR13","doi-asserted-by":"publisher","unstructured":"Tomov, S., Dongarra, J., Baboulin, M.: Towards dense linear algebra for hybrid GPU accelerated manycore systems. Parallel Comput. 36(5\u20136), 232\u2013240 (2010). \nhttps:\/\/doi.org\/10.1016\/j.parco.2009.12.005","DOI":"10.1016\/j.parco.2009.12.005"},{"issue":"6","key":"50_CR14","doi-asserted-by":"publisher","first-page":"56","DOI":"10.1109\/MCSE.2009.207","volume":"11","author":"FGV Zee","year":"2009","unstructured":"Zee, F.G.V., Chan, E., van de Geijn, R.A., Quintana-Ort\u00ed, E.S., Quintana-Ort\u00ed, G.: The libflame library for dense matrix computations. Comput. Sci. Eng. 11(6), 56\u201363 (2009). \nhttps:\/\/doi.org\/10.1109\/MCSE.2009.207","journal-title":"Comput. Sci. Eng."}],"container-title":["Lecture Notes in Computer Science","Parallel Processing and Applied Mathematics"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-78024-5_50","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2018,3,22]],"date-time":"2018-03-22T08:47:29Z","timestamp":1521708449000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-78024-5_50"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783319780238","9783319780245"],"references-count":14,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-78024-5_50","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2018]]}}}