{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,9]],"date-time":"2024-09-09T14:59:39Z","timestamp":1725893979645},"publisher-location":"Berlin, Heidelberg","reference-count":16,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783642330773"},{"type":"electronic","value":"9783642330780"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2012]]},"DOI":"10.1007\/978-3-642-33078-0_31","type":"book-chapter","created":{"date-parts":[[2012,9,3]],"date-time":"2012-09-03T21:37:49Z","timestamp":1346708269000},"page":"428-442","source":"Crossref","is-referenced-by-count":4,"title":["The Impact of Global Communication Latency at Extreme Scales on Krylov Methods"],"prefix":"10.1007","author":[{"given":"Thomas J.","family":"Ashby","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pieter","family":"Ghysels","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wim","family":"Heirman","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wim","family":"Vanroose","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"key":"31_CR1","unstructured":"Retrieved from MVAPICH2 website (2012), http:\/\/mvapich.cse.ohio-state.edu\/performance\/interNode.shtml (2011)"},{"key":"31_CR2","unstructured":"Adiga, N., et al.: An overview of the BlueGene\/L supercomputer. In: ACM\/IEEE 2002 Conference on Supercomputing, p. 60 (November 2002)"},{"issue":"11","key":"31_CR3","doi-asserted-by":"publisher","first-page":"36","DOI":"10.1109\/MC.2009.370","volume":"42","author":"Y. Ajima","year":"2009","unstructured":"Ajima, Y., Sumimoto, S., Shimizu, T.: Tofu: A 6D mesh\/torus interconnect for exascale computers. Computer\u00a042(11), 36\u201340 (2009)","journal-title":"Computer"},{"key":"31_CR4","doi-asserted-by":"crossref","unstructured":"Arimilli, B., et al.: The PERCS high-performance interconnect. In: IEEE HOTI 2010, pp. 75\u201382 (August 2010)","DOI":"10.1109\/HOTI.2010.16"},{"key":"31_CR5","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"202","DOI":"10.1007\/11688839_17","volume-title":"Compiler Construction","author":"T.J. Ashby","year":"2006","unstructured":"Ashby, T.J., O\u2019Boyle, M.: Iterative collective loop fusion. In: Mycroft, A., Zeller, A. (eds.) CC 2006. LNCS, vol.\u00a03923, pp. 202\u2013216. Springer, Heidelberg (2006)"},{"key":"31_CR6","series-title":"SC 2011","first-page":"26","volume-title":"Proceedings of 2011 International Conference for High Performance Computing, Networking, Storage and Analysis","author":"D. Chen","year":"2011","unstructured":"Chen, D., Eisley, N.A., Heidelberger, P., Senger, R.M., Sugawara, Y., Kumar, S., Salapura, V., Satterfield, D.L., Steinmacher-Burow, B., Parker, J.J.: The IBM BlueGene\/Q interconnection network and message unit. In: Proceedings of 2011 International Conference for High Performance Computing, Networking, Storage and Analysis. SC 2011, pp. 26\u201327. ACM, New York (2011)"},{"key":"31_CR7","doi-asserted-by":"crossref","unstructured":"Ghysels, P., Ashby, T.J., Meerbergen, K., Vanroose, W.: Hiding global communication latency in the GMRES algorithm on massively parallel machines (to be published, 2012)","DOI":"10.1137\/12086563X"},{"key":"31_CR8","unstructured":"Gmeiner, B., Gradl, T., K\u00f6stler, H., R\u00fcde, U.: Analysis of a flat highly parallel geometric multigrid algorithm for hierarchical hybrid grids. Technical report, Dept. Comp. Sci., Universit\u00e4t Erlangen-N\u00fcrnberg (2011)"},{"key":"31_CR9","unstructured":"Hern\u00e1ndez, V., Rom\u00e1n, J.E., Tom\u00e1s, A.: A parallel variant of the Gram-Schmidt process with reorthogonalization. In: PARCO, pp. 221\u2013228 (2005)"},{"key":"31_CR10","doi-asserted-by":"crossref","unstructured":"Hoefler, T., Lumsdaine, A.: Overlapping communication and computation with high level communication routines. In: Proceedings of the 8th IEEE Symposium on Cluster Computing and the Grid (CCGrid 2008) (May 2008)","DOI":"10.1109\/CCGRID.2008.15"},{"key":"31_CR11","doi-asserted-by":"crossref","unstructured":"Hoefler, T., Schneider, T., Lumsdaine, A.: Characterizing the influence of system noise on large-scale applications by simulation. In: ACM\/IEEE Supercomputing 2010, pp. 1\u201311 (2010)","DOI":"10.1109\/SC.2010.12"},{"key":"31_CR12","doi-asserted-by":"crossref","unstructured":"Moody, A., Fernandez, J., Petrini, F., Panda, D.K.: Scalable NIC-based reduction on large-scale clusters. In: ACM\/IEEE Supercomputing 2003, pages 59 (2003)","DOI":"10.1145\/1048935.1050209"},{"key":"31_CR13","unstructured":"Stevens, R., White, A., et al.: Architectures and technology for extreme scale computing. Technical report, ASCR Scientic Grand Challenges Workshop Series (December 2009)"},{"key":"31_CR14","doi-asserted-by":"crossref","unstructured":"Tianruo Yang, L., Brent, R.: The improved Krylov subspace methods for large and sparse linear systems on bulk synchronous parallel architectures. In: IEEE IPDPS 2003, p. 11 (April 2003)","DOI":"10.1109\/IPDPS.2002.1016651"},{"key":"31_CR15","doi-asserted-by":"crossref","unstructured":"Udipi, A.N., Muralimanohar, N., Balasubramonian, R., Davis, A., Jouppi, N.P.: Combining memory and a controller with photonics through 3D-stacking to enable scalable and energy-efficient systems. In: ISCA 2011, pp. 425\u2013436 (2011)","DOI":"10.1145\/2024723.2000115"},{"key":"31_CR16","doi-asserted-by":"crossref","unstructured":"Woo, D.H., Seong, N.H., Lewis, D., Lee, H.-H.: An optimized 3D-stacked memory architecture by exploiting excessive, high-density TSV bandwidth. In: IEEE HPCA 2010, pp. 1\u201312 (January 2010)","DOI":"10.1109\/HPCA.2010.5416628"}],"container-title":["Lecture Notes in Computer Science","Algorithms and Architectures for Parallel Processing"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-33078-0_31.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,28]],"date-time":"2022-01-28T03:47:25Z","timestamp":1643341645000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-33078-0_31"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2012]]},"ISBN":["9783642330773","9783642330780"],"references-count":16,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-33078-0_31","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2012]]}}}