{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T01:56:10Z","timestamp":1742954170509,"version":"3.40.3"},"publisher-location":"Cham","reference-count":38,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319201184"},{"type":"electronic","value":"9783319201191"}],"license":[{"start":{"date-parts":[[2015,1,1]],"date-time":"2015-01-01T00:00:00Z","timestamp":1420070400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2015,1,1]],"date-time":"2015-01-01T00:00:00Z","timestamp":1420070400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2015]]},"DOI":"10.1007\/978-3-319-20119-1_14","type":"book-chapter","created":{"date-parts":[[2015,6,19]],"date-time":"2015-06-19T10:36:48Z","timestamp":1434710208000},"page":"179-196","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["Lattice-CSC: Optimizing and Building an Efficient Supercomputer for Lattice-QCD and to Achieve First Place in Green500"],"prefix":"10.1007","author":[{"given":"David","family":"Rohr","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Matthias","family":"Bach","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gvozden","family":"Ne\u0161kovi\u0107","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Volker","family":"Lindenstruth","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Christopher","family":"Pinke","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Owe","family":"Philipsen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2015,6,20]]},"reference":[{"key":"14_CR1","unstructured":"Rohr, D., Kalcher, S., Bach, M., Alaqeeli, A., Alzaid, H., et al.: An energy-efficient multi-GPU supercomputer. In: Proceedings of the 16th IEEE International Conference on High Performance Computing and Communications, IEEE, Paris, France (2014)"},{"key":"14_CR2","unstructured":"Gupta, R.: Introduction to Lattice QCD (1998). http:\/\/arxiv.org\/abs\/hep-lat\/9807028"},{"key":"14_CR3","doi-asserted-by":"crossref","unstructured":"Babich, R., Clark, M., Jo\u00f3, B., Shi, G., Brower, R. C., Gottlieb, S.: Scaling lattice QCD beyond 100 GPUs. In: SC 2011 Proceedings of 2011 International Conference for High Performance Computing, Networking, Storage and Analysis, pp. 70:1\u201370:11 (2011)","DOI":"10.1145\/2063384.2063478"},{"key":"14_CR4","doi-asserted-by":"publisher","first-page":"2042","DOI":"10.1016\/j.cpc.2013.03.020","volume":"184","author":"M Bach","year":"2013","unstructured":"Bach, M., Lindenstruth, V., Philipsen, O., Pinke, C.: Lattice QCD based on OpenCL. Comput. Phys. Commun. 184, 2042\u20132052 (2013)","journal-title":"Comput. Phys. Commun."},{"key":"14_CR5","doi-asserted-by":"crossref","unstructured":"Bach, M., Lindenstruth, V., Pinke, C., Philipsen, O.: Twisted-Mass Lattice QCD using OpenCL. In: PoS LATTICE2013, p. 032 (2013)","DOI":"10.1016\/j.cpc.2013.03.020"},{"key":"14_CR6","unstructured":"Philipsen, O., Pinke, C., Sciarra, A., Bach, M.: CL2QCD - lattice QCD based on OpenCL. In: PoS LATTICE2014, p. 038 (2014)"},{"key":"14_CR7","unstructured":"http:\/\/code.compeng.uni-frankfurt.de\/projects\/clhmc"},{"key":"14_CR8","unstructured":"Khronos OpenCL Registry, OpenCL API and C Language Specifications. https:\/\/www.khronos.org\/registry\/cl\/"},{"key":"14_CR9","unstructured":"NVIDIA, CUDA Toolkit Documentation. http:\/\/docs.nvidia.com\/cuda\/index.html"},{"issue":"9","key":"14_CR10","doi-asserted-by":"publisher","first-page":"094504","DOI":"10.1103\/PhysRevD.89.094504","volume":"89","author":"O Philipsen","year":"2014","unstructured":"Philipsen, O., Pinke, C.: The nature of the Roberge-Weiss transition in $$N_f=2$$. Phys. Rev. D 89(9), 094504 (2014)","journal-title":"Phys. Rev. D"},{"key":"14_CR11","unstructured":"Philipsen, O., Bach, M., Lindenstruth, V., Pinke, C.: The thermal quark hadron transition in lattice QCD with two quark flavours. In: Proceedings of Conference: C14\u201302-12.1, pp. 33\u201340"},{"issue":"9","key":"14_CR12","doi-asserted-by":"publisher","first-page":"803","DOI":"10.1002\/cpe.728","volume":"15","author":"J Dongarra","year":"2003","unstructured":"Dongarra, J., Luszczek, P., Petitet, A.: The LINPACK benchmark: past, present and future. Concurrency Comput.: Pract. Experience 15(9), 803\u2013820 (2003)","journal-title":"Concurrency Comput.: Pract. Experience"},{"key":"14_CR13","unstructured":"TOP500 Supercomputer Sites. http:\/\/www.top500.org"},{"issue":"3\u20134","key":"14_CR14","doi-asserted-by":"publisher","first-page":"153","DOI":"10.1007\/s00450-011-0161-5","volume":"26","author":"M Bach","year":"2011","unstructured":"Bach, M., Kretz, M., Lindenstruth, V., Rohr, D.: Optimized HPL for AMD GPU and multi-core CPU usage. Comput. Sci. - Res. Dev. 26(3\u20134), 153\u2013164 (2011)","journal-title":"Comput. Sci. - Res. Dev."},{"key":"14_CR15","doi-asserted-by":"crossref","unstructured":"Rohr, D., Bach, M., Kretz, M., Lindenstruth, V.: Multi-GPU DGEMM and HPL on highly energy efficient clusters. In: IEEE Micro, Special Issue, CPU, GPU, and Hybrid Computing (2011)","DOI":"10.1109\/MM.2011.66"},{"key":"14_CR16","doi-asserted-by":"crossref","unstructured":"Sharma, S., Hsu, C., Feng, W.: Making a case for a Green500 list. In: Proceedings of the 20th IEEE International Parallel Distributed Processing Symposium p. 343 (2006)","DOI":"10.1109\/IPDPS.2006.1639600"},{"key":"14_CR17","unstructured":"The Green500 List. http:\/\/www.green500.org"},{"key":"14_CR18","doi-asserted-by":"crossref","unstructured":"Bach, M., De Cuveland, J., Ebermann, H., Eschweiler, D., Kretz, M., et al.: The LOEWE-CSC: a comprehensive approach for a power efficient general purpose supercomputer. In: 21st Euromicro International Conference on Parallel, Distributed and Network-Based Processing (2013)","DOI":"10.1109\/PDP.2013.55"},{"key":"14_CR19","unstructured":"Rohr, D., Nescovic, G., Radtke, M., Lindenstruth, V.: The L-CSC cluster: greenest supercomputer in the world in Green500 list of November 2014. In: Proceedings of Supercomputing Frontiers (2015)"},{"key":"14_CR20","unstructured":"High Energy Accelerator Research Organization. http:\/\/www.kek.jp"},{"key":"14_CR21","unstructured":"PEZY Computing, PEZY-SC Many Core Processor (2014). http:\/\/www.pezy.co.jp\/en\/products\/pezy-sc.html"},{"key":"14_CR22","unstructured":"http:\/\/www.gsic.titech.ac.jp\/tsubame"},{"key":"14_CR23","volume-title":"How to Build a Beowulf: A Guide to the Implementation and Application of PC Clusters","author":"TL Sterling","year":"1999","unstructured":"Sterling, T.L.: How to Build a Beowulf: A Guide to the Implementation and Application of PC Clusters. MIT Press, Cambridge (1999)"},{"key":"14_CR24","unstructured":"Intel Corporation, Intel MKL BLAS Library. https:\/\/software.intel.com\/en-us\/intel-mkl"},{"key":"14_CR25","doi-asserted-by":"crossref","unstructured":"Rohr, D., Lindenstruth, V.: A flexible and portable large-scale DGEMM library for linpack on next-generation multi-GPU systems. In: 23rd Euromicro International Conference on Parallel, Distributed and Network-Based Processing (2015)","DOI":"10.1109\/PDP.2015.89"},{"key":"14_CR26","unstructured":"https:\/\/www.kernel.org\/pub\/linux\/utils\/kernel\/cpufreq\/"},{"key":"14_CR27","unstructured":"Kidd, T.I.: What exactly is a P-state? (2008). https:\/\/software.intel.com\/en-us\/blogs\/2008\/05\/29\/what-exactly-is-a-p-state-pt-1"},{"key":"14_CR28","unstructured":"EEHPC Working Group: Energy Efficient High Performance Computing Power Measurement Methodology v1.2 RC 2"},{"key":"14_CR29","unstructured":"ZES Zimmer: LMG95 1 Phase Power Analyzer. http:\/\/www.zes.com\/en\/Products\/Precision-Power-Analyzer\/LMG95"},{"key":"14_CR30","unstructured":"Rohr, D.: On Development, Feasibility, and Limits of Highly Efficient CPU and GPU Programs in Several Fields. Dissertation Thesis (2013)"},{"key":"14_CR31","doi-asserted-by":"publisher","first-page":"1517","DOI":"10.1016\/j.cpc.2010.05.002","volume":"181","author":"MA Clark","year":"2010","unstructured":"Clark, M.A., Babich, R., Barros, K., Brower, R.C., Rebbi, C.: Solving lattice QCD systems of equations using mixed precision solvers on GPUs. Comput. Phys. Commun. 181, 1517\u20131528 (2010)","journal-title":"Comput. Phys. Commun."},{"issue":"04","key":"14_CR32","doi-asserted-by":"publisher","first-page":"637","DOI":"10.1142\/S0129053393000268","volume":"05","author":"C Battista","year":"1993","unstructured":"Battista, C., Cabasino, S., Marzano, F., Paolucci, P., Pech, J., et al.: APE-100 computer: (i) the architecture. Int. J. High Speed Comput. 05(04), 637\u2013656 (1993)","journal-title":"Int. J. High Speed Comput."},{"key":"14_CR33","unstructured":"Boyle, P. A., Chen, D., Christ, N. H., Clark, M. A., Cohen, S. D., et al.: QCDOC: a 10 teraflops computer for tightly-coupled calculations. In: SC 2004 Proceedings of 2004 International Conference for High Performance Computing, Networking, Storage and Analysis (2004)"},{"key":"14_CR34","unstructured":"Baier, H., Boettiger, H., Drochner, M., Eicker, N., Fischer, U.: QPACE - a QCD parallel computer based on cell processors. In: Proceedings of Science, p. 21, November 2009"},{"key":"14_CR35","first-page":"012080","volume":"78","author":"P Vranas","year":"2007","unstructured":"Vranas, P.: QCD and the BlueGene. J. Phys.: Conf. Ser. 78, 012080 (2007)","journal-title":"J. Phys.: Conf. Ser."},{"key":"14_CR36","doi-asserted-by":"crossref","unstructured":"Smelyanskiy, M., Vaidyanathan, K., Choi, J., Jo\u00f3, B., Chhugani, J., et al.: High-performance lattice QCD for Multi-Core based parallel systems using a cache-friendly hybrid threaded-MPI approach. In: SC 2011 Proceedings of 2011 International Conference for High Performance Computing, Networking, Storage and Analysis (2011)","DOI":"10.1145\/2063384.2063477"},{"key":"14_CR37","doi-asserted-by":"crossref","unstructured":"Winter, F. T., Clark, M. A., Edwards, R. G., Jo\u00f3, B.: A framework for lattice QCD calculations on GPUs. In: Proceedings of the 2014 IEEE 28th International Parallel and Distributed Processing Symposium, pp. 1073\u20131082 (2014)","DOI":"10.1109\/IPDPS.2014.112"},{"key":"14_CR38","series-title":"Lecture Notes in Computer Science","first-page":"40","volume-title":"Lattice QCD on Intel Xeon Phi Coprocessors","author":"B Jo\u00f3","year":"2014","unstructured":"Jo\u00f3, B., Kalamkar, D.D., Vaidyanathan, K., Smelyanskiy, M., Pamnany, K., et al.: Supercomputing. In: Kunkel, J.M., Ludwig, T., Meuer, H.W. (eds.) ISC 2013. Lecture Notes in Computer Science, vol. 7905, pp. 40\u201354. Springer, Heidelberg (2014)"}],"container-title":["Lecture Notes in Computer Science","High Performance Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-20119-1_14","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,2,8]],"date-time":"2023-02-08T12:50:45Z","timestamp":1675860645000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-319-20119-1_14"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015]]},"ISBN":["9783319201184","9783319201191"],"references-count":38,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-20119-1_14","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2015]]},"assertion":[{"value":"20 June 2015","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}}]}}