{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T04:51:39Z","timestamp":1755838299085,"version":"3.40.4"},"publisher-location":"Berlin, Heidelberg","reference-count":13,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783642369483"},{"type":"electronic","value":"9783642369490"}],"license":[{"start":{"date-parts":[[2013,1,1]],"date-time":"2013-01-01T00:00:00Z","timestamp":1356998400000},"content-version":"tdm","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":[[2013]]},"DOI":"10.1007\/978-3-642-36949-0_50","type":"book-chapter","created":{"date-parts":[[2013,2,15]],"date-time":"2013-02-15T01:34:27Z","timestamp":1360892067000},"page":"451-460","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":14,"title":["Performance Patterns and Hardware Metrics on Modern Multicore Processors: Best Practices for Performance Engineering"],"prefix":"10.1007","author":[{"given":"Jan","family":"Treibig","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Georg","family":"Hager","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gerhard","family":"Wellein","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"issue":"5","key":"50_CR1","doi-asserted-by":"publisher","first-page":"1634","DOI":"10.1137\/040604078","volume":"28","author":"F. G\u00fcnther","year":"2006","unstructured":"G\u00fcnther, F., Mehl, M., P\u00f6gl, M., Zenger, C.: A cache-aware algorithm for PDEs on hierarchical data structures based on space-filling curves. SIAM Journal on Scientific Computing\u00a028(5), 1634\u20131650 (2006), http:\/\/www5.in.tum.de\/pub\/int\/guenther_siam06.pdf","journal-title":"SIAM Journal on Scientific Computing"},{"key":"50_CR2","first-page":"219","volume":"3","author":"T. Klug","year":"2011","unstructured":"Klug, T., Ott, M., Weidendorfer, J., Trinitis, C.: Autopin \u2013 automated optimization of thread-to-core pinning on multicore systems. T. HiPEAC\u00a03, 219\u2013235 (2011)","journal-title":"T. HiPEAC"},{"key":"50_CR3","doi-asserted-by":"crossref","unstructured":"Chen, H., Chung Hsu, W., Lu, J., Chung Yew, P.: Dynamic trace selection using performance monitoring hardware sampling. In: Proceedings of the 1st International Symposium on Code Generation and Optimization, pp. 79\u201390 (2003)","DOI":"10.1109\/CGO.2003.1191535"},{"key":"50_CR4","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/SC.2010.41","volume-title":"Proceedings of the 2010 ACM\/IEEE International Conference for High Performance Computing, Networking, Storage and Analysis, SC 2010","author":"M. Burtscher","year":"2010","unstructured":"Burtscher, M., Kim, B.-D., Diamond, J., McCalpin, J., Koesterke, L., Browne, J.: PerfExpert: An easy-to-use performance diagnosis tool for HPC applications. In: Proceedings of the 2010 ACM\/IEEE International Conference for High Performance Computing, Networking, Storage and Analysis, SC 2010, pp. 1\u201311. IEEE Computer Society, Washington, DC (2010), http:\/\/dx.doi.org\/10.1109\/SC.2010.41 , ISBN 978-1-4244-7559-9"},{"key":"50_CR5","unstructured":"de la Cruz, R., Araya-Polo, M.: Towards a multi-level cache performance model for 3d stencil computation. Procedia Computer Science\u00a04, 2146\u20132155 (2011); Proceedings of the International Conference on Computational Science, ICCS 2011, http:\/\/www.sciencedirect.com\/science\/article\/pii\/S1877050911002936"},{"key":"50_CR6","doi-asserted-by":"crossref","unstructured":"Pfeiffer, W., Wright, N.: Modeling and predicting application performance on parallel computers using HPC challenge benchmarks. In: IEEE International Symposium on Parallel and Distributed Processing, IPDPS 2008, pp. 1\u201312 (2008) ISSN 1530-2075","DOI":"10.1109\/IPDPS.2008.4536278"},{"key":"50_CR7","unstructured":"Williams, S.W., Waterman, A., Patterson, D.A.: Roofline: An insightful visual performance model for floating-point programs and multicore architectures. Tech. Rep. UCB\/EECS-2008-134, EECS Department, University of California, Berkeley (October 2008) http:\/\/www.eecs.berkeley.edu\/Pubs\/TechRpts\/2008\/EECS-2008-134.html"},{"key":"50_CR8","first-page":"207","volume-title":"The First International Workshop on Parallel Software Tools and Tool Infrastructures, PSTI 2010","author":"J. Treibig","year":"2010","unstructured":"Treibig, J., Hager, G., Wellein, G.: LIKWID: A lightweight performance-oriented tool suite for x86 multicore environments. In: The First International Workshop on Parallel Software Tools and Tool Infrastructures, PSTI 2010, pp. 207\u2013216. IEEE Computer Society, Los Alamitos (2010), http:\/\/dx.doi.org\/10.1109\/ICPPW.2010.38"},{"key":"50_CR9","unstructured":"LIKWID performance tools, http:\/\/code.google.com\/p\/likwid"},{"issue":"2","key":"50_CR10","doi-asserted-by":"crossref","first-page":"C42","DOI":"10.1137\/110830125","volume":"34","author":"K. Iglberger","year":"2012","unstructured":"Iglberger, K., Hager, G., Treibig, J., R\u00fcde, U.: Expression templates revisited: A performance analysis of current ET methodologies. SIAM Journal on Scientific Computing\u00a034(2), C42\u2013C69 (2012), http:\/\/dx.doi.org\/10.1137\/110830125","journal-title":"SIAM Journal on Scientific Computing"},{"key":"50_CR11","unstructured":"Iglberger, K., Hager, G., Treibig, J., R\u00fcde, U.: High performance smart expression template math libraries. In: Proceedings of APMM 2012, the 2nd International Workshop on New Algorithms and Programming Models for the Manycore Era at HPCS 2012, Madrid, Spain, July 2-6 (accepted, 2012)"},{"key":"50_CR12","unstructured":"Treibig, J., Hager, G., Hofmann, H.G., Hornegger, J., Wellein, G.: Pushing the limits for medical image reconstruction on recent standard multicore processors. International Journal of High Performance Computing Applications (accepted), http:\/\/arxiv.org\/abs\/1104.5243"},{"key":"50_CR13","unstructured":"Intel architecture code analyzer, http:\/\/software.intel.com\/en-us\/articles\/intel-architecture-code-analyzer\/"}],"container-title":["Lecture Notes in Computer Science","Euro-Par 2012: Parallel Processing Workshops"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-36949-0_50","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,29]],"date-time":"2025-04-29T21:22:06Z","timestamp":1745961726000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-36949-0_50"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013]]},"ISBN":["9783642369483","9783642369490"],"references-count":13,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-36949-0_50","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2013]]},"assertion":[{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}