{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T17:17:56Z","timestamp":1743095876930,"version":"3.40.3"},"publisher-location":"Cham","reference-count":30,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319102139"},{"type":"electronic","value":"9783319102146"}],"license":[{"start":{"date-parts":[[2014,1,1]],"date-time":"2014-01-01T00:00:00Z","timestamp":1388534400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2014,1,1]],"date-time":"2014-01-01T00:00:00Z","timestamp":1388534400000},"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":[[2014]]},"DOI":"10.1007\/978-3-319-10214-6_4","type":"book-chapter","created":{"date-parts":[[2014,9,30]],"date-time":"2014-09-30T11:56:12Z","timestamp":1412078172000},"page":"73-87","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Analysis of Data Reuse in Task-Parallel Runtimes"],"prefix":"10.1007","author":[{"given":"Miquel","family":"Peric\u00e0s","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Abdelhalim","family":"Amer","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kenjiro","family":"Taura","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Satoshi","family":"Matsuoka","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2014,10,1]]},"reference":[{"unstructured":"OpenMP ARB: Openmp specification (July 2013), http:\/\/www.openmp.org\/mp-documents\/OpenMP4.0.0.pdf","key":"4_CR1"},{"unstructured":"Intel Corporation: Threading building blocks, https:\/\/www.threadingbuildingblocks.org\/","key":"4_CR2"},{"unstructured":"MIT Csail Supertech Research Group: The cilk project, http:\/\/supertech.csail.mit.edu\/cilk\/","key":"4_CR3"},{"doi-asserted-by":"crossref","unstructured":"Frigo, M., Leiserson, C.E., Randall, K.H.: The Implementation of the Cilk-5 Multithreaded Language. In: Proceedings of SIGPLAN 1998 (June 1998)","key":"4_CR4","DOI":"10.1145\/277650.277725"},{"doi-asserted-by":"crossref","unstructured":"Mohr, E., Kranz, D.A., Halstead, R.H.: Lazy Task Creation: A technique for Increasing the Granularity of Parallel Programs. IEEE Transactions on Parallel and Distributed Systems 2(3) (July 1991)","key":"4_CR5","DOI":"10.1109\/71.86103"},{"doi-asserted-by":"crossref","unstructured":"Olivier, S.L., de Supinski, B.R., Schulz, M., Prins, J.F.: Characterizing and Mitigating Work Time Inflation in Task Parallel Programs. In: Proceedings of SC 2012 (November 2012)","key":"4_CR6","DOI":"10.1109\/SC.2012.27"},{"doi-asserted-by":"crossref","unstructured":"Tallent, N.R., Mellor-Crummey, J.M.: Effective Performance Measurement and Analysis of Multithreaded Applications. In: Proceedings of PPoPP 2009 (February 2009)","key":"4_CR7","DOI":"10.1145\/1504176.1504210"},{"doi-asserted-by":"crossref","unstructured":"Kn\u00fcpfer, A., Brunst, H., Doleschal, J., Jurenz, M., Lieber, M., Mickler, H., M\u00fcller, M.S., Nagel, W.E.: The Vampir Performance Analysis Tool-Set, pp. 139\u2013155. Springer, Heidelberg (2008)","key":"4_CR8","DOI":"10.1007\/978-3-540-68564-7_9"},{"unstructured":"Barcelona Supercomputing Center: Extrae User Guide Manual (May 2013)","key":"4_CR9"},{"unstructured":"Virtual Institute - High Productivity Supercomputing: SCORE-P User Manual (2013)","key":"4_CR10"},{"doi-asserted-by":"crossref","unstructured":"McCurdy, C., Vetter, J.: Memphis: Finding and Fixing NUMA-related Performance Problems on Multi-core Platforms. In: Proceedings of ISPASS 2010 (March 2010)","key":"4_CR11","DOI":"10.1109\/ISPASS.2010.5452060"},{"doi-asserted-by":"crossref","unstructured":"Liu, X., Mellor-Crummey, J.: Pinpointing Data Locality Problems Using Data-centric Analysis. In: Proceedings of CGO 2011 (April 2011)","key":"4_CR12","DOI":"10.1109\/CGO.2011.5764685"},{"unstructured":"Intel Corporation: Intel VTune Amplifier XE 2013 (2013), http:\/\/software.intel.com\/en-us\/intel-vtune-amplifier-xe","key":"4_CR13"},{"issue":"2","key":"4_CR14","doi-asserted-by":"publisher","first-page":"78","DOI":"10.1147\/sj.92.0078","volume":"9","author":"R Mattson","year":"1970","unstructured":"Mattson, R., Gecsei, J., Slutz, D., Traiger, I.: Evaluation techniques for storage hierarchies. IBM Systems Journal 9(2), 78\u2013117 (1970)","journal-title":"IBM Systems Journal"},{"unstructured":"Yokota, R.: exafmm-dev, https:\/\/bitbucket.org\/rioyokota\/exafmm-dev","key":"4_CR15"},{"doi-asserted-by":"crossref","unstructured":"Taura, K., Yokota, R., Maruyama, N.: A Task Parallelism Meets Fast Multipole Methods. In: Proceedings of the SCALA 2012 Workshop (November 2012)","key":"4_CR16","DOI":"10.1109\/SC.Companion.2012.86"},{"unstructured":"The MassiveThreads Team: Massivethreads: A lightweight thread library for high productivity languages, http:\/\/code.google.com\/p\/massivethreads\/","key":"4_CR17"},{"doi-asserted-by":"crossref","unstructured":"Nakashima, J., Nakatani, S., Taura, K.: Design and implementation of a customizable work stealing scheduler. In: Proceedings of the 3rd International Workshop on Runtime and Operating Systems for Supercomputers, ROSS 2013, pp. 9:1\u20139:8 (2013)","key":"4_CR18","DOI":"10.1145\/2491661.2481433"},{"unstructured":"Intel Corporation: TBB: Scheduling algorithm, http:\/\/www.threadingbuildingblocks.org\/docs\/help\/reference\/task_scheduler\/scheduling_algorithm.htm","key":"4_CR19"},{"doi-asserted-by":"crossref","unstructured":"Acar, U.A., Blelloch, G.E., Blumofe, R.D.: The Data Locality of Work Stealing. In: Proceedings of SPAA 2000 (2000)","key":"4_CR20","DOI":"10.1145\/341800.341801"},{"unstructured":"The Qthread Team: The qthread library, http:\/\/www.cs.sandia.gov\/qthreads\/","key":"4_CR21"},{"doi-asserted-by":"crossref","unstructured":"Wheeler, K., Murphy, R., Thain, D.: Qthreads: An API for programming with millions of lightweight threads. In: IEEE International Symposium on Parallel and Distributed Processing, pp. 1\u20138 (2008)","key":"4_CR22","DOI":"10.1109\/IPDPS.2008.4536359"},{"doi-asserted-by":"crossref","unstructured":"Olivier, S.L., Porterfield, A.K., Wheeler, K.B., Prins, J.F.: Scheduling Task Parallelism on Multi-Socket Multicore Systems. In: Proceedings of ROSS 2011, pp. 49\u201356 (2011)","key":"4_CR23","DOI":"10.1145\/1988796.1988804"},{"unstructured":"Weaver, V.M.: Linux perf_event Features and Overhead. In: Proceedings of the 2013 FastPath Workshop (2013)","key":"4_CR24"},{"unstructured":"Beyls, K., D\u2019Hollander, E.H.: Reuse distance as a metric for cache behavior. In: Proceedings of the IASTED Conference on Parallel and Distributed Computing and Systems, pp. 617\u2013662 (2001)","key":"4_CR25"},{"unstructured":"Intel Corporation: Intel 64 and ia-32 architectures software developer\u2019s manual volume 3b, http:\/\/www.intel.com\/content\/www\/us\/en\/processors\/architectures-software-developer-manuals.html","key":"4_CR26"},{"unstructured":"PAPI Team: Performance application programming interface, http:\/\/icl.cs.utk.edu\/papi\/","key":"4_CR27"},{"unstructured":"Weinberg, J., McCracken, M.O., Strohmaier, E., Snavely, A.: Quantifying Locality In The Memory Access Patterns of HPC Applications. In: Proceedings of the 2005 ACM\/IEEE Conference on Supercomputing (November 2005)","key":"4_CR28"},{"unstructured":"Intel Corporation: An Introduction to the Intel QuickPath Interconnect (2009)","key":"4_CR29"},{"doi-asserted-by":"crossref","unstructured":"Hackenberg, D., Molka, D., Nagel, W.E.: Comparing Cache Architectures and Coherency Protocols on x86\u201364 Multicore SMP Systems. In: Proceedings of MICRO 2009 (December 2009)","key":"4_CR30","DOI":"10.1145\/1669112.1669165"}],"container-title":["Lecture Notes in Computer Science","High Performance Computing Systems. Performance Modeling, Benchmarking and Simulation"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-10214-6_4","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,2,14]],"date-time":"2023-02-14T22:06:22Z","timestamp":1676412382000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-319-10214-6_4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014]]},"ISBN":["9783319102139","9783319102146"],"references-count":30,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-10214-6_4","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2014]]},"assertion":[{"value":"1 October 2014","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}}]}}