{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,4]],"date-time":"2025-12-04T09:54:34Z","timestamp":1764842074520,"version":"3.37.3"},"reference-count":28,"publisher":"Springer Science and Business Media LLC","issue":"3-4","license":[{"start":{"date-parts":[[2018,4,24]],"date-time":"2018-04-24T00:00:00Z","timestamp":1524528000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100007601","name":"Horizon 2020","doi-asserted-by":"publisher","award":["671603"],"award-info":[{"award-number":["671603"]}],"id":[{"id":"10.13039\/501100007601","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Sign Process Syst"],"published-print":{"date-parts":[[2019,3]]},"DOI":"10.1007\/s11265-018-1356-9","type":"journal-article","created":{"date-parts":[[2018,4,24]],"date-time":"2018-04-24T02:19:24Z","timestamp":1524536364000},"page":"303-320","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Static Compiler Analyses for Application-specific Optimization of Task-Parallel Runtime Systems"],"prefix":"10.1007","volume":"91","author":[{"given":"Peter","family":"Thoman","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5146-1251","authenticated-orcid":false,"given":"Peter","family":"Zangerl","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Thomas","family":"Fahringer","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2018,4,24]]},"reference":[{"key":"1356_CR1","unstructured":"Asanovic, K., Bodik, R., Catanzaro, B.C., Gebis, J.J., Husbands, P., Keutzer, K., Patterson, D.A., Plishker, W.L., Shalf, J., Williams, S.W., et al. (2006). The landscape of parallel computing research: A view from Berkeley. Tech. rep., Technical Report UCB\/EECS-2006-183, EECS Department University of California, Berkeley."},{"key":"1356_CR2","doi-asserted-by":"crossref","unstructured":"Augonnet, C., Thibault, S., Namyst, R., Wacrenier, P.A. (2009). StarPU: a unified platform for task scheduling on heterogeneous multicore architectures.","DOI":"10.1007\/978-3-642-03869-3_80"},{"issue":"3","key":"1356_CR3","doi-asserted-by":"publisher","first-page":"404","DOI":"10.1109\/TPDS.2008.105","volume":"20","author":"E Ayguad\u00e9","year":"2009","unstructured":"Ayguad\u00e9, E., Copty, N., Duran, A., Hoeflinger, J., Lin, Y., Massaioli, F., Teruel, X., Unnikrishnan, P., Zhang, G. (2009). The design of openmp tasks. IEEE Transactions on Parallel and Distributed Systems, 20(3), 404\u2013418.","journal-title":"IEEE Transactions on Parallel and Distributed Systems"},{"key":"1356_CR4","doi-asserted-by":"crossref","unstructured":"Baskaran, M.M., Vydyanathan, N., Bondhugula, U.K.R., Ramanujam, J., Rountev, A., Sadayappan, P. (2009). Compiler-assisted dynamic scheduling for effective parallelization of loop nests on multicore processors. In ACM sigplan notices (Vol. 44, pp. 219\u2013228). ACM.","DOI":"10.1145\/1594835.1504209"},{"issue":"1","key":"1356_CR5","doi-asserted-by":"publisher","first-page":"55","DOI":"10.1006\/jpdc.1996.0107","volume":"37","author":"RD Blumofe","year":"1996","unstructured":"Blumofe, R.D., Joerg, C.F., Kuszmaul, B.C., Leiserson, C.E., Randall, K.H., Zhou, Y. (1996). Cilk: an efficient multithreaded runtime system. Journal of Parallel and Distributed Computing, 37(1), 55\u201369.","journal-title":"Journal of Parallel and Distributed Computing"},{"key":"1356_CR6","doi-asserted-by":"publisher","unstructured":"Chen, S., Gibbons, P.B., Kozuch, M., Liaskovitis, V., Ailamaki, A., Blelloch, G.E., Falsafi, B., Fix, L., Hardavellas, N., Mowry, T.C., Wilkerson, C. (2007). Scheduling threads for constructive cache sharing on CMPs. In Proceedings of the nineteenth annual ACM symposium on parallel algorithms and architectures, SPAA \u201907. (pp. 105\u2013115). New York: ACM. \n                    https:\/\/doi.org\/10.1145\/1248377.1248396\n                    \n                  .","DOI":"10.1145\/1248377.1248396"},{"key":"1356_CR7","doi-asserted-by":"publisher","unstructured":"Duran, A., Teruel, X., Ferrer, R., Martorell, X., Ayguade, E. (2009). Barcelona openMP tasks suite: a set of benchmarks targeting the exploitation of task parallelism in openMP. In 2009 international conference on parallel processing (pp. 124\u2013131). \n                    https:\/\/doi.org\/10.1109\/ICPP.2009.64\n                    \n                  .","DOI":"10.1109\/ICPP.2009.64"},{"key":"1356_CR8","doi-asserted-by":"publisher","unstructured":"Dwarkadas, S., Cox, A.L., Zwaenepoel, W. (1996). An integrated compile-time\/run-time software distributed shared memory system. In Proceedings of the seventh international conference on architectural support for programming languages and operating systems, ASPLOS VII (pp. 186\u2013197). New York: ACM. \n                    https:\/\/doi.org\/10.1145\/237090.237181\n                    \n                  .","DOI":"10.1145\/237090.237181"},{"key":"1356_CR9","doi-asserted-by":"publisher","unstructured":"Frigo, M., Leiserson, C.E., Randall, K.H. (1998). The implementation of the Cilk-5 multithreaded language. In Proceedings of the ACM SIGPLAN 1998 conference on programming language design and implementation, PLDI \u201998 (pp. 212\u2013223). New York: ACM. \n                    https:\/\/doi.org\/10.1145\/277650.277725\n                    \n                  .","DOI":"10.1145\/277650.277725"},{"key":"1356_CR10","unstructured":"Ghemawat, S., & Menage, P. (2009). Tcmalloc: Thread-caching malloc."},{"key":"1356_CR11","unstructured":"Jordan, H. (2014). Insieme: a compiler infrastructure for parallel programs. Ph.D. thesis, Ph D. dissertation, University of Innsbruck."},{"key":"1356_CR12","unstructured":"Jordan, H., Pellegrini, S., Thoman, P., Kofler, K., Fahringer, T. (2013). INSPIRE: the Insieme Parallel intermediate representation. In Proceedings of the 22nd international conference on parallel architectures and compilation techniques, PACT \u201913 (pp. 7\u201318). Piscataway: IEEE Press."},{"key":"1356_CR13","doi-asserted-by":"publisher","unstructured":"Jordan, H., Thoman, P., Durillo, J.J., Pellegrini, S., Gschwandtner, P., Fahringer, T., Moritsch, H. (2012). A multi-objective auto-tuning framework for parallel codes. In 2012 international conference for high performance computing, networking, storage and analysis (SC) (pp. 1\u201312). \n                    https:\/\/doi.org\/10.1109\/SC.2012.7\n                    \n                  .","DOI":"10.1109\/SC.2012.7"},{"key":"1356_CR14","doi-asserted-by":"crossref","unstructured":"Kaiser, H., Heller, T., Adelstein-Lelbach, B., Serio, A., Fey, D. (2014). Hpx: a task based programming model in a global address space. In Proceedings of the 8th international conference on partitioned global address space programming models (p. 6). ACM.","DOI":"10.1145\/2676870.2676883"},{"issue":"3","key":"1356_CR15","doi-asserted-by":"publisher","first-page":"264","DOI":"10.1109\/71.86103","volume":"2","author":"E Mohr","year":"1991","unstructured":"Mohr, E., Kranz, D.A., Halstead, R.H. (1991). Lazy task creation: a technique for increasing the granularity of parallel programs. IEEE Transactions on Parallel and Distributed Systems, 2(3), 264\u2013280. \n                    https:\/\/doi.org\/10.1109\/71.86103\n                    \n                  .","journal-title":"IEEE Transactions on Parallel and Distributed Systems"},{"key":"1356_CR16","doi-asserted-by":"publisher","unstructured":"Nikolopoulos, D.S., Papatheodorou, T.S., Polychronopoulos, C.D., Labarta, J., Ayguad\u00e9, E. (2000). UPMLIB: a runtime system for tuning the memory performance of OpenMP programs on scalable shared-memory multiprocessors. In Dwarkadas, S. (Ed.) Languages, compilers, and run-time systems for scalable computers: 5th international workshop, LCR 2000 Rochester, NY, USA, May 25\u201327, 2000 Selected Papers (pp. 85\u201399). Berlin: Springer. \n                    https:\/\/doi.org\/10.1007\/3-540-40889-4_7\n                    \n                  .","DOI":"10.1007\/3-540-40889-4_7"},{"key":"1356_CR17","unstructured":"Novillo, D. (2006). Openmp and automatic parallelization in gcc. In Proceedings of the GCC developers summit."},{"issue":"2","key":"1356_CR18","doi-asserted-by":"publisher","first-page":"110","DOI":"10.1177\/1094342011434065","volume":"26","author":"SL Olivier","year":"2012","unstructured":"Olivier, S.L., Porterfield, A.K., Wheeler, K.B., Spiegel, M., Prins, J.F. (2012). OpenMP task scheduling strategies for multicore NUMA systems. The International Journal of High Performance Computing Applications, 26(2), 110\u2013124. \n                    https:\/\/doi.org\/10.1177\/1094342011434065\n                    \n                  .","journal-title":"The International Journal of High Performance Computing Applications"},{"issue":"5","key":"1356_CR19","doi-asserted-by":"publisher","first-page":"341","DOI":"10.1007\/s10766-010-0140-7","volume":"38","author":"SL Olivier","year":"2010","unstructured":"Olivier, S.L., & Prins, J.F. (2010). Comparison of openmp 3.0 and other task parallel frameworks on unbalanced task graphs. International Journal of Parallel Programming, 38(5), 341\u2013360.","journal-title":"International Journal of Parallel Programming"},{"key":"1356_CR20","unstructured":"Reinders, J. (2007). Intel threading building blocks: outfitting C++ for multi-core processor parallelism. O\u2019Reilly Media Inc."},{"key":"1356_CR21","doi-asserted-by":"crossref","unstructured":"Sabeghi, M., Sima, V.M., Bertels, K. (2009). Compiler assisted runtime task scheduling on a reconfigurable computer. In International conference on field programmable logic and applications, 2009. FPL 2009 (pp. 44\u201350). IEEE.","DOI":"10.1109\/FPL.2009.5272555"},{"key":"1356_CR22","doi-asserted-by":"publisher","unstructured":"Thoman, P., Gschwandtner, P., Fahringer, T. (2015). On the quality of implementation of the c++\u200911 thread support library. In 2015 23rd euromicro international conference on parallel, distributed, and network-based processing (pp. 94\u201398). \n                    https:\/\/doi.org\/10.1109\/PDP.2015.33\n                    \n                  .","DOI":"10.1109\/PDP.2015.33"},{"key":"1356_CR23","doi-asserted-by":"publisher","unstructured":"Thoman, P., Jordan, H., Fahringer, T. (2013). Adaptive granularity control in task parallel programs using multiversioning. In Wolf, F., Mohr, B., an Mey, D. (Eds.) Euro-Par 2013 parallel processing: 19th international conference, Aachen, Germany, August 26-30, 2013. Proceedings (pp. 164\u2013177). Berlin: Springer. \n                    https:\/\/doi.org\/10.1007\/978-3-642-40047-6_19\n                    \n                  .","DOI":"10.1007\/978-3-642-40047-6_19"},{"key":"1356_CR24","doi-asserted-by":"publisher","unstructured":"Thoman, P., Jordan, H., Pellegrini, S., Fahringer, T. (2012). Automatic OpenMP loop scheduling: a combined compiler and runtime approach (pp. 88\u2013101). Berlin: Springer. \n                    https:\/\/doi.org\/10.1007\/978-3-642-30961-8_7\n                    \n                  .","DOI":"10.1007\/978-3-642-30961-8_7"},{"key":"1356_CR25","doi-asserted-by":"publisher","first-page":"237","DOI":"10.1007\/978-3-662-48096-0_19","volume-title":"Optimizing task parallelism with library-semantics-aware compilation","author":"P Thoman","year":"2015","unstructured":"Thoman, P., Moosbrugger, S., Fahringer, T. (2015). Optimizing task parallelism with library-semantics-aware compilation (pp. 237\u2013249). Berlin: Springer. \n                    https:\/\/doi.org\/10.1007\/978-3-662-48096-0_19\n                    \n                  ."},{"key":"1356_CR26","doi-asserted-by":"crossref","unstructured":"Thoman, P., Zangerl, P., Fahringer, T. (2017). Task-parallel runtime system optimization using static compiler analysis. In Proceedings of the computing frontiers conference (pp. 201\u2013210). ACM.","DOI":"10.1145\/3075564.3075574"},{"issue":"3","key":"1356_CR27","doi-asserted-by":"publisher","first-page":"271","DOI":"10.1007\/BF03037179","volume":"11","author":"E Tick","year":"1993","unstructured":"Tick, E., & Zhong, X. (1993). A compile-time granularity analysis algorithm and its performance evaluation. New Generation Computing, 11(3), 271. \n                    https:\/\/doi.org\/10.1007\/BF03037179\n                    \n                  .","journal-title":"New Generation Computing"},{"issue":"1","key":"1356_CR28","doi-asserted-by":"publisher","first-page":"65","DOI":"10.1177\/1094342004041293","volume":"18","author":"R Vuduc","year":"2004","unstructured":"Vuduc, R., Demmel, J.W., Bilmes, J.A. (2004). Statistical models for empirical search-based performance tuning. The International Journal of High Performance Computing Applications, 18(1), 65\u201394. \n                    https:\/\/doi.org\/10.1177\/1094342004041293\n                    \n                  .","journal-title":"The International Journal of High Performance Computing Applications"}],"container-title":["Journal of Signal Processing Systems"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11265-018-1356-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11265-018-1356-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11265-018-1356-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,4,23]],"date-time":"2019-04-23T19:18:16Z","timestamp":1556047096000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11265-018-1356-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,4,24]]},"references-count":28,"journal-issue":{"issue":"3-4","published-print":{"date-parts":[[2019,3]]}},"alternative-id":["1356"],"URL":"https:\/\/doi.org\/10.1007\/s11265-018-1356-9","relation":{},"ISSN":["1939-8018","1939-8115"],"issn-type":[{"type":"print","value":"1939-8018"},{"type":"electronic","value":"1939-8115"}],"subject":[],"published":{"date-parts":[[2018,4,24]]},"assertion":[{"value":"10 August 2017","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 December 2017","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 March 2018","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 April 2018","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}