{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,8]],"date-time":"2026-01-08T03:13:34Z","timestamp":1767842014160,"version":"3.49.0"},"reference-count":36,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2016,4,29]],"date-time":"2016-04-29T00:00:00Z","timestamp":1461888000000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100003176","name":"Ministerio de Educaci\u00f3n, Cultura y Deporte","doi-asserted-by":"publisher","award":["TIN2012-34557"],"award-info":[{"award-number":["TIN2012-34557"]}],"id":[{"id":"10.13039\/501100003176","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Parallel Prog"],"published-print":{"date-parts":[[2017,6]]},"DOI":"10.1007\/s10766-016-0431-8","type":"journal-article","created":{"date-parts":[[2016,4,29]],"date-time":"2016-04-29T14:48:19Z","timestamp":1461941299000},"page":"530-550","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Adaptive Runtime-Assisted Block Prefetching on Chip-Multiprocessors"],"prefix":"10.1007","volume":"45","author":[{"given":"Victor","family":"Garcia","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alejandro","family":"Rico","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Carlos","family":"Villavieja","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Paul","family":"Carpenter","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nacho","family":"Navarro","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alex","family":"Ramirez","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2016,4,29]]},"reference":[{"key":"431_CR1","unstructured":"ARM, Cortex-A9 Technical Reference Manual. http:\/\/infocenter.arm.com\/help\/topic\/com.arm.doc.ddi0388f\/DDI0388F_cortex_a9_r2p2_trm.pdf (2008). Accessed 10 Nov 2014"},{"issue":"2","key":"431_CR2","doi-asserted-by":"crossref","first-page":"187","DOI":"10.1002\/cpe.1631","volume":"23","author":"C Augonnet","year":"2011","unstructured":"Augonnet, C., Thibault, S., Namyst, R., Wacrenier, P.-A.: Starpu: a unified platform for task scheduling on heterogeneous multicore architectures. Concurr. Comput. Pract. Exp. 23(2), 187\u2013198 (2011)","journal-title":"Concurr. Comput. Pract. Exp."},{"issue":"5","key":"431_CR3","doi-asserted-by":"crossref","first-page":"609","DOI":"10.1109\/12.381947","volume":"44","author":"J-L Baer","year":"1995","unstructured":"Baer, J.-L., Chen, T.-F.: Effective hardware-based data prefetching for high-performance processors. IEEE Trans. Comput. 44(5), 609\u2013623 (1995)","journal-title":"IEEE Trans. Comput."},{"key":"431_CR4","doi-asserted-by":"publisher","unstructured":"Byna, S., Chen, Y., Sun, X.H.: A taxonomy of data prefetching mechanisms. In: 2008 International Symposium on Parallel Architectures, Algorithms, and Networks (i-span 2008), Sydney, NSW, pp. 19\u201324 (2008). doi: 10.1109\/I-SPAN.2008.24","DOI":"10.1109\/I-SPAN.2008.24"},{"issue":"3","key":"431_CR5","doi-asserted-by":"crossref","first-page":"291","DOI":"10.1177\/1094342007078442","volume":"21","author":"B Chamberlain","year":"2007","unstructured":"Chamberlain, B., Callahan, D., Zima, H.: Parallel programmability and the chapel language. Int. J. High Perform. Comput. Appl. 21(3), 291\u2013312 (2007)","journal-title":"Int. J. High Perform. Comput. Appl."},{"key":"431_CR6","doi-asserted-by":"crossref","unstructured":"Charles, P., Grothoff, C., Saraswat, V., Donawa, C., Kielstra, A., Ebcioglu, K., von Praun, C., Sarkar, V.: X10: An object-oriented approach to non-uniform cluster computing. SIGPLAN Not. 40(10), 519\u2013538","DOI":"10.1145\/1103845.1094852"},{"key":"431_CR7","doi-asserted-by":"crossref","unstructured":"Chen, T.-F., Baer, J.-L.: A performance study of software and hardware data prefetching Schemes. In: Proceedings the 21st Annual International Symposium on Computer Architecture, 1994, Chicago, IL, pp. 223\u2013232 (1994)","DOI":"10.1109\/ISCA.1994.288147"},{"key":"431_CR8","doi-asserted-by":"publisher","unstructured":"Chung, I.H., Hollingsworth, J.K.: A case study using automatic performance tuning for large-scale scientific programs. In: 15th IEEE International Conference on High Performance Distributed Computing, Paris, 2006, pp. 45\u201356 (2006). doi: 10.1109\/HPDC.2006.1652135","DOI":"10.1109\/HPDC.2006.1652135"},{"key":"431_CR9","unstructured":"OpenMP Consortium. http:\/\/openmp.org\/wp\/ (2014). Accessed 25 July 2014"},{"key":"431_CR10","doi-asserted-by":"crossref","unstructured":"Dahlgren, F., Dubois, M., Stenstrom, P.: Fixed and adaptive sequential prefetching in shared memory multiprocessors. In: International Conference on Parallel Processing, 1993. ICPP 1993, Syracuse, NY, pp. 56\u201363 (1993)","DOI":"10.1109\/ICPP.1993.92"},{"key":"431_CR11","doi-asserted-by":"publisher","unstructured":"Dahlgren, F., Stenstrom, P.: Effectiveness of hardware-based stride and sequential prefetching in shared-memory multiprocessors. In: Proceedings., First IEEE Symposium on High-Performance Computer Architecture, 1995, Raleigh, NC, pp. 68\u201377 (1995). doi: 10.1109\/HPCA.1995.386554","DOI":"10.1109\/HPCA.1995.386554"},{"key":"431_CR12","unstructured":"GCC Developers: GCC Optimization Options. https:\/\/gcc.gnu.org\/onlinedocs\/gcc-4.0.4\/gcc\/Optimize-Options.html (2014). Accessed 14 Aug 2014"},{"issue":"2","key":"431_CR13","doi-asserted-by":"crossref","first-page":"173","DOI":"10.1142\/S0129626411000151","volume":"21","author":"A Duran","year":"2011","unstructured":"Duran, A., Ayguad\u00e9, E., Badia, R.M., Labarta, J., Martinell, L., Martorell, X., Planas, J.: Ompss: a proposal for programming heterogeneous multi-core architectures. Parallel Process. Lett. 21(2), 173\u2013193 (2011)","journal-title":"Parallel Process. Lett."},{"issue":"1","key":"431_CR14","doi-asserted-by":"crossref","first-page":"335","DOI":"10.1145\/1735970.1736058","volume":"38","author":"E Ebrahimi","year":"2010","unstructured":"Ebrahimi, E., Lee, C.J., Mutlu, O., Patt, Y.N.: Fairness via source throttling: a configurable and high-performance fairness substrate for multi-core memory systems. SIGARCH Comput. Archit. News 38(1), 335\u2013346 (2010)","journal-title":"SIGARCH Comput. Archit. News"},{"key":"431_CR15","doi-asserted-by":"crossref","unstructured":"Fatahalian, K., Horn, D.R., Knight, T.J., Leem, L., Houston, M., Park, J.Y., Erez, M., Ren, M., Aiken, A., Dally, W.J., Hanrahan, P.: Sequoia: programming the memory hierarchy. In: Proceedings of the 2006 ACM\/IEEE Conference on Supercomputing, SC \u201906, ACM, New York, NY, USA (2006)","DOI":"10.1109\/SC.2006.55"},{"key":"431_CR16","doi-asserted-by":"publisher","unstructured":"Feng, X., Cameron, K.W., Buell, D.A.: PBPI: a high performance implementation of bayesian phylogenetic inference. In: Proceedings of the ACM\/IEEE, SC 2006 Conference, Tampa, FL, pp. 40 (2006). doi: 10.1109\/SC.2006.47","DOI":"10.1109\/SC.2006.47"},{"key":"431_CR17","doi-asserted-by":"crossref","unstructured":"Frigo, M., Leiserson, C.E., Randall, K.H.: 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, ACM, New York, NY, USA (1998)","DOI":"10.1145\/277650.277725"},{"key":"431_CR18","doi-asserted-by":"crossref","unstructured":"Gornish, E.H., Granston, E.D., Veidenbaum, A.V.: Compiler-directed data prefetching in multiprocessors with memory hierarchies. In: In International Conference on Supercomputing, pp. 354\u2013368 (1990)","DOI":"10.1145\/77726.255176"},{"issue":"2","key":"431_CR19","doi-asserted-by":"crossref","first-page":"250","DOI":"10.1109\/TVLSI.2009.2032916","volume":"19","author":"Y Guo","year":"2011","unstructured":"Guo, Y., Narayanan, P., Bennaser, M., Chheda, S., Moritz, C.: Energy-efficient hardware data prefetching. Very Large Scale Integration (VLSI) Syst. IEEE Trans. 19(2), 250\u2013263 (2011)","journal-title":"Very Large Scale Integration (VLSI) Syst. IEEE Trans."},{"key":"431_CR20","doi-asserted-by":"crossref","unstructured":"D.\u00a0Lowenthal and M.\u00a0James. Run-time selection of block size in pipelined parallel programs. In: Parallel Processing, 1999. Proceedings13th International and 10th Symposium on Parallel and Distributed Processing, 1999. 1999 IPPS\/SPDP, pp. 82\u201387","DOI":"10.1109\/IPPS.1999.760439"},{"key":"431_CR21","unstructured":"Lu, J.: Design and Implementation of a Lightweight Runtime Optimization System on Modern Computer Architectures. Ph.D. Thesis, Minneapolis, MN, USA, AAI3220014 (2006)"},{"key":"431_CR22","doi-asserted-by":"crossref","unstructured":"Luk, C.-K., Cohn, R., Muth, R., Patil, H., Klauser, A., Lowney, G., Wallace, S., Reddi, V.J., Hazelwood, K.: Pin: building customized program analysis tools with dynamic instrumentation. In: Proceedings of the 2005 ACM SIGPLAN Conference on Programming Language Design and Implementation, PLDI \u201905, pp. 190\u2013200, New York, NY, USA, 2005. ACM","DOI":"10.1145\/1065010.1065034"},{"key":"431_CR23","unstructured":"Martonosi, M.R.: Analyzing and tuning memory performance in sequential and parallel programs. Technical report, Stanford, CA, USA (1994)"},{"key":"431_CR24","doi-asserted-by":"crossref","first-page":"87","DOI":"10.1016\/0743-7315(91)90014-Z","volume":"12","author":"T Mowry","year":"1991","unstructured":"Mowry, T., Gupta, A.: Tolerating latency through software-controlled prefetching in shared-memory multiprocessors. J. Parallel Distrib. Comput. 12, 87\u2013106 (1991)","journal-title":"J. Parallel Distrib. Comput."},{"key":"431_CR25","doi-asserted-by":"crossref","unstructured":"Nesbit, K., Smith, J.: Data cache prefetching using a global history buffer. In: Software, IEE Proceedings, p. 96 (2004)","DOI":"10.1109\/HPCA.2004.10030"},{"key":"431_CR26","doi-asserted-by":"crossref","unstructured":"Papaefstathiou, V., Katevenis, M.G., Nikolopoulos, D.S., Pnevmatikatos, D.: Prefetching and cache management using task lifetimes. In: Proceedings of the 27th International ACM Conference on International Conference on Supercomputing, ICS \u201913, pp. 325\u2013334, ACM, New York, NY, USA (2013)","DOI":"10.1145\/2464996.2465443"},{"key":"431_CR27","volume-title":"Intel Threading Building Blocks","author":"J Reinders","year":"2007","unstructured":"Reinders, J.: Intel Threading Building Blocks, 1st edn. O\u2019Reilly and Associates Inc, Sebastopol (2007)","edition":"1"},{"issue":"4","key":"431_CR28","doi-asserted-by":"crossref","first-page":"36:1","DOI":"10.1145\/2086696.2086715","volume":"8","author":"A Rico","year":"2012","unstructured":"Rico, A., Cabarcas, F., Villavieja, C., Pavlovic, M., Vega, A., Etsion, Y., Ramirez, A., Valero, M.: On the simulation of large-scale architectures using multiple application abstraction levels. ACM Trans. Archit. Code Optim. 8(4), 36:1\u201336:20 (2012)","journal-title":"ACM Trans. Archit. Code Optim."},{"issue":"1\u20132","key":"431_CR29","first-page":"59","volume":"17","author":"A Rico","year":"2009","unstructured":"Rico, A., Ramirez, A., Valero, M.: Available task-level parallelism on the cell BE. Sci. Program. 17(1\u20132), 59\u201376 (2009)","journal-title":"Sci. Program."},{"key":"431_CR30","unstructured":"Rothberg, E., Singh, J.P., Gupta, A.: Working sets, cache sizes, and node granularity issues for large-scale multiprocessors. In: Proceedings of the 20th Annual International Symposium on Computer Architecture, 1993, pp. 14\u201325 (1993)"},{"key":"431_CR31","doi-asserted-by":"crossref","unstructured":"Solihin, Y., Lee, J., Torrellas, J.: Using a user-level memory thread for correlation prefetching. In: Proceedings of the 29th Annual International Symposium on Computer Architecture, ISCA \u201902, pp. 171\u2013182, IEEE Computer Society, Washington, DC, USA (2002)","DOI":"10.1109\/ISCA.2002.1003576"},{"key":"431_CR32","doi-asserted-by":"publisher","unstructured":"Tandri, S., Abdelrahman, T.S.: Automatic partitioning of data and computations on scalable shared memory multiprocessors. In: Proceedings of the 1997 International Conference on Parallel Processing, 1997, Bloomington, IL, pp. 64\u201373 (1997). doi: 10.1109\/ICPP.1997.622557","DOI":"10.1109\/ICPP.1997.622557"},{"issue":"1","key":"431_CR33","doi-asserted-by":"crossref","first-page":"57","DOI":"10.1145\/200912.201006","volume":"13","author":"DM Tullsen","year":"1995","unstructured":"Tullsen, D.M., Eggers, S.J.: Effective cache prefetching on bus-based multiprocessors. ACM Trans. Comput. Syst. 13(1), 57\u201388 (1995)","journal-title":"ACM Trans. Comput. Syst."},{"key":"431_CR34","doi-asserted-by":"crossref","unstructured":"Villavieja, C., Karakostas, V., Vilanova, L., Etsion, Y., Ramirez, A., Mendelson, A., Navarro, N., Cristal, A., Unsal, O.S.: Didi: Mitigating the performance impact of tlb shootdowns using a shared tlb directory. In: 2011 International Conference on Parallel Architectures and Compilation Techniques (PACT), Galveston, TX, pp. 340\u2013349 (2011)","DOI":"10.1109\/PACT.2011.65"},{"key":"431_CR35","unstructured":"Wall, M.: Using block prefetch for optimized memory performance. http:\/\/web.mit.edu\/ehliu\/Public\/ProjectX\/Meetings\/AMD_block_prefetch_paper.pdf (2001). Accessed 10 July 2014"},{"issue":"1","key":"431_CR36","doi-asserted-by":"crossref","first-page":"20","DOI":"10.1145\/216585.216588","volume":"23","author":"WA Wulf","year":"1995","unstructured":"Wulf, W.A., McKee, S.A.: Hitting the memory wall: implications of the obvious. SIGARCH Comput. Archit. News 23(1), 20\u201324 (1995)","journal-title":"SIGARCH Comput. Archit. News"}],"container-title":["International Journal of Parallel Programming"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10766-016-0431-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10766-016-0431-8\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10766-016-0431-8","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10766-016-0431-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,5,30]],"date-time":"2019-05-30T20:02:35Z","timestamp":1559246555000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10766-016-0431-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,4,29]]},"references-count":36,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2017,6]]}},"alternative-id":["431"],"URL":"https:\/\/doi.org\/10.1007\/s10766-016-0431-8","relation":{},"ISSN":["0885-7458","1573-7640"],"issn-type":[{"value":"0885-7458","type":"print"},{"value":"1573-7640","type":"electronic"}],"subject":[],"published":{"date-parts":[[2016,4,29]]}}}