{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,2]],"date-time":"2025-07-02T12:46:36Z","timestamp":1751460396494,"version":"3.37.3"},"reference-count":46,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2016,4,8]],"date-time":"2016-04-08T00:00:00Z","timestamp":1460073600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"funder":[{"name":"Castilla y Leon Regional Government","award":["VA172A12-2"],"award-info":[{"award-number":["VA172A12-2"]}]},{"DOI":"10.13039\/501100004837","name":"Ministerio de Ciencia e Innovaci\u00f3n (ES)","doi-asserted-by":"publisher","award":["TIN2011-25639"],"award-info":[{"award-number":["TIN2011-25639"]}],"id":[{"id":"10.13039\/501100004837","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004837","name":"Ministerio de Ciencia e Innovaci\u00f3n (ES)","doi-asserted-by":"publisher","award":["TIN2014-58876-P"],"award-info":[{"award-number":["TIN2014-58876-P"]}],"id":[{"id":"10.13039\/501100004837","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004837","name":"Ministerio de Ciencia e Innovaci\u00f3n (ES)","doi-asserted-by":"publisher","award":["TIN2014-53522-REDT"],"award-info":[{"award-number":["TIN2014-53522-REDT"]}],"id":[{"id":"10.13039\/501100004837","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":[[2017,4]]},"DOI":"10.1007\/s10766-016-0421-x","type":"journal-article","created":{"date-parts":[[2016,4,8]],"date-time":"2016-04-08T21:19:58Z","timestamp":1460150398000},"page":"225-241","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Using the Xeon Phi Platform to Run Speculatively-Parallelized Codes"],"prefix":"10.1007","volume":"45","author":[{"given":"Alvaro","family":"Estebanez","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Diego R.","family":"Llanos","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Arturo","family":"Gonzalez-Escribano","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2016,4,8]]},"reference":[{"key":"421_CR1","unstructured":"AMD $$\\text{ Opteron }^{{\\rm TM}}$$ Opteron TM 6300 Series processor - quick reference guide. https:\/\/www.amd.com\/Documents\/Opteron_6300_QRG.pdf . Accessed June 2015"},{"key":"421_CR2","unstructured":"Intel $$\\textregistered $$ \u00ae Xeon $$\\text{ Phi }^{{\\rm TM}}$$ Phi TM product family: Product brief. https:\/\/www-ssl.intel.com\/content\/dam\/www\/public\/us\/en\/documents\/product-briefs\/high-performance-xeon-phi-coprocessor-brief.pdf . Accessed June 2015"},{"key":"421_CR3","unstructured":"Intel $$\\textregistered $$ \u00ae Xeon $$\\text{ Phi }^{{\\rm TM}}$$ Phi TM coprocessor instruction set architecture reference manual. https:\/\/software.intel.com\/sites\/default\/files\/forum\/278102\/327364001en.pdf . Accessed June 2015"},{"issue":"99","key":"421_CR4","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TPDS.2015.2393870","volume":"PP","author":"S Aldea","year":"2015","unstructured":"Aldea, S., Estebanez, A., Llanos, D., Gonzalez-Escribano, A.: An OpenMP extension that supports thread-level speculation. IEEE Trans. Parallel Distrib. Syst. PP(99), 1\u20131 (2015). doi: 10.1109\/TPDS.2015.2393870","journal-title":"IEEE Trans. Parallel Distrib. Syst."},{"key":"421_CR5","unstructured":"Barnes, J.E.: TREE. Institute for Astronomy. University of Hawaii (1997). ftp:\/\/hubble.ifa.hawaii.edu\/pub\/barnes\/treecode\/"},{"key":"421_CR6","doi-asserted-by":"publisher","unstructured":"Cadambi, S., Coviello, G., Li, C.H., Phull, R., Rao, K., Sankaradass, M., Chakradhar, S.: Cosmic: middleware for high performance and reliable multiprocessing on Xeon Phi coprocessors. In: Proceedings of the 22nd International Symposium on High-Performance Parallel and Distributed Computing, HPDC \u201913, pp. 215\u2013226. ACM, New York (2013). doi: 10.1145\/2462902.2462921","DOI":"10.1145\/2462902.2462921"},{"key":"421_CR7","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/978-981-287-134-3_1","volume-title":"GPU Comput. Appl.","author":"P Cai","year":"2015","unstructured":"Cai, P., Cai, Y., Chandrasekaran, I., Zheng, J.: A GPU-enabled parallel genetic algorithm for path planning of robotic operators. In: Cai, Y., See, S. (eds.) GPU Comput. Appl., pp. 1\u201313. Springer, Singapore (2015). doi: 10.1007\/978-981-287-134-3_1"},{"key":"421_CR8","doi-asserted-by":"crossref","unstructured":"Cintra, M., Llanos, D.R.: Toward efficient and robust software speculative parallelization on multiprocessors. In: Proceedings of the SIGPLAN Symposium on Principles and Practice of Parallel Programming (PPoPP) (2003)","DOI":"10.1145\/781498.781501"},{"issue":"6","key":"421_CR9","doi-asserted-by":"crossref","first-page":"562","DOI":"10.1109\/TPDS.2005.69","volume":"16","author":"M Cintra","year":"2005","unstructured":"Cintra, M., Llanos, D.R.: Design space exploration of a software speculative parallelization scheme. IEEE Trans. Parallel Distrib. Syst. 16(6), 562\u2013576 (2005)","journal-title":"IEEE Trans. Parallel Distrib. Syst."},{"issue":"4","key":"421_CR10","doi-asserted-by":"crossref","first-page":"185","DOI":"10.1016\/0925-7721(93)90009-U","volume":"3","author":"KL Clarkson","year":"1993","unstructured":"Clarkson, K.L., Mehlhorn, K., Seidel, R.: Four results on randomized incremental constructions. Comput. Geom. Theory Appl. 3(4), 185\u2013212 (1993)","journal-title":"Comput. Geom. Theory Appl."},{"key":"421_CR11","unstructured":"Cramer, T., Schmidl, D., Klemm, M., an\u00a0Mey, D.: OpenMP programming on Intel Xeon Phi coprocessors: An early performance comparison. In: Proceedings of the Many-core Applications Research Community (MARC) Symposium (2012)"},{"issue":"1","key":"421_CR12","doi-asserted-by":"publisher","first-page":"46","DOI":"10.1109\/99.660313","volume":"5","author":"L Dagum","year":"1998","unstructured":"Dagum, L., Menon, R.: OpenMP: an industry standard API for shared-memory programming. IEEE Comput. Sci. Eng. 5(1), 46\u201355 (1998). doi: 10.1109\/99.660313","journal-title":"IEEE Comput. Sci. Eng."},{"key":"421_CR13","doi-asserted-by":"crossref","first-page":"477","DOI":"10.1007\/PL00009234","volume":"22","author":"L Devroye","year":"1998","unstructured":"Devroye, L., M\u00fccke, E.P., Zhu, B.: A note on point location in Delaunay triangulations of random points. Algorithmica 22, 477\u2013482 (1998)","journal-title":"Algorithmica"},{"key":"421_CR14","unstructured":"Dou, J., Cintra, M.: Compiler estimation of load imbalance overhead in speculative parallelization. In: Proceedings of the 13th International Conference on Parallel Architectures and Compilation Techniques, PACT \u201904. IEEE Computer Society, Washington, DC (2004)"},{"key":"421_CR15","doi-asserted-by":"publisher","unstructured":"Estebanez, A., Llanos, D., Gonzalez-Escribano, A.: New data structures to handle speculative parallelization at runtime. Int. J. Parallel Program. 1\u201320 (2015). doi: 10.1007\/s10766-014-0347-0","DOI":"10.1007\/s10766-014-0347-0"},{"key":"421_CR16","doi-asserted-by":"publisher","unstructured":"Fang, J., Sips, H., Zhang, L., Xu, C., Che, Y., Varbanescu, A.L.: Test-driving Intel Xeon Phi. In: Proceedings of the 5th ACM\/SPEC International Conference on Performance Engineering, ICPE \u201914, pp. 137\u2013148. ACM, New York (2014). doi: 10.1145\/2568088.2576799","DOI":"10.1145\/2568088.2576799"},{"issue":"5","key":"421_CR17","doi-asserted-by":"publisher","first-page":"552","DOI":"10.1109\/12.509907","volume":"45","author":"M Franklin","year":"1996","unstructured":"Franklin, M., Sohi, G.S.: ARB: a hardware mechanism for dynamic reordering of memory references. IEEE Trans. Comput. 45(5), 552\u2013571 (1996). doi: 10.1109\/12.509907","journal-title":"IEEE Trans. Comput."},{"issue":"5","key":"421_CR18","doi-asserted-by":"crossref","first-page":"1004","DOI":"10.1109\/TC.2012.41","volume":"62","author":"L Gao","year":"2013","unstructured":"Gao, L., Li, L., Xue, J., Yew, P.C.: SEED: a statically-greedy and dynamically-adaptive approach for speculative loop execution. IEEE Trans. Comput. 62(5), 1004\u20131016 (2013)","journal-title":"IEEE Trans. Comput."},{"key":"421_CR19","doi-asserted-by":"publisher","unstructured":"Gopal, S., Vijaykumar, T.N., Smith, J., Sohi, G.: Speculative versioning cache. In: High-Performance Computer Architecture, 1998. Proceedings, 1998 Fourth International Symposium on, pp. 195\u2013205 (1998). doi: 10.1109\/HPCA.1998.650559","DOI":"10.1109\/HPCA.1998.650559"},{"key":"421_CR20","volume-title":"Intel Xeon Phi Coprocessor High-Performance Programming","author":"J Jeffers","year":"2013","unstructured":"Jeffers, J., Reinders, J.: Intel Xeon Phi Coprocessor High-Performance Programming. Newnes, Boston (2013)"},{"issue":"4","key":"421_CR21","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1007\/s10766-013-0259-4","volume":"42","author":"A Jimborean","year":"2014","unstructured":"Jimborean, A., Clauss, P., Dollinger, J.F., Loechner, V., Martinez Caamao, J.: Dynamic and speculative polyhedral parallelization using compiler-generated skeletons. Int. J. Parallel Program. 42(4), 529\u2013545 (2014)","journal-title":"Int. J. Parallel Program."},{"key":"421_CR22","doi-asserted-by":"publisher","unstructured":"Kelsey, K., Bai, T., Ding, C., Zhang, C.: Fast track: a software system for speculative program optimization. In: Proceedings of the 7th Annual IEEE\/ACM International Symposium on Code Generation and Optimization, CGO \u201909, pp. 157\u2013168. IEEE Computer Society, Washington, DC (2009). doi: 10.1109\/CGO.2009.18","DOI":"10.1109\/CGO.2009.18"},{"key":"421_CR23","unstructured":"Khronos: Open Computing Language (OpenCL) (2010). http:\/\/www.khronos.org\/opencl\/ , Accessed 2 Dec 2013"},{"issue":"9","key":"421_CR24","doi-asserted-by":"crossref","first-page":"866","DOI":"10.1109\/12.795218","volume":"48","author":"V Krishnan","year":"1999","unstructured":"Krishnan, V., Torrellas, J.: A chip-multiprocessor architecture with speculative multithreading. IEEE Trans. Comput. 48(9), 866\u2013880 (1999)","journal-title":"IEEE Trans. Comput."},{"key":"421_CR25","doi-asserted-by":"crossref","unstructured":"Kulkarni, M., Pingali, K., Walter, B., Ramanarayanan, G., Bala, K., Chew, L.P.: Optimistic parallelism requires abstractions. In: PLDI 2007 Proceedings. ACM (2007)","DOI":"10.1145\/1250734.1250759"},{"issue":"9","key":"421_CR26","doi-asserted-by":"crossref","first-page":"89","DOI":"10.1145\/1562164.1562188","volume":"52","author":"M Kulkarni","year":"2009","unstructured":"Kulkarni, M., Pingali, K., Walter, B., Ramanarayanan, G., Bala, K., Chew, L.P.: Optimistic parallelism requires abstractions. Commun. ACM 52(9), 89\u201397 (2009)","journal-title":"Commun. ACM"},{"key":"421_CR27","doi-asserted-by":"publisher","unstructured":"Liu, X., Smelyanskiy, M., Chow, E., Dubey, P.: Efficient sparse matrix-vector multiplication on x86-based many-core processors. In: Proceedings of the 27th International ACM Conference on International Conference on Supercomputing, ICS \u201913, pp. 273\u2013282. ACM, New York (2013). doi: 10.1145\/2464996.2465013","DOI":"10.1145\/2464996.2465013"},{"key":"421_CR28","doi-asserted-by":"crossref","unstructured":"Marcuello, P., Gonzalez, A., Tubella, J.: Speculative multithreaded processors. In: Proceedings of the 12th International Conference on Supercomputing, ICS \u201998. ACM, New York (1998)","DOI":"10.1145\/277830.277850"},{"key":"421_CR29","doi-asserted-by":"crossref","unstructured":"M\u00fccke, E.P., Saias, I., Zhu, B.: Fast randomized point location without preprocessing in two- and three-dimensional Delaunay triangulations. In: SoCG \u201996 Proceedings, pp. 274\u2013283 (1996)","DOI":"10.1145\/237218.237396"},{"key":"421_CR30","unstructured":"NVIDIA: NVIDIA CUDA Architecture Introduction and Overview Version 1.1 (2009)"},{"key":"421_CR31","doi-asserted-by":"crossref","unstructured":"Oancea, C.E., Mycroft, A., Harris, T.: A lightweight in-place implementation for software thread-level speculation. In: Proceedings of the Twenty-First Annual Symposium on Parallelism in Algorithms and Architectures, SPAA \u201909. ACM, New York (2009)","DOI":"10.1145\/1583991.1584050"},{"key":"421_CR32","doi-asserted-by":"publisher","unstructured":"Olsen, S., Romoser, B., Zong, Z.: SQLPhi: A SQL-based database engine for Intel Xeon Phi coprocessors. In: Proceedings of the 2014 International Conference on Big Data Science and Computing, BigDataScience \u201914, pp. 17:1\u201317:6. ACM, New York (2014). doi: 10.1145\/2640087.2644172","DOI":"10.1145\/2640087.2644172"},{"key":"421_CR33","doi-asserted-by":"publisher","unstructured":"Park, J., Bikshandi, G., Vaidyanathan, K., Tang, P.T.P., Dubey, P., Kim, D.: Tera-scale 1D FFT with low-communication algorithm and Intel Xeon Phi coprocessors. In: Proceedings of the International Conference on High Performance Computing, Networking, Storage and Analysis, SC \u201913, pp. 34:1\u201334:12. ACM, New York (2013). doi: 10.1145\/2503210.2503242","DOI":"10.1145\/2503210.2503242"},{"key":"421_CR34","doi-asserted-by":"crossref","unstructured":"Raman, E., Vahharajani, N., Rangan, R., August, D.I.: Spice: speculative parallel iteration chunk execution. In: Proceedings of the 6th Annual IEEE\/ACM International Symposium on Code Generation and Optimization, CGO \u201908. ACM, New York (2008)","DOI":"10.1145\/1356058.1356082"},{"key":"421_CR35","doi-asserted-by":"publisher","unstructured":"Rauchwerger, L., Padua, D.: The lrpd test: speculative run-time parallelization of loops with privatization and reduction parallelization (1995). doi: 10.1145\/207110.207148","DOI":"10.1145\/207110.207148"},{"key":"421_CR36","doi-asserted-by":"publisher","unstructured":"Rezaei, A., Coviello, G., Li, C.H., Chakradhar, S., Mueller, F.: Snapify: capturing snapshots of offload applications on Xeon Phi manycore processors. In: Proceedings of the 23rd International Symposium on High-Performance Parallel and Distributed Computing, HPDC \u201914, pp. 1\u201312. ACM, New York (2014). doi: 10.1145\/2600212.2600215","DOI":"10.1145\/2600212.2600215"},{"key":"421_CR37","doi-asserted-by":"crossref","unstructured":"Rotenberg, E., Bennett, S., Smith, J.E.: Trace cache: a low latency approach to high bandwidth instruction fetching. In: Proceedings of the 29th Annual ACM\/IEEE International Symposium on Microarchitecture. MICRO 29, pp. 24\u201335. IEEE Computer Society, Washington, DC (1996)","DOI":"10.1109\/MICRO.1996.566447"},{"key":"421_CR38","doi-asserted-by":"crossref","unstructured":"Satish, N., Kim, C., Chhugani, J., Saito, H., Krishnaiyer, R., Smelyanskiy, M., Girkar, M., Dubey, P.: Can traditional programming bridge the ninja performance gap for parallel computing applications? In: Proceedings of the 39th Annual International Symposium on Computer Architecture, ISCA \u201912, pp. 440\u2013451. IEEE Computer Society, Washington, DC (2012). http:\/\/dl.acm.org\/citation.cfm?id=2337159.2337210","DOI":"10.1109\/ISCA.2012.6237038"},{"key":"421_CR39","doi-asserted-by":"publisher","unstructured":"Schmidl, D., Cramer, T., Wienke, S., Terboven, C., Mller, M.: Assessing the performance of OpenMP programs on the Intel Xeon Phi. In: Wolf, F., Mohr, B., an\u00a0Mey, D. (eds.) Euro-Par 2013 Parallel Processing, Lecture Notes in Computer Science, vol. 8097, pp. 547\u2013558. Springer, Heidelberg (2013). doi: 10.1007\/978-3-642-40047-6_56","DOI":"10.1007\/978-3-642-40047-6_56"},{"key":"421_CR40","doi-asserted-by":"publisher","unstructured":"Sohi, G.S., Breach, S.E., Vijaykumar, T.N.: Multiscalar processors. In: Proceedings of the 22nd Annual International Symposium on Computer Architecture, ISCA \u201995, pp. 414\u2013425. ACM, New York (1995). doi: 10.1145\/223982.224451","DOI":"10.1145\/223982.224451"},{"key":"421_CR41","doi-asserted-by":"crossref","unstructured":"Tian, C., Feng, M., Gupta, R.: Supporting speculative parallelization in the presence of dynamic data structures. In: Proceedings of the 2010 ACM SIGPLAN Conference on Programming Language Design and Implementation, PLDI \u201910. ACM, New York (2010)","DOI":"10.1145\/1806596.1806604"},{"key":"421_CR42","unstructured":"Tian, C., Feng, M., Nagarajan, V., Gupta, R.: Copy or discard execution model for speculative parallelization on multicores. In: Proceedings of the 41st Annual IEEE\/ACM International Symposium on Microarchitecture, MICRO \u201941. Washington, DC (2008)"},{"key":"421_CR43","doi-asserted-by":"crossref","unstructured":"Walker, D.W.: The design of a standard message passing interface for distributed memory concurrent computers. Parallel Comput. 20(4), 657\u2013673 (1994). http:\/\/portal.acm.org\/citation.cfm?id=180103","DOI":"10.1016\/0167-8191(94)90033-7"},{"key":"421_CR44","doi-asserted-by":"publisher","unstructured":"Wallace, S., Calder, B., Tullsen, D.M.: Threaded multiple path execution. In: Proceedings of the 25th Annual International Symposium on Computer Architecture, ISCA \u201998, pp. 238\u2013249. IEEE Computer Society, Washington, DC (1998). doi: 10.1145\/279358.279392","DOI":"10.1145\/279358.279392"},{"issue":"4","key":"421_CR45","doi-asserted-by":"crossref","first-page":"39:1","DOI":"10.1145\/2400682.2400698","volume":"9","author":"P Yiapanis","year":"2013","unstructured":"Yiapanis, P., Rosas-Ham, D., Brown, G., Luj\u00e1n, M.: Optimizing software runtime systems for speculative parallelization. ACM Trans. Archit. Code Optim. 9(4), 39:1\u201339:27 (2013)","journal-title":"ACM Trans. Archit. Code Optim."},{"key":"421_CR46","doi-asserted-by":"crossref","unstructured":"Zhao, Z., Wu, B., Shen, X.: Speculative parallelization needs rigor: probabilistic analysis for optimal speculation of finite-state machine applications. In: Proceedings of the 21st International Conference on Parallel Architectures and Compilation Techniques, PACT \u201912. New York (2012)","DOI":"10.1145\/2370816.2370882"}],"container-title":["International Journal of Parallel Programming"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10766-016-0421-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10766-016-0421-x\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10766-016-0421-x","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10766-016-0421-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,5,30]],"date-time":"2019-05-30T20:02:34Z","timestamp":1559246554000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10766-016-0421-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,4,8]]},"references-count":46,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2017,4]]}},"alternative-id":["421"],"URL":"https:\/\/doi.org\/10.1007\/s10766-016-0421-x","relation":{},"ISSN":["0885-7458","1573-7640"],"issn-type":[{"type":"print","value":"0885-7458"},{"type":"electronic","value":"1573-7640"}],"subject":[],"published":{"date-parts":[[2016,4,8]]}}}