{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,20]],"date-time":"2026-09-20T16:42:17Z","timestamp":1789922537542,"version":"4.0.1"},"publisher-location":"Cham","reference-count":25,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783319271392","type":"print"},{"value":"9783319271408","type":"electronic"}],"license":[{"start":{"date-parts":[[2015,1,1]],"date-time":"2015-01-01T00:00:00Z","timestamp":1420070400000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2015]]},"DOI":"10.1007\/978-3-319-27140-8_40","type":"book-chapter","created":{"date-parts":[[2015,11,16]],"date-time":"2015-11-16T13:27:57Z","timestamp":1447680477000},"page":"583-596","source":"Crossref","is-referenced-by-count":6,"title":["Fast Data-Dependence Profiling by Skipping Repeatedly Executed Memory Operations"],"prefix":"10.1007","author":[{"given":"Zhen","family":"Li","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Michael","family":"Beaumont","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ali","family":"Jannesari","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Felix","family":"Wolf","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2015,12,16]]},"reference":[{"key":"40_CR1","unstructured":"Amini, M., Goubier, O., Guelton, S., Mcmahon, J.O., Pasquier, F.X., Pan, G., Villalon, P.: Par4All: From convex array regions to heterogeneous computing. In: Proceedings of the 2nd International Workshop on Polyhedral Compilation Techniques, IMPACT 2012 (2012)"},{"key":"40_CR2","doi-asserted-by":"crossref","unstructured":"Andersch, M., Juurlink, B., Chi, C.C.: A benchmark suite for evaluating parallel programming models. In: Proceedings 24th Workshop on Parallel Systems and Algorithms, PARS 2011, pp. 7\u201317 (2011)","DOI":"10.1007\/BF03341980"},{"key":"40_CR3","doi-asserted-by":"crossref","unstructured":"Atre, R., Jannesari, A., Wolf, F.: The basic building blocks of parallel tasks. In: Proceedings of the 2015 International Workshop on Code Optimisation for Multi and Many Cores, COSMIC 2015, pp. 3:1\u20133:11. ACM, New York (2015)","DOI":"10.1145\/2723772.2723778"},{"key":"40_CR4","doi-asserted-by":"crossref","unstructured":"August, D.I., Huang, J., Beard, S.R., Johnson, N.P., Jablin, T.B.: Automatically exploiting cross-invocation parallelism using runtime information. In: Proceedings of the 2013 IEEE\/ACM International Symposium on Code Generation and Optimization, CGO 2013, pp. 1\u201311. IEEE Computer Society (2013)","DOI":"10.1109\/CGO.2013.6495001"},{"issue":"3","key":"40_CR5","doi-asserted-by":"publisher","first-page":"63","DOI":"10.1177\/109434209100500306","volume":"5","author":"DH Bailey","year":"1991","unstructured":"Bailey, D.H., Barszcz, E., Barton, J.T., Browning, D.S., Carter, R.L., Fatoohi, R.A., Frederickson, P.O., Lasinski, T.A., Simon, H.D., Venkatakrishnan, V., Weeratunga, S.K.: The NAS parallel benchmarks. Int. J. Supercomput. Appl. 5(3), 63\u201373 (1991)","journal-title":"Int. J. Supercomput. Appl."},{"key":"40_CR6","doi-asserted-by":"crossref","unstructured":"Garcia, S., Jeon, D., Louie, C.M., Taylor, M.B.: Kremlin: rethinking and rebooting gprof for the multicore age. In: Proceedings of the 32nd ACM SIGPLAN Conference on Programming Language Design and Implementation, PLDI 2011, pp. 458\u2013469. ACM (2011)","DOI":"10.1145\/1993498.1993553"},{"key":"40_CR7","doi-asserted-by":"crossref","unstructured":"Govindarajan, R., Anantpur, J.: Runtime dependence computation and execution of loops on heterogeneous systems. In: Proceedings of the 2013 IEEE\/ACM International Symposium on Code Generation and Optimization, CGO 2013, pp. 1\u201310. IEEE Computer Society (2013)","DOI":"10.1109\/CGO.2013.6494992"},{"issue":"04","key":"40_CR8","doi-asserted-by":"publisher","first-page":"1250010","DOI":"10.1142\/S0129626412500107","volume":"22","author":"T Grosser","year":"2012","unstructured":"Grosser, T., Groesslinger, A., Lengauer, C.: Polly - performing polyhedral optimizations on a low-level intermediate representation. Parallel Process. Lett. 22(04), 1250010 (2012)","journal-title":"Parallel Process. Lett."},{"issue":"4","key":"40_CR9","doi-asserted-by":"publisher","first-page":"64:1","DOI":"10.1145\/2688905","volume":"11","author":"ZU Huda","year":"2015","unstructured":"Huda, Z.U., Jannesari, A., Wolf, F.: Using template matching to infer parallel design patterns. ACM Trans. Archit. Code Optim. 11(4), 64:1\u201364:21 (2015)","journal-title":"ACM Trans. Archit. Code Optim."},{"key":"40_CR10","doi-asserted-by":"crossref","unstructured":"Ketterlin, A., Clauss, P.: Profiling data-dependence to assist parallelization: Framework, scope, and optimization. In: Proceedings of the 45th Annual IEEE\/ACM International Symposium on Microarchitecture, MICRO 45, pp. 437\u2013448. IEEE Computer Society (2012)","DOI":"10.1109\/MICRO.2012.47"},{"key":"40_CR11","unstructured":"Kim, M., Kim, H., Luk, C.K.: Prospector: discovering parallelism via dynamic data-dependence profiling. In: Proceedings of the 2nd USENIX Workshop on Hot Topics in Parallelism, HOTPAR 2010 (2010)"},{"key":"40_CR12","doi-asserted-by":"crossref","unstructured":"Kim, M., Kim, H., Luk, C.K.: SD3: A scalable approach to dynamic data-dependence profiling. In: Proceedings of the 43rd Annual IEEE\/ACM International Symposium on Microarchitecture, MICRO 43, pp. 535\u2013546. IEEE Computer Society (2010)","DOI":"10.1109\/MICRO.2010.49"},{"key":"40_CR13","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"539","DOI":"10.1007\/978-3-540-24644-2_35","volume-title":"Languages and Compilers for Parallel Computing","author":"SI Lee","year":"2004","unstructured":"Lee, S.I., Johnson, T., Eigenmann, R.: Cetus - an extensible compiler infrastructure for source-to-source transformation. In: Rauchwerger, L. (ed.) Languages and Compilers for Parallel Computing. Lecture Notes in Computer Science, vol. 2958, pp. 539\u2013553. Springer, Heidelberg (2004)"},{"key":"40_CR14","first-page":"1","volume-title":"Tools for High Performance Computing 2014","author":"Z Li","year":"2015","unstructured":"Li, Z., Atre, R., Ul-Huda, Z., Jannesari, A., Wolf, F.: DiscoPoP: A profiling tool to identify parallelization opportunities. In: Niethammer, C., Gracia, J., Kn\u00fcpfer, A., Resch, M.M., Nagel, W.E. (eds.) Tools for High Performance Computing 2014, 1st edn, pp. 1\u201310. Springer International Publishing, Switzerland (2015)","edition":"1"},{"key":"40_CR15","doi-asserted-by":"crossref","unstructured":"Li, Z., Jannesari, A., Wolf, F.: Discovery of potential parallelism in sequential programs. In: Proceedings of the 42nd International Conference on Parallel Processing, PSTI 2013, pp. 1004\u20131013, vol. 13. IEEE Computer Society (2013)","DOI":"10.1109\/ICPP.2013.119"},{"key":"40_CR16","doi-asserted-by":"crossref","unstructured":"Li, Z., Jannesari, A., Wolf, F.: An efficient data-dependence profiler for sequential and parallel programs. In: Proceedings of the 29th IEEE International Parallel & Distributed Processing Symposium, IPDPS 2015, pp. 484\u2013493 (2015)","DOI":"10.1109\/IPDPS.2015.41"},{"key":"40_CR17","doi-asserted-by":"crossref","unstructured":"Ottoni, G., Rangan, R., Stoler, A., August, D.I.: Automatic thread extraction with decoupled software pipelining. In: Proceedings of the 38th Annual IEEE\/ACM International Symposium on Microarchitecture, MICRO 38, pp. 105\u2013118. IEEE Computer Society (2005)","DOI":"10.1109\/MICRO.2005.13"},{"issue":"1","key":"40_CR18","doi-asserted-by":"publisher","first-page":"55","DOI":"10.1145\/1241601.1241612","volume":"35","author":"S Rul","year":"2007","unstructured":"Rul, S., Vandierendonck, H., De Bosschere, K.: Function level parallelism driven by data dependencies. SIGARCH Comput. Archit. News 35(1), 55\u201362 (2007)","journal-title":"SIGARCH Comput. Archit. News"},{"issue":"9","key":"40_CR19","doi-asserted-by":"publisher","first-page":"531","DOI":"10.1016\/j.parco.2010.05.006","volume":"36","author":"S Rul","year":"2010","unstructured":"Rul, S., Vandierendonck, H., De Bosschere, K.: A profile-based tool for finding pipeline parallelism in sequential programs. Parallel Comput. 36(9), 531\u2013551 (2010)","journal-title":"Parallel Comput."},{"key":"40_CR20","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"110","DOI":"10.1007\/978-3-642-29860-8_9","volume-title":"Runtime Verification","author":"K Serebryany","year":"2012","unstructured":"Serebryany, K., Potapenko, A., Iskhodzhanov, T., Vyukov, D.: Dynamic race detection with LLVM compiler. In: Khurshid, S., Sen, K. (eds.) RV 2011. LNCS, vol. 7186, pp. 110\u2013114. Springer, Heidelberg (2012)"},{"key":"40_CR21","doi-asserted-by":"crossref","unstructured":"Vanka, R., Tuck, J.: Efficient and accurate data dependence profiling using software signatures. In: Proceedings of the 10th International Symposium on Code Generation and Optimization, CGO 2012, pp. 186\u2013195. ACM, New York (2012)","DOI":"10.1145\/2259016.2259041"},{"key":"40_CR22","doi-asserted-by":"crossref","unstructured":"Ye, J.M., Chen, T.: Exploring potential parallelism of sequential programs with superblock reordering. In: Proceedings of the 2012 IEEE 14th International Conference on High Performance Computing and Communication & 2012 IEEE 9th International Conference on Embedded Software and Systems, HPCC 2012, pp. 9\u201316. IEEE Computer Society (2012)","DOI":"10.1109\/HPCC.2012.12"},{"key":"40_CR23","doi-asserted-by":"crossref","unstructured":"Yu, H., Li, Z.: Multi-slicing: a compiler-supported parallel approach to data dependence profiling. In: Proceedings of the 2012 International Symposium on Software Testing and Analysis, ISSTA 2012, pp. 23\u201333. ACM (2012)","DOI":"10.1145\/2338965.2336756"},{"key":"40_CR24","doi-asserted-by":"crossref","unstructured":"Zhang, X., Navabi, A., Jagannathan, S.: Alchemist: a transparent dependence distance profiling infrastructure. In: Proceedings of the 7th Annual IEEE\/ACM International Symposium on Code Generation and Optimization, CGO 2009, pp. 47\u201358. IEEE Computer Society (2009)","DOI":"10.1109\/CGO.2009.15"},{"key":"40_CR25","doi-asserted-by":"crossref","unstructured":"Zhao, B., Li, Z., Jannesari, A., Wolf, F., Wu, W.: Dependence-based code transformation for coarse-grained parallelism. In: Proceedings of the 2015 International Workshop on Code Optimisation for Multi and Many Cores, COSMIC 2015, pp. 1\u201310. ACM, New York (2015)","DOI":"10.1145\/2723772.2723777"}],"container-title":["Lecture Notes in Computer Science","Algorithms and Architectures for Parallel Processing"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-27140-8_40","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,31]],"date-time":"2025-05-31T12:05:59Z","timestamp":1748693159000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-27140-8_40"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015]]},"ISBN":["9783319271392","9783319271408"],"references-count":25,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-27140-8_40","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2015]]}}}