{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,4]],"date-time":"2025-05-04T12:40:06Z","timestamp":1746362406856,"version":"3.40.4"},"reference-count":32,"publisher":"Institute of Electronics, Information and Communications Engineers (IEICE)","issue":"9","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEICE Trans. Inf. &amp; Syst."],"published-print":{"date-parts":[[2014]]},"DOI":"10.1587\/transinf.2013edp7455","type":"journal-article","created":{"date-parts":[[2014,8,31]],"date-time":"2014-08-31T23:32:28Z","timestamp":1409527948000},"page":"2371-2385","source":"Crossref","is-referenced-by-count":3,"title":["Identifying Program Loop Nesting Structures during Execution of Machine Code"],"prefix":"10.1587","volume":"E97.D","author":[{"given":"Yukinori","family":"SATO","sequence":"first","affiliation":[{"name":"Japan Advanced Institute of Science and Technology (JAIST)"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yasushi","family":"INOGUCHI","sequence":"additional","affiliation":[{"name":"Japan Advanced Institute of Science and Technology (JAIST)"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tadao","family":"NAKAMURA","sequence":"additional","affiliation":[{"name":"Keio University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"532","reference":[{"key":"1","doi-asserted-by":"crossref","unstructured":"[1] J. Larus, \u201cSpending Moore&apos;s dividend,\u201d Commun. ACM, vol.52, no.5, pp.62-69, May 2009.","DOI":"10.1145\/1506409.1506425"},{"key":"2","doi-asserted-by":"crossref","unstructured":"[2] J.L. Henning, \u201cSPEC CPU suite growth: An historical perspective,\u201d SIGARCH Comput. Archit. News, vol.35, no.1, pp.65-68, March 2007.","DOI":"10.1145\/1241601.1241615"},{"key":"3","doi-asserted-by":"crossref","unstructured":"[3] M. Terai, H. Murai, K. Minami, M. Yokokawa, and E. Tomiyama, \u201cK-scope: A java-based fortran source code analyzer with graphical user interface for performance improvement,\u201d Third International Workshop on Parallel Software Tools and Tool Infrastructures (PSTI 2012), pp.434-443, 2012.","DOI":"10.1109\/ICPPW.2012.61"},{"key":"4","doi-asserted-by":"crossref","unstructured":"[4] P. Havlak, \u201cNesting of reducible and irreducible loops,\u201d ACM Trans. Program. Lang. Syst., vol.19, no.4, pp.557-567, 1997.","DOI":"10.1145\/262004.262005"},{"key":"5","doi-asserted-by":"crossref","unstructured":"[5] M. Hall, J. Chame, C. Chen, J. Shin, G. Rudy, and M.M. Khan, \u201cLoop transformation recipes for code generation and auto-tuning,\u201d 22nd International Workshop on Languages and Compilers for Parallel Computing, LCPC 2009, Lect. Notes Comput. Sci., 2010.","DOI":"10.1007\/978-3-642-13374-9_4"},{"key":"6","doi-asserted-by":"crossref","unstructured":"[6] K. Beyls and E.H. D&apos;Hollander, \u201cRefactoring for data locality,\u201d Computer, vol.42, no.2, pp.62-71, 2009.","DOI":"10.1109\/MC.2009.57"},{"key":"7","doi-asserted-by":"crossref","unstructured":"[7] T. Moseley, D.A. Connors, D. Grunwald, and Peri,\u201cIdentifying potential parallelism via loop-centric profiling,\u201d Proc. 4th International Conference on Computing Frontiers, pp.143-152, 2007.","DOI":"10.1145\/1242531.1242554"},{"key":"8","unstructured":"[8] N.R. Tallent, J.M. Mellor-Crummey, and M.W. Fagan, \u201cBinary analysis for measurement and attribution of program performance,\u201d Proc. 2009 ACM SIGPLAN Conference on Programming Language Design and Implementation, pp.441-452, 2009."},{"key":"9","doi-asserted-by":"crossref","unstructured":"[9] Y. Sato, Y. Inoguchi, and T. Nakamura, \u201cOn-the-fly detection of precise loop nests across procedures on a dynamic binary translation system,\u201d Proc. 8th ACM International Conference on Computing Frontiers, May 2011.","DOI":"10.1145\/2016604.2016634"},{"key":"10","unstructured":"[10] M.R. de Alba and D.R. Kaeli, \u201cRuntime predictability of loops,\u201d Proc. Workload Characterization, 2001. WWC-4. 2001 IEEE International Workshop, pp.91-98, 2001."},{"key":"11","unstructured":"[11] Y. Wu, M. Breternitz, and T. Devor, \u201cContinuous trip count profiling for loop optimizations in two-phase dynamic binary translators,\u201d Proc. Eighth Annual Workshop on Interaction between Compilers and Computer Architectures (INTERACT&apos;04), pp.3-12, 2004."},{"key":"12","doi-asserted-by":"crossref","unstructured":"[12] M. Kim, H. Kim, and C.-K. Luk, \u201c<i>SD<\/i><sup>3<\/sup>: A scalable approach to dynamic data-dependence profiling,\u201d MICRO &apos;43, pp.535-546, 2010.","DOI":"10.1109\/MICRO.2010.49"},{"key":"13","doi-asserted-by":"crossref","unstructured":"[13] Y. Sato, Y. Inoguchi, and T. Nakamura, \u201cWhole program data dependence profiling to unveil parallel regions in the dynamic execution,\u201d 2012 IEEE International Symposium on Workload Characterization (IISWC2012), pp.69-80, Nov. 2012.","DOI":"10.1109\/IISWC.2012.6402902"},{"key":"14","doi-asserted-by":"crossref","unstructured":"[14] Y. Sato, K. Suzuki, and T. Nakamura, \u201cRun-time detection mechanism of nested call-loop structure to monitor the actual execution of codes,\u201d Proc. First International Workshop on Software Technologies for Future Dependable Distributed Systems, pp.184-188, 2009.","DOI":"10.1109\/STFSSD.2009.30"},{"key":"15","doi-asserted-by":"crossref","unstructured":"[15] J. Tubella and A. Gonz\u00e1lez, \u201cControl speculation in multithreaded processors through dynamic loop detection,\u201d Proc. 4th International Symposium on High-Performance Computer Architecture, p.14, 1998.","DOI":"10.1109\/HPCA.1998.650542"},{"key":"16","unstructured":"[16] A.V. Aho, M.S. Lam, R. Sethi, and J.D. Ullman, Compilers: Principles, Techniques, and Tools, 2nd ed., Addison Wesley, 2006."},{"key":"17","doi-asserted-by":"crossref","unstructured":"[17] G. Ammons, T. Ball, and J.R. Larus, \u201cExploiting hardware performance counters with flow and context sensitive profiling,\u201d Proc. ACM SIGPLAN 1997 Conference on Programming Language Design and Implementation, pp.85-96, 1997.","DOI":"10.1145\/258916.258924"},{"key":"18","unstructured":"[18] T.H. Cormen, C.E. Leiserson, R.L. Rivest, and C. Stein, Introduction to Algorithms, Third ed., The MIT Press, 2009."},{"key":"19","doi-asserted-by":"crossref","unstructured":"[19] D. K\u00e4stner and S. Wilhelm, \u201cGeneric control flow reconstruction from assembly code,\u201d Proc. Joint Conference on Languages, Compilers and Tools for Embedded Systems: Software and Compilers for Embedded Systems, LCTES\/SCOPES &apos;02, pp.46-55, 2002.","DOI":"10.1145\/513829.513839"},{"key":"20","doi-asserted-by":"crossref","unstructured":"[20] N. Froyd, J. Mellor-Crummey, and R. Fowler, \u201cLow-overhead call path profiling of unmodified, optimized code,\u201d Proc. 19th Annual International Conference on Supercomputing, ICS &apos;05, pp.81-90, 2005.","DOI":"10.1145\/1088149.1088161"},{"key":"21","unstructured":"[21] C.K. Luk, R. Cohn, R. Muth, H. Patil, A. Klauser, G. Lowney, S. Wallace, V.J. Reddi, and K. Hazelwood, \u201cPin: building customized program analysis tools with dynamic instrumentation,\u201d Proc. 2005 ACM SIGPLAN Conference on Programming Language Design and Implementation, pp.190-200, 2005."},{"key":"22","doi-asserted-by":"crossref","unstructured":"[22] J.L. Henning, \u201cSpec CPU2006 benchmark descriptions,\u201d SIGARCH Comput. Archit. News, vol.34, no.4, pp.1-17, Sept. 2006.","DOI":"10.1145\/1186736.1186737"},{"key":"23","unstructured":"[23] E. Borin and Y. Wu, \u201cCharacterization of DBT overhead,\u201d Proc. 2009 IEEE International Symposium on Workload Characterization (IISWC), pp.178-187, 2009."},{"key":"24","doi-asserted-by":"crossref","unstructured":"[24] E. Borin, Y. Wu, C. Wang, W. Liu, M. Breternitz, Jr., S. Hu, E. Natanzon, S. Rotem, and R. Rosner, \u201cTAO: Two-level atomicity for dynamic binary optimizations,\u201d Proc. 8th Annual IEEE\/ACM International Symposium on Code Generation and Optimization, pp.12-21, 2010.","DOI":"10.1145\/1772954.1772959"},{"key":"25","unstructured":"[25] L. Djoudi, D. Barthou, P. Carribault, C. Lemuet, J.T. Acquaviva, and W. Jalby, \u201cExploring application performance: A new tool for a static\/dynamic approach,\u201d Los Alamos Computer Science Institute Symp., 2005."},{"key":"26","doi-asserted-by":"crossref","unstructured":"[26] S. Koliai, S. Zuckerman, E. Oseret, M. Ivascot, T. Moseley, D. Quang, and W. Jalby, \u201cA balanced approach to application performance tuning,\u201d Proc. 22nd International Conference on Languages and Compilers for Parallel Computing, LCPC&apos;09, pp.111-125, 2009.","DOI":"10.1007\/978-3-642-13374-9_8"},{"key":"27","doi-asserted-by":"crossref","unstructured":"[27] S. Rul, H. Vandierendonck, and K. De Bosschere, \u201cTowards automatic program partitioning,\u201d Proc. 6th ACM Conference on Computing Frontiers, pp.89-98, 2009.","DOI":"10.1145\/1531743.1531759"},{"key":"28","doi-asserted-by":"crossref","unstructured":"[28] S. Wang, X. Dai, K.S. Yellajyosula, A. Zhai, and P.C. Yew, \u201cLoop selection for thread-level speculation,\u201d Workshops on Languages and Compilers for Parallel Computing (LCPC 2005), 2005.","DOI":"10.1007\/978-3-540-69330-7_20"},{"key":"29","doi-asserted-by":"crossref","unstructured":"[29] J. Lau, E. Perelman, and B. Calder, \u201cSelecting software phase markers with code structure analysis,\u201d Proc. International Symposium on Code Generation and Optimization, pp.135-146, 2006.","DOI":"10.1109\/CGO.2006.32"},{"key":"30","doi-asserted-by":"crossref","unstructured":"[30] K. Beyls and E.H. D&apos;Hollander, \u201cIntermediately executed code is the key to find refactorings that improve temporal data locality,\u201d Proc. 3rd Conference on Computing Furontiers, CF &apos;06, pp.373-382, 2006.","DOI":"10.1145\/1128022.1128071"},{"key":"31","doi-asserted-by":"crossref","unstructured":"[31] M. Chen and K. Olukotun, \u201cTEST: A tracer for extracting speculative threads,\u201d Proc. International Symposium on Code Generation and Optimization, pp.301-312, 2003.","DOI":"10.1109\/CGO.2003.1191554"},{"key":"32","doi-asserted-by":"crossref","unstructured":"[32] G. Balakrishnan and T. Reps, \u201cWYSINWYX: What you see is not what you eXecute,\u201d ACM Trans. Program. Lang. Syst., vol.32, no.6, pp.23: 1-23: 84, Aug. 2010.","DOI":"10.1145\/1749608.1749612"}],"container-title":["IEICE Transactions on Information and Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/transinf\/E97.D\/9\/E97.D_2013EDP7455\/_pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,4]],"date-time":"2025-05-04T12:13:02Z","timestamp":1746360782000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/transinf\/E97.D\/9\/E97.D_2013EDP7455\/_article"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014]]},"references-count":32,"journal-issue":{"issue":"9","published-print":{"date-parts":[[2014]]}},"URL":"https:\/\/doi.org\/10.1587\/transinf.2013edp7455","relation":{},"ISSN":["0916-8532","1745-1361"],"issn-type":[{"type":"print","value":"0916-8532"},{"type":"electronic","value":"1745-1361"}],"subject":[],"published":{"date-parts":[[2014]]}}}