{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T06:20:11Z","timestamp":1742970011058,"version":"3.40.3"},"publisher-location":"Cham","reference-count":45,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030352240"},{"type":"electronic","value":"9783030352257"}],"license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019]]},"DOI":"10.1007\/978-3-030-35225-7_6","type":"book-chapter","created":{"date-parts":[[2019,11,19]],"date-time":"2019-11-19T08:04:56Z","timestamp":1574150696000},"page":"65-85","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Efficient Cache Simulation for Affine Computations"],"prefix":"10.1007","author":[{"given":"Wenlei","family":"Bao","sequence":"first","affiliation":[]},{"given":"Prashant Singh","family":"Rawat","sequence":"additional","affiliation":[]},{"given":"Martin","family":"Kong","sequence":"additional","affiliation":[]},{"given":"Sriram","family":"Krishnamoorthy","sequence":"additional","affiliation":[]},{"given":"Louis-Noel","family":"Pouchet","sequence":"additional","affiliation":[]},{"given":"P.","family":"Sadayappan","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2019,11,15]]},"reference":[{"issue":"2","key":"6_CR1","doi-asserted-by":"publisher","first-page":"184","DOI":"10.1145\/63404.63407","volume":"7","author":"A Agarwal","year":"1989","unstructured":"Agarwal, A., Hennessy, J., Horowitz, M.: An analytical cache model. ACM Trans. Comput. Syst. (TOCS) 7(2), 184\u2013215 (1989)","journal-title":"ACM Trans. Comput. Syst. (TOCS)"},{"key":"6_CR2","doi-asserted-by":"crossref","unstructured":"Bao, W., Tavarageri, S., Ozguner, F., Sadayappan, P.: PWCET: power-aware worst case execution time analysis. In: 2014 43rd International Conference on Parallel Processing Workshops, pp. 439\u2013447, September 2014","DOI":"10.1109\/ICPPW.2014.64"},{"key":"6_CR3","unstructured":"Bao, W.: Power aware WCET analysis (2014)"},{"issue":"4","key":"6_CR4","doi-asserted-by":"publisher","first-page":"51:1","DOI":"10.1145\/3011017","volume":"13","author":"W Bao","year":"2016","unstructured":"Bao, W., et al.: Static and dynamic frequency scaling on multicore CPUs. ACM Trans. Arch. Code Optim. (TACO) 13(4), 51:1\u201351:26 (2016). \nhttps:\/\/doi.org\/10.1145\/3011017","journal-title":"ACM Trans. Arch. Code Optim. (TACO)"},{"issue":"1","key":"6_CR5","doi-asserted-by":"publisher","first-page":"539","DOI":"10.1145\/2914770.2837656","volume":"51","author":"W Bao","year":"2016","unstructured":"Bao, W., Krishnamoorthy, S., Pouchet, L.N., Rastello, F., Sadayappan, P.: PolyCheck: dynamic verification of iteration space transformations on affine programs. SIGPLAN Not. 51(1), 539\u2013554 (2016). \nhttps:\/\/doi.org\/10.1145\/2914770.2837656","journal-title":"SIGPLAN Not."},{"key":"6_CR6","doi-asserted-by":"crossref","unstructured":"Barriga, L., Ayani, R.: Parallel cache simulation on multiprocessor workstattions. In: 1993 International Conference on Parallel Processing, ICPP 1993, vol. 1, pp. 171\u2013174. IEEE (1993)","DOI":"10.1109\/ICPP.1993.134"},{"key":"6_CR7","first-page":"10","volume":"2","author":"C Bastoul","year":"2004","unstructured":"Bastoul, C.: Generating loops for scanning polyhedra: CLooG users guide. Polyhedron 2, 10 (2004)","journal-title":"Polyhedron"},{"issue":"6","key":"6_CR8","doi-asserted-by":"publisher","first-page":"714","DOI":"10.1109\/12.689650","volume":"47","author":"TM Conte","year":"1998","unstructured":"Conte, T.M., Hirsch, M.A., Hwu, W.M.: Combining trace sampling with single pass methods for efficient cache simulation. IEEE Trans. Comput. 47(6), 714\u2013720 (1998)","journal-title":"IEEE Trans. Comput."},{"key":"6_CR9","doi-asserted-by":"crossref","unstructured":"Dundar, M., Kou, Q., Zhang, B., He, Y., Rajwa, B.: Simplicity of kmeans versus deepness of deep learning: a case of unsupervised feature learning with limited data. In: 2015 IEEE 14th International Conference on Machine Learning and Applications (ICMLA), pp. 883\u2013888. IEEE (2015)","DOI":"10.1109\/ICMLA.2015.78"},{"key":"6_CR10","unstructured":"Edler, J., Hill, M.D.: Dinero IV trace-driven uniprocessor cache simulator (1999). \nhttp:\/\/www.cs.wisc.edu\/markhill"},{"issue":"6","key":"6_CR11","doi-asserted-by":"publisher","first-page":"389","DOI":"10.1007\/BF01379404","volume":"21","author":"P Feautrier","year":"1992","unstructured":"Feautrier, P.: Some efficient solutions to the affine scheduling problem, part II: multidimensional time. Int. J. Parallel Prog. 21(6), 389\u2013420 (1992)","journal-title":"Int. J. Parallel Prog."},{"key":"6_CR12","doi-asserted-by":"publisher","unstructured":"Ghosh, S., Martonosi, M., Malik, S.: Precise miss analysis for program transformations with caches of arbitrary associativity. In: Proceedings of the Eighth International Conference on Architectural Support for Programming Languages and Operating Systems, ASPLOS VIII, pp. 228\u2013239. ACM, New York (1998). \nhttps:\/\/doi.org\/10.1145\/291069.291051","DOI":"10.1145\/291069.291051"},{"issue":"4","key":"6_CR13","doi-asserted-by":"publisher","first-page":"703","DOI":"10.1145\/325478.325479","volume":"21","author":"S Ghosh","year":"1999","unstructured":"Ghosh, S., Martonosi, M., Malik, S.: Cache miss equations: a compiler framework for analyzing and tuning memory behavior. ACM Trans. Program. Lang. Syst. (TOPLAS) 21(4), 703\u2013746 (1999)","journal-title":"ACM Trans. Program. Lang. Syst. (TOPLAS)"},{"issue":"3","key":"6_CR14","doi-asserted-by":"publisher","first-page":"261","DOI":"10.1007\/s10766-006-0012-3","volume":"34","author":"S Girbal","year":"2006","unstructured":"Girbal, S., et al.: Semi-automatic composition of loop transformations. Int. J. Parallel Prog. 34(3), 261\u2013317 (2006)","journal-title":"Int. J. Parallel Prog."},{"key":"6_CR15","unstructured":"Heidelberger, P., Stone, H.S.: Parallel trace-driven cache simulation by time partitioning. In: 1990 Proceedings of the Simulation Conference, Winter, pp. 734\u2013737. IEEE (1990)"},{"issue":"12","key":"6_CR16","doi-asserted-by":"publisher","first-page":"1612","DOI":"10.1109\/12.40842","volume":"38","author":"MD Hill","year":"1989","unstructured":"Hill, M.D., Smith, A.J.: Evaluating associativity in CPU caches. IEEE Trans. Comput. 38(12), 1612\u20131630 (1989)","journal-title":"IEEE Trans. Comput."},{"issue":"6","key":"6_CR17","doi-asserted-by":"publisher","first-page":"129","DOI":"10.1145\/2980983.2908123","volume":"51","author":"C Hong","year":"2016","unstructured":"Hong, C., et al.: Effective padding of multidimensional arrays to avoid cache conflict misses. SIGPLAN Not. 51(6), 129\u2013144 (2016). \nhttps:\/\/doi.org\/10.1145\/2980983.2908123","journal-title":"SIGPLAN Not."},{"key":"6_CR18","doi-asserted-by":"crossref","unstructured":"Zhang, J., Lu, X., Panda, D.: High performance MPI library for container-based HPC cloud on InfiniBand clusters, August 2016","DOI":"10.1109\/ICPP.2016.38"},{"key":"6_CR19","unstructured":"Kiesling, T.: Approximate time-parallel cache simulation. In: Proceedings of the 36th Conference on Winter Simulation, pp. 345\u2013354. Winter Simulation Conference (2004)"},{"key":"6_CR20","doi-asserted-by":"crossref","unstructured":"Kiesling, T., Pohl, S.: Time-parallel simulation with approximative state matching. In: Proceedings of the Eighteenth Workshop on Parallel and Distributed Simulation, pp. 195\u2013202. ACM (2004)","DOI":"10.1145\/1013329.1013361"},{"key":"6_CR21","doi-asserted-by":"crossref","unstructured":"Lauterbach, G.: Accelerating architectural simulation by parallel execution of trace samples. In: 1994 Proceedings of the Twenty-Seventh Hawaii International Conference on System Sciences, vol. 1, pp. 205\u2013210. IEEE (1994)","DOI":"10.1109\/HICSS.1994.323171"},{"key":"6_CR22","doi-asserted-by":"crossref","unstructured":"Li, M., Lu, X., Hamidouche, K., Zhang, J., Panda, D.K.: Mizan-RMA: accelerating Mizan graph processing framework with MPI RMA. In: 2016 IEEE 23rd International Conference on High Performance Computing (HiPC), pp. 42\u201351, December 2016","DOI":"10.1109\/HiPC.2016.015"},{"key":"6_CR23","doi-asserted-by":"publisher","unstructured":"Li, M., Potluri, S., Hamidouche, K., Jose, J., Panda, D.K.: Efficient and truly passive MPI-3 RMA using InfiniBand atomics. In: Proceedings of the 20th European MPI Users\u2019 Group Meeting, EuroMPI 2013, pp. 91\u201396. ACM, New York (2013). \nhttps:\/\/doi.org\/10.1145\/2488551.2488573","DOI":"10.1145\/2488551.2488573"},{"key":"6_CR24","unstructured":"Li, M., Hamidouche, K., Lu, X., Subramoni, H., Zhang, J., Panda, D.K.: Designing MPI library with on-demand paging (ODP) of InfiniBand: challenges and benefits. In: Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis, SC 2016, pp. 37:1\u201337:11. IEEE Press, Piscataway (2016). \nhttp:\/\/dl.acm.org\/citation.cfm?id=3014904.3014954"},{"issue":"2","key":"6_CR25","doi-asserted-by":"publisher","first-page":"78","DOI":"10.1147\/sj.92.0078","volume":"9","author":"RL Mattson","year":"1970","unstructured":"Mattson, R.L., Gecsei, J., Slutz, D.R., Traiger, I.L.: Evaluation techniques for storage hierarchies. IBM Syst. J. 9(2), 78\u2013117 (1970)","journal-title":"IBM Syst. J."},{"issue":"8","key":"6_CR26","doi-asserted-by":"publisher","first-page":"849","DOI":"10.1109\/71.298211","volume":"5","author":"DM Nicol","year":"1994","unstructured":"Nicol, D.M., Greenberg, A.G., Lubachevsky, B.D.: Massively parallel algorithms for trace-driven cache simulations. IEEE Trans. Parallel Distrib. Syst. 5(8), 849\u2013859 (1994)","journal-title":"IEEE Trans. Parallel Distrib. Syst."},{"key":"6_CR27","volume-title":"Computer Architecture: A Quantitative Approach","author":"DA Patterson","year":"2011","unstructured":"Patterson, D.A.: Computer Architecture: A Quantitative Approach. Elsevier, Amsterdam (2011)"},{"key":"6_CR28","doi-asserted-by":"crossref","unstructured":"Pieper, J.J., Mellan, A., Paul, J.M., Thomas, D.E., Karim, F.: High level cache simulation for heterogeneous multiprocessors. In: Proceedings of the 41st Annual Design Automation Conference, pp. 287\u2013292. ACM (2004)","DOI":"10.1145\/996566.996652"},{"key":"6_CR29","unstructured":"Pouchet, L.N.: Polybench: the polyhedral benchmark suite (2012). \nhttp:\/\/www.cs.ucla.edu\/pouchet\/software\/polybench"},{"key":"6_CR30","unstructured":"Puzak, T.R.: Analysis of cache replacement-algorithms (1985)"},{"key":"6_CR31","doi-asserted-by":"publisher","unstructured":"Schuff, D.L., Kulkarni, M., Pai, V.S.: Accelerating multicore reuse distance analysis with sampling and parallelization. In: Proceedings of the 19th International Conference on Parallel Architectures and Compilation Techniques, PACT 2010, pp. 53\u201364. ACM, New York (2010). \nhttps:\/\/doi.org\/10.1145\/1854273.1854286","DOI":"10.1145\/1854273.1854286"},{"issue":"1","key":"6_CR32","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1145\/200912.200918","volume":"13","author":"RA Sugumar","year":"1995","unstructured":"Sugumar, R.A., Abraham, S.G.: Set-associative cache simulation using generalized binomial trees. ACM Trans. Comput. Syst. (TOCS) 13(1), 32\u201356 (1995)","journal-title":"ACM Trans. Comput. Syst. (TOCS)"},{"key":"6_CR33","unstructured":"Sugumar, R.A.: Multi-configuration simulation algorithms for the evaluation of computer architecture designs (1993)"},{"issue":"2","key":"6_CR34","doi-asserted-by":"publisher","first-page":"128","DOI":"10.1145\/254180.254184","volume":"29","author":"RA Uhlig","year":"1997","unstructured":"Uhlig, R.A., Mudge, T.N.: Trace-driven memory simulation: a survey. ACM Comput. Surv. (CSUR) 29(2), 128\u2013170 (1997)","journal-title":"ACM Comput. Surv. (CSUR)"},{"key":"6_CR35","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"299","DOI":"10.1007\/978-3-642-15582-6_49","volume-title":"Mathematical Software \u2013 ICMS 2010","author":"S Verdoolaege","year":"2010","unstructured":"Verdoolaege, S.: isl: an integer set library for the polyhedral model. In: Fukuda, K., Hoeven, J., Joswig, M., Takayama, N. (eds.) ICMS 2010. LNCS, vol. 6327, pp. 299\u2013302. Springer, Heidelberg (2010). \nhttps:\/\/doi.org\/10.1007\/978-3-642-15582-6_49"},{"key":"6_CR36","unstructured":"Verdoolaege, S., Grosser, T.: Polyhedral extraction tool. In: Second International Workshop on Polyhedral Compilation Techniques (IMPACT 2012), Paris, France (2012)"},{"key":"6_CR37","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"177","DOI":"10.1007\/978-3-642-03644-6_14","volume-title":"Advanced Parallel Processing Technologies","author":"H Wan","year":"2009","unstructured":"Wan, H., Gao, X., Long, X., Wang, Z.: GCSim: a GPU-based trace-driven simulator for multi-level cache. In: Dou, Y., Gruber, R., Joller, J.M. (eds.) APPT 2009. LNCS, vol. 5737, pp. 177\u2013190. Springer, Heidelberg (2009). \nhttps:\/\/doi.org\/10.1007\/978-3-642-03644-6_14"},{"issue":"1","key":"6_CR38","doi-asserted-by":"publisher","first-page":"1:1","DOI":"10.1145\/2427631.2427632","volume":"31","author":"MJ Wu","year":"2013","unstructured":"Wu, M.J., Yeung, D.: Efficient reuse distance analysis of multicore scaling for loop-based parallel programs. ACM Trans. Comput. Syst. 31(1), 1:1\u20131:37 (2013). \nhttps:\/\/doi.org\/10.1145\/2427631.2427632","journal-title":"ACM Trans. Comput. Syst."},{"issue":"9","key":"6_CR39","doi-asserted-by":"publisher","first-page":"930","DOI":"10.1109\/71.466631","volume":"6","author":"Y Wu","year":"1995","unstructured":"Wu, Y., Muntz, R.: Stack evaluation of arbitrary set-associative multiprocessor caches. IEEE Trans. Parallel Distrib. Syst. 6(9), 930\u2013942 (1995)","journal-title":"IEEE Trans. Parallel Distrib. Syst."},{"key":"6_CR40","unstructured":"Zhang, B., et al.: Trust from the past: Bayesian personalized ranking based link prediction in knowledge graphs. In: SDM Workshop on Mining Networks and Graphs (MNG 2016) (2016)"},{"key":"6_CR41","doi-asserted-by":"crossref","unstructured":"Zhang, B., Dundar, M., Hasan, M.A.: Bayesian non-exhaustive classification a case study: online name disambiguation using temporal record streams. In: CIKM 2016 Proceedings of the 25th ACM International Conference on Information and Knowledge Management, pp. 1341\u20131350. ACM (2016)","DOI":"10.1145\/2983323.2983714"},{"key":"6_CR42","doi-asserted-by":"crossref","unstructured":"Zhang, B., Dundar, M., Hasan, M.A.: Bayesian non-exhaustive classification for active online name disambiguation. arXiv preprint \narXiv:1708.04531\n\n (2017)","DOI":"10.1145\/2983323.2983714"},{"key":"6_CR43","doi-asserted-by":"crossref","unstructured":"Zhang, B., Hasan, M.A.: Name disambiguation in anonymized graphs using network embedding. In: The 26th ACM International Conference on Information and Knowledge Management (CIKM 2017) (2017)","DOI":"10.1145\/3132847.3132873"},{"key":"6_CR44","first-page":"1","volume":"10","author":"B Zhang","year":"2017","unstructured":"Zhang, B., Mohammed, N., Dave, V., Hasan, M.A.: Feature selection for classification under anonymity constraint. Trans. Data Priv. 10, 1\u201325 (2017)","journal-title":"Trans. Data Priv."},{"key":"6_CR45","doi-asserted-by":"crossref","unstructured":"Zhang, B., Saha, T.K., Al Hasan, M.: Name disambiguation from link data in a collaboration graph. In: 2014 IEEE\/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM), pp. 81\u201384. IEEE (2014)","DOI":"10.1109\/ASONAM.2014.6921563"}],"container-title":["Lecture Notes in Computer Science","Languages and Compilers for Parallel Computing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-35225-7_6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,11,19]],"date-time":"2019-11-19T18:03:44Z","timestamp":1574186624000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-35225-7_6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"ISBN":["9783030352240","9783030352257"],"references-count":45,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-35225-7_6","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2019]]},"assertion":[{"value":"15 November 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"LCPC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Workshop on Languages and Compilers for Parallel Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"College Station, TX","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"USA","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2017","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"11 October 2017","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13 October 2017","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"lcpc2017","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/parasol.tamu.edu\/lcpc2017\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Hotcrp.com","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"24","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"13","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"4","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"54% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}