{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,12]],"date-time":"2026-03-12T12:34:33Z","timestamp":1773318873756,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":90,"publisher":"ACM","license":[{"start":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T00:00:00Z","timestamp":1763164800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/100000015","name":"U.S. Department of Energy","doi-asserted-by":"publisher","award":["DE-AC52-07NA2734"],"award-info":[{"award-number":["DE-AC52-07NA2734"]}],"id":[{"id":"10.13039\/100000015","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100006227","name":"Lawrence Livermore National Laboratory","doi-asserted-by":"publisher","award":["LDRD 23-ERD-022"],"award-info":[{"award-number":["LDRD 23-ERD-022"]}],"id":[{"id":"10.13039\/100006227","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000781","name":"European Research Council","doi-asserted-by":"publisher","award":["101002047"],"award-info":[{"award-number":["101002047"]}],"id":[{"id":"10.13039\/501100000781","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,11,16]]},"DOI":"10.1145\/3712285.3759797","type":"proceedings-article","created":{"date-parts":[[2025,11,12]],"date-time":"2025-11-12T16:05:39Z","timestamp":1762963539000},"page":"331-348","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["C.A.T.S.: Memory and Control Flow Tracing for Whole-Program Performance Analysis"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8429-7803","authenticated-orcid":false,"given":"Philipp","family":"Schaad","sequence":"first","affiliation":[{"name":"ETH Zurich, Zurich, Switzerland"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3657-6568","authenticated-orcid":false,"given":"Tal","family":"Ben-Nun","sequence":"additional","affiliation":[{"name":"Lawrence Livermore National Laboratory (LLNL), Livermore, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1333-9797","authenticated-orcid":false,"given":"Torsten","family":"Hoefler","sequence":"additional","affiliation":[{"name":"ETH Zurich, Zurich, Switzerland"}]}],"member":"320","published-online":{"date-parts":[[2025,11,15]]},"reference":[{"key":"e_1_3_3_3_2_2","doi-asserted-by":"publisher","DOI":"10.1145\/1879211.1879224"},{"key":"e_1_3_3_3_3_2","doi-asserted-by":"publisher","unstructured":"L. Adhianto S. Banerjee M. Fagan M. Krentel G. Marin J. Mellor\u2010Crummey and N.\u00a0R. Tallent. 2010. HPCTOOLKIT: tools for performance analysis of optimized parallel programs. Concurrency and Computation: Practice and Experience 22 6 (4 2010) 685\u2013701. 10.1002\/cpe.1553","DOI":"10.1002\/cpe.1553"},{"key":"e_1_3_3_3_4_2","doi-asserted-by":"publisher","DOI":"10.1145\/1879211.1879222"},{"key":"e_1_3_3_3_5_2","doi-asserted-by":"publisher","DOI":"10.1145\/3373376.3378498"},{"key":"e_1_3_3_3_6_2","doi-asserted-by":"publisher","unstructured":"Roberto Baldoni Emilio Coppa Daniele\u00a0Cono D\u2019elia Camil Demetrescu and Irene Finocchi. 2019. A Survey of Symbolic Execution Techniques. Comput. Surveys 51 3 (5 2019) 1\u201339. 10.1145\/3182657","DOI":"10.1145\/3182657"},{"key":"e_1_3_3_3_7_2","doi-asserted-by":"publisher","DOI":"10.1145\/3295500.3356173"},{"key":"e_1_3_3_3_8_2","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2011.24"},{"key":"e_1_3_3_3_9_2","doi-asserted-by":"publisher","unstructured":"Alison\u00a0Fernandez Blanco Alexandre Bergel and Juan Pablo\u00a0Sandoval Alcocer. 2023. Software Visualizations to Analyze Memory Consumption: A Literature Review. Comput. Surveys 55 1 (1 2023) 1\u201334. 10.1145\/3485134","DOI":"10.1145\/3485134"},{"key":"e_1_3_3_3_10_2","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2016.46"},{"key":"e_1_3_3_3_11_2","doi-asserted-by":"publisher","DOI":"10.1145\/1375581.1375595"},{"key":"e_1_3_3_3_12_2","doi-asserted-by":"publisher","DOI":"10.1145\/3696443.3708956"},{"key":"e_1_3_3_3_13_2","doi-asserted-by":"publisher","DOI":"10.1145\/3210563.3210564"},{"key":"e_1_3_3_3_14_2","doi-asserted-by":"publisher","DOI":"10.5555\/1855741.1855756"},{"key":"e_1_3_3_3_15_2","doi-asserted-by":"publisher","DOI":"10.1145\/305138.305231"},{"key":"e_1_3_3_3_16_2","doi-asserted-by":"publisher","DOI":"10.1145\/1133956.1133972"},{"key":"e_1_3_3_3_17_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICPC.2007.39"},{"key":"e_1_3_3_3_18_2","doi-asserted-by":"publisher","unstructured":"Steven Dalton Luke Olson and Nathan Bell. 2015. Optimizing Sparse Matrix\u2014Matrix Multiplication for the GPU. ACM Trans. Math. Software 41 4 (10 2015) 1\u201320. 10.1145\/2699470","DOI":"10.1145\/2699470"},{"key":"e_1_3_3_3_19_2","doi-asserted-by":"publisher","DOI":"10.1109\/WOLFHPC.2014.8"},{"key":"e_1_3_3_3_20_2","doi-asserted-by":"publisher","DOI":"10.1145\/1879211.1879233"},{"key":"e_1_3_3_3_21_2","doi-asserted-by":"publisher","DOI":"10.1145\/781131.781159"},{"key":"e_1_3_3_3_22_2","doi-asserted-by":"publisher","DOI":"10.1109\/WCRE.2002.1173071"},{"key":"e_1_3_3_3_23_2","doi-asserted-by":"publisher","unstructured":"Thomas Eisenbarth Rainer Koschke and Gunther Vogel. 2005. Static object trace extraction for programs with pointers. Journal of Systems and Software 77 3 (9 2005) 263\u2013284. 10.1016\/j.jss.2004.04.028","DOI":"10.1016\/j.jss.2004.04.028"},{"key":"e_1_3_3_3_24_2","volume-title":"CLOUDSC cloud microphysics scheme","author":"Forecasts European Centre for Medium-Range Weather","year":"2003","unstructured":"European Centre for Medium-Range Weather Forecasts. 2003. CLOUDSC cloud microphysics scheme. https:\/\/github.com\/ecmwf-ifs\/dwarf-p-cloudsc"},{"key":"e_1_3_3_3_25_2","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-36614-82"},{"key":"e_1_3_3_3_26_2","doi-asserted-by":"publisher","unstructured":"Paul Feautrier. 1991. Dataflow analysis of array and scalar references. International Journal of Parallel Programming 20 1 (2 1991) 23\u201353. 10.1007\/BF01407931","DOI":"10.1007\/BF01407931"},{"key":"e_1_3_3_3_27_2","doi-asserted-by":"publisher","DOI":"10.1109\/VISSOFT.2018.00013"},{"key":"e_1_3_3_3_28_2","doi-asserted-by":"publisher","unstructured":"Jianhua Gao Weixing Ji Fangli Chang Shiyu Han Bingxin Wei Zeming Liu and Yizhuo Wang. 2023. A Systematic Survey of General Sparse Matrix-matrix Multiplication. Comput. Surveys 55 12 (12 2023) 1\u201336. 10.1145\/3571157","DOI":"10.1145\/3571157"},{"key":"e_1_3_3_3_29_2","doi-asserted-by":"publisher","unstructured":"Markus Geimer Felix Wolf Brian J.\u00a0N. Wylie Erika \u00c1brah\u00e1m Daniel Becker and Bernd Mohr. 2010. The Scalasca performance toolset architecture. Concurrency and Computation: Practice and Experience 22 6 (4 2010) 702\u2013719. 10.1002\/cpe.1556","DOI":"10.1002\/cpe.1556"},{"key":"e_1_3_3_3_30_2","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2012.32"},{"key":"e_1_3_3_3_31_2","doi-asserted-by":"publisher","DOI":"10.1145\/3627535.3638496"},{"key":"e_1_3_3_3_32_2","doi-asserted-by":"publisher","unstructured":"Alfredo Gimenez Todd Gamblin Ilir Jusufi Abhinav Bhatele Martin Schulz Peer-Timo Bremer and Bernd Hamann. 2018. MemAxes: Visualization and Analytics for Characterizing Complex Memory Performance Behaviors. IEEE Transactions on Visualization and Computer Graphics 24 7 (7 2018) 2180\u20132193. 10.1109\/TVCG.2017.2718532","DOI":"10.1109\/TVCG.2017.2718532"},{"key":"e_1_3_3_3_33_2","doi-asserted-by":"publisher","unstructured":"Ant\u00f4nio Tadeu\u00a0A. Gomes Enzo Molion Roberto\u00a0P. Souto and Jean\u2010Fran\u00e7ois M\u00e9haut. 2021. Memory allocation anomalies in high\u2010performance computing applications: A study with numerical simulations. Concurrency and Computation: Practice and Experience 33 18 (9 2021). 10.1002\/cpe.6094","DOI":"10.1002\/cpe.6094"},{"key":"e_1_3_3_3_34_2","doi-asserted-by":"publisher","unstructured":"Susan\u00a0L. Graham Peter\u00a0B. Kessler and Marshall\u00a0K. McKusick. 1982. Gprof: a Call Graph Execution Profiler. ACM SIGPLAN Notices 17 6 (6 1982) 120\u2013126. 10.1145\/872726.806987","DOI":"10.1145\/872726.806987"},{"key":"e_1_3_3_3_35_2","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2016.44"},{"key":"e_1_3_3_3_36_2","volume-title":"GT4Py: GridTools for Python","year":"2025","unstructured":"GridTools. 2025. GT4Py: GridTools for Python. https:\/\/github.com\/GridTools\/gt4py"},{"key":"e_1_3_3_3_37_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-56702-01"},{"key":"e_1_3_3_3_38_2","doi-asserted-by":"publisher","unstructured":"Charles\u00a0R. Harris K.\u00a0Jarrod Millman St\u00e9fan\u00a0J. van\u00a0der Walt Ralf Gommers Pauli Virtanen David Cournapeau Eric Wieser Julian Taylor Sebastian Berg Nathaniel\u00a0J. Smith Robert Kern Matti Picus Stephan Hoyer Marten\u00a0H. van Kerkwijk Matthew Brett Allan Haldane Jaime\u00a0Fern\u00e1ndez del R\u00edo Mark Wiebe Pearu Peterson Pierre G\u00e9rard-Marchant Kevin Sheppard Tyler Reddy Warren Weckesser Hameer Abbasi Christoph Gohlke and Travis\u00a0E. Oliphant. 2020. Array programming with NumPy. Nature 585 7825 (9 2020) 357\u2013362. 10.1038\/s41586-020-2649-2","DOI":"10.1038\/s41586-020-2649-2"},{"key":"e_1_3_3_3_39_2","doi-asserted-by":"publisher","DOI":"10.1145\/3236024.3236085"},{"key":"e_1_3_3_3_40_2","doi-asserted-by":"publisher","DOI":"10.2172\/1089988"},{"key":"e_1_3_3_3_41_2","doi-asserted-by":"publisher","unstructured":"Roman Iakymchuk and Paolo Bientinesi. 2012. Modeling performance through memory-stalls. ACM SIGMETRICS Performance Evaluation Review 40 2 (10 2012) 86\u201391. 10.1145\/2381056.2381076","DOI":"10.1145\/2381056.2381076"},{"key":"e_1_3_3_3_42_2","volume-title":"Intel VTune Profiler","year":"2025","unstructured":"Intel. 2025. Intel VTune Profiler. https:\/\/software.intel.com\/content\/www\/us\/en\/develop\/tools\/oneapi\/components\/vtune-profiler.html"},{"key":"e_1_3_3_3_43_2","unstructured":"Katherine\u00a0E Isaacs Alfredo Gim\u00e9nez Ilir Jusufi Todd Gamblin Abhinav Bhatele Martin Schulz Bernd Hamann and Peer-timo Bremer. 2014. State of the Art of Performance Visualization. EuroVis 2014 (2014) 141\u2013160."},{"key":"e_1_3_3_3_44_2","doi-asserted-by":"publisher","DOI":"10.1109\/SC.Companion.2012.202"},{"key":"e_1_3_3_3_45_2","unstructured":"Andrei Ivanov Nikoli Dryden Tal Ben-Nun Shigang Li and Torsten Hoefler. 2021. Data Movement Is All You Need: A Case Study on Optimizing Transformers. Proceedings of Machine Learning and Systems (2021)."},{"key":"e_1_3_3_3_46_2","doi-asserted-by":"publisher","DOI":"10.25923\/ztzy-qn82"},{"key":"e_1_3_3_3_47_2","doi-asserted-by":"publisher","DOI":"10.1109\/MSR59073.2023.00037"},{"key":"e_1_3_3_3_48_2","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.1998.742790"},{"key":"e_1_3_3_3_49_2","doi-asserted-by":"publisher","DOI":"10.2172\/1090032"},{"key":"e_1_3_3_3_50_2","doi-asserted-by":"publisher","DOI":"10.6028\/NBS.SP.440"},{"key":"e_1_3_3_3_51_2","doi-asserted-by":"publisher","unstructured":"Suraj\u00a0P. Kesavan Harsh Bhatia Abhinav Bhatele Stephanie Brink Olga Pearce Todd Gamblin Peer-Timo Bremer and Kwan-Liu Ma. 2023. Scalable Comparative Visualization of Ensembles of Call Graphs. IEEE Transactions on Visualization and Computer Graphics 29 3 (3 2023) 1691\u20131704. 10.1109\/TVCG.2021.3129414","DOI":"10.1109\/TVCG.2021.3129414"},{"key":"e_1_3_3_3_52_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-31476-67"},{"key":"e_1_3_3_3_53_2","doi-asserted-by":"publisher","unstructured":"J.\u00a0B. Kruskal and J.\u00a0M. Landwehr. 1983. Icicle Plots: Better Displays for Hierarchical Clustering. The American Statistician 37 2 (5 1983) 162\u2013168. 10.1080\/00031305.1983.10482733","DOI":"10.1080\/00031305.1983.10482733"},{"key":"e_1_3_3_3_54_2","doi-asserted-by":"publisher","unstructured":"A.\u00a0G. Landge J.\u00a0A. Levine A. Bhatele K.\u00a0E. Isaacs T. Gamblin M. Schulz S.\u00a0H. Langer Peer-Timo Bremer and V. Pascucci. 2012. Visualizing Network Traffic to Understand the Performance of Massively Parallel Simulations. IEEE Transactions on Visualization and Computer Graphics 18 12 (12 2012) 2467\u20132476. 10.1109\/TVCG.2012.286","DOI":"10.1109\/TVCG.2012.286"},{"key":"e_1_3_3_3_55_2","volume-title":"Livermore Unstructured Lagrangian Explicit Shock Hydrodynamics (LULESH)","author":"Laboratory Lawrence Livermore National","year":"2025","unstructured":"Lawrence Livermore National Laboratory. 2025. Livermore Unstructured Lagrangian Explicit Shock Hydrodynamics (LULESH). https:\/\/github.com\/LLNL\/LULESH"},{"key":"e_1_3_3_3_56_2","volume-title":"Python Port of the Livermore Unstructured Lagrangian Explicit Shock Hydrodynamics (LULESH)","author":"Laboratory Lawrence Livermore National","year":"2025","unstructured":"Lawrence Livermore National Laboratory. 2025. Python Port of the Livermore Unstructured Lagrangian Explicit Shock Hydrodynamics (LULESH). https:\/\/github.com\/LLNL\/pylulesh"},{"key":"e_1_3_3_3_57_2","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2012.33"},{"key":"e_1_3_3_3_58_2","doi-asserted-by":"publisher","DOI":"10.1145\/2503210.2503297"},{"key":"e_1_3_3_3_59_2","doi-asserted-by":"publisher","DOI":"10.1145\/2807591.2807648"},{"key":"e_1_3_3_3_60_2","doi-asserted-by":"publisher","unstructured":"R.L. Mattson J. Gecsei D.\u00a0R. Slutz and I.\u00a0L. Traiger. 1970. Evaluation techniques for storage hierarchies. IBM Systems Journal 9 2 (1970) 78\u2013117. 10.1147\/sj.92.0078","DOI":"10.1147\/sj.92.0078"},{"key":"e_1_3_3_3_61_2","unstructured":"Wolfgang\u00a0E. Nagel Alfred Arnold Michael Weber Hans-Christian Hoppe and Karl Solchenbach. 1996. VAMPIR: Visualization and analysis of MPI resources. Supercomputer (1996)."},{"key":"e_1_3_3_3_62_2","volume-title":"Pace","author":"(NOAA-GFDL) National Oceanic and Atmospheric Administration - Geophysical Fluid Dynamics Laboratory","year":"2025","unstructured":"National Oceanic and Atmospheric Administration - Geophysical Fluid Dynamics Laboratory (NOAA-GFDL). 2025. Pace. https:\/\/github.com\/NOAA-GFDL\/pace"},{"key":"e_1_3_3_3_63_2","doi-asserted-by":"publisher","unstructured":"Nicholas Nethercote and Julian Seward. 2007. Valgrind: A framework for heavyweight dynamic binary instrumentation. Proceedings of the ACM SIGPLAN Conference on Programming Language Design and Implementation (PLDI) (2007) 89\u2013100. 10.1145\/1250734.1250746","DOI":"10.1145\/1250734.1250746"},{"key":"e_1_3_3_3_64_2","doi-asserted-by":"publisher","unstructured":"Neungsoo Park Bo Hong and V.K. Prasanna. 2003. Tiling block data layout and memory hierarchy performance. IEEE Transactions on Parallel and Distributed Systems 14 7 (7 2003) 640\u2013654. 10.1109\/TPDS.2003.1214317","DOI":"10.1109\/TPDS.2003.1214317"},{"key":"e_1_3_3_3_65_2","doi-asserted-by":"publisher","unstructured":"Huu\u00a0Tan Nguyen Abhinav Bhatele Nikhil Jain Suraj\u00a0P. Kesavan Harsh Bhatia Todd Gamblin Kwan-Liu Ma and Peer-Timo Bremer. 2021. Visualizing Hierarchical Performance Profiles of Parallel Codes Using CallFlow. IEEE Transactions on Visualization and Computer Graphics 27 4 (4 2021) 2455\u20132468. 10.1109\/TVCG.2019.2953746","DOI":"10.1109\/TVCG.2019.2953746"},{"key":"e_1_3_3_3_66_2","doi-asserted-by":"publisher","DOI":"10.1109\/VPA.2016.009"},{"key":"e_1_3_3_3_67_2","doi-asserted-by":"publisher","DOI":"10.1145\/3503221.3508431"},{"key":"e_1_3_3_3_68_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2014.6835955"},{"key":"e_1_3_3_3_69_2","doi-asserted-by":"publisher","unstructured":"Md. Mostofa\u00a0Ali Patwary Nadathur\u00a0Rajagopalan Satish Narayanan Sundaram Jongsoo Park Michael\u00a0J. Anderson Satya\u00a0Gautam Vadlamudi Dipankar Das Sergey\u00a0G. Pudov Vadim\u00a0O. Pirogov and Pradeep Dubey. 2015. Parallel Efficient Sparse Matrix-Matrix Multiplication on Multicore Platforms. Lecture Notes in Computer Science Vol.\u00a09137. Springer International Publishing Cham 48\u201357. 10.1007\/978-3-319-20119-14","DOI":"10.1007\/978-3-319-20119-14"},{"key":"e_1_3_3_3_70_2","unstructured":"V Pillet J Labarta T Cortes and S Girona. 1995. Paraver: A tool to visualize and analyze parallel code. Proceedings of WoTUG-18: transputer and occam developmentsFebruary (1995) 17\u201331."},{"key":"e_1_3_3_3_71_2","first-page":"181","volume-title":"29th USENIX Security Symposium (USENIX Security 20)","author":"Poeplau Sebastian","year":"2020","unstructured":"Sebastian Poeplau and Aur\u00e9lien Francillon. 2020. Symbolic execution with SYMCC: Don\u2019t interpret, compile!. In 29th USENIX Security Symposium (USENIX Security 20). USENIX Association, 181\u2013198. https:\/\/www.usenix.org\/conference\/usenixsecurity20\/presentation\/poeplau"},{"key":"e_1_3_3_3_72_2","doi-asserted-by":"publisher","unstructured":"Tony Printezis and Richard Jones. 2012. GCSPY: An adaptable heap visualisation framework. ACM SIGPLAN Notices 37 11 (2012) 343\u2013358. 10.1145\/583854.582451","DOI":"10.1145\/583854.582451"},{"key":"e_1_3_3_3_73_2","doi-asserted-by":"publisher","DOI":"10.1145\/125826.125848"},{"key":"e_1_3_3_3_74_2","doi-asserted-by":"publisher","unstructured":"Ashay Rane and James Browne. 2014. Enhancing Performance Optimization of Multicore\/Multichip Nodes with Data Structure Metrics. ACM Transactions on Parallel Computing 1 1 (10 2014) 1\u201320. 10.1145\/2588788","DOI":"10.1145\/2588788"},{"key":"e_1_3_3_3_75_2","doi-asserted-by":"publisher","DOI":"10.5555\/647699.734156"},{"key":"e_1_3_3_3_76_2","doi-asserted-by":"publisher","DOI":"10.1109\/SC41404.2022.00069"},{"key":"e_1_3_3_3_77_2","doi-asserted-by":"publisher","DOI":"10.1145\/1854273.1854286"},{"key":"e_1_3_3_3_78_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISQED.2019.8697641"},{"key":"e_1_3_3_3_79_2","doi-asserted-by":"publisher","unstructured":"Sameer\u00a0S. Shende and Allen\u00a0D. Malony. 2006. The Tau Parallel Performance System. The International Journal of High Performance Computing Applications 20 2 (5 2006) 287\u2013311. 10.1177\/1094342006064482","DOI":"10.1177\/1094342006064482"},{"key":"e_1_3_3_3_80_2","doi-asserted-by":"publisher","unstructured":"Xulong Tang Mahmut\u00a0Taylan Kandemir Hui Zhao Myoungsoo Jung and Mustafa Karakoy. 2018. Computing with Near Data. Proceedings of the ACM on Measurement and Analysis of Computing Systems 2 3 (12 2018) 1\u201330. 10.1145\/3287321","DOI":"10.1145\/3287321"},{"key":"e_1_3_3_3_81_2","doi-asserted-by":"publisher","unstructured":"Peter Thoman Kiril Dichev Thomas Heller Roman Iakymchuk Xavier Aguilar Khalid Hasanov Philipp Gschwandtner Pierre Lemarinier Stefano Markidis Herbert Jordan Thomas Fahringer Kostas Katrinis Erwin Laure and Dimitrios\u00a0S. Nikolopoulos. 2018. A taxonomy of task-based parallel programming technologies for high-performance computing. The Journal of Supercomputing 74 4 (4 2018) 1422\u20131434. 10.1007\/s11227-018-2238-4","DOI":"10.1007\/s11227-018-2238-4"},{"key":"e_1_3_3_3_82_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICSM.2003.1235418"},{"key":"e_1_3_3_3_83_2","doi-asserted-by":"publisher","unstructured":"Didem Unat Anshu Dubey Torsten Hoefler John\u00a0Berkeley Shalf Mark Abraham Mauro Bianco Bradford\u00a0L. Chamberlain Romain Cledat H.\u00a0Carter Edwards Hal Finkel Karl Fuerlinger Frank Hannig Emmanuel Jeannot Amir Kamil Jeff Keasler Paul\u00a0H.J. Kelly Vitus Leung Hatem Ltaief Naoya Maruyama Chris\u00a0J. Newburn and Miquel Pericas. 2017. Trends in Data Locality Abstractions for HPC Systems. IEEE Transactions on Parallel and Distributed Systems 28 10 (2017) 3007\u20133020. 10.1109\/TPDS.2017.2703149","DOI":"10.1109\/TPDS.2017.2703149"},{"key":"e_1_3_3_3_84_2","doi-asserted-by":"publisher","unstructured":"Ronald Veldema Ceriel J.\u00a0H. Jacobs Rutger F.\u00a0H. Hofman and Henri\u00a0E. Bal. 2005. Object combining: a new aggressive optimization for object intensive programs. Concurrency and Computation: Practice and Experience 17 5-6 (4 2005) 439\u2013464. 10.1002\/cpe.836","DOI":"10.1002\/cpe.836"},{"key":"e_1_3_3_3_85_2","doi-asserted-by":"publisher","unstructured":"Chao Wang Chengjie Cao Liyu Ye Chunhui Wang and ChunYu Guo. 2023. An efficient peridynamic method and its MPI parallelization for simulating the continuous icebreaking process. Ocean Engineering 279 (7 2023) 114460. 10.1016\/j.oceaneng.2023.114460","DOI":"10.1016\/j.oceaneng.2023.114460"},{"key":"e_1_3_3_3_86_2","doi-asserted-by":"publisher","DOI":"10.1109\/VISSOFT51673.2020.00017"},{"key":"e_1_3_3_3_87_2","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2000.10050"},{"key":"e_1_3_3_3_88_2","doi-asserted-by":"publisher","unstructured":"Omer Zaki Ewing Lusk William Gropp and Deborah Swider. 1999. Toward Scalable Performance Visualization with Jumpshot. The International Journal of High Performance Computing Applications 13 3 (8 1999) 277\u2013288. 10.1177\/109434209901300310","DOI":"10.1177\/109434209901300310"},{"key":"e_1_3_3_3_89_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA45697.2020.00092"},{"key":"e_1_3_3_3_90_2","doi-asserted-by":"publisher","DOI":"10.1145\/3392717.3392752"},{"key":"e_1_3_3_3_91_2","doi-asserted-by":"publisher","unstructured":"Darko Zivanovic Milan Pavlovic Milan Radulovic Hyunsung Shin Jongpil Son Sally\u00a0A. McKee Paul\u00a0M. Carpenter Petar Radojkovi\u0107 and Eduard Ayguad\u00e9. 2017. Main Memory in HPC: Do We Need More or Could We Live with Less? ACM Transactions on Architecture and Code Optimization 14 1 (3 2017) 1\u201326. 10.1145\/3023362","DOI":"10.1145\/3023362"}],"event":{"name":"SC '25: The International Conference for High Performance Computing, Networking, Storage and Analysis","location":"St. Louis MO USA","acronym":"SC '25","sponsor":["SIGHPC ACM Special Interest Group on High Performance Computing, Special Interest Group on High Performance Computing"]},"container-title":["Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/abs\/10.1145\/3712285.3759797","content-type":"text\/html","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3712285.3759797","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3712285.3759797","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T18:54:04Z","timestamp":1773255244000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3712285.3759797"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,15]]},"references-count":90,"alternative-id":["10.1145\/3712285.3759797","10.1145\/3712285"],"URL":"https:\/\/doi.org\/10.1145\/3712285.3759797","relation":{},"subject":[],"published":{"date-parts":[[2025,11,15]]},"assertion":[{"value":"2025-11-15","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}