{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,23]],"date-time":"2026-04-23T07:55:14Z","timestamp":1776930914191,"version":"3.51.2"},"publisher-location":"New York, NY, USA","reference-count":46,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,11,16]]},"DOI":"10.1145\/3712285.3759773","type":"proceedings-article","created":{"date-parts":[[2025,11,12]],"date-time":"2025-11-12T16:04:47Z","timestamp":1762963487000},"page":"383-396","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["TraceFlow: Efficient Trace Analysis for Large-Scale Parallel Applications via Interaction Pattern-Aware Trace Distribution"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2358-3395","authenticated-orcid":false,"given":"Yuyang","family":"Jin","sequence":"first","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-8867-3718","authenticated-orcid":false,"given":"Xirui","family":"Shui","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-7573-2250","authenticated-orcid":false,"given":"Mingshu","family":"Zhai","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7828-9030","authenticated-orcid":false,"given":"Zan","family":"Zong","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1983-7321","authenticated-orcid":false,"given":"Feng","family":"Zhang","sequence":"additional","affiliation":[{"name":"Renmin University of China, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6595-3599","authenticated-orcid":false,"given":"Felix","family":"Wolf","sequence":"additional","affiliation":[{"name":"Technical University of Darmstadt, Darmstadt, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7656-6428","authenticated-orcid":false,"given":"Jidong","family":"Zhai","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,11,15]]},"reference":[{"key":"e_1_3_3_2_2_2","doi-asserted-by":"crossref","unstructured":"Laksono Adhianto Sinchan Banerjee Mike Fagan Mark Krentel Gabriel Marin John Mellor-Crummey and Nathan\u00a0R Tallent. 2010. HPCToolkit: Tools for performance analysis of optimized parallel programs. Concurrency and Computation: Practice and Experience 22 6 (2010) 685\u2013701.","DOI":"10.1002\/cpe.1553"},{"key":"e_1_3_3_2_3_2","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2017.9"},{"key":"e_1_3_3_2_4_2","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2007.370254"},{"key":"e_1_3_3_2_5_2","unstructured":"Large-scale Atomic and Molecular Massively\u00a0Parallel Simulator. 2013. Lammps. available at: http:\/lammps. sandia. gov (2013)."},{"key":"e_1_3_3_2_6_2","volume-title":"The NAS Parallel Benchmarks 2.0","author":"Bailey D.","year":"1995","unstructured":"D. Bailey, T. Harris, W. Saphir, R.\u00a0V.\u00a0D. Wijngaart, A. Woo, and M. Yarrow. 1995. The NAS Parallel Benchmarks 2.0. NAS Systems Division, NASA Ames Research Center, Moffett Field, CA."},{"key":"e_1_3_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICPP.2010.18"},{"key":"e_1_3_3_2_8_2","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2012.120"},{"key":"e_1_3_3_2_9_2","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPSW.2012.321"},{"key":"e_1_3_3_2_10_2","unstructured":"Barcelona\u00a0Supercomputing Center.2005. Extrae.https:\/\/tools.bsc.es\/extrae"},{"key":"e_1_3_3_2_11_2","unstructured":"Barcelona\u00a0Supercomputing Center.2025. Paraver.http:\/\/www.bsc.es\/paraver"},{"key":"e_1_3_3_2_12_2","doi-asserted-by":"crossref","unstructured":"Yunji Chen Shijin Zhang Qi Guo Ling Li Ruiyang Wu and Tianshi Chen. 2015. Deterministic replay: A survey. ACM Computing Surveys (CSUR) 48 2 (2015) 1\u201347.","DOI":"10.1145\/2790077"},{"key":"e_1_3_3_2_13_2","doi-asserted-by":"publisher","DOI":"10.17487\/rfc1950"},{"key":"e_1_3_3_2_14_2","doi-asserted-by":"publisher","DOI":"10.3233\/978-1-61499-041-3-481"},{"key":"e_1_3_3_2_15_2","unstructured":"Jean-loup Gailly and Mark Adler. 1992. Gnu gzip. GNU Operating System (1992) 8\u201318."},{"key":"e_1_3_3_2_16_2","doi-asserted-by":"crossref","unstructured":"Markus Geimer Felix Wolf Brian\u00a0JN Wylie Erika \u00c1brah\u00e1m Daniel Becker and Bernd Mohr. 2010. The Scalasca performance toolset architecture. Concurrency and Computation: Practice and Experience 22 6 (2010) 702\u2013719.","DOI":"10.1002\/cpe.1556"},{"key":"e_1_3_3_2_17_2","doi-asserted-by":"publisher","DOI":"10.1007\/11846802_43"},{"key":"e_1_3_3_2_18_2","doi-asserted-by":"crossref","unstructured":"Susan\u00a0L Graham Peter\u00a0B Kessler and Marshall\u00a0K McKusick. 1982. Gprof: A call graph execution profiler. ACM Sigplan Notices 17 6 (1982) 120\u2013126.","DOI":"10.1145\/872726.806987"},{"key":"e_1_3_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.2172\/1113870"},{"key":"e_1_3_3_2_20_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICWS.2018.00020"},{"key":"e_1_3_3_2_21_2","unstructured":"Intel.2025. Intel Trace Analyzer and Collector.https:\/\/software.intel.com\/en-us\/trace-analyzer"},{"key":"e_1_3_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.1109\/SC41405.2020.00032"},{"key":"e_1_3_3_2_23_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-68564-7_9"},{"key":"e_1_3_3_2_24_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-31476-6_7"},{"key":"e_1_3_3_2_25_2","doi-asserted-by":"crossref","unstructured":"Chi-Keung Luk Robert Cohn Robert Muth Harish Patil Artur Klauser Geoff Lowney Steven Wallace Vijay\u00a0Janapa Reddi and Kim Hazelwood. 2005. Pin: building customized program analysis tools with dynamic instrumentation. Acm sigplan notices 40 6 (2005) 190\u2013200.","DOI":"10.1145\/1064978.1065034"},{"key":"e_1_3_3_2_26_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-45209-6_177"},{"key":"e_1_3_3_2_27_2","doi-asserted-by":"crossref","unstructured":"Michael Noeth Prasun Ratn Frank Mueller Martin Schulz and Bronis\u00a0R De\u00a0Supinski. 2009. Scalatrace: Scalable compression and replay of communication traces for high-performance computing. J. Parallel and Distrib. Comput. 69 8 (2009) 696\u2013710.","DOI":"10.1016\/j.jpdc.2008.09.001"},{"key":"e_1_3_3_2_28_2","doi-asserted-by":"publisher","DOI":"10.1145\/1629575.1629593"},{"key":"e_1_3_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.1145\/1772954.1772958"},{"key":"e_1_3_3_2_30_2","doi-asserted-by":"publisher","DOI":"10.1109\/WSC.1998.745023"},{"key":"e_1_3_3_2_31_2","unstructured":"PyTorch.2025. PyTorch Profiler.https:\/\/pytorch.org\/tutorials\/recipes\/recipes\/profiler_recipe.html"},{"key":"e_1_3_3_2_32_2","doi-asserted-by":"crossref","unstructured":"Fabien Reumont-Locke Naser Ezzati-Jivan and Michel\u00a0R Dagenais. 2019. Efficient methods for trace analysis parallelization. International Journal of Parallel Programming 47 (2019) 951\u2013972.","DOI":"10.1007\/s10766-019-00631-4"},{"key":"e_1_3_3_2_33_2","doi-asserted-by":"crossref","unstructured":"Arun\u00a0F Rodrigues K\u00a0Scott Hemmert Brian\u00a0W Barrett Chad Kersey Ron Oldfield Marlo Weston Rolf Risen Jeanine Cook Paul Rosenfeld Elliot Cooper-Balis et\u00a0al. 2011. The structural simulation toolkit. ACM SIGMETRICS Performance Evaluation Review 38 4 (2011) 37\u201342.","DOI":"10.1145\/1964218.1964225"},{"key":"e_1_3_3_2_34_2","volume-title":"Proceedings of the Third Annual Workshop on Modeling, Benchmarking and Simulation (MoBS 2007)","author":"Sheldon Min Xu Vyacheslav Malyugin\u00a0Jeffrey","year":"2007","unstructured":"Min Xu Vyacheslav Malyugin\u00a0Jeffrey Sheldon and Ganesh Venkitachalam\u00a0Boris Weissman. 2007. Retrace: Collecting execution trace with virtual machine deterministic replay. In Proceedings of the Third Annual Workshop on Modeling, Benchmarking and Simulation (MoBS 2007). Citeseer."},{"key":"e_1_3_3_2_35_2","doi-asserted-by":"crossref","unstructured":"Sameer\u00a0S Shende and Allen\u00a0D Malony. 2006. The TAU parallel performance system. The International Journal of High Performance Computing Applications 20 2 (2006) 287\u2013311.","DOI":"10.1177\/1094342006064482"},{"key":"e_1_3_3_2_36_2","volume-title":"A scalable parallel sorting algorithm using exact splitting","author":"Siebert Christian","year":"2011","unstructured":"Christian Siebert and Felix Gerd\u00a0Eugen Wolf. 2011. A scalable parallel sorting algorithm using exact splitting. Universit\u00e4tsbibliothek der RWTH Aachen."},{"key":"e_1_3_3_2_37_2","unstructured":"Jeffrey Vetter and Chris Chambreau. 2024. mpip: Lightweight scalable mpi profiling. https:\/\/github.com\/LLNL\/mpiP"},{"key":"e_1_3_3_2_38_2","doi-asserted-by":"publisher","DOI":"10.1145\/3458817.3476196"},{"key":"e_1_3_3_2_39_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-39589-0_1"},{"key":"e_1_3_3_2_40_2","doi-asserted-by":"publisher","DOI":"10.1145\/2464996.2465001"},{"key":"e_1_3_3_2_41_2","doi-asserted-by":"crossref","unstructured":"Young Yoon James\u00a0C Browne Mathew Crocker Samit Jain and Nasim Mahmood. 2007. Productivity and performance through components: the ASCI Sweep3D application. Concurrency and Computation: Practice and Experience 19 5 (2007) 721\u2013742.","DOI":"10.1002\/cpe.1149"},{"key":"e_1_3_3_2_42_2","doi-asserted-by":"publisher","DOI":"10.1109\/SC41405.2020.00033"},{"key":"e_1_3_3_2_43_2","doi-asserted-by":"crossref","unstructured":"Jidong Zhai Wenguang Chen and Weimin Zheng. 2010. Phantom: predicting performance of parallel applications on large-scale parallel machines using a single node. ACM sigplan notices 45 5 (2010) 305\u2013314.","DOI":"10.1145\/1837853.1693493"},{"key":"e_1_3_3_2_44_2","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2014.17"},{"key":"e_1_3_3_2_45_2","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2004.1303013"},{"key":"e_1_3_3_2_46_2","first-page":"527","volume-title":"13th USENIX Symposium on Operating Systems Design and Implementation (OSDI\u201918)","author":"Zhou Fang","year":"2018","unstructured":"Fang Zhou, Yifan Gan, Sixiang Ma, and Yang Wang. 2018. wPerf: generic Off-CPU analysis to identify bottleneck waiting events. In 13th USENIX Symposium on Operating Systems Design and Implementation (OSDI\u201918). 527\u2013543."},{"key":"e_1_3_3_2_47_2","doi-asserted-by":"publisher","DOI":"10.1109\/SC41405.2020.00093"}],"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\/pdf\/10.1145\/3712285.3759773","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T18:45:30Z","timestamp":1773254730000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3712285.3759773"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,15]]},"references-count":46,"alternative-id":["10.1145\/3712285.3759773","10.1145\/3712285"],"URL":"https:\/\/doi.org\/10.1145\/3712285.3759773","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"}}]}}