{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,16]],"date-time":"2026-09-16T18:05:28Z","timestamp":1789581928340,"version":"build-2803163510"},"publisher-location":"New York, NY, USA","reference-count":30,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,9,27]],"date-time":"2026-09-27T00:00:00Z","timestamp":1790467200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,9,28]]},"DOI":"10.1145\/3832810.3832838","type":"proceedings-article","created":{"date-parts":[[2026,9,13]],"date-time":"2026-09-13T00:19:06Z","timestamp":1789258746000},"page":"671-681","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["StreamTrace: Fast Trace Analysis for Large-Scale Parallel Applications on a Single Node"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2358-3395","authenticated-orcid":false,"given":"Yuyang","family":"Jin","sequence":"first","affiliation":[{"name":"Department of Computer Science and Technology, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7656-6428","authenticated-orcid":false,"given":"Jidong","family":"Zhai","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,9,27]]},"reference":[{"key":"e_1_3_3_1_2_2","first-page":"61","volume-title":"Proceedings of the 10th International Workshop on OpenMP","author":"Aguilar Xavier","year":"2014","unstructured":"Xavier Aguilar, Harald Servat, Diego Cabrera, Ger\u00f2nimo Llort, Rosa\u00a0M. Badia, and Jes\u00fas Labarta. 2014. Event-Based Instrumentation of OpenMP Runtimes for Task-Based Parallel Programs. In Proceedings of the 10th International Workshop on OpenMP. 61\u201376."},{"key":"e_1_3_3_1_3_2","unstructured":"Large-scale Atomic and Molecular Massively\u00a0Parallel Simulator. 2013. Lammps. available at: http:\/lammps. sandia. gov (2013)."},{"key":"e_1_3_3_1_4_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_1_5_2","doi-asserted-by":"publisher","DOI":"10.1109\/PACT.2015.39"},{"key":"e_1_3_3_1_6_2","doi-asserted-by":"crossref","unstructured":"David B\u00f6hme Markus Geimer Lukas Arnold Felix Voigtlaender and Felix Wolf. 2016. Identifying the root causes of wait states in large-scale parallel applications. ACM Transactions on Parallel Computing (TOPC) 3 2 (2016) 1\u201324.","DOI":"10.1145\/2934661"},{"key":"e_1_3_3_1_7_2","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2012.120"},{"key":"e_1_3_3_1_8_2","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPSW.2012.321"},{"key":"e_1_3_3_1_9_2","first-page":"93","volume-title":"Tools for High Performance Computing 2009","author":"Brunst Holger","year":"2010","unstructured":"Holger Brunst and Andreas Knupfer. 2010. Vampir and Vampir Server: A Tool Platform for Performance Analysis. In Tools for High Performance Computing 2009. Springer, 93\u2013110."},{"key":"e_1_3_3_1_10_2","unstructured":"Paris Carbone Asterios Katsifodimos Stephan Ewen Volker Markl Seif Haridi and Kostas Tzoumas. 2015. Apache Flink: Stream and Batch Processing in a Single Engine. IEEE Data Engineering Bulletin 38 4 (2015) 28\u201338."},{"key":"e_1_3_3_1_11_2","unstructured":"K De\u00a0Bosschere et\u00a0al. 2012. Open Trace Format 2 The Next Generation of Scalable Trace Formats and Support Libraries. Applications Tools and Techniques on the Road to Exascale Computing 22 (2012) 481."},{"key":"e_1_3_3_1_12_2","doi-asserted-by":"crossref","unstructured":"Markus Geimer Felix Wolf Brian J.\u00a0N. Wylie Erika Abraham 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_1_13_2","doi-asserted-by":"publisher","DOI":"10.2172\/1113870"},{"key":"e_1_3_3_1_14_2","doi-asserted-by":"crossref","unstructured":"Haruna Isah Tariq Abughofa Sazia Mahfuz Dharmitha Ajerla Farhana Zulkernine and Shahzad Khan. 2019. A survey of distributed data stream processing frameworks. IEEE Access 7 (2019) 154300\u2013154316.","DOI":"10.1109\/ACCESS.2019.2946884"},{"key":"e_1_3_3_1_15_2","doi-asserted-by":"publisher","DOI":"10.1145\/3712285.3759773"},{"key":"e_1_3_3_1_16_2","doi-asserted-by":"publisher","DOI":"10.1109\/SC41405.2020.00032"},{"key":"e_1_3_3_1_17_2","doi-asserted-by":"publisher","DOI":"10.1145\/3503221.3508405"},{"key":"e_1_3_3_1_18_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-31476-6_7"},{"key":"e_1_3_3_1_19_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-45209-6_177"},{"key":"e_1_3_3_1_20_2","doi-asserted-by":"crossref","unstructured":"Michael Noeth Prasun Ratn Frank Mueller Martin Schulz and Bronis\u00a0R. de Supinski. 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_1_21_2","first-page":"1","volume-title":"Proceedings of the 22nd European MPI Users\u2019 Group Meeting","author":"Sato Kento","year":"2015","unstructured":"Kento Sato, Dong\u00a0H. Ahn, Ignacio Laguna, Gregory\u00a0L. Lee, and Martin Schulz. 2015. Design and Implementation of a Scalable Parallel MPI Trace Replayer. In Proceedings of the 22nd European MPI Users\u2019 Group Meeting. 1\u201310."},{"key":"e_1_3_3_1_22_2","doi-asserted-by":"crossref","unstructured":"Felix Schmitt Robert Dietrich and Guido Juckeland. 2017. Scalable critical-path analysis and optimization guidance for hybrid MPI-CUDA applications. The International Journal of High Performance Computing Applications 31 6 (2017) 485\u2013498.","DOI":"10.1177\/1094342016661865"},{"key":"e_1_3_3_1_23_2","doi-asserted-by":"crossref","unstructured":"Sameer\u00a0S. Shende and Allen\u00a0D. Malony. 2006. The TAU Parallel Performance System. International Journal of High Performance Computing Applications 20 2 (2006) 287\u2013311.","DOI":"10.1177\/1094342006064482"},{"key":"e_1_3_3_1_24_2","unstructured":"Apache Spark. 2018. Apache spark. Retrieved January 17 1 (2018) 2018."},{"key":"e_1_3_3_1_25_2","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2010.47"},{"key":"e_1_3_3_1_26_2","doi-asserted-by":"crossref","unstructured":"Jeffrey\u00a0Scott Vitter. 2001. External Memory Algorithms and Data Structures: Dealing with Massive Data. Comput. Surveys 33 2 (2001) 209\u2013271.","DOI":"10.1145\/384192.384193"},{"key":"e_1_3_3_1_27_2","doi-asserted-by":"publisher","DOI":"10.1145\/3458817.3476196"},{"key":"e_1_3_3_1_28_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_1_29_2","doi-asserted-by":"publisher","DOI":"10.1145\/2517349.2522737"},{"key":"e_1_3_3_1_30_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_1_31_2","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2014.17"}],"event":{"name":"ICPP '26: Proceedings of the 55th International Conference on Parallel Processing","location":"Singapore , Singapore","acronym":"ICPP '26"},"container-title":["Proceedings of the 55th International Conference on Parallel Processing"],"original-title":[],"deposited":{"date-parts":[[2026,9,16]],"date-time":"2026-09-16T17:57:00Z","timestamp":1789581420000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3832810.3832838"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,27]]},"references-count":30,"alternative-id":["10.1145\/3832810.3832838","10.1145\/3832810"],"URL":"https:\/\/doi.org\/10.1145\/3832810.3832838","relation":{},"subject":[],"published":{"date-parts":[[2026,9,27]]},"assertion":[{"value":"2026-09-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}