{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,5]],"date-time":"2026-02-05T22:33:37Z","timestamp":1770330817950,"version":"3.49.0"},"publisher-location":"New York, NY, USA","reference-count":48,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,8,12]],"date-time":"2024-08-12T00:00:00Z","timestamp":1723420800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,8,12]]},"DOI":"10.1145\/3673038.3673100","type":"proceedings-article","created":{"date-parts":[[2024,8,8]],"date-time":"2024-08-08T18:29:01Z","timestamp":1723141741000},"page":"220-230","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["Enabling Performance Observability for Heterogeneous HPC Workflows with SOMA"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1453-5906","authenticated-orcid":false,"given":"Dewi","family":"Yokelson","sequence":"first","affiliation":[{"name":"University of Oregon, United States of America"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2357-7382","authenticated-orcid":false,"given":"Mikhail","family":"Titov","sequence":"additional","affiliation":[{"name":"Brookhaven National Laboratory, United States of America"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1679-922X","authenticated-orcid":false,"given":"Srinivasan","family":"Ramesh","sequence":"additional","affiliation":[{"name":"Nvidia, United States of America"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2129-408X","authenticated-orcid":false,"given":"Ozgur","family":"Kilic","sequence":"additional","affiliation":[{"name":"Brookhaven National Laboratory, United States of America"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0527-1435","authenticated-orcid":false,"given":"Matteo","family":"Turilli","sequence":"additional","affiliation":[{"name":"Rutgers University, United States of America"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5040-026X","authenticated-orcid":false,"given":"Shantenu","family":"Jha","sequence":"additional","affiliation":[{"name":"Rutgers University, United States of America"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9598-7201","authenticated-orcid":false,"given":"Allen","family":"Malony","sequence":"additional","affiliation":[{"name":"University of Oregon, United States of America"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,8,12]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2014.18"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2024.3365462"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/WORKS56498.2022.00009"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3307681.3325400"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3624062.3626283"},{"key":"e_1_3_2_1_6_1","volume-title":"Towards Advanced Monitoring for Scientific Workflows. In 2022 IEEE International Conference on Big Data (Big Data). IEEE, 2709\u20132715","author":"Bader Jonathan","year":"2022","unstructured":"Jonathan Bader, Joel Witzke, Soeren Becker, Ansgar L\u00f6\u00dfer, Fabian Lehmann, Leon Doehler, Anh\u00a0Duc Vu, and Odej Kao. 2022. Towards Advanced Monitoring for Scientific Workflows. In 2022 IEEE International Conference on Big Data (Big Data). IEEE, 2709\u20132715."},{"key":"e_1_3_2_1_7_1","volume-title":"Leveraging Reinforcement Learning for Task Resource Allocation in Scientific Workflows. In 2022 IEEE International Conference on Big Data (Big Data). IEEE, 3714\u20133719","author":"Bader Jonathan","year":"2022","unstructured":"Jonathan Bader, Nicolas Zunker, Soeren Becker, and Odej Kao. 2022. Leveraging Reinforcement Learning for Task Resource Allocation in Scientific Workflows. In 2022 IEEE International Conference on Big Data (Big Data). IEEE, 3714\u20133719."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICPP.2016.59"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/P3HPC51967.2020.00011"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3624062.3624103"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","unstructured":"John Coleman Kellis Kincaid Gerald\u00a0L. Knapp Benjamin Stump and Alexander\u00a0J. Plotkowski. 2023. ORNL\/AdditiveFOAM: Release 1.0. https:\/\/doi.org\/10.5281\/zenodo.8034098","DOI":"10.5281\/zenodo.8034098"},{"key":"e_1_3_2_1_12_1","volume-title":"Conduit: A Successful Strategy for Describing and Sharing Data In Situ. 2022 IEEE\/ACM International Workshop on In Situ Infrastructures for Enabling Extreme-Scale Analysis and Visualization","author":"Harrison Cyrus","year":"2022","unstructured":"Cyrus Harrison, Matthew Larsen, Brian\u00a0S. Ryujin, Adam\u00a0J. Kunen, Arlie\u00a0G. Capps, and Justin Privitera. 2022. Conduit: A Successful Strategy for Describing and Sharing Data In Situ. 2022 IEEE\/ACM International Workshop on In Situ Infrastructures for Enabling Extreme-Scale Analysis and Visualization (2022), 1\u20136."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/e-Science58273.2023.10254912"},{"key":"e_1_3_2_1_14_1","unstructured":"Pieter Hintjens. 2013. ZeroMQ: Messaging for Many Applications. https:\/\/api.semanticscholar.org\/CorpusID:190148604"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3624062.3624145"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3364228.3364232"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/CLUSTER51413.2022.00080"},{"key":"e_1_3_2_1_18_1","volume-title":"Dynamic and Adaptive Monitoring and Analysis for Many-task Ensemble Computing. In 2021 IEEE International Conference on Cluster Computing (CLUSTER). 637\u2013641","author":"Jha Shantenu","year":"2021","unstructured":"Shantenu Jha and Allen\u00a0D. Malony. 2021. Dynamic and Adaptive Monitoring and Analysis for Many-task Ensemble Computing. In 2021 IEEE International Conference on Cluster Computing (CLUSTER). 637\u2013641. https:\/\/api.semanticscholar.org\/CorpusID:238751313"},{"key":"e_1_3_2_1_19_1","volume-title":"Line Pouchard, and Shantenu Jha","author":"Kilic Ozgur\u00a0Ozan","year":"2024","unstructured":"Ozgur\u00a0Ozan Kilic, Tianle Wang, Matteo Turilli, Mikhail Titov, Andre Merzky, Line Pouchard, and Shantenu Jha. 2024. Workflow Mini-Apps: Portable, Scalable, Tunable & Faithful Representations of Scientific Workflows. arxiv:2403.18073\u00a0[cs.DC]"},{"key":"e_1_3_2_1_20_1","volume-title":"Accelerated Real-time Network Monitoring and Profiling at Scale using OSU INAM. Practice and Experience in Advanced Research Computing","author":"Kousha Pouya","year":"2020","unstructured":"Pouya Kousha, D. KamalRajS., Hari Subramoni, Dhabaleswar\u00a0Kumar Panda, Heechang Na, Trey Dockendorf, and Karen\u00a0A. Tomko. 2020. Accelerated Real-time Network Monitoring and Profiling at Scale using OSU INAM. Practice and Experience in Advanced Research Computing (2020). https:\/\/api.semanticscholar.org\/CorpusID:220666832"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3144769.3144778"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/DLS49591.2019.00007"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPSW.2016.166"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/eScience.2012.6404423"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCS48598.2019.9188097"},{"key":"e_1_3_2_1_26_1","volume-title":"Advances in the TAU Performance System. In Parallel Tools Workshop.","author":"Malony D.","year":"2011","unstructured":"Allen\u00a0D. Malony, Sameer\u00a0S. Shende, Wyatt Spear, Chee\u00a0Wai Lee, and Scott Biersdorff. 2011. Advances in the TAU Performance System. In Parallel Tools Workshop."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPSW.2016.202"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.parco.2004.04.001"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2014.11.017"},{"key":"e_1_3_2_1_30_1","volume-title":"PanDA and RADICAL-Pilot Integration: Enabling the Pilot Paradigm on HPC Resources. In EPJ Web of Conferences, Vol.\u00a0214","author":"Merzky Andre","year":"2019","unstructured":"Andre Merzky, Pavlo Svirin, and Matteo Turilli. 2019. PanDA and RADICAL-Pilot Integration: Enabling the Pilot Paradigm on HPC Resources. In EPJ Web of Conferences, Vol.\u00a0214. EDP Sciences, 03057."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/CCGrid54584.2022.00069"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-10632-4_4"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2021.3105994"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-74466-5_11"},{"key":"e_1_3_2_1_35_1","unstructured":"OLCF. 2024. Summit System Overview. https:\/\/docs.olcf.ornl.gov\/systems\/summit_user_guide.html#system-overview. Accessed: 2024-4-30."},{"key":"e_1_3_2_1_36_1","unstructured":"RADICAL Development Team. 2023. RADICAL-pilot: Integration with Flux. https:\/\/github.com\/radical-cybertools\/radical.pilot\/blob\/devel\/src\/radical\/pilot\/agent\/executing\/flux.py last accessed 2023-08-07."},{"key":"e_1_3_2_1_37_1","volume-title":"SERVIZ: A Shared In Situ Visualization Service. In SC22: International Conference for High Performance Computing, Networking, Storage and Analysis. 1\u201314","author":"Ramesh Srinivasan","year":"2022","unstructured":"Srinivasan Ramesh, Hank Childs, and Allen\u00a0D. Malony. 2022. SERVIZ: A Shared In Situ Visualization Service. In SC22: International Conference for High Performance Computing, Networking, Storage and Analysis. 1\u201314."},{"key":"e_1_3_2_1_38_1","volume-title":"Composable Monitoring Service. In 2021 IEEE 28th International Conference on High Performance Computing, Data, and Analytics (HiPC). 332\u2013342","author":"Ramesh Srinivasan","year":"2021","unstructured":"Srinivasan Ramesh, Robert\u00a0B. Ross, Matthieu Dorier, Allen\u00a0D. Malony, Philip\u00a0H. Carns, and Kevin\u00a0A. Huck. 2021. SYMBIOMON: A High-Performance, Composable Monitoring Service. In 2021 IEEE 28th International Conference on High Performance Computing, Data, and Analytics (HiPC). 332\u2013342."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11390-020-9802-0"},{"key":"e_1_3_2_1_40_1","volume-title":"Monitoring and Measuring. In 2020 29th International Conference on Computer Communications and Networks (ICCCN). IEEE, 1\u20139.","author":"Sperhac Jeanette","year":"2020","unstructured":"Jeanette Sperhac, Robert\u00a0L DeLeon, Joseph\u00a0P White, Matthew Jones, Andrew\u00a0E Bruno, Renette\u00a0Jones Ivey, Thomas\u00a0R Furlani, Jonathan\u00a0E Bard, and Vipin Chaudhary. 2020. Towards Performant Workflows, Monitoring and Measuring. In 2020 29th International Conference on Computer Communications and Networks (ICCCN). IEEE, 1\u20139."},{"key":"e_1_3_2_1_41_1","unstructured":"The OpenFOAM Foundation. 2023. OpenFOAM open source software for Computational Fluid Dynamics (CFD). https:\/\/openfoam.org"},{"key":"e_1_3_2_1_42_1","volume-title":"Workshop on Job Scheduling Strategies for Parallel Processing. Springer, 88\u2013107","author":"Titov Mikhail","year":"2022","unstructured":"Mikhail Titov, Matteo Turilli, Andre Merzky, Thomas Naughton, Wael Elwasif, and Shantenu Jha. 2022. RADICAL-pilot and PMIx\/PRRTE: Executing heterogeneous workloads at large scale on partitioned HPC resources. In Workshop on Job Scheduling Strategies for Parallel Processing. Springer, 88\u2013107."},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/MCSE.2019.2920048"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2016.64"},{"key":"e_1_3_2_1_45_1","volume-title":"Characterizing the Performance of Executing Many-tasks on Summit. In 2019 IEEE\/ACM Third Annual Workshop on Emerging Parallel and Distributed Runtime Systems and Middleware (IPDRM). IEEE, 18\u201325","author":"Turilli Matteo","year":"2019","unstructured":"Matteo Turilli, Andre Merzky, Thomas Naughton, Wael Elwasif, and Shantenu Jha. 2019. Characterizing the Performance of Executing Many-tasks on Summit. In 2019 IEEE\/ACM Third Annual Workshop on Emerging Parallel and Distributed Runtime Systems and Middleware (IPDRM). IEEE, 18\u201325."},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1145\/3177851"},{"key":"e_1_3_2_1_47_1","volume-title":"Scalable Performance Awareness for In Situ Scientific Applications. 2019 15th International Conference on eScience (eScience)","author":"Wolf Matthew","year":"2019","unstructured":"Matthew Wolf, Julien Dominski, Gabriele Merlo, J. Choi, Greg Eisenhauer, St\u00e9phane Ethier, Kevin\u00a0A. Huck, Scott Klasky, Jeremy\u00a0S. Logan, Allen\u00a0D. Malony, and Chad Wood. 2019. Scalable Performance Awareness for In Situ Scientific Applications. 2019 15th International Conference on eScience (eScience) (2019), 266\u2013276. https:\/\/api.semanticscholar.org\/CorpusID:214596196"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1002\/cpe.8141"}],"event":{"name":"ICPP '24: the 53rd International Conference on Parallel Processing","location":"Gotland Sweden","acronym":"ICPP '24"},"container-title":["Proceedings of the 53rd International Conference on Parallel Processing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3673038.3673100","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3673038.3673100","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,23]],"date-time":"2025-09-23T17:32:19Z","timestamp":1758648739000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3673038.3673100"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8,12]]},"references-count":48,"alternative-id":["10.1145\/3673038.3673100","10.1145\/3673038"],"URL":"https:\/\/doi.org\/10.1145\/3673038.3673100","relation":{},"subject":[],"published":{"date-parts":[[2024,8,12]]},"assertion":[{"value":"2024-08-12","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}