{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,21]],"date-time":"2026-01-21T14:50:16Z","timestamp":1769007016062,"version":"3.49.0"},"publisher-location":"New York, NY, USA","reference-count":46,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,11,12]],"date-time":"2023-11-12T00:00:00Z","timestamp":1699747200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,11,12]]},"DOI":"10.1145\/3624062.3624286","type":"proceedings-article","created":{"date-parts":[[2023,11,10]],"date-time":"2023-11-10T13:53:39Z","timestamp":1699624419000},"page":"2077-2088","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":7,"title":["Fluxion: A Scalable Graph-Based Resource Model for HPC Scheduling Challenges"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2543-9688","authenticated-orcid":false,"given":"Tapasya","family":"Patki","sequence":"first","affiliation":[{"name":"Lawrence Livermore National Laboratory, United States of America"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6722-0532","authenticated-orcid":false,"given":"Dong","family":"Ahn","sequence":"additional","affiliation":[{"name":"NVIDIA Corporation, United States of America"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6500-3227","authenticated-orcid":false,"given":"Daniel","family":"Milroy","sequence":"additional","affiliation":[{"name":"Lawrence Livermore National Laboratory, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5464-6040","authenticated-orcid":false,"given":"Jae-Seung","family":"Yeom","sequence":"additional","affiliation":[{"name":"Lawrence Livermore National Laboratory, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-2334-8675","authenticated-orcid":false,"given":"Jim","family":"Garlick","sequence":"additional","affiliation":[{"name":"Lawrence Livermore National Laboratory, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-2938-9536","authenticated-orcid":false,"given":"Mark","family":"Grondona","sequence":"additional","affiliation":[{"name":"Lawrence Livermore National Laboratory, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0141-0653","authenticated-orcid":false,"given":"Stephen","family":"Herbein","sequence":"additional","affiliation":[{"name":"NVIDIA Corporation, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7234-5743","authenticated-orcid":false,"given":"Thomas","family":"Scogland","sequence":"additional","affiliation":[{"name":"Lawrence Livermore National Laboratory, United States of America"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,11,12]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICPPW.2014.15"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"crossref","unstructured":"Aymen Alsaadi Logan Ward Andre Merzky Kyle Chard Ian Foster Shantenu Jha and Matteo Turilli. 2021. RADICAL-Pilot and Parsl: Executing Heterogeneous Workflows on HPC Platforms. arXiv.","DOI":"10.1109\/WORKS56498.2022.00009"},{"key":"e_1_3_2_1_3_1","unstructured":"Altair. [n. d.]. PBSPro: An HPC workload manager and job scheduler for desktops clusters and clouds. https:\/\/github.com\/PBSPro\/pbspro."},{"key":"e_1_3_2_1_4_1","unstructured":"Altair. 2023. Hierarchical Scheduling for High-throughput Computing Workloads in PBSPro. https:\/\/www.altair.com\/resource\/hierarchical-scheduling-for-high-throughput-computing-workloads."},{"key":"e_1_3_2_1_5_1","unstructured":"Altair. 2023. Using PBS Professional Hooks: Examples and Benefits. https:\/\/www.scientific-computing.com\/sites\/default\/files\/PBS_TechPaper_hooks_08.29.12.pdf."},{"key":"e_1_3_2_1_6_1","volume-title":"DRMaestro: Orchestrating Disaggregated Resources on Virtualized Data-Centers. J. of Cloud Computing (Mar","author":"Amaral Marcelo","year":"2021","unstructured":"Marcelo Amaral, Jord\u00e0 Polo, David Carrera, Nelson Gonzalez, Chih-Chieh Yang, Alessandro Morari, Bruce D\u2019Amora, Alaa Youssef, and Malgorzata Steinder. 2021. DRMaestro: Orchestrating Disaggregated Resources on Virtualized Data-Centers. J. of Cloud Computing (Mar 2021)."},{"key":"e_1_3_2_1_7_1","unstructured":"Amazon Inc.2023. AWS Batch Scheduler. https:\/\/docs.aws.amazon.com\/batch\/latest\/userguide\/what-is-batch.html."},{"key":"e_1_3_2_1_8_1","unstructured":"Gabriel Antoniu Patrick Valduriez Hans-Christian Hoppe and Jens Kr\u00fcger. 2021. Towards Integrated Hardware\/Software Ecosystems for the Edge-Cloud-HPC Continuum."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"crossref","unstructured":"Daniel Balouek-Thomert Eduard\u00a0Gibert Renart Ali\u00a0Reza Zamani Anthony Simonet and M. Parashar. 2019. Towards a computing continuum: Enabling edge-to-cloud integration for data-driven workflows. The Intl. J. of High Performance Computing Applications (2019).","DOI":"10.1177\/1094342019877383"},{"key":"e_1_3_2_1_10_1","volume-title":"Designing Reliable Systems from Unreliable Components: The Challenges of Transistor Variability and Degradation. Micro","author":"Borkar Shekhar","year":"2005","unstructured":"Shekhar Borkar. 2005. Designing Reliable Systems from Unreliable Components: The Challenges of Transistor Variability and Degradation. Micro, IEEE (Nov 2005)."},{"key":"e_1_3_2_1_11_1","unstructured":"Cloud Native Computing Foundation. [n. d.]. Kubernetes: Production-Grade Container Orchestration. https:\/\/kubernetes.io\/."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.5555\/3571885.3571916"},{"key":"e_1_3_2_1_13_1","volume-title":"The Evolution of the Pegasus Workflow Management Software. Computing in Science and Engineering","author":"Deelman Ewa","year":"2019","unstructured":"Ewa Deelman, Karan Vahi, Mats Rynge, Rajiv Mayani, Rafael\u00a0Ferreira da Silva, George Papadimitriou, and Miron Livny. 2019. The Evolution of the Pegasus Workflow Management Software. Computing in Science and Engineering (2019)."},{"key":"e_1_3_2_1_14_1","unstructured":"Rob F.\u00a0Van der Wijngaart and Haoqiang Jin. 2003. NAS Parallel Benchmarks. Technical Report."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.5555\/646378.689517"},{"key":"e_1_3_2_1_16_1","volume-title":"Network Requirements for Resource Disaggregation. In 12th USENIX Conf. on Operating Systems Design and Implementation.","author":"Gao X.","unstructured":"Peter\u00a0X. Gao, Akshay Narayan, Sagar Karandikar, Joao Carreira, Sangjin Han, Rachit Agarwal, Sylvia Ratnasamy, and Scott Shenker. [n. d.]. Network Requirements for Resource Disaggregation. In 12th USENIX Conf. on Operating Systems Design and Implementation."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3007748.3007768"},{"key":"e_1_3_2_1_18_1","volume-title":"Proc. of the 12th USENIX Conf. on Operating Systems Design and Implementation. 99\u2013115","author":"Gog Ionel","year":"2016","unstructured":"Ionel Gog, Malte Schwarzkopf, Adam Gleave, Robert N.\u00a0M. Watson, and Steven Hand. 2016. Firmament: Fast, Centralized Cluster Scheduling at Scale. In Proc. of the 12th USENIX Conf. on Operating Systems Design and Implementation. 99\u2013115."},{"key":"e_1_3_2_1_19_1","volume-title":"Flux: Overcoming Scheduling Challenges for Exascale Workflows. In 2018 IEEE\/ACM Workflows in Support of Large-Scale Science (WORKS). 10\u201319.","author":"Ahn Dong","year":"2018","unstructured":"Dong H.\u00a0Ahn, Ned Bass, Albert Chu, Jim Garlick, Mark Grondona, Stephen Herbein, Joseph Koning, T Patki, Thomas R.\u00a0W.\u00a0Scogland, Becky Springmeyer, and Michela Taufer. 2018. Flux: Overcoming Scheduling Challenges for Exascale Workflows. In 2018 IEEE\/ACM Workflows in Support of Large-Scale Science (WORKS). 10\u201319."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1177\/10943420211051039"},{"key":"e_1_3_2_1_21_1","volume-title":"Mesos: A Platform for Fine-grained Resource Sharing. In USENIX Conf.e on Networked Systems Design and Implementation.","author":"Hindman Benjamin","year":"2011","unstructured":"Benjamin Hindman, Andy Konwinski, Matei Zaharia, Ali Ghodsi, Anthony\u00a0D. Joseph, Randy Katz, Scott Shenker, and Ion Stoica. 2011. Mesos: A Platform for Fine-grained Resource Sharing. In USENIX Conf.e on Networked Systems Design and Implementation."},{"key":"e_1_3_2_1_22_1","unstructured":"IBM. 2020. IBM LSF Scheduler. https:\/\/www.ibm.com\/docs\/en\/spectrum-lsf\/10.1.0."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/2807591.2807638"},{"key":"e_1_3_2_1_24_1","volume-title":"Minimizing The Effects of Manufacturing Variation During Physcial Layout. Chip Design Magazine","author":"Jilla Sudhakar","year":"2013","unstructured":"Sudhakar Jilla. 2013. Minimizing The Effects of Manufacturing Variation During Physcial Layout. Chip Design Magazine (2013). http:\/\/chipdesignmag.com\/display.php?articleId=2437."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2013.115"},{"key":"e_1_3_2_1_26_1","unstructured":"KubeFlow. [n. d.]. The Machine Learning Toolkit for Kubernetes. https:\/\/www.kubeflow.org\/docs\/components\/pipelines\/v1\/concepts\/graph\/."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2017.2757479"},{"key":"e_1_3_2_1_28_1","unstructured":"Feng Liu. 2018. Elastic Scheduling in HPC Resource Management Systems. https:\/\/hdl.handle.net\/11299\/202169. [University of Minnesota]."},{"key":"e_1_3_2_1_29_1","volume-title":"Scheduling Algorithms in Fog Computing: A Survey. Intl. J. of Networked and Distributed Computing","author":"Matrouk Khaled","year":"2021","unstructured":"Khaled Matrouk and Kholoud Alatoun. 2021. Scheduling Algorithms in Fog Computing: A Survey. Intl. J. of Networked and Distributed Computing (2021)."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"crossref","unstructured":"Satoshi Matsuoka Jens Domke Mohamed Wahib Aleksandr Drozd and Torsten Hoefler. 2023. Myths and Legends in High-Performance Computing. arXiv.","DOI":"10.1177\/10943420231166608"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/CANOPIE-HPC56864.2022.00011"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/CANOPIEHPC54579.2021.00006"},{"key":"e_1_3_2_1_33_1","volume-title":"Maurizio Drocco, Stephen Herbein, Dong\u00a0H. Ahn, Zvonko Kaiser, and Yoonho Park.","author":"Misale Claudia","year":"2022","unstructured":"Claudia Misale, Daniel\u00a0J. Milroy, Carlos Eduardo\u00a0Arango Gutierrez, Maurizio Drocco, Stephen Herbein, Dong\u00a0H. Ahn, Zvonko Kaiser, and Yoonho Park. 2022. Towards Standard Kubernetes Scheduling Interfaces for Converged Computing. In Driving Scientific and Engineering Discoveries Through the Integration of Experiment, Big Data, and Modeling and Simulation, Jeffrey Nichols, Arthur\u00a0\u2018Barney\u2019 Maccabe, James Nutaro, Swaroop Pophale, Pravallika Devineni, Theresa Ahearn, and Becky Verastegui (Eds.). Springer Intl. Publishing, Cham, 310\u2013326."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1134\/S1995080221070192"},{"key":"e_1_3_2_1_35_1","volume-title":"On the Memory Underutilization: Exploring Disaggregated Memory on HPC Systems. In 2020 IEEE 32nd Intl. Symp. on Computer Architecture and High Performance Computing.","author":"Peng Ivy","unstructured":"Ivy Peng, Roger Pearce, and Maya Gokhale. [n. d.]. On the Memory Underutilization: Exploring Disaggregated Memory on HPC Systems. In 2020 IEEE 32nd Intl. Symp. on Computer Architecture and High Performance Computing."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2015.34"},{"key":"e_1_3_2_1_37_1","unstructured":"SchedMD. 2023. Generic Resource Scheduling. https:\/\/slurm.schedmd.com\/gres.html."},{"key":"e_1_3_2_1_38_1","unstructured":"SchedMD. 2023. High Throughput Computing in SLURM. https:\/\/slurm.schedmd.com\/high_throughput.html."},{"key":"e_1_3_2_1_39_1","unstructured":"SchedMD. 2023. SLURM Heterogeneous Jobs: Limitations. https:\/\/slurm.schedmd.com\/heterogeneous_jobs.html#limitations."},{"key":"e_1_3_2_1_40_1","unstructured":"SchedMD. 2023. Slurm Power Management. https:\/\/slurm.schedmd.com\/power_mgmt.html."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/2465351.2465386"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1364\/OFC.2015.W1D.5"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/2523616.2523633"},{"key":"e_1_3_2_1_44_1","unstructured":"Deepak Vij and Shivram Shrivastava. [n. d.]. Poseidon-Firmament Scheduler: Flow Network Graph Based Scheduler. kubernetes.io\/blog\/2019\/02\/06\/poseidon-firmament-scheduler-flow-network-graph-based-scheduler\/."},{"key":"e_1_3_2_1_45_1","volume-title":"SLURM: Simple Linux Utility for Resource Management. In Job Scheduling Strategies for Parallel Processing(Lecture Notes in Computer Science, Vol.\u00a02862). 44\u201360.","author":"Yoo Andy","year":"2003","unstructured":"Andy Yoo, Morris Jette, and Mark Grondona. 2003. SLURM: Simple Linux Utility for Resource Management. In Job Scheduling Strategies for Parallel Processing(Lecture Notes in Computer Science, Vol.\u00a02862). 44\u201360."},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"crossref","unstructured":"Chaojie Zhang and Andrew\u00a0A. Chien. 2021. Scheduling Challenges for Variable Capacity Resources. In Job Scheduling Strategies for Parallel Processing.","DOI":"10.1007\/978-3-030-88224-2_10"}],"event":{"name":"SC-W 2023: Workshops of The International Conference on High Performance Computing, Network, Storage, and Analysis","location":"Denver CO USA","acronym":"SC-W 2023"},"container-title":["Proceedings of the SC '23 Workshops of the International Conference on High Performance Computing, Network, Storage, and Analysis"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3624062.3624286","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3624062.3624286","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T03:02:35Z","timestamp":1755745355000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3624062.3624286"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11,12]]},"references-count":46,"alternative-id":["10.1145\/3624062.3624286","10.1145\/3624062"],"URL":"https:\/\/doi.org\/10.1145\/3624062.3624286","relation":{},"subject":[],"published":{"date-parts":[[2023,11,12]]},"assertion":[{"value":"2023-11-12","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}