{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T15:44:39Z","timestamp":1783784679194,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":62,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,7,5]],"date-time":"2026-07-05T00:00:00Z","timestamp":1783209600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"U.S. National Science Foundation","award":["#2321123"],"award-info":[{"award-number":["#2321123"]}]},{"name":"U.S. National Science Foundation","award":["#2623548"],"award-info":[{"award-number":["#2623548"]}]},{"name":"U.S. National Science Foundation","award":["#2623610"],"award-info":[{"award-number":["#2623610"]}]},{"name":"United States Department of Energy","award":["DE-SC0024207"],"award-info":[{"award-number":["DE-SC0024207"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,7,6]]},"DOI":"10.1145\/3797905.3807853","type":"proceedings-article","created":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T11:50:37Z","timestamp":1782993037000},"page":"436-449","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["PACER: A Userspace Network Rate Controller in MPI with Adaptive Compression for Parallel Applications"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-5806-7228","authenticated-orcid":false,"given":"Yuke","family":"Li","sequence":"first","affiliation":[{"name":"University of California, Merced, Merced, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-9774-5514","authenticated-orcid":false,"given":"Darren","family":"Ng","sequence":"additional","affiliation":[{"name":"University of Florida, Gainesville, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-0941-1295","authenticated-orcid":false,"given":"Arjun","family":"Kashyap","sequence":"additional","affiliation":[{"name":"University of California, Merced, Merced, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9935-5674","authenticated-orcid":false,"given":"Sheng","family":"Di","sequence":"additional","affiliation":[{"name":"Argonne National Laboratory, Lemont, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7773-7826","authenticated-orcid":false,"given":"Guanpeng","family":"Li","sequence":"additional","affiliation":[{"name":"University of Florida, Gainesville, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7581-8905","authenticated-orcid":false,"given":"Xiaoyi","family":"Lu","sequence":"additional","affiliation":[{"name":"University of Florida, Gainesville, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,7,5]]},"reference":[{"key":"e_1_3_3_2_2_2","unstructured":"Rashid Al-Ali Shaleeza Sohail Omer Rana Abdelhakim Hafid Gregor von Laszewski Kaizar Amin Sanjay Jha and David Walker. 2004. Network QoS Provision for Distributed Grid Applications. Intl. Journal of Simulations Systems Science and Technology Special Issue on Grid Performance and Dependability 5 5 (2004)."},{"key":"e_1_3_3_2_3_2","doi-asserted-by":"publisher","DOI":"10.1145\/3624062.3624153"},{"key":"e_1_3_3_2_4_2","series-title":"(SC \u201925)","volume-title":"Proceedings of the 38th International Conference for High Performance Computing, Networking, Storage and Analysis (SC)","author":"Chen Zhonghao","year":"2025","unstructured":"Zhonghao Chen, Yuke Li, Duo Zhang, and Xiaoyi Lu. 2025. Can Long-Haul RDMA Benefit Federated Learning?. In Proceedings of the 38th International Conference for High Performance Computing, Networking, Storage and Analysis (SC)(SC \u201925). IEEE Computer Society, St. Louis, MO, USA. Research Poster Paper, Best Poster Candidate."},{"key":"e_1_3_3_2_5_2","first-page":"299","volume-title":"14th USENIX Symposium on Operating Systems Design and Implementation (OSDI 20)","author":"Cho Inho","year":"2020","unstructured":"Inho Cho, Ahmed Saeed, Joshua Fried, Seo\u00a0Jin Park, Mohammad Alizadeh, and Adam Belay. 2020. Overload Control for \u00b5s-Scale RPCs with Breakwater. In 14th USENIX Symposium on Operating Systems Design and Implementation (OSDI 20). USENIX Association, 299\u2013314. https:\/\/www.usenix.org\/conference\/osdi20\/presentation\/cho"},{"key":"e_1_3_3_2_6_2","unstructured":"Yann Collet. 2025. Zstandard \u2013 Real-Time Data Compression Algorithm. https:\/\/github.com\/facebook\/zstd."},{"key":"e_1_3_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2008.5222004"},{"key":"e_1_3_3_2_8_2","unstructured":"DeepSeek-AI. 2025. DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning. arxiv:https:\/\/arXiv.org\/abs\/2501.12948\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2501.12948"},{"key":"e_1_3_3_2_9_2","doi-asserted-by":"crossref","unstructured":"P. Deutsch. 1996. DEFLATE Compressed Data Format Specification Version 1.3. https:\/\/www.rfc-editor.org\/rfc\/rfc1951.html.","DOI":"10.17487\/rfc1951"},{"key":"e_1_3_3_2_10_2","unstructured":"eBPF Community. 2026. eBPF \u2013 Introduction Tutorials & Community Resources. https:\/\/ebpf.io\/."},{"key":"e_1_3_3_2_11_2","doi-asserted-by":"publisher","unstructured":"Jesus Escudero-Sahuquillo Ernst\u00a0Gunnar Gran Pedro\u00a0J. Garcia Jos\u00e9 Flich Tor Skeie Olav Lysne Francisco\u00a0J. Quiles and Jos\u00e9 Duato. 2015. Efficient and Cost-Effective Hybrid Congestion Control for HPC Interconnection Networks. IEEE Transactions on Parallel and Distributed Systems 26 1 (2015) 107\u2013119. 10.1109\/TPDS.2014.2307851","DOI":"10.1109\/TPDS.2014.2307851"},{"key":"e_1_3_3_2_12_2","doi-asserted-by":"publisher","unstructured":"Stijn Eyerman and Lieven Eeckhout. 2008. System-Level Performance Metrics for Multiprogram Workloads. IEEE Micro 28 3 (May 2008) 42\u201353. 10.1109\/MM.2008.44","DOI":"10.1109\/MM.2008.44"},{"key":"e_1_3_3_2_13_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA59077.2024.00065"},{"key":"e_1_3_3_2_14_2","doi-asserted-by":"publisher","DOI":"10.1007\/11752578_29"},{"key":"e_1_3_3_2_15_2","doi-asserted-by":"publisher","DOI":"10.1109\/HOTI.2015.19"},{"key":"e_1_3_3_2_16_2","series-title":"(SC \u201922)","volume-title":"Proceedings of the International Conference on High Performance Computing, Networking, Storage and Analysis","author":"Hoefler Torsten","year":"2022","unstructured":"Torsten Hoefler, Tommaso Bonato, Daniele De\u00a0Sensi, Salvatore Di\u00a0Girolamo, Shigang Li, Marco Heddes, Jon Belk, Deepak Goel, Miguel Castro, and Steve Scott. 2022. HammingMesh: A Network Topology for Large-Scale Deep Learning. In Proceedings of the International Conference on High Performance Computing, Networking, Storage and Analysis (Dallas, Texas) (SC \u201922). IEEE Press, Article 11, 18\u00a0pages."},{"key":"e_1_3_3_2_17_2","doi-asserted-by":"publisher","DOI":"10.1145\/3712285.3759817"},{"key":"e_1_3_3_2_18_2","doi-asserted-by":"publisher","unstructured":"David\u00a0A. Huffman. 1952. A Method for the Construction of Minimum-Redundancy Codes. Proceedings of the IRE 40 9 (1952) 1098\u20131101. 10.1109\/JRPROC.1952.273898","DOI":"10.1109\/JRPROC.1952.273898"},{"key":"e_1_3_3_2_19_2","unstructured":"Intel Corporation. 2026. Intel\u00ae In-Memory Analytics Accelerator (Intel\u00ae IAA). https:\/\/www.intel.com\/content\/www\/us\/en\/products\/docs\/accelerator-engines\/in-memory-analytics-accelerator.html."},{"key":"e_1_3_3_2_20_2","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2016.13"},{"key":"e_1_3_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.1145\/3552326.3587450"},{"key":"e_1_3_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.1109\/ExaMPI54564.2021.00006"},{"key":"e_1_3_3_2_23_2","unstructured":"Alexey\u00a0N. Kuznetsov and Bert Hubert. 2026. tc(8) \u2013 Linux Manual Page. https:\/\/man7.org\/linux\/man-pages\/man8\/tc.8.html."},{"key":"e_1_3_3_2_24_2","doi-asserted-by":"publisher","unstructured":"Hochan Lee Jaewook Lee Heewon Kim and Sangheon Pack. 2023. Straggler-Aware In-Network Aggregation for Accelerating Distributed Deep Learning. IEEE Transactions on Services Computing 16 6 (2023) 4198\u20134204. 10.1109\/TSC.2023.3309318","DOI":"10.1109\/TSC.2023.3309318"},{"key":"e_1_3_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.1145\/3458817.3476191"},{"key":"e_1_3_3_2_26_2","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS57955.2024.00040"},{"key":"e_1_3_3_2_27_2","doi-asserted-by":"publisher","unstructured":"Yuke Li Hao Qi Gang Lu Feng Jin Yanfei Guo and Xiaoyi Lu. 2022. Understanding Hot Interconnects with an Extensive Benchmark Survey. BenchCouncil Transactions on Benchmarks Standards and Evaluations 2 3 (2022) 100074. 10.1016\/j.tbench.2022.100074","DOI":"10.1016\/j.tbench.2022.100074"},{"key":"e_1_3_3_2_28_2","doi-asserted-by":"publisher","unstructured":"Xin Liang Kai Zhao Sheng Di Sihuan Li Robert Underwood Ali\u00a0M. Gok Jiannan Tian Junjing Deng Jon\u00a0C. Calhoun Dingwen Tao Zizhong Chen and Franck Cappello. 2023. SZ3: A Modular Framework for Composing Prediction-Based Error-Bounded Lossy Compressors. IEEE Transactions on Big Data 9 2 (2023) 485\u2013498. 10.1109\/TBDATA.2022.3201176","DOI":"10.1109\/TBDATA.2022.3201176"},{"key":"e_1_3_3_2_29_2","unstructured":"Yujun Lin Song Han Huizi Mao Yu Wang and William Dally. 2018. Deep Gradient Compression: Reducing the Communication Bandwidth for Distributed Training. https:\/\/openreview.net\/pdf?id=SkhQHMW0W"},{"key":"e_1_3_3_2_30_2","doi-asserted-by":"publisher","unstructured":"Peter Lindstrom. 2014. Fixed-Rate Compressed Floating-Point Arrays. IEEE Transactions on Visualization and Computer Graphics 20 12 (2014) 2674\u20132683. 10.1109\/TVCG.2014.2346458","DOI":"10.1109\/TVCG.2014.2346458"},{"key":"e_1_3_3_2_31_2","doi-asserted-by":"publisher","unstructured":"Xiaoyi Lu. 2026. HEC: Heterogeneity-Enriched Communication for AI Symphony. Journal of Computer Science and Technology 41 1 (2026) 170\u2013192. 10.1007\/s11390-026-6076-1","DOI":"10.1007\/s11390-026-6076-1"},{"key":"e_1_3_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2014.90"},{"key":"e_1_3_3_2_33_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCT62411.2024.10946583"},{"key":"e_1_3_3_2_34_2","unstructured":"Message Passing Interface Forum. 2025. MPI: A Message-Passing Interface Standard Version 5.0. https:\/\/www.mpi-forum.org\/docs\/mpi-5.0\/mpi50-report.pdf."},{"key":"e_1_3_3_2_35_2","doi-asserted-by":"publisher","unstructured":"Misbah Mubarak Christopher\u00a0D. Carothers Robert\u00a0B. Ross and Philip Carns. 2017. Enabling Parallel Simulation of Large-Scale HPC Network Systems. IEEE Transactions on Parallel and Distributed Systems 28 1 (2017) 87\u2013100. 10.1109\/TPDS.2016.2543725","DOI":"10.1109\/TPDS.2016.2543725"},{"key":"e_1_3_3_2_36_2","doi-asserted-by":"publisher","DOI":"10.1109\/WSC.2017.8247823"},{"key":"e_1_3_3_2_37_2","unstructured":"NERSC. 2025. Perlmutter Architecture. https:\/\/docs.nersc.gov\/systems\/perlmutter\/architecture\/."},{"key":"e_1_3_3_2_38_2","doi-asserted-by":"publisher","unstructured":"H. Ohnishi T. Okada and K. Noguchi. 1988. Flow Control Schemes and Delay\/Loss Tradeoff in ATM Networks. IEEE Journal on Selected Areas in Communications 6 9 (1988) 1609\u20131616. 10.1109\/49.12888","DOI":"10.1109\/49.12888"},{"key":"e_1_3_3_2_39_2","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/11451.001.0001"},{"key":"e_1_3_3_2_40_2","doi-asserted-by":"publisher","unstructured":"Dhabaleswar\u00a0Kumar Panda Hari Subramoni Ching-Hsiang Chu and Mohammadreza Bayatpour. 2021. The MVAPICH Project: Transforming Research into High-Performance MPI Library for HPC Community. Journal of Computational Science 52 (2021) 101208. 10.1016\/j.jocs.2020.101208Case Studies in Translational Computer Science.","DOI":"10.1016\/j.jocs.2020.101208"},{"key":"e_1_3_3_2_41_2","doi-asserted-by":"publisher","DOI":"10.1145\/3447818.3460362"},{"key":"e_1_3_3_2_42_2","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2000.10017"},{"key":"e_1_3_3_2_43_2","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPSW55747.2022.00175"},{"key":"e_1_3_3_2_44_2","doi-asserted-by":"publisher","DOI":"10.1145\/3098822.3098852"},{"key":"e_1_3_3_2_45_2","unstructured":"Sandia National Laboratories. 2025. Structural Simulation Toolkit (SST). https:\/\/www.sandia.gov\/ccr\/project\/structural-simulation-toolkit-sst\/."},{"key":"e_1_3_3_2_46_2","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPSW.2018.00204"},{"key":"e_1_3_3_2_47_2","doi-asserted-by":"publisher","DOI":"10.1109\/PACT.2017.19"},{"key":"e_1_3_3_2_48_2","unstructured":"Alexander Sergeev and Mike\u00a0Del Balso. 2018. Horovod: Fast and Easy Distributed Deep Learning in TensorFlow. CoRR abs\/1802.05799 (2018). arXiv:https:\/\/arXiv.org\/abs\/1802.05799http:\/\/arxiv.org\/abs\/1802.05799"},{"key":"e_1_3_3_2_49_2","doi-asserted-by":"publisher","DOI":"10.1109\/HOTI.2015.13"},{"key":"e_1_3_3_2_50_2","doi-asserted-by":"publisher","DOI":"10.17487\/rfc2215"},{"key":"e_1_3_3_2_51_2","doi-asserted-by":"publisher","unstructured":"J. Turner. 1986. New Directions in Communications (or Which Way to the Information Age?). IEEE Communications Magazine 24 10 (1986) 8\u201315. 10.1109\/MCOM.1986.1092946","DOI":"10.1109\/MCOM.1986.1092946"},{"key":"e_1_3_3_2_52_2","doi-asserted-by":"publisher","DOI":"10.1145\/3600006.3613145"},{"key":"e_1_3_3_2_53_2","doi-asserted-by":"crossref","unstructured":"Adam Weingram Yuke Li Hao Qi Darren Ng Liuyao Dai and Xiaoyi Lu. 2023. xCCL: A Survey of Industry-Led Collective Communication Libraries for Deep Learning. Journal of Computer Science and Technology 38 (2023) 166\u2013195. https:\/\/api.semanticscholar.org\/CorpusID:257839221","DOI":"10.1007\/s11390-023-2894-6"},{"key":"e_1_3_3_2_54_2","doi-asserted-by":"publisher","DOI":"10.1145\/3712285.3759827"},{"key":"e_1_3_3_2_55_2","volume-title":"Opportunities and Limitations of Quality-of-Service (QoS) in Message Passing (MPI) Applications on Adaptively Routed Dragonfly and Fat Tree Networks.","author":"Wilke Jeremiah\u00a0J","year":"2020","unstructured":"Jeremiah\u00a0J Wilke and Joseph\u00a0P Kenny. 2020. Opportunities and Limitations of Quality-of-Service (QoS) in Message Passing (MPI) Applications on Adaptively Routed Dragonfly and Fat Tree Networks.Technical Report. Sandia National Lab.(SNL-CA), Livermore, CA (United States)."},{"key":"e_1_3_3_2_56_2","doi-asserted-by":"publisher","DOI":"10.1145\/3615979.3656055"},{"key":"e_1_3_3_2_57_2","doi-asserted-by":"publisher","DOI":"10.1145\/3502181.3531473"},{"key":"e_1_3_3_2_58_2","unstructured":"Weizhe Yuan Jane Yu Song Jiang Karthik Padthe Yang Li Dong Wang Ilia Kulikov Kyunghyun Cho Yuandong Tian Jason\u00a0E Weston and Xian Li. 2025. NaturalReasoning: Reasoning in the Wild with 2.8M Challenging Questions. arxiv:https:\/\/arXiv.org\/abs\/2502.13124\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2502.13124"},{"key":"e_1_3_3_2_59_2","doi-asserted-by":"publisher","DOI":"10.1109\/CLUSTER49012.2020.00026"},{"key":"e_1_3_3_2_60_2","doi-asserted-by":"publisher","DOI":"10.1145\/3544216.3544271"},{"key":"e_1_3_3_2_61_2","doi-asserted-by":"publisher","DOI":"10.1145\/3373376.3378457"},{"key":"e_1_3_3_2_62_2","doi-asserted-by":"publisher","DOI":"10.23919\/ISC.2024.10528931"},{"key":"e_1_3_3_2_63_2","doi-asserted-by":"publisher","unstructured":"J. Ziv and A. Lempel. 1978. Compression of Individual Sequences via Variable-Rate Coding. IEEE Transactions on Information Theory 24 5 (1978) 530\u2013536. 10.1109\/TIT.1978.1055934","DOI":"10.1109\/TIT.1978.1055934"}],"event":{"name":"ICS '26: 2026 International Conference on Supercomputing","location":"Belfast United Kingdom","acronym":"ICS '26","sponsor":["SIGHPC ACM Special Interest Group on High Performance Computing, Special Interest Group on High Performance Computing","SIGARCH ACM Special Interest Group on Computer Architecture"]},"container-title":["Proceedings of the 40th ACM International Conference on Supercomputing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/abs\/10.1145\/3797905.3807853","content-type":"text\/html","content-version":"vor","intended-application":"syndication"}],"deposited":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T12:47:12Z","timestamp":1782996432000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3797905.3807853"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,5]]},"references-count":62,"alternative-id":["10.1145\/3797905.3807853","10.1145\/3797905"],"URL":"https:\/\/doi.org\/10.1145\/3797905.3807853","relation":{},"subject":[],"published":{"date-parts":[[2026,7,5]]},"assertion":[{"value":"2026-07-05","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}