{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,5]],"date-time":"2026-08-05T06:45:25Z","timestamp":1785912325090,"version":"3.56.0"},"reference-count":70,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Science Foundation of China","award":["T2325001"],"award-info":[{"award-number":["T2325001"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,6]]},"DOI":"10.1109\/isca66397.2026.00152","type":"proceedings-article","created":{"date-parts":[[2026,8,4]],"date-time":"2026-08-04T19:19:12Z","timestamp":1785871152000},"page":"2142-2157","source":"Crossref","is-referenced-by-count":0,"title":["PipeComm: Maximizing Link Utilization Through Pipeline-Aware Collective Communication Synthesis"],"prefix":"10.1109","author":[{"given":"Ruifan","family":"Xu","sequence":"first","affiliation":[{"name":"Peking University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuze","family":"Luo","sequence":"additional","affiliation":[{"name":"Peking University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuhao","family":"Meng","sequence":"additional","affiliation":[{"name":"Peking University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Size","family":"Zheng","sequence":"additional","affiliation":[{"name":"Peking University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Meng","family":"Li","sequence":"additional","affiliation":[{"name":"Peking University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yun","family":"Liang","sequence":"additional","affiliation":[{"name":"Peking University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA45697.2020.00023"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3620665.3640366"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/hoti63208.2024.00020"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080231"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3437801.3441620"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/1122971.1122975"},{"key":"ref7","volume-title":"Flux: Fast software-based communication overlap on gpus through kernel fusion","author":"Chang","year":"2024"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3620666.3651379"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3669940.3707223"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1147\/jrd.2019.2947013"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3575693.3575724"},{"key":"ref12","first-page":"1223","article-title":"Large scale distributed deep networks","volume-title":"Proceedings of the 26th International Conference on Neural Information Processing Systems - Volume1, ser. NIPS\u201912","author":"Dean"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/hpca47549.2020.00056"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/mm.2024.3373763"},{"key":"ref15","volume-title":"Google tensor processing unit","year":"2024"},{"key":"ref16","volume-title":"Gurobi Optimizer Reference Manual","year":"2024"},{"key":"ref17","article-title":"Local sgd with periodic averaging: Tighter analysis and adaptive synchro-nization","volume":"32","author":"Haddadpour","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2016.90"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-8191(06)80021-9"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/isca52012.2021.00023"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3503222.3507778"},{"key":"ref22","author":"Jin","year":"2016","journal-title":"How to scale distributed deep learning?"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3579371.3589350"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3620666.3651362"},{"key":"ref25","first-page":"1106","article-title":"Imagenet classification with deep convolutional neural networks","volume-title":"Advances in Neural Information Processing Systems25: 26th Annual Conference on Neural Information Processing Systems 2012","author":"Krizhevsky","year":"2012"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/960116.54022"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/hpca57654.2024.00069"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3725843.3756085"},{"key":"ref29","doi-asserted-by":"crossref","first-page":"279","DOI":"10.1145\/3307650.3322259","article-title":"Accelerating distributed reinforcement learning with in-switch computing","volume-title":"Proceedings of the 46th International Symposium on Computer Architecture","author":"Li","year":"2019"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA51647.2021.00071"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3651890.3672249"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ISPA-BDCloud-SocialCom-SustainCom52081.2021.00045"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3458817.3476209"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/isca59077.2024.00027"},{"key":"ref35","volume-title":"Dgx platform","year":"2023"},{"key":"ref36","volume-title":"Gb200 nvl72","year":"2023"},{"key":"ref37","volume-title":"Nvidia collective communications library (nccl)","year":"2023"},{"key":"ref38","volume-title":"Nvlink technology","year":"2023"},{"key":"ref39","volume-title":"Ethernet products","year":"2024"},{"key":"ref40","volume-title":"Infiniband products","year":"2024"},{"key":"ref41","volume-title":"Gpt-4 technical report","author":"Achiam","year":"2024"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/2968455.2968512"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpdc.2008.09.002"},{"key":"ref44","volume-title":"Qwen2.5 technical report","author":"Qwen","year":"2025"},{"key":"ref45","first-page":"10425","article-title":"Designing network design spaces","volume-title":"2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2020","author":"Radosavovic","year":"2020"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/3470496.3527382"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/1014192.802449"},{"key":"ref48","first-page":"551","article-title":"{Zero-offload}: Democratizing billion-scale model training","volume-title":"2021 USENIX Annual Technical Conference (USENIX ATC 21)","author":"Ren","year":"2021"},{"key":"ref49","volume-title":"Code llama: Open foundation models for code","author":"Rozi\u00e8re","year":"2024"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/hpca56546.2023.10071117"},{"key":"ref51","first-page":"593","article-title":"TACCL: guiding collective algorithm synthesis using communication sketches","volume-title":"20th USENIX Symposium on Networked Systems Design and Implementation, NSDI 2023","author":"Shah","year":"2023"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1145\/3352460.3358302"},{"key":"ref53","author":"Shoeybi","year":"2019","journal-title":"Megatron-Im: Training multi-billion parameter language models using model parallelism"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1177\/1094342005051521"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1177\/1094342005051521"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1002\/cpe.5574"},{"key":"ref57","author":"Touvron","year":"2023","journal-title":"Llama2: Open foundation and fine-tuned chat models"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CCGRID.2019.00057"},{"key":"ref59","first-page":"5998","article-title":"Attention is all you need","volume-title":"Advances in Neural Information Processing Systems30: Annual Conference on Neural Information Processing Systems 2017","author":"Vaswani","year":"2017"},{"key":"ref60","article-title":"Blink: Fast and generic collectives for distributed ML","volume-title":"Proceedings of the Third Conference on Machine Learning and Systems, MLSys2020","author":"Wang","year":"2020"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1145\/3567955.3567959"},{"key":"ref62","first-page":"739","article-title":"Topoopt: Co-optimizing network topology and parallelization strategy for distributed training jobs","volume-title":"20th USENIX Symposium on Networked Systems Design and Implementation, NSDI2023","author":"Wang","year":"2023"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/micro61859.2024.00068"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ispass57527.2023.00035"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ispass57527.2023.00035"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ASP-DAC66049.2026.11420389"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2018.00066"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICCAD.2013.6691121"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1145\/3613424.3623792"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1145\/3373376.3378508"}],"event":{"name":"2026 ACM\/IEEE 53rd Annual International Symposium on Computer Architecture (ISCA)","location":"Raleigh, NC, USA","start":{"date-parts":[[2026,6,27]]},"end":{"date-parts":[[2026,7,1]]}},"container-title":["2026 ACM\/IEEE 53rd Annual International Symposium on Computer Architecture (ISCA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11617393\/11617394\/11617964.pdf?arnumber=11617964","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,5]],"date-time":"2026-08-05T05:53:41Z","timestamp":1785909221000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11617964\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6]]},"references-count":70,"URL":"https:\/\/doi.org\/10.1109\/isca66397.2026.00152","relation":{},"subject":[],"published":{"date-parts":[[2026,6]]}}}