{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T23:28:09Z","timestamp":1777937289978,"version":"3.51.4"},"reference-count":32,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,9,22]],"date-time":"2025-09-22T00:00:00Z","timestamp":1758499200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,9,22]],"date-time":"2025-09-22T00:00:00Z","timestamp":1758499200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,9,22]]},"DOI":"10.1109\/icnp65844.2025.11192370","type":"proceedings-article","created":{"date-parts":[[2025,10,13]],"date-time":"2025-10-13T17:38:54Z","timestamp":1760377134000},"page":"1-11","source":"Crossref","is-referenced-by-count":1,"title":["TuCCL: Tailored and Unified Configuration Optimizations for High-Performance Collective Communication Library"],"prefix":"10.1109","author":[{"given":"Ziming","family":"Li","sequence":"first","affiliation":[{"name":"Northeastern University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chenyang","family":"Hei","sequence":"additional","affiliation":[{"name":"Northeastern University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fuliang","family":"Li","sequence":"additional","affiliation":[{"name":"Northeastern University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tongrui","family":"Liu","sequence":"additional","affiliation":[{"name":"Northeastern University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chengxi","family":"Gao","sequence":"additional","affiliation":[{"name":"Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiuzhu","family":"Sha","sequence":"additional","affiliation":[{"name":"Northeastern University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xingwei","family":"Wang","sequence":"additional","affiliation":[{"name":"Northeastern University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"652","article-title":"On the utility of gradient compression in distributed training systems","volume-title":"Proceedings of Machine Learning and Systems","volume":"4","author":"Agarwal"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3575693.3575724"},{"key":"ref3","first-page":"593","article-title":"TACCL: Guiding collective algorithm synthesis using communication sketches","volume-title":"Proc. 20th USENIX Symp. Networked Syst. Des. Implement. (NSDI)","author":"Shah"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3437963.3441727"},{"key":"ref5","article-title":"NVIDIA Collective Communications Library (NCCL)","year":"2024"},{"key":"ref6","article-title":"ROCm Communication Collectives Library (RCCL)","year":"2024"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/2966884.2966912"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3558481.3591073"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2023.10.010"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3458817.3476178"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3651890.3672249"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3437801.3441620"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3600061.3600068"},{"key":"ref14","article-title":"MSCCL","year":"2022"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3437801.3441620"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3582078"},{"key":"ref17","article-title":"Optimized network architectures for training large language models with billions of parameters","author":"Wang","year":"2023"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM42981.2021.9488803"},{"key":"ref19","article-title":"Nvidia NVLink and NVSwitch","author":"Corporation","year":"2021"},{"key":"ref20","article-title":"Nvidia ConnectX-5","year":"2024"},{"key":"ref21","article-title":"Adaptive input representations for neural language modeling","author":"Baevski","year":"2018"},{"key":"ref22","article-title":"Roberta: A robustly optimized bert pretraining approach","author":"Liu","year":"2019"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1082"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3620666.3651362"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA56546.2023.10071117"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3567955.3567959"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3503222.3507778"},{"key":"ref28","first-page":"809","article-title":"Better Together: Jointly Optimizing ML Collective Scheduling and Execution Planning using SYNDICATE","volume-title":"Proc. of USENIX NSDI","author":"Mahajan"},{"key":"ref29","first-page":"745","article-title":"MegaScale: Scaling Large Language Model Training to More Than 10, 000 GPUs","volume-title":"Proc. of USENIX NSDI","author":"Jiang"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3651890.3672252"},{"key":"ref31","first-page":"785","article-title":"Scaling Distributed Machine Learning with In-Network Aggregation","volume-title":"Proc. of USENIX NSDI","author":"Sapio"},{"key":"ref32","first-page":"741","article-title":"ATP: In-network Aggregation for Multi-tenant Learning","volume-title":"Proc. of USENIX NSDI","author":"Lao"}],"event":{"name":"2025 IEEE 33rd International Conference on Network Protocols (ICNP)","location":"Seoul, Korea, Republic of","start":{"date-parts":[[2025,9,22]]},"end":{"date-parts":[[2025,9,25]]}},"container-title":["2025 IEEE 33rd International Conference on Network Protocols (ICNP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11192357\/11192322\/11192370.pdf?arnumber=11192370","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,14]],"date-time":"2025-10-14T05:10:11Z","timestamp":1760418611000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11192370\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,22]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/icnp65844.2025.11192370","relation":{},"subject":[],"published":{"date-parts":[[2025,9,22]]}}}