{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T22:00:21Z","timestamp":1757628021159,"version":"3.44.0"},"reference-count":29,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,7,2]],"date-time":"2025-07-02T00:00:00Z","timestamp":1751414400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,7,2]],"date-time":"2025-07-02T00:00:00Z","timestamp":1751414400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,7,2]]},"DOI":"10.1109\/iwqos65803.2025.11143446","type":"proceedings-article","created":{"date-parts":[[2025,9,9]],"date-time":"2025-09-09T17:29:52Z","timestamp":1757438992000},"page":"1-10","source":"Crossref","is-referenced-by-count":0,"title":["HiPIPE: Adaptive-Chunk Pipeline Scheduling for Hierarchical Collective Communication"],"prefix":"10.1109","author":[{"given":"Xin","family":"Song","sequence":"first","affiliation":[{"name":"Huawei Technologies,Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Manaf","family":"Bin-Yahya","sequence":"additional","affiliation":[{"name":"Huawei Technologies,Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Amir","family":"Shani","sequence":"additional","affiliation":[{"name":"Huawei Technologies,Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"2397","article-title":"Pythia: A Suite for Analyzing Large Language Models across Training and Scaling","volume-title":"International Conference on Machine Learning","author":"Biderman","year":"2023"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3437801.3441620"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3641289"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/IWQoS61813.2024.10682856"},{"key":"ref5","article-title":"BlueConnect: Novel Hierarchical All-Reduce on Multi-tired Network for Deep Learning","volume-title":"Proceedings of the 2nd SysML Conference","author":"Cho","year":"2019"},{"key":"ref6","volume-title":"Ualink: Ultra accelerator link","year":"2024"},{"key":"ref7","volume-title":"Intel MPI Library","year":"2024"},{"key":"ref8","volume-title":"Nvidia nccl: Optimized primitives for collective multi-gpu communication","year":"2020"},{"key":"ref9","volume-title":"Infiniband networking solutions","year":"2025"},{"key":"ref10","volume-title":"Nvlink and nvswitch","year":"2025"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3651890.3672233"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ipdps64566.2025.00089"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA52012.2021.00023"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/s12532-017-0130-5"},{"key":"ref15","volume-title":"Gloo: Collective communications library","year":"2020"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3503222.3507778"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3579371.3589350"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3605573.3605613"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3651890.3672249"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/IWQoS61813.2024.10682877"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3651890.3672265"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-24685-5_1"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3470496.3527382"},{"key":"ref24","first-page":"593","article-title":"TACCL: Guiding Collective Algorithm Synthesis using Communication Sketches","volume-title":"Proc. 20th USENIX Symposium on Networked Systems Design and Implementation (NSDI)","author":"Shah","year":"2023"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1177\/1094342005051521"},{"key":"ref26","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 (NSDI 23)","author":"Wang","year":"2023"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS57527.2023.00035"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS61541.2024.00028"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO61859.2024.00068"}],"event":{"name":"2025 IEEE\/ACM International Symposium on Quality of Service (IWQoS)","location":"Gold Coast, Australia","start":{"date-parts":[[2025,7,2]]},"end":{"date-parts":[[2025,7,4]]}},"container-title":["2025 IEEE\/ACM 33rd International Symposium on Quality of Service (IWQoS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11143240\/11143247\/11143446.pdf?arnumber=11143446","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,10]],"date-time":"2025-09-10T05:31:55Z","timestamp":1757482315000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11143446\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,2]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/iwqos65803.2025.11143446","relation":{},"subject":[],"published":{"date-parts":[[2025,7,2]]}}}