{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T06:03:02Z","timestamp":1730268182815,"version":"3.28.0"},"reference-count":23,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,5,20]],"date-time":"2024-05-20T00:00:00Z","timestamp":1716163200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,5,20]],"date-time":"2024-05-20T00:00:00Z","timestamp":1716163200000},"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":[[2024,5,20]]},"DOI":"10.1109\/infocomwkshps61880.2024.10620705","type":"proceedings-article","created":{"date-parts":[[2024,8,13]],"date-time":"2024-08-13T17:19:39Z","timestamp":1723569579000},"page":"1-6","source":"Crossref","is-referenced-by-count":0,"title":["Simulating LLM Training in CXL-Based Heterogeneous Computing Cluster"],"prefix":"10.1109","author":[{"given":"Yinan","family":"Tang","sequence":"first","affiliation":[{"name":"Inspur Electronic Information Industry Co., Ltd,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tongtong","family":"Yuan","sequence":"additional","affiliation":[{"name":"Beijing University of Technology,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fang","family":"Cao","sequence":"additional","affiliation":[{"name":"Inspur Electronic Information Industry Co., Ltd,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Li","family":"Wang","sequence":"additional","affiliation":[{"name":"Inspur Electronic Information Industry Co., Ltd,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhenhua","family":"Guo","sequence":"additional","affiliation":[{"name":"Inspur Electronic Information Industry Co., Ltd,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yaqian","family":"Zhao","sequence":"additional","affiliation":[{"name":"Inspur Electronic Information Industry Co., Ltd,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rengang","family":"Li","sequence":"additional","affiliation":[{"name":"Inspur Electronic Information Industry Co., Ltd,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2023.123618"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/csci62032.2023.00009"},{"key":"ref3","article-title":"Llama: Open and efficient foundation language models [J]","author":"Touvron","year":"2023","journal-title":"arv preprint arv:2302.13971"},{"key":"ref4","article-title":"GPT-3[M]","author":"Kublik","year":"2022","journal-title":"OReilly Media, Incorporated"},{"journal-title":"CXL SPECIFICATION - Compute Express Link","key":"ref7"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3575693.3578835"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS57527.2023.00037"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3190508.3190517"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2017.29"},{"article-title":"Paleo: A performance model for deep neural networks[C]","volume-title":"International Conference on Learning Representations","author":"Qi","key":"ref14"},{"key":"ref15","first-page":"623","article-title":"dPRO: A Generic Performance Diagnosis and Optimization Toolkit for Expediting Distributed DNN Training[J]","volume-title":"Proceedings of Machine Learning and Systems","volume":"4","author":"Hu"},{"key":"ref16","first-page":"337","article-title":"Daydream: Accurately estimating the efficacy of optimizations for DNN training[C]","volume-title":"2020 USENIX Annual Technical Conference (USENIX ATC 20)","author":"Zhu"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3587135.3592200"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS48437.2020.00018"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CloudIntelligence52565.2021.00012"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2021.3061394"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2019.2928289"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.4236\/jcc.2023.116006"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CCGRID.2001.923223"},{"volume-title":"Exploring network structure, dynamics, and function using NetworkX. No. LA-UR-08\u201305495; LA-UR-08-5495","year":"2008","author":"Aric","key":"ref24"},{"journal-title":"A survey of large language models","year":"2023","author":"Wayne Xin","key":"ref25"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3341301.3359642"}],"event":{"name":"IEEE INFOCOM 2024 - IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS)","start":{"date-parts":[[2024,5,20]]},"location":"Vancouver, BC, Canada","end":{"date-parts":[[2024,5,20]]}},"container-title":["IEEE INFOCOM 2024 - IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10620660\/10620661\/10620705.pdf?arnumber=10620705","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,14]],"date-time":"2024-08-14T05:10:00Z","timestamp":1723612200000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10620705\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,20]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/infocomwkshps61880.2024.10620705","relation":{},"subject":[],"published":{"date-parts":[[2024,5,20]]}}}