{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T01:47:15Z","timestamp":1740102435396,"version":"3.37.3"},"reference-count":24,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,10,31]],"date-time":"2023-10-31T00:00:00Z","timestamp":1698710400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,10,31]],"date-time":"2023-10-31T00:00:00Z","timestamp":1698710400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000015","name":"U.S. Department of Energy","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000015","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000015","name":"U.S. Department of Energy","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000015","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100006132","name":"Office of Science","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006132","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,10,31]]},"DOI":"10.1109\/cluster52292.2023.00037","type":"proceedings-article","created":{"date-parts":[[2023,11,21]],"date-time":"2023-11-21T19:21:45Z","timestamp":1700594505000},"page":"354-364","source":"Crossref","is-referenced-by-count":1,"title":["PiP-MColl: Process-in-Process-based Multi-object MPI Collectives"],"prefix":"10.1109","author":[{"given":"Jiajun","family":"Huang","sequence":"first","affiliation":[{"name":"University of California,Riverside"}]},{"given":"Kaiming","family":"Ouyang","sequence":"additional","affiliation":[{"name":"NVIDIA Corporation"}]},{"given":"Yujia","family":"Zhai","sequence":"additional","affiliation":[{"name":"University of California,Riverside"}]},{"given":"Jinyang","family":"Liu","sequence":"additional","affiliation":[{"name":"University of California,Riverside"}]},{"given":"Min","family":"Si","sequence":"additional","affiliation":[{"name":"Meta Platforms, Inc."}]},{"given":"Ken","family":"Raffenetti","sequence":"additional","affiliation":[{"name":"Argonne National Laboratory"}]},{"given":"Hui","family":"Zhou","sequence":"additional","affiliation":[{"name":"Argonne National Laboratory"}]},{"given":"Atsushi","family":"Hori","sequence":"additional","affiliation":[{"name":"National Institute of Informatics"}]},{"given":"Zizhong","family":"Chen","sequence":"additional","affiliation":[{"name":"University of California,Riverside"}]},{"given":"Yanfei","family":"Guo","sequence":"additional","affiliation":[{"name":"Argonne National Laboratory"}]},{"given":"Rajeev","family":"Thakur","sequence":"additional","affiliation":[{"name":"Argonne National Laboratory"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3018743.3018769"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1063\/1.2409141"},{"article-title":"gzccl: Compression-accelerated collective communication framework for gpu clusters","year":"2023","author":"Huang","key":"ref3"},{"key":"ref4","first-page":"265","article-title":"Tensorflow: A system for large-scale machine learning","volume-title":"12th {USENIX} symposium on operating systems design and implementation ({OSDI} 16)","author":"Abadi"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ExaMPI49596.2019.00007"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3588195.3595955"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/DLS49591.2019.00015"},{"article-title":"C-coll: Introducing error-bounded lossy compression into mpi collectives","year":"2023","author":"Huang","key":"ref8"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2018.00033"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2018.00032"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICPP.2005.48"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICPP.2011.29"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CLUSTER.2017.106"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2014.32"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2018.00111"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3208040.3208045"},{"volume-title":"MVAPICH2-X 2.3 User Guide","year":"2020","author":"TEAM","key":"ref17"},{"volume-title":"Documentation for Open MPI","year":"2023","key":"ref18"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/HOTI.2015.22"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-8191(06)80021-9"},{"key":"ref21","first-page":"10","article-title":"Collmark: Mpi collective communication benchmark","volume-title":"International Conference on Supercomputing","author":"Shroff"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/71.642949"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1177\/1094342005051521"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-24685-5_1"}],"event":{"name":"2023 IEEE International Conference on Cluster Computing (CLUSTER)","start":{"date-parts":[[2023,10,31]]},"location":"Santa Fe, NM, USA","end":{"date-parts":[[2023,11,3]]}},"container-title":["2023 IEEE International Conference on Cluster Computing (CLUSTER)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10319881\/10319941\/10319969.pdf?arnumber=10319969","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,2]],"date-time":"2024-03-02T20:36:32Z","timestamp":1709411792000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10319969\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,31]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/cluster52292.2023.00037","relation":{},"subject":[],"published":{"date-parts":[[2023,10,31]]}}}