{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,8]],"date-time":"2026-01-08T04:02:07Z","timestamp":1767844927068,"version":"3.49.0"},"reference-count":56,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,2,1]],"date-time":"2023-02-01T00:00:00Z","timestamp":1675209600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,2,1]],"date-time":"2023-02-01T00:00:00Z","timestamp":1675209600000},"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":[[2023,2]]},"DOI":"10.1109\/hpca56546.2023.10070949","type":"proceedings-article","created":{"date-parts":[[2023,3,24]],"date-time":"2023-03-24T13:42:55Z","timestamp":1679665375000},"page":"516-529","source":"Crossref","is-referenced-by-count":9,"title":["FinePack: Transparently Improving the Efficiency of Fine-Grained Transfers in Multi-GPU Systems"],"prefix":"10.1109","author":[{"given":"Harini","family":"Muthukrishnan","sequence":"first","affiliation":[{"name":"NVIDIA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Daniel","family":"Lustig","sequence":"additional","affiliation":[{"name":"NVIDIA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Oreste","family":"Villa","sequence":"additional","affiliation":[{"name":"NVIDIA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Thomas","family":"Wenisch","sequence":"additional","affiliation":[{"name":"University of Michigan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"David","family":"Nellans","sequence":"additional","affiliation":[{"name":"NVIDIA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/2049662.2049663"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/2451116.2451157"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1145\/2688500.2688507"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/2641764"},{"key":"ref14","article-title":"Multi-GPU (CUDA-MPI) Baseline Implementation of Heat Equation and the Inviscid Burgers’ Equation","author":"diaz","year":"0"},{"key":"ref53","article-title":"Bellman Ford Algorithm","year":"2022"},{"key":"ref52","article-title":"PageRank","year":"2018"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3092255.3092256"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2018.00035"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/HOTCHIPS.2016.7936202"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/3307650.3322223"},{"key":"ref17","article-title":"Beyond Data and Model Parallelism for Deep Neural Networks","author":"jia","year":"2018"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.284"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2003.1213166"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/2807591.2807600"},{"key":"ref51","article-title":"Jacobi Method","year":"0"},{"key":"ref50","article-title":"PCI Express","year":"0"},{"key":"ref46","first-page":"664","article-title":"Exploiting Adaptive Data Compression to Improve Performance and Energy-Efficiency of Compute Workloads in Multi-GPU Systems","author":"tavana","year":"2019","journal-title":"International Parallel and Distributed Processing Symposium (IPDPS)"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/2365952.2365972"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/3352460.3358307"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA51647.2021.00077"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/223982.224419"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA47549.2020.00054"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2018.00042"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2013.6522351"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICPP.2014.30"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2012.72"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.23919\/DATE.2019.8715196"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA53966.2022.00056"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA47549.2020.00055"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080231"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3399730"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/2989081.2989092"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2017.40"},{"key":"ref35","article-title":"PTX: Parallel Thread Execution ISA Version 7.0","year":"2020"},{"key":"ref34","article-title":"NVIDIA NVLink High-Speed GPU Interconnect","year":"2020"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/MASCOT.2000.876559"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3126908.3126914"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3466752.3480088"},{"key":"ref30","article-title":"GMT: Enabling Easy Development and Efficient Execution of Irregular Applications on Commodity Clusters","author":"morari","year":"2013","journal-title":"International Conference for High Performance Computing Networking Storage and Analysis (SC)"},{"key":"ref33","article-title":"NVLink AND NVSwitch The Building Blocks of Advanced Multi-GPU Communication","year":"2019"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA52012.2021.00020"},{"key":"ref2","first-page":"220","article-title":"Automatic Communication Coalescing for Irregular Computations in UPC Language","author":"alvanos","year":"2012","journal-title":"Conference of the Center for Advanced Studies on Collaborative Research(CASCON)"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/2694344.2694381"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.14778\/2824032.2824043"},{"key":"ref38","first-page":"457","article-title":"Heterogeneous system coherence for integrated CPU-GPU systems","author":"power","year":"2013","journal-title":"2013 46th Annual IEEE\/ACM International Symposium on Microarchitecture (MICRO) MICRO"},{"key":"ref24","article-title":"Efficient Large-scale Parallel Stencil Computation on Multi-Core and Multi-GPU Accelerated Clusters","author":"liu","year":"0"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC.2018.8573483"},{"key":"ref26","article-title":"HIT: A Parallel GPGPU Code to Simulate Homogeneous Isotropic Turbulence","author":"mart?n","year":"0"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2013.6522332"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3373376.3378529"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2019.2928289"},{"key":"ref21","article-title":"Thread and Memory Placement on NUMA Systems: Asymmetry Matters","author":"lepers","year":"2015","journal-title":"USENIX Annual Technical Conference (USENIX ATC)"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3123939.3124534"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TCI.2015.2479555"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1002\/cpe.4061"}],"event":{"name":"2023 IEEE International Symposium on High-Performance Computer Architecture (HPCA)","location":"Montreal, QC, Canada","start":{"date-parts":[[2023,2,25]]},"end":{"date-parts":[[2023,3,1]]}},"container-title":["2023 IEEE International Symposium on High-Performance Computer Architecture (HPCA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10070856\/10070923\/10070949.pdf?arnumber=10070949","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,4,17]],"date-time":"2023-04-17T13:35:50Z","timestamp":1681738550000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10070949\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,2]]},"references-count":56,"URL":"https:\/\/doi.org\/10.1109\/hpca56546.2023.10070949","relation":{},"subject":[],"published":{"date-parts":[[2023,2]]}}}