{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,17]],"date-time":"2025-10-17T14:19:37Z","timestamp":1760710777666},"reference-count":45,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,9,20]],"date-time":"2021-09-20T00:00:00Z","timestamp":1632096000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,9,20]],"date-time":"2021-09-20T00:00:00Z","timestamp":1632096000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,9,20]],"date-time":"2021-09-20T00:00:00Z","timestamp":1632096000000},"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":[[2021,9,20]]},"DOI":"10.1109\/hpec49654.2021.9622847","type":"proceedings-article","created":{"date-parts":[[2021,12,1]],"date-time":"2021-12-01T20:57:36Z","timestamp":1638392256000},"page":"1-8","source":"Crossref","is-referenced-by-count":10,"title":["Workload Imbalance in HPC Applications: Effect on Performance of In-Network Processing"],"prefix":"10.1109","author":[{"given":"Pouya","family":"Haghi","sequence":"first","affiliation":[]},{"given":"Anqi","family":"Guo","sequence":"additional","affiliation":[]},{"given":"Tong","family":"Geng","sequence":"additional","affiliation":[]},{"given":"Anthony","family":"Skjellum","sequence":"additional","affiliation":[]},{"given":"Martin C.","family":"Herbordt","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1016\/B978-044482851-4.50031-1"},{"key":"ref38","first-page":"121","article-title":"Automatic thread distribution for nested parallelism in openmp","author":"duran","year":"0"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3093338.3093385"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1998.681704"},{"article-title":"Miniamr - a miniapp for adaptive mesh refinement","year":"2016","author":"sasidharan","key":"ref31"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/0021-9991(89)90035-1"},{"key":"ref37","first-page":"79","article-title":"Dynamic mesh partitioning load-balancing for parallel computational mechanics codes","author":"walshaw","year":"1999","journal-title":"Parallel Distributed Processing for Computational Mechanics Saxe-Coburg Publications"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/SC.1998.10018"},{"year":"0","key":"ref35","article-title":"METIS - serial graph partitioning and fill-reducing matrix ordering"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-45718-6_13"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3039902.3039904"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2008.5217785"},{"key":"ref11","article-title":"Accelerating MPI Reduce with FPGAs in the Network","author":"stern","year":"2017","journal-title":"Workshop on Exascale MPI"},{"key":"ref12","article-title":"A Novel Approach to Supporting Communicators for In-Switch Processing of MPI Collectives","author":"stern","year":"2018","journal-title":"Workshop on Exascale MPI"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/FCCM48280.2020.00028"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/HPEC43674.2020.9286200"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/FCCM48280.2020.00046"},{"article-title":"An evaluation of the coral interconnects","year":"0","author":"zimmer","key":"ref16"},{"year":"0","key":"ref17","article-title":"Top500 Supercomputer List"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/FCCM.2018.00053"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1177\/1094342005051521"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.2172\/993908"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/IPDRM51949.2020.00007"},{"year":"0","key":"ref27","article-title":"ECP Proxy Applications"},{"key":"ref3","first-page":"51","article-title":"Azure Accel-erated Networking: SmartNICs in the Public Cloud","author":"firestone","year":"2018","journal-title":"15th USENIX Symposium on Networked Systems Design and Implementation (NSDI 18)"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/FPL.2018.00039"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1137\/0612048"},{"journal-title":"Fabric Collective Accelerator (FCA)","year":"2019","key":"ref5"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/1088149.1088183"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1002\/cpe.5150"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/SC41405.2020.00039"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/COMHPC.2016.006"},{"journal-title":"Future Directions for NSF Advanced Computing Infrastructure to Support U S Science and Engineering in 2017-2020","year":"2016","key":"ref1"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CLUSTER.2012.75"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/3236367.3236376"},{"year":"0","key":"ref22","article-title":"ECP Proxy Applications, miniFE Catalog"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICFPT51103.2020.00030"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2008.5219920"},{"year":"0","key":"ref24","article-title":"miniAMR - Adaptive Mesh Refinement Mini-App"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/2642769.2642786"},{"year":"0","key":"ref23","article-title":"HPCCG Benchmark"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CCGrid.2013.65"},{"year":"0","key":"ref26","article-title":"Ember Communication Pattern Library"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/s10586-007-0047-2"},{"year":"0","key":"ref25","article-title":"Mantevo Project"}],"event":{"name":"2021 IEEE High Performance Extreme Computing Conference (HPEC)","start":{"date-parts":[[2021,9,20]]},"location":"Waltham, MA, USA","end":{"date-parts":[[2021,9,24]]}},"container-title":["2021 IEEE High Performance Extreme Computing Conference (HPEC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9622740\/9622741\/09622847.pdf?arnumber=9622847","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T16:53:49Z","timestamp":1652201629000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9622847\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,9,20]]},"references-count":45,"URL":"https:\/\/doi.org\/10.1109\/hpec49654.2021.9622847","relation":{},"subject":[],"published":{"date-parts":[[2021,9,20]]}}}