{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T18:06:39Z","timestamp":1730225199754,"version":"3.28.0"},"reference-count":28,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,7,1]],"date-time":"2019-07-01T00:00:00Z","timestamp":1561939200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,7,1]],"date-time":"2019-07-01T00:00:00Z","timestamp":1561939200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,7,1]],"date-time":"2019-07-01T00:00:00Z","timestamp":1561939200000},"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":[[2019,7]]},"DOI":"10.1109\/hpcs48598.2019.9188154","type":"proceedings-article","created":{"date-parts":[[2020,9,9]],"date-time":"2020-09-09T20:58:33Z","timestamp":1599685113000},"page":"348-357","source":"Crossref","is-referenced-by-count":6,"title":["Scalability of Hybrid SpMV on Intel Xeon Phi Knights Landing"],"prefix":"10.1109","author":[{"given":"Brian A.","family":"Page","sequence":"first","affiliation":[]},{"given":"Peter M.","family":"Kogge","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"journal-title":"Performance on trinity phase 2 (a cray xc40 utilizing intel xeon phi processors) with acceptance-applications and benchmarks","year":"2017","author":"agelastos","key":"ref10"},{"journal-title":"Efficient Sparse Matrix-Vector Multiplication on CUDA","year":"2008","author":"bell","key":"ref11"},{"key":"ref12","first-page":"17","author":"sedaghati","year":"2015","journal-title":"Characterizing Dataset Dependence for Sparse Matrix-Vector Multiplication on GPUs"},{"key":"ref13","doi-asserted-by":"crossref","first-page":"49","DOI":"10.1016\/j.jpdc.2016.12.023","article-title":"A hybrid computing method of SpMV on CPUGPU heterogeneous computing systems","volume":"104","author":"yang","year":"2017","journal-title":"Journal of Parallel and Distributed Computing"},{"key":"ref14","doi-asserted-by":"crossref","first-page":"149","DOI":"10.1145\/3168818","article-title":"Cvr: Efficient vectorization of spmv on x86 processors","author":"xie","year":"2018","journal-title":"Proceedings of the 2018 International Symposium on Code Generation and Optimization CGO 2018"},{"key":"ref15","doi-asserted-by":"crossref","first-page":"172","DOI":"10.1007\/978-3-319-17248-4_9","article-title":"Performance modeling of the hpcg benchmark","author":"marjanovi?","year":"2015","journal-title":"High Performance Computing Systems Performance Modeling Benchmarking and Simulation"},{"key":"ref16","volume":"2","author":"vzquez","year":"2009","journal-title":"The Sparse Matrix Vector Product on GPUs"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/2597652.2597678"},{"key":"ref18","article-title":"Performance evaluation of sparse matrix multiplication kernels on intel xeon phi","volume":"abs 1302 1078","author":"saule","year":"2013","journal-title":"CoRR"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/2464996.2465013"},{"key":"ref28","doi-asserted-by":"crossref","first-page":"889","DOI":"10.15439\/2016F498","article-title":"Superlinear Speedup in HPC Systems: Why and When?","author":"sasko ristov","year":"2016","journal-title":"2016 Federated Conference on Computer Science and Information Systems (FedCSIS)"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.eml.2015.12.009"},{"key":"ref27","article-title":"Evaluating the networking characteristics of the cray xc40 intel knights landingbased cori supercomputer at nersc","volume":"30","author":"doerfler","year":"2017","journal-title":"Concurrency and Computation Practice and Experience"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1002\/nme.4755"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/HPCS48598.2019.9188143"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1137\/1.9780898719918"},{"key":"ref8","doi-asserted-by":"crossref","first-page":"406","DOI":"10.1109\/HPCS.2018.00072","article-title":"Scalability of hybrid sparse matrix dense vector (spmv) multiplication","author":"page","year":"2018","journal-title":"2018 International Conference on High Performance Computing Simulation (HPCS)"},{"journal-title":"Graph BLAS Forum","year":"0","key":"ref7"},{"key":"ref2","doi-asserted-by":"crossref","first-page":"632","DOI":"10.1007\/3-540-47789-6_66","article-title":"hypre: A library of high performance preconditioners","author":"falgout","year":"2002","journal-title":"Computational Science — ICCS 2002"},{"journal-title":"Intel Xeon Phi Processor High Performance Programming Knights Landing","year":"2016","author":"jeffers","key":"ref9"},{"journal-title":"Toward A New Metric for Ranking High Performance Computing Systems","year":"2013","author":"dongarra","key":"ref1"},{"key":"ref20","first-page":"295","author":"liu","year":"2003","journal-title":"High performance RDMA-Based MPI implementation over InfiniBand"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2016.25"},{"journal-title":"Improving Message-Passing Performance and Scalability in High-Performance Clusters","year":"2011","author":"rashti","key":"ref21"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/2049662.2049663"},{"key":"ref23","first-page":"37:1","article-title":"Optimizing for knl usage modes when data doesn’t fit in mcdram","author":"butcher","year":"2018","journal-title":"Proceedings of the 47th International Conference on Parallel Processing ser ICPP 2018"},{"journal-title":"Cray XC Series Network","year":"0","author":"alverson","key":"ref26"},{"journal-title":"Performance on trinity phase 2 (a cray xc40 utilizing intel xeon phi processors) with acceptance-applications and benchmarks","year":"2017","author":"agelastos","key":"ref25"}],"event":{"name":"2019 International Conference on High Performance Computing & Simulation (HPCS)","start":{"date-parts":[[2019,7,15]]},"location":"Dublin, Ireland","end":{"date-parts":[[2019,7,19]]}},"container-title":["2019 International Conference on High Performance Computing & Simulation (HPCS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9183768\/9188050\/09188154.pdf?arnumber=9188154","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,17]],"date-time":"2022-07-17T21:50:27Z","timestamp":1658094627000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9188154\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,7]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/hpcs48598.2019.9188154","relation":{},"subject":[],"published":{"date-parts":[[2019,7]]}}}