{"id":"https://openalex.org/W4378803429","doi":"https://doi.org/10.1177/10943420231178552","title":"HipBone: A performance-portable graphics processing unit-accelerated C++ version of the NekBone benchmark","display_name":"HipBone: A performance-portable graphics processing unit-accelerated C++ version of the NekBone benchmark","publication_year":2023,"publication_date":"2023-05-31","ids":{"openalex":"https://openalex.org/W4378803429","doi":"https://doi.org/10.1177/10943420231178552"},"language":"en","primary_location":{"id":"doi:10.1177/10943420231178552","is_oa":false,"landing_page_url":"https://doi.org/10.1177/10943420231178552","pdf_url":null,"source":{"id":"https://openalex.org/S60606485","display_name":"The International Journal of High Performance Computing Applications","issn_l":"0890-2720","issn":["0890-2720","1094-3420","1741-2846"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The International Journal of High Performance Computing Applications","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5020250502","display_name":"Noel Chalmers","orcid":"https://orcid.org/0000-0002-1293-7525"},"institutions":[{"id":"https://openalex.org/I4210137977","display_name":"Advanced Micro Devices (United States)","ror":"https://ror.org/04kd6c783","country_code":"US","type":"company","lineage":["https://openalex.org/I4210137977"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Noel Chalmers","raw_affiliation_strings":["Data Center GPU and Accelerated Processing, Advanced Micro Devices Inc, Austin, TX, USA"],"raw_orcid":"https://orcid.org/0000-0002-1293-7525","affiliations":[{"raw_affiliation_string":"Data Center GPU and Accelerated Processing, Advanced Micro Devices Inc, Austin, TX, USA","institution_ids":["https://openalex.org/I4210137977"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100778263","display_name":"Abhishek Mishra","orcid":"https://orcid.org/0000-0001-7445-066X"},"institutions":[{"id":"https://openalex.org/I63190737","display_name":"University at Buffalo, State University of New York","ror":"https://ror.org/01y64my43","country_code":"US","type":"education","lineage":["https://openalex.org/I63190737"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Abhishek Mishra","raw_affiliation_strings":["Institute for Computational and Data Sciences, University at Buffalo, Buffalo, NY, USA"],"raw_orcid":"https://orcid.org/0000-0001-7445-066X","affiliations":[{"raw_affiliation_string":"Institute for Computational and Data Sciences, University at Buffalo, Buffalo, NY, USA","institution_ids":["https://openalex.org/I63190737"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006676862","display_name":"Damon McDougall","orcid":"https://orcid.org/0009-0008-5865-9322"},"institutions":[{"id":"https://openalex.org/I4210137977","display_name":"Advanced Micro Devices (United States)","ror":"https://ror.org/04kd6c783","country_code":"US","type":"company","lineage":["https://openalex.org/I4210137977"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Damon McDougall","raw_affiliation_strings":["Data Center GPU and Accelerated Processing, Advanced Micro Devices Inc, Austin, TX, USA"],"raw_orcid":"https://orcid.org/0009-0008-5865-9322","affiliations":[{"raw_affiliation_string":"Data Center GPU and Accelerated Processing, Advanced Micro Devices Inc, Austin, TX, USA","institution_ids":["https://openalex.org/I4210137977"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084171041","display_name":"Tim Warburton","orcid":"https://orcid.org/0000-0002-3202-1151"},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tim Warburton","raw_affiliation_strings":["Department of Mathematics, Virginia Tech, McBryde Hall, VA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mathematics, Virginia Tech, McBryde Hall, VA, USA","institution_ids":["https://openalex.org/I859038795"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5020250502"],"corresponding_institution_ids":["https://openalex.org/I4210137977"],"apc_list":null,"apc_paid":null,"fwci":1.8463,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.84188912,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"37","issue":"5","first_page":"560","last_page":"577"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9990000128746033,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9990000128746033,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9983000159263611,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9950000047683716,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8649708032608032},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6710993051528931},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.60735684633255},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.5998408794403076},{"id":"https://openalex.org/keywords/software-portability","display_name":"Software portability","score":0.5819445252418518},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.5576305389404297},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5366961359977722},{"id":"https://openalex.org/keywords/infiniband","display_name":"InfiniBand","score":0.4437275528907776},{"id":"https://openalex.org/keywords/graphics-processing-unit","display_name":"Graphics processing unit","score":0.44049137830734253},{"id":"https://openalex.org/keywords/remote-direct-memory-access","display_name":"Remote direct memory access","score":0.43840456008911133},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.4368618130683899},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.3702903389930725},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.3340959846973419},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.20969972014427185}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8649708032608032},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6710993051528931},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.60735684633255},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.5998408794403076},{"id":"https://openalex.org/C63000827","wikidata":"https://www.wikidata.org/wiki/Q3080428","display_name":"Software portability","level":2,"score":0.5819445252418518},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.5576305389404297},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5366961359977722},{"id":"https://openalex.org/C2781030343","wikidata":"https://www.wikidata.org/wiki/Q922437","display_name":"InfiniBand","level":2,"score":0.4437275528907776},{"id":"https://openalex.org/C2779851693","wikidata":"https://www.wikidata.org/wiki/Q183484","display_name":"Graphics processing unit","level":2,"score":0.44049137830734253},{"id":"https://openalex.org/C130795937","wikidata":"https://www.wikidata.org/wiki/Q2561570","display_name":"Remote direct memory access","level":2,"score":0.43840456008911133},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.4368618130683899},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.3702903389930725},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.3340959846973419},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.20969972014427185},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1177/10943420231178552","is_oa":false,"landing_page_url":"https://doi.org/10.1177/10943420231178552","pdf_url":null,"source":{"id":"https://openalex.org/S60606485","display_name":"The International Journal of High Performance Computing Applications","issn_l":"0890-2720","issn":["0890-2720","1094-3420","1741-2846"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The International Journal of High Performance Computing Applications","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.46000000834465027,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W207877228","https://openalex.org/W1900162302","https://openalex.org/W1955542447","https://openalex.org/W1985401272","https://openalex.org/W2008968423","https://openalex.org/W2021261510","https://openalex.org/W2028425870","https://openalex.org/W2047352485","https://openalex.org/W2049744236","https://openalex.org/W2053572944","https://openalex.org/W2076301462","https://openalex.org/W2104736438","https://openalex.org/W2109241917","https://openalex.org/W2117752372","https://openalex.org/W2120919211","https://openalex.org/W2142673658","https://openalex.org/W2163798155","https://openalex.org/W2309966696","https://openalex.org/W2502318050","https://openalex.org/W2947863501","https://openalex.org/W2963610942","https://openalex.org/W2969262004","https://openalex.org/W3016268593","https://openalex.org/W3040786754","https://openalex.org/W3087782549","https://openalex.org/W3100569748","https://openalex.org/W3131967960","https://openalex.org/W3155036733","https://openalex.org/W3196536671","https://openalex.org/W4287775099","https://openalex.org/W4298060601"],"related_works":["https://openalex.org/W1978254186","https://openalex.org/W4245217724","https://openalex.org/W4390917331","https://openalex.org/W4253931064","https://openalex.org/W1984788566","https://openalex.org/W3166154920","https://openalex.org/W2154082760","https://openalex.org/W1964981582","https://openalex.org/W4282599985","https://openalex.org/W2139382794"],"abstract_inverted_index":{"We":[0,88,106,157],"present":[1,107],"hipBone,":[2],"an":[3],"open-source":[4],"performance-portable":[5],"proxy":[6,29],"application":[7,30,114],"for":[8,111,127],"the":[9,25,55,60,69,75,83,93,113,116,155,159,174,178],"Nek5000":[10],"(and":[11],"NekRS)":[12],"computational":[13],"fluid":[14],"dynamics":[15],"applications.":[16],"HipBone":[17],"is":[18],"a":[19,51,79,108],"fully":[20],"GPU-accelerated":[21],"C++":[22],"implementation":[23,36,81,134],"of":[24,57,59,71,82,92,115,135,154,161],"original":[26],"NekBone":[27],"CPU":[28],"with":[31],"several":[32,141],"novel":[33,109],"algorithmic":[34],"and":[35,78,131,145,177,183,193],"improvements":[37],"which":[38,121,151],"optimize":[39],"its":[40],"performance":[41,91,160],"on":[42,96,119,163,199],"modern":[43,99],"fine-grain":[44],"parallel":[45],"GPU":[46,100],"accelerators.":[47],"Our":[48,133,185],"optimizations":[49],"include":[50],"conversion":[52],"to":[53,67],"store":[54],"degrees":[56],"freedom":[58],"problem":[61],"in":[62,65],"assembled":[63],"form":[64],"order":[66],"reduce":[68],"amount":[70],"data":[72],"moved":[73],"during":[74],"main":[76,84],"iteration":[77],"portable":[80],"Poisson":[85,117],"operator":[86,94,118],"kernel.":[87],"demonstrate":[89,158,187],"near-roofline":[90],"kernel":[95],"three":[97,164],"different":[98,104,142,165,191],"accelerators":[101],"from":[102],"two":[103],"vendors.":[105],"algorithm":[110],"splitting":[112],"GPUs":[120],"aggressively":[122],"hides":[123],"MPI":[124,137],"communication":[125,138],"required":[126],"both":[128,188],"halo":[129],"exchange":[130],"assembly.":[132],"nearest-neighbor":[136],"then":[139],"leverages":[140],"routing":[143],"algorithms":[144],"GPU-Direct":[146],"RDMA":[147],"capabilities,":[148],"when":[149],"available,":[150],"improves":[152],"scalability":[153],"benchmark.":[156],"hipBone":[162],"clusters":[166,192],"housed":[167],"at":[168],"Oak":[169],"Ridge":[170],"National":[171],"Laboratory,":[172],"namely,":[173],"Summit":[175],"supercomputer":[176],"Frontier":[179],"early-access":[180],"clusters,":[181],"Spock":[182],"Crusher.":[184],"tests":[186],"portability":[189],"across":[190],"very":[194],"good":[195],"scaling":[196],"efficiency,":[197],"especially":[198],"large":[200],"problems.":[201]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2}],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2025-10-10T00:00:00"}