{"id":"https://openalex.org/W7116345625","doi":"https://doi.org/10.1145/3754598.3754668","title":"Cross-Architecture Performance Analysis Using the RAJA Performance Suite","display_name":"Cross-Architecture Performance Analysis Using the RAJA Performance Suite","publication_year":2025,"publication_date":"2025-09-08","ids":{"openalex":"https://openalex.org/W7116345625","doi":"https://doi.org/10.1145/3754598.3754668"},"language":null,"primary_location":{"id":"doi:10.1145/3754598.3754668","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3754598.3754668","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 54th International Conference on Parallel Processing","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3754598.3754668","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5120880954","display_name":"Dewi Yokelson","orcid":null},"institutions":[{"id":"https://openalex.org/I1282311441","display_name":"Lawrence Livermore National Laboratory","ror":"https://ror.org/041nk4h53","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282311441","https://openalex.org/I1330989302","https://openalex.org/I198811213","https://openalex.org/I4210138311"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dewi Yokelson","raw_affiliation_strings":["Lawrence Livermore National Laboratory, Livermore, USA"],"raw_orcid":"https://orcid.org/0000-0003-1453-5906","affiliations":[{"raw_affiliation_string":"Lawrence Livermore National Laboratory, Livermore, USA","institution_ids":["https://openalex.org/I1282311441"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010860138","display_name":"Stephanie Brink","orcid":"https://orcid.org/0000-0002-1458-8453"},"institutions":[{"id":"https://openalex.org/I1282311441","display_name":"Lawrence Livermore National Laboratory","ror":"https://ror.org/041nk4h53","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282311441","https://openalex.org/I1330989302","https://openalex.org/I198811213","https://openalex.org/I4210138311"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Stephanie Brink","raw_affiliation_strings":["Lawrence Livermore National Laboratory, Livermore, USA"],"raw_orcid":"https://orcid.org/0000-0002-1458-8453","affiliations":[{"raw_affiliation_string":"Lawrence Livermore National Laboratory, Livermore, USA","institution_ids":["https://openalex.org/I1282311441"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079015680","display_name":"Jason Burmark","orcid":"https://orcid.org/0009-0005-3036-0108"},"institutions":[{"id":"https://openalex.org/I1282311441","display_name":"Lawrence Livermore National Laboratory","ror":"https://ror.org/041nk4h53","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282311441","https://openalex.org/I1330989302","https://openalex.org/I198811213","https://openalex.org/I4210138311"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jason Burmark","raw_affiliation_strings":["Lawrence Livermore National Laboratory, Livermore, USA"],"raw_orcid":"https://orcid.org/0009-0005-3036-0108","affiliations":[{"raw_affiliation_string":"Lawrence Livermore National Laboratory, Livermore, USA","institution_ids":["https://openalex.org/I1282311441"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091836403","display_name":"Michael McKinsey","orcid":"https://orcid.org/0009-0001-7201-5733"},"institutions":[{"id":"https://openalex.org/I1282311441","display_name":"Lawrence Livermore National Laboratory","ror":"https://ror.org/041nk4h53","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282311441","https://openalex.org/I1330989302","https://openalex.org/I198811213","https://openalex.org/I4210138311"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael McKinsey","raw_affiliation_strings":["Lawrence Livermore National Laboratory, Livermore, USA"],"raw_orcid":"https://orcid.org/0009-0001-7201-5733","affiliations":[{"raw_affiliation_string":"Lawrence Livermore National Laboratory, Livermore, USA","institution_ids":["https://openalex.org/I1282311441"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093240750","display_name":"Befikir Bogale","orcid":"https://orcid.org/0000-0003-1007-9384"},"institutions":[{"id":"https://openalex.org/I2802706902","display_name":"Knoxville College","ror":"https://ror.org/02bxrp522","country_code":"US","type":"education","lineage":["https://openalex.org/I2802706902"]},{"id":"https://openalex.org/I75027704","display_name":"University of Tennessee at Knoxville","ror":"https://ror.org/020f3ap87","country_code":"US","type":"education","lineage":["https://openalex.org/I75027704"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Befikir Bogale","raw_affiliation_strings":["University of Tennessee, Knoxville, Knoxville, USA"],"raw_orcid":"https://orcid.org/0000-0003-1007-9384","affiliations":[{"raw_affiliation_string":"University of Tennessee, Knoxville, Knoxville, USA","institution_ids":["https://openalex.org/I2802706902","https://openalex.org/I75027704"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088217764","display_name":"Ian Lumsden","orcid":"https://orcid.org/0000-0003-0009-5487"},"institutions":[{"id":"https://openalex.org/I2802706902","display_name":"Knoxville College","ror":"https://ror.org/02bxrp522","country_code":"US","type":"education","lineage":["https://openalex.org/I2802706902"]},{"id":"https://openalex.org/I75027704","display_name":"University of Tennessee at Knoxville","ror":"https://ror.org/020f3ap87","country_code":"US","type":"education","lineage":["https://openalex.org/I75027704"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ian Lumsden","raw_affiliation_strings":["University of Tennessee, Knoxville, Knoxville, USA"],"raw_orcid":"https://orcid.org/0000-0003-0009-5487","affiliations":[{"raw_affiliation_string":"University of Tennessee, Knoxville, Knoxville, USA","institution_ids":["https://openalex.org/I2802706902","https://openalex.org/I75027704"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078387820","display_name":"Michela Taufer","orcid":"https://orcid.org/0000-0002-0031-6377"},"institutions":[{"id":"https://openalex.org/I2802706902","display_name":"Knoxville College","ror":"https://ror.org/02bxrp522","country_code":"US","type":"education","lineage":["https://openalex.org/I2802706902"]},{"id":"https://openalex.org/I75027704","display_name":"University of Tennessee at Knoxville","ror":"https://ror.org/020f3ap87","country_code":"US","type":"education","lineage":["https://openalex.org/I75027704"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michela Taufer","raw_affiliation_strings":["University of Tennessee, Knoxville, Knoxville, USA"],"raw_orcid":"https://orcid.org/0000-0002-0031-6377","affiliations":[{"raw_affiliation_string":"University of Tennessee, Knoxville, Knoxville, USA","institution_ids":["https://openalex.org/I2802706902","https://openalex.org/I75027704"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120902469","display_name":"Tom Scogland","orcid":null},"institutions":[{"id":"https://openalex.org/I1282311441","display_name":"Lawrence Livermore National Laboratory","ror":"https://ror.org/041nk4h53","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282311441","https://openalex.org/I1330989302","https://openalex.org/I198811213","https://openalex.org/I4210138311"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tom Scogland","raw_affiliation_strings":["Lawrence Livermore National Laboratory, Livermore, USA"],"raw_orcid":"https://orcid.org/0000-0001-7234-5743","affiliations":[{"raw_affiliation_string":"Lawrence Livermore National Laboratory, Livermore, USA","institution_ids":["https://openalex.org/I1282311441"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5012779678","display_name":"Olga Pearce","orcid":"https://orcid.org/0000-0002-1904-9627"},"institutions":[{"id":"https://openalex.org/I1282311441","display_name":"Lawrence Livermore National Laboratory","ror":"https://ror.org/041nk4h53","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282311441","https://openalex.org/I1330989302","https://openalex.org/I198811213","https://openalex.org/I4210138311"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Olga Pearce","raw_affiliation_strings":["Lawrence Livermore National Laboratory, Livermore, USA and Texas A&amp;M University, Livermore, USA"],"raw_orcid":"https://orcid.org/0000-0002-1904-9627","affiliations":[{"raw_affiliation_string":"Lawrence Livermore National Laboratory, Livermore, USA and Texas A&amp;M University, Livermore, USA","institution_ids":["https://openalex.org/I1282311441"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"617","last_page":"626"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9783999919891357,"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":0.9783999919891357,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.003000000026077032,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.002300000051036477,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/software-portability","display_name":"Software portability","score":0.9283999800682068},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.7986000180244446},{"id":"https://openalex.org/keywords/porting","display_name":"Porting","score":0.7728999853134155},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.5695000290870667},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5554999709129333},{"id":"https://openalex.org/keywords/suite","display_name":"Suite","score":0.5194000005722046},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.41780000925064087},{"id":"https://openalex.org/keywords/performance-improvement","display_name":"Performance improvement","score":0.40959998965263367},{"id":"https://openalex.org/keywords/performance-tuning","display_name":"Performance tuning","score":0.40380001068115234},{"id":"https://openalex.org/keywords/source-lines-of-code","display_name":"Source lines of code","score":0.3896999955177307}],"concepts":[{"id":"https://openalex.org/C63000827","wikidata":"https://www.wikidata.org/wiki/Q3080428","display_name":"Software portability","level":2,"score":0.9283999800682068},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8543000221252441},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.7986000180244446},{"id":"https://openalex.org/C106251023","wikidata":"https://www.wikidata.org/wiki/Q851989","display_name":"Porting","level":3,"score":0.7728999853134155},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6517000198364258},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.5695000290870667},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5554999709129333},{"id":"https://openalex.org/C79581498","wikidata":"https://www.wikidata.org/wiki/Q1367530","display_name":"Suite","level":2,"score":0.5194000005722046},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.41780000925064087},{"id":"https://openalex.org/C2778915421","wikidata":"https://www.wikidata.org/wiki/Q3643177","display_name":"Performance improvement","level":2,"score":0.40959998965263367},{"id":"https://openalex.org/C2777138346","wikidata":"https://www.wikidata.org/wiki/Q1714153","display_name":"Performance tuning","level":2,"score":0.40380001068115234},{"id":"https://openalex.org/C199519371","wikidata":"https://www.wikidata.org/wiki/Q942695","display_name":"Source lines of code","level":3,"score":0.3896999955177307},{"id":"https://openalex.org/C96972482","wikidata":"https://www.wikidata.org/wiki/Q1049168","display_name":"Xeon Phi","level":2,"score":0.3865000009536743},{"id":"https://openalex.org/C2778100165","wikidata":"https://www.wikidata.org/wiki/Q1589327","display_name":"Memory hierarchy","level":3,"score":0.38100001215934753},{"id":"https://openalex.org/C202491316","wikidata":"https://www.wikidata.org/wiki/Q272683","display_name":"Instruction set","level":2,"score":0.3799000084400177},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3767000138759613},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.3659000098705292},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.3580999970436096},{"id":"https://openalex.org/C2778565505","wikidata":"https://www.wikidata.org/wiki/Q2207566","display_name":"Spec#","level":2,"score":0.35030001401901245},{"id":"https://openalex.org/C154690210","wikidata":"https://www.wikidata.org/wiki/Q1668499","display_name":"Rewriting","level":2,"score":0.34439998865127563},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.33550000190734863},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.3176000118255615},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.3165000081062317},{"id":"https://openalex.org/C2777115002","wikidata":"https://www.wikidata.org/wiki/Q7168246","display_name":"Performance prediction","level":2,"score":0.298799991607666},{"id":"https://openalex.org/C85687889","wikidata":"https://www.wikidata.org/wiki/Q445962","display_name":"Legacy code","level":3,"score":0.29429998993873596},{"id":"https://openalex.org/C12186640","wikidata":"https://www.wikidata.org/wiki/Q6815743","display_name":"Memory model","level":3,"score":0.27950000762939453},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.27889999747276306},{"id":"https://openalex.org/C201410400","wikidata":"https://www.wikidata.org/wiki/Q1064412","display_name":"Multithreading","level":3,"score":0.275299996137619},{"id":"https://openalex.org/C34165917","wikidata":"https://www.wikidata.org/wiki/Q188267","display_name":"Programming paradigm","level":2,"score":0.27230000495910645},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.27070000767707825},{"id":"https://openalex.org/C98183937","wikidata":"https://www.wikidata.org/wiki/Q2112188","display_name":"Program analysis","level":2,"score":0.26989999413490295},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.26899999380111694},{"id":"https://openalex.org/C115051666","wikidata":"https://www.wikidata.org/wiki/Q6522493","display_name":"Ranging","level":2,"score":0.2624000012874603},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.25619998574256897},{"id":"https://openalex.org/C189783530","wikidata":"https://www.wikidata.org/wiki/Q352090","display_name":"CPU cache","level":3,"score":0.2549999952316284},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.25189998745918274},{"id":"https://openalex.org/C49154492","wikidata":"https://www.wikidata.org/wiki/Q5300","display_name":"Central processing unit","level":2,"score":0.2502000033855438}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3754598.3754668","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3754598.3754668","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 54th International Conference on Parallel Processing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3754598.3754668","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3754598.3754668","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 54th International Conference on Parallel Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","score":0.46438974142074585,"display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W1988888548","https://openalex.org/W2013062050","https://openalex.org/W2078794610","https://openalex.org/W2996807164","https://openalex.org/W3015498000","https://openalex.org/W3195293013","https://openalex.org/W3197964808","https://openalex.org/W4200140025","https://openalex.org/W4318603355","https://openalex.org/W4385623175","https://openalex.org/W4388581111","https://openalex.org/W4388581254","https://openalex.org/W4388581267"],"related_works":[],"abstract_inverted_index":{"Modern":[0],"supercomputer":[1],"architectures":[2],"are":[3,10],"diverse":[4,93],"and":[5,14,35,69,71,80,97,123,147],"becoming":[6],"increasingly":[7],"complex.":[8],"Scientists":[9],"constantly":[11],"porting":[12],"code":[13,43],"re-optimizing":[15],"it":[16],"for":[17,47,209],"the":[18,102,140,164,186,189,195,215],"new":[19,170],"architecture,":[20],"but":[21],"achieving":[22],"good":[23],"performance":[24,60,131,141,152,196],"is":[25],"challenging.":[26],"Performance":[27,104],"portability":[28,52,132,142,197],"programming":[29],"models":[30,53],"such":[31],"as":[32,61,126,128],"RAJA,":[33],"Kokkos,":[34],"OpenMP":[36],"enable":[37],"codes":[38],"to":[39,118,149,182,203,211],"maintain":[40],"a":[41,85,92,108,129,157,177],"single-source":[42],"rather":[44],"than":[45],"rewriting":[46],"each":[48],"target":[49],"architecture.":[50],"However,":[51],"alone":[54],"will":[55],"not":[56],"result":[57],"in":[58,115],"optimal":[59],"hardware":[62],"has":[63],"varying":[64,76],"specifications":[65],"(e.g.,":[66],"cache":[67],"sizes":[68],"speeds)":[70],"parallel":[72],"algorithms":[73],"may":[74],"use":[75],"amounts":[77],"of":[78,88,95,111,180,192,214],"memory":[79,124,172],"compute":[81,136],"resources.":[82],"We":[83,100,155],"present":[84],"systematic":[86],"analysis":[87,125,159],"application":[89],"behaviors":[90],"across":[91,134,153,160],"set":[94,110],"CPU":[96],"GPU":[98,122,167],"hardware.":[99],"leverage":[101],"RAJA":[103],"Suite,":[105],"which":[106],"contains":[107],"curated":[109],"kernels":[112,175],"commonly":[113],"found":[114],"HPC":[116],"applications,":[117],"perform":[119],"an":[120],"in-depth":[121],"well":[127],"quantitative":[130],"evaluation":[133],"different":[135],"platforms.":[137,154],"In":[138],"analyzing":[139],"scores,":[143],"we":[144],"identify":[145],"gaps":[146],"opportunities":[148,207],"achieve":[150],"consistent":[151],"provide":[156],"comprehensive":[158],"seven":[161],"architectures,":[162],"including":[163],"most":[165],"recent":[166],"systems":[168],"with":[169],"physical":[171],"layouts,":[173],"where":[174,206],"demonstrate":[176],"runtime":[178],"speedup":[179,187],"up":[181],"44":[183],"\u00d7.":[184],"Although":[185],"highlights":[188],"baseline":[190],"improvements":[191],"newer":[193,216],"hardware,":[194],"scores":[198],"calculated,":[199],"ranging":[200],"from":[201],"0%":[202],"92%,":[204],"showcase":[205],"remain":[208],"scientists":[210],"increase":[212],"utilization":[213],"systems.":[217]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-12-21T00:00:00"}
