{"id":"https://openalex.org/W4288421628","doi":"https://doi.org/10.1145/3535508.3545591","title":"Performance portability study of epistasis detection using SYCL on NVIDIA GPU","display_name":"Performance portability study of epistasis detection using SYCL on NVIDIA GPU","publication_year":2022,"publication_date":"2022-07-28","ids":{"openalex":"https://openalex.org/W4288421628","doi":"https://doi.org/10.1145/3535508.3545591"},"language":"en","primary_location":{"id":"doi:10.1145/3535508.3545591","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3535508.3545591","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 13th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.osti.gov/servlets/purl/1883813","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101790023","display_name":"Zheming Jin","orcid":"https://orcid.org/0000-0002-7197-780X"},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zheming Jin","raw_affiliation_strings":["Oak Ridge National Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Oak Ridge National Laboratory","institution_ids":["https://openalex.org/I1289243028"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061838490","display_name":"Jeffrey S. Vetter","orcid":"https://orcid.org/0000-0002-2449-6720"},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jeffrey S. Vetter","raw_affiliation_strings":["Oak Ridge National Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Oak Ridge National Laboratory","institution_ids":["https://openalex.org/I1289243028"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.7753,"has_fulltext":true,"cited_by_count":20,"citation_normalized_percentile":{"value":0.91610981,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9879000186920166,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T11269","display_name":"Algorithms and Data Compression","score":0.9879000186920166,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9876999855041504,"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":0.9858999848365784,"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/cuda","display_name":"CUDA","score":0.9387699365615845},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7845989465713501},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6981281042098999},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.6277948021888733},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.5224977135658264},{"id":"https://openalex.org/keywords/software-portability","display_name":"Software portability","score":0.5181642770767212},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.49003517627716064},{"id":"https://openalex.org/keywords/loop-unrolling","display_name":"Loop unrolling","score":0.42300617694854736},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.21034780144691467},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.153466135263443},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1305614709854126}],"concepts":[{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.9387699365615845},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7845989465713501},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6981281042098999},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.6277948021888733},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.5224977135658264},{"id":"https://openalex.org/C63000827","wikidata":"https://www.wikidata.org/wiki/Q3080428","display_name":"Software portability","level":2,"score":0.5181642770767212},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.49003517627716064},{"id":"https://openalex.org/C76970557","wikidata":"https://www.wikidata.org/wiki/Q1869750","display_name":"Loop unrolling","level":3,"score":0.42300617694854736},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.21034780144691467},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.153466135263443},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1305614709854126},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3535508.3545591","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3535508.3545591","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 13th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics","raw_type":"proceedings-article"},{"id":"pmh:oai:osti.gov:1883813","is_oa":true,"landing_page_url":"https://www.osti.gov/biblio/1883813","pdf_url":"https://www.osti.gov/servlets/purl/1883813","source":{"id":"https://openalex.org/S4306402487","display_name":"OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I139351228","host_organization_name":"Office of Scientific and Technical Information","host_organization_lineage":["https://openalex.org/I139351228"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"pmh:oai:osti.gov:1883813","is_oa":true,"landing_page_url":"https://www.osti.gov/biblio/1883813","pdf_url":"https://www.osti.gov/servlets/purl/1883813","source":{"id":"https://openalex.org/S4306402487","display_name":"OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I139351228","host_organization_name":"Office of Scientific and Technical Information","host_organization_lineage":["https://openalex.org/I139351228"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.7599999904632568}],"awards":[{"id":"https://openalex.org/G1645119126","display_name":null,"funder_award_id":"AC05-00OR22725","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G4423657506","display_name":null,"funder_award_id":"AC05-00OR22725","funder_id":"https://openalex.org/F4320338287","funder_display_name":"Oak Ridge National Laboratory"},{"id":"https://openalex.org/G7995982022","display_name":null,"funder_award_id":"DE-AC05","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G8906985441","display_name":null,"funder_award_id":"00OR22725","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"}],"funders":[{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"},{"id":"https://openalex.org/F4320337506","display_name":"Advanced Scientific Computing Research","ror":"https://ror.org/0012c7r22"},{"id":"https://openalex.org/F4320338287","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4288421628.pdf"},"referenced_works_count":11,"referenced_works":["https://openalex.org/W599934088","https://openalex.org/W1558439203","https://openalex.org/W2015130320","https://openalex.org/W2016939324","https://openalex.org/W2080914619","https://openalex.org/W2739332150","https://openalex.org/W3046777110","https://openalex.org/W3209449653","https://openalex.org/W4224320534","https://openalex.org/W4225270014","https://openalex.org/W4225271295"],"related_works":["https://openalex.org/W3020739840","https://openalex.org/W2913998709","https://openalex.org/W2128640905","https://openalex.org/W2011460173","https://openalex.org/W2021092055","https://openalex.org/W4386875822","https://openalex.org/W3177128669","https://openalex.org/W1963859303","https://openalex.org/W2364044215","https://openalex.org/W2389600408"],"abstract_inverted_index":{"We":[0],"describe":[1],"the":[2,43,56,67,77,85,91,110,115,122,126],"experience":[3],"of":[4,9,35,58,76,104,117,125],"converting":[5],"a":[6,10,32],"CUDA":[7,39,44,86,129],"implementation":[8],"high-order":[11],"epistasis":[12],"detection":[13],"algorithm":[14],"to":[15,23,26,62,66,84],"SYCL.":[16,41],"The":[17,74,97],"goals":[18],"are":[19,131],"for":[20,70],"our":[21],"work":[22,94],"be":[24,63],"useful":[25],"application":[27],"and":[28,40,45,93,128],"compiler":[29],"developers":[30],"with":[31,102],"detailed":[33],"description":[34],"migration":[36],"paths":[37],"between":[38],"Evaluating":[42],"SYCL":[46,68,78,127],"applications":[47,130],"on":[48,90],"an":[49,82],"NVIDIA":[50],"V100":[51],"GPU,":[52],"we":[53],"find":[54],"that":[55],"optimization":[57],"loop":[59],"unrolling":[60],"needs":[61],"applied":[64],"manually":[65],"kernel":[69],"obtaining":[71],"comparable":[72],"performance.":[73],"performance":[75,124],"group":[79,95],"reduce":[80],"function,":[81],"alternative":[83],"warp-based":[87],"reduction,":[88],"depends":[89],"problem":[92],"sizes.":[96],"64-bit":[98],"popcount":[99,112],"operation":[100],"implemented":[101],"tree":[103],"adders":[105],"is":[106,120],"slightly":[107],"faster":[108],"than":[109],"built-in":[111],"operation.":[113],"When":[114],"number":[116],"OpenMP":[118],"threads":[119],"four,":[121],"highest":[123],"comparable.":[132]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":1}],"updated_date":"2026-06-17T08:01:34.144755","created_date":"2025-10-10T00:00:00"}