{"id":"https://openalex.org/W4289522463","doi":"https://doi.org/10.1145/3554736","title":"COX : Exposing CUDA Warp-level Functions to CPUs","display_name":"COX : Exposing CUDA Warp-level Functions to CPUs","publication_year":2022,"publication_date":"2022-08-02","ids":{"openalex":"https://openalex.org/W4289522463","doi":"https://doi.org/10.1145/3554736"},"language":"en","primary_location":{"id":"doi:10.1145/3554736","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3554736","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3554736","source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Architecture and Code Optimization","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3554736","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5045920192","display_name":"Ruobing Han","orcid":"https://orcid.org/0000-0002-3090-3951"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ruobing Han","raw_affiliation_strings":["Georgia Institute of Technology, North Avenue Atlanta, GA , USA"],"raw_orcid":"https://orcid.org/0000-0002-3090-3951","affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology, North Avenue Atlanta, GA , USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100329194","display_name":"Jaewon Lee","orcid":"https://orcid.org/0000-0002-0768-384X"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jaewon Lee","raw_affiliation_strings":["Georgia Institute of Technology, North Avenue Atlanta, GA , USA"],"raw_orcid":"https://orcid.org/0000-0002-0768-384X","affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology, North Avenue Atlanta, GA , USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004251886","display_name":"Jaewoong Sim","orcid":"https://orcid.org/0000-0002-0403-9928"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jaewoong Sim","raw_affiliation_strings":["Seoul National University, Gwanak-gu, Seoul, South Korea"],"raw_orcid":"https://orcid.org/0000-0002-0403-9928","affiliations":[{"raw_affiliation_string":"Seoul National University, Gwanak-gu, Seoul, South Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5000822269","display_name":"Hyesoon Kim","orcid":"https://orcid.org/0000-0002-6061-7825"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hyesoon Kim","raw_affiliation_strings":["Georgia Institute of Technology, North Avenue Atlanta, GA , USA"],"raw_orcid":"https://orcid.org/0000-0002-6061-7825","affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology, North Avenue Atlanta, GA , USA","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.2167,"has_fulltext":true,"cited_by_count":13,"citation_normalized_percentile":{"value":0.87316422,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":"19","issue":"4","first_page":"1","last_page":"25"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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":0.998199999332428,"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":0.9965999722480774,"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/cuda","display_name":"CUDA","score":0.9863115549087524},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.841839075088501},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7312377691268921},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.598605751991272},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5478026270866394},{"id":"https://openalex.org/keywords/coprocessor","display_name":"Coprocessor","score":0.4209626615047455},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.22806581854820251},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.21205464005470276},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1741289496421814}],"concepts":[{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.9863115549087524},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.841839075088501},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7312377691268921},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.598605751991272},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5478026270866394},{"id":"https://openalex.org/C86111242","wikidata":"https://www.wikidata.org/wiki/Q859595","display_name":"Coprocessor","level":2,"score":0.4209626615047455},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.22806581854820251},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.21205464005470276},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1741289496421814},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3554736","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3554736","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3554736","source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Architecture and Code Optimization","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/3554736","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3554736","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3554736","source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Architecture and Code Optimization","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G671461575","display_name":"CCRI: Medium: Rogues Gallery: A Community Research Infrastructure for Post-Moore Computing","funder_award_id":"2016701","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4289522463.pdf","grobid_xml":"https://content.openalex.org/works/W4289522463.grobid-xml"},"referenced_works_count":38,"referenced_works":["https://openalex.org/W38257615","https://openalex.org/W110609005","https://openalex.org/W1502558230","https://openalex.org/W1597968260","https://openalex.org/W1975274780","https://openalex.org/W1988826338","https://openalex.org/W1991592471","https://openalex.org/W2010936531","https://openalex.org/W2013156670","https://openalex.org/W2028914809","https://openalex.org/W2051260099","https://openalex.org/W2052863973","https://openalex.org/W2055813380","https://openalex.org/W2059654835","https://openalex.org/W2067635581","https://openalex.org/W2080592089","https://openalex.org/W2090268225","https://openalex.org/W2124556751","https://openalex.org/W2128046183","https://openalex.org/W2157729530","https://openalex.org/W2399715892","https://openalex.org/W2528784626","https://openalex.org/W2600258283","https://openalex.org/W2613143750","https://openalex.org/W2616928384","https://openalex.org/W2765425776","https://openalex.org/W2794160862","https://openalex.org/W2913998709","https://openalex.org/W3017538311","https://openalex.org/W3021447659","https://openalex.org/W3032789239","https://openalex.org/W3097652614","https://openalex.org/W3149591378","https://openalex.org/W3160498990","https://openalex.org/W3198679967","https://openalex.org/W3204255478","https://openalex.org/W4298883496","https://openalex.org/W6635694052"],"related_works":["https://openalex.org/W1978663335","https://openalex.org/W2539329681","https://openalex.org/W2794923745","https://openalex.org/W2011840458","https://openalex.org/W189420351","https://openalex.org/W1977987009","https://openalex.org/W2144511445","https://openalex.org/W2123859042","https://openalex.org/W4231288671","https://openalex.org/W4296337698"],"abstract_inverted_index":{"As":[0],"CUDA":[1,21,36,65,82,98,119,134],"becomes":[2,25],"the":[3,48,50,63,69,73,79,81,123,151],"de":[4],"facto":[5],"programming":[6,66,74],"language":[7],"among":[8],"data":[9],"parallel":[10],"applications":[11,157],"such":[12],"as":[13],"high-performance":[14],"computing":[15],"or":[16,169],"machine":[17],"learning":[18],"applications,":[19],"running":[20],"on":[22,37,101,122,140],"other":[23,39],"platforms":[24],"a":[26,54,112],"compelling":[27],"option.":[28],"Although":[29],"several":[30],"efforts":[31],"have":[32],"attempted":[33],"to":[34,44,87],"support":[35,51],"devices":[38],"than":[40,144,173],"NVIDIA":[41],"GPUs,":[42],"due":[43],"extra":[45],"steps":[46],"in":[47,72,133,176],"translation,":[49],"is":[52,103],"always":[53],"few":[55],"years":[56],"behind":[57],"CUDA\u2019s":[58],"latest":[59],"features.":[60],"In":[61,90],"particular,":[62],"new":[64],"model":[67],"exposes":[68],"warp":[70],"concept":[71],"language,":[75],"which":[76],"greatly":[77],"changes":[78],"way":[80],"code":[83,121],"should":[84],"be":[85,138],"mapped":[86],"CPU":[88,124,165],"programs.":[89],"this":[91],"article,":[92],"hierarchical":[93,107,127,161],"collapsing":[94,108,128,162],"that":[95,116,160],"correctly":[96],"supports":[97,117],"warp-level":[99],"functions":[100],"CPUs":[102],"proposed.":[104],"To":[105],"verify":[106],",":[109,115,129],"we":[110],"build":[111],"framework,":[113],"COX":[114],"executing":[118],"source":[120],"backend.":[125],"With":[126],"90%":[130],"of":[131],"kernels":[132],"SDK":[135],"samples":[136],"can":[137,163],"executed":[139],"CPUs,":[141],"much":[142],"higher":[143,171],"previous":[145,174],"works":[146],"(68%).":[147],"We":[148],"also":[149],"evaluate":[150],"performance":[152,172],"with":[153,167],"benchmarks":[154],"for":[155],"real":[156],"and":[158],"show":[159],"generate":[164],"programs":[166],"comparable":[168],"even":[170],"projects":[175],"general.":[177]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":3}],"updated_date":"2026-08-12T21:12:35.861297","created_date":"2025-10-10T00:00:00"}