{"id":"https://openalex.org/W4386519283","doi":"https://doi.org/10.1145/3605731.3605907","title":"Mapping-Free GPU Offloading in OpenMP Using Unified Memory","display_name":"Mapping-Free GPU Offloading in OpenMP Using Unified Memory","publication_year":2023,"publication_date":"2023-08-07","ids":{"openalex":"https://openalex.org/W4386519283","doi":"https://doi.org/10.1145/3605731.3605907"},"language":"en","primary_location":{"id":"doi:10.1145/3605731.3605907","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1145/3605731.3605907","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 52nd International Conference on Parallel Processing Workshops","raw_type":"proceedings-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/A5103066312","display_name":"Jia-Sian Hong","orcid":"https://orcid.org/0009-0004-5080-2295"},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Jia-Sian Hong","raw_affiliation_strings":["Department of Computer Science, National Yang Ming Chiao Tung University, Taiwan"],"raw_orcid":"https://orcid.org/0009-0004-5080-2295","affiliations":[{"raw_affiliation_string":"Department of Computer Science, National Yang Ming Chiao Tung University, Taiwan","institution_ids":["https://openalex.org/I148366613"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5059393275","display_name":"Yi\u2010Ping You","orcid":"https://orcid.org/0000-0002-4455-3147"},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yi-Ping You","raw_affiliation_strings":["Department of Computer Science, National Yang Ming Chiao Tung University, Taiwan"],"raw_orcid":"https://orcid.org/0000-0002-4455-3147","affiliations":[{"raw_affiliation_string":"Department of Computer Science, National Yang Ming Chiao Tung University, Taiwan","institution_ids":["https://openalex.org/I148366613"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5103066312"],"corresponding_institution_ids":["https://openalex.org/I148366613"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.1249619,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"104","last_page":"111"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":1.0,"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":1.0,"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":0.9983999729156494,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9976999759674072,"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":0.7905669212341309},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.765608549118042},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.45118221640586853},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.3345283269882202}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7905669212341309},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.765608549118042},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.45118221640586853},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.3345283269882202}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3605731.3605907","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1145/3605731.3605907","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 52nd International Conference on Parallel Processing Workshops","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":2,"referenced_works":["https://openalex.org/W2080592089","https://openalex.org/W2767028519"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W4402327032"],"abstract_inverted_index":{"With":[0],"the":[1,34,53,65,77,82,85,104,107,132,159,163,170,177,194],"increasing":[2],"demand":[3],"for":[4,91,172,198,234,246],"heterogeneous":[5],"computing,":[6],"OpenMP":[7,50,68,133,224],"has":[8,70],"introduced":[9],"an":[10,27,229,241],"offloading":[11],"feature":[12],"that":[13,59,211,236],"allows":[14],"programmers":[15,56,92],"to":[16,20,33,40,57,93,97,124,141,157,189,221],"offload":[17,222],"a":[18,21,24,71,149],"task":[19,35],"device":[22],"(e.g.,":[23],"GPU":[25],"or":[26],"FPGA)":[28],"by":[29],"adding":[30],"appropriate":[31],"directives":[32,96,174],"since":[36],"version":[37],"4.0.":[38],"Compared":[39],"other":[41],"low-level":[42],"programming":[43],"models,":[44],"such":[45,114],"as":[46,115,193],"CUDA":[47,164],"and":[48,84,106,118,127,151,175,205,240],"OpenCL,":[49],"significantly":[51],"reduces":[52,176],"burden":[54,217],"on":[55,64],"ensure":[58],"tasks":[60],"are":[61,101],"performed":[62],"correctly":[63],"device.":[66,86,108],"However,":[67],"still":[69,89],"data-mapping":[72,95,129,142,160,173,181,220],"problem,":[73],"which":[74],"arises":[75],"from":[76],"separate":[78],"memory":[79,166,192,196],"spaces":[80],"between":[81,103],"host":[83,105,200],"It":[87],"is":[88,188],"necessary":[90],"specify":[94],"indicate":[98],"how":[99],"data":[100,112],"transferred":[102],"When":[109],"using":[110],"complex":[111],"structures":[113],"linked":[116],"lists":[117],"graphs,":[119],"it":[120],"becomes":[121],"more":[122],"difficult":[123],"compose":[125],"reliable":[126],"efficient":[128],"directives.":[130],"Moreover,":[131],"runtime":[134,152],"library":[135],"may":[136],"incur":[137],"substantial":[138],"overhead":[139,178],"due":[140],"management.":[143,182],"In":[144],"this":[145],"paper,":[146],"we":[147],"propose":[148],"compiler":[150],"collaborative":[153],"framework,":[154],"called":[155],"OpenMP-UM,":[156],"address":[158],"problem.":[161],"Using":[162],"unified":[165,191],"mechanism,":[167],"OpenMP-UM":[168,187,212],"eliminates":[169],"need":[171],"associated":[179],"with":[180],"The":[183],"key":[184],"concept":[185],"behind":[186],"use":[190],"default":[195],"storage":[197],"all":[199],"data,":[201],"including":[202],"automatic,":[203],"static,":[204],"dynamic":[206],"data.":[207],"Experiments":[208],"have":[209],"demonstrated":[210],"not":[213],"only":[214],"removed":[215],"programmers\u2019":[216],"in":[218,223],"writing":[219],"applications":[225,235],"but":[226],"also":[227],"achieved":[228],"average":[230,242],"of":[231,243],"7.3x":[232],"speedup":[233,245],"involve":[237],"deep":[238],"copies":[239],"1.02x":[244],"regular":[247],"applications.":[248]},"counts_by_year":[],"updated_date":"2025-12-25T23:11:45.687758","created_date":"2025-10-10T00:00:00"}