{"id":"https://openalex.org/W4386528956","doi":"https://doi.org/10.1145/3605731.3606016","title":"Maximizing Parallelism and GPU Utilization For Direct GPU Compilation Through Ensemble Execution","display_name":"Maximizing Parallelism and GPU Utilization For Direct GPU Compilation Through Ensemble Execution","publication_year":2023,"publication_date":"2023-08-07","ids":{"openalex":"https://openalex.org/W4386528956","doi":"https://doi.org/10.1145/3605731.3606016"},"language":"en","primary_location":{"id":"doi:10.1145/3605731.3606016","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1145/3605731.3606016","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":true,"oa_status":"green","oa_url":"https://www.osti.gov/biblio/1994027","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5083617935","display_name":"Shilei Tian","orcid":"https://orcid.org/0000-0001-6468-6839"},"institutions":[{"id":"https://openalex.org/I59553526","display_name":"Stony Brook University","ror":"https://ror.org/05qghxh33","country_code":"US","type":"education","lineage":["https://openalex.org/I59553526"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Shilei Tian","raw_affiliation_strings":["Stony Brook University, USA"],"raw_orcid":"https://orcid.org/0000-0001-6468-6839","affiliations":[{"raw_affiliation_string":"Stony Brook University, USA","institution_ids":["https://openalex.org/I59553526"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053733660","display_name":"Barbara Chapman","orcid":"https://orcid.org/0000-0001-8449-8579"},"institutions":[{"id":"https://openalex.org/I59553526","display_name":"Stony Brook University","ror":"https://ror.org/05qghxh33","country_code":"US","type":"education","lineage":["https://openalex.org/I59553526"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Barbara Chapman","raw_affiliation_strings":["Stony Brook University, USA"],"raw_orcid":"https://orcid.org/0000-0001-8449-8579","affiliations":[{"raw_affiliation_string":"Stony Brook University, USA","institution_ids":["https://openalex.org/I59553526"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032645176","display_name":"Johannes Doerfert","orcid":"https://orcid.org/0000-0001-7870-8963"},"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":"Johannes Doerfert","raw_affiliation_strings":["Lawrence Livermore National Laboratory, USA"],"raw_orcid":"https://orcid.org/0000-0001-7870-8963","affiliations":[{"raw_affiliation_string":"Lawrence Livermore National Laboratory, USA","institution_ids":["https://openalex.org/I1282311441"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5083617935"],"corresponding_institution_ids":["https://openalex.org/I59553526"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.12541908,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"112","last_page":"118"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9986000061035156,"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":0.9980999827384949,"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":0.9030399322509766},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7744256258010864},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.5363688468933105},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.5082128047943115},{"id":"https://openalex.org/keywords/thread","display_name":"Thread (computing)","score":0.47933587431907654},{"id":"https://openalex.org/keywords/parallelism","display_name":"Parallelism (grammar)","score":0.46880748867988586},{"id":"https://openalex.org/keywords/synchronization","display_name":"Synchronization (alternating current)","score":0.46821287274360657},{"id":"https://openalex.org/keywords/data-parallelism","display_name":"Data parallelism","score":0.4584803581237793},{"id":"https://openalex.org/keywords/task-parallelism","display_name":"Task parallelism","score":0.443888783454895},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.4193165600299835},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.22765526175498962},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.1652548909187317},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.09174588322639465}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9030399322509766},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7744256258010864},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.5363688468933105},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.5082128047943115},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.47933587431907654},{"id":"https://openalex.org/C2781172179","wikidata":"https://www.wikidata.org/wiki/Q853109","display_name":"Parallelism (grammar)","level":2,"score":0.46880748867988586},{"id":"https://openalex.org/C2778562939","wikidata":"https://www.wikidata.org/wiki/Q1298791","display_name":"Synchronization (alternating current)","level":3,"score":0.46821287274360657},{"id":"https://openalex.org/C61483411","wikidata":"https://www.wikidata.org/wiki/Q3124522","display_name":"Data parallelism","level":3,"score":0.4584803581237793},{"id":"https://openalex.org/C42992933","wikidata":"https://www.wikidata.org/wiki/Q691169","display_name":"Task parallelism","level":3,"score":0.443888783454895},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4193165600299835},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.22765526175498962},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.1652548909187317},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.09174588322639465},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3605731.3606016","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1145/3605731.3606016","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"},{"id":"pmh:oai:osti.gov:1994027","is_oa":true,"landing_page_url":"https://www.osti.gov/biblio/1994027","pdf_url":null,"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:1994027","is_oa":true,"landing_page_url":"https://www.osti.gov/biblio/1994027","pdf_url":null,"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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W583100948","https://openalex.org/W1968197401","https://openalex.org/W2019143817","https://openalex.org/W2042381780","https://openalex.org/W2127510911","https://openalex.org/W2180288011","https://openalex.org/W2296687957","https://openalex.org/W2898134157","https://openalex.org/W2912825911","https://openalex.org/W2963104418","https://openalex.org/W2964971560","https://openalex.org/W2969535219","https://openalex.org/W2969953515","https://openalex.org/W2996929894","https://openalex.org/W3098098342","https://openalex.org/W3099814709","https://openalex.org/W3154968648","https://openalex.org/W3164974885","https://openalex.org/W3167401864","https://openalex.org/W3197725231","https://openalex.org/W3208752547","https://openalex.org/W4213291706","https://openalex.org/W4221061044","https://openalex.org/W4221128531","https://openalex.org/W4234180294","https://openalex.org/W4235762625","https://openalex.org/W4285429071","https://openalex.org/W4318603192","https://openalex.org/W4386268984"],"related_works":["https://openalex.org/W2950520577","https://openalex.org/W1501159154","https://openalex.org/W2003935582","https://openalex.org/W74409296","https://openalex.org/W1554644772","https://openalex.org/W2494130044","https://openalex.org/W2468095077","https://openalex.org/W29548032","https://openalex.org/W2593878938","https://openalex.org/W305742777"],"abstract_inverted_index":{"GPUs":[0,15],"are":[1],"renowned":[2],"for":[3,16,25,63,71],"their":[4],"exceptional":[5],"computational":[6],"acceleration":[7,45],"capabilities":[8],"achieved":[9],"through":[10],"massive":[11],"parallelism.":[12],"However,":[13,75],"utilizing":[14],"computation":[17],"requires":[18],"manual":[19],"identification":[20],"of":[21],"code":[22],"regions":[23],"suitable":[24],"offloading,":[26],"data":[27],"transfer":[28],"management,":[29],"and":[30],"synchronization.":[31],"Recent":[32],"advancements":[33],"have":[34],"capitalized":[35],"on":[36,65],"the":[37,53,59,66,69,82],"LLVM/OpenMP":[38],"portable":[39],"target":[40],"offloading":[41,73],"interface,":[42],"elevating":[43],"GPU":[44,55,77],"to":[46,81,94],"new":[47],"heights.":[48],"This":[49],"approach,":[50],"known":[51],"as":[52],"direct":[54,76],"compilation,":[56],"involves":[57],"compiling":[58],"entire":[60],"host":[61],"application":[62,87],"execution":[64],"GPU,":[67],"eliminating":[68],"need":[70],"explicit":[72],"directives.":[74],"compilation":[78],"is":[79,90],"limited":[80],"thread":[83],"parallelism":[84],"a":[85,96],"CPU":[86],"exposes,":[88],"which":[89],"often":[91],"not":[92],"enough":[93],"saturate":[95],"modern":[97],"GPU.":[98]},"counts_by_year":[],"updated_date":"2025-12-25T23:11:45.687758","created_date":"2025-10-10T00:00:00"}
