{"id":"https://openalex.org/W3203828302","doi":"https://doi.org/10.1145/3458744.3473360","title":"Evaluating the Performance of Integer Sum Reduction in SYCL on GPUs","display_name":"Evaluating the Performance of Integer Sum Reduction in SYCL on GPUs","publication_year":2021,"publication_date":"2021-08-09","ids":{"openalex":"https://openalex.org/W3203828302","doi":"https://doi.org/10.1145/3458744.3473360","mag":"3203828302"},"language":"en","primary_location":{"id":"doi:10.1145/3458744.3473360","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3458744.3473360","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"50th International Conference on Parallel Processing Workshop","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/1840191","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, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Oak Ridge National Laboratory, USA","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 Vetter","raw_affiliation_strings":["Oak Ridge National Laboratory, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Oak Ridge National Laboratory, USA","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":0.7079,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.68223583,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9994000196456909,"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":0.9994000196456909,"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/T10682","display_name":"Quantum Computing Algorithms and Architecture","score":0.996999979019165,"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/T12808","display_name":"Ferroelectric and Negative Capacitance Devices","score":0.9965000152587891,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.8060652017593384},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7164270877838135},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6994072198867798},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.6004290580749512},{"id":"https://openalex.org/keywords/implementation","display_name":"Implementation","score":0.5087142586708069},{"id":"https://openalex.org/keywords/parameterized-complexity","display_name":"Parameterized complexity","score":0.48498889803886414},{"id":"https://openalex.org/keywords/integer","display_name":"Integer (computer science)","score":0.4514145851135254},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.3532022535800934},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.24601981043815613},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.17763984203338623},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.16469520330429077},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.08470961451530457}],"concepts":[{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.8060652017593384},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7164270877838135},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6994072198867798},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.6004290580749512},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.5087142586708069},{"id":"https://openalex.org/C165464430","wikidata":"https://www.wikidata.org/wiki/Q1570441","display_name":"Parameterized complexity","level":2,"score":0.48498889803886414},{"id":"https://openalex.org/C97137487","wikidata":"https://www.wikidata.org/wiki/Q729138","display_name":"Integer (computer science)","level":2,"score":0.4514145851135254},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.3532022535800934},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.24601981043815613},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.17763984203338623},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.16469520330429077},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.08470961451530457},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3458744.3473360","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3458744.3473360","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"50th International Conference on Parallel Processing Workshop","raw_type":"proceedings-article"},{"id":"pmh:oai:osti.gov:1840191","is_oa":true,"landing_page_url":"https://www.osti.gov/biblio/1840191","pdf_url":"https://www.osti.gov/servlets/purl/1840191","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:1840191","is_oa":true,"landing_page_url":"https://www.osti.gov/biblio/1840191","pdf_url":"https://www.osti.gov/servlets/purl/1840191","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":[{"display_name":"Affordable and clean energy","score":0.4099999964237213,"id":"https://metadata.un.org/sdg/7"}],"awards":[{"id":"https://openalex.org/G1489425746","display_name":null,"funder_award_id":"DE-AC05-00OR22725","funder_id":"https://openalex.org/F4320332359","funder_display_name":"Office of Science"},{"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/G8269158468","display_name":null,"funder_award_id":"AC05-00OR22725","funder_id":"https://openalex.org/F4320332359","funder_display_name":"Office of Science"},{"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/F4320332359","display_name":"Office of Science","ror":"https://ror.org/00mmn6b08"},{"id":"https://openalex.org/F4320338287","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3203828302.pdf","grobid_xml":"https://content.openalex.org/works/W3203828302.grobid-xml"},"referenced_works_count":12,"referenced_works":["https://openalex.org/W1480958225","https://openalex.org/W1984222112","https://openalex.org/W2016939324","https://openalex.org/W2052863973","https://openalex.org/W2613143750","https://openalex.org/W2802647233","https://openalex.org/W2913998709","https://openalex.org/W2998114460","https://openalex.org/W3011794212","https://openalex.org/W3013081263","https://openalex.org/W3110372091","https://openalex.org/W4235158490"],"related_works":["https://openalex.org/W2058965144","https://openalex.org/W2164382479","https://openalex.org/W2146343568","https://openalex.org/W98480971","https://openalex.org/W2150291671","https://openalex.org/W2013643406","https://openalex.org/W2027972911","https://openalex.org/W2157978810","https://openalex.org/W2051058708","https://openalex.org/W1500978221"],"abstract_inverted_index":{"SYCL":[0,37,61,82,98,124],"is":[1,25,100,126],"a":[2,9,26,71],"promising":[3],"programming":[4],"model":[5],"for":[6,29],"heterogeneous":[7],"computing\u2014allowing":[8],"single-source":[10],"code":[11],"to":[12],"target":[13],"devices":[14],"from":[15],"multiple":[16],"vendors.":[17],"One":[18],"significant":[19],"task":[20],"performed":[21],"on":[22,91,118,144],"these":[23],"accelerators":[24],"primitive":[27],"operation":[28],"integer":[30,40],"sum":[31,41],"reduction.":[32,69],"This":[33],"paper":[34],"presents":[35],"several":[36],"implementations":[38,65,83,90],"of":[39,60,66,75,80],"reduction\u2014using":[42],"atomic":[43],"functions,":[44],"shared":[45],"local":[46],"memory,":[47],"vectorized":[48],"memory":[49],"accesses":[50],"and":[51,58,109,135],"parameterized":[52],"workload":[53],"sizes\u2014to":[54],"compare":[55],"the":[56,67,78,88,104,113,130,139],"performance":[57],"maturity":[59],"against":[62],"open-source":[63,89],"vendor-specific":[64],"same":[68],"For":[70],"sufficiently":[72],"large":[73],"number":[74],"integers,":[76],"tuning":[77],"parameters":[79],"our":[81],"achieves":[84],"1.4X":[85],"speedup":[86],"over":[87],"an":[92,119,145],"Intel":[93],"UHD630":[94],"integrated":[95],"GPU.":[96,122,148],"The":[97,123],"reduction":[99,106,115,125,132,141],"3%":[101],"faster":[102,111,128,137],"than":[103,112,129,138],"templated":[105,131],"in":[107,116,133,142],"Thrust,":[108,134],"0.3%":[110],"device":[114,140],"CUB":[117,143],"Nvidia":[120,146],"P100":[121],"1.9%":[127],"0.4%":[136],"V100":[147]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":2}],"updated_date":"2026-06-17T08:01:34.144755","created_date":"2025-10-10T00:00:00"}