{"id":"https://openalex.org/W3031533177","doi":"https://doi.org/10.1145/3378678.3391885","title":"Efficient parallel reduction on GPUs with Hipacc","display_name":"Efficient parallel reduction on GPUs with Hipacc","publication_year":2020,"publication_date":"2020-05-25","ids":{"openalex":"https://openalex.org/W3031533177","doi":"https://doi.org/10.1145/3378678.3391885","mag":"3031533177"},"language":"en","primary_location":{"id":"doi:10.1145/3378678.3391885","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3378678.3391885","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 23th International Workshop on Software and Compilers for Embedded Systems","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/A5035954398","display_name":"Bo Qiao","orcid":"https://orcid.org/0000-0001-9644-0577"},"institutions":[{"id":"https://openalex.org/I181369854","display_name":"Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg","ror":"https://ror.org/00f7hpc57","country_code":"DE","type":"education","lineage":["https://openalex.org/I181369854"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Bo Qiao","raw_affiliation_strings":["Friedrich-Alexander University Erlangen-N\u00fcrnberg (FAU), Germany"],"affiliations":[{"raw_affiliation_string":"Friedrich-Alexander University Erlangen-N\u00fcrnberg (FAU), Germany","institution_ids":["https://openalex.org/I181369854"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051274212","display_name":"Oliver Reiche","orcid":"https://orcid.org/0000-0002-5125-4508"},"institutions":[{"id":"https://openalex.org/I4210153902","display_name":"Siemens Healthcare (Germany)","ror":"https://ror.org/0449c4c15","country_code":"DE","type":"company","lineage":["https://openalex.org/I4210153902"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Oliver Reiche","raw_affiliation_strings":["Siemens Healthineers AG, Erlangen, Germany"],"affiliations":[{"raw_affiliation_string":"Siemens Healthineers AG, Erlangen, Germany","institution_ids":["https://openalex.org/I4210153902"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061837918","display_name":"M. Akif \u00d6zkan","orcid":"https://orcid.org/0000-0001-5067-2268"},"institutions":[{"id":"https://openalex.org/I181369854","display_name":"Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg","ror":"https://ror.org/00f7hpc57","country_code":"DE","type":"education","lineage":["https://openalex.org/I181369854"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"M. Akif \u00d6zkan","raw_affiliation_strings":["Friedrich-Alexander University Erlangen-N\u00fcrnberg (FAU), Germany"],"affiliations":[{"raw_affiliation_string":"Friedrich-Alexander University Erlangen-N\u00fcrnberg (FAU), Germany","institution_ids":["https://openalex.org/I181369854"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076672029","display_name":"J\u00fcrgen Teich","orcid":"https://orcid.org/0000-0001-6285-5862"},"institutions":[{"id":"https://openalex.org/I181369854","display_name":"Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg","ror":"https://ror.org/00f7hpc57","country_code":"DE","type":"education","lineage":["https://openalex.org/I181369854"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"J\u00fcrgen Teich","raw_affiliation_strings":["Friedrich-Alexander University Erlangen-N\u00fcrnberg (FAU), Germany"],"affiliations":[{"raw_affiliation_string":"Friedrich-Alexander University Erlangen-N\u00fcrnberg (FAU), Germany","institution_ids":["https://openalex.org/I181369854"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072039340","display_name":"Frank Hannig","orcid":"https://orcid.org/0000-0003-3663-6484"},"institutions":[{"id":"https://openalex.org/I181369854","display_name":"Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg","ror":"https://ror.org/00f7hpc57","country_code":"DE","type":"education","lineage":["https://openalex.org/I181369854"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Frank Hannig","raw_affiliation_strings":["Friedrich-Alexander University Erlangen-N\u00fcrnberg (FAU), Germany"],"affiliations":[{"raw_affiliation_string":"Friedrich-Alexander University Erlangen-N\u00fcrnberg (FAU), Germany","institution_ids":["https://openalex.org/I181369854"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5035954398"],"corresponding_institution_ids":["https://openalex.org/I181369854"],"apc_list":null,"apc_paid":null,"fwci":0.0977,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.37579821,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":93},"biblio":{"volume":null,"issue":null,"first_page":"58","last_page":"61"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9980000257492065,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9980000257492065,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9958999752998352,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10531","display_name":"Advanced Vision and Imaging","score":0.9941999912261963,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/speedup","display_name":"Speedup","score":0.9000744819641113},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8556704521179199},{"id":"https://openalex.org/keywords/porting","display_name":"Porting","score":0.8295807242393494},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5731036067008972},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.5359118580818176},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.483692467212677},{"id":"https://openalex.org/keywords/instruction-set","display_name":"Instruction set","score":0.4243597984313965},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.3960868716239929},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.286685585975647},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1756102740764618}],"concepts":[{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.9000744819641113},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8556704521179199},{"id":"https://openalex.org/C106251023","wikidata":"https://www.wikidata.org/wiki/Q851989","display_name":"Porting","level":3,"score":0.8295807242393494},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5731036067008972},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.5359118580818176},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.483692467212677},{"id":"https://openalex.org/C202491316","wikidata":"https://www.wikidata.org/wiki/Q272683","display_name":"Instruction set","level":2,"score":0.4243597984313965},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.3960868716239929},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.286685585975647},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1756102740764618},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3378678.3391885","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3378678.3391885","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 23th International Workshop on Software and Compilers for Embedded Systems","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.44999998807907104,"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W631225344","https://openalex.org/W1480958225","https://openalex.org/W2055312318","https://openalex.org/W2075745057","https://openalex.org/W2086105136","https://openalex.org/W2113841249","https://openalex.org/W2808498336","https://openalex.org/W2901549770","https://openalex.org/W3006830071","https://openalex.org/W3104528661","https://openalex.org/W4244917406","https://openalex.org/W4250027548","https://openalex.org/W4255653201","https://openalex.org/W6676674358"],"related_works":["https://openalex.org/W1662038552","https://openalex.org/W3021568819","https://openalex.org/W2045177269","https://openalex.org/W2116582200","https://openalex.org/W1580752477","https://openalex.org/W1998013902","https://openalex.org/W2061453039","https://openalex.org/W2550108858","https://openalex.org/W1781968824","https://openalex.org/W4247993032"],"abstract_inverted_index":{"Hipacc":[0,118],"is":[1,44],"a":[2,109,125],"domain-specific":[3],"language":[4],"for":[5,28,94],"ease":[6],"of":[7,22,33,53,86,111,127],"programming":[8],"image":[9,42,59],"processing":[10,43],"applications":[11],"on":[12,74],"hardware":[13,27,92],"accelerators":[14],"such":[15],"as":[16],"GPUs.":[17],"It":[18],"relieves":[19],"the":[20,31,50,83,98,135],"burden":[21],"manually":[23],"porting":[24],"algorithms":[25],"to":[26,70,113,129],"developers":[29],"with":[30,76,120],"help":[32],"domain-":[34],"and":[35,88,124],"architecture-specific":[36],"knowledge.":[37],"One":[38],"fundamental":[39],"operation":[40],"in":[41],"reduction.":[45],"Global":[46],"reduction":[47],"operators":[48],"are":[49],"building":[51],"blocks":[52],"many":[54],"widely":[55],"used":[56],"algorithms,":[57],"including":[58],"normalization,":[60],"similarity":[61],"estimation,":[62],"etc.":[63],"This":[64],"paper":[65],"presents":[66],"an":[67,116,132],"efficient":[68],"approach":[69,80,107],"perform":[71],"parallel":[72],"reductions":[73],"GPUs":[75],"Hipacc.":[77],"Our":[78],"proposed":[79],"benefits":[81],"from":[82,102,138],"continuous":[84],"effort":[85],"performance":[87],"programmability":[89],"improvement":[90],"by":[91,96],"vendors,":[93],"example,":[95],"utilizing":[97],"latest":[99],"low-level":[100],"primitives":[101],"Nvidia.":[103,139],"Results":[104],"show":[105],"our":[106],"achieves":[108],"speedup":[110,126],"up":[112,128],"3.43":[114],"over":[115,131],"existing":[117],"implementation":[119,133],"traditional":[121],"optimization":[122],"methods,":[123],"9.02":[130],"using":[134],"Thrust":[136],"library":[137]},"counts_by_year":[{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
