{"id":"https://openalex.org/W2954922220","doi":"https://doi.org/10.1145/3318170.3318178","title":"Exploring Integer Sum Reduction using Atomics on Intel CPU","display_name":"Exploring Integer Sum Reduction using Atomics on Intel CPU","publication_year":2019,"publication_date":"2019-05-13","ids":{"openalex":"https://openalex.org/W2954922220","doi":"https://doi.org/10.1145/3318170.3318178","mag":"2954922220"},"language":"en","primary_location":{"id":"doi:10.1145/3318170.3318178","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3318170.3318178","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Workshop on OpenCL","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/A5101790023","display_name":"Zheming Jin","orcid":"https://orcid.org/0000-0002-7197-780X"},"institutions":[{"id":"https://openalex.org/I1282105669","display_name":"Argonne National Laboratory","ror":"https://ror.org/05gvnxz63","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282105669","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zheming Jin","raw_affiliation_strings":["Argonne National Laboratory, Argonne, IL, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Argonne National Laboratory, Argonne, IL, USA","institution_ids":["https://openalex.org/I1282105669"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050512119","display_name":"Hal Finkel","orcid":"https://orcid.org/0000-0002-7551-7122"},"institutions":[{"id":"https://openalex.org/I1282105669","display_name":"Argonne National Laboratory","ror":"https://ror.org/05gvnxz63","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282105669","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hal Finkel","raw_affiliation_strings":["Argonne National Laboratory, Argonne, IL, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Argonne National Laboratory, Argonne, IL, USA","institution_ids":["https://openalex.org/I1282105669"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2468,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.48911117,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"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":0.9987999796867371,"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/T10772","display_name":"Distributed systems and fault tolerance","score":0.9976000189781189,"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":0.8081415891647339},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7919881343841553},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.7130272388458252},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.6394856572151184},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.6090512275695801},{"id":"https://openalex.org/keywords/shared-memory","display_name":"Shared memory","score":0.508396565914154},{"id":"https://openalex.org/keywords/vendor","display_name":"Vendor","score":0.4866545796394348},{"id":"https://openalex.org/keywords/vectorization","display_name":"Vectorization (mathematics)","score":0.4546357989311218},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11987292766571045}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8081415891647339},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7919881343841553},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.7130272388458252},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.6394856572151184},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.6090512275695801},{"id":"https://openalex.org/C133875982","wikidata":"https://www.wikidata.org/wiki/Q764810","display_name":"Shared memory","level":2,"score":0.508396565914154},{"id":"https://openalex.org/C2777338717","wikidata":"https://www.wikidata.org/wiki/Q1762621","display_name":"Vendor","level":2,"score":0.4866545796394348},{"id":"https://openalex.org/C41681595","wikidata":"https://www.wikidata.org/wiki/Q7917855","display_name":"Vectorization (mathematics)","level":2,"score":0.4546357989311218},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11987292766571045},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3318170.3318178","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3318170.3318178","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Workshop on OpenCL","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W1906046253","https://openalex.org/W1984222112","https://openalex.org/W2086105136","https://openalex.org/W2117689653","https://openalex.org/W2140861996","https://openalex.org/W2157729530","https://openalex.org/W2159392969","https://openalex.org/W2260448916","https://openalex.org/W2802381594","https://openalex.org/W2885127949","https://openalex.org/W2886641760","https://openalex.org/W2894663577","https://openalex.org/W4235158490","https://openalex.org/W6636711802"],"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/W4391547476","https://openalex.org/W2597809628"],"abstract_inverted_index":{"Atomic":[0],"functions":[1],"are":[2],"useful":[3],"in":[4,65],"updating":[5],"a":[6,36,51,87,93,121,189],"shared":[7],"variable":[8],"by":[9],"multiple":[10],"threads,":[11],"barrier":[12],"synchronizations,":[13],"constructing":[14],"complex":[15],"data":[16,38],"structures,":[17],"and":[18,30,61,90],"building":[19],"high-level":[20],"frameworks.":[21],"In":[22],"this":[23],"paper,":[24],"we":[25,67],"focus":[26],"on":[27,50],"the":[28,43,55,58,62,73,114,117,128,133,141,150,154,159,167,177,181,184],"evaluation":[29],"analysis":[31],"of":[32,75,116,124,162,192],"integer":[33],"sum":[34,105],"reduction,":[35,66],"common":[37],"parallel":[39,47],"primitive.":[40],"We":[41,137,175],"convert":[42],"sequential":[44],"reduction":[45,106],"into":[46],"OpenCL":[48,144],"implementations":[49],"CPU.":[52],"To":[53],"understand":[54],"relationships":[56],"between":[57],"kernel":[59,107,119,145,151,186],"performance":[60,115,160,178],"operations":[63],"involved":[64],"develop":[68],"three":[69],"microkernels":[70],"that":[71,140,183],"show":[72],"costs":[74],"one":[76,83,99],"atomic":[77,100],"addition":[78,101],"to":[79,95,173,180],"global":[80],"memory":[81,97,110],"from":[82,171],"work-item":[84],"per":[85,102],"work-group,":[86],"work-group":[88,94,125,135],"barrier,":[89],"reducing":[91],"within":[92],"local":[96],"using":[98],"work-item.":[103],"The":[104],"with":[108,132],"vectorized":[109],"accesses":[111],"can":[112],"improve":[113,149],"baseline":[118],"for":[120],"wide":[122],"range":[123],"sizes.":[126],"However,":[127],"vectorization":[129,155,165],"efficiency":[130],"shrinks":[131],"growing":[134],"size.":[136],"also":[138],"find":[139],"vendor's":[142,168],"default":[143,185],"optimization":[146],"does":[147],"not":[148],"performance.":[152],"When":[153],"width":[156],"is":[157],"16,":[158],"speedup":[161],"our":[163],"manual":[164],"over":[166],"auto-vectorization":[169],"ranges":[170],"1.03":[172],"16.7.":[174],"attribute":[176],"drop":[179],"fact":[182],"optimizations":[187],"instantiate":[188],"large":[190],"number":[191],"atomics":[193],"operations.":[194]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}