{"id":"https://openalex.org/W2894663577","doi":"https://doi.org/10.1145/3241793.3241809","title":"A Case Study of Integer Sum Reduction using Atomics","display_name":"A Case Study of Integer Sum Reduction using Atomics","publication_year":2018,"publication_date":"2018-06-20","ids":{"openalex":"https://openalex.org/W2894663577","doi":"https://doi.org/10.1145/3241793.3241809","mag":"2894663577"},"language":"en","primary_location":{"id":"doi:10.1145/3241793.3241809","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3241793.3241809","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3241793.3241809","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 9th International Symposium on Highly-Efficient Accelerators and Reconfigurable Technologies","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3241793.3241809","any_repository_has_fulltext":null},"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, Lemont, IL"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Argonne National Laboratory, Lemont, IL","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, Lemont, IL"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Argonne National Laboratory, Lemont, IL","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":0.4751,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.64136579,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9997000098228455,"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":0.9997000098228455,"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/T10772","display_name":"Distributed systems and fault tolerance","score":0.998199999332428,"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/T10829","display_name":"Interconnection Networks and Systems","score":0.9973000288009644,"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/xeon","display_name":"Xeon","score":0.7358719110488892},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.7177278995513916},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6936582326889038},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.6370263695716858},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.5711140632629395},{"id":"https://openalex.org/keywords/central-processing-unit","display_name":"Central processing unit","score":0.49849510192871094},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.48122596740722656},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.229067862033844},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07239517569541931}],"concepts":[{"id":"https://openalex.org/C145108525","wikidata":"https://www.wikidata.org/wiki/Q656154","display_name":"Xeon","level":2,"score":0.7358719110488892},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.7177278995513916},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6936582326889038},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.6370263695716858},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.5711140632629395},{"id":"https://openalex.org/C49154492","wikidata":"https://www.wikidata.org/wiki/Q5300","display_name":"Central processing unit","level":2,"score":0.49849510192871094},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.48122596740722656},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.229067862033844},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07239517569541931},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3241793.3241809","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3241793.3241809","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3241793.3241809","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 9th International Symposium on Highly-Efficient Accelerators and Reconfigurable Technologies","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3241793.3241809","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3241793.3241809","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3241793.3241809","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 9th International Symposium on Highly-Efficient Accelerators and Reconfigurable Technologies","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Affordable and clean energy","score":0.75,"id":"https://metadata.un.org/sdg/7"}],"awards":[{"id":"https://openalex.org/G2777053550","display_name":null,"funder_award_id":"AC02-06CH11357","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G4030212589","display_name":null,"funder_award_id":"contract DE-AC02-06CH11357","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G6558272803","display_name":null,"funder_award_id":"DE-AC02","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G6848031779","display_name":null,"funder_award_id":"06CH11357","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G7938963221","display_name":null,"funder_award_id":"DE-AC02-06CH11357","funder_id":"https://openalex.org/F4320337674","funder_display_name":"Wind Energy Technologies Office"},{"id":"https://openalex.org/G7954425250","display_name":null,"funder_award_id":"DE-AC02-06CH11357","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G969889393","display_name":null,"funder_award_id":"DE-AC02-","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/F4320337674","display_name":"Wind Energy Technologies Office","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2894663577.pdf","grobid_xml":"https://content.openalex.org/works/W2894663577.grobid-xml"},"referenced_works_count":13,"referenced_works":["https://openalex.org/W1762731526","https://openalex.org/W2044709030","https://openalex.org/W2086105136","https://openalex.org/W2117689653","https://openalex.org/W2128870271","https://openalex.org/W2140861996","https://openalex.org/W2157729530","https://openalex.org/W2159392969","https://openalex.org/W2260448916","https://openalex.org/W2343695530","https://openalex.org/W2475663704","https://openalex.org/W4235158490","https://openalex.org/W6607941966"],"related_works":["https://openalex.org/W2981664121","https://openalex.org/W2936534257","https://openalex.org/W2887282140","https://openalex.org/W2526069705","https://openalex.org/W2741421049","https://openalex.org/W2108305411","https://openalex.org/W1980140364","https://openalex.org/W2024016913","https://openalex.org/W2295585735","https://openalex.org/W2214459866"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"the":[3,20,25,40,43,59,85,94,104,112,120],"implementations":[4,21],"of":[5,24,42],"integer":[6],"sum":[7],"reduction":[8,44,60],"using":[9,27,45],"atomic":[10],"functions":[11],"on":[12,61,103,111,119],"FPGA,":[13,82],"CPU,":[14],"and":[15,22,51,68,77,89,96,114],"GPU":[16,65],"platforms.":[17],"We":[18],"explain":[19],"optimizations":[23,41],"kernel":[26],"an":[28,34,62,72,78],"OpenCL-based":[29],"highlevel":[30],"synthesis":[31],"flow":[32],"for":[33,47],"FPGA.":[35],"In":[36],"addition,":[37],"we":[38],"describe":[39],"directives":[46],"a":[48,52],"multi-core":[49],"CPU":[50,76,95,113],"GPU.":[53,121],"The":[54,99],"experimental":[55],"results":[56],"show":[57],"that":[58,110,118],"Nvidia":[63],"K80":[64],"is":[66,106],"3.4X":[67],"6.7X":[69],"faster":[70],"than":[71,93,109,117],"Intel":[73],"Xeon":[74],"16-core":[75],"Arria":[79],"10":[80],"GX1150":[81],"respectively.":[83,98],"However,":[84],"FPGA":[86,105],"consumes":[87],"4.4X":[88],"2.3X":[90],"less":[91],"power":[92],"GPU,":[97],"performance":[100],"per":[101],"watt":[102],"2.2X":[107],"higher":[108],"2.9X":[115],"lower":[116]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2026-06-17T08:01:34.144755","created_date":"2025-10-10T00:00:00"}