{"id":"https://openalex.org/W4280592298","doi":"https://doi.org/10.1109/fccm53951.2022.9786209","title":"TopSort: A High-Performance Two-Phase Sorting Accelerator Optimized on HBM-based FPGAs","display_name":"TopSort: A High-Performance Two-Phase Sorting Accelerator Optimized on HBM-based FPGAs","publication_year":2022,"publication_date":"2022-05-15","ids":{"openalex":"https://openalex.org/W4280592298","doi":"https://doi.org/10.1109/fccm53951.2022.9786209"},"language":"en","primary_location":{"id":"doi:10.1109/fccm53951.2022.9786209","is_oa":false,"landing_page_url":"https://doi.org/10.1109/fccm53951.2022.9786209","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE 30th Annual International Symposium on Field-Programmable Custom Computing Machines (FCCM)","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/A5003981003","display_name":"Weikang Qiao","orcid":"https://orcid.org/0000-0003-1946-2021"},"institutions":[{"id":"https://openalex.org/I4210093034","display_name":"Specific Technologies (United States)","ror":"https://ror.org/00fwkdt40","country_code":"US","type":"company","lineage":["https://openalex.org/I4210093034"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Weikang Qiao","raw_affiliation_strings":["Center for Domain-Specific Computing, UCLA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Domain-Specific Computing, UCLA","institution_ids":["https://openalex.org/I4210093034"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032647120","display_name":"Licheng Guo","orcid":"https://orcid.org/0000-0002-0705-9510"},"institutions":[{"id":"https://openalex.org/I4210093034","display_name":"Specific Technologies (United States)","ror":"https://ror.org/00fwkdt40","country_code":"US","type":"company","lineage":["https://openalex.org/I4210093034"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Licheng Guo","raw_affiliation_strings":["Center for Domain-Specific Computing, UCLA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Domain-Specific Computing, UCLA","institution_ids":["https://openalex.org/I4210093034"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065889904","display_name":"Zhenman Fang","orcid":"https://orcid.org/0000-0003-0603-9697"},"institutions":[{"id":"https://openalex.org/I18014758","display_name":"Simon Fraser University","ror":"https://ror.org/0213rcc28","country_code":"CA","type":"education","lineage":["https://openalex.org/I18014758"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Zhenman Fang","raw_affiliation_strings":["Simon Fraser University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Simon Fraser University","institution_ids":["https://openalex.org/I18014758"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051454330","display_name":"Mau-Chung Frank Chang","orcid":"https://orcid.org/0000-0002-2934-9359"},"institutions":[{"id":"https://openalex.org/I4210093034","display_name":"Specific Technologies (United States)","ror":"https://ror.org/00fwkdt40","country_code":"US","type":"company","lineage":["https://openalex.org/I4210093034"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mau-Chung Frank Chang","raw_affiliation_strings":["Center for Domain-Specific Computing, UCLA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Domain-Specific Computing, UCLA","institution_ids":["https://openalex.org/I4210093034"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111649811","display_name":"Jason Cong","orcid":null},"institutions":[{"id":"https://openalex.org/I4210093034","display_name":"Specific Technologies (United States)","ror":"https://ror.org/00fwkdt40","country_code":"US","type":"company","lineage":["https://openalex.org/I4210093034"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jason Cong","raw_affiliation_strings":["Center for Domain-Specific Computing, UCLA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Domain-Specific Computing, UCLA","institution_ids":["https://openalex.org/I4210093034"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5549,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.71356382,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"1"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9984999895095825,"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"}},"topics":[{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9984999895095825,"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/T10829","display_name":"Interconnection Networks and Systems","score":0.9983000159263611,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.998199999332428,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.7706706523895264},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.7509785294532776},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7326077222824097},{"id":"https://openalex.org/keywords/sorting","display_name":"Sorting","score":0.6553984880447388},{"id":"https://openalex.org/keywords/chip","display_name":"Chip","score":0.5435698628425598},{"id":"https://openalex.org/keywords/sort","display_name":"sort","score":0.509002685546875},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.4448525607585907},{"id":"https://openalex.org/keywords/sorting-algorithm","display_name":"Sorting algorithm","score":0.41702014207839966},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.34042632579803467},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.12469902634620667},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.0871114730834961}],"concepts":[{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.7706706523895264},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.7509785294532776},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7326077222824097},{"id":"https://openalex.org/C111696304","wikidata":"https://www.wikidata.org/wiki/Q2303697","display_name":"Sorting","level":2,"score":0.6553984880447388},{"id":"https://openalex.org/C165005293","wikidata":"https://www.wikidata.org/wiki/Q1074500","display_name":"Chip","level":2,"score":0.5435698628425598},{"id":"https://openalex.org/C88548561","wikidata":"https://www.wikidata.org/wiki/Q347599","display_name":"sort","level":2,"score":0.509002685546875},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.4448525607585907},{"id":"https://openalex.org/C108094655","wikidata":"https://www.wikidata.org/wiki/Q181593","display_name":"Sorting algorithm","level":3,"score":0.41702014207839966},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.34042632579803467},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.12469902634620667},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0871114730834961},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/fccm53951.2022.9786209","is_oa":false,"landing_page_url":"https://doi.org/10.1109/fccm53951.2022.9786209","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE 30th Annual International Symposium on Field-Programmable Custom Computing Machines (FCCM)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":2,"referenced_works":["https://openalex.org/W1902965424","https://openalex.org/W3043363332"],"related_works":["https://openalex.org/W2809748609","https://openalex.org/W2095055219","https://openalex.org/W2908348257","https://openalex.org/W3033694952","https://openalex.org/W2994182992","https://openalex.org/W2372558933","https://openalex.org/W2116295091","https://openalex.org/W2362374543","https://openalex.org/W2085265870","https://openalex.org/W2348196682"],"abstract_inverted_index":{"The":[0],"emergence":[1],"of":[2,13,53,83,126],"high-bandwidth":[3],"memory":[4,26],"(HBM)":[5],"brings":[6],"new":[7],"opportunities":[8],"to":[9,34,86,112],"boost":[10],"the":[11,23,41,50,58,72,89],"performance":[12,74,125],"sorting":[14,73,102,124],"acceleration":[15],"on":[16],"FPGAs,":[17],"which":[18],"was":[19],"conventionally":[20],"bounded":[21],"by":[22],"available":[24,54],"off-chip":[25,55],"bandwidth.":[27,39,91],"However,":[28],"it":[29],"is":[30,130],"nontrivial":[31],"for":[32,105],"designers":[33,78],"fully":[35],"utilize":[36,88],"this":[37],"immense":[38],"First,":[40],"existing":[42],"sorter":[43],"designs":[44],"cannot":[45],"be":[46],"directly":[47],"scaled":[48],"at":[49,64],"increasing":[51],"rate":[52,68],"bandwidth,":[56],"as":[57],"required":[59],"on-chip":[60],"resource":[61],"usage":[62],"grows":[63],"a":[65,99],"much":[66],"faster":[67,134],"and":[69,132,138],"would":[70],"bound":[71],"in":[75],"turn.":[76],"Second,":[77],"need":[79],"an":[80,122],"in-depth":[81],"understanding":[82],"HBM\u2019s":[84],"characteristics":[85],"effectively":[87],"HBM":[90,119],"To":[92],"tackle":[93],"these":[94],"challenges,":[95],"we":[96],"present":[97],"TopSort,":[98],"novel":[100],"two-phase":[101],"solution":[103],"optimized":[104],"HBMbased":[106],"FPGAs.":[107],"TopSort":[108,129],"can":[109],"sort":[110],"up":[111],"4":[113],"GB":[114],"data":[115],"using":[116],"all":[117],"32":[118],"channels,":[120],"with":[121],"overall":[123],"15.6":[127],"GB/s.":[128],"6.7\u00d7":[131],"2.2\u00d7":[133],"than":[135],"state-of-the-art":[136],"CPU":[137],"FPGA":[139],"sorters.":[140]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}