{"id":"https://openalex.org/W4211147898","doi":"https://doi.org/10.1145/3490422.3502368","title":"High-Performance Sparse Linear Algebra on HBM-Equipped FPGAs Using HLS","display_name":"High-Performance Sparse Linear Algebra on HBM-Equipped FPGAs Using HLS","publication_year":2022,"publication_date":"2022-02-11","ids":{"openalex":"https://openalex.org/W4211147898","doi":"https://doi.org/10.1145/3490422.3502368"},"language":"en","primary_location":{"id":"doi:10.1145/3490422.3502368","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3490422.3502368","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2022 ACM/SIGDA International Symposium on Field-Programmable Gate Arrays","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/A5039033697","display_name":"Yixiao Du","orcid":"https://orcid.org/0000-0002-6106-1283"},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yixiao Du","raw_affiliation_strings":["Cornell University, Ithaca, NY, USA"],"affiliations":[{"raw_affiliation_string":"Cornell University, Ithaca, NY, USA","institution_ids":["https://openalex.org/I205783295"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101586926","display_name":"Yuwei Hu","orcid":"https://orcid.org/0009-0001-1070-2597"},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuwei Hu","raw_affiliation_strings":["Cornell University, Ithaca, NY, USA"],"affiliations":[{"raw_affiliation_string":"Cornell University, Ithaca, NY, USA","institution_ids":["https://openalex.org/I205783295"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028367760","display_name":"Zhongchun Zhou","orcid":"https://orcid.org/0009-0000-7037-7418"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhongchun Zhou","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037210004","display_name":"Zhiru Zhang","orcid":"https://orcid.org/0000-0002-0778-0308"},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhiru Zhang","raw_affiliation_strings":["Cornell University, Ithaca, NY, USA"],"affiliations":[{"raw_affiliation_string":"Cornell University, Ithaca, NY, USA","institution_ids":["https://openalex.org/I205783295"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5039033697"],"corresponding_institution_ids":["https://openalex.org/I205783295"],"apc_list":null,"apc_paid":null,"fwci":13.1693,"has_fulltext":false,"cited_by_count":61,"citation_normalized_percentile":{"value":0.99329983,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"54","last_page":"64"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":1.0,"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":1.0,"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/T10829","display_name":"Interconnection Networks and Systems","score":0.9998000264167786,"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.9983999729156494,"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/computer-science","display_name":"Computer science","score":0.7490827441215515},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.6342309713363647},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.6100791692733765},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6073175072669983},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.5799276232719421},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.5108308792114258},{"id":"https://openalex.org/keywords/linear-algebra","display_name":"Linear algebra","score":0.5014071464538574},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.5008368492126465},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.4921216368675232},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.47750037908554077},{"id":"https://openalex.org/keywords/memory-bandwidth","display_name":"Memory bandwidth","score":0.4619813859462738},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.4163423776626587},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.2786208391189575},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10529515147209167}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7490827441215515},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.6342309713363647},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.6100791692733765},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6073175072669983},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.5799276232719421},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.5108308792114258},{"id":"https://openalex.org/C139352143","wikidata":"https://www.wikidata.org/wiki/Q82571","display_name":"Linear algebra","level":2,"score":0.5014071464538574},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.5008368492126465},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.4921216368675232},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.47750037908554077},{"id":"https://openalex.org/C188045654","wikidata":"https://www.wikidata.org/wiki/Q17148339","display_name":"Memory bandwidth","level":2,"score":0.4619813859462738},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.4163423776626587},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.2786208391189575},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10529515147209167},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C84114770","wikidata":"https://www.wikidata.org/wiki/Q46344","display_name":"Quantum","level":2,"score":0.0},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","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},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3490422.3502368","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3490422.3502368","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2022 ACM/SIGDA International Symposium on Field-Programmable Gate Arrays","raw_type":"proceedings-article"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-125647","is_oa":false,"landing_page_url":"https://repository.hkust.edu.hk/ir/Record/1783.1-125647","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"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":"Conference paper"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","score":0.4000000059604645,"display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1537260300","https://openalex.org/W2106111377","https://openalex.org/W2344729295","https://openalex.org/W2461193710","https://openalex.org/W2899644485","https://openalex.org/W2899691047","https://openalex.org/W3007436455","https://openalex.org/W3007959289","https://openalex.org/W3098650335","https://openalex.org/W3132871189","https://openalex.org/W3133395503","https://openalex.org/W3200826900","https://openalex.org/W4245683599","https://openalex.org/W6600360367","https://openalex.org/W6639055396","https://openalex.org/W6739901393"],"related_works":["https://openalex.org/W2031026393","https://openalex.org/W2727953781","https://openalex.org/W2256144436","https://openalex.org/W2126944241","https://openalex.org/W2557039832","https://openalex.org/W1992476323","https://openalex.org/W2617819327","https://openalex.org/W1981718088","https://openalex.org/W1501847821","https://openalex.org/W2535419693"],"abstract_inverted_index":{"Sparse":[0],"linear":[1,56,70],"algebra":[2,57,71],"operators":[3],"are":[4],"memory":[5,12,29,41,87],"bound":[6],"due":[7,101],"to":[8,11,38,49,94,102,127,164,234],"low":[9,77,98],"compute":[10,44,99,179],"access":[13,18],"ratio":[14],"and":[15,43,105,109,156,173,181,224,240],"irregular":[16],"data":[17],"patterns.":[19],"The":[20,215],"exceptional":[21],"bandwidth":[22,79,230],"improvement":[23],"provided":[24],"by":[25],"the":[26,34,40,47,52,90,132,191],"emerging":[27],"high-bandwidth":[28],"(HBM)":[30],"technologies,":[31],"coupled":[32],"with":[33,81,228],"ability":[35],"of":[36,54,161,212],"FPGAs":[37,75],"customize":[39],"hierarchy":[42],"engines,":[45],"brings":[46],"potential":[48],"significantly":[50],"boost":[51],"performance":[53],"sparse":[55,69,83,123,141],"operators.":[58],"In":[59],"this":[60],"paper":[61],"we":[62,193],"identify":[63],"four":[64,133],"challenges":[65],"when":[66,92,232],"developing":[67],"high-performance":[68,197],"accelerators":[72],"on":[73,112,122,200,209,237],"HBM-equipped":[74,203],"---":[76],"HBM":[78,96],"utilization":[80],"conventional":[82],"storage,":[84],"limited":[85],"on-chip":[86,150],"capacity":[88],"being":[89],"bottleneck":[91],"scaling":[93],"multiple":[95],"channels,":[97],"occupancy":[100],"bank":[103,171],"conflicts":[104,172],"inter-iteration":[106],"carried":[107,174],"dependencies,":[108],"timing":[110],"closure":[111],"multi-die":[113,202],"heterogeneous":[114],"fabrics.":[115],"We":[116,206],"conduct":[117],"an":[118],"in-depth":[119],"case":[120],"study":[121],"matrix-vector":[124],"multiplication":[125],"(SpMV)":[126],"explore":[128],"techniques":[129,136],"that":[130,153,168,218],"tackle":[131],"challenges.":[134],"These":[135],"include":[137],"(1)":[138],"a":[139,148,183,196,201,210,221],"customized":[140],"matrix":[142,213],"format":[143],"tailored":[144],"for":[145,176,187],"HBMs,":[146],"(2)":[147],"scalable":[149],"buffer":[151],"design":[152,185],"combines":[154],"replication":[155],"banking,":[157],"(3)":[158],"best":[159],"practices":[160],"using":[162],"HLS":[163],"implement":[165],"hardware":[166],"modules":[167],"dynamically":[169],"resolve":[170],"dependencies":[175],"achieving":[177],"high":[178,222],"occupancy,":[180],"(4)":[182],"split-kernel":[184],"methodology":[186],"frequency":[188,223],"optimization.":[189],"Using":[190],"techniques,":[192],"demonstrate":[194],"HiSparse,":[195],"SpMV":[198],"accelerator":[199],"FPGA":[204],"device.":[205],"evaluated":[207],"HiSparse":[208,219,242],"variety":[211],"datasets.":[214],"results":[216],"show":[217],"achieves":[220],"delivers":[225],"promising":[226],"speedup":[227],"increased":[229],"efficiency":[231],"compared":[233],"prior":[235],"arts":[236],"CPUs,":[238],"GPUs,":[239],"FPGAs.":[241],"is":[243],"available":[244],"at":[245],"https://github.com/cornell-zhang/HiSparse.":[246]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":16},{"year":2024,"cited_by_count":22},{"year":2023,"cited_by_count":15},{"year":2022,"cited_by_count":5}],"updated_date":"2026-02-25T08:12:03.925757","created_date":"2025-10-10T00:00:00"}