{"id":"https://openalex.org/W4408327158","doi":"https://doi.org/10.1145/3723046","title":"Productively Generating a High-Performance Linear Algebra Library on FPGAs","display_name":"Productively Generating a High-Performance Linear Algebra Library on FPGAs","publication_year":2025,"publication_date":"2025-03-11","ids":{"openalex":"https://openalex.org/W4408327158","doi":"https://doi.org/10.1145/3723046"},"language":"en","primary_location":{"id":"doi:10.1145/3723046","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3723046","pdf_url":null,"source":{"id":"https://openalex.org/S112809824","display_name":"ACM Transactions on Reconfigurable Technology and Systems","issn_l":"1936-7406","issn":["1936-7406","1936-7414"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Reconfigurable Technology and Systems","raw_type":"journal-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/A5072764450","display_name":"X. Q. Hao","orcid":"https://orcid.org/0009-0004-2127-6011"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xiaochen Hao","raw_affiliation_strings":["Peking University, Beijing, China","Peking University, China"],"affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"Peking University, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064870158","display_name":"Mingzhe Zhang","orcid":"https://orcid.org/0009-0007-1464-5271"},"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":"Mingzhe Zhang","raw_affiliation_strings":["Tsinghua University, Beijing, China","Tsinghua University, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104141491","display_name":"Ce Sun","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ce Sun","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China","University of Science and Technology of China, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"University of Science and Technology of China, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005340074","display_name":"Zhuofu Tao","orcid":"https://orcid.org/0000-0003-0951-1811"},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhuofu Tao","raw_affiliation_strings":["University of California, Los Angeles, Los Angeles, California, USA","University of California, Los Angeles, USA"],"affiliations":[{"raw_affiliation_string":"University of California, Los Angeles, Los Angeles, California, USA","institution_ids":["https://openalex.org/I161318765"]},{"raw_affiliation_string":"University of California, Los Angeles, USA","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023962594","display_name":"Hongbo Rong","orcid":"https://orcid.org/0000-0002-3275-7791"},"institutions":[{"id":"https://openalex.org/I4210131745","display_name":"Parallel Consulting (United States)","ror":"https://ror.org/03cssbw37","country_code":"US","type":"company","lineage":["https://openalex.org/I4210131745"]},{"id":"https://openalex.org/I1343180700","display_name":"Intel (United States)","ror":"https://ror.org/01ek73717","country_code":"US","type":"company","lineage":["https://openalex.org/I1343180700"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hongbo Rong","raw_affiliation_strings":["Parallel Computing Lab, Intel Corporation, Santa Clara, California, USA","Intel Labs, USA"],"affiliations":[{"raw_affiliation_string":"Parallel Computing Lab, Intel Corporation, Santa Clara, California, USA","institution_ids":["https://openalex.org/I1343180700","https://openalex.org/I4210131745"]},{"raw_affiliation_string":"Intel Labs, USA","institution_ids":["https://openalex.org/I1343180700"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036488225","display_name":"Yu Zhang","orcid":"https://orcid.org/0000-0001-6638-6442"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Zhang","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China","University of Science and Technology of China, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"University of Science and Technology of China, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008695429","display_name":"Lei He","orcid":"https://orcid.org/0000-0002-5266-3805"},"institutions":[{"id":"https://openalex.org/I40036882","display_name":"Institute for Advanced Study","ror":"https://ror.org/00f809463","country_code":"US","type":"facility","lineage":["https://openalex.org/I40036882"]},{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lei He","raw_affiliation_strings":["University of California, Los Angeles, Los Angeles, California, USA and Eastern Institute of Technology, Ningbo, China","University of California, Los Angeles, USA and Eastern Institute for Advanced Study, China"],"affiliations":[{"raw_affiliation_string":"University of California, Los Angeles, Los Angeles, California, USA and Eastern Institute of Technology, Ningbo, China","institution_ids":["https://openalex.org/I161318765"]},{"raw_affiliation_string":"University of California, Los Angeles, USA and Eastern Institute for Advanced Study, China","institution_ids":["https://openalex.org/I40036882","https://openalex.org/I161318765"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027015251","display_name":"Eric Petit","orcid":"https://orcid.org/0000-0001-5047-1407"},"institutions":[{"id":"https://openalex.org/I1343180700","display_name":"Intel (United States)","ror":"https://ror.org/01ek73717","country_code":"US","type":"company","lineage":["https://openalex.org/I1343180700"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Eric Petit","raw_affiliation_strings":["Intel Corporation, Santa Clara, California, USA","Intel, USA"],"affiliations":[{"raw_affiliation_string":"Intel Corporation, Santa Clara, California, USA","institution_ids":["https://openalex.org/I1343180700"]},{"raw_affiliation_string":"Intel, USA","institution_ids":["https://openalex.org/I1343180700"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103141832","display_name":"Wenguang Chen","orcid":"https://orcid.org/0000-0002-4281-1018"},"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":"Wenguang Chen","raw_affiliation_strings":["Tsinghua University, Beijing, China","Tsinghua University, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100604860","display_name":"Yun Liang","orcid":"https://orcid.org/0000-0002-9076-7998"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yun Liang","raw_affiliation_strings":["Peking University, Beijing, China","Peking University, China"],"affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"Peking University, China","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":10,"corresponding_author_ids":["https://openalex.org/A5072764450"],"corresponding_institution_ids":["https://openalex.org/I20231570"],"apc_list":null,"apc_paid":null,"fwci":7.3326,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.96311952,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":"18","issue":"2","first_page":"1","last_page":"32"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9983999729156494,"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"}},"topics":[{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization 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"}},{"id":"https://openalex.org/T11522","display_name":"VLSI and FPGA Design Techniques","score":0.998199999332428,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10904","display_name":"Embedded Systems Design Techniques","score":0.9976999759674072,"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":0.7314521670341492},{"id":"https://openalex.org/keywords/linear-algebra","display_name":"Linear algebra","score":0.6569781303405762},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.45140540599823},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.44737565517425537},{"id":"https://openalex.org/keywords/algebra-over-a-field","display_name":"Algebra over a field","score":0.37545329332351685},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.365306556224823},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.19104599952697754},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1817546784877777},{"id":"https://openalex.org/keywords/pure-mathematics","display_name":"Pure mathematics","score":0.0939008891582489}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7314521670341492},{"id":"https://openalex.org/C139352143","wikidata":"https://www.wikidata.org/wiki/Q82571","display_name":"Linear algebra","level":2,"score":0.6569781303405762},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.45140540599823},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.44737565517425537},{"id":"https://openalex.org/C136119220","wikidata":"https://www.wikidata.org/wiki/Q1000660","display_name":"Algebra over a field","level":2,"score":0.37545329332351685},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.365306556224823},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.19104599952697754},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1817546784877777},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0939008891582489},{"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:10.1145/3723046","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3723046","pdf_url":null,"source":{"id":"https://openalex.org/S112809824","display_name":"ACM Transactions on Reconfigurable Technology and Systems","issn_l":"1936-7406","issn":["1936-7406","1936-7414"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Reconfigurable Technology and Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W2002252837","https://openalex.org/W2017369466","https://openalex.org/W2038469228","https://openalex.org/W2040863504","https://openalex.org/W2055312318","https://openalex.org/W2119766542","https://openalex.org/W2132020380","https://openalex.org/W2132367502","https://openalex.org/W2325556328","https://openalex.org/W2625954420","https://openalex.org/W2788007484","https://openalex.org/W2899644485","https://openalex.org/W2906737788","https://openalex.org/W2950001020","https://openalex.org/W2962193180","https://openalex.org/W2990714382","https://openalex.org/W3033414614","https://openalex.org/W3090389586","https://openalex.org/W3092007829","https://openalex.org/W3112630515","https://openalex.org/W3130920634","https://openalex.org/W3131482099","https://openalex.org/W3190092209","https://openalex.org/W3193212547","https://openalex.org/W3200826900","https://openalex.org/W3210312974","https://openalex.org/W3211485653","https://openalex.org/W3212403328","https://openalex.org/W3213528054","https://openalex.org/W4211118386","https://openalex.org/W4211209812","https://openalex.org/W4224265992","https://openalex.org/W4234407207","https://openalex.org/W4281707342","https://openalex.org/W4281932226","https://openalex.org/W4293023583","https://openalex.org/W4312121094","https://openalex.org/W4383749402","https://openalex.org/W4386763982","https://openalex.org/W4393576142","https://openalex.org/W4393576618","https://openalex.org/W4394661856","https://openalex.org/W4404955125"],"related_works":["https://openalex.org/W1967938402","https://openalex.org/W4285303061","https://openalex.org/W2386041993","https://openalex.org/W2525488343","https://openalex.org/W1608572506","https://openalex.org/W622366405","https://openalex.org/W2477677129","https://openalex.org/W2378563121","https://openalex.org/W2383666998","https://openalex.org/W2063186542"],"abstract_inverted_index":{"Linear":[0],"algebra":[1,19],"computations":[2],"can":[3],"be":[4],"greatly":[5],"accelerated":[6],"using":[7,114],"spatial":[8,106,144],"accelerators":[9],"on":[10,49,157,172],"FPGAs.":[11,173],"As":[12],"a":[13,23,79,83,87,105,150,179],"standard":[14],"building":[15],"block":[16],"of":[17,26,46,56,72,82,104,137],"linear":[18],"applications,":[20],"BLAS":[21,47,181,192],"covers":[22],"wide":[24],"range":[25],"compute":[27],"patterns":[28],"that":[29],"vary":[30],"vastly":[31],"in":[32,53,185],"data":[33,41,141],"reuse,":[34],"bottleneck":[35],"resources,":[36],"matrix":[37,211],"storage":[38],"layouts,":[39],"and":[40,58,86,98,118,135,139,202,205,217],"types.":[42],"However,":[43],"existing":[44],"implementations":[45],"routines":[48,73],"FPGAs":[50],"are":[51],"stuck":[52],"the":[54,70,92,102,132,143,167,210],"dilemma":[55,93],"productivity":[57],"performance.":[59],"They":[60],"either":[61],"require":[62],"extensive":[63],"human":[64],"effort":[65],"or":[66],"fail":[67],"to":[68,90,129,147],"leverage":[69],"properties":[71,212],"for":[74,191,199],"acceleration.":[75],"We":[76],"introduce":[77],"Lasa,":[78],"framework":[80],"composed":[81],"programming":[84,109],"model":[85,110],"compiler,":[88],"designed":[89],"address":[91],"by":[94,160,208],"abstracting":[95],"(for":[96,100],"productivity)":[97],"specializing":[99],"performance)":[101],"architecture":[103,168],"accelerator.":[107],"The":[108,163],"realizes":[111],"systolic":[112],"arrays":[113],"uniform":[115],"recurrence":[116],"equations":[117],"space-time":[119],"transforms.":[120],"Streaming":[121],"tensors,":[122,149],"an":[123,158],"intuitive":[124],"dataflow-style":[125],"abstraction,":[126],"is":[127,154],"proposed":[128],"uniformly":[130],"describe":[131],"movement,":[133],"storage,":[134],"transpose":[136],"input":[138],"output":[140],"across":[142],"components.":[145],"According":[146],"streaming":[148],"customized":[151],"memory":[152],"hierarchy":[153],"automatically":[155],"built":[156],"FPGA":[159],"our":[161],"compiler.":[162],"compiler":[164],"further":[165],"specializes":[166],"with":[169,187],"transparent":[170],"optimizations":[171],"Using":[174],"this":[175],"framework,":[176],"we":[177],"develop":[178],"complete":[180],"library,":[182],"demonstrating":[183],"performance":[184],"parity":[186],"expert-written":[188],"HLS":[189],"code":[190],"level":[193,200],"3":[194],"routines,":[195,204],"76%\u201394%":[196],"machine":[197],"peak":[198],"1":[201],"2":[203],"1.6X\u201313X":[206],"speedup":[207],"leveraging":[209],"such":[213],"as":[214],"symmetry,":[215],"triangularity,":[216],"bandness.":[218]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2}],"updated_date":"2026-03-12T08:34:05.389933","created_date":"2025-10-10T00:00:00"}
