{"id":"https://openalex.org/W4319870545","doi":"https://doi.org/10.1145/3543622.3573210","title":"CHARM: <u>C</u> omposing <u>H</u> eterogeneous <u>A</u> ccele <u>R</u> ators for <u>M</u> atrix Multiply on Versal ACAP Architecture","display_name":"CHARM: <u>C</u> omposing <u>H</u> eterogeneous <u>A</u> ccele <u>R</u> ators for <u>M</u> atrix Multiply on Versal ACAP Architecture","publication_year":2023,"publication_date":"2023-02-10","ids":{"openalex":"https://openalex.org/W4319870545","doi":"https://doi.org/10.1145/3543622.3573210"},"language":"en","primary_location":{"id":"doi:10.1145/3543622.3573210","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3543622.3573210","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3543622.3573210","source":null,"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2023 ACM/SIGDA International Symposium on Field Programmable Gate Arrays","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/10.1145/3543622.3573210","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5074853634","display_name":"Jinming Zhuang","orcid":"https://orcid.org/0000-0003-3659-339X"},"institutions":[{"id":"https://openalex.org/I170201317","display_name":"University of Pittsburgh","ror":"https://ror.org/01an3r305","country_code":"US","type":"education","lineage":["https://openalex.org/I170201317"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jinming Zhuang","raw_affiliation_strings":["University of Pittsburgh, Pittsburgh, PA, USA"],"affiliations":[{"raw_affiliation_string":"University of Pittsburgh, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I170201317"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068809285","display_name":"Jason Lau","orcid":null},"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":"Jason Lau","raw_affiliation_strings":["University of California, Los Angeles, Los Angeles, CA, USA"],"affiliations":[{"raw_affiliation_string":"University of California, Los Angeles, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088715551","display_name":"Hanchen Ye","orcid":"https://orcid.org/0000-0002-6646-8146"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hanchen Ye","raw_affiliation_strings":["University of Illinois at Urbana-Champaign, Urbana, IL, USA"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, Urbana, IL, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088193007","display_name":"Zhuoping Yang","orcid":"https://orcid.org/0000-0002-7655-4080"},"institutions":[{"id":"https://openalex.org/I170201317","display_name":"University of Pittsburgh","ror":"https://ror.org/01an3r305","country_code":"US","type":"education","lineage":["https://openalex.org/I170201317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhuoping Yang","raw_affiliation_strings":["University of Pittsburgh, Pittsburgh, PA, USA"],"affiliations":[{"raw_affiliation_string":"University of Pittsburgh, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I170201317"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041091411","display_name":"Yubo Du","orcid":"https://orcid.org/0000-0002-9153-7318"},"institutions":[{"id":"https://openalex.org/I170201317","display_name":"University of Pittsburgh","ror":"https://ror.org/01an3r305","country_code":"US","type":"education","lineage":["https://openalex.org/I170201317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yubo Du","raw_affiliation_strings":["University of Pittsburgh, Pittsburgh, PA, USA"],"affiliations":[{"raw_affiliation_string":"University of Pittsburgh, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I170201317"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003541162","display_name":"Jack Lo","orcid":"https://orcid.org/0000-0003-4918-478X"},"institutions":[{"id":"https://openalex.org/I4210137977","display_name":"Advanced Micro Devices (United States)","ror":"https://ror.org/04kd6c783","country_code":"US","type":"company","lineage":["https://openalex.org/I4210137977"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jack Lo","raw_affiliation_strings":["Advanced Micro Devices Inc, San Jose, CA, USA"],"affiliations":[{"raw_affiliation_string":"Advanced Micro Devices Inc, San Jose, CA, USA","institution_ids":["https://openalex.org/I4210137977"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035560671","display_name":"Kristof Denolf","orcid":"https://orcid.org/0000-0001-6668-4562"},"institutions":[{"id":"https://openalex.org/I4210137977","display_name":"Advanced Micro Devices (United States)","ror":"https://ror.org/04kd6c783","country_code":"US","type":"company","lineage":["https://openalex.org/I4210137977"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kristof Denolf","raw_affiliation_strings":["Advanced Micro Devices Inc, Longmont, CO, USA"],"affiliations":[{"raw_affiliation_string":"Advanced Micro Devices Inc, Longmont, CO, USA","institution_ids":["https://openalex.org/I4210137977"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014827775","display_name":"Stephen Neuendorffer","orcid":"https://orcid.org/0000-0003-2956-8428"},"institutions":[{"id":"https://openalex.org/I4210137977","display_name":"Advanced Micro Devices (United States)","ror":"https://ror.org/04kd6c783","country_code":"US","type":"company","lineage":["https://openalex.org/I4210137977"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Stephen Neuendorffer","raw_affiliation_strings":["Advanced Micro Devices Inc, San Jose, CA, USA"],"affiliations":[{"raw_affiliation_string":"Advanced Micro Devices Inc, San Jose, CA, USA","institution_ids":["https://openalex.org/I4210137977"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030875484","display_name":"Alex K. Jones","orcid":"https://orcid.org/0000-0001-7498-0206"},"institutions":[{"id":"https://openalex.org/I170201317","display_name":"University of Pittsburgh","ror":"https://ror.org/01an3r305","country_code":"US","type":"education","lineage":["https://openalex.org/I170201317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alex Jones","raw_affiliation_strings":["University of Pittsburgh, Pittsburgh, PA, USA"],"affiliations":[{"raw_affiliation_string":"University of Pittsburgh, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I170201317"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066534595","display_name":"Jingtong Hu","orcid":"https://orcid.org/0000-0003-4029-4034"},"institutions":[{"id":"https://openalex.org/I170201317","display_name":"University of Pittsburgh","ror":"https://ror.org/01an3r305","country_code":"US","type":"education","lineage":["https://openalex.org/I170201317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jingtong Hu","raw_affiliation_strings":["University of Pittsburgh, Pittsburgh, PA, USA"],"affiliations":[{"raw_affiliation_string":"University of Pittsburgh, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I170201317"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056321228","display_name":"Deming Chen","orcid":"https://orcid.org/0000-0002-3016-0270"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Deming Chen","raw_affiliation_strings":["University of Illinois at Urbana-Champaign, Urbana, IL, USA"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, Urbana, IL, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016776689","display_name":"Jason Cong","orcid":"https://orcid.org/0000-0003-2887-6963"},"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":"Jason Cong","raw_affiliation_strings":["University of California, Los Angeles, Los Angeles, CA, USA"],"affiliations":[{"raw_affiliation_string":"University of California, Los Angeles, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063866156","display_name":"Peipei Zhou","orcid":"https://orcid.org/0000-0002-0493-1844"},"institutions":[{"id":"https://openalex.org/I170201317","display_name":"University of Pittsburgh","ror":"https://ror.org/01an3r305","country_code":"US","type":"education","lineage":["https://openalex.org/I170201317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Peipei Zhou","raw_affiliation_strings":["University of Pittsburgh, Pittsburgh, PA, USA"],"affiliations":[{"raw_affiliation_string":"University of Pittsburgh, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I170201317"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":13,"corresponding_author_ids":["https://openalex.org/A5074853634"],"corresponding_institution_ids":["https://openalex.org/I170201317"],"apc_list":null,"apc_paid":null,"fwci":11.4951,"has_fulltext":true,"cited_by_count":38,"citation_normalized_percentile":{"value":0.99309498,"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":"153","last_page":"164"},"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.9994000196456909,"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":0.9986000061035156,"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":0.649644136428833},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.6371132135391235},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.6227911710739136},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.5425264835357666},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.494978129863739},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.4894172251224518},{"id":"https://openalex.org/keywords/application-specific-integrated-circuit","display_name":"Application-specific integrated circuit","score":0.4485284090042114},{"id":"https://openalex.org/keywords/floating-point","display_name":"Floating point","score":0.42157718539237976},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.35330531001091003},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.2887079119682312},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.2371281385421753},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.10860764980316162},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.10079756379127502}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.649644136428833},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.6371132135391235},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.6227911710739136},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.5425264835357666},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.494978129863739},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.4894172251224518},{"id":"https://openalex.org/C77390884","wikidata":"https://www.wikidata.org/wiki/Q217302","display_name":"Application-specific integrated circuit","level":2,"score":0.4485284090042114},{"id":"https://openalex.org/C84211073","wikidata":"https://www.wikidata.org/wiki/Q117879","display_name":"Floating point","level":2,"score":0.42157718539237976},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.35330531001091003},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.2887079119682312},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.2371281385421753},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.10860764980316162},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.10079756379127502},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3543622.3573210","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3543622.3573210","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3543622.3573210","source":null,"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2023 ACM/SIGDA International Symposium on Field Programmable Gate Arrays","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3543622.3573210","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3543622.3573210","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3543622.3573210","source":null,"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2023 ACM/SIGDA International Symposium on Field Programmable Gate Arrays","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7369618037","display_name":null,"funder_award_id":"2217003,2213701","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320332222","display_name":"University of Illinois at Urbana-Champaign","ror":"https://ror.org/047426m28"},{"id":"https://openalex.org/F4320333934","display_name":"Center for Research Computing, University of Pittsburgh","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4319870545.pdf","grobid_xml":"https://content.openalex.org/works/W4319870545.grobid-xml"},"referenced_works_count":31,"referenced_works":["https://openalex.org/W2067523571","https://openalex.org/W2108019747","https://openalex.org/W2113263062","https://openalex.org/W2141597697","https://openalex.org/W2166029537","https://openalex.org/W2512527800","https://openalex.org/W2605347906","https://openalex.org/W2605350416","https://openalex.org/W2606722458","https://openalex.org/W2788007484","https://openalex.org/W2883929540","https://openalex.org/W2892147049","https://openalex.org/W2935331687","https://openalex.org/W2945146780","https://openalex.org/W2950533501","https://openalex.org/W2953044030","https://openalex.org/W2962193180","https://openalex.org/W2996351509","https://openalex.org/W3098863686","https://openalex.org/W3111157406","https://openalex.org/W3111721177","https://openalex.org/W3112948415","https://openalex.org/W3130309348","https://openalex.org/W3131482099","https://openalex.org/W3158233068","https://openalex.org/W3163275603","https://openalex.org/W3196818429","https://openalex.org/W3198975860","https://openalex.org/W4224265992","https://openalex.org/W4293024216","https://openalex.org/W6739901393"],"related_works":["https://openalex.org/W2165367082","https://openalex.org/W2111241003","https://openalex.org/W1485756991","https://openalex.org/W2376218453","https://openalex.org/W2984236338","https://openalex.org/W1967938402","https://openalex.org/W3028347934","https://openalex.org/W2386041993","https://openalex.org/W1608572506","https://openalex.org/W2185692674"],"abstract_inverted_index":{"Dense":[0],"matrix":[1],"multiply":[2],"(MM)":[3],"serves":[4],"as":[5,38],"one":[6,153],"of":[7,24,66,147,180],"the":[8,20,43,128,148,165],"most":[9],"heavily":[10],"used":[11],"kernels":[12],"in":[13,140],"deep":[14],"learning":[15,90],"applications.":[16],"To":[17],"cope":[18],"with":[19,56,176],"high":[21],"computation":[22,167],"demands":[23],"these":[25],"applications,":[26],"heterogeneous":[27],"architectures":[28],"featuring":[29],"both":[30,94],"FPGA":[31],"and":[32,52,96],"dedicated":[33],"ASIC":[34],"accelerators":[35,161],"have":[36],"emerged":[37],"promising":[39],"platforms.":[40],"For":[41],"example,":[42],"AMD/Xilinx":[44],"Versal":[45,141],"ACAP":[46,142],"architecture":[47],"combines":[48],"general-purpose":[49],"CPU":[50],"cores":[51],"programmable":[53],"logic":[54],"(PL)":[55],"AI":[57,68],"Engine":[58,69],"processors":[59,70],"(AIE)":[60],"optimized":[61],"for":[62,83,173],"AI/ML.":[63],"An":[64],"array":[65],"400":[67],"executing":[71,122],"at":[72],"1":[73],"GHz":[74],"can":[75,104,158],"theoretically":[76],"provide":[77],"up":[78],"to":[79,162],"6.4":[80],"TFLOPs":[81],"performance":[82],"32-bit":[84],"floating-point":[85],"(fp32)":[86],"data.":[87],"However,":[88],"machine":[89],"models":[91],"often":[92],"contain":[93],"large":[95,101],"small":[97,111,124],"MM":[98,102,112,125,138,178],"operations.":[99],"While":[100],"operations":[103,113],"be":[105],"parallelized":[106],"efficiently":[107],"across":[108],"many":[109],"cores,":[110],"typically":[114],"cannot.":[115],"In":[116],"our":[117],"investigation,":[118],"we":[119,159],"observe":[120],"that":[121],"some":[123],"layers":[126,179],"from":[127],"BERT":[129],"natural":[130],"language":[131],"processing":[132],"model":[133],"on":[134],"a":[135],"large,":[136],"monolithic":[137],"accelerator":[139],"achieved":[143],"less":[144],"than":[145],"5%":[146],"theoretical":[149],"peak":[150],"performance.":[151],"Therefore,":[152],"key":[154],"question":[155],"arises:":[156],"How":[157],"design":[160],"fully":[163],"use":[164],"abundant":[166],"resources":[168],"under":[169],"limited":[170],"communication":[171],"bandwidth":[172],"end-to-end":[174],"applications":[175],"multiple":[177],"diverse":[181],"sizes?":[182]},"counts_by_year":[{"year":2025,"cited_by_count":21},{"year":2024,"cited_by_count":12},{"year":2023,"cited_by_count":5}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}
