{"id":"https://openalex.org/W4401331008","doi":"https://doi.org/10.1145/3686163","title":"CHARM 2.0: Composing Heterogeneous Accelerators for Deep Learning on Versal ACAP Architecture","display_name":"CHARM 2.0: Composing Heterogeneous Accelerators for Deep Learning on Versal ACAP Architecture","publication_year":2024,"publication_date":"2024-08-05","ids":{"openalex":"https://openalex.org/W4401331008","doi":"https://doi.org/10.1145/3686163"},"language":"en","primary_location":{"id":"doi:10.1145/3686163","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3686163","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3686163","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":true,"oa_status":"bronze","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3686163","any_repository_has_fulltext":false},"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/A5103205936","display_name":"Shixin Ji","orcid":"https://orcid.org/0009-0003-3429-4692"},"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":"Shixin Ji","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, 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/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/A5000141831","display_name":"Yiyu Shi","orcid":"https://orcid.org/0000-0002-6788-9823"},"institutions":[{"id":"https://openalex.org/I107639228","display_name":"University of Notre Dame","ror":"https://ror.org/00mkhxb43","country_code":"US","type":"education","lineage":["https://openalex.org/I107639228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yiyu Shi","raw_affiliation_strings":["University of Notre Dame, Notre Dame, IN, USA"],"affiliations":[{"raw_affiliation_string":"University of Notre Dame, Notre Dame, IN, USA","institution_ids":["https://openalex.org/I107639228"]}]},{"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":14,"corresponding_author_ids":["https://openalex.org/A5074853634"],"corresponding_institution_ids":["https://openalex.org/I170201317"],"apc_list":null,"apc_paid":null,"fwci":6.3624,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.97698849,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"17","issue":"3","first_page":"1","last_page":"31"},"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/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":0.9973000288009644,"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/computer-science","display_name":"Computer science","score":0.8458935022354126},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.7360577583312988},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.6251091957092285},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.5798925757408142},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.5104255080223083},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5073921084403992},{"id":"https://openalex.org/keywords/application-specific-integrated-circuit","display_name":"Application-specific integrated circuit","score":0.4965999722480774},{"id":"https://openalex.org/keywords/hardware-acceleration","display_name":"Hardware acceleration","score":0.4529035985469818},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.43433547019958496},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.4255322813987732},{"id":"https://openalex.org/keywords/symmetric-multiprocessor-system","display_name":"Symmetric multiprocessor system","score":0.4201611280441284},{"id":"https://openalex.org/keywords/pci-express","display_name":"PCI Express","score":0.41852006316185},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.41051509976387024},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.38186272978782654},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.13266468048095703}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8458935022354126},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.7360577583312988},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.6251091957092285},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.5798925757408142},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.5104255080223083},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5073921084403992},{"id":"https://openalex.org/C77390884","wikidata":"https://www.wikidata.org/wiki/Q217302","display_name":"Application-specific integrated circuit","level":2,"score":0.4965999722480774},{"id":"https://openalex.org/C13164978","wikidata":"https://www.wikidata.org/wiki/Q600158","display_name":"Hardware acceleration","level":3,"score":0.4529035985469818},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.43433547019958496},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.4255322813987732},{"id":"https://openalex.org/C172430144","wikidata":"https://www.wikidata.org/wiki/Q17111997","display_name":"Symmetric multiprocessor system","level":2,"score":0.4201611280441284},{"id":"https://openalex.org/C64270927","wikidata":"https://www.wikidata.org/wiki/Q206924","display_name":"PCI Express","level":3,"score":0.41852006316185},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.41051509976387024},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.38186272978782654},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.13266468048095703},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"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},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3686163","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3686163","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3686163","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":{"id":"doi:10.1145/3686163","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3686163","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3686163","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"},"sustainable_development_goals":[{"score":0.4000000059604645,"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4401331008.pdf"},"referenced_works_count":38,"referenced_works":["https://openalex.org/W1493774699","https://openalex.org/W2012469746","https://openalex.org/W2015332951","https://openalex.org/W2067523571","https://openalex.org/W2094756095","https://openalex.org/W2108019747","https://openalex.org/W2128317332","https://openalex.org/W2141597697","https://openalex.org/W2166029537","https://openalex.org/W2442974303","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/W2899644485","https://openalex.org/W2899915146","https://openalex.org/W2935331687","https://openalex.org/W2945146780","https://openalex.org/W2950533501","https://openalex.org/W2953044030","https://openalex.org/W2996351509","https://openalex.org/W3098863686","https://openalex.org/W3111721177","https://openalex.org/W3112948415","https://openalex.org/W3130281579","https://openalex.org/W3130920634","https://openalex.org/W3158233068","https://openalex.org/W3163275603","https://openalex.org/W3196818429","https://openalex.org/W3198975860","https://openalex.org/W4224265992","https://openalex.org/W4241238426","https://openalex.org/W4293024216","https://openalex.org/W4321637087","https://openalex.org/W4386763439"],"related_works":["https://openalex.org/W2532502681","https://openalex.org/W3094239885","https://openalex.org/W2319262638","https://openalex.org/W2783386063","https://openalex.org/W2904152126","https://openalex.org/W1910046164","https://openalex.org/W2922154889","https://openalex.org/W2566887379","https://openalex.org/W2945182031","https://openalex.org/W2995408604"],"abstract_inverted_index":{"Dense":[0],"matrix":[1],"multiply":[2],"(MM)":[3],"serves":[4],"as":[5,38],"one":[6,147,194,230,339],"of":[7,24,64,141,174,193,202,347],"the":[8,20,43,122,142,159,179,186,189,198,206,214,263,286,344,358,363,373,400],"most":[9],"heavily":[10],"used":[11],"kernels":[12],"in":[13,134,205,272,316,357,372,403,419],"deep":[14,269],"learning":[15,87,270],"applications.":[16,365],"To":[17,208,248],"cope":[18],"with":[19,55,170],"high":[21],"computation":[22,161,191],"demands":[23],"these":[25],"applications,":[26],"heterogeneous":[27],"architectures":[28,223],"featuring":[29],"both":[30,91],"FPGA":[31],"and":[32,52,93,197,245,275,283,305,314,332,354,384,406,413,417],"dedicated":[33],"ASIC":[34],"accelerators":[35,155],"have":[36,389],"emerged":[37],"promising":[39],"platforms.":[40],"For":[41],"example,":[42],"AMD/Xilinx":[44,287],"Versal":[45,135,288],"ACAP":[46,136,289],"architecture":[47],"combines":[48],"general-purpose":[49],"CPU":[50],"cores":[51],"programmable":[53],"logic":[54],"AI":[56,66],"Engine":[57,67],"processors":[58,68],"optimized":[59],"for":[60,80,167,310,362],"AI/ML.":[61],"An":[62],"array":[63],"400":[65],"executing":[69,116],"at":[70],"1":[71],"GHz":[72],"can":[73,101,152],"provide":[74],"up":[75],"to":[76,156,217,241,338,397,407,411],"6.4":[77],"TFLOPS":[78,307],"performance":[79],"32-bit":[81],"floating-point":[82],"(FP32)":[83],"data.":[84],"However,":[85],"machine":[86],"models":[88,235],"often":[89],"contain":[90],"large":[92,98],"small":[94,108,118,203],"MM":[95,99,109,119,132,172,200,221],"operations.":[96],"While":[97],"operations":[100,110],"be":[102],"parallelized":[103],"efficiently":[104],"across":[105],"many":[106],"cores,":[107],"typically":[111],"cannot.":[112],"We":[113,177,261,388],"observe":[114],"that":[115,236,296],"some":[117],"layers":[120,173,201,228],"from":[121,185],"BERT":[123],"natural":[124],"language":[125],"processing":[126],"model":[127],"on":[128,226,266,285],"a":[129],"large,":[130],"monolithic":[131,195,340],"accelerator":[133,196,222,243],"achieved":[137,369],"less":[138],"than":[139],"5%":[140],"theoretical":[143],"peak":[144],"performance.":[145],"Therefore,":[146],"key":[148],"question":[149],"arises:":[150],"How":[151],"we":[153,212,297],"design":[154,238,259],"fully":[157],"use":[158],"abundant":[160],"resources":[162,192],"under":[163],"limited":[164],"communication":[165],"bandwidth":[166],"end-to-end":[168,421],"applications":[169,271],"multiple":[171,219],"diverse":[175,220],"sizes?":[176],"identify":[178],"biggest":[180],"system":[181,250],"throughput":[182,309,335,346,368],"bottleneck":[183],"resulting":[184],"mismatch":[187],"between":[188],"massive":[190],"various":[199],"sizes":[204],"application.":[207,231],"resolve":[209],"this":[210,404],"problem,":[211],"propose":[213],"CHARM":[215,232,252,264,342,371,415],"framework":[216,265,416],"compose":[218],"working":[224],"concurrently":[225],"different":[227,268],"within":[229],"includes":[233],"analytical":[234],"guide":[237],"space":[239],"exploration":[240],"determine":[242],"partitions":[244],"layer":[246],"scheduling.":[247],"facilitate":[249],"designs,":[251],"automatically":[253],"generates":[254],"code,":[255],"enabling":[256],"thorough":[257],"onboard":[258],"verification.":[260],"deploy":[262],"four":[267,364],"FP32,":[273],"INT16,":[274],"INT8":[276,374],"data":[277,318,360,375],"types,":[278],"including":[279,393],"BERT,":[280,311],"ViT,":[281,312],"NCF,":[282,313],"MLP,":[284],"VCK190":[290],"evaluation":[291],"board.":[292],"Our":[293],"experiments":[294],"show":[295],"achieve":[298],"1.46":[299],"TFLOPS,":[300,302,304],"1.61":[301],"1.74":[303],"2.94":[306],"inference":[308],"MLP":[315],"FP32":[317],"type,":[319],"respectively,":[320],"which":[321],"obtain":[322],"5.29":[323],"\\(\\times\\)":[324,327,330,334],",":[325,328,331],"32.51":[326],"1.00":[329,333],"gains":[336],"compared":[337],"accelerator.":[341],"achieves":[343],"maximum":[345,367],"1.91":[348],"TOPS,":[349,351,353,379,381,383,386],"1.18":[350],"4.06":[352],"5.81":[355],"TOPS":[356],"INT16":[359],"type":[361,376],"The":[366],"by":[370],"is":[377],"3.65":[378],"1.28":[380],"10.19":[382],"21.58":[385],"respectively.":[387],"open-sourced":[390],"our":[391],"tools,":[392],"detailed":[394],"step-by-step":[395],"guides":[396],"reproduce":[398],"all":[399],"results":[401],"presented":[402],"article":[405],"enable":[408],"other":[409],"users":[410],"learn":[412],"leverage":[414],"tools":[418],"their":[420],"systems:":[422],"https://github.com/arc-research-lab/CHARM":[423],".":[424]},"counts_by_year":[{"year":2025,"cited_by_count":12},{"year":2024,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}
