{"id":"https://openalex.org/W4412987267","doi":"https://doi.org/10.1109/ispass64960.2025.00025","title":"COCOSSim: A Cycle-Accurate Simulator for Heterogeneous Systolic Array Architectures","display_name":"COCOSSim: A Cycle-Accurate Simulator for Heterogeneous Systolic Array Architectures","publication_year":2025,"publication_date":"2025-05-11","ids":{"openalex":"https://openalex.org/W4412987267","doi":"https://doi.org/10.1109/ispass64960.2025.00025"},"language":"en","primary_location":{"id":"doi:10.1109/ispass64960.2025.00025","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ispass64960.2025.00025","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Symposium on Performance Analysis of Systems and Software (ISPASS)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5101797632","display_name":"Manoj Choudhary","orcid":"https://orcid.org/0000-0003-1258-3963"},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mansi Choudhary","raw_affiliation_strings":["Duke University,Dept. of ECE,Durham,NC,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Duke University,Dept. of ECE,Durham,NC,USA","institution_ids":["https://openalex.org/I170897317"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009440291","display_name":"Chris Kjellqvist","orcid":"https://orcid.org/0000-0002-4792-1910"},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chris Kjellqvist","raw_affiliation_strings":["Duke University,Dept. of Computer Science,Durham,NC,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Duke University,Dept. of Computer Science,Durham,NC,USA","institution_ids":["https://openalex.org/I170897317"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102527346","display_name":"Jiaao Ma","orcid":null},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiaao Ma","raw_affiliation_strings":["Duke University,Dept. of Computer Science,Durham,NC,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Duke University,Dept. of Computer Science,Durham,NC,USA","institution_ids":["https://openalex.org/I170897317"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042221799","display_name":"Lisa Wu Wills","orcid":"https://orcid.org/0000-0002-3574-3440"},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lisa Wu Wills","raw_affiliation_strings":["Duke University,Dept. of Computer Science,Durham,NC,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Duke University,Dept. of Computer Science,Durham,NC,USA","institution_ids":["https://openalex.org/I170897317"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I170897317"],"apc_list":null,"apc_paid":null,"fwci":4.5452,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.94892687,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"174","last_page":"185"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10904","display_name":"Embedded Systems Design Techniques","score":0.9879999756813049,"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.9879999756813049,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.967199981212616,"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/T10187","display_name":"Radio Frequency Integrated Circuit Design","score":0.9399999976158142,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6856508255004883},{"id":"https://openalex.org/keywords/systolic-array","display_name":"Systolic array","score":0.4856890141963959},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4343319535255432},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.3544258773326874},{"id":"https://openalex.org/keywords/simulation","display_name":"Simulation","score":0.34287357330322266},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.228307843208313},{"id":"https://openalex.org/keywords/very-large-scale-integration","display_name":"Very-large-scale integration","score":0.1460931897163391}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6856508255004883},{"id":"https://openalex.org/C150741067","wikidata":"https://www.wikidata.org/wiki/Q2377218","display_name":"Systolic array","level":3,"score":0.4856890141963959},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4343319535255432},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.3544258773326874},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.34287357330322266},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.228307843208313},{"id":"https://openalex.org/C14580979","wikidata":"https://www.wikidata.org/wiki/Q876049","display_name":"Very-large-scale integration","level":2,"score":0.1460931897163391}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ispass64960.2025.00025","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ispass64960.2025.00025","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Symposium on Performance Analysis of Systems and Software (ISPASS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5109862983","display_name":null,"funder_award_id":"CCF-2045973","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"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W2606722458","https://openalex.org/W2940862705","https://openalex.org/W2980200167","https://openalex.org/W2998732502","https://openalex.org/W3006586535","https://openalex.org/W3017024317","https://openalex.org/W3036878841","https://openalex.org/W3097528158","https://openalex.org/W3159727696","https://openalex.org/W4212863848","https://openalex.org/W4285335127","https://openalex.org/W4312933868","https://openalex.org/W4380874786","https://openalex.org/W4385245566","https://openalex.org/W4394998532","https://openalex.org/W6755207826","https://openalex.org/W6766978945","https://openalex.org/W6778883912","https://openalex.org/W6779823529","https://openalex.org/W6810876399","https://openalex.org/W6850162387","https://openalex.org/W6854866820"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W4240320454","https://openalex.org/W2070314832","https://openalex.org/W2395557210","https://openalex.org/W2010232134","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433"],"abstract_inverted_index":{"Performance":[0],"modeling":[1,178],"is":[2,156],"an":[3,147,163],"essential":[4],"tool":[5],"for":[6,18,34,73,100,105,113],"enabling":[7],"cost-effective":[8],"and":[9,14,32,53,76,103,121,127,135,159,176,201],"efficient":[10],"exploration":[11],"of":[12,43,89,151,165],"architectural":[13,27,75,126,193],"microarchitectural":[15,77,128],"design":[16,136],"decisions":[17],"hardware":[19],"development.":[20],"However,":[21],"existing":[22],"simulators":[23],"face":[24],"limitations":[25],"in":[26,79,118],"flexibility,":[28],"memory":[29,106],"hierarchy":[30],"modeling,":[31],"support":[33],"modern":[35,196],"accelerators":[36],"that":[37],"cater":[38],"to":[39,124,191,195],"the":[40,122,141],"computational":[41],"demands":[42],"contemporary":[44],"machine":[45],"learning":[46],"models,":[47],"where":[48],"non-linear":[49,101],"operations":[50,102],"like":[51],"softmax":[52],"other":[54],"vectorized":[55],"activations":[56],"have":[57],"become":[58],"increasingly":[59],"important.":[60],"To":[61],"address":[62],"these":[63],"gaps,":[64],"we":[65],"present":[66,181],"COCOSSim,":[67],"a":[68,86,110],"cycleaccurate":[69],"performance":[70,133],"simulator":[71],"designed":[72],"evaluating":[74],"modifications":[78,194],"heterogeneous":[80,197],"systolic":[81,95],"array-based":[82],"accelerators.":[83],"COCOSSim":[84,130,145,155,187],"supports":[85],"wide":[87],"range":[88],"neural":[90],"network":[91],"inference":[92],"workloads,":[93],"integrating":[94],"arrays":[96],"with":[97],"vector":[98],"units":[99],"DRAMSim3":[104],"modeling.":[107],"By":[108],"offering":[109],"PyTorch":[111],"frontend":[112],"seamless":[114],"model":[115,199],"integration,":[116],"flexibility":[117,175],"scheduling":[119],"strategies,":[120],"ability":[123],"make":[125],"modifications,":[129],"enables":[131],"detailed":[132],"analysis":[134],"exploration.":[137],"When":[138],"validated":[139],"against":[140],"Google":[142],"TPU":[143],"v3,":[144],"achieves":[146],"average":[148],"error":[149],"rate":[150],"13":[152],"%.":[153],"Additionally,":[154],"highly":[157],"scalable":[158],"offers":[160],"simulation":[161],"speeds":[162],"order":[164],"magnitude":[166],"faster":[167],"than":[168],"prior":[169],"work":[170],"while":[171],"providing":[172],"significantly":[173],"greater":[174],"enhanced":[177],"capabilities.":[179],"We":[180],"two":[182],"case":[183],"studies":[184],"demonstrating":[185],"how":[186],"can":[188],"be":[189],"used":[190],"evaluate":[192],"accelerators:":[198],"parallelism":[200],"operation":[202],"fusion.":[203]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}