{"id":"https://openalex.org/W4400656480","doi":"https://doi.org/10.1145/3678010","title":"EA4RCA: Efficient AIE accelerator design framework for regular Communication-Avoiding Algorithm","display_name":"EA4RCA: Efficient AIE accelerator design framework for regular Communication-Avoiding Algorithm","publication_year":2024,"publication_date":"2024-07-15","ids":{"openalex":"https://openalex.org/W4400656480","doi":"https://doi.org/10.1145/3678010"},"language":"en","primary_location":{"id":"doi:10.1145/3678010","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3678010","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3678010","source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"is_oa":true,"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 Architecture and Code Optimization","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3678010","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100398462","display_name":"Wenbo Zhang","orcid":"https://orcid.org/0000-0002-8601-802X"},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenbo Zhang","raw_affiliation_strings":["Faculty of Information, Beijing University of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-8601-802X","affiliations":[{"raw_affiliation_string":"Faculty of Information, Beijing University of Technology, Beijing, China","institution_ids":["https://openalex.org/I37796252"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087352252","display_name":"Yiqi Liu","orcid":"https://orcid.org/0009-0000-8262-2185"},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yiqi Liu","raw_affiliation_strings":["Faculty of Information, Beijing University of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0000-8262-2185","affiliations":[{"raw_affiliation_string":"Faculty of Information, Beijing University of Technology, Beijing, China","institution_ids":["https://openalex.org/I37796252"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108326646","display_name":"Tianhao Zang","orcid":null},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianhao Zang","raw_affiliation_strings":["Faculty of Information, Beijing University of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0000-6514-8266","affiliations":[{"raw_affiliation_string":"Faculty of Information, Beijing University of Technology, Beijing, China","institution_ids":["https://openalex.org/I37796252"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102257344","display_name":"Zhenshan Bao","orcid":"https://orcid.org/0000-0003-4714-8312"},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenshan Bao","raw_affiliation_strings":["Faculty of Information, Beijing University of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-4714-8312","affiliations":[{"raw_affiliation_string":"Faculty of Information, Beijing University of Technology, Beijing, China","institution_ids":["https://openalex.org/I37796252"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I37796252"],"apc_list":null,"apc_paid":null,"fwci":0.8523,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.73805553,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"21","issue":"4","first_page":"1","last_page":"24"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9980999827384949,"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"}},"topics":[{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9980999827384949,"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/T12808","display_name":"Ferroelectric and Negative Capacitance Devices","score":0.9962000250816345,"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/T11321","display_name":"Error Correcting Code Techniques","score":0.9955000281333923,"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":0.8403964042663574},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.4956866502761841},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.48659050464630127},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4777768850326538},{"id":"https://openalex.org/keywords/efficient-energy-use","display_name":"Efficient energy use","score":0.4730193614959717},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.4623592495918274},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.44368892908096313},{"id":"https://openalex.org/keywords/acceleration","display_name":"Acceleration","score":0.42548540234565735},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.32535475492477417},{"id":"https://openalex.org/keywords/wireless","display_name":"Wireless","score":0.19379186630249023},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.12027651071548462},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.11700636148452759}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8403964042663574},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.4956866502761841},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.48659050464630127},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4777768850326538},{"id":"https://openalex.org/C2742236","wikidata":"https://www.wikidata.org/wiki/Q924713","display_name":"Efficient energy use","level":2,"score":0.4730193614959717},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.4623592495918274},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.44368892908096313},{"id":"https://openalex.org/C117896860","wikidata":"https://www.wikidata.org/wiki/Q11376","display_name":"Acceleration","level":2,"score":0.42548540234565735},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.32535475492477417},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.19379186630249023},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.12027651071548462},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.11700636148452759},{"id":"https://openalex.org/C74650414","wikidata":"https://www.wikidata.org/wiki/Q11397","display_name":"Classical mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"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/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3678010","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3678010","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3678010","source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"is_oa":true,"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 Architecture and Code Optimization","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/3678010","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3678010","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3678010","source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"is_oa":true,"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 Architecture and Code Optimization","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Affordable and clean energy","score":0.8999999761581421,"id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4400656480.pdf"},"referenced_works_count":46,"referenced_works":["https://openalex.org/W174555674","https://openalex.org/W1969648707","https://openalex.org/W2012469746","https://openalex.org/W2061171222","https://openalex.org/W2551625567","https://openalex.org/W2590211456","https://openalex.org/W2799537975","https://openalex.org/W2884607893","https://openalex.org/W2915644294","https://openalex.org/W2917909627","https://openalex.org/W2918037051","https://openalex.org/W2981712449","https://openalex.org/W2989331028","https://openalex.org/W2996351509","https://openalex.org/W3017262157","https://openalex.org/W3019560945","https://openalex.org/W3098863686","https://openalex.org/W3130106255","https://openalex.org/W3176814699","https://openalex.org/W3201761987","https://openalex.org/W3205286820","https://openalex.org/W4206149382","https://openalex.org/W4220832929","https://openalex.org/W4221142709","https://openalex.org/W4285181627","https://openalex.org/W4289827962","https://openalex.org/W4318719410","https://openalex.org/W4319870545","https://openalex.org/W4321637087","https://openalex.org/W4321637212","https://openalex.org/W4321637250","https://openalex.org/W4321637356","https://openalex.org/W4379031105","https://openalex.org/W4381251538","https://openalex.org/W4381327281","https://openalex.org/W4381328365","https://openalex.org/W4383749341","https://openalex.org/W4383749374","https://openalex.org/W4383749441","https://openalex.org/W4383860503","https://openalex.org/W4386144903","https://openalex.org/W4386709692","https://openalex.org/W4386941882","https://openalex.org/W4388855669","https://openalex.org/W4389162879","https://openalex.org/W6734039260"],"related_works":["https://openalex.org/W2390829436","https://openalex.org/W1989791859","https://openalex.org/W2136583354","https://openalex.org/W2111238207","https://openalex.org/W2565094479","https://openalex.org/W602859758","https://openalex.org/W2006439817","https://openalex.org/W1971289376","https://openalex.org/W2379101322","https://openalex.org/W3013241373"],"abstract_inverted_index":{"With":[0],"the":[1,4,9,22,58,78,82,133,146,160,173,181,185,189,200,208],"introduction":[2],"of":[3,25,61,85,140,148,193,213],"Adaptive":[5,11],"Intelligence":[6],"Engine":[7],"(AIE),":[8],"Versal":[10,62],"Compute":[12],"Acceleration":[13],"Platform":[14],"(Versal":[15],"ACAP)":[16],"has":[17,31,64],"garnered":[18],"great":[19],"attention.":[20],"However,":[21],"current":[23,201],"focus":[24],"Vitis":[26],"Libraries":[27],"and":[28,123,164,172,196,207,216],"limited":[29],"research":[30],"mainly":[32],"been":[33,65],"on":[34,46],"how":[35],"to":[36,131,144],"invoke":[37],"AIE":[38,49,79,86,106,126,134,149],"modules,":[39],"without":[40],"delving":[41],"into":[42],"a":[43,56,74,99],"thorough":[44],"discussion":[45],"effectively":[47],"utilizing":[48],"in":[50,87],"its":[51],"typical":[52,75],"use":[53],"cases.":[54],"As":[55],"result,":[57],"widespread":[59],"adoption":[60],"ACAP":[63],"restricted.":[66],"The":[67,137],"Communication":[68],"Avoidance":[69],"(CA)":[70],"algorithm":[71,162,175],"is":[72,143],"considered":[73],"application":[76],"within":[77],"architecture.":[80],"Nevertheless,":[81],"effective":[83],"utilization":[84],"CA":[88,117],"applications":[89],"remains":[90],"an":[91],"area":[92],"that":[93,158],"requires":[94],"further":[95],"exploration.":[96],"We":[97],"propose":[98],"top-down":[100],"customized":[101],"design":[102,108,135],"framework,":[103],"EA4RCA":[104],"(Efficient":[105],"accelerator":[107],"framework":[109,142,187],"for":[110,116,159],"regular":[111,120],"Communication-Avoiding":[112],"Algorithm),":[113],"specifically":[114],"tailored":[115],"algorithms":[118],"with":[119,125,168,177,199],"communication":[121,170,179],"patterns,":[122],"equipped":[124],"Graph":[127],"Code":[128],"Generator":[129],"software":[130],"accelerate":[132],"process.":[136],"primary":[138],"objective":[139],"this":[141],"maximize":[145],"performance":[147,203],"while":[150],"incorporating":[151],"high-speed":[152],"data":[153],"streaming":[154],"services.":[155],"Experiments":[156],"show":[157],"RCA":[161,174],"Filter2D":[163],"Matrix":[165],"Multiple":[166],"(MM)":[167],"lower":[169],"requirements":[171],"FFT":[176],"higher":[178],"requirements,":[180],"accelerators":[182],"implemented":[183],"by":[184],"RA4RCA":[186],"achieve":[188],"highest":[190,202,209],"throughput":[191],"improvements":[192,212],"22.19\u00d7,":[194],"1.05\u00d7,":[195],"3.88\u00d7":[197],"compared":[198],"acceleration":[204],"scheme":[205],"(SOTA),":[206],"energy":[210],"efficiency":[211],"6.11\u00d7,":[214],"1.30\u00d7":[215],"7.00\u00d7.":[217]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
