{"id":"https://openalex.org/W4393578448","doi":"https://doi.org/10.1145/3626202.3637571","title":"MiCache: An MSHR-inclusive Non-blocking Cache Design for FPGAs","display_name":"MiCache: An MSHR-inclusive Non-blocking Cache Design for FPGAs","publication_year":2024,"publication_date":"2024-04-01","ids":{"openalex":"https://openalex.org/W4393578448","doi":"https://doi.org/10.1145/3626202.3637571"},"language":"en","primary_location":{"id":"doi:10.1145/3626202.3637571","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3626202.3637571","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3626202.3637571","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 ACM/SIGDA International Symposium on Field Programmable Gate Arrays","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3626202.3637571","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5048999092","display_name":"Shaoxian Xu","orcid":"https://orcid.org/0000-0001-7580-0668"},"institutions":[{"id":"https://openalex.org/I4210123185","display_name":"Zhejiang Lab","ror":"https://ror.org/02m2h7991","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210123185"]},{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shaoxian Xu","raw_affiliation_strings":["Huazhong University of Science and Technology &amp; Zhejiang Lab, Wuhan, China"],"raw_orcid":"https://orcid.org/0000-0001-7580-0668","affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology &amp; Zhejiang Lab, Wuhan, China","institution_ids":["https://openalex.org/I4210123185","https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021790527","display_name":"S.-L. Lu","orcid":"https://orcid.org/0009-0002-8056-0309"},"institutions":[{"id":"https://openalex.org/I4210123185","display_name":"Zhejiang Lab","ror":"https://ror.org/02m2h7991","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210123185"]},{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sitong Lu","raw_affiliation_strings":["Huazhong University of Science and Technology &amp; Zhejiang Lab, Wuhan, China"],"raw_orcid":"https://orcid.org/0009-0002-8056-0309","affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology &amp; Zhejiang Lab, Wuhan, China","institution_ids":["https://openalex.org/I4210123185","https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066761150","display_name":"Zhiyuan Shao","orcid":"https://orcid.org/0000-0003-2139-6465"},"institutions":[{"id":"https://openalex.org/I4210123185","display_name":"Zhejiang Lab","ror":"https://ror.org/02m2h7991","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210123185"]},{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiyuan Shao","raw_affiliation_strings":["Huazhong University of Science and Technology &amp; Zhejiang Lab, Wuhan, China"],"raw_orcid":"https://orcid.org/0000-0003-2139-6465","affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology &amp; Zhejiang Lab, Wuhan, China","institution_ids":["https://openalex.org/I4210123185","https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022398389","display_name":"Xiaofei Liao","orcid":"https://orcid.org/0000-0001-6302-813X"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaofei Liao","raw_affiliation_strings":["Huazhong University of Science and Technology, Wuhan, China"],"raw_orcid":"https://orcid.org/0000-0001-6302-813X","affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022262922","display_name":"Hai Jin","orcid":"https://orcid.org/0000-0002-3934-7605"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hai Jin","raw_affiliation_strings":["Huazhong University of Science and Technology, Wuhan, China"],"raw_orcid":"https://orcid.org/0000-0002-3934-7605","affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":8,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"22","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":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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9998000264167786,"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/T10829","display_name":"Interconnection Networks and Systems","score":0.9994000196456909,"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/cache","display_name":"Cache","score":0.877892255783081},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8626037836074829},{"id":"https://openalex.org/keywords/cache-pollution","display_name":"Cache pollution","score":0.641139805316925},{"id":"https://openalex.org/keywords/cache-algorithms","display_name":"Cache algorithms","score":0.6252374649047852},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6092274188995361},{"id":"https://openalex.org/keywords/cache-coloring","display_name":"Cache coloring","score":0.5789787769317627},{"id":"https://openalex.org/keywords/cpu-cache","display_name":"CPU cache","score":0.49878787994384766},{"id":"https://openalex.org/keywords/cache-oblivious-algorithm","display_name":"Cache-oblivious algorithm","score":0.46236804127693176},{"id":"https://openalex.org/keywords/page-cache","display_name":"Page cache","score":0.43795448541641235},{"id":"https://openalex.org/keywords/blocking","display_name":"Blocking (statistics)","score":0.43526357412338257},{"id":"https://openalex.org/keywords/smart-cache","display_name":"Smart Cache","score":0.42461422085762024},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.379956990480423},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.15639671683311462}],"concepts":[{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.877892255783081},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8626037836074829},{"id":"https://openalex.org/C113166858","wikidata":"https://www.wikidata.org/wiki/Q5015981","display_name":"Cache pollution","level":5,"score":0.641139805316925},{"id":"https://openalex.org/C38556500","wikidata":"https://www.wikidata.org/wiki/Q13404475","display_name":"Cache algorithms","level":4,"score":0.6252374649047852},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6092274188995361},{"id":"https://openalex.org/C201148951","wikidata":"https://www.wikidata.org/wiki/Q5015976","display_name":"Cache coloring","level":4,"score":0.5789787769317627},{"id":"https://openalex.org/C189783530","wikidata":"https://www.wikidata.org/wiki/Q352090","display_name":"CPU cache","level":3,"score":0.49878787994384766},{"id":"https://openalex.org/C59687516","wikidata":"https://www.wikidata.org/wiki/Q5015938","display_name":"Cache-oblivious algorithm","level":5,"score":0.46236804127693176},{"id":"https://openalex.org/C36340418","wikidata":"https://www.wikidata.org/wiki/Q7124288","display_name":"Page cache","level":5,"score":0.43795448541641235},{"id":"https://openalex.org/C144745244","wikidata":"https://www.wikidata.org/wiki/Q4927286","display_name":"Blocking (statistics)","level":2,"score":0.43526357412338257},{"id":"https://openalex.org/C167713795","wikidata":"https://www.wikidata.org/wiki/Q352090","display_name":"Smart Cache","level":5,"score":0.42461422085762024},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.379956990480423},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.15639671683311462}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3626202.3637571","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3626202.3637571","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3626202.3637571","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 ACM/SIGDA International Symposium on Field Programmable Gate Arrays","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3626202.3637571","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3626202.3637571","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3626202.3637571","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 ACM/SIGDA International Symposium on Field Programmable Gate Arrays","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/8","display_name":"Decent work and economic growth","score":0.4000000059604645}],"awards":[{"id":"https://openalex.org/G3607577353","display_name":"FPGA\u56fe\u8ba1\u7b97\u52a0\u901f\u5668\u7684\u6027\u80fd\u6269\u5c55\u65b9\u6cd5\u7814\u7a76","funder_award_id":"61972444","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4393578448.pdf","grobid_xml":"https://content.openalex.org/works/W4393578448.grobid-xml"},"referenced_works_count":16,"referenced_works":["https://openalex.org/W2035080386","https://openalex.org/W2102885578","https://openalex.org/W2122862680","https://openalex.org/W2132292283","https://openalex.org/W2809221427","https://openalex.org/W2899915146","https://openalex.org/W2917336187","https://openalex.org/W2949537427","https://openalex.org/W2962953210","https://openalex.org/W3012279555","https://openalex.org/W3121413886","https://openalex.org/W3139689176","https://openalex.org/W3142900117","https://openalex.org/W3158338328","https://openalex.org/W3183258681","https://openalex.org/W3187809022"],"related_works":["https://openalex.org/W2098406302","https://openalex.org/W2535115842","https://openalex.org/W2734782074","https://openalex.org/W2546991807","https://openalex.org/W2020176098","https://openalex.org/W2436169747","https://openalex.org/W2116323004","https://openalex.org/W2121191383","https://openalex.org/W2076114130","https://openalex.org/W1584415117"],"abstract_inverted_index":{"On":[0],"FPGAs,":[1,222],"customizing":[2],"data":[3,167],"parallelism":[4],"can":[5],"significantly":[6],"improve":[7,171],"performances":[8],"of":[9,15,144,181,241],"applications.":[10,145],"However,":[11,82],"a":[12,148,158,176,205],"large":[13],"number":[14],"applications,":[16],"such":[17],"as":[18,102],"sparse":[19],"matrix":[20],"multiplication,":[21],"exhibit":[22],"irregular":[23],"memory":[24,36],"access":[25,37],"patterns,":[26],"for":[27,89,139,152,163],"which":[28,182],"further":[29,170],"improvements":[30],"are":[31,59],"limited":[32],"by":[33,79,232],"their":[34],"low":[35],"efficiency.":[38],"It":[39,92],"is":[40,105],"challenging":[41],"to":[42,48,61,70,134,215,234,247],"solve":[43],"using":[44,237],"traditional":[45],"caches":[46,64],"due":[47],"the":[49,72,80,130,136,142,172,184,190,193,216,229,238],"massive":[50],"cache":[51,73,121,124,153,219,225],"misses.":[52,81],"To":[53,169],"address":[54],"this,":[55],"prior":[56],"research":[57],"efforts":[58],"dedicated":[60],"developing":[62],"non-blocking":[63,120,218],"withMiss":[65],"Status":[66],"Holding":[67],"Registers":[68],"(MSHRs)":[69],"manage":[71],"misses":[74],"and":[75,98,126,154,160,166,189,200],"mitigate":[76],"stalls":[77],"caused":[78],"exsiting":[83],"approaches":[84],"allocate":[85],"dedicatedBlock":[86],"RAMs":[87],"(BRAMs)":[88],"implementing":[90],"MSHRs.":[91],"introduces":[93],"complexities":[94],"in":[95],"MSHR":[96,103,127,155],"configurations":[97],"potential":[99],"resource":[100],"inefficiencies,":[101],"demand":[104,138],"highly":[106],"dynamic":[107,137],"when":[108],"solving":[109],"real-world":[110],"problems.":[111],"In":[112],"this":[113],"paper,":[114],"we":[115,174],"present":[116],"MiCache,":[117],"an":[118],"MSHR-inclusive":[119],"design":[122,147,175,220],"where":[123],"entries":[125,128],"share":[129],"same":[131,239],"storage":[132,150],"spaces":[133],"support":[135],"MSHRs":[140],"during":[141],"executions":[143],"We":[146,198],"consistent":[149],"structure":[151],"entries,":[156],"ensuring":[157],"unified":[159],"efficient":[161],"mechanism":[162],"cache/MSHR":[164],"lookup":[165],"access.":[168],"performance,":[173],"parallel":[177],"dual":[178],"pipeline,":[179],"one":[180],"processes":[183,192],"requests":[185],"from":[186,195],"processing":[187],"elements,":[188],"other":[191],"responses":[194],"off-chip":[196],"memory.":[197],"implement":[199],"evaluate":[201],"our":[202],"proposal":[203],"on":[204,221],"Xilinx":[206],"Alveo":[207],"U280":[208],"board.":[209],"Evaluation":[210],"results":[211],"show":[212],"that,":[213],"compared":[214],"state-of-the-art":[217],"with":[223],"equivalent":[224],"configurations,":[226],"MiCache":[227,244],"reduces":[228],"BRAM":[230,242],"consumption":[231],"up":[233,246],"17%.":[235],"When":[236],"amount":[240],"resources,":[243],"achieves":[245],"1.56x":[248],"performance":[249],"improvement.":[250]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
