{"id":"https://openalex.org/W4395106386","doi":"https://doi.org/10.1145/3620666.3651381","title":"ACES: Accelerating Sparse Matrix Multiplication with Adaptive Execution Flow and Concurrency-Aware Cache Optimizations","display_name":"ACES: Accelerating Sparse Matrix Multiplication with Adaptive Execution Flow and Concurrency-Aware Cache Optimizations","publication_year":2024,"publication_date":"2024-04-24","ids":{"openalex":"https://openalex.org/W4395106386","doi":"https://doi.org/10.1145/3620666.3651381"},"language":"en","primary_location":{"id":"doi:10.1145/3620666.3651381","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3620666.3651381","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 3","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3620666.3651381","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5071271406","display_name":"Xiaoyang Lu","orcid":"https://orcid.org/0009-0005-9481-7234"},"institutions":[{"id":"https://openalex.org/I180949307","display_name":"Illinois Institute of Technology","ror":"https://ror.org/037t3ry66","country_code":"US","type":"education","lineage":["https://openalex.org/I180949307"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaoyang Lu","raw_affiliation_strings":["Illinois Institute of Technology, Chicago, United States of America"],"raw_orcid":"https://orcid.org/0009-0005-9481-7234","affiliations":[{"raw_affiliation_string":"Illinois Institute of Technology, Chicago, United States of America","institution_ids":["https://openalex.org/I180949307"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083896412","display_name":"Boyu Long","orcid":"https://orcid.org/0009-0002-5774-6893"},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Boyu Long","raw_affiliation_strings":["Institute of Computing Technology, Chinese Academy of Sciences, University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0002-5774-6893","affiliations":[{"raw_affiliation_string":"Institute of Computing Technology, Chinese Academy of Sciences, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100420361","display_name":"Xiaoming Chen","orcid":"https://orcid.org/0000-0002-7337-1844"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoming Chen","raw_affiliation_strings":["Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-7337-1844","affiliations":[{"raw_affiliation_string":"Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016864694","display_name":"Yinhe Han","orcid":"https://orcid.org/0000-0003-0904-6681"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yinhe Han","raw_affiliation_strings":["Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-0904-6681","affiliations":[{"raw_affiliation_string":"Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057665558","display_name":"Xian\u2010He Sun","orcid":"https://orcid.org/0000-0002-1093-0792"},"institutions":[{"id":"https://openalex.org/I180949307","display_name":"Illinois Institute of Technology","ror":"https://ror.org/037t3ry66","country_code":"US","type":"education","lineage":["https://openalex.org/I180949307"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xian-He Sun","raw_affiliation_strings":["Illinois Institute of Technology, Chicago, USA"],"raw_orcid":"https://orcid.org/0000-0002-1093-0792","affiliations":[{"raw_affiliation_string":"Illinois Institute of Technology, Chicago, USA","institution_ids":["https://openalex.org/I180949307"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.0223,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.96716004,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"71","last_page":"85"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9994999766349792,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9968000054359436,"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":0.8841670751571655},{"id":"https://openalex.org/keywords/concurrency","display_name":"Concurrency","score":0.6678544282913208},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6414783000946045},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.5396184921264648},{"id":"https://openalex.org/keywords/cache-algorithms","display_name":"Cache algorithms","score":0.46300533413887024},{"id":"https://openalex.org/keywords/locality","display_name":"Locality","score":0.4306184649467468},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.4066859483718872},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.3647780120372772},{"id":"https://openalex.org/keywords/cpu-cache","display_name":"CPU cache","score":0.3508104979991913}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8841670751571655},{"id":"https://openalex.org/C193702766","wikidata":"https://www.wikidata.org/wiki/Q1414548","display_name":"Concurrency","level":2,"score":0.6678544282913208},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6414783000946045},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.5396184921264648},{"id":"https://openalex.org/C38556500","wikidata":"https://www.wikidata.org/wiki/Q13404475","display_name":"Cache algorithms","level":4,"score":0.46300533413887024},{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.4306184649467468},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4066859483718872},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.3647780120372772},{"id":"https://openalex.org/C189783530","wikidata":"https://www.wikidata.org/wiki/Q352090","display_name":"CPU cache","level":3,"score":0.3508104979991913},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3620666.3651381","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3620666.3651381","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 3","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3620666.3651381","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3620666.3651381","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 3","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4444615682","display_name":null,"funder_award_id":"62025404","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4528313372","display_name":"Collaborative Research: PPoSS: Planning: Towards an Integrated, Full-stack System for Memory-centric Computing","funder_award_id":"2029014","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G504268425","display_name":"Collaborative Research: SHF: Small: Optimization of Memory Architectures: A Foundation Approach","funder_award_id":"2008907","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G534854344","display_name":null,"funder_award_id":"62122076","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5592980734","display_name":"CNS Core: Small: Practical Memory Access Pattern Obfuscation with Algorithm, Application and Architecture Co-designs","funder_award_id":"2152497","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7069841724","display_name":"Collaborative Research: CSR: Medium: Towards A Unified Memory-centric Computing System with Cross-layer Support","funder_award_id":"2310422","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7683272049","display_name":null,"funder_award_id":"ZDBS-LY-JSC012","funder_id":"https://openalex.org/F4320338202","funder_display_name":"Key Research Program of Frontier Science, Chinese Academy of Sciences"},{"id":"https://openalex.org/G818288671","display_name":null,"funder_award_id":"2018YFA0701500","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null},{"id":"https://openalex.org/F4320338202","display_name":"Key Research Program of Frontier Science, Chinese Academy of Sciences","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":56,"referenced_works":["https://openalex.org/W1526797232","https://openalex.org/W1555915743","https://openalex.org/W1589265174","https://openalex.org/W1980282429","https://openalex.org/W1987225815","https://openalex.org/W1992432622","https://openalex.org/W1994687200","https://openalex.org/W2035080386","https://openalex.org/W2037392185","https://openalex.org/W2060108852","https://openalex.org/W2093825995","https://openalex.org/W2095249664","https://openalex.org/W2096169320","https://openalex.org/W2120230074","https://openalex.org/W2120692212","https://openalex.org/W2121711421","https://openalex.org/W2126274747","https://openalex.org/W2152290683","https://openalex.org/W2154111453","https://openalex.org/W2285660444","https://openalex.org/W2606722458","https://openalex.org/W2626696598","https://openalex.org/W2725179571","https://openalex.org/W2732588537","https://openalex.org/W2765234579","https://openalex.org/W2794952988","https://openalex.org/W2900228909","https://openalex.org/W2904902077","https://openalex.org/W2917336187","https://openalex.org/W2979310060","https://openalex.org/W2980104813","https://openalex.org/W3016542674","https://openalex.org/W3016832937","https://openalex.org/W3040024858","https://openalex.org/W3091512799","https://openalex.org/W3103168911","https://openalex.org/W3117515082","https://openalex.org/W3155922894","https://openalex.org/W3158831985","https://openalex.org/W3184376546","https://openalex.org/W3191660382","https://openalex.org/W3213528054","https://openalex.org/W4200139702","https://openalex.org/W4234552385","https://openalex.org/W4280557024","https://openalex.org/W4289441319","https://openalex.org/W4309620166","https://openalex.org/W4317815260","https://openalex.org/W4318540786","https://openalex.org/W4327930477","https://openalex.org/W4360832006","https://openalex.org/W4362566383","https://openalex.org/W4380875466","https://openalex.org/W4393406936","https://openalex.org/W6640289440","https://openalex.org/W6723833011"],"related_works":["https://openalex.org/W2147122795","https://openalex.org/W2061075966","https://openalex.org/W3147501184","https://openalex.org/W2167303720","https://openalex.org/W2268996566","https://openalex.org/W2109715593","https://openalex.org/W3161817247","https://openalex.org/W2012518269","https://openalex.org/W2068309140","https://openalex.org/W4239937081"],"abstract_inverted_index":{"Sparse":[0],"matrix-matrix":[1],"multiplication":[2],"(SpMM)":[3],"is":[4,151],"a":[5,70,113,132,185,190],"critical":[6],"computational":[7,143],"kernel":[8],"in":[9,49,74,193],"numerous":[10],"scientific":[11],"and":[12,22,59,99,122,141,170,188],"machine":[13],"learning":[14],"applications.":[15],"SpMM":[16,33,40,44,72,194],"involves":[17],"massive":[18],"irregular":[19],"memory":[20],"accesses":[21],"poses":[23],"great":[24],"challenges":[25,48],"to":[26,38,51,87,153],"conventional":[27],"cache-based":[28],"computer":[29],"architectures.":[30],"Recently":[31],"dedicated":[32],"accelerators":[34,45],"have":[35],"been":[36],"proposed":[37],"enhance":[39],"performance.":[41,62],"However,":[42],"current":[43],"still":[46],"face":[47],"adapting":[50],"varied":[52],"sparse":[53,89],"patterns,":[54],"fully":[55],"exploiting":[56],"inherent":[57],"parallelism,":[58],"optimizing":[60],"cache":[61,115,138,168],"To":[63],"address":[64],"these":[65],"issues,":[66],"we":[67],"introduce":[68],"ACES,":[69],"novel":[71],"accelerator":[73],"this":[75],"study.":[76],"First,":[77],"ACES":[78,103,111,150,179],"features":[79],"an":[80],"adaptive":[81,92,164],"execution":[82,93,165],"flow":[83,94],"that":[84,178],"dynamically":[85],"adjusts":[86],"diverse":[88],"patterns.":[90],"The":[91,157],"balances":[95],"parallel":[96,172],"computing":[97],"efficiency":[98],"data":[100,120],"reuse.":[101],"Second,":[102],"incorporates":[104],"locality-concurrency":[105],"co-optimizations":[106],"within":[107],"the":[108,129,136,146,163],"global":[109,137],"cache.":[110],"utilizes":[112],"concurrency-aware":[114],"management":[116],"policy,":[117],"which":[118],"considers":[119],"locality":[121],"concurrency":[123,140],"for":[124],"optimal":[125],"replacement":[126],"decisions.":[127],"Additionally,":[128],"integration":[130],"of":[131,149],"non-blocking":[133],"buffer":[134],"with":[135],"enhances":[139],"reduces":[142],"stalls.":[144],"Third,":[145],"hardware":[147],"architecture":[148,158],"designed":[152],"integrate":[154],"all":[155],"innovations.":[156],"ensures":[159],"efficient":[160],"support":[161],"across":[162],"flow,":[166],"advanced":[167],"optimizations,":[169],"fine-grained":[171],"processing.":[173],"Our":[174],"performance":[175],"evaluation":[176],"demonstrates":[177],"significantly":[180],"outperforms":[181],"existing":[182],"solutions,":[183],"providing":[184],"2.1\u00d7":[186],"speedup":[187],"marking":[189],"substantial":[191],"advancement":[192],"acceleration.":[195]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":1}],"updated_date":"2026-08-16T07:02:28.622633","created_date":"2025-10-10T00:00:00"}
