{"id":"https://openalex.org/W4400907330","doi":"https://doi.org/10.1109/tpds.2024.3432579","title":"IrGEMM: An Input-Aware Tuning Framework for Irregular GEMM on ARM and X86 CPUs","display_name":"IrGEMM: An Input-Aware Tuning Framework for Irregular GEMM on ARM and X86 CPUs","publication_year":2024,"publication_date":"2024-07-23","ids":{"openalex":"https://openalex.org/W4400907330","doi":"https://doi.org/10.1109/tpds.2024.3432579"},"language":"en","primary_location":{"id":"doi:10.1109/tpds.2024.3432579","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2024.3432579","pdf_url":null,"source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Parallel and Distributed Systems","raw_type":"journal-article"},"type":"article","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/A5039652101","display_name":"Cunyang Wei","orcid":"https://orcid.org/0009-0001-8910-4951"},"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":"Cunyang Wei","raw_affiliation_strings":["Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0001-8910-4951","affiliations":[{"raw_affiliation_string":"Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101816350","display_name":"Haipeng Jia","orcid":"https://orcid.org/0000-0002-9855-5367"},"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":"Haipeng Jia","raw_affiliation_strings":["State Key Lab of Processors, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-9855-5367","affiliations":[{"raw_affiliation_string":"State Key Lab of Processors, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016255357","display_name":"Yunquan Zhang","orcid":"https://orcid.org/0000-0001-7520-9640"},"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":"Yunquan Zhang","raw_affiliation_strings":["Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-7520-9640","affiliations":[{"raw_affiliation_string":"Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100639385","display_name":"Jianyu Yao","orcid":"https://orcid.org/0009-0003-2889-4499"},"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":"Jianyu Yao","raw_affiliation_strings":["Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028785761","display_name":"Chendi Li","orcid":"https://orcid.org/0009-0000-2610-042X"},"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":"Chendi Li","raw_affiliation_strings":["Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0000-2610-042X","affiliations":[{"raw_affiliation_string":"Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101054651","display_name":"Wenxuan Cao","orcid":null},"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":"Wenxuan Cao","raw_affiliation_strings":["Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.7719,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.85221063,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":"35","issue":"9","first_page":"1672","last_page":"1689"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9973000288009644,"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":0.9973000288009644,"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":0.973800003528595,"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/x86","display_name":"x86","score":0.8910660743713379},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8571404218673706},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7170906066894531},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.32620877027511597},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.26237645745277405},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.11080121994018555}],"concepts":[{"id":"https://openalex.org/C170723468","wikidata":"https://www.wikidata.org/wiki/Q182933","display_name":"x86","level":3,"score":0.8910660743713379},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8571404218673706},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7170906066894531},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.32620877027511597},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.26237645745277405},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.11080121994018555}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tpds.2024.3432579","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2024.3432579","pdf_url":null,"source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Parallel and Distributed Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4559757919","display_name":null,"funder_award_id":"62372432","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W1983157164","https://openalex.org/W2038080797","https://openalex.org/W2073061372","https://openalex.org/W2084379367","https://openalex.org/W2091087653","https://openalex.org/W2183156981","https://openalex.org/W2252007067","https://openalex.org/W2268122618","https://openalex.org/W2293241800","https://openalex.org/W2516525699","https://openalex.org/W2753648062","https://openalex.org/W2782326306","https://openalex.org/W2786374423","https://openalex.org/W2805108849","https://openalex.org/W2949953997","https://openalex.org/W2951894856","https://openalex.org/W2971383048","https://openalex.org/W3048263222","https://openalex.org/W3099506637","https://openalex.org/W3145384893","https://openalex.org/W3210601829","https://openalex.org/W4200572757","https://openalex.org/W4244254628","https://openalex.org/W4249716558","https://openalex.org/W4285327612","https://openalex.org/W4289276774","https://openalex.org/W4320067944","https://openalex.org/W4361733329","https://openalex.org/W4385245566","https://openalex.org/W6713134421","https://openalex.org/W6745834200","https://openalex.org/W6756580189"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W1992604140","https://openalex.org/W1990800384","https://openalex.org/W2766023593","https://openalex.org/W2091202943","https://openalex.org/W4386211790","https://openalex.org/W4388466106","https://openalex.org/W2463487949","https://openalex.org/W2053400496"],"abstract_inverted_index":{"The":[0,75,87,107],"matrix":[1,35,44,68],"multiplication":[2,45,69],"algorithm":[3,113],"is":[4],"a":[5,14,111],"fundamental":[6],"numerical":[7],"technique":[8],"in":[9,17],"linear":[10,29],"algebra":[11,30],"and":[12,61,72,83,103,123,162],"plays":[13],"crucial":[15],"role":[16],"many":[18],"scientific":[19],"computing":[20],"applications.":[21],"Despite":[22],"the":[23,80,84,120,138,147],"high":[24],"performance":[25,40,154],"of":[26,141],"mainstream":[27,168],"basic":[28],"libraries":[31],"for":[32,58,99,115,156],"large-scale":[33],"dense":[34],"multiplications,":[36],"they":[37],"exhibit":[38],"poor":[39],"when":[41],"applied":[42],"to":[43,64,95,118,136,166],"with":[46],"irregular":[47,67,116,157],"input.":[48],"This":[49],"paper":[50],"proposes":[51],"an":[52,126],"input-aware":[53],"tuning":[54],"framework":[55,76,150],"that":[56,146],"accounts":[57],"application":[59],"scenarios":[60],"computer":[62],"architectures":[63],"provide":[65],"high-performance":[66,97],"on":[70,159],"ARMv8":[71,161],"X86":[73,163],"CPUs.":[74],"comprises":[77],"two":[78],"stages:":[79],"install-time":[81,88],"stage":[82,89,109],"run-time":[85,108],"stage.":[86],"utilizes":[90,110],"our":[91],"proposed":[92,148],"computational":[93],"template":[94],"generate":[96],"kernels":[98],"general":[100],"data":[101,105],"layout":[102],"SIMD-friendly":[104],"layout.":[106],"tiling":[112],"suitable":[114],"GEMM":[117,158],"select":[119],"optimal":[121],"kernel":[122],"link":[124],"as":[125],"execution":[127],"plan.":[128],"Additionally,":[129],"load-balanced":[130],"multi-threaded":[131],"optimization":[132],"algorithms":[133],"are":[134],"defined":[135],"exploit":[137],"multi-threading":[139],"capability":[140],"modern":[142],"processors.":[143],"Experiments":[144],"demonstrate":[145],"IrGEMM":[149],"can":[151],"achieve":[152],"significant":[153],"improvements":[155],"both":[160],"CPUs":[164],"compared":[165],"other":[167],"BLAS":[169],"libraries.":[170]},"counts_by_year":[{"year":2025,"cited_by_count":4}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
