{"id":"https://openalex.org/W4392265904","doi":"https://doi.org/10.1109/cgo57630.2024.10444827","title":"JITSPMM: Just-in-Time Instruction Generation for Accelerated Sparse Matrix-Matrix Multiplication","display_name":"JITSPMM: Just-in-Time Instruction Generation for Accelerated Sparse Matrix-Matrix Multiplication","publication_year":2024,"publication_date":"2024-02-28","ids":{"openalex":"https://openalex.org/W4392265904","doi":"https://doi.org/10.1109/cgo57630.2024.10444827"},"language":"en","primary_location":{"id":"doi:10.1109/cgo57630.2024.10444827","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cgo57630.2024.10444827","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/ACM International Symposium on Code Generation and Optimization (CGO)","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/A5060623990","display_name":"Qiang Fu","orcid":"https://orcid.org/0000-0002-0594-8832"},"institutions":[{"id":"https://openalex.org/I4210137977","display_name":"Advanced Micro Devices (United States)","ror":"https://ror.org/04kd6c783","country_code":"US","type":"company","lineage":["https://openalex.org/I4210137977"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Qiang Fu","raw_affiliation_strings":["Advanced Micro Devices Inc.,Austin,TX,USA","Advanced Micro Devices Inc., Austin, TX, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Advanced Micro Devices Inc.,Austin,TX,USA","institution_ids":["https://openalex.org/I4210137977"]},{"raw_affiliation_string":"Advanced Micro Devices Inc., Austin, TX, USA","institution_ids":["https://openalex.org/I4210137977"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026169135","display_name":"Thomas B. Rolinger","orcid":"https://orcid.org/0000-0001-8383-4737"},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Thomas B. Rolinger","raw_affiliation_strings":["NVIDIA,Austin,TX,USA","NVIDIA, Austin, TX, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA,Austin,TX,USA","institution_ids":["https://openalex.org/I4210127875"]},{"raw_affiliation_string":"NVIDIA, Austin, TX, USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002254350","display_name":"H. Howie Huang","orcid":"https://orcid.org/0000-0001-8588-7680"},"institutions":[{"id":"https://openalex.org/I193531525","display_name":"George Washington University","ror":"https://ror.org/00y4zzh67","country_code":"US","type":"education","lineage":["https://openalex.org/I193531525"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"H. Howie Huang","raw_affiliation_strings":["George Washington University,Washington, DC,USA","George Washington University, Washington, DC, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"George Washington University,Washington, DC,USA","institution_ids":["https://openalex.org/I193531525"]},{"raw_affiliation_string":"George Washington University, Washington, DC, USA","institution_ids":["https://openalex.org/I193531525"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"448","last_page":"459"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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/T12808","display_name":"Ferroelectric and Negative Capacitance Devices","score":0.9984999895095825,"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/T10829","display_name":"Interconnection Networks and Systems","score":0.9934999942779541,"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":0.8572183847427368},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6717309355735779},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.6250973343849182},{"id":"https://openalex.org/keywords/simd","display_name":"SIMD","score":0.5781972408294678},{"id":"https://openalex.org/keywords/workload","display_name":"Workload","score":0.5046848058700562},{"id":"https://openalex.org/keywords/instruction-set","display_name":"Instruction set","score":0.5040737390518188},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.3215540647506714},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.1764371395111084}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8572183847427368},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6717309355735779},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.6250973343849182},{"id":"https://openalex.org/C150552126","wikidata":"https://www.wikidata.org/wiki/Q339387","display_name":"SIMD","level":2,"score":0.5781972408294678},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.5046848058700562},{"id":"https://openalex.org/C202491316","wikidata":"https://www.wikidata.org/wiki/Q272683","display_name":"Instruction set","level":2,"score":0.5040737390518188},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.3215540647506714},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.1764371395111084},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"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/C84114770","wikidata":"https://www.wikidata.org/wiki/Q46344","display_name":"Quantum","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cgo57630.2024.10444827","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cgo57630.2024.10444827","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/ACM International Symposium on Code Generation and Optimization (CGO)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G807676689","display_name":"SHF: Small: Towards High-Performance Machine Learning on Graphs","funder_award_id":"2127207","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":54,"referenced_works":["https://openalex.org/W143174683","https://openalex.org/W182691100","https://openalex.org/W1556859836","https://openalex.org/W1749918898","https://openalex.org/W1987840949","https://openalex.org/W2035080386","https://openalex.org/W2040404421","https://openalex.org/W2054141820","https://openalex.org/W2085248745","https://openalex.org/W2087507944","https://openalex.org/W2088866486","https://openalex.org/W2129094586","https://openalex.org/W2129393463","https://openalex.org/W2143588523","https://openalex.org/W2249320699","https://openalex.org/W2271295020","https://openalex.org/W2461018655","https://openalex.org/W2626696598","https://openalex.org/W2725179571","https://openalex.org/W2734941459","https://openalex.org/W2753189782","https://openalex.org/W2808128431","https://openalex.org/W2914631005","https://openalex.org/W2963757395","https://openalex.org/W2964337156","https://openalex.org/W2979310060","https://openalex.org/W2980186997","https://openalex.org/W2996268457","https://openalex.org/W3003257820","https://openalex.org/W3090369187","https://openalex.org/W3132695675","https://openalex.org/W3148529197","https://openalex.org/W3152893301","https://openalex.org/W3169307980","https://openalex.org/W3173204484","https://openalex.org/W3201678711","https://openalex.org/W4239331546","https://openalex.org/W4241608695","https://openalex.org/W4247828381","https://openalex.org/W4281691175","https://openalex.org/W4283377648","https://openalex.org/W4287829537","https://openalex.org/W4288419263","https://openalex.org/W4290648346","https://openalex.org/W4307887693","https://openalex.org/W4327911434","https://openalex.org/W4385567855","https://openalex.org/W6633830849","https://openalex.org/W6748856961","https://openalex.org/W6754777574","https://openalex.org/W6760045743","https://openalex.org/W6767710714","https://openalex.org/W6771932116","https://openalex.org/W6774097426"],"related_works":["https://openalex.org/W2291920536","https://openalex.org/W2022397046","https://openalex.org/W2162726111","https://openalex.org/W1603583590","https://openalex.org/W338671845","https://openalex.org/W1587248296","https://openalex.org/W2117755361","https://openalex.org/W2286348849","https://openalex.org/W2063770303","https://openalex.org/W2018511057"],"abstract_inverted_index":{"Achieving":[0],"high":[1],"performance":[2,185],"for":[3,35,55,125],"Sparse":[4],"Matrix-Matrix":[5],"Multiplication":[6],"(SpMM)":[7],"has":[8],"received":[9],"increasing":[10],"research":[11],"attention,":[12],"especially":[13],"on":[14,104],"multi-core":[15,105],"CPUs,":[16],"due":[17],"to":[18,80,100,127,150,164,169,178],"the":[19,39,74,113,137,156,203,212],"large":[20],"input":[21],"data":[22,168],"size":[23],"in":[24],"applications":[25],"such":[26],"as":[27],"graph":[28],"neural":[29],"networks":[30],"(GNNs).":[31],"Most":[32],"existing":[33,198],"solutions":[34],"SpMM":[36,56,81,102,126,199,214],"computation":[37,103],"follow":[38],"ahead-of-time":[40],"(AOT)":[41],"compilation":[42,54],"approach,":[43],"which":[44],"compiles":[45],"a":[46,93,144,184],"program":[47],"entirely":[48],"before":[49],"it":[50,191],"is":[51,82],"executed.":[52],"AOT":[53,193],"faces":[57],"three":[58,120],"key":[59],"limitations:":[60],"unnecessary":[61],"memory":[62,171],"access,":[63],"additional":[64],"branch":[65],"overhead,":[66],"and":[67,173,189,231],"redundant":[68],"instructions.":[69],"These":[70],"limitations":[71],"stem":[72],"from":[73],"fact":[75],"that":[76,223],"crucial":[77],"information":[78],"pertaining":[79],"not":[83],"known":[84],"until":[85],"runtime.":[86],"In":[87],"this":[88],"paper,":[89],"we":[90],"propose":[91],"JITSpMM,":[92],"just-in-time":[94],"(JIT)":[95],"assembly":[96,115],"code":[97,116],"generation":[98,117],"framework":[99],"accelerated":[101],"CPUs":[106],"with":[107,136,207],"SIMD":[108,176],"extensions.":[109],"First,":[110],"JITSpMM":[111,142,160,188,224],"integrates":[112],"JIT":[114],"technique":[118],"into":[119],"widely-used":[121],"workload":[122,130],"division":[123],"methods":[124],"achieve":[128],"balanced":[129],"distribution":[131],"among":[132],"CPU":[133],"threads.":[134],"Next,":[135],"availability":[138],"of":[139,187,229],"runtime":[140],"information,":[141],"employs":[143,174],"novel":[145],"technique,":[146],"coarse-grain":[147],"column":[148],"merging,":[149],"maximize":[151],"instruction-level":[152],"parallelism":[153],"by":[154,217],"unrolling":[155],"performance-critical":[157],"loop.":[158],"Furthermore,":[159],"intelligently":[161],"allocates":[162],"registers":[163],"cache":[165],"frequently":[166],"accessed":[167],"minimizing":[170],"accesses,":[172],"selected":[175],"instructions":[177],"enhance":[179],"arithmetic":[180],"throughput.":[181],"We":[182],"conduct":[183],"evaluation":[186],"compare":[190],"two":[192],"baselines.":[194],"The":[195,209],"first":[196],"involves":[197],"implementations":[200],"compiled":[201],"using":[202],"Intel":[204,218],"icc":[205],"compiler":[206],"auto-vectorization.":[208],"second":[210],"utilizes":[211],"highly-optimized":[213],"routine":[215],"provided":[216],"MKL.":[219],"Our":[220],"results":[221],"show":[222],"provides":[225],"an":[226],"average":[227],"improvement":[228],"3.8\u00d7":[230],"1.4\u00d7,":[232],"respectively.":[233]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}