{"id":"https://openalex.org/W7131070069","doi":"https://doi.org/10.1109/cgo68049.2026.11395201","title":"SparseX: Synergizing GPU Libraries for Sparse Matrix Multiplication on Heterogeneous Processors","display_name":"SparseX: Synergizing GPU Libraries for Sparse Matrix Multiplication on Heterogeneous Processors","publication_year":2026,"publication_date":"2026-01-31","ids":{"openalex":"https://openalex.org/W7131070069","doi":"https://doi.org/10.1109/cgo68049.2026.11395201"},"language":null,"primary_location":{"id":"doi:10.1109/cgo68049.2026.11395201","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cgo68049.2026.11395201","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/ACM International Symposium on Code Generation and Optimization (CGO)","raw_type":"proceedings-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/A5081747758","display_name":"Ruifeng Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I137902535","display_name":"North Carolina State University","ror":"https://ror.org/04tj63d06","country_code":"US","type":"education","lineage":["https://openalex.org/I137902535"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Ruifeng Zhang","raw_affiliation_strings":["North Carolina State University,Department of Computer Science,Raleigh,NC,USA"],"affiliations":[{"raw_affiliation_string":"North Carolina State University,Department of Computer Science,Raleigh,NC,USA","institution_ids":["https://openalex.org/I137902535"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101688508","display_name":"Xiangwei Wang","orcid":"https://orcid.org/0009-0001-3649-0852"},"institutions":[{"id":"https://openalex.org/I137902535","display_name":"North Carolina State University","ror":"https://ror.org/04tj63d06","country_code":"US","type":"education","lineage":["https://openalex.org/I137902535"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiangwei Wang","raw_affiliation_strings":["North Carolina State University,Department of Computer Science,Raleigh,NC,USA"],"affiliations":[{"raw_affiliation_string":"North Carolina State University,Department of Computer Science,Raleigh,NC,USA","institution_ids":["https://openalex.org/I137902535"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126629322","display_name":"Ang Li","orcid":null},"institutions":[{"id":"https://openalex.org/I1286936699","display_name":"Pacific Northwest Diabetes Research Institute","ror":"https://ror.org/03x0d4x24","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1286936699"]},{"id":"https://openalex.org/I142606810","display_name":"Pacific Northwest National Laboratory","ror":"https://ror.org/05h992307","country_code":"US","type":"facility","lineage":["https://openalex.org/I1325736334","https://openalex.org/I1330989302","https://openalex.org/I142606810","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ang Li","raw_affiliation_strings":["Pacific Northwest National Laboratory and University of Washington,Seattle,WA,USA"],"affiliations":[{"raw_affiliation_string":"Pacific Northwest National Laboratory and University of Washington,Seattle,WA,USA","institution_ids":["https://openalex.org/I142606810","https://openalex.org/I1286936699"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5126604611","display_name":"Xipeng Shen","orcid":null},"institutions":[{"id":"https://openalex.org/I137902535","display_name":"North Carolina State University","ror":"https://ror.org/04tj63d06","country_code":"US","type":"education","lineage":["https://openalex.org/I137902535"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xipeng Shen","raw_affiliation_strings":["North Carolina State University,Department of Computer Science,Raleigh,NC,USA"],"affiliations":[{"raw_affiliation_string":"North Carolina State University,Department of Computer Science,Raleigh,NC,USA","institution_ids":["https://openalex.org/I137902535"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5081747758"],"corresponding_institution_ids":["https://openalex.org/I137902535"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.30784766,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"453","last_page":"465"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.8282999992370605,"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":0.8282999992370605,"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/T11697","display_name":"Numerical Methods and Algorithms","score":0.02329999953508377,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T10363","display_name":"Low-power high-performance VLSI design","score":0.020899999886751175,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.7940999865531921},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.6320000290870667},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.5454999804496765},{"id":"https://openalex.org/keywords/multiplication","display_name":"Multiplication (music)","score":0.4634999930858612},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.44179999828338623},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.4359999895095825},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.414900004863739},{"id":"https://openalex.org/keywords/ranging","display_name":"Ranging","score":0.39959999918937683}],"concepts":[{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.7940999865531921},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7914000153541565},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.6320000290870667},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6169000267982483},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.5454999804496765},{"id":"https://openalex.org/C2780595030","wikidata":"https://www.wikidata.org/wiki/Q3860309","display_name":"Multiplication (music)","level":2,"score":0.4634999930858612},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.44179999828338623},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.4359999895095825},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.414900004863739},{"id":"https://openalex.org/C115051666","wikidata":"https://www.wikidata.org/wiki/Q6522493","display_name":"Ranging","level":2,"score":0.39959999918937683},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.3917999863624573},{"id":"https://openalex.org/C155281189","wikidata":"https://www.wikidata.org/wiki/Q3518150","display_name":"Tensor (intrinsic definition)","level":2,"score":0.36000001430511475},{"id":"https://openalex.org/C32833848","wikidata":"https://www.wikidata.org/wiki/Q4115054","display_name":"Extensibility","level":2,"score":0.3589000105857849},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.3513999879360199},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.35010001063346863},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.32919999957084656},{"id":"https://openalex.org/C14185376","wikidata":"https://www.wikidata.org/wiki/Q30232","display_name":"Agile software development","level":2,"score":0.31630000472068787},{"id":"https://openalex.org/C164620267","wikidata":"https://www.wikidata.org/wiki/Q376953","display_name":"Adder","level":3,"score":0.3009999990463257},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.28769999742507935},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.27709999680519104},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.27410000562667847},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.26409998536109924},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.26260000467300415}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cgo68049.2026.11395201","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cgo68049.2026.11395201","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/ACM International Symposium on Code Generation and Optimization (CGO)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1783256592","https://openalex.org/W2295598076","https://openalex.org/W2590246587","https://openalex.org/W2788264912","https://openalex.org/W2965706220","https://openalex.org/W2979310060","https://openalex.org/W2980186997","https://openalex.org/W2995872593","https://openalex.org/W3130660608","https://openalex.org/W3132695675","https://openalex.org/W3158112431","https://openalex.org/W4200090124","https://openalex.org/W4320063610","https://openalex.org/W4321466355","https://openalex.org/W4386709686","https://openalex.org/W4388667495","https://openalex.org/W4390097706","https://openalex.org/W4392266035","https://openalex.org/W4395106472","https://openalex.org/W4401090539","https://openalex.org/W4401408710"],"related_works":[],"abstract_inverted_index":{"Sparse":[0,37],"Matrix-Matrix":[1],"Multiplication":[2],"(SpMM)":[3],"on":[4,88,136,144,163],"GPU":[5,146,172],"is":[6,78,117],"critical":[7],"to":[8,14,46,98,103,190,193],"applications":[9],"ranging":[10],"from":[11],"scientific":[12],"simulations":[13],"Graph":[15],"Neural":[16,21],"Networks":[17,22],"(GNNs)":[18],"and":[19,36,65,85,109,197],"Deep":[20],"(DNNs).":[23],"Modern":[24],"GPUs":[25],"offer":[26],"diverse":[27],"processing":[28],"units,":[29],"such":[30],"as":[31,178,180],"CUDA":[32],"cores,":[33],"Tensor":[34,38],"Cores,":[35],"Cores.":[39],"Many":[40],"SpMM":[41],"libraries":[42,102,196],"have":[43],"been":[44,57],"built":[45],"harness":[47,105],"those":[48],"different":[49],"types":[50,133],"of":[51,112,134,165],"processors.":[52],"Although":[53],"impressive":[54],"performance":[55],"has":[56],"reported":[58],"by":[59],"each,":[60],"including":[61],"cuSparse,":[62],"Sputnik,":[63],"CLASP,":[64],"Jigsaw,":[66],"a":[67,79,140,145],"systematic":[68],"study":[69],"in":[70],"this":[71,92],"work":[72,93],"shows":[73],"that":[74,123,155],"no":[75],"single":[76],"library":[77,131],"clear":[80],"winner":[81],"across":[82],"all":[83],"matrices":[84,167],"scenarios.":[86],"Based":[87],"the":[89,95,100,106,110,127,137,170],"empirical":[90],"observations,":[91],"proposes":[94],"first":[96],"solution":[97,116],"synergize":[99],"various":[101],"best":[104,128],"heterogeneous":[107],"processors":[108],"array":[111],"cutting-edge":[113],"libraries.":[114],"The":[115],"an":[118,148],"extensible":[119,185],"framework,":[120],"namely":[121],"SparseX,":[122],"can":[124,157],"automatically":[125],"select":[126],"matrix":[129,143,161],"multiplication":[130],"(and":[132],"processors)":[135],"fly":[138],"for":[139],"given":[141],"sparse":[142,160],"through":[147],"agile":[149],"accurate":[150],"predictive":[151],"model.":[152],"Experiments":[153],"show":[154],"SparseX":[156],"speed":[158],"up":[159],"multiplications":[162],"thousands":[164],"real-world":[166],"significantly":[168],"over":[169,182],"SOTA":[171],"libraries,":[173],"achieving":[174],"significant":[175],"speedups":[176],"(e.g.,":[177],"much":[179],"95.34x":[181],"cuSparse).":[183],"Its":[184],"design":[186],"makes":[187],"it":[188],"easy":[189],"be":[191],"extended":[192],"cover":[194],"new":[195],"hardware":[198],"architectures.":[199]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2026-02-24T00:00:00"}