{"id":"https://openalex.org/W7133496162","doi":"https://doi.org/10.1109/hpca68181.2026.11408500","title":"Uni-STC: Unified Sparse Tensor Core","display_name":"Uni-STC: Unified Sparse Tensor Core","publication_year":2026,"publication_date":"2026-01-31","ids":{"openalex":"https://openalex.org/W7133496162","doi":"https://doi.org/10.1109/hpca68181.2026.11408500"},"language":null,"primary_location":{"id":"doi:10.1109/hpca68181.2026.11408500","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpca68181.2026.11408500","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE International Symposium on High Performance Computer Architecture (HPCA)","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/A5059172019","display_name":"Haocheng Lian","orcid":null},"institutions":[{"id":"https://openalex.org/I204553293","display_name":"China University of Petroleum, Beijing","ror":"https://ror.org/041qf4r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I204553293"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Haocheng Lian","raw_affiliation_strings":["China University of Petroleum-Beijing,Super Scientific Software Laboratory,Department of CST,Beijing,China"],"affiliations":[{"raw_affiliation_string":"China University of Petroleum-Beijing,Super Scientific Software Laboratory,Department of CST,Beijing,China","institution_ids":["https://openalex.org/I204553293"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128079905","display_name":"Qiyue Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I204553293","display_name":"China University of Petroleum, Beijing","ror":"https://ror.org/041qf4r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I204553293"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiyue Zhang","raw_affiliation_strings":["China University of Petroleum-Beijing,Super Scientific Software Laboratory,Department of CST,Beijing,China"],"affiliations":[{"raw_affiliation_string":"China University of Petroleum-Beijing,Super Scientific Software Laboratory,Department of CST,Beijing,China","institution_ids":["https://openalex.org/I204553293"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128114758","display_name":"Xinran Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I204553293","display_name":"China University of Petroleum, Beijing","ror":"https://ror.org/041qf4r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I204553293"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinran Zhao","raw_affiliation_strings":["China University of Petroleum-Beijing,Super Scientific Software Laboratory,Department of CST,Beijing,China"],"affiliations":[{"raw_affiliation_string":"China University of Petroleum-Beijing,Super Scientific Software Laboratory,Department of CST,Beijing,China","institution_ids":["https://openalex.org/I204553293"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080604666","display_name":"Meichen Dong","orcid":"https://orcid.org/0000-0001-9437-9290"},"institutions":[{"id":"https://openalex.org/I204553293","display_name":"China University of Petroleum, Beijing","ror":"https://ror.org/041qf4r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I204553293"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Meichen Dong","raw_affiliation_strings":["China University of Petroleum-Beijing,Super Scientific Software Laboratory,Department of CST,Beijing,China"],"affiliations":[{"raw_affiliation_string":"China University of Petroleum-Beijing,Super Scientific Software Laboratory,Department of CST,Beijing,China","institution_ids":["https://openalex.org/I204553293"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5117092202","display_name":"Yijie Nie","orcid":null},"institutions":[{"id":"https://openalex.org/I204553293","display_name":"China University of Petroleum, Beijing","ror":"https://ror.org/041qf4r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I204553293"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yijie Nie","raw_affiliation_strings":["China University of Petroleum-Beijing,Super Scientific Software Laboratory,Department of CST,Beijing,China"],"affiliations":[{"raw_affiliation_string":"China University of Petroleum-Beijing,Super Scientific Software Laboratory,Department of CST,Beijing,China","institution_ids":["https://openalex.org/I204553293"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128047148","display_name":"Zhengyi Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I204553293","display_name":"China University of Petroleum, Beijing","ror":"https://ror.org/041qf4r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I204553293"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhengyi Zhao","raw_affiliation_strings":["China University of Petroleum-Beijing,Super Scientific Software Laboratory,Department of CST,Beijing,China"],"affiliations":[{"raw_affiliation_string":"China University of Petroleum-Beijing,Super Scientific Software Laboratory,Department of CST,Beijing,China","institution_ids":["https://openalex.org/I204553293"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037428152","display_name":"Junzhong Shen","orcid":"https://orcid.org/0000-0001-6233-6800"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junzhong Shen","raw_affiliation_strings":["National University of Defense Technology,Changsha,China"],"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,Changsha,China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122171057","display_name":"W. Guo","orcid":null},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Guo","raw_affiliation_strings":["National University of Defense Technology,Changsha,China"],"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,Changsha,China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101626850","display_name":"Chun Huang","orcid":"https://orcid.org/0000-0002-0317-8192"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chun Huang","raw_affiliation_strings":["National University of Defense Technology,Changsha,China"],"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,Changsha,China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059001985","display_name":"Bingcai Sui","orcid":null},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bingcai Sui","raw_affiliation_strings":["National University of Defense Technology,Changsha,China"],"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,Changsha,China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5128074138","display_name":"Weifeng Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I204553293","display_name":"China University of Petroleum, Beijing","ror":"https://ror.org/041qf4r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I204553293"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weifeng Liu","raw_affiliation_strings":["China University of Petroleum-Beijing,Super Scientific Software Laboratory,Department of CST,Beijing,China"],"affiliations":[{"raw_affiliation_string":"China University of Petroleum-Beijing,Super Scientific Software Laboratory,Department of CST,Beijing,China","institution_ids":["https://openalex.org/I204553293"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":11,"corresponding_author_ids":["https://openalex.org/A5059172019"],"corresponding_institution_ids":["https://openalex.org/I204553293"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.61238532,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"18"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12303","display_name":"Tensor decomposition and applications","score":0.1728000044822693,"subfield":{"id":"https://openalex.org/subfields/2605","display_name":"Computational Mathematics"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12303","display_name":"Tensor decomposition and applications","score":0.1728000044822693,"subfield":{"id":"https://openalex.org/subfields/2605","display_name":"Computational Mathematics"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10792","display_name":"Matrix Theory and Algorithms","score":0.03220000118017197,"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/T10271","display_name":"Seismic Imaging and Inversion Techniques","score":0.030899999663233757,"subfield":{"id":"https://openalex.org/subfields/1908","display_name":"Geophysics"},"field":{"id":"https://openalex.org/fields/19","display_name":"Earth and Planetary Sciences"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.7113999724388123},{"id":"https://openalex.org/keywords/generality","display_name":"Generality","score":0.6743999719619751},{"id":"https://openalex.org/keywords/tensor","display_name":"Tensor (intrinsic definition)","score":0.6625999808311462},{"id":"https://openalex.org/keywords/sparse-approximation","display_name":"Sparse approximation","score":0.6523000001907349},{"id":"https://openalex.org/keywords/multiplication","display_name":"Multiplication (music)","score":0.5450999736785889},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.541100025177002},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.47130000591278076},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.42750000953674316}],"concepts":[{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.7113999724388123},{"id":"https://openalex.org/C2780767217","wikidata":"https://www.wikidata.org/wiki/Q5532421","display_name":"Generality","level":2,"score":0.6743999719619751},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6682000160217285},{"id":"https://openalex.org/C155281189","wikidata":"https://www.wikidata.org/wiki/Q3518150","display_name":"Tensor (intrinsic definition)","level":2,"score":0.6625999808311462},{"id":"https://openalex.org/C124066611","wikidata":"https://www.wikidata.org/wiki/Q28684319","display_name":"Sparse approximation","level":2,"score":0.6523000001907349},{"id":"https://openalex.org/C2780595030","wikidata":"https://www.wikidata.org/wiki/Q3860309","display_name":"Multiplication (music)","level":2,"score":0.5450999736785889},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.541100025177002},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.47130000591278076},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.4375},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.42750000953674316},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.3901999890804291},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.36230000853538513},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.34869998693466187},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.3244999945163727},{"id":"https://openalex.org/C186370098","wikidata":"https://www.wikidata.org/wiki/Q442787","display_name":"Energy (signal processing)","level":2,"score":0.32280001044273376},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.3172000050544739},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.30300000309944153},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.3021000027656555},{"id":"https://openalex.org/C122280245","wikidata":"https://www.wikidata.org/wiki/Q620622","display_name":"Kernel method","level":3,"score":0.3000999987125397},{"id":"https://openalex.org/C106515295","wikidata":"https://www.wikidata.org/wiki/Q26806595","display_name":"Parallel processing","level":2,"score":0.2948000133037567},{"id":"https://openalex.org/C3826847","wikidata":"https://www.wikidata.org/wiki/Q188768","display_name":"FLOPS","level":2,"score":0.29440000653266907},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.2671999931335449},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2572000026702881},{"id":"https://openalex.org/C156439662","wikidata":"https://www.wikidata.org/wiki/Q7573793","display_name":"Sparse grid","level":2,"score":0.2508000135421753}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/hpca68181.2026.11408500","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpca68181.2026.11408500","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE International Symposium on High Performance Computer Architecture (HPCA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3437868033","display_name":null,"funder_award_id":"U23A20301,62372467,62202481","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":83,"referenced_works":["https://openalex.org/W2009654791","https://openalex.org/W2035080386","https://openalex.org/W2039417226","https://openalex.org/W2095249664","https://openalex.org/W2111667319","https://openalex.org/W2115052535","https://openalex.org/W2168931017","https://openalex.org/W2285660444","https://openalex.org/W2583522611","https://openalex.org/W2625457103","https://openalex.org/W2725159389","https://openalex.org/W2794952988","https://openalex.org/W2908198074","https://openalex.org/W2949674408","https://openalex.org/W2952598959","https://openalex.org/W2953212265","https://openalex.org/W2979310060","https://openalex.org/W2979439447","https://openalex.org/W2980186997","https://openalex.org/W3016542674","https://openalex.org/W3016832937","https://openalex.org/W3042267743","https://openalex.org/W3043072009","https://openalex.org/W3102510044","https://openalex.org/W3102587717","https://openalex.org/W3155922894","https://openalex.org/W3158275024","https://openalex.org/W3158543914","https://openalex.org/W3158831985","https://openalex.org/W3159727696","https://openalex.org/W3175189837","https://openalex.org/W3175878603","https://openalex.org/W3185702163","https://openalex.org/W3187481008","https://openalex.org/W3187908937","https://openalex.org/W3190062760","https://openalex.org/W3190761184","https://openalex.org/W3208370264","https://openalex.org/W3210117238","https://openalex.org/W4220912491","https://openalex.org/W4280557024","https://openalex.org/W4281708367","https://openalex.org/W4281800613","https://openalex.org/W4293024216","https://openalex.org/W4297097464","https://openalex.org/W4308083753","https://openalex.org/W4318540786","https://openalex.org/W4318541558","https://openalex.org/W4327930517","https://openalex.org/W4360831840","https://openalex.org/W4360831848","https://openalex.org/W4360831960","https://openalex.org/W4360831975","https://openalex.org/W4380875466","https://openalex.org/W4380875572","https://openalex.org/W4383749629","https://openalex.org/W4386709563","https://openalex.org/W4386764035","https://openalex.org/W4387323274","https://openalex.org/W4387799594","https://openalex.org/W4388661983","https://openalex.org/W4388855631","https://openalex.org/W4389476163","https://openalex.org/W4389476299","https://openalex.org/W4389500318","https://openalex.org/W4389500474","https://openalex.org/W4393407064","https://openalex.org/W4393407116","https://openalex.org/W4393407269","https://openalex.org/W4395106386","https://openalex.org/W4395106460","https://openalex.org/W4401211761","https://openalex.org/W4401212157","https://openalex.org/W4401212175","https://openalex.org/W4401212179","https://openalex.org/W4401568107","https://openalex.org/W4403211793","https://openalex.org/W4404954358","https://openalex.org/W4405756173","https://openalex.org/W4408891420","https://openalex.org/W4409248726","https://openalex.org/W4409307111","https://openalex.org/W4416146776"],"related_works":[],"abstract_inverted_index":{"Modern":[0],"processors":[1],"are":[2],"increasingly":[3],"adopting":[4],"tensor":[5,23,68],"cores":[6,24],"as":[7],"key":[8,76],"computational":[9],"units.":[10],"Compared":[11],"to":[12,27,128,136,145],"existing":[13,32],"designs":[14],"for":[15,74],"dense":[16],"and":[17,46,56,93,140,150,157,177],"structured":[18],"sparsity,":[19],"recent":[20],"dual-side":[21],"sparse":[22,40,67,77,79,83,88,94,104,112],"have":[25],"evolved":[26],"support":[28,42,101],"general":[29,95],"sparsity.":[30],"However,":[31],"methods":[33],"still":[34],"face":[35],"limitations":[36],"on":[37],"generality":[38],"(incomplete":[39],"kernel":[41],"prevents":[43],"broad":[44],"applicability)":[45],"performance":[47],"(outer-product/row-row":[48],"schemes":[49],"yield":[50],"unsatisfactory":[51],"hardware":[52],"utilisation,":[53,131],"data":[54,138,148],"reuse,":[55,139],"energy":[57,151,183],"efficiency).":[58],"In":[59],"this":[60],"paper,":[61],"we":[62,106],"propose":[63],"Uni-STC,":[64],"a":[65,110,142,170],"unified":[66,111],"core":[69],"that":[70],"delivers":[71],"high-performance":[72],"dataflows":[73],"four":[75],"kernels:":[78],"matrix-vector":[80],"multiplication":[81,86,91,97],"(SpMV),":[82],"matrixsparse":[84],"vector":[85,90],"(SpMSpV),":[87],"matrix-multiple":[89],"(SpMM),":[92],"matrix-matrix":[96],"(SpGEMM).":[98],"To":[99],"efficiently":[100],"these":[102],"diverse":[103],"workloads,":[105],"first":[107],"introduce":[108],"BBC,":[109],"format":[113],"co-designed":[114],"with":[115,169],"Uni-STC's":[116],"dataflow.":[117],"We":[118],"then":[119],"design":[120],"UniSTC's":[121],"architecture":[122],"supporting":[123],"(1)":[124],"fine-grained":[125],"task":[126],"partitioning":[127],"improve":[129],"resource":[130],"(2)":[132],"parallel":[133],"sparse-tile":[134],"processing":[135],"enhance":[137],"(3)":[141],"dynamic":[143],"network":[144],"reduce":[146],"intermediate":[147],"movement":[149],"consumption.":[152],"Evaluated":[153],"across":[154],"2893":[155],"SuiteSparse":[156],"302":[158],"DLMC":[159],"matrices,":[160],"Uni-STC":[161],"demonstrates":[162],"significant":[163],"improvements,":[164],"outperforming":[165],"the":[166],"state-of-the-art":[167],"RM-STC":[168],"<tex":[171,178],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[172,179],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">$2.21":[173],"\\times$</tex>":[174,181],"geomean":[175],"speedup":[176],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">$2.96":[180],"higher":[182],"efficiency.":[184]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2026-03-05T00:00:00"}