{"id":"https://openalex.org/W4414197580","doi":"https://doi.org/10.1109/dac63849.2025.11133371","title":"An Input-Aware Sparse Tensor Compiler Empowered by Vectorized Acceleration","display_name":"An Input-Aware Sparse Tensor Compiler Empowered by Vectorized Acceleration","publication_year":2025,"publication_date":"2025-06-22","ids":{"openalex":"https://openalex.org/W4414197580","doi":"https://doi.org/10.1109/dac63849.2025.11133371"},"language":"en","primary_location":{"id":"doi:10.1109/dac63849.2025.11133371","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dac63849.2025.11133371","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 62nd ACM/IEEE Design Automation Conference (DAC)","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/A5055315302","display_name":"Xianhao He","orcid":"https://orcid.org/0000-0001-7348-1157"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xianhao He","raw_affiliation_strings":["Hunan University,College of Computer Science and Electronic Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hunan University,College of Computer Science and Electronic Engineering","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100383993","display_name":"Haotian Wang","orcid":"https://orcid.org/0000-0002-0086-6301"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haotian Wang","raw_affiliation_strings":["Hunan University,College of Computer Science and Electronic Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hunan University,College of Computer Science and Electronic Engineering","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100662067","display_name":"Jiapeng Zhang","orcid":"https://orcid.org/0000-0002-0364-3568"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiapeng Zhang","raw_affiliation_strings":["Hunan University,College of Computer Science and Electronic Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hunan University,College of Computer Science and Electronic Engineering","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016247312","display_name":"Wangdong Yang","orcid":"https://orcid.org/0000-0003-2681-7898"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wangdong Yang","raw_affiliation_strings":["Hunan University,College of Computer Science and Electronic Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hunan University,College of Computer Science and Electronic Engineering","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052968066","display_name":"Anthony T. Chronopoulos","orcid":"https://orcid.org/0000-0002-0094-1017"},"institutions":[{"id":"https://openalex.org/I45438204","display_name":"The University of Texas at San Antonio","ror":"https://ror.org/01kd65564","country_code":"US","type":"education","lineage":["https://openalex.org/I45438204"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anthony Theodore Chronopoulos","raw_affiliation_strings":["The University of Texas at,Department of Computer Science,San Antonio"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Texas at,Department of Computer Science,San Antonio","institution_ids":["https://openalex.org/I45438204"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078793726","display_name":"Kenli Li","orcid":"https://orcid.org/0000-0002-2635-7716"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kenli Li","raw_affiliation_strings":["Hunan University,College of Computer Science and Electronic Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hunan University,College of Computer Science and Electronic Engineering","institution_ids":["https://openalex.org/I16609230"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.996399998664856,"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":0.996399998664856,"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/T12303","display_name":"Tensor decomposition and applications","score":0.9868999719619751,"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.9617000222206116,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.7867000102996826},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.67330002784729},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.5885000228881836},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.5386000275611877},{"id":"https://openalex.org/keywords/sparse-approximation","display_name":"Sparse approximation","score":0.5310999751091003},{"id":"https://openalex.org/keywords/tensor","display_name":"Tensor (intrinsic definition)","score":0.4537999927997589},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.44929999113082886},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.4133000075817108},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4120999872684479}],"concepts":[{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.7867000102996826},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7598000168800354},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.67330002784729},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.5885000228881836},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5789999961853027},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.5386000275611877},{"id":"https://openalex.org/C124066611","wikidata":"https://www.wikidata.org/wiki/Q28684319","display_name":"Sparse approximation","level":2,"score":0.5310999751091003},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4553999900817871},{"id":"https://openalex.org/C155281189","wikidata":"https://www.wikidata.org/wiki/Q3518150","display_name":"Tensor (intrinsic definition)","level":2,"score":0.4537999927997589},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.44929999113082886},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.4133000075817108},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4120999872684479},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.40209999680519104},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.3806999921798706},{"id":"https://openalex.org/C133162039","wikidata":"https://www.wikidata.org/wiki/Q1061077","display_name":"Code generation","level":3,"score":0.36320000886917114},{"id":"https://openalex.org/C190902152","wikidata":"https://www.wikidata.org/wiki/Q1325106","display_name":"Optimizing compiler","level":3,"score":0.3492000102996826},{"id":"https://openalex.org/C17020691","wikidata":"https://www.wikidata.org/wiki/Q139677","display_name":"Operator (biology)","level":5,"score":0.34040001034736633},{"id":"https://openalex.org/C117896860","wikidata":"https://www.wikidata.org/wiki/Q11376","display_name":"Acceleration","level":2,"score":0.33559998869895935},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.3336000144481659},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3301999866962433},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.3276999890804291},{"id":"https://openalex.org/C35912277","wikidata":"https://www.wikidata.org/wiki/Q1243369","display_name":"Double-precision floating-point format","level":3,"score":0.31450000405311584},{"id":"https://openalex.org/C2780595030","wikidata":"https://www.wikidata.org/wiki/Q3860309","display_name":"Multiplication (music)","level":2,"score":0.31029999256134033},{"id":"https://openalex.org/C156439662","wikidata":"https://www.wikidata.org/wiki/Q7573793","display_name":"Sparse grid","level":2,"score":0.30640000104904175},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.3061999976634979},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.30000001192092896},{"id":"https://openalex.org/C42355184","wikidata":"https://www.wikidata.org/wiki/Q1361088","display_name":"Matrix decomposition","level":3,"score":0.28279998898506165},{"id":"https://openalex.org/C164833996","wikidata":"https://www.wikidata.org/wiki/Q2323839","display_name":"Automatic parallelization","level":3,"score":0.2793999910354614},{"id":"https://openalex.org/C2777472644","wikidata":"https://www.wikidata.org/wiki/Q16968992","display_name":"Approximate inference","level":3,"score":0.2768999934196472},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.2639999985694885},{"id":"https://openalex.org/C6802819","wikidata":"https://www.wikidata.org/wiki/Q1072174","display_name":"Linear system","level":2,"score":0.26109999418258667}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/dac63849.2025.11133371","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dac63849.2025.11133371","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 62nd ACM/IEEE Design Automation Conference (DAC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321543","display_name":"China Postdoctoral Science Foundation","ror":"https://ror.org/0426zh255"},{"id":"https://openalex.org/F4320335768","display_name":"National Postdoctoral Program for Innovative Talents","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W182691100","https://openalex.org/W639708223","https://openalex.org/W2194775991","https://openalex.org/W2252007067","https://openalex.org/W2590246587","https://openalex.org/W2914631005","https://openalex.org/W2980186997","https://openalex.org/W2996874060","https://openalex.org/W3130660608","https://openalex.org/W3210601829","https://openalex.org/W4251637954","https://openalex.org/W4379518528","https://openalex.org/W4385245566","https://openalex.org/W4389265856","https://openalex.org/W4392680648","https://openalex.org/W4392736841","https://openalex.org/W4396723396","https://openalex.org/W4403223049","https://openalex.org/W4403223472"],"related_works":[],"abstract_inverted_index":{"Sparsity":[0],"is":[1,24,33],"widely":[2],"prevalent":[3],"in":[4,28,97],"real-world":[5],"applications,":[6],"yet":[7],"existing":[8,50],"compiler":[9],"optimizations":[10],"and":[11,42,62,120,154],"code":[12,77],"generation":[13],"techniques":[14],"for":[15,85,126,172],"sparse":[16,29,40,64,86,106,111,173],"computations":[17],"remain":[18],"underdeveloped.":[19],"Sparse":[20],"matrix-matrix":[21],"multiplication":[22],"(SpMM)":[23],"a":[25,110,122,163],"representative":[26],"operator":[27],"computations,":[30],"whose":[31],"performance":[32],"often":[34],"limited":[35,83],"by":[36],"the":[37,43,129,177],"design":[38],"of":[39,45,141,165],"formats":[41],"extent":[44],"hardware":[46],"architecture":[47],"optimization.":[48],"Most":[49],"solutions":[51],"achieve":[52],"highperformance":[53],"SpMM":[54,127],"through":[55],"two":[56],"approaches:":[57],"(1)":[58],"meticulously":[59],"designed":[60],"kernels":[61],"specialized":[63],"formats,":[65],"which":[66],"require":[67],"extensive":[68],"manual":[69],"effort,":[70],"or":[71],"(2)":[72],"tensor":[73,107],"compilers":[74],"that":[75],"support":[76,84],"generation,":[78],"though":[79],"these":[80],"typically":[81],"offer":[82],"patterns,":[87],"making":[88],"it":[89],"challenging":[90],"to":[91,93,144,167],"adapt":[92],"complex":[94],"sparsity":[95],"patterns":[96],"practical":[98],"applications.":[99],"This":[100],"paper":[101],"presents":[102],"SpMMTC,":[103],"an":[104],"input-aware":[105],"compiler.":[108],"Given":[109],"matrix":[112],"as":[113,151],"input,":[114],"SpMMTC":[115,134],"analyzes":[116],"its":[117],"non-zero":[118],"distribution":[119],"generates":[121],"vectorized":[123],"kernel":[124],"optimized":[125],"on":[128,135,156,176],"specific":[130],"matrix.":[131],"We":[132],"evaluated":[133],"various":[136],"workloads.":[137],"It":[138,160],"achieves":[139],"speedups":[140],"1.21":[142],"x":[143,146],"2.97":[145],"over":[147],"state-of-the-art":[148],"methods":[149],"such":[150],"TACO,":[152],"TVM,":[153],"ASpT":[155],"different":[157],"multi-core":[158],"processors.":[159],"also":[161],"provides":[162],"speedup":[164],"up":[166],"$\\mathbf{1.":[168],"5":[169],"2":[170],"x}$":[171],"MobileNetV1":[174],"inference":[175],"edge":[178],"device.":[179]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}