{"id":"https://openalex.org/W7125963162","doi":"https://doi.org/10.1145/3771775.3786267","title":"Optimizing Sparse Tensor Compilation for Sparse Output","display_name":"Optimizing Sparse Tensor Compilation for Sparse Output","publication_year":2026,"publication_date":"2026-01-28","ids":{"openalex":"https://openalex.org/W7125963162","doi":"https://doi.org/10.1145/3771775.3786267"},"language":null,"primary_location":{"id":"doi:10.1145/3771775.3786267","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3771775.3786267","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 35th ACM SIGPLAN International Conference on Compiler Construction","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/A5067753435","display_name":"Shideh Hashemian","orcid":"https://orcid.org/0009-0004-3787-3136"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Shideh Hashemian","raw_affiliation_strings":["University of Edinburgh, Edinburgh, United Kingdom"],"affiliations":[{"raw_affiliation_string":"University of Edinburgh, Edinburgh, United Kingdom","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124128871","display_name":"Michael F. P. O\u2019Boyle","orcid":null},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Michael F. P. O\u2019Boyle","raw_affiliation_strings":["University of Edinburgh, Edinburgh, United Kingdom"],"affiliations":[{"raw_affiliation_string":"University of Edinburgh, Edinburgh, United Kingdom","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5123561275","display_name":"Amir Shaikhha","orcid":null},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Amir Shaikhha","raw_affiliation_strings":["University of Edinburgh, Edinburgh, United Kingdom"],"affiliations":[{"raw_affiliation_string":"University of Edinburgh, Edinburgh, United Kingdom","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5067753435"],"corresponding_institution_ids":["https://openalex.org/I98677209"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.17037037,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"27","last_page":"39"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.7871999740600586,"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":0.7871999740600586,"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":0.060100000351667404,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.031599998474121094,"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/tensor","display_name":"Tensor (intrinsic definition)","score":0.718999981880188},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.704200029373169},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.6075999736785889},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.5852000117301941},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.5034000277519226},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.49570000171661377},{"id":"https://openalex.org/keywords/tensor-algebra","display_name":"Tensor algebra","score":0.4489000141620636},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.42590001225471497}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7394000291824341},{"id":"https://openalex.org/C155281189","wikidata":"https://www.wikidata.org/wiki/Q3518150","display_name":"Tensor (intrinsic definition)","level":2,"score":0.718999981880188},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.704200029373169},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.6075999736785889},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.5852000117301941},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.5034000277519226},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.49570000171661377},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4697999954223633},{"id":"https://openalex.org/C1680195","wikidata":"https://www.wikidata.org/wiki/Q2296021","display_name":"Tensor algebra","level":5,"score":0.4489000141620636},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4375},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.42890000343322754},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.42590001225471497},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.40610000491142273},{"id":"https://openalex.org/C124066611","wikidata":"https://www.wikidata.org/wiki/Q28684319","display_name":"Sparse approximation","level":2,"score":0.38850000500679016},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.3831000030040741},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.36910000443458557},{"id":"https://openalex.org/C139352143","wikidata":"https://www.wikidata.org/wiki/Q82571","display_name":"Linear algebra","level":2,"score":0.35690000653266907},{"id":"https://openalex.org/C133162039","wikidata":"https://www.wikidata.org/wiki/Q1061077","display_name":"Code generation","level":3,"score":0.3043000102043152},{"id":"https://openalex.org/C190902152","wikidata":"https://www.wikidata.org/wiki/Q1325106","display_name":"Optimizing compiler","level":3,"score":0.3034000098705292},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.2906999886035919},{"id":"https://openalex.org/C2986737658","wikidata":"https://www.wikidata.org/wiki/Q30103009","display_name":"Tensor decomposition","level":3,"score":0.2694000005722046},{"id":"https://openalex.org/C2989134064","wikidata":"https://www.wikidata.org/wiki/Q288510","display_name":"Execution time","level":2,"score":0.25839999318122864},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.2549999952316284},{"id":"https://openalex.org/C2778915421","wikidata":"https://www.wikidata.org/wiki/Q3643177","display_name":"Performance improvement","level":2,"score":0.2513999938964844},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.25130000710487366},{"id":"https://openalex.org/C3017489831","wikidata":"https://www.wikidata.org/wiki/Q2393193","display_name":"Running time","level":2,"score":0.25130000710487366}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3771775.3786267","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3771775.3786267","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 35th ACM SIGPLAN International Conference on Compiler Construction","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.4593176245689392}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1511885491","https://openalex.org/W2065607954","https://openalex.org/W2298668594","https://openalex.org/W2590246587","https://openalex.org/W2753916251","https://openalex.org/W2898123186","https://openalex.org/W3003257820","https://openalex.org/W3135515481","https://openalex.org/W3165460533","https://openalex.org/W4220690649","https://openalex.org/W4255450819","https://openalex.org/W4281658036","https://openalex.org/W4283033672","https://openalex.org/W4290648346","https://openalex.org/W4307380766","https://openalex.org/W4307887693","https://openalex.org/W4318541538","https://openalex.org/W4321500319","https://openalex.org/W4321636673","https://openalex.org/W4327911434","https://openalex.org/W4387667068","https://openalex.org/W4392736841","https://openalex.org/W4399852843","https://openalex.org/W4409248587","https://openalex.org/W4409310702","https://openalex.org/W4411403183","https://openalex.org/W4413411914","https://openalex.org/W6929013889"],"related_works":[],"abstract_inverted_index":{"Sparse":[0],"tensor":[1,24,115],"algebra":[2],"plays":[3],"an":[4,101],"important":[5],"role":[6],"in":[7],"many":[8],"scientific":[9],"and":[10,17,37,53,85,98,110],"engineering":[11],"applications,":[12],"yet":[13],"existing":[14],"sparse":[15,45,71,114],"libraries":[16],"compilers":[18],"face":[19],"challenges":[20],"when":[21],"the":[22,48,74],"output":[23,75],"is":[25],"sparse.":[26],"Array-based":[27],"storage":[28,66],"formats,":[29],"such":[30],"as":[31],"CSR,":[32],"require":[33],"costly":[34],"memory":[35],"reallocations":[36],"rely":[38],"on":[39],"intermediate":[40],"tensors":[41],"(workspaces)":[42],"to":[43,68,88],"handle":[44],"scattering":[46,72],"into":[47,73],"output,":[49],"which":[50],"limits":[51],"performance":[52],"scalability.":[54],"We":[55],"introduce":[56],"a":[57,94,107,113],"new":[58],"approach":[59],"that":[60],"employs":[61],"our":[62],"proposed":[63],"flexible":[64],"map-based":[65],"format":[67],"directly":[69],"support":[70],"without":[76],"requiring":[77],"extra":[78],"workspaces.":[79],"Our":[80],"system":[81],"then":[82],"applies":[83],"code":[84],"storage-specific":[86],"optimizations":[87],"maximize":[89],"efficiency.":[90],"Experimental":[91],"results":[92],"across":[93],"range":[95],"of":[96,104],"kernels":[97],"datasets":[99],"demonstrate":[100],"average":[102],"speedup":[103],"8.06\u00d7":[105],"over":[106,112],"state-of-the-art":[108],"compiler":[109],"5.28\u00d7":[111],"library.":[116]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2026-01-29T00:00:00"}