{"id":"https://openalex.org/W4416146849","doi":"https://doi.org/10.1145/3712285.3759841","title":"FaSTCC: Fast Sparse Tensor Contractions on CPUs","display_name":"FaSTCC: Fast Sparse Tensor Contractions on CPUs","publication_year":2025,"publication_date":"2025-11-12","ids":{"openalex":"https://openalex.org/W4416146849","doi":"https://doi.org/10.1145/3712285.3759841"},"language":null,"primary_location":{"id":"doi:10.1145/3712285.3759841","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3712285.3759841","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3712285.3759841","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5055962929","display_name":"Saurabh Raje","orcid":"https://orcid.org/0000-0003-3294-1481"},"institutions":[{"id":"https://openalex.org/I223532165","display_name":"University of Utah","ror":"https://ror.org/03r0ha626","country_code":"US","type":"education","lineage":["https://openalex.org/I223532165"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Saurabh Raje","raw_affiliation_strings":["University of Utah, Salt Lake City, USA"],"raw_orcid":"https://orcid.org/0000-0003-3294-1481","affiliations":[{"raw_affiliation_string":"University of Utah, Salt Lake City, USA","institution_ids":["https://openalex.org/I223532165"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089348824","display_name":"Hunter McCoy","orcid":"https://orcid.org/0000-0002-4233-9796"},"institutions":[{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hunter McCoy","raw_affiliation_strings":["Northeastern University, Boston, USA"],"raw_orcid":"https://orcid.org/0000-0002-4233-9796","affiliations":[{"raw_affiliation_string":"Northeastern University, Boston, USA","institution_ids":["https://openalex.org/I12912129"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039624297","display_name":"Atanas Rountev","orcid":"https://orcid.org/0000-0003-4556-4937"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Atanas Rountev","raw_affiliation_strings":["Ohio State University, Columbus, USA"],"raw_orcid":"https://orcid.org/0000-0003-4556-4937","affiliations":[{"raw_affiliation_string":"Ohio State University, Columbus, USA","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014159929","display_name":"Prashant Pandey","orcid":"https://orcid.org/0000-0001-5576-0320"},"institutions":[{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Prashant Pandey","raw_affiliation_strings":["Northeastern University, Boston, USA"],"raw_orcid":"https://orcid.org/0000-0001-5576-0320","affiliations":[{"raw_affiliation_string":"Northeastern University, Boston, USA","institution_ids":["https://openalex.org/I12912129"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027517817","display_name":"P. Sadayappan","orcid":"https://orcid.org/0000-0002-4737-2034"},"institutions":[{"id":"https://openalex.org/I223532165","display_name":"University of Utah","ror":"https://ror.org/03r0ha626","country_code":"US","type":"education","lineage":["https://openalex.org/I223532165"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"P. Sadayappan","raw_affiliation_strings":["University of Utah, Salt Lake City, USA"],"raw_orcid":"https://orcid.org/0000-0002-4737-2034","affiliations":[{"raw_affiliation_string":"University of Utah, Salt Lake City, USA","institution_ids":["https://openalex.org/I223532165"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.7868,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.76436856,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"617","last_page":"630"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11804","display_name":"Quantum many-body systems","score":0.32350000739097595,"subfield":{"id":"https://openalex.org/subfields/3107","display_name":"Atomic and Molecular Physics, and Optics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11804","display_name":"Quantum many-body systems","score":0.32350000739097595,"subfield":{"id":"https://openalex.org/subfields/3107","display_name":"Atomic and Molecular Physics, and Optics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.12359999865293503,"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/T10682","display_name":"Quantum Computing Algorithms and Architecture","score":0.08389999717473984,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.6675999760627747},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.499099999666214},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.49900001287460327},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.47690001130104065},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.46219998598098755},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.4339999854564667},{"id":"https://openalex.org/keywords/loop","display_name":"Loop (graph theory)","score":0.43209999799728394},{"id":"https://openalex.org/keywords/computational-complexity-theory","display_name":"Computational complexity theory","score":0.3621000051498413}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.680899977684021},{"id":"https://openalex.org/C155281189","wikidata":"https://www.wikidata.org/wiki/Q3518150","display_name":"Tensor (intrinsic definition)","level":2,"score":0.6675999760627747},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5680999755859375},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.499099999666214},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.49900001287460327},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.47690001130104065},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.46219998598098755},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.4339999854564667},{"id":"https://openalex.org/C184670325","wikidata":"https://www.wikidata.org/wiki/Q512604","display_name":"Loop (graph theory)","level":2,"score":0.43209999799728394},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4207000136375427},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.4124000072479248},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.37700000405311584},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.3621000051498413},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.36169999837875366},{"id":"https://openalex.org/C1306188","wikidata":"https://www.wikidata.org/wiki/Q4060687","display_name":"Nested loop join","level":2,"score":0.3343999981880188},{"id":"https://openalex.org/C79470037","wikidata":"https://www.wikidata.org/wiki/Q279748","display_name":"Out-of-core algorithm","level":2,"score":0.32829999923706055},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.3255000114440918},{"id":"https://openalex.org/C124007464","wikidata":"https://www.wikidata.org/wiki/Q428091","display_name":"Tensor contraction","level":3,"score":0.30219998955726624},{"id":"https://openalex.org/C124066611","wikidata":"https://www.wikidata.org/wiki/Q28684319","display_name":"Sparse approximation","level":2,"score":0.29649999737739563},{"id":"https://openalex.org/C2778100165","wikidata":"https://www.wikidata.org/wiki/Q1589327","display_name":"Memory hierarchy","level":3,"score":0.2809000015258789},{"id":"https://openalex.org/C2989134064","wikidata":"https://www.wikidata.org/wiki/Q288510","display_name":"Execution time","level":2,"score":0.26980000734329224},{"id":"https://openalex.org/C47487241","wikidata":"https://www.wikidata.org/wiki/Q5227230","display_name":"Data access","level":2,"score":0.2606000006198883},{"id":"https://openalex.org/C3826847","wikidata":"https://www.wikidata.org/wiki/Q188768","display_name":"FLOPS","level":2,"score":0.2563000023365021},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.25529998540878296},{"id":"https://openalex.org/C51255310","wikidata":"https://www.wikidata.org/wiki/Q1163016","display_name":"Tensor product","level":2,"score":0.2529999911785126}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3712285.3759841","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3712285.3759841","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3712285.3759841","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3712285.3759841","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1511885491","https://openalex.org/W1554563779","https://openalex.org/W1597769341","https://openalex.org/W2006973305","https://openalex.org/W2020445514","https://openalex.org/W2089437293","https://openalex.org/W2093135480","https://openalex.org/W2111667319","https://openalex.org/W2411765360","https://openalex.org/W2588061952","https://openalex.org/W2590246587","https://openalex.org/W2754727929","https://openalex.org/W2783426071","https://openalex.org/W2922451262","https://openalex.org/W2963137752","https://openalex.org/W3020638658","https://openalex.org/W3045710579","https://openalex.org/W3048232878","https://openalex.org/W3103168911","https://openalex.org/W3131379896","https://openalex.org/W3131704052","https://openalex.org/W3155922894","https://openalex.org/W3170905359","https://openalex.org/W3175189837","https://openalex.org/W3188917597","https://openalex.org/W4200390336","https://openalex.org/W4220912491","https://openalex.org/W4252721932","https://openalex.org/W4281550828","https://openalex.org/W4307380766","https://openalex.org/W4383710626","https://openalex.org/W4391983395","https://openalex.org/W4399344346","https://openalex.org/W4401657015","https://openalex.org/W4403295008","https://openalex.org/W7077158327"],"related_works":[],"abstract_inverted_index":{"Sparse":[0],"tensor":[1,46,62],"contractions":[2,18],"are":[3],"a":[4,55,66,73,104],"core":[5],"computational":[6],"primitive":[7],"in":[8],"scientific":[9],"computing":[10],"and":[11,38,72,86,91,103,116],"machine":[12],"learning.":[13],"Effective":[14],"optimization":[15],"of":[16,34,60,106],"such":[17],"through":[19],"loop":[20,42],"permutation/tiling":[21],"remains":[22],"an":[23],"open":[24],"challenge.":[25],"Our":[26],"work":[27],"perform":[28],"the":[29],"first":[30],"comprehensive":[31],"comparative":[32],"analysis":[33],"data":[35],"access":[36],"costs":[37],"memory":[39],"requirements":[40],"for":[41,44],"permutations":[43],"sparse":[45,61,87],"contractions.":[47,63],"Based":[48],"on":[49,112],"these":[50],"insights,":[51],"we":[52],"develop":[53],"FaSTCC,":[54],"novel":[56],"hashing-based":[57],"parallel":[58],"implementation":[59],"FaSTCC":[64,98],"introduces":[65],"new":[67],"2D":[68],"tiled":[69],"contraction-index-outer":[70],"scheme":[71],"corresponding":[74],"tile-aware":[75],"design.":[76],"Using":[77],"probabilistic":[78],"modeling,":[79],"our":[80],"approach":[81],"automatically":[82],"chooses":[83],"between":[84],"dense":[85],"output":[88],"tile":[89,94],"accumulators":[90],"selects":[92],"suitable":[93],"size.":[95],"We":[96],"evaluate":[97],"across":[99],"two":[100],"CPU":[101],"platforms":[102],"range":[105],"real-world":[107],"workloads,":[108],"demonstrating":[109],"significant":[110],"speedups":[111],"benchmarks":[113],"from":[114,117],"FROSTT":[115],"quantum":[118],"chemistry.":[119]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-03T08:13:44.112507","created_date":"2025-11-12T00:00:00"}