{"id":"https://openalex.org/W2985039650","doi":"https://doi.org/10.1145/3295500.3356218","title":"Analytical cache modeling and tilesize optimization for tensor contractions","display_name":"Analytical cache modeling and tilesize optimization for tensor contractions","publication_year":2019,"publication_date":"2019-11-07","ids":{"openalex":"https://openalex.org/W2985039650","doi":"https://doi.org/10.1145/3295500.3356218","mag":"2985039650"},"language":"en","primary_location":{"id":"doi:10.1145/3295500.3356218","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3295500.3356218","pdf_url":null,"source":null,"license":null,"license_id":null,"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":"preprint","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://inria.hal.science/hal-02418875","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101491625","display_name":"Rui Li","orcid":"https://orcid.org/0000-0001-9847-5642"},"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"]},{"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":true,"raw_author_name":"Rui Li","raw_affiliation_strings":["University of Utah","Ohio State University [Columbus]"],"affiliations":[{"raw_affiliation_string":"University of Utah","institution_ids":["https://openalex.org/I223532165"]},{"raw_affiliation_string":"Ohio State University [Columbus]","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015460842","display_name":"Aravind Sukumaran-Rajam","orcid":"https://orcid.org/0000-0002-4062-0293"},"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":"Aravind Sukumaran-Rajam","raw_affiliation_strings":["Ohio State University","Ohio State University [Columbus]"],"affiliations":[{"raw_affiliation_string":"Ohio State University","institution_ids":["https://openalex.org/I52357470"]},{"raw_affiliation_string":"Ohio State University [Columbus]","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011290316","display_name":"Richard Veras","orcid":"https://orcid.org/0000-0003-2633-3391"},"institutions":[{"id":"https://openalex.org/I121820613","display_name":"Louisiana State University","ror":"https://ror.org/05ect4e57","country_code":"US","type":"education","lineage":["https://openalex.org/I121820613"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Richard Veras","raw_affiliation_strings":["Louisiana State University"],"affiliations":[{"raw_affiliation_string":"Louisiana State University","institution_ids":["https://openalex.org/I121820613"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019607600","display_name":"Tze Meng Low","orcid":"https://orcid.org/0000-0002-5179-8249"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tze Meng Low","raw_affiliation_strings":["Carnegie Mellon University","Carnegie Mellon University [Pittsburgh]"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie Mellon University [Pittsburgh]","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089282120","display_name":"Fabrice Rastello","orcid":"https://orcid.org/0000-0002-6589-9956"},"institutions":[{"id":"https://openalex.org/I899635006","display_name":"Universit\u00e9 Grenoble Alpes","ror":"https://ror.org/02rx3b187","country_code":"FR","type":"education","lineage":["https://openalex.org/I899635006"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Fabrice Rastello","raw_affiliation_strings":["Univ. Grenoble Alpes","Compiler Optimization and Run-time Systems"],"affiliations":[{"raw_affiliation_string":"Univ. Grenoble Alpes","institution_ids":["https://openalex.org/I899635006"]},{"raw_affiliation_string":"Compiler Optimization and Run-time Systems","institution_ids":[]}]},{"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","Ohio State University [Columbus]"],"affiliations":[{"raw_affiliation_string":"Ohio State University","institution_ids":["https://openalex.org/I52357470"]},{"raw_affiliation_string":"Ohio State University [Columbus]","institution_ids":["https://openalex.org/I52357470"]}]},{"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/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]},{"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","Ohio State University [Columbus]"],"affiliations":[{"raw_affiliation_string":"University of Utah","institution_ids":["https://openalex.org/I223532165"]},{"raw_affiliation_string":"Ohio State University [Columbus]","institution_ids":["https://openalex.org/I52357470"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5101491625"],"corresponding_institution_ids":["https://openalex.org/I223532165","https://openalex.org/I52357470"],"apc_list":null,"apc_paid":null,"fwci":3.6893,"has_fulltext":false,"cited_by_count":23,"citation_normalized_percentile":{"value":0.93774716,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"13"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":1.0,"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":1.0,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9965000152587891,"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"}},{"id":"https://openalex.org/T12303","display_name":"Tensor decomposition and applications","score":0.9962999820709229,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7775513529777527},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.7617483139038086},{"id":"https://openalex.org/keywords/memory-hierarchy","display_name":"Memory hierarchy","score":0.7333319187164307},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.6535269021987915},{"id":"https://openalex.org/keywords/tensor","display_name":"Tensor (intrinsic definition)","score":0.5860955715179443},{"id":"https://openalex.org/keywords/permutation","display_name":"Permutation (music)","score":0.5856691598892212},{"id":"https://openalex.org/keywords/locality","display_name":"Locality","score":0.5758992433547974},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.5668365955352783},{"id":"https://openalex.org/keywords/loop-tiling","display_name":"Loop tiling","score":0.5231010913848877},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5116391777992249},{"id":"https://openalex.org/keywords/loop-fusion","display_name":"Loop fusion","score":0.46522897481918335},{"id":"https://openalex.org/keywords/tensor-contraction","display_name":"Tensor contraction","score":0.4542132616043091},{"id":"https://openalex.org/keywords/loop","display_name":"Loop (graph theory)","score":0.4490830600261688},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.44062063097953796},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.4324561357498169},{"id":"https://openalex.org/keywords/loop-optimization","display_name":"Loop optimization","score":0.4293113648891449},{"id":"https://openalex.org/keywords/tile","display_name":"Tile","score":0.429132878780365},{"id":"https://openalex.org/keywords/cpu-cache","display_name":"CPU cache","score":0.4155423641204834},{"id":"https://openalex.org/keywords/optimizing-compiler","display_name":"Optimizing compiler","score":0.3729957640171051},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3620288372039795},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.169565349817276},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.12793150544166565},{"id":"https://openalex.org/keywords/tensor-product","display_name":"Tensor product","score":0.1120118498802185},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.08023077249526978}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7775513529777527},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.7617483139038086},{"id":"https://openalex.org/C2778100165","wikidata":"https://www.wikidata.org/wiki/Q1589327","display_name":"Memory hierarchy","level":3,"score":0.7333319187164307},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.6535269021987915},{"id":"https://openalex.org/C155281189","wikidata":"https://www.wikidata.org/wiki/Q3518150","display_name":"Tensor (intrinsic definition)","level":2,"score":0.5860955715179443},{"id":"https://openalex.org/C21308566","wikidata":"https://www.wikidata.org/wiki/Q7169365","display_name":"Permutation (music)","level":2,"score":0.5856691598892212},{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.5758992433547974},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.5668365955352783},{"id":"https://openalex.org/C11799548","wikidata":"https://www.wikidata.org/wiki/Q6675847","display_name":"Loop tiling","level":3,"score":0.5231010913848877},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5116391777992249},{"id":"https://openalex.org/C82653869","wikidata":"https://www.wikidata.org/wiki/Q6675821","display_name":"Loop fusion","level":3,"score":0.46522897481918335},{"id":"https://openalex.org/C124007464","wikidata":"https://www.wikidata.org/wiki/Q428091","display_name":"Tensor contraction","level":3,"score":0.4542132616043091},{"id":"https://openalex.org/C184670325","wikidata":"https://www.wikidata.org/wiki/Q512604","display_name":"Loop (graph theory)","level":2,"score":0.4490830600261688},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.44062063097953796},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.4324561357498169},{"id":"https://openalex.org/C29331672","wikidata":"https://www.wikidata.org/wiki/Q3354468","display_name":"Loop optimization","level":4,"score":0.4293113648891449},{"id":"https://openalex.org/C2780728851","wikidata":"https://www.wikidata.org/wiki/Q468402","display_name":"Tile","level":2,"score":0.429132878780365},{"id":"https://openalex.org/C189783530","wikidata":"https://www.wikidata.org/wiki/Q352090","display_name":"CPU cache","level":3,"score":0.4155423641204834},{"id":"https://openalex.org/C190902152","wikidata":"https://www.wikidata.org/wiki/Q1325106","display_name":"Optimizing compiler","level":3,"score":0.3729957640171051},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3620288372039795},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.169565349817276},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.12793150544166565},{"id":"https://openalex.org/C51255310","wikidata":"https://www.wikidata.org/wiki/Q1163016","display_name":"Tensor product","level":2,"score":0.1120118498802185},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.08023077249526978},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3295500.3356218","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3295500.3356218","pdf_url":null,"source":null,"license":null,"license_id":null,"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"},{"id":"pmh:oai:HAL:hal-02418875v1","is_oa":true,"landing_page_url":"https://inria.hal.science/hal-02418875","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"SC 2019 - International Conference for High Performance Computing, Networking, Storage and Analysis, Nov 2019, Denver, United States. pp.1-13, ⟨10.1145/3295500.3356218⟩","raw_type":"Conference papers"}],"best_oa_location":{"id":"pmh:oai:HAL:hal-02418875v1","is_oa":true,"landing_page_url":"https://inria.hal.science/hal-02418875","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"SC 2019 - International Conference for High Performance Computing, Networking, Storage and Analysis, Nov 2019, Denver, United States. pp.1-13, ⟨10.1145/3295500.3356218⟩","raw_type":"Conference papers"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W38784877","https://openalex.org/W182691100","https://openalex.org/W1584675441","https://openalex.org/W1970141743","https://openalex.org/W2043275593","https://openalex.org/W2073061372","https://openalex.org/W2077143534","https://openalex.org/W2108737583","https://openalex.org/W2156316655","https://openalex.org/W2158158791","https://openalex.org/W2166906890","https://openalex.org/W2252007067","https://openalex.org/W2468576082","https://openalex.org/W2516525699","https://openalex.org/W2588061952","https://openalex.org/W2963482281","https://openalex.org/W3113163436","https://openalex.org/W3203568064","https://openalex.org/W4232940466"],"related_works":["https://openalex.org/W2014071052","https://openalex.org/W1596526459","https://openalex.org/W2040522199","https://openalex.org/W2122418911","https://openalex.org/W4251798485","https://openalex.org/W2340721088","https://openalex.org/W2069279716","https://openalex.org/W2147483891","https://openalex.org/W4281296111","https://openalex.org/W2049641447"],"abstract_inverted_index":{"Data":[0],"movement":[1],"between":[2],"processor":[3],"and":[4,23,37,60,85,106],"memory":[5],"hierarchy":[6],"is":[7,40],"a":[8],"fundamental":[9],"bottleneck":[10],"that":[11,95],"limits":[12],"the":[13,48],"performance":[14,102],"of":[15,51],"many":[16],"applications":[17],"on":[18,66],"modern":[19],"computer":[20],"architectures.":[21],"Tiling":[22],"loop":[24,38,61],"permutation":[25,86],"are":[26],"key":[27],"techniques":[28],"for":[29,43,88,108],"improving":[30],"data":[31],"locality.":[32],"However,":[33],"selecting":[34],"effective":[35],"tile-sizes":[36,59],"permutations":[39],"particularly":[41],"challenging":[42],"tensor":[44,89,109],"contractions":[45],"due":[46],"to":[47,80],"large":[49],"number":[50],"loops.":[52],"Even":[53],"state-of-the-art":[54,104],"compilers":[55],"usually":[56],"produce":[57],"sub-optimal":[58],"permutations,":[62],"as":[63],"they":[64],"rely":[65],"na\u00efve":[67],"cost":[68],"models.":[69],"In":[70],"this":[71,96],"paper":[72],"we":[73],"provide":[74],"an":[75],"analytical":[76],"model":[77],"based":[78],"approach":[79,97],"multi-level":[81],"tile":[82],"size":[83],"optimization":[84],"selection":[87],"contractions.":[90,110],"Our":[91],"experimental":[92],"results":[93],"show":[94],"achieves":[98],"comparable":[99],"or":[100],"better":[101],"than":[103],"frameworks":[105],"libraries":[107]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":1}],"updated_date":"2026-03-06T13:50:29.536080","created_date":"2025-10-10T00:00:00"}