{"id":"https://openalex.org/W4248445937","doi":"https://doi.org/10.1109/cgo.2019.8661182","title":"A Code Generator for High-Performance Tensor Contractions on GPUs","display_name":"A Code Generator for High-Performance Tensor Contractions on GPUs","publication_year":2019,"publication_date":"2019-02-01","ids":{"openalex":"https://openalex.org/W4248445937","doi":"https://doi.org/10.1109/cgo.2019.8661182"},"language":"en","primary_location":{"id":"doi:10.1109/cgo.2019.8661182","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cgo.2019.8661182","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE/ACM International Symposium on Code Generation and Optimization (CGO)","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/A5100676208","display_name":"Jinsung Kim","orcid":"https://orcid.org/0000-0003-3751-8869"},"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":true,"raw_author_name":"Jinsung Kim","raw_affiliation_strings":["The Ohio State University, Ohio, USA"],"affiliations":[{"raw_affiliation_string":"The Ohio State University, Ohio, USA","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":["The Ohio State University, Ohio, USA"],"affiliations":[{"raw_affiliation_string":"The Ohio State University, Ohio, USA","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085689053","display_name":"Vineeth Thumma","orcid":null},"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":"Vineeth Thumma","raw_affiliation_strings":["The Ohio State University, Ohio, USA"],"affiliations":[{"raw_affiliation_string":"The Ohio State University, Ohio, USA","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006650430","display_name":"Sriram Krishnamoorthy","orcid":"https://orcid.org/0000-0002-4682-1002"},"institutions":[{"id":"https://openalex.org/I142606810","display_name":"Pacific Northwest National Laboratory","ror":"https://ror.org/05h992307","country_code":"US","type":"facility","lineage":["https://openalex.org/I1325736334","https://openalex.org/I1330989302","https://openalex.org/I142606810","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sriram Krishnamoorthy","raw_affiliation_strings":["Pacific Northwest National Laboratory, Washington, USA"],"affiliations":[{"raw_affiliation_string":"Pacific Northwest National Laboratory, Washington, USA","institution_ids":["https://openalex.org/I142606810"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080124836","display_name":"Ajay Panyala","orcid":"https://orcid.org/0000-0002-0846-3347"},"institutions":[{"id":"https://openalex.org/I142606810","display_name":"Pacific Northwest National Laboratory","ror":"https://ror.org/05h992307","country_code":"US","type":"facility","lineage":["https://openalex.org/I1325736334","https://openalex.org/I1330989302","https://openalex.org/I142606810","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ajay Panyala","raw_affiliation_strings":["Pacific Northwest National Laboratory, Washington, USA"],"affiliations":[{"raw_affiliation_string":"Pacific Northwest National Laboratory, Washington, USA","institution_ids":["https://openalex.org/I142606810"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040769038","display_name":"Louis-No\u00ebl Pouchet","orcid":"https://orcid.org/0000-0001-5103-3097"},"institutions":[{"id":"https://openalex.org/I92446798","display_name":"Colorado State University","ror":"https://ror.org/03k1gpj17","country_code":"US","type":"education","lineage":["https://openalex.org/I92446798"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Louis-Noel Pouchet","raw_affiliation_strings":["Colorado State University, Colorado, USA"],"affiliations":[{"raw_affiliation_string":"Colorado State University, Colorado, USA","institution_ids":["https://openalex.org/I92446798"]}]},{"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":["The Ohio State University, Ohio, USA"],"affiliations":[{"raw_affiliation_string":"The Ohio State University, Ohio, USA","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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"P. Sadayappan","raw_affiliation_strings":["The Ohio State University, Ohio, USA"],"affiliations":[{"raw_affiliation_string":"The Ohio State University, Ohio, USA","institution_ids":["https://openalex.org/I52357470"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5100676208"],"corresponding_institution_ids":["https://openalex.org/I52357470"],"apc_list":null,"apc_paid":null,"fwci":4.3338,"has_fulltext":false,"cited_by_count":29,"citation_normalized_percentile":{"value":0.9527785,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"85","last_page":"95"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9993000030517578,"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":0.9993000030517578,"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":0.9940999746322632,"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":0.9747999906539917,"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/computer-science","display_name":"Computer science","score":0.7382747530937195},{"id":"https://openalex.org/keywords/tensor-contraction","display_name":"Tensor contraction","score":0.6776990294456482},{"id":"https://openalex.org/keywords/code-generation","display_name":"Code generation","score":0.6481845378875732},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5680879950523376},{"id":"https://openalex.org/keywords/memory-hierarchy","display_name":"Memory hierarchy","score":0.5670037865638733},{"id":"https://openalex.org/keywords/tensor","display_name":"Tensor (intrinsic definition)","score":0.5217588543891907},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.4817393124103546},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.46976563334465027},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.442375123500824},{"id":"https://openalex.org/keywords/generator","display_name":"Generator (circuit theory)","score":0.4310239553451538},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.42101913690567017},{"id":"https://openalex.org/keywords/schema","display_name":"Schema (genetic algorithms)","score":0.41314461827278137},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.4024091064929962},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.36729490756988525},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.35575175285339355},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.34141457080841064},{"id":"https://openalex.org/keywords/tensor-product","display_name":"Tensor product","score":0.138567715883255},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13252407312393188},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.11048838496208191},{"id":"https://openalex.org/keywords/quantum","display_name":"Quantum","score":0.08607217669487}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7382747530937195},{"id":"https://openalex.org/C124007464","wikidata":"https://www.wikidata.org/wiki/Q428091","display_name":"Tensor contraction","level":3,"score":0.6776990294456482},{"id":"https://openalex.org/C133162039","wikidata":"https://www.wikidata.org/wiki/Q1061077","display_name":"Code generation","level":3,"score":0.6481845378875732},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5680879950523376},{"id":"https://openalex.org/C2778100165","wikidata":"https://www.wikidata.org/wiki/Q1589327","display_name":"Memory hierarchy","level":3,"score":0.5670037865638733},{"id":"https://openalex.org/C155281189","wikidata":"https://www.wikidata.org/wiki/Q3518150","display_name":"Tensor (intrinsic definition)","level":2,"score":0.5217588543891907},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.4817393124103546},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.46976563334465027},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.442375123500824},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.4310239553451538},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.42101913690567017},{"id":"https://openalex.org/C52146309","wikidata":"https://www.wikidata.org/wiki/Q7431116","display_name":"Schema (genetic algorithms)","level":2,"score":0.41314461827278137},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.4024091064929962},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.36729490756988525},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.35575175285339355},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.34141457080841064},{"id":"https://openalex.org/C51255310","wikidata":"https://www.wikidata.org/wiki/Q1163016","display_name":"Tensor product","level":2,"score":0.138567715883255},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13252407312393188},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.11048838496208191},{"id":"https://openalex.org/C84114770","wikidata":"https://www.wikidata.org/wiki/Q46344","display_name":"Quantum","level":2,"score":0.08607217669487},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.0},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"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/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.0},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","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},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cgo.2019.8661182","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cgo.2019.8661182","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE/ACM International Symposium on Code Generation and Optimization (CGO)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1527865336","https://openalex.org/W1584675441","https://openalex.org/W1967329527","https://openalex.org/W2036660245","https://openalex.org/W2051325990","https://openalex.org/W2054658678","https://openalex.org/W2077143534","https://openalex.org/W2080182206","https://openalex.org/W2105724942","https://openalex.org/W2252007067","https://openalex.org/W2466677533","https://openalex.org/W2471966094","https://openalex.org/W2588061952","https://openalex.org/W2591096648","https://openalex.org/W2786320458","https://openalex.org/W2794066882","https://openalex.org/W2804500013","https://openalex.org/W2963137752","https://openalex.org/W2963482281","https://openalex.org/W3099221095","https://openalex.org/W3101321165","https://openalex.org/W4293777437","https://openalex.org/W6631831896","https://openalex.org/W6676039487","https://openalex.org/W6737608435","https://openalex.org/W6748324931","https://openalex.org/W6752057402"],"related_works":["https://openalex.org/W2033101018","https://openalex.org/W2099278314","https://openalex.org/W2468576082","https://openalex.org/W4298226192","https://openalex.org/W2029856617","https://openalex.org/W2099571870","https://openalex.org/W2922451262","https://openalex.org/W2383929727","https://openalex.org/W2139208832","https://openalex.org/W3036899338"],"abstract_inverted_index":{"Tensor":[0],"contractions":[1,46],"are":[2],"higher":[3],"dimensional":[4],"generalizations":[5],"of":[6,14,65,71,83],"matrix-matrix":[7],"multiplication.":[8],"They":[9],"form":[10],"the":[11,74],"compute-intensive":[12],"core":[13],"many":[15],"applications":[16],"in":[17,44],"computational":[18],"science":[19],"and":[20,69,102],"data":[21,42,72],"science.":[22],"In":[23],"this":[24],"paper,":[25],"we":[26],"describe":[27],"a":[28,81],"high-performance":[29],"GPU":[30,75],"code":[31,51,93,103],"generator":[32],"for":[33,63],"arbitrary":[34],"tensor":[35,45,84,99],"contractions.":[36],"It":[37],"exploits":[38],"domain-specific":[39],"properties":[40],"about":[41],"reuse":[43],"to":[47,60,67],"devise":[48],"an":[49,56],"effective":[50,57],"generation":[52,94],"schema,":[53],"coupled":[54],"with":[55],"model-driven":[58],"search,":[59],"determine":[61],"parameters":[62],"mapping":[64],"computation":[66],"threads":[68],"staging":[70],"through":[73],"memory":[76],"hierarchy.":[77],"Experimental":[78],"evaluation":[79],"using":[80],"set":[82],"contraction":[85,100],"benchmarks":[86],"demonstrates":[87],"performance":[88],"improvement":[89],"and/or":[90],"significantly":[91],"reduced":[92],"time":[95],"over":[96],"other":[97],"state-of-the-art":[98],"libraries":[101],"generators.":[104]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}