{"id":"https://openalex.org/W4388667345","doi":"https://doi.org/10.1145/3581784.3607096","title":"Automatic Generation of Distributed-Memory Mappings for Tensor Computations","display_name":"Automatic Generation of Distributed-Memory Mappings for Tensor Computations","publication_year":2023,"publication_date":"2023-11-11","ids":{"openalex":"https://openalex.org/W4388667345","doi":"https://doi.org/10.1145/3581784.3607096"},"language":"en","primary_location":{"id":"doi:10.1145/3581784.3607096","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3581784.3607096","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3581784.3607096","source":null,"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","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":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3581784.3607096","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5048530008","display_name":"Martin Kong","orcid":"https://orcid.org/0000-0001-8008-0220"},"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":"Martin Kong","raw_affiliation_strings":["Ohio State University, Columbus, United States of America"],"raw_orcid":"https://orcid.org/0000-0001-8008-0220","affiliations":[{"raw_affiliation_string":"Ohio State University, Columbus, United States of America","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093260821","display_name":"Raneem Abu-Yosef","orcid":"https://orcid.org/0009-0000-6599-565X"},"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":"Raneem Abu Yosef","raw_affiliation_strings":["Ohio State University, Columbus, United States of America"],"raw_orcid":"https://orcid.org/0009-0000-6599-565X","affiliations":[{"raw_affiliation_string":"Ohio State University, Columbus, United States of America","institution_ids":["https://openalex.org/I52357470"]}]},{"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, United States of America"],"raw_orcid":"https://orcid.org/0000-0003-4556-4937","affiliations":[{"raw_affiliation_string":"Ohio State University, Columbus, United States of America","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/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, United States of America"],"raw_orcid":"https://orcid.org/0000-0002-4737-2034","affiliations":[{"raw_affiliation_string":"University of Utah, Salt Lake City, United States of America","institution_ids":["https://openalex.org/I223532165"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.8793,"has_fulltext":true,"cited_by_count":9,"citation_normalized_percentile":{"value":0.90790569,"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":"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":0.9991999864578247,"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":0.9991999864578247,"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":0.9969000220298767,"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/T11809","display_name":"Advanced NMR Techniques and Applications","score":0.9908999800682068,"subfield":{"id":"https://openalex.org/subfields/1607","display_name":"Spectroscopy"},"field":{"id":"https://openalex.org/fields/16","display_name":"Chemistry"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8453773260116577},{"id":"https://openalex.org/keywords/distributed-memory","display_name":"Distributed memory","score":0.708284318447113},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.6776537895202637},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6364080905914307},{"id":"https://openalex.org/keywords/affine-transformation","display_name":"Affine transformation","score":0.5397414565086365},{"id":"https://openalex.org/keywords/tensor","display_name":"Tensor (intrinsic definition)","score":0.5318325161933899},{"id":"https://openalex.org/keywords/automatic-parallelization","display_name":"Automatic parallelization","score":0.5189304351806641},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.42172369360923767},{"id":"https://openalex.org/keywords/shared-memory","display_name":"Shared memory","score":0.4118228554725647},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.39290517568588257},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.34882014989852905},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2360120415687561},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.21961688995361328},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.11621767282485962},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.07821452617645264}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8453773260116577},{"id":"https://openalex.org/C91481028","wikidata":"https://www.wikidata.org/wiki/Q1054686","display_name":"Distributed memory","level":3,"score":0.708284318447113},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.6776537895202637},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6364080905914307},{"id":"https://openalex.org/C92757383","wikidata":"https://www.wikidata.org/wiki/Q382497","display_name":"Affine transformation","level":2,"score":0.5397414565086365},{"id":"https://openalex.org/C155281189","wikidata":"https://www.wikidata.org/wiki/Q3518150","display_name":"Tensor (intrinsic definition)","level":2,"score":0.5318325161933899},{"id":"https://openalex.org/C164833996","wikidata":"https://www.wikidata.org/wiki/Q2323839","display_name":"Automatic parallelization","level":3,"score":0.5189304351806641},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.42172369360923767},{"id":"https://openalex.org/C133875982","wikidata":"https://www.wikidata.org/wiki/Q764810","display_name":"Shared memory","level":2,"score":0.4118228554725647},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.39290517568588257},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.34882014989852905},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2360120415687561},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.21961688995361328},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.11621767282485962},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.07821452617645264},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3581784.3607096","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3581784.3607096","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3581784.3607096","source":null,"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","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:10.1145/3581784.3607096","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3581784.3607096","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3581784.3607096","source":null,"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","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":[{"id":"https://openalex.org/G2361063028","display_name":null,"funder_award_id":"223437","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G2488707916","display_name":"Collaborative Research: PPoSS: Large: A comprehensive framework for efficient, scalable, and performance-portable tensor applications","funder_award_id":"2234376","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6139544349","display_name":"Collaborative Research: PPoSS: Large: A Comprehensive Framework for Efficient, Scalable, and Performance-Portable Tensor Applications","funder_award_id":"2217154","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8181984440","display_name":"Collaborative Research: PPoSS: Large: A comprehensive framework for efficient, scalable, and performance-portable tensor applications","funder_award_id":"2216903","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4388667345.pdf","grobid_xml":"https://content.openalex.org/works/W4388667345.grobid-xml"},"referenced_works_count":22,"referenced_works":["https://openalex.org/W201315547","https://openalex.org/W1509197282","https://openalex.org/W1598993252","https://openalex.org/W1964711958","https://openalex.org/W1999360210","https://openalex.org/W2002897809","https://openalex.org/W2008117760","https://openalex.org/W2008677874","https://openalex.org/W2056999868","https://openalex.org/W2076517649","https://openalex.org/W2085036300","https://openalex.org/W2127226421","https://openalex.org/W2140639562","https://openalex.org/W2157237396","https://openalex.org/W2478459296","https://openalex.org/W2905135312","https://openalex.org/W2962976813","https://openalex.org/W2984305089","https://openalex.org/W3146625038","https://openalex.org/W3151489216","https://openalex.org/W4220690649","https://openalex.org/W6969132865"],"related_works":["https://openalex.org/W2026512611","https://openalex.org/W1985165680","https://openalex.org/W4245497162","https://openalex.org/W2353146130","https://openalex.org/W1990817968","https://openalex.org/W2150064838","https://openalex.org/W1933089384","https://openalex.org/W2185094550","https://openalex.org/W2088823210","https://openalex.org/W2135766592"],"abstract_inverted_index":{"While":[0],"considerable":[1],"research":[2],"has":[3,14],"been":[4,15],"directed":[5],"at":[6],"automatic":[7,18],"parallelization":[8,19],"for":[9,21,35],"shared-memory":[10],"platforms,":[11],"little":[12],"progress":[13],"made":[16],"in":[17],"schemes":[20],"distributed-memory":[22,32],"systems.":[23],"We":[24],"introduce":[25],"an":[26,36],"innovative":[27],"approach":[28],"to":[29,44],"automatically":[30],"produce":[31],"parallel":[33],"code":[34],"important":[37],"subclass":[38],"of":[39],"affine":[40],"tensor":[41],"computations":[42],"common":[43],"Coupled":[45],"Cluster":[46],"(CC)":[47],"electronic":[48],"structure":[49],"methods,":[50],"neuro-imaging":[51],"applications,":[52],"and":[53],"deep":[54],"learning":[55],"models.":[56]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}