{"id":"https://openalex.org/W2787898679","doi":"https://doi.org/10.1145/3178433.3178436","title":"SIMDization of Small Tensor Multiplication Kernels for Wide SIMD Vector Processors","display_name":"SIMDization of Small Tensor Multiplication Kernels for Wide SIMD Vector Processors","publication_year":2018,"publication_date":"2018-02-16","ids":{"openalex":"https://openalex.org/W2787898679","doi":"https://doi.org/10.1145/3178433.3178436","mag":"2787898679"},"language":"en","primary_location":{"id":"doi:10.1145/3178433.3178436","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3178433.3178436","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2018 4th Workshop on Programming Models for SIMD/Vector Processing","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/A5087702701","display_name":"Christopher Rodrigues","orcid":null},"institutions":[{"id":"https://openalex.org/I4210146936","display_name":"Huawei Technologies (United States)","ror":"https://ror.org/03jyqk712","country_code":"US","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210146936"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Christopher Rodrigues","raw_affiliation_strings":["Huawei America Research Lab, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei America Research Lab, United States","institution_ids":["https://openalex.org/I4210146936"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041821526","display_name":"Amarin Phaosawasdi","orcid":null},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Amarin Phaosawasdi","raw_affiliation_strings":["University of Illinois at Urbana-Champaign, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, United States","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108630261","display_name":"Peng Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210146936","display_name":"Huawei Technologies (United States)","ror":"https://ror.org/03jyqk712","country_code":"US","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210146936"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Peng Wu","raw_affiliation_strings":["Huawei America Research Lab, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei America Research Lab, United States","institution_ids":["https://openalex.org/I4210146936"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.7126,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.68401015,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9939000010490417,"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"}},{"id":"https://openalex.org/T12303","display_name":"Tensor decomposition and applications","score":0.9847999811172485,"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/simd","display_name":"SIMD","score":0.9232580065727234},{"id":"https://openalex.org/keywords/vectorization","display_name":"Vectorization (mathematics)","score":0.850785493850708},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.8341948986053467},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8279287219047546},{"id":"https://openalex.org/keywords/multiplication","display_name":"Multiplication (music)","score":0.5086851716041565},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.483218789100647},{"id":"https://openalex.org/keywords/vector-processor","display_name":"Vector processor","score":0.4729570746421814},{"id":"https://openalex.org/keywords/loop","display_name":"Loop (graph theory)","score":0.47295495867729187},{"id":"https://openalex.org/keywords/nested-loop-join","display_name":"Nested loop join","score":0.43060770630836487},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.40881460905075073},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.15047860145568848},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07823500037193298}],"concepts":[{"id":"https://openalex.org/C150552126","wikidata":"https://www.wikidata.org/wiki/Q339387","display_name":"SIMD","level":2,"score":0.9232580065727234},{"id":"https://openalex.org/C41681595","wikidata":"https://www.wikidata.org/wiki/Q7917855","display_name":"Vectorization (mathematics)","level":2,"score":0.850785493850708},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.8341948986053467},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8279287219047546},{"id":"https://openalex.org/C2780595030","wikidata":"https://www.wikidata.org/wiki/Q3860309","display_name":"Multiplication (music)","level":2,"score":0.5086851716041565},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.483218789100647},{"id":"https://openalex.org/C161824985","wikidata":"https://www.wikidata.org/wiki/Q919509","display_name":"Vector processor","level":2,"score":0.4729570746421814},{"id":"https://openalex.org/C184670325","wikidata":"https://www.wikidata.org/wiki/Q512604","display_name":"Loop (graph theory)","level":2,"score":0.47295495867729187},{"id":"https://openalex.org/C1306188","wikidata":"https://www.wikidata.org/wiki/Q4060687","display_name":"Nested loop join","level":2,"score":0.43060770630836487},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.40881460905075073},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.15047860145568848},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07823500037193298},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3178433.3178436","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3178433.3178436","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2018 4th Workshop on Programming Models for SIMD/Vector Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1494930385","https://openalex.org/W1939907483","https://openalex.org/W1975166067","https://openalex.org/W1975594295","https://openalex.org/W1991009705","https://openalex.org/W2011393414","https://openalex.org/W2022711417","https://openalex.org/W2073061372","https://openalex.org/W2111394443","https://openalex.org/W2118031182","https://openalex.org/W2128344236","https://openalex.org/W2137857636","https://openalex.org/W2157273783","https://openalex.org/W2167639788","https://openalex.org/W2590246587","https://openalex.org/W4245987756"],"related_works":["https://openalex.org/W2566637483","https://openalex.org/W2127324789","https://openalex.org/W3024308452","https://openalex.org/W4244894488","https://openalex.org/W4285390450","https://openalex.org/W1605349877","https://openalex.org/W2368918171","https://openalex.org/W881027429","https://openalex.org/W2085171150","https://openalex.org/W4287322835"],"abstract_inverted_index":{"Developers":[0],"often":[1],"rely":[2],"on":[3],"automatic":[4,26],"vectorization":[5,27],"to":[6,32,52],"speed":[7],"up":[8],"fine-grained":[9],"data-parallel":[10],"code.":[11],"However,":[12],"for":[13],"loop":[14],"nests":[15],"where":[16],"the":[17,22,44],"loops":[18,56],"are":[19],"shorter":[20],"than":[21],"processor's":[23,45],"SIMD":[24,46],"width,":[25],"performs":[28],"poorly.":[29],"Vectorizers":[30],"attempt":[31],"vectorize":[33,53],"a":[34,41],"single":[35],"short":[36],"loop,":[37],"using":[38],"(at":[39],"best)":[40],"fraction":[42],"of":[43],"capacity.":[47],"It":[48],"is":[49],"not":[50],"straightforward":[51],"multiple":[54,65],"nested":[55],"together":[57],"because":[58],"they":[59],"typically":[60],"have":[61],"memory":[62],"accesses":[63],"with":[64],"strides,":[66],"which":[67],"conventional":[68],"methods":[69],"cannot":[70],"profitably":[71],"vectorize.":[72]},"counts_by_year":[{"year":2021,"cited_by_count":2},{"year":2019,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}