{"id":"https://openalex.org/W2466677533","doi":"https://doi.org/10.1145/2935323.2935328","title":"TTC: a tensor transposition compiler for multiple architectures","display_name":"TTC: a tensor transposition compiler for multiple architectures","publication_year":2016,"publication_date":"2016-06-02","ids":{"openalex":"https://openalex.org/W2466677533","doi":"https://doi.org/10.1145/2935323.2935328","mag":"2466677533"},"language":"en","primary_location":{"id":"doi:10.1145/2935323.2935328","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2935323.2935328","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 3rd ACM SIGPLAN International Workshop on Libraries, Languages, and Compilers for Array Programming","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1607.01249","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5025638687","display_name":"Paul Springer","orcid":"https://orcid.org/0000-0002-8760-8793"},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Paul Springer","raw_affiliation_strings":["RWTH Aachen University, Germany"],"affiliations":[{"raw_affiliation_string":"RWTH Aachen University, Germany","institution_ids":["https://openalex.org/I887968799"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085441820","display_name":"Aravind Sankaran","orcid":"https://orcid.org/0000-0003-2810-7531"},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Aravind Sankaran","raw_affiliation_strings":["RWTH Aachen University, Germany"],"affiliations":[{"raw_affiliation_string":"RWTH Aachen University, Germany","institution_ids":["https://openalex.org/I887968799"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048393932","display_name":"Paolo Bientinesi","orcid":"https://orcid.org/0000-0002-4972-7097"},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Paolo Bientinesi","raw_affiliation_strings":["RWTH Aachen University, Germany"],"affiliations":[{"raw_affiliation_string":"RWTH Aachen University, Germany","institution_ids":["https://openalex.org/I887968799"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5025638687"],"corresponding_institution_ids":["https://openalex.org/I887968799"],"apc_list":null,"apc_paid":null,"fwci":3.8525,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.93471512,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"41","last_page":"46"},"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.983299970626831,"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":0.982699990272522,"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/compiler","display_name":"Compiler","score":0.9179636240005493},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8423041105270386},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.8134114146232605},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.810244083404541},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.24668288230895996}],"concepts":[{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.9179636240005493},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8423041105270386},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.8134114146232605},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.810244083404541},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.24668288230895996}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/2935323.2935328","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2935323.2935328","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 3rd ACM SIGPLAN International Workshop on Libraries, Languages, and Compilers for Array Programming","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1607.01249","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1607.01249","pdf_url":"https://arxiv.org/pdf/1607.01249","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:publications.rwth-aachen.de:682429","is_oa":false,"landing_page_url":"https://publications.rwth-aachen.de/search?p=id:%22RWTH-CONV-211805%22","pdf_url":null,"source":{"id":"https://openalex.org/S4306401033","display_name":"RWTH Publications (RWTH Aachen)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I887968799","host_organization_name":"RWTH Aachen University","host_organization_lineage":["https://openalex.org/I887968799"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1607.01249","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1607.01249","pdf_url":"https://arxiv.org/pdf/1607.01249","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1789336918","https://openalex.org/W1979796968","https://openalex.org/W1985734797","https://openalex.org/W2017345827","https://openalex.org/W2019463754","https://openalex.org/W2038945443","https://openalex.org/W2051325990","https://openalex.org/W2060987590","https://openalex.org/W2069864004","https://openalex.org/W2072991195","https://openalex.org/W2098614082","https://openalex.org/W2102182691","https://openalex.org/W2115897625","https://openalex.org/W2176391467","https://openalex.org/W2187904758","https://openalex.org/W2252007067","https://openalex.org/W2271840356","https://openalex.org/W2295543477","https://openalex.org/W3103952756","https://openalex.org/W3105468881","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W3213381848","https://openalex.org/W2005148983","https://openalex.org/W2017587301","https://openalex.org/W2012954338","https://openalex.org/W2096672917","https://openalex.org/W2392023973","https://openalex.org/W2939411666","https://openalex.org/W2009169896"],"abstract_inverted_index":{"We":[0,69,123],"consider":[1],"the":[2,32,84,107,138,147,150],"problem":[3],"of":[4,7,31,72,116,140,149],"transposing":[5],"tensors":[6],"arbitrary":[8],"dimension":[9],"and":[10,66,109,120],"describe":[11],"TTC,":[12],"an":[13],"open":[14],"source":[15],"domain-specific":[16,89],"parallel":[17,22],"compiler.":[18],"TTC":[19,37,73,113],"generates":[20],"optimized":[21],"C++/CUDA":[23],"C":[24],"code":[25],"that":[26,87,144],"achieves":[27],"a":[28,75,88,134],"significant":[29],"fraction":[30],"system's":[33],"peak":[34],"memory":[35],"bandwidth.":[36],"exhibits":[38],"high":[39],"performance":[40],"across":[41],"multiple":[42,129],"architectures,":[43],"including":[44],"modern":[45],"AVX-based":[46],"systems":[47],"(e.g.,":[48],"Intel":[49],"Haswell,":[50],"AMD":[51],"Steamroller),":[52],"Intel's":[53,102],"Knights":[54,110],"Corner":[55,111],"as":[56,58,63],"well":[57],"different":[59],"CUDA-based":[60],"GPUs":[61],"such":[62],"NVIDIA's":[64],"Kepler":[65],"Maxwell":[67],"architectures.":[68],"report":[70],"speedups":[71,115],"over":[74],"meaningful":[76],"baseline":[77],"implementation":[78],"generated":[79],"by":[80],"external":[81],"C++":[82,104],"compilers;":[83],"results":[85],"suggest":[86],"compiler":[90,105],"can":[91],"outperform":[92],"its":[93],"general":[94],"purpose":[95],"counterpart":[96],"significantly:":[97],"For":[98],"instance,":[99],"comparing":[100],"with":[101],"latest":[103],"on":[106],"Haswell":[108],"architecture,":[112],"yields":[114],"up":[117],"to":[118],"8x":[119],"32x,":[121],"respectively.":[122],"also":[124],"showcase":[125],"TTC's":[126],"support":[127],"for":[128,137],"leading":[130],"dimensions,":[131],"making":[132],"it":[133],"suitable":[135],"candidate":[136],"generation":[139],"performance-critical":[141],"packing":[142],"functions":[143],"are":[145],"at":[146],"core":[148],"ubiquitous":[151],"BLAS":[152],"3":[153],"routines.":[154]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":3}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
