{"id":"https://openalex.org/W2955510233","doi":"https://doi.org/10.1145/3316482.3326351","title":"Optimizing tensor contractions for embedded devices with racetrack memory scratch-pads","display_name":"Optimizing tensor contractions for embedded devices with racetrack memory scratch-pads","publication_year":2019,"publication_date":"2019-06-07","ids":{"openalex":"https://openalex.org/W2955510233","doi":"https://doi.org/10.1145/3316482.3326351","mag":"2955510233"},"language":"en","primary_location":{"id":"doi:10.1145/3316482.3326351","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3316482.3326351","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 20th ACM SIGPLAN/SIGBED International Conference on Languages, Compilers, and Tools for Embedded Systems","raw_type":"proceedings-article"},"type":"conference-paper","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/A5090070224","display_name":"Asif Ali Khan","orcid":"https://orcid.org/0000-0002-5130-9855"},"institutions":[{"id":"https://openalex.org/I78650965","display_name":"Technische Universit\u00e4t Dresden","ror":"https://ror.org/042aqky30","country_code":"DE","type":"education","lineage":["https://openalex.org/I78650965"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Asif Ali Khan","raw_affiliation_strings":["TU Dresden, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TU Dresden, Germany","institution_ids":["https://openalex.org/I78650965"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042792053","display_name":"Norman A. Rink","orcid":null},"institutions":[{"id":"https://openalex.org/I78650965","display_name":"Technische Universit\u00e4t Dresden","ror":"https://ror.org/042aqky30","country_code":"DE","type":"education","lineage":["https://openalex.org/I78650965"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Norman A. Rink","raw_affiliation_strings":["TU Dresden, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TU Dresden, Germany","institution_ids":["https://openalex.org/I78650965"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070038996","display_name":"Fazal Hameed","orcid":"https://orcid.org/0000-0002-2763-8755"},"institutions":[{"id":"https://openalex.org/I78650965","display_name":"Technische Universit\u00e4t Dresden","ror":"https://ror.org/042aqky30","country_code":"DE","type":"education","lineage":["https://openalex.org/I78650965"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Fazal Hameed","raw_affiliation_strings":["TU Dresden, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TU Dresden, Germany","institution_ids":["https://openalex.org/I78650965"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030115692","display_name":"Jer\u00f3nimo Castrill\u00f3n","orcid":"https://orcid.org/0000-0002-5007-445X"},"institutions":[{"id":"https://openalex.org/I78650965","display_name":"Technische Universit\u00e4t Dresden","ror":"https://ror.org/042aqky30","country_code":"DE","type":"education","lineage":["https://openalex.org/I78650965"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Jeronimo Castrillon","raw_affiliation_strings":["TU Dresden, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TU Dresden, Germany","institution_ids":["https://openalex.org/I78650965"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I78650965"],"apc_list":null,"apc_paid":null,"fwci":2.5885,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.89977105,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"5","last_page":"18"},"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9970999956130981,"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/T12326","display_name":"Network Packet Processing and Optimization","score":0.9850999712944031,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7851083278656006},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6266888380050659},{"id":"https://openalex.org/keywords/static-random-access-memory","display_name":"Static random-access memory","score":0.6011994481086731},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.5870958566665649},{"id":"https://openalex.org/keywords/tensor-contraction","display_name":"Tensor contraction","score":0.5131090879440308},{"id":"https://openalex.org/keywords/design-space-exploration","display_name":"Design space exploration","score":0.47786039113998413},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.4755903482437134},{"id":"https://openalex.org/keywords/efficient-energy-use","display_name":"Efficient energy use","score":0.470103919506073},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.45423170924186707},{"id":"https://openalex.org/keywords/scratch","display_name":"Scratch","score":0.4487239718437195},{"id":"https://openalex.org/keywords/optimizing-compiler","display_name":"Optimizing compiler","score":0.43132591247558594},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.43113622069358826},{"id":"https://openalex.org/keywords/memory-management","display_name":"Memory management","score":0.42674171924591064},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.41809308528900146},{"id":"https://openalex.org/keywords/energy-consumption","display_name":"Energy consumption","score":0.4158226549625397},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.368447870016098},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.29407358169555664},{"id":"https://openalex.org/keywords/tensor-product","display_name":"Tensor product","score":0.14433377981185913},{"id":"https://openalex.org/keywords/semiconductor-memory","display_name":"Semiconductor memory","score":0.14150312542915344},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.11600494384765625},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09142455458641052}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7851083278656006},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6266888380050659},{"id":"https://openalex.org/C68043766","wikidata":"https://www.wikidata.org/wiki/Q267416","display_name":"Static random-access memory","level":2,"score":0.6011994481086731},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.5870958566665649},{"id":"https://openalex.org/C124007464","wikidata":"https://www.wikidata.org/wiki/Q428091","display_name":"Tensor contraction","level":3,"score":0.5131090879440308},{"id":"https://openalex.org/C2776221188","wikidata":"https://www.wikidata.org/wiki/Q21072556","display_name":"Design space exploration","level":2,"score":0.47786039113998413},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.4755903482437134},{"id":"https://openalex.org/C2742236","wikidata":"https://www.wikidata.org/wiki/Q924713","display_name":"Efficient energy use","level":2,"score":0.470103919506073},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.45423170924186707},{"id":"https://openalex.org/C2781235140","wikidata":"https://www.wikidata.org/wiki/Q275131","display_name":"Scratch","level":2,"score":0.4487239718437195},{"id":"https://openalex.org/C190902152","wikidata":"https://www.wikidata.org/wiki/Q1325106","display_name":"Optimizing compiler","level":3,"score":0.43132591247558594},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.43113622069358826},{"id":"https://openalex.org/C176649486","wikidata":"https://www.wikidata.org/wiki/Q2308807","display_name":"Memory management","level":3,"score":0.42674171924591064},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.41809308528900146},{"id":"https://openalex.org/C2780165032","wikidata":"https://www.wikidata.org/wiki/Q16869822","display_name":"Energy consumption","level":2,"score":0.4158226549625397},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.368447870016098},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.29407358169555664},{"id":"https://openalex.org/C51255310","wikidata":"https://www.wikidata.org/wiki/Q1163016","display_name":"Tensor product","level":2,"score":0.14433377981185913},{"id":"https://openalex.org/C98986596","wikidata":"https://www.wikidata.org/wiki/Q1143031","display_name":"Semiconductor memory","level":2,"score":0.14150312542915344},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.11600494384765625},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09142455458641052},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3316482.3326351","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3316482.3326351","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 20th ACM SIGPLAN/SIGBED International Conference on Languages, Compilers, and Tools for Embedded Systems","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.9100000262260437,"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":65,"referenced_works":["https://openalex.org/W821744907","https://openalex.org/W1492553566","https://openalex.org/W1546569454","https://openalex.org/W1816932979","https://openalex.org/W1935056755","https://openalex.org/W1964031104","https://openalex.org/W1981443800","https://openalex.org/W1988425770","https://openalex.org/W1993445765","https://openalex.org/W1995812446","https://openalex.org/W2002711855","https://openalex.org/W2005242923","https://openalex.org/W2017836239","https://openalex.org/W2038073775","https://openalex.org/W2039762410","https://openalex.org/W2059696856","https://openalex.org/W2065359960","https://openalex.org/W2073061372","https://openalex.org/W2073505815","https://openalex.org/W2078760460","https://openalex.org/W2079103493","https://openalex.org/W2080063509","https://openalex.org/W2080312218","https://openalex.org/W2086329118","https://openalex.org/W2090032487","https://openalex.org/W2107114182","https://openalex.org/W2111435398","https://openalex.org/W2114067856","https://openalex.org/W2128344236","https://openalex.org/W2135653967","https://openalex.org/W2147926533","https://openalex.org/W2149590159","https://openalex.org/W2152175008","https://openalex.org/W2152595169","https://openalex.org/W2152839228","https://openalex.org/W2154367383","https://openalex.org/W2157456954","https://openalex.org/W2162528816","https://openalex.org/W2291372353","https://openalex.org/W2293405513","https://openalex.org/W2319633961","https://openalex.org/W2320746669","https://openalex.org/W2474317821","https://openalex.org/W2526202524","https://openalex.org/W2590246587","https://openalex.org/W2604449259","https://openalex.org/W2606722458","https://openalex.org/W2728600909","https://openalex.org/W2753463544","https://openalex.org/W2759062045","https://openalex.org/W2793767356","https://openalex.org/W2794066882","https://openalex.org/W2891477368","https://openalex.org/W2898373684","https://openalex.org/W2899771611","https://openalex.org/W2913174568","https://openalex.org/W2921853831","https://openalex.org/W2922451262","https://openalex.org/W2949251082","https://openalex.org/W2963137752","https://openalex.org/W3136479147","https://openalex.org/W4248073216","https://openalex.org/W4248271346","https://openalex.org/W4248445937","https://openalex.org/W4250534157"],"related_works":["https://openalex.org/W2475116013","https://openalex.org/W2770018148","https://openalex.org/W2358308169","https://openalex.org/W2385135707","https://openalex.org/W2140315382","https://openalex.org/W2059109728","https://openalex.org/W322691623","https://openalex.org/W2494989134","https://openalex.org/W2509444723","https://openalex.org/W4289810729"],"abstract_inverted_index":{"Tensor":[0],"contraction":[1],"is":[2],"a":[3,10],"fundamental":[4],"operation":[5],"in":[6,58,114],"many":[7],"algorithms":[8],"with":[9,99],"plethora":[11],"of":[12,29,38,44,50],"applications":[13],"ranging":[14],"from":[15],"quantum":[16],"chemistry":[17],"over":[18],"fluid":[19],"dynamics":[20],"and":[21,72,94,105,127,132],"image":[22],"processing":[23],"to":[24,60,109,136],"machine":[25],"learning.":[26],"The":[27],"performance":[28,126],"tensor":[30,74],"computations":[31],"critically":[32],"depends":[33],"on":[34,76],"the":[35,42,51,90,111,120,124],"efficient":[36,48],"utilization":[37],"on-chip":[39],"memories.":[40],"In":[41],"context":[43],"low-power":[45],"embedded":[46,77],"devices,":[47],"management":[49],"memory":[52,81,84],"space":[53],"becomes":[54],"even":[55],"more":[56],"crucial,":[57],"order":[59,93],"meet":[61],"energy":[62,128],"constraints.":[63],"This":[64],"work":[65],"aims":[66],"at":[67],"investigating":[68],"strategies":[69],"for":[70],"performance-":[71],"energy-efficient":[73],"contractions":[75],"systems,":[78],"using":[79],"racetrack":[80],"(RTM)-based":[82],"scratch-pad":[83],"(SPM).":[85],"Compiler":[86],"optimizations":[87,101,122],"such":[88,102],"as":[89,103],"loop":[91],"access":[92],"data":[95],"layout":[96],"transformations":[97],"paired":[98],"architectural":[100],"prefetching":[104],"preshifting":[106],"are":[107],"employed":[108],"reduce":[110],"shifting":[112],"overhead":[113],"RTMs.":[115],"Experimental":[116],"results":[117],"demonstrate":[118],"that":[119],"proposed":[121],"improve":[123],"SPM":[125],"consumption":[129],"by":[130],"24%":[131],"74%":[133],"respectively":[134],"compared":[135],"an":[137],"iso-capacity":[138],"SRAM.":[139]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":3}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}