{"id":"https://openalex.org/W2806891462","doi":"https://doi.org/10.1145/3211346.3211354","title":"Diesel: DSL for linear algebra and neural net computations on GPUs","display_name":"Diesel: DSL for linear algebra and neural net computations on GPUs","publication_year":2018,"publication_date":"2018-06-07","ids":{"openalex":"https://openalex.org/W2806891462","doi":"https://doi.org/10.1145/3211346.3211354","mag":"2806891462"},"language":"en","primary_location":{"id":"doi:10.1145/3211346.3211354","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3211346.3211354","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2nd ACM SIGPLAN International Workshop on Machine Learning and Programming Languages","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/A5007976782","display_name":"Venmugil Elango","orcid":"https://orcid.org/0000-0002-7031-9020"},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Venmugil Elango","raw_affiliation_strings":["NVIDIA, USA"],"affiliations":[{"raw_affiliation_string":"NVIDIA, USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034777515","display_name":"Norm Rubin","orcid":null},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Norm Rubin","raw_affiliation_strings":["NVIDIA, USA"],"affiliations":[{"raw_affiliation_string":"NVIDIA, USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023732985","display_name":"M. Ravishankar","orcid":null},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mahesh Ravishankar","raw_affiliation_strings":["NVIDIA, USA"],"affiliations":[{"raw_affiliation_string":"NVIDIA, USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055671465","display_name":"Hariharan Sandanagobalane","orcid":null},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hariharan Sandanagobalane","raw_affiliation_strings":["NVIDIA, USA"],"affiliations":[{"raw_affiliation_string":"NVIDIA, USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077691647","display_name":"Vinod Grover","orcid":null},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vinod Grover","raw_affiliation_strings":["NVIDIA, USA"],"affiliations":[{"raw_affiliation_string":"NVIDIA, USA","institution_ids":["https://openalex.org/I4210127875"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5007976782"],"corresponding_institution_ids":["https://openalex.org/I4210127875"],"apc_list":null,"apc_paid":null,"fwci":7.8265,"has_fulltext":false,"cited_by_count":45,"citation_normalized_percentile":{"value":0.98007822,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"42","last_page":"51"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9995999932289124,"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":0.9995999932289124,"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/T12808","display_name":"Ferroelectric and Negative Capacitance Devices","score":0.9990000128746033,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.9884999990463257,"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/computer-science","display_name":"Computer science","score":0.7706134915351868},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.638008177280426},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.6361165046691895},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.628192663192749},{"id":"https://openalex.org/keywords/linear-algebra","display_name":"Linear algebra","score":0.5897209644317627},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5600005388259888},{"id":"https://openalex.org/keywords/code-generation","display_name":"Code generation","score":0.4932700991630554},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4869493246078491},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.46422335505485535},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.41938483715057373},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.41375264525413513},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.35427314043045044},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.32821667194366455},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.28925228118896484},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.18724337220191956},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11037373542785645}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7706134915351868},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.638008177280426},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.6361165046691895},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.628192663192749},{"id":"https://openalex.org/C139352143","wikidata":"https://www.wikidata.org/wiki/Q82571","display_name":"Linear algebra","level":2,"score":0.5897209644317627},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5600005388259888},{"id":"https://openalex.org/C133162039","wikidata":"https://www.wikidata.org/wiki/Q1061077","display_name":"Code generation","level":3,"score":0.4932700991630554},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4869493246078491},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.46422335505485535},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.41938483715057373},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.41375264525413513},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.35427314043045044},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.32821667194366455},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.28925228118896484},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.18724337220191956},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11037373542785645},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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},{"id":"https://openalex.org/C84114770","wikidata":"https://www.wikidata.org/wiki/Q46344","display_name":"Quantum","level":2,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3211346.3211354","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3211346.3211354","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2nd ACM SIGPLAN International Workshop on Machine Learning and Programming Languages","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":5,"referenced_works":["https://openalex.org/W1191262899","https://openalex.org/W1558370006","https://openalex.org/W2034761517","https://openalex.org/W2077143534","https://openalex.org/W3042286635"],"related_works":["https://openalex.org/W650988184","https://openalex.org/W2162410319","https://openalex.org/W2137356287","https://openalex.org/W4321184925","https://openalex.org/W60915090","https://openalex.org/W2025840053","https://openalex.org/W2161692994","https://openalex.org/W3121314575","https://openalex.org/W3147497457","https://openalex.org/W4206336957"],"abstract_inverted_index":{"We":[0],"present":[1],"a":[2,37,41,52,109,132],"domain":[3],"specific":[4,151],"language":[5],"compiler,":[6],"Diesel,":[7],"for":[8,29,93,128,150,163,197,212],"basic":[9],"linear":[10],"algebra":[11],"and":[12,24,59,76,182],"neural":[13,38],"network":[14,39],"computations,":[15,214],"that":[16,189],"accepts":[17],"input":[18],"expressions":[19],"in":[20,47],"an":[21],"intuitive":[22],"form":[23],"generates":[25,116],"high":[26],"performing":[27],"code":[28,125,145,196],"GPUs.":[30],"The":[31],"current":[32],"trend":[33],"is":[34,97,126],"to":[35,51,64,89,100,106,147,154,202],"represent":[36],"as":[40,56,74,131],"computation":[42,110,130],"DAG,":[43],"where":[44,123,143],"each":[45],"node":[46],"the":[48,61,124,129,144,190,203],"DAG":[49],"corresponds":[50],"single":[53],"operation":[54],"such":[55,73],"matrix-matrix":[57],"multiplication,":[58],"map":[60],"individual":[62,94,198],"operations":[63,199],"hand":[65],"tuned":[66,205],"library":[67,87],"functions":[68],"provided":[69,171,207],"by":[70,193,208],"standard":[71,159,209],"libraries":[72,160],"CuBLAS":[75],"CuDNN.":[77],"While":[78,158],"this":[79],"method":[80],"takes":[81],"advantage":[82],"of":[83,112,119],"readily":[84],"available":[85],"optimized":[86,127],"codes":[88],"achieve":[90,155],"good":[91],"performance":[92,191],"operations,":[95,114],"it":[96],"not":[98],"possible":[99],"optimize":[101],"across":[102],"operations.":[103],"As":[104],"opposed":[105],"this,":[107],"given":[108],"composed":[111],"several":[113],"Diesel":[115,174,194,215],"(a":[117],"set)":[118],"efficient":[120],"device":[121],"functions,":[122],"whole,":[133],"using":[134],"polyhedral":[135],"compilation":[136],"techniques.":[137],"In":[138],"addition,":[139],"there":[140],"are":[141,161,170,200],"cases":[142],"needs":[146],"be":[148],"specialized":[149,184],"problem":[152,165,168,177],"sizes":[153,166,169,178],"optimal":[156],"performance.":[157],"written":[162,218],"parametric":[164],"(where":[167],"at":[172,179],"runtime),":[173],"can":[175],"accept":[176],"compile":[180],"time":[181],"generate":[183],"codes.":[185],"Experimental":[186],"results":[187],"show":[188],"achieved":[192],"generated":[195],"comparable":[201],"highly":[204],"versions":[206],"libraries,":[210],"while":[211],"composite":[213],"outperforms":[216],"manually":[217],"versions.":[219]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":12},{"year":2020,"cited_by_count":12},{"year":2019,"cited_by_count":7}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}