{"id":"https://openalex.org/W2564103638","doi":"https://doi.org/10.1145/3012011","title":"Designing a Tunable Nested Data-Parallel Programming System","display_name":"Designing a Tunable Nested Data-Parallel Programming System","publication_year":2016,"publication_date":"2016-12-28","ids":{"openalex":"https://openalex.org/W2564103638","doi":"https://doi.org/10.1145/3012011","mag":"2564103638"},"language":"en","primary_location":{"id":"doi:10.1145/3012011","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3012011","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=3012011&type=pdf","source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Architecture and Code Optimization","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"http://dl.acm.org/ft_gateway.cfm?id=3012011&type=pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5033185286","display_name":"Saurav Muralidharan","orcid":"https://orcid.org/0000-0003-4024-3958"},"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":true,"raw_author_name":"Saurav Muralidharan","raw_affiliation_strings":["University of Utah"],"affiliations":[{"raw_affiliation_string":"University of Utah","institution_ids":["https://openalex.org/I223532165"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024606205","display_name":"Michael Garland","orcid":"https://orcid.org/0000-0001-6093-7602"},"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":"Michael Garland","raw_affiliation_strings":["NVIDIA Corporation, Santa Clara, CA"],"affiliations":[{"raw_affiliation_string":"NVIDIA Corporation, Santa Clara, CA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004915198","display_name":"Albert Sidelnik","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":"Albert Sidelnik","raw_affiliation_strings":["NVIDIA Corporation, Santa Clara, CA"],"affiliations":[{"raw_affiliation_string":"NVIDIA Corporation, Santa Clara, CA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030152493","display_name":"Mary Hall","orcid":"https://orcid.org/0000-0002-3058-7573"},"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":"Mary Hall","raw_affiliation_strings":["University of Utah, Salt Lake City, UT"],"affiliations":[{"raw_affiliation_string":"University of Utah, Salt Lake City, UT","institution_ids":["https://openalex.org/I223532165"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5033185286"],"corresponding_institution_ids":["https://openalex.org/I223532165"],"apc_list":null,"apc_paid":null,"fwci":0.3153,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.6037239,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"13","issue":"4","first_page":"1","last_page":"24"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":1.0,"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":1.0,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9994000196456909,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9983000159263611,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8765959739685059},{"id":"https://openalex.org/keywords/porting","display_name":"Porting","score":0.8645480871200562},{"id":"https://openalex.org/keywords/implementation","display_name":"Implementation","score":0.7407233119010925},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5181645154953003},{"id":"https://openalex.org/keywords/interface","display_name":"Interface (matter)","score":0.5176756381988525},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5081336498260498},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.45350977778434753},{"id":"https://openalex.org/keywords/nested-loop-join","display_name":"Nested loop join","score":0.4102455675601959},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.35293781757354736},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.16441097855567932}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8765959739685059},{"id":"https://openalex.org/C106251023","wikidata":"https://www.wikidata.org/wiki/Q851989","display_name":"Porting","level":3,"score":0.8645480871200562},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.7407233119010925},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5181645154953003},{"id":"https://openalex.org/C113843644","wikidata":"https://www.wikidata.org/wiki/Q901882","display_name":"Interface (matter)","level":4,"score":0.5176756381988525},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5081336498260498},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.45350977778434753},{"id":"https://openalex.org/C1306188","wikidata":"https://www.wikidata.org/wiki/Q4060687","display_name":"Nested loop join","level":2,"score":0.4102455675601959},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.35293781757354736},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.16441097855567932},{"id":"https://openalex.org/C129307140","wikidata":"https://www.wikidata.org/wiki/Q6795880","display_name":"Maximum bubble pressure method","level":3,"score":0.0},{"id":"https://openalex.org/C157915830","wikidata":"https://www.wikidata.org/wiki/Q2928001","display_name":"Bubble","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3012011","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3012011","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=3012011&type=pdf","source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Architecture and Code Optimization","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/3012011","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3012011","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=3012011&type=pdf","source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Architecture and Code Optimization","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5388338410","display_name":null,"funder_award_id":"HR0011-13-3-0001","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"}],"funders":[{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2564103638.pdf","grobid_xml":"https://content.openalex.org/works/W2564103638.grobid-xml"},"referenced_works_count":39,"referenced_works":["https://openalex.org/W1480958225","https://openalex.org/W1503668062","https://openalex.org/W1583210003","https://openalex.org/W1971367716","https://openalex.org/W1971520093","https://openalex.org/W1988888548","https://openalex.org/W1997978901","https://openalex.org/W2026049208","https://openalex.org/W2035080386","https://openalex.org/W2053999255","https://openalex.org/W2054625910","https://openalex.org/W2055312318","https://openalex.org/W2061313045","https://openalex.org/W2079577430","https://openalex.org/W2088394577","https://openalex.org/W2100218206","https://openalex.org/W2120497510","https://openalex.org/W2121546953","https://openalex.org/W2128853364","https://openalex.org/W2130179171","https://openalex.org/W2138163628","https://openalex.org/W2148599839","https://openalex.org/W2148603752","https://openalex.org/W2150593711","https://openalex.org/W2150848984","https://openalex.org/W2154697693","https://openalex.org/W2158626113","https://openalex.org/W2165461546","https://openalex.org/W2165673828","https://openalex.org/W2289151794","https://openalex.org/W2293881866","https://openalex.org/W2521313883","https://openalex.org/W2554770544","https://openalex.org/W2911472304","https://openalex.org/W2913602891","https://openalex.org/W4230614322","https://openalex.org/W4232836277","https://openalex.org/W4251164127","https://openalex.org/W6832800064"],"related_works":["https://openalex.org/W190731304","https://openalex.org/W2083338789","https://openalex.org/W1541860819","https://openalex.org/W1499552465","https://openalex.org/W1984757784","https://openalex.org/W1554764448","https://openalex.org/W2348711589","https://openalex.org/W1517184264","https://openalex.org/W3005521981","https://openalex.org/W2170197447"],"abstract_inverted_index":{"This":[0],"article":[1],"describes":[2],"Surge,":[3],"a":[4,31,61,77,87],"nested":[5],"data-parallel":[6,53],"programming":[7,33],"system":[8,80,99],"designed":[9],"to":[10,19,75,105],"simplify":[11],"the":[12,48,128],"porting":[13],"and":[14,44,84,96,122,126,135],"tuning":[15],"of":[16,27,63,90],"parallel":[17],"applications":[18],"multiple":[20],"target":[21],"architectures.":[22],"Surge":[23,112,131],"decouples":[24],"high-level":[25,129],"specification":[26],"computations,":[28],"expressed":[29],"using":[30,39],"C++":[32],"interface,":[34],"from":[35,116,127],"low-level":[36],"implementation":[37],"details":[38],"two":[40,71],"first-class":[41],"constructs:":[42],"schedules":[43],"policies.":[45],"Schedules":[46],"describe":[47],"valid":[49,91],"ways":[50],"in":[51,111],"which":[52],"operators":[54],"may":[55],"be":[56],"implemented,":[57],"while":[58],"policies":[59],"encapsulate":[60],"set":[62],"parameters":[64],"that":[65,81,138],"govern":[66],"platform-specific":[67,92],"code":[68,78],"generation.":[69],"These":[70],"mechanisms":[72],"are":[73],"used":[74],"implement":[76],"generation":[79],"analyzes":[82],"computations":[83],"automatically":[85,132],"generates":[86,133],"search":[88,103],"space":[89,104],"implementations.":[93,108],"An":[94],"input":[95],"architecture-adaptive":[97],"autotuning":[98],"then":[100],"explores":[101],"this":[102],"find":[106],"optimized":[107,147],"We":[109],"express":[110],"five":[113],"real-world":[114],"benchmarks":[115],"domains":[117],"such":[118],"as":[119],"machine":[120],"learning":[121],"sparse":[123],"linear":[124],"algebra":[125],"specifications,":[130],"CPU":[134],"GPU":[136],"implementations":[137],"perform":[139],"on":[140],"par":[141],"with":[142],"or":[143],"better":[144],"than":[145],"manually":[146],"versions.":[148]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2018,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}