{"id":"https://openalex.org/W2146606012","doi":"https://doi.org/10.1109/ipdps.2009.5161039","title":"A framework for efficient and scalable execution of domain-specific templates on GPUs","display_name":"A framework for efficient and scalable execution of domain-specific templates on GPUs","publication_year":2009,"publication_date":"2009-05-01","ids":{"openalex":"https://openalex.org/W2146606012","doi":"https://doi.org/10.1109/ipdps.2009.5161039","mag":"2146606012"},"language":"en","primary_location":{"id":"doi:10.1109/ipdps.2009.5161039","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipdps.2009.5161039","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE International Symposium on Parallel & Distributed 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/A5110744540","display_name":"Narayanan Sundaram","orcid":null},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]},{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Narayanan Sundaram","raw_affiliation_strings":["Department of EECS, University of California at Berkeley, CA, USA","NEC Laboratories America Princeton, NJ, USA"],"affiliations":[{"raw_affiliation_string":"Department of EECS, University of California at Berkeley, CA, USA","institution_ids":["https://openalex.org/I95457486"]},{"raw_affiliation_string":"NEC Laboratories America Princeton, NJ, USA","institution_ids":["https://openalex.org/I20089843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065766721","display_name":"Anand Raghunathan","orcid":"https://orcid.org/0000-0002-4624-564X"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]},{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anand Raghunathan","raw_affiliation_strings":["NEC Laboratories America Princeton, NJ, USA","School of ECE Purdue University, IN, USA"],"affiliations":[{"raw_affiliation_string":"NEC Laboratories America Princeton, NJ, USA","institution_ids":["https://openalex.org/I20089843"]},{"raw_affiliation_string":"School of ECE Purdue University, IN, USA","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042424184","display_name":"Srimat Chakradhar","orcid":"https://orcid.org/0000-0003-3530-3901"},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Srimat T. Chakradhar","raw_affiliation_strings":["NEC Laboratories America Princeton, Princeton, NJ, USA"],"affiliations":[{"raw_affiliation_string":"NEC Laboratories America Princeton, Princeton, NJ, USA","institution_ids":["https://openalex.org/I20089843"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5110744540"],"corresponding_institution_ids":["https://openalex.org/I20089843","https://openalex.org/I95457486"],"apc_list":null,"apc_paid":null,"fwci":9.3835,"has_fulltext":false,"cited_by_count":46,"citation_normalized_percentile":{"value":0.98378896,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"12"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9988999962806702,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9988999962806702,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9987000226974487,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9962000250816345,"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":0.9044688940048218},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.6861507296562195},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6714200973510742},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.6657925844192505},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6592053174972534},{"id":"https://openalex.org/keywords/graphics-processing-unit","display_name":"Graphics processing unit","score":0.5381907224655151},{"id":"https://openalex.org/keywords/programming-paradigm","display_name":"Programming paradigm","score":0.44879451394081116},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.44816234707832336},{"id":"https://openalex.org/keywords/template","display_name":"Template","score":0.44758692383766174},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.18017259240150452},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.1397019922733307}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9044688940048218},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.6861507296562195},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6714200973510742},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.6657925844192505},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6592053174972534},{"id":"https://openalex.org/C2779851693","wikidata":"https://www.wikidata.org/wiki/Q183484","display_name":"Graphics processing unit","level":2,"score":0.5381907224655151},{"id":"https://openalex.org/C34165917","wikidata":"https://www.wikidata.org/wiki/Q188267","display_name":"Programming paradigm","level":2,"score":0.44879451394081116},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.44816234707832336},{"id":"https://openalex.org/C82714645","wikidata":"https://www.wikidata.org/wiki/Q438331","display_name":"Template","level":2,"score":0.44758692383766174},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.18017259240150452},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.1397019922733307}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ipdps.2009.5161039","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipdps.2009.5161039","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE International Symposium on Parallel & Distributed Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.46000000834465027,"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1264773896","https://openalex.org/W1992851788","https://openalex.org/W2032309817","https://openalex.org/W2109426995","https://openalex.org/W2116758077","https://openalex.org/W2121758805","https://openalex.org/W2126952393","https://openalex.org/W2135518093","https://openalex.org/W2138763931","https://openalex.org/W2139605600","https://openalex.org/W2153492376","https://openalex.org/W2163229756","https://openalex.org/W2170634604","https://openalex.org/W4241513866","https://openalex.org/W6628139786"],"related_works":["https://openalex.org/W1963859303","https://openalex.org/W2364044215","https://openalex.org/W2389600408","https://openalex.org/W240129890","https://openalex.org/W3048701459","https://openalex.org/W2149078538","https://openalex.org/W2080146221","https://openalex.org/W2370314112","https://openalex.org/W2153506571","https://openalex.org/W3104348697"],"abstract_inverted_index":{"Graphics":[0],"processing":[1],"units":[2],"(GPUs)":[3],"have":[4,75,168],"emerged":[5],"as":[6,112,165],"important":[7],"players":[8],"in":[9,79,153,191],"the":[10,13,39,90,98,132,135,156,170,176],"transition":[11],"of":[12,30,42,125,241,258],"computing":[14,210],"industry":[15],"from":[16,175,204],"sequential":[17],"to":[18,52,137,173,233],"multi-":[19],"and":[20,45,56,63,93,100,116,123,128,134,183,193,212,237,244,255],"many-core":[21],"computing.":[22],"We":[23,167,196,229],"propose":[24],"a":[25,139,145,149,213],"software":[26],"framework":[27,68,103,172],"for":[28],"execution":[29,48,142,158],"domain-specific":[31,105],"parallel":[32,106,113],"templates":[33,108,174],"on":[34,70,199,248],"GPUs,":[35],"which":[36],"simultaneously":[37],"raises":[38],"abstraction":[40],"level":[41],"GPU":[43,58,65,91,202,209,227,249],"programming":[44,107],"ensures":[46],"efficient":[47,64],"with":[49,155,251],"forward":[50],"scalability":[51,232],"large":[53,82],"data":[54,83,95,129,235],"sizes":[55],"new":[57],"platforms.":[59],"To":[60],"achieve":[61],"scalable":[62],"execution,":[66],"our":[67],"focuses":[69],"two":[71,200],"critical":[72],"problems":[73],"that":[74,85,109,160,187,218],"been":[76],"largely":[77],"ignored":[78],"previous":[80],"efforts-processing":[81],"sets":[84,236],"do":[86],"not":[87],"fit":[88],"within":[89],"memory,":[92],"minimizing":[94],"transfers":[96,130],"between":[97,131],"host":[99,133],"GPU.":[101],"Our":[102],"takes":[104],"are":[110,188],"expressed":[111],"operator":[114,118],"graphs,":[115],"performs":[117],"splitting,":[119],"of-fload":[120],"unit":[121],"identification,":[122],"scheduling":[124],"off-loaded":[126],"computations":[127],"GPU,":[136],"generate":[138],"highly":[140],"optimized":[141],"plan.":[143],"Finally,":[144],"code":[146],"generator":[147],"produces":[148],"hybrid":[150],"CPU/GPU":[151],"program":[152],"accordance":[154],"derived":[157],"plan,":[159],"uses":[161],"lower-level":[162],"frameworks":[163],"such":[164],"CUDA.":[166],"applied":[169],"proposed":[171],"recognition":[177],"domain,":[178],"specifically":[179],"edge":[180],"detection":[181],"kernels":[182],"convolutional":[184],"neural":[185],"networks":[186],"commonly":[189],"used":[190],"image":[192],"video":[194],"analysis.":[195],"present":[197],"results":[198],"different":[201],"platforms":[203,250],"NVIDIA":[205],"(a":[206],"Tesla":[207],"C870":[208],"card":[211],"GeForce":[214],"8800":[215],"graphics":[216],"card)":[217],"demonstrate":[219,231],"1.7-7.8X":[220],"performance":[221],"improvements":[222],"over":[223],"already":[224],"accelerated":[225],"baseline":[226],"implementations.":[228],"also":[230],"input":[234],"application":[238],"memory":[239],"footprints":[240],"6":[242],"GB":[243,257],"17":[245],"GB,":[246],"respectively,":[247],"only":[252],"768":[253],"MB":[254],"1.5":[256],"memory.":[259]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":6},{"year":2012,"cited_by_count":7}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}