{"id":"https://openalex.org/W2093578582","doi":"https://doi.org/10.1145/2675744.2675767","title":"Execution profile driven speedup estimation for porting sequential code to GPU","display_name":"Execution profile driven speedup estimation for porting sequential code to GPU","publication_year":2014,"publication_date":"2014-10-09","ids":{"openalex":"https://openalex.org/W2093578582","doi":"https://doi.org/10.1145/2675744.2675767","mag":"2093578582"},"language":"en","primary_location":{"id":"doi:10.1145/2675744.2675767","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2675744.2675767","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 7th ACM India Computing Conference","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/A5005045185","display_name":"Santonu Sarkar","orcid":"https://orcid.org/0000-0001-9470-7012"},"institutions":[{"id":"https://openalex.org/I74796645","display_name":"Birla Institute of Technology and Science, Pilani","ror":"https://ror.org/001p3jz28","country_code":"IN","type":"education","lineage":["https://openalex.org/I74796645"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Santonu Sarkar","raw_affiliation_strings":["BITS Pilani, India","[BITS Pilani, India]"],"affiliations":[{"raw_affiliation_string":"BITS Pilani, India","institution_ids":["https://openalex.org/I74796645"]},{"raw_affiliation_string":"[BITS Pilani, India]","institution_ids":["https://openalex.org/I74796645"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001647402","display_name":"Sayantan Mitra","orcid":"https://orcid.org/0000-0001-8140-6499"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sayantan Mitra","raw_affiliation_strings":["Bangalore, India"],"affiliations":[{"raw_affiliation_string":"Bangalore, India","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5005045185"],"corresponding_institution_ids":["https://openalex.org/I74796645"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.14670924,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9955999851226807,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.991599977016449,"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/speedup","display_name":"Speedup","score":0.9733783006668091},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8712466955184937},{"id":"https://openalex.org/keywords/porting","display_name":"Porting","score":0.7978895306587219},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.79189133644104},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5657413601875305},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5141756534576416},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.44725990295410156},{"id":"https://openalex.org/keywords/instruction-set","display_name":"Instruction set","score":0.4151243567466736},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4092632234096527},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.3468398451805115},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.14492061734199524},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.08709487318992615}],"concepts":[{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.9733783006668091},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8712466955184937},{"id":"https://openalex.org/C106251023","wikidata":"https://www.wikidata.org/wiki/Q851989","display_name":"Porting","level":3,"score":0.7978895306587219},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.79189133644104},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5657413601875305},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5141756534576416},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.44725990295410156},{"id":"https://openalex.org/C202491316","wikidata":"https://www.wikidata.org/wiki/Q272683","display_name":"Instruction set","level":2,"score":0.4151243567466736},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4092632234096527},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.3468398451805115},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.14492061734199524},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.08709487318992615},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"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:10.1145/2675744.2675767","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2675744.2675767","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 7th ACM India Computing Conference","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.6299999952316284}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W27867058","https://openalex.org/W1976139981","https://openalex.org/W1981896890","https://openalex.org/W2000335122","https://openalex.org/W2033803631","https://openalex.org/W2080592089","https://openalex.org/W2083056254","https://openalex.org/W2105545110","https://openalex.org/W2153185479","https://openalex.org/W2154713585","https://openalex.org/W2258459172","https://openalex.org/W2963264264","https://openalex.org/W4249726315","https://openalex.org/W6647327998"],"related_works":["https://openalex.org/W2356602486","https://openalex.org/W2058965144","https://openalex.org/W2164382479","https://openalex.org/W2351992668","https://openalex.org/W1662038552","https://openalex.org/W3021568819","https://openalex.org/W2045177269","https://openalex.org/W2116582200","https://openalex.org/W1580752477","https://openalex.org/W2061453039"],"abstract_inverted_index":{"Parallelization":[0],"of":[1,23,55,72,75,89,102,114,138,158,162],"an":[2,57],"existing":[3,34,58],"sequential":[4,59,91,169],"application":[5,35],"to":[6,30,43,94,117,127,130,146],"achieve":[7,147],"a":[8,12,53,68,112,131,179,195,201],"good":[9],"speed-up":[10],"on":[11,189],"data-parallel":[13,64,107],"infrastructure":[14],"is":[15,29,126],"quite":[16],"difficult":[17],"and":[18,66,86,134,200],"time":[19,97],"consuming":[20],"effort.":[21,176],"One":[22],"the":[24,33,45,73,90,96,103,106,124,136,142,148,163,168,173],"important":[25],"steps":[26],"towards":[27],"this":[28,49,79],"assess":[31],"whether":[32],"in":[36,144,167],"its":[37],"current":[38],"form":[39],"can":[40],"be":[41,128],"parallelized":[42],"get":[44],"desired":[46,149],"speedup.":[47,151],"In":[48],"paper,":[50],"we":[51,185],"propose":[52],"method":[54,83],"analyzing":[56],"source":[60,92],"code":[61,93,160],"that":[62,121],"contains":[63],"loops,":[65],"give":[67],"reasonably":[69,180],"accurate":[70,181],"prediction":[71,175,183],"extent":[74,137],"speedup":[76,182],"possible":[77],"from":[78],"algorithm.":[80],"The":[81],"proposed":[82],"performs":[84],"static":[85],"dynamic":[87],"analysis":[88],"determine":[95],"required":[98],"by":[99,141],"various":[100,119],"portions":[101,166],"code,":[104,170],"including":[105],"portions.":[108],"Subsequently,":[109],"it":[110],"uses":[111],"set":[113],"novel":[115],"invariants":[116],"calculate":[118],"bottlenecks":[120],"exists":[122],"if":[123],"program":[125,199],"transferred":[129],"GPGPU":[132],"platform":[133],"predicts":[135],"parallelization":[139],"necessary":[140],"GPU":[143,159],"order":[145],"end-to-end":[150],"Our":[152],"approach":[153,188],"does":[154],"not":[155],"require":[156],"creation":[157],"skeletons":[161],"data":[164],"parallel":[165],"thereby":[171],"reducing":[172],"performance":[174],"We":[177],"observed":[178],"when":[184],"tested":[186],"our":[187],"multiple":[190],"well-known":[191],"Rodinia":[192],"benchmark":[193],"applications,":[194],"popular":[196],"matrix":[197],"multiplication":[198],"fast":[202],"Walsh":[203],"transform":[204],"program.":[205]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
