{"id":"https://openalex.org/W2050019858","doi":"https://doi.org/10.1145/2688500.2688527","title":"SemCache++: semantics-aware caching for efficient multi-GPU offloading","display_name":"SemCache++: semantics-aware caching for efficient multi-GPU offloading","publication_year":2015,"publication_date":"2015-01-24","ids":{"openalex":"https://openalex.org/W2050019858","doi":"https://doi.org/10.1145/2688500.2688527","mag":"2050019858"},"language":"en","primary_location":{"id":"doi:10.1145/2688500.2688527","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2688500.2688527","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 Symposium on Principles and Practice of Parallel Programming","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/A5006388577","display_name":"Nabeel Al-Saber","orcid":null},"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"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Nabeel Al-Saber","raw_affiliation_strings":["Purdue University, USA","Purdue University , USA"],"affiliations":[{"raw_affiliation_string":"Purdue University, USA","institution_ids":["https://openalex.org/I219193219"]},{"raw_affiliation_string":"Purdue University , USA","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075916086","display_name":"Milind Kulkarni","orcid":"https://orcid.org/0000-0001-6827-345X"},"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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Milind Kulkarni","raw_affiliation_strings":["Purdue University, USA","Purdue University , USA"],"affiliations":[{"raw_affiliation_string":"Purdue University, USA","institution_ids":["https://openalex.org/I219193219"]},{"raw_affiliation_string":"Purdue University , USA","institution_ids":["https://openalex.org/I219193219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5006388577"],"corresponding_institution_ids":["https://openalex.org/I219193219"],"apc_list":null,"apc_paid":null,"fwci":2.40506249,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.90334139,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"255","last_page":"256"},"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/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9977999925613403,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9976000189781189,"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":0.9172953963279724},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.5002443790435791},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.48809707164764404},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.4673612117767334},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.46063292026519775},{"id":"https://openalex.org/keywords/reuse","display_name":"Reuse","score":0.4187437891960144},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.4139562249183655},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.16590091586112976}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9172953963279724},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.5002443790435791},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.48809707164764404},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.4673612117767334},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.46063292026519775},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.4187437891960144},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4139562249183655},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.16590091586112976},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2688500.2688527","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2688500.2688527","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 Symposium on Principles and Practice of Parallel Programming","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W1483880184","https://openalex.org/W1966124831","https://openalex.org/W2047614366","https://openalex.org/W2123031400","https://openalex.org/W3187688612","https://openalex.org/W4252178669"],"related_works":["https://openalex.org/W4399354997","https://openalex.org/W3062287","https://openalex.org/W2380390332","https://openalex.org/W2742145873","https://openalex.org/W2023572661","https://openalex.org/W2005148983","https://openalex.org/W2012954338","https://openalex.org/W2096672917","https://openalex.org/W2392023973","https://openalex.org/W2076165488"],"abstract_inverted_index":{"Offloading":[0],"computations":[1,15,29],"to":[2,27,30,86,98,112,139],"multiple":[3,31,82],"GPUs":[4,32,83],"is":[5,96,130],"not":[6],"an":[7],"easy":[8,26],"task.":[9],"It":[10],"requires":[11,121],"decomposing":[12],"data,":[13],"distributing":[14],"and":[16,81,115,119,142,154],"handling":[17],"communication":[18,77,88,118,153],"manually.":[19],"Drop-in":[20],"GPU":[21,72],"libraries":[22,61,161],"have":[23],"made":[24],"it":[25,132],"offload":[28],"by":[33,89],"hiding":[34],"this":[35,65],"complexity":[36],"inside":[37],"library":[38,105],"calls.":[39],"Such":[40],"encapsulation":[41],"prevents":[42],"the":[43,46,79,100,109],"reuse":[44],"of":[45],"data":[47],"between":[48,78],"successive":[49],"kernel":[50],"invocations":[51],"resulting":[52],"in":[53,59,84],"redundant":[54,91,152],"communication.":[55],"This":[56],"limitation":[57],"exists":[58],"multi-GPU":[60,102,117,160],"like":[62,162],"CUBLASXT.":[63,163],"In":[64],"paper,":[66],"we":[67],"introduce":[68],"SemCache++,":[69],"a":[70,134],"semantics-aware":[71],"cache":[73],"that":[74,106,147],"automatically":[75,113],"manages":[76],"CPU":[80],"addition":[85],"optimizing":[87],"eliminating":[90],"transfers":[92],"using":[93],"caching.":[94],"SemCache++":[95],"used":[97],"build":[99],"first":[101],"drop-in":[103],"replacement":[104],"(a)":[107],"uses":[108,133],"virtual":[110],"memory":[111],"manage":[114],"optimize":[116],"(b)":[120],"no":[122],"program":[123],"rewriting":[124],"or":[125],"annotations.":[126],"Our":[127],"caching":[128,137],"technique":[129],"efficient;":[131],"two":[135],"level":[136],"directory":[138],"track":[140],"matrices":[141],"sub-matrices.":[143],"Experimental":[144],"results":[145],"show":[146],"our":[148],"system":[149],"can":[150],"eliminate":[151],"deliver":[155],"significant":[156],"performance":[157],"improvements":[158],"over":[159]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}