{"id":"https://openalex.org/W1979717209","doi":"https://doi.org/10.1109/hpca.2013.6522332","title":"Reducing GPU offload latency via fine-grained CPU-GPU synchronization","display_name":"Reducing GPU offload latency via fine-grained CPU-GPU synchronization","publication_year":2013,"publication_date":"2013-02-01","ids":{"openalex":"https://openalex.org/W1979717209","doi":"https://doi.org/10.1109/hpca.2013.6522332","mag":"1979717209"},"language":"en","primary_location":{"id":"doi:10.1109/hpca.2013.6522332","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpca.2013.6522332","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE 19th International Symposium on High Performance Computer Architecture (HPCA)","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/A5078894707","display_name":"Daniel Lustig","orcid":"https://orcid.org/0000-0001-9763-7304"},"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":true,"raw_author_name":"D. Lustig","raw_affiliation_strings":["Princeton University, USA"],"affiliations":[{"raw_affiliation_string":"Princeton University, USA","institution_ids":["https://openalex.org/I20089843"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002015508","display_name":"Margaret Martonosi","orcid":"https://orcid.org/0000-0001-9683-8032"},"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":"M. Martonosi","raw_affiliation_strings":["Princeton University, USA"],"affiliations":[{"raw_affiliation_string":"Princeton University, USA","institution_ids":["https://openalex.org/I20089843"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5078894707"],"corresponding_institution_ids":["https://openalex.org/I20089843"],"apc_list":null,"apc_paid":null,"fwci":15.843,"has_fulltext":false,"cited_by_count":108,"citation_normalized_percentile":{"value":0.99372822,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"354","last_page":"365"},"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":0.9997000098228455,"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":0.9987000226974487,"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":0.8689336776733398},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6549738049507141},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.6451231837272644},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.6188267469406128},{"id":"https://openalex.org/keywords/synchronization","display_name":"Synchronization (alternating current)","score":0.5397527813911438},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.5245830416679382},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.4785535931587219},{"id":"https://openalex.org/keywords/central-processing-unit","display_name":"Central processing unit","score":0.46979770064353943},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.4486277401447296},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.24738538265228271},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.16762730479240417},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.09393393993377686},{"id":"https://openalex.org/keywords/wireless","display_name":"Wireless","score":0.09161746501922607}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8689336776733398},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6549738049507141},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.6451231837272644},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.6188267469406128},{"id":"https://openalex.org/C2778562939","wikidata":"https://www.wikidata.org/wiki/Q1298791","display_name":"Synchronization (alternating current)","level":3,"score":0.5397527813911438},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.5245830416679382},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.4785535931587219},{"id":"https://openalex.org/C49154492","wikidata":"https://www.wikidata.org/wiki/Q5300","display_name":"Central processing unit","level":2,"score":0.46979770064353943},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4486277401447296},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.24738538265228271},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.16762730479240417},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.09393393993377686},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.09161746501922607},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.0},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/hpca.2013.6522332","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpca.2013.6522332","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE 19th International Symposium on High Performance Computer Architecture (HPCA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7200000286102295,"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W70437322","https://openalex.org/W1504291959","https://openalex.org/W1575732703","https://openalex.org/W1629313432","https://openalex.org/W1827927472","https://openalex.org/W1897254069","https://openalex.org/W1971470809","https://openalex.org/W1978709910","https://openalex.org/W1979527452","https://openalex.org/W1994439893","https://openalex.org/W1998040188","https://openalex.org/W2003838150","https://openalex.org/W2016352575","https://openalex.org/W2020572638","https://openalex.org/W2032309817","https://openalex.org/W2080592089","https://openalex.org/W2100415730","https://openalex.org/W2103742924","https://openalex.org/W2106579652","https://openalex.org/W2111734949","https://openalex.org/W2113167168","https://openalex.org/W2117689653","https://openalex.org/W2124415012","https://openalex.org/W2129960401","https://openalex.org/W2134427337","https://openalex.org/W2150329270","https://openalex.org/W2159481344","https://openalex.org/W2160454978","https://openalex.org/W2165039583","https://openalex.org/W2165301438","https://openalex.org/W2167502740","https://openalex.org/W3143589697","https://openalex.org/W4241513866","https://openalex.org/W4244381167","https://openalex.org/W4245306667","https://openalex.org/W4249058798","https://openalex.org/W4251868814"],"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/W1912958759","https://openalex.org/W2792081825"],"abstract_inverted_index":{"GPUs":[0],"are":[1,28],"seeing":[2],"increasingly":[3],"widespread":[4],"use":[5],"for":[6,15],"general":[7],"purpose":[8],"computation":[9],"due":[10],"to":[11],"their":[12],"excellent":[13],"performance":[14,24],"highly-parallel,":[16],"throughput-oriented":[17],"applications.":[18],"For":[19],"many":[20],"workloads,":[21],"however,":[22],"the":[23,31],"benefits":[25],"of":[26,36,41],"offloading":[27],"hindered":[29],"by":[30],"large":[32],"and":[33,40,46],"unpredictable":[34],"overheads":[35],"launching":[37],"GPU":[38],"kernels":[39],"transferring":[42],"data":[43],"between":[44],"CPU":[45],"GPU.":[47]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":10},{"year":2019,"cited_by_count":7},{"year":2018,"cited_by_count":7},{"year":2017,"cited_by_count":7},{"year":2016,"cited_by_count":15},{"year":2015,"cited_by_count":14},{"year":2014,"cited_by_count":18},{"year":2013,"cited_by_count":2}],"updated_date":"2026-03-12T08:34:05.389933","created_date":"2025-10-10T00:00:00"}