{"id":"https://openalex.org/W2805559595","doi":"https://doi.org/10.1109/vlsi-dat.2018.8373237","title":"A glance of the CASLab HSAIL SIMT GPU for OpenCL and TensorFlow applications","display_name":"A glance of the CASLab HSAIL SIMT GPU for OpenCL and TensorFlow applications","publication_year":2018,"publication_date":"2018-04-01","ids":{"openalex":"https://openalex.org/W2805559595","doi":"https://doi.org/10.1109/vlsi-dat.2018.8373237","mag":"2805559595"},"language":"en","primary_location":{"id":"doi:10.1109/vlsi-dat.2018.8373237","is_oa":false,"landing_page_url":"https://doi.org/10.1109/vlsi-dat.2018.8373237","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 International Symposium on VLSI Design, Automation and Test (VLSI-DAT)","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/A5111582905","display_name":"Chung\u2010Ho Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I91807558","display_name":"National Cheng Kung University","ror":"https://ror.org/01b8kcc49","country_code":"TW","type":"education","lineage":["https://openalex.org/I91807558"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Chung-Ho Chen","raw_affiliation_strings":["National Cheng Kung University"],"affiliations":[{"raw_affiliation_string":"National Cheng Kung University","institution_ids":["https://openalex.org/I91807558"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5111582905"],"corresponding_institution_ids":["https://openalex.org/I91807558"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.06025422,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"1"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9855999946594238,"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":0.9855999946594238,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9702000021934509,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9667999744415283,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8851771950721741},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.5777243375778198},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5710502862930298},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5698788166046143},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5579268932342529},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5345757603645325},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.4841054677963257},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.4654000699520111},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.45700275897979736},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.45436009764671326},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4451860785484314},{"id":"https://openalex.org/keywords/presentation","display_name":"Presentation (obstetrics)","score":0.4200219511985779},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.4143711030483246},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.39118584990501404},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.26352816820144653},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.25960928201675415},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.18942546844482422},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.12018129229545593}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8851771950721741},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.5777243375778198},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5710502862930298},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5698788166046143},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5579268932342529},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5345757603645325},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.4841054677963257},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.4654000699520111},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.45700275897979736},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.45436009764671326},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4451860785484314},{"id":"https://openalex.org/C2777601897","wikidata":"https://www.wikidata.org/wiki/Q3409113","display_name":"Presentation (obstetrics)","level":2,"score":0.4200219511985779},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.4143711030483246},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.39118584990501404},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.26352816820144653},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.25960928201675415},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.18942546844482422},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.12018129229545593},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C126838900","wikidata":"https://www.wikidata.org/wiki/Q77604","display_name":"Radiology","level":1,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/vlsi-dat.2018.8373237","is_oa":false,"landing_page_url":"https://doi.org/10.1109/vlsi-dat.2018.8373237","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 International Symposium on VLSI Design, Automation and Test (VLSI-DAT)","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":0.44999998807907104}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"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/W2370314112","https://openalex.org/W1912958759","https://openalex.org/W2792081825","https://openalex.org/W2893308117"],"abstract_inverted_index":{"This":[0,36,86],"presentation":[1],"introduces":[2],"an":[3,53],"on-going":[4],"OpenCL":[5,43,112],"HSAIL":[6],"GPU":[7,10,26],"project.":[8],"The":[9],"ISA":[11],"is":[12,52],"based":[13],"on":[14],"the":[15,25,29,34,42,45,91],"open":[16,54],"Heterogeneous":[17],"System":[18],"Architecture":[19],"Intermediate":[20],"Language,":[21],"HSAIL.":[22],"We":[23],"introduce":[24],"microarchitecture":[27],"and":[28,44],"methodology":[30],"used":[31],"to":[32,39,81,111],"develop":[33],"system.":[35],"HSAILGPU":[37,88],"intends":[38],"support":[40],"both":[41],"TensorFlow":[46,65,87],"framework.":[47],"TensorFlow,":[48],"released":[49],"by":[50],"Google,":[51],"source":[55],"software":[56],"library":[57],"for":[58,98],"numerical":[59],"computation":[60],"using":[61],"data":[62],"flow":[63],"graphs.":[64],"provides":[66],"a":[67],"rich":[68],"set":[69],"of":[70,93],"APIs":[71],"that":[72],"facilitate":[73],"deep":[74],"neural":[75],"network":[76],"(DNN)":[77],"learning":[78],"algorithm":[79],"developers":[80],"explore":[82],"their":[83],"DNN":[84,103],"models.":[85],"targets":[89],"at":[90],"deployment":[92],"edge":[94],"AI":[95],"computing":[96],"devices":[97],"applications":[99],"such":[100],"as":[101],"distributed":[102],"learning,":[104],"embedded":[105],"AI,":[106],"or":[107],"inference":[108],"in":[109],"addition":[110],"computations.":[113]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
