{"id":"https://openalex.org/W2169659447","doi":"https://doi.org/10.1145/2716282.2716293","title":"A comparative investigation of device-specific mechanisms for exploiting HPC accelerators","display_name":"A comparative investigation of device-specific mechanisms for exploiting HPC accelerators","publication_year":2015,"publication_date":"2015-02-03","ids":{"openalex":"https://openalex.org/W2169659447","doi":"https://doi.org/10.1145/2716282.2716293","mag":"2169659447"},"language":"en","primary_location":{"id":"doi:10.1145/2716282.2716293","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2716282.2716293","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 8th Workshop on General Purpose Processing using GPUs","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/A5054107871","display_name":"Ayman Tarakji","orcid":null},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Ayman Tarakji","raw_affiliation_strings":["RWTH Aachen University, Germany"],"affiliations":[{"raw_affiliation_string":"RWTH Aachen University, Germany","institution_ids":["https://openalex.org/I887968799"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074432585","display_name":"Lukas B\u00f6rger","orcid":null},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Lukas B\u00f6rger","raw_affiliation_strings":["RWTH Aachen University, Germany"],"affiliations":[{"raw_affiliation_string":"RWTH Aachen University, Germany","institution_ids":["https://openalex.org/I887968799"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023470562","display_name":"Rainer Leupers","orcid":"https://orcid.org/0000-0002-6735-3033"},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Rainer Leupers","raw_affiliation_strings":["RWTH Aachen University, Germany"],"affiliations":[{"raw_affiliation_string":"RWTH Aachen University, Germany","institution_ids":["https://openalex.org/I887968799"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5054107871"],"corresponding_institution_ids":["https://openalex.org/I887968799"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.09065513,"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":"12"},"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":0.9991000294685364,"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":0.9966999888420105,"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":0.8898290395736694},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.6167266368865967},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6098155379295349},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5646105408668518},{"id":"https://openalex.org/keywords/suite","display_name":"Suite","score":0.5394945740699768},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.5000052452087402},{"id":"https://openalex.org/keywords/parallelism","display_name":"Parallelism (grammar)","score":0.47965410351753235},{"id":"https://openalex.org/keywords/instruction-level-parallelism","display_name":"Instruction-level parallelism","score":0.4624408185482025},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.45326703786849976},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.44804394245147705},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.4382404386997223},{"id":"https://openalex.org/keywords/data-parallelism","display_name":"Data parallelism","score":0.42888617515563965},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.4269815683364868},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.09500277042388916}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8898290395736694},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.6167266368865967},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6098155379295349},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5646105408668518},{"id":"https://openalex.org/C79581498","wikidata":"https://www.wikidata.org/wiki/Q1367530","display_name":"Suite","level":2,"score":0.5394945740699768},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.5000052452087402},{"id":"https://openalex.org/C2781172179","wikidata":"https://www.wikidata.org/wiki/Q853109","display_name":"Parallelism (grammar)","level":2,"score":0.47965410351753235},{"id":"https://openalex.org/C140763907","wikidata":"https://www.wikidata.org/wiki/Q2714055","display_name":"Instruction-level parallelism","level":3,"score":0.4624408185482025},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.45326703786849976},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.44804394245147705},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.4382404386997223},{"id":"https://openalex.org/C61483411","wikidata":"https://www.wikidata.org/wiki/Q3124522","display_name":"Data parallelism","level":3,"score":0.42888617515563965},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.4269815683364868},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.09500277042388916},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","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/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2716282.2716293","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2716282.2716293","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 8th Workshop on General Purpose Processing using GPUs","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6000000238418579,"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W348433680","https://openalex.org/W1483717008","https://openalex.org/W1678662003","https://openalex.org/W1906046253","https://openalex.org/W1972062954","https://openalex.org/W2003526442","https://openalex.org/W2018401627","https://openalex.org/W2056862683","https://openalex.org/W2078994750","https://openalex.org/W2081245617","https://openalex.org/W2096553377","https://openalex.org/W2120230074","https://openalex.org/W2122078011","https://openalex.org/W2149234156","https://openalex.org/W2170268965","https://openalex.org/W2203203427","https://openalex.org/W2273440736"],"related_works":["https://openalex.org/W2950520577","https://openalex.org/W2003935582","https://openalex.org/W1991844655","https://openalex.org/W2105992728","https://openalex.org/W1229628","https://openalex.org/W4400951174","https://openalex.org/W74409296","https://openalex.org/W2009213655","https://openalex.org/W2593878938","https://openalex.org/W2494130044"],"abstract_inverted_index":{"A":[0,59],"variety":[1,106],"of":[2,35,51,56,70,107,161,165],"computational":[3],"accelerators":[4],"have":[5],"been":[6],"greatly":[7],"improved":[8],"in":[9,32,76],"recent":[10],"years.":[11],"Intel's":[12],"MIC":[13],"(Many":[14],"Integrated":[15],"Core)":[16],"and":[17,23,64,87,104],"both":[18],"GPU":[19],"architectures,":[20],"NVIDIA's":[21],"Kepler":[22],"AMD's":[24],"Graphics":[25],"Core":[26],"Next,":[27],"all":[28],"represent":[29],"real":[30,154],"innovations":[31],"the":[33,39,68,81,142,162],"field":[34],"HPC.":[36],"Based":[37],"on":[38,91],"single":[40],"unified":[41],"programing":[42,85],"interface":[43],"OpenCL,":[44],"this":[45],"paper":[46],"reports":[47],"a":[48,52,105,149,153,159],"careful":[49],"study":[50,151],"well":[53,133],"thought-out":[54],"selection":[55],"such":[57],"devices.":[58],"micro-benchmark":[60],"suite":[61],"is":[62,156],"designed":[63],"implemented":[65],"to":[66,73,129,141],"investigate":[67],"capability":[69],"each":[71],"accelerator":[72],"exploit":[74],"parallelism":[75],"OpenCL.":[77],"Our":[78],"results":[79],"expose":[80],"relationship":[82],"between":[83],"several":[84],"aspects":[86,109],"their":[88,113],"possible":[89],"impact":[90],"performance.":[92],"Instruction":[93],"level":[94],"parallelism,":[95,98],"intra-kernel":[96],"vector":[97],"multiple-issue,":[99],"work-group":[100],"size,":[101],"instruction":[102],"scheduling":[103],"other":[108],"are":[110,137],"explored,":[111],"highlighting":[112],"interaction":[114],"that":[115],"must":[116],"be":[117],"carefully":[118],"considered":[119],"when":[120],"developing":[121],"applications":[122],"for":[123],"heterogeneous":[124],"architectures.":[125],"Evidence-based":[126],"findings":[127],"related":[128],"microarchitectural":[130],"features":[131],"as":[132,134,158],"performance":[135],"characteristics":[136],"cross-checked":[138],"with":[139],"reference":[140],"compiled":[143],"code":[144],"being":[145],"executed.":[146],"In":[147],"conclusion,":[148],"case":[150],"involving":[152],"application":[155],"presented":[157],"part":[160],"verification":[163],"process":[164],"statements.":[166]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}