{"id":"https://openalex.org/W2416330002","doi":"https://doi.org/10.1109/ispass.2016.7482093","title":"A comprehensive performance analysis of HSA and OpenCL 2.0","display_name":"A comprehensive performance analysis of HSA and OpenCL 2.0","publication_year":2016,"publication_date":"2016-04-01","ids":{"openalex":"https://openalex.org/W2416330002","doi":"https://doi.org/10.1109/ispass.2016.7482093","mag":"2416330002"},"language":"en","primary_location":{"id":"doi:10.1109/ispass.2016.7482093","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ispass.2016.7482093","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Symposium on Performance Analysis of Systems and Software (ISPASS)","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/A5071370685","display_name":"Saoni Mukherjee","orcid":null},"institutions":[{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Saoni Mukherjee","raw_affiliation_strings":["Northeastern University, Boston, MA"],"affiliations":[{"raw_affiliation_string":"Northeastern University, Boston, MA","institution_ids":["https://openalex.org/I12912129"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041025969","display_name":"Yifan Sun","orcid":"https://orcid.org/0000-0003-3532-6521"},"institutions":[{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yifan Sun","raw_affiliation_strings":["Northeastern University, Boston, MA"],"affiliations":[{"raw_affiliation_string":"Northeastern University, Boston, MA","institution_ids":["https://openalex.org/I12912129"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061368393","display_name":"Paul Blinzer","orcid":null},"institutions":[{"id":"https://openalex.org/I4210137977","display_name":"Advanced Micro Devices (United States)","ror":"https://ror.org/04kd6c783","country_code":"US","type":"company","lineage":["https://openalex.org/I4210137977"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Paul Blinzer","raw_affiliation_strings":["Advanced Micro Devices, Sunnyvale, CA"],"affiliations":[{"raw_affiliation_string":"Advanced Micro Devices, Sunnyvale, CA","institution_ids":["https://openalex.org/I4210137977"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021996030","display_name":"Amir Kavyan Ziabari","orcid":"https://orcid.org/0000-0002-5963-2374"},"institutions":[{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Amir Kavyan Ziabari","raw_affiliation_strings":["Northeastern University, Boston, MA"],"affiliations":[{"raw_affiliation_string":"Northeastern University, Boston, MA","institution_ids":["https://openalex.org/I12912129"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061128237","display_name":"David Kaeli","orcid":"https://orcid.org/0000-0002-5692-0151"},"institutions":[{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David Kaeli","raw_affiliation_strings":["Northeastern University, Boston, MA"],"affiliations":[{"raw_affiliation_string":"Northeastern University, Boston, MA","institution_ids":["https://openalex.org/I12912129"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5071370685"],"corresponding_institution_ids":["https://openalex.org/I12912129"],"apc_list":null,"apc_paid":null,"fwci":7.8834,"has_fulltext":false,"cited_by_count":34,"citation_normalized_percentile":{"value":0.98091029,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"62","issue":null,"first_page":"183","last_page":"193"},"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9970999956130981,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9965000152587891,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.9018498659133911},{"id":"https://openalex.org/keywords/runtime-system","display_name":"Runtime system","score":0.6035626530647278},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.6008744835853577},{"id":"https://openalex.org/keywords/suite","display_name":"Suite","score":0.5665818452835083},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.5533721446990967},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.5402197241783142},{"id":"https://openalex.org/keywords/symmetric-multiprocessor-system","display_name":"Symmetric multiprocessor system","score":0.5150927901268005},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.47619664669036865},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.42624184489250183},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.37198930978775024},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.36812257766723633},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.2925751805305481}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9018498659133911},{"id":"https://openalex.org/C2780870223","wikidata":"https://www.wikidata.org/wiki/Q1004415","display_name":"Runtime system","level":2,"score":0.6035626530647278},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.6008744835853577},{"id":"https://openalex.org/C79581498","wikidata":"https://www.wikidata.org/wiki/Q1367530","display_name":"Suite","level":2,"score":0.5665818452835083},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.5533721446990967},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.5402197241783142},{"id":"https://openalex.org/C172430144","wikidata":"https://www.wikidata.org/wiki/Q17111997","display_name":"Symmetric multiprocessor system","level":2,"score":0.5150927901268005},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.47619664669036865},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.42624184489250183},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.37198930978775024},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.36812257766723633},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.2925751805305481},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"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/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","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},{"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:10.1109/ispass.2016.7482093","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ispass.2016.7482093","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Symposium on Performance Analysis of Systems and Software (ISPASS)","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":0.5400000214576721}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W164895899","https://openalex.org/W780656674","https://openalex.org/W1559450590","https://openalex.org/W1565383065","https://openalex.org/W1717365219","https://openalex.org/W1968432902","https://openalex.org/W1972783048","https://openalex.org/W1984222112","https://openalex.org/W1995545331","https://openalex.org/W1999808014","https://openalex.org/W2007321142","https://openalex.org/W2021760654","https://openalex.org/W2037518952","https://openalex.org/W2080592089","https://openalex.org/W2127218421","https://openalex.org/W2149234156","https://openalex.org/W2270001852","https://openalex.org/W2273440736","https://openalex.org/W2417350949","https://openalex.org/W2544425549","https://openalex.org/W3144771461","https://openalex.org/W3147878143","https://openalex.org/W3148573243","https://openalex.org/W4230343448","https://openalex.org/W6622596894","https://openalex.org/W6634020214","https://openalex.org/W6678914141"],"related_works":["https://openalex.org/W1966837078","https://openalex.org/W2319262638","https://openalex.org/W2783386063","https://openalex.org/W2904152126","https://openalex.org/W2242847901","https://openalex.org/W2785820621","https://openalex.org/W2762992606","https://openalex.org/W153259801","https://openalex.org/W3186309308","https://openalex.org/W2072208258"],"abstract_inverted_index":{"Heterogeneous":[0,99],"systems,":[1,34],"that":[2,110,204],"marry":[3],"CPUs":[4],"and":[5,69,89,107,124,140,168,199],"GPUs":[6],"together":[7],"in":[8,30],"a":[9,48,64,105,154,196,232,241],"range":[10],"of":[11,23,63,67,91,137,156,164,213],"configurations,":[12],"are":[13,57],"quickly":[14],"becoming":[15],"the":[16,35,44,51,61,72,94,98,133,148,162,185,190,214,225,236],"design":[17],"paradigm":[18],"for":[19,114],"today's":[20],"platforms":[21],"because":[22],"their":[24,176],"impressive":[25],"parallel":[26],"processing":[27],"capabilities.":[28],"However,":[29],"many":[31],"existing":[32],"heterogeneous":[33,92],"GPU":[36],"is":[37],"only":[38],"treated":[39,81],"as":[40,47,82,147],"an":[41,179],"accelerator":[42],"by":[43,189,205],"CPU,":[45],"working":[46],"slave":[49],"to":[50,59,71,79,160,173,217,231],"CPU":[52],"master.":[53],"But":[54],"recently":[55],"we":[56,131,152,193,209],"starting":[58],"see":[60],"introduction":[62],"new":[65,186],"class":[66],"devices":[68],"changes":[70],"system":[73],"runtime":[74,108,228,239],"model,":[75,192],"which":[76,103],"enable":[77],"accelerators":[78],"be":[80],"first-class":[83],"computing":[84],"devices.":[85],"To":[86,182],"support":[87,113],"programmability":[88],"efficiency":[90],"programming,":[93],"HSA":[95,141,191,207,237],"foundation":[96],"introduced":[97],"System":[100],"Architecture":[101],"(HSA),":[102],"defines":[104],"platform":[106],"architecture":[109],"provides":[111],"rich":[112],"OpenCL":[115,138,145,157,226,245],"2.0":[116,139,227],"features":[117,163,187],"including":[118],"shared":[119],"virtual":[120],"memory,":[121],"dynamic":[122],"parallelism,":[123],"improved":[125],"atomic":[126],"operations.":[127],"In":[128,221],"this":[129],"paper,":[130],"provide":[132],"first":[134],"comprehensive":[135],"study":[136],"1.0":[142,238],"execution,":[143],"considering":[144],"1.2":[146],"baseline.":[149],"For":[150],"workloads,":[151],"develop":[153],"suite":[155],"micro-benchmarks":[158],"designed":[159],"highlight":[161],"these":[165],"emerging":[166],"standards":[167],"also":[169],"utilize":[170],"real-world":[171,223],"applications":[172],"better":[174],"understand":[175],"impact":[177],"at":[178],"application":[180],"level.":[181],"fully":[183],"exercise":[184],"provided":[188],"experiment":[194],"with":[195],"producer-consumer":[197],"algorithm":[198],"persistent":[200],"kernels.":[201],"We":[202],"find":[203],"using":[206],"signals,":[208],"can":[210],"remove":[211],"92%":[212],"overhead":[215],"due":[216],"synchronous":[218],"kernel":[219],"launches.":[220],"our":[222],"applications,":[224],"achieves":[229,240],"up":[230],"1.2X":[233],"speedup,":[234],"while":[235],"2.7X":[242],"speedup":[243],"over":[244],"1.2.":[246]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":7},{"year":2017,"cited_by_count":12},{"year":2016,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}