{"id":"https://openalex.org/W2053060341","doi":"https://doi.org/10.1109/hpec.2013.6670319","title":"PAKCK: Performance and power analysis of key computational kernels on CPUs and GPUs","display_name":"PAKCK: Performance and power analysis of key computational kernels on CPUs and GPUs","publication_year":2013,"publication_date":"2013-09-01","ids":{"openalex":"https://openalex.org/W2053060341","doi":"https://doi.org/10.1109/hpec.2013.6670319","mag":"2053060341"},"language":"en","primary_location":{"id":"doi:10.1109/hpec.2013.6670319","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpec.2013.6670319","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE High Performance Extreme Computing Conference (HPEC)","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/A5000588209","display_name":"Julia Mullen","orcid":"https://orcid.org/0000-0002-0015-6182"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]},{"id":"https://openalex.org/I4210122954","display_name":"MIT Lincoln Laboratory","ror":"https://ror.org/022z6jk58","country_code":"US","type":"facility","lineage":["https://openalex.org/I4210122954","https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Julia S. Mullen","raw_affiliation_strings":["MIT Lincoln Laboratory, Lexington, MA","MIT Lincoln Lab. Lexington, MA, USA"],"affiliations":[{"raw_affiliation_string":"MIT Lincoln Laboratory, Lexington, MA","institution_ids":["https://openalex.org/I4210122954"]},{"raw_affiliation_string":"MIT Lincoln Lab. Lexington, MA, USA","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109239575","display_name":"Michael M. Wolf","orcid":"https://orcid.org/0009-0001-7203-423X"},"institutions":[{"id":"https://openalex.org/I4210122954","display_name":"MIT Lincoln Laboratory","ror":"https://ror.org/022z6jk58","country_code":"US","type":"facility","lineage":["https://openalex.org/I4210122954","https://openalex.org/I63966007"]},{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael M. Wolf","raw_affiliation_strings":["MIT Lincoln Laboratory, Lexington, MA","MIT Lincoln Lab. Lexington, MA, USA"],"affiliations":[{"raw_affiliation_string":"MIT Lincoln Laboratory, Lexington, MA","institution_ids":["https://openalex.org/I4210122954"]},{"raw_affiliation_string":"MIT Lincoln Lab. Lexington, MA, USA","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051173640","display_name":"Anna Klein","orcid":null},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]},{"id":"https://openalex.org/I4210122954","display_name":"MIT Lincoln Laboratory","ror":"https://ror.org/022z6jk58","country_code":"US","type":"facility","lineage":["https://openalex.org/I4210122954","https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anna Klein","raw_affiliation_strings":["MIT Lincoln Laboratory, Lexington, MA","MIT Lincoln Lab. Lexington, MA, USA"],"affiliations":[{"raw_affiliation_string":"MIT Lincoln Laboratory, Lexington, MA","institution_ids":["https://openalex.org/I4210122954"]},{"raw_affiliation_string":"MIT Lincoln Lab. Lexington, MA, USA","institution_ids":["https://openalex.org/I63966007"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5000588209"],"corresponding_institution_ids":["https://openalex.org/I4210122954","https://openalex.org/I63966007"],"apc_list":null,"apc_paid":null,"fwci":0.8293,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.76916961,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12292","display_name":"Graph Theory and Algorithms","score":0.9995999932289124,"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"}},"topics":[{"id":"https://openalex.org/T12292","display_name":"Graph Theory and Algorithms","score":0.9995999932289124,"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"}},{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9994000196456909,"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":0.9957000017166138,"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/flops","display_name":"FLOPS","score":0.8523347973823547},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7838406562805176},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.6868836283683777},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6762650609016418},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.566828191280365},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.47542884945869446},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.4634992778301239},{"id":"https://openalex.org/keywords/instruction-set","display_name":"Instruction set","score":0.4344113767147064},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.42280715703964233},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.39891332387924194},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.3408083915710449},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2601911723613739},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08494046330451965}],"concepts":[{"id":"https://openalex.org/C3826847","wikidata":"https://www.wikidata.org/wiki/Q188768","display_name":"FLOPS","level":2,"score":0.8523347973823547},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7838406562805176},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.6868836283683777},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6762650609016418},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.566828191280365},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.47542884945869446},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4634992778301239},{"id":"https://openalex.org/C202491316","wikidata":"https://www.wikidata.org/wiki/Q272683","display_name":"Instruction set","level":2,"score":0.4344113767147064},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.42280715703964233},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.39891332387924194},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.3408083915710449},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2601911723613739},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08494046330451965},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C84114770","wikidata":"https://www.wikidata.org/wiki/Q46344","display_name":"Quantum","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/hpec.2013.6670319","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpec.2013.6670319","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE High Performance Extreme Computing Conference (HPEC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306078","display_name":"U.S. Department of Defense","ror":"https://ror.org/0447fe631"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W1482680420","https://openalex.org/W1986989509","https://openalex.org/W2012181719","https://openalex.org/W2022916138","https://openalex.org/W2066804546","https://openalex.org/W2070525241","https://openalex.org/W2095929395","https://openalex.org/W2124007994","https://openalex.org/W2400587201","https://openalex.org/W2532258155","https://openalex.org/W6712626706"],"related_works":["https://openalex.org/W1970548269","https://openalex.org/W2380696053","https://openalex.org/W2293771254","https://openalex.org/W2891818448","https://openalex.org/W3121828480","https://openalex.org/W2039875226","https://openalex.org/W4221142455","https://openalex.org/W2032786851","https://openalex.org/W2914631005","https://openalex.org/W2123154672"],"abstract_inverted_index":{"Recent":[0],"projections":[1],"suggest":[2],"that":[3,71,102,129],"applications":[4],"and":[5,28,36,52,55,84,93,109,114,118],"architectures":[6,113],"will":[7],"need":[8],"to":[9,15,61,67],"attain":[10],"75":[11,130],"GFLOPS/W":[12,131],"in":[13],"order":[14],"support":[16],"future":[17],"DoD":[18,47,68],"missions.":[19,69],"Meeting":[20],"this":[21],"goal":[22],"requires":[23],"deeper":[24],"understanding":[25],"of":[26,34,40,46,77,149],"kernel":[27],"application":[29,48],"performance":[30,63,110,119,146],"as":[31],"a":[32,44,133],"function":[33],"power":[35,107,116],"architecture.":[37],"As":[38],"part":[39],"the":[41,75,90,100,142],"PAKCK":[42],"study,":[43],"set":[45],"areas,":[49],"including":[50],"signal":[51],"image":[53],"processing":[54],"big":[56],"data/graph":[57],"computation,":[58],"were":[59],"surveyed":[60],"identify":[62],"critical":[64],"kernels":[65],"relevant":[66],"From":[70],"survey,":[72],"we":[73],"present":[74,115],"characterization":[76],"dense":[78,153],"matrix-vector":[79],"product,":[80],"two":[81],"dimensional":[82],"FFTs,":[83],"sparse":[85,143],"matrix-dense":[86],"vector":[87],"multiplication":[88],"on":[89,111],"NVIDIA":[91],"Fermi":[92],"Intel":[94],"Sandy":[95],"Bridge":[96],"architectures.":[97],"We":[98],"describe":[99],"methodology":[101],"was":[103,147],"developed":[104],"for":[105,122,137,141],"characterizing":[106],"usage":[108,117],"these":[112,138],"per":[120],"Watt":[121],"all":[123],"three":[124],"kernels.":[125,154],"Our":[126],"results":[127],"indicate":[128],"is":[132],"very":[134],"challenging":[135],"target":[136],"kernels,":[139,144],"especially":[140],"whose":[145],"orders":[148],"magnitude":[150],"lower":[151],"than":[152]},"counts_by_year":[{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2014,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}