{"id":"https://openalex.org/W2092602356","doi":"https://doi.org/10.1177/1094342012444795","title":"Optimizing the performance of streaming numerical kernels on the IBM Blue Gene/P PowerPC 450 processor","display_name":"Optimizing the performance of streaming numerical kernels on the IBM Blue Gene/P PowerPC 450 processor","publication_year":2012,"publication_date":"2012-05-21","ids":{"openalex":"https://openalex.org/W2092602356","doi":"https://doi.org/10.1177/1094342012444795","mag":"2092602356"},"language":"en","primary_location":{"id":"doi:10.1177/1094342012444795","is_oa":false,"landing_page_url":"https://doi.org/10.1177/1094342012444795","pdf_url":null,"source":{"id":"https://openalex.org/S60606485","display_name":"The International Journal of High Performance Computing Applications","issn_l":"1094-3420","issn":["1094-3420","1741-2846"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The International Journal of High Performance Computing Applications","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1201.3496","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Tareq Malas","orcid":null},"institutions":[{"id":"https://openalex.org/I71920554","display_name":"King Abdullah University of Science and Technology","ror":"https://ror.org/01q3tbs38","country_code":"SA","type":"education","lineage":["https://openalex.org/I71920554"]}],"countries":["SA"],"is_corresponding":true,"raw_author_name":"Tareq Malas","raw_affiliation_strings":["King Abdullah University of Science and Technology, Thuwal, Saudi Arabia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"King Abdullah University of Science and Technology, Thuwal, Saudi Arabia","institution_ids":["https://openalex.org/I71920554"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Aron J. Ahmadia","orcid":null},"institutions":[{"id":"https://openalex.org/I71920554","display_name":"King Abdullah University of Science and Technology","ror":"https://ror.org/01q3tbs38","country_code":"SA","type":"education","lineage":["https://openalex.org/I71920554"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"Aron J. Ahmadia","raw_affiliation_strings":["King Abdullah University of Science and Technology, Thuwal, Saudi Arabia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"King Abdullah University of Science and Technology, Thuwal, Saudi Arabia","institution_ids":["https://openalex.org/I71920554"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jed Brown","orcid":null},"institutions":[{"id":"https://openalex.org/I1282105669","display_name":"Argonne National Laboratory","ror":"https://ror.org/05gvnxz63","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282105669","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jed Brown","raw_affiliation_strings":["Argonne National Laboratory, Argonne, IL, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Argonne National Laboratory, Argonne, IL, USA","institution_ids":["https://openalex.org/I1282105669"]}]},{"author_position":"middle","author":{"id":null,"display_name":"John A. Gunnels","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"John A. Gunnels","raw_affiliation_strings":["IBM T.J. Watson Research Center, Yorktown Heights, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM T.J. Watson Research Center, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I4210114115"]}]},{"author_position":"last","author":{"id":null,"display_name":"David E. Keyes","orcid":null},"institutions":[{"id":"https://openalex.org/I71920554","display_name":"King Abdullah University of Science and Technology","ror":"https://ror.org/01q3tbs38","country_code":"SA","type":"education","lineage":["https://openalex.org/I71920554"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"David E. Keyes","raw_affiliation_strings":["King Abdullah University of Science and Technology, Thuwal, Saudi Arabia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"King Abdullah University of Science and Technology, Thuwal, Saudi Arabia","institution_ids":["https://openalex.org/I71920554"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I71920554"],"apc_list":null,"apc_paid":null,"fwci":0.869,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.7452577,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"27","issue":"2","first_page":"193","last_page":"209"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.7369999885559082,"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":0.7369999885559082,"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/T11697","display_name":"Numerical Methods and Algorithms","score":0.11829999834299088,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T11206","display_name":"Model Reduction and Neural Networks","score":0.029500000178813934,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/powerpc","display_name":"PowerPC","score":0.8895999789237976},{"id":"https://openalex.org/keywords/stencil","display_name":"Stencil","score":0.8892999887466431},{"id":"https://openalex.org/keywords/ibm","display_name":"IBM","score":0.6301000118255615},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.4966999888420105},{"id":"https://openalex.org/keywords/python","display_name":"Python (programming language)","score":0.44429999589920044},{"id":"https://openalex.org/keywords/program-optimization","display_name":"Program optimization","score":0.41499999165534973},{"id":"https://openalex.org/keywords/simd","display_name":"SIMD","score":0.4092999994754791},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.3889999985694885}],"concepts":[{"id":"https://openalex.org/C56005371","wikidata":"https://www.wikidata.org/wiki/Q209860","display_name":"PowerPC","level":3,"score":0.8895999789237976},{"id":"https://openalex.org/C76752949","wikidata":"https://www.wikidata.org/wiki/Q7607499","display_name":"Stencil","level":2,"score":0.8892999887466431},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8342999815940857},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7178000211715698},{"id":"https://openalex.org/C70388272","wikidata":"https://www.wikidata.org/wiki/Q5968558","display_name":"IBM","level":2,"score":0.6301000118255615},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.4966999888420105},{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.44429999589920044},{"id":"https://openalex.org/C139571649","wikidata":"https://www.wikidata.org/wiki/Q1156793","display_name":"Program optimization","level":3,"score":0.41499999165534973},{"id":"https://openalex.org/C150552126","wikidata":"https://www.wikidata.org/wiki/Q339387","display_name":"SIMD","level":2,"score":0.4092999994754791},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.3889999985694885},{"id":"https://openalex.org/C185410017","wikidata":"https://www.wikidata.org/wiki/Q7171778","display_name":"Petascale computing","level":3,"score":0.36010000109672546},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.34060001373291016},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.33559998869895935},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.31189998984336853},{"id":"https://openalex.org/C2776303644","wikidata":"https://www.wikidata.org/wiki/Q1020499","display_name":"Interfacing","level":2,"score":0.30489999055862427},{"id":"https://openalex.org/C189783530","wikidata":"https://www.wikidata.org/wiki/Q352090","display_name":"CPU cache","level":3,"score":0.29679998755455017},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.28790000081062317},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.2870999872684479},{"id":"https://openalex.org/C2777611316","wikidata":"https://www.wikidata.org/wiki/Q39045282","display_name":"Streaming data","level":2,"score":0.28630000352859497},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.2824999988079071},{"id":"https://openalex.org/C75608658","wikidata":"https://www.wikidata.org/wiki/Q44395","display_name":"Pascal (unit)","level":2,"score":0.2782000005245209},{"id":"https://openalex.org/C2778241615","wikidata":"https://www.wikidata.org/wiki/Q83303","display_name":"Fortran","level":2,"score":0.2782000005245209},{"id":"https://openalex.org/C188045654","wikidata":"https://www.wikidata.org/wiki/Q17148339","display_name":"Memory bandwidth","level":2,"score":0.2752000093460083},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.27000001072883606},{"id":"https://openalex.org/C201410400","wikidata":"https://www.wikidata.org/wiki/Q1064412","display_name":"Multithreading","level":3,"score":0.2606000006198883}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1177/1094342012444795","is_oa":false,"landing_page_url":"https://doi.org/10.1177/1094342012444795","pdf_url":null,"source":{"id":"https://openalex.org/S60606485","display_name":"The International Journal of High Performance Computing Applications","issn_l":"1094-3420","issn":["1094-3420","1741-2846"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The International Journal of High Performance Computing Applications","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:1201.3496","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1201.3496","pdf_url":"https://arxiv.org/pdf/1201.3496","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:repository.kaust.edu.sa:10754/562189","is_oa":false,"landing_page_url":"http://hdl.handle.net/10754/562189","pdf_url":null,"source":{"id":"https://openalex.org/S4306401596","display_name":"King Abdullah University of Science and Technology Repository (King Abdullah University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I71920554","host_organization_name":"King Abdullah University of Science and Technology","host_organization_lineage":["https://openalex.org/I71920554"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1201.3496","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1201.3496","pdf_url":"https://arxiv.org/pdf/1201.3496","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1480947737","https://openalex.org/W1504320321","https://openalex.org/W1559264847","https://openalex.org/W1967264375","https://openalex.org/W1979457157","https://openalex.org/W2011900848","https://openalex.org/W2048936605","https://openalex.org/W2049514147","https://openalex.org/W2055253125","https://openalex.org/W2057577013","https://openalex.org/W2074352684","https://openalex.org/W2076535184","https://openalex.org/W2104244530","https://openalex.org/W2105524676","https://openalex.org/W2129471558","https://openalex.org/W2135682468","https://openalex.org/W2138007781","https://openalex.org/W2140303949","https://openalex.org/W2150319905","https://openalex.org/W2153287508","https://openalex.org/W2155503253","https://openalex.org/W2156300652","https://openalex.org/W2157685422","https://openalex.org/W2160962794","https://openalex.org/W2165384099","https://openalex.org/W2293033107","https://openalex.org/W2964101311","https://openalex.org/W3149084271","https://openalex.org/W3162222544","https://openalex.org/W4245302940","https://openalex.org/W4247913514","https://openalex.org/W4249968602","https://openalex.org/W4250959568","https://openalex.org/W4292169137"],"related_works":[],"abstract_inverted_index":{"Several":[0],"emerging":[1],"petascale":[2],"architectures":[3,17],"use":[4],"energy-efficient":[5],"processors":[6],"with":[7],"vectorized":[8],"computational":[9],"units":[10],"and":[11,67,101,134],"in-order":[12],"thread":[13],"processing.":[14],"On":[15],"these":[16,104],"the":[18,27,37,50,80,95,110,116,136,155],"sustained":[19],"performance":[20],"of":[21,29,39,74,103,109,118,130],"streaming":[22,59],"numerical":[23,60],"kernels,":[24],"ubiquitous":[25],"in":[26,77],"solution":[28],"partial":[30],"differential":[31],"equations,":[32],"represents":[33],"a":[34,54,63,107,128,141,145],"challenge":[35],"despite":[36],"regularity":[38],"memory":[40,132],"access.":[41],"Sophisticated":[42],"optimization":[43,68],"techniques":[44],"are":[45],"required":[46],"to":[47],"fully":[48],"utilize":[49],"CPU.":[51],"We":[52,70,114],"propose":[53],"new":[55],"method":[56,76],"for":[57],"constructing":[58],"kernels":[61,105,126],"using":[62],"high-level":[64,96],"assembly":[65],"synthesis":[66],"framework.":[69],"describe":[71],"an":[72],"implementation":[73],"this":[75],"Python":[78],"targeting":[79],"IBM":[81],"\u00ae":[82,85,89],"Blue":[83],"Gene":[84],"/P":[86],"supercomputer\u2019s":[87],"PowerPC":[88],"450":[90],"core.":[91],"This":[92],"paper":[93],"details":[94],"design,":[97],"construction,":[98],"simulation,":[99],"verification,":[100],"analysis":[102],"utilizing":[106],"subset":[108],"CPU\u2019s":[111],"instruction":[112],"set.":[113],"demonstrate":[115],"effectiveness":[117],"our":[119],"approach":[120],"by":[121],"implementing":[122],"several":[123],"three-dimensional":[124],"stencil":[125,143],"over":[127,154],"variety":[129],"cached":[131],"scenarios":[133],"analyzing":[135],"mechanically":[137],"scheduled":[138],"variants,":[139],"including":[140],"27-point":[142],"achieving":[144],"1.7":[146],"<mml:math":[147],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[148],"overflow=\"scroll\">":[149],"<mml:mo":[150],"stretchy=\"false\">\u00d7</mml:mo>":[151],"</mml:math>":[152],"speedup":[153],"best":[156],"previously":[157],"published":[158],"results.":[159]},"counts_by_year":[{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2016-06-24T00:00:00"}
