{"id":"https://openalex.org/W2042381780","doi":"https://doi.org/10.1147/jrd.2009.5429074","title":"The reverse-acceleration model for programming petascale hybrid systems","display_name":"The reverse-acceleration model for programming petascale hybrid systems","publication_year":2009,"publication_date":"2009-09-01","ids":{"openalex":"https://openalex.org/W2042381780","doi":"https://doi.org/10.1147/jrd.2009.5429074","mag":"2042381780"},"language":"en","primary_location":{"id":"doi:10.1147/jrd.2009.5429074","is_oa":false,"landing_page_url":"https://doi.org/10.1147/jrd.2009.5429074","pdf_url":null,"source":{"id":"https://openalex.org/S4210219925","display_name":"IBM Journal of Research and Development","issn_l":"0018-8646","issn":["0018-8646","2151-8556"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320652","host_organization_name":"IBM","host_organization_lineage":["https://openalex.org/P4310320652"],"host_organization_lineage_names":["IBM"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IBM Journal of Research and Development","raw_type":"journal-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/A5060855642","display_name":"Scott Pakin","orcid":"https://orcid.org/0000-0002-5220-1985"},"institutions":[{"id":"https://openalex.org/I1343871089","display_name":"Los Alamos National Laboratory","ror":"https://ror.org/01e41cf67","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I1343871089","https://openalex.org/I198811213","https://openalex.org/I4210120050"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"S. Pakin","raw_affiliation_strings":["Los Alamos National Laboratory, 30 Bikini Atoll Road, New Mexico 87545, USA","(Los Alamos National Laboratory, Los Alamos, New Mexico)"],"affiliations":[{"raw_affiliation_string":"Los Alamos National Laboratory, 30 Bikini Atoll Road, New Mexico 87545, USA","institution_ids":["https://openalex.org/I1343871089"]},{"raw_affiliation_string":"(Los Alamos National Laboratory, Los Alamos, New Mexico)","institution_ids":["https://openalex.org/I1343871089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078475557","display_name":"Michael Lang","orcid":"https://orcid.org/0000-0002-3498-6352"},"institutions":[{"id":"https://openalex.org/I1343871089","display_name":"Los Alamos National Laboratory","ror":"https://ror.org/01e41cf67","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I1343871089","https://openalex.org/I198811213","https://openalex.org/I4210120050"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"M. Lang","raw_affiliation_strings":["Los Alamos National Laboratory, 30 Bikini Atoll Road, New Mexico 87545, USA","(Los Alamos National Laboratory, Los Alamos, New Mexico)"],"affiliations":[{"raw_affiliation_string":"Los Alamos National Laboratory, 30 Bikini Atoll Road, New Mexico 87545, USA","institution_ids":["https://openalex.org/I1343871089"]},{"raw_affiliation_string":"(Los Alamos National Laboratory, Los Alamos, New Mexico)","institution_ids":["https://openalex.org/I1343871089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064935199","display_name":"Darren J. Kerbyson","orcid":null},"institutions":[{"id":"https://openalex.org/I1343871089","display_name":"Los Alamos National Laboratory","ror":"https://ror.org/01e41cf67","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I1343871089","https://openalex.org/I198811213","https://openalex.org/I4210120050"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"D. J. Kerbyson","raw_affiliation_strings":["Los Alamos National Laboratory, 30 Bikini Atoll Road, New Mexico 87545, USA","(Los Alamos National Laboratory, Los Alamos, New Mexico)"],"affiliations":[{"raw_affiliation_string":"Los Alamos National Laboratory, 30 Bikini Atoll Road, New Mexico 87545, USA","institution_ids":["https://openalex.org/I1343871089"]},{"raw_affiliation_string":"(Los Alamos National Laboratory, Los Alamos, New Mexico)","institution_ids":["https://openalex.org/I1343871089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5060855642"],"corresponding_institution_ids":["https://openalex.org/I1343871089"],"apc_list":null,"apc_paid":null,"fwci":1.3388,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.81212752,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"53","issue":"5","first_page":"8:1","last_page":"8:15"},"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/T10715","display_name":"Distributed and Parallel Computing Systems","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/T10772","display_name":"Distributed systems and fault tolerance","score":0.9980000257492065,"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":0.821074366569519},{"id":"https://openalex.org/keywords/petascale-computing","display_name":"Petascale computing","score":0.8203134536743164},{"id":"https://openalex.org/keywords/porting","display_name":"Porting","score":0.7723662257194519},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.7150636911392212},{"id":"https://openalex.org/keywords/programming-paradigm","display_name":"Programming paradigm","score":0.6275522708892822},{"id":"https://openalex.org/keywords/acceleration","display_name":"Acceleration","score":0.6086844801902771},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5995794534683228},{"id":"https://openalex.org/keywords/general-purpose","display_name":"General purpose","score":0.5531604290008545},{"id":"https://openalex.org/keywords/computer-cluster","display_name":"Computer cluster","score":0.5343934893608093},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.49365195631980896},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.4653874933719635},{"id":"https://openalex.org/keywords/host","display_name":"Host (biology)","score":0.4417663812637329},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.42007073760032654},{"id":"https://openalex.org/keywords/neutron-transport","display_name":"Neutron transport","score":0.4152417778968811},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.3292183578014374},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.27639859914779663},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.25258076190948486},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.15509045124053955}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.821074366569519},{"id":"https://openalex.org/C185410017","wikidata":"https://www.wikidata.org/wiki/Q7171778","display_name":"Petascale computing","level":3,"score":0.8203134536743164},{"id":"https://openalex.org/C106251023","wikidata":"https://www.wikidata.org/wiki/Q851989","display_name":"Porting","level":3,"score":0.7723662257194519},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.7150636911392212},{"id":"https://openalex.org/C34165917","wikidata":"https://www.wikidata.org/wiki/Q188267","display_name":"Programming paradigm","level":2,"score":0.6275522708892822},{"id":"https://openalex.org/C117896860","wikidata":"https://www.wikidata.org/wiki/Q11376","display_name":"Acceleration","level":2,"score":0.6086844801902771},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5995794534683228},{"id":"https://openalex.org/C2982832238","wikidata":"https://www.wikidata.org/wiki/Q5531640","display_name":"General purpose","level":2,"score":0.5531604290008545},{"id":"https://openalex.org/C29140674","wikidata":"https://www.wikidata.org/wiki/Q206637","display_name":"Computer cluster","level":2,"score":0.5343934893608093},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.49365195631980896},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4653874933719635},{"id":"https://openalex.org/C126831891","wikidata":"https://www.wikidata.org/wiki/Q221673","display_name":"Host (biology)","level":2,"score":0.4417663812637329},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.42007073760032654},{"id":"https://openalex.org/C66963500","wikidata":"https://www.wikidata.org/wiki/Q3338735","display_name":"Neutron transport","level":3,"score":0.4152417778968811},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.3292183578014374},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.27639859914779663},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.25258076190948486},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.15509045124053955},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C152568617","wikidata":"https://www.wikidata.org/wiki/Q2348","display_name":"Neutron","level":2,"score":0.0},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C74650414","wikidata":"https://www.wikidata.org/wiki/Q11397","display_name":"Classical mechanics","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1147/jrd.2009.5429074","is_oa":false,"landing_page_url":"https://doi.org/10.1147/jrd.2009.5429074","pdf_url":null,"source":{"id":"https://openalex.org/S4210219925","display_name":"IBM Journal of Research and Development","issn_l":"0018-8646","issn":["0018-8646","2151-8556"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320652","host_organization_name":"IBM","host_organization_lineage":["https://openalex.org/P4310320652"],"host_organization_lineage_names":["IBM"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IBM Journal of Research and Development","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.158.3287","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.158.3287","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.c3.lanl.gov/PAL/publications/papers/Pakin2009:rev-accel.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Affordable and clean energy","score":0.5099999904632568,"id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320308377","display_name":"National Center for Atmospheric Research","ror":"https://ror.org/05cvfcr44"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1968411163","https://openalex.org/W1977043846","https://openalex.org/W1988888548","https://openalex.org/W2017503457","https://openalex.org/W2026571096","https://openalex.org/W2042876290","https://openalex.org/W2059807497","https://openalex.org/W2079726719","https://openalex.org/W2083419061","https://openalex.org/W2098829930","https://openalex.org/W2099032432","https://openalex.org/W2099148634","https://openalex.org/W2103817093","https://openalex.org/W2109514628","https://openalex.org/W2111530316","https://openalex.org/W2130498673","https://openalex.org/W2132666119","https://openalex.org/W2137963118","https://openalex.org/W2137985407","https://openalex.org/W2138509304","https://openalex.org/W2139613964","https://openalex.org/W2140370341","https://openalex.org/W2143126120","https://openalex.org/W2151994818","https://openalex.org/W2153092996","https://openalex.org/W2155263300","https://openalex.org/W2161762385","https://openalex.org/W2165231728","https://openalex.org/W2167173222","https://openalex.org/W2167671418","https://openalex.org/W2169150396","https://openalex.org/W2169631286","https://openalex.org/W2199281787"],"related_works":["https://openalex.org/W2515491806","https://openalex.org/W4232104505","https://openalex.org/W1500804266","https://openalex.org/W2080435752","https://openalex.org/W164663419","https://openalex.org/W4226437700","https://openalex.org/W2783925434","https://openalex.org/W2042381780","https://openalex.org/W2807216313","https://openalex.org/W2142485288"],"abstract_inverted_index":{"Current":[0],"technology":[1],"trends":[2],"favor":[3],"hybrid":[4,103],"architectures,":[5],"typically":[6],"with":[7],"each":[8],"node":[9],"in":[10],"a":[11,54,111,115,146],"cluster":[12],"containing":[13],"both":[14],"general-purpose":[15,30,47,81,90],"and":[16,41,105,126],"specialized":[17],"accelerator":[18],"processors.":[19,48,82,91],"The":[20,29],"typical":[21],"model":[22,98],"for":[23],"programming":[24],"such":[25],"systems":[26,104],"is":[27,84,94],"host-centric:":[28],"processor":[31],"orchestrates":[32],"the":[33,39,62,68,71,80,96,129,137,151,155],"computation,":[34,72],"offloading":[35,73],"performance-critical":[36],"work":[37,74],"to":[38,79,102,122],"accelerator,":[40],"data":[42],"are":[43],"communicated":[44,85],"only":[45],"among":[46,86,89],"In":[49,65],"this":[50,66],"paper,":[51],"we":[52,60,120],"propose":[53],"radically":[55],"different":[56],"hybrid-programming":[57],"approach,":[58],"which":[59],"call":[61],"reverse-acceleration":[63,97],"model.":[64],"model,":[67],"accelerators":[69],"orchestrate":[70],"that":[75,95,119],"cannot":[76],"be":[77],"accelerated":[78],"Data":[83],"accelerators,":[87],"not":[88],"Our":[92],"thesis":[93],"simplifies":[99],"porting":[100],"codes":[101],"facilitates":[106],"performance":[107,148],"optimization.":[108],"We":[109],"present":[110],"case":[112],"study":[113],"of":[114,136,154],"legacy":[116],"neutron-transport":[117],"code":[118],"modified":[121],"use":[123],"reverse":[124],"acceleration":[125],"ran":[127],"across":[128],"full":[130],"122,400":[131],"cores":[132],"(general-purpose":[133],"plus":[134],"accelerator)":[135],"Los":[138],"Alamos":[139],"National":[140],"Laboratory":[141],"Roadrunner":[142],"supercomputer.":[143],"Results":[144],"indicate":[145],"substantial":[147],"improvement":[149],"over":[150],"unaccelerated":[152],"version":[153],"code.":[156]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
