{"id":"https://openalex.org/W2068528924","doi":"https://doi.org/10.1109/sc.2010.40","title":"Parallelizing the QUDA Library for Multi-GPU Calculations in Lattice Quantum Chromodynamics","display_name":"Parallelizing the QUDA Library for Multi-GPU Calculations in Lattice Quantum Chromodynamics","publication_year":2010,"publication_date":"2010-11-01","ids":{"openalex":"https://openalex.org/W2068528924","doi":"https://doi.org/10.1109/sc.2010.40","mag":"2068528924"},"language":"en","primary_location":{"id":"doi:10.1109/sc.2010.40","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sc.2010.40","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 ACM/IEEE International Conference for High Performance Computing, Networking, Storage and Analysis","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.1011.0024","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5110294841","display_name":"Ronald Babich","orcid":null},"institutions":[{"id":"https://openalex.org/I111088046","display_name":"Boston University","ror":"https://ror.org/05qwgg493","country_code":"US","type":"education","lineage":["https://openalex.org/I111088046"]},{"id":"https://openalex.org/I4388482696","display_name":"Naval Research Laboratory Information Technology Division","ror":"https://ror.org/04xfp8b22","country_code":null,"type":"facility","lineage":["https://openalex.org/I1288214837","https://openalex.org/I1330347796","https://openalex.org/I175003984","https://openalex.org/I3130687028","https://openalex.org/I4388482696"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ronald Babich","raw_affiliation_strings":["Center for Computational Science Boston University, Boston, Massachusetts, USA","Center for Comput. Sci., Boston Univ., Boston, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Computational Science Boston University, Boston, Massachusetts, USA","institution_ids":["https://openalex.org/I111088046","https://openalex.org/I4388482696"]},{"raw_affiliation_string":"Center for Comput. Sci., Boston Univ., Boston, MA, USA","institution_ids":["https://openalex.org/I111088046"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046199609","display_name":"M. A. Clark","orcid":"https://orcid.org/0000-0001-5211-2002"},"institutions":[{"id":"https://openalex.org/I136199984","display_name":"Harvard University","ror":"https://ror.org/03vek6s52","country_code":"US","type":"education","lineage":["https://openalex.org/I136199984"]},{"id":"https://openalex.org/I4210124175","display_name":"Center for Astrophysics Harvard & Smithsonian","ror":"https://ror.org/03c3r2d17","country_code":"US","type":"education","lineage":["https://openalex.org/I103187081","https://openalex.org/I136199984","https://openalex.org/I4210124175"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael A. Clark","raw_affiliation_strings":["Harvard-Smithsonian Center for Astrophysics Cambridge, Massachusetts, USA","[Harvard-Smithsonian Center for Astrophys., Cambridge, MA, USA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harvard-Smithsonian Center for Astrophysics Cambridge, Massachusetts, USA","institution_ids":["https://openalex.org/I4210124175"]},{"raw_affiliation_string":"[Harvard-Smithsonian Center for Astrophys., Cambridge, MA, USA]","institution_ids":["https://openalex.org/I136199984"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5104955988","display_name":"B\u00e1lint Jo\u00f3","orcid":null},"institutions":[{"id":"https://openalex.org/I29801172","display_name":"Thomas Jefferson National Accelerator Facility","ror":"https://ror.org/02vwzrd76","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I29801172","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Balint Jo\u00f3","raw_affiliation_strings":["Jefferson Laboratory Newport News, Virginia, USA","Jefferson Lab. Newport News, Jefferson, VA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Jefferson Laboratory Newport News, Virginia, USA","institution_ids":["https://openalex.org/I29801172"]},{"raw_affiliation_string":"Jefferson Lab. Newport News, Jefferson, VA, USA","institution_ids":["https://openalex.org/I29801172"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"11"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9857000112533569,"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"}},"topics":[{"id":"https://openalex.org/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9857000112533569,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9782000184059143,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.906000018119812,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/infiniband","display_name":"InfiniBand","score":0.8766694664955139},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.799859881401062},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.7992603182792664},{"id":"https://openalex.org/keywords/gpu-cluster","display_name":"GPU cluster","score":0.7835524082183838},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.6069724559783936},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6016877293586731},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.5617130994796753},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.4988541603088379},{"id":"https://openalex.org/keywords/graphics-processing-unit","display_name":"Graphics processing unit","score":0.4611198604106903},{"id":"https://openalex.org/keywords/quantum-computer","display_name":"Quantum computer","score":0.4157125949859619},{"id":"https://openalex.org/keywords/quantum","display_name":"Quantum","score":0.3342090845108032},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.19745337963104248},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.1907898187637329},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.09656229615211487}],"concepts":[{"id":"https://openalex.org/C2781030343","wikidata":"https://www.wikidata.org/wiki/Q922437","display_name":"InfiniBand","level":2,"score":0.8766694664955139},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.799859881401062},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.7992603182792664},{"id":"https://openalex.org/C2781335571","wikidata":"https://www.wikidata.org/wiki/Q2633544","display_name":"GPU cluster","level":3,"score":0.7835524082183838},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.6069724559783936},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6016877293586731},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.5617130994796753},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4988541603088379},{"id":"https://openalex.org/C2779851693","wikidata":"https://www.wikidata.org/wiki/Q183484","display_name":"Graphics processing unit","level":2,"score":0.4611198604106903},{"id":"https://openalex.org/C58053490","wikidata":"https://www.wikidata.org/wiki/Q176555","display_name":"Quantum computer","level":3,"score":0.4157125949859619},{"id":"https://openalex.org/C84114770","wikidata":"https://www.wikidata.org/wiki/Q46344","display_name":"Quantum","level":2,"score":0.3342090845108032},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.19745337963104248},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.1907898187637329},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.09656229615211487},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/sc.2010.40","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sc.2010.40","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 ACM/IEEE International Conference for High Performance Computing, Networking, Storage and Analysis","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.750.8211","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.750.8211","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://arxiv.org/pdf/1011.0024.pdf","raw_type":"text"},{"id":"doi:10.48550/arxiv.1011.0024","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1011.0024","pdf_url":null,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article-journal"},{"id":"mag:2068528924","is_oa":false,"landing_page_url":"https://inspirehep.net/record/875156","pdf_url":null,"source":{"id":"https://openalex.org/S4306533014","display_name":"To appear in the proceedings of","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":"To appear in the proceedings of","raw_type":null}],"best_oa_location":{"id":"doi:10.48550/arxiv.1011.0024","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1011.0024","pdf_url":null,"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":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article-journal"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1496910322","https://openalex.org/W1984450486","https://openalex.org/W1987779630","https://openalex.org/W2000315635","https://openalex.org/W2042381780","https://openalex.org/W2045315360","https://openalex.org/W2065489259","https://openalex.org/W2071150184","https://openalex.org/W2090058354","https://openalex.org/W2121444153","https://openalex.org/W2155216327","https://openalex.org/W2155967869","https://openalex.org/W2157213407","https://openalex.org/W2316564661","https://openalex.org/W6603245178","https://openalex.org/W6630155607","https://openalex.org/W6630779416","https://openalex.org/W6635781126","https://openalex.org/W6764940406"],"related_works":["https://openalex.org/W2962679172","https://openalex.org/W2240870112","https://openalex.org/W1971418186","https://openalex.org/W3040356634","https://openalex.org/W2001981629","https://openalex.org/W2000015278","https://openalex.org/W1996820070","https://openalex.org/W2106821446","https://openalex.org/W2755264124","https://openalex.org/W2575521048","https://openalex.org/W2159497832","https://openalex.org/W3211968776","https://openalex.org/W1976651123","https://openalex.org/W2026150332","https://openalex.org/W1590700761","https://openalex.org/W2141579716","https://openalex.org/W2153149286","https://openalex.org/W1973603787","https://openalex.org/W2052488773","https://openalex.org/W2765587783"],"abstract_inverted_index":{"Graphics":[0],"Processing":[1],"Units":[2],"(GPUs)":[3],"are":[4],"having":[5],"a":[6,28,78],"transformational":[7],"effect":[8],"on":[9,44,66,87,126,140],"numerical":[10],"lattice":[11],"quantum":[12],"chromo-":[13],"dynamics":[14],"(LQCD)":[15],"calculations":[16],"of":[17,30,80,106,120,146],"importance":[18],"in":[19,63,82,144],"nuclear":[20],"and":[21,122,129],"particle":[22],"physics.":[23],"The":[24],"QUDA":[25,108],"library":[26,109],"provides":[27],"package":[29],"mixed":[31],"precision":[32],"sparse":[33],"matrix":[34],"linear":[35],"solvers":[36],"for":[37,58,77,117,132],"LQCD":[38,59],"applications,":[39],"supporting":[40],"single":[41],"GPUs":[42,112,136],"based":[43],"NVIDIA's":[45],"Compute":[46],"Unified":[47],"Device":[48],"Architecture":[49],"(CUDA).":[50],"This":[51],"library,":[52],"interfaced":[53],"to":[54,134],"the":[55,67,71,92,104,107,118],"QDP++/Chroma":[56],"framework":[57],"calculations,":[60],"is":[61],"currently":[62],"production":[64],"use":[65],"\"9g\"":[68],"cluster":[69],"at":[70],"Jefferson":[72],"Laboratory,":[73],"enabling":[74],"unprecedented":[75],"price/performance":[76],"range":[79],"problems":[81],"LQCD.":[83],"Nevertheless,":[84],"memory":[85],"constraints":[86],"current":[88],"GPU":[89],"devices":[90],"limit":[91],"problem":[93],"sizes":[94],"that":[95],"can":[96],"be":[97],"tackled.":[98],"In":[99],"this":[100],"contribution":[101],"we":[102,142],"describe":[103],"parallelization":[105],"onto":[110],"multiple":[111],"using":[113],"MPI,":[114],"including":[115],"strategies":[116],"overlapping":[119],"communication":[121],"computation.":[123],"We":[124],"report":[125],"both":[127],"weak":[128],"strong":[130],"scaling":[131],"up":[133],"32":[135],"interconnected":[137],"by":[138],"InfiniBand,":[139],"which":[141],"sustain":[143],"excess":[145],"4":[147],"Tflops.":[148]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
