{"id":"https://openalex.org/W1982599317","doi":"https://doi.org/10.1145/2148600.2148637","title":"Poster","display_name":"Poster","publication_year":2011,"publication_date":"2011-11-12","ids":{"openalex":"https://openalex.org/W1982599317","doi":"https://doi.org/10.1145/2148600.2148637","mag":"1982599317"},"language":"en","primary_location":{"id":"doi:10.1145/2148600.2148637","is_oa":true,"landing_page_url":"https://doi.org/10.1145/2148600.2148637","pdf_url":"https://dl.acm.org/action/downloadSupplement?doi=10.1145%2F2148600.2148637&file=post218.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2011 companion on High Performance Computing Networking, Storage and Analysis Companion","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/action/downloadSupplement?doi=10.1145%2F2148600.2148637&file=post218.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5009705616","display_name":"Szil\u00e1rd P\u00e1ll","orcid":"https://orcid.org/0000-0003-0603-5514"},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Szil\u00e1rd P\u00e1ll","raw_affiliation_strings":["Royal Institute of Technology, Stockholm, Sweden"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Royal Institute of Technology, Stockholm, Sweden","institution_ids":["https://openalex.org/I86987016"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050108763","display_name":"Berk Hess","orcid":"https://orcid.org/0000-0002-7498-7763"},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Berk Hess","raw_affiliation_strings":["Royal Institute of Technology, Stockholm, Sweden"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Royal Institute of Technology, Stockholm, Sweden","institution_ids":["https://openalex.org/I86987016"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008875190","display_name":"Erik Lindahl","orcid":"https://orcid.org/0000-0002-2734-2794"},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Erik Lindahl","raw_affiliation_strings":["Royal Institute of Technology, Stockholm, Sweden"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Royal Institute of Technology, Stockholm, Sweden","institution_ids":["https://openalex.org/I86987016"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I86987016"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"71","last_page":"72"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10044","display_name":"Protein Structure and Dynamics","score":0.9994999766349792,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T10044","display_name":"Protein Structure and Dynamics","score":0.9994999766349792,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10222","display_name":"Genomics and Chromatin Dynamics","score":0.9958999752998352,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10521","display_name":"RNA and protein synthesis mechanisms","score":0.9954000115394592,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8717544674873352},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.8221307396888733},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.7851799130439758},{"id":"https://openalex.org/keywords/simd","display_name":"SIMD","score":0.7551120519638062},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.6625485420227051},{"id":"https://openalex.org/keywords/central-processing-unit","display_name":"Central processing unit","score":0.6042126417160034},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.472053587436676},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.4608144164085388},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.4440465271472931},{"id":"https://openalex.org/keywords/implementation","display_name":"Implementation","score":0.4113653302192688},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.3652092516422272},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.14104819297790527}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8717544674873352},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.8221307396888733},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.7851799130439758},{"id":"https://openalex.org/C150552126","wikidata":"https://www.wikidata.org/wiki/Q339387","display_name":"SIMD","level":2,"score":0.7551120519638062},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.6625485420227051},{"id":"https://openalex.org/C49154492","wikidata":"https://www.wikidata.org/wiki/Q5300","display_name":"Central processing unit","level":2,"score":0.6042126417160034},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.472053587436676},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.4608144164085388},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.4440465271472931},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.4113653302192688},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.3652092516422272},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.14104819297790527},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"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:10.1145/2148600.2148637","is_oa":true,"landing_page_url":"https://doi.org/10.1145/2148600.2148637","pdf_url":"https://dl.acm.org/action/downloadSupplement?doi=10.1145%2F2148600.2148637&file=post218.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2011 companion on High Performance Computing Networking, Storage and Analysis Companion","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/2148600.2148637","is_oa":true,"landing_page_url":"https://doi.org/10.1145/2148600.2148637","pdf_url":"https://dl.acm.org/action/downloadSupplement?doi=10.1145%2F2148600.2148637&file=post218.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2011 companion on High Performance Computing Networking, Storage and Analysis Companion","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.46000000834465027}],"awards":[],"funders":[{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"},{"id":"https://openalex.org/F4320322581","display_name":"Vetenskapsr\u00e5det","ror":"https://ror.org/03zttf063"},{"id":"https://openalex.org/F4320323868","display_name":"Barcelona Supercomputing Center","ror":"https://ror.org/05sd8tv96"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W1982599317.pdf","grobid_xml":"https://content.openalex.org/works/W1982599317.grobid-xml"},"referenced_works_count":7,"referenced_works":["https://openalex.org/W1815794495","https://openalex.org/W1966078827","https://openalex.org/W2078391824","https://openalex.org/W2078713630","https://openalex.org/W2082586732","https://openalex.org/W2167173222","https://openalex.org/W4295211600"],"related_works":["https://openalex.org/W2983282793","https://openalex.org/W2099629705","https://openalex.org/W1992352827","https://openalex.org/W3012895752","https://openalex.org/W3000570965","https://openalex.org/W4232853593","https://openalex.org/W2473478803","https://openalex.org/W2022441525","https://openalex.org/W2729363167","https://openalex.org/W2060611139"],"abstract_inverted_index":{"Several":[0],"GPU-based":[1],"algorithms":[2],"have":[3,19],"been":[4,21],"developed":[5],"to":[6,23,36,84,94,132,158],"accelerate":[7],"biomolecular":[8],"simulations,":[9],"but":[10],"although":[11],"they":[12,18],"provide":[13],"benefits":[14],"over":[15],"single-core":[16],"implementations,":[17],"not":[20,35],"able":[22],"surpass":[24],"the":[25,68,105,145,151],"performance":[26],"of":[27,147],"state-of-the":[28],"art":[29],"SIMD":[30,69],"CPU":[31,49,106,135],"implementations":[32],"(e.g.":[33],"GROMACS),":[34],"mention":[37],"efficient":[38],"scaling.":[39,143],"Here,":[40],"we":[41],"present":[42],"a":[43],"heterogenous":[44],"parallelization":[45],"that":[46],"utilizes":[47],"both":[48],"and":[50,99,137,141],"GPU":[51,113,153],"resources":[52],"efficiently.":[53],"A":[54],"novel":[55],"fixed-particle-number":[56],"sub-cell":[57],"algorithm":[58,66],"for":[59],"non-bonded":[60,89],"force":[61],"calculation":[62],"was":[63],"developed.":[64],"The":[65,87],"uses":[67],"width":[70],"as":[71,119,121],"algorithmic":[72],"work":[73],"unit,":[74],"it":[75,80],"is":[76,125],"intrinsically":[77],"future-proof":[78],"since":[79],"can":[81],"be":[82],"adapted":[83],"future":[85],"hardware.":[86],"CUDA":[88],"kernel":[90],"implementation":[91,156],"achieves":[92],"up":[93],"60\\%":[95],"work-efficiency,":[96],"1.5":[97],"IPC,":[98],"95\\%":[100],"L1":[101],"cache":[102],"utilization.":[103],"On":[104],"OpenMP-parallelized":[107],"SSE-accelerated":[108],"code":[109,136],"runs":[110],"overlapping":[111],"with":[112],"execution.":[114],"Fully":[115],"automated":[116],"dynamic":[117],"inter-process":[118],"well":[120],"CPU-GPU":[122],"load":[123],"balancing":[124],"employed.":[126],"We":[127],"achieve":[128],"threefold":[129],"speedup":[130],"compared":[131],"equivalent":[133],"GROMACS":[134],"show":[138],"good":[139],"strong":[140],"weak":[142],"To":[144],"best":[146],"our":[148],"knowledge":[149],"this":[150],"fastest":[152],"molecular":[154],"dynamics":[155],"presented":[157],"date.":[159]},"counts_by_year":[{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2016-06-24T00:00:00"}
