{"id":"https://openalex.org/W1498943610","doi":"https://doi.org/10.1109/hpcsim.2015.7237020","title":"Acceleration of dRMSD calculation and efficient usage of GPU caches","display_name":"Acceleration of dRMSD calculation and efficient usage of GPU caches","publication_year":2015,"publication_date":"2015-07-01","ids":{"openalex":"https://openalex.org/W1498943610","doi":"https://doi.org/10.1109/hpcsim.2015.7237020","mag":"1498943610"},"language":"en","primary_location":{"id":"doi:10.1109/hpcsim.2015.7237020","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpcsim.2015.7237020","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 International Conference on High Performance Computing &amp; Simulation (HPCS)","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/A5089216324","display_name":"Ji\u0159\u00ed Filipovi\u010d","orcid":"https://orcid.org/0000-0002-5703-9673"},"institutions":[{"id":"https://openalex.org/I21449261","display_name":"Masaryk University","ror":"https://ror.org/02j46qs45","country_code":"CZ","type":"education","lineage":["https://openalex.org/I21449261"]}],"countries":["CZ"],"is_corresponding":true,"raw_author_name":"Jiri Filipovic","raw_affiliation_strings":["Faculty of Informatics, Masaryk University, Brno, Czech Republic","Faculty of Informatics; Masaryk University; Brno, Czech Republic"],"affiliations":[{"raw_affiliation_string":"Faculty of Informatics, Masaryk University, Brno, Czech Republic","institution_ids":["https://openalex.org/I21449261"]},{"raw_affiliation_string":"Faculty of Informatics; Masaryk University; Brno, Czech Republic","institution_ids":["https://openalex.org/I21449261"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014123660","display_name":"Jan Plh\u00e1k","orcid":null},"institutions":[{"id":"https://openalex.org/I21449261","display_name":"Masaryk University","ror":"https://ror.org/02j46qs45","country_code":"CZ","type":"education","lineage":["https://openalex.org/I21449261"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Jan Plhak","raw_affiliation_strings":["Faculty of Informatics, Masaryk University, Brno, Czech Republic","Faculty of Informatics; Masaryk University; Brno, Czech Republic"],"affiliations":[{"raw_affiliation_string":"Faculty of Informatics, Masaryk University, Brno, Czech Republic","institution_ids":["https://openalex.org/I21449261"]},{"raw_affiliation_string":"Faculty of Informatics; Masaryk University; Brno, Czech Republic","institution_ids":["https://openalex.org/I21449261"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068360342","display_name":"David St\u0159el\u00e1k","orcid":"https://orcid.org/0000-0003-4513-4718"},"institutions":[{"id":"https://openalex.org/I21449261","display_name":"Masaryk University","ror":"https://ror.org/02j46qs45","country_code":"CZ","type":"education","lineage":["https://openalex.org/I21449261"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"David Strelak","raw_affiliation_strings":["Faculty of Informatics, Masaryk University, Brno, Czech Republic","Faculty of Informatics; Masaryk University; Brno, Czech Republic"],"affiliations":[{"raw_affiliation_string":"Faculty of Informatics, Masaryk University, Brno, Czech Republic","institution_ids":["https://openalex.org/I21449261"]},{"raw_affiliation_string":"Faculty of Informatics; Masaryk University; Brno, Czech Republic","institution_ids":["https://openalex.org/I21449261"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5089216324"],"corresponding_institution_ids":["https://openalex.org/I21449261"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.01937461,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"47","last_page":"54"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9983999729156494,"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":0.9983999729156494,"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":0.992900013923645,"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/T10591","display_name":"Theoretical and Computational Physics","score":0.9926999807357788,"subfield":{"id":"https://openalex.org/subfields/3104","display_name":"Condensed Matter 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/speedup","display_name":"Speedup","score":0.9053434133529663},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8801150321960449},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.8565936088562012},{"id":"https://openalex.org/keywords/locality","display_name":"Locality","score":0.7048038244247437},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.6650199890136719},{"id":"https://openalex.org/keywords/shared-memory","display_name":"Shared memory","score":0.5821112990379333},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5334950089454651},{"id":"https://openalex.org/keywords/cpu-cache","display_name":"CPU cache","score":0.5325186848640442},{"id":"https://openalex.org/keywords/acceleration","display_name":"Acceleration","score":0.4591069221496582},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.4421083629131317},{"id":"https://openalex.org/keywords/locality-of-reference","display_name":"Locality of reference","score":0.43005362153053284},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.19712185859680176}],"concepts":[{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.9053434133529663},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8801150321960449},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.8565936088562012},{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.7048038244247437},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.6650199890136719},{"id":"https://openalex.org/C133875982","wikidata":"https://www.wikidata.org/wiki/Q764810","display_name":"Shared memory","level":2,"score":0.5821112990379333},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5334950089454651},{"id":"https://openalex.org/C189783530","wikidata":"https://www.wikidata.org/wiki/Q352090","display_name":"CPU cache","level":3,"score":0.5325186848640442},{"id":"https://openalex.org/C117896860","wikidata":"https://www.wikidata.org/wiki/Q11376","display_name":"Acceleration","level":2,"score":0.4591069221496582},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.4421083629131317},{"id":"https://openalex.org/C27602214","wikidata":"https://www.wikidata.org/wiki/Q1868547","display_name":"Locality of reference","level":3,"score":0.43005362153053284},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.19712185859680176},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/hpcsim.2015.7237020","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpcsim.2015.7237020","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 International Conference on High Performance Computing &amp; Simulation (HPCS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7","score":0.5600000023841858}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W2002638840","https://openalex.org/W2019821619","https://openalex.org/W2040556424","https://openalex.org/W2056295840","https://openalex.org/W2125725340","https://openalex.org/W2150472159","https://openalex.org/W2157654386","https://openalex.org/W2162171655","https://openalex.org/W2183420951","https://openalex.org/W6664917920"],"related_works":["https://openalex.org/W1555349535","https://openalex.org/W2583128298","https://openalex.org/W2053359564","https://openalex.org/W2161159383","https://openalex.org/W1495260638","https://openalex.org/W1511204342","https://openalex.org/W2369125128","https://openalex.org/W2369223577","https://openalex.org/W2010020348","https://openalex.org/W1982580072"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,24,59],"introduce":[4],"the":[5,66,111],"GPU":[6,69],"acceleration":[7],"of":[8,16,65,83],"dRMSD":[9,36,42],"algorithm,":[10],"used":[11],"to":[12,20,62,71,99,109],"compare":[13],"different":[14],"structures":[15],"a":[17],"molecule.":[18],"Comparing":[19],"multithreaded":[21],"CPU":[22],"implementation,":[23],"have":[25,60,93],"reached":[26],"13.4\u00d7":[27],"speedup":[28,33],"in":[29,34,102],"clustering":[30],"and":[31,48,81,89,105],"62.7\u00d7":[32],"I:I":[35],"computation":[37,43],"using":[38,56,68,77],"mid-end":[39],"GPU.":[40],"The":[41],"exposes":[44],"strong":[45],"memory":[46,73,85],"locality":[47],"thus":[49],"is":[50],"compute-bound.":[51],"Along":[52],"with":[53],"conservative":[54],"implementation":[55,76],"shared":[57,84],"memory,":[58],"decided":[61],"implement":[63],"variants":[64],"algorithm":[67],"caches":[70],"maintain":[72],"locality.":[74],"Our":[75],"cache":[78,100],"reaches":[79],"96.5%":[80],"91.6%":[82],"performance":[86,96],"on":[87],"Fermi":[88],"Maxwell,":[90],"respectively.":[91],"We":[92],"identified":[94],"several":[95],"pitfalls":[97],"related":[98],"blocking":[101],"compute-bound":[103],"codes":[104],"suggested":[106],"optimization":[107],"techniques":[108],"improve":[110],"performance.":[112]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
