{"id":"https://openalex.org/W2051517999","doi":"https://doi.org/10.1145/1996130.1996157","title":"Experience of parallelizing cryo-EM 3D reconstruction on a CPU-GPU heterogeneous system","display_name":"Experience of parallelizing cryo-EM 3D reconstruction on a CPU-GPU heterogeneous system","publication_year":2011,"publication_date":"2011-06-08","ids":{"openalex":"https://openalex.org/W2051517999","doi":"https://doi.org/10.1145/1996130.1996157","mag":"2051517999"},"language":"en","primary_location":{"id":"doi:10.1145/1996130.1996157","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1996130.1996157","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 20th international symposium on High performance distributed computing","raw_type":"proceedings-article"},"type":"conference-paper","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/A5070465173","display_name":"Linchuan Li","orcid":null},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Linchuan Li","raw_affiliation_strings":["Institute of Computing Technology, Chinese Academy of Science, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Computing Technology, Chinese Academy of Science, Beijing, China","institution_ids":["https://openalex.org/I4210090176"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100770663","display_name":"Xingjian Li","orcid":"https://orcid.org/0000-0001-8073-7552"},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xingjian Li","raw_affiliation_strings":["Institute of Computing Technology, Chinese Academy of Science, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Computing Technology, Chinese Academy of Science, Beijing, China","institution_ids":["https://openalex.org/I4210090176"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104072170","display_name":"Guangming Tan","orcid":null},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guangming Tan","raw_affiliation_strings":["Institute of Computing Technology, Chinese Academy of Science, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Computing Technology, Chinese Academy of Science, Beijing, China","institution_ids":["https://openalex.org/I4210090176"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101645579","display_name":"Mingyu Chen","orcid":"https://orcid.org/0000-0003-4469-1037"},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingyu Chen","raw_affiliation_strings":["Institute of Computing Technology, Chinese Academy of Science, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Computing Technology, Chinese Academy of Science, Beijing, China","institution_ids":["https://openalex.org/I4210090176"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055477377","display_name":"Peiheng Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peiheng Zhang","raw_affiliation_strings":["Institute of Computing Technology, Chinese Academy of Science, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Computing Technology, Chinese Academy of Science, Beijing, China","institution_ids":["https://openalex.org/I4210090176"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210090176"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"195","last_page":"204"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9990000128746033,"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":0.9990000128746033,"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":0.9988999962806702,"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/T11181","display_name":"Advanced Data Storage Technologies","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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8948020935058594},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.8531486988067627},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.7731143236160278},{"id":"https://openalex.org/keywords/data-parallelism","display_name":"Data parallelism","score":0.5385665893554688},{"id":"https://openalex.org/keywords/gpu-cluster","display_name":"GPU cluster","score":0.5304365158081055},{"id":"https://openalex.org/keywords/xeon-phi","display_name":"Xeon Phi","score":0.5240705013275146},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.5205931663513184},{"id":"https://openalex.org/keywords/task-parallelism","display_name":"Task parallelism","score":0.5129455924034119},{"id":"https://openalex.org/keywords/xeon","display_name":"Xeon","score":0.5040263533592224},{"id":"https://openalex.org/keywords/instruction-level-parallelism","display_name":"Instruction-level parallelism","score":0.48768508434295654},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.4723148047924042},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.45447689294815063},{"id":"https://openalex.org/keywords/central-processing-unit","display_name":"Central processing unit","score":0.4483260214328766},{"id":"https://openalex.org/keywords/parallelism","display_name":"Parallelism (grammar)","score":0.4353404641151428},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.16132113337516785}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8948020935058594},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.8531486988067627},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.7731143236160278},{"id":"https://openalex.org/C61483411","wikidata":"https://www.wikidata.org/wiki/Q3124522","display_name":"Data parallelism","level":3,"score":0.5385665893554688},{"id":"https://openalex.org/C2781335571","wikidata":"https://www.wikidata.org/wiki/Q2633544","display_name":"GPU cluster","level":3,"score":0.5304365158081055},{"id":"https://openalex.org/C96972482","wikidata":"https://www.wikidata.org/wiki/Q1049168","display_name":"Xeon Phi","level":2,"score":0.5240705013275146},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.5205931663513184},{"id":"https://openalex.org/C42992933","wikidata":"https://www.wikidata.org/wiki/Q691169","display_name":"Task parallelism","level":3,"score":0.5129455924034119},{"id":"https://openalex.org/C145108525","wikidata":"https://www.wikidata.org/wiki/Q656154","display_name":"Xeon","level":2,"score":0.5040263533592224},{"id":"https://openalex.org/C140763907","wikidata":"https://www.wikidata.org/wiki/Q2714055","display_name":"Instruction-level parallelism","level":3,"score":0.48768508434295654},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.4723148047924042},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.45447689294815063},{"id":"https://openalex.org/C49154492","wikidata":"https://www.wikidata.org/wiki/Q5300","display_name":"Central processing unit","level":2,"score":0.4483260214328766},{"id":"https://openalex.org/C2781172179","wikidata":"https://www.wikidata.org/wiki/Q853109","display_name":"Parallelism (grammar)","level":2,"score":0.4353404641151428},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.16132113337516785},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1996130.1996157","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1996130.1996157","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 20th international symposium on High performance distributed computing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W178909140","https://openalex.org/W1986431220","https://openalex.org/W2001024934","https://openalex.org/W2006158980","https://openalex.org/W2019708326","https://openalex.org/W2048982317","https://openalex.org/W2080804082","https://openalex.org/W2114983120","https://openalex.org/W2118936983","https://openalex.org/W2140092984","https://openalex.org/W2141579716","https://openalex.org/W2151207225","https://openalex.org/W2165831368","https://openalex.org/W3000120212","https://openalex.org/W4386313974"],"related_works":["https://openalex.org/W2475524688","https://openalex.org/W2739740241","https://openalex.org/W2085105049","https://openalex.org/W2592417500","https://openalex.org/W2883383827","https://openalex.org/W4214765606","https://openalex.org/W2058527440","https://openalex.org/W2334331871","https://openalex.org/W2612954225","https://openalex.org/W2952973539"],"abstract_inverted_index":{"Heterogeneous":[0],"architecture":[1,66],"is":[2,25,76,122,141],"becoming":[3],"an":[4,79,142],"important":[5],"way":[6],"to":[7,28,51,59,97,148],"build":[8],"a":[9,26,47,92,99,114,157],"massive":[10,31],"parallel":[11,146],"computer":[12],"system,":[13],"i.e.":[14],"the":[15,104,170,180,183,189,196],"CPU-GPU":[16,185],"heterogeneous":[17,40,158],"systems":[18],"ranked":[19],"in":[20,86,156],"Top500":[21],"list.":[22],"However,":[23],"it":[24],"challenge":[27],"efficiently":[29],"utilize":[30,149],"parallelism":[32,55,64,85,101,140],"of":[33,62,116,124,145,151],"both":[34,152],"applications":[35],"and":[36,53,90,106,130,154],"architectures":[37],"on":[38,49,113,179,195],"such":[39],"systems.":[41],"In":[42],"this":[43],"paper":[44],"we":[45],"present":[46],"practice":[48],"how":[50],"exploit":[52,82],"orchestrate":[54],"at":[56,65],"algorithm":[57,96],"level":[58],"take":[60],"advantage":[61],"underlying":[63],"level.":[67],"A":[68],"potential":[69],"Petaflops":[70],"application":[71,105],"--":[72],"cryo-EM":[73,87],"3D":[74,88],"reconstruction":[75],"selected":[77],"as":[78],"example.":[80],"We":[81],"all":[83],"possible":[84],"reconstruction,":[89],"leverage":[91],"self-adaptive":[93],"dynamic":[94],"scheduling":[95],"create":[98],"proper":[100],"mapping":[102],"between":[103],"architecture.":[107],"The":[108,135,160],"parallelized":[109,172],"programs":[110],"are":[111],"evaluated":[112],"subsystem":[115],"Dawning":[117],"Nebulae":[118],"supercomputer,":[119],"whose":[120],"node":[121],"composed":[123],"two":[125],"Intel":[126],"six-core":[127],"Xeon":[128],"CPUs":[129],"one":[131],"Nvidia":[132],"Fermi":[133],"GPU.":[134],"experiment":[136],"confirms":[137],"that":[138],"hierarchical":[139],"efficient":[143],"pattern":[144],"programming":[147],"capabilities":[150],"CPU":[153],"GPU":[155],"system.":[159],"CUDA":[161],"kernels":[162],"run":[163],"more":[164],"than":[165,169],"3":[166],"times":[167],"faster":[168],"OpenMP":[171],"ones":[173],"using":[174],"12":[175],"cores":[176],"(threads).":[177],"Based":[178],"GPU-only":[181],"version,":[182],"hybrid":[184],"program":[186],"further":[187],"improves":[188],"whole":[190],"application's":[191],"performance":[192],"by":[193],"30%":[194],"average.":[197]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":4},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}