{"id":"https://openalex.org/W2066310479","doi":"https://doi.org/10.1145/2484762.2484785","title":"Exploiting MapReduce and data compression for data-intensive applications","display_name":"Exploiting MapReduce and data compression for data-intensive applications","publication_year":2013,"publication_date":"2013-07-22","ids":{"openalex":"https://openalex.org/W2066310479","doi":"https://doi.org/10.1145/2484762.2484785","mag":"2066310479"},"language":"en","primary_location":{"id":"doi:10.1145/2484762.2484785","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2484762.2484785","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Conference on Extreme Science and Engineering Discovery Environment: Gateway to Discovery","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/A5024575129","display_name":"Guangchen Ruan","orcid":"https://orcid.org/0000-0001-8316-5027"},"institutions":[{"id":"https://openalex.org/I592451","display_name":"Indiana University","ror":"https://ror.org/01kg8sb98","country_code":"US","type":"education","lineage":["https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Guangchen Ruan","raw_affiliation_strings":["Indiana University"],"affiliations":[{"raw_affiliation_string":"Indiana University","institution_ids":["https://openalex.org/I592451"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100323357","display_name":"Hui Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I592451","display_name":"Indiana University","ror":"https://ror.org/01kg8sb98","country_code":"US","type":"education","lineage":["https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hui Zhang","raw_affiliation_strings":["Indiana University"],"affiliations":[{"raw_affiliation_string":"Indiana University","institution_ids":["https://openalex.org/I592451"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060672408","display_name":"Beth Plale","orcid":"https://orcid.org/0000-0003-2164-8132"},"institutions":[{"id":"https://openalex.org/I592451","display_name":"Indiana University","ror":"https://ror.org/01kg8sb98","country_code":"US","type":"education","lineage":["https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Beth Plale","raw_affiliation_strings":["Indiana University"],"affiliations":[{"raw_affiliation_string":"Indiana University","institution_ids":["https://openalex.org/I592451"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5024575129"],"corresponding_institution_ids":["https://openalex.org/I592451"],"apc_list":null,"apc_paid":null,"fwci":1.8123,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.87032422,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","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/T11181","display_name":"Advanced Data Storage Technologies","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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9983999729156494,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T11986","display_name":"Scientific Computing and Data Management","score":0.9865000247955322,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8786022663116455},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.6291065812110901},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.5410356521606445},{"id":"https://openalex.org/keywords/data-intensive-computing","display_name":"Data-intensive computing","score":0.5201804637908936},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4894791841506958},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.48626768589019775},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.45046019554138184},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.42909735441207886},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.41505953669548035},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.21712639927864075},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.1272868514060974},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.1176733672618866}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8786022663116455},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.6291065812110901},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.5410356521606445},{"id":"https://openalex.org/C76831024","wikidata":"https://www.wikidata.org/wiki/Q5227096","display_name":"Data-intensive computing","level":4,"score":0.5201804637908936},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4894791841506958},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.48626768589019775},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.45046019554138184},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.42909735441207886},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.41505953669548035},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.21712639927864075},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.1272868514060974},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.1176733672618866},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C70429105","wikidata":"https://www.wikidata.org/wiki/Q249999","display_name":"Grid computing","level":3,"score":0.0},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2484762.2484785","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2484762.2484785","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Conference on Extreme Science and Engineering Discovery Environment: Gateway to Discovery","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","score":0.44999998807907104,"display_name":"Industry, innovation and infrastructure"}],"awards":[{"id":"https://openalex.org/G1414815486","display_name":null,"funder_award_id":"OCI-1053575","funder_id":"https://openalex.org/F4320337377","funder_display_name":"Office of Advanced Cyberinfrastructure"}],"funders":[{"id":"https://openalex.org/F4320337377","display_name":"Office of Advanced Cyberinfrastructure","ror":"https://ror.org/04nh1dc89"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1528380545","https://openalex.org/W1978660499","https://openalex.org/W2019449516","https://openalex.org/W2032648817","https://openalex.org/W2042036937","https://openalex.org/W2045410780","https://openalex.org/W2045886945","https://openalex.org/W2095977162","https://openalex.org/W2098633863","https://openalex.org/W2098935637","https://openalex.org/W2122465391","https://openalex.org/W2147982258","https://openalex.org/W2154158105","https://openalex.org/W2154399174","https://openalex.org/W2290868772","https://openalex.org/W2995564009"],"related_works":["https://openalex.org/W4390608645","https://openalex.org/W4247566972","https://openalex.org/W4394895745","https://openalex.org/W2960264696","https://openalex.org/W3090563135","https://openalex.org/W2497432351","https://openalex.org/W4206777497","https://openalex.org/W2910064364","https://openalex.org/W4200136508","https://openalex.org/W2794953737"],"abstract_inverted_index":{"HPC":[0,16,69],"platform":[1,17],"shows":[2],"good":[3],"success":[4],"for":[5,44],"predominantly":[6],"compute-intensive":[7],"jobs,":[8],"however,":[9],"data":[10,23,51,63,71,105,114,178],"intensive":[11],"jobs":[12],"still":[13],"struggle":[14],"on":[15,54,67,108,123,144,162],"as":[18,81,118,120],"large":[19,145,157],"amounts":[20],"of":[21,112,127,135,175],"concurrent":[22],"movement":[24],"from":[25,75],"I/O":[26],"nodes":[27,30],"to":[28,41,83,115],"compute":[29],"can":[31,87,92],"easily":[32],"saturate":[33],"the":[34,38,62,116,124],"network":[35],"links.":[36],"MapReduce,":[37],"\"moving":[39],"computation":[40,58],"data\"":[42],"paradigm":[43],"many":[45],"pleasingly":[46],"parallel":[47],"applications,":[48,136],"assumes":[49],"that":[50],"are":[52,64],"resident":[53],"local":[55],"disks":[56],"and":[57,150,181],"is":[59],"scheduled":[60],"where":[61,85],"located.":[65],"However,":[66],"an":[68],"machine":[70],"must":[72],"be":[73,88],"staged":[74],"a":[76,94,137,151],"broader":[77],"file":[78],"system":[79],"(such":[80],"Luster),":[82],"HDFS":[84],"it":[86],"accessed;":[89],"this":[90,100],"staging":[91],"represent":[93],"substantial":[95],"delay":[96],"in":[97,173],"processing.":[98],"In":[99],"paper":[101],"we":[102],"look":[103],"at":[104],"compression's":[106],"effect":[107],"reducing":[109],"bandwidth":[110],"needs":[111],"getting":[113],"application,":[117],"well":[119],"its":[121],"impact":[122],"overall":[125],"performance":[126,171],"data-intensive":[128],"applications.":[129],"Our":[130,165],"study":[131],"examines":[132],"two":[133],"types":[134],"3D-time":[138],"series":[139],"caries":[140],"lesion":[141],"assessment":[142],"focusing":[143],"scale":[146,158],"medical":[147],"image":[148],"dataset,":[149],"HTRC":[152],"word":[153],"counting":[154],"task":[155],"concerning":[156],"text":[159],"analysis":[160],"running":[161],"XSEDE":[163],"resources.":[164],"extensive":[166],"experimental":[167],"results":[168],"demonstrate":[169],"significant":[170],"improvement":[172],"terms":[174],"storage":[176],"space,":[177],"stage-in":[179],"time,":[180],"job":[182],"execution":[183],"time.":[184]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
