{"id":"https://openalex.org/W4367147520","doi":"https://doi.org/10.1109/hipc56025.2022.00039","title":"An Algorithmic and Software Pipeline for Very Large Scale Scientific Data Compression with Error Guarantees","display_name":"An Algorithmic and Software Pipeline for Very Large Scale Scientific Data Compression with Error Guarantees","publication_year":2022,"publication_date":"2022-12-01","ids":{"openalex":"https://openalex.org/W4367147520","doi":"https://doi.org/10.1109/hipc56025.2022.00039"},"language":"en","primary_location":{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/hipc56025.2022.00039","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},"type":"article","type_crossref":"proceedings-article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.osti.gov/biblio/2000257","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5073938611","display_name":"Tania Banerjee","orcid":"https://orcid.org/0000-0003-4737-0001"},"institutions":[{"id":"https://openalex.org/I33213144","display_name":"University of Florida","ror":"https://ror.org/02y3ad647","country_code":"US","type":"education","lineage":["https://openalex.org/I33213144"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tania Banerjee","raw_affiliation_strings":["University of Florida, USA"],"affiliations":[{"raw_affiliation_string":"University of Florida, USA","institution_ids":["https://openalex.org/I33213144"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054451484","display_name":"Jong Youl Choi","orcid":"https://orcid.org/0000-0002-6459-6152"},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jong Choi","raw_affiliation_strings":["Oak Ridge National Laboratory, USA"],"affiliations":[{"raw_affiliation_string":"Oak Ridge National Laboratory, USA","institution_ids":["https://openalex.org/I1289243028"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057988780","display_name":"Jaemoon Lee","orcid":"https://orcid.org/0000-0002-9868-9410"},"institutions":[{"id":"https://openalex.org/I33213144","display_name":"University of Florida","ror":"https://ror.org/02y3ad647","country_code":"US","type":"education","lineage":["https://openalex.org/I33213144"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jaemoon Lee","raw_affiliation_strings":["University of Florida, USA"],"affiliations":[{"raw_affiliation_string":"University of Florida, USA","institution_ids":["https://openalex.org/I33213144"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063502813","display_name":"Qian Gong","orcid":"https://orcid.org/0000-0002-3570-4142"},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Qian Gong","raw_affiliation_strings":["Oak Ridge National Laboratory, USA"],"affiliations":[{"raw_affiliation_string":"Oak Ridge National Laboratory, USA","institution_ids":["https://openalex.org/I1289243028"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100644566","display_name":"Ruonan Wang","orcid":"https://orcid.org/0000-0002-9660-2924"},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ruonan Wang","raw_affiliation_strings":["Oak Ridge National Laboratory, USA"],"affiliations":[{"raw_affiliation_string":"Oak Ridge National Laboratory, USA","institution_ids":["https://openalex.org/I1289243028"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030373337","display_name":"Scott Klasky","orcid":"https://orcid.org/0000-0003-3559-5772"},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Scott Klasky","raw_affiliation_strings":["Oak Ridge National Laboratory, USA"],"affiliations":[{"raw_affiliation_string":"Oak Ridge National Laboratory, USA","institution_ids":["https://openalex.org/I1289243028"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059870257","display_name":"Anand Rangarajan","orcid":"https://orcid.org/0000-0001-8695-8436"},"institutions":[{"id":"https://openalex.org/I33213144","display_name":"University of Florida","ror":"https://ror.org/02y3ad647","country_code":"US","type":"education","lineage":["https://openalex.org/I33213144"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anand Rangarajan","raw_affiliation_strings":["University of Florida, USA"],"affiliations":[{"raw_affiliation_string":"University of Florida, USA","institution_ids":["https://openalex.org/I33213144"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077570468","display_name":"Sanjay Ranka","orcid":"https://orcid.org/0000-0003-4886-1988"},"institutions":[{"id":"https://openalex.org/I33213144","display_name":"University of Florida","ror":"https://ror.org/02y3ad647","country_code":"US","type":"education","lineage":["https://openalex.org/I33213144"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sanjay Ranka","raw_affiliation_strings":["University of Florida, USA"],"affiliations":[{"raw_affiliation_string":"University of Florida, USA","institution_ids":["https://openalex.org/I33213144"]}]}],"institution_assertions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.952,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.690554,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":82,"max":85},"biblio":{"volume":null,"issue":null,"first_page":"226","last_page":"235"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9999,"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":0.9999,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9985,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.998,"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/code","display_name":"Code (set theory)","score":0.47001958},{"id":"https://openalex.org/keywords/lossy-compression","display_name":"Lossy compression","score":0.45088682}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.81554383},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.70576704},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.5876302},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5804526},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.5083074},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.47001958},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.4690621},{"id":"https://openalex.org/C165021410","wikidata":"https://www.wikidata.org/wiki/Q55564","display_name":"Lossy compression","level":2,"score":0.45088682},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.41926292},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4138616},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3695506},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.34636015},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3320639},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.12104842},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.10727462},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/hipc56025.2022.00039","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},{"is_oa":true,"landing_page_url":"https://www.osti.gov/biblio/2000257","pdf_url":null,"source":{"id":"https://openalex.org/S4306402487","display_name":"OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I139351228","host_organization_name":"Office of Scientific and Technical Information","host_organization_lineage":["https://openalex.org/I139351228"],"host_organization_lineage_names":["Office of Scientific and Technical Information"],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false}],"best_oa_location":{"is_oa":true,"landing_page_url":"https://www.osti.gov/biblio/2000257","pdf_url":null,"source":{"id":"https://openalex.org/S4306402487","display_name":"OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I139351228","host_organization_name":"Office of Scientific and Technical Information","host_organization_lineage":["https://openalex.org/I139351228"],"host_organization_lineage_names":["Office of Scientific and Technical Information"],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false},"sustainable_development_goals":[],"grants":[],"datasets":[],"versions":[],"referenced_works_count":33,"referenced_works":["https://openalex.org/W1669104078","https://openalex.org/W1982388645","https://openalex.org/W1984845482","https://openalex.org/W1984958640","https://openalex.org/W2025945642","https://openalex.org/W2033468335","https://openalex.org/W2048494347","https://openalex.org/W2052440657","https://openalex.org/W2065360261","https://openalex.org/W2083045868","https://openalex.org/W2142265837","https://openalex.org/W2486202470","https://openalex.org/W2625759119","https://openalex.org/W2793315650","https://openalex.org/W2899601494","https://openalex.org/W2904210572","https://openalex.org/W2912174957","https://openalex.org/W2940637162","https://openalex.org/W2955516565","https://openalex.org/W2969494351","https://openalex.org/W3041193038","https://openalex.org/W3046904342","https://openalex.org/W3126702256","https://openalex.org/W3164444385","https://openalex.org/W3167885647","https://openalex.org/W3174738244","https://openalex.org/W3180329928","https://openalex.org/W3187640201","https://openalex.org/W4220775246","https://openalex.org/W4224283320","https://openalex.org/W4230804723","https://openalex.org/W4283777163","https://openalex.org/W4300059844"],"related_works":["https://openalex.org/W4384342390","https://openalex.org/W4247601675","https://openalex.org/W3180760233","https://openalex.org/W3035703949","https://openalex.org/W2888954728","https://openalex.org/W2552401318","https://openalex.org/W2547124190","https://openalex.org/W2385628723","https://openalex.org/W108076602","https://openalex.org/W1033938421"],"abstract_inverted_index":{"Efficient":[0],"data":[1,10,30,39,59,73,129,191,224,246],"compression":[2,31,82,153,168,264,281],"is":[3,83,154,173,200],"becoming":[4],"increasingly":[5],"critical":[6,289],"for":[7,29,117,170,225,245],"storing":[8],"scientific":[9,13],"because":[11],"many":[12,110],"applications":[14],"produce":[15],"vast":[16],"amounts":[17],"of":[18,47,53,70,72,133,149,158,182,209,267,271],"data.":[19],"This":[20],"paper":[21],"presents":[22],"an":[23],"end-to-end":[24],"algorithmic":[25],"and":[26,41,94,143],"software":[27],"pipeline":[28,55,106,180],"that":[32,80,123,166,217,287],"guarantees":[33],"both":[34,140],"error":[35,219],"bounds":[36,220],"on":[37,139,221,237,285],"primary":[38,223],"(PD)":[40],"derived":[42],"data,":[43],"known":[44,90],"as":[45,91,113],"Quantities":[46],"Interest":[48],"(QoI).We":[49],"demonstrate":[50,79],"the":[51,54,81,98,105,128,141,144,147,159,167,176,190,222,242,263,268,291],"effectiveness":[52],"by":[56,61,85,130,152,162],"compressing":[57],"fusion":[58,64],"generated":[60,254],"a":[62,75,155,206,232],"large-scale":[63],"code,":[65],"XGC,":[66],"which":[67,109],"produces":[68],"tens":[69],"petabytes":[71],"in":[74],"single":[76],"day.":[77],"We":[78,121],"conducted":[84],"setting":[86],"aside":[87],"computational":[88],"resources":[89,150,160],"staging":[92],"nodes,":[93],"does":[95],"not":[96],"impact":[97],"simulation":[99,163,178],"performance.":[100],"For":[101],"efficient":[102],"parallel":[103,119],"I/O,":[104],"uses":[107,214,231],"ADIOS2,":[108],"codes":[111],"such":[112],"XGC":[114],"already":[115],"use":[116],"their":[118],"I/O.":[120],"show":[122],"our":[124,272],"approach":[125,273],"can":[126,255],"compress":[127],"two":[131],"orders":[132],"magnitude":[134],"while":[135,164,282],"guaranteeing":[136,283],"high":[137,207],"accuracy":[138],"PD":[142],"QoIs.":[145],"Further,":[146],"amount":[148],"required":[151,161],"few":[156],"percent":[157],"ensuring":[165],"time":[169],"each":[171,226,249],"stage":[172],"less":[174],"than":[175],"corresponding":[177,247],"time.This":[179],"consists":[181],"three":[183],"main":[184],"steps.":[185],"The":[186,211,228,251],"first":[187],"step":[188,213,230],"decomposes":[189],"using":[192],"domain":[193],"decomposition":[194],"into":[195],"small":[196],"subdomains.":[197],"Each":[198],"subdomain":[199],"then":[201],"compressed":[202],"independently":[203],"to":[204,240,248,261,278,290],"achieve":[205],"level":[208],"parallelism.":[210],"second":[212],"existing":[215],"techniques":[216],"guarantee":[218],"subdomain.":[227,250],"third":[229],"post-processing":[233],"optimization":[234],"technique":[235],"based":[236],"Lagrange":[238,252],"multipliers":[239,253],"reduce":[241],"QoI":[243],"errors":[244,284],"be":[256],"further":[257],"quantized":[258],"or":[259],"truncated":[260],"increase":[262],"level.":[265],"All":[266],"above":[269],"characteristics":[270],"make":[274],"it":[275],"highly":[276],"practical":[277],"apply":[279],"on-the-fly":[280],"QoIs":[286],"are":[288],"scientists.":[292]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W4367147520","counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":4}],"updated_date":"2025-01-15T06:06:22.975108","created_date":"2023-04-28"}