{"id":"https://openalex.org/W4367176010","doi":"https://doi.org/10.1145/3588195.3592994","title":"FZ-GPU: A Fast and High-Ratio Lossy Compressor for Scientific Computing Applications on GPUs","display_name":"FZ-GPU: A Fast and High-Ratio Lossy Compressor for Scientific Computing Applications on GPUs","publication_year":2023,"publication_date":"2023-08-07","ids":{"openalex":"https://openalex.org/W4367176010","doi":"https://doi.org/10.1145/3588195.3592994"},"language":"en","primary_location":{"id":"doi:10.1145/3588195.3592994","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3588195.3592994","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd International Symposium on High-Performance Parallel and Distributed Computing","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2304.12557","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101684490","display_name":"Boyuan Zhang","orcid":"https://orcid.org/0009-0003-8937-4067"},"institutions":[{"id":"https://openalex.org/I4210119109","display_name":"Indiana University Bloomington","ror":"https://ror.org/02k40bc56","country_code":"US","type":"education","lineage":["https://openalex.org/I4210119109","https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Boyuan Zhang","raw_affiliation_strings":["Indiana University, Bloomington, IN, USA"],"affiliations":[{"raw_affiliation_string":"Indiana University, Bloomington, IN, USA","institution_ids":["https://openalex.org/I4210119109"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064166827","display_name":"Jiannan Tian","orcid":"https://orcid.org/0000-0003-1101-9148"},"institutions":[{"id":"https://openalex.org/I4210119109","display_name":"Indiana University Bloomington","ror":"https://ror.org/02k40bc56","country_code":"US","type":"education","lineage":["https://openalex.org/I4210119109","https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiannan Tian","raw_affiliation_strings":["Indiana University, Bloomington, IN, USA"],"affiliations":[{"raw_affiliation_string":"Indiana University, Bloomington, IN, USA","institution_ids":["https://openalex.org/I4210119109"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103124363","display_name":"Sheng Di","orcid":"https://orcid.org/0000-0002-9935-5674"},"institutions":[{"id":"https://openalex.org/I1282105669","display_name":"Argonne National Laboratory","ror":"https://ror.org/05gvnxz63","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282105669","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sheng Di","raw_affiliation_strings":["Argonne National Laboratory, Lemont, IL, USA"],"affiliations":[{"raw_affiliation_string":"Argonne National Laboratory, Lemont, IL, USA","institution_ids":["https://openalex.org/I1282105669"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052001478","display_name":"Xiaodong Yu","orcid":"https://orcid.org/0000-0001-6244-1264"},"institutions":[{"id":"https://openalex.org/I1282105669","display_name":"Argonne National Laboratory","ror":"https://ror.org/05gvnxz63","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282105669","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaodong Yu","raw_affiliation_strings":["Argonne National Laboratory, Lemont, IL, USA"],"affiliations":[{"raw_affiliation_string":"Argonne National Laboratory, Lemont, IL, USA","institution_ids":["https://openalex.org/I1282105669"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073748933","display_name":"Yunhe Feng","orcid":"https://orcid.org/0000-0001-6577-227X"},"institutions":[{"id":"https://openalex.org/I123534392","display_name":"University of North Texas","ror":"https://ror.org/00v97ad02","country_code":"US","type":"education","lineage":["https://openalex.org/I123534392"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yunhe Feng","raw_affiliation_strings":["University of North Texas, Denton, TX, USA"],"affiliations":[{"raw_affiliation_string":"University of North Texas, Denton, TX, USA","institution_ids":["https://openalex.org/I123534392"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103064768","display_name":"Xin Liang","orcid":"https://orcid.org/0000-0002-0630-1600"},"institutions":[{"id":"https://openalex.org/I143302722","display_name":"University of Kentucky","ror":"https://ror.org/02k3smh20","country_code":"US","type":"education","lineage":["https://openalex.org/I143302722"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xin Liang","raw_affiliation_strings":["University of Kentucky, Lexington, KY, USA"],"affiliations":[{"raw_affiliation_string":"University of Kentucky, Lexington, KY, USA","institution_ids":["https://openalex.org/I143302722"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063703614","display_name":"Dingwen Tao","orcid":"https://orcid.org/0000-0001-5422-4497"},"institutions":[{"id":"https://openalex.org/I4210119109","display_name":"Indiana University Bloomington","ror":"https://ror.org/02k40bc56","country_code":"US","type":"education","lineage":["https://openalex.org/I4210119109","https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dingwen Tao","raw_affiliation_strings":["Indiana University, Bloomington, IN, USA"],"affiliations":[{"raw_affiliation_string":"Indiana University, Bloomington, IN, USA","institution_ids":["https://openalex.org/I4210119109"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046613458","display_name":"Franck Cappello","orcid":"https://orcid.org/0000-0002-7890-3934"},"institutions":[{"id":"https://openalex.org/I1282105669","display_name":"Argonne National Laboratory","ror":"https://ror.org/05gvnxz63","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282105669","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Franck Cappello","raw_affiliation_strings":["Argonne National Laboratory, Lemont, IL, USA"],"affiliations":[{"raw_affiliation_string":"Argonne National Laboratory, Lemont, IL, USA","institution_ids":["https://openalex.org/I1282105669"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5101684490"],"corresponding_institution_ids":["https://openalex.org/I4210119109"],"apc_list":null,"apc_paid":null,"fwci":3.2974,"has_fulltext":true,"cited_by_count":19,"citation_normalized_percentile":{"value":0.93498589,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"129","last_page":"142"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9997000098228455,"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"}},"topics":[{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9997000098228455,"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9983000159263611,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.9980999827384949,"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/lossy-compression","display_name":"Lossy compression","score":0.740106463432312},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7325266003608704},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.5786202549934387},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5779013633728027},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.5619819164276123},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.5479552149772644},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.5120856761932373},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.3879414498806},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.26122546195983887},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.09434443712234497}],"concepts":[{"id":"https://openalex.org/C165021410","wikidata":"https://www.wikidata.org/wiki/Q55564","display_name":"Lossy compression","level":2,"score":0.740106463432312},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7325266003608704},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.5786202549934387},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5779013633728027},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.5619819164276123},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.5479552149772644},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.5120856761932373},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.3879414498806},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.26122546195983887},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.09434443712234497}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3588195.3592994","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3588195.3592994","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd International Symposium on High-Performance Parallel and Distributed Computing","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2304.12557","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2304.12557","pdf_url":"https://arxiv.org/pdf/2304.12557","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:info:ark/67531/metadc2201584","is_oa":true,"landing_page_url":"https://digital.library.unt.edu/ark:/67531/metadc2201584/","pdf_url":"https://digital.library.unt.edu/ark:/67531/metadc2201584/m2/1/high_res_d/2304.12557.pdf","source":{"id":"https://openalex.org/S4306400792","display_name":"University of North Texas Digital Library (University of North Texas)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I123534392","host_organization_name":"University of North Texas","host_organization_lineage":["https://openalex.org/I123534392"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"HPDC '23: The 32nd International Symposium on High-Performance Parallel and Distributed Computing, June 16-23, 2023. Orlando, FL, United States","raw_type":"Article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2304.12557","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2304.12557","pdf_url":"https://arxiv.org/pdf/2304.12557","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy","score":0.5299999713897705}],"awards":[{"id":"https://openalex.org/G3719964770","display_name":null,"funder_award_id":"2003709,2104023,2303064,2247080,2312673","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"},{"id":"https://openalex.org/F4320309409","display_name":"Lilly Endowment","ror":"https://ror.org/00cpsd622"},{"id":"https://openalex.org/F4320332359","display_name":"Office of Science","ror":"https://ror.org/00mmn6b08"},{"id":"https://openalex.org/F4320332369","display_name":"National Nuclear Security Administration","ror":"https://ror.org/03sk1we31"},{"id":"https://openalex.org/F4320337506","display_name":"Advanced Scientific Computing Research","ror":"https://ror.org/0012c7r22"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4367176010.pdf"},"referenced_works_count":59,"referenced_works":["https://openalex.org/W164384110","https://openalex.org/W1528999146","https://openalex.org/W1777016212","https://openalex.org/W2024171325","https://openalex.org/W2040903332","https://openalex.org/W2052440657","https://openalex.org/W2060108852","https://openalex.org/W2107745473","https://openalex.org/W2115907784","https://openalex.org/W2142265837","https://openalex.org/W2168694323","https://openalex.org/W2214373473","https://openalex.org/W2486202470","https://openalex.org/W2562764966","https://openalex.org/W2625759119","https://openalex.org/W2808348679","https://openalex.org/W2883458770","https://openalex.org/W2886627854","https://openalex.org/W2899412261","https://openalex.org/W2912174957","https://openalex.org/W2959531572","https://openalex.org/W2971247417","https://openalex.org/W2990629325","https://openalex.org/W2999957348","https://openalex.org/W3041216812","https://openalex.org/W3042625184","https://openalex.org/W3043058721","https://openalex.org/W3043494828","https://openalex.org/W3094531373","https://openalex.org/W3096281486","https://openalex.org/W3106011734","https://openalex.org/W3118530556","https://openalex.org/W3137006678","https://openalex.org/W3138054712","https://openalex.org/W3173669904","https://openalex.org/W3176053424","https://openalex.org/W3177445289","https://openalex.org/W3205797155","https://openalex.org/W3212420620","https://openalex.org/W3213234881","https://openalex.org/W4221157832","https://openalex.org/W4226057480","https://openalex.org/W4226076355","https://openalex.org/W4226196214","https://openalex.org/W4230077428","https://openalex.org/W4283394632","https://openalex.org/W4285503881","https://openalex.org/W4287169010","https://openalex.org/W4287765354","https://openalex.org/W4302440534","https://openalex.org/W4307097729","https://openalex.org/W4311444970","https://openalex.org/W4311787046","https://openalex.org/W4321636572","https://openalex.org/W4394650336","https://openalex.org/W6654544606","https://openalex.org/W6660586467","https://openalex.org/W6722043901","https://openalex.org/W6780466743"],"related_works":["https://openalex.org/W1963859303","https://openalex.org/W2364044215","https://openalex.org/W2389600408","https://openalex.org/W240129890","https://openalex.org/W3048701459","https://openalex.org/W2149078538","https://openalex.org/W2370314112","https://openalex.org/W1912958759","https://openalex.org/W2792081825","https://openalex.org/W2893308117"],"abstract_inverted_index":{"Today's":[0],"large-scale":[1],"scientific":[2,35,78,169],"applications":[3,51],"running":[4],"on":[5,75,157,174],"high-performance":[6],"computing":[7],"(HPC)":[8],"systems":[9],"generate":[10],"vast":[11],"data":[12,15,36,79,132,146,229],"volumes.":[13],"Thus,":[14],"compression":[16,41,88,151,219],"is":[17],"becoming":[18],"a":[19,39,67,86,106,127,196],"critical":[20],"technique":[21],"to":[22,118,130],"mitigate":[23],"the":[24,116,175,204,227],"storage":[25],"burden":[26],"and":[27,43,69,97,143,163,189,216],"data-movement":[28],"cost.":[29],"However,":[30],"existing":[31],"lossy":[32,73],"compressors":[33],"for":[34,77,112,134],"cannot":[37],"achieve":[38],"high":[40],"ratio":[42,71,220],"throughput":[44],"simultaneously,":[45],"hindering":[46],"their":[47],"adoption":[48],"in":[49,62,115,137],"many":[50],"requiring":[52],"fast":[53,68,101],"compression,":[54],"such":[55],"as":[56],"in-memory":[57],"compression.":[58],"To":[59],"this":[60,63],"end,":[61],"work,":[64],"we":[65,83,104,154],"develop":[66],"high-":[70],"error-bounded":[72],"compressor":[74],"GPUs":[76,160],"(called":[80],"FZ-GPU).":[81],"Specifically,":[82],"first":[84],"design":[85],"new":[87],"pipeline":[89,117],"that":[90,179],"consists":[91],"of":[92,108,122,185,193,200,214,222],"fully":[93],"parallelized":[94],"quantization,":[95],"bitshuffle,":[96,138],"our":[98,201],"newly":[99],"designed":[100],"encoding.":[102],"Then,":[103],"propose":[105,126],"series":[107],"deep":[109],"architectural":[110],"optimizations":[111],"each":[113],"kernel":[114],"take":[119],"full":[120],"advantage":[121],"CUDA":[123],"architectures.":[124],"We":[125],"warp-level":[128],"optimization":[129],"avoid":[131],"conflicts":[133],"bit-wise":[135],"operations":[136],"maximize":[139],"shared":[140],"memory":[141],"utilization,":[142],"eliminate":[144],"unnecessary":[145],"movements":[147],"by":[148],"fusing":[149],"different":[150],"kernels.":[152],"Finally,":[153],"evaluate":[155],"FZ-GPU":[156,180,208],"two":[158],"NVIDIA":[159],"(i.e.,":[161],"A100":[162,176],"RTX":[164],"A4000)":[165],"using":[166],"six":[167],"representative":[168],"datasets":[170],"from":[171],"SDRBench.":[172],"Results":[173],"GPU":[177],"show":[178],"achieves":[181,210],"an":[182,190,211,217],"average":[183,191,212,218],"speedup":[184,192,213],"4.2\u00d7":[186],"over":[187,195,224],"cuSZ":[188],"37.0\u00d7":[194],"multi-threaded":[197],"CPU":[198],"implementation":[199],"algorithm":[202],"under":[203,226],"same":[205,228],"error":[206],"bound.":[207],"also":[209],"2.3\u00d7":[215],"improvement":[221],"2.0\u00d7":[223],"cuZFP":[225],"distortion.":[230]},"counts_by_year":[{"year":2025,"cited_by_count":12},{"year":2024,"cited_by_count":7}],"updated_date":"2026-04-06T07:47:59.780226","created_date":"2023-04-28T00:00:00"}