{"id":"https://openalex.org/W4376864771","doi":"https://doi.org/10.1145/3577193.3593706","title":"GPULZ: Optimizing LZSS Lossless Compression for Multi-byte Data on Modern GPUs","display_name":"GPULZ: Optimizing LZSS Lossless Compression for Multi-byte Data on Modern GPUs","publication_year":2023,"publication_date":"2023-06-20","ids":{"openalex":"https://openalex.org/W4376864771","doi":"https://doi.org/10.1145/3577193.3593706"},"language":"en","primary_location":{"id":"doi:10.1145/3577193.3593706","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3577193.3593706","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 37th International Conference on Supercomputing","raw_type":"proceedings-article"},"type":"preprint","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/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, United States"],"affiliations":[{"raw_affiliation_string":"Indiana University, Bloomington, IN, United States","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, United States"],"affiliations":[{"raw_affiliation_string":"Argonne National Laboratory, Lemont, IL, United States","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, United States"],"affiliations":[{"raw_affiliation_string":"Argonne National Laboratory, Lemont, IL, United States","institution_ids":["https://openalex.org/I1282105669"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044461835","display_name":"Martin Swany","orcid":"https://orcid.org/0000-0001-8028-1161"},"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":"Martin Swany","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/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, United States"],"affiliations":[{"raw_affiliation_string":"Indiana University, Bloomington, IN, United States","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, United States of America"],"affiliations":[{"raw_affiliation_string":"Argonne National Laboratory, Lemont, IL, United States of America","institution_ids":["https://openalex.org/I1282105669"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5101684490"],"corresponding_institution_ids":["https://openalex.org/I4210119109"],"apc_list":null,"apc_paid":null,"fwci":3.57620043,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.91322484,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"348","last_page":"359"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9998000264167786,"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":0.9998000264167786,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9983000159263611,"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/T12326","display_name":"Network Packet Processing and Optimization","score":0.9979000091552734,"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/computer-science","display_name":"Computer science","score":0.8880497217178345},{"id":"https://openalex.org/keywords/byte","display_name":"Byte","score":0.7312541007995605},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7004779577255249},{"id":"https://openalex.org/keywords/lossless-compression","display_name":"Lossless compression","score":0.6413673162460327},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.5722300410270691},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.5256146788597107},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.48459088802337646},{"id":"https://openalex.org/keywords/high-memory","display_name":"High memory","score":0.47171562910079956},{"id":"https://openalex.org/keywords/data-structure","display_name":"Data structure","score":0.4347071051597595},{"id":"https://openalex.org/keywords/graphics-processing-unit","display_name":"Graphics processing unit","score":0.422067254781723},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.25426170229911804},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.22317048907279968},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.10385653376579285}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8880497217178345},{"id":"https://openalex.org/C43364308","wikidata":"https://www.wikidata.org/wiki/Q8799","display_name":"Byte","level":2,"score":0.7312541007995605},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7004779577255249},{"id":"https://openalex.org/C81081738","wikidata":"https://www.wikidata.org/wiki/Q55542","display_name":"Lossless compression","level":3,"score":0.6413673162460327},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.5722300410270691},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.5256146788597107},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.48459088802337646},{"id":"https://openalex.org/C2781357197","wikidata":"https://www.wikidata.org/wiki/Q5757597","display_name":"High memory","level":2,"score":0.47171562910079956},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.4347071051597595},{"id":"https://openalex.org/C2779851693","wikidata":"https://www.wikidata.org/wiki/Q183484","display_name":"Graphics processing unit","level":2,"score":0.422067254781723},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.25426170229911804},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.22317048907279968},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.10385653376579285}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3577193.3593706","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3577193.3593706","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 37th International Conference on Supercomputing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2658683238","display_name":null,"funder_award_id":"2003709","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G2902793134","display_name":null,"funder_award_id":"2312673","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4530329298","display_name":null,"funder_award_id":"2247080","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6618524086","display_name":null,"funder_award_id":"2303064","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7379358484","display_name":null,"funder_award_id":"2104023","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"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W1595783387","https://openalex.org/W1773069773","https://openalex.org/W1972971542","https://openalex.org/W1991300616","https://openalex.org/W2022126655","https://openalex.org/W2024171325","https://openalex.org/W2028094098","https://openalex.org/W2036481648","https://openalex.org/W2052440657","https://openalex.org/W2060108852","https://openalex.org/W2076799934","https://openalex.org/W2100981650","https://openalex.org/W2107745473","https://openalex.org/W2111221242","https://openalex.org/W2128029258","https://openalex.org/W2562764966","https://openalex.org/W2625759119","https://openalex.org/W2959531572","https://openalex.org/W2971247417","https://openalex.org/W3007005426","https://openalex.org/W3043058721","https://openalex.org/W3043494828","https://openalex.org/W3083639242","https://openalex.org/W3106011734","https://openalex.org/W3137006678","https://openalex.org/W3141728994","https://openalex.org/W3171200431","https://openalex.org/W3174986514","https://openalex.org/W3176053424","https://openalex.org/W3205797155","https://openalex.org/W3212420620","https://openalex.org/W4207012351","https://openalex.org/W4225425598","https://openalex.org/W4226196214","https://openalex.org/W4233358539","https://openalex.org/W4244332584","https://openalex.org/W4253696084","https://openalex.org/W4254155307","https://openalex.org/W4285503881","https://openalex.org/W4312508241","https://openalex.org/W4323061066"],"related_works":["https://openalex.org/W2119534391","https://openalex.org/W1966576946","https://openalex.org/W2503137108","https://openalex.org/W2023770367","https://openalex.org/W2062253548","https://openalex.org/W2393490604","https://openalex.org/W2393707426","https://openalex.org/W2030707850","https://openalex.org/W2146871484","https://openalex.org/W2794923745"],"abstract_inverted_index":{"Today's":[0],"graphics":[1],"processing":[2],"unit":[3],"(GPU)":[4],"applications":[5,69],"produce":[6,70],"vast":[7],"volumes":[8],"of":[9,62,111,122,211],"data,":[10],"which":[11],"are":[12],"challenging":[13],"to":[14,27,58,149,156,175,200,226,233,239],"store":[15],"and":[16,32,128,152,163,166,179,217,231],"transfer":[17],"efficiently.":[18],"Thus,":[19],"data":[20,72,86,158,198],"compression":[21,82,102,236],"is":[22,36,114],"becoming":[23],"a":[24,98],"critical":[25],"technique":[26],"mitigate":[28],"the":[29,37,59,63,79],"storage":[30],"burden":[31],"communication":[33],"cost.":[34],"LZSS":[35,51,64,81,101],"core":[38],"algorithm":[39],"in":[40,92],"many":[41,67],"widely":[42],"used":[43],"compressors,":[44],"such":[45,190],"as":[46,87,191],"Deflate.":[47],"However,":[48],"existing":[49,123,169],"GPU-based":[50],"compressors":[52,125],"suffer":[53],"from":[54,146],"low":[55],"throughput":[56],"due":[57],"sequential":[60],"nature":[61],"algorithm.":[65],"Moreover,":[66],"GPU":[68,202],"multi-byte":[71,107,173],"(e.g.,":[73],"int16/int32":[74],"index,":[75],"floating-point":[76],"numbers),":[77],"while":[78],"current":[80],"only":[83],"takes":[84],"single-byte":[85],"input.":[88],"To":[89],"this":[90,93],"end,":[91],"work,":[94],"we":[95,117,134,141,185,205],"propose":[96,135],"GPULZ,":[97],"highly":[99],"efficient":[100],"on":[103,208,229],"modern":[104],"GPUs":[105,127],"for":[106,126,172],"data.":[108],"The":[109],"contribution":[110],"our":[112],"work":[113],"fourfold:":[115],"First,":[116],"perform":[118,186],"an":[119],"in-depth":[120],"analysis":[121],"LZ":[124],"investigate":[129],"their":[130],"main":[131,137],"issues.":[132],"Then,":[133],"two":[136,150],"algorithm-level":[138],"optimizations.":[139],"Specifically,":[140],"(1)":[142],"change":[143],"prefix":[144],"sum":[145],"one":[147],"pass":[148],"passes":[151],"fuse":[153],"multiple":[154],"kernels":[155],"reduce":[157,176],"movement":[159],"between":[160],"shared":[161,193],"memory":[162,194],"global":[164],"memory,":[165],"(2)":[167],"optimize":[168],"pattern-matching":[170],"approach":[171],"symbols":[174],"computation":[177],"complexity":[178],"explore":[180],"longer":[181],"repeated":[182],"patterns.":[183],"Third,":[184],"architectural":[187],"performance":[188],"optimizations,":[189],"maximizing":[192],"utilization":[195],"by":[196],"adapting":[197],"partitions":[199],"different":[201],"architectures.":[203],"Finally,":[204],"evaluate":[206],"GPULZ":[207,223],"six":[209],"datasets":[210],"various":[212],"types":[213],"with":[214],"NVIDIA":[215],"A100":[216],"A4000":[218,230],"GPUs.":[219],"Results":[220],"show":[221],"that":[222],"achieves":[224],"up":[225,232],"272.1X":[227],"speedup":[228],"1.4X":[234],"higher":[235],"ratio":[237],"compared":[238],"state-of-the-art":[240],"solutions.":[241]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":7}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}