{"id":"https://openalex.org/W2963916847","doi":"https://doi.org/10.1145/3337821.3337888","title":"Massively Parallel ANS Decoding on GPUs","display_name":"Massively Parallel ANS Decoding on GPUs","publication_year":2019,"publication_date":"2019-07-25","ids":{"openalex":"https://openalex.org/W2963916847","doi":"https://doi.org/10.1145/3337821.3337888","mag":"2963916847"},"language":"en","primary_location":{"id":"doi:10.1145/3337821.3337888","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3337821.3337888","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 48th International Conference on Parallel Processing","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/A5017666635","display_name":"Andr\u00e9 Wei\u00dfenberger","orcid":null},"institutions":[{"id":"https://openalex.org/I114090438","display_name":"Goethe University Frankfurt","ror":"https://ror.org/04cvxnb49","country_code":"DE","type":"education","lineage":["https://openalex.org/I114090438"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Andr\u00e9 Wei\u00dfenberger","raw_affiliation_strings":["Johann Wolfgang Goethe University, Frankfurt am Main, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johann Wolfgang Goethe University, Frankfurt am Main, Germany","institution_ids":["https://openalex.org/I114090438"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020388832","display_name":"Bertil Schmidt","orcid":"https://orcid.org/0000-0003-2597-8331"},"institutions":[{"id":"https://openalex.org/I197323543","display_name":"Johannes Gutenberg University Mainz","ror":"https://ror.org/023b0x485","country_code":"DE","type":"education","lineage":["https://openalex.org/I197323543"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Bertil Schmidt","raw_affiliation_strings":["Institute of Computer Science, Johannes Gutenberg University, Mainz, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Computer Science, Johannes Gutenberg University, Mainz, Germany","institution_ids":["https://openalex.org/I197323543"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"10"},"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/T11321","display_name":"Error Correcting Code Techniques","score":0.9952999949455261,"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9909999966621399,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.884164571762085},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6435806751251221},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5899533033370972},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.5883845090866089},{"id":"https://openalex.org/keywords/massively-parallel","display_name":"Massively parallel","score":0.5835245847702026},{"id":"https://openalex.org/keywords/simd","display_name":"SIMD","score":0.5829517841339111},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.5518985390663147},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.5469350218772888},{"id":"https://openalex.org/keywords/thread","display_name":"Thread (computing)","score":0.4805215299129486},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.44202345609664917},{"id":"https://openalex.org/keywords/graphics-processing-unit","display_name":"Graphics processing unit","score":0.4141917824745178},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.17977580428123474},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.17707842588424683},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.1454039216041565},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.08106279373168945}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.884164571762085},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6435806751251221},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5899533033370972},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.5883845090866089},{"id":"https://openalex.org/C190475519","wikidata":"https://www.wikidata.org/wiki/Q544384","display_name":"Massively parallel","level":2,"score":0.5835245847702026},{"id":"https://openalex.org/C150552126","wikidata":"https://www.wikidata.org/wiki/Q339387","display_name":"SIMD","level":2,"score":0.5829517841339111},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.5518985390663147},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.5469350218772888},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.4805215299129486},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.44202345609664917},{"id":"https://openalex.org/C2779851693","wikidata":"https://www.wikidata.org/wiki/Q183484","display_name":"Graphics processing unit","level":2,"score":0.4141917824745178},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.17977580428123474},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.17707842588424683},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.1454039216041565},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.08106279373168945}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3337821.3337888","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3337821.3337888","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 48th International Conference on Parallel Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W566388058","https://openalex.org/W1577505202","https://openalex.org/W1874489690","https://openalex.org/W2066637933","https://openalex.org/W2100981650","https://openalex.org/W2123243337","https://openalex.org/W2411127466","https://openalex.org/W2549625900","https://openalex.org/W2554502527","https://openalex.org/W2887854925","https://openalex.org/W2899833479"],"related_works":["https://openalex.org/W2255048617","https://openalex.org/W2064856044","https://openalex.org/W1512604874","https://openalex.org/W2092102951","https://openalex.org/W2140636994","https://openalex.org/W2154638730","https://openalex.org/W2158982898","https://openalex.org/W2142204081","https://openalex.org/W2119534391","https://openalex.org/W1966576946"],"abstract_inverted_index":{"In":[0,19,124],"recent":[1],"years,":[2],"graphics":[3],"processors":[4],"have":[5,111],"enabled":[6],"significant":[7],"advances":[8],"in":[9,69,121],"the":[10,54,75,129],"fields":[11],"of":[12,24,28,42,53,162],"big":[13],"data":[14,29,63],"and":[15,30,101,179],"streamed":[16],"deep":[17,47],"learning.":[18],"order":[20],"to":[21,31,91,136,164,171,181],"keep":[22],"control":[23],"rapidly":[25],"growing":[26],"amounts":[27],"achieve":[32],"sufficient":[33],"throughput":[34],"rates,":[35],"compression":[36,96,100],"features":[37],"are":[38],"a":[39,67,88,143,174],"key":[40],"part":[41],"many":[43],"applications":[44],"including":[45],"popular":[46],"learning":[48],"pipelines.":[49],"However,":[50,115],"as":[51],"most":[52],"respective":[55],"APIs":[56],"rely":[57],"on":[58,109,139,142,150],"CPU-based":[59],"preprocessing":[60],"for":[61,77,81,105],"decoding,":[62],"decompression":[64,102,108],"frequently":[65],"becomes":[66],"bottleneck":[68],"accelerated":[70],"compute":[71],"systems.":[72],"This":[73],"establishes":[74],"need":[76],"efficient":[78],"GPU-based":[79],"solutions":[80],"decompression.":[82],"Asymmetric":[83],"numeral":[84],"systems":[85],"(ANS)":[86],"represent":[87],"modern":[89],"approach":[90,135],"entropy":[92,185],"coding,":[93],"combining":[94],"superior":[95],"results":[97],"with":[98],"high":[99,175],"speeds.":[103],"Concepts":[104],"parallelizing":[106],"ANS":[107,137],"GPUs":[110,154],"been":[112],"published":[113],"recently.":[114],"they":[116],"only":[117],"exhibit":[118],"limited":[119],"scalability":[120],"practical":[122],"applications.":[123],"this":[125],"paper,":[126],"we":[127],"present":[128],"first":[130],"massively":[131],"parallel,":[132],"arbitrarily":[133],"scalable":[134],"decoding":[138],"GPUs,":[140],"based":[141],"novel":[144],"overflow":[145],"pattern.":[146],"Our":[147,187],"performance":[148,176],"evaluation":[149],"three":[151],"different":[152],"CUDA-enabled":[153],"(V100,":[155],"TITAN":[156],"V,":[157],"GTX":[158],"1080)":[159],"demonstrates":[160],"speedups":[161],"up":[163,170,180],"17":[165],"over":[166,173,183],"64":[167],"CPU":[168],"threads,":[169],"31":[172],"SIMD-based":[177],"solution,":[178],"39":[182],"Zstandard's":[184],"codec.":[186],"implementation":[188],"is":[189],"publicly":[190],"available":[191],"at":[192],"https://github.com/weissenberger/multians.":[193]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}