{"id":"https://openalex.org/W4401408758","doi":"https://doi.org/10.1145/3673038.3673067","title":"Massively Parallel Inverse Block-sorting Transforms for bzip2 Decompression on GPUs","display_name":"Massively Parallel Inverse Block-sorting Transforms for bzip2 Decompression on GPUs","publication_year":2024,"publication_date":"2024-08-08","ids":{"openalex":"https://openalex.org/W4401408758","doi":"https://doi.org/10.1145/3673038.3673067"},"language":"en","primary_location":{"id":"doi:10.1145/3673038.3673067","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3673038.3673067","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3673038.3673067","source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 53rd International Conference on Parallel Processing","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3673038.3673067","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5017666635","display_name":"Andr\u00e9 Wei\u00dfenberger","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Andr\u00e9 Wei\u00dfenberger","raw_affiliation_strings":["Johannes Gutenberg University, Germany"],"raw_orcid":"https://orcid.org/0009-0004-4823-8162","affiliations":[{"raw_affiliation_string":"Johannes Gutenberg University, Germany","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020388832","display_name":"Bertil Schmidt","orcid":"https://orcid.org/0000-0003-2597-8331"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bertil Schmidt","raw_affiliation_strings":["Johannes Gutenberg University, Germany"],"raw_orcid":"https://orcid.org/0000-0003-2597-8331","affiliations":[{"raw_affiliation_string":"Johannes Gutenberg University, Germany","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"856","last_page":"865"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9991999864578247,"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":0.9991999864578247,"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":0.9965000152587891,"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"}},{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9958999752998352,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/massively-parallel","display_name":"Massively parallel","score":0.799676775932312},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7403355240821838},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.691243588924408},{"id":"https://openalex.org/keywords/sorting","display_name":"Sorting","score":0.615324854850769},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.5491381883621216},{"id":"https://openalex.org/keywords/inverse","display_name":"Inverse","score":0.49831271171569824},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.4893640875816345},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.3532131314277649},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.15615719556808472},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08571881055831909},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.07130759954452515}],"concepts":[{"id":"https://openalex.org/C190475519","wikidata":"https://www.wikidata.org/wiki/Q544384","display_name":"Massively parallel","level":2,"score":0.799676775932312},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7403355240821838},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.691243588924408},{"id":"https://openalex.org/C111696304","wikidata":"https://www.wikidata.org/wiki/Q2303697","display_name":"Sorting","level":2,"score":0.615324854850769},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.5491381883621216},{"id":"https://openalex.org/C207467116","wikidata":"https://www.wikidata.org/wiki/Q4385666","display_name":"Inverse","level":2,"score":0.49831271171569824},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.4893640875816345},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.3532131314277649},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.15615719556808472},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08571881055831909},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.07130759954452515},{"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:10.1145/3673038.3673067","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3673038.3673067","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3673038.3673067","source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 53rd International Conference on Parallel Processing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3673038.3673067","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3673038.3673067","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3673038.3673067","source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 53rd International Conference on Parallel Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4401408758.pdf"},"referenced_works_count":20,"referenced_works":["https://openalex.org/W1621170073","https://openalex.org/W1964225906","https://openalex.org/W2024171325","https://openalex.org/W2060108852","https://openalex.org/W2066637933","https://openalex.org/W2087217176","https://openalex.org/W2087977509","https://openalex.org/W2100981650","https://openalex.org/W2158125089","https://openalex.org/W2292188194","https://openalex.org/W2335962142","https://openalex.org/W2747704798","https://openalex.org/W2887854925","https://openalex.org/W2950858207","https://openalex.org/W2963235000","https://openalex.org/W2963916847","https://openalex.org/W3048040256","https://openalex.org/W3176053424","https://openalex.org/W3210465286","https://openalex.org/W4285503881"],"related_works":["https://openalex.org/W3189307731","https://openalex.org/W2167527468","https://openalex.org/W2949962288","https://openalex.org/W2364686214","https://openalex.org/W1428699136","https://openalex.org/W1998560227","https://openalex.org/W2586370661","https://openalex.org/W2314053740","https://openalex.org/W2960681633","https://openalex.org/W1970113381"],"abstract_inverted_index":{"Lossless":[0],"data":[1,11],"compression":[2,43,53],"has":[3],"evolved":[4],"into":[5],"an":[6,157],"indispensable":[7],"tool":[8],"for":[9,80,105,123,141,151],"reducing":[10],"transfer":[12],"times":[13],"in":[14],"heterogeneous":[15],"systems.":[16],"However,":[17,50],"performing":[18],"decompression":[19,117,161],"on":[20,57,74,93,102,156,173],"host":[21],"systems":[22],"can":[23],"create":[24],"performance":[25],"bottlenecks.":[26],"Accelerator":[27],"libraries,":[28],"such":[29],"as":[30,119],"nvCOMP,":[31],"address":[32],"this":[33],"problem":[34],"by":[35],"providing":[36],"custom":[37],"GPU-enabled":[38,115],"versions":[39],"of":[40,83,99,132,146,162,167],"some":[41],"general-purpose":[42],"methods,":[44],"including":[45],"Snappy,":[46],"ZStandard":[47],"and":[48,88,143,154],"gzip.":[49],"popular":[51],"bzip-like":[52],"schemes,":[54],"which":[55,95],"rely":[56],"block-sorting":[58],"transforms":[59],"have":[60],"not":[61],"yet":[62],"been":[63],"integrated":[64],"since":[65],"their":[66],"fine-grained":[67,81],"parallelization":[68,82],"is":[69,171],"challenging.":[70],"With":[71],"a":[72,120,137,165,174],"focus":[73],"decompression,":[75],"we":[76,110],"propose":[77],"novel":[78],"techniques":[79],"inverse":[84,89],"Burrows-Wheeler":[85],"transform":[86,92],"(iBWT)":[87],"Move-to-Front":[90],"(iMTF)":[91],"GPUs,":[94],"enable":[96],"efficient":[97],"processing":[98],"bzip2-based":[100],"archives":[101],"CUDA-enabled":[103],"accelerators":[104],"the":[106,112,124],"first":[107,113],"time.":[108],"Consequently,":[109],"present":[111],"fully":[114],"bzip2":[116,163],"pipeline":[118],"use":[121],"case":[122],"proposed":[125],"algorithms.":[126],"Our":[127],"experimental":[128],"results":[129],"reveal":[130],"speedups":[131],"up":[133,147],"to":[134,148],"6.1x":[135],"over":[136,168],"multicore":[138],"CPU":[139],"implementation":[140],"iBWT,":[142],"throughput":[144,166],"rates":[145],"2400":[149],"MB/s":[150],"combined":[152],"iBWT":[153],"iMTF":[155],"A100":[158],"GPU.":[159],"For":[160],"archives,":[164],"11.62":[169],"GB/s":[170],"achieved":[172],"DGX":[175],"H100":[176],"server.":[177]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-19T07:52:34.831488","created_date":"2025-10-10T00:00:00"}