{"id":"https://openalex.org/W7125599619","doi":"https://doi.org/10.1109/tcbbio.2026.3657252","title":"gpuPairHMM: High-Speed Pair-HMM Forward Algorithm for DNA Variant Calling on GPUs","display_name":"gpuPairHMM: High-Speed Pair-HMM Forward Algorithm for DNA Variant Calling on GPUs","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7125599619","doi":"https://doi.org/10.1109/tcbbio.2026.3657252","pmid":"https://pubmed.ncbi.nlm.nih.gov/41576120"},"language":"en","primary_location":{"id":"doi:10.1109/tcbbio.2026.3657252","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcbbio.2026.3657252","pdf_url":null,"source":{"id":"https://openalex.org/S5407042751","display_name":"IEEE Transactions on Computational Biology and Bioinformatics","issn_l":"2998-4165","issn":["2998-4165"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Computational Biology and Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5112780307","display_name":"Bertil Schmidt","orcid":null},"institutions":[{"id":"https://openalex.org/I4210094062","display_name":"University Medical Center of the Johannes Gutenberg University Mainz","ror":"https://ror.org/00q1fsf04","country_code":"DE","type":"healthcare","lineage":["https://openalex.org/I4210094062"]},{"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":true,"raw_author_name":"Bertil Schmidt","raw_affiliation_strings":["Insitute of Computer Science, Johannes Gutenberg University, Germany"],"affiliations":[{"raw_affiliation_string":"Insitute of Computer Science, Johannes Gutenberg University, Germany","institution_ids":["https://openalex.org/I197323543","https://openalex.org/I4210094062"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075168236","display_name":"Felix Kallenborn","orcid":"https://orcid.org/0000-0003-4516-6357"},"institutions":[{"id":"https://openalex.org/I4210094062","display_name":"University Medical Center of the Johannes Gutenberg University Mainz","ror":"https://ror.org/00q1fsf04","country_code":"DE","type":"healthcare","lineage":["https://openalex.org/I4210094062"]},{"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":"Felix Kallenborn","raw_affiliation_strings":["Insitute of Computer Science, Johannes Gutenberg University, Germany"],"affiliations":[{"raw_affiliation_string":"Insitute of Computer Science, Johannes Gutenberg University, Germany","institution_ids":["https://openalex.org/I197323543","https://openalex.org/I4210094062"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054938143","display_name":"Alexander Wichmann","orcid":"https://orcid.org/0000-0002-6138-6475"},"institutions":[{"id":"https://openalex.org/I4210094062","display_name":"University Medical Center of the Johannes Gutenberg University Mainz","ror":"https://ror.org/00q1fsf04","country_code":"DE","type":"healthcare","lineage":["https://openalex.org/I4210094062"]},{"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":"Alexander Wichmann","raw_affiliation_strings":["Insitute of Computer Science, Johannes Gutenberg University, Germany"],"affiliations":[{"raw_affiliation_string":"Insitute of Computer Science, Johannes Gutenberg University, Germany","institution_ids":["https://openalex.org/I197323543","https://openalex.org/I4210094062"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072699100","display_name":"Alejandro Chac\u00f3n","orcid":"https://orcid.org/0000-0001-8851-7618"},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alejandro Chacon","raw_affiliation_strings":["NVIDIA Corporation, Santa Clara, USA"],"affiliations":[{"raw_affiliation_string":"NVIDIA Corporation, Santa Clara, USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027561629","display_name":"Christian Hundt","orcid":"https://orcid.org/0000-0002-7995-1858"},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Christian Hundt","raw_affiliation_strings":["NVIDIA Corporation, Santa Clara, USA"],"affiliations":[{"raw_affiliation_string":"NVIDIA Corporation, Santa Clara, USA","institution_ids":["https://openalex.org/I4210127875"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5112780307"],"corresponding_institution_ids":["https://openalex.org/I4210094062","https://openalex.org/I197323543"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.97062399,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":"PP","issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10261","display_name":"Genetic Associations and Epidemiology","score":0.2620296776294708,"subfield":{"id":"https://openalex.org/subfields/1311","display_name":"Genetics"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T10261","display_name":"Genetic Associations and Epidemiology","score":0.2620296776294708,"subfield":{"id":"https://openalex.org/subfields/1311","display_name":"Genetics"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.18731148540973663,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10044","display_name":"Protein Structure and Dynamics","score":0.10691330581903458,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.534782350063324},{"id":"https://openalex.org/keywords/implementation","display_name":"Implementation","score":0.5087271928787231},{"id":"https://openalex.org/keywords/massively-parallel","display_name":"Massively parallel","score":0.46946707367897034},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4408935308456421},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.4228103756904602},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.4127674698829651},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.411982923746109},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.4094164967536926},{"id":"https://openalex.org/keywords/volume","display_name":"Volume (thermodynamics)","score":0.3934079706668854},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.3826731741428375}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8288799524307251},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7026916742324829},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.534782350063324},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.5087271928787231},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4743584394454956},{"id":"https://openalex.org/C190475519","wikidata":"https://www.wikidata.org/wiki/Q544384","display_name":"Massively parallel","level":2,"score":0.46946707367897034},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4408935308456421},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4228103756904602},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.4127674698829651},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.411982923746109},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.4094164967536926},{"id":"https://openalex.org/C20556612","wikidata":"https://www.wikidata.org/wiki/Q4469374","display_name":"Volume (thermodynamics)","level":2,"score":0.3934079706668854},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.3826731741428375},{"id":"https://openalex.org/C2781039887","wikidata":"https://www.wikidata.org/wiki/Q1391724","display_name":"Factor (programming language)","level":2,"score":0.36638161540031433},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.3635559678077698},{"id":"https://openalex.org/C129844170","wikidata":"https://www.wikidata.org/wiki/Q41299","display_name":"Quadratic equation","level":2,"score":0.3393166959285736},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.3338358700275421},{"id":"https://openalex.org/C150552126","wikidata":"https://www.wikidata.org/wiki/Q339387","display_name":"SIMD","level":2,"score":0.32282236218452454},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.3138622045516968},{"id":"https://openalex.org/C120373497","wikidata":"https://www.wikidata.org/wiki/Q1087987","display_name":"Parallel algorithm","level":2,"score":0.30478546023368835},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.2978551387786865},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.296892911195755},{"id":"https://openalex.org/C79470037","wikidata":"https://www.wikidata.org/wiki/Q279748","display_name":"Out-of-core algorithm","level":2,"score":0.29408907890319824},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.29168397188186646},{"id":"https://openalex.org/C2781357197","wikidata":"https://www.wikidata.org/wiki/Q5757597","display_name":"High memory","level":2,"score":0.29004621505737305},{"id":"https://openalex.org/C106515295","wikidata":"https://www.wikidata.org/wiki/Q26806595","display_name":"Parallel processing","level":2,"score":0.2881176471710205},{"id":"https://openalex.org/C311688","wikidata":"https://www.wikidata.org/wiki/Q2393193","display_name":"Time complexity","level":2,"score":0.2778233587741852},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.27428165078163147},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.2686581611633301},{"id":"https://openalex.org/C501734568","wikidata":"https://www.wikidata.org/wiki/Q42918","display_name":"Mutation","level":3,"score":0.26582127809524536},{"id":"https://openalex.org/C51679486","wikidata":"https://www.wikidata.org/wiki/Q380546","display_name":"DNA sequencing","level":3,"score":0.2628636062145233},{"id":"https://openalex.org/C106516650","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm design","level":2,"score":0.2538723647594452},{"id":"https://openalex.org/C111696304","wikidata":"https://www.wikidata.org/wiki/Q2303697","display_name":"Sorting","level":2,"score":0.25194841623306274}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tcbbio.2026.3657252","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcbbio.2026.3657252","pdf_url":null,"source":{"id":"https://openalex.org/S5407042751","display_name":"IEEE Transactions on Computational Biology and Bioinformatics","issn_l":"2998-4165","issn":["2998-4165"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Computational Biology and Bioinformatics","raw_type":"journal-article"},{"id":"pmid:41576120","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41576120","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on computational biology and bioinformatics","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0],"continually":[1],"increasing":[2],"volume":[3],"of":[4,17,21,62,80,144,166],"DNA":[5,37],"sequence":[6],"data":[7],"has":[8],"resulted":[9],"in":[10,36],"a":[11,33,106,164],"growing":[12],"demand":[13],"for":[14,94,111],"fast":[15],"implementations":[16,157],"core":[18],"algorithms.":[19],"Computation":[20],"pairwise":[22],"alignments":[23],"between":[24],"candidate":[25],"haplotypes":[26],"and":[27,58,121,131,161,171],"sequencing":[28],"reads":[29],"using":[30,74],"Pair-HMMs":[31],"is":[32,175],"key":[34],"component":[35],"variant":[38],"calling":[39],"tools":[40],"such":[41],"as":[42],"the":[43,59,75,92,112],"GATK":[44],"HaplotypeCaller":[45],"but":[46],"can":[47],"be":[48,65],"highly":[49],"time":[50,56],"consuming":[51],"due":[52],"to":[53,64,70],"its":[54],"quadratic":[55],"complexity":[57],"large":[60],"number":[61],"pairs":[63],"aligned.":[66],"Unfortunately,":[67],"previous":[68],"approaches":[69],"accelerate":[71],"this":[72,100],"task":[73],"massively":[76],"parallel":[77],"processing":[78],"capabilities":[79],"modern":[81,145],"GPUs":[82,147],"are":[83],"limited":[84],"by":[85,102,126,163],"inefficient":[86],"memory":[87,129],"access":[88],"schemes.":[89],"This":[90],"established":[91],"need":[93,101],"significantly":[95],"faster":[96],"solutions.":[97],"We":[98,133],"address":[99],"presenting":[103],"gpuPairHMM":[104,174],"-":[105],"novel":[107],"GPU-based":[108],"parallelization":[109],"scheme":[110],"dynamic-programming":[113],"based":[114,118],"Pair-HMM":[115],"forward":[116],"algorithm":[117],"on":[119,141,158],"wavefronts":[120],"warp-shuffles.":[122],"It":[123,153],"gains":[124],"efficiency":[125],"minimizing":[127],"both":[128],"accesses":[130],"instructions.":[132],"show":[134],"that":[135],"our":[136],"approach":[137],"achieves":[138],"close-to-peak":[139],"performance":[140],"several":[142],"generations":[143],"CUDA-enabled":[146],"(Volta,":[148],"Ampere,":[149],"Ada,":[150],"Hopper,":[151],"Blackwell).":[152],"also":[154],"outperforms":[155],"prior":[156],"GPUs,":[159],"CPUs,":[160],"FPGAs":[162],"factor":[165],"at":[167,178],"least":[168],"11.7,":[169],"14.2,":[170],"19.8,":[172],"respectively.":[173],"publicly":[176],"available":[177],"https://github.com/asbschmidt/gpuPairHMM.":[179]},"counts_by_year":[],"updated_date":"2026-01-27T00:41:06.130819","created_date":"2026-01-25T00:00:00"}