{"id":"https://openalex.org/W4416429688","doi":"https://doi.org/10.1109/iccad66269.2025.11240646","title":"GenomeDPU: A Cost-Effective In-Memory Data Processing Unit for GPU-based Genome Analysis","display_name":"GenomeDPU: A Cost-Effective In-Memory Data Processing Unit for GPU-based Genome Analysis","publication_year":2025,"publication_date":"2025-10-26","ids":{"openalex":"https://openalex.org/W4416429688","doi":"https://doi.org/10.1109/iccad66269.2025.11240646"},"language":null,"primary_location":{"id":"doi:10.1109/iccad66269.2025.11240646","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccad66269.2025.11240646","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/ACM International Conference On Computer Aided Design (ICCAD)","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/A5066388470","display_name":"Shouzhe Zhang","orcid":null},"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":"Shouzhe Zhang","raw_affiliation_strings":["University of North Texas,Department of Computer Science and Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of North Texas,Department of Computer Science and Engineering","institution_ids":["https://openalex.org/I123534392"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086201198","display_name":"Zhuren Liu","orcid":null},"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":"Zhuren Liu","raw_affiliation_strings":["University of North Texas,Department of Computer Science and Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of North Texas,Department of Computer Science and Engineering","institution_ids":["https://openalex.org/I123534392"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075897842","display_name":"Ruixiao Huang","orcid":"https://orcid.org/0009-0009-6633-893X"},"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":"Ruixiao Huang","raw_affiliation_strings":["University of North Texas,Department of Computer Science and Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of North Texas,Department of Computer Science and Engineering","institution_ids":["https://openalex.org/I123534392"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058413620","display_name":"Hui Zhao","orcid":"https://orcid.org/0000-0003-3683-4077"},"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":"Hui Zhao","raw_affiliation_strings":["University of North Texas,Department of Computer Science and Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of North Texas,Department of Computer Science and Engineering","institution_ids":["https://openalex.org/I123534392"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I123534392"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.2790565,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"9"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.37950000166893005,"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"}},"topics":[{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.37950000166893005,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.31709998846054077,"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/T12326","display_name":"Network Packet Processing and Optimization","score":0.10989999771118164,"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/pipeline","display_name":"Pipeline (software)","score":0.6786999702453613},{"id":"https://openalex.org/keywords/data-processing","display_name":"Data processing","score":0.5799999833106995},{"id":"https://openalex.org/keywords/graphics-processing-unit","display_name":"Graphics processing unit","score":0.5454000234603882},{"id":"https://openalex.org/keywords/genomics","display_name":"Genomics","score":0.5310999751091003},{"id":"https://openalex.org/keywords/dram","display_name":"Dram","score":0.5065000057220459},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.4115999937057495},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.38609999418258667},{"id":"https://openalex.org/keywords/parallel-processing","display_name":"Parallel processing","score":0.3774999976158142},{"id":"https://openalex.org/keywords/interface","display_name":"Interface (matter)","score":0.3594000041484833}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7865999937057495},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6786999702453613},{"id":"https://openalex.org/C138827492","wikidata":"https://www.wikidata.org/wiki/Q6661985","display_name":"Data processing","level":2,"score":0.5799999833106995},{"id":"https://openalex.org/C2779851693","wikidata":"https://www.wikidata.org/wiki/Q183484","display_name":"Graphics processing unit","level":2,"score":0.5454000234603882},{"id":"https://openalex.org/C189206191","wikidata":"https://www.wikidata.org/wiki/Q222046","display_name":"Genomics","level":4,"score":0.5310999751091003},{"id":"https://openalex.org/C7366592","wikidata":"https://www.wikidata.org/wiki/Q1255620","display_name":"Dram","level":2,"score":0.5065000057220459},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.4115999937057495},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.38609999418258667},{"id":"https://openalex.org/C106515295","wikidata":"https://www.wikidata.org/wiki/Q26806595","display_name":"Parallel processing","level":2,"score":0.3774999976158142},{"id":"https://openalex.org/C113843644","wikidata":"https://www.wikidata.org/wiki/Q901882","display_name":"Interface (matter)","level":4,"score":0.3594000041484833},{"id":"https://openalex.org/C2780165032","wikidata":"https://www.wikidata.org/wiki/Q16869822","display_name":"Energy consumption","level":2,"score":0.3580999970436096},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.32409998774528503},{"id":"https://openalex.org/C123593499","wikidata":"https://www.wikidata.org/wiki/Q6008583","display_name":"In-Memory Processing","level":5,"score":0.3199999928474426},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.3151000142097473},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.31310001015663147},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.30869999527931213},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.3041999936103821},{"id":"https://openalex.org/C112118009","wikidata":"https://www.wikidata.org/wiki/Q4925872","display_name":"Data processing system","level":2,"score":0.30230000615119934},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.2939999997615814},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.2930000126361847},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.28700000047683716},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.2793000042438507},{"id":"https://openalex.org/C2742236","wikidata":"https://www.wikidata.org/wiki/Q924713","display_name":"Efficient energy use","level":2,"score":0.26919999718666077},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.2662999927997589},{"id":"https://openalex.org/C2984118289","wikidata":"https://www.wikidata.org/wiki/Q29954","display_name":"Power consumption","level":3,"score":0.2605000138282776},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.25850000977516174},{"id":"https://openalex.org/C116409475","wikidata":"https://www.wikidata.org/wiki/Q1385056","display_name":"External Data Representation","level":2,"score":0.25}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iccad66269.2025.11240646","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccad66269.2025.11240646","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/ACM International Conference On Computer Aided Design (ICCAD)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W1828154403","https://openalex.org/W1844274058","https://openalex.org/W1975237352","https://openalex.org/W1981943579","https://openalex.org/W2061680337","https://openalex.org/W2086320398","https://openalex.org/W2086399100","https://openalex.org/W2104595023","https://openalex.org/W2121716038","https://openalex.org/W2171336109","https://openalex.org/W2466930524","https://openalex.org/W2513721464","https://openalex.org/W2560228154","https://openalex.org/W2605347906","https://openalex.org/W2725159389","https://openalex.org/W2766890412","https://openalex.org/W2790091177","https://openalex.org/W2944187830","https://openalex.org/W2947777875","https://openalex.org/W2962775754","https://openalex.org/W2979449748","https://openalex.org/W2981619930","https://openalex.org/W2983859156","https://openalex.org/W2988529598","https://openalex.org/W3042505432","https://openalex.org/W3043148535","https://openalex.org/W3102510044","https://openalex.org/W3105003914","https://openalex.org/W3128942747","https://openalex.org/W3192261267","https://openalex.org/W3202731849","https://openalex.org/W4214559301","https://openalex.org/W4226148550","https://openalex.org/W4234833047","https://openalex.org/W4245698512","https://openalex.org/W4283074266","https://openalex.org/W4309999671","https://openalex.org/W4311302642","https://openalex.org/W4381894561","https://openalex.org/W4386763533","https://openalex.org/W4391827215","https://openalex.org/W4401691725","https://openalex.org/W4406047553"],"related_works":[],"abstract_inverted_index":{"In":[0],"recent":[1],"years,":[2],"High-Throughput":[3],"Sequencing":[4],"(HTS)":[5],"technologies":[6],"have":[7,40],"revolutionized":[8],"the":[9,16,20,64,131,141,151,176],"research":[10],"field":[11],"of":[12,22,78],"genomics":[13,23,50],"analysis.":[14,35],"With":[15],"advances":[17],"in":[18,32,115],"HTS,":[19],"amount":[21],"data":[24,105,120],"has":[25,180],"grown":[26],"exponentially,":[27],"creating":[28],"a":[29,45,89,119,181],"major":[30,46],"challenge":[31],"efficient":[33],"genomic":[34],"Graphics":[36],"Processing":[37],"Units":[38],"(GPU)":[39],"been":[41],"widely":[42],"used":[43,112],"as":[44,195,197],"platform":[47],"to":[48,63,125,175],"accelerate":[49],"analysis,":[51],"but":[52],"their":[53],"massive":[54],"parallel":[55],"processing":[56,121,127,168],"power":[57,154],"cannot":[58],"be":[59],"fully":[60],"exploited":[61],"due":[62],"memory":[65,71,132,142],"bottleneck.":[66],"Our":[67,185],"investigation":[68],"shows":[69],"that":[70,94,162,189],"accesses":[72],"account":[73],"for":[74,82],"more":[75,155],"than":[76],"60%":[77],"GPU":[79,145,152],"pipeline":[80],"stalls":[81],"Genomics":[83],"applications.In":[84],"this":[85],"work,":[86],"we":[87],"propose":[88],"lightweight":[90],"process-in-memory":[91],"(PIM)":[92],"architecture":[93],"can":[95,138,191],"significantly":[96,139],"speed":[97],"up":[98],"GPU-based":[99],"genome":[100],"analysis":[101],"by":[102,194,203],"minimizing":[103],"off-chip":[104],"movement.":[106],"We":[107],"first":[108],"identify":[109],"several":[110],"commonly":[111],"memory-bound":[113],"functions":[114],"sequence":[116],"alignments.":[117],"Then,":[118],"unit":[122],"is":[123],"developed":[124],"integrate":[126],"capabilities":[128],"directly":[129],"within":[130],"system.":[133],"The":[134],"proposed":[135],"PIM":[136],"technique":[137],"reduce":[140,200],"transfer":[143],"between":[144],"processors":[146],"and":[147,166,179,199],"memory,":[148],"thereby":[149],"exploiting":[150],"computational":[153],"effectively.":[156],"Compared":[157],"with":[158],"other":[159],"Process-in-Memory":[160],"techniques":[161],"involve":[163],"complicated":[164],"design":[165],"memory-embedded":[167],"cores,":[169],"GenomeDPU":[170,190],"only":[171],"adds":[172],"simple":[173],"logics":[174],"DRAM":[177],"interface":[178],"much":[182,196],"smaller":[183],"overhead.":[184],"evaluation":[186],"results":[187],"show":[188],"improve":[192],"performance":[193],"8.37x":[198],"energy":[201],"consumption":[202],"55%.":[204]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-11-20T00:00:00"}