{"id":"https://openalex.org/W4415314965","doi":"https://doi.org/10.48550/arxiv.2509.12232","title":"Towards High-Performance and Portable Molecular Docking on CPUs through Vectorization","display_name":"Towards High-Performance and Portable Molecular Docking on CPUs through Vectorization","publication_year":2025,"publication_date":"2025-09-08","ids":{"openalex":"https://openalex.org/W4415314965","doi":"https://doi.org/10.48550/arxiv.2509.12232"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2509.12232","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2509.12232","pdf_url":"https://arxiv.org/pdf/2509.12232","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2509.12232","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5055263185","display_name":"Gianmarco Accordi","orcid":"https://orcid.org/0000-0001-8023-2108","observed_orcids":["https://orcid.org/0000-0001-8023-2108"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Accordi, Gianmarco","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039069961","display_name":"Jens Domke","orcid":"https://orcid.org/0000-0002-5343-414X","observed_orcids":["https://orcid.org/0000-0002-5343-414X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Domke, Jens","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079210568","display_name":"Theresa Pollinger","orcid":"https://orcid.org/0000-0002-0186-4340","observed_orcids":["https://orcid.org/0000-0002-0186-4340"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pollinger, Theresa","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059293847","display_name":"Davide Gadioli","orcid":"https://orcid.org/0000-0002-0143-0737","observed_orcids":["https://orcid.org/0000-0002-0143-0737"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gadioli, Davide","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5077005193","display_name":"Gianluca Palermo","orcid":"https://orcid.org/0000-0001-7955-8012","observed_orcids":["https://orcid.org/0000-0001-7955-8012"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Palermo, Gianluca","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"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":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9994999766349792,"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"}},"topics":[{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9994999766349792,"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/T10904","display_name":"Embedded Systems Design Techniques","score":9.999999747378752e-05,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.0,"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/molecular-docking","display_name":"molecular docking","score":0.8899999856948853},{"id":"https://openalex.org/keywords/vectorization","display_name":"vectorization","score":0.8629999756813049},{"id":"https://openalex.org/keywords/performance-portability","display_name":"performance portability","score":0.9200000166893005},{"id":"https://openalex.org/keywords/processor-architecture","display_name":"processor architecture","score":0.5709999799728394},{"id":"https://openalex.org/keywords/energy-consumption","display_name":"energy consumption","score":0.6570000052452087},{"id":"https://openalex.org/keywords/program-transformation","display_name":"program transformation","score":0.4909999966621399},{"id":"https://openalex.org/keywords/scientific-applications","display_name":"scientific applications","score":0.37700000405311584}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7943000197410583},{"id":"https://openalex.org/C170723468","wikidata":"https://www.wikidata.org/wiki/Q182933","display_name":"x86","level":3,"score":0.7904999852180481},{"id":"https://openalex.org/C63000827","wikidata":"https://www.wikidata.org/wiki/Q3080428","display_name":"Software portability","level":2,"score":0.786899983882904},{"id":"https://openalex.org/C41681595","wikidata":"https://www.wikidata.org/wiki/Q7917855","display_name":"Vectorization (mathematics)","level":2,"score":0.7386000156402588},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.6273999810218811},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.4968000054359436},{"id":"https://openalex.org/C51929080","wikidata":"https://www.wikidata.org/wiki/Q2425187","display_name":"Codebase","level":3,"score":0.4948999881744385},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4779999852180481},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.44130000472068787},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.41670000553131104},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.3749000132083893},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.34540000557899475},{"id":"https://openalex.org/C2780165032","wikidata":"https://www.wikidata.org/wiki/Q16869822","display_name":"Energy consumption","level":2,"score":0.34369999170303345},{"id":"https://openalex.org/C34165917","wikidata":"https://www.wikidata.org/wiki/Q188267","display_name":"Programming paradigm","level":2,"score":0.3336000144481659},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3310999870300293},{"id":"https://openalex.org/C2742236","wikidata":"https://www.wikidata.org/wiki/Q924713","display_name":"Efficient energy use","level":2,"score":0.3294000029563904},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.3183000087738037},{"id":"https://openalex.org/C49154492","wikidata":"https://www.wikidata.org/wiki/Q5300","display_name":"Central processing unit","level":2,"score":0.3084999918937683},{"id":"https://openalex.org/C133162039","wikidata":"https://www.wikidata.org/wiki/Q1061077","display_name":"Code generation","level":3,"score":0.2919999957084656},{"id":"https://openalex.org/C160145156","wikidata":"https://www.wikidata.org/wiki/Q778586","display_name":"Executable","level":2,"score":0.2766000032424927},{"id":"https://openalex.org/C2778915421","wikidata":"https://www.wikidata.org/wiki/Q3643177","display_name":"Performance improvement","level":2,"score":0.26179999113082886},{"id":"https://openalex.org/C96972482","wikidata":"https://www.wikidata.org/wiki/Q1049168","display_name":"Xeon Phi","level":2,"score":0.25929999351501465},{"id":"https://openalex.org/C2778100165","wikidata":"https://www.wikidata.org/wiki/Q1589327","display_name":"Memory hierarchy","level":3,"score":0.2563999891281128},{"id":"https://openalex.org/C76752949","wikidata":"https://www.wikidata.org/wiki/Q7607499","display_name":"Stencil","level":2,"score":0.25380000472068787}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2509.12232","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2509.12232","pdf_url":"https://arxiv.org/pdf/2509.12232","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2509.12232","doi":"https://doi.org/10.48550/arxiv.2509.12232","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2509.12232","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2509.12232","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2509.12232","pdf_url":"https://arxiv.org/pdf/2509.12232","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Recent":[0],"trends":[1],"in":[2],"the":[3,39,51,100,110],"HPC":[4,94],"field":[5],"have":[6],"introduced":[7],"new":[8],"CPU":[9],"architectures":[10,156],"with":[11,73],"improved":[12],"vectorization":[13,65,152],"capabilities":[14],"that":[15,136],"require":[16],"optimization":[17,106],"to":[18,66,109,130,149],"achieve":[19,67,140],"peak":[20],"performance":[21,27,68,128,143],"and":[22,41,57,63,105,161],"thus":[23],"pose":[24],"challenges":[25],"for":[26,35,43,116],"portability.":[28],"The":[29],"deployment":[30],"of":[31,113],"high-performing":[32],"scientific":[33,114],"applications":[34,47,115],"CPUs":[36,72,138],"requires":[37],"adapting":[38],"codebase":[40],"optimizing":[42],"performance.":[44],"Evaluating":[45],"these":[46],"provides":[48],"insights":[49,98],"into":[50,99],"complex":[52],"interactions":[53],"between":[54],"code,":[55],"compilers,":[56],"hardware.":[58],"We":[59,76,96],"evaluate":[60],"compiler":[61],"auto-vectorization":[62],"explicit":[64,131],"portability":[69],"across":[70,93],"modern":[71],"long":[74],"vectors.":[75],"select":[77],"a":[78,83],"molecular":[79],"docking":[80],"application":[81],"as":[82,86],"case":[84],"study,":[85],"it":[87],"represents":[88],"computational":[89],"patterns":[90],"commonly":[91],"found":[92],"workloads.":[95],"report":[97],"technical":[101],"challenges,":[102],"architectural":[103],"trends,":[104],"strategies":[107],"relevant":[108],"future":[111],"development":[112],"HPC.":[117],"Our":[118],"results":[119],"show":[120],"which":[121],"code":[122],"transformations":[123],"enable":[124],"portable":[125],"auto-vectorization,":[126],"reaching":[127],"similar":[129],"vectorization.":[132],"Experimental":[133],"data":[134],"confirms":[135],"x86":[137],"typically":[139],"higher":[141],"execution":[142],"than":[144],"ARM":[145,155],"CPUs,":[146],"primarily":[147],"due":[148],"their":[150],"wider":[151],"units.":[153],"However,":[154],"demonstrate":[157],"competitive":[158],"energy":[159],"consumption":[160],"cost-effectiveness.":[162]},"counts_by_year":[],"updated_date":"2026-08-26T07:47:46.906454","created_date":"2025-10-18T00:00:00"}