{"id":"https://openalex.org/W4308090281","doi":"https://doi.org/10.1109/hpec55821.2022.9926309","title":"Powering Practical Performance: Accelerated Numerical Computing in Pure Python","display_name":"Powering Practical Performance: Accelerated Numerical Computing in Pure Python","publication_year":2022,"publication_date":"2022-09-19","ids":{"openalex":"https://openalex.org/W4308090281","doi":"https://doi.org/10.1109/hpec55821.2022.9926309"},"language":"en","primary_location":{"id":"doi:10.1109/hpec55821.2022.9926309","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpec55821.2022.9926309","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE High Performance Extreme Computing Conference (HPEC)","raw_type":"proceedings-article"},"type":"article","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/A5028742823","display_name":"Matthew J. Penn","orcid":"https://orcid.org/0000-0001-8682-5393"},"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":true,"raw_author_name":"Matthew Penn","raw_affiliation_strings":["NVIDIA Corporation,Santa Clara,CA,USA","NVIDIA Corporation, Santa Clara, CA, USA"],"affiliations":[{"raw_affiliation_string":"NVIDIA Corporation,Santa Clara,CA,USA","institution_ids":["https://openalex.org/I4210127875"]},{"raw_affiliation_string":"NVIDIA Corporation, Santa Clara, CA, USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108628384","display_name":"Chris Milroy","orcid":null},"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":"Chris Milroy","raw_affiliation_strings":["NVIDIA Corporation,Santa Clara,CA,USA","NVIDIA Corporation, Santa Clara, CA, USA"],"affiliations":[{"raw_affiliation_string":"NVIDIA Corporation,Santa Clara,CA,USA","institution_ids":["https://openalex.org/I4210127875"]},{"raw_affiliation_string":"NVIDIA Corporation, Santa Clara, CA, USA","institution_ids":["https://openalex.org/I4210127875"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5028742823"],"corresponding_institution_ids":["https://openalex.org/I4210127875"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.11855574,"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":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9965999722480774,"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":0.9965999722480774,"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/T13650","display_name":"Computational Physics and Python Applications","score":0.9868000149726868,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9506999850273132,"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/python","display_name":"Python (programming language)","score":0.8714147210121155},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8229042291641235},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.6868032217025757},{"id":"https://openalex.org/keywords/workstation","display_name":"Workstation","score":0.5559384226799011},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5286294221878052},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.47635555267333984},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.4348652958869934},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.43000805377960205},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.4264914095401764},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.32571113109588623},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.29041576385498047},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.27468812465667725},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.2710381746292114}],"concepts":[{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.8714147210121155},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8229042291641235},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.6868032217025757},{"id":"https://openalex.org/C67953723","wikidata":"https://www.wikidata.org/wiki/Q192525","display_name":"Workstation","level":2,"score":0.5559384226799011},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5286294221878052},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.47635555267333984},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.4348652958869934},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.43000805377960205},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.4264914095401764},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.32571113109588623},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.29041576385498047},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.27468812465667725},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2710381746292114}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/hpec55821.2022.9926309","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpec55821.2022.9926309","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE High Performance Extreme Computing Conference (HPEC)","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":0,"referenced_works":[],"related_works":["https://openalex.org/W2152751187","https://openalex.org/W2134581225","https://openalex.org/W1963859303","https://openalex.org/W2364044215","https://openalex.org/W2389600408","https://openalex.org/W240129890","https://openalex.org/W3048701459","https://openalex.org/W2149078538","https://openalex.org/W2080146221","https://openalex.org/W2370314112"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,74],"tackle":[4],"a":[5,77,125,156,161],"generic":[6],"n-dimensional":[7],"numerical":[8,44,127],"computing":[9,45,128],"problem":[10,60,129],"to":[11,96,115,149],"compare":[12],"performance":[13],"and":[14,40,52,69],"analyze":[15],"tradeoffs":[16],"between":[17],"popular":[18],"frameworks":[19],"using":[20],"open":[21],"source":[22],"Jupyter":[23],"notebook":[24],"examples.":[25],"Most":[26],"data":[27,97,120],"science":[28,121],"practitioners":[29],"perform":[30],"their":[31],"work":[32],"in":[33,135,144],"Python":[34,106],"because":[35],"of":[36,43,50,80,90,163],"its":[37,142],"high-level":[38],"abstraction":[39],"rich":[41],"set":[42],"libraries.":[46],"However,":[47],"the":[48,88,105,132],"choice":[49],"library":[51],"methodology":[53],"is":[54,112],"driven":[55],"by":[56,109],"complexity-impacting":[57],"constraints":[58],"like":[59],"size,":[61,65],"latency,":[62],"memory,":[63],"physical":[64],"weight,":[66],"power,":[67],"hardware,":[68],"others.":[70],"To":[71],"that":[72,76],"end,":[73],"demonstrate":[75],"wide":[78],"selection":[79],"GPU-accelerated":[81],"libraries":[82],"(RAPIDS,":[83],"CuPy,":[84],"Numba,":[85],"Dask),":[86],"including":[87],"development":[89],"hand-tuned":[91],"CUDA":[92],"kernels,":[93],"are":[94],"accessible":[95],"scientists":[98],"without":[99,159],"ever":[100],"leaving":[101],"Python.":[102],"We":[103,123],"address":[104],"developer":[107],"community":[108],"showing":[110],"C/C++":[111],"not":[113],"necessary":[114],"access":[116],"single/multi-GPU":[117],"acceleration":[118],"for":[119],"applications.":[122],"solve":[124],"common":[126],"-":[130,154],"finding":[131],"closest":[133],"point":[134,140],"array":[136,145],"B":[137],"from":[138],"every":[139],"(and":[141],"index)":[143],"A,":[146],"requiring":[147],"up":[148],"8.8":[150],"trillion":[151],"distance":[152],"comparisons":[153],"on":[155],"GPU-equipped":[157],"workstation":[158],"writing":[160],"line":[162],"C/C++.":[164]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}