{"id":"https://openalex.org/W2903069957","doi":"https://doi.org/10.1109/globalsip.2018.8646675","title":"Large-Scale Algorithm Design for Parallel FFT-based Simulations on GPUs","display_name":"Large-Scale Algorithm Design for Parallel FFT-based Simulations on GPUs","publication_year":2018,"publication_date":"2018-11-01","ids":{"openalex":"https://openalex.org/W2903069957","doi":"https://doi.org/10.1109/globalsip.2018.8646675","mag":"2903069957"},"language":"en","primary_location":{"id":"doi:10.1109/globalsip.2018.8646675","is_oa":false,"landing_page_url":"https://doi.org/10.1109/globalsip.2018.8646675","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE Global Conference on Signal and Information Processing (GlobalSIP)","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/A5078947104","display_name":"Anuva Kulkarni","orcid":"https://orcid.org/0000-0001-8896-7504"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anuva Kulkarni","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062806943","display_name":"Franz Franchetti","orcid":"https://orcid.org/0000-0002-3529-8973"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Franz Franchetti","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101863660","display_name":"Jelena Kova\u010devi\u0107","orcid":"https://orcid.org/0000-0003-0139-2803"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jelena Kovacevic","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"25","issue":null,"first_page":"301","last_page":"305"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10688","display_name":"Image and Signal Denoising Methods","score":0.996999979019165,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10688","display_name":"Image and Signal Denoising Methods","score":0.996999979019165,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T11034","display_name":"Digital Filter Design and Implementation","score":0.9937000274658203,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.9900000095367432,"subfield":{"id":"https://openalex.org/subfields/1704","display_name":"Computer Graphics and Computer-Aided Design"},"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/computer-science","display_name":"Computer science","score":0.8183923959732056},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7302778363227844},{"id":"https://openalex.org/keywords/fast-fourier-transform","display_name":"Fast Fourier transform","score":0.7258255481719971},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.5919275879859924},{"id":"https://openalex.org/keywords/lossy-compression","display_name":"Lossy compression","score":0.5820677280426025},{"id":"https://openalex.org/keywords/solver","display_name":"Solver","score":0.569324254989624},{"id":"https://openalex.org/keywords/fortran","display_name":"Fortran","score":0.5451681613922119},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.4897453784942627},{"id":"https://openalex.org/keywords/partial-differential-equation","display_name":"Partial differential equation","score":0.45191699266433716},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4493836760520935},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.4340093433856964},{"id":"https://openalex.org/keywords/parallel-algorithm","display_name":"Parallel algorithm","score":0.4216892719268799},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.41951116919517517},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4169308841228485},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.3272656798362732},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08651500940322876}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8183923959732056},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7302778363227844},{"id":"https://openalex.org/C75172450","wikidata":"https://www.wikidata.org/wiki/Q623950","display_name":"Fast Fourier transform","level":2,"score":0.7258255481719971},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.5919275879859924},{"id":"https://openalex.org/C165021410","wikidata":"https://www.wikidata.org/wiki/Q55564","display_name":"Lossy compression","level":2,"score":0.5820677280426025},{"id":"https://openalex.org/C2778770139","wikidata":"https://www.wikidata.org/wiki/Q1966904","display_name":"Solver","level":2,"score":0.569324254989624},{"id":"https://openalex.org/C2778241615","wikidata":"https://www.wikidata.org/wiki/Q83303","display_name":"Fortran","level":2,"score":0.5451681613922119},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.4897453784942627},{"id":"https://openalex.org/C93779851","wikidata":"https://www.wikidata.org/wiki/Q271977","display_name":"Partial differential equation","level":2,"score":0.45191699266433716},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4493836760520935},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.4340093433856964},{"id":"https://openalex.org/C120373497","wikidata":"https://www.wikidata.org/wiki/Q1087987","display_name":"Parallel algorithm","level":2,"score":0.4216892719268799},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.41951116919517517},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4169308841228485},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.3272656798362732},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08651500940322876},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/globalsip.2018.8646675","is_oa":false,"landing_page_url":"https://doi.org/10.1109/globalsip.2018.8646675","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE Global Conference on Signal and Information Processing (GlobalSIP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W2001762851","https://openalex.org/W2003410902","https://openalex.org/W2007427596","https://openalex.org/W2025759093","https://openalex.org/W2052440657","https://openalex.org/W2097269032","https://openalex.org/W2102182691","https://openalex.org/W2110455446","https://openalex.org/W2147688967","https://openalex.org/W2312290487","https://openalex.org/W2486202470","https://openalex.org/W3112597099","https://openalex.org/W4292179373","https://openalex.org/W6651107605","https://openalex.org/W6722043901"],"related_works":["https://openalex.org/W1995805316","https://openalex.org/W2384867379","https://openalex.org/W2387503788","https://openalex.org/W4400094300","https://openalex.org/W2066731161","https://openalex.org/W2329539859","https://openalex.org/W1986195078","https://openalex.org/W2227905990","https://openalex.org/W2059658550","https://openalex.org/W2096246226"],"abstract_inverted_index":{"We":[0],"describe":[1],"and":[2,8,37,82],"analyze":[3],"a":[4,14],"co-design":[5],"of":[6,13,66,69,93,106],"algorithm":[7,107],"software":[9],"for":[10,21,103],"high-performance":[11],"simulation":[12],"partial":[15],"differential":[16],"equation":[17],"(PDE)":[18],"numerical":[19],"solver":[20],"large-scale":[22],"datasets.":[23],"Large-scale":[24],"scientific":[25,57],"simulations":[26],"involving":[27],"parallel":[28],"Fast":[29],"Fourier":[30],"Transforms":[31],"(FFTs)":[32],"have":[33],"extreme":[34],"memory":[35,67],"requirements":[36],"high":[38,43],"communication":[39],"cost.":[40],"This":[41],"hampers":[42],"resolution":[44],"analysis":[45],"with":[46,59],"fine":[47],"grids.":[48],"Moreover,":[49],"it":[50],"is":[51],"difficult":[52],"to":[53,85],"accelerate":[54],"legacy":[55],"Fortran":[56],"codes":[58],"modern":[60],"hardware":[61],"such":[62,78],"as":[63,79],"GPUs":[64],"because":[65],"constraints":[68],"GPUs.":[70],"Our":[71],"proposed":[72],"solution":[73],"uses":[74],"signal":[75],"processing":[76],"techniques":[77],"lossy":[80],"compression":[81],"domain-local":[83],"FFTs":[84],"lower":[86],"iteration":[87],"cost":[88],"without":[89],"adversely":[90],"impacting":[91],"accuracy":[92],"the":[94],"result.":[95],"In":[96],"this":[97],"work,":[98],"we":[99],"discuss":[100],"proof-of-concept":[101],"results":[102],"various":[104],"aspects":[105],"development.":[108]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2026-07-19T07:52:34.831488","created_date":"2025-10-10T00:00:00"}