{"id":"https://openalex.org/W2160837736","doi":"https://doi.org/10.1109/ispass.2011.5762726","title":"A comparative benchmarking of the FFT on Fermi and Evergreen GPUs","display_name":"A comparative benchmarking of the FFT on Fermi and Evergreen GPUs","publication_year":2011,"publication_date":"2011-04-01","ids":{"openalex":"https://openalex.org/W2160837736","doi":"https://doi.org/10.1109/ispass.2011.5762726","mag":"2160837736"},"language":"en","primary_location":{"id":"doi:10.1109/ispass.2011.5762726","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ispass.2011.5762726","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"(IEEE ISPASS) IEEE INTERNATIONAL SYMPOSIUM ON PERFORMANCE ANALYSIS OF SYSTEMS AND SOFTWARE","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/A5113460024","display_name":"Mohamed F. Ahmed","orcid":null},"institutions":[{"id":"https://openalex.org/I80693520","display_name":"American University in Cairo","ror":"https://ror.org/0176yqn58","country_code":"EG","type":"education","lineage":["https://openalex.org/I80693520"]}],"countries":["EG"],"is_corresponding":false,"raw_author_name":"Mohamed F. Ahmed","raw_affiliation_strings":["Computer Science and Engineering, American University, Cairo, Cairo, Egypt"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science and Engineering, American University, Cairo, Cairo, Egypt","institution_ids":["https://openalex.org/I80693520"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088505250","display_name":"Omar Haridy","orcid":null},"institutions":[{"id":"https://openalex.org/I96823368","display_name":"German University in Cairo","ror":"https://ror.org/03rjt0z37","country_code":"EG","type":"education","lineage":["https://openalex.org/I96823368"]}],"countries":["EG"],"is_corresponding":false,"raw_author_name":"Omar Haridy","raw_affiliation_strings":["Media Engineering and Technology, German University in Cairo, Cairo, Egypt"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Media Engineering and Technology, German University in Cairo, Cairo, Egypt","institution_ids":["https://openalex.org/I96823368"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"127","last_page":"128"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9991999864578247,"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":0.9991999864578247,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9944000244140625,"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"}},{"id":"https://openalex.org/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9923999905586243,"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/benchmarking","display_name":"Benchmarking","score":0.8302776217460632},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7531261444091797},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.6061861515045166},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5625297427177429},{"id":"https://openalex.org/keywords/fast-fourier-transform","display_name":"Fast Fourier transform","score":0.5476176142692566},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.5109230875968933},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.4265854060649872},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.3140530288219452},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.06252694129943848}],"concepts":[{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.8302776217460632},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7531261444091797},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.6061861515045166},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5625297427177429},{"id":"https://openalex.org/C75172450","wikidata":"https://www.wikidata.org/wiki/Q623950","display_name":"Fast Fourier transform","level":2,"score":0.5476176142692566},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.5109230875968933},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.4265854060649872},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.3140530288219452},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.06252694129943848},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ispass.2011.5762726","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ispass.2011.5762726","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"(IEEE ISPASS) IEEE INTERNATIONAL SYMPOSIUM ON PERFORMANCE ANALYSIS OF SYSTEMS AND SOFTWARE","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Sustainable cities and communities","score":0.4000000059604645,"id":"https://metadata.un.org/sdg/11"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":1,"referenced_works":["https://openalex.org/W2085614566"],"related_works":["https://openalex.org/W4238897586","https://openalex.org/W435179959","https://openalex.org/W2619091065","https://openalex.org/W2341842940","https://openalex.org/W2059640416","https://openalex.org/W2025911710","https://openalex.org/W1967938402","https://openalex.org/W2386041993","https://openalex.org/W1608572506","https://openalex.org/W2160474882"],"abstract_inverted_index":{"NVIDIA":[0],"and":[1,13,22,40,44,49],"AMD":[2],"GPUs":[3],"are":[4,5],"gaining":[6],"traction":[7],"in":[8],"HPC":[9],"for":[10],"their":[11],"performance":[12,72],"architectural":[14],"aspects.":[15],"It":[16],"is":[17],"very":[18],"important":[19],"to":[20,51,69],"measure":[21],"analyze":[23,34],"the":[24,35,46,54,61],"relative":[25],"power":[26],"of":[27,37,56],"each":[28,57],"architecture.":[29,58],"In":[30],"this":[31],"paper,":[32],"we":[33],"architecture":[36],"NVIDIA's":[38],"Fermi":[39],"AMD's":[41],"Evergreen":[42],"processors":[43],"demonstrate":[45],"best":[47,52],"practices":[48],"techniques":[50],"utilize":[53],"capabilities":[55],"We":[59],"implemented":[60],"FFT":[62],"on":[63,74],"both":[64,75],"cards":[65],"utilizing":[66],"our":[67],"findings":[68],"reach":[70],"new":[71],"ceilings":[73],"GPUs.":[76]},"counts_by_year":[{"year":2014,"cited_by_count":8},{"year":2013,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}