{"id":"https://openalex.org/W2765377629","doi":"https://doi.org/10.1109/hpec.2017.8091024","title":"Mixed data layout kernels for vectorized complex arithmetic","display_name":"Mixed data layout kernels for vectorized complex arithmetic","publication_year":2017,"publication_date":"2017-09-01","ids":{"openalex":"https://openalex.org/W2765377629","doi":"https://doi.org/10.1109/hpec.2017.8091024","mag":"2765377629"},"language":"en","primary_location":{"id":"doi:10.1109/hpec.2017.8091024","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpec.2017.8091024","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE High Performance Extreme Computing Conference (HPEC)","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/A5019066795","display_name":"Doru Thom Popovici","orcid":"https://orcid.org/0000-0002-7271-8092"},"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":"Doru T. Popovici","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/A5019607600","display_name":"Tze Meng Low","orcid":"https://orcid.org/0000-0002-5179-8249"},"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":"Tze Meng Low","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":13,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"4395","issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9998000264167786,"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":0.9998000264167786,"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/T11697","display_name":"Numerical Methods and Algorithms","score":0.9994000196456909,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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":0.994700014591217,"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/computer-science","display_name":"Computer science","score":0.7684229612350464},{"id":"https://openalex.org/keywords/saturation-arithmetic","display_name":"Saturation arithmetic","score":0.7329081892967224},{"id":"https://openalex.org/keywords/simd","display_name":"SIMD","score":0.7178677320480347},{"id":"https://openalex.org/keywords/arithmetic","display_name":"Arithmetic","score":0.6790145039558411},{"id":"https://openalex.org/keywords/multiplication","display_name":"Multiplication (music)","score":0.6605039238929749},{"id":"https://openalex.org/keywords/arbitrary-precision-arithmetic","display_name":"Arbitrary-precision arithmetic","score":0.6400997042655945},{"id":"https://openalex.org/keywords/fast-fourier-transform","display_name":"Fast Fourier transform","score":0.5538962483406067},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5114077925682068},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.4823743402957916},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.43299925327301025},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.28002917766571045},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15913429856300354}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7684229612350464},{"id":"https://openalex.org/C182775192","wikidata":"https://www.wikidata.org/wiki/Q913725","display_name":"Saturation arithmetic","level":3,"score":0.7329081892967224},{"id":"https://openalex.org/C150552126","wikidata":"https://www.wikidata.org/wiki/Q339387","display_name":"SIMD","level":2,"score":0.7178677320480347},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.6790145039558411},{"id":"https://openalex.org/C2780595030","wikidata":"https://www.wikidata.org/wiki/Q3860309","display_name":"Multiplication (music)","level":2,"score":0.6605039238929749},{"id":"https://openalex.org/C83581934","wikidata":"https://www.wikidata.org/wiki/Q527381","display_name":"Arbitrary-precision arithmetic","level":2,"score":0.6400997042655945},{"id":"https://openalex.org/C75172450","wikidata":"https://www.wikidata.org/wiki/Q623950","display_name":"Fast Fourier transform","level":2,"score":0.5538962483406067},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5114077925682068},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4823743402957916},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.43299925327301025},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.28002917766571045},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15913429856300354},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","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},{"id":"https://openalex.org/C84114770","wikidata":"https://www.wikidata.org/wiki/Q46344","display_name":"Quantum","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/hpec.2017.8091024","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpec.2017.8091024","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE High Performance Extreme Computing Conference (HPEC)","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"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1543833969","https://openalex.org/W1839118408","https://openalex.org/W1978005976","https://openalex.org/W2061171222","https://openalex.org/W2069441027","https://openalex.org/W2073061372","https://openalex.org/W2079658918","https://openalex.org/W2084379367","https://openalex.org/W2102182691","https://openalex.org/W2136952590","https://openalex.org/W2146406121","https://openalex.org/W2164197394","https://openalex.org/W2252007067","https://openalex.org/W2498043873","https://openalex.org/W2516525699","https://openalex.org/W2737067755","https://openalex.org/W6632704574","https://openalex.org/W6638946568"],"related_works":["https://openalex.org/W1560663560","https://openalex.org/W3099313426","https://openalex.org/W4287593139","https://openalex.org/W1559551218","https://openalex.org/W752783541","https://openalex.org/W2073476805","https://openalex.org/W1506547947","https://openalex.org/W2995605830","https://openalex.org/W2752588380","https://openalex.org/W1221789869"],"abstract_inverted_index":{"Implementing":[0],"complex":[1,38,55,73,91,136],"arithmetic":[2,24,39,49],"routines":[3],"with":[4,114],"Single":[5],"Instruction":[6],"Multiple":[7],"Data":[8],"(SIMD)":[9],"instructions":[10,15,53],"requires":[11],"the":[12,79,85,118,133],"use":[13,86],"of":[14,66,78,87,107],"that":[16,104],"are":[17,33],"usually":[18,44],"not":[19],"found":[20],"in":[21],"their":[22],"real":[23,48],"counter-parts.":[25],"These":[26],"instructions,":[27],"such":[28],"as":[29,41,82,99],"shuffles":[30],"and":[31,94],"addsub,":[32],"often":[34],"bottlenecks":[35],"for":[36,54,71],"many":[37],"kernels":[40],"modern":[42],"architectures":[43],"can":[45,111,127],"perform":[46],"more":[47],"operations":[50],"than":[51],"execute":[52],"arithmetic.":[56],"In":[57],"this":[58],"work,":[59],"we":[60,102],"focus":[61],"on":[62],"using":[63],"a":[64],"variety":[65],"data":[67],"layouts":[68],"(mixed":[69],"format)":[70],"storing":[72],"numbers":[74],"at":[75],"different":[76],"stages":[77],"computation":[80],"so":[81],"to":[83,109,131],"limit":[84],"these":[88],"instructions.":[89],"Using":[90],"matrix":[92],"multiplication":[93],"Fast":[95],"Fourier":[96],"Transforms":[97],"(FFTs)":[98],"our":[100],"examples,":[101],"demonstrate":[103],"performance":[105],"improvements":[106],"up":[108],"2\u00d7":[110],"be":[112,128],"attained":[113],"mixed":[115,134],"format":[116,135],"within":[117],"computational":[119],"routines.":[120],"We":[121],"also":[122],"described":[123],"how":[124],"existing":[125],"algorithms":[126],"easily":[129],"modified":[130],"implement":[132],"layout.":[137]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}