{"id":"https://openalex.org/W2916528865","doi":"https://doi.org/10.1109/cahpc.2018.8645913","title":"Optimization of a Sparse Grid-Based Data Mining Kernel for Architectures Using AVX-512","display_name":"Optimization of a Sparse Grid-Based Data Mining Kernel for Architectures Using AVX-512","publication_year":2018,"publication_date":"2018-09-01","ids":{"openalex":"https://openalex.org/W2916528865","doi":"https://doi.org/10.1109/cahpc.2018.8645913","mag":"2916528865"},"language":"en","primary_location":{"id":"doi:10.1109/cahpc.2018.8645913","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cahpc.2018.8645913","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 30th International Symposium on Computer Architecture and High Performance Computing (SBAC-PAD)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://mediatum.ub.tum.de/node?id=1462617","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5004381223","display_name":"Paul-Cristian Sarbu","orcid":null},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Paul-Cristian Sarbu","raw_affiliation_strings":["Chair of Scientific Computing, Technical University of Munich, Garching, Germany"],"affiliations":[{"raw_affiliation_string":"Chair of Scientific Computing, Technical University of Munich, Garching, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068403289","display_name":"Hans\u2010Joachim Bungartz","orcid":"https://orcid.org/0000-0002-0171-0712"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Hans-Joachim Bungartz","raw_affiliation_strings":["Chair of Scientific Computing, Technical University of Munich, Garching, Germany"],"affiliations":[{"raw_affiliation_string":"Chair of Scientific Computing, Technical University of Munich, Garching, Germany","institution_ids":["https://openalex.org/I62916508"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5004381223"],"corresponding_institution_ids":["https://openalex.org/I62916508"],"apc_list":null,"apc_paid":null,"fwci":0.2525,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.5494989,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"31","issue":null,"first_page":"364","last_page":"371"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9994000196456909,"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":0.9994000196456909,"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":0.9987999796867371,"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/T12303","display_name":"Tensor decomposition and applications","score":0.9882000088691711,"subfield":{"id":"https://openalex.org/subfields/2605","display_name":"Computational Mathematics"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/vectorization","display_name":"Vectorization (mathematics)","score":0.7930233478546143},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7823363542556763},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.7459429502487183},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7137424945831299},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.6646546721458435},{"id":"https://openalex.org/keywords/instruction-set","display_name":"Instruction set","score":0.577816903591156},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5422433614730835},{"id":"https://openalex.org/keywords/xeon-phi","display_name":"Xeon Phi","score":0.4886074662208557},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4852287769317627},{"id":"https://openalex.org/keywords/grid","display_name":"Grid","score":0.4533885419368744},{"id":"https://openalex.org/keywords/computer-cluster","display_name":"Computer cluster","score":0.45272377133369446},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.38215383887290955},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.3574126660823822},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.34879785776138306}],"concepts":[{"id":"https://openalex.org/C41681595","wikidata":"https://www.wikidata.org/wiki/Q7917855","display_name":"Vectorization (mathematics)","level":2,"score":0.7930233478546143},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7823363542556763},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.7459429502487183},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7137424945831299},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.6646546721458435},{"id":"https://openalex.org/C202491316","wikidata":"https://www.wikidata.org/wiki/Q272683","display_name":"Instruction set","level":2,"score":0.577816903591156},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5422433614730835},{"id":"https://openalex.org/C96972482","wikidata":"https://www.wikidata.org/wiki/Q1049168","display_name":"Xeon Phi","level":2,"score":0.4886074662208557},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4852287769317627},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.4533885419368744},{"id":"https://openalex.org/C29140674","wikidata":"https://www.wikidata.org/wiki/Q206637","display_name":"Computer cluster","level":2,"score":0.45272377133369446},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.38215383887290955},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.3574126660823822},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.34879785776138306},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/cahpc.2018.8645913","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cahpc.2018.8645913","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 30th International Symposium on Computer Architecture and High Performance Computing (SBAC-PAD)","raw_type":"proceedings-article"},{"id":"pmh:oai:mediatum.ub.tum.de:node/1462617","is_oa":true,"landing_page_url":"http://mediatum.ub.tum.de/node?id=1462617","pdf_url":null,"source":{"id":"https://openalex.org/S4377196330","display_name":"mediaTUM  (Technical University of Munich)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I62916508","host_organization_name":"Technical University of Munich","host_organization_lineage":["https://openalex.org/I62916508"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"article"},{"id":"pmh:oai:mediatum.ub.tum.de:node/1462624","is_oa":true,"landing_page_url":"http://mediatum.ub.tum.de/node?id=1462624","pdf_url":null,"source":{"id":"https://openalex.org/S4377196330","display_name":"mediaTUM  (Technical University of Munich)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I62916508","host_organization_name":"Technical University of Munich","host_organization_lineage":["https://openalex.org/I62916508"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:mediatum.ub.tum.de:node/1462617","is_oa":true,"landing_page_url":"http://mediatum.ub.tum.de/node?id=1462617","pdf_url":null,"source":{"id":"https://openalex.org/S4377196330","display_name":"mediaTUM  (Technical University of Munich)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I62916508","host_organization_name":"Technical University of Munich","host_organization_lineage":["https://openalex.org/I62916508"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W2019377400","https://openalex.org/W2054314432","https://openalex.org/W2394917699","https://openalex.org/W2475636809","https://openalex.org/W2773017799","https://openalex.org/W4240776251","https://openalex.org/W4255975175"],"related_works":["https://openalex.org/W32529763","https://openalex.org/W1908180445","https://openalex.org/W2035419609","https://openalex.org/W1766386015","https://openalex.org/W2597386847","https://openalex.org/W2963706620","https://openalex.org/W1939907483","https://openalex.org/W2106561276","https://openalex.org/W2912502764","https://openalex.org/W2761234150"],"abstract_inverted_index":{"Sparse":[0],"grids":[1],"have":[2],"already":[3],"been":[4],"successfully":[5],"used":[6,52],"in":[7,72,147],"various":[8],"high-performance":[9],"computing":[10],"(HPC)":[11],"applications,":[12],"including":[13],"data":[14,136],"mining.":[15],"In":[16,44],"this":[17],"article,":[18],"we":[19],"take":[20],"a":[21,95,108],"legacy":[22],"classification":[23,124],"kernel":[24,106],"previously":[25],"optimized":[26],"for":[27,121],"the":[28,34,38,46,55,60,86,89,113,139,142],"AVX2":[29],"instruction":[30],"set":[31],"and":[32,75,78],"investigate":[33],"benefits":[35],"of":[36,59,88,99,141],"using":[37,138],"newer":[39],"AVX-512-based":[40],"multi-and":[41],"many-core":[42],"architectures.":[43],"particular,":[45],"Knights":[47],"Landing":[48],"(KNL)":[49],"processor":[50],"is":[51],"to":[53,82,128],"study":[54],"possible":[56],"performance":[57],"gains":[58],"code.":[61],"Not":[62],"all":[63],"kernels":[64],"benefit":[65],"equally":[66],"from":[67,118],"such":[68],"architectures,":[69],"therefore":[70],"choices":[71],"optimization":[73,114],"steps":[74],"KNL":[76],"cluster":[77],"memory":[79],"modes":[80],"need":[81],"be":[83],"filtered":[84],"through":[85,102],"lens":[87],"code":[90],"implementation":[91],"at":[92],"hand.":[93],"With":[94],"less":[96],"traditional":[97],"approach":[98],"manual":[100],"vectorization":[101],"instruction-level":[103],"intrinsics,":[104],"our":[105],"provides":[107],"differently":[109],"faceted":[110],"look":[111],"into":[112],"process.":[115],"Observations":[116],"stem":[117],"results":[119],"obtained":[120],"node-and":[122],"cluster-level":[123],"simulations":[125],"with":[126],"up":[127],"2":[129],"<sup":[130],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[131],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">^</sup>":[132],"28":[133],"multidimensional":[134],"training":[135],"points,":[137],"CooLMUC-3cluster":[140],"Leibniz":[143],"Supercomputing":[144],"Center":[145],"(LRZ)":[146],"Garching,":[148],"Germany.":[149]},"counts_by_year":[{"year":2019,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
