{"id":"https://openalex.org/W4378505321","doi":"https://doi.org/10.1145/3592979.3593422","title":"Model-Based Performance Analysis of the HyTeG Finite Element Framework","display_name":"Model-Based Performance Analysis of the HyTeG Finite Element Framework","publication_year":2023,"publication_date":"2023-06-26","ids":{"openalex":"https://openalex.org/W4378505321","doi":"https://doi.org/10.1145/3592979.3593422"},"language":"en","primary_location":{"id":"doi:10.1145/3592979.3593422","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3592979.3593422","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Platform for Advanced Scientific Computing Conference","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3592979.3593422","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5085094235","display_name":"Dominik Th\u00f6nnes","orcid":null},"institutions":[{"id":"https://openalex.org/I181369854","display_name":"Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg","ror":"https://ror.org/00f7hpc57","country_code":"DE","type":"education","lineage":["https://openalex.org/I181369854"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Dominik Th\u00f6nnes","raw_affiliation_strings":["Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg (FAU), Erlangen, Germany"],"raw_orcid":"https://orcid.org/0000-0002-8340-4849","affiliations":[{"raw_affiliation_string":"Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg (FAU), Erlangen, Germany","institution_ids":["https://openalex.org/I181369854"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109197540","display_name":"Ulrich R\u00fcde","orcid":null},"institutions":[{"id":"https://openalex.org/I181369854","display_name":"Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg","ror":"https://ror.org/00f7hpc57","country_code":"DE","type":"education","lineage":["https://openalex.org/I181369854"]},{"id":"https://openalex.org/I4210106946","display_name":"Centre Europ\u00e9en de Recherche et de Formation Avanc\u00e9e en Calcul Scientifique","ror":"https://ror.org/02dzbc556","country_code":"FR","type":"facility","lineage":["https://openalex.org/I4210106946"]}],"countries":["DE","FR"],"is_corresponding":false,"raw_author_name":"Ulrich R\u00fcde","raw_affiliation_strings":["CERFACS, Toulouse, France","Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg (FAU), Erlangen, Germany"],"raw_orcid":"https://orcid.org/0000-0001-8796-8599","affiliations":[{"raw_affiliation_string":"CERFACS, Toulouse, France","institution_ids":["https://openalex.org/I4210106946"]},{"raw_affiliation_string":"Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg (FAU), Erlangen, Germany","institution_ids":["https://openalex.org/I181369854"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.05596958,"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":"12"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":1.0,"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":1.0,"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":0.9997000098228455,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9976999759674072,"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":0.8231492042541504},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7128937244415283},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.687394380569458},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.5604720711708069},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.5068982243537903},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.5050607323646545},{"id":"https://openalex.org/keywords/multigrid-method","display_name":"Multigrid method","score":0.4777904450893402},{"id":"https://openalex.org/keywords/toolbox","display_name":"Toolbox","score":0.4727947413921356},{"id":"https://openalex.org/keywords/polygon-mesh","display_name":"Polygon mesh","score":0.4438695013523102},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.437531977891922},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4297782778739929},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.3700397312641144},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.10767287015914917}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8231492042541504},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7128937244415283},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.687394380569458},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.5604720711708069},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.5068982243537903},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.5050607323646545},{"id":"https://openalex.org/C137119250","wikidata":"https://www.wikidata.org/wiki/Q1413101","display_name":"Multigrid method","level":3,"score":0.4777904450893402},{"id":"https://openalex.org/C2777655017","wikidata":"https://www.wikidata.org/wiki/Q1501161","display_name":"Toolbox","level":2,"score":0.4727947413921356},{"id":"https://openalex.org/C31487907","wikidata":"https://www.wikidata.org/wiki/Q1154597","display_name":"Polygon mesh","level":2,"score":0.4438695013523102},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.437531977891922},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4297782778739929},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.3700397312641144},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.10767287015914917},{"id":"https://openalex.org/C93779851","wikidata":"https://www.wikidata.org/wiki/Q271977","display_name":"Partial differential equation","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},{"id":"https://openalex.org/C84114770","wikidata":"https://www.wikidata.org/wiki/Q46344","display_name":"Quantum","level":2,"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/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","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/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3592979.3593422","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3592979.3593422","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Platform for Advanced Scientific Computing Conference","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2305.15116","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2305.15116","pdf_url":"https://arxiv.org/pdf/2305.15116","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.1145/3592979.3593422","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3592979.3593422","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Platform for Advanced Scientific Computing Conference","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320331625","display_name":"Gauss Centre for Supercomputing","ror":"https://ror.org/0585fsj26"},{"id":"https://openalex.org/F4320334763","display_name":"Leibniz-Gemeinschaft","ror":"https://ror.org/01n6r0e97"},{"id":"https://openalex.org/F4320336863","display_name":"Leibniz-Rechenzentrum","ror":"https://ror.org/05558nw16"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W153514170","https://openalex.org/W1480947737","https://openalex.org/W1569090332","https://openalex.org/W1575701986","https://openalex.org/W1974122416","https://openalex.org/W2002555321","https://openalex.org/W2018850201","https://openalex.org/W2078636996","https://openalex.org/W2096642134","https://openalex.org/W2530769523","https://openalex.org/W2887308724","https://openalex.org/W2985201073","https://openalex.org/W3038517668","https://openalex.org/W3046621064","https://openalex.org/W3125983777","https://openalex.org/W3130373099","https://openalex.org/W3135711703","https://openalex.org/W4230252700"],"related_works":["https://openalex.org/W4205140848","https://openalex.org/W2068663075","https://openalex.org/W2077078424","https://openalex.org/W2978678743","https://openalex.org/W2182328658","https://openalex.org/W2797837731","https://openalex.org/W4393677513","https://openalex.org/W4390832911","https://openalex.org/W1519938374","https://openalex.org/W1537807642"],"abstract_inverted_index":{"In":[0,99],"this":[1],"work,":[2],"we":[3,107,112],"present":[4],"how":[5],"code":[6,43],"generation":[7,44],"techniques":[8],"significantly":[9],"improve":[10],"the":[11,14,18,26,36,50,74,86,93,97,102,109,120],"performance":[12,27,61,77,94],"of":[13,31,38,62,64],"computational":[15],"kernels":[16,54,66],"in":[17],"HyTeG":[19],"software":[20],"framework.":[21],"This":[22],"HPC":[23],"framework":[24],"combines":[25],"and":[28],"memory":[29],"advantages":[30],"matrix-free":[32],"multigrid":[33],"solvers":[34],"with":[35,55],"flexibility":[37],"unstructured":[39],"meshes.":[40],"The":[41,60,89],"pystencils":[42],"toolbox":[45],"is":[46,70],"used":[47],"to":[48],"replace":[49],"original":[51],"abstract":[52],"C++":[53],"highly":[56],"optimized":[57],"loop":[58],"nests.":[59],"one":[63],"those":[65],"(the":[67],"matrix-vector":[68],"multiplication)":[69],"thoroughly":[71],"analyzed":[72],"using":[73],"Execution-Cache-Memory":[75],"(ECM)":[76],"model.":[78],"We":[79],"validate":[80],"these":[81],"predictions":[82],"by":[83],"measurements":[84],"on":[85],"SuperMUC-NG":[87],"supercomputer.":[88],"experiments":[90],"show":[91],"that":[92],"mostly":[95],"matches":[96],"predictions.":[98],"cases":[100],"where":[101],"prediction":[103],"does":[104],"not":[105],"match,":[106],"discuss":[108],"discrepancies.":[110],"Additionally,":[111],"conduct":[113],"a":[114,124],"node-level":[115],"scaling":[116],"study":[117],"which":[118],"shows":[119],"expected":[121],"behavior":[122],"for":[123],"memory-bound":[125],"compute":[126],"kernel.":[127]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2023-05-27T00:00:00"}