{"id":"https://openalex.org/W4400945385","doi":"https://doi.org/10.7148/2024-0208","title":"Analysis of performance differences of fem numerical integration algorithm on two generations of intel xe-lp gpus","display_name":"Analysis of performance differences of fem numerical integration algorithm on two generations of intel xe-lp gpus","publication_year":2024,"publication_date":"2024-06-07","ids":{"openalex":"https://openalex.org/W4400945385","doi":"https://doi.org/10.7148/2024-0208"},"language":"en","primary_location":{"id":"doi:10.7148/2024-0208","is_oa":true,"landing_page_url":"http://dx.doi.org/10.7148/2024-0208","pdf_url":"http://www.scs-europe.net/dlib/2024/ecms2024acceptedpapers/0208_fdem_ecms2024_0030.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ECMS 2024 Proceedings edited by Daniel Grzonka, Natalia Rylko, Grazyna Suchacka, Vladimir Mityushev","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"http://www.scs-europe.net/dlib/2024/ecms2024acceptedpapers/0208_fdem_ecms2024_0030.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5049462234","display_name":"Filip Kru\u017cel","orcid":"https://orcid.org/0000-0002-3462-9144"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Filip Kruzel","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5083798800","display_name":"Mateusz Nytko","orcid":"https://orcid.org/0000-0003-0606-1835"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mateusz Nytko","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5049462234"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.11701978,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"208","last_page":"215"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T14225","display_name":"Advanced Sensor and Control Systems","score":0.31630000472068787,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T14225","display_name":"Advanced Sensor and Control Systems","score":0.31630000472068787,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7035844326019287},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6252519488334656},{"id":"https://openalex.org/keywords/finite-element-method","display_name":"Finite element method","score":0.5790020227432251},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.52558833360672},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.3788577914237976},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.12508291006088257},{"id":"https://openalex.org/keywords/structural-engineering","display_name":"Structural engineering","score":0.08310678601264954}],"concepts":[{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7035844326019287},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6252519488334656},{"id":"https://openalex.org/C135628077","wikidata":"https://www.wikidata.org/wiki/Q220184","display_name":"Finite element method","level":2,"score":0.5790020227432251},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.52558833360672},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.3788577914237976},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12508291006088257},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.08310678601264954}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.7148/2024-0208","is_oa":true,"landing_page_url":"http://dx.doi.org/10.7148/2024-0208","pdf_url":"http://www.scs-europe.net/dlib/2024/ecms2024acceptedpapers/0208_fdem_ecms2024_0030.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ECMS 2024 Proceedings edited by Daniel Grzonka, Natalia Rylko, Grazyna Suchacka, Vladimir Mityushev","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.7148/2024-0208","is_oa":true,"landing_page_url":"http://dx.doi.org/10.7148/2024-0208","pdf_url":"http://www.scs-europe.net/dlib/2024/ecms2024acceptedpapers/0208_fdem_ecms2024_0030.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ECMS 2024 Proceedings edited by Daniel Grzonka, Natalia Rylko, Grazyna Suchacka, Vladimir Mityushev","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.46000000834465027,"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4400945385.pdf","grobid_xml":"https://content.openalex.org/works/W4400945385.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2051487156","https://openalex.org/W2073681303","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"This":[0,74],"article":[1],"analyses":[2],"the":[3,13,27,57,62,71,82,85,89,96,117,134],"performance":[4,31,86,120,136],"differences":[5],"between":[6],"two":[7,97],"generations":[8,98,152],"of":[9,84,99,103,119,137],"integrated":[10,43],"GPUs":[11,44,55,100],"on":[12,46],"Finite":[14],"Element":[15],"Method":[16],"(FEM)":[17],"Numerical":[18],"Integration":[19],"Algorithm.":[20],"The":[21,54],"algorithm":[22],"employs":[23],"linear":[24],"approximation":[25],"in":[26,70,88,101,129],"convection-diffusion":[28],"problem,":[29],"where":[30],"is":[32],"highly":[33],"memory-dependent.":[34],"We":[35,93],"used":[36],"Intel":[37,47],"11th":[38],"and":[39,66,110,151],"12th-generation":[40],"processors":[41],"with":[42],"based":[45],"Xe-LP":[48],"architecture":[49],"to":[50,80,114,143],"conduct":[51],"our":[52],"research.":[53],"have":[56],"same":[58],"parameters":[59],"except":[60],"for":[61],"slightly":[63],"lower":[64],"bandwidth":[65],"a":[67,126],"narrower":[68],"bus":[69],"newer":[72],"architecture.":[73],"makes":[75],"it":[76],"an":[77,138],"ideal":[78],"choice":[79],"test":[81],"significance":[83],"loss":[87],"highly-parallel":[90],"memory-bound":[91],"algorithm.":[92,139],"also":[94],"compare":[95],"terms":[102],"their":[104],"computational":[105],"power,":[106],"memory":[107],"access":[108],"patterns,":[109],"other":[111],"relevant":[112],"factors":[113],"identify":[115],"all":[116],"sources":[118],"loss.":[121],"Our":[122,140],"research":[123],"shows":[124],"how":[125,147],"slight":[127],"change":[128],"one":[130],"parameter":[131],"can":[132],"affect":[133,153],"overall":[135],"experiments":[141],"aim":[142],"provide":[144],"insight":[145],"into":[146],"different":[148],"GPU":[149],"architectures":[150],"FEM":[154],"numerical":[155],"integration":[156],"performance.":[157]},"counts_by_year":[],"updated_date":"2026-03-13T14:20:09.374765","created_date":"2025-10-10T00:00:00"}