{"id":"https://openalex.org/W7166699340","doi":"https://doi.org/10.7148/2026-0215","title":"Application of avx512 technique to the finite element solver parfes","display_name":"Application of avx512 technique to the finite element solver parfes","publication_year":2026,"publication_date":"2026-06-23","ids":{"openalex":"https://openalex.org/W7166699340","doi":"https://doi.org/10.7148/2026-0215"},"language":null,"primary_location":{"id":"doi:10.7148/2026-0215","is_oa":true,"landing_page_url":"https://doi.org/10.7148/2026-0215","pdf_url":"https://doi.org/10.7148/2026-0215","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ECMS 2026 Proceedings edited by Filippo Sanfilippo, Florenc Demrozi, Fabio Sgarbossa, Mohammad Poursina","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.7148/2026-0215","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139648504","display_name":"Sergiy Fialko","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Sergiy Fialko","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5139648504"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"215","last_page":"220"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.361299991607666,"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":0.361299991607666,"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/T10792","display_name":"Matrix Theory and Algorithms","score":0.2094999998807907,"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/T11697","display_name":"Numerical Methods and Algorithms","score":0.1462000012397766,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/microkernel","display_name":"Microkernel","score":0.8654999732971191},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.5982999801635742},{"id":"https://openalex.org/keywords/solver","display_name":"Solver","score":0.5285000205039978},{"id":"https://openalex.org/keywords/cholesky-decomposition","display_name":"Cholesky decomposition","score":0.5112000107765198},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.5067999958992004},{"id":"https://openalex.org/keywords/blocking","display_name":"Blocking (statistics)","score":0.4934000074863434},{"id":"https://openalex.org/keywords/multiplication","display_name":"Multiplication (music)","score":0.4921000003814697},{"id":"https://openalex.org/keywords/workstation","display_name":"Workstation","score":0.47130000591278076}],"concepts":[{"id":"https://openalex.org/C2777127024","wikidata":"https://www.wikidata.org/wiki/Q726378","display_name":"Microkernel","level":2,"score":0.8654999732971191},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7699999809265137},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6116999983787537},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.5982999801635742},{"id":"https://openalex.org/C2778770139","wikidata":"https://www.wikidata.org/wiki/Q1966904","display_name":"Solver","level":2,"score":0.5285000205039978},{"id":"https://openalex.org/C34727166","wikidata":"https://www.wikidata.org/wiki/Q515375","display_name":"Cholesky decomposition","level":3,"score":0.5112000107765198},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5067999958992004},{"id":"https://openalex.org/C144745244","wikidata":"https://www.wikidata.org/wiki/Q4927286","display_name":"Blocking (statistics)","level":2,"score":0.4934000074863434},{"id":"https://openalex.org/C2780595030","wikidata":"https://www.wikidata.org/wiki/Q3860309","display_name":"Multiplication (music)","level":2,"score":0.4921000003814697},{"id":"https://openalex.org/C67953723","wikidata":"https://www.wikidata.org/wiki/Q192525","display_name":"Workstation","level":2,"score":0.47130000591278076},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.4442000091075897},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.43050000071525574},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.41780000925064087},{"id":"https://openalex.org/C55526617","wikidata":"https://www.wikidata.org/wiki/Q719375","display_name":"Operand","level":2,"score":0.3840999901294708},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.37779998779296875},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.3301999866962433},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.32100000977516174},{"id":"https://openalex.org/C123213974","wikidata":"https://www.wikidata.org/wiki/Q833089","display_name":"LU decomposition","level":4,"score":0.2791999876499176},{"id":"https://openalex.org/C85817219","wikidata":"https://www.wikidata.org/wiki/Q884772","display_name":"Block matrix","level":3,"score":0.27709999680519104},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.2759999930858612},{"id":"https://openalex.org/C2778400913","wikidata":"https://www.wikidata.org/wiki/Q1639024","display_name":"Mathematical software","level":3,"score":0.26809999346733093},{"id":"https://openalex.org/C66882249","wikidata":"https://www.wikidata.org/wiki/Q169336","display_name":"Homogeneous","level":2,"score":0.25380000472068787},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.25360000133514404},{"id":"https://openalex.org/C6802819","wikidata":"https://www.wikidata.org/wiki/Q1072174","display_name":"Linear system","level":2,"score":0.25220000743865967}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.7148/2026-0215","is_oa":true,"landing_page_url":"https://doi.org/10.7148/2026-0215","pdf_url":"https://doi.org/10.7148/2026-0215","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ECMS 2026 Proceedings edited by Filippo Sanfilippo, Florenc Demrozi, Fabio Sgarbossa, Mohammad Poursina","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.7148/2026-0215","is_oa":true,"landing_page_url":"https://doi.org/10.7148/2026-0215","pdf_url":"https://doi.org/10.7148/2026-0215","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ECMS 2026 Proceedings edited by Filippo Sanfilippo, Florenc Demrozi, Fabio Sgarbossa, Mohammad Poursina","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7","score":0.5331562161445618}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166699340.pdf","grobid_xml":"https://content.openalex.org/works/W7166699340.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0,29,41],"microkernel":[1,87,130,160],"of":[2,21,59,74,99,106,109],"dense":[3],"matrix":[4,77,137],"blocks":[5,101],"multiplication":[6,78,139],"is":[7,31,187],"considered":[8],"in":[9,67,71,136],"relation":[10],"to":[11,16,102,149,177],"direct":[12],"supernodal":[13],"solvers":[14],"designed":[15],"solve":[17],"sparse":[18],"symmetric":[19],"systems":[20],"linear":[22],"algebraic":[23],"equations":[24],"using":[25],"the":[26,49,57,60,72,75,85,90,104,128,141,147,156,178,182],"Cholesky":[27],"method.":[28],"method":[30],"intended":[32],"for":[33,43,164,189],"computers":[34],"with":[35,169],"processors":[36,163,191],"that":[37,48],"support":[38],"AVX512":[39],"instructions.":[40],"reason":[42],"creating":[44],"this":[45,159],"approach":[46,116],"was":[47],"Intel":[50,162,183],"MKL":[51,153,184],"library":[52,79],"does":[53],"not":[54],"always":[55],"utilize":[56,151],"capabilities":[58],"latest":[61],"AMD":[62,143],"processor":[63,91,118],"generations":[64],"correctly,":[65],"resulting":[66],"a":[68,126,132],"significant":[69,133],"decrease":[70],"performance":[73,134,173],"dgemm":[76,179],"procedure.":[80],"To":[81],"achieve":[82],"high":[83],"performance,":[84],"proposed":[86],"utilizes":[88],"blocking":[89,93],"cache,":[92],"ZMM":[94,113],"registers,":[95],"and":[96,121,167],"repacking":[97],"elements":[98,111],"multiplied":[100],"enable":[103],"use":[105],"fast":[107],"loading":[108],"these":[110,190],"into":[112],"registers.":[114],"This":[115],"minimizes":[117],"pipeline":[119],"delays":[120],"leverages":[122],"OpenMP-based":[123],"multithreading.":[124],"As":[125],"result,":[127],"developed":[129],"enabled":[131],"increase":[135],"block":[138],"on":[140,161],"aforementioned":[142],"processors,":[144],"while":[145],"maintaining":[146],"ability":[148],"effectively":[150],"other":[152],"procedures.":[154],"At":[155],"same":[157],"time,":[158],"desktops,":[165],"laptops,":[166],"workstations":[168],"shared":[170],"memory":[171],"delivers":[172],"only":[174],"slightly":[175],"inferior":[176],"procedure":[180],"from":[181],"library,":[185],"which":[186],"optimized":[188],"as":[192,194],"much":[193],"possible.":[195]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-07-01T00:00:00"}