{"id":"https://openalex.org/W2998114460","doi":"https://doi.org/10.1109/p3hpc49587.2019.00008","title":"Performance Portability of Multi-Material Kernels","display_name":"Performance Portability of Multi-Material Kernels","publication_year":2019,"publication_date":"2019-11-01","ids":{"openalex":"https://openalex.org/W2998114460","doi":"https://doi.org/10.1109/p3hpc49587.2019.00008","mag":"2998114460"},"language":"en","primary_location":{"id":"doi:10.1109/p3hpc49587.2019.00008","is_oa":false,"landing_page_url":"https://doi.org/10.1109/p3hpc49587.2019.00008","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE/ACM International Workshop on Performance, Portability and Productivity in HPC (P3HPC)","raw_type":"proceedings-article"},"type":"article","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/A5048478302","display_name":"Istv\u00e1n Z. Reguly","orcid":"https://orcid.org/0000-0002-4385-4204"},"institutions":[{"id":"https://openalex.org/I31882830","display_name":"P\u00e1zm\u00e1ny P\u00e9ter Catholic University","ror":"https://ror.org/05v9kya57","country_code":"HU","type":"education","lineage":["https://openalex.org/I31882830"]}],"countries":["HU"],"is_corresponding":true,"raw_author_name":"Istvan Z. Reguly","raw_affiliation_strings":["Pazmaany Peter Catholic University, Budapest, Hungary"],"affiliations":[{"raw_affiliation_string":"Pazmaany Peter Catholic University, Budapest, Hungary","institution_ids":["https://openalex.org/I31882830"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5048478302"],"corresponding_institution_ids":["https://openalex.org/I31882830"],"apc_list":null,"apc_paid":null,"fwci":2.8892,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.91325333,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"26","last_page":"35"},"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.996999979019165,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9961000084877014,"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/software-portability","display_name":"Software portability","score":0.955487847328186},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8618834614753723},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.7664269804954529},{"id":"https://openalex.org/keywords/ibm","display_name":"IBM","score":0.6583538055419922},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6103212237358093},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.5479287505149841},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.5132689476013184},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4761999845504761},{"id":"https://openalex.org/keywords/implementation","display_name":"Implementation","score":0.4639427661895752},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.4460870027542114},{"id":"https://openalex.org/keywords/instruction-set","display_name":"Instruction set","score":0.4459437429904938},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.3877537250518799},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.2634744942188263}],"concepts":[{"id":"https://openalex.org/C63000827","wikidata":"https://www.wikidata.org/wiki/Q3080428","display_name":"Software portability","level":2,"score":0.955487847328186},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8618834614753723},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.7664269804954529},{"id":"https://openalex.org/C70388272","wikidata":"https://www.wikidata.org/wiki/Q5968558","display_name":"IBM","level":2,"score":0.6583538055419922},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6103212237358093},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.5479287505149841},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.5132689476013184},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4761999845504761},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.4639427661895752},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.4460870027542114},{"id":"https://openalex.org/C202491316","wikidata":"https://www.wikidata.org/wiki/Q272683","display_name":"Instruction set","level":2,"score":0.4459437429904938},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.3877537250518799},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2634744942188263},{"id":"https://openalex.org/C171250308","wikidata":"https://www.wikidata.org/wiki/Q11468","display_name":"Nanotechnology","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/p3hpc49587.2019.00008","is_oa":false,"landing_page_url":"https://doi.org/10.1109/p3hpc49587.2019.00008","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE/ACM International Workshop on Performance, Portability and Productivity in HPC (P3HPC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Decent work and economic growth","id":"https://metadata.un.org/sdg/8","score":0.49000000953674316}],"awards":[{"id":"https://openalex.org/G5783490283","display_name":null,"funder_award_id":"EP/P020224/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1483717008","https://openalex.org/W1717365219","https://openalex.org/W2019143817","https://openalex.org/W2049846809","https://openalex.org/W2078794610","https://openalex.org/W2105672886","https://openalex.org/W2254450385","https://openalex.org/W2274477847","https://openalex.org/W2296126509","https://openalex.org/W2506485539","https://openalex.org/W2743401659","https://openalex.org/W2791673912","https://openalex.org/W2810547602","https://openalex.org/W2913310273","https://openalex.org/W3101543398","https://openalex.org/W4245673786","https://openalex.org/W6697508226","https://openalex.org/W6742290553","https://openalex.org/W7035639922"],"related_works":["https://openalex.org/W4311649166","https://openalex.org/W2081245617","https://openalex.org/W4321009748","https://openalex.org/W3213381848","https://openalex.org/W2292282166","https://openalex.org/W1567366217","https://openalex.org/W3162678246","https://openalex.org/W1583465708","https://openalex.org/W4287068551","https://openalex.org/W2267856444"],"abstract_inverted_index":{"Trying":[0],"to":[1,17],"improve":[2],"performance,":[3,131],"portability,":[4,26,132],"and":[5,47,56,74,76,87,95,112,126,133],"productivity":[6,32],"of":[7,31,42,53,103],"an":[8],"application":[9],"presents":[10],"non-trivial":[11],"trade-offs,":[12],"which":[13],"are":[14,65],"often":[15],"difficult":[16],"quantify.":[18],"Recent":[19],"work":[20],"has":[21],"developed":[22],"metrics":[23],"for":[24],"performance":[25,121,124],"as":[27,90,92],"well":[28,91],"some":[29],"aspects":[30],"-":[33],"in":[34],"this":[35],"case":[36],"study,":[37],"we":[38],"present":[39,118],"a":[40,119],"set":[41],"challeng-":[43],"ing":[44],"computational":[45],"kernels":[46,64],"their":[48],"implementations":[49],"from":[50],"the":[51,101],"domain":[52],"multi-material":[54],"simulations,":[55],"evaluate":[57],"them":[58],"using":[59,67],"these":[60],"metrics.":[61],"Three":[62],"key":[63],"implemented":[66],"OpenMP,":[68],"OpenMP":[69],"offload,":[70],"OpenACC,":[71],"CUDA,":[72],"SYCL,":[73],"KOKKOS,":[75],"tested":[77],"on":[78],"ARM":[79],"ThunderX2,":[80],"IBM":[81,110],"Power":[82],"9,":[83],"Intel":[84],"KNL,":[85],"Broadwell,":[86],"Skylake":[88],"CPUs,":[89],"NVIDIA":[93],"P100":[94],"V100":[96],"GPUs.":[97],"We":[98,117],"also":[99],"consider":[100],"choice":[102],"compilers,":[104,114],"evaluating":[105],"LLVM/Clang,":[106],"GCC,":[107],"PGI,":[108],"Intel,":[109],"XL,":[111],"Cray":[113],"where":[115],"available.":[116],"detailed":[120],"analysis,":[122],"calculate":[123],"portability":[125],"code":[127],"divergence":[128],"metrics,":[129],"contrasting":[130],"productivity.":[134]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}