{"id":"https://openalex.org/W4416004312","doi":"https://doi.org/10.1145/3731599.3767506","title":"Weak Scaling of NVSHMEM Applied To Hashed Distributed Structured Data","display_name":"Weak Scaling of NVSHMEM Applied To Hashed Distributed Structured Data","publication_year":2025,"publication_date":"2025-11-07","ids":{"openalex":"https://openalex.org/W4416004312","doi":"https://doi.org/10.1145/3731599.3767506"},"language":null,"primary_location":{"id":"doi:10.1145/3731599.3767506","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3731599.3767506","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 SC '25 Workshops of the International Conference for High Performance Computing, Networking, Storage and Analysis","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3731599.3767506","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5109551776","display_name":"Anna Davis","orcid":"https://orcid.org/0009-0005-5345-1942"},"institutions":[{"id":"https://openalex.org/I51556381","display_name":"University of Virginia","ror":"https://ror.org/0153tk833","country_code":"US","type":"education","lineage":["https://openalex.org/I51556381"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Andrew Davis","raw_affiliation_strings":["University of Virginia, Charlottesville, USA"],"raw_orcid":"https://orcid.org/0009-0005-5345-1942","affiliations":[{"raw_affiliation_string":"University of Virginia, Charlottesville, USA","institution_ids":["https://openalex.org/I51556381"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082013692","display_name":"Hans Johansen","orcid":"https://orcid.org/0000-0002-9644-9982"},"institutions":[{"id":"https://openalex.org/I148283060","display_name":"Lawrence Berkeley National Laboratory","ror":"https://ror.org/02jbv0t02","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I148283060","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hans Johansen","raw_affiliation_strings":["Lawrence Berkeley National Laboratory, Berkely, USA"],"raw_orcid":"https://orcid.org/0000-0002-9644-9982","affiliations":[{"raw_affiliation_string":"Lawrence Berkeley National Laboratory, Berkely, USA","institution_ids":["https://openalex.org/I148283060"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069006934","display_name":"Xinfeng Gao","orcid":"https://orcid.org/0000-0002-7313-7070"},"institutions":[{"id":"https://openalex.org/I51556381","display_name":"University of Virginia","ror":"https://ror.org/0153tk833","country_code":"US","type":"education","lineage":["https://openalex.org/I51556381"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xinfeng Gao","raw_affiliation_strings":["University of Virginia, Charlottesville, USA"],"raw_orcid":"https://orcid.org/0000-0002-7313-7070","affiliations":[{"raw_affiliation_string":"University of Virginia, Charlottesville, USA","institution_ids":["https://openalex.org/I51556381"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068702699","display_name":"Stephen M. Guzik","orcid":"https://orcid.org/0000-0001-9163-8787"},"institutions":[{"id":"https://openalex.org/I51556381","display_name":"University of Virginia","ror":"https://ror.org/0153tk833","country_code":"US","type":"education","lineage":["https://openalex.org/I51556381"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Stephen Guzik","raw_affiliation_strings":["University of Virginia, Charlottesville, USA"],"raw_orcid":"https://orcid.org/0000-0001-9163-8787","affiliations":[{"raw_affiliation_string":"University of Virginia, Charlottesville, USA","institution_ids":["https://openalex.org/I51556381"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5109551776"],"corresponding_institution_ids":["https://openalex.org/I51556381"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.35112936,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1302","last_page":"1313"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.13449999690055847,"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":0.13449999690055847,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.07980000227689743,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.07720000296831131,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/scaling","display_name":"Scaling","score":0.7145000100135803},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6132000088691711},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5871999859809875},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.46470001339912415},{"id":"https://openalex.org/keywords/constant","display_name":"Constant (computer programming)","score":0.44530001282691956},{"id":"https://openalex.org/keywords/flexibility","display_name":"Flexibility (engineering)","score":0.4219000041484833},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.38109999895095825},{"id":"https://openalex.org/keywords/message-passing","display_name":"Message passing","score":0.3792000114917755}],"concepts":[{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.7145000100135803},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7116000056266785},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6132000088691711},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5871999859809875},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5347999930381775},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5080999732017517},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.46470001339912415},{"id":"https://openalex.org/C2777027219","wikidata":"https://www.wikidata.org/wiki/Q1284190","display_name":"Constant (computer programming)","level":2,"score":0.44530001282691956},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.4219000041484833},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3982999920845032},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.38109999895095825},{"id":"https://openalex.org/C854659","wikidata":"https://www.wikidata.org/wiki/Q1859284","display_name":"Message passing","level":2,"score":0.3792000114917755},{"id":"https://openalex.org/C110121322","wikidata":"https://www.wikidata.org/wiki/Q865811","display_name":"Distribution (mathematics)","level":2,"score":0.3569999933242798},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.3499999940395355},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.34790000319480896},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.34689998626708984},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.3312999904155731},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.3199000060558319},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.3068000078201294},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.28630000352859497},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2703999876976013},{"id":"https://openalex.org/C179145077","wikidata":"https://www.wikidata.org/wiki/Q5154130","display_name":"Communication complexity","level":2,"score":0.266400009393692},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.25780001282691956}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3731599.3767506","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3731599.3767506","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 SC '25 Workshops of the International Conference for High Performance Computing, Networking, Storage and Analysis","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3731599.3767506","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3731599.3767506","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 SC '25 Workshops of the International Conference for High Performance Computing, Networking, Storage and Analysis","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5667354828","display_name":null,"funder_award_id":"2403579","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1573878051","https://openalex.org/W1837242739","https://openalex.org/W2095954861","https://openalex.org/W2145478293","https://openalex.org/W2163852233","https://openalex.org/W2944412207","https://openalex.org/W2984920043","https://openalex.org/W3132763358","https://openalex.org/W3184127410","https://openalex.org/W4388581111","https://openalex.org/W4388581217","https://openalex.org/W4401705886","https://openalex.org/W4406164050","https://openalex.org/W4407413392","https://openalex.org/W6958147036"],"related_works":[],"abstract_inverted_index":{"We":[0,17,108],"present":[1],"a":[2,19,74,79,86],"parallel,":[3],"hash-based":[4],"software":[5],"library,":[6],"HashBrick,":[7],"for":[8,45,53,60,143],"sparse,":[9],"block-structured":[10],"applications":[11],"on":[12,85],"CPUs":[13],"and":[14,30,48,78,101,131],"NVIDIA":[15,87],"GPUs.":[16],"use":[18],"brick-based":[20],"layout,":[21],"where":[22],"data":[23,47],"is":[24,58,99],"aggregated":[25],"into":[26],"small":[27],"regular":[28],"bricks,":[29],"hashes":[31],"hide":[32],"the":[33,96,111,114],"complexity":[34],"of":[35,43,63,67,116],"neighbor":[36],"indexing.":[37],"This":[38],"exposes":[39],"an":[40,64],"extra":[41],"level":[42],"flexibility":[44],"irregular":[46,65],"avoids":[49],"packing":[50],"communication":[51,62,102],"buffers":[52],"ghost":[54,68,117],"zones.":[55],"One-sided":[56],"NVSHMEM":[57,132],"used":[59],"GPU-GPU":[61],"distribution":[66,115],"bricks.":[69],"Weak":[70],"scaling":[71,124],"experiments":[72],"using":[73],"high-order":[75],"CFD":[76],"application":[77],"Jacobi":[80],"iteration":[81],"benchmark":[82],"were":[83],"run":[84],"GH200":[88],"cluster.":[89],"For":[90],"constant":[91],"problem":[92],"size":[93],"per":[94],"node,":[95],"computation":[97],"time":[98],"constant,":[100],"scales":[103],"well":[104],"despite":[105],"load":[106],"imbalance.":[107],"find":[109],"that":[110,129],"variation":[112],"in":[113],"bricks":[118],"more":[119],"or":[120],"less":[121],"correlates":[122],"with":[123],"efficiency.":[125],"Our":[126],"results":[127],"show":[128],"MPI":[130,137],"have":[133],"similar":[134],"scaling,":[135],"but":[136],"wall-clock":[138],"times":[139],"are":[140],"64-84%":[141],"higher":[142],"these":[144],"experiments.":[145]},"counts_by_year":[],"updated_date":"2026-05-04T08:30:34.212998","created_date":"2025-11-07T00:00:00"}