{"id":"https://openalex.org/W3119123388","doi":"https://doi.org/10.1109/llvmhpchipar51896.2020.00013","title":"A Case Study and Characterization of a Many-socket, Multi-tier NUMA HPC Platform","display_name":"A Case Study and Characterization of a Many-socket, Multi-tier NUMA HPC Platform","publication_year":2020,"publication_date":"2020-11-01","ids":{"openalex":"https://openalex.org/W3119123388","doi":"https://doi.org/10.1109/llvmhpchipar51896.2020.00013","mag":"3119123388"},"language":"en","primary_location":{"id":"doi:10.1109/llvmhpchipar51896.2020.00013","is_oa":false,"landing_page_url":"https://doi.org/10.1109/llvmhpchipar51896.2020.00013","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE/ACM 6th Workshop on the LLVM Compiler Infrastructure in HPC (LLVM-HPC) and Workshop on Hierarchical Parallelism for Exascale Computing (HiPar)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5003773058","display_name":"Connor Imes","orcid":"https://orcid.org/0000-0003-1683-8353"},"institutions":[{"id":"https://openalex.org/I32135785","display_name":"Foreign Service Institute","ror":"https://ror.org/05hb6w248","country_code":"US","type":"government","lineage":["https://openalex.org/I1340685415","https://openalex.org/I32135785"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Connor Imes","raw_affiliation_strings":["USC Information Sciences Institute,Arlington,VA,USA","USC Information Sciences Institute, Arlington, VA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"USC Information Sciences Institute,Arlington,VA,USA","institution_ids":["https://openalex.org/I32135785"]},{"raw_affiliation_string":"USC Information Sciences Institute, Arlington, VA, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016671058","display_name":"Steven Hofmeyr","orcid":"https://orcid.org/0000-0002-3299-472X"},"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":"Steven Hofmeyr","raw_affiliation_strings":["Lawrence Berkeley National Laboratory,Berkeley,CA,USA","Lawrence Berkeley National Laboratory, Berkeley, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lawrence Berkeley National Laboratory,Berkeley,CA,USA","institution_ids":["https://openalex.org/I148283060"]},{"raw_affiliation_string":"Lawrence Berkeley National Laboratory, Berkeley, CA, USA","institution_ids":["https://openalex.org/I148283060"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108734130","display_name":"Dong In D. Kang","orcid":null},"institutions":[{"id":"https://openalex.org/I32135785","display_name":"Foreign Service Institute","ror":"https://ror.org/05hb6w248","country_code":"US","type":"government","lineage":["https://openalex.org/I1340685415","https://openalex.org/I32135785"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dong In D. Kang","raw_affiliation_strings":["USC Information Sciences Institute,Arlington,VA,USA","USC Information Sciences Institute, Arlington, VA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"USC Information Sciences Institute,Arlington,VA,USA","institution_ids":["https://openalex.org/I32135785"]},{"raw_affiliation_string":"USC Information Sciences Institute, Arlington, VA, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023774940","display_name":"John Paul Walters","orcid":"https://orcid.org/0000-0001-5281-6237"},"institutions":[{"id":"https://openalex.org/I32135785","display_name":"Foreign Service Institute","ror":"https://ror.org/05hb6w248","country_code":"US","type":"government","lineage":["https://openalex.org/I1340685415","https://openalex.org/I32135785"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"John Paul Walters","raw_affiliation_strings":["USC Information Sciences Institute,Arlington,VA,USA","USC Information Sciences Institute, Arlington, VA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"USC Information Sciences Institute,Arlington,VA,USA","institution_ids":["https://openalex.org/I32135785"]},{"raw_affiliation_string":"USC Information Sciences Institute, Arlington, VA, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4508,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.56032172,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"15","issue":null,"first_page":"74","last_page":"84"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9998000264167786,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9994000196456909,"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/computer-science","display_name":"Computer science","score":0.8671215772628784},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6973865628242493},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6747323274612427},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.552937924861908},{"id":"https://openalex.org/keywords/memory-hierarchy","display_name":"Memory hierarchy","score":0.5187699794769287},{"id":"https://openalex.org/keywords/shared-memory","display_name":"Shared memory","score":0.49577316641807556},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.45095670223236084},{"id":"https://openalex.org/keywords/xeon","display_name":"Xeon","score":0.4336961507797241},{"id":"https://openalex.org/keywords/non-uniform-memory-access","display_name":"Non-uniform memory access","score":0.4241529703140259},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.3873429000377655},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.34556084871292114},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.3364575505256653},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.32920172810554504},{"id":"https://openalex.org/keywords/cpu-cache","display_name":"CPU cache","score":0.28398439288139343}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8671215772628784},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6973865628242493},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6747323274612427},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.552937924861908},{"id":"https://openalex.org/C2778100165","wikidata":"https://www.wikidata.org/wiki/Q1589327","display_name":"Memory hierarchy","level":3,"score":0.5187699794769287},{"id":"https://openalex.org/C133875982","wikidata":"https://www.wikidata.org/wiki/Q764810","display_name":"Shared memory","level":2,"score":0.49577316641807556},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.45095670223236084},{"id":"https://openalex.org/C145108525","wikidata":"https://www.wikidata.org/wiki/Q656154","display_name":"Xeon","level":2,"score":0.4336961507797241},{"id":"https://openalex.org/C133371097","wikidata":"https://www.wikidata.org/wiki/Q868014","display_name":"Non-uniform memory access","level":5,"score":0.4241529703140259},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.3873429000377655},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.34556084871292114},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3364575505256653},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.32920172810554504},{"id":"https://openalex.org/C189783530","wikidata":"https://www.wikidata.org/wiki/Q352090","display_name":"CPU cache","level":3,"score":0.28398439288139343},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C201148951","wikidata":"https://www.wikidata.org/wiki/Q5015976","display_name":"Cache coloring","level":4,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/llvmhpchipar51896.2020.00013","is_oa":false,"landing_page_url":"https://doi.org/10.1109/llvmhpchipar51896.2020.00013","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE/ACM 6th Workshop on the LLVM Compiler Infrastructure in HPC (LLVM-HPC) and Workshop on Hierarchical Parallelism for Exascale Computing (HiPar)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W1495021188","https://openalex.org/W1973923004","https://openalex.org/W1977661221","https://openalex.org/W1983545421","https://openalex.org/W2005202728","https://openalex.org/W2039789965","https://openalex.org/W2093188697","https://openalex.org/W2113679889","https://openalex.org/W2157948788","https://openalex.org/W2296250660","https://openalex.org/W2337228275","https://openalex.org/W2412864092","https://openalex.org/W2417690246","https://openalex.org/W2508028078","https://openalex.org/W2612615472","https://openalex.org/W2754016293","https://openalex.org/W2885584382","https://openalex.org/W2889881879","https://openalex.org/W2902041647","https://openalex.org/W2946150205","https://openalex.org/W2951799940","https://openalex.org/W2962703427","https://openalex.org/W2972900649","https://openalex.org/W2983811377","https://openalex.org/W2991157588","https://openalex.org/W3033725271","https://openalex.org/W3035587886","https://openalex.org/W3038187997","https://openalex.org/W3040269689","https://openalex.org/W4205568063","https://openalex.org/W6703177460","https://openalex.org/W6780697455"],"related_works":["https://openalex.org/W2791177606","https://openalex.org/W3210911584","https://openalex.org/W2043143850","https://openalex.org/W4252163020","https://openalex.org/W2594155508","https://openalex.org/W2545380179","https://openalex.org/W2056476515","https://openalex.org/W3083624021","https://openalex.org/W4220660085","https://openalex.org/W2070652215"],"abstract_inverted_index":{"As":[0],"the":[1,126,161,190,198,218],"number":[2],"of":[3,53,63,66,95,119,156,222],"processor":[4,80],"cores":[5,84],"and":[6,13,51,98,149,167,178],"sockets":[7,50],"on":[8,71],"HPC":[9,42,121,136,141,151],"compute":[10,43,122],"nodes":[11,44],"increase":[12],"systems":[14,58],"expose":[15],"more":[16,35,49,65],"hierarchical":[17],"non-uniform":[18],"memory":[19,31,99,186,226],"access":[20,187],"(NUMA)":[21],"architectures,":[22],"efficiently":[23],"scaling":[24,174,180,195],"applications":[25],"within":[26],"even":[27],"a":[28,72,90,106,139,146,154],"single":[29],"shared":[30,225],"system":[32,77],"is":[33,38],"becoming":[34],"challenging.":[36],"It":[37],"now":[39],"common":[40],"for":[41,135,175,184],"to":[45,109,159,215],"have":[46],"two":[47],"or":[48,114,209],"dozens":[52],"cores,":[54],"but":[55,182],"future":[56,120],"generation":[57],"may":[59,212],"contain":[60],"an":[61],"order":[62],"magnitude":[64],"each.":[67],"We":[68,124],"conduct":[69],"experiments":[70],"state-of-the-art":[73],"Intel":[74],"Xeon":[75],"Platinum":[76],"with":[78,153,197],"12":[79],"sockets,":[81],"totaling":[82],"288":[83],"(576":[85],"hardware":[86],"threads),":[87],"arranged":[88],"in":[89],"multi-tier":[91,128,219],"NUMA":[92,129,220],"hierarchy.":[93],"Platforms":[94],"this":[96],"scale":[97],"hierarchy":[100],"are":[101],"uncommon":[102],"today,":[103],"providing":[104],"us":[105],"unique":[107],"opportunity":[108],"empirically":[110],"evaluate-rather":[111],"than":[112],"model":[113],"simulate-an":[115],"architecture":[116],"potentially":[117],"representative":[118],"nodes.":[123],"quantify":[125],"platform's":[127],"patterns,":[130,166],"then":[131],"evaluate":[132],"its":[133],"suitability":[134],"workloads":[137],"using":[138],"modern":[140],"metagenome":[142],"assembler":[143],"application":[144],"as":[145],"case":[147],"study,":[148],"other":[150],"benchmarks":[152],"variety":[155],"parallelization":[157],"techniques":[158],"characterize":[160],"system's":[162],"performance,":[163],"scalability,":[164],"I/O":[165],"performance/power":[168],"behavior.":[169],"Our":[170],"results":[171],"demonstrate":[172],"near-perfect":[173],"embarrassingly":[176],"parallel":[177],"weak":[179],"workloads,":[181],"challenges":[183],"random":[185],"workloads.":[188],"For":[189],"latter,":[191],"we":[192],"find":[193],"poor":[194],"performance":[196],"default":[199],"scheduling":[200],"approaches-e.g.,":[201],"which":[202],"do":[203],"not":[204],"pin":[205],"threads-suggesting":[206],"that":[207],"userspace":[208],"kernel":[210],"schedulers":[211],"require":[213],"changes":[214],"better":[216],"manage":[217],"hierarchies":[221],"very":[223],"large":[224],"platforms.":[227]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
