{"id":"https://openalex.org/W4416004315","doi":"https://doi.org/10.1145/3731599.3767519","title":"Extending THAPI with CXI Hardware Counter Sampling for High Resolution NIC Telemetry","display_name":"Extending THAPI with CXI Hardware Counter Sampling for High Resolution NIC Telemetry","publication_year":2025,"publication_date":"2025-11-07","ids":{"openalex":"https://openalex.org/W4416004315","doi":"https://doi.org/10.1145/3731599.3767519"},"language":null,"primary_location":{"id":"doi:10.1145/3731599.3767519","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3731599.3767519","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/10.1145/3731599.3767519","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5026241102","display_name":"Nathan Nichols","orcid":"https://orcid.org/0000-0002-7386-8893"},"institutions":[{"id":"https://openalex.org/I1282105669","display_name":"Argonne National Laboratory","ror":"https://ror.org/05gvnxz63","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282105669","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Nathan Nichols","raw_affiliation_strings":["Argonne National Laboratory, Lemont, USA"],"affiliations":[{"raw_affiliation_string":"Argonne National Laboratory, Lemont, USA","institution_ids":["https://openalex.org/I1282105669"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047914322","display_name":"Thomas Applencourt","orcid":"https://orcid.org/0000-0001-7522-9449"},"institutions":[{"id":"https://openalex.org/I1282105669","display_name":"Argonne National Laboratory","ror":"https://ror.org/05gvnxz63","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282105669","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Thomas Applencourt","raw_affiliation_strings":["Argonne National Laboratory, Lemont, USA"],"affiliations":[{"raw_affiliation_string":"Argonne National Laboratory, Lemont, USA","institution_ids":["https://openalex.org/I1282105669"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5026241102"],"corresponding_institution_ids":["https://openalex.org/I1282105669"],"apc_list":null,"apc_paid":null,"fwci":1.6666,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.89428436,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1601","last_page":"1610"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12216","display_name":"Network Time Synchronization Technologies","score":0.3418000042438507,"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"}},"topics":[{"id":"https://openalex.org/T12216","display_name":"Network Time Synchronization Technologies","score":0.3418000042438507,"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/T12127","display_name":"Software System Performance and Reliability","score":0.19830000400543213,"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/T10933","display_name":"Real-Time Systems Scheduling","score":0.08389999717473984,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/tracing","display_name":"Tracing","score":0.7717000246047974},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.5271000266075134},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.5138000249862671},{"id":"https://openalex.org/keywords/trace","display_name":"TRACE (psycholinguistics)","score":0.5095000267028809},{"id":"https://openalex.org/keywords/timeline","display_name":"Timeline","score":0.48010000586509705},{"id":"https://openalex.org/keywords/interface","display_name":"Interface (matter)","score":0.4447999894618988},{"id":"https://openalex.org/keywords/plug-and-play","display_name":"Plug and play","score":0.4228000044822693},{"id":"https://openalex.org/keywords/network-interface","display_name":"Network interface","score":0.39329999685287476},{"id":"https://openalex.org/keywords/telemetry","display_name":"Telemetry","score":0.38019999861717224}],"concepts":[{"id":"https://openalex.org/C138673069","wikidata":"https://www.wikidata.org/wiki/Q322229","display_name":"Tracing","level":2,"score":0.7717000246047974},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7613000273704529},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.5271000266075134},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.5138000249862671},{"id":"https://openalex.org/C75291252","wikidata":"https://www.wikidata.org/wiki/Q1315756","display_name":"TRACE (psycholinguistics)","level":2,"score":0.5095000267028809},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.5077000260353088},{"id":"https://openalex.org/C4438859","wikidata":"https://www.wikidata.org/wiki/Q186117","display_name":"Timeline","level":2,"score":0.48010000586509705},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.45879998803138733},{"id":"https://openalex.org/C113843644","wikidata":"https://www.wikidata.org/wiki/Q901882","display_name":"Interface (matter)","level":4,"score":0.4447999894618988},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.4343999922275543},{"id":"https://openalex.org/C2780070844","wikidata":"https://www.wikidata.org/wiki/Q857815","display_name":"Plug and play","level":2,"score":0.4228000044822693},{"id":"https://openalex.org/C103987645","wikidata":"https://www.wikidata.org/wiki/Q985806","display_name":"Network interface","level":3,"score":0.39329999685287476},{"id":"https://openalex.org/C183121708","wikidata":"https://www.wikidata.org/wiki/Q209867","display_name":"Telemetry","level":2,"score":0.38019999861717224},{"id":"https://openalex.org/C157497606","wikidata":"https://www.wikidata.org/wiki/Q603227","display_name":"traceroute","level":3,"score":0.3783000111579895},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.3546999990940094},{"id":"https://openalex.org/C3020199158","wikidata":"https://www.wikidata.org/wiki/Q210521","display_name":"High resolution","level":2,"score":0.3472000062465668},{"id":"https://openalex.org/C4924752","wikidata":"https://www.wikidata.org/wiki/Q184148","display_name":"Plug-in","level":2,"score":0.3379000127315521},{"id":"https://openalex.org/C2779696439","wikidata":"https://www.wikidata.org/wiki/Q7512811","display_name":"Signature (topology)","level":2,"score":0.3091000020503998},{"id":"https://openalex.org/C19527686","wikidata":"https://www.wikidata.org/wiki/Q1665453","display_name":"System integration","level":2,"score":0.30820000171661377},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.30720001459121704},{"id":"https://openalex.org/C81877898","wikidata":"https://www.wikidata.org/wiki/Q1965787","display_name":"Network monitoring","level":2,"score":0.2985999882221222},{"id":"https://openalex.org/C195563490","wikidata":"https://www.wikidata.org/wiki/Q180368","display_name":"Network congestion","level":3,"score":0.2944999933242798},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.28630000352859497},{"id":"https://openalex.org/C2778751112","wikidata":"https://www.wikidata.org/wiki/Q835016","display_name":"Window (computing)","level":2,"score":0.2802000045776367},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.26969999074935913},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.26840001344680786},{"id":"https://openalex.org/C119404949","wikidata":"https://www.wikidata.org/wiki/Q4503","display_name":"Network switch","level":2,"score":0.2535000145435333}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3731599.3767519","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3731599.3767519","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:10.1145/3731599.3767519","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3731599.3767519","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":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":2,"referenced_works":["https://openalex.org/W2101778912","https://openalex.org/W2136434791"],"related_works":[],"abstract_inverted_index":{"High":[0],"performance":[1,107],"computing":[2],"(HPC)":[3],"applications":[4],"are":[5],"sensitive":[6],"to":[7,47],"network":[8,19,22,89],"variability,":[9],"yet":[10],"existing":[11],"tracing":[12,51,136],"tools":[13],"lack":[14],"insight":[15],"into":[16,73,133],"low":[17],"level":[18],"behavior.":[20],"Modern":[21],"interface":[23],"controllers":[24],"(NICs),":[25],"such":[26,109],"as":[27,110],"HPE\u2019s":[28],"Slingshot-11":[29],"Cassini,":[30],"provide":[31],"detailed":[32],"hardware":[33],"counters":[34,69],"that":[35],"can":[36],"reveal":[37],"conditions":[38],"like":[39],"congestion":[40,111],"and":[41,70,91,103,113,120,138],"retries,":[42],"but":[43],"remain":[44],"underused":[45],"due":[46],"limited":[48],"integration":[49,132],"with":[50,58],"frameworks.":[52],"We":[53],"extend":[54],"the":[55,78,129],"THAPI":[56],"framework":[57],"a":[59,134],"sampling":[60,101],"plugin":[61],"for":[62,142],"Cassini\u2019s":[63],"CXI":[64],"interface,":[65],"periodically":[66],"collecting":[67],"NIC":[68],"integrating":[71],"them":[72],"HPC":[74,144],"trace":[75],"timelines":[76],"via":[77],"iprof":[79],"tool.":[80],"Data":[81],"is":[82],"visualized":[83],"in":[84],"Perfetto,":[85],"enabling":[86],"correlation":[87],"between":[88],"telemetry":[90],"application":[92],"events.":[93],"Our":[94],"approach":[95],"imposes":[96],"negligible":[97],"overhead":[98],"at":[99],"typical":[100],"rates":[102],"exposes":[104],"previously":[105],"hidden":[106],"factors,":[108],"delays":[112],"load":[114],"imbalances.":[115],"Case":[116],"studies":[117],"on":[118],"point-to-point":[119],"collective":[121],"patterns":[122],"demonstrate":[123],"new":[124],"diagnostic":[125],"capabilities.":[126],"Contributions":[127],"include":[128],"plugin\u2019s":[130],"design,":[131],"state-of-the-art":[135],"toolchain,":[137],"evaluation":[139],"highlighting":[140],"opportunities":[141],"improved":[143],"communication":[145],"performance.":[146]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-11-07T00:00:00"}
