{"id":"https://openalex.org/W4415250893","doi":"https://doi.org/10.1109/hpec67600.2025.11196678","title":"Load Imbalance in HPC Applications: Improved Profiling and New Ways to Use Wasted Cycles","display_name":"Load Imbalance in HPC Applications: Improved Profiling and New Ways to Use Wasted Cycles","publication_year":2025,"publication_date":"2025-09-15","ids":{"openalex":"https://openalex.org/W4415250893","doi":"https://doi.org/10.1109/hpec67600.2025.11196678"},"language":"en","primary_location":{"id":"doi:10.1109/hpec67600.2025.11196678","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpec67600.2025.11196678","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE High Performance Extreme Computing Conference (HPEC)","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/A5012033077","display_name":"Shining Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I111088046","display_name":"Boston University","ror":"https://ror.org/05qwgg493","country_code":"US","type":"education","lineage":["https://openalex.org/I111088046"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Shining Yang","raw_affiliation_strings":["Boston University,Department of Electrical and Computer Engineering"],"affiliations":[{"raw_affiliation_string":"Boston University,Department of Electrical and Computer Engineering","institution_ids":["https://openalex.org/I111088046"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031814188","display_name":"Xiteng Yao","orcid":null},"institutions":[{"id":"https://openalex.org/I111088046","display_name":"Boston University","ror":"https://ror.org/05qwgg493","country_code":"US","type":"education","lineage":["https://openalex.org/I111088046"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiteng Yao","raw_affiliation_strings":["Boston University,Department of Electrical and Computer Engineering"],"affiliations":[{"raw_affiliation_string":"Boston University,Department of Electrical and Computer Engineering","institution_ids":["https://openalex.org/I111088046"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060935056","display_name":"Grace Nansamba","orcid":null},"institutions":[{"id":"https://openalex.org/I63920570","display_name":"Tennessee Technological University","ror":"https://ror.org/05drmrq39","country_code":"US","type":"education","lineage":["https://openalex.org/I63920570"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Grace Nansamba","raw_affiliation_strings":["Tennessee Technological University,Department of Computer Science"],"affiliations":[{"raw_affiliation_string":"Tennessee Technological University,Department of Computer Science","institution_ids":["https://openalex.org/I63920570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5116901233","display_name":"Amr Akmal Abouelmagd","orcid":null},"institutions":[{"id":"https://openalex.org/I63920570","display_name":"Tennessee Technological University","ror":"https://ror.org/05drmrq39","country_code":"US","type":"education","lineage":["https://openalex.org/I63920570"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Amr Akmal Abouelmagd","raw_affiliation_strings":["Tennessee Technological University,Department of Computer Science"],"affiliations":[{"raw_affiliation_string":"Tennessee Technological University,Department of Computer Science","institution_ids":["https://openalex.org/I63920570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026440046","display_name":"Anthony Skjellum","orcid":"https://orcid.org/0000-0001-5252-6600"},"institutions":[{"id":"https://openalex.org/I63920570","display_name":"Tennessee Technological University","ror":"https://ror.org/05drmrq39","country_code":"US","type":"education","lineage":["https://openalex.org/I63920570"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anthony Skjellum","raw_affiliation_strings":["Tennessee Technological University,Department of Computer Science"],"affiliations":[{"raw_affiliation_string":"Tennessee Technological University,Department of Computer Science","institution_ids":["https://openalex.org/I63920570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021051610","display_name":"Martin Herbordt","orcid":"https://orcid.org/0000-0002-3443-9113"},"institutions":[{"id":"https://openalex.org/I111088046","display_name":"Boston University","ror":"https://ror.org/05qwgg493","country_code":"US","type":"education","lineage":["https://openalex.org/I111088046"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Martin Herbordt","raw_affiliation_strings":["Boston University,Department of Electrical and Computer Engineering"],"affiliations":[{"raw_affiliation_string":"Boston University,Department of Electrical and Computer Engineering","institution_ids":["https://openalex.org/I111088046"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5012033077"],"corresponding_institution_ids":["https://openalex.org/I111088046"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.36698142,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"9"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9975000023841858,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9975000023841858,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9915000200271606,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.98580002784729,"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/profiling","display_name":"Profiling (computer programming)","score":0.777400016784668},{"id":"https://openalex.org/keywords/idle","display_name":"Idle","score":0.741100013256073},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.6449000239372253},{"id":"https://openalex.org/keywords/work","display_name":"Work (physics)","score":0.3813999891281128},{"id":"https://openalex.org/keywords/processor-scheduling","display_name":"Processor scheduling","score":0.35740000009536743},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.350600004196167}],"concepts":[{"id":"https://openalex.org/C187191949","wikidata":"https://www.wikidata.org/wiki/Q1138496","display_name":"Profiling (computer programming)","level":2,"score":0.777400016784668},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.775600016117096},{"id":"https://openalex.org/C16320812","wikidata":"https://www.wikidata.org/wiki/Q1812200","display_name":"Idle","level":2,"score":0.741100013256073},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.6449000239372253},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.42969998717308044},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.3813999891281128},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3774000108242035},{"id":"https://openalex.org/C2984822820","wikidata":"https://www.wikidata.org/wiki/Q1123036","display_name":"Processor scheduling","level":3,"score":0.35740000009536743},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.350600004196167},{"id":"https://openalex.org/C2989134064","wikidata":"https://www.wikidata.org/wiki/Q288510","display_name":"Execution time","level":2,"score":0.34360000491142273},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.33899998664855957},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.32829999923706055},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.31850001215934753},{"id":"https://openalex.org/C138959212","wikidata":"https://www.wikidata.org/wiki/Q1806783","display_name":"Load balancing (electrical power)","level":3,"score":0.31690001487731934},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.31470000743865967},{"id":"https://openalex.org/C200601418","wikidata":"https://www.wikidata.org/wiki/Q2193887","display_name":"Reliability engineering","level":1,"score":0.3012000024318695},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.2721000015735626},{"id":"https://openalex.org/C49154492","wikidata":"https://www.wikidata.org/wiki/Q5300","display_name":"Central processing unit","level":2,"score":0.2669999897480011}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/hpec67600.2025.11196678","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpec67600.2025.11196678","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE High Performance Extreme Computing Conference (HPEC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1522914210","https://openalex.org/W1986905947","https://openalex.org/W2000882268","https://openalex.org/W2045271686","https://openalex.org/W2077047259","https://openalex.org/W2095954861","https://openalex.org/W2143624342","https://openalex.org/W3027450532","https://openalex.org/W3140689773","https://openalex.org/W4200162828","https://openalex.org/W4200623295","https://openalex.org/W4308090234","https://openalex.org/W4381327268","https://openalex.org/W4399283082","https://openalex.org/W4409132037","https://openalex.org/W4413411979"],"related_works":[],"abstract_inverted_index":{"As":[0],"the":[1,111],"scale":[2],"of":[3,87],"High":[4],"Performance":[5],"Computing":[6],"(HPC)":[7],"applications":[8],"increases,":[9],"load":[10],"imbalance":[11],"and":[12,50],"other":[13],"inefficiencies":[14],"become":[15],"correspondingly":[16],"more":[17],"significant.":[18],"In":[19],"this":[20],"work":[21],"we":[22],"extend":[23],"a":[24,40,44,85,97],"previously":[25],"described":[26],"system":[27,47],"that":[28,56,89,101],"reclaims":[29],"idle":[30],"computation":[31],"time":[32],"during":[33],"MPI":[34],"synchronization.":[35],"We":[36,54,94],"begin":[37],"by":[38,79,84,106],"applying":[39],"new":[41,45,98],"profiler":[42],"to":[43,75],"target":[46],"(Stampede":[48],"III)":[49],"observing":[51],"application":[52],"characteristics.":[53],"find":[55],"for":[57,63],"miniFE":[58],"there":[59],"is":[60],"immense":[61],"potential":[62],"capturing":[64],"wasted":[65],"cycles":[66,71],"(roughly":[67],"30%).":[68],"Moreover":[69],"these":[70],"do":[72],"not":[73],"appear":[74],"be":[76],"caused":[77],"systematically":[78],"particular":[80],"ranks,":[81],"but":[82],"rather":[83],"number":[86],"ranks":[88],"vary":[90],"without":[91],"obvious":[92],"pattern.":[93],"then":[95],"propose":[96],"runtime":[99],"algorithm":[100],"improves":[102],"CPU":[103],"cycle":[104],"utilization":[105],"an":[107],"additional":[108],"10\u201315%":[109],"over":[110],"previous":[112],"best":[113],"result.":[114]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-16T00:00:00"}
