Performance Measurements Within Asynchronous Task-Based Runtime Systems: A Double White Dwarf Merger as an Application
Analyzing performance within asynchronous many-task-based runtime systems is challenging because millions of tasks are launched concurrently. Especially for long-term runs, the amount of data collected becomes overwhelming. We study HPX and its performance-counter framework and autonomic performance...
Gespeichert in:
| Veröffentlicht in: | Computing in science & engineering 2021-05, Vol.23 (3), p.73-81 |
|---|---|
| Hauptverfasser: | , , , , , , , , , , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext bestellen |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 81 |
|---|---|
| container_issue | 3 |
| container_start_page | 73 |
| container_title | Computing in science & engineering |
| container_volume | 23 |
| creator | Diehl, Patrick Marcello, Dominic Amini, Parsa Kaiser, Hartmut Shiber, Sagiv Clayton, Geoffrey C. Frank, Juhan Dais, Gregor Pfluger, Dirk Eder, David Koniges, Alice Huck, Kevin |
| description | Analyzing performance within asynchronous many-task-based runtime systems is challenging because millions of tasks are launched concurrently. Especially for long-term runs, the amount of data collected becomes overwhelming. We study HPX and its performance-counter framework and autonomic performance environment for Exascale to collect performance data and energy consumption. We added HPX application-specific performance counters to the Octo-Tiger full 3-D adaptive multigrid code astrophysics application. This enables the combined visualization of physical and performance data to highlight bottlenecks with respect to different solvers. We examine the overhead introduced by these measurements, which is around 1%, with respect to the overall application runtime. We perform a resolution study for four different levels of refinement and analyze the application's performance with respect to adaptive grid refinement. The measurements’ overheads are small, enabling the combined use of performance data and physical properties with the goal of improving the code's performance. All runs were obtained on NERSC's Cori, Louisiana Optical Network Infrastructure's QueenBee2, and Indiana University's Big Red 3. |
| doi_str_mv | 10.1109/MCSE.2021.3073626 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_RIE</sourceid><recordid>TN_cdi_crossref_primary_10_1109_MCSE_2021_3073626</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>9405442</ieee_id><sourcerecordid>2542503725</sourcerecordid><originalsourceid>FETCH-LOGICAL-c288t-1c6dba0d88ff52d270df9f4e939f31e21ffed340d7694a0042f8e751c30161b53</originalsourceid><addsrcrecordid>eNo9kMtOwzAQRS0EEqXwAYiNJdYpfubBrrTlIbUC0aKyi9xkTF0ap9gOqH9PoiJWM4tz72gOQpeUDCgl2c1sNJ8MGGF0wEnCYxYfoR6VMo14HL8fdzujURZTeYrOvN8QQkSayR76fgGna1cpWwCegfKNgwps8HhpwtpYPPR7W6xdbevG44Xyn9Gd8lDi18YGUwGe732Ayt_iIR7XzWoLeLk2AfD4RzndNroPcFh5rNqq3W5rChVMbc_RiVZbDxd_s4_e7ieL0WM0fX54Gg2nUcHSNES0iMuVImWaai1ZyRJS6kwLyHimOQVGtYaSC1ImcSZU-xPTKSSSFpzQmK4k76PrQ-_O1V8N-JBv6sbZ9mTOpGCS8IR1FD1Qhau9d6DznTOVcvuckrzTm3d6805v_qe3zVwdMgYA_vlMECkE47_PCHcp</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2542503725</pqid></control><display><type>article</type><title>Performance Measurements Within Asynchronous Task-Based Runtime Systems: A Double White Dwarf Merger as an Application</title><source>IEEE Electronic Library (IEL)</source><creator>Diehl, Patrick ; Marcello, Dominic ; Amini, Parsa ; Kaiser, Hartmut ; Shiber, Sagiv ; Clayton, Geoffrey C. ; Frank, Juhan ; Dais, Gregor ; Pfluger, Dirk ; Eder, David ; Koniges, Alice ; Huck, Kevin</creator><creatorcontrib>Diehl, Patrick ; Marcello, Dominic ; Amini, Parsa ; Kaiser, Hartmut ; Shiber, Sagiv ; Clayton, Geoffrey C. ; Frank, Juhan ; Dais, Gregor ; Pfluger, Dirk ; Eder, David ; Koniges, Alice ; Huck, Kevin</creatorcontrib><description>Analyzing performance within asynchronous many-task-based runtime systems is challenging because millions of tasks are launched concurrently. Especially for long-term runs, the amount of data collected becomes overwhelming. We study HPX and its performance-counter framework and autonomic performance environment for Exascale to collect performance data and energy consumption. We added HPX application-specific performance counters to the Octo-Tiger full 3-D adaptive multigrid code astrophysics application. This enables the combined visualization of physical and performance data to highlight bottlenecks with respect to different solvers. We examine the overhead introduced by these measurements, which is around 1%, with respect to the overall application runtime. We perform a resolution study for four different levels of refinement and analyze the application's performance with respect to adaptive grid refinement. The measurements’ overheads are small, enabling the combined use of performance data and physical properties with the goal of improving the code's performance. All runs were obtained on NERSC's Cori, Louisiana Optical Network Infrastructure's QueenBee2, and Indiana University's Big Red 3.</description><identifier>ISSN: 1521-9615</identifier><identifier>EISSN: 1558-366X</identifier><identifier>DOI: 10.1109/MCSE.2021.3073626</identifier><identifier>CODEN: CSENFA</identifier><language>eng</language><publisher>New York: IEEE</publisher><subject>Astrophysics ; Computational modeling ; Corporate acquisitions ; Data models ; Data visualization ; Energy consumption ; Extraterrestrial measurements ; Grid refinement (mathematics) ; Optical communication ; Physical properties ; Runtime ; Task analysis ; White dwarf stars</subject><ispartof>Computing in science & engineering, 2021-05, Vol.23 (3), p.73-81</ispartof><rights>Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2021</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><cites>FETCH-LOGICAL-c288t-1c6dba0d88ff52d270df9f4e939f31e21ffed340d7694a0042f8e751c30161b53</cites><orcidid>0000-0002-4360-0212 ; 0000-0003-3922-8419 ; 0000-0001-6107-0887</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/9405442$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>314,780,784,796,27923,27924,54757</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/9405442$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Diehl, Patrick</creatorcontrib><creatorcontrib>Marcello, Dominic</creatorcontrib><creatorcontrib>Amini, Parsa</creatorcontrib><creatorcontrib>Kaiser, Hartmut</creatorcontrib><creatorcontrib>Shiber, Sagiv</creatorcontrib><creatorcontrib>Clayton, Geoffrey C.</creatorcontrib><creatorcontrib>Frank, Juhan</creatorcontrib><creatorcontrib>Dais, Gregor</creatorcontrib><creatorcontrib>Pfluger, Dirk</creatorcontrib><creatorcontrib>Eder, David</creatorcontrib><creatorcontrib>Koniges, Alice</creatorcontrib><creatorcontrib>Huck, Kevin</creatorcontrib><title>Performance Measurements Within Asynchronous Task-Based Runtime Systems: A Double White Dwarf Merger as an Application</title><title>Computing in science & engineering</title><addtitle>CISE-M</addtitle><description>Analyzing performance within asynchronous many-task-based runtime systems is challenging because millions of tasks are launched concurrently. Especially for long-term runs, the amount of data collected becomes overwhelming. We study HPX and its performance-counter framework and autonomic performance environment for Exascale to collect performance data and energy consumption. We added HPX application-specific performance counters to the Octo-Tiger full 3-D adaptive multigrid code astrophysics application. This enables the combined visualization of physical and performance data to highlight bottlenecks with respect to different solvers. We examine the overhead introduced by these measurements, which is around 1%, with respect to the overall application runtime. We perform a resolution study for four different levels of refinement and analyze the application's performance with respect to adaptive grid refinement. The measurements’ overheads are small, enabling the combined use of performance data and physical properties with the goal of improving the code's performance. All runs were obtained on NERSC's Cori, Louisiana Optical Network Infrastructure's QueenBee2, and Indiana University's Big Red 3.</description><subject>Astrophysics</subject><subject>Computational modeling</subject><subject>Corporate acquisitions</subject><subject>Data models</subject><subject>Data visualization</subject><subject>Energy consumption</subject><subject>Extraterrestrial measurements</subject><subject>Grid refinement (mathematics)</subject><subject>Optical communication</subject><subject>Physical properties</subject><subject>Runtime</subject><subject>Task analysis</subject><subject>White dwarf stars</subject><issn>1521-9615</issn><issn>1558-366X</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2021</creationdate><recordtype>article</recordtype><sourceid>RIE</sourceid><recordid>eNo9kMtOwzAQRS0EEqXwAYiNJdYpfubBrrTlIbUC0aKyi9xkTF0ap9gOqH9PoiJWM4tz72gOQpeUDCgl2c1sNJ8MGGF0wEnCYxYfoR6VMo14HL8fdzujURZTeYrOvN8QQkSayR76fgGna1cpWwCegfKNgwps8HhpwtpYPPR7W6xdbevG44Xyn9Gd8lDi18YGUwGe732Ayt_iIR7XzWoLeLk2AfD4RzndNroPcFh5rNqq3W5rChVMbc_RiVZbDxd_s4_e7ieL0WM0fX54Gg2nUcHSNES0iMuVImWaai1ZyRJS6kwLyHimOQVGtYaSC1ImcSZU-xPTKSSSFpzQmK4k76PrQ-_O1V8N-JBv6sbZ9mTOpGCS8IR1FD1Qhau9d6DznTOVcvuckrzTm3d6805v_qe3zVwdMgYA_vlMECkE47_PCHcp</recordid><startdate>202105</startdate><enddate>202105</enddate><creator>Diehl, Patrick</creator><creator>Marcello, Dominic</creator><creator>Amini, Parsa</creator><creator>Kaiser, Hartmut</creator><creator>Shiber, Sagiv</creator><creator>Clayton, Geoffrey C.</creator><creator>Frank, Juhan</creator><creator>Dais, Gregor</creator><creator>Pfluger, Dirk</creator><creator>Eder, David</creator><creator>Koniges, Alice</creator><creator>Huck, Kevin</creator><general>IEEE</general><general>The Institute of Electrical and Electronics Engineers, Inc. (IEEE)</general><scope>97E</scope><scope>RIA</scope><scope>RIE</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7SC</scope><scope>7SP</scope><scope>7TB</scope><scope>8FD</scope><scope>FR3</scope><scope>JQ2</scope><scope>KR7</scope><scope>L7M</scope><scope>L~C</scope><scope>L~D</scope><orcidid>https://orcid.org/0000-0002-4360-0212</orcidid><orcidid>https://orcid.org/0000-0003-3922-8419</orcidid><orcidid>https://orcid.org/0000-0001-6107-0887</orcidid></search><sort><creationdate>202105</creationdate><title>Performance Measurements Within Asynchronous Task-Based Runtime Systems: A Double White Dwarf Merger as an Application</title><author>Diehl, Patrick ; Marcello, Dominic ; Amini, Parsa ; Kaiser, Hartmut ; Shiber, Sagiv ; Clayton, Geoffrey C. ; Frank, Juhan ; Dais, Gregor ; Pfluger, Dirk ; Eder, David ; Koniges, Alice ; Huck, Kevin</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c288t-1c6dba0d88ff52d270df9f4e939f31e21ffed340d7694a0042f8e751c30161b53</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2021</creationdate><topic>Astrophysics</topic><topic>Computational modeling</topic><topic>Corporate acquisitions</topic><topic>Data models</topic><topic>Data visualization</topic><topic>Energy consumption</topic><topic>Extraterrestrial measurements</topic><topic>Grid refinement (mathematics)</topic><topic>Optical communication</topic><topic>Physical properties</topic><topic>Runtime</topic><topic>Task analysis</topic><topic>White dwarf stars</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Diehl, Patrick</creatorcontrib><creatorcontrib>Marcello, Dominic</creatorcontrib><creatorcontrib>Amini, Parsa</creatorcontrib><creatorcontrib>Kaiser, Hartmut</creatorcontrib><creatorcontrib>Shiber, Sagiv</creatorcontrib><creatorcontrib>Clayton, Geoffrey C.</creatorcontrib><creatorcontrib>Frank, Juhan</creatorcontrib><creatorcontrib>Dais, Gregor</creatorcontrib><creatorcontrib>Pfluger, Dirk</creatorcontrib><creatorcontrib>Eder, David</creatorcontrib><creatorcontrib>Koniges, Alice</creatorcontrib><creatorcontrib>Huck, Kevin</creatorcontrib><collection>IEEE All-Society Periodicals Package (ASPP) 2005-present</collection><collection>IEEE All-Society Periodicals Package (ASPP) 1998-Present</collection><collection>IEEE Electronic Library (IEL)</collection><collection>CrossRef</collection><collection>Computer and Information Systems Abstracts</collection><collection>Electronics & Communications Abstracts</collection><collection>Mechanical & Transportation Engineering Abstracts</collection><collection>Technology Research Database</collection><collection>Engineering Research Database</collection><collection>ProQuest Computer Science Collection</collection><collection>Civil Engineering Abstracts</collection><collection>Advanced Technologies Database with Aerospace</collection><collection>Computer and Information Systems Abstracts Academic</collection><collection>Computer and Information Systems Abstracts Professional</collection><jtitle>Computing in science & engineering</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Diehl, Patrick</au><au>Marcello, Dominic</au><au>Amini, Parsa</au><au>Kaiser, Hartmut</au><au>Shiber, Sagiv</au><au>Clayton, Geoffrey C.</au><au>Frank, Juhan</au><au>Dais, Gregor</au><au>Pfluger, Dirk</au><au>Eder, David</au><au>Koniges, Alice</au><au>Huck, Kevin</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Performance Measurements Within Asynchronous Task-Based Runtime Systems: A Double White Dwarf Merger as an Application</atitle><jtitle>Computing in science & engineering</jtitle><stitle>CISE-M</stitle><date>2021-05</date><risdate>2021</risdate><volume>23</volume><issue>3</issue><spage>73</spage><epage>81</epage><pages>73-81</pages><issn>1521-9615</issn><eissn>1558-366X</eissn><coden>CSENFA</coden><abstract>Analyzing performance within asynchronous many-task-based runtime systems is challenging because millions of tasks are launched concurrently. Especially for long-term runs, the amount of data collected becomes overwhelming. We study HPX and its performance-counter framework and autonomic performance environment for Exascale to collect performance data and energy consumption. We added HPX application-specific performance counters to the Octo-Tiger full 3-D adaptive multigrid code astrophysics application. This enables the combined visualization of physical and performance data to highlight bottlenecks with respect to different solvers. We examine the overhead introduced by these measurements, which is around 1%, with respect to the overall application runtime. We perform a resolution study for four different levels of refinement and analyze the application's performance with respect to adaptive grid refinement. The measurements’ overheads are small, enabling the combined use of performance data and physical properties with the goal of improving the code's performance. All runs were obtained on NERSC's Cori, Louisiana Optical Network Infrastructure's QueenBee2, and Indiana University's Big Red 3.</abstract><cop>New York</cop><pub>IEEE</pub><doi>10.1109/MCSE.2021.3073626</doi><tpages>9</tpages><orcidid>https://orcid.org/0000-0002-4360-0212</orcidid><orcidid>https://orcid.org/0000-0003-3922-8419</orcidid><orcidid>https://orcid.org/0000-0001-6107-0887</orcidid><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | ISSN: 1521-9615 |
| ispartof | Computing in science & engineering, 2021-05, Vol.23 (3), p.73-81 |
| issn | 1521-9615 1558-366X |
| language | eng |
| recordid | cdi_crossref_primary_10_1109_MCSE_2021_3073626 |
| source | IEEE Electronic Library (IEL) |
| subjects | Astrophysics Computational modeling Corporate acquisitions Data models Data visualization Energy consumption Extraterrestrial measurements Grid refinement (mathematics) Optical communication Physical properties Runtime Task analysis White dwarf stars |
| title | Performance Measurements Within Asynchronous Task-Based Runtime Systems: A Double White Dwarf Merger as an Application |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-11T16%3A30%3A30IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_RIE&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Performance%20Measurements%20Within%20Asynchronous%20Task-Based%20Runtime%20Systems:%20A%20Double%20White%20Dwarf%20Merger%20as%20an%20Application&rft.jtitle=Computing%20in%20science%20&%20engineering&rft.au=Diehl,%20Patrick&rft.date=2021-05&rft.volume=23&rft.issue=3&rft.spage=73&rft.epage=81&rft.pages=73-81&rft.issn=1521-9615&rft.eissn=1558-366X&rft.coden=CSENFA&rft_id=info:doi/10.1109/MCSE.2021.3073626&rft_dat=%3Cproquest_RIE%3E2542503725%3C/proquest_RIE%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2542503725&rft_id=info:pmid/&rft_ieee_id=9405442&rfr_iscdi=true |