Leveraging HPC Profiling & Tracing Tools to Understand the Performance of Particle-in-Cell Monte Carlo Simulations
Large-scale plasma simulations are critical for designing and developing next-generation fusion energy devices and modeling industrial plasmas. BIT1 is a massively parallel Particle-in-Cell code designed for specifically studying plasma material interaction in fusion devices. Its most salient charac...
Gespeichert in:
| Veröffentlicht in: | arXiv.org 2023-06 |
|---|---|
| Hauptverfasser: | , , , , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | |
|---|---|
| container_issue | |
| container_start_page | |
| container_title | arXiv.org |
| container_volume | |
| creator | Williams, Jeremy J Tskhakaya, David Costea, Stefan Peng, Ivy B Garcia-Gasulla, Marta Markidis, Stefano |
| description | Large-scale plasma simulations are critical for designing and developing next-generation fusion energy devices and modeling industrial plasmas. BIT1 is a massively parallel Particle-in-Cell code designed for specifically studying plasma material interaction in fusion devices. Its most salient characteristic is the inclusion of collision Monte Carlo models for different plasma species. In this work, we characterize single node, multiple nodes, and I/O performances of the BIT1 code in two realistic cases by using several HPC profilers, such as perf, IPM, Extrae/Paraver, and Darshan tools. We find that the BIT1 sorting function on-node performance is the main performance bottleneck. Strong scaling tests show a parallel performance of 77% and 96% on 2,560 MPI ranks for the two test cases. We demonstrate that communication, load imbalance and self-synchronization are important factors impacting the performance of the BIT1 on large-scale runs. |
| doi_str_mv | 10.48550/arxiv.2306.16512 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_arxiv</sourceid><recordid>TN_cdi_arxiv_primary_2306_16512</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2831674444</sourcerecordid><originalsourceid>FETCH-LOGICAL-a952-a2595cffeea3e946d6427c61b92f9268b847e8b3e884a8ab2db9fc1532b9055a3</originalsourceid><addsrcrecordid>eNotkF1LwzAUhoMgOOZ-gFcGBO8606RJ00sp6oSJBet1OW1PZkaWzLQb-u_dh-_NeQ88HA4PITcpm2daSvYA8cfu51wwNU-VTPkFmXAh0kRnnF-R2TCsGWNc5VxKMSFxiXuMsLJ-RRdVSasYjHXH7Z7WEbpjq0NwAx0D_fQ9xmEE39PxC2mF0YS4Ad8hDYZWEEfbOUysT0p0jr4FPyItIbpAP-xm52C0wQ_X5NKAG3D2P6ekfn6qy0WyfH95LR-XCRSSJ8BlITtjEEFgkaleZTzvVNoW3BRc6VZnOepWoNYZaGh53xamS6XgbcGkBDElt-ezJyHNNtoNxN_mKKY5iTkQd2diG8P3DoexWYdd9IefGq5FqvLsEPEHbtpmWw</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2831674444</pqid></control><display><type>article</type><title>Leveraging HPC Profiling & Tracing Tools to Understand the Performance of Particle-in-Cell Monte Carlo Simulations</title><source>arXiv.org</source><source>Free E- Journals</source><creator>Williams, Jeremy J ; Tskhakaya, David ; Costea, Stefan ; Peng, Ivy B ; Garcia-Gasulla, Marta ; Markidis, Stefano</creator><creatorcontrib>Williams, Jeremy J ; Tskhakaya, David ; Costea, Stefan ; Peng, Ivy B ; Garcia-Gasulla, Marta ; Markidis, Stefano</creatorcontrib><description>Large-scale plasma simulations are critical for designing and developing next-generation fusion energy devices and modeling industrial plasmas. BIT1 is a massively parallel Particle-in-Cell code designed for specifically studying plasma material interaction in fusion devices. Its most salient characteristic is the inclusion of collision Monte Carlo models for different plasma species. In this work, we characterize single node, multiple nodes, and I/O performances of the BIT1 code in two realistic cases by using several HPC profilers, such as perf, IPM, Extrae/Paraver, and Darshan tools. We find that the BIT1 sorting function on-node performance is the main performance bottleneck. Strong scaling tests show a parallel performance of 77% and 96% on 2,560 MPI ranks for the two test cases. We demonstrate that communication, load imbalance and self-synchronization are important factors impacting the performance of the BIT1 on large-scale runs.</description><identifier>EISSN: 2331-8422</identifier><identifier>DOI: 10.48550/arxiv.2306.16512</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Computer Science - Distributed, Parallel, and Cluster Computing ; Particle in cell technique ; Synchronism</subject><ispartof>arXiv.org, 2023-06</ispartof><rights>2023. This work is published under http://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><rights>http://creativecommons.org/licenses/by/4.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,780,784,885,27925</link.rule.ids><backlink>$$Uhttps://doi.org/10.1007/978-3-031-50684-0_10$$DView published paper (Access to full text may be restricted)$$Hfree_for_read</backlink><backlink>$$Uhttps://doi.org/10.48550/arXiv.2306.16512$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Williams, Jeremy J</creatorcontrib><creatorcontrib>Tskhakaya, David</creatorcontrib><creatorcontrib>Costea, Stefan</creatorcontrib><creatorcontrib>Peng, Ivy B</creatorcontrib><creatorcontrib>Garcia-Gasulla, Marta</creatorcontrib><creatorcontrib>Markidis, Stefano</creatorcontrib><title>Leveraging HPC Profiling & Tracing Tools to Understand the Performance of Particle-in-Cell Monte Carlo Simulations</title><title>arXiv.org</title><description>Large-scale plasma simulations are critical for designing and developing next-generation fusion energy devices and modeling industrial plasmas. BIT1 is a massively parallel Particle-in-Cell code designed for specifically studying plasma material interaction in fusion devices. Its most salient characteristic is the inclusion of collision Monte Carlo models for different plasma species. In this work, we characterize single node, multiple nodes, and I/O performances of the BIT1 code in two realistic cases by using several HPC profilers, such as perf, IPM, Extrae/Paraver, and Darshan tools. We find that the BIT1 sorting function on-node performance is the main performance bottleneck. Strong scaling tests show a parallel performance of 77% and 96% on 2,560 MPI ranks for the two test cases. We demonstrate that communication, load imbalance and self-synchronization are important factors impacting the performance of the BIT1 on large-scale runs.</description><subject>Computer Science - Distributed, Parallel, and Cluster Computing</subject><subject>Particle in cell technique</subject><subject>Synchronism</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2023</creationdate><recordtype>article</recordtype><sourceid>ABUWG</sourceid><sourceid>AFKRA</sourceid><sourceid>AZQEC</sourceid><sourceid>BENPR</sourceid><sourceid>CCPQU</sourceid><sourceid>DWQXO</sourceid><sourceid>GOX</sourceid><recordid>eNotkF1LwzAUhoMgOOZ-gFcGBO8606RJ00sp6oSJBet1OW1PZkaWzLQb-u_dh-_NeQ88HA4PITcpm2daSvYA8cfu51wwNU-VTPkFmXAh0kRnnF-R2TCsGWNc5VxKMSFxiXuMsLJ-RRdVSasYjHXH7Z7WEbpjq0NwAx0D_fQ9xmEE39PxC2mF0YS4Ad8hDYZWEEfbOUysT0p0jr4FPyItIbpAP-xm52C0wQ_X5NKAG3D2P6ekfn6qy0WyfH95LR-XCRSSJ8BlITtjEEFgkaleZTzvVNoW3BRc6VZnOepWoNYZaGh53xamS6XgbcGkBDElt-ezJyHNNtoNxN_mKKY5iTkQd2diG8P3DoexWYdd9IefGq5FqvLsEPEHbtpmWw</recordid><startdate>20230628</startdate><enddate>20230628</enddate><creator>Williams, Jeremy J</creator><creator>Tskhakaya, David</creator><creator>Costea, Stefan</creator><creator>Peng, Ivy B</creator><creator>Garcia-Gasulla, Marta</creator><creator>Markidis, Stefano</creator><general>Cornell University Library, arXiv.org</general><scope>8FE</scope><scope>8FG</scope><scope>ABJCF</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>HCIFZ</scope><scope>L6V</scope><scope>M7S</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>PTHSS</scope><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20230628</creationdate><title>Leveraging HPC Profiling & Tracing Tools to Understand the Performance of Particle-in-Cell Monte Carlo Simulations</title><author>Williams, Jeremy J ; Tskhakaya, David ; Costea, Stefan ; Peng, Ivy B ; Garcia-Gasulla, Marta ; Markidis, Stefano</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a952-a2595cffeea3e946d6427c61b92f9268b847e8b3e884a8ab2db9fc1532b9055a3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2023</creationdate><topic>Computer Science - Distributed, Parallel, and Cluster Computing</topic><topic>Particle in cell technique</topic><topic>Synchronism</topic><toplevel>online_resources</toplevel><creatorcontrib>Williams, Jeremy J</creatorcontrib><creatorcontrib>Tskhakaya, David</creatorcontrib><creatorcontrib>Costea, Stefan</creatorcontrib><creatorcontrib>Peng, Ivy B</creatorcontrib><creatorcontrib>Garcia-Gasulla, Marta</creatorcontrib><creatorcontrib>Markidis, Stefano</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science & Engineering Collection</collection><collection>ProQuest Central (Alumni Edition)</collection><collection>ProQuest Central UK/Ireland</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central Korea</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Engineering Collection</collection><collection>Engineering Database</collection><collection>Publicly Available Content Database</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><collection>Engineering Collection</collection><collection>arXiv Computer Science</collection><collection>arXiv.org</collection><jtitle>arXiv.org</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Williams, Jeremy J</au><au>Tskhakaya, David</au><au>Costea, Stefan</au><au>Peng, Ivy B</au><au>Garcia-Gasulla, Marta</au><au>Markidis, Stefano</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Leveraging HPC Profiling & Tracing Tools to Understand the Performance of Particle-in-Cell Monte Carlo Simulations</atitle><jtitle>arXiv.org</jtitle><date>2023-06-28</date><risdate>2023</risdate><eissn>2331-8422</eissn><abstract>Large-scale plasma simulations are critical for designing and developing next-generation fusion energy devices and modeling industrial plasmas. BIT1 is a massively parallel Particle-in-Cell code designed for specifically studying plasma material interaction in fusion devices. Its most salient characteristic is the inclusion of collision Monte Carlo models for different plasma species. In this work, we characterize single node, multiple nodes, and I/O performances of the BIT1 code in two realistic cases by using several HPC profilers, such as perf, IPM, Extrae/Paraver, and Darshan tools. We find that the BIT1 sorting function on-node performance is the main performance bottleneck. Strong scaling tests show a parallel performance of 77% and 96% on 2,560 MPI ranks for the two test cases. We demonstrate that communication, load imbalance and self-synchronization are important factors impacting the performance of the BIT1 on large-scale runs.</abstract><cop>Ithaca</cop><pub>Cornell University Library, arXiv.org</pub><doi>10.48550/arxiv.2306.16512</doi><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext |
| identifier | EISSN: 2331-8422 |
| ispartof | arXiv.org, 2023-06 |
| issn | 2331-8422 |
| language | eng |
| recordid | cdi_arxiv_primary_2306_16512 |
| source | arXiv.org; Free E- Journals |
| subjects | Computer Science - Distributed, Parallel, and Cluster Computing Particle in cell technique Synchronism |
| title | Leveraging HPC Profiling & Tracing Tools to Understand the Performance of Particle-in-Cell Monte Carlo Simulations |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-26T09%3A29%3A09IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_arxiv&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Leveraging%20HPC%20Profiling%20&%20Tracing%20Tools%20to%20Understand%20the%20Performance%20of%20Particle-in-Cell%20Monte%20Carlo%20Simulations&rft.jtitle=arXiv.org&rft.au=Williams,%20Jeremy%20J&rft.date=2023-06-28&rft.eissn=2331-8422&rft_id=info:doi/10.48550/arxiv.2306.16512&rft_dat=%3Cproquest_arxiv%3E2831674444%3C/proquest_arxiv%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2831674444&rft_id=info:pmid/&rfr_iscdi=true |