A Massively Parallel Infrastructure for Adaptive Multiscale Simulations: Modeling RAS Initiation Pathway for Cancer
Computational models can define the functional dynamics of complex systems in exceptional detail. However, many modeling studies face seemingly incommensurate requirements: to gain meaningful insights into some phenomena requires models with high resolution (microscopic) detail that must nevertheles...
Saved in:
| Published in: | SC19: International Conference for High Performance Computing, Networking, Storage and Analysis pp. 1 - 16 |
|---|---|
| Main Authors: | , , , , , , , , , , , , , , , , , , , , , , , , |
| Format: | Conference Proceeding |
| Language: | English |
| Published: |
ACM
17.11.2019
|
| Subjects: | |
| ISSN: | 2167-4337 |
| Online Access: | Get full text |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Abstract | Computational models can define the functional dynamics of complex systems in exceptional detail. However, many modeling studies face seemingly incommensurate requirements: to gain meaningful insights into some phenomena requires models with high resolution (microscopic) detail that must nevertheless evolve over large (macroscopic) length- and time-scales. Multiscale modeling has become increasingly important to bridge this gap. Executing complex multiscale models on current petascale computers with high levels of parallelism and heterogeneous architectures is challenging. Many distinct types of resources need to be simultaneously managed, such as GPUs and CPUs, memory size and latencies, communication bottlenecks, and filesystem bandwidth. In addition, robustness to failure of compute nodes, network, and filesystems is critical. We introduce a first-of-its-kind, massively parallel Multiscale Machine-Learned Modeling Infrastructure (MuMMI), which couples a macro scale model spanning micrometer length- and millisec-ond time-scales with a micro scale model employing high-fidelity molecular dynamics (MD) simulations. MuMMI is a cohesive and transferable infrastructure designed for scalability and efficient execution on heterogeneous resources. A central workflow manager simultaneously allocates GPUs and CPUs while robustly han-dling failures in compute nodes, communication networks, and filesystems. A hierarchical scheduler controls GPU-accelerated MD simulations and in situ analysis. We present the various MUMMI components, including the macro model, GPU-accelerated MD, in situ analysis of MD data, machine learning selection module, a highly scalable hierarchical scheduler, and detail the central workflow manager that ties these modules together. In addition, we present performance data from our runs on Sierra, in which we validated MuMMI by investigating an experimentally intractable biological system: the dynamic interaction between RAS proteins and a plasma membrane. We used up to 4000 nodes of the Sierra supercomputer, concurrently utilizing over 16,000 GPUs and 176,000 CPU cores, and running up to 36,000 different tasks. This multiscale simulation includes about 120,000 MD simulations aggregating over 200 milliseconds, which is orders of magnitude greater than comparable studies. |
|---|---|
| AbstractList | Computational models can define the functional dynamics of complex systems in exceptional detail. However, many modeling studies face seemingly incommensurate requirements: to gain meaningful insights into some phenomena requires models with high resolution (microscopic) detail that must nevertheless evolve over large (macroscopic) length- and time-scales. Multiscale modeling has become increasingly important to bridge this gap. Executing complex multiscale models on current petascale computers with high levels of parallelism and heterogeneous architectures is challenging. Many distinct types of resources need to be simultaneously managed, such as GPUs and CPUs, memory size and latencies, communication bottlenecks, and filesystem bandwidth. In addition, robustness to failure of compute nodes, network, and filesystems is critical. We introduce a first-of-its-kind, massively parallel Multiscale Machine-Learned Modeling Infrastructure (MuMMI), which couples a macro scale model spanning micrometer length- and millisec-ond time-scales with a micro scale model employing high-fidelity molecular dynamics (MD) simulations. MuMMI is a cohesive and transferable infrastructure designed for scalability and efficient execution on heterogeneous resources. A central workflow manager simultaneously allocates GPUs and CPUs while robustly han-dling failures in compute nodes, communication networks, and filesystems. A hierarchical scheduler controls GPU-accelerated MD simulations and in situ analysis. We present the various MUMMI components, including the macro model, GPU-accelerated MD, in situ analysis of MD data, machine learning selection module, a highly scalable hierarchical scheduler, and detail the central workflow manager that ties these modules together. In addition, we present performance data from our runs on Sierra, in which we validated MuMMI by investigating an experimentally intractable biological system: the dynamic interaction between RAS proteins and a plasma membrane. We used up to 4000 nodes of the Sierra supercomputer, concurrently utilizing over 16,000 GPUs and 176,000 CPU cores, and running up to 36,000 different tasks. This multiscale simulation includes about 120,000 MD simulations aggregating over 200 milliseconds, which is orders of magnitude greater than comparable studies. |
| Author | Scogland, Thomas R. W. Schumacher, Sara Kokkila Nissley, Dwight V. D'Amora, Bruce Bremer, Peer-Timo Zhang, Xiaohua Sundram, Shiv Misale, Claudia Carpenter, Timothy S. Gnanakaran, Sandrasegaram Stanton, Liam Bhatia, Harsh Lightstone, Felice C. Oppelstrup, Tomas Schneidenbach, Lars Streitz, Fred Kim, Changhoan Neale, Chris Surh, Michael P. Dharuman, Gautham Glosli, James N. Costa, Carlos Ingolfsson, Helgi I. Yang, Yue Di Natale, Francesco |
| Author_xml | – sequence: 1 givenname: Francesco surname: Di Natale fullname: Di Natale, Francesco email: dinatale3@llnl.gov organization: Applications, Simulations, and Quality, Lawrence Livermore National Laboratory,Livermore,California,94550 – sequence: 2 givenname: Chris surname: Neale fullname: Neale, Chris email: cneale@lanl.gov organization: Los Alamos National Laboratory,Theoretical Biology and Biophysics,Los Alamos,New Mexico,87545 – sequence: 3 givenname: Liam surname: Stanton fullname: Stanton, Liam email: liam.stanton@sjsu.edu organization: San Jose State University,Department of Mathematics and Statistics,San Jose,California,95192 – sequence: 4 givenname: Thomas R. W. surname: Scogland fullname: Scogland, Thomas R. W. email: scogland1@llnl.gov organization: Lawrence Livermore National Laboratory,Center for Applied Scientific Computing,Livermore,California,94550 – sequence: 5 givenname: Yue surname: Yang fullname: Yang, Yue email: yang30@llnl.gov organization: Physical and Life Sciences, Lawrence Livermore National Laboratory,Livermore,California,94550 – sequence: 6 givenname: Carlos surname: Costa fullname: Costa, Carlos email: chcost@us.ibm.com organization: IBM Thomas J. Watson Research Center,Yorktown Heights,New York,10598 – sequence: 7 givenname: Sandrasegaram surname: Gnanakaran fullname: Gnanakaran, Sandrasegaram email: gnana@lanl.gov organization: Los Alamos National Laboratory,Theoretical Biology and Biophysics,Los Alamos,New Mexico,87545 – sequence: 8 givenname: Felice C. surname: Lightstone fullname: Lightstone, Felice C. email: lightstone1@llnl.gov organization: Physical and Life Sciences, Lawrence Livermore National Laboratory,Livermore,California,94550 – sequence: 9 givenname: Harsh surname: Bhatia fullname: Bhatia, Harsh email: hbhatia@llnl.gov organization: Lawrence Livermore National Laboratory,Center for Applied Scientific Computing,Livermore,California,94550 – sequence: 10 givenname: Sara Kokkila surname: Schumacher fullname: Schumacher, Sara Kokkila email: saraks@ibm.com organization: IBM Thomas J. Watson Research Center,Yorktown Heights,New York,10598 – sequence: 11 givenname: Xiaohua surname: Zhang fullname: Zhang, Xiaohua email: zhang30@llnl.gov organization: Physical and Life Sciences, Lawrence Livermore National Laboratory,Livermore,California,94550 – sequence: 12 givenname: Gautham surname: Dharuman fullname: Dharuman, Gautham email: dharuman1@Hnl.gov organization: Physical and Life Sciences, Lawrence Livermore National Laboratory,Livermore,California,94550 – sequence: 13 givenname: Claudia surname: Misale fullname: Misale, Claudia email: c.misale@ibm.com organization: IBM Thomas J. Watson Research Center,Yorktown Heights,New York,10598 – sequence: 14 givenname: Changhoan surname: Kim fullname: Kim, Changhoan email: ck624@hotmail.com organization: IBM Thomas J. Watson Research Center,Yorktown Heights,New York,10598 – sequence: 15 givenname: Dwight V. surname: Nissley fullname: Nissley, Dwight V. email: nissleyd@mail.nih.gov organization: Frederick National Laboratory,Frederick,Maryland,21701 – sequence: 16 givenname: Peer-Timo surname: Bremer fullname: Bremer, Peer-Timo email: bremer5@llnl.gov organization: Lawrence Livermore National Laboratory,Center for Applied Scientific Computing,Livermore,California,94550 – sequence: 17 givenname: Helgi I. surname: Ingolfsson fullname: Ingolfsson, Helgi I. email: ingolfsson1@llnl.gov organization: Physical and Life Sciences, Lawrence Livermore National Laboratory,Livermore,California,94550 – sequence: 18 givenname: Timothy S. surname: Carpenter fullname: Carpenter, Timothy S. email: carpenter36@llnl.gov organization: Physical and Life Sciences, Lawrence Livermore National Laboratory,Livermore,California,94550 – sequence: 19 givenname: Tomas surname: Oppelstrup fullname: Oppelstrup, Tomas email: oppelstrup2@llnl.gov organization: Lawrence Livermore National Laboratory,Center for Applied Scientific Computing,Livermore,California,94550 – sequence: 20 givenname: Shiv surname: Sundram fullname: Sundram, Shiv email: shivsundram@gmail.com organization: Applications, Simulations, and Quality, Lawrence Livermore National Laboratory,Livermore,California,94550 – sequence: 21 givenname: Michael P. surname: Surh fullname: Surh, Michael P. email: surh1@Hnl.gov organization: Lawrence Livermore National Laboratory,Center for Applied Scientific Computing,Livermore,California,94550 – sequence: 22 givenname: Lars surname: Schneidenbach fullname: Schneidenbach, Lars email: schneidenbach@us.ibm.com organization: IBM Thomas J. Watson Research Center,Yorktown Heights,New York,10598 – sequence: 23 givenname: Bruce surname: D'Amora fullname: D'Amora, Bruce email: damora@us.ibm.com organization: IBM Thomas J. Watson Research Center,Yorktown Heights,New York,10598 – sequence: 24 givenname: Fred surname: Streitz fullname: Streitz, Fred email: streitz1@llnl.gov organization: Lawrence Livermore National Laboratory,Livermore,California,94550 – sequence: 25 givenname: James N. surname: Glosli fullname: Glosli, James N. email: glosli1@llnl.gov organization: Physical and Life Sciences, Lawrence Livermore National Laboratory,Livermore,California,94550 |
| BookMark | eNotzDtPwzAYhWGDQKKUziwM_gMpn-04dtiiikulViAKc-X4AkZuUtkOqP-eqDCd4T16LtFZ13cWoWsCc0JKfstozTnAnDFekVqcoFkt5BiAVZTWcIomlFSiKBkTF2iW0hcAMAolkTBBqcFrlZL_tuGAX1RUIdiAl52LKuU46DxEi10fcWPUPo83vB5C9kmrYPHG74agsu-7dIfXvbHBdx_4tdmMgM_-WEY0f_6owxFZqE7beIXOnQrJzv53it4f7t8WT8Xq-XG5aFaFoqXMhQDniJEgCFOiZHXrDG95pbSU2rZStpUpQUtuRa1aQzU3lpXM2Uow4YzUbIpu_lxvrd3uo9-peNgSqIHSirBfmoVe1w |
| ContentType | Conference Proceeding |
| DBID | 6IE 6IL CBEJK RIE RIL |
| DOI | 10.1145/3295500.3356197 |
| DatabaseName | IEEE Electronic Library (IEL) Conference Proceedings IEEE Proceedings Order Plan All Online (POP All Online) 1998-present by volume IEEE Xplore All Conference Proceedings IEEE Xplore IEEE Proceedings Order Plans (POP All) 1998-Present |
| DatabaseTitleList | |
| Database_xml | – sequence: 1 dbid: RIE name: IEEE Electronic Library (IEL) url: https://ieeexplore.ieee.org/ sourceTypes: Publisher |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Computer Science |
| EISBN | 9781450362290 145036229X |
| EISSN | 2167-4337 |
| EndPage | 16 |
| ExternalDocumentID | 10902261 |
| Genre | orig-research |
| GroupedDBID | 6IE 6IF 6IH 6IK 6IL 6IN AAWTH ABLEC ADZIZ ALMA_UNASSIGNED_HOLDINGS BEFXN BFFAM BGNUA BKEBE BPEOZ CBEJK CHZPO IEGSK IPLJI OCL RIE RIL |
| ID | FETCH-LOGICAL-a248t-70ff1d80713a7439bfd5b56ac88ceb88b6d40c85e79abd2c5de343fe6737fd8c3 |
| IEDL.DBID | RIE |
| ISICitedReferencesCount | 38 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000545976800057&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| IngestDate | Wed Mar 12 06:17:07 EDT 2025 |
| IsPeerReviewed | false |
| IsScholarly | false |
| Language | English |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-a248t-70ff1d80713a7439bfd5b56ac88ceb88b6d40c85e79abd2c5de343fe6737fd8c3 |
| PageCount | 16 |
| ParticipantIDs | ieee_primary_10902261 |
| PublicationCentury | 2000 |
| PublicationDate | 2019-Nov.-17 |
| PublicationDateYYYYMMDD | 2019-11-17 |
| PublicationDate_xml | – month: 11 year: 2019 text: 2019-Nov.-17 day: 17 |
| PublicationDecade | 2010 |
| PublicationTitle | SC19: International Conference for High Performance Computing, Networking, Storage and Analysis |
| PublicationTitleAbbrev | SC |
| PublicationYear | 2019 |
| Publisher | ACM |
| Publisher_xml | – name: ACM |
| SSID | ssj0003204180 ssj0002871321 |
| Score | 2.0218446 |
| Snippet | Computational models can define the functional dynamics of complex systems in exceptional detail. However, many modeling studies face seemingly incommensurate... |
| SourceID | ieee |
| SourceType | Publisher |
| StartPage | 1 |
| SubjectTerms | Adaptation models adaptive simulations Analytical models Biological system modeling cancer research Computational modeling heterogenous architecture machine learning massively parallel multiscale simulations Parallel processing Plasmas Proteins Robustness Scalability Supercomputers |
| Title | A Massively Parallel Infrastructure for Adaptive Multiscale Simulations: Modeling RAS Initiation Pathway for Cancer |
| URI | https://ieeexplore.ieee.org/document/10902261 |
| WOSCitedRecordID | wos000545976800057&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV07T8MwELagYmAqjyLe8sAampdjm62qqECCqqIgdav8uIhKJa3SFtR_j89JixgY2JIMp-jOsb_P8XcfITeWSwdDrApC4DxIs1AFOgMWMMfEsC2uyayv9BPv98VoJAe1WN1rYQDAHz6DW7z0__LtzKxwq6ztDxHGSHZ2Oc8qsdZ2QwWhf1KvRXifxGEaibBu5xOlrJ3E0uFxR1MTBxrkbz8Vv5z0mv98kQPS-hHm0cF2yTkkO1AckebGmYHWH-oxWXTos0PFbiabrulAlWiYMqWPRV6qqmHsqgTq4CrtWDXHCY96Ie7CFQzocPJRe3ot7ih6paFinb50hi7AZFmV0gVdvn-ptQ_SxZFTtshb7_61-xDU9gqBilOxDHiY55EVSFMV0hKdW6ZZpowQBrQQOrNpaAQDLpW2sWEWkjTJAZ1tcitMckIaxayAU0KZjlKuOETGsa8oi1VkNQ6OnEuQAsIz0sIkjudVB43xJn_nfzy_IPsOmEjU_EX8kjRcZuCK7JlPl4ny2tf9G9J2rvQ |
| linkProvider | IEEE |
| linkToHtml | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LTwIxEG4MmugJHxjf9uB1Zbuvtt4IkUAEQgQTbqTbzkYSBLKAhn9vpywYDx687e5hspmZ7XzT7TcfIQ-GSwtDjPJ84NyLEl95aQKxF9tODMfi6sS4SLd5tyuGQ9kryOqOCwMA7vAZPOKl-5dvZnqFW2VVd4gwwGZnH6WzCrrWbksFwX9YVCO8DwM_YsIvBvqwKK6GgbSI3DaqoYUN8reiiisojfI_X-WYVH6oebS3KzonZA-mp6S81Wagxad6RhY12rG42K5lkzXtqRwlUya0Nc1ytRkZu8qBWsBKa0bNccmjjoq7sCED2h9_FKpeiyeKamnIWaevtb41MF5ugmmNLt-_1NoZqWPu5BXy1nge1JteIbDgqSASS4_7WcaMwEZVYWOSZiZO40RpITSkQqSJiXwtYuBSpSbQsYEwCjNAbZvMCB2ek9J0NoULQuOURVxxYNr2XywJFDMppkfGJUgB_iWpoBNH880MjdHWf1d_PL8nh81Bpz1qt7ov1-TIwhSJDEDGb0jJegluyYH-tF7J71wOfAMaubI9 |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=proceeding&rft.title=SC19%3A+International+Conference+for+High+Performance+Computing%2C+Networking%2C+Storage+and+Analysis&rft.atitle=A+Massively+Parallel+Infrastructure+for+Adaptive+Multiscale+Simulations%3A+Modeling+RAS+Initiation+Pathway+for+Cancer&rft.au=Di+Natale%2C+Francesco&rft.au=Neale%2C+Chris&rft.au=Stanton%2C+Liam&rft.au=Scogland%2C+Thomas+R.+W.&rft.date=2019-11-17&rft.pub=ACM&rft.eissn=2167-4337&rft.spage=1&rft.epage=16&rft_id=info:doi/10.1145%2F3295500.3356197&rft.externalDocID=10902261 |