Resource allocation for task-level speculative scientific applications: A proof of concept using Parallel Trajectory Splicing
The constant increase in parallelism available on large-scale distributed computers poses major scalability challenges to many scientific applications. A common strategy to improve scalability is to express algorithms in terms of independent tasks that can be executed concurrently on a runtime syste...
Uloženo v:
| Vydáno v: | Parallel computing Ročník 112; s. 102936 |
|---|---|
| Hlavní autoři: | , , |
| Médium: | Journal Article |
| Jazyk: | angličtina |
| Vydáno: |
Elsevier B.V
01.09.2022
|
| Témata: | |
| ISSN: | 0167-8191, 1872-7336 |
| On-line přístup: | Získat plný text |
| Tagy: |
Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
|
| Abstract | The constant increase in parallelism available on large-scale distributed computers poses major scalability challenges to many scientific applications. A common strategy to improve scalability is to express algorithms in terms of independent tasks that can be executed concurrently on a runtime system. In this manuscript, we consider a generalization of this approach where task-level speculation is allowed. In this context, a probability is attached to each task which corresponds to the likelihood that the output of the speculative task will be consumed as part of the larger calculation. We consider the problem of optimal resource allocation to each of the possible tasks so as to maximize the total expected computational throughput. The power of this approach is demonstrated by analyzing its application to Parallel Trajectory Splicing, a massively-parallel long-time-dynamics method for atomistic simulations.
•Efficiently utilizing large-scale HPC machines has become increasingly difficult.•Speculative task-based execution serves as a means of increasing parallelism.•Performance relies on optimal resource allocation among speculative tasks.•Improved scaling of traditionally scale-limited applications; Molecular Dynamics. |
|---|---|
| AbstractList | The constant increase in parallelism available on large-scale distributed computers poses major scalability challenges to many scientific applications. A common strategy to improve scalability is to express algorithms in terms of independent tasks that can be executed concurrently on a runtime system. In this manuscript, we consider a generalization of this approach where task-level speculation is allowed. In this context, a probability is attached to each task which corresponds to the likelihood that the output of the speculative task will be consumed as part of the larger calculation. We consider the problem of optimal resource allocation to each of the possible tasks so as to maximize the total expected computational throughput. The power of this approach is demonstrated by analyzing its application to Parallel Trajectory Splicing, a massively-parallel long-time-dynamics method for atomistic simulations.
•Efficiently utilizing large-scale HPC machines has become increasingly difficult.•Speculative task-based execution serves as a means of increasing parallelism.•Performance relies on optimal resource allocation among speculative tasks.•Improved scaling of traditionally scale-limited applications; Molecular Dynamics. |
| ArticleNumber | 102936 |
| Author | Perez, Danny Garmon, Andrew Ramakrishnaiah, Vinay |
| Author_xml | – sequence: 1 givenname: Andrew orcidid: 0000-0002-5478-5160 surname: Garmon fullname: Garmon, Andrew email: agarmon@lanl.gov organization: Theoretical Division, Los Alamos National Laboratory, Los Alamos, NM, 87545, USA – sequence: 2 givenname: Vinay surname: Ramakrishnaiah fullname: Ramakrishnaiah, Vinay email: vinayr@lanl.gov organization: Computer, Computational, and Statistical Sciences Division, Los Alamos National Laboratory, Los Alamos, NM, 87545, USA – sequence: 3 givenname: Danny surname: Perez fullname: Perez, Danny email: danny_perez@lanl.gov organization: Theoretical Division, Los Alamos National Laboratory, Los Alamos, NM, 87545, USA |
| BookMark | eNqFkM9KAzEQh4NUsFafwEteYGuy2W52BQ-l-A8KitZziLMTSV03S5IWevDdTbuePCiECWTm-zH5Tsmocx0ScsHZlDNeXq6nvfbgpjnL8_SS16I8ImNeyTyTQpQjMk5TMqt4zU_IaQhrxlhZVGxMvp4xuI0HpLptHehoXUeN8zTq8JG1uMWWhh5h06bWFmkAi120xgLVfd_agQhXdE5775yh6YDrAPtIN8F27_RJ-xSdYlZerxGi8zv6sidT84wcG90GPP-5J-T19ma1uM-Wj3cPi_kyA8FEzCrGjYaybgoDKBtgUBvRFJLlemZMVZtClHzGBNMyZ1xUsm5YKqJAiW_ccDEh9ZAL3oXg0Siw8bB59Nq2ijO196jW6uBR7T2qwWNixS-29_ZT-90_1PVAYfrW1qJXB3OAjfVJgmqc_ZP_Bjwnkn0 |
| CitedBy_id | crossref_primary_10_7717_peerj_cs_2966 crossref_primary_10_1038_s41598_024_61647_6 |
| Cites_doi | 10.1109/JSYST.2017.2722476 10.1016/0021-9991(75)90060-1 10.1021/acs.jctc.5b00916 10.7717/peerj-cs.183 10.1016/S0167-8191(02)00216-8 10.1145/2742347 10.1145/224538.224564 10.1098/rsta.2019.0056 10.1137/18M1177792 10.1177/1094342007078442 10.1016/0377-2217(93)90177-O 10.1142/S0129626411000060 10.1145/2821505 10.1557/jmr.2017.456 10.1063/5.0014475 10.1287/trsc.36.2.231.561 10.1063/1.1415500 10.1177/0037549716674806 10.1016/j.cpc.2020.107262 10.1103/PhysRevLett.78.3908 10.1109/TCC.2015.2481400 10.1145/1465482.1465560 10.1145/165854.165874 10.1147/JRD.2011.2109230 10.1006/jcph.1995.1039 10.1145/2699715 10.1016/S1574-1400(09)00504-0 10.1016/j.commatsci.2014.12.011 10.1016/S0377-2217(99)00287-8 10.1063/1.481576 10.1088/1361-651X/aba511 10.1145/2400682.2400698 |
| ContentType | Journal Article |
| Copyright | 2022 Elsevier B.V. |
| Copyright_xml | – notice: 2022 Elsevier B.V. |
| DBID | AAYXX CITATION |
| DOI | 10.1016/j.parco.2022.102936 |
| DatabaseName | CrossRef |
| DatabaseTitle | CrossRef |
| DatabaseTitleList | |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Computer Science |
| EISSN | 1872-7336 |
| ExternalDocumentID | 10_1016_j_parco_2022_102936 S0167819122000369 |
| GroupedDBID | --K --M -~X .DC .~1 0R~ 123 1B1 1~. 1~5 29O 4.4 457 4G. 5VS 6OB 7-5 71M 8P~ 9JN AACTN AAEDT AAEDW AAIAV AAIKJ AAKOC AALRI AAOAW AAQFI AAQXK AAXUO AAYFN ABBOA ABEFU ABFNM ABJNI ABMAC ABXDB ABYKQ ACDAQ ACGFS ACNNM ACRLP ACZNC ADBBV ADEZE ADJOM ADMUD ADTZH AEBSH AECPX AEKER AENEX AFKWA AFTJW AGHFR AGUBO AGYEJ AHHHB AHJVU AHZHX AIALX AIEXJ AIKHN AITUG AJBFU AJOXV ALMA_UNASSIGNED_HOLDINGS AMFUW AMRAJ AOUOD ASPBG AVWKF AXJTR AZFZN BJAXD BKOJK BLXMC CS3 DU5 EBS EFJIC EFLBG EJD EO8 EO9 EP2 EP3 F5P FDB FEDTE FGOYB FIRID FNPLU FYGXN G-Q G8K GBLVA GBOLZ HLZ HVGLF HZ~ H~9 IHE J1W JJJVA KOM LG9 M41 MO0 N9A O-L O9- OAUVE OZT P-8 P-9 P2P PC. Q38 R2- RIG ROL RPZ SBC SCC SDF SDG SDP SES SEW SPC SPCBC SST SSV SSZ T5K WH7 WUQ XPP ZMT ~G- 9DU AATTM AAXKI AAYWO AAYXX ABDPE ABWVN ACLOT ACRPL ACVFH ADCNI ADNMO AEIPS AEUPX AFJKZ AFPUW AGQPQ AIGII AIIUN AKBMS AKRWK AKYEP ANKPU APXCP CITATION EFKBS ~HD |
| ID | FETCH-LOGICAL-c303t-801fac69d4fce7dc0c9f3d4702a5ff89f43615030a72013879d087934e7eb1f13 |
| ISICitedReferencesCount | 3 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000805900400001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 0167-8191 |
| IngestDate | Sat Nov 29 07:26:14 EST 2025 Tue Nov 18 21:44:55 EST 2025 Fri Feb 23 02:40:11 EST 2024 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Keywords | Task-based programming Discrete event simulation Accelerated molecular dynamics Speculation Resource allocation |
| Language | English |
| LinkModel | OpenURL |
| MergedId | FETCHMERGED-LOGICAL-c303t-801fac69d4fce7dc0c9f3d4702a5ff89f43615030a72013879d087934e7eb1f13 |
| ORCID | 0000-0002-5478-5160 |
| ParticipantIDs | crossref_citationtrail_10_1016_j_parco_2022_102936 crossref_primary_10_1016_j_parco_2022_102936 elsevier_sciencedirect_doi_10_1016_j_parco_2022_102936 |
| PublicationCentury | 2000 |
| PublicationDate | September 2022 2022-09-00 |
| PublicationDateYYYYMMDD | 2022-09-01 |
| PublicationDate_xml | – month: 09 year: 2022 text: September 2022 |
| PublicationDecade | 2020 |
| PublicationTitle | Parallel computing |
| PublicationYear | 2022 |
| Publisher | Elsevier B.V |
| Publisher_xml | – name: Elsevier B.V |
| References | Morales, Almeida, Garcıa, Roda, Rodrıguez (b29) 2000; 126 Mouad Ramil, Private communication. Alexander, Almgren, Bell, Bhattacharjee, Chen, Colella, Daniel, DeSlippe, Diachin, Draeger (b1) 2020; 378 LAMMPS website Minarolli, Freisleben (b24) 2014 Mniszewski, Junghans, Voter, Perez, Eidenbenz (b49) 2015; 25 Perez, Cubuk, Waterland, Kaxiras, Voter (b10) 2016; 12 Ma, Wang, Tak, Wang, Tang (b26) 2016 Robson, Buch, Kale (b2) 2016 Denardo (b32) 2012 Zamora, Voter, Perez, Santhi, Mniszewski, Thulasidasan, Eidenbenz (b48) 2016; 92 Rajamony, Arimilli, Gildea (b18) 2011; 55 Balaji, Buntinas, Goodell, Gropp, Hoefler, Kumar, Lusk, Thakur, Träff (b21) 2011; 21 Perez, Uberuaga, Voter (b46) 2015; 100 Plimpton (b38) 1995; 117 F. Almeida, F. Garcia, J. Roda, D. Morales, C. Rodríguez, A comparative study of two distributed systems: PVM and transputers, in: Transputers Applications and Systems’ 95, 1995, pp. 244–258. D. Morales, J. Roda, Francisco Almeida, Casiano Rodríguez, F. Garcia, Integral knapsack problems: Parallel algorithms and their implementations on distributed systems, in: Proceedings of the 9th International Conference on Supercomputing, 1995, pp. 218–226. . Perez, Huang, Voter (b41) 2018; 33 Tseng, Wang, Chou, Chao, Leung (b27) 2017; 12 Hilario Torres, Manolis Papadakis, Lluís Jofre Cruanyes, Soleil-X: Turbulence, particles, and radiation in the Regent programming language, in: SC’19: Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis, 2019, pp. 1–4. Wei, Foh, He, Cai (b25) 2015; 6 Bramas (b36) 2019; 5 Llanos, Orden, Palop (b33) 2008 Sorensen, Voter (b44) 2000; 112 Zamora, Perez, Martinez, Uberuaga, Voter (b45) 2020 Xu, Yan, Wan (b23) 2009 González, Almeida, Moreno, Rodrıguez (b34) 2003; 29 Chamberlain, Callahan, Zima (b12) 2007; 21 Gene M. Amdahl, Validity of the single processor approach to achieving large scale computing capabilities, in: Proceedings of the April 18-20, 1967, Spring Joint Computer Conference, 1967, pp. 483–485. Yiapanis, Rosas-Ham, Brown, Luján (b8) 2013; 9 Gibbons (b17) 1988 Bauer, Treichler, Slaughter, Aiken (b3) 2012 Garmon, Perez (b51) 2020; 28 Chen, Fu, Tang, Zhu (b28) 2015 Yiapanis, Brown, Luján (b9) 2015; 38 Jahn, Pagani, Kobbe, Chen, Henkel (b35) 2015; 2 Di Renzo, Fu, Urzay (b4) 2020 Tsolakis, Thomadakis, Chrisochoides (b37) 2021 Jain, Bohm, Mikida, Mandal, Kim, Jindal, Li, Ismail-Beigi, Martyna, Kale (b7) 2016 Moussa, Embaby, Farag (b22) 2017 Bortz, Kalos, Lebowitz (b53) 1975; 17 Henkelman, Jónsson (b42) 2001; 115 Andonov, Raimbault, Quinton (b15) 1993 Rosu, Schwan, Yalamanchili, Jha (b20) 1997 Elmaghraby (b30) 1993; 64 Aristoff (b47) 2019; 7 Phillips, Hardy, Maia, Stone, Ribeiro, Bernardi, Buch, Fiorin, Henin, Jiang, McGreevy, Melo, Radak, Skeel, Singharoy, Wang, Roux, Aksimentiev, Luthey-Schulten, Kale, Schulten, Chipot, Tajkhorshid (b5) 2020; 153 Faanes, Bataineh, Roweth, Court, Froese, Alverson, Johnson, Kopnick, Higgins, Reinhard (b19) 2012 OpenMP application programming interface Perez, Uberuaga, Shim, Amar, Voter (b50) 2009; 5 Laxmikant V. Kale, Sanjeev Krishnan, Charm＋＋ a portable concurrent object oriented system based on C＋＋, in: Proceedings of the Eighth Annual Conference on Object-Oriented Programming Systems, Languages, and Applications, 1993, pp. 91–108. Powell, Shapiro, Simão (b31) 2002; 36 Voter (b43) 1997; 78 Aristoff (10.1016/j.parco.2022.102936_b47) 2019; 7 Bramas (10.1016/j.parco.2022.102936_b36) 2019; 5 10.1016/j.parco.2022.102936_b6 Henkelman (10.1016/j.parco.2022.102936_b42) 2001; 115 Bortz (10.1016/j.parco.2022.102936_b53) 1975; 17 Denardo (10.1016/j.parco.2022.102936_b32) 2012 Andonov (10.1016/j.parco.2022.102936_b15) 1993 Chamberlain (10.1016/j.parco.2022.102936_b12) 2007; 21 Xu (10.1016/j.parco.2022.102936_b23) 2009 Faanes (10.1016/j.parco.2022.102936_b19) 2012 Voter (10.1016/j.parco.2022.102936_b43) 1997; 78 Chen (10.1016/j.parco.2022.102936_b28) 2015 Morales (10.1016/j.parco.2022.102936_b29) 2000; 126 Bauer (10.1016/j.parco.2022.102936_b3) 2012 Yiapanis (10.1016/j.parco.2022.102936_b9) 2015; 38 Tsolakis (10.1016/j.parco.2022.102936_b37) 2021 Plimpton (10.1016/j.parco.2022.102936_b38) 1995; 117 10.1016/j.parco.2022.102936_b16 Zamora (10.1016/j.parco.2022.102936_b48) 2016; 92 Zamora (10.1016/j.parco.2022.102936_b45) 2020 Powell (10.1016/j.parco.2022.102936_b31) 2002; 36 Jain (10.1016/j.parco.2022.102936_b7) 2016 Gibbons (10.1016/j.parco.2022.102936_b17) 1988 Sorensen (10.1016/j.parco.2022.102936_b44) 2000; 112 Perez (10.1016/j.parco.2022.102936_b41) 2018; 33 Yiapanis (10.1016/j.parco.2022.102936_b8) 2013; 9 Ma (10.1016/j.parco.2022.102936_b26) 2016 Elmaghraby (10.1016/j.parco.2022.102936_b30) 1993; 64 Perez (10.1016/j.parco.2022.102936_b46) 2015; 100 Llanos (10.1016/j.parco.2022.102936_b33) 2008 González (10.1016/j.parco.2022.102936_b34) 2003; 29 Phillips (10.1016/j.parco.2022.102936_b5) 2020; 153 Perez (10.1016/j.parco.2022.102936_b10) 2016; 12 Alexander (10.1016/j.parco.2022.102936_b1) 2020; 378 Garmon (10.1016/j.parco.2022.102936_b51) 2020; 28 Di Renzo (10.1016/j.parco.2022.102936_b4) 2020 10.1016/j.parco.2022.102936_b14 Robson (10.1016/j.parco.2022.102936_b2) 2016 10.1016/j.parco.2022.102936_b13 Mniszewski (10.1016/j.parco.2022.102936_b49) 2015; 25 10.1016/j.parco.2022.102936_b11 Balaji (10.1016/j.parco.2022.102936_b21) 2011; 21 10.1016/j.parco.2022.102936_b52 Wei (10.1016/j.parco.2022.102936_b25) 2015; 6 10.1016/j.parco.2022.102936_b39 Perez (10.1016/j.parco.2022.102936_b50) 2009; 5 Tseng (10.1016/j.parco.2022.102936_b27) 2017; 12 Minarolli (10.1016/j.parco.2022.102936_b24) 2014 Moussa (10.1016/j.parco.2022.102936_b22) 2017 10.1016/j.parco.2022.102936_b40 Rajamony (10.1016/j.parco.2022.102936_b18) 2011; 55 Rosu (10.1016/j.parco.2022.102936_b20) 1997 Jahn (10.1016/j.parco.2022.102936_b35) 2015; 2 |
| References_xml | – reference: Hilario Torres, Manolis Papadakis, Lluís Jofre Cruanyes, Soleil-X: Turbulence, particles, and radiation in the Regent programming language, in: SC’19: Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis, 2019, pp. 1–4. – volume: 17 start-page: 10 year: 1975 end-page: 18 ident: b53 article-title: A new algorithm for Monte Carlo simulation of Ising spin systems publication-title: J. Comput. Phys. – start-page: 1 year: 2012 end-page: 9 ident: b19 article-title: Cray cascade: A scalable HPC system based on a dragonfly network publication-title: SC’12: Proceedings of the International Conference on High Performance Computing, Networking, Storage and Analysis – volume: 7 start-page: 685 year: 2019 end-page: 719 ident: b47 article-title: Generalizing parallel replica dynamics: Trajectory fragments, asynchronous computing, and PDMPs publication-title: SIAM/ASA J. Uncertain. Quantif. – reference: Gene M. Amdahl, Validity of the single processor approach to achieving large scale computing capabilities, in: Proceedings of the April 18-20, 1967, Spring Joint Computer Conference, 1967, pp. 483–485. – year: 1988 ident: b17 article-title: Efficient Parallel Algorithms – volume: 12 start-page: 18 year: 2016 end-page: 28 ident: b10 article-title: Long-time dynamics through parallel trajectory splicing publication-title: J. Chem. Theory Comput. – volume: 21 start-page: 291 year: 2007 end-page: 312 ident: b12 article-title: Parallel programmability and the chapel language publication-title: Int. J. High Perform. Comput. Appl. – start-page: 334 year: 2008 end-page: 342 ident: b33 article-title: Just-in-time scheduling for loop-based speculative parallelization publication-title: 16th Euromicro Conference on Parallel, Distributed and Network-Based Processing, PDP 2008 – volume: 5 year: 2019 ident: b36 article-title: Increasing the degree of parallelism using speculative execution in task-based runtime systems publication-title: PeerJ Comput. Sci. – start-page: 1 year: 2017 end-page: 4 ident: b22 article-title: Intelligent real-time scheduling of dynamic processes in MPI publication-title: 2017 IEEE International Conference on Fuzzy Systems, FUZZ-IEEE – reference: F. Almeida, F. Garcia, J. Roda, D. Morales, C. Rodríguez, A comparative study of two distributed systems: PVM and transputers, in: Transputers Applications and Systems’ 95, 1995, pp. 244–258. – reference: Mouad Ramil, Private communication. – year: 1993 ident: b15 article-title: Dynamic programming parallel implementations for the knapsack problem – volume: 9 start-page: 1 year: 2013 end-page: 27 ident: b8 article-title: Optimizing software runtime systems for speculative parallelization publication-title: ACM Transactions on Architecture and Code Optimization (TACO) – reference: Laxmikant V. Kale, Sanjeev Krishnan, Charm＋＋ a portable concurrent object oriented system based on C＋＋, in: Proceedings of the Eighth Annual Conference on Object-Oriented Programming Systems, Languages, and Applications, 1993, pp. 91–108. – volume: 115 start-page: 9657 year: 2001 end-page: 9666 ident: b42 article-title: Long time scale kinetic Monte Carlo simulations without lattice approximation and predefined event table publication-title: J. Chem. Phys. – volume: 78 start-page: 3908 year: 1997 ident: b43 article-title: Hyperdynamics: Accelerated molecular dynamics of infrequent events publication-title: Phys. Rev. Lett. – volume: 55 year: 2011 ident: b18 article-title: PERCS: The IBM POWER7-IH high-performance computing system publication-title: IBM J. Res. Dev. – volume: 38 start-page: 1 year: 2015 end-page: 45 ident: b9 article-title: Compiler-driven software speculation for thread-level parallelism publication-title: ACM Transactions on Programming Languages and Systems (TOPLAS) – volume: 153 year: 2020 ident: b5 article-title: Scalable molecular dynamics on CPU and GPU architectures with NAMD publication-title: J. Chem. Phys. – volume: 112 start-page: 9599 year: 2000 end-page: 9606 ident: b44 article-title: Temperature-accelerated dynamics for simulation of infrequent events publication-title: J. Chem. Phys. – start-page: 40 year: 2016 end-page: 43 ident: b2 article-title: Runtime coordinated heterogeneous tasks in Charm＋＋ publication-title: Proceedings of the Second Internationsl Workshop on Extreme Scale Programming Models and Middleware – volume: 36 start-page: 231 year: 2002 end-page: 249 ident: b31 article-title: An adaptive dynamic programming algorithm for the heterogeneous resource allocation problem publication-title: Transp. Sci. – volume: 64 start-page: 199 year: 1993 end-page: 215 ident: b30 article-title: Resource allocation via dynamic programming in activity networks publication-title: European J. Oper. Res. – reference: LAMMPS website, – volume: 2 start-page: 1 year: 2015 end-page: 23 ident: b35 article-title: Runtime resource allocation for software pipelines publication-title: ACM Trans. Parallel Comput. – volume: 33 start-page: 813 year: 2018 end-page: 822 ident: b41 article-title: Long-time molecular dynamics simulations on massively parallel platforms: A comparison of parallel replica dynamics and parallel trajectory splicing publication-title: J. Mater. Res. – start-page: 745 year: 2020 end-page: 772 ident: b45 article-title: Accelerated molecular dynamics methods in a massively parallel world publication-title: Handbook of Materials Modeling: Methods: Theory and Modeling – reference: D. Morales, J. Roda, Francisco Almeida, Casiano Rodríguez, F. Garcia, Integral knapsack problems: Parallel algorithms and their implementations on distributed systems, in: Proceedings of the 9th International Conference on Supercomputing, 1995, pp. 218–226. – volume: 25 start-page: 1 year: 2015 end-page: 26 ident: b49 article-title: Tadsim: Discrete event-based performance prediction for temperature-accelerated dynamics publication-title: ACM Trans. Model. Comput. Simul. – start-page: 139 year: 2016 end-page: 158 ident: b7 article-title: Openatom: scalable ab-initio molecular dynamics with diverse capabilities publication-title: International Conference on High Performance Computing – start-page: 320 year: 1997 end-page: 329 ident: b20 article-title: On adaptive resource allocation for complex real-time applications publication-title: Proceedings Real-Time Systems Symposium – volume: 6 start-page: 264 year: 2015 end-page: 275 ident: b25 article-title: Towards efficient resource allocation for heterogeneous workloads in IaaS clouds publication-title: IEEE Trans. Cloud Comput. – start-page: 288 year: 2015 end-page: 292 ident: b28 article-title: Resource monitoring and prediction in cloud computing environments publication-title: 2015 3rd International Conference on Applied Computing and Information Technology/2nd International Conference on Computational Science and Intelligence – volume: 126 start-page: 166 year: 2000 end-page: 174 ident: b29 article-title: Design of parallel algorithms for the single resource allocation problem publication-title: European J. Oper. Res. – volume: 21 start-page: 45 year: 2011 end-page: 60 ident: b21 article-title: MPI on millions of cores publication-title: Parallel Process. Lett. – start-page: 109 year: 2009 end-page: 114 ident: b23 article-title: Grey prediction control of adaptive resources allocation in virtualized computing system publication-title: 2009 Eighth IEEE International Conference on Dependable, Autonomic and Secure Computing – volume: 29 start-page: 241 year: 2003 end-page: 254 ident: b34 article-title: Towards the automatic optimal mapping of pipeline algorithms publication-title: Parallel Comput. – volume: 28 year: 2020 ident: b51 article-title: Exploiting model uncertainty to improve the scalability of long-time simulations using parallel trajectory splicing publication-title: Modelling Simulation Mater. Sci. Eng. – volume: 378 year: 2020 ident: b1 article-title: Exascale applications: Skin in the game publication-title: Phil. Trans. R. Soc. A – start-page: 545 year: 2016 end-page: 552 ident: b26 article-title: Auto-tuning performance of MPI parallel programs using resource management in container-based virtual cloud publication-title: 2016 IEEE 9th International Conference on Cloud Computing, CLOUD – volume: 100 start-page: 90 year: 2015 end-page: 103 ident: b46 article-title: The parallel replica dynamics method–Coming of age publication-title: Comput. Mater. Sci. – year: 2020 ident: b4 article-title: HTR solver: An open-source exascale-oriented task-based multi-GPU high-order code for hypersonic aerothermodynamics publication-title: Comput. Phys. Comm. – volume: 92 start-page: 1065 year: 2016 end-page: 1086 ident: b48 article-title: Discrete event performance prediction of speculatively parallel temperature-accelerated dynamics publication-title: Simulation – volume: 5 start-page: 79 year: 2009 end-page: 98 ident: b50 article-title: Accelerated molecular dynamics methods: Introduction and recent developments publication-title: Annu. Rep. Comput. Chem. – volume: 12 start-page: 1688 year: 2017 end-page: 1699 ident: b27 article-title: Dynamic resource prediction and allocation for cloud data center using the multiobjective genetic algorithm publication-title: IEEE Syst. J. – volume: 117 start-page: 1 year: 1995 end-page: 19 ident: b38 article-title: Fast parallel algorithms for short-range molecular dynamics publication-title: J. Comput. Phys. – reference: . – start-page: 1 year: 2012 end-page: 11 ident: b3 article-title: Legion: Expressing locality and independence with logical regions publication-title: SC’12: Proceedings of the International Conference on High Performance Computing, Networking, Storage and Analysis – start-page: 490 year: 2014 end-page: 499 ident: b24 article-title: Distributed resource allocation to virtual machines via artificial neural networks publication-title: 2014 22nd Euromicro International Conference on Parallel, Distributed, and Network-Based Processing – reference: OpenMP application programming interface, – year: 2012 ident: b32 article-title: Dynamic Programming: Models and Applications – start-page: 1 year: 2021 end-page: 32 ident: b37 article-title: Tasking framework for adaptive speculative parallel mesh generation publication-title: J. Supercomput. – volume: 12 start-page: 1688 issue: 2 year: 2017 ident: 10.1016/j.parco.2022.102936_b27 article-title: Dynamic resource prediction and allocation for cloud data center using the multiobjective genetic algorithm publication-title: IEEE Syst. J. doi: 10.1109/JSYST.2017.2722476 – year: 1988 ident: 10.1016/j.parco.2022.102936_b17 – start-page: 745 year: 2020 ident: 10.1016/j.parco.2022.102936_b45 article-title: Accelerated molecular dynamics methods in a massively parallel world – volume: 17 start-page: 10 issue: 1 year: 1975 ident: 10.1016/j.parco.2022.102936_b53 article-title: A new algorithm for Monte Carlo simulation of Ising spin systems publication-title: J. Comput. Phys. doi: 10.1016/0021-9991(75)90060-1 – volume: 12 start-page: 18 issue: 1 year: 2016 ident: 10.1016/j.parco.2022.102936_b10 article-title: Long-time dynamics through parallel trajectory splicing publication-title: J. Chem. Theory Comput. doi: 10.1021/acs.jctc.5b00916 – volume: 5 year: 2019 ident: 10.1016/j.parco.2022.102936_b36 article-title: Increasing the degree of parallelism using speculative execution in task-based runtime systems publication-title: PeerJ Comput. Sci. doi: 10.7717/peerj-cs.183 – volume: 29 start-page: 241 issue: 2 year: 2003 ident: 10.1016/j.parco.2022.102936_b34 article-title: Towards the automatic optimal mapping of pipeline algorithms publication-title: Parallel Comput. doi: 10.1016/S0167-8191(02)00216-8 – volume: 2 start-page: 1 issue: 1 year: 2015 ident: 10.1016/j.parco.2022.102936_b35 article-title: Runtime resource allocation for software pipelines publication-title: ACM Trans. Parallel Comput. doi: 10.1145/2742347 – ident: 10.1016/j.parco.2022.102936_b16 doi: 10.1145/224538.224564 – ident: 10.1016/j.parco.2022.102936_b52 – ident: 10.1016/j.parco.2022.102936_b14 – volume: 378 issue: 2166 year: 2020 ident: 10.1016/j.parco.2022.102936_b1 article-title: Exascale applications: Skin in the game publication-title: Phil. Trans. R. Soc. A doi: 10.1098/rsta.2019.0056 – start-page: 40 year: 2016 ident: 10.1016/j.parco.2022.102936_b2 article-title: Runtime coordinated heterogeneous tasks in Charm＋＋ – volume: 7 start-page: 685 issue: 2 year: 2019 ident: 10.1016/j.parco.2022.102936_b47 article-title: Generalizing parallel replica dynamics: Trajectory fragments, asynchronous computing, and PDMPs publication-title: SIAM/ASA J. Uncertain. Quantif. doi: 10.1137/18M1177792 – volume: 21 start-page: 291 issue: 3 year: 2007 ident: 10.1016/j.parco.2022.102936_b12 article-title: Parallel programmability and the chapel language publication-title: Int. J. High Perform. Comput. Appl. doi: 10.1177/1094342007078442 – volume: 64 start-page: 199 issue: 2 year: 1993 ident: 10.1016/j.parco.2022.102936_b30 article-title: Resource allocation via dynamic programming in activity networks publication-title: European J. Oper. Res. doi: 10.1016/0377-2217(93)90177-O – volume: 21 start-page: 45 issue: 01 year: 2011 ident: 10.1016/j.parco.2022.102936_b21 article-title: MPI on millions of cores publication-title: Parallel Process. Lett. doi: 10.1142/S0129626411000060 – start-page: 490 year: 2014 ident: 10.1016/j.parco.2022.102936_b24 article-title: Distributed resource allocation to virtual machines via artificial neural networks – volume: 38 start-page: 1 issue: 2 year: 2015 ident: 10.1016/j.parco.2022.102936_b9 article-title: Compiler-driven software speculation for thread-level parallelism publication-title: ACM Transactions on Programming Languages and Systems (TOPLAS) doi: 10.1145/2821505 – year: 1993 ident: 10.1016/j.parco.2022.102936_b15 – volume: 33 start-page: 813 issue: 7 year: 2018 ident: 10.1016/j.parco.2022.102936_b41 article-title: Long-time molecular dynamics simulations on massively parallel platforms: A comparison of parallel replica dynamics and parallel trajectory splicing publication-title: J. Mater. Res. doi: 10.1557/jmr.2017.456 – start-page: 334 year: 2008 ident: 10.1016/j.parco.2022.102936_b33 article-title: Just-in-time scheduling for loop-based speculative parallelization – volume: 153 issue: 4 year: 2020 ident: 10.1016/j.parco.2022.102936_b5 article-title: Scalable molecular dynamics on CPU and GPU architectures with NAMD publication-title: J. Chem. Phys. doi: 10.1063/5.0014475 – volume: 36 start-page: 231 issue: 2 year: 2002 ident: 10.1016/j.parco.2022.102936_b31 article-title: An adaptive dynamic programming algorithm for the heterogeneous resource allocation problem publication-title: Transp. Sci. doi: 10.1287/trsc.36.2.231.561 – start-page: 545 year: 2016 ident: 10.1016/j.parco.2022.102936_b26 article-title: Auto-tuning performance of MPI parallel programs using resource management in container-based virtual cloud – volume: 115 start-page: 9657 issue: 21 year: 2001 ident: 10.1016/j.parco.2022.102936_b42 article-title: Long time scale kinetic Monte Carlo simulations without lattice approximation and predefined event table publication-title: J. Chem. Phys. doi: 10.1063/1.1415500 – start-page: 1 year: 2017 ident: 10.1016/j.parco.2022.102936_b22 article-title: Intelligent real-time scheduling of dynamic processes in MPI – ident: 10.1016/j.parco.2022.102936_b11 – volume: 92 start-page: 1065 issue: 12 year: 2016 ident: 10.1016/j.parco.2022.102936_b48 article-title: Discrete event performance prediction of speculatively parallel temperature-accelerated dynamics publication-title: Simulation doi: 10.1177/0037549716674806 – start-page: 139 year: 2016 ident: 10.1016/j.parco.2022.102936_b7 article-title: Openatom: scalable ab-initio molecular dynamics with diverse capabilities – year: 2012 ident: 10.1016/j.parco.2022.102936_b32 – year: 2020 ident: 10.1016/j.parco.2022.102936_b4 article-title: HTR solver: An open-source exascale-oriented task-based multi-GPU high-order code for hypersonic aerothermodynamics publication-title: Comput. Phys. Comm. doi: 10.1016/j.cpc.2020.107262 – volume: 78 start-page: 3908 issue: 20 year: 1997 ident: 10.1016/j.parco.2022.102936_b43 article-title: Hyperdynamics: Accelerated molecular dynamics of infrequent events publication-title: Phys. Rev. Lett. doi: 10.1103/PhysRevLett.78.3908 – volume: 6 start-page: 264 issue: 1 year: 2015 ident: 10.1016/j.parco.2022.102936_b25 article-title: Towards efficient resource allocation for heterogeneous workloads in IaaS clouds publication-title: IEEE Trans. Cloud Comput. doi: 10.1109/TCC.2015.2481400 – ident: 10.1016/j.parco.2022.102936_b40 doi: 10.1145/1465482.1465560 – ident: 10.1016/j.parco.2022.102936_b13 doi: 10.1145/165854.165874 – start-page: 1 year: 2021 ident: 10.1016/j.parco.2022.102936_b37 article-title: Tasking framework for adaptive speculative parallel mesh generation publication-title: J. Supercomput. – volume: 55 issue: 3 year: 2011 ident: 10.1016/j.parco.2022.102936_b18 article-title: PERCS: The IBM POWER7-IH high-performance computing system publication-title: IBM J. Res. Dev. doi: 10.1147/JRD.2011.2109230 – volume: 117 start-page: 1 issue: 1 year: 1995 ident: 10.1016/j.parco.2022.102936_b38 article-title: Fast parallel algorithms for short-range molecular dynamics publication-title: J. Comput. Phys. doi: 10.1006/jcph.1995.1039 – volume: 25 start-page: 1 issue: 3 year: 2015 ident: 10.1016/j.parco.2022.102936_b49 article-title: Tadsim: Discrete event-based performance prediction for temperature-accelerated dynamics publication-title: ACM Trans. Model. Comput. Simul. doi: 10.1145/2699715 – ident: 10.1016/j.parco.2022.102936_b39 – volume: 5 start-page: 79 year: 2009 ident: 10.1016/j.parco.2022.102936_b50 article-title: Accelerated molecular dynamics methods: Introduction and recent developments publication-title: Annu. Rep. Comput. Chem. doi: 10.1016/S1574-1400(09)00504-0 – volume: 100 start-page: 90 year: 2015 ident: 10.1016/j.parco.2022.102936_b46 article-title: The parallel replica dynamics method–Coming of age publication-title: Comput. Mater. Sci. doi: 10.1016/j.commatsci.2014.12.011 – start-page: 320 year: 1997 ident: 10.1016/j.parco.2022.102936_b20 article-title: On adaptive resource allocation for complex real-time applications – start-page: 288 year: 2015 ident: 10.1016/j.parco.2022.102936_b28 article-title: Resource monitoring and prediction in cloud computing environments – ident: 10.1016/j.parco.2022.102936_b6 – volume: 126 start-page: 166 issue: 1 year: 2000 ident: 10.1016/j.parco.2022.102936_b29 article-title: Design of parallel algorithms for the single resource allocation problem publication-title: European J. Oper. Res. doi: 10.1016/S0377-2217(99)00287-8 – volume: 112 start-page: 9599 issue: 21 year: 2000 ident: 10.1016/j.parco.2022.102936_b44 article-title: Temperature-accelerated dynamics for simulation of infrequent events publication-title: J. Chem. Phys. doi: 10.1063/1.481576 – volume: 28 issue: 6 year: 2020 ident: 10.1016/j.parco.2022.102936_b51 article-title: Exploiting model uncertainty to improve the scalability of long-time simulations using parallel trajectory splicing publication-title: Modelling Simulation Mater. Sci. Eng. doi: 10.1088/1361-651X/aba511 – volume: 9 start-page: 1 issue: 4 year: 2013 ident: 10.1016/j.parco.2022.102936_b8 article-title: Optimizing software runtime systems for speculative parallelization publication-title: ACM Transactions on Architecture and Code Optimization (TACO) doi: 10.1145/2400682.2400698 – start-page: 1 year: 2012 ident: 10.1016/j.parco.2022.102936_b19 article-title: Cray cascade: A scalable HPC system based on a dragonfly network – start-page: 1 year: 2012 ident: 10.1016/j.parco.2022.102936_b3 article-title: Legion: Expressing locality and independence with logical regions – start-page: 109 year: 2009 ident: 10.1016/j.parco.2022.102936_b23 article-title: Grey prediction control of adaptive resources allocation in virtualized computing system |
| SSID | ssj0006480 |
| Score | 2.3427765 |
| Snippet | The constant increase in parallelism available on large-scale distributed computers poses major scalability challenges to many scientific applications. A... |
| SourceID | crossref elsevier |
| SourceType | Enrichment Source Index Database Publisher |
| StartPage | 102936 |
| SubjectTerms | Accelerated molecular dynamics Discrete event simulation Resource allocation Speculation Task-based programming |
| Title | Resource allocation for task-level speculative scientific applications: A proof of concept using Parallel Trajectory Splicing |
| URI | https://dx.doi.org/10.1016/j.parco.2022.102936 |
| Volume | 112 |
| WOSCitedRecordID | wos000805900400001&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 | |
| journalDatabaseRights | – providerCode: PRVESC databaseName: Elsevier SD Freedom Collection Journals 2021 customDbUrl: eissn: 1872-7336 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0006480 issn: 0167-8191 databaseCode: AIEXJ dateStart: 19950101 isFulltext: true titleUrlDefault: https://www.sciencedirect.com providerName: Elsevier |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1Li9swEBZptode-i7dvtCht9TFKymW1VsoW9oelkC3JTcjyzIkm_UGbzbspfSvd0YP2zRlaQuFIIJjWSHzZebTaB6EvAYSLrmRMgHrwxNhRJrotLSJsHisVGZ5qoxrNiFPTvLFQs1Hox8xF2a3lk2TX1-rzX8VNVwDYWPq7F-Iu3soXID3IHQYQeww_pHgo0N-gkfqZhBLqC_PkjXGCE0wvdK17drZkBGJAUOT4WG2z1gH9Qpk0kWeu-zGyZVzLcx1iy1Y1lgafeXc_qCBcG60g4HtdvcZ1zsiforhPro9D92s-4hKd9x0rs-w6X2jl9p5fL4tmz7OZ25b7_EGsAYlFjwWsNmNIVnBjbaXSuM9m6CxcffoDZPXxrkE-s99hZROXfuw6z3V770Qq7cbQA1mdTKGZSkU_6XQtjPdX3A1XIwxV5FH3SIHTE5VPiYHs0_Hi8-dMc-Ea77XfbtYuMqFCO4t9XtyMyAsp_fJ3bDToDOPkAdkZJuH5F7s4kGDUn9EvkfA0B4wFABDe8DQAWBoDxg6BMw7OqMOLhReAS7UwYVGGNAeLjTC5TH5-uH49P3HJDTlSAywnS0ymlqbTFWiNlZWJjWq5pWQKdPTus5VLTj2GOCplgxPwaWqUhi4sBJoQX3En5Bxc9HYp4TqaaqN1YyXohRVKXRpU1tnujwCHstFeUhY_DULEyrWY-OUdRFDE1eFE0GBIii8CA7Jm27Sxhdsufn2LIqpCJzTc8kCcHXTxGf_OvE5udP_KV6Q8ba9si_JbbPbLi_bVwF_PwF3iaxU |
| linkProvider | Elsevier |
| 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%3Ajournal&rft.genre=article&rft.atitle=Resource+allocation+for+task-level+speculative+scientific+applications%3A+A+proof+of+concept+using+Parallel+Trajectory+Splicing&rft.jtitle=Parallel+computing&rft.au=Garmon%2C+Andrew&rft.au=Ramakrishnaiah%2C+Vinay&rft.au=Perez%2C+Danny&rft.date=2022-09-01&rft.pub=Elsevier+B.V&rft.issn=0167-8191&rft.eissn=1872-7336&rft.volume=112&rft_id=info:doi/10.1016%2Fj.parco.2022.102936&rft.externalDocID=S0167819122000369 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0167-8191&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0167-8191&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0167-8191&client=summon |