# A Metascalable Computing Framework for Large Spatiotemporal-Scale Atomistic Simulations

## Abstract

A metascalable (or 'design once, scale on new architectures') parallel computing framework has been developed for large spatiotemporal-scale atomistic simulations of materials based on spatiotemporal data locality principles, which is expected to scale on emerging multipetaflops architectures. The framework consists of: (1) an embedded divide-and-conquer (EDC) algorithmic framework based on spatial locality to design linear-scaling algorithms for high complexity problems; (2) a space-time-ensemble parallel (STEP) approach based on temporal locality to predict long-time dynamics, while introducing multiple parallelization axes; and (3) a tunable hierarchical cellular decomposition (HCD) parallelization framework to map these O(N) algorithms onto a multicore cluster based on hybrid implementation combining message passing and critical section-free multithreading. The EDC-STEP-HCD framework exposes maximal concurrency and data locality, thereby achieving: (1) inter-node parallel efficiency well over 0.95 for 218 billion-atom molecular-dynamics and 1.68 trillion electronic-degrees-of-freedom quantum-mechanical simulations on 212,992 IBM BlueGene/L processors (superscalability); (2) high intra-node, multithreading parallel efficiency (nanoscalability); and (3) nearly perfect time/ensemble parallel efficiency (eon-scalability). The spatiotemporal scale covered by MD simulation on a sustained petaflops computer per day (i.e. petaflops {center_dot} day of computing) is estimated as NT = 2.14 (e.g. N = 2.14 million atoms for T = 1 microseconds).

- Authors:

- Publication Date:

- Research Org.:
- Lawrence Livermore National Lab. (LLNL), Livermore, CA (United States)

- Sponsoring Org.:
- USDOE

- OSTI Identifier:
- 956831

- Report Number(s):
- LLNL-PROC-411166

TRN: US1002133

- DOE Contract Number:
- W-7405-ENG-48

- Resource Type:
- Conference

- Resource Relation:
- Conference: Presented at: The 23rd IEEE International Parallel & Distributed Processing Symposium, Rome, Italy, May 25 - May 29, 2009

- Country of Publication:
- United States

- Language:
- English

- Subject:
- 75 CONDENSED MATTER PHYSICS, SUPERCONDUCTIVITY AND SUPERFLUIDITY; ALGORITHMS; ATOMS; COMPUTERS; DESIGN; EFFICIENCY; IMPLEMENTATION; PROCESSING; SIMULATION

### Citation Formats

```
Nomura, K, Seymour, R, Wang, W, Kalia, R, Nakano, A, Vashishta, P, Shimojo, F, and Yang, L H.
```*A Metascalable Computing Framework for Large Spatiotemporal-Scale Atomistic Simulations*. United States: N. p., 2009.
Web. doi:10.1109/IPDPS.2009.5160992.

```
Nomura, K, Seymour, R, Wang, W, Kalia, R, Nakano, A, Vashishta, P, Shimojo, F, & Yang, L H.
```*A Metascalable Computing Framework for Large Spatiotemporal-Scale Atomistic Simulations*. United States. https://doi.org/10.1109/IPDPS.2009.5160992

```
Nomura, K, Seymour, R, Wang, W, Kalia, R, Nakano, A, Vashishta, P, Shimojo, F, and Yang, L H. Tue .
"A Metascalable Computing Framework for Large Spatiotemporal-Scale Atomistic Simulations". United States. https://doi.org/10.1109/IPDPS.2009.5160992. https://www.osti.gov/servlets/purl/956831.
```

```
@article{osti_956831,
```

title = {A Metascalable Computing Framework for Large Spatiotemporal-Scale Atomistic Simulations},

author = {Nomura, K and Seymour, R and Wang, W and Kalia, R and Nakano, A and Vashishta, P and Shimojo, F and Yang, L H},

abstractNote = {A metascalable (or 'design once, scale on new architectures') parallel computing framework has been developed for large spatiotemporal-scale atomistic simulations of materials based on spatiotemporal data locality principles, which is expected to scale on emerging multipetaflops architectures. The framework consists of: (1) an embedded divide-and-conquer (EDC) algorithmic framework based on spatial locality to design linear-scaling algorithms for high complexity problems; (2) a space-time-ensemble parallel (STEP) approach based on temporal locality to predict long-time dynamics, while introducing multiple parallelization axes; and (3) a tunable hierarchical cellular decomposition (HCD) parallelization framework to map these O(N) algorithms onto a multicore cluster based on hybrid implementation combining message passing and critical section-free multithreading. The EDC-STEP-HCD framework exposes maximal concurrency and data locality, thereby achieving: (1) inter-node parallel efficiency well over 0.95 for 218 billion-atom molecular-dynamics and 1.68 trillion electronic-degrees-of-freedom quantum-mechanical simulations on 212,992 IBM BlueGene/L processors (superscalability); (2) high intra-node, multithreading parallel efficiency (nanoscalability); and (3) nearly perfect time/ensemble parallel efficiency (eon-scalability). The spatiotemporal scale covered by MD simulation on a sustained petaflops computer per day (i.e. petaflops {center_dot} day of computing) is estimated as NT = 2.14 (e.g. N = 2.14 million atoms for T = 1 microseconds).},

doi = {10.1109/IPDPS.2009.5160992},

url = {https://www.osti.gov/biblio/956831},
journal = {},

number = ,

volume = ,

place = {United States},

year = {2009},

month = {2}

}