Extending stability beyond CPU millennium
Citations Over TimeTop 10% of 2007 papers
Abstract
We report the computational advances that have enabled the first micron-scale simulation of a Kelvin-Helmholtz (KH) instability using molecular dynamics (MD). The advances are in three key areas for massively parallel computation such as on BlueGene/L (BG/L): fault tolerance, application kernel optimization, and highly efficient parallel I/O. In particular, we have developed novel capabilities for handling hardware parity errors and improving the speed of interatomic force calculations, while achieving near optimal I/O speeds on BG/L, allowing us to achieve excellent scalability and improve overall application performance. As a result we have successfully conducted a 2-billion atom KH simulation amounting to 2.8 CPU-millennia of run time, including a single, continuous simulation run in excess of 1.5 CPU-millennia. We have also conducted 9-billion and 62.5-billion atom KH simulations. The current optimized ddcMD code is benchmarked at 115.1 TFlop/s in our scaling study and 103.9 TFlop/s in a sustained science run, with additional improvements ongoing. These improvements enabled us to run the first MD simulations of micron-scale systems developing the KH instability.
Related Papers
- → Characterization and identification of HPC applications at leadership computing facility(2020)23 cited
- → Analysis of the efficiency characteristics of the first High-Temperature Direct Liquid Cooled Petascale supercomputer and its cooling infrastructure(2017)15 cited
- → Chronicles of Astra: Challenges and Lessons from the First Petascale Arm Supercomputer(2020)13 cited
- → The next-generation supercomputer project and a plan for the advanced institute for computational science(2010)1 cited
- Data-intensive computing on numerically-insensitive supercomputers(2010)