Inspired R&D is at the heart of computing at LLNL
Computation advances the frontiers of computational science and delivers game-changing solutions to society’s biggest challenges in energy, environment, and national and global security. Our research and development activities are applications driven and are focused on LLNL programmatic objectives. By embedding our experts in multidisciplinary mission support teams throughout the Lab, we are a cornerstone of LLNL’s success.
Among the many R&D areas Computation actively pursues are three overarching “core capabilities,” which are the skills and competencies that set LLNL apart and give it a competitive advantage. Computation currently owns three of the Lab’s core capabilities and initiatives:
High Performance Computing
Computation is home to an entire ecosystem of computer systems with massive numbers of multicore processors connected via high-speed interconnects running specialized system software to enable parallelism. We deliver a world-class HPC environment with constantly evolving hardware resources and a wealth of expertise in porting, running, and tuning large-scale applications. We have a stellar reputation of delivering multiple petaFLOP/s of productive compute power, massive shared parallel file systems, powerful data analysis platforms, and archival storage capable of storing hundreds of petabytes of data.
We conduct research and development of algorithms and software for solving linear and nonlinear systems, which are often obtained from approximations of partial differential equations and arise in numerous areas of science and engineering, including fluid dynamics, solid mechanics, combustion, elasticity, electromagnetics, large-scale data mining, and cyber security. We’re developing both innovative grid-based techniques for the computational modeling of physical problems and code infrastructures that facilitate the software implementation of such algorithms.
Current and emerging Laboratory missions demand innovation in all areas of data science. Petascale simulations are producing ever-larger data sets, and sensors from diverse sources such as the energy grid, satellites, and NIF experiments generate data that requires rapid analysis. We need better ways to organize, manage, share, analyze, and act on this data. To meet these needs, we’re developing fundamental data science technologies. We’re also creating signature applications to specifically address cyber security, electric grid optimization, biodefense, and climate change.
These core capabilities provide the foundation for research and development throughout LLNL.