HPE has expanded NASA's Aitken supercomputer with HPE Apollo systems that are purpose-built for compute-intensive modeling and simulation needs. The expansion of computational power, which will be operational in January 2021, supports NASA's ongoing research involving computational fluid dynamics (CFD) that are critical to understanding aerodynamic events.
"At HPE, we are inspired by breakthroughs in scientific research that leverage our high-performance computing technologies. The researchers and engineers at NASA's Ames Research Center continue to push boundaries to advance space flight", stated Bill Mannel, vice president and general manager, HPC, at HPE. "We are honoured to continue collaborating with NASA and play a role in a historical moment by further expanding NASA's Aitken supercomputer with HPE Apollo systems to accelerate time-to-insight and safely land the first woman and the next man on the moon."
NASA's Aitken supercomputer was built by HPE in August 2019 to support NASA missions, including research for the Artemis programme, a mission to land the first woman and next man on the lunar South Pole region by 2024.
NASA's Aitken is housed in the first of 12 computer modules in the Modular Supercomputing Facility (MSF), jointly developed by NASA and HPE, to drive greater efficiency and significantly reduce electricity and water use. As a result, NASA's Aitken supercomputer, during its first year of operation, consumed only 16% of the energy needed for cooling, saving over $100K in costs and 1,4 million kilowatt-hours. It also reduced water usage, used to cool the supercomputer, by 91%, saving over one million gallons of water per day.
The supercomputer will expand with HPE Apollo systems using 2ndGen AMD EPYC processors to provide advanced compute power to support ongoing research.
NASA's Aitken supercomputer has already helped researchers make progress for the Artemis mission in the following areas:
NASA's engineers need to understand possible events that could occur during booster separation from the core of the Artemis rocket during liftoff, which is critical to the safety of the crew and success of the mission. NASA considers the possibilities that the two solid rocket boosters (SRBs), developed for the mission, will strike the core centre or each other during the separation event.
To simulate and model all variables during separation events during the Artemis mission, NASA has developed a database of aerodynamic data to showcase possible positioning of the boosters during separation. By applying computational fluid dynamics (CFD) tools using NASA's Aitken supercomputer and accounting for 22 different engine rocket plumes, which are moving hot exhaust gases, researchers were able to develop a database of 13 independent variables to model all possible in-flight events during booster separation. The project can be viewed online .
The expansion to NASA's Aitken supercomputer will enable even more detailed and comprehensive databases to improve accuracy in analysis for a safer flight.
The Artemis mission is set to launch at the Kennedy Space Center in Merritt Island, Florida. NASA's researchers need to understand the effects of ignition overpressure (IOP) and duct overpressure (DOP) waves that are caused by the rapid expansion of gas from the rocket nozzle during launch.
NASA's Launch, Ascent, and Vehicle Aerodynamics (LAVA) team has been using NASA's Aitken supercomputer to apply computational fluid dynamics (CFD) to simulate these waves and how they interact with the launch vehicle to examine any potential dangers to the mission.
The ongoing analysis helps NASA's engineers make advancements to the design of the launch environment. With the expanded Aitken supercomputer, researchers will gain additional compute power to further improve time-to-solution for the launch pad redesign to accommodate the Space Launch System. The project can be viewed online .
OpenMP ARB releases OpenMP 5.1 with vital usability enhancements ...
Lenovo delivers breakthrough HPC and AI solutions to help customers build a smarter way forward ...
NVIDIA announces A100 80GB GPU, supercharging world's most powerful GPU for AI supercomputing ...
NVIDIA DGX Station A100 offers researchers AI Data-Center-in-a-Box ...
Breadth, depth and scientific value of computational research in New England on display at SC20 ...
Fugaku tops supercomputer rankings again as Arm HPC ecosystem expands ...
Three RSC supercomputers represent Russia in global IO500 rating ...