It can take up to 10 months for a spacecraft to get from Earth to Mars. But the entire journey can be in vain if something goes wrong in the last six minutes. To plan the landing for NASA’s first manned mission to Mars, a team of NASA scientists and engineers are relying on high-resolution, NVIDIA GPU-powered physics simulations.
This demo from NASA shows a simulation of retropropulsion of a Mars lander using NASA’s FUN3D, a computational fluid dynamics simulation library. The resulting 150TBs of data is interactively visualized in real-time with NVIDIA IndeX and MagnumIO.
This research leverages three NVIDIA technologies—NVIDIA V100 GPUs, NVIDIA IndeX and GPUDirect Storage, part Magnum IO —to allow researchers to fly through the massive dataset in real time, volumetrically, and navigate while the simulation data continuously updates.
- The NVIDIA V100 Tensor Core GPUs, powering the Summit supercomputer, allows the team to incorporate a much higher resolution than prior projects, running large-scale problems while still capturing more of the physics involved than ever before
- NVIDIA Index allows users to interactively visualize large volumetric datasets.
- GPUDirect Storage speeds up data transfers by bypassing CPUs and sending data directly from storage to the GPU memory.
Each FUN3D simulation shows a specific moment in time along the lander’s descent trajectory. After being processed on Summit, each one can be rendered into a visualization showing different fluid dynamics variables such as density, vorticity and velocity.
Using the NVIDIA IndeX volumetric visualization SDK, a dynamic visualization can for the first time be generated out of the FUN3D data, each simulation measuring a colossal 150 terabytes.
GPUDirect Storage, part of the MagnumIO stack, transfers data directly from storage to the GPU memory, allowing users to visualize the entire dataset in real-time
Gaining a more detailed picture of the force fields on the vehicle when flying with retropropulsion can inform the team’s engine design choices for the Mars lander. They could use the visualizations to detect necessary adjustments, find design optimizations and test different configurations of how the engines integrate with the vehicle.