Skip to content
Hallway
0:00 / 0:00

#spacex#raptor#cuda

GPUs to Mars: Full-Scale Simulation of SpaceX's Mars Rocket Engine

insideHPC Report

11K subscribers • 1 video on Hallway

YouTube
  • Recommended by 5 people: 5 on Hacker News.
  • A classic. People kept recommending it from 2015 to 2024.
  • Presented by Stephen Jones and Adam Lichtl, SpaceX engineers

Advanced. Deep dive for people who know the field.

126K views11 years ago5 recommendations

Systems programmingGraphics and audioGPUs, shaders and CUDAPerformance and optimizationAlgorithms

Stephen Jones and Adam Lichtl explain how SpaceX uses wavelets and adaptive grids on GPUs to simulate the Raptor rocket engine.

In this video presentation from the GPU Technology Conference, Stephen Jones and Adam Lichtl from SpaceX present: GPUs to Mars: Full-Scale Simulation of SpaceX's Mars Rocket Engine. "SpaceX is designing a new, methane-fueled engine powerful enough to lift the equipment and personnel needed to colonize Mars. A vital aspect of this effort involves the creation of a multi-physics code to accurately model a running rocket engine. The scale and complexity of turbulent non-premixed combustion has so far made it impractical to simulate, even on today's largest supercomputers. We present a novel approach using wavelets on GPUs, capable of capturing physics down to the finest turbulent scales." See more talks from GTC 2015: gputechconf.com/ Sign up for our newsletter: insideHPC.com/newsletter

Why it's here

5 people recommend this

What people say. Recommended as an impressive real-world showcase of high-performance GPU computing, adaptive grids, and wavelet-based fluid dynamics simulation.

paulsutteron Hacker News • Recommends

On “Can SpaceX land a rocket with 1/2 cm accuracy?”

The key was the full scale combustion simulator software that SpaceX developed to design the Raptor. This talk was given at NVIDIA GTC 2015 and inspired me to go into manufacturing link to this video title: "GPUs To Mars: Full Scale Simulation of SpaceX's Mars Rocket Engine"
View on Hacker News

T-Aon Hacker News • Recommends

On “Ask HN: What companies are doing work related to scientific computing?”

Here's a fun recent link: link to this video Plenty more options to explore in the links under the video, starting from link Then there is NVIDIA's CUDA Zone with lists like link
View on Hacker News

cmaon Hacker News • Recommends

On “The first plasma: the Wendelstein 7-X fusion device is now in operation”

There are bigger optimizations than 10X with some of the adaptive grid / wavelet compression stuff. I think these are still 2D, but pretty amazing: link to this video
View on Hacker News

cmaon Hacker News • Recommends

On “The first plasma: the Wendelstein 7-X fusion device is now in operation”

There are bigger optimizations than 10X with some of the adaptive grid / wavelet compression stuff. I think these are still 2D, but pretty amazing: link to this video
View on Hacker News

swimfaron Hacker News • Recommends

On “Trump Administration Might “Re-Examine” Climate Modeling”

I remember that. Fluid dynamics is a very tricky thing to model and the work they did was really cool. There's a good video presentation on it here: link to this video
View on Hacker News

danielvfon Hacker News • Recommends

On “Some things I realized about AI while contemplating slide rule prices on eBay”

Or maybe it is that SpaceX is doing simulations on a level ahead of what everyone else does. Here's one of several amazing videos from SpaceX simulations. (There are more, but I don't have the link to the others) link to this video
View on Hacker News

DiThion Hacker News • Mentions

On “Hyperloop One Becomes ‘Virgin Hyperloop One’”

…adjusted accordingly." And if that doesn't work, the tube can have some kind of rails or just to roll over wheels on top of the pylons. (my own thoughts as non expert) Rocket engineers with advanced simulation tools0 have been working on this for 5 months before releasing the paper. Do you really think they somehow missed this obvious issue? 0 link to this video Edit: Further in the paper it says: "The tube will be supported by pillars which constrain the tube in the vertical direction but allow longitudinal slip for thermal expansion as well as dampened lateral slip to reduce the risk posed by earthquakes." So pretty much what I've said. The other quoted sentence refers to placement of pylons them…
View on Hacker News

Const-meon Hacker News • Mentions

On “Tesla GPU Accelerator Bang for the Buck, Kepler to Volta”

> that would be complex and severely impact performance on GPU architectures Agree about the complexity. However, adaptive grids can be a huge win in terms of performance. The GPU doesn’t need to simulate the whole 8G grid nodes, it only simulates much fewer nodes, only in the areas of large gradients / higher frequencies of the simulated fields. Here’s an old SpaceX presentation about their GPU simulations of rockets: link to this video
View on Hacker News

paulsutteron Hacker News • Mentions

On “SpaceX test flight of Starship SN-5 [video]”

In addition to being full-flow, Raptor runs on methane (CH4, the simplest hydrocarbon), which already exists many places in the solar system (including Mars), and is easier to manufacture than kerosene or liquid hydrogen. SpaceX developed an incredibly advanced simulator to make it happen: link to this video
View on Hacker News

NortySpockon Hacker News • Mentions

On “SpaceX SN9 Explodes on Landing”

link to this video Yeah, they were doing high fidelity high performance computational fluid dynamics simulations and aerodynamic simulations by 2015. So I think they've done the sims, and now they're doing it in real life.
View on Hacker News

hwillison Hacker News • Mentions

On “SpaceX launches Starlink sats in record 10th liftoff, landing of reused rocket”

To put those phrases in context, I think they would have required more effort than the Apollo project. > Obviously, although I have doubts that the computations being performed by these "GPU solvers" really require a modern custom-built GPU and couldn't have been done on FPGAs or arrays of microcontrollers from the 80s. Here's a talk by the guys: link to this video The Cray 2 could do <2 gigaflops. So a single simulation with 10,000 points per side at 1 microsecond timesteps for .1 seconds with ~50 flops per cell-step would have taken 79 years to run, assuming the Cray had 50 cycle fetch/store times. Engineers need to run lots of simulations to come up with a working design. And that's just simulating…
View on Hacker News

Const-meon Hacker News • Mentions

On “WebGPU computations performance in comparison to WebGL”

> are there other good applications the GPU pipeline tends to be useful for? Pretty much everything compute-bound. SpaceX presentation about rocket engines: link to this video Unreal Engine 5 presentation about rendering many millions of small triangles using compute shaders: link > Are there guidelines on how complex a program you can run on GPU cores and still reap benefit? Arbitrarily complex. Many real-world GPGPU programs are split over multiple compute shaders / kernels. When implemented properly, they even run in parallel. This is critically important on Windows with DirectCompute, because 2 seconds TDR timeout. When a single compute shader takes more than 2 seconds, the OS concludes the GPU’s…
View on Hacker News

mlindneron Hacker News • Mentions

On “SpaceX closing in on first Starship Super Heavy launch”

…w and are 5 segment versions of the boosters used on Shuttle, the tank design is a load-bearing version of the Shuttle. It's all 70s/80s tech at best. There's nothing new in using supercomputers to compute aerodynamics. It's been done for decades with ever further precision. SpaceX has even done talks that can be found on youtube on it themselves. link to this video The heat protection technology is literally the exact same material as used on Apollo, except re-formed into tiles, something SpaceX has been doing with their own heat shielding technology for decades. The landing/pacifying procedures are variants of Shuttle procedures as the same propellants are used (which are also very old). They're even…
View on Hacker News

paulsutteron Hacker News • Mentions

On “Computers Reduce Efficiency: Case Studies of the Solow Paradox (2023)”

SpaceX Raptor engine was designed using a full engine combustion simulator, without which the engine would have been impossible 1. Not to mention the rapid evolution from Raptor 1 to 3 2 Jet aircraft are 70% more efficient since 1967, largely from simulation 3, similar in automotive Unclear how the NVIDIA H100 would have been designed by hand-drawing 80 billion transistors Net-net: Computers necessary, but we need much better UIs and systems. Maybe AI will help us improve this 1 link to this video 2 link 3 link > Jet airliners became 70% more fuel efficient between 1967 and 2007, 40% due to improvements in engine efficiency and 30% from airframes.
View on Hacker News

timschmidton Hacker News • Mentions

On “Johns Hopkins medical school will be free for most after $1B donation”

…one off the list already. Firing ullage thrusters before lighting engines is technically rocket science, but not the hard part. > I can guess that there was some money up front This isn't pictionary. Guesses don't count. > Ability for modelling and simulations and to test things properly And SpaceX has the best simulation software in the business: link to this video It is not sufficient to molecularly model a system as large and complex as Starship, nor as fast as building and flying a rocket.…
View on Hacker News