Interstellar movie black hole implemented with Einstein's equations in C++ • Hacker News Board

Re: Interstellar movie black hole implemented with Einstein's equations in C++

#71

Post by lossolo » Mon, Aug 12, 2024, 12:59 PM UTC

jsheard wrote: post #32

slig wrote: post #28

Earlier quoted context omitted.

How fast could this run in a modern CPU with a modern GPU?

GPUs are almost irrelevant for VFX work at this scale due to the memory requirements. The render nodes used for Interstellar had 156GB of RAM, and a decade later the biggest GPUs still don't have that much memory (unless you count Macs I suppose but the existing software ecosystem is very CUDA-centric). Small VFX shops do typically render on GPUs nowadays, but the high end is still dominated by CPU rendering.

> The render nodes used for Interstellar had 156GB of RAM, and a decade later the biggest GPUs still don't have that much memory

NVIDIA H200 GPU has 141 GB of memory, and the AMD Instinct MI300X GPU has 192 GB of HBM3 memory.

Re: Interstellar movie black hole implemented with Einstein's equations in C++

#72

Post by m4rtink » Mon, Aug 12, 2024, 1:02 PM UTC

hermitcrab wrote: post #67

GTP wrote: post #59

Earlier quoted context omitted.

Well, if you look for this, many if not most movies will have some inaccuracy or holes in explanation like this. In the end, I watch movies for entertainment. If I'm looking for scientific precision, I see a documentary instead.

Yes. Maybe don't make scientific accuracy a big part of your marketing campaign though.

Still better than what Ad Astra! :D

Liked the killer space monkeys though. ;-)

Re: Interstellar movie black hole implemented with Einstein's equations in C++

#73

Post by m4rtink » Mon, Aug 12, 2024, 1:02 PM UTC

hermitcrab wrote: post #65

Qem wrote: post #52

Earlier quoted context omitted.

Also the robots were cool.

The robot's form of locomotion seemed rather daft. But it was at least original.

I think its just how "regular" fractal robots work in general ? :)

Re: Interstellar movie black hole implemented with Einstein's equations in C++

#74

Post by m4rtink » Mon, Aug 12, 2024, 1:05 PM UTC

hermitcrab wrote: post #58

anentropic wrote: post #39

Earlier quoted context omitted.

100% agree, like you I was hyped after the pre-release teaser PR stuff came out about the realistic black hole rendering etc, was hoping for an actually decent sci-fi and then just a lame story culminating in "space ghosts" for me, arguably most disappointing movie ever

Don't watch 'Ad Astra' then. That's also incredibly disappointing (IMHO).

Not if you take it as a comedy - then the buggy joy ride, monkey station & space surfing make perfect sense. ;-)

Re: Interstellar movie black hole implemented with Einstein's equations in C++

#75

Post by jsheard » Mon, Aug 12, 2024, 1:05 PM UTC

lossolo wrote: post #71

jsheard wrote: post #32

Earlier quoted context omitted.

GPUs are almost irrelevant for VFX work at this scale due to the memory requirements. The render nodes used for Interstellar had 156GB of RAM, and a decade later the biggest GPUs still don't have that much memory (unless you count Macs I suppose but the existing software ecosystem is very CUDA-centric). Small VFX shops do typically render on GPUs nowadays, but the high end is still dominated by CPU rendering.

> The render nodes used for Interstellar had 156GB of RAM, and a decade later the biggest GPUs still don't have that much memory NVIDIA H200 GPU has 141 GB of memory, and the AMD Instinct MI300X GPU has 192 GB of HBM3 memory.

I was thinking of their graphics cards which currently max out at 48GB, but true, their HPC accelerators do have a lot more memory now. In the case of Nvidia they would be a trade-off for rendering though since their HPC chips lack the raytracing acceleration hardware which their graphics chips have.

Besides, in the current climate I don't think VFX companies would be eager to bid against AI companies for access to H100/H200s, the VFX companies don't have infinite venture capital goldrush money to burn...

Re: Interstellar movie black hole implemented with Einstein's equations in C++

#76

Post by throw310822 » Mon, Aug 12, 2024, 1:10 PM UTC

hermitcrab wrote: post #64

throw310822 wrote: post #41

Earlier quoted context omitted.

We're talking about a movie in which a space agency builds an enormous rocket entirely in secret and without any suppliers; then enrolls the astronaut at the head of the mission on the same day of the departure; and finally launches the rocket from inside its office halls. ¯\_(ツ)_/¯ https://www.youtube.com/watch?v=x9xFRch7N5o

They obviously used the same contractors that Bond villains use to build super bases inside volcanoes without anyone noticing.

Indeed.

https://youtu.be/tDedpreZH-0

Re: Interstellar movie black hole implemented with Einstein's equations in C++

#77

Post by greggsy » Mon, Aug 12, 2024, 1:11 PM UTC

FrustratedMonky wrote: post #68

KaiserPro wrote: post #48

I worked on this movie, I was at DNEG at the time. One of the standout things that I remember is that this particular simulation was toxic to the fileserver that it was being stored on. From what I recall, I don't think that it was running on that many machines at once. Mainly because it required the high memory nodes that were expensive. I think it was only running on ~10 possibly 50 machines concurrently. But I cou…

Is it just so much read/write? I'm having hard time understanding why a simulation would need so much read/write to disk? Wouldn't the CPU and RAM be more important for calculations, then write them to disk when done?

I was thinking the same. It took 30 minutes to ‘several hours’ to produce 23 megapixel renders, which are 100MB max.

Either the renders were heavily paging memory to disk, or OP was working at the compositing phase.

Re: Interstellar movie black hole implemented with Einstein's equations in C++

#78

Post by deep_merge » Mon, Aug 12, 2024, 1:16 PM UTC

didgeoridoo wrote: post #37

kjrfghslkdjfl wrote: post #9

Earlier quoted context omitted.

What did you expect from the title? That they used Einstein's equations to render the actors? Of course it's the black hole.

Since the digital movie camera used to film the actors relies on the photoelectric effect to turn light into pixel data, you could say Einstein’s equations were used for the live-action portion too!

Um actually…

Chris Nolan doesn’t shoot digital. His more recent pictures (Interstellar included) are shot on a mixture of 35mm, 70mm and IMAX 70mm (!)

Re: Interstellar movie black hole implemented with Einstein's equations in C++

#79

Post by hermitcrab » Mon, Aug 12, 2024, 1:27 PM UTC

m4rtink wrote: post #72

hermitcrab wrote: post #67

Earlier quoted context omitted.

Yes. Maybe don't make scientific accuracy a big part of your marketing campaign though.

Still better than what Ad Astra! :D Liked the killer space monkeys though. ;-)

'Ad Astra' was a real stinker.

Re: Interstellar movie black hole implemented with Einstein's equations in C++

#80

Post by didgeoridoo » Mon, Aug 12, 2024, 1:30 PM UTC

deep_merge wrote: post #78

didgeoridoo wrote: post #37

Earlier quoted context omitted.

Since the digital movie camera used to film the actors relies on the photoelectric effect to turn light into pixel data, you could say Einstein’s equations were used for the live-action portion too!

Um actually… Chris Nolan doesn’t shoot digital. His more recent pictures (Interstellar included) are shot on a mixture of 35mm, 70mm and IMAX 70mm (!)

The light-sensitive chemicals in film also rely on the photoelectric effect! YOU CAN’T ESCAPE EINSTEIN, NOLAN.