Noah Hähnel

I am soon upgrading my System with a new GPU and am wondering if Houdini benefits from reBar a.k.a resizable Bar a.k.a Smart Access Memory in some way?

I am unsure if there would be any benefit in Karma XPU but I could potentially think of benefits when doing GPU simulations that still require some CPU workload (or transferring collider meshes to the GPU?).

In case you don't know what it is, this is what NVIDIA writes in their blogpost [www.nvidia.com]:

What Is Resizable BAR?
Resizable BAR is an optional PCI Express interface technology. As you move through a world in a game, GPU memory (VRAM) constantly transfers textures, shaders and geometry via many small CPU to GPU transfers.

With the ever-growing size of modern game assets, this results in a lot of transfers. Using Resizable BAR, assets can instead be requested as-needed and sent in full, so the CPU can efficiently access the entire frame buffer. And if multiple requests are made, transfers can occur concurrently, rather than queuing.

If there is any benefit I would probably upgrade my whole System, if there isn't then I doubt upgrading my CPU right now would give me any noticeable performance increase as it has got more than enough cores and speed.

Maybe somebody who does have a System that supports it and is interested could do a small benchmark with Karma XPU, Vellum, or the new MPM solver by running it once with it enabled and once disabled. Or maybe a Dev could also answer this question.

Update from myself:

I "fixed" the issue by massively increasing the available RAM swap in Windows. For me, it wasn't an issue of the actually consumed RAM, just the committed RAM that increased exponentially and eventually led to a crash.
I have monitored this a couple of times in the last few weeks and it seems like it doesn't overcommit as much anymore. It usually only commits a few GBs over the used RAM now.


Otherwise, I didn't experience any RAM usage out of the ordinary.

Htogrom
I am encountering same problems. When loading bunch of USD file caches for cloth, Solaris tries to consume large amounts of RAM. On 128 gb machines works fine, while on 64gb it crashes. When render actually kicks in, it consumes less than 64gb of ram, just that start is problematic.

I assume you just ran out of RAM the normal way. If the scene is too big there is no way around using "flush each frame".

I've had some good days and some bad ones but overall very happy to have made something every day.