NVIDIA R550 Linux Driver's Open Kernel Modules Performing Well On GeForce GPUs

[cend]

So when will Pascal and Volta get the same level of support in nouveau?

AFAIK Kernel has a policy not not include code that requires proprietary userspace components, unless there is also open source alternative for these userspace blobs. So they only way this gets merged mainline kernel is by making it work with Mesa (idk of this is possible).

I think it will be mostly competition with Mesa rather than cooperation at this stage, similar to how Mesa and AMD made different Vulkan drivers (RADV vs. AMDVLK) for Radeon GPUs. NVK has at least a very devoted following.

[Anux]

Someone was trying to convince me recently that you can't run ANY games with the open-source nvidia GPU driver yet....

Why would you need to be convinced, didn't you read the article? You could try it yourself or read up on it and spare yourself much wasted time.

You could use nouveau but that's not related to nvidia and also doesn't use the open kernel modules currently I think and it's slow.

[cend]

Why would you need to be convinced, didn't you read the article? You could try it yourself or read up on it and spare yourself much wasted time.

You could use nouveau but that's not related to nvidia and also doesn't use the open kernel modules currently I think and it's slow.

Actually I am doubting the "slow" statement if your card is RTX 20-ish or later, given how much steam NVK has picked up...

[Anux]

Actually I am doubting the "slow" statement if your card is RTX 20-ish or later, given how much steam NVK has picked up...

Do you have any recent benchmarks? I can only remeber this one: https://www.phoronix.com/review/opensource-turing-3d

[cend]

Do you have any recent benchmarks? I can only remeber this one: https://www.phoronix.com/review/opensource-turing-3d

That benchmark predates GSP support at the kernel side and NVK at Mesa's side, so I can say it is practically irrelevant for setups running kernel 6.7 (and newer, which is still prerelease yet), like Fedora and most rolling-release distros.

Phoronix has benchmarked NVK around its reaching Vulkan 1.0 compatibility: https://www.phoronix.com/review/nvk-vulkan-performance

One game even won NVIDIA's drivers in performance, which looks like a good sign: https://www.phoronix.com/news/Nouveau-NVK-One-Win

Have to admit it is more optimism from me than nouveau being actually on par, but that's BIG improvement already.

[theriddick]

Why would you need to be convinced, didn't you read the article? You could try it yourself or read up on it and spare yourself much wasted time.

That was my quote; but I was shot down with the usual, nar nar your wrong, you don't know what your talking about... Meh, I just said, whatever and moved on. I'll keep this article link in my ammo box for next time

[partcyborg]

Why won't they include it in the kernel?

It won't ever be accepted. It literally has inline compiled binary code as char arrays.

https://github.com/NVIDIA/open-gpu-kernel-modules/issues/286

[Rovano]

Why would you need to be convinced, didn't you read the article? You could try it yourself or read up on it and spare yourself much wasted time.

You could use nouveau but that's not related to nvidia and also doesn't use the open kernel modules currently I think and it's slow.

When you install an Nvidia binary blob, you get a choice of which module to use.
I think the only practical difference for the average user is whether they have a card that already supports GPS or not.
GSP guarantees card overclocking and other things.

If your card supports GPS, it will be used regardless of whether you have the module open or closed.

Nouveau(NVK) will be interesting from MESA 24.1. Vulkan 1.3 etc.

[dragon321]

Recently (this version or maybe the previous one) it was noted that to use some new CUDA features (unified heterogeneous memory) it was a requirement to be using the open kernel drivers. I don't know why or how that would be so, but it was mentioned in the new feature info release notes.

It that was so, I suspect it could be possible that other disparate features could exist between the open kernel drivers installation and the other.

This is actually a good point.

Yes. Using it will force nVidia to keep it in good shape, and therefore will remain an up-to-date reference implementation for Nouveau developers, and an up-to-date kernel module for any future developer willing to build an open user space module to go with this open kernel module. Also, having an open kernel space module and a closed user space module is still better than having both modules being closed.

Another good point but I guess they will move to it in the future anyway. Probably one of the reason why this driver exist is the fact that it will be able to use GPL only symbols in kernel and provide more functionality than proprietary driver can.

One less 3rd party repo to add for some distros.

It's useless without proprietary userspace but I guess you can get it in some different way. Since kernel module is open source I guess distributions can keep prebuilt version in repositories and avoid the need for recompilation during every kernel update.

Anyway thank you all for answer, I'm going to try it on my PC. Since support for desktop GPUs is now considered as "certified" and performance is more or less the same I guess there is no good reason why not to.

[RealNC]

I think it would be cool to directly integrate the kernel modules with a patch into the kernel

If you mean upstream this into the kernel, then hell no. I want to be able to update my GPU driver without having to switch to non-LTS kernels.