big difference. almost nobody is going to give you the sauce hidden behind blobs. but i hope the dumb issues of the past (imagine using it on laptops with switchable graphics) go away slowly with this and it is not only for pleasing the enterprise crowd.
NVIDIA Transitions Fully Towards Open-Source Linux GPU Kernel Modules
151–160 of 259 posts
Re: NVIDIA Transitions Fully Towards Open-Source Linux GPU Kernel Modules
#152Earlier quoted context omitted.
Am I correct in reading that as Turing architecture cards include a small CPU on the GPU board, running parts of the driver/other code?
In Turing microarchitecture, nVidia replaced their old "falcon" cpu with NV-RISCV RV64 chip, running various internal tasks. "Open Drivers" from nVidia include different firmware that utilizes the new-found performance.
Re: NVIDIA Transitions Fully Towards Open-Source Linux GPU Kernel Modules
#153Earlier quoted context omitted.
AFAIK I believe all they did was move the closed source user space driver code to their opaque firmware blob leaving a thin shim in the kernel. In essence I don’t believe that much has really changed here.
Having as open-source all the kernel, more precisely all the privileged code, is much more important for security than having as open-source all the firmware of the peripheral devices. Any closed-source privileged code cannot be audited and it may contain either intentional backdoors, or, more likely, bugs that can cause various undesirable effects, like crashes or privilege escalation. On the other hand, in a proper…
Re: NVIDIA Transitions Fully Towards Open-Source Linux GPU Kernel Modules
#154Earlier quoted context omitted.
In Turing microarchitecture, nVidia replaced their old "falcon" cpu with NV-RISCV RV64 chip, running various internal tasks. "Open Drivers" from nVidia include different firmware that utilizes the new-found performance.
How well isolated is this secondary computer? Do we have reason to fear the proprietary software running on it?
So you better actually use IOMMU
Re: NVIDIA Transitions Fully Towards Open-Source Linux GPU Kernel Modules
#155How is the NVIDIA driver situation on Linux these days? I built a new desktop with an AMD GPU since I didn't want to deal with all the weirdness of closed source or lacking/obsolete open source drivers.
The current stable proprietary driver is a nightmare on Wayland with my 3070, constant flickering and stuttering everywhere. Apparently the upcoming version 555 is much better, I'm sticking with X11 until it comes out. I never tried the open-source one yet, not sure if it supports my GPU at all.
Maybe NVIDIA drivers have kind of worked on 12 month old kernels that Ubuntu on average uses.
Re: NVIDIA Transitions Fully Towards Open-Source Linux GPU Kernel Modules
#156Huh. Sway and Wayland was such a nightmare on Nvidia that it convinced me to switch to AMD. I wonder if it's better now. (IIRC the main issue was https://gitlab.freedesktop.org/xorg/xserver/-/issues/1317 , which is now complete.)
Re: NVIDIA Transitions Fully Towards Open-Source Linux GPU Kernel Modules
#157I wonder if we'll ever get hdcp on nvidia. As much as I enjoy 480p video from streaming services.
Which service goes that low? The ones I know limit you from using 4k, but anything up to 1080p works fine.
Re: NVIDIA Transitions Fully Towards Open-Source Linux GPU Kernel Modules
#158Re: NVIDIA Transitions Fully Towards Open-Source Linux GPU Kernel Modules
#159Earlier quoted context omitted.
Which service goes that low? The ones I know limit you from using 4k, but anything up to 1080p works fine.
Nonsense that a 1080p limit is acceptable for (and accepted by) paying customers.
Re: NVIDIA Transitions Fully Towards Open-Source Linux GPU Kernel Modules
#160How is the NVIDIA driver situation on Linux these days? I built a new desktop with an AMD GPU since I didn't want to deal with all the weirdness of closed source or lacking/obsolete open source drivers.
I've literally never had an issue in decades of using NVIDIA and linux. They're closed source, but the drivers work very consistently for me. NVIDIA's just the only option if you want something actually good and to run ML workloads as well.