LookingGlass VS LibVF.IO

Unfortunately AMD cards suffer from a reset bug, still.

The reset bug being that you can pass through the card fine, once. But if you try to pass it through again (or the card experiences an issue and needs to reset), they get caught in some kind of bad state and won’t work until power is removed and restored. Which requires a reboot or a only slightly less disruptive dance with system power states.

For vega and 5000 series gpu’s, there’s https://github.com/gnif/vendor-reset

Incidentally, nvidia gpus are so good at resetting, they’ve probably done so without you noticing. If the screen ever goes black for a fraction of a second and returns in normal usage, it was probably because it reset itself.

The lower 6000 series lower than the 6800’s for example may or may not have the issue. It seems most “reference” cards are fine, but custom vendor cards often but not always have issues. My reference 6700 works fine, but a sapphire 6700 probably won’t.

And the 7000 series is also fucky in a new way somehow. Gnif knows far more about this than me, and has basically thrown up his hands at how AMD doesn’t care. He’s made occasional posts about it on https://forum.level1techs.com/

Gnif is also responsible for Looking glass: https://github.com/gnif/LookingGlass

You could try LookingGlass. That may require two GPUs.

It's a pair of apps, one runs on a Windows virtual machine, the other on the host OS, that uses shared memory to copy a passed-through GPUs frame buffer. Runs fast enough to get 4k/120fps very low latency, so if you have a spare GPU you can game on it in Windows, from a Linux desktop. https://github.com/gnif/LookingGlass

Check out https://github.com/gnif/LookingGlass if you can accept a separate window.

then everything looks normal. It's all up to EGL though, as looking-glass really doesn't have any code that handles image scaling (see here).

https://github.com/Arc-Compute/LibVF.IO/tree/master/ plus https://github.com/gnif/LookingGlass works pretty well. If you use an Intel GPU, particularly one of their new Arc dedicated GPUs, it supports the functionality on the consumer grade hardware without any trickery and you just need Looking Glass to map the outputs.

I'd like to introduce you to Looking Glass as a much higher quality and lower latency alternative to NDI when you are trying to relay frames between virtual machines within the same computer. With a patched nvidia driver to enable nvfbc on the gaming VM there is almost zero performance penalty when capturing gameplay. It also has options for audio, which I don't use because they didn't exist when I was configuring my system. I have a similar use case (gaming and streaming) and hardware (5950X + two gpus). I am not using proxmox, however. My configuration using QEMU and libvirt has this XML:

What stopping from tagging a stable release? The milestone has no open issues.

Maybe you can try LibVF.IO

I'm on Linux and I'm running a 3070 Ti (Nvidia). I have always wanted to do GPU virtualization but because NVIDIA won't release vGPU for consumer card no one can do it without crossing legal red tape or problems with bricking your GPU. I did find this [https://github.com/jamesstringerparsec/Easy-GPU-PV] however it is only for windows, I found this [https://github.com/Arc-Compute/LibVF.IO/] and does not work with my GPU, and this [https://github.com/DualCoder/vgpu_unlock] and can't get it to work. Done any one know an alternative on Linux that work just like this, overcoming these problems (on KVM)?

If you are willing to thinker with you gpu driver you could look up libvfio and create multiple VM with the same gpu.

It seems they have issues with recent drivers/kernel, too: https://github.com/Arc-Compute/LibVF.IO/issues/61

I ran it like a year ago it was fine but not for my workflow. Might revisit the setup soon since it matured a lot since then. I suggest you also look at: https://github.com/Arc-Compute/LibVF.IO

For Affinity, I don't know. I have heard of people using Photoshop via VM, the problem usually comes when you need to utilize a lot of GPU because outside of GPU passthrough (might worth researching single-GPU passthrough and libvfio if you don't want to use two GPUs), GPU performance isn't great for VMs. I did find a few threads on the subject of Affinity on Linux, though, so maybe those could help.

I feel you on this. Looking forward to running libvf. Wine has come a long ways, but I ended up keeping a old PC a secondary to not deal with the hacking/workarounds to run some games. Using the older system for my Linux.

It's theoretically possible using a method like libvfio. This should allow you to split your gpu into 2 virtual gpus. It's designed for use with a vm, but could likely work with multi seat

Perhaps not the "best" source code I've ever read, but libVF.io had some beautiful code for what's generally gnarly system-glue code. The iommu setup code is a good example and inspires me to think that system-glue code doesn't need to be gross or impenetrable: https://github.com/Arc-Compute/LibVF.IO/blob/master/src/libv...

Another one I've appreciated reading (and learned more about 2d graphics from) is Pixie, a 2d graphics library written in Nim. Here's the implementation of a fair subset of SVG paths: https://github.com/treeform/pixie/blob/master/src/pixie/path...

And one last one for basic algorithms: https://github.com/nim-lang/Nim/blob/version-1-6/lib/pure/al...

Of course Knuth's original code is still some of the best classic code. K&R's original C book is a classic.