You are likely confusing what is better termed "PCIe passthrough" with virtual functions wherein one physical GPU presents itself on the PCIe bus as (dozen's in the case of SR-IOV or thousands in the case of SIOV) of GPU functions which can be passed to dozens or thousands of GPU enabled VM's.
It's not difficult but it misses the point. SIOV supports 1k's of VF's because that's what you need if you want a sandboxed app-per-VM security model. When statically compiled VM's are just as performant as containers but more secure.
GVT-g was intel's first crack at virtualization and is now abandoned. It was supplanted by Intel supporting SR-IOV which itself was succeeded by intel's SIOV.
>Correct me if I am wrong on this, but to me, it would seem that something like VirGL would still serve a purpose with wider spreader full SR-IOV support on consumer GPUs, as VirGL could find application in many scenarios where a GPU vendor's drivers are not compatible with the guest.
Pretty much every guest OS (windows, Linux, BSD) has drivers that would work with a native PCIe VF GPU device. MacOS still has AMD drivers but only up to RDNA 2. I can't think of any guest that would support a GL device but not have a native driver.
>Saying that, I do agree that vendors should enable support in customer GPUs and feel that their focus on protecting server sales is going to turn out misguided in the long term. Intel especially disappointed in this area, as they in the past did allow such functionality on their GPUs, but have recently removed that.
Intel supports SRIOV/SIOV on consumer CPU iGPU's (Xe, 11th, 12th, and 13th gen) but not dGPU's (A770, A750..) which is very frustrating. Indeed 'enterprise features' such as ECC or IOMMU on consumer chips have not affected server sales.
>That being said, any effort focused on GPU virtualization or drivers impresses me immensly and I very much appreciate the work done on VirGL.
VirGL is a poor solution to the pressing problem of virtualized graphics. It only really exists because the hardware makers AMD/Intel/Nvidia in their infinite greed refuse to support VFIO on all GPU's like how IOMMU is supported on nearly all CPU's.
https://events19.linuxfoundation.cn/wp-content/uploads/2017/...