You could definitely do that for rasterization, but if any part of the graphics API required something the card didn’t have (like ray tracing) you couldn’t synchronize the work between it and another RT capable card fast enough.
See also: why they killed crossfire and sli in the gaming space, and why the derivative works of that technology only exists in the data center for non latency-intensive workloads.
GPU pass through to a VM perhaps? Home cloud gaming servers!!! Get a bunch of old AI GPUs and stick them in a system and give each VM it’s own GPU and stick steam on the VM. Play games from anything that can run steam link.
Basic output? probably. Gaming? Probably not. Again same problem of some cards missing hardware components that are required for a rendering pipeline, regardless of physical or virtual outputs
The 6000 Blackwell has all of this and would totally work, the H200 does not, etc
Probably easier to build a modified driver that uses the Blackwell card for rendering and pushes the frames back to a lower powered display card.
You could definitely do that for rasterization, but if any part of the graphics API required something the card didn’t have (like ray tracing) you couldn’t synchronize the work between it and another RT capable card fast enough.
See also: why they killed crossfire and sli in the gaming space, and why the derivative works of that technology only exists in the data center for non latency-intensive workloads.
GPU pass through to a VM perhaps? Home cloud gaming servers!!! Get a bunch of old AI GPUs and stick them in a system and give each VM it’s own GPU and stick steam on the VM. Play games from anything that can run steam link.
Basic output? probably. Gaming? Probably not. Again same problem of some cards missing hardware components that are required for a rendering pipeline, regardless of physical or virtual outputs
The 6000 Blackwell has all of this and would totally work, the H200 does not, etc