Proof Of Concept: Open-Source Multi-GPU Rendering!
Now that David Airlie's vga_switcheroo has went upstream in the Linux 2.6.34 kernel that provides hybrid graphics support and delayed GPU switching, David went on to look for something new to work on in his downtime when not busy with tasks at Red Hat. This new work is on GPU offloading / multi-GPU rendering.
Last month NVIDIA introduced Optimus as a way for dual-GPU notebooks to seamlessly switch between the two GPUs but also to offload the rendering workload to the other graphics processor. This is somewhat similar to NVIDIA's SLI and ATI/AMD's CrossFire for splitting the rendering workload across multiple GPUs, but it has its differences. David ended up developing a proof-of-concept similar to NVIDIA's Optimus that he is calling "Prime" and it works with Intel and ATI GPUs.
David's goals with Prime are to allow a second GPU to render 3D applications onto the screen of the first GPU, with it being configurable by the client, and just to handle the rendering side. This work isn't as simple as his vga_switcheroo implementation, but it required changes to the Linux kernel and the Graphics Execution Manager (GEM), the DRI2 protocol, the X Server and DRI2 modules, and then the actual Linux hardware drivers.
All of this code has already been published as a proof-of-concept, but David shares on his blog that he's unlikely to personally take this work further by upstreaming the code. He has been successful though in using this code to offload the rendering work from an Intel IGP that's driving a display to a discrete ATI graphics processor.
Right now Intel and ATI hardware is supported, but NVIDIA GPUs could be supported too. This work depends upon a system using DRI2 (albeit with these out-of-tree patches) and a compositing manager must be running. David also shares, "To make this as good as Windows we need to seriously re-architect the X server + drivers. At the moment you can't load an X driver without having a screen to attach it to, I don't really want a screen for the slave driver, however I still have to have one all setup and doing nothing and hopefully not getting in the way. We'd need to separate screen + drivers a lot better. Having some sort of dynamic screens would probably fall out of this work if someone decides to actually do it."
It would be wonderful if this work on Prime could be continued and it works its way upstream or that someone takes the reigns from David to continue on with this GPU offloading work for open-source drivers. First though it may make more sense to focus on getting decent performance out of a single GPU before dealing with multi-GPU excitement.