We asked AMD if the techniques could be used to provide gains to existing OpenGL and Direct3D programs. For example, Direct3D 11 permits command buffer generation to be done in parallel, with a feature called deferred contexts and multithreaded rendering. However, some video driver developers—including AMD—have not implemented multithreaded rendering support, so while the API supports parallelism, the work is done serially anyway, and sometimes more slowly than if no multithreading was used. As a result of this poor driver support, some game developers have removed multithreaded rendering support from their game engines.

In response, AMD told us that developers have tried to do it but haven't had much success with using such techniques with existing APIs, and that it requires Mantle to do the job properly. It's not immediately clear to us if this is because of AMD's refusal to implement the support in its drivers, or if there really is a problem with using Direct3D in this way; there is clearly something of the chicken and the egg at work here.
What's the future for Mantle?

Until independent testing can take place—which won't happen until the driver is finally made available—the benefits of Mantle are uncertain, but assuming AMD's numbers are replicated by third parties, it does seem that the API can provide significant gains in CPU-bottlenecked systems.

This could make it attractive to game developers. The problem, of course, is that Mantle is an AMD-specific API. While Nvidia and Intel GPUs are, at a high level, comparable to AMD GPUs—they're all processors for crunching shader programs—their implementations and drivers are, of course, significantly different.

As long as these other GPUs are supported, developers will at the very least have to create an OpenGL and/or Direct3D implementation alongside the Mantle implementation of their engines. EA DICE has done this for Battlefield 4, and it's certainly not impossible to see other developers follow suit.

Mantle may also have repercussions for the Xbox One and PlayStation 4. Both of these consoles are built around AMD APUs, albeit somewhat customized, and so in principle they too could support a Mantle-like API. If this were to materialize it would make Mantle support in PC versions something of a no-brainer. However, it's not immediately clear if either Sony or Microsoft is willing to go down this route, especially as they are already able to do things like reduce validation and enforce multithreading support in their consoles' existing APIs anyway.

Long term, it's hard to see a vendor-specific API like Mantle being the one that the industry settles on. Since the dim and distant past of the 1990s and the birth of the GPU, such APIs have been a feature of the computing landscape, with 3Dfx's Glide, PowerVR MiniGL, and Rendition's Speed3D and RRedline, but cross-vendor compatibility has prevailed, with OpenGL and Direct3D.

We can probably expect the same thing to happen this time around. Mantle may inform future developments of OpenGL and Direct3D and encourage those APIs to reduce their overheads and become friendlier to multithreading, but it's hard to see it displacing either.