By using this site, you agree to our Privacy Policy and our Terms of Use. Close
Pemalite said:

Ray Tracing tends to inherently be compute limited, which ironically is one of the big strengths of Graphics Core Next.
I don't think AMD will spend transistors on fixed function blocks for Ray Tracing tasks, but simply make their shader pipelines more flexible to take on the task instead, then as they scale up in shader counts, then performance in old/current games get a boost as well... Should also mean that porting Ray Tracing to older GCN GPU's will likely be a little more feasible.

In saying that, various games have been dabbling in Ray Tracing for years... But RTX Ray Tracing just stepped it up a big level.

It definitely can be since you end up shading indirect contributions to light that don't appear within the camera but the other big bottlenecks to ray tracing is BVH traversal and ray-triangle intersection tests so it's ideal that they be fixed function for higher performance and efficiency ... 

There could be some specialized instructions for making these things optimal but doing so could lead to higher power consumption. During this generation, even though some cases of GPU compute rasterization could be made it was still arguably more performant to use the rasterizer on the consoles ... 

Let's at least figure out a way to get rid of the rasterizer first before we even tackle ray tracing since it's a much harder problem. Without those specialized instructions, I don't think ray tracing could be all that performant on older parts ... 

We'll never be able to get rid of the texture sampler in like 10 years, in maybe 20 but even then having them fixed function will give programmable shaders a good run for their money too ...