Please remember that any mention of competitors, hinting at competitors or offering to provide details of competitors will result in an account suspension. The full rules can be found under the 'Terms and Rules' link in the bottom right corner of your screen. Just don't mention competitors in any way, shape or form and you'll be OK.
The ray accelerator units in the RDNA2 CU performs Ray-Box and Ray-Triangle Intersection checks -- the same as the RT Cores do in Ampere. However, Ampere's RT cores, also accelerate BVH Traversal Algorithms -- whereas in RDNA 2 this is done via the compute shaders using SIMD 32 units.
And for denoising, Ampere is using Tensor Cores, But on RDNA2, it's using it's compute shaders.
That's why RDNA2 is much slower.
This about sums up the video in a few seconds