GPU processing of pixel data

[totaam]

Follow up from #365#comment:12.

We can do more with the GPU:

• keep the gpu buffer active, just in case we decide to actually use a video encoder, even after doing the scrolling detection and downloading the pixels to the CPU side (and we could make the scrolling detection tighter too when the gpu buffer is present)
• do scrolling detection via CUDA on the GPU
• delta / lz4 / zlib / whatever on GPU for small changes

[totaam]

See also #1598.

[totaam]

See also: #1317 (original NVFBC ticket) and #1763 (CUDA buffer regression)

[totaam]

There's already a library we can use for lz4: https://github.com/NVIDIA/nvcomp

[totaam]

See also #3408 and #3370

NVIDIA's VideoProcessingFramework: It’s set of C++ libraries and Python bindings which provides full HW acceleration for video processing tasks such as decoding, encoding, transcoding and GPU-accelerated color space and pixel format conversions.