Stone Chen

Hi, I've created a new pull request here https://github.com/ffvvc/FFmpeg/pull/215 I believe I did this correctly but I'm still relatively unfamiliar with git haha.

Hiya, Is anyone currently working on this? If not could I try it?

Hi @nuomi2021 Oh has the non-arm vvc project been taken? I've already met the qualification requirement (patch accepted for ffmpeg) but I wanted to try this as well. I will...

> No, but maybe you can choose a tough one Fair enough 😂 I'll give it an attempt Quick question re: VPGATHERDD, it seems like since it's only operating on...

> vvdec has an implementation, you can refer to it :) ah took me a bit to realize that vvdec was a different repo haha. They are using a shuf...

Quick update/Q's Updated the 2 byte version to take multiple widths, I noticed however there were some 8 and 16 pixel widths in predict_inter (printing `cu->cb_width`) are these also possible...

In my fork I've created a pr with my current implementation. https://github.com/stone-d-chen/ffvvc/pull/1 - AVX2 code paths for width 8, 16, 32, 64, 128 (width 4 downshifts to the scalar version)...

Yep that fixed the issue! All conformance tests pass now https://github.com/stone-d-chen/ffvvc/pull/3 - Cleaned up 16bpc and redid 8 pixels to take advantage for YMM registers - 8bpc for widths 32-128;...

Sounds good no rush, @nuomi2021 Latest update: - 8bpc should be fully complete now, I need to clean up my checkasm still https://github.com/stone-d-chen/ffvvc/pull/4 I'll probably take a pause on this...

Hmm I was just basing it off of this paper, and assumed any CU size is valid but I will search the spec... it could be the block type used...