Live data from Hacker News

Viewing profile — pandaforce

pandaforce

HN member
Joined
Thu, Jul 02, 2020, 1:27 PM UTC
HN karma
65
Public activity
18 items

About pandaforce

No profile information was provided.

Recent public activity

  1. comment
    Comment #48551779

    Bellard hasn't been involved in FFmpeg for *over 20 years* at this point, and more like 23. His code was not great and reeked of sphagetti due to FFmpeg back then lacking any frame…

  2. story
  3. comment
    Comment #47468559

    Yes. I get 300fps decoding 8k ProRes on a 4090 and barely 50fps on a Zen 3 with all 16 cores running. The CPU doesn't touch anything, actually. We map the packet memory and let the…

  4. comment
    Comment #47460826

    Most vision models are trained on images or conventional video codecs. There's a good reason why H200's have 7 JPEG + 7 nvdec ASICS.

  5. comment
    Comment #47460589

    That's basically what VC-2 is, as well as JPEG2000-HT. Wavelets are nice in that they have no need for deblocking since each slice complements one another, and they're simple to ca…

  6. comment
    Comment #47458216

    Proxy files have issues when doing coloring, greenscreens, effects shots. The bit depth, chroma resolution, primaries/transfer/colorspace gets changed. Basically only really usable…

  7. comment
    Comment #47457820

    FFv1's range coder has higher complexity than CABAC. The issue is serialization. Mainstream codecs require that the a block depends on previously decoded blocks. Tiles exist, but t…

  8. comment
    Comment #47456222

    > A crash mid video write out can corrupt a lengthy render. With image sequences you only lose the current frame. You wouldn't contain FFv1 in MP4, the only format incompetent enou…

  9. comment
    Comment #47455344

    6k ProRes streams that consumer cameras record in are still too heavy for modern CPUs to decode in realtime. Not to mention 12k ProRes that professional cameras output.

  10. comment
    Comment #47455241

    The main target for this are NLEs like Blender. Performance is a large part of the issue. Most users still just create TIFF files per frame before importing them into a "real edito…

  11. comment
    Comment #47454824

    Yes, but no. No, in that these days, GPUs are entirely scalar from the point of view of invocations. Using vectors in shaders is pointless - it will be as fast as scalar variables …

  12. comment
    Comment #47454686

    Yeah, Vulkan is shedding most of the abstractions off. Buffers are no longer needed - just device addresses. Shaders don't need to be baked into a pipeline - you can use shader obj…

  13. comment
    Comment #47454538

    The article explicitly mentions that mainstream codecs like H264 are not the target. This is for very high bitrate high resolution professional codecs.

  14. comment
    Comment #47454493

    These are all gripes you might have with Vulkan Video. Unlike with Vulkan Video, in Compute, bounds checking is the norm. Overreading a regular buffer will not result in a GPU hang…

  15. comment
    Comment #47414559

    Khronos published a post on the Vulkan compute codecs in FFmpeg: https://www.khronos.org/blog/video-encoding-and-decoding-wit...

  16. story
  17. comment
    Comment #47410180

    Cheaters are always 2 steps ahead, all that developers can do is to trim the less willing ones.

  18. story