Comment by amiga386
7 months ago
Hopefully that improves. The guy giving the presentation on AV2 made clear there was "rigorous scrutiny for hardware decoding complexity", and they were advised by Realtek and AMD on this.
So it seems like they checked that all their ideas could be implemented efficiently in hardware as they went along, with advice from real hardware producers.
Hopefully AV2-capable hardware will appear much quicker than AV1-capable hardware did.
Oh, I don't doubt that it'll be hardware implementable, but it's a shame that current hardware is usually mostly out of luck with new codecs. (Sometimes parts can be reused in more programmable/compartmentalized decoding pipelines, but I haven't seen that often.)
That's reason I prefer firesticks over TVs
Maybe not only reference software, but also reference RTL should be provided? Yes, this is more work, but should speed up adoption immensely.
There's no point having reference RTL. The point of reference software is to demonstrate the correct behaviour for people implementing production grade libraries and RTL. Having an RTL version of that wouldn't add anything - it should have identical behaviour.
Providing a production grade verified RTL implementation would obviously be useful but also entire companies exist to do that and they charge a lot of money for it.
Could help people on the hobby or lower budget FPGA side. H.264/5/etc never really made it
9 replies →
I have to wonder whether PCIe devices that do hardware encoding / decoding might be the more viable path going forward?
Wait, I just discovered GPUs, nevermind. [giggles]
Still, the ability to do specialized work should probably be offloaded to specialized but pluggable hardware. I wonder what the economics of this would be...