Daala: A Next-Generation Video Codec From Xiph

[droidhacker]

@silix
About hardware acceleration mattering on mobile.
Most high-end and mid range mobile GPU's are starting to support OpenCL,
which could provide for a good basis for video decoding.
Allowing things like Daala be done good enough (fast enough video decoding for fluent playback) without having to add extra hardware.

There has been a lot of talk about this idea over the years, but the problem is that it has NEVER been pushed past PARTIAL and/or THEORETICAL. There was some partial GPU assistance on some older video cards, but all in all, video decoding has always been done either in software or on dedicated hardware.

Now that being said, this new side-transition may be more suitable for general purpose opencl acceleration. Of course, that's at the expense of the massive power consumption typical of all GPUs.

[KellyClowers]

Xiph actually have a pretty good track record of industry acceptance. Vorbis audio was quickly adopted by chip manufacturers and was on any cheap (generic chinese) mp3 player back in the day. Opus is expected to be the next standard for audio and it's showing immediate adoption.
This new thing coming from Xiph + Mozilla + independent developers (to the level of Jason Garrett-Glaser aka. Dark Shikari with x264 fame) has to happen. I think it has all the odds on it's favor and a great team. I have a lot of respect for Monty. If he says it's gonna happen and already has a proof implementation, then it's gonna happen.

If Jason (and hopefully other x264 devs) then I have even more faith in this project.

[jntesteves]

the only thing i'm worried about is, what kind of acceptance this can hope for, given that:
-it's not an industry-wide standard (as in, embraced by sw AND appliance vendors)
-it's based on different techniques, thus doesnt rely on the same processing "blocks" (eg DCT) that chips with video decoding capabilities can usually handle
-desktop computing is on the decline, more and more replaced by portable, small device, computing - but hw based video decoding (offloading) matters on those devices...

Xiph actually have a pretty good track record of industry acceptance. Vorbis audio was quickly adopted by chip manufacturers and was on any cheap (generic chinese) mp3 player back in the day. Opus is expected to be the next standard for audio and it's showing immediate adoption.
This new thing coming from Xiph + Mozilla + independent developers (to the level of Jason Garrett-Glaser aka. Dark Shikari with x264 fame) has to happen. I think it has all the odds on it's favor and a great team. I have a lot of respect for Monty. If he says it's gonna happen and already has a proof implementation, then it's gonna happen.

[GreatEmerald]

I hope this ends better than Theora did.

[smitty3268]

Doesn't hurt to have an option. I don't think Xiph has ever expected devices to quickly adopt any of their new technology. It'll come around eventually, so long as it's truly an improvement. There's more open software in consumers' homes today than ever before, so there's a chance it will make in-roads someday. Aside from that, it could be interesting to experiment with for the potential applications, so I'd say it's worth the effort.

The best thing about this is that if the underlying technology behind this ever takes off there will be a significant base of prior art to invalidate all the inevitable patents people will try to claim around it. You can't get them all, but at least there should be a basis for something decent without them.

[scionicspectre]

Doesn't hurt to have an option. I don't think Xiph has ever expected devices to quickly adopt any of their new technology. It'll come around eventually, so long as it's truly an improvement. There's more open software in consumers' homes today than ever before, so there's a chance it will make in-roads someday. Aside from that, it could be interesting to experiment with for the potential applications, so I'd say it's worth the effort.

[Ancurio]

?

"Hey, let's create a mobile device with FPGAs! It will be many times slower than similarly priced devices with dedicated HW,
but on the upside, 5 years later we can patch our hardware to do new tasks,
so consumers don't even have to buy a new product from us to keep up!"

[liam]

FPGAs? LOL, it will never happen.

There are very few things I would say could never happen. This isn't one of those things, but I get your point. FPGAs are expensive, large, and relatively power hungry compared to asics, but are ideal for situations like this where you have a quasi-embedded system but with that will experience significent software upgrades over the course of its useful life, and has tight power constraints.

> Mass market consumer devices
> FPGAs

You wot m8

?

[Ancurio]

Edit: These wouldn't be problems if device makers started including fpgas as a matter of fact.

> Mass market consumer devices
> FPGAs

You wot m8

[darkbasic]

These wouldn't be problems if device makers started including fpgas as a matter of fact.

FPGAs? LOL, it will never happen.