[HN Gopher] Netflix Now Streaming AV1 on Android
___________________________________________________________________
Netflix Now Streaming AV1 on Android
Author : discreditable
Score : 65 points
Date : 2020-02-05 20:21 UTC (2 hours ago)
(HTM) web link (netflixtechblog.com)
(TXT) w3m dump (netflixtechblog.com)
| Jonnax wrote:
| How much slower are encodes vs H.264 or HEVC?
|
| The way some of the comments here are talking about it. It's like
| it requires a 2 hour encode to encode 1 hour.
|
| For Netflix this is an encode once then just CDN the files. I
| can't imagine that this would be a significant cost.
| spenczar5 wrote:
| Hugely slower, and there is little (maybe zero?) hardware
| encoding support out there, which makes it too expensive for
| most use cases.
|
| You are completely right about Netflix's needs here. Spending
| thousands of dollars on re-encoding video to shave off 1% of
| its size in bytes can easily be profitable at the scale of a
| hit show like Stranger Things.
| microcolonel wrote:
| And the savings are much better than 1%, if they really do
| spend that much time encoding. The complexity of encoding is
| relatively similar for equivalent quality/bitrate (at least
| with some of the encoders).
| jedberg wrote:
| There is a significant one time cost to a new codec, because
| the entire library needs to be re-encoded, but that cost is
| more than made up for as long as one of two things are true:
|
| 1) It takes significantly fewer resources to stream to
| customers (bandwidth, CPU, disk, RAM, etc) or
|
| 2) It provides a significantly better experience for the user,
| which translates to more retention (either better picture
| quality or fewer video pauses or both).
|
| If you can find a codec that does _both_ , that's worth far
| more than any encoding cost.
| babypuncher wrote:
| I can list multiple streaming services off the top of my head
| that could really use better picture quality.
| oliwarner wrote:
| 30fps on a 9900KS at 1080p. Three to four times slower than
| x264. As you say, for ahead of time, write once, read many
| media like Netflix, that's an acceptable trade. It's not going
| to work for live media yet.
|
| But 10bit 4k streams need nearly 50gb RAM and exponentially
| more time than 1080p. I've never had much luck.
| jl6 wrote:
| A 20% data saving but how much extra battery usage for devices
| which don't have hardware decoding for AV1 (which last time I
| checked was all of them)?
| ksec wrote:
| Exactly. I am thinking if this is going to be some sort of play
| against VVC.
|
| Or will Youtube and Netflix force AV1 upon everyone where if
| you want high quality HDR or 4K Content you will require AV1.
| jhasse wrote:
| > Or will Youtube and Netflix force AV1 upon everyone where
| if you want high quality HDR or 4K Content you will require
| AV1.
|
| I sure hope so!
| cbhl wrote:
| Which is why they launched it behind an opt-in checkbox.
|
| New codecs are always chicken-and-egg -- you need to have
| content available before the hardware encoders/decoder silicon
| gets produced and then trickles down to the phones.
| xxpor wrote:
| Do phones have HW support for VP9?
|
| edit: looks like it, at least for recent snapdragon phones:
|
| https://en.wikipedia.org/wiki/VP9#Hardware_implementations
| Grazester wrote:
| Do 2+ plus year old phones count as recent?
| gruez wrote:
| From the link,
|
| Snapdragon 820: launched early 2016
|
| Snapdragon 660: announced on May 9, 2017
|
| Not saying that all phones made after 2017 will have it,
| but there are mid range phones on sale that do.
| apocalyptic0n3 wrote:
| No word on what their encoding toolset is. That's been the
| limiting factor with widespread adoption thus far; it just takes
| too much CPU and too much time to encode as AV1 vs 264, 265, or
| VP9
| CharlesW wrote:
| > _No word on what their encoding toolset is._
|
| They're using ST-AV1[1], the encoder they've collaborated with
| Intel on.[2][3]
|
| [1] https://github.com/OpenVisualCloud/SVT-AV1
|
| [2] https://newsroom.intel.com/news/intel-netflix-deliver-
| av1-sc...
|
| [3] https://netflixtechblog.com/introducing-svt-
| av1-a-scalable-o...
| ksec wrote:
| So SVT-AV1 now does 20% better than VP9?
|
| Edit: They did mention the 20% is from AV1-libaom compression
| efficiency as measured against VP9-libvpx. So not SVT-AV1.
| CharlesW wrote:
| They cite AV1-libaom for the 20% efficiency improvement
| over VP9, but I didn't take that to mean that they're using
| the reference encoder in production. Do you happen to know
| for sure?
| jjcm wrote:
| For Netflix this likely doesn't matter. While Youtube deals
| with 300+ hours of content uploaded every minute that it has to
| encode, Netflix only has to encode ~100 titles per month. Even
| if it takes a month to encode 1 of these, it's still easily
| doable for Netflix.
| apocalyptic0n3 wrote:
| Yes and no. It's a cost-benefit deal. Just because they _can_
| (and they surely can), doesn't mean it is cost beneficial to
| do so now. It takes CPU time (and therefore money) for each
| encode they do. If one takes much more resources to do, it
| may not be beneficial to do so yet. I originally posted my
| comment wondering if there had been some encoder breakthrough
| that I had missed that had made AV1 a viable option finally.
| Looks like there was, but it's still not nearly as good as it
| needs to be fore widespread adoption (looks like it's still
| 30x slower than a comparable HEVC or VP9 encode). So I guess
| it comes down to: are they saving enough on downstream
| bandwidth to balance out the CPU time for the encode?
| Releasing it would suggest yes, or they see some benefit to
| pushing the standard into the mainstream now rather than in
| six months regardless of the cost to them.
| frandroid wrote:
| That kind of CPU load is a drop in the bucket for Netflix.
| ryder9 wrote:
| savings on bandwidth will make up for it
|
| Almost like Netflix has data analysts and experts in the
| field who have already calculated the cost benefits based
| on internal metrics unavailable to us and chosen to
| implement it...
| chx wrote:
| I would argue that since the CPU is a one time cost but the
| bandwidth benefit is recurring and not just for the company
| but for the customers as well especially on mobile the
| calculation is rather easy.
| nomel wrote:
| Does Netflix encode realtime? I would think they would encode
| all of the possible data rates exactly once, then stream off
| disk. I would think realtime encoding would add a significant
| cost per client.
|
| * Disclaimer: I know nothing of AV1.
| wmf wrote:
| No, they don't have much time constraint on encoding. But the
| bill still matters; if AV1 costs $$$$$ to encode because you
| need so many servers it's a bad situation.
| Miraste wrote:
| Theoretically yes, but the hardware cost of encoding their
| microscopic, in streaming terms, number of videos would
| have to be _absurd_ to even come close to the savings they
| get from lowering their bandwidth by 20%.
| thrusong wrote:
| They encode once then stream off disk.
| brobot182 wrote:
| What does "hardware support" mean exactly? Are we talking about
| general-purpose SIMD instructions? Or do phones have dedicated
| circuits that do larger parts of the decoding?
| shmerl wrote:
| I assume they are using AV1+Opus?
|
| When are hardware decoders and encoders for AV1 coming for common
| GPUs (Intel, AMD, Nvidia, Qualcomm, etc.?).
| solarkraft wrote:
| How is the hardware decoding story nowadays? Have devices with
| hardware decoders already started shipping?
| babypuncher wrote:
| Newer Snapdragon SoCs, and that's about it right now.
___________________________________________________________________
(page generated 2020-02-05 23:00 UTC)