Too much traffic from HN?

``` Too Many Requests The page you have tried to access is not available because the owner of the file you are trying to access has exceeded our short term bandwidth limits. Please try again shortly.

Details: Actioning this file would cause "jbkempf.com//blog/2026/dav2d/" to exceed the per-day file actions limit of 160000 actions, try again later ```

Intel's Arc dGPUs were really compelling for dedicated AV1 encode and decode, especially the small form factor of some cards. You could even fit it as a secondary card in a PC dedicated to recording and encode workflows for OBS.

Hope we get a similar option with future lineups that support AV2, especially given how popular video creation and streaming are now.

I came to post this as well. Until widespread, inexpensive hardware catches up to a 2018 codec, AV# will remain a niche ideal.

> AV1 software decoding is already very intensive so AV2 decoding benchmarks are the next thing that would be really interesting (or mortifying) to see.

Yes, this is going to be fun to watch.

Almost every Intel CPU released since 2013 has AVX2 support. Some Atom SKUs were longer holdouts, but the fraction of x86 CPUs shipped in the last decade that have AVX2 support is very high.

it got archived by the wayback machine: https://web.archive.org/web/20260531115337/https://jbkempf.c...

Same

I understood it as compression is 25% better : a quality of 10mbps in av1 can be achieved with 8mbps in Av2. But, it needs 5 times more compute power for this 25% gain.

> I'm not sure what these two lines mean or if we can compare them, any help?

AV2 saves 25% bandwidth at the cost of 5x more decoding complexity.

Smaller files but harder to decode

Return of the 8MB Shrek encodes?

One would imagine given the name that it would specialize in codecs

Or Dave2D, popular tech youtuber

> Not to be confused with Da4vid (world-class hacker and owner of the Black sun)

*Da5id

I'm pretty sure it is a homage. As for dav1d it's not a reference decoder (although partially funded by AOM iirc) so they might not know that the next iteration will simply be AV2, we have h264, h265, h266 naming though

Tangent but I cannot wait for h269 (or h267 for the younger gen)

As with all naming schemes in the tech world, I am sure no future scenarios, including successor names, were ever considered

I think it's a reasonable decision. The only people who will interact with dav2d by name are codec nerds, and a simple increment makes the lineage more obvious to that audience.

1dav2codecs?

2av2furious?

> experience Dav... Now in 3D!

Da5id could potentially work as a Snow Crash reference.

The algorithms deployed in these kind of codecs take into account not only human vision and mathematical laws of information, but also nitty-gritty details of how computers work, which are optimally exploited by directly having humans write detailed assembly rather than a compiler make a best guess and effort.

Because it's 5 times more complex, you need to get the maximum performance available. Therefore more ASM than ever.

Rust does not bring more performance. Just more safety.

Encoder and decoder writers frequently need extremely fine grain control over SIMD instructions in order to get good performance.

The way they weave these instructions can be very hard to express with a high level language.

Further, there's a ton of work with arrays and importantly parts of arrays. They can, for example, need to extract every other element up to 1/2 the array. Unfortunately, rust has runtime array bounds checks which make writing that sort of code slower. The compiler can elade those checks, but usually only in simple cases.

The authors would be writing a bunch of unsafe rust to get the performance they want and rust makes that more painful on purpose.

I like rust, but C/ASM really is the right choice here. This is one of the few cases where rust's safety is a major detriment.

The ffmpeg devs have said many times in public that they routinely get speedups of 10x or more over C code. I'm not a reputable source on this myself but I highly recommend looking into their channels, mails, or posts.

yes it makes sense to use C/ASM here, but if you're curious, there is a rust port of dav1d named rav1d: https://github.com/memorysafety/rav1d

it's not much slower than the original C/ASM implementation (last i checked ~5%?) but that matters here

Go ask FFmpeg what they're writing their encoders and decoders in.

Yes? There is 5x more code to optimize the ASM for.

Norbert Wiener in the 1940s. He invented the technique.

It's a semi-common last name.

https://en.wikipedia.org/wiki/Wiener_filter?wprov=sfla1

They filed a suit, henceforth making a claim of an issue...... They haven't "proved" anything other then they have lawyers on staff that can file some paperwork until the suit is settled in court...

How does that prove anything?

They're claiming that there are patents, but that doesn't mean there are.

No codec can ever avoid patent-pool claims.

Every single AV2 news here in the last week has seen exactly the same question.

Either go back read the answers there first, or I will assume you are part of a FUD campaign (yes, I know HN guidelines, but again every single AV2 news in the last week has seen the same rhetorical "questions" as top "comments").