dav1d 0.2.1 'Antelope', the fast and small AV1 decoder

This is the second release of dav1d, the fast and small AV1 decoder,
codename 'Antelope'.

It still supports all AV1 features and all bitdepths, from 8 to 12bits,
and decodes more samples than before.

While still being the fastest decoder on AVX-2 CPUs, dav1d is now also
faster on ARM, ARM64 and SSSE3 CPUs in normal loads.
0.2.x is around 2x/2.5x faster on SSSE3 and achieves 1080p at 80fps
on an iPhone XS

0.2.1 is a small bugfix release above 0.2.0 to fix build issues, and
increase a bit the speed of SSSE3
build: use the project version as product version in the windows resource file

And the API version as the file version.
2 files changed
tree: 4e28df6d4e7d3b3b832f2b7ba899f5609b36eb03
  1. .gitignore
  2. .gitlab-ci.yml
  5. NEWS
  6. README.md
  7. THANKS.md
  8. doc/
  9. include/
  10. meson.build
  11. meson_options.txt
  12. snap/
  13. src/
  14. tests/
  15. tools/


dav1d is a new AV1 cross-platform decoder, open-source, and focused on speed and correctness.

The canonical repository URL for this repo is https://code.videolan.org/videolan/dav1d

This project is partially funded by the Alliance for Open Media/AOM.

Goal and Features

The goal of this project is to provide a decoder for most platforms, and achieve the highest speed possible to overcome the temporary lack of AV1 hardware decoder.

It supports all features from AV1, including all subsampling and bit-depth parameters.

In the future, this project will host simple tools or simple wrappings (like, for example, an MFT transform).


dav1d is released under a very liberal license, a contrario from the other VideoLAN projects, so that it can be embedded anywhere, including non-open-source software; or even drivers, to allow the creation of hybrid decoders.

The reasoning behind this decision is the same as for libvorbis, see RMS on vorbis.


The plan is the folllowing:


  1. Complete C implementation of the decoder,
  2. Provide a usable API,
  3. Port to most platforms,
  4. Make it fast on desktop, by writing asm for AVX-2 chips.


  1. Make it fast on mobile, by writing asm for ARMv8 chips,
  2. Make it fast on older desktop, by writing asm for SSE chips.


  1. Improve C code base with various tweaks,
  2. Accelerate for less common architectures,
  3. Use more GPU, when possible.


Currently, we are looking for help from:

  • C developers,
  • asm developers,
  • platform-specific developers,
  • GPGPU developers,
  • testers.

Our contributions guidelines are quite strict. We want to build a coherent codebase to simplify maintenance and achieve the highest possible speed.

Notably, the codebase is in pure C and asm.

We are on IRC, on the #dav1d channel on Freenode.

See the contributions document.


There is no CLA.

People will keep their copyright and their authorship rights, while adhering to the BSD 2-clause license.

VideoLAN will only have the collective work rights.


The VideoLAN Code of Conduct applies to this project.


  1. Install Meson (0.47 or higher), Ninja, and, for x86* targets, nasm (2.13.02 or higher)
  2. Run meson build --buildtype release
  3. Build with ninja -C build

Run tests

  1. During initial build dir setup or meson configure specify -Dbuild_tests=true
  2. In the build directory run meson test optionally with -v for more verbose output, especially useful for checkasm

Run testdata based tests

  1. Checkout the test data repository

    git clone https://code.videolan.org/videolan/dav1d-test-data.git tests/dav1d-test-data
  2. During initial build dir setup or meson configure specify -Dbuild_tests=true and -Dtestdata_tests=true

    meson .test -Dbuild_tests=true -Dtestdata_tests=true
  3. In the build directory run meson test optionally with -v for more verbose output


This project is partially funded by the Alliance for Open Media/AOM and is supported by TwoOrioles and VideoLabs.

These companies can provide support and integration help, should you need it.


Why do you not improve libaom rather than starting a new project?

  • We believe that libaom is a very good library. It was however developed for research purposes during AV1 design. We think that an implementation written from scratch can achieve faster decoding, in the same way that ffvp9 was faster than libvpx.

Is dav1d a recursive acronym?

  • Yes.

Can I help?

I am not a developer. Can I help?

  • Yes. We need testers, bug reporters, and documentation writers.

What about the AV1 patent license?

  • This project is an implementation of a decoder. It gives you no special rights on the AV1 patents.

Please read the AV1 patent license that applies to the AV1 specification and codec.

Will you care about <my_arch>? <my_os>?

  • We do, but we don't have either the time or the knowledge. Therefore, patches and contributions welcome.