Tags

dav1d 1.4.3 'Road Runner'

1.4.3 is a very small release focused on security issues:
 - AArch64: Fix potential out of bounds access in DotProd H/HV filters
 - cli: Prevent buffer over-read

dav1d 1.4.2 'Road Runner'

1.4.2 is a small release of dav1d, improving notably ARM, AVX-512, RISC-V and Power9 speed

It adds numerous new optimizations on 8-tap/6-tap for AVX2, AVX-512;
on convolutions for ARM64 extensions (DotProd, i8mm); on prep/put/msac for ARM64
and on loopfilter for Power9.

dav1d 1.4.1 'Road Runner'

1.4.1 is a small release of dav1d, improving notably ARM and RISC-V
speed and fixing a small security issue.

The ARM speed improvements can be significative, depening on the
samples.

Finally, the binary size of dav1d was reduced on ARM and RISC-V

dav1d 1.4.0 'Road Runner':

dav1d 1.4.0 is a medium release of dav1d, adding RISC-V and loongarch
architecture and adding more AVX-512 optimizations
It also fixes a potential security issue

dav1d 1.3.0 'Tundra Peregrine Falcon':

1.3.0 is a medium release reducing memory footprint, increasing again
the speed on x86 and ARM and extending the API functions.

dav1d 1.2.1 'Arctic Peregrine Falcon'

1.2.1 is a small release of dav1d, adding more SIMD, notably
for z2 in SSSE3 and NEON; numerous fixes on headers, OBU parsing and
buildsystem. Finally, it should reduce memory consumption...

1.2.0 'Arctic Peregrine Falcon':

1.2.0 is a small release of dav1d, adding more SIMD, notably for
z1/z2/z3 on all platforms, and some itx optimizations.
It also brings fixes and improvements on props and T.35

dav1d 1.1.0 'Arctic Peregrine Falcon'

A new release of dav1d, fixing numerous bugs, and adding SIMD
optimizations, notably for AVX-512, SSSE3 and NEON

On this 14th of Feb, from VideoLAN, with love

dav1d 1.0.0 'Peregrine falcon'

1.0.0 is a major release of dav1d, adding important features and bug fixes.

It notably changes, in an important way, the way threading works, by adding
an automatic thread management. It also continues the relentless work on
optimizations.

1.0.0 is here, it's great, fast and lean. Great job the team \o/

                                     .''.
         .''.      .        *''*    :_\/_:     .
        :_\/_:   _\(/_  .:.*_\/_*   : /\ :  .'.:.'.
    .''.: /\ :   ./)\   ':'* /\ * :  '..'.  -=:o:=-
   :_\/_:'.:::.    ' *''*    * '.\'/.' _\(/_'.':'.'
   : /\ : :::::     *_\/_*     -= o =-  /)\    '  *
    '..'  ':::'     * /\ *     .'/.\'.   '
        *            *..*         :
          *                       :
          *         1.0.0

dav1d 0.9.2 'Golden Eargle' the fast and lean AV1 decoder

0.9.2 is a small update of dav1d on the 0.9.x branch, focusing on
numerous small optimizations for SSSE3, AVX2 and NEON in high bitdepth.

dav1d 0.9.0 'Golden Eargle' the fast and lean AV1 decoder

0.9.1 is a middle-sized version of dav1d, adding notably 10b acceleration on SSSE3 CPUs.

It also adds more NEON optimizations for film grain and a few other
small fixes.

dav1d 0.9.0 'Golden Eargle' the fast and lean AV1 decoder

0.9.0 is a major version of dav1d, adding notably 10b acceleration on x86-64.

This release adds acceleration in SIMD for most functions in 10b and 12b.
The SIMD written is for AVX2 chips, running in 64b.

This release continues the ARM optimizations, with FilmGrain implemented
for ARM64 processors.

dav1d 0.8.2 'Eurasian hobby' the fast and lean AV1 decoder

This is a middle-size update of the dav1d decoder, from the 0.8.x branch.

This release adds most of the remaining NEON optimizations for ARM,
especially for 10/12bit bitdepth, in both ARM32 and ARM64.

This release also split the post-filters into their own threads.

This release speeds up quite a bit the desktop version, notably in the
coefficient decoding and the MSAC parts. It also introduces the first
10bit optimizations for x86.

Finally, this release improves the speed in numerous parts of the
decoder, improves the player shipped and brings other fixes.

dav1d 0.8.1 'Eurasian hobby' the fast and lean AV1 decoder

This is a minor update of the dav1d decoder, from the 0.8.x branch.

This releases fixes a regression in the buffer reference handling
introduced by the buffer pool added in 0.8.0. dav1d_close() invalidated
all buffer references.
It also contains further ARM32 high bit depth SIMD optimizations, x86 wiener
filter optimizations and fixes a couple of minor issues.

dav1d 0.8.0 'Eurasian hobby' the fast and lean AV1 decoder

This is a major update of the dav1d, the fast and lean AV1 decoder,
codename 'Eurasian hobby'.

This release improves, once again, the speed on all platforms.

On the desktop platforms, it improves the performance (up to 10%)
by doing less allocations and adding more optimizations for AVX2 and SSE.

On the ARM platforms, this release brings numerous improvements for ARM32
and notably optimizes most of the 10/12bit bitdepth filters.

dav1d 0.7.1 'Frigatebird' the fast and lean AV1 decoder

This is a minor update of the dav1d decoder, from the 0.7.x branch.

This release increases the speed of decoding on ARM32 by up to 28%,
adds some SSE2 optimizations, some AVX2 for MC scaled
and fixes a couple of minor issues.

dav1d 0.7.0 'Frigatebird' the fast and lean AV1 decoder

This is a major update of the dav1d, the fast and lean AV1 decoder,
codename 'Frigatebird'.

This release improves, once again, the speed on all platforms.

A rewrite of refmv made an important speed boost on x86 while reducing
RAM usage. It should improve the speed on every platform.

A large number of assembly optimizations went for ARM64 for 8/10/12bit,
a few for x86, notably for film grain and AVX-512 optimizations for CDEF.

dav1d 0.6.0 'Gyrfalcon', the fast and lean AV1 decoder

This is a major update of the dav1d, the fast and lean AV1 decoder,
codename 'Gyrfalcon'.

0.6.0 brings major improvements in 10/12bit decoding on ARMv8 CPUs,
up to 2.5 times faster than 0.5.2.
It also brings new AVX-512, AVX2 and SSSE3 optimizations and improves
the existing optimizations on all platforms.
Finally, it also fixes some decoder mismatches and minor crashes.

dav1d 0.5.2 'Asiatic Cheetah', the fast and small AV1 decoder

This is a minor update of the 0.5.x version of dav1d, the fast and small AV1 decoder,
codename 'Asiatic Cheetah'.
It supports all the AV1 features and all bitdepths.

0.5.2 brings improvements in speed for ARMv7 CPUs (a few % speedup), on
top of the already big speedups of 0.5.1. It should also improve the
speed for large videos on all platforms.

It also fixes minor issues, brings stability and introduces an OBU demuxer.

dav1d 0.5.1 'Asiatic Cheetah', the fast and small AV1 decoder

This is a minor update of the 0.5.0 version of dav1d, the fast and small AV1 decoder,
codename 'Asiatic Cheetah'.

It supports all the AV1 features and all bitdepths.

0.5.1 brings improvements in speed for SSE2 CPUs (up to 50% speedup), and
ARMv7 CPUs (up to 41% speedup).
It also fixes minor issues and minor speed improvements for other
architectures.