[Cin] New dav1d is out - 0.5.1, claims even more speed on older processors

Andrew Randrianasulu randrianasulu at gmail.com
Mon Oct 28 16:09:43 CET 2019

I can't believe my eyes, but apparently this is not a typo ...


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'.

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.

Changes for 0.5.1 'Asiatic Cheetah':

0.5.1 is a small release improving speeds and fixing minor issues
compared to 0.5.0:
 - SSE2 optimizations for CDEF, wiener and warp_affine
 - NEON optimizations for SGR on ARM32
 - Fix mismatch issue in x86 asm in inverse identity transforms
 - Fix build issue in ARM64 assembly if debug info was enabled
 - Add a workaround for Xcode 11 -fstack-check bug

Found via Phoronix.

Compiled and installed .. apparently no .so bump this time, so no recompile needed :P

More information about the Cin mailing list