dav1d 0.9.1: a ton of asm

dav1d 0.9.0 optimizations about 10bit Since 0.7.1 release from last year, we’ve focused on optimizing high-bitdepth decoding, on ARM and x86 platforms.
For those who don’t know, high-bitdepth means 10bit and 12bit per pixels instead of 8, which increases the precision of colors and is necessary for UHD and HDR images and videos. (Note: 12bit is very rarely used in consumer cases.)
Because the data uses 10bit per component, we need to write specific assembly code, different from the 8bit code.