[FFmpeg-devel] [PATCH]levc/hevc_cabac Optimise ff_hevc_hls_residual_coding (v2)

[James Almer]

On 1/21/2016 11:39 PM, Michael Niedermayer wrote:
> On Thu, Jan 21, 2016 at 10:45:55AM +0000, John Cox wrote:
>> Hi
>>
>> v2 of my hevc residual patch
>>
>> I've fixed the fate regression
>> I've split it into more pieces
>> Now uses ff_clz
>> Some reformating of function headers
>>
>> The patches can also be found on
>> https://github.com/jc-kynesim/rpi-ffmpeg.git on branch
>> test/ff_hevc_cabac_4 from tag ff_hevc_cabac_4_base
>>
>> Note that I will be going on holiday from the end of Friday (UK time)
>> till the 1st Feb and will be unable to edit code or read this list
>> during that period.
> 
> applied the first 3 patches
> one #endif was moved to another patch, one typo fixed
> and confirmed that clz is faster
> 
> thx

http://fate.ffmpeg.org/report.cgi?time=20160123040651&slot=x86_64-archlinux-gcc-valgrindundef
The "cabac_functions: Count zeros with ctz if it is fast" commit seems to be at fault.