diff options
author | Jun Zhao <barryjzhao@tencent.com> | 2019-10-02 05:31:13 +0300 |
---|---|---|
committer | Jun Zhao <barryjzhao@tencent.com> | 2019-10-10 04:33:09 +0300 |
commit | da0c0c7247fbf1596ec768746071d6d2f91d0fb0 (patch) | |
tree | 52d9569a165b3e3d5bc3d45557b7d1cf3c26062d /libavfilter/vf_hqdn3d.h | |
parent | 7ab4fbdebcf1c319298d7319b89fc514620a824f (diff) |
lavfi/hqdn3d: add slice thread optimization
Enabled one thread per plane, used the test command for 1080P video
(YUV420P format) as follow:
ffmpeg -i 1080p.mp4 -an -vf hqdn3d -f null /dev/nul
This optimization improved the performance about 30% in 1080P YUV420P
case (from 110fps to 143fps), also pass the framemd5 check and FATE.
Reviewed-by: Paul B Mahol <onemda@gmail.com>
Reviewed-by: Moritz Barsnick <barsnick@gmx.net>
Signed-off-by: Jun Zhao <barryjzhao@tencent.com>
Diffstat (limited to 'libavfilter/vf_hqdn3d.h')
-rw-r--r-- | libavfilter/vf_hqdn3d.h | 2 |
1 files changed, 1 insertions, 1 deletions
diff --git a/libavfilter/vf_hqdn3d.h b/libavfilter/vf_hqdn3d.h index 03a79a108c..3279bbcc77 100644 --- a/libavfilter/vf_hqdn3d.h +++ b/libavfilter/vf_hqdn3d.h @@ -31,7 +31,7 @@ typedef struct HQDN3DContext { const AVClass *class; int16_t *coefs[4]; - uint16_t *line; + uint16_t *line[3]; uint16_t *frame_prev[3]; double strength[4]; int hsub, vsub; |