libavfilter/x86/vf_gblur: add ff_verti_slice_avx2/512()

The new vertical slice with AVX2/512 acceleration can significantly
improve the performance of Gaussian Filter 2D.

Performance data:
ff_verti_slice_c: 32.57
ff_verti_slice_avx2: 476.19
ff_verti_slice_avx512: 833.33

Co-authored-by: Cheng Yanfei <yanfei.cheng@intel.com>
Co-authored-by: Jin Jun <jun.i.jin@intel.com>
Signed-off-by: Wu Jianhua <jianhua.wu@intel.com>

1 files changed, 2 insertions, 0 deletions

diff --git a/libavfilter/gblur.h b/libavfilter/gblur.h
index dce50671f6..367575a6db 100644
--- a/libavfilter/gblur.h
+++ b/libavfilter/gblur.h
@@ -50,6 +50,8 @@ typedef struct GBlurContext {
     float nuV;
     int nb_planes;
     void (*horiz_slice)(float *buffer, int width, int height, int steps, float nu, float bscale);
+    void (*verti_slice)(float *buffer, int width, int height, int slice_start, int slice_end, int steps,
+                            float nu, float bscale);
     void (*postscale_slice)(float *buffer, int length, float postscale, float min, float max);
 } GBlurContext;