libavfilter/x86/vf_gblur: add localbuf and ff_horiz_slice_avx2/512()

We introduced a ff_horiz_slice_avx2/512() implemented on a new algorithm.
In a nutshell, the new algorithm does three things, gathering data from
8/16 rows, blurring data, and scattering data back to the image buffer.
Here we used a customized transpose 8x8/16x16 to avoid the huge overhead
brought by gather and scatter instructions, which is dependent on the
temporary buffer called localbuf added newly.

Performance data:
ff_horiz_slice_avx2(old): 109.89
ff_horiz_slice_avx2(new): 666.67
ff_horiz_slice_avx512: 1000

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, 14 insertions, 3 deletions

diff --git a/libavfilter/x86/vf_gblur_init.c b/libavfilter/x86/vf_gblur_init.c
index 3e173410c2..b47f6fbffb 100644
--- a/libavfilter/x86/vf_gblur_init.c
+++ b/libavfilter/x86/vf_gblur_init.c
@@ -24,8 +24,9 @@
 #include "libavutil/x86/cpu.h"
 #include "libavfilter/gblur.h"
 
-void ff_horiz_slice_sse4(float *ptr, int width, int height, int steps, float nu, float bscale);
-void ff_horiz_slice_avx2(float *ptr, int width, int height, int steps, float nu, float bscale);
+void ff_horiz_slice_sse4(float *ptr, int width, int height, int steps, float nu, float bscale, float *localbuf);
+void ff_horiz_slice_avx2(float *ptr, int width, int height, int steps, float nu, float bscale, float *localbuf);
+void ff_horiz_slice_avx512(float *ptr, int width, int height, int steps, float nu, float bscale, float *localbuf);
 
 void ff_postscale_slice_sse(float *ptr, int length, float postscale, float min, float max);
 void ff_postscale_slice_avx2(float *ptr, int length, float postscale, float min, float max);
@@ -51,12 +52,22 @@ av_cold void ff_gblur_init_x86(GBlurContext *s)
         s->horiz_slice = ff_horiz_slice_sse4;
     }
     if (EXTERNAL_AVX2(cpu_flags)) {
-        s->horiz_slice = ff_horiz_slice_avx2;
         s->verti_slice = ff_verti_slice_avx2;
     }
     if (EXTERNAL_AVX512(cpu_flags)) {
         s->postscale_slice = ff_postscale_slice_avx512;
         s->verti_slice = ff_verti_slice_avx512;
     }
+    if (EXTERNAL_AVX2(cpu_flags)) {
+        s->stride = EXTERNAL_AVX512(cpu_flags) ? 16 : 8;
+        s->localbuf = av_malloc(s->stride * sizeof(float) * s->planewidth[0] * s->planeheight[0]);
+        if (!s->localbuf)
+            return;
+
+        s->horiz_slice = ff_horiz_slice_avx2;
+        if (EXTERNAL_AVX512(cpu_flags)) {
+            s->horiz_slice = ff_horiz_slice_avx512;
+        }
+    }
 #endif
 }