avcodec/h264: sse2, avx h luma mbaff deblock/loop filter

x86-64 only

Yorkfield:
- sse2: ~2.17x (434 vs. 200 cycles)

Nehalem:
- sse2: ~2.94x (409 vs. 139 cycles)

Skylake:
- sse2: ~3.10x (370 vs. 119 cycles)
- avx:  ~3.29x (370 vs. 112 cycles)

1 files changed, 10 insertions, 0 deletions

diff --git a/libavcodec/x86/h264dsp_init.c b/libavcodec/x86/h264dsp_init.c
index 7b3d17f971..10f19401ef 100644
--- a/libavcodec/x86/h264dsp_init.c
+++ b/libavcodec/x86/h264dsp_init.c
@@ -137,6 +137,9 @@ LF_IFUNC(h, chroma422_intra, depth, avx)        \
 LF_FUNC(v,  chroma,          depth, avx)        \
 LF_IFUNC(v, chroma_intra,    depth, avx)
 
+LF_FUNC(h, luma_mbaff, 8, sse2)
+LF_FUNC(h, luma_mbaff, 8, avx)
+
 LF_FUNCS(uint8_t,   8)
 LF_FUNCS(uint16_t, 10)
 
@@ -297,6 +300,10 @@ av_cold void ff_h264dsp_init_x86(H264DSPContext *c, const int bit_depth,
             c->h264_h_loop_filter_luma       = ff_deblock_h_luma_8_sse2;
             c->h264_v_loop_filter_luma_intra = ff_deblock_v_luma_intra_8_sse2;
             c->h264_h_loop_filter_luma_intra = ff_deblock_h_luma_intra_8_sse2;
+
+#if ARCH_X86_64
+            c->h264_h_loop_filter_luma_mbaff = ff_deblock_h_luma_mbaff_8_sse2;
+#endif
         }
         if (EXTERNAL_SSSE3(cpu_flags)) {
             c->biweight_h264_pixels_tab[0] = ff_h264_biweight_16_ssse3;
@@ -307,6 +314,9 @@ av_cold void ff_h264dsp_init_x86(H264DSPContext *c, const int bit_depth,
             c->h264_h_loop_filter_luma       = ff_deblock_h_luma_8_avx;
             c->h264_v_loop_filter_luma_intra = ff_deblock_v_luma_intra_8_avx;
             c->h264_h_loop_filter_luma_intra = ff_deblock_h_luma_intra_8_avx;
+#if ARCH_X86_64
+            c->h264_h_loop_filter_luma_mbaff = ff_deblock_h_luma_mbaff_8_avx;
+#endif
         }
     } else if (bit_depth == 10) {
         if (EXTERNAL_MMXEXT(cpu_flags)) {