lavc/aarch64: add pred functions for 10-bit

Benchmarks:                        A53     A72
pred8x8_dc_10_c:                   64.2    49.5
pred8x8_dc_10_neon:                62.0    53.7
pred8x8_dc_128_10_c:               26.0    14.0
pred8x8_dc_128_10_neon:            30.7    17.5
pred8x8_horizontal_10_c:           60.0    27.7
pred8x8_horizontal_10_neon:        38.0    34.0
pred8x8_left_dc_10_c:              42.5    27.5
pred8x8_left_dc_10_neon:           51.0    41.2
pred8x8_mad_cow_dc_0l0_10_c:       55.7    37.2
pred8x8_mad_cow_dc_0l0_10_neon:    50.2    35.2
pred8x8_mad_cow_dc_0lt_10_c:       89.2    67.0
pred8x8_mad_cow_dc_0lt_10_neon:    52.2    46.7
pred8x8_mad_cow_dc_l0t_10_c:       74.7    51.0
pred8x8_mad_cow_dc_l0t_10_neon:    50.5    45.2
pred8x8_mad_cow_dc_l00_10_c:       58.0    38.0
pred8x8_mad_cow_dc_l00_10_neon:    42.5    37.5
pred8x8_plane_10_c:               354.0   288.7
pred8x8_plane_10_neon:            141.0   101.2
pred8x8_top_dc_10_c:               44.5    30.5
pred8x8_top_dc_10_neon:            40.0    31.0
pred8x8_vertical_10_c:             27.5    14.5
pred8x8_vertical_10_neon:          21.0    17.5
pred16x16_plane_10_c:            1242.0  1070.5
pred16x16_plane_10_neon:          324.0   196.7

Signed-off-by: Mikhail Nitenko <mnitenko@gmail.com>
Signed-off-by: Martin Storsjö <martin@martin.st>

1 files changed, 37 insertions, 3 deletions

diff --git a/libavcodec/aarch64/h264pred_init.c b/libavcodec/aarch64/h264pred_init.c
index 325a86bfcd..0ae8f70d23 100644
--- a/libavcodec/aarch64/h264pred_init.c
+++ b/libavcodec/aarch64/h264pred_init.c
@@ -45,10 +45,23 @@ void ff_pred8x8_0lt_dc_neon(uint8_t *src, ptrdiff_t stride);
 void ff_pred8x8_l00_dc_neon(uint8_t *src, ptrdiff_t stride);
 void ff_pred8x8_0l0_dc_neon(uint8_t *src, ptrdiff_t stride);
 
-void ff_pred16x16_top_dc_neon_10(uint8_t *src, ptrdiff_t stride);
-void ff_pred16x16_dc_neon_10(uint8_t *src, ptrdiff_t stride);
-void ff_pred16x16_hor_neon_10(uint8_t *src, ptrdiff_t stride);
 void ff_pred16x16_vert_neon_10(uint8_t *src, ptrdiff_t stride);
+void ff_pred16x16_hor_neon_10(uint8_t *src, ptrdiff_t stride);
+void ff_pred16x16_plane_neon_10(uint8_t *src, ptrdiff_t stride);
+void ff_pred16x16_dc_neon_10(uint8_t *src, ptrdiff_t stride);
+void ff_pred16x16_top_dc_neon_10(uint8_t *src, ptrdiff_t stride);
+
+void ff_pred8x8_vert_neon_10(uint8_t *src, ptrdiff_t stride);
+void ff_pred8x8_hor_neon_10(uint8_t *src, ptrdiff_t stride);
+void ff_pred8x8_plane_neon_10(uint8_t *src, ptrdiff_t stride);
+void ff_pred8x8_dc_neon_10(uint8_t *src, ptrdiff_t stride);
+void ff_pred8x8_128_dc_neon_10(uint8_t *src, ptrdiff_t stride);
+void ff_pred8x8_left_dc_neon_10(uint8_t *src, ptrdiff_t stride);
+void ff_pred8x8_top_dc_neon_10(uint8_t *src, ptrdiff_t stride);
+void ff_pred8x8_l0t_dc_neon_10(uint8_t *src, ptrdiff_t stride);
+void ff_pred8x8_0lt_dc_neon_10(uint8_t *src, ptrdiff_t stride);
+void ff_pred8x8_l00_dc_neon_10(uint8_t *src, ptrdiff_t stride);
+void ff_pred8x8_0l0_dc_neon_10(uint8_t *src, ptrdiff_t stride);
 
 static av_cold void h264_pred_init_neon(H264PredContext *h, int codec_id,
                                         const int bit_depth,
@@ -84,10 +97,31 @@ static av_cold void h264_pred_init_neon(H264PredContext *h, int codec_id,
             h->pred16x16[PLANE_PRED8x8  ] = ff_pred16x16_plane_neon;
     }
     if (bit_depth == 10) {
+        if (chroma_format_idc <= 1) {
+            h->pred8x8[VERT_PRED8x8     ] = ff_pred8x8_vert_neon_10;
+            h->pred8x8[HOR_PRED8x8      ] = ff_pred8x8_hor_neon_10;
+            if (codec_id != AV_CODEC_ID_VP7 && codec_id != AV_CODEC_ID_VP8)
+                h->pred8x8[PLANE_PRED8x8] = ff_pred8x8_plane_neon_10;
+            h->pred8x8[DC_128_PRED8x8   ] = ff_pred8x8_128_dc_neon_10;
+            if (codec_id != AV_CODEC_ID_RV40 && codec_id != AV_CODEC_ID_VP7 &&
+                codec_id != AV_CODEC_ID_VP8) {
+                h->pred8x8[DC_PRED8x8     ] = ff_pred8x8_dc_neon_10;
+                h->pred8x8[LEFT_DC_PRED8x8] = ff_pred8x8_left_dc_neon_10;
+                h->pred8x8[TOP_DC_PRED8x8 ] = ff_pred8x8_top_dc_neon_10;
+                h->pred8x8[ALZHEIMER_DC_L0T_PRED8x8] = ff_pred8x8_l0t_dc_neon_10;
+                h->pred8x8[ALZHEIMER_DC_0LT_PRED8x8] = ff_pred8x8_0lt_dc_neon_10;
+                h->pred8x8[ALZHEIMER_DC_L00_PRED8x8] = ff_pred8x8_l00_dc_neon_10;
+                h->pred8x8[ALZHEIMER_DC_0L0_PRED8x8] = ff_pred8x8_0l0_dc_neon_10;
+            }
+        }
+
         h->pred16x16[DC_PRED8x8     ] = ff_pred16x16_dc_neon_10;
         h->pred16x16[VERT_PRED8x8   ] = ff_pred16x16_vert_neon_10;
         h->pred16x16[HOR_PRED8x8    ] = ff_pred16x16_hor_neon_10;
         h->pred16x16[TOP_DC_PRED8x8 ] = ff_pred16x16_top_dc_neon_10;
+        if (codec_id != AV_CODEC_ID_SVQ3 && codec_id != AV_CODEC_ID_RV40 &&
+            codec_id != AV_CODEC_ID_VP7 && codec_id != AV_CODEC_ID_VP8)
+            h->pred16x16[PLANE_PRED8x8  ] = ff_pred16x16_plane_neon_10;
     }
 }