From 84ac1440b2a726b8a989dafdf634081651de1c10 Mon Sep 17 00:00:00 2001 From: Mikhail Nitenko Date: Thu, 15 Apr 2021 12:13:52 +0300 Subject: lavc/aarch64: add pred16x16 10-bit functions Benchmarks: A53 A72 pred16x16_dc_10_c: 136.0 124.0 pred16x16_dc_10_neon: 121.2 106.0 pred16x16_horizontal_10_c: 155.0 73.2 pred16x16_horizontal_10_neon: 82.2 67.7 pred16x16_top_dc_10_c: 106.0 93.7 pred16x16_top_dc_10_neon: 87.7 77.2 pred16x16_vertical_10_c: 83.0 67.7 pred16x16_vertical_10_neon: 54.2 61.7 Some functions work slower than C and are left commented out. --- libavcodec/aarch64/h264pred_init.c | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'libavcodec/aarch64/h264pred_init.c') diff --git a/libavcodec/aarch64/h264pred_init.c b/libavcodec/aarch64/h264pred_init.c index fc8989ae0d..325a86bfcd 100644 --- a/libavcodec/aarch64/h264pred_init.c +++ b/libavcodec/aarch64/h264pred_init.c @@ -45,6 +45,11 @@ 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); + static av_cold void h264_pred_init_neon(H264PredContext *h, int codec_id, const int bit_depth, const int chroma_format_idc) @@ -78,6 +83,12 @@ static av_cold void h264_pred_init_neon(H264PredContext *h, int codec_id, codec_id != AV_CODEC_ID_VP7 && codec_id != AV_CODEC_ID_VP8) h->pred16x16[PLANE_PRED8x8 ] = ff_pred16x16_plane_neon; } + if (bit_depth == 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; + } } av_cold void ff_h264_pred_init_aarch64(H264PredContext *h, int codec_id, -- cgit v1.2.3