From 00c916ef61873cdbd3558e48b03a9d054f0b90f7 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Reimar=20D=C3=B6ffinger?= Date: Sun, 10 Jan 2021 10:27:00 +0000 Subject: lavc/aarch64: port HEVC add_residual NEON Speedup is fairly small, around 1.5%, but these are fairly simple. Signed-off-by: Josh Dekker --- libavcodec/aarch64/hevcdsp_init_aarch64.c | 24 ++++++++++++++++++++++++ 1 file changed, 24 insertions(+) (limited to 'libavcodec/aarch64/hevcdsp_init_aarch64.c') diff --git a/libavcodec/aarch64/hevcdsp_init_aarch64.c b/libavcodec/aarch64/hevcdsp_init_aarch64.c index 19d9a7f9ed..4c29daa6d5 100644 --- a/libavcodec/aarch64/hevcdsp_init_aarch64.c +++ b/libavcodec/aarch64/hevcdsp_init_aarch64.c @@ -25,6 +25,22 @@ #include "libavutil/aarch64/cpu.h" #include "libavcodec/hevcdsp.h" +void ff_hevc_add_residual_4x4_8_neon(uint8_t *_dst, int16_t *coeffs, + ptrdiff_t stride); +void ff_hevc_add_residual_4x4_10_neon(uint8_t *_dst, int16_t *coeffs, + ptrdiff_t stride); +void ff_hevc_add_residual_8x8_8_neon(uint8_t *_dst, int16_t *coeffs, + ptrdiff_t stride); +void ff_hevc_add_residual_8x8_10_neon(uint8_t *_dst, int16_t *coeffs, + ptrdiff_t stride); +void ff_hevc_add_residual_16x16_8_neon(uint8_t *_dst, int16_t *coeffs, + ptrdiff_t stride); +void ff_hevc_add_residual_16x16_10_neon(uint8_t *_dst, int16_t *coeffs, + ptrdiff_t stride); +void ff_hevc_add_residual_32x32_8_neon(uint8_t *_dst, int16_t *coeffs, + ptrdiff_t stride); +void ff_hevc_add_residual_32x32_10_neon(uint8_t *_dst, int16_t *coeffs, + ptrdiff_t stride); void ff_hevc_idct_8x8_8_neon(int16_t *coeffs, int col_limit); void ff_hevc_idct_8x8_10_neon(int16_t *coeffs, int col_limit); void ff_hevc_idct_16x16_8_neon(int16_t *coeffs, int col_limit); @@ -35,10 +51,18 @@ av_cold void ff_hevc_dsp_init_aarch64(HEVCDSPContext *c, const int bit_depth) if (!have_neon(av_get_cpu_flags())) return; if (bit_depth == 8) { + c->add_residual[0] = ff_hevc_add_residual_4x4_8_neon; + c->add_residual[1] = ff_hevc_add_residual_8x8_8_neon; + c->add_residual[2] = ff_hevc_add_residual_16x16_8_neon; + c->add_residual[3] = ff_hevc_add_residual_32x32_8_neon; c->idct[1] = ff_hevc_idct_8x8_8_neon; c->idct[2] = ff_hevc_idct_16x16_8_neon; } if (bit_depth == 10) { + c->add_residual[0] = ff_hevc_add_residual_4x4_10_neon; + c->add_residual[1] = ff_hevc_add_residual_8x8_10_neon; + c->add_residual[2] = ff_hevc_add_residual_16x16_10_neon; + c->add_residual[3] = ff_hevc_add_residual_32x32_10_neon; c->idct[1] = ff_hevc_idct_8x8_10_neon; c->idct[2] = ff_hevc_idct_16x16_10_neon; } -- cgit v1.2.3