swscale/aarch64: Add bgr24 to yuv

Test on Apple M1 with kperf
				: -O3		: -O3 -fno-vectorize
bgr24_to_uv_8_c			: 28.5		: 52.5
bgr24_to_uv_8_neon		: 54.5		: 59.7
bgr24_to_uv_128_c		: 294.0		: 830.7
bgr24_to_uv_128_neon		: 99.7		: 112.0
bgr24_to_uv_1080_c		: 965.0		: 6624.0
bgr24_to_uv_1080_neon		: 751.5		: 754.7
bgr24_to_uv_1920_c		: 1693.2	: 11554.5
bgr24_to_uv_1920_neon		: 1292.5	: 1307.5
bgr24_to_uv_half_8_c		: 54.2		: 37.0
bgr24_to_uv_half_8_neon		: 27.2		: 22.5
bgr24_to_uv_half_128_c		: 127.2		: 392.5
bgr24_to_uv_half_128_neon	: 63.0		: 52.0
bgr24_to_uv_half_1080_c		: 880.2		: 3329.0
bgr24_to_uv_half_1080_neon	: 401.5		: 390.7
bgr24_to_uv_half_1920_c		: 1585.7	: 6390.7
bgr24_to_uv_half_1920_neon	: 694.7		: 698.7
bgr24_to_y_8_c			: 21.7		: 22.5
bgr24_to_y_8_neon		: 797.2		: 25.5
bgr24_to_y_128_c		: 88.0		: 280.5
bgr24_to_y_128_neon		: 63.7		: 55.0
bgr24_to_y_1080_c		: 616.7		: 2208.7
bgr24_to_y_1080_neon		: 900.0		: 452.0
bgr24_to_y_1920_c		: 1093.2	: 3894.7
bgr24_to_y_1920_neon		: 777.2		: 767.5

Signed-off-by: Zhao Zhili <zhilizhao@tencent.com>

1 files changed, 19 insertions, 13 deletions

diff --git a/libswscale/aarch64/swscale.c b/libswscale/aarch64/swscale.c
index e4ea3309ba..c6594944c3 100644
--- a/libswscale/aarch64/swscale.c
+++ b/libswscale/aarch64/swscale.c
@@ -201,19 +201,18 @@ void ff_yuv2plane1_8_neon(
     default: break;                                                     \
     }
 
-void ff_rgb24ToY_neon(uint8_t *_dst, const uint8_t *src, const uint8_t *unused1,
-                      const uint8_t *unused2, int width,
-                      uint32_t *rgb2yuv, void *opq);
-
-void ff_rgb24ToUV_neon(uint8_t *_dstU, uint8_t *_dstV, const uint8_t *unused0,
-                       const uint8_t *src1,
-                       const uint8_t *src2, int width, uint32_t *rgb2yuv,
-                       void *opq);
-
-void ff_rgb24ToUV_half_neon(uint8_t *_dstU, uint8_t *_dstV, const uint8_t *unused0,
-                       const uint8_t *src1,
-                       const uint8_t *src2, int width, uint32_t *rgb2yuv,
-                       void *opq);
+#define NEON_INPUT(name) \
+void ff_##name##ToY_neon(uint8_t *dst, const uint8_t *src, const uint8_t *, \
+                        const uint8_t *, int w, uint32_t *coeffs, void *); \
+void ff_##name##ToUV_neon(uint8_t *, uint8_t *, const uint8_t *, \
+                         const uint8_t *, const uint8_t *, int w, \
+                         uint32_t *coeffs, void *); \
+void ff_##name##ToUV_half_neon(uint8_t *, uint8_t *, const uint8_t *, \
+                              const uint8_t *, const uint8_t *, int w, \
+                              uint32_t *coeffs, void *)
+
+NEON_INPUT(bgr24);
+NEON_INPUT(rgb24);
 
 void ff_lumRangeFromJpeg_neon(int16_t *dst, int width);
 void ff_chrRangeFromJpeg_neon(int16_t *dstU, int16_t *dstV, int width);
@@ -247,6 +246,13 @@ av_cold void ff_sws_init_swscale_aarch64(SwsContext *c)
             c->yuv2planeX = ff_yuv2planeX_8_neon;
         }
         switch (c->srcFormat) {
+        case AV_PIX_FMT_BGR24:
+            c->lumToYV12 = ff_bgr24ToY_neon;
+            if (c->chrSrcHSubSample)
+                c->chrToYV12 = ff_bgr24ToUV_half_neon;
+            else
+                c->chrToYV12 = ff_bgr24ToUV_neon;
+            break;
         case AV_PIX_FMT_RGB24:
             c->lumToYV12 = ff_rgb24ToY_neon;
             if (c->chrSrcHSubSample)