swscale/aarch64: Add rgb24 to yuv implementation

Test on Apple M1:

rgb24_to_uv_8_c: 0.0
rgb24_to_uv_8_neon: 0.2
rgb24_to_uv_128_c: 1.0
rgb24_to_uv_128_neon: 0.5
rgb24_to_uv_1080_c: 7.0
rgb24_to_uv_1080_neon: 5.7
rgb24_to_uv_1920_c: 12.5
rgb24_to_uv_1920_neon: 9.5
rgb24_to_uv_half_8_c: 0.2
rgb24_to_uv_half_8_neon: 0.2
rgb24_to_uv_half_128_c: 1.0
rgb24_to_uv_half_128_neon: 0.5
rgb24_to_uv_half_1080_c: 6.2
rgb24_to_uv_half_1080_neon: 3.0
rgb24_to_uv_half_1920_c: 11.2
rgb24_to_uv_half_1920_neon: 5.2
rgb24_to_y_8_c: 0.2
rgb24_to_y_8_neon: 0.0
rgb24_to_y_128_c: 0.5
rgb24_to_y_128_neon: 0.5
rgb24_to_y_1080_c: 4.7
rgb24_to_y_1080_neon: 3.2
rgb24_to_y_1920_c: 8.0
rgb24_to_y_1920_neon: 5.7

On Pixel 6:

rgb24_to_uv_8_c: 30.7
rgb24_to_uv_8_neon: 56.9
rgb24_to_uv_128_c: 213.9
rgb24_to_uv_128_neon: 173.2
rgb24_to_uv_1080_c: 1649.9
rgb24_to_uv_1080_neon: 1424.4
rgb24_to_uv_1920_c: 2907.9
rgb24_to_uv_1920_neon: 2480.7
rgb24_to_uv_half_8_c: 36.2
rgb24_to_uv_half_8_neon: 33.4
rgb24_to_uv_half_128_c: 167.9
rgb24_to_uv_half_128_neon: 99.4
rgb24_to_uv_half_1080_c: 1293.9
rgb24_to_uv_half_1080_neon: 778.7
rgb24_to_uv_half_1920_c: 2292.7
rgb24_to_uv_half_1920_neon: 1328.7
rgb24_to_y_8_c: 19.7
rgb24_to_y_8_neon: 27.7
rgb24_to_y_128_c: 129.9
rgb24_to_y_128_neon: 96.7
rgb24_to_y_1080_c: 995.4
rgb24_to_y_1080_neon: 767.7
rgb24_to_y_1920_c: 1747.4
rgb24_to_y_1920_neon: 1337.2

Note both tests use clang as compiler, which has vectorization
enabled by default with -O3.

Reviewed-by: Rémi Denis-Courmont <remi@remlab.net>
Reviewed-by: Martin Storsjö <martin@martin.st>
Signed-off-by: Zhao Zhili <zhilizhao@tencent.com>

1 files changed, 25 insertions, 0 deletions

diff --git a/libswscale/aarch64/swscale.c b/libswscale/aarch64/swscale.c
index bbd9719a44..4c4ea39dc1 100644
--- a/libswscale/aarch64/swscale.c
+++ b/libswscale/aarch64/swscale.c
@@ -201,6 +201,20 @@ 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);
+
 av_cold void ff_sws_init_swscale_aarch64(SwsContext *c)
 {
     int cpu_flags = av_get_cpu_flags();
@@ -212,5 +226,16 @@ av_cold void ff_sws_init_swscale_aarch64(SwsContext *c)
         if (c->dstBpc == 8) {
             c->yuv2planeX = ff_yuv2planeX_8_neon;
         }
+        switch (c->srcFormat) {
+        case AV_PIX_FMT_RGB24:
+            c->lumToYV12 = ff_rgb24ToY_neon;
+            if (c->chrSrcHSubSample)
+                c->chrToYV12 = ff_rgb24ToUV_half_neon;
+            else
+                c->chrToYV12 = ff_rgb24ToUV_neon;
+            break;
+        default:
+            break;
+        }
     }
 }