lavc/aarch64: Add neon implementation for vsad16

Provide optimized implementation of vsad16 function for arm64.

Performance comparison tests are shown below.
- vsad_0_c: 285.2
- vsad_0_neon: 39.5

Benchmarks and tests are run with checkasm tool on AWS Graviton 3.

Co-authored-by: Martin Storsjö <martin@martin.st>
Signed-off-by: Hubert Mazur <hum@semihalf.com>
Signed-off-by: Martin Storsjö <martin@martin.st>

2 files changed, 70 insertions, 0 deletions

diff --git a/libavcodec/aarch64/me_cmp_init_aarch64.c b/libavcodec/aarch64/me_cmp_init_aarch64.c
index fb7c3f5059..ddc5d05611 100644
--- a/libavcodec/aarch64/me_cmp_init_aarch64.c
+++ b/libavcodec/aarch64/me_cmp_init_aarch64.c
@@ -41,6 +41,9 @@ int sse8_neon(MpegEncContext *v, const uint8_t *pix1, const uint8_t *pix2,
 int sse4_neon(MpegEncContext *v, const uint8_t *pix1, const uint8_t *pix2,
               ptrdiff_t stride, int h);
 
+int vsad16_neon(MpegEncContext *c, const uint8_t *s1, const uint8_t *s2,
+                ptrdiff_t stride, int h);
+
 av_cold void ff_me_cmp_init_aarch64(MECmpContext *c, AVCodecContext *avctx)
 {
     int cpu_flags = av_get_cpu_flags();
@@ -57,5 +60,7 @@ av_cold void ff_me_cmp_init_aarch64(MECmpContext *c, AVCodecContext *avctx)
         c->sse[0] = sse16_neon;
         c->sse[1] = sse8_neon;
         c->sse[2] = sse4_neon;
+
+        c->vsad[0] = vsad16_neon;
     }
 }
diff --git a/libavcodec/aarch64/me_cmp_neon.S b/libavcodec/aarch64/me_cmp_neon.S
index 4198985c6c..1d0b166d69 100644
--- a/libavcodec/aarch64/me_cmp_neon.S
+++ b/libavcodec/aarch64/me_cmp_neon.S
@@ -584,3 +584,68 @@ function sse4_neon, export=1
 
         ret
 endfunc
+
+function vsad16_neon, export=1
+        // x0           unused
+        // x1           uint8_t *pix1
+        // x2           uint8_t *pix2
+        // x3           ptrdiff_t stride
+        // w4           int h
+
+        ld1             {v0.16b}, [x1], x3              // Load pix1[0], first iteration
+        ld1             {v1.16b}, [x2], x3              // Load pix2[0], first iteration
+
+        sub             w4, w4, #1                      // we need to make h-1 iterations
+        movi            v16.8h, #0
+
+        cmp             w4, #3                          // check if we can make 3 iterations at once
+        usubl           v31.8h, v0.8b, v1.8b            // Signed difference pix1[0] - pix2[0], first iteration
+        usubl2          v30.8h, v0.16b, v1.16b          // Signed difference pix1[0] - pix2[0], first iteration
+
+        b.lt            2f
+
+1:
+        // abs(pix1[0] - pix2[0] - pix1[0 + stride] + pix2[0 + stride])
+        ld1             {v0.16b}, [x1], x3              // Load pix1[0 + stride], first iteration
+        ld1             {v1.16b}, [x2], x3              // Load pix2[0 + stride], first iteration
+        ld1             {v2.16b}, [x1], x3              // Load pix1[0 + stride], second iteration
+        ld1             {v3.16b}, [x2], x3              // Load pix2[0 + stride], second iteration
+        usubl           v29.8h, v0.8b,  v1.8b           // Signed difference pix1[0 + stride] - pix2[0 + stride], first iteration
+        usubl2          v28.8h, v0.16b, v1.16b          // Signed difference pix1[0 + stride] - pix2[0 + stride], first iteration
+        ld1             {v4.16b}, [x1], x3              // Load pix1[0 + stride], third iteration
+        ld1             {v5.16b}, [x2], x3              // Load pix2[0 + stride], third iteration
+        usubl           v27.8h, v2.8b,  v3.8b           // Signed difference pix1[0 + stride] - pix2[0 + stride], second iteration
+        saba            v16.8h, v31.8h, v29.8h          // Signed absolute difference and accumulate the result. first iteration
+        usubl2          v26.8h, v2.16b, v3.16b          // Signed difference pix1[0 + stride] - pix2[0 + stride], second iteration
+        saba            v16.8h, v30.8h, v28.8h          // Signed absolute difference and accumulate the result. first iteration
+        usubl           v25.8h, v4.8b,  v5.8b           // Signed difference pix1[0 + stride] - pix2[0 + stride], third iteration
+        usubl2          v24.8h, v4.16b, v5.16b          // Signed difference pix1[0 + stride] - pix2[0 + stride], third iteration
+        saba            v16.8h, v29.8h, v27.8h          // Signed absolute difference and accumulate the result. second iteration
+        mov             v31.16b, v25.16b
+        saba            v16.8h, v28.8h, v26.8h          // Signed absolute difference and accumulate the result. second iteration
+        sub             w4, w4, #3                      // h -= 3
+        mov             v30.16b, v24.16b
+        saba            v16.8h, v27.8h, v25.8h          // Signed absolute difference and accumulate the result. third iteration
+        cmp             w4, #3
+        saba            v16.8h, v26.8h, v24.8h          // Signed absolute difference and accumulate the result. third iteration
+
+        b.ge            1b
+        cbz             w4, 3f
+2:
+        ld1             {v0.16b}, [x1], x3
+        ld1             {v1.16b}, [x2], x3
+        subs            w4, w4, #1
+        usubl           v29.8h,  v0.8b,   v1.8b
+        usubl2          v28.8h,  v0.16b,  v1.16b
+        saba            v16.8h,  v31.8h,  v29.8h
+        mov             v31.16b, v29.16b
+        saba            v16.8h,  v30.8h,  v28.8h
+        mov             v30.16b, v28.16b
+
+        b.ne            2b
+3:
+        uaddlv          s17, v16.8h
+        fmov            w0, s17
+
+        ret
+endfunc