lavc/aarch64: Add neon implementation for vsse_intra8

Provide optimized implementation for vsse_intra8 for arm64.

Performance tests are shown below.
- vsse_5_c: 87.7
- vsse_5_neon: 26.2

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

Co-authored-by: Martin Storsjö <martin@martin.st>
Signed-off-by: Martin Storsjö <martin@martin.st>

libavcodec/aarch64/me_cmp_init_aarch64.c

@@ -74,6 +74,9 @@ int nsse8_neon_wrapper(MpegEncContext *c, const uint8_t *s1, const uint8_t *s2,
 int vsse8_neon(MpegEncContext *c, const uint8_t *s1, const uint8_t *s2,
                ptrdiff_t stride, int h);
 
+int vsse_intra8_neon(MpegEncContext *c, const uint8_t *s, const uint8_t *dummy,
+                     ptrdiff_t stride, int h);
+
 av_cold void ff_me_cmp_init_aarch64(MECmpContext *c, AVCodecContext *avctx)
 {
     int cpu_flags = av_get_cpu_flags();
@@ -102,6 +105,7 @@ av_cold void ff_me_cmp_init_aarch64(MECmpContext *c, AVCodecContext *avctx)
         c->vsse[1] = vsse8_neon;
 
         c->vsse[4] = vsse_intra16_neon;
+        c->vsse[5] = vsse_intra8_neon;
 
         c->nsse[0] = nsse16_neon_wrapper;
         c->nsse[1] = nsse8_neon_wrapper;

libavcodec/aarch64/me_cmp_neon.S

@@ -1106,6 +1106,59 @@ function vsse_intra16_neon, export=1
         ret
 endfunc
 
+function vsse_intra8_neon, export=1
+        // x0           unused
+        // x1           uint8_t *pix1
+        // x2           uint8_t *dummy
+        // x3           ptrdiff_t stride
+        // w4           int h
+
+        sub             w4, w4, #1 // we need to make h-1 iterations
+        ld1             {v0.8b}, [x1], x3
+        cmp             w4, #3
+        movi            v16.4s, #0
+
+        b.lt            2f
+
+1:
+        // v = abs( pix1[0] - pix1[0 + stride] )
+        // score = sum( v * v )
+        ld1             {v1.8b}, [x1], x3
+        ld1             {v2.8b}, [x1], x3
+        uabd            v30.8b, v0.8b, v1.8b
+        ld1             {v3.8b}, [x1], x3
+        uabd            v27.8b, v1.8b, v2.8b
+        umull           v29.8h, v30.8b, v30.8b
+        uabd            v25.8b, v2.8b, v3.8b
+        umull           v26.8h, v27.8b, v27.8b
+        uadalp          v16.4s, v29.8h
+        umull           v24.8h, v25.8b, v25.8b
+        uadalp          v16.4s, v26.8h
+        sub             w4, w4, #3
+        uadalp          v16.4s, v24.8h
+        cmp             w4, #3
+        mov             v0.8b, v3.8b
+
+        b.ge            1b
+        cbz             w4, 3f
+
+// iterate by one
+2:
+        ld1             {v1.8b}, [x1], x3
+        subs            w4, w4, #1
+        uabd            v30.8b, v0.8b, v1.8b
+        mov             v0.8b, v1.8b
+        umull           v29.8h, v30.8b, v30.8b
+        uadalp          v16.4s, v29.8h
+        cbnz            w4, 2b
+
+3:
+        uaddlv          d17, v16.4s
+        fmov            w0, s17
+
+        ret
+endfunc
+
 function nsse16_neon, export=1
         // x0           multiplier
         // x1           uint8_t *pix1