lavc/aarch64: Add neon implementation for vsse_intra16

Provide optimized implementation for vsse_intra16 for arm64.

Performance tests are shown below.
- vsse_4_c: 155.2
- vsse_4_neon: 36.2

Benchmarks and tests are run with checkasm tool on AWS Graviton 3.
Signed-off-by: Hubert Mazur <hum@semihalf.com>
Signed-off-by: Martin Storsjö <martin@martin.st>

libavcodec/aarch64/me_cmp_init_aarch64.c

@@ -47,6 +47,8 @@ int vsad_intra16_neon(MpegEncContext *c, const uint8_t *s, const uint8_t *dummy,
                       ptrdiff_t stride, int h) ;
 int vsse16_neon(MpegEncContext *c, const uint8_t *s1, const uint8_t *s2,
                 ptrdiff_t stride, int h);
+int vsse_intra16_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)
 {
@@ -69,5 +71,6 @@ av_cold void ff_me_cmp_init_aarch64(MECmpContext *c, AVCodecContext *avctx)
         c->vsad[4] = vsad_intra16_neon;
 
         c->vsse[0] = vsse16_neon;
+        c->vsse[4] = vsse_intra16_neon;
     }
 }

libavcodec/aarch64/me_cmp_neon.S

@@ -784,3 +784,66 @@ function vsad_intra16_neon, export=1
 
         ret
 endfunc
+
+function vsse_intra16_neon, export=1
+        // x0           unused
+        // x1           uint8_t *pix1
+        // x2           uint8_t *dummy
+        // x3           ptrdiff_t stride
+        // w4           int h
+
+        ld1             {v0.16b}, [x1], x3
+        movi            v16.4s, #0
+        movi            v17.4s, #0
+
+        sub             w4, w4, #1 // we need to make h-1 iterations
+        cmp             w4, #3
+        b.lt            2f
+
+1:
+        // v = abs( pix1[0] - pix1[0 + stride] )
+        // score = sum( v * v )
+        ld1             {v1.16b}, [x1], x3
+        ld1             {v2.16b}, [x1], x3
+        uabd            v30.16b, v0.16b, v1.16b
+        ld1             {v3.16b}, [x1], x3
+        umull           v29.8h, v30.8b, v30.8b
+        umull2          v28.8h, v30.16b, v30.16b
+        uabd            v27.16b, v1.16b, v2.16b
+        uadalp          v16.4s, v29.8h
+        umull           v26.8h, v27.8b, v27.8b
+        umull2          v27.8h, v27.16b, v27.16b
+        uadalp          v17.4s, v28.8h
+        uabd            v25.16b, v2.16b, v3.16b
+        uadalp          v16.4s, v26.8h
+        umull           v24.8h, v25.8b, v25.8b
+        umull2          v25.8h, v25.16b, v25.16b
+        uadalp          v17.4s, v27.8h
+        sub             w4, w4, #3
+        uadalp          v16.4s, v24.8h
+        cmp             w4, #3
+        uadalp          v17.4s, v25.8h
+        mov             v0.16b, v3.16b
+
+        b.ge            1b
+        cbz             w4, 3f
+
+// iterate by one
+2:
+        ld1             {v1.16b}, [x1], x3
+        subs            w4, w4, #1
+        uabd            v30.16b, v0.16b, v1.16b
+        mov             v0.16b, v1.16b
+        umull           v29.8h, v30.8b, v30.8b
+        umull2          v30.8h, v30.16b, v30.16b
+        uadalp          v16.4s, v29.8h
+        uadalp          v17.4s, v30.8h
+        cbnz            w4, 2b
+
+3:
+        add             v16.4s, v16.4s, v17.4S
+        uaddlv          d17, v16.4s
+        fmov            w0, s17
+
+        ret
+endfunc