lavc/aarch64: Add neon implementation for sse4

Provide neon implementation for sse4 function.

Performance comparison tests are shown below.
- sse_2_c: 80.7
- sse_2_neon: 31.0

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

@@ -32,6 +32,8 @@ int ff_pix_abs16_x2_neon(MpegEncContext *v, const uint8_t *pix1, const uint8_t *
 
 int sse16_neon(MpegEncContext *v, const uint8_t *pix1, const uint8_t *pix2,
                ptrdiff_t stride, int h);
+int sse4_neon(MpegEncContext *v, const uint8_t *pix1, const uint8_t *pix2,
+              ptrdiff_t stride, int h);
 
 av_cold void ff_me_cmp_init_aarch64(MECmpContext *c, AVCodecContext *avctx)
 {
@@ -44,5 +46,6 @@ av_cold void ff_me_cmp_init_aarch64(MECmpContext *c, AVCodecContext *avctx)
 
         c->sad[0] = ff_pix_abs16_neon;
         c->sse[0] = sse16_neon;
+        c->sse[2] = sse4_neon;
     }
 }

libavcodec/aarch64/me_cmp_neon.S

@@ -344,3 +344,59 @@ function sse16_neon, export=1
 
         ret
 endfunc
+
+function sse4_neon, export=1
+        // x0 - unused
+        // x1 - pix1
+        // x2 - pix2
+        // x3 - stride
+        // w4 - h
+
+        movi            v16.4s, #0                      // clear the result accumulator
+        cmp             w4, #4
+        b.le            2f
+
+// make 4 iterations at once
+1:
+
+        // res = abs(pix1[0] - pix2[0])
+        // res * res
+
+        ld1             {v0.s}[0], [x1], x3             // Load pix1, first iteration
+        ld1             {v1.s}[0], [x2], x3             // Load pix2, first iteration
+        ld1             {v2.s}[0], [x1], x3             // Load pix1, second iteration
+        ld1             {v3.s}[0], [x2], x3             // Load pix2, second iteration
+        uabdl           v30.8h, v0.8b, v1.8b            // Absolute difference, first iteration
+        ld1             {v4.s}[0], [x1], x3             // Load pix1, third iteration
+        ld1             {v5.s}[0], [x2], x3             // Load pix2, third iteration
+        uabdl           v29.8h, v2.8b, v3.8b            // Absolute difference, second iteration
+        umlal           v16.4s, v30.4h, v30.4h          // Multiply vectors, first iteration
+        ld1             {v6.s}[0], [x1], x3             // Load pix1, fourth iteration
+        ld1             {v7.s}[0], [x2], x3             // Load pix2, fourth iteration
+        uabdl           v28.8h, v4.8b, v5.8b            // Absolute difference, third iteration
+        umlal           v16.4s, v29.4h, v29.4h          // Multiply and accumulate, second iteration
+        sub             w4, w4, #4
+        uabdl           v27.8h, v6.8b, v7.8b            // Absolue difference, fourth iteration
+        umlal           v16.4s, v28.4h, v28.4h          // Multiply and accumulate, third iteration
+        cmp             w4, #4
+        umlal           v16.4s, v27.4h, v27.4h          // Multiply and accumulate, fourth iteration
+        b.ge            1b
+
+        cbz             w4, 3f
+
+// iterate by one
+2:
+        ld1             {v0.s}[0], [x1], x3               // Load pix1
+        ld1             {v1.s}[0], [x2], x3               // Load pix2
+        uabdl           v30.8h, v0.8b, v1.8b
+        subs            w4, w4, #1
+        umlal           v16.4s, v30.4h, v30.4h
+
+        b.ne            2b
+
+3:
+        uaddlv          d17, v16.4s                     // Add vector
+        fmov            w0, s17
+
+        ret
+endfunc