lavc/aarch64: Add neon implementation for sse16

Provide neon implementation for sse16 function.

Performance comparison tests are shown below.
- sse_0_c: 268.2
- sse_0_neon: 43.5

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

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

2 files changed, 78 insertions, 0 deletions

diff --git a/libavcodec/aarch64/me_cmp_init_aarch64.c b/libavcodec/aarch64/me_cmp_init_aarch64.c
index dfb9583320..ab2a1909ba 100644
--- a/libavcodec/aarch64/me_cmp_init_aarch64.c
+++ b/libavcodec/aarch64/me_cmp_init_aarch64.c
@@ -30,6 +30,9 @@ int ff_pix_abs16_xy2_neon(MpegEncContext *s, const uint8_t *blk1, const uint8_t
 int ff_pix_abs16_x2_neon(MpegEncContext *v, const uint8_t *pix1, const uint8_t *pix2,
                          ptrdiff_t stride, int h);
 
+int sse16_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)
 {
     int cpu_flags = av_get_cpu_flags();
@@ -40,5 +43,6 @@ av_cold void ff_me_cmp_init_aarch64(MECmpContext *c, AVCodecContext *avctx)
         c->pix_abs[0][3] = ff_pix_abs16_xy2_neon;
 
         c->sad[0] = ff_pix_abs16_neon;
+        c->sse[0] = sse16_neon;
     }
 }
diff --git a/libavcodec/aarch64/me_cmp_neon.S b/libavcodec/aarch64/me_cmp_neon.S
index cda7ce0408..b98b2b7e03 100644
--- a/libavcodec/aarch64/me_cmp_neon.S
+++ b/libavcodec/aarch64/me_cmp_neon.S
@@ -270,3 +270,77 @@ function ff_pix_abs16_x2_neon, export=1
 
         ret
 endfunc
+
+function sse16_neon, export=1
+        // x0 - unused
+        // x1 - pix1
+        // x2 - pix2
+        // x3 - stride
+        // w4 - h
+
+        cmp             w4, #4
+        movi            v17.4s, #0
+        b.lt            2f
+
+// Make 4 iterations at once
+1:
+
+        // res = abs(pix1[0] - pix2[0])
+        // res * res
+
+        ld1             {v0.16b}, [x1], x3              // Load pix1 vector for first iteration
+        ld1             {v1.16b}, [x2], x3              // Load pix2 vector for first iteration
+        ld1             {v2.16b}, [x1], x3              // Load pix1 vector for second iteration
+        uabd            v30.16b, v0.16b, v1.16b         // Absolute difference, first iteration
+        ld1             {v3.16b}, [x2], x3              // Load pix2 vector for second iteration
+        umull           v29.8h, v30.8b, v30.8b          // Multiply lower half of vectors, first iteration
+        umull2          v28.8h, v30.16b, v30.16b        // Multiply upper half of vectors, first iteration
+        uabd            v27.16b, v2.16b, v3.16b         // Absolute difference, second iteration
+        uadalp          v17.4s, v29.8h                  // Pairwise add, first iteration
+        ld1             {v4.16b}, [x1], x3              // Load pix1 for third iteration
+        umull           v26.8h, v27.8b, v27.8b          // Mulitply lower half, second iteration
+        umull2          v25.8h, v27.16b, v27.16b        // Multiply upper half, second iteration
+        ld1             {v5.16b}, [x2], x3              // Load pix2 for third iteration
+        uadalp          v17.4s, v26.8h                  // Pairwise add and accumulate, second iteration
+        uabd            v24.16b, v4.16b, v5.16b         // Absolute difference, third iteration
+        ld1             {v6.16b}, [x1], x3              // Load pix1 for fourth iteration
+        uadalp          v17.4s, v25.8h                  // Pairwise add and accumulate, second iteration
+        umull           v23.8h, v24.8b, v24.8b          // Multiply lower half, third iteration
+        umull2          v22.8h, v24.16b, v24.16b        // Multiply upper half, third iteration
+        uadalp          v17.4s, v23.8h                  // Pairwise add and accumulate, third iteration
+        ld1             {v7.16b}, [x2], x3              // Load pix2 for fouth iteration
+        uadalp          v17.4s, v22.8h                  // Pairwise add and accumulate, third iteration
+        uabd            v21.16b, v6.16b, v7.16b         // Absolute difference, fourth iteration
+        uadalp          v17.4s, v28.8h                  // Pairwise add and accumulate, first iteration
+        umull           v20.8h, v21.8b, v21.8b          // Multiply lower half, fourth iteration
+        sub             w4, w4, #4                      // h -= 4
+        umull2          v19.8h, v21.16b, v21.16b        // Multiply upper half, fourth iteration
+        uadalp          v17.4s, v20.8h                  // Pairwise add and accumulate, fourth iteration
+        cmp             w4, #4
+        uadalp          v17.4s, v19.8h                  // Pairwise add and accumulate, fourth iteration
+        b.ge            1b
+
+        cbz             w4, 3f
+
+// iterate by one
+2:
+
+        ld1             {v0.16b}, [x1], x3              // Load pix1
+        ld1             {v1.16b}, [x2], x3              // Load pix2
+
+        uabd            v30.16b, v0.16b, v1.16b
+        umull           v29.8h, v30.8b, v30.8b
+        umull2          v28.8h, v30.16b, v30.16b
+        uadalp          v17.4s, v29.8h
+        subs            w4, w4, #1
+        uadalp          v17.4s, v28.8h
+
+        b.ne            2b
+
+3:
+        uaddlv          d16, v17.4s                     // add up accumulator vector
+
+        fmov            w0, s16
+
+        ret
+endfunc