[FFmpeg-devel] [PATCH 4/5] lavc/aarch64: Add neon implementation for sse8

[Hubert Mazur]

Provide optimized implementation of sse8 function for arm64.

Performance comparison tests are shown below.
- sse_1_c: 130.7
- sse_1_neon: 29.7

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

Signed-off-by: Hubert Mazur <hum at semihalf.com>
---
 libavcodec/aarch64/me_cmp_init_aarch64.c |  4 ++
 libavcodec/aarch64/me_cmp_neon.S         | 66 ++++++++++++++++++++++++
 2 files changed, 70 insertions(+)

diff --git a/libavcodec/aarch64/me_cmp_init_aarch64.c b/libavcodec/aarch64/me_cmp_init_aarch64.c
index 1c36d3d7cb..2f51f0497e 100644
--- a/libavcodec/aarch64/me_cmp_init_aarch64.c
+++ b/libavcodec/aarch64/me_cmp_init_aarch64.c
@@ -34,9 +34,12 @@ int ff_pix_abs16_y2_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 sse8_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)
 {
     int cpu_flags = av_get_cpu_flags();
@@ -49,6 +52,7 @@ 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[1] = sse8_neon;
         c->sse[2] = sse4_neon;
     }
 }
diff --git a/libavcodec/aarch64/me_cmp_neon.S b/libavcodec/aarch64/me_cmp_neon.S
index 0ec9c0465b..3f4266d4d5 100644
--- a/libavcodec/aarch64/me_cmp_neon.S
+++ b/libavcodec/aarch64/me_cmp_neon.S
@@ -347,6 +347,72 @@ function sse16_neon, export=1
         ret
 endfunc
 
+function sse8_neon, export=1
+        // x0 - unused
+        // x1 - pix1
+        // x2 - pix2
+        // x3 - stride
+        // w4 - h
+
+        movi            d18, #0
+        movi            v21.4s, #0
+        movi            v20.4s, #0
+        cmp             w4, #4
+        b.le            2f
+
+// make 4 iterations at once
+1:
+
+        // res = abs(pix1[0] - pix2[0])
+        // res * res
+
+        ld1             {v0.8b}, [x1], x3               // Load pix1 for first iteration
+        ld1             {v1.8b}, [x2], x3               // Load pix2 for second iteration
+        ld1             {v2.8b}, [x1], x3               // Load pix1 for second iteration
+        ld1             {v3.8b}, [x2], x3               // Load pix2 for second iteration
+        uabdl           v30.8h, v0.8b, v1.8b            // Absolute difference, first iteration
+        ld1             {v4.8b}, [x1], x3               // Load pix1 for third iteration
+        ld1             {v5.8b}, [x2], x3               // Load pix2 for third iteration
+        uabdl           v29.8h, v2.8b, v3.8b            // Absolute difference, second iteration
+        umlal           v21.4s, v30.4h, v30.4h          // Multiply lower half, first iteration
+        ld1             {v6.8b}, [x1], x3               // Load pix1 for fourth iteration
+        ld1             {v7.8b}, [x2], x3               // Load pix2 for fourth iteration
+        uabdl           v28.8h, v4.8b, v5.8b            // Absolute difference, third iteration
+        umlal           v21.4s, v29.4h, v29.4h          // Multiply lower half, second iteration
+        umlal2          v20.4s, v30.8h, v30.8h          // Multiply upper half, second iteration
+        uabdl           v27.8h, v6.8b, v7.8b            // Absolute difference, fourth iteration
+        umlal           v21.4s, v28.4h, v28.4h          // Multiply lower half, third iteration
+        umlal2          v20.4s, v29.8h, v29.8h          // Multiply upper half, second iteration
+        sub             w4, w4, #4                      // h -= 4
+        umlal2          v20.4s, v28.8h, v28.8h          // Multiply upper half, third iteration
+        umlal           v21.4s, v27.4h, v27.4h          // Multiply lower half, fourth iteration
+        cmp             w4, #4
+        umlal2          v20.4s, v27.8h, v27.8h          // Multiply upper half, fourth iteration
+        b.ge            1b
+
+        cbz             w4, 3f
+
+// iterate by one
+2:
+        ld1             {v0.8b}, [x1], x3               // Load pix1
+        ld1             {v1.8b}, [x2], x3               // Load pix2
+        subs            w4, w4, #1
+        uabdl           v30.8h, v0.8b, v1.8b
+        umlal           v21.4s, v30.4h, v30.4h
+        umlal2          v20.4s, v30.8h, v30.8h
+
+        b.ne            2b
+
+3:
+        add             v21.4s, v21.4s, v20.4s          // Add accumulator vectors together
+        uaddlv          d17, v21.4s                     // Add up vector
+        add             d18, d18, d17
+
+        fmov            w0, s18
+        ret
+
+endfunc
+
 function sse4_neon, export=1
         // x0 - unused
         // x1 - pix1
-- 
2.34.1