[FFmpeg-devel] [PATCH 2/3] lavc/aarch64: Add neon implementation for vsad8_intra

[Hubert Mazur]

Provide optimized implementation for vsad8_intra function.

Performance comparison tests are shown below.
- vsad_5_c: 94.7
- vsad_5_neon: 20.7

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 |  3 ++
 libavcodec/aarch64/me_cmp_neon.S         | 42 ++++++++++++++++++++++++
 2 files changed, 45 insertions(+)

diff --git a/libavcodec/aarch64/me_cmp_init_aarch64.c b/libavcodec/aarch64/me_cmp_init_aarch64.c
index fb51a833be..d3fa047a86 100644
--- a/libavcodec/aarch64/me_cmp_init_aarch64.c
+++ b/libavcodec/aarch64/me_cmp_init_aarch64.c
@@ -45,6 +45,8 @@ int vsad16_neon(MpegEncContext *c, const uint8_t *s1, const uint8_t *s2,
                 ptrdiff_t stride, int h);
 int vsad_intra16_neon(MpegEncContext *c, const uint8_t *s, const uint8_t *dummy,
                       ptrdiff_t stride, int h) ;
+int vsad_intra8_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,
@@ -75,6 +77,7 @@ av_cold void ff_me_cmp_init_aarch64(MECmpContext *c, AVCodecContext *avctx)
 
         c->vsad[0] = vsad16_neon;
         c->vsad[4] = vsad_intra16_neon;
+        c->vsad[5] = vsad_intra8_neon;
 
         c->vsse[0] = vsse16_neon;
         c->vsse[4] = vsse_intra16_neon;
diff --git a/libavcodec/aarch64/me_cmp_neon.S b/libavcodec/aarch64/me_cmp_neon.S
index 1e08d04869..1587f2ea43 100644
--- a/libavcodec/aarch64/me_cmp_neon.S
+++ b/libavcodec/aarch64/me_cmp_neon.S
@@ -1047,3 +1047,45 @@ function pix_median_abs16_neon, export=1
         ret
 
 endfunc
+
+function vsad_intra8_neon, export=1
+        // x0           unused
+        // x1           uint8_t *pix1
+        // x2           uint8_t *dummy
+        // x3           ptrdiff_t stride
+        // w4           int h
+
+        ld1             {v0.8b}, [x1], x3
+        sub             w4, w4, #1 // we need to make h-1 iterations
+        cmp             w4, #3
+        movi            v16.8h, #0
+        b.lt            2f
+
+1:
+        // v = abs( pix1[0] - pix1[0 + stride] )
+        // score = sum(v)
+        ld1             {v1.8b}, [x1], x3
+        sub             w4, w4, #3
+        ld1             {v2.8b}, [x1], x3
+        uabal           v16.8h, v0.8b, v1.8b
+        ld1             {v3.8b}, [x1], x3
+        uabal           v16.8h, v1.8b, v2.8b
+        cmp             w4, #3
+        mov             v0.8b, v3.8b
+        uabal           v16.8h, v2.8b, v3.8b
+        b.ge            1b
+        cbz             w4, 3f
+
+2:
+        ld1             {v1.8b}, [x1], x3
+        subs            w4, w4, #1
+        uabal           v16.8h, v0.8b, v1.8b
+        mov             v0.8b, v1.8b
+        cbnz            w4, 2b
+
+3:
+        uaddlv          s17, v16.8h
+        fmov            w0, s17
+
+        ret
+endfunc
-- 
2.34.1