[FFmpeg-cvslog] lavc/aarch64: Add neon implementation for pix_abs8

[Hubert Mazur]

ffmpeg | branch: master | Hubert Mazur <hum at semihalf.com> | Tue Aug 16 14:20:16 2022 +0200| [70efa4d01188b61efc0b82e7241a59a32c7e2e22] | committer: Martin Storsjö

lavc/aarch64: Add neon implementation for pix_abs8

Provide optimized implementation of pix_abs8 function for arm64.

Performance comparison tests are shown below.
- pix_abs_1_0_c: 101.2
- pix_abs_1_0_neon: 22.5
- sad_1_c: 101.2
- sad_1_neon: 22.5

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

Signed-off-by: Martin Storsjö <martin at martin.st>

> http://git.videolan.org/gitweb.cgi/ffmpeg.git/?a=commit;h=70efa4d01188b61efc0b82e7241a59a32c7e2e22
---

 libavcodec/aarch64/me_cmp_init_aarch64.c |  4 +++
 libavcodec/aarch64/me_cmp_neon.S         | 47 ++++++++++++++++++++++++++++++++
 2 files changed, 51 insertions(+)

diff --git a/libavcodec/aarch64/me_cmp_init_aarch64.c b/libavcodec/aarch64/me_cmp_init_aarch64.c
index 7c03ce8c50..fb7c3f5059 100644
--- a/libavcodec/aarch64/me_cmp_init_aarch64.c
+++ b/libavcodec/aarch64/me_cmp_init_aarch64.c
@@ -31,6 +31,8 @@ int ff_pix_abs16_x2_neon(MpegEncContext *v, const uint8_t *pix1, const uint8_t *
                          ptrdiff_t stride, int h);
 int ff_pix_abs16_y2_neon(MpegEncContext *v, const uint8_t *pix1, const uint8_t *pix2,
                          ptrdiff_t stride, int h);
+int ff_pix_abs8_neon(MpegEncContext *s, const uint8_t *blk1, const uint8_t *blk2,
+                     ptrdiff_t stride, int h);
 
 int sse16_neon(MpegEncContext *v, const uint8_t *pix1, const uint8_t *pix2,
                ptrdiff_t stride, int h);
@@ -48,8 +50,10 @@ av_cold void ff_me_cmp_init_aarch64(MECmpContext *c, AVCodecContext *avctx)
         c->pix_abs[0][1] = ff_pix_abs16_x2_neon;
         c->pix_abs[0][2] = ff_pix_abs16_y2_neon;
         c->pix_abs[0][3] = ff_pix_abs16_xy2_neon;
+        c->pix_abs[1][0] = ff_pix_abs8_neon;
 
         c->sad[0] = ff_pix_abs16_neon;
+        c->sad[1] = ff_pix_abs8_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 c0647c49e9..b89c25438e 100644
--- a/libavcodec/aarch64/me_cmp_neon.S
+++ b/libavcodec/aarch64/me_cmp_neon.S
@@ -72,6 +72,53 @@ function ff_pix_abs16_neon, export=1
         ret
 endfunc
 
+function ff_pix_abs8_neon, export=1
+        // x0           unused
+        // x1           uint8_t *pix1
+        // x2           uint8_t *pix2
+        // x3           ptrdiff_t stride
+        // w4           int h
+
+        movi            v30.8h, #0
+        cmp             w4, #4
+        b.lt            2f
+
+// make 4 iterations at once
+1:
+        ld1             {v0.8b}, [x1], x3               // Load pix1 for first iteration
+        ld1             {v1.8b}, [x2], x3               // Load pix2 for first iteration
+        ld1             {v2.8b}, [x1], x3               // Load pix1 for second iteration
+        uabal           v30.8h, v0.8b, v1.8b            // Absolute difference, first iteration
+        ld1             {v3.8b}, [x2], x3               // Load pix2 for second iteration
+        ld1             {v4.8b}, [x1], x3               // Load pix1 for third iteration
+        uabal           v30.8h, v2.8b, v3.8b            // Absolute difference, second iteration
+        ld1             {v5.8b}, [x2], x3               // Load pix2 for third iteration
+        sub             w4, w4, #4                      // h -= 4
+        ld1             {v6.8b}, [x1], x3               // Load pix1 for foruth iteration
+        ld1             {v7.8b}, [x2], x3               // Load pix2 for fourth iteration
+        uabal           v30.8h, v4.8b, v5.8b            // Absolute difference, third iteration
+        cmp             w4, #4
+        uabal           v30.8h, v6.8b, v7.8b            // Absolute difference, foruth 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
+        uabal           v30.8h, v0.8b, v1.8b
+        b.ne            2b
+
+3:
+        uaddlv          s20, v30.8h                     // Add up vector
+        fmov            w0, s20
+
+        ret
+endfunc
+
 function ff_pix_abs16_xy2_neon, export=1
         // x0           unused
         // x1           uint8_t *pix1