On Mon, 26 Sep 2022, Grzegorz Bernacki wrote:

Provide optimized implementation of vsse8 for arm64.

Performance comparison tests are shown below.
- vsse_1_c: 141.5
- vsse_1_neon: 32.5

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

Signed-off-by: Grzegorz Bernacki <g...@semihalf.com>
---
libavcodec/aarch64/me_cmp_init_aarch64.c |  5 ++
libavcodec/aarch64/me_cmp_neon.S         | 70 ++++++++++++++++++++++++
2 files changed, 75 insertions(+)

diff --git a/libavcodec/aarch64/me_cmp_init_aarch64.c 
b/libavcodec/aarch64/me_cmp_init_aarch64.c
index 2c61cfcf63..f247372c94 100644
--- a/libavcodec/aarch64/me_cmp_init_aarch64.c
+++ b/libavcodec/aarch64/me_cmp_init_aarch64.c
@@ -71,6 +71,9 @@ int nsse8_neon(int multiplier, const uint8_t *s, const 
uint8_t *s2,
int nsse8_neon_wrapper(MpegEncContext *c, const uint8_t *s1, const uint8_t *s2,
                       ptrdiff_t stride, int h);

+int vsse8_neon(MpegEncContext *c, const uint8_t *s1, const uint8_t *s2,
+               ptrdiff_t stride, int h);
+
av_cold void ff_me_cmp_init_aarch64(MECmpContext *c, AVCodecContext *avctx)
{
    int cpu_flags = av_get_cpu_flags();
@@ -96,6 +99,8 @@ av_cold void ff_me_cmp_init_aarch64(MECmpContext *c, 
AVCodecContext *avctx)
        c->vsad[5] = vsad_intra8_neon;

        c->vsse[0] = vsse16_neon;
+        c->vsse[1] = vsse8_neon;
+
        c->vsse[4] = vsse_intra16_neon;

        c->nsse[0] = nsse16_neon_wrapper;
diff --git a/libavcodec/aarch64/me_cmp_neon.S b/libavcodec/aarch64/me_cmp_neon.S
index 6f7c7c1690..386d2de0c5 100644
--- a/libavcodec/aarch64/me_cmp_neon.S
+++ b/libavcodec/aarch64/me_cmp_neon.S
@@ -843,6 +843,76 @@ function vsad16_neon, export=1
        ret
endfunc

+function vsse8_neon, export=1
+        // x0           unused
+        // x1           uint8_t *pix1
+        // x2           uint8_t *pix2
+        // x3           ptrdiff_t stride
+        // w4           int h
+
+        ld1             {v0.8b}, [x1], x3              // Load pix1[0], first 
iteration
+        ld1             {v1.8b}, [x2], x3              // Load pix2[0], first 
iteration
+
+        sub             w4, w4, #1                      // we need to make h-1 
iterations
+        movi            v16.4s, #0
+        movi            v17.4s, #0
+
+        cmp             w4, #3                          // check if we can 
make 3 iterations at once
+        usubl           v31.8h, v0.8b, v1.8b            // Signed difference 
of pix1[0] - pix2[0], first iteration
+        b.le            2f

Why the b.le here, shouldn't it be enough with b.lt? If we're run with h=<unroll amount>, it should be enough to run one round in the unrolled loop.

I see that we've got the same issue in a couple preexisting functions; I'll send a patch to fix that.

Other than that, this looks reasonable to me.

// Martin

_______________________________________________
ffmpeg-devel mailing list
ffmpeg-devel@ffmpeg.org
https://ffmpeg.org/mailman/listinfo/ffmpeg-devel

To unsubscribe, visit link above, or email
ffmpeg-devel-requ...@ffmpeg.org with subject "unsubscribe".

Reply via email to