On Mon, 22 Aug 2022, Hubert Mazur wrote:
Provide optimized implementation of vsse16 for arm64.
Performance comparison tests are shown below.
- vsse_0_c: 254.4
- vsse_0_neon: 64.7
Benchmarks and tests are run with checkasm tool on AWS Graviton 3.
Signed-off-by: Hubert Mazur <[email protected]>
---
libavcodec/aarch64/me_cmp_init_aarch64.c | 4 +
libavcodec/aarch64/me_cmp_neon.S | 97 ++++++++++++++++++++++++
2 files changed, 101 insertions(+)
diff --git a/libavcodec/aarch64/me_cmp_init_aarch64.c
b/libavcodec/aarch64/me_cmp_init_aarch64.c
index ddc5d05611..7b81e48d16 100644
--- a/libavcodec/aarch64/me_cmp_init_aarch64.c
+++ b/libavcodec/aarch64/me_cmp_init_aarch64.c
@@ -43,6 +43,8 @@ int sse4_neon(MpegEncContext *v, const uint8_t *pix1, const
uint8_t *pix2,
int vsad16_neon(MpegEncContext *c, const uint8_t *s1, const uint8_t *s2,
ptrdiff_t stride, int h);
+int vsse16_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)
{
@@ -62,5 +64,7 @@ av_cold void ff_me_cmp_init_aarch64(MECmpContext *c,
AVCodecContext *avctx)
c->sse[2] = sse4_neon;
c->vsad[0] = vsad16_neon;
+
+ c->vsse[0] = vsse16_neon;
}
}
diff --git a/libavcodec/aarch64/me_cmp_neon.S b/libavcodec/aarch64/me_cmp_neon.S
index d4c0099854..279bae7cb5 100644
--- a/libavcodec/aarch64/me_cmp_neon.S
+++ b/libavcodec/aarch64/me_cmp_neon.S
@@ -659,3 +659,100 @@ function vsad16_neon, export=1
ret
endfunc
+
+function vsse16_neon, export=1
+ // x0 unused
+ // x1 uint8_t *pix1
+ // x2 uint8_t *pix2
+ // x3 ptrdiff_t stride
+ // w4 int h
+
+ movi v30.4s, #0
+ movi v29.4s, #0
+
+ add x5, x1, x3 // pix1 + stride
+ add x6, x2, x3 // pix2 + stride
+ sub w4, w4, #1 // we need to make h-1
iterations
+ cmp w4, #3 // check if we can
make 4 iterations at once
+ b.le 2f
+
+// make 4 iterations at once
The comments seem to talk about 4 iterations at once while the code
actually only does 3.
+1:
+ // x = abs(pix1[0] - pix2[0] - pix1[0 + stride] + pix2[0 + stride]) =
The comment seems a bit un-updated here, since there's no abs() involved
here
+ // res = (x) * (x)
+ ld1 {v0.16b}, [x1], x3 // Load pix1[0], first
iteration
+ ld1 {v1.16b}, [x2], x3 // Load pix2[0], first
iteration
+ ld1 {v2.16b}, [x5], x3 // Load pix1[0 +
stride], first iteration
+ usubl v28.8h, v0.8b, v1.8b // Signed difference
of pix1[0] - pix2[0], first iteration
+ ld1 {v3.16b}, [x6], x3 // Load pix2[0 +
stride], first iteration
+ usubl2 v27.8h, v0.16b, v1.16b // Signed difference
of pix1[0] - pix2[0], first iteration
+ usubl v26.8h, v3.8b, v2.8b // Signed difference
of pix1[0 + stride] - pix2[0 + stride], first iteration
+ usubl2 v25.8h, v3.16b, v2.16b // Signed difference
of pix1[0 + stride] - pix2[0 + stride], first iteration
Same thing about reusing data from the previous row, as for the previous
patch.
// Martin
_______________________________________________
ffmpeg-devel mailing list
[email protected]
https://ffmpeg.org/mailman/listinfo/ffmpeg-devel
To unsubscribe, visit link above, or email
[email protected] with subject "unsubscribe".
