On Mon, 25 Jul 2022, Hubert Mazur wrote:
Provide optimized implementation of pix_abs8 function for arm64.
Performance comparison tests are shown below.
- pix_abs_1_0_c: 105.2
- pix_abs_1_0_neon: 21.4
- sad_1_c: 107.2
- sad_1_neon: 20.9
Benchmarks and tests are run with checkasm tool on AWS Graviton 3.
---
libavcodec/aarch64/me_cmp_init_aarch64.c | 4 ++
libavcodec/aarch64/me_cmp_neon.S | 53 ++++++++++++++++++++++++
2 files changed, 57 insertions(+)
diff --git a/libavcodec/aarch64/me_cmp_init_aarch64.c
b/libavcodec/aarch64/me_cmp_init_aarch64.c
index 89c817990c..7d7dc38754 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, uint8_t *pix1,
uint8_t *pix2,
ptrdiff_t stride, int h);
int ff_pix_abs16_y2_neon(MpegEncContext *v, uint8_t *pix1, uint8_t *pix2,
ptrdiff_t stride, int h);
+int ff_pix_abs8_neon(MpegEncContext *s, uint8_t *blk1, uint8_t *blk2,
+ ptrdiff_t stride, int h);
int sse16_neon(MpegEncContext *v, uint8_t *pix1, 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 dcaffc9b73..f2dd63ced1 100644
--- a/libavcodec/aarch64/me_cmp_neon.S
+++ b/libavcodec/aarch64/me_cmp_neon.S
@@ -72,6 +72,59 @@ 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
+ // x4 int h
+
+ movi d18, #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
+ uabdl v30.8h, v0.8b, v1.8b // Absolute
difference, first iteration
+ ld1 {v2.8b}, [x1], x3 // Load pix1 for
second iteration
+ ld1 {v3.8b}, [x2], x3 // Load pix2 for
second iteration
+ uabal v30.8h, v2.8b, v3.8b // Absolute
difference, second iteration
+ ld1 {v4.8b}, [x1], x3 // Load pix1 for third
iteration
+ ld1 {v5.8b}, [x2], x3 // Load pix2 for third
iteration
+ uabal v30.8h, v4.8b, v5.8b // Absolute
difference, third iteration
+ ld1 {v6.8b}, [x1], x3 // Load pix1 for
foruth iteration
+ ld1 {v7.8b}, [x2], x3 // Load pix2 for
fourth iteration
+ uabal v30.8h, v6.8b, v7.8b // Absolute
difference, foruth iteration
This is maybe the simplest example so far, where the unrolled version here
just is 4 identical serial copies of the same set of 3 instructions; this
maybe helps a bit on some CPUs, but it doesn't help nearly as much as it
can on others, if it would be better unrolled.
I.e., same comments as for the other patches; improve interleaving, don't
do uaddlv once per iteration.
// 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".