* [FFmpeg-devel] [PATCH 0/5] Provide optimized neon implementation
@ 2022-09-06 10:27 Hubert Mazur
2022-09-06 10:27 ` [FFmpeg-devel] [PATCH 1/5] lavc/aarch64: Add neon implementation for vsad16 Hubert Mazur
` (5 more replies)
0 siblings, 6 replies; 13+ messages in thread
From: Hubert Mazur @ 2022-09-06 10:27 UTC (permalink / raw)
To: ffmpeg-devel; +Cc: gjb, upstream, jswinney, Hubert Mazur, martin, mw, spop
Provide optimized implementations for me_cmp functions.
This set of patches fixes all issues addressed in previous review.
Major changes:
- Remove redundant loads since the data can be reused.
- Improve style.
- Fix issues with unrecognized symbols.
Hubert Mazur (5):
lavc/aarch64: Add neon implementation for vsad16
lavc/aarch64: Add neon implementation of vsse16
lavc/aarch64: Add neon implementation for vsad_intra16
lavc/aarch64: Add neon implementation for vsse_intra16
lavc/aarch64: Provide neon implementation of nsse16
libavcodec/aarch64/me_cmp_init_aarch64.c | 30 ++
libavcodec/aarch64/me_cmp_neon.S | 387 +++++++++++++++++++++++
2 files changed, 417 insertions(+)
--
2.34.1
_______________________________________________
ffmpeg-devel mailing list
ffmpeg-devel@ffmpeg.org
https://ffmpeg.org/mailman/listinfo/ffmpeg-devel
To unsubscribe, visit link above, or email
ffmpeg-devel-request@ffmpeg.org with subject "unsubscribe".
^ permalink raw reply [flat|nested] 13+ messages in thread
* [FFmpeg-devel] [PATCH 1/5] lavc/aarch64: Add neon implementation for vsad16
2022-09-06 10:27 [FFmpeg-devel] [PATCH 0/5] Provide optimized neon implementation Hubert Mazur
@ 2022-09-06 10:27 ` Hubert Mazur
2022-09-06 10:27 ` [FFmpeg-devel] [PATCH 2/5] lavc/aarch64: Add neon implementation of vsse16 Hubert Mazur
` (4 subsequent siblings)
5 siblings, 0 replies; 13+ messages in thread
From: Hubert Mazur @ 2022-09-06 10:27 UTC (permalink / raw)
To: ffmpeg-devel; +Cc: gjb, upstream, jswinney, Hubert Mazur, martin, mw, spop
Provide optimized implementation of vsad16 function for arm64.
Performance comparison tests are shown below.
- vsad_0_c: 285.0
- vsad_0_neon: 42.5
Benchmarks and tests are run with checkasm tool on AWS Graviton 3.
Co-authored-by: Martin Storsjö <martin@martin.st>
Signed-off-by: Hubert Mazur <hum@semihalf.com>
---
libavcodec/aarch64/me_cmp_init_aarch64.c | 5 ++
libavcodec/aarch64/me_cmp_neon.S | 65 ++++++++++++++++++++++++
2 files changed, 70 insertions(+)
diff --git a/libavcodec/aarch64/me_cmp_init_aarch64.c b/libavcodec/aarch64/me_cmp_init_aarch64.c
index fb7c3f5059..ddc5d05611 100644
--- a/libavcodec/aarch64/me_cmp_init_aarch64.c
+++ b/libavcodec/aarch64/me_cmp_init_aarch64.c
@@ -41,6 +41,9 @@ int sse8_neon(MpegEncContext *v, const uint8_t *pix1, const uint8_t *pix2,
int sse4_neon(MpegEncContext *v, const uint8_t *pix1, const uint8_t *pix2,
ptrdiff_t stride, int h);
+int vsad16_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();
@@ -57,5 +60,7 @@ av_cold void ff_me_cmp_init_aarch64(MECmpContext *c, AVCodecContext *avctx)
c->sse[0] = sse16_neon;
c->sse[1] = sse8_neon;
c->sse[2] = sse4_neon;
+
+ c->vsad[0] = vsad16_neon;
}
}
diff --git a/libavcodec/aarch64/me_cmp_neon.S b/libavcodec/aarch64/me_cmp_neon.S
index 4198985c6c..1d0b166d69 100644
--- a/libavcodec/aarch64/me_cmp_neon.S
+++ b/libavcodec/aarch64/me_cmp_neon.S
@@ -584,3 +584,68 @@ function sse4_neon, export=1
ret
endfunc
+
+function vsad16_neon, export=1
+ // x0 unused
+ // x1 uint8_t *pix1
+ // x2 uint8_t *pix2
+ // x3 ptrdiff_t stride
+ // w4 int h
+
+ ld1 {v0.16b}, [x1], x3 // Load pix1[0], first iteration
+ ld1 {v1.16b}, [x2], x3 // Load pix2[0], first iteration
+
+ sub w4, w4, #1 // we need to make h-1 iterations
+ movi v16.8h, #0
+
+ cmp w4, #3 // check if we can make 3 iterations at once
+ usubl v31.8h, v0.8b, v1.8b // Signed difference pix1[0] - pix2[0], first iteration
+ usubl2 v30.8h, v0.16b, v1.16b // Signed difference pix1[0] - pix2[0], first iteration
+
+ b.lt 2f
+
+1:
+ // abs(pix1[0] - pix2[0] - pix1[0 + stride] + pix2[0 + stride])
+ ld1 {v0.16b}, [x1], x3 // Load pix1[0 + stride], first iteration
+ ld1 {v1.16b}, [x2], x3 // Load pix2[0 + stride], first iteration
+ ld1 {v2.16b}, [x1], x3 // Load pix1[0 + stride], second iteration
+ ld1 {v3.16b}, [x2], x3 // Load pix2[0 + stride], second iteration
+ usubl v29.8h, v0.8b, v1.8b // Signed difference pix1[0 + stride] - pix2[0 + stride], first iteration
+ usubl2 v28.8h, v0.16b, v1.16b // Signed difference pix1[0 + stride] - pix2[0 + stride], first iteration
+ ld1 {v4.16b}, [x1], x3 // Load pix1[0 + stride], third iteration
+ ld1 {v5.16b}, [x2], x3 // Load pix2[0 + stride], third iteration
+ usubl v27.8h, v2.8b, v3.8b // Signed difference pix1[0 + stride] - pix2[0 + stride], second iteration
+ saba v16.8h, v31.8h, v29.8h // Signed absolute difference and accumulate the result. first iteration
+ usubl2 v26.8h, v2.16b, v3.16b // Signed difference pix1[0 + stride] - pix2[0 + stride], second iteration
+ saba v16.8h, v30.8h, v28.8h // Signed absolute difference and accumulate the result. first iteration
+ usubl v25.8h, v4.8b, v5.8b // Signed difference pix1[0 + stride] - pix2[0 + stride], third iteration
+ usubl2 v24.8h, v4.16b, v5.16b // Signed difference pix1[0 + stride] - pix2[0 + stride], third iteration
+ saba v16.8h, v29.8h, v27.8h // Signed absolute difference and accumulate the result. second iteration
+ mov v31.16b, v25.16b
+ saba v16.8h, v28.8h, v26.8h // Signed absolute difference and accumulate the result. second iteration
+ sub w4, w4, #3 // h -= 3
+ mov v30.16b, v24.16b
+ saba v16.8h, v27.8h, v25.8h // Signed absolute difference and accumulate the result. third iteration
+ cmp w4, #3
+ saba v16.8h, v26.8h, v24.8h // Signed absolute difference and accumulate the result. third iteration
+
+ b.ge 1b
+ cbz w4, 3f
+2:
+ ld1 {v0.16b}, [x1], x3
+ ld1 {v1.16b}, [x2], x3
+ subs w4, w4, #1
+ usubl v29.8h, v0.8b, v1.8b
+ usubl2 v28.8h, v0.16b, v1.16b
+ saba v16.8h, v31.8h, v29.8h
+ mov v31.16b, v29.16b
+ saba v16.8h, v30.8h, v28.8h
+ mov v30.16b, v28.16b
+
+ b.ne 2b
+3:
+ uaddlv s17, v16.8h
+ fmov w0, s17
+
+ ret
+endfunc
--
2.34.1
_______________________________________________
ffmpeg-devel mailing list
ffmpeg-devel@ffmpeg.org
https://ffmpeg.org/mailman/listinfo/ffmpeg-devel
To unsubscribe, visit link above, or email
ffmpeg-devel-request@ffmpeg.org with subject "unsubscribe".
^ permalink raw reply [flat|nested] 13+ messages in thread
* [FFmpeg-devel] [PATCH 2/5] lavc/aarch64: Add neon implementation of vsse16
2022-09-06 10:27 [FFmpeg-devel] [PATCH 0/5] Provide optimized neon implementation Hubert Mazur
2022-09-06 10:27 ` [FFmpeg-devel] [PATCH 1/5] lavc/aarch64: Add neon implementation for vsad16 Hubert Mazur
@ 2022-09-06 10:27 ` Hubert Mazur
2022-09-07 8:57 ` Martin Storsjö
2022-09-06 10:27 ` [FFmpeg-devel] [PATCH 3/5] lavc/aarch64: Add neon implementation for vsad_intra16 Hubert Mazur
` (3 subsequent siblings)
5 siblings, 1 reply; 13+ messages in thread
From: Hubert Mazur @ 2022-09-06 10:27 UTC (permalink / raw)
To: ffmpeg-devel; +Cc: gjb, upstream, jswinney, Hubert Mazur, martin, mw, spop
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 <hum@semihalf.com>
---
libavcodec/aarch64/me_cmp_init_aarch64.c | 4 ++
libavcodec/aarch64/me_cmp_neon.S | 87 ++++++++++++++++++++++++
2 files changed, 91 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 1d0b166d69..b3f376aa60 100644
--- a/libavcodec/aarch64/me_cmp_neon.S
+++ b/libavcodec/aarch64/me_cmp_neon.S
@@ -649,3 +649,90 @@ 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
+
+ ld1 {v0.16b}, [x1], x3 // Load pix1[0], first iteration
+ ld1 {v1.16b}, [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
+ usubl2 v30.8h, v0.16b, v1.16b // Signed difference of pix1[0] - pix2[0], first iteration
+ b.le 2f
+
+
+1:
+ // x = abs(pix1[0] - pix2[0] - pix1[0 + stride] + pix2[0 + stride])
+ // res = (x) * (x)
+ ld1 {v0.16b}, [x1], x3 // Load pix1[0 + stride], first iteration
+ ld1 {v1.16b}, [x2], x3 // Load pix2[0 + stride], first iteration
+ ld1 {v2.16b}, [x1], x3 // Load pix1[0 + stride], second iteration
+ ld1 {v3.16b}, [x2], x3 // Load pix2[0 + stride], second iteration
+ usubl v29.8h, v0.8b, v1.8b
+ usubl2 v28.8h, v0.16b, v1.16b
+ ld1 {v4.16b}, [x1], x3 // Load pix1[0 + stride], third iteration
+ ld1 {v5.16b}, [x2], x3 // Load pix1[0 + stride], third iteration
+ sabd v31.8h, v31.8h, v29.8h
+ sabd v30.8h, v30.8h, v28.8h
+ usubl v27.8h, v2.8b, v3.8b
+ usubl2 v26.8h, v2.16b, v3.16b
+ usubl v25.8h, v4.8b, v5.8b
+ usubl2 v24.8h, v4.16b, v5.16b
+ sabd v29.8h, v29.8h, v27.8h
+ sabd v27.8h, v27.8h, v25.8h
+ umlal v16.4s, v31.4h, v31.4h
+ umlal2 v17.4s, v31.8h, v31.8h
+ sabd v28.8h, v28.8h, v26.8h
+ sabd v26.8h, v26.8h, v24.8h
+ umlal v16.4s, v30.4h, v30.4h
+ umlal2 v17.4s, v30.8h, v30.8h
+ mov v31.16b, v25.16b
+ umlal v16.4s, v29.4h, v29.4h
+ umlal2 v17.4s, v29.8h, v29.8h
+ mov v30.16b, v24.16b
+ umlal v16.4s, v28.4h, v28.4h
+ umlal2 v17.4s, v28.8h, v28.8h
+ sub w4, w4, #3
+ umlal v16.4s, v27.4h, v27.4h
+ umlal2 v17.4s, v27.8h, v27.8h
+ cmp w4, #3
+ umlal v16.4s, v26.4h, v26.4h
+ umlal2 v17.4s, v26.8h, v26.8h
+
+ b.ge 1b
+
+ cbz w4, 3f
+
+// iterate by once
+2:
+ ld1 {v0.16b}, [x1], x3
+ ld1 {v1.16b}, [x2], x3
+ subs w4, w4, #1
+ usubl v29.8h, v0.8b, v1.8b
+ usubl2 v28.8h, v0.16b, v1.16b
+ sabd v31.8h, v31.8h, v29.8h
+ sabd v30.8h, v30.8h, v28.8h
+ umlal v16.4s, v31.4h, v31.4h
+ umlal2 v17.4s, v31.8h, v31.8h
+ mov v31.16b, v29.16b
+ umlal v16.4s, v30.4h, v30.4h
+ umlal2 v17.4s, v30.8h, v30.8h
+ mov v30.16b, v28.16b
+ b.ne 2b
+
+3:
+ add v16.4s, v16.4s, v17.4s
+ uaddlv d17, v16.4s
+ fmov w0, s17
+
+ ret
+endfunc
--
2.34.1
_______________________________________________
ffmpeg-devel mailing list
ffmpeg-devel@ffmpeg.org
https://ffmpeg.org/mailman/listinfo/ffmpeg-devel
To unsubscribe, visit link above, or email
ffmpeg-devel-request@ffmpeg.org with subject "unsubscribe".
^ permalink raw reply [flat|nested] 13+ messages in thread
* [FFmpeg-devel] [PATCH 3/5] lavc/aarch64: Add neon implementation for vsad_intra16
2022-09-06 10:27 [FFmpeg-devel] [PATCH 0/5] Provide optimized neon implementation Hubert Mazur
2022-09-06 10:27 ` [FFmpeg-devel] [PATCH 1/5] lavc/aarch64: Add neon implementation for vsad16 Hubert Mazur
2022-09-06 10:27 ` [FFmpeg-devel] [PATCH 2/5] lavc/aarch64: Add neon implementation of vsse16 Hubert Mazur
@ 2022-09-06 10:27 ` Hubert Mazur
2022-09-06 10:27 ` [FFmpeg-devel] [PATCH 4/5] lavc/aarch64: Add neon implementation for vsse_intra16 Hubert Mazur
` (2 subsequent siblings)
5 siblings, 0 replies; 13+ messages in thread
From: Hubert Mazur @ 2022-09-06 10:27 UTC (permalink / raw)
To: ffmpeg-devel; +Cc: gjb, upstream, jswinney, Hubert Mazur, martin, mw, spop
Provide optimized implementation for vsad_intra16 function for arm64.
Performance comparison tests are shown below.
- vsad_4_c: 177.2
- vsad_4_neon: 24.5
Benchmarks and tests are run with checkasm tool on AWS Gravtion 3.
Signed-off-by: Hubert Mazur <hum@semihalf.com>
---
libavcodec/aarch64/me_cmp_init_aarch64.c | 3 ++
libavcodec/aarch64/me_cmp_neon.S | 48 ++++++++++++++++++++++++
2 files changed, 51 insertions(+)
diff --git a/libavcodec/aarch64/me_cmp_init_aarch64.c b/libavcodec/aarch64/me_cmp_init_aarch64.c
index 7b81e48d16..af83f7ed1e 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 vsad_intra16_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);
@@ -64,6 +66,7 @@ av_cold void ff_me_cmp_init_aarch64(MECmpContext *c, AVCodecContext *avctx)
c->sse[2] = sse4_neon;
c->vsad[0] = vsad16_neon;
+ c->vsad[4] = vsad_intra16_neon;
c->vsse[0] = vsse16_neon;
}
diff --git a/libavcodec/aarch64/me_cmp_neon.S b/libavcodec/aarch64/me_cmp_neon.S
index b3f376aa60..ce198ea227 100644
--- a/libavcodec/aarch64/me_cmp_neon.S
+++ b/libavcodec/aarch64/me_cmp_neon.S
@@ -736,3 +736,51 @@ function vsse16_neon, export=1
ret
endfunc
+
+function vsad_intra16_neon, export=1
+ // x0 unused
+ // x1 uint8_t *pix1
+ // x2 uint8_t *dummy
+ // x3 ptrdiff_t stride
+ // w4 int h
+
+ ld1 {v0.16b}, [x1], x3
+ sub w4, w4, #1 // we need to make h-1 iterations
+ cmp w4, #3
+ movi v16.8h, #0
+ b.lt 2f
+
+// make 4 iterations at once
+1:
+ // v = abs( pix1[0] - pix1[0 + stride] )
+ // score = sum(v)
+ ld1 {v1.16b}, [x1], x3
+ ld1 {v2.16b}, [x1], x3
+ uabal v16.8h, v0.8b, v1.8b
+ ld1 {v3.16b}, [x1], x3
+ uabal2 v16.8h, v0.16b, v1.16b
+ sub w4, w4, #3
+ uabal v16.8h, v1.8b, v2.8b
+ cmp w4, #3
+ uabal2 v16.8h, v1.16b, v2.16b
+ mov v0.16b, v3.16b
+ uabal v16.8h, v2.8b, v3.8b
+ uabal2 v16.8h, v2.16b, v3.16b
+ b.ge 1b
+ cbz w4, 3f
+
+// iterate by one
+2:
+ ld1 {v1.16b}, [x1], x3
+ subs w4, w4, #1
+ uabal v16.8h, v0.8b, v1.8b
+ uabal2 v16.8h, v0.16b, v1.16b
+ mov v0.16b, v1.16b
+ cbnz w4, 2b
+
+3:
+ uaddlv s17, v16.8h
+ fmov w0, s17
+
+ ret
+endfunc
--
2.34.1
_______________________________________________
ffmpeg-devel mailing list
ffmpeg-devel@ffmpeg.org
https://ffmpeg.org/mailman/listinfo/ffmpeg-devel
To unsubscribe, visit link above, or email
ffmpeg-devel-request@ffmpeg.org with subject "unsubscribe".
^ permalink raw reply [flat|nested] 13+ messages in thread
* [FFmpeg-devel] [PATCH 4/5] lavc/aarch64: Add neon implementation for vsse_intra16
2022-09-06 10:27 [FFmpeg-devel] [PATCH 0/5] Provide optimized neon implementation Hubert Mazur
` (2 preceding siblings ...)
2022-09-06 10:27 ` [FFmpeg-devel] [PATCH 3/5] lavc/aarch64: Add neon implementation for vsad_intra16 Hubert Mazur
@ 2022-09-06 10:27 ` Hubert Mazur
2022-09-06 10:27 ` [FFmpeg-devel] [PATCH 5/5] lavc/aarch64: Provide neon implementation of nsse16 Hubert Mazur
2022-09-07 8:55 ` [FFmpeg-devel] [PATCH 0/5] Provide optimized neon implementation Martin Storsjö
5 siblings, 0 replies; 13+ messages in thread
From: Hubert Mazur @ 2022-09-06 10:27 UTC (permalink / raw)
To: ffmpeg-devel; +Cc: gjb, upstream, jswinney, Hubert Mazur, martin, mw, spop
Provide optimized implementation for vsse_intra16 for arm64.
Performance tests are shown below.
- vsse_4_c: 153.7
- vsse_4_neon: 34.2
Benchmarks and tests are run with checkasm tool on AWS Graviton 3.
Signed-off-by: Hubert Mazur <hum@semihalf.com>
---
libavcodec/aarch64/me_cmp_init_aarch64.c | 3 ++
libavcodec/aarch64/me_cmp_neon.S | 63 ++++++++++++++++++++++++
2 files changed, 66 insertions(+)
diff --git a/libavcodec/aarch64/me_cmp_init_aarch64.c b/libavcodec/aarch64/me_cmp_init_aarch64.c
index af83f7ed1e..8c295d5457 100644
--- a/libavcodec/aarch64/me_cmp_init_aarch64.c
+++ b/libavcodec/aarch64/me_cmp_init_aarch64.c
@@ -47,6 +47,8 @@ int vsad_intra16_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,
+ ptrdiff_t stride, int h);
av_cold void ff_me_cmp_init_aarch64(MECmpContext *c, AVCodecContext *avctx)
{
@@ -69,5 +71,6 @@ av_cold void ff_me_cmp_init_aarch64(MECmpContext *c, AVCodecContext *avctx)
c->vsad[4] = vsad_intra16_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 ce198ea227..cf2b8da425 100644
--- a/libavcodec/aarch64/me_cmp_neon.S
+++ b/libavcodec/aarch64/me_cmp_neon.S
@@ -784,3 +784,66 @@ function vsad_intra16_neon, export=1
ret
endfunc
+
+function vsse_intra16_neon, export=1
+ // x0 unused
+ // x1 uint8_t *pix1
+ // x2 uint8_t *dummy
+ // x3 ptrdiff_t stride
+ // w4 int h
+
+ ld1 {v0.16b}, [x1], x3
+ movi v16.4s, #0
+ movi v17.4s, #0
+
+ sub w4, w4, #1 // we need to make h-1 iterations
+ cmp w4, #3
+ b.lt 2f
+
+1:
+ // v = abs( pix1[0] - pix1[0 + stride] )
+ // score = sum( v * v )
+ ld1 {v1.16b}, [x1], x3
+ ld1 {v2.16b}, [x1], x3
+ uabd v30.16b, v0.16b, v1.16b
+ ld1 {v3.16b}, [x1], x3
+ umull v29.8h, v30.8b, v30.8b
+ umull2 v28.8h, v30.16b, v30.16b
+ uabd v27.16b, v1.16b, v2.16b
+ uadalp v16.4s, v29.8h
+ umull v26.8h, v27.8b, v27.8b
+ umull2 v27.8h, v27.16b, v27.16b
+ uadalp v17.4s, v28.8h
+ uabd v25.16b, v2.16b, v3.16b
+ uadalp v16.4s, v26.8h
+ umull v24.8h, v25.8b, v25.8b
+ umull2 v25.8h, v25.16b, v25.16b
+ uadalp v17.4s, v27.8h
+ sub w4, w4, #3
+ uadalp v16.4s, v24.8h
+ cmp w4, #3
+ uadalp v17.4s, v25.8h
+ mov v0.16b, v3.16b
+
+ b.ge 1b
+ cbz w4, 3f
+
+// iterate by one
+2:
+ ld1 {v1.16b}, [x1], x3
+ subs w4, w4, #1
+ uabd v30.16b, v0.16b, v1.16b
+ mov v0.16b, v1.16b
+ umull v29.8h, v30.8b, v30.8b
+ umull2 v30.8h, v30.16b, v30.16b
+ uadalp v16.4s, v29.8h
+ uadalp v17.4s, v30.8h
+ cbnz w4, 2b
+
+3:
+ add v16.4s, v16.4s, v17.4S
+ uaddlv d17, v16.4s
+ fmov w0, s17
+
+ ret
+endfunc
--
2.34.1
_______________________________________________
ffmpeg-devel mailing list
ffmpeg-devel@ffmpeg.org
https://ffmpeg.org/mailman/listinfo/ffmpeg-devel
To unsubscribe, visit link above, or email
ffmpeg-devel-request@ffmpeg.org with subject "unsubscribe".
^ permalink raw reply [flat|nested] 13+ messages in thread
* [FFmpeg-devel] [PATCH 5/5] lavc/aarch64: Provide neon implementation of nsse16
2022-09-06 10:27 [FFmpeg-devel] [PATCH 0/5] Provide optimized neon implementation Hubert Mazur
` (3 preceding siblings ...)
2022-09-06 10:27 ` [FFmpeg-devel] [PATCH 4/5] lavc/aarch64: Add neon implementation for vsse_intra16 Hubert Mazur
@ 2022-09-06 10:27 ` Hubert Mazur
2022-09-07 9:06 ` Martin Storsjö
2022-09-07 8:55 ` [FFmpeg-devel] [PATCH 0/5] Provide optimized neon implementation Martin Storsjö
5 siblings, 1 reply; 13+ messages in thread
From: Hubert Mazur @ 2022-09-06 10:27 UTC (permalink / raw)
To: ffmpeg-devel; +Cc: gjb, upstream, jswinney, Hubert Mazur, martin, mw, spop
Add vectorized implementation of nsse16 function.
Performance comparison tests are shown below.
- nsse_0_c: 707.0
- nsse_0_neon: 120.0
Benchmarks and tests run with checkasm tool on AWS Graviton 3.
Signed-off-by: Hubert Mazur <hum@semihalf.com>
---
libavcodec/aarch64/me_cmp_init_aarch64.c | 15 +++
libavcodec/aarch64/me_cmp_neon.S | 124 +++++++++++++++++++++++
2 files changed, 139 insertions(+)
diff --git a/libavcodec/aarch64/me_cmp_init_aarch64.c b/libavcodec/aarch64/me_cmp_init_aarch64.c
index 8c295d5457..ea7f295373 100644
--- a/libavcodec/aarch64/me_cmp_init_aarch64.c
+++ b/libavcodec/aarch64/me_cmp_init_aarch64.c
@@ -49,6 +49,10 @@ 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,
ptrdiff_t stride, int h);
+int nsse16_neon(int multiplier, const uint8_t *s, const uint8_t *s2,
+ ptrdiff_t stride, int h);
+int nsse16_neon_wrapper(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)
{
@@ -72,5 +76,16 @@ av_cold void ff_me_cmp_init_aarch64(MECmpContext *c, AVCodecContext *avctx)
c->vsse[0] = vsse16_neon;
c->vsse[4] = vsse_intra16_neon;
+
+ c->nsse[0] = nsse16_neon_wrapper;
}
}
+
+int nsse16_neon_wrapper(MpegEncContext *c, const uint8_t *s1, const uint8_t *s2,
+ ptrdiff_t stride, int h)
+{
+ if (c)
+ return nsse16_neon(c->avctx->nsse_weight, s1, s2, stride, h);
+ else
+ return nsse16_neon(8, s1, s2, stride, h);
+}
diff --git a/libavcodec/aarch64/me_cmp_neon.S b/libavcodec/aarch64/me_cmp_neon.S
index cf2b8da425..bd21122a21 100644
--- a/libavcodec/aarch64/me_cmp_neon.S
+++ b/libavcodec/aarch64/me_cmp_neon.S
@@ -847,3 +847,127 @@ function vsse_intra16_neon, export=1
ret
endfunc
+
+function nsse16_neon, export=1
+ // x0 multiplier
+ // x1 uint8_t *pix1
+ // x2 uint8_t *pix2
+ // x3 ptrdiff_t stride
+ // w4 int h
+
+ str x0, [sp, #-0x40]!
+ stp x1, x2, [sp, #0x10]
+ stp x3, x4, [sp, #0x20]
+ str x30, [sp, #0x30]
+ bl X(sse16_neon)
+ ldr x30, [sp, #0x30]
+ mov w9, w0 // here we store score1
+ ldr x5, [sp]
+ ldp x1, x2, [sp, #0x10]
+ ldp x3, x4, [sp, #0x20]
+ add sp, sp, #0x40
+
+ movi v16.8h, #0
+ movi v17.8h, #0
+ movi v18.8h, #0
+ movi v19.8h, #0
+
+ ld1 {v0.16b}, [x1], x3
+ subs w4, w4, #1 // we need to make h-1 iterations
+ ext v1.16b, v0.16b, v0.16b, #1 // x1 + 1
+ ld1 {v2.16b}, [x2], x3
+ cmp w4, #2
+ ext v3.16b, v2.16b, v2.16b, #1 // x2 + 1
+
+ b.lt 2f
+
+// make 2 iterations at once
+1:
+ ld1 {v4.16b}, [x1], x3
+ ld1 {v20.16b}, [x1], x3
+ ext v5.16b, v4.16b, v4.16b, #1 // x1 + stride + 1
+ ext v21.16b, v20.16b, v20.16b, #1
+ ld1 {v6.16b}, [x2], x3
+ ld1 {v22.16b}, [x2], x3
+ ext v7.16b, v6.16b, v6.16b, #1 // x2 + stride + 1
+ ext v23.16b, v22.16b, v22.16b, #1
+
+ usubl v31.8h, v0.8b, v4.8b
+ usubl2 v30.8h, v0.16b, v4.16b
+ usubl v29.8h, v1.8b, v5.8b
+ usubl2 v28.8h, v1.16b, v5.16b
+ saba v16.8h, v31.8h, v29.8h
+ saba v17.8h, v30.8h, v28.8h
+ usubl v27.8h, v2.8b, v6.8b
+ usubl2 v26.8h, v2.16b, v6.16b
+ usubl v25.8h, v3.8b, v7.8b
+ usubl2 v24.8h, v3.16b, v7.16b
+ saba v18.8h, v27.8h, v25.8h
+ saba v19.8h, v26.8h, v24.8h
+
+ usubl v31.8h, v4.8b, v20.8b
+ usubl2 v30.8h, v4.16b, v20.16b
+ usubl v29.8h, v5.8b, v21.8b
+ usubl2 v28.8h, v5.16b, v21.16b
+ saba v16.8h, v31.8h, v29.8h
+ saba v17.8h, v30.8h, v28.8h
+ usubl v27.8h, v6.8b, v22.8b
+ usubl2 v26.8h, v6.16b, v22.16b
+ usubl v25.8h, v7.8b, v23.8b
+ usubl2 v24.8h, v7.16b, v23.16b
+ saba v18.8h, v27.8h, v25.8h
+ saba v19.8h, v26.8h, v24.8h
+
+ mov v0.16b, v20.16b
+ mov v1.16b, v21.16b
+ mov v2.16b, v22.16b
+ mov v3.16b, v23.16b
+
+ sub w4, w4, #2
+ cmp w4, #2
+
+ b.ge 1b
+ cbz w4, 3f
+
+// iterate by one
+2:
+ ld1 {v4.16b}, [x1], x3
+ subs w4, w4, #1
+ ext v5.16b, v4.16b, v4.16b, #1 // x1 + stride + 1
+ ld1 {v6.16b}, [x2], x3
+ usubl v31.8h, v0.8b, v4.8b
+ ext v7.16b, v6.16b, v6.16b, #1 // x2 + stride + 1
+
+ usubl2 v30.8h, v0.16b, v4.16b
+ usubl v29.8h, v1.8b, v5.8b
+ usubl2 v28.8h, v1.16b, v5.16b
+ saba v16.8h, v31.8h, v29.8h
+ saba v17.8h, v30.8h, v28.8h
+ usubl v27.8h, v2.8b, v6.8b
+ usubl2 v26.8h, v2.16b, v6.16b
+ usubl v25.8h, v3.8b, v7.8b
+ usubl2 v24.8h, v3.16b, v7.16b
+ saba v18.8h, v27.8h, v25.8h
+ saba v19.8h, v26.8h, v24.8h
+
+ mov v0.16b, v4.16b
+ mov v1.16b, v5.16b
+ mov v2.16b, v6.16b
+ mov v3.16b, v7.16b
+
+ cbnz w4, 2b
+
+3:
+ sqsub v16.8h, v16.8h, v18.8h
+ sqsub v17.8h, v17.8h, v19.8h
+ ins v17.h[7], wzr
+ sqadd v16.8h, v16.8h, v17.8h
+ saddlv s16, v16.8h
+ sqabs s16, s16
+ fmov w0, s16
+
+ mul w0, w0, w5
+ add w0, w0, w9
+
+ ret
+endfunc
--
2.34.1
_______________________________________________
ffmpeg-devel mailing list
ffmpeg-devel@ffmpeg.org
https://ffmpeg.org/mailman/listinfo/ffmpeg-devel
To unsubscribe, visit link above, or email
ffmpeg-devel-request@ffmpeg.org with subject "unsubscribe".
^ permalink raw reply [flat|nested] 13+ messages in thread
* Re: [FFmpeg-devel] [PATCH 0/5] Provide optimized neon implementation
2022-09-06 10:27 [FFmpeg-devel] [PATCH 0/5] Provide optimized neon implementation Hubert Mazur
` (4 preceding siblings ...)
2022-09-06 10:27 ` [FFmpeg-devel] [PATCH 5/5] lavc/aarch64: Provide neon implementation of nsse16 Hubert Mazur
@ 2022-09-07 8:55 ` Martin Storsjö
5 siblings, 0 replies; 13+ messages in thread
From: Martin Storsjö @ 2022-09-07 8:55 UTC (permalink / raw)
To: Hubert Mazur; +Cc: gjb, upstream, jswinney, ffmpeg-devel, mw, spop
On Tue, 6 Sep 2022, Hubert Mazur wrote:
> Provide optimized implementations for me_cmp functions.
> This set of patches fixes all issues addressed in previous review.
> Major changes:
> - Remove redundant loads since the data can be reused.
> - Improve style.
> - Fix issues with unrecognized symbols.
Thanks! This looks quite good to me now. I have a minor comment on vsse16
and a slightly bigger one on nsse16, but other than that, this is almost
good to go.
I noticed that you haven't updated the checkasm benchmark numbers in the
commit messages since the previous round, while the code has seen some
quite major changes. Please do rerun the numbers since I think they have
changed notably.
// 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-request@ffmpeg.org with subject "unsubscribe".
^ permalink raw reply [flat|nested] 13+ messages in thread
* Re: [FFmpeg-devel] [PATCH 2/5] lavc/aarch64: Add neon implementation of vsse16
2022-09-06 10:27 ` [FFmpeg-devel] [PATCH 2/5] lavc/aarch64: Add neon implementation of vsse16 Hubert Mazur
@ 2022-09-07 8:57 ` Martin Storsjö
0 siblings, 0 replies; 13+ messages in thread
From: Martin Storsjö @ 2022-09-07 8:57 UTC (permalink / raw)
To: Hubert Mazur; +Cc: gjb, upstream, jswinney, ffmpeg-devel, mw, spop
On Tue, 6 Sep 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 <hum@semihalf.com>
> ---
> libavcodec/aarch64/me_cmp_init_aarch64.c | 4 ++
> libavcodec/aarch64/me_cmp_neon.S | 87 ++++++++++++++++++++++++
> 2 files changed, 91 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 1d0b166d69..b3f376aa60 100644
> --- a/libavcodec/aarch64/me_cmp_neon.S
> +++ b/libavcodec/aarch64/me_cmp_neon.S
> @@ -649,3 +649,90 @@ 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
> +
> + ld1 {v0.16b}, [x1], x3 // Load pix1[0], first iteration
> + ld1 {v1.16b}, [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
> + usubl2 v30.8h, v0.16b, v1.16b // Signed difference of pix1[0] - pix2[0], first iteration
> + b.le 2f
> +
> +
> +1:
> + // x = abs(pix1[0] - pix2[0] - pix1[0 + stride] + pix2[0 + stride])
> + // res = (x) * (x)
Technically, there's no need for abs() here, we can just as well just do a
plain subtraction. I tested this by replacing sabd with sub here (and
changing umlal into smlal). It doesn't make any difference for the
performance on the cores I tested on though - apparently there's no
difference in performance between sabd and sub. So in practice, both
should be fine. And I don't think that either of them is better for
handling overflows/edge cases here either (which shouldn't be happening
anyway).
// 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-request@ffmpeg.org with subject "unsubscribe".
^ permalink raw reply [flat|nested] 13+ messages in thread
* Re: [FFmpeg-devel] [PATCH 5/5] lavc/aarch64: Provide neon implementation of nsse16
2022-09-06 10:27 ` [FFmpeg-devel] [PATCH 5/5] lavc/aarch64: Provide neon implementation of nsse16 Hubert Mazur
@ 2022-09-07 9:06 ` Martin Storsjö
0 siblings, 0 replies; 13+ messages in thread
From: Martin Storsjö @ 2022-09-07 9:06 UTC (permalink / raw)
To: Hubert Mazur; +Cc: gjb, upstream, jswinney, ffmpeg-devel, mw, spop
[-- Attachment #1: Type: text/plain, Size: 4851 bytes --]
On Tue, 6 Sep 2022, Hubert Mazur wrote:
> Add vectorized implementation of nsse16 function.
>
> Performance comparison tests are shown below.
> - nsse_0_c: 707.0
> - nsse_0_neon: 120.0
>
> Benchmarks and tests run with checkasm tool on AWS Graviton 3.
>
> Signed-off-by: Hubert Mazur <hum@semihalf.com>
> ---
> libavcodec/aarch64/me_cmp_init_aarch64.c | 15 +++
> libavcodec/aarch64/me_cmp_neon.S | 124 +++++++++++++++++++++++
> 2 files changed, 139 insertions(+)
>
> diff --git a/libavcodec/aarch64/me_cmp_init_aarch64.c b/libavcodec/aarch64/me_cmp_init_aarch64.c
> index 8c295d5457..ea7f295373 100644
> --- a/libavcodec/aarch64/me_cmp_init_aarch64.c
> +++ b/libavcodec/aarch64/me_cmp_init_aarch64.c
> @@ -49,6 +49,10 @@ 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,
> ptrdiff_t stride, int h);
> +int nsse16_neon(int multiplier, const uint8_t *s, const uint8_t *s2,
> + ptrdiff_t stride, int h);
> +int nsse16_neon_wrapper(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)
> {
> @@ -72,5 +76,16 @@ av_cold void ff_me_cmp_init_aarch64(MECmpContext *c, AVCodecContext *avctx)
>
> c->vsse[0] = vsse16_neon;
> c->vsse[4] = vsse_intra16_neon;
> +
> + c->nsse[0] = nsse16_neon_wrapper;
> }
> }
> +
> +int nsse16_neon_wrapper(MpegEncContext *c, const uint8_t *s1, const uint8_t *s2,
> + ptrdiff_t stride, int h)
> +{
> + if (c)
> + return nsse16_neon(c->avctx->nsse_weight, s1, s2, stride, h);
> + else
> + return nsse16_neon(8, s1, s2, stride, h);
> +}
The body of this function is still indented 4 spaces too much.
> diff --git a/libavcodec/aarch64/me_cmp_neon.S b/libavcodec/aarch64/me_cmp_neon.S
> index cf2b8da425..bd21122a21 100644
> --- a/libavcodec/aarch64/me_cmp_neon.S
> +++ b/libavcodec/aarch64/me_cmp_neon.S
> @@ -847,3 +847,127 @@ function vsse_intra16_neon, export=1
>
> ret
> endfunc
> +
> +function nsse16_neon, export=1
> + // x0 multiplier
> + // x1 uint8_t *pix1
> + // x2 uint8_t *pix2
> + // x3 ptrdiff_t stride
> + // w4 int h
> +
> + str x0, [sp, #-0x40]!
> + stp x1, x2, [sp, #0x10]
> + stp x3, x4, [sp, #0x20]
> + str x30, [sp, #0x30]
> + bl X(sse16_neon)
> + ldr x30, [sp, #0x30]
> + mov w9, w0 // here we store score1
> + ldr x5, [sp]
> + ldp x1, x2, [sp, #0x10]
> + ldp x3, x4, [sp, #0x20]
> + add sp, sp, #0x40
> +
> + movi v16.8h, #0
> + movi v17.8h, #0
> + movi v18.8h, #0
> + movi v19.8h, #0
> +
> + ld1 {v0.16b}, [x1], x3
> + subs w4, w4, #1 // we need to make h-1 iterations
> + ext v1.16b, v0.16b, v0.16b, #1 // x1 + 1
> + ld1 {v2.16b}, [x2], x3
> + cmp w4, #2
> + ext v3.16b, v2.16b, v2.16b, #1 // x2 + 1
The scheduling here (and in both loops below) is a bit non-ideal; we use
v0 very early after loading it, while we could start the load of v2 before
that.
> +
> + b.lt 2f
> +
> +// make 2 iterations at once
> +1:
> + ld1 {v4.16b}, [x1], x3
> + ld1 {v20.16b}, [x1], x3
The load of v20 here would stall a bit, since the first load updates x1.
Instead we can launch the load of v6 inbetween these two
> + ext v5.16b, v4.16b, v4.16b, #1 // x1 + stride + 1
> + ext v21.16b, v20.16b, v20.16b, #1
We can move the use of v20 a bit later here, inbetween the two other
exts.
These changes (plus a similar minor one to the non-unrolled version at the
bottom) produces the following benchmark change for me:
Before: Cortex A53 A72 A73
nsse_0_neon: 401.0 198.0 194.5
After:
nsse_0_neon: 377.0 198.7 196.5
(The differences on A72 and A73 are within the measurement noise, those
numbers vary more than that from one run to another.)
You can squash in the attached patch for simplicity. Also, remember to fix
the indentation of the wrapper function.
With those changes, plus updated benchmark numbers in the commit messages,
I think this patchset should be good to go.
// Martin
[-- Warning: decoded text below may be mangled, UTF-8 assumed --]
[-- Attachment #2: Type: text/x-diff; name=0001-squash-nsse16-Tune-scheduling.patch, Size: 2496 bytes --]
From 081aff967d4fdc3d475c777033223625db3bb532 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Martin=20Storsj=C3=B6?= <martin@martin.st>
Date: Wed, 7 Sep 2022 11:50:29 +0300
Subject: [PATCH] squash: nsse16: Tune scheduling
Before: Cortex A53 A72 A73
nsse_0_neon: 401.0 198.0 194.5
After:
nsse_0_neon: 377.0 198.7 196.5
(The differences on A72 and A73 are within the measurement noise,
those numbers vary more than that from one run to another.)
---
libavcodec/aarch64/me_cmp_neon.S | 8 ++++----
1 file changed, 4 insertions(+), 4 deletions(-)
diff --git a/libavcodec/aarch64/me_cmp_neon.S b/libavcodec/aarch64/me_cmp_neon.S
index bd21122a21..2a2af7a788 100644
--- a/libavcodec/aarch64/me_cmp_neon.S
+++ b/libavcodec/aarch64/me_cmp_neon.S
@@ -874,8 +874,8 @@ function nsse16_neon, export=1
ld1 {v0.16b}, [x1], x3
subs w4, w4, #1 // we need to make h-1 iterations
- ext v1.16b, v0.16b, v0.16b, #1 // x1 + 1
ld1 {v2.16b}, [x2], x3
+ ext v1.16b, v0.16b, v0.16b, #1 // x1 + 1
cmp w4, #2
ext v3.16b, v2.16b, v2.16b, #1 // x2 + 1
@@ -884,12 +884,12 @@ function nsse16_neon, export=1
// make 2 iterations at once
1:
ld1 {v4.16b}, [x1], x3
+ ld1 {v6.16b}, [x2], x3
ld1 {v20.16b}, [x1], x3
ext v5.16b, v4.16b, v4.16b, #1 // x1 + stride + 1
- ext v21.16b, v20.16b, v20.16b, #1
- ld1 {v6.16b}, [x2], x3
ld1 {v22.16b}, [x2], x3
ext v7.16b, v6.16b, v6.16b, #1 // x2 + stride + 1
+ ext v21.16b, v20.16b, v20.16b, #1
ext v23.16b, v22.16b, v22.16b, #1
usubl v31.8h, v0.8b, v4.8b
@@ -933,8 +933,8 @@ function nsse16_neon, export=1
2:
ld1 {v4.16b}, [x1], x3
subs w4, w4, #1
- ext v5.16b, v4.16b, v4.16b, #1 // x1 + stride + 1
ld1 {v6.16b}, [x2], x3
+ ext v5.16b, v4.16b, v4.16b, #1 // x1 + stride + 1
usubl v31.8h, v0.8b, v4.8b
ext v7.16b, v6.16b, v6.16b, #1 // x2 + stride + 1
--
2.25.1
[-- Attachment #3: Type: text/plain, Size: 251 bytes --]
_______________________________________________
ffmpeg-devel mailing list
ffmpeg-devel@ffmpeg.org
https://ffmpeg.org/mailman/listinfo/ffmpeg-devel
To unsubscribe, visit link above, or email
ffmpeg-devel-request@ffmpeg.org with subject "unsubscribe".
^ permalink raw reply [flat|nested] 13+ messages in thread
* [FFmpeg-devel] [PATCH 5/5] lavc/aarch64: Provide neon implementation of nsse16
2022-09-08 9:25 Hubert Mazur
@ 2022-09-08 9:25 ` Hubert Mazur
0 siblings, 0 replies; 13+ messages in thread
From: Hubert Mazur @ 2022-09-08 9:25 UTC (permalink / raw)
To: ffmpeg-devel; +Cc: gjb, upstream, jswinney, Hubert Mazur, martin, mw, spop
Add vectorized implementation of nsse16 function.
Performance comparison tests are shown below.
- nsse_0_c: 682.2
- nsse_0_neon: 116.5
Benchmarks and tests run with checkasm tool on AWS Graviton 3.
Co-authored-by: Martin Storsjö <martin@martin.st>
Signed-off-by: Hubert Mazur <hum@semihalf.com>
---
libavcodec/aarch64/me_cmp_init_aarch64.c | 15 +++
libavcodec/aarch64/me_cmp_neon.S | 122 +++++++++++++++++++++++
2 files changed, 137 insertions(+)
diff --git a/libavcodec/aarch64/me_cmp_init_aarch64.c b/libavcodec/aarch64/me_cmp_init_aarch64.c
index 8c295d5457..ade3e9a4c1 100644
--- a/libavcodec/aarch64/me_cmp_init_aarch64.c
+++ b/libavcodec/aarch64/me_cmp_init_aarch64.c
@@ -49,6 +49,10 @@ 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,
ptrdiff_t stride, int h);
+int nsse16_neon(int multiplier, const uint8_t *s, const uint8_t *s2,
+ ptrdiff_t stride, int h);
+int nsse16_neon_wrapper(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)
{
@@ -72,5 +76,16 @@ av_cold void ff_me_cmp_init_aarch64(MECmpContext *c, AVCodecContext *avctx)
c->vsse[0] = vsse16_neon;
c->vsse[4] = vsse_intra16_neon;
+
+ c->nsse[0] = nsse16_neon_wrapper;
}
}
+
+int nsse16_neon_wrapper(MpegEncContext *c, const uint8_t *s1, const uint8_t *s2,
+ ptrdiff_t stride, int h)
+{
+ if (c)
+ return nsse16_neon(c->avctx->nsse_weight, s1, s2, stride, h);
+ else
+ return nsse16_neon(8, s1, s2, stride, h);
+}
diff --git a/libavcodec/aarch64/me_cmp_neon.S b/libavcodec/aarch64/me_cmp_neon.S
index cf2b8da425..f8998749a5 100644
--- a/libavcodec/aarch64/me_cmp_neon.S
+++ b/libavcodec/aarch64/me_cmp_neon.S
@@ -847,3 +847,125 @@ function vsse_intra16_neon, export=1
ret
endfunc
+
+function nsse16_neon, export=1
+ // x0 multiplier
+ // x1 uint8_t *pix1
+ // x2 uint8_t *pix2
+ // x3 ptrdiff_t stride
+ // w4 int h
+
+ str x0, [sp, #-0x40]!
+ stp x1, x2, [sp, #0x10]
+ stp x3, x4, [sp, #0x20]
+ str x30, [sp, #0x30]
+ bl X(sse16_neon)
+ ldr x30, [sp, #0x30]
+ mov w9, w0 // here we store score1
+ ldr x5, [sp]
+ ldp x1, x2, [sp, #0x10]
+ ldp x3, x4, [sp, #0x20]
+ add sp, sp, #0x40
+
+ movi v16.8h, #0
+ movi v17.8h, #0
+ movi v18.8h, #0
+ movi v19.8h, #0
+
+ ld1 {v0.16b}, [x1], x3
+ subs w4, w4, #1 // we need to make h-1 iterations
+ ld1 {v2.16b}, [x2], x3
+ ext v1.16b, v0.16b, v0.16b, #1 // x1 + 1
+ cmp w4, #2
+ ext v3.16b, v2.16b, v2.16b, #1 // x2 + 1
+
+ b.lt 2f
+
+// make 2 iterations at once
+1:
+ ld1 {v4.16b}, [x1], x3
+ ld1 {v6.16b}, [x2], x3
+ ld1 {v20.16b}, [x1], x3
+ ext v5.16b, v4.16b, v4.16b, #1 // x1 + stride + 1
+ usubl v31.8h, v0.8b, v4.8b
+ usubl2 v30.8h, v0.16b, v4.16b
+ ld1 {v22.16b}, [x2], x3
+ usubl v29.8h, v1.8b, v5.8b
+ usubl2 v28.8h, v1.16b, v5.16b
+ ext v7.16b, v6.16b, v6.16b, #1 // x2 + stride + 1
+ saba v16.8h, v31.8h, v29.8h
+ ext v21.16b, v20.16b, v20.16b, #1
+ saba v17.8h, v30.8h, v28.8h
+ usubl v27.8h, v2.8b, v6.8b
+ usubl2 v26.8h, v2.16b, v6.16b
+ ext v23.16b, v22.16b, v22.16b, #1
+ usubl v25.8h, v3.8b, v7.8b
+ usubl2 v24.8h, v3.16b, v7.16b
+ saba v18.8h, v27.8h, v25.8h
+ saba v19.8h, v26.8h, v24.8h
+
+ usubl v31.8h, v4.8b, v20.8b
+ usubl2 v30.8h, v4.16b, v20.16b
+ usubl v29.8h, v5.8b, v21.8b
+ usubl2 v28.8h, v5.16b, v21.16b
+ saba v16.8h, v31.8h, v29.8h
+ saba v17.8h, v30.8h, v28.8h
+ usubl v27.8h, v6.8b, v22.8b
+ usubl2 v26.8h, v6.16b, v22.16b
+ usubl v25.8h, v7.8b, v23.8b
+ usubl2 v24.8h, v7.16b, v23.16b
+ saba v18.8h, v27.8h, v25.8h
+ saba v19.8h, v26.8h, v24.8h
+ sub w4, w4, #2
+
+ mov v0.16b, v20.16b
+ mov v1.16b, v21.16b
+ cmp w4, #2
+ mov v2.16b, v22.16b
+ mov v3.16b, v23.16b
+
+ b.ge 1b
+ cbz w4, 3f
+
+// iterate by one
+2:
+ ld1 {v4.16b}, [x1], x3
+ subs w4, w4, #1
+ ld1 {v6.16b}, [x2], x3
+ ext v5.16b, v4.16b, v4.16b, #1 // x1 + stride + 1
+ usubl v31.8h, v0.8b, v4.8b
+ ext v7.16b, v6.16b, v6.16b, #1 // x2 + stride + 1
+
+ usubl2 v30.8h, v0.16b, v4.16b
+ usubl v29.8h, v1.8b, v5.8b
+ usubl2 v28.8h, v1.16b, v5.16b
+ saba v16.8h, v31.8h, v29.8h
+ saba v17.8h, v30.8h, v28.8h
+ usubl v27.8h, v2.8b, v6.8b
+ usubl2 v26.8h, v2.16b, v6.16b
+ usubl v25.8h, v3.8b, v7.8b
+ usubl2 v24.8h, v3.16b, v7.16b
+ saba v18.8h, v27.8h, v25.8h
+ saba v19.8h, v26.8h, v24.8h
+
+ mov v0.16b, v4.16b
+ mov v1.16b, v5.16b
+ mov v2.16b, v6.16b
+ mov v3.16b, v7.16b
+
+ cbnz w4, 2b
+
+3:
+ sqsub v17.8h, v17.8h, v19.8h
+ sqsub v16.8h, v16.8h, v18.8h
+ ins v17.h[7], wzr
+ sqadd v16.8h, v16.8h, v17.8h
+ saddlv s16, v16.8h
+ sqabs s16, s16
+ fmov w0, s16
+
+ mul w0, w0, w5
+ add w0, w0, w9
+
+ ret
+endfunc
--
2.34.1
_______________________________________________
ffmpeg-devel mailing list
ffmpeg-devel@ffmpeg.org
https://ffmpeg.org/mailman/listinfo/ffmpeg-devel
To unsubscribe, visit link above, or email
ffmpeg-devel-request@ffmpeg.org with subject "unsubscribe".
^ permalink raw reply [flat|nested] 13+ messages in thread
* Re: [FFmpeg-devel] [PATCH 5/5] lavc/aarch64: Provide neon implementation of nsse16
2022-08-22 15:26 ` [FFmpeg-devel] [PATCH 5/5] lavc/aarch64: Provide neon implementation of nsse16 Hubert Mazur
2022-09-02 21:29 ` Martin Storsjö
@ 2022-09-04 21:23 ` Martin Storsjö
1 sibling, 0 replies; 13+ messages in thread
From: Martin Storsjö @ 2022-09-04 21:23 UTC (permalink / raw)
To: Hubert Mazur; +Cc: gjb, upstream, jswinney, ffmpeg-devel, mw, spop
On Mon, 22 Aug 2022, Hubert Mazur wrote:
> Add vectorized implementation of nsse16 function.
>
> Performance comparison tests are shown below.
> - nsse_0_c: 707.0
> - nsse_0_neon: 120.0
>
> Benchmarks and tests run with checkasm tool on AWS Graviton 3.
>
> Signed-off-by: Hubert Mazur <hum@semihalf.com>
> ---
> libavcodec/aarch64/me_cmp_init_aarch64.c | 15 +++
> libavcodec/aarch64/me_cmp_neon.S | 126 +++++++++++++++++++++++
> 2 files changed, 141 insertions(+)
>
> diff --git a/libavcodec/aarch64/me_cmp_init_aarch64.c b/libavcodec/aarch64/me_cmp_init_aarch64.c
> index 8c295d5457..146ef04345 100644
> --- a/libavcodec/aarch64/me_cmp_init_aarch64.c
> +++ b/libavcodec/aarch64/me_cmp_init_aarch64.c
> @@ -49,6 +49,10 @@ 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,
> ptrdiff_t stride, int h);
> +int nsse16_neon(int multiplier, const uint8_t *s, const uint8_t *s2,
> + ptrdiff_t stride, int h);
> +int nsse16_neon_wrapper(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)
> {
> @@ -72,5 +76,16 @@ av_cold void ff_me_cmp_init_aarch64(MECmpContext *c, AVCodecContext *avctx)
>
> c->vsse[0] = vsse16_neon;
> c->vsse[4] = vsse_intra16_neon;
> +
> + c->nsse[0] = nsse16_neon_wrapper;
> }
> }
> +
> +int nsse16_neon_wrapper(MpegEncContext *c, const uint8_t *s1, const uint8_t *s2,
> + ptrdiff_t stride, int h)
> +{
> + if (c)
> + return nsse16_neon(c->avctx->nsse_weight, s1, s2, stride, h);
> + else
> + return nsse16_neon(8, s1, s2, stride, h);
> +}
> \ No newline at end of file
The indentation is off for this file, and it's missing the final newline.
> diff --git a/libavcodec/aarch64/me_cmp_neon.S b/libavcodec/aarch64/me_cmp_neon.S
> index 46d4dade5d..9fe96e111c 100644
> --- a/libavcodec/aarch64/me_cmp_neon.S
> +++ b/libavcodec/aarch64/me_cmp_neon.S
> @@ -889,3 +889,129 @@ function vsse_intra16_neon, export=1
>
> ret
> endfunc
> +
> +function nsse16_neon, export=1
> + // x0 multiplier
> + // x1 uint8_t *pix1
> + // x2 uint8_t *pix2
> + // x3 ptrdiff_t stride
> + // w4 int h
> +
> + str x0, [sp, #-0x40]!
> + stp x1, x2, [sp, #0x10]
> + stp x3, x4, [sp, #0x20]
> + str lr, [sp, #0x30]
> + bl sse16_neon
> + ldr lr, [sp, #0x30]
> + mov w9, w0 // here we store score1
> + ldr x5, [sp]
> + ldp x1, x2, [sp, #0x10]
> + ldp x3, x4, [sp, #0x20]
> + add sp, sp, #0x40
> +
> + movi v16.8h, #0
> + movi v17.8h, #0
> + movi v18.8h, #0
> + movi v19.8h, #0
> +
> + mov x10, x1 // x1
> + mov x14, x2 // x2
I don't see why you need to make a copy of x1/x2 here, as you don't use
x1/x2 after this at all.
> + add x11, x1, x3 // x1 + stride
> + add x15, x2, x3 // x2 + stride
> + add x12, x1, #1 // x1 + 1
> + add x16, x2, #1 // x2 + 1
FWIW, instead of making two loads, for [x1] and [x1+1], as we don't need
the final value at [x1+16], I would normally just do one load of [x1] and
then make a shifted version with the 'ext' instruction; ext is generally
cheaper than doing redundant loads. On the other hand, by doing two loads,
you don't have a serial dependency on the first load.
> +// iterate by one
> +2:
> + ld1 {v0.16b}, [x10], x3
> + ld1 {v1.16b}, [x11], x3
> + ld1 {v2.16b}, [x12], x3
> + usubl v31.8h, v0.8b, v1.8b
> + ld1 {v3.16b}, [x13], x3
> + usubl2 v30.8h, v0.16b, v1.16b
> + usubl v29.8h, v2.8b, v3.8b
> + usubl2 v28.8h, v2.16b, v3.16b
> + saba v16.8h, v31.8h, v29.8h
> + ld1 {v4.16b}, [x14], x3
> + ld1 {v5.16b}, [x15], x3
> + saba v17.8h, v30.8h, v28.8h
> + ld1 {v6.16b}, [x16], x3
> + usubl v27.8h, v4.8b, v5.8b
> + ld1 {v7.16b}, [x17], x3
So, looking at the main implementation structure here, by looking at the
non-unrolled version: You're doing 8 loads per iteration here - and I
would say you can do this with 2 loads per iteration.
By reusing the loaded data from the previous iteration instead of
duplicated loading, you can get this down from 8 to 4 loads. And by
shifting with 'ext' instead of a separate load, you can get it down to 2
loads. (Then again, with 4 loads instead of 2, you can have the
overlapping loads running in parallel, instead of having to wait for the
first load to complete if using ext. I'd suggest trying both and seeing
which one worke better - although the tradeoff might be different between
different cores. But storing data from the previous line instead of such
duplicated loading is certainly better in any case.)
> + usubl2 v26.8h, v4.16b, v5.16b
> + usubl v25.8h, v6.8b, v7.8b
> + usubl2 v24.8h, v6.16b, v7.16b
> + saba v18.8h, v27.8h, v25.8h
> + subs w4, w4, #1
> + saba v19.8h, v26.8h, v24.8h
> +
> + cbnz w4, 2b
> +
> +3:
> + sqsub v16.8h, v16.8h, v18.8h
> + sqsub v17.8h, v17.8h, v19.8h
> + ins v17.h[7], wzr
This is very good, that you figured out how to handle the odd element here
outside of the loops!
// 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-request@ffmpeg.org with subject "unsubscribe".
^ permalink raw reply [flat|nested] 13+ messages in thread
* Re: [FFmpeg-devel] [PATCH 5/5] lavc/aarch64: Provide neon implementation of nsse16
2022-08-22 15:26 ` [FFmpeg-devel] [PATCH 5/5] lavc/aarch64: Provide neon implementation of nsse16 Hubert Mazur
@ 2022-09-02 21:29 ` Martin Storsjö
2022-09-04 21:23 ` Martin Storsjö
1 sibling, 0 replies; 13+ messages in thread
From: Martin Storsjö @ 2022-09-02 21:29 UTC (permalink / raw)
To: Hubert Mazur; +Cc: gjb, upstream, jswinney, ffmpeg-devel, mw, spop
On Mon, 22 Aug 2022, Hubert Mazur wrote:
> Add vectorized implementation of nsse16 function.
>
> Performance comparison tests are shown below.
> - nsse_0_c: 707.0
> - nsse_0_neon: 120.0
>
> Benchmarks and tests run with checkasm tool on AWS Graviton 3.
>
> Signed-off-by: Hubert Mazur <hum@semihalf.com>
> ---
> libavcodec/aarch64/me_cmp_init_aarch64.c | 15 +++
> libavcodec/aarch64/me_cmp_neon.S | 126 +++++++++++++++++++++++
> 2 files changed, 141 insertions(+)
>
> diff --git a/libavcodec/aarch64/me_cmp_neon.S b/libavcodec/aarch64/me_cmp_neon.S
> index 46d4dade5d..9fe96e111c 100644
> --- a/libavcodec/aarch64/me_cmp_neon.S
> +++ b/libavcodec/aarch64/me_cmp_neon.S
> @@ -889,3 +889,129 @@ function vsse_intra16_neon, export=1
>
> ret
> endfunc
> +
> +function nsse16_neon, export=1
> + // x0 multiplier
> + // x1 uint8_t *pix1
> + // x2 uint8_t *pix2
> + // x3 ptrdiff_t stride
> + // w4 int h
> +
> + str x0, [sp, #-0x40]!
> + stp x1, x2, [sp, #0x10]
> + stp x3, x4, [sp, #0x20]
> + str lr, [sp, #0x30]
> + bl sse16_neon
> + ldr lr, [sp, #0x30]
This breaks building in two configurations; old binutils doesn't recognize
the register name lr, you need to spell out x30.
Building on macOS breaks since there's no symbol named sse16_neon; this is
an exported function, so it has got the symbol prefix _. So you need to do
"bl X(sse16_neon)" here.
Didn't look at the code from a performance perspective yet.
// 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-request@ffmpeg.org with subject "unsubscribe".
^ permalink raw reply [flat|nested] 13+ messages in thread
* [FFmpeg-devel] [PATCH 5/5] lavc/aarch64: Provide neon implementation of nsse16
2022-08-22 15:26 [FFmpeg-devel] [PATCH 0/5] me_cmp: Provide arm64 neon implementations Hubert Mazur
@ 2022-08-22 15:26 ` Hubert Mazur
2022-09-02 21:29 ` Martin Storsjö
2022-09-04 21:23 ` Martin Storsjö
0 siblings, 2 replies; 13+ messages in thread
From: Hubert Mazur @ 2022-08-22 15:26 UTC (permalink / raw)
To: ffmpeg-devel; +Cc: gjb, upstream, jswinney, Hubert Mazur, martin, mw, spop
Add vectorized implementation of nsse16 function.
Performance comparison tests are shown below.
- nsse_0_c: 707.0
- nsse_0_neon: 120.0
Benchmarks and tests run with checkasm tool on AWS Graviton 3.
Signed-off-by: Hubert Mazur <hum@semihalf.com>
---
libavcodec/aarch64/me_cmp_init_aarch64.c | 15 +++
libavcodec/aarch64/me_cmp_neon.S | 126 +++++++++++++++++++++++
2 files changed, 141 insertions(+)
diff --git a/libavcodec/aarch64/me_cmp_init_aarch64.c b/libavcodec/aarch64/me_cmp_init_aarch64.c
index 8c295d5457..146ef04345 100644
--- a/libavcodec/aarch64/me_cmp_init_aarch64.c
+++ b/libavcodec/aarch64/me_cmp_init_aarch64.c
@@ -49,6 +49,10 @@ 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,
ptrdiff_t stride, int h);
+int nsse16_neon(int multiplier, const uint8_t *s, const uint8_t *s2,
+ ptrdiff_t stride, int h);
+int nsse16_neon_wrapper(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)
{
@@ -72,5 +76,16 @@ av_cold void ff_me_cmp_init_aarch64(MECmpContext *c, AVCodecContext *avctx)
c->vsse[0] = vsse16_neon;
c->vsse[4] = vsse_intra16_neon;
+
+ c->nsse[0] = nsse16_neon_wrapper;
}
}
+
+int nsse16_neon_wrapper(MpegEncContext *c, const uint8_t *s1, const uint8_t *s2,
+ ptrdiff_t stride, int h)
+{
+ if (c)
+ return nsse16_neon(c->avctx->nsse_weight, s1, s2, stride, h);
+ else
+ return nsse16_neon(8, s1, s2, stride, h);
+}
\ No newline at end of file
diff --git a/libavcodec/aarch64/me_cmp_neon.S b/libavcodec/aarch64/me_cmp_neon.S
index 46d4dade5d..9fe96e111c 100644
--- a/libavcodec/aarch64/me_cmp_neon.S
+++ b/libavcodec/aarch64/me_cmp_neon.S
@@ -889,3 +889,129 @@ function vsse_intra16_neon, export=1
ret
endfunc
+
+function nsse16_neon, export=1
+ // x0 multiplier
+ // x1 uint8_t *pix1
+ // x2 uint8_t *pix2
+ // x3 ptrdiff_t stride
+ // w4 int h
+
+ str x0, [sp, #-0x40]!
+ stp x1, x2, [sp, #0x10]
+ stp x3, x4, [sp, #0x20]
+ str lr, [sp, #0x30]
+ bl sse16_neon
+ ldr lr, [sp, #0x30]
+ mov w9, w0 // here we store score1
+ ldr x5, [sp]
+ ldp x1, x2, [sp, #0x10]
+ ldp x3, x4, [sp, #0x20]
+ add sp, sp, #0x40
+
+ movi v16.8h, #0
+ movi v17.8h, #0
+ movi v18.8h, #0
+ movi v19.8h, #0
+
+ mov x10, x1 // x1
+ mov x14, x2 // x2
+ add x11, x1, x3 // x1 + stride
+ add x15, x2, x3 // x2 + stride
+ add x12, x1, #1 // x1 + 1
+ add x16, x2, #1 // x2 + 1
+ add x13, x11, #1 // x1 + stride + 1
+ add x17, x15, #1 // x2 + stride + 1
+
+ subs w4, w4, #1 // we need to make h-1 iterations
+ cmp w4, #2
+ b.lt 2f
+
+// make 2 iterations at once
+1:
+ ld1 {v0.16b}, [x10], x3
+ ld1 {v1.16b}, [x11], x3
+ ld1 {v2.16b}, [x12], x3
+ usubl v31.8h, v0.8b, v1.8b
+ ld1 {v3.16b}, [x13], x3
+ usubl2 v30.8h, v0.16b, v1.16b
+ usubl v29.8h, v2.8b, v3.8b
+ usubl2 v28.8h, v2.16b, v3.16b
+ ld1 {v4.16b}, [x14], x3
+ saba v16.8h, v31.8h, v29.8h
+ ld1 {v5.16b}, [x15], x3
+ ld1 {v6.16b}, [x16], x3
+ saba v17.8h, v30.8h, v28.8h
+ ld1 {v7.16b}, [x17], x3
+ usubl v27.8h, v4.8b, v5.8b
+ usubl2 v26.8h, v4.16b, v5.16b
+ usubl v25.8h, v6.8b, v7.8b
+ ld1 {v31.16b}, [x10], x3
+ saba v18.8h, v27.8h, v25.8h
+ usubl2 v24.8h, v6.16b, v7.16b
+ ld1 {v30.16b}, [x11], x3
+ ld1 {v29.16b}, [x12], x3
+ saba v19.8h, v26.8h, v24.8h
+ usubl v23.8h, v31.8b, v30.8b
+ ld1 {v28.16b}, [x13], x3
+ usubl2 v22.8h, v31.16b, v30.16b
+ usubl v21.8h, v29.8b, v28.8b
+ ld1 {v27.16b}, [x14], x3
+ usubl2 v20.8h, v29.16b, v28.16b
+ saba v16.8h, v23.8h, v21.8h
+ ld1 {v26.16b}, [x15], x3
+ ld1 {v25.16b}, [x16], x3
+ saba v17.8h, v22.8h, v20.8h
+ ld1 {v24.16b}, [x17], x3
+ usubl v31.8h, v27.8b, v26.8b
+ usubl v29.8h, v25.8b, v24.8b
+ usubl2 v30.8h, v27.16b, v26.16b
+ saba v18.8h, v31.8h, v29.8h
+ usubl2 v28.8h, v25.16b, v24.16b
+ sub w4, w4, #2
+ cmp w4, #2
+ saba v19.8h, v30.8h, v28.8h
+
+ b.ge 1b
+ cbz w4, 3f
+
+// iterate by one
+2:
+ ld1 {v0.16b}, [x10], x3
+ ld1 {v1.16b}, [x11], x3
+ ld1 {v2.16b}, [x12], x3
+ usubl v31.8h, v0.8b, v1.8b
+ ld1 {v3.16b}, [x13], x3
+ usubl2 v30.8h, v0.16b, v1.16b
+ usubl v29.8h, v2.8b, v3.8b
+ usubl2 v28.8h, v2.16b, v3.16b
+ saba v16.8h, v31.8h, v29.8h
+ ld1 {v4.16b}, [x14], x3
+ ld1 {v5.16b}, [x15], x3
+ saba v17.8h, v30.8h, v28.8h
+ ld1 {v6.16b}, [x16], x3
+ usubl v27.8h, v4.8b, v5.8b
+ ld1 {v7.16b}, [x17], x3
+ usubl2 v26.8h, v4.16b, v5.16b
+ usubl v25.8h, v6.8b, v7.8b
+ usubl2 v24.8h, v6.16b, v7.16b
+ saba v18.8h, v27.8h, v25.8h
+ subs w4, w4, #1
+ saba v19.8h, v26.8h, v24.8h
+
+ cbnz w4, 2b
+
+3:
+ sqsub v16.8h, v16.8h, v18.8h
+ sqsub v17.8h, v17.8h, v19.8h
+ ins v17.h[7], wzr
+ sqadd v16.8h, v16.8h, v17.8h
+ saddlv s16, v16.8h
+ sqabs s16, s16
+ fmov w0, s16
+
+ mul w0, w0, w5
+ add w0, w0, w9
+
+ ret
+endfunc
--
2.34.1
_______________________________________________
ffmpeg-devel mailing list
ffmpeg-devel@ffmpeg.org
https://ffmpeg.org/mailman/listinfo/ffmpeg-devel
To unsubscribe, visit link above, or email
ffmpeg-devel-request@ffmpeg.org with subject "unsubscribe".
^ permalink raw reply [flat|nested] 13+ messages in thread
end of thread, other threads:[~2022-09-08 9:26 UTC | newest]
Thread overview: 13+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2022-09-06 10:27 [FFmpeg-devel] [PATCH 0/5] Provide optimized neon implementation Hubert Mazur
2022-09-06 10:27 ` [FFmpeg-devel] [PATCH 1/5] lavc/aarch64: Add neon implementation for vsad16 Hubert Mazur
2022-09-06 10:27 ` [FFmpeg-devel] [PATCH 2/5] lavc/aarch64: Add neon implementation of vsse16 Hubert Mazur
2022-09-07 8:57 ` Martin Storsjö
2022-09-06 10:27 ` [FFmpeg-devel] [PATCH 3/5] lavc/aarch64: Add neon implementation for vsad_intra16 Hubert Mazur
2022-09-06 10:27 ` [FFmpeg-devel] [PATCH 4/5] lavc/aarch64: Add neon implementation for vsse_intra16 Hubert Mazur
2022-09-06 10:27 ` [FFmpeg-devel] [PATCH 5/5] lavc/aarch64: Provide neon implementation of nsse16 Hubert Mazur
2022-09-07 9:06 ` Martin Storsjö
2022-09-07 8:55 ` [FFmpeg-devel] [PATCH 0/5] Provide optimized neon implementation Martin Storsjö
-- strict thread matches above, loose matches on Subject: below --
2022-09-08 9:25 Hubert Mazur
2022-09-08 9:25 ` [FFmpeg-devel] [PATCH 5/5] lavc/aarch64: Provide neon implementation of nsse16 Hubert Mazur
2022-08-22 15:26 [FFmpeg-devel] [PATCH 0/5] me_cmp: Provide arm64 neon implementations Hubert Mazur
2022-08-22 15:26 ` [FFmpeg-devel] [PATCH 5/5] lavc/aarch64: Provide neon implementation of nsse16 Hubert Mazur
2022-09-02 21:29 ` Martin Storsjö
2022-09-04 21:23 ` Martin Storsjö
Git Inbox Mirror of the ffmpeg-devel mailing list - see https://ffmpeg.org/mailman/listinfo/ffmpeg-devel
This inbox may be cloned and mirrored by anyone:
git clone --mirror https://master.gitmailbox.com/ffmpegdev/0 ffmpegdev/git/0.git
# If you have public-inbox 1.1+ installed, you may
# initialize and index your mirror using the following commands:
public-inbox-init -V2 ffmpegdev ffmpegdev/ https://master.gitmailbox.com/ffmpegdev \
ffmpegdev@gitmailbox.com
public-inbox-index ffmpegdev
Example config snippet for mirrors.
AGPL code for this site: git clone https://public-inbox.org/public-inbox.git