Am So., 2. Juli 2023 um 14:34 Uhr schrieb John Cox <j...@kynesim.co.uk>:
Add an optional filter_line3 to the available optimisations.
filter_line3 is equivalent to filter_line, memcpy, filter_line
filter_line shares quite a number of loads and some calculations
in
common with its next iteration and testing shows that using
aarch64
neon filter_line3s performance is 30% better than two
filter_lines
and a memcpy.
Signed-off-by: John Cox <j...@kynesim.co.uk>
---
libavfilter/bwdif.h | 7 +++++++
libavfilter/vf_bwdif.c | 31 +++++++++++++++++++++++++++++++
2 files changed, 38 insertions(+)
diff --git a/libavfilter/bwdif.h b/libavfilter/bwdif.h
index cce99953f3..496cec72ef 100644
--- a/libavfilter/bwdif.h
+++ b/libavfilter/bwdif.h
@@ -35,6 +35,9 @@ typedef struct BWDIFContext {
void (*filter_edge)(void *dst, void *prev, void *cur, void
*next,
int w, int prefs, int mrefs, int
prefs2, int mrefs2,
int parity, int clip_max, int spat);
+ void (*filter_line3)(void *dst, int dstride,
+ const void *prev, const void *cur,
const void *next, int prefs,
+ int w, int parity, int clip_max);
} BWDIFContext;
void ff_bwdif_init_filter_line(BWDIFContext *bwdif, int
bit_depth);
@@ -53,4 +56,8 @@ void ff_bwdif_filter_line_c(void *dst1, void
*prev1, void *cur1, void *next1,
int prefs3, int mrefs3, int prefs4,
int mrefs4,
int parity, int clip_max);
+void ff_bwdif_filter_line3_c(void * dst1, int d_stride,
+ const void * prev1, const void *
cur1, const void * next1, int s_stride,
+ int w, int parity, int clip_max);
+
#endif /* AVFILTER_BWDIF_H */
diff --git a/libavfilter/vf_bwdif.c b/libavfilter/vf_bwdif.c
index 26349da1fd..52bc676cf8 100644
--- a/libavfilter/vf_bwdif.c
+++ b/libavfilter/vf_bwdif.c
@@ -150,6 +150,31 @@ void ff_bwdif_filter_line_c(void *dst1,
void *prev1, void *cur1, void *next1,
FILTER2()
}
+#define NEXT_LINE()\
+ dst += d_stride; \
+ prev += prefs; \
+ cur += prefs; \
+ next += prefs;
+
+void ff_bwdif_filter_line3_c(void * dst1, int d_stride,
+ const void * prev1, const void *
cur1, const void * next1, int s_stride,
+ int w, int parity, int clip_max)
+{
+ const int prefs = s_stride;
+ uint8_t * dst = dst1;
+ const uint8_t * prev = prev1;
+ const uint8_t * cur = cur1;
+ const uint8_t * next = next1;
+
+ ff_bwdif_filter_line_c(dst, (void*)prev, (void*)cur,
(void*)next, w,
+ prefs, -prefs, prefs * 2, - prefs *
2, prefs * 3, -prefs * 3, prefs * 4, -prefs * 4, parity,
clip_max);
+ NEXT_LINE();
+ memcpy(dst, cur, w);
+ NEXT_LINE();
+ ff_bwdif_filter_line_c(dst, (void*)prev, (void*)cur,
(void*)next, w,
+ prefs, -prefs, prefs * 2, - prefs *
2, prefs * 3, -prefs * 3, prefs * 4, -prefs * 4, parity,
clip_max);
+}
+
void ff_bwdif_filter_edge_c(void *dst1, void *prev1, void
*cur1, void *next1,
int w, int prefs, int mrefs, int
prefs2, int mrefs2,
int parity, int clip_max, int spat)
@@ -244,6 +269,11 @@ static int filter_slice(AVFilterContext
*ctx, void *arg, int jobnr, int nb_jobs)
refs << 1, -(refs << 1),
td->parity ^ td->tff, clip_max,
(y < 2) || ((y + 3) > td->h) ? 0
: 1);
+ } else if (s->filter_line3 && y + 2 < slice_end &&
y + 6 < td->h) {
+ s->filter_line3(dst,
td->frame->linesize[td->plane],
+ prev, cur, next, linesize,
td->w,
+ td->parity ^ td->tff,
clip_max);
+ y += 2;
} else {
s->filter_line(dst, prev, cur, next, td->w,
refs, -refs, refs << 1, -(refs
<< 1),
Maybe I'm missing something, but doesn't this kick out most of the x86 SIMD
optimization because there is no filter_line3?
