Signed-off-by: John Cox <j...@kynesim.co.uk>
---
libavfilter/aarch64/vf_bwdif_init_aarch64.c | 17 +++++++
libavfilter/aarch64/vf_bwdif_neon.S | 53 +++++++++++++++++++++
2 files changed, 70 insertions(+)
diff --git a/libavfilter/aarch64/vf_bwdif_init_aarch64.c
b/libavfilter/aarch64/vf_bwdif_init_aarch64.c
index 86d53b2ca1..3ffaa07ab3 100644
--- a/libavfilter/aarch64/vf_bwdif_init_aarch64.c
+++ b/libavfilter/aarch64/vf_bwdif_init_aarch64.c
@@ -24,6 +24,22 @@
#include "libavfilter/bwdif.h"
#include "libavutil/aarch64/cpu.h"
+void ff_bwdif_filter_intra_neon(void *dst1, void *cur1, int w, int prefs, int
mrefs,
+ int prefs3, int mrefs3, int parity, int
clip_max);
+
+
+static void filter_intra_helper(void *dst1, void *cur1, int w, int prefs, int
mrefs,
+ int prefs3, int mrefs3, int parity, int
clip_max)
+{
+ const int w0 = clip_max != 255 ? 0 : w & ~15;
+
+ ff_bwdif_filter_intra_neon(dst1, cur1, w0, prefs, mrefs, prefs3, mrefs3,
parity, clip_max);
+
+ if (w0 < w)
+ ff_bwdif_filter_intra_c((char *)dst1 + w0, (char *)cur1 + w0,
+ w - w0, prefs, mrefs, prefs3, mrefs3, parity,
clip_max);
+}
+
void
ff_bwdif_init_aarch64(BWDIFContext *s, int bit_depth)
{
@@ -35,5 +51,6 @@ ff_bwdif_init_aarch64(BWDIFContext *s, int bit_depth)
if (!have_neon(cpu_flags))
return;
+ s->filter_intra = filter_intra_helper;
}
diff --git a/libavfilter/aarch64/vf_bwdif_neon.S
b/libavfilter/aarch64/vf_bwdif_neon.S
index a8f0ed525a..b863b3447d 100644
--- a/libavfilter/aarch64/vf_bwdif_neon.S
+++ b/libavfilter/aarch64/vf_bwdif_neon.S
@@ -69,3 +69,56 @@ coeffs:
.hword 5570, 3801, 1016, -3801 // hf[0] = v0.h[2],
-hf[1] = v0.h[5]
.hword 5077, 981 // sp[0] = v0.h[6]
+// ============================================================================
+//
+// void ff_bwdif_filter_intra_neon(
+// void *dst1, // x0
+// void *cur1, // x1
+// int w, // w2
+// int prefs, // w3
+// int mrefs, // w4
+// int prefs3, // w5
+// int mrefs3, // w6
+// int parity, // w7 unused
+// int clip_max) // [sp, #0] unused
+
+function ff_bwdif_filter_intra_neon, export=1
+ cmp w2, #0
+ ble 99f
+
+ ldr q0, coeffs
+
+// for (x = 0; x < w; x++) {
+10:
+
+// interpol = (coef_sp[0] * (cur[mrefs] + cur[prefs]) - coef_sp[1] *
(cur[mrefs3] + cur[prefs3])) >> 13;
+ ldr q31, [x1, w4, SXTW]
+ ldr q30, [x1, w3, SXTW]
+ ldr q29, [x1, w6, SXTW]
+ ldr q28, [x1, w5, SXTW]
+
+ uaddl v20.8h, v31.8b, v30.8b
+ uaddl2 v21.8h, v31.16b, v30.16b
+
+ UMULL4K v2, v3, v4, v5, v20, v21, v0.h[6]
+
+ uaddl v20.8h, v29.8b, v28.8b
+ uaddl2 v21.8h, v29.16b, v28.16b
+
+ UMLSL4K v2, v3, v4, v5, v20, v21, v0.h[7]
+
+// dst[0] = av_clip(interpol, 0, clip_max);
+ SQSHRUNN v2, v2, v3, v4, v5, 13
+ str q2, [x0], #16
+
+// dst++;
+// cur++;
+// }
+
+ subs w2, w2, #16
+ add x1, x1, #16
+ bgt 10b
+
+99:
+ ret
+endfunc
--
2.39.2
_______________________________________________
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".
