[FFmpeg-devel] [PATCH v2 02/15] avfilter/vf_bwdif: Add common macros and consts for aarch64 neon

[John Cox]

Add macros for dual scalar half->single multiply and accumulate
Add macro for shift, saturate and shorten single to byte
Add filter constants

Signed-off-by: John Cox <jc at kynesim.co.uk>
---
 libavfilter/aarch64/vf_bwdif_neon.S | 53 +++++++++++++++++++++++++++++
 1 file changed, 53 insertions(+)

diff --git a/libavfilter/aarch64/vf_bwdif_neon.S b/libavfilter/aarch64/vf_bwdif_neon.S
index 639ab22998..c2f5eb1f73 100644
--- a/libavfilter/aarch64/vf_bwdif_neon.S
+++ b/libavfilter/aarch64/vf_bwdif_neon.S
@@ -23,3 +23,56 @@
 
 #include "libavutil/aarch64/asm.S"
 
+// Space taken on the stack by an int (32-bit)
+#ifdef __APPLE__
+.set    SP_INT, 4
+#else
+.set    SP_INT, 8
+#endif
+
+.macro SQSHRUNN b, s0, s1, s2, s3, n
+        sqshrun         \s0\().4h, \s0\().4s, #\n - 8
+        sqshrun2        \s0\().8h, \s1\().4s, #\n - 8
+        sqshrun         \s1\().4h, \s2\().4s, #\n - 8
+        sqshrun2        \s1\().8h, \s3\().4s, #\n - 8
+        uzp2            \b\().16b, \s0\().16b, \s1\().16b
+.endm
+
+.macro SMULL4K a0, a1, a2, a3, s0, s1, k
+        smull           \a0\().4s, \s0\().4h, \k
+        smull2          \a1\().4s, \s0\().8h, \k
+        smull           \a2\().4s, \s1\().4h, \k
+        smull2          \a3\().4s, \s1\().8h, \k
+.endm
+
+.macro UMULL4K a0, a1, a2, a3, s0, s1, k
+        umull           \a0\().4s, \s0\().4h, \k
+        umull2          \a1\().4s, \s0\().8h, \k
+        umull           \a2\().4s, \s1\().4h, \k
+        umull2          \a3\().4s, \s1\().8h, \k
+.endm
+
+.macro UMLAL4K a0, a1, a2, a3, s0, s1, k
+        umlal           \a0\().4s, \s0\().4h, \k
+        umlal2          \a1\().4s, \s0\().8h, \k
+        umlal           \a2\().4s, \s1\().4h, \k
+        umlal2          \a3\().4s, \s1\().8h, \k
+.endm
+
+.macro UMLSL4K a0, a1, a2, a3, s0, s1, k
+        umlsl           \a0\().4s, \s0\().4h, \k
+        umlsl2          \a1\().4s, \s0\().8h, \k
+        umlsl           \a2\().4s, \s1\().4h, \k
+        umlsl2          \a3\().4s, \s1\().8h, \k
+.endm
+
+// static const uint16_t coef_lf[2] = { 4309, 213 };
+// static const uint16_t coef_hf[3] = { 5570, 3801, 1016 };
+// static const uint16_t coef_sp[2] = { 5077, 981 };
+
+        .balign 16
+coeffs:
+        .hword          4309 * 4, 213 * 4               // lf[0]*4 = v0.h[0]
+        .hword          5570, 3801, 1016, -3801         // hf[0] = v0.h[2], -hf[1] = v0.h[5]
+        .hword          5077, 981                       // sp[0] = v0.h[6]
+
-- 
2.39.2