[FFmpeg-cvslog] arm: vp9lpf: Interleave the start of flat8in into the calculation above

[Martin Storsjö]

ffmpeg | branch: master | Martin Storsjö <martin at martin.st> | Tue Jan 10 16:49:13 2017 +0200| [e18c39005ad1dbb178b336f691da1de91afd434e] | committer: Martin Storsjö

arm: vp9lpf: Interleave the start of flat8in into the calculation above

This adds lots of extra .ifs, but speeds it up by a couple cycles,
by avoiding stalls.

Signed-off-by: Martin Storsjö <martin at martin.st>

> http://git.videolan.org/gitweb.cgi/ffmpeg.git/?a=commit;h=e18c39005ad1dbb178b336f691da1de91afd434e
---

 libavcodec/arm/vp9lpf_neon.S | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/libavcodec/arm/vp9lpf_neon.S b/libavcodec/arm/vp9lpf_neon.S
index c2f1c95427..1e161e0c63 100644
--- a/libavcodec/arm/vp9lpf_neon.S
+++ b/libavcodec/arm/vp9lpf_neon.S
@@ -182,16 +182,20 @@
 
         vmovl.u8        q0,  d22                @ p1
         vmovl.u8        q1,  d25                @ q1
+.if \wd >= 8
+        vmov            r2,  r3,  d6
+.endif
         vaddw.s8        q0,  q0,  \tmp3         @ p1 + f
         vsubw.s8        q1,  q1,  \tmp3         @ q1 - f
+.if \wd >= 8
+        orrs            r2,  r2,  r3
+.endif
         vqmovun.s16     d0,  q0                 @ out p1
         vqmovun.s16     d2,  q1                 @ out q1
         vbit            d22, d0,  d5            @ if (!hev && fm && !flat8in)
         vbit            d25, d2,  d5
 
 .if \wd >= 8
-        vmov            r2,  r3,  d6
-        orrs            r2,  r2,  r3
         @ If no pixels need flat8in, jump to flat8out
         @ (or to a writeout of the inner 4 pixels, for wd=8)
         beq             6f