[FFmpeg-cvslog] x86/vf_w3fdif: use aligned loads in w3fdif_simple_high

[James Almer]

ffmpeg | branch: master | James Almer <jamrial at gmail.com> | Sun Oct 11 20:07:12 2015 -0300| [224a529b449f1c159921fb3014dbd0de591e12c5] | committer: James Almer

x86/vf_w3fdif: use aligned loads in w3fdif_simple_high

Found-by: Ronald S. Bultje <rsbultje at gmail.com>
Signed-off-by: James Almer <jamrial at gmail.com>

> http://git.videolan.org/gitweb.cgi/ffmpeg.git/?a=commit;h=224a529b449f1c159921fb3014dbd0de591e12c5
---

 libavfilter/x86/vf_w3fdif.asm |    6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/libavfilter/x86/vf_w3fdif.asm b/libavfilter/x86/vf_w3fdif.asm
index f2001a4..fb33f41 100644
--- a/libavfilter/x86/vf_w3fdif.asm
+++ b/libavfilter/x86/vf_w3fdif.asm
@@ -143,10 +143,8 @@ cglobal w3fdif_simple_high, 5, 9, 8, 0, work_line, in_lines_cur0, in_lines_adj0,
     pmaddwd                                m6, m2
     paddd                                  m3, m5
     paddd                                  m4, m6
-    movu                                   m5, [work_lineq+offsetq*4]
-    movu                                   m6, [work_lineq+offsetq*4+mmsize]
-    paddd                                  m3, m5
-    paddd                                  m4, m6
+    paddd                                  m3, [work_lineq+offsetq*4]
+    paddd                                  m4, [work_lineq+offsetq*4+mmsize]
     mova               [work_lineq+offsetq*4], m3
     mova        [work_lineq+offsetq*4+mmsize], m4
     add                               offsetq, mmsize/2