swscale/x86/yuv2yuvX: use movq to load 8 bytes in all non-AVX2 functions

mova expands to movq on non-XMM functions

Signed-off-by: James Almer <jamrial@gmail.com>

diff --git a/libswscale/x86/yuv2yuvX.asm b/libswscale/x86/yuv2yuvX.asm
index a6b70d52477bf60b0222e893bc9227bb23ccb229..062028471aad4b997f24b5d6f8d627d0f17ddfff 100644 (file)
--- a/libswscale/x86/yuv2yuvX.asm
+++ b/libswscale/x86/yuv2yuvX.asm
@@ -47,10 +47,8 @@ cglobal yuv2yuvX, 7, 7, 8, filter, filterSize, src, dest, dstW, dither, offset
 %endif ; x86-64
 %if cpuflag(avx2)
     vpbroadcastq         m3, [ditherq]
-%elif cpuflag(sse3)
-    movq                 xmm3, [ditherq]
 %else
-    mova                 m3, [ditherq]
+    movq                 xm3, [ditherq]
 %endif ; avx2
     cmp                  offsetd, 0
     jz                   .offset