dsputil x86: use SSE float instruction instead of SSE2 integer equivalent

All the more required since the users are pure SSE functions.
Signed-off-by: Ronald S. Bultje <rsbultje@gmail.com>

libavcodec/x86/dsputil_yasm.asm

@@ -473,7 +473,7 @@ cglobal scalarproduct_float_sse, 3,3,2, v1, v2, offset
     shufps  xmm0, xmm0, 1
     addss   xmm0, xmm1
 %if ARCH_X86_64 == 0
-    movd    r0m,  xmm0
+    movss   r0m,  xmm0
     fld     dword r0m
 %endif
     RET

libavcodec/x86/sbrdsp.asm

@@ -68,7 +68,7 @@ cglobal sbr_sum_square, 2, 3, 6
     shufps      m0, m0, 1
     addss       m0, m1
 %if ARCH_X86_64 == 0
-    movd        r0m,  m0
+    movss       r0m,  m0
     fld         dword r0m
 %endif
     RET