Blender Git Loki

Cycles: Fix preprocessor directives around SSE3 replacement functions

The code is supposed to implement replacements for a few SSE4.1-specific functions so that they can be used with SSE3 as well.
Therefore, it was enabled when __KERNEL_SSE3__ was set, but __KERNEL_SSE4__ wasn't.

However, __KERNEL_SSE4__ is never set anywhere - the correct one is __KERNEL_SSE41__.
Because of that, the replacements were enabled for SSE4.1 and better (AVX) as well, where they're not needed, but only slow things down.