[X86][SSE] Lower shuffle as ANY_EXTEND_VECTOR_INREG

[X86][SSE] Lower shuffle as ANY_EXTEND_VECTOR_INREG

On SSE41+ targets we always lower vector shuffles to ZERO_EXTEND_VECTOR_INREG, even if we don't need the extended bits.

This patch relaxes this so that we lower to ANY_EXTEND_VECTOR_INREG if we can, meaning that shuffle combines have a better idea of what elements need to be kept zero. This helps the multiple reduction code as we can now combine away a lot more of the pack+extend codes.

Differential Revision: https://reviews.llvm.org/D65741

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@368515 91177308-0d34-0410-b5e6-96231b3b80d8