[CostModel][X86] Fix constant vector XOP rights shifts

We'll constant fold these cases so they are as cheap as vector left shift cases.

Noticed while improving funnel shift costs.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@346760 91177308-0d34-0410-b5e6-96231b3b80d8
3 files changed