[AMDGPU] Enable LICM in the BE pipeline

This allows to hoist code portion to compute reciprocal of loop
invariant denominator in integer division after codegen prepare
expansion.

Differential Revision: https://reviews.llvm.org/D48604

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@335988 91177308-0d34-0410-b5e6-96231b3b80d8
9 files changed