[AMDGPU] fcaninicalize optimization for GFX9+

[AMDGPU] fcaninicalize optimization for GFX9+

Since GFX9 supports denorm modes for v_min_f32/v_max_f32 that
is possible to further optimize fcanonicalize and remove it
if applied to min/max given their operands are known not to be
an sNaN or that sNaNs are not supported.

Additionally we can remove fcanonicalize if denorms are supported
for the VT and we know that its argument is never a NaN.

Differential Revision: https://reviews.llvm.org/D35335

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@307976 91177308-0d34-0410-b5e6-96231b3b80d8