The current implementation generates stack loads/stores, which are
really just mov instructions from/to "special" registers. This may
not be the most efficient implementation, compared to an approach where
the stack registers are directly folded into instructions, but this is
easier to implement and I have yet to see a case where ptxas is unable
to see through this kind of register usage and know what is really
going on.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@133443 91177308-0d34-0410-b5e6-96231b3b80d8
