Eliminates some more cases where some subset of the addressing
computation remains flat. Some cases with addrspacecasts
in nested constant expressions are still left behind however.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@301704 91177308-0d34-0410-b5e6-96231b3b80d8
Fixes leaving intermediate flat addressing computations
where a GEP instruction's source is a constant expression.
Still leaves behind a trivial addrspacecast + gep pair that
instcombine is able to handle, which ideally could be folded
here directly.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@301044 91177308-0d34-0410-b5e6-96231b3b80d8
Currently the default C calling convention functions are treated
the same as compute kernels. Make this explicit so the default
calling convention can be changed to a non-kernel.
Converted with perl -pi -e 's/define void/define amdgpu_kernel void/'
on the relevant test directories (and undoing in one place that actually
wanted a non-kernel).
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@298444 91177308-0d34-0410-b5e6-96231b3b80d8
For now just port some of the existing NVPTX tests
and from an old HSAIL optimization pass which
approximately did the same thing.
Don't enable the pass yet until more testing is done.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@293580 91177308-0d34-0410-b5e6-96231b3b80d8
Matt Arsenault