[llvm] [AMDGPU] Enable amdgpu-sw-lower-lds pass to lower LDS accesses to use device global memory (PR #87265)

[Matt Arsenault via llvm-commits]

================
@@ -234,17 +235,6 @@ cl::opt<LoweringKind> LoweringKindLoc(
         clEnumValN(LoweringKind::hybrid, "hybrid",
                    "Lower via mixture of above strategies")));
 
-bool isKernelLDS(const Function *F) {
----------------
arsenm wrote:

Can you split out the refactor of this into utilities into a separate PR? 

https://github.com/llvm/llvm-project/pull/87265