[Mlir-commits] [mlir] [MLIR][GPU-LLVM] Convert `gpu.func` to `llvm.func` (PR #101664)

[Petr Kurapov]

================
@@ -35,16 +35,42 @@ struct GPUDynamicSharedMemoryOpLowering
   unsigned alignmentBit;
 };
 
+struct GPUFuncOpLoweringOptions {
+  /// The address space to use for `alloca`s in private memory.
+  unsigned allocaAddrSpace;
+  /// The address space to use declaring workgroup memory.
+  unsigned workgroupAddrSpace;
----------------
kurapov-peter wrote:

Just a thought: why is it that we only propagate specific ones and not an entire address space map? The lowering would need information on other types as well anyway.

https://github.com/llvm/llvm-project/pull/101664