[Flang][Transform] Modify stack reclaim pass to use allocation address space when generating intrinsics (#96836)

This PR aims to factor in the allocation address space provided by an
architectures data layout when generating the intrinsic instructions,
this allows them to be lowered later with the address spaces in tow.
This aligns the intrinsic creation with the LLVM IRBuilder's
https://github.com/llvm/llvm-project/blob/main/llvm/include/llvm/IR/IRBuilder.h#L1053

This is also necessary for the below example to compile for OpenMP AMD
GPU and not ICE the compiler in ISEL as AMD's stackrestore and stacksave
are expected to have the appropriate allocation address space for AMD
GPU.

program main
    integer(4), allocatable :: test
    allocate(test)

!$omp target map(tofrom:test)
    do i = 1, 10
      test = test + 50
    end do
!$omp end target

  deallocate(test)
end program

The PR also fixes the issue I opened a while ago which hits the same
error when compiling for AMDGPU:
#82368

Although, you have to have the appropriate GPU LIBC and Fortran offload
runtime (both compiled for AMDGPU) added to the linker for the command
or it will reach another ISEL error and ICE weirdly. But with the
pre-requisites it works fine with this PR.

Author: agozillon

flang/lib/Optimizer/Transforms/StackReclaim.cpp

@@ -31,11 +31,23 @@ class StackReclaimPass : public fir::impl::StackReclaimBase<StackReclaimPass> {
 };
 } // namespace
 
+uint64_t getAllocaAddressSpace(Operation *op) {
+  mlir::ModuleOp module = mlir::dyn_cast_or_null<mlir::ModuleOp>(op);
+  if (!module)
+    module = op->getParentOfType<mlir::ModuleOp>();
+
+  if (mlir::Attribute addrSpace =
+          mlir::DataLayout(module).getAllocaMemorySpace())
+    return llvm::cast<mlir::IntegerAttr>(addrSpace).getUInt();
+  return 0;
+}
+
 void StackReclaimPass::runOnOperation() {
   auto *op = getOperation();
   auto *context = &getContext();
   mlir::OpBuilder builder(context);
-  mlir::Type voidPtr = mlir::LLVM::LLVMPointerType::get(context);
+  mlir::Type voidPtr =
+      mlir::LLVM::LLVMPointerType::get(context, getAllocaAddressSpace(op));
 
   op->walk([&](fir::DoLoopOp loopOp) {
     mlir::Location loc = loopOp.getLoc();

flang/test/Transforms/stack-reclaime.fir

@@ -12,3 +12,20 @@ func.func @alloca_in_loop(%lb : index, %ub : index, %step : index, %b : i1, %add
 // CHECK: %[[STACKPTR:.*]] = llvm.intr.stacksave : !llvm.ptr
 // CHECK: %{{.*}} = fir.alloca !fir.box<!fir.heap<!fir.char<1,?>>>
 // CHECK: llvm.intr.stackrestore %0 : !llvm.ptr
+
+// -----
+
+module attributes {dlti.dl_spec = #dlti.dl_spec<#dlti.dl_entry<"dlti.alloca_memory_space", 5 : ui64>>} {
+  func.func @stack_restore_save_alloca_address(%lb : index, %ub : index, %step : index, %b : i1, %addr : !fir.ref<index>) {
+    fir.do_loop %iv = %lb to %ub step %step unordered {
+      %0 = fir.alloca !fir.box<!fir.heap<!fir.char<1,?>>>
+    }
+    return
+  }
+}
+
+// CHECK-LABEL: func.func @stack_restore_save_alloca_address
+// CHECK: fir.do_loop
+// CHECK: %[[STACKPTR:.*]] = llvm.intr.stacksave : !llvm.ptr<5>
+// CHECK: %{{.*}} = fir.alloca !fir.box<!fir.heap<!fir.char<1,?>>>
+// CHECK: llvm.intr.stackrestore %0 : !llvm.ptr<5>