[Flang][NFC] Split runtime headers in preparation for cross-compilation. (#112188)

Split some headers into headers for public and private declarations in
preparation for #110217. Moving the runtime-private headers in
runtime-private include directory will occur in #110298.

* Do not use `sizeof(Descriptor)` in the compiler. The size of the
descriptor is target-dependent while `sizeof(Descriptor)` is the size of
the Descriptor for the host platform which might be too small when
cross-compiling to a different platform. Another problem is that the
emitted assembly ((cross-)compiling to the same target) is not identical
between Flang's running on different systems. Moving the declaration of
`class Descriptor` out of the included header will also reduce the
amount of #included sources.

* Do not use `sizeof(ArrayConstructorVector)` and
`alignof(ArrayConstructorVector)` in the compiler. Same reason as with
`Descriptor`.

* Compute the descriptor's extra flags without instantiating a
Descriptor. `Fortran::runtime::Descriptor` is defined in the runtime
source, but not the compiler source.

* Move `InquiryKeywordHashDecode` into runtime-private header. The
function is defined in the runtime sources and trying to call it in the
compiler would lead to a link-error.

* Move allocator-kind magic numbers into common header. They are the
only declarations out of `allocator-registry.h` in the compiler as well.
 
This does not make Flang cross-compile ready yet, the main goal is to
avoid transitive header dependencies from Flang to clang-rt. There are
more assumptions that host platform is the same as the target platform.

Author: Meinersbur

flang/include/flang/Lower/Allocatable.h

@@ -15,7 +15,7 @@
 
 #include "flang/Lower/AbstractConverter.h"
 #include "flang/Optimizer/Builder/MutableBox.h"
-#include "flang/Runtime/allocator-registry.h"
+#include "flang/Runtime/allocator-registry-consts.h"
 #include "llvm/ADT/StringRef.h"
 
 namespace mlir {

flang/include/flang/Optimizer/Builder/IntrinsicCall.h

@@ -16,7 +16,7 @@
 #include "flang/Optimizer/Builder/Runtime/Numeric.h"
 #include "flang/Optimizer/Builder/Runtime/RTBuilder.h"
 #include "flang/Runtime/entry-names.h"
-#include "flang/Runtime/iostat.h"
+#include "flang/Runtime/iostat-consts.h"
 #include "mlir/Dialect/Complex/IR/Complex.h"
 #include "mlir/Dialect/LLVMIR/LLVMDialect.h"
 #include "mlir/Dialect/Math/IR/Math.h"

flang/include/flang/Optimizer/Builder/MutableBox.h

@@ -14,7 +14,7 @@
 #define FORTRAN_OPTIMIZER_BUILDER_MUTABLEBOX_H
 
 #include "flang/Optimizer/Builder/BoxValue.h"
-#include "flang/Runtime/allocator-registry.h"
+#include "flang/Runtime/allocator-registry-consts.h"
 #include "llvm/ADT/StringRef.h"
 
 namespace mlir {

flang/include/flang/Optimizer/CodeGen/DescriptorModel.h

@@ -23,7 +23,7 @@
 #define OPTIMIZER_DESCRIPTOR_MODEL_H
 
 #include "flang/ISO_Fortran_binding_wrapper.h"
-#include "flang/Runtime/descriptor.h"
+#include "flang/Runtime/descriptor-consts.h"
 #include "mlir/Dialect/LLVMIR/LLVMTypes.h"
 #include "mlir/IR/BuiltinTypes.h"
 #include "llvm/Support/ErrorHandling.h"

flang/include/flang/Runtime/CUDA/allocatable.h

@@ -9,7 +9,7 @@
 #ifndef FORTRAN_RUNTIME_CUDA_ALLOCATABLE_H_
 #define FORTRAN_RUNTIME_CUDA_ALLOCATABLE_H_
 
-#include "flang/Runtime/descriptor.h"
+#include "flang/Runtime/descriptor-consts.h"
 #include "flang/Runtime/entry-names.h"
 
 namespace Fortran::runtime::cuda {

flang/include/flang/Runtime/CUDA/allocator.h

@@ -10,7 +10,7 @@
 #define FORTRAN_RUNTIME_CUDA_ALLOCATOR_H_
 
 #include "common.h"
-#include "flang/Runtime/descriptor.h"
+#include "flang/Runtime/descriptor-consts.h"
 #include "flang/Runtime/entry-names.h"
 
 namespace Fortran::runtime::cuda {

flang/include/flang/Runtime/CUDA/common.h

@@ -9,7 +9,7 @@
 #ifndef FORTRAN_RUNTIME_CUDA_COMMON_H_
 #define FORTRAN_RUNTIME_CUDA_COMMON_H_
 
-#include "flang/Runtime/descriptor.h"
+#include "flang/Runtime/descriptor-consts.h"
 #include "flang/Runtime/entry-names.h"
 
 /// Type of memory for allocation/deallocation

flang/include/flang/Runtime/CUDA/descriptor.h

@@ -9,7 +9,7 @@
 #ifndef FORTRAN_RUNTIME_CUDA_DESCRIPTOR_H_
 #define FORTRAN_RUNTIME_CUDA_DESCRIPTOR_H_
 
-#include "flang/Runtime/descriptor.h"
+#include "flang/Runtime/descriptor-consts.h"
 #include "flang/Runtime/entry-names.h"
 #include <cstddef>
 

flang/include/flang/Runtime/CUDA/memory.h

@@ -9,7 +9,7 @@
 #ifndef FORTRAN_RUNTIME_CUDA_MEMORY_H_
 #define FORTRAN_RUNTIME_CUDA_MEMORY_H_
 
-#include "flang/Runtime/descriptor.h"
+#include "flang/Runtime/descriptor-consts.h"
 #include "flang/Runtime/entry-names.h"
 #include <cstddef>
 

flang/include/flang/Runtime/allocator-registry-consts.h

@@ -0,0 +1,20 @@
+//===-- include/flang/Runtime/allocator-registry-consts.h -------*- C++ -*-===//
+//
+// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+// See https://llvm.org/LICENSE.txt for license information.
+// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+//
+//===----------------------------------------------------------------------===//
+
+#ifndef FORTRAN_RUNTIME_ALLOCATOR_REGISTRY_CONSTS_H_
+#define FORTRAN_RUNTIME_ALLOCATOR_REGISTRY_CONSTS_H_
+
+static constexpr unsigned kDefaultAllocator = 0;
+
+// Allocator used for CUF
+static constexpr unsigned kPinnedAllocatorPos = 1;
+static constexpr unsigned kDeviceAllocatorPos = 2;
+static constexpr unsigned kManagedAllocatorPos = 3;
+static constexpr unsigned kUnifiedAllocatorPos = 4;
+
+#endif /* FORTRAN_RUNTIME_ALLOCATOR_REGISTRY_CONSTS_H_ */