[flang][cuda] Add new entry points function for data transfer (#108244)

Add new entry points for more complex data transfer involving
descriptors. These functions will be called when converting
`cuf.data_transfer` operations.

Author: clementval

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

@@ -0,0 +1,47 @@
+//===-- include/flang/Runtime/CUDA/memory.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_CUDA_MEMORY_H_
+#define FORTRAN_RUNTIME_CUDA_MEMORY_H_
+
+#include "flang/Runtime/descriptor.h"
+#include "flang/Runtime/entry-names.h"
+#include <cstddef>
+
+static constexpr unsigned kHostToDevice = 0;
+static constexpr unsigned kDeviceToHost = 1;
+static constexpr unsigned kDeviceToDevice = 2;
+
+namespace Fortran::runtime::cuda {
+
+extern "C" {
+
+/// Set value to the data hold by a descriptor. The \p value pointer must be
+/// addressable to the same amount of bytes specified by the element size of
+/// the descriptor \p desc.
+void RTDECL(CUFMemsetDescriptor)(const Descriptor &desc, void *value,
+    const char *sourceFile = nullptr, int sourceLine = 0);
+
+/// Data transfer from a pointer to a descriptor.
+void RTDECL(CUFDataTransferDescPtr)(const Descriptor &dst, void *src,
+    std::size_t bytes, unsigned mode, const char *sourceFile = nullptr,
+    int sourceLine = 0);
+
+/// Data transfer from a descriptor to a pointer.
+void RTDECL(CUFDataTransferPtrDesc)(void *dst, const Descriptor &src,
+    std::size_t bytes, unsigned mode, const char *sourceFile = nullptr,
+    int sourceLine = 0);
+
+/// Data transfer from a descriptor to a descriptor.
+void RTDECL(CUFDataTransferDescDesc)(const Descriptor &dst,
+    const Descriptor &src, unsigned mode, const char *sourceFile = nullptr,
+    int sourceLine = 0);
+
+} // extern "C"
+} // namespace Fortran::runtime::cuda
+#endif // FORTRAN_RUNTIME_CUDA_MEMORY_H_

flang/lib/Optimizer/Dialect/FIRType.cpp

@@ -1467,4 +1467,4 @@ fir::getTypeSizeAndAlignmentOrCrash(mlir::Location loc, mlir::Type ty,
   if (result)
     return *result;
   TODO(loc, "computing size of a component");
-}
+}

flang/runtime/CUDA/CMakeLists.txt

@@ -16,6 +16,7 @@ set(CUFRT_LIBNAME CufRuntime_cuda_${CUDAToolkit_VERSION_MAJOR})
 add_flang_library(${CUFRT_LIBNAME}
   allocator.cpp
   descriptor.cpp
+  memory.cpp
 )
 
 if (BUILD_SHARED_LIBS)

flang/runtime/CUDA/memory.cpp

@@ -0,0 +1,46 @@
+//===-- runtime/CUDA/memory.cpp -------------------------------------------===//
+//
+// 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
+//
+//===----------------------------------------------------------------------===//
+
+#include "flang/Runtime/CUDA/memory.h"
+#include "../terminator.h"
+
+#include "cuda_runtime.h"
+
+namespace Fortran::runtime::cuda {
+extern "C" {
+
+void RTDEF(CUFMemsetDescriptor)(const Descriptor &desc, void *value,
+    const char *sourceFile, int sourceLine) {
+  Terminator terminator{sourceFile, sourceLine};
+  terminator.Crash("not yet implemented: CUDA data transfer from a scalar "
+                   "value to a descriptor");
+}
+
+void RTDEF(CUFDataTransferDescPtr)(const Descriptor &desc, void *addr,
+    std::size_t bytes, unsigned mode, const char *sourceFile, int sourceLine) {
+  Terminator terminator{sourceFile, sourceLine};
+  terminator.Crash(
+      "not yet implemented: CUDA data transfer from a pointer to a descriptor");
+}
+
+void RTDEF(CUFDataTransferPtrDesc)(void *addr, const Descriptor &desc,
+    std::size_t bytes, unsigned mode, const char *sourceFile, int sourceLine) {
+  Terminator terminator{sourceFile, sourceLine};
+  terminator.Crash(
+      "not yet implemented: CUDA data transfer from a descriptor to a pointer");
+}
+
+void RTDECL(CUFDataTransferDescDesc)(const Descriptor &dstDesc,
+    const Descriptor &srcDesc, unsigned mode, const char *sourceFile,
+    int sourceLine) {
+  Terminator terminator{sourceFile, sourceLine};
+  terminator.Crash(
+      "not yet implemented: CUDA data transfer between two descriptors");
+}
+}
+} // namespace Fortran::runtime::cuda