[llvm][frontend][offloading] Move clang-linker-wrapper/OffloadWrapper…

….* to llvm/Frontend/Offloading (llvm#78057)

This patch moves `clang/tools/clang-linker-wrapper/OffloadWrapper.*` to
`llvm/Frontend/Offloading` allowing them to be re-utilized by other
projects.

Additionally, it makes minor modifications to the API to make it more
flexible.
Concretely:
 - The `wrap*` methods now have additional arguments `EntryArray`, 
`Suffix` and `EmitSurfacesAndTextures` to specify some additional options.
- The `EntryArray` is now constructed by the caller. This change is needed to
enable JIT compilation, as ORC doesn't fully support `__start_` and `__stop_` 
symbols. Thus, to JIT the code, the `EntryArray` has to be constructed explicitly in the IR.
- The `Suffix` field is used when emitting the descriptor, registration
methods, etc, to make them more readable. It is empty by default.
- The `EmitSurfacesAndTextures` field controls whether to emit surface
and texture registration code, as those functions were removed from `CUDART`
in CUDA 12. It is true by default.
- The function `getOffloadingEntryInitializer` was added to help create
the `EntryArray`, as it returns the constant initializer and not a global
variable.

clang/test/Driver/linker-wrapper-image.c

@@ -45,17 +45,17 @@
 // RUN: clang-linker-wrapper --print-wrapped-module --dry-run --host-triple=x86_64-unknown-windows-gnu \
 // RUN:   --linker-path=/usr/bin/ld -- %t.o -o a.out 2>&1 | FileCheck %s --check-prefixes=CUDA,CUDA-COFF
 
-//      CUDA: @.fatbin_image = internal constant [0 x i8] zeroinitializer, section ".nv_fatbin"
-// CUDA-NEXT: @.fatbin_wrapper = internal constant %fatbin_wrapper { i32 1180844977, i32 1, ptr @.fatbin_image, ptr null }, section ".nvFatBinSegment", align 8
-// CUDA-NEXT: @.cuda.binary_handle = internal global ptr null
-
 //      CUDA-ELF: @__start_cuda_offloading_entries = external hidden constant [0 x %struct.__tgt_offload_entry]
 // CUDA-ELF-NEXT: @__stop_cuda_offloading_entries = external hidden constant [0 x %struct.__tgt_offload_entry]
 // CUDA-ELF-NEXT: @__dummy.cuda_offloading_entries = hidden constant [0 x %struct.__tgt_offload_entry] zeroinitializer, section "cuda_offloading_entries"
 
 //      CUDA-COFF: @__start_cuda_offloading_entries = hidden constant [0 x %struct.__tgt_offload_entry] zeroinitializer, section "cuda_offloading_entries$OA"
 // CUDA-COFF-NEXT: @__stop_cuda_offloading_entries = hidden constant [0 x %struct.__tgt_offload_entry] zeroinitializer, section "cuda_offloading_entries$OZ"
 
+//      CUDA: @.fatbin_image = internal constant [0 x i8] zeroinitializer, section ".nv_fatbin"
+// CUDA-NEXT: @.fatbin_wrapper = internal constant %fatbin_wrapper { i32 1180844977, i32 1, ptr @.fatbin_image, ptr null }, section ".nvFatBinSegment", align 8
+// CUDA-NEXT: @.cuda.binary_handle = internal global ptr null
+
 // CUDA: @llvm.global_ctors = appending global [1 x { i32, ptr, ptr }] [{ i32, ptr, ptr } { i32 1, ptr @.cuda.fatbin_reg, ptr null }]
 
 //      CUDA: define internal void @.cuda.fatbin_reg() section ".text.startup" {
@@ -145,17 +145,17 @@
 // RUN: clang-linker-wrapper --print-wrapped-module --dry-run --host-triple=x86_64-unknown-windows-gnu \
 // RUN:   --linker-path=/usr/bin/ld -- %t.o -o a.out 2>&1 | FileCheck %s --check-prefixes=HIP,HIP-COFF
 
-//      HIP: @.fatbin_image = internal constant [0 x i8] zeroinitializer, section ".hip_fatbin"
-// HIP-NEXT: @.fatbin_wrapper = internal constant %fatbin_wrapper { i32 1212764230, i32 1, ptr @.fatbin_image, ptr null }, section ".hipFatBinSegment", align 8
-// HIP-NEXT: @.hip.binary_handle = internal global ptr null
-
 //      HIP-ELF: @__start_hip_offloading_entries = external hidden constant [0 x %struct.__tgt_offload_entry]
 // HIP-ELF-NEXT: @__stop_hip_offloading_entries = external hidden constant [0 x %struct.__tgt_offload_entry]
 // HIP-ELF-NEXT: @__dummy.hip_offloading_entries = hidden constant [0 x %struct.__tgt_offload_entry] zeroinitializer, section "hip_offloading_entries"
 
 //      HIP-COFF: @__start_hip_offloading_entries = hidden constant [0 x %struct.__tgt_offload_entry] zeroinitializer, section "hip_offloading_entries$OA"
 // HIP-COFF-NEXT: @__stop_hip_offloading_entries = hidden constant [0 x %struct.__tgt_offload_entry] zeroinitializer, section "hip_offloading_entries$OZ"
 
+//      HIP: @.fatbin_image = internal constant [0 x i8] zeroinitializer, section ".hip_fatbin"
+// HIP-NEXT: @.fatbin_wrapper = internal constant %fatbin_wrapper { i32 1212764230, i32 1, ptr @.fatbin_image, ptr null }, section ".hipFatBinSegment", align 8
+// HIP-NEXT: @.hip.binary_handle = internal global ptr null
+
 // HIP: @llvm.global_ctors = appending global [1 x { i32, ptr, ptr }] [{ i32, ptr, ptr } { i32 1, ptr @.hip.fatbin_reg, ptr null }]
 
 //      HIP: define internal void @.hip.fatbin_reg() section ".text.startup" {

clang/tools/clang-linker-wrapper/CMakeLists.txt

@@ -28,7 +28,6 @@ endif()
 
 add_clang_tool(clang-linker-wrapper
   ClangLinkerWrapper.cpp
-  OffloadWrapper.cpp
 
   DEPENDS
   ${tablegen_deps}

clang/tools/clang-linker-wrapper/ClangLinkerWrapper.cpp

@@ -14,11 +14,12 @@
 //
 //===---------------------------------------------------------------------===//
 
-#include "OffloadWrapper.h"
 #include "clang/Basic/Version.h"
 #include "llvm/BinaryFormat/Magic.h"
 #include "llvm/Bitcode/BitcodeWriter.h"
 #include "llvm/CodeGen/CommandFlags.h"
+#include "llvm/Frontend/Offloading/OffloadWrapper.h"
+#include "llvm/Frontend/Offloading/Utility.h"
 #include "llvm/IR/Constants.h"
 #include "llvm/IR/DiagnosticPrinter.h"
 #include "llvm/IR/Module.h"
@@ -906,15 +907,21 @@ wrapDeviceImages(ArrayRef<std::unique_ptr<MemoryBuffer>> Buffers,
 
   switch (Kind) {
   case OFK_OpenMP:
-    if (Error Err = wrapOpenMPBinaries(M, BuffersToWrap))
+    if (Error Err = offloading::wrapOpenMPBinaries(
+            M, BuffersToWrap,
+            offloading::getOffloadEntryArray(M, "omp_offloading_entries")))
       return std::move(Err);
     break;
   case OFK_Cuda:
-    if (Error Err = wrapCudaBinary(M, BuffersToWrap.front()))
+    if (Error Err = offloading::wrapCudaBinary(
+            M, BuffersToWrap.front(),
+            offloading::getOffloadEntryArray(M, "cuda_offloading_entries")))
       return std::move(Err);
     break;
   case OFK_HIP:
-    if (Error Err = wrapHIPBinary(M, BuffersToWrap.front()))
+    if (Error Err = offloading::wrapHIPBinary(
+            M, BuffersToWrap.front(),
+            offloading::getOffloadEntryArray(M, "hip_offloading_entries")))
       return std::move(Err);
     break;
   default:

llvm/include/llvm/Frontend/Offloading/OffloadWrapper.h

@@ -0,0 +1,52 @@
+//===- OffloadWrapper.h --r-------------------------------------*- 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 LLVM_FRONTEND_OFFLOADING_OFFLOADWRAPPER_H
+#define LLVM_FRONTEND_OFFLOADING_OFFLOADWRAPPER_H
+
+#include "llvm/ADT/ArrayRef.h"
+#include "llvm/IR/Module.h"
+
+namespace llvm {
+namespace offloading {
+using EntryArrayTy = std::pair<GlobalVariable *, GlobalVariable *>;
+/// Wraps the input device images into the module \p M as global symbols and
+/// registers the images with the OpenMP Offloading runtime libomptarget.
+/// \param EntryArray Optional pair pointing to the `__start` and `__stop`
+/// symbols holding the `__tgt_offload_entry` array.
+/// \param Suffix An optional suffix appended to the emitted symbols.
+llvm::Error wrapOpenMPBinaries(llvm::Module &M,
+                               llvm::ArrayRef<llvm::ArrayRef<char>> Images,
+                               EntryArrayTy EntryArray,
+                               llvm::StringRef Suffix = "");
+
+/// Wraps the input fatbinary image into the module \p M as global symbols and
+/// registers the images with the CUDA runtime.
+/// \param EntryArray Optional pair pointing to the `__start` and `__stop`
+/// symbols holding the `__tgt_offload_entry` array.
+/// \param Suffix An optional suffix appended to the emitted symbols.
+/// \param EmitSurfacesAndTextures Whether to emit surface and textures
+/// registration code. It defaults to false.
+llvm::Error wrapCudaBinary(llvm::Module &M, llvm::ArrayRef<char> Images,
+                           EntryArrayTy EntryArray, llvm::StringRef Suffix = "",
+                           bool EmitSurfacesAndTextures = true);
+
+/// Wraps the input bundled image into the module \p M as global symbols and
+/// registers the images with the HIP runtime.
+/// \param EntryArray Optional pair pointing to the `__start` and `__stop`
+/// symbols holding the `__tgt_offload_entry` array.
+/// \param Suffix An optional suffix appended to the emitted symbols.
+/// \param EmitSurfacesAndTextures Whether to emit surface and textures
+/// registration code. It defaults to false.
+llvm::Error wrapHIPBinary(llvm::Module &M, llvm::ArrayRef<char> Images,
+                          EntryArrayTy EntryArray, llvm::StringRef Suffix = "",
+                          bool EmitSurfacesAndTextures = true);
+} // namespace offloading
+} // namespace llvm
+
+#endif // LLVM_FRONTEND_OFFLOADING_OFFLOADWRAPPER_H

llvm/include/llvm/Frontend/Offloading/Utility.h

@@ -61,6 +61,12 @@ StructType *getEntryTy(Module &M);
 void emitOffloadingEntry(Module &M, Constant *Addr, StringRef Name,
                          uint64_t Size, int32_t Flags, int32_t Data,
                          StringRef SectionName);
+/// Create a constant struct initializer used to register this global at
+/// runtime.
+/// \return the constant struct and the global variable holding the symbol name.
+std::pair<Constant *, GlobalVariable *>
+getOffloadingEntryInitializer(Module &M, Constant *Addr, StringRef Name,
+                              uint64_t Size, int32_t Flags, int32_t Data);
 
 /// Creates a pair of globals used to iterate the array of offloading entries by
 /// accessing the section variables provided by the linker.

llvm/lib/Frontend/Offloading/CMakeLists.txt

@@ -1,5 +1,6 @@
 add_llvm_component_library(LLVMFrontendOffloading
   Utility.cpp
+  OffloadWrapper.cpp
 
   ADDITIONAL_HEADER_DIRS
   ${LLVM_MAIN_INCLUDE_DIR}/llvm/Frontend
@@ -9,6 +10,7 @@ add_llvm_component_library(LLVMFrontendOffloading
 
   LINK_COMPONENTS
   Core
+  BinaryFormat
   Support
   TransformUtils
   TargetParser