[LinkerWrapper] Add AMDGPU specific options to the LLD invocation

[jhuber6]

Summary

We use LLD to perform AMDGPU linking. This linker accepts some arguments
through the -plugin-opt facilities. These options match what Clang
will output when given the same input.

[yaxunl]

LGTM. Thanks.

clang/test/Driver/linker-wrapper.c

 
 // RUN: clang-offload-packager -o %t.out \
 // RUN:   --image=file=%S/Inputs/dummy-elf.o,kind=openmp,triple=amdgcn-amd-amdhsa,arch=gfx908 \
 // RUN:   --image=file=%S/Inputs/dummy-elf.o,kind=openmp,triple=amdgcn-amd-amdhsa,arch=gfx908
 // RUN: %clang -cc1 %s -triple x86_64-unknown-linux-gnu -emit-obj -o %t.o -fembed-offload-object=%t.out
 // RUN: clang-linker-wrapper --host-triple x86_64-unknown-linux-gnu --dry-run -linker-path \
 // RUN:   /usr/bin/ld -- %t.o -o a.out 2>&1 | FileCheck %s --check-prefix=AMDGPU_LINK
 
-// AMDGPU_LINK: lld{{.*}}-flavor gnu --no-undefined -shared -o {{.*}}.out {{.*}}.o {{.*}}.o
+// AMDGPU_LINK: lld{{.*}}-flavor gnu --no-undefined -shared -plugin-opt=-amdgpu-internalize-symbols -plugin-opt=mcpu=gfx908 -o {{.*}}.out {{.*}}.o {{.*}}.o
 
 // RUN: clang-offload-packager -o %t.out \
 // RUN:   --image=file=%S/Inputs/dummy-elf.o,kind=openmp,triple=x86_64-unknown-linux-gnu \
 // RUN:   --image=file=%S/Inputs/dummy-elf.o,kind=openmp,triple=x86_64-unknown-linux-gnu
 // RUN: %clang -cc1 %s -triple x86_64-unknown-linux-gnu -emit-obj -o %t.o -fembed-offload-object=%t.out
 // RUN: clang-linker-wrapper --host-triple x86_64-unknown-linux-gnu --dry-run -linker-path \
 // RUN:   /usr/bin/ld.lld -- %t.o -o a.out 2>&1 | FileCheck %s --check-prefix=CPU_LINK
 

 // RUN:   --image=file=%S/Inputs/dummy-elf.o,kind=openmp,triple=amdgcn-amd-amdhsa,arch=gfx908 \
 // RUN:   --image=file=%S/Inputs/dummy-elf.o,kind=openmp,triple=nvptx64-nvidia-cuda,arch=sm_70
 // RUN: %clang -cc1 %s -triple x86_64-unknown-linux-gnu -emit-obj -o %t.o \
 // RUN:   -fembed-offload-object=%t.out
 // RUN: clang-linker-wrapper --dry-run --host-triple x86_64-unknown-linux-gnu -linker-path \
 // RUN:   /usr/bin/ld --device-linker=a --device-linker=nvptx64-nvidia-cuda=b -- \
 // RUN:   %t.o -o a.out 2>&1 | FileCheck %s --check-prefix=LINKER_ARGS
 
-// LINKER_ARGS: lld{{.*}}-flavor gnu --no-undefined -shared -o {{.*}}.out {{.*}}.o a
+// LINKER_ARGS: lld{{.*}}-flavor gnu --no-undefined -shared -plugin-opt=-amdgpu-internalize-symbols -plugin-opt=mcpu=gfx908 -o {{.*}}.out {{.*}}.o a
 // LINKER_ARGS: nvlink{{.*}}-m64 -o {{.*}}.out -arch sm_70 {{.*}}.o a b
 
 // RUN: clang-offload-packager -o %t-lib.out \
 // RUN:   --image=file=%S/Inputs/dummy-elf.o,kind=openmp,triple=nvptx64-nvidia-cuda,arch=sm_70 \
 // RUN:   --image=file=%S/Inputs/dummy-elf.o,kind=cuda,triple=nvptx64-nvidia-cuda,arch=sm_52
 // RUN: %clang -cc1 %s -triple x86_64-unknown-linux-gnu -emit-obj -o %t.o -fembed-offload-object=%t-lib.out
 // RUN: llvm-ar rcs %t.a %t.o
 // RUN: rm -f %t.o
 // RUN: %clang -cc1 %s -triple x86_64-unknown-linux-gnu -emit-obj -o %t-obj.o
 // RUN: clang-linker-wrapper --host-triple x86_64-unknown-linux-gnu --dry-run -save-temps \
 // RUN:   -linker-path /usr/bin/ld -- %t.a %t-obj.o -o a.out
 // RUN: not ls *-device-*

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

 //===-- clang-linker-wrapper/ClangLinkerWrapper.cpp - wrapper over linker-===//
 //
 // 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
 //
 //===---------------------------------------------------------------------===//
 //
 // This tool works as a wrapper over a linking job. This tool is used to create
 // linked device images for offloading. It scans the linker's input for embedded
-// device offloading data stored in sections `.llvm.offloading.<triple>.<arch>`
-// and extracts it as a temporary file. The extracted device files will then be
-// passed to a device linking job to create a final device image.
+// device offloading data stored in sections `.llvm.offloading` and extracts it
+// as a temporary file. The extracted device files will then be passed to a
+// device linking job to create a final device image.
 //
 //===---------------------------------------------------------------------===//
 
 #include "OffloadWrapper.h"
 #include "clang/Basic/Version.h"
 #include "llvm/BinaryFormat/Magic.h"
 #include "llvm/Bitcode/BitcodeWriter.h"
 #include "llvm/CodeGen/CommandFlags.h"
Expected<StringRef> link(ArrayRef<StringRef> InputFiles, Triple TheTriple,
 
   // Create a new file to write the linked device image to.
   auto TempFileOrErr =
       createOutputFile(sys::path::filename(ExecutableName) + "-" +
                            TheTriple.getArchName() + "-" + Arch,
                        "out");
   if (!TempFileOrErr)
     return TempFileOrErr.takeError();
+  std::string ArchArg = ("-plugin-opt=mcpu=" + Arch).str();
 
   SmallVector<StringRef, 16> CmdArgs;
   CmdArgs.push_back(*LLDPath);
   CmdArgs.push_back("-flavor");
   CmdArgs.push_back("gnu");
   CmdArgs.push_back("--no-undefined");
   CmdArgs.push_back("-shared");
+  CmdArgs.push_back("-plugin-opt=-amdgpu-internalize-symbols");
+  CmdArgs.push_back(ArchArg);
   CmdArgs.push_back("-o");
   CmdArgs.push_back(*TempFileOrErr);
 
   // Add extracted input files.
   for (StringRef Input : InputFiles)
     CmdArgs.push_back(Input);
 
   renderXLinkerArgs(CmdArgs, TheTriple.getTriple());