[LinkerWrapper] Add AMDGPU specific options to the LLD invocation

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.

Reviewed By: yaxunl

Differential Revision: https://reviews.llvm.org/D128923

diff --git a/clang/test/Driver/linker-wrapper.c b/clang/test/Driver/linker-wrapper.c
index ecd1963..c9855ec 100644 (file)
--- a/clang/test/Driver/linker-wrapper.c
+++ b/clang/test/Driver/linker-wrapper.c
@@ -18,7 +18,7 @@
 // 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 \
@@ -90,7 +90,7 @@
 // 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 \

diff --git a/clang/tools/clang-linker-wrapper/ClangLinkerWrapper.cpp b/clang/tools/clang-linker-wrapper/ClangLinkerWrapper.cpp
index ffd17b6..3e935bc 100644 (file)
--- a/clang/tools/clang-linker-wrapper/ClangLinkerWrapper.cpp
+++ b/clang/tools/clang-linker-wrapper/ClangLinkerWrapper.cpp
@@ -8,9 +8,9 @@
 //
 // 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.
 //
 //===---------------------------------------------------------------------===//
 
@@ -573,6 +573,7 @@ Expected<StringRef> link(ArrayRef<StringRef> InputFiles, Triple TheTriple,
                        "out");
   if (!TempFileOrErr)
     return TempFileOrErr.takeError();
+  std::string ArchArg = ("-plugin-opt=mcpu=" + Arch).str();
 
   SmallVector<StringRef, 16> CmdArgs;
   CmdArgs.push_back(*LLDPath);
@@ -580,6 +581,8 @@ Expected<StringRef> link(ArrayRef<StringRef> InputFiles, Triple TheTriple,
   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);