[OpenMP] Add flag for linking runtime bitcode library

Summary: This patch adds an additional flag to the OpenMP device offloading toolchain to link in the runtime library bitcode.

Reviewers: Hahnfeld, ABataev, carlo.bertolli, caomhin, grokos, hfinkel

Reviewed By: ABataev, grokos

Subscribers: jholewinski, guansong, cfe-commits

Differential Revision: https://reviews.llvm.org/D43197

llvm-svn: 327438

4 files changed, 62 insertions, 0 deletions

diff --git a/clang/include/clang/Basic/DiagnosticDriverKinds.td b/clang/include/clang/Basic/DiagnosticDriverKinds.td
index 182136f8df1..ccc4db8fc7a 100644
--- a/clang/include/clang/Basic/DiagnosticDriverKinds.td
+++ b/clang/include/clang/Basic/DiagnosticDriverKinds.td
@@ -203,6 +203,9 @@ def err_drv_expecting_fopenmp_with_fopenmp_targets : Error<
 def warn_drv_omp_offload_target_duplicate : Warning<
   "The OpenMP offloading target '%0' is similar to target '%1' already specified - will be ignored.">, 
   InGroup<OpenMPTarget>;
+def warn_drv_omp_offload_target_missingbcruntime : Warning<
+  "No library '%0' found in the default clang lib directory or in LIBRARY_PATH. Expect degraded performance due to no inlining of runtime functions on target devices.">,
+  InGroup<OpenMPTarget>;
 def err_drv_bitcode_unsupported_on_toolchain : Error<
   "-fembed-bitcode is not supported on versions of iOS prior to 6.0">;
 
diff --git a/clang/lib/Driver/ToolChains/Cuda.cpp b/clang/lib/Driver/ToolChains/Cuda.cpp
index 86a11847e5a..64e62cb3e0e 100644
--- a/clang/lib/Driver/ToolChains/Cuda.cpp
+++ b/clang/lib/Driver/ToolChains/Cuda.cpp
@@ -21,6 +21,7 @@
 #include "llvm/Option/ArgList.h"
 #include "llvm/Support/FileSystem.h"
 #include "llvm/Support/Path.h"
+#include "llvm/Support/Process.h"
 #include "llvm/Support/Program.h"
 #include <system_error>
 
@@ -580,6 +581,44 @@ void CudaToolChain::addClangTargetOptions(
     CC1Args.push_back("-target-feature");
     CC1Args.push_back("+ptx42");
   }
+
+  if (DeviceOffloadingKind == Action::OFK_OpenMP) {
+    SmallVector<StringRef, 8> LibraryPaths;
+    // Add path to lib and/or lib64 folders.
+    SmallString<256> DefaultLibPath =
+      llvm::sys::path::parent_path(getDriver().Dir);
+    llvm::sys::path::append(DefaultLibPath,
+        Twine("lib") + CLANG_LIBDIR_SUFFIX);
+    LibraryPaths.emplace_back(DefaultLibPath.c_str());
+
+    // Add user defined library paths from LIBRARY_PATH.
+    llvm::Optional<std::string> LibPath =
+        llvm::sys::Process::GetEnv("LIBRARY_PATH");
+    if (LibPath) {
+      SmallVector<StringRef, 8> Frags;
+      const char EnvPathSeparatorStr[] = {llvm::sys::EnvPathSeparator, '\0'};
+      llvm::SplitString(*LibPath, Frags, EnvPathSeparatorStr);
+      for (StringRef Path : Frags)
+        LibraryPaths.emplace_back(Path.trim());
+    }
+
+    std::string LibOmpTargetName =
+      "libomptarget-nvptx-" + GpuArch.str() + ".bc";
+    bool FoundBCLibrary = false;
+    for (StringRef LibraryPath : LibraryPaths) {
+      SmallString<128> LibOmpTargetFile(LibraryPath);
+      llvm::sys::path::append(LibOmpTargetFile, LibOmpTargetName);
+      if (llvm::sys::fs::exists(LibOmpTargetFile)) {
+        CC1Args.push_back("-mlink-cuda-bitcode");
+        CC1Args.push_back(DriverArgs.MakeArgString(LibOmpTargetFile));
+        FoundBCLibrary = true;
+        break;
+      }
+    }
+    if (!FoundBCLibrary)
+      getDriver().Diag(diag::warn_drv_omp_offload_target_missingbcruntime)
+          << LibOmpTargetName;
+  }
 }
 
 void CudaToolChain::AddCudaIncludeArgs(const ArgList &DriverArgs,
diff --git a/clang/test/Driver/Inputs/libomptarget/libomptarget-nvptx-sm_20.bc b/clang/test/Driver/Inputs/libomptarget/libomptarget-nvptx-sm_20.bc
new file mode 100644
index 00000000000..e69de29bb2d
--- /dev/null
+++ b/clang/test/Driver/Inputs/libomptarget/libomptarget-nvptx-sm_20.bc
diff --git a/clang/test/Driver/openmp-offload-gpu.c b/clang/test/Driver/openmp-offload-gpu.c
index 16c321b9f49..bc1ecccf2f5 100644
--- a/clang/test/Driver/openmp-offload-gpu.c
+++ b/clang/test/Driver/openmp-offload-gpu.c
@@ -142,3 +142,23 @@
 // RUN:   | FileCheck -check-prefix=CHK-NOLIBDEVICE %s
 
 // CHK-NOLIBDEVICE-NOT: error:{{.*}}sm_60
+
+/// ###########################################################################
+
+/// Check that the runtime bitcode library is part of the compile line. Create a bogus
+/// bitcode library and add it to the LIBRARY_PATH.
+// RUN:   env LIBRARY_PATH=%S/Inputs/libomptarget %clang -### -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda \
+// RUN:   -Xopenmp-target -march=sm_20 -fopenmp-relocatable-target -save-temps \
+// RUN:   -no-canonical-prefixes %s 2>&1 | FileCheck -check-prefix=CHK-BCLIB %s
+
+// CHK-BCLIB: clang{{.*}}-triple{{.*}}nvptx64-nvidia-cuda{{.*}}-mlink-cuda-bitcode{{.*}}libomptarget-nvptx-sm_20.bc
+
+/// ###########################################################################
+
+/// Check that the warning is thrown when the libomptarget bitcode library is not found.
+/// Libomptarget requires sm_35 or newer so an sm_20 bitcode library should never exist.
+// RUN:   %clang -### -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda \
+// RUN:   -Xopenmp-target -march=sm_20 -fopenmp-relocatable-target -save-temps \
+// RUN:   -no-canonical-prefixes %s 2>&1 | FileCheck -check-prefix=CHK-BCLIB-WARN %s
+
+// CHK-BCLIB-WARN: No library 'libomptarget-nvptx-sm_20.bc' found in the default clang lib directory or in LIBRARY_PATH. Expect degraded performance due to no inlining of runtime functions on target devices.