[cuda] Driver changes to compile and stitch together host and device-side CUDA code.

  NOTE: reverts r242077 to reinstate r242058, r242065, 242067
        and includes fix for OS X test failures.

  - Changed driver pipeline to compile host and device side of CUDA
    files and incorporate results of device-side compilation into host
    object file.

  - Added a test for cuda pipeline creation in clang driver.

  New clang options:
  --cuda-host-only   - Do host-side compilation only.
  --cuda-device-only - Do device-side compilation only.

  --cuda-gpu-arch=<ARCH> - specify GPU architecture for device-side
    compilation. E.g. sm_35, sm_30. Default is sm_20. May be used more
    than once in which case one device-compilation will be done per
    unique specified GPU architecture.

  Differential Revision: http://reviews.llvm.org/D9509

llvm-svn: 242085

1 files changed, 59 insertions, 0 deletions

diff --git a/clang/lib/Driver/ToolChains.cpp b/clang/lib/Driver/ToolChains.cpp
index eafc72b6b12..15e36a1e6ce 100644
--- a/clang/lib/Driver/ToolChains.cpp
+++ b/clang/lib/Driver/ToolChains.cpp
@@ -3652,6 +3652,65 @@ Tool *DragonFly::buildLinker() const {
   return new tools::dragonfly::Linker(*this);
 }
 
+/// Stub for CUDA toolchain. At the moment we don't have assembler or
+/// linker and need toolchain mainly to propagate device-side options
+/// to CC1.
+
+CudaToolChain::CudaToolChain(const Driver &D, const llvm::Triple &Triple,
+                             const ArgList &Args)
+    : Linux(D, Triple, Args) {}
+
+void
+CudaToolChain::addClangTargetOptions(const llvm::opt::ArgList &DriverArgs,
+                                     llvm::opt::ArgStringList &CC1Args) const {
+  Linux::addClangTargetOptions(DriverArgs, CC1Args);
+  CC1Args.push_back("-fcuda-is-device");
+}
+
+llvm::opt::DerivedArgList *
+CudaToolChain::TranslateArgs(const llvm::opt::DerivedArgList &Args,
+                             const char *BoundArch) const {
+  DerivedArgList *DAL = new DerivedArgList(Args.getBaseArgs());
+  const OptTable &Opts = getDriver().getOpts();
+
+  for (Arg *A : Args) {
+    if (A->getOption().matches(options::OPT_Xarch__)) {
+      // Skip this argument unless the architecture matches BoundArch
+      if (A->getValue(0) != StringRef(BoundArch))
+        continue;
+
+      unsigned Index = Args.getBaseArgs().MakeIndex(A->getValue(1));
+      unsigned Prev = Index;
+      std::unique_ptr<Arg> XarchArg(Opts.ParseOneArg(Args, Index));
+
+      // If the argument parsing failed or more than one argument was
+      // consumed, the -Xarch_ argument's parameter tried to consume
+      // extra arguments. Emit an error and ignore.
+      //
+      // We also want to disallow any options which would alter the
+      // driver behavior; that isn't going to work in our model. We
+      // use isDriverOption() as an approximation, although things
+      // like -O4 are going to slip through.
+      if (!XarchArg || Index > Prev + 1) {
+        getDriver().Diag(diag::err_drv_invalid_Xarch_argument_with_args)
+            << A->getAsString(Args);
+        continue;
+      } else if (XarchArg->getOption().hasFlag(options::DriverOption)) {
+        getDriver().Diag(diag::err_drv_invalid_Xarch_argument_isdriver)
+            << A->getAsString(Args);
+        continue;
+      }
+      XarchArg->setBaseArg(A);
+      A = XarchArg.release();
+      DAL->AddSynthesizedArg(A);
+    }
+    DAL->append(A);
+  }
+
+  DAL->AddJoinedArg(nullptr, Opts.getOption(options::OPT_march_EQ), BoundArch);
+  return DAL;
+}
+
 /// XCore tool chain
 XCore::XCore(const Driver &D, const llvm::Triple &Triple, const ArgList &Args)
     : ToolChain(D, Triple, Args) {