[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

clang/lib/Frontend/CreateInvocationFromCommandLine.cpp

@@ -15,6 +15,7 @@
 #include "clang/Basic/DiagnosticOptions.h"
 #include "clang/Driver/Compilation.h"
 #include "clang/Driver/Driver.h"
+#include "clang/Driver/Action.h"
 #include "clang/Driver/Options.h"
 #include "clang/Driver/Tool.h"
 #include "clang/Frontend/CompilerInstance.h"
@@ -61,9 +62,25 @@ clang::createInvocationFromCommandLine(ArrayRef<const char *> ArgList,
   }
 
   // We expect to get back exactly one command job, if we didn't something
-  // failed.
+  // failed. CUDA compilation is an exception as it creates multiple jobs. If
+  // that's the case, we proceed with the first job. If caller needs particular
+  // CUDA job, it should be controlled via --cuda-{host|device}-only option
+  // passed to the driver.
   const driver::JobList &Jobs = C->getJobs();
-  if (Jobs.size() != 1 || !isa<driver::Command>(*Jobs.begin())) {
+  bool CudaCompilation = false;
+  if (Jobs.size() > 1) {
+    for (auto &A : C->getActions()){
+      // On MacOSX real actions may end up being wrapped in BindArchAction
+      if (isa<driver::BindArchAction>(A))
+        A = *A->begin();
+      if (isa<driver::CudaDeviceAction>(A)) {
+        CudaCompilation = true;
+        break;
+      }
+    }
+  }
+  if (Jobs.size() == 0 || !isa<driver::Command>(*Jobs.begin()) ||
+      (Jobs.size() > 1 && !CudaCompilation)) {
     SmallString<256> Msg;
     llvm::raw_svector_ostream OS(Msg);
     Jobs.Print(OS, "; ", true);