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

  - 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

git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@242058 91177308-0d34-0410-b5e6-96231b3b80d8

1 files changed, 18 insertions, 3 deletions

diff --git a/lib/Driver/Types.cpp b/lib/Driver/Types.cpp
index 7b28145755..2085b01242 100644
--- a/lib/Driver/Types.cpp
+++ b/lib/Driver/Types.cpp
@@ -86,6 +86,7 @@ bool types::isAcceptedByClang(ID Id) {
   case TY_C: case TY_PP_C:
   case TY_CL:
   case TY_CUDA: case TY_PP_CUDA:
+  case TY_CUDA_DEVICE:
   case TY_ObjC: case TY_PP_ObjC: case TY_PP_ObjC_Alias:
   case TY_CXX: case TY_PP_CXX:
   case TY_ObjCXX: case TY_PP_ObjCXX: case TY_PP_ObjCXX_Alias:
@@ -122,7 +123,19 @@ bool types::isCXX(ID Id) {
   case TY_ObjCXX: case TY_PP_ObjCXX: case TY_PP_ObjCXX_Alias:
   case TY_CXXHeader: case TY_PP_CXXHeader:
   case TY_ObjCXXHeader: case TY_PP_ObjCXXHeader:
-  case TY_CUDA: case TY_PP_CUDA:
+  case TY_CUDA: case TY_PP_CUDA: case TY_CUDA_DEVICE:
+    return true;
+  }
+}
+
+bool types::isCuda(ID Id) {
+  switch (Id) {
+  default:
+    return false;
+
+  case TY_CUDA:
+  case TY_PP_CUDA:
+  case TY_CUDA_DEVICE:
     return true;
   }
 }
@@ -206,10 +219,12 @@ void types::getCompilationPhases(ID Id, llvm::SmallVectorImpl<phases::ID> &P) {
         P.push_back(phases::Compile);
         P.push_back(phases::Backend);
       }
-      P.push_back(phases::Assemble);
+      if (Id != TY_CUDA_DEVICE)
+        P.push_back(phases::Assemble);
     }
   }
-  if (!onlyPrecompileType(Id)) {
+
+  if (!onlyPrecompileType(Id) && Id != TY_CUDA_DEVICE) {
     P.push_back(phases::Link);
   }
   assert(0 < P.size() && "Not enough phases in list");