[CUDA] Make CUDA compilation usable by default.

Currently clang requires several additional command
line options in order to enable new features needed
during CUDA compilation. This patch makes these
options default.

* Automatically include cuda_runtime.h if we've found
  a valid CUDA installation.
* Disable automatic CUDA header inclusion during unit tests.
* Added test case for command line construction.
* Enabled target overloads and relaxed call checks that are
  needed in order to include CUDA headers.
* Added CUDA-7.5 installation path to the CUDA installation search list.
* Define __CUDA__ macro to indicate CUDA compilation.

llvm-svn: 253389

clang/lib/Driver/ToolChains.cpp

@@ -1629,6 +1629,7 @@ void Generic_GCC::CudaInstallationDetector::init(
         Args.getLastArgValue(options::OPT_cuda_path_EQ));
   else {
     CudaPathCandidates.push_back(D.SysRoot + "/usr/local/cuda");
+    CudaPathCandidates.push_back(D.SysRoot + "/usr/local/cuda-7.5");
     CudaPathCandidates.push_back(D.SysRoot + "/usr/local/cuda-7.0");
   }
 
@@ -4134,8 +4135,11 @@ void Linux::AddCudaIncludeArgs(const ArgList &DriverArgs,
   if (DriverArgs.hasArg(options::OPT_nocudainc))
     return;
 
-  if (CudaInstallation.isValid())
+  if (CudaInstallation.isValid()) {
     addSystemInclude(DriverArgs, CC1Args, CudaInstallation.getIncludePath());
+    CC1Args.push_back("-include");
+    CC1Args.push_back("cuda_runtime.h");
+  }
 }
 
 bool Linux::isPIEDefault() const { return getSanitizerArgs().requiresPIE(); }

clang/lib/Driver/Tools.cpp

@@ -3292,6 +3292,8 @@ void Clang::ConstructJob(Compilation &C, const JobAction &JA,
     assert(AuxToolChain != nullptr && "No aux toolchain.");
     CmdArgs.push_back("-aux-triple");
     CmdArgs.push_back(Args.MakeArgString(AuxToolChain->getTriple().str()));
+    CmdArgs.push_back("-fcuda-target-overloads");
+    CmdArgs.push_back("-fcuda-disable-target-call-checks");
   }
 
   if (Triple.isOSWindows() && (Triple.getArch() == llvm::Triple::arm ||

clang/lib/Frontend/InitPreprocessor.cpp

@@ -411,6 +411,8 @@ static void InitializeStandardPredefinedMacros(const TargetInfo &TI,
   // Not "standard" per se, but available even with the -undef flag.
   if (LangOpts.AsmPreprocessor)
     Builder.defineMacro("__ASSEMBLER__");
+  if (LangOpts.CUDA)
+    Builder.defineMacro("__CUDA__");
 }
 
 /// Initialize the predefined C++ language feature test macros defined in

clang/test/Driver/cuda-detect.cu

@@ -8,8 +8,6 @@
 // RUN: %clang -v --target=i386-unknown-linux \
 // RUN:   --sysroot=%S/Inputs/CUDA 2>&1 | FileCheck %s
 // RUN: %clang -v --target=i386-unknown-linux \
-// RUN:   --sysroot=%S/Inputs/CUDA 2>&1 | FileCheck %s
-// RUN: %clang -v --target=i386-unknown-linux \
 // RUN:   --cuda-path=%S/Inputs/CUDA/usr/local/cuda 2>&1 | FileCheck %s
 
 // Make sure we map libdevice bitcode files to proper GPUs.
@@ -40,6 +38,12 @@
 // RUN: %clang -### -v --target=i386-unknown-linux --cuda-gpu-arch=sm_35 \
 // RUN:   -nocudalib --cuda-path=%S/Inputs/CUDA/usr/local/cuda %s 2>&1 \
 // RUN:   | FileCheck %s -check-prefix COMMON -check-prefix NOLIBDEVICE
+// Verify that we don't add include paths, link with libdevice or
+// -include cuda_runtime without valid CUDA installation.
+// RUN: %clang -### -v --target=i386-unknown-linux --cuda-gpu-arch=sm_35 \
+// RUN:   --cuda-path=%S/no-cuda-there %s 2>&1 \
+// RUN:   | FileCheck %s -check-prefix COMMON \
+// RUN:     -check-prefix NOCUDAINC -check-prefix NOLIBDEVICE
 
 // CHECK: Found CUDA installation: {{.*}}/Inputs/CUDA/usr/local/cuda
 // NOCUDA-NOT: Found CUDA installation:
@@ -55,5 +59,6 @@
 // NOLIBDEVICE-NOT: "-target-feature" "+ptx42"
 // CUDAINC-SAME: "-internal-isystem" "{{.*}}/Inputs/CUDA/usr/local/cuda/include"
 // NOCUDAINC-NOT: "-internal-isystem" "{{.*}}/cuda/include"
+// CUDAINC-SAME: "-include" "cuda_runtime.h"
+// NOCUDAINC-NOT: "-include" "cuda_runtime.h"
 // COMMON-SAME: "-x" "cuda"
-

clang/unittests/ASTMatchers/ASTMatchersTest.h

@@ -178,6 +178,7 @@ testing::AssertionResult matchesConditionallyWithCuda(
   Args.push_back("-xcuda");
   Args.push_back("-fno-ms-extensions");
   Args.push_back("--cuda-host-only");
+  Args.push_back("-nocudainc");
   Args.push_back(CompileArg);
   if (!runToolOnCodeWithArgs(Factory->create(),
                              CudaHeader + Code, Args)) {