Index: include/clang/Driver/Options.td
===================================================================
--- include/clang/Driver/Options.td
+++ include/clang/Driver/Options.td
@@ -359,6 +359,8 @@
   Flags<[DriverOption, HelpHidden]>, HelpText<"CUDA GPU architecture">;
 def cuda_host_only : Flag<["--"], "cuda-host-only">,
   HelpText<"Do host-side CUDA compilation only">;
+def cuda_path_EQ : Joined<["--"], "cuda-path=">, Group<i_Group>,
+  HelpText<"CUDA installation path">;
 def dA : Flag<["-"], "dA">, Group<d_Group>;
 def dD : Flag<["-"], "dD">, Group<d_Group>, Flags<[CC1Option]>,
   HelpText<"Print macro definitions in -E mode in addition to normal output">;
Index: lib/Driver/ToolChains.h
===================================================================
--- lib/Driver/ToolChains.h
+++ lib/Driver/ToolChains.h
@@ -157,6 +157,42 @@
 protected:
   GCCInstallationDetector GCCInstallation;
 
+  // \brief A class to find a viable CUDA installation
+
+  class CudaInstallationDetector {
+    bool IsValid;
+    std::string CudaInstallPath;
+    std::string CudaLibPath;
+    std::string CudaLibDevicePath;
+    std::string CudaIncludePath;
+    llvm::StringMap<std::string> CudaLibDeviceMap;
+
+  public:
+    CudaInstallationDetector() : IsValid(false) {}
+    void init(const Driver &D, const llvm::Triple &TargetTriple,
+              const llvm::opt::ArgList &Args);
+
+    /// \brief Check whether we detected a valid Cuda install.
+    bool isValid() const { return IsValid; }
+    /// \brief Print information about the detected CUDA installation.
+    void print(raw_ostream &OS) const;
+
+    /// \brief Get the detected Cuda installation path.
+    StringRef getInstallPath() const { return CudaInstallPath; }
+    /// \brief Get the detected Cuda Include path.
+    StringRef getIncludePath() const { return CudaIncludePath; }
+    /// \brief Get the detected Cuda library path.
+    StringRef getLibPath() const { return CudaLibPath; }
+    /// \brief Get the detected Cuda device library path.
+    StringRef getLibDevicePath() const { return CudaLibDevicePath; }
+    /// \brief Get libdevice file for given architecture
+    StringRef getLibDeviceFile(StringRef Gpu) const {
+      return CudaLibDeviceMap.lookup(Gpu);
+    }
+  };
+
+  CudaInstallationDetector CudaInstallation;
+
 public:
   Generic_GCC(const Driver &D, const llvm::Triple &Triple,
               const llvm::opt::ArgList &Args);
Index: lib/Driver/ToolChains.cpp
===================================================================
--- lib/Driver/ToolChains.cpp
+++ lib/Driver/ToolChains.cpp
@@ -1482,6 +1482,74 @@
     BiarchTripleAliases.push_back(BiarchTriple.str());
 }
 
+// \brief -- try common CUDA installation paths looking for files we need for
+// CUDA compilation.
+
+void
+Generic_GCC::CudaInstallationDetector::init(const Driver &D,
+                                            const llvm::Triple &TargetTriple,
+                                            const llvm::opt::ArgList &Args) {
+  SmallVector<StringRef, 4> CudaPathCandidates;
+
+  if (Args.hasArg(options::OPT_cuda_path_EQ))
+    CudaPathCandidates.push_back(
+        Args.getLastArgValue(options::OPT_cuda_path_EQ));
+  else {
+    std::string Prefix = D.SysRoot.empty() ? "" : D.SysRoot;
+    CudaPathCandidates.push_back(Prefix + "/usr/local/cuda");
+    CudaPathCandidates.push_back(Prefix + "/usr/local/cuda-7.0");
+  }
+
+  for (const auto CudaPath : CudaPathCandidates) {
+    if (CudaPath.empty() || !llvm::sys::fs::exists(CudaPath))
+      continue;
+
+    CudaInstallPath = CudaPath;
+    CudaIncludePath = CudaInstallPath + "/include";
+    CudaLibDevicePath = CudaInstallPath + "/nvvm/libdevice";
+    CudaLibPath =
+        CudaInstallPath + (TargetTriple.isArch64Bit() ? "/lib64" : "/lib");
+
+    if (!(llvm::sys::fs::exists(CudaIncludePath) &&
+          llvm::sys::fs::exists(CudaLibPath) &&
+          llvm::sys::fs::exists(CudaLibDevicePath)))
+      continue;
+
+    const StringRef LibDeviceName = "libdevice.";
+    std::error_code EC;
+    for (llvm::sys::fs::directory_iterator LI(CudaLibDevicePath, EC), LE;
+         !EC && LI != LE; LI = LI.increment(EC)) {
+      StringRef FilePath = LI->path();
+      StringRef FileName = llvm::sys::path::filename(FilePath);
+      // Process all bitcode filenames that look like libdevice.compute_XX.YY.bc
+      if (!(FileName.startswith(LibDeviceName) && FileName.endswith(".bc")))
+        continue;
+      StringRef GpuArch = FileName.slice(
+          LibDeviceName.size(), FileName.find('.', LibDeviceName.size()));
+      CudaLibDeviceMap[GpuArch] = FilePath.str();
+      // Insert map entries for specifc devices with this compute capability.
+      if (GpuArch == "compute_20") {
+        CudaLibDeviceMap["sm_20"] = FilePath;
+        CudaLibDeviceMap["sm_21"] = FilePath;
+      } else if (GpuArch == "compute_30") {
+        CudaLibDeviceMap["sm_30"] = FilePath;
+        CudaLibDeviceMap["sm_32"] = FilePath;
+      } else if (GpuArch == "compute_35") {
+        CudaLibDeviceMap["sm_35"] = FilePath;
+        CudaLibDeviceMap["sm_37"] = FilePath;
+      }
+    }
+
+    IsValid = true;
+    break;
+  }
+}
+
+void Generic_GCC::CudaInstallationDetector::print(raw_ostream &OS) const {
+  if (isValid())
+    OS << "Found CUDA installation: " << CudaInstallPath << "\n";
+}
+
 namespace {
 // Filter to remove Multilibs that don't exist as a suffix to Path
 class FilterNonExistent {
@@ -2053,7 +2121,7 @@
 
 Generic_GCC::Generic_GCC(const Driver &D, const llvm::Triple &Triple,
                          const ArgList &Args)
-    : ToolChain(D, Triple, Args), GCCInstallation() {
+    : ToolChain(D, Triple, Args), GCCInstallation(), CudaInstallation() {
   getProgramPaths().push_back(getDriver().getInstalledDir());
   if (getDriver().getInstalledDir() != getDriver().Dir)
     getProgramPaths().push_back(getDriver().Dir);
@@ -2085,6 +2153,7 @@
 void Generic_GCC::printVerboseInfo(raw_ostream &OS) const {
   // Print the information about how we detected the GCC installation.
   GCCInstallation.print(OS);
+  CudaInstallation.print(OS);
 }
 
 bool Generic_GCC::IsUnwindTablesDefault() const {
@@ -3261,6 +3330,7 @@
 Linux::Linux(const Driver &D, const llvm::Triple &Triple, const ArgList &Args)
     : Generic_ELF(D, Triple, Args) {
   GCCInstallation.init(D, Triple, Args);
+  CudaInstallation.init(D, Triple, Args);
   Multilibs = GCCInstallation.getMultilibs();
   llvm::Triple::ArchType Arch = Triple.getArch();
   std::string SysRoot = computeSysRoot();