Index: include/clang/Basic/DiagnosticDriverKinds.td
===================================================================
--- include/clang/Basic/DiagnosticDriverKinds.td
+++ include/clang/Basic/DiagnosticDriverKinds.td
@@ -26,6 +26,9 @@
 def err_drv_no_cuda_installation : Error<
   "cannot find CUDA installation.  Provide its path via --cuda-path, or pass "
   "-nocudainc to build without CUDA includes.">;
+def err_drv_no_cuda_libdevice : Error<
+  "cannot find libdevice for %0. Provide path to different CUDA installation "
+  "via --cuda-path, or pass -nocudalib to build without linking with libdevice.">;
 def err_drv_cuda_version_too_low : Error<
   "GPU arch %1 requires CUDA version at least %3, but installation at %0 is %2. "
   "Use --cuda-path to specify a different CUDA install, or pass "
Index: lib/Driver/ToolChains.cpp
===================================================================
--- lib/Driver/ToolChains.cpp
+++ lib/Driver/ToolChains.cpp
@@ -1791,22 +1791,32 @@
           LibDeviceName.size(), FileName.find('.', LibDeviceName.size()));
       LibDeviceMap[GpuArch] = FilePath.str();
       // Insert map entries for specifc devices with this compute capability.
+      // NVCC's choice of libdevice library version is rather peculiar:
+      // http://docs.nvidia.com/cuda/libdevice-users-guide/basic-usage.html#version-selection
+      // TODO: this will need to be updated once CUDA-8 is released.
       if (GpuArch == "compute_20") {
         LibDeviceMap["sm_20"] = FilePath;
         LibDeviceMap["sm_21"] = FilePath;
+        LibDeviceMap["sm_32"] = FilePath;
       } else if (GpuArch == "compute_30") {
         LibDeviceMap["sm_30"] = FilePath;
-        LibDeviceMap["sm_32"] = FilePath;
-      } else if (GpuArch == "compute_35") {
-        LibDeviceMap["sm_35"] = FilePath;
-        LibDeviceMap["sm_37"] = FilePath;
-      } else if (GpuArch == "compute_50") {
+        // compute_30 is the fallback libdevice variant for sm_30+,
+        // unless CUDA specifies different version for specific GPU
+        // arch.
         LibDeviceMap["sm_50"] = FilePath;
         LibDeviceMap["sm_52"] = FilePath;
         LibDeviceMap["sm_53"] = FilePath;
+        // sm_6? are currently all aliases for sm_53 in LLVM and
+        // should use compute_30.
         LibDeviceMap["sm_60"] = FilePath;
         LibDeviceMap["sm_61"] = FilePath;
         LibDeviceMap["sm_62"] = FilePath;
+      } else if (GpuArch == "compute_35") {
+        LibDeviceMap["sm_35"] = FilePath;
+        LibDeviceMap["sm_37"] = FilePath;
+      } else if (GpuArch == "compute_50") {
+        // NVCC does not use compute_50 libdevice at all at the moment.
+        // The version that's shipped with CUDA-7.5 is a copy of compute_30.
       }
     }
 
@@ -4759,18 +4769,23 @@
   if (DriverArgs.hasArg(options::OPT_nocudalib))
     return;
 
-  std::string LibDeviceFile = CudaInstallation.getLibDeviceFile(
-      DriverArgs.getLastArgValue(options::OPT_march_EQ));
-  if (!LibDeviceFile.empty()) {
-    CC1Args.push_back("-mlink-cuda-bitcode");
-    CC1Args.push_back(DriverArgs.MakeArgString(LibDeviceFile));
+  StringRef GpuArch =
+      DriverArgs.getLastArgValue(options::OPT_march_EQ, "sm_20");
+  std::string LibDeviceFile = CudaInstallation.getLibDeviceFile(GpuArch);
 
-    // Libdevice in CUDA-7.0 requires PTX version that's more recent
-    // than LLVM defaults to. Use PTX4.2 which is the PTX version that
-    // came with CUDA-7.0.
-    CC1Args.push_back("-target-feature");
-    CC1Args.push_back("+ptx42");
+  if (LibDeviceFile.empty()) {
+    getDriver().Diag(diag::err_drv_no_cuda_libdevice) << GpuArch;
+    return;
   }
+
+  CC1Args.push_back("-mlink-cuda-bitcode");
+  CC1Args.push_back(DriverArgs.MakeArgString(LibDeviceFile));
+
+  // Libdevice in CUDA-7.0 requires PTX version that's more recent
+  // than LLVM defaults to. Use PTX4.2 which is the PTX version that
+  // came with CUDA-7.0.
+  CC1Args.push_back("-target-feature");
+  CC1Args.push_back("+ptx42");
 }
 
 void CudaToolChain::AddCudaIncludeArgs(const ArgList &DriverArgs,
@@ -4778,8 +4793,7 @@
   // Check our CUDA version if we're going to include the CUDA headers.
   if (!DriverArgs.hasArg(options::OPT_nocudainc) &&
       !DriverArgs.hasArg(options::OPT_no_cuda_version_check)) {
-    StringRef Arch = DriverArgs.getLastArgValue(options::OPT_march_EQ);
-    assert(!Arch.empty() && "Must have an explicit GPU arch.");
+    StringRef Arch = DriverArgs.getLastArgValue(options::OPT_march_EQ, "sm_20");
     CudaInstallation.CheckCudaVersionSupportsArch(StringToCudaArch(Arch));
   }
   Linux::AddCudaIncludeArgs(DriverArgs, CC1Args);
Index: test/Driver/cuda-detect.cu
===================================================================
--- test/Driver/cuda-detect.cu
+++ test/Driver/cuda-detect.cu
@@ -29,12 +29,12 @@
 // RUN:   --cuda-path=%S/no-cuda-there %s 2>&1 \
 // RUN:   | FileCheck %s -check-prefix COMMON -check-prefix NOCUDAINC
 
-// Verify that no options related to bitcode linking are passes if
-// there's no bitcode file.
+// Verify that we get an error if there's no libdevice library to link with.
 // RUN: %clang -### -v --target=i386-unknown-linux --cuda-gpu-arch=sm_30 \
 // RUN:   --cuda-path=%S/Inputs/CUDA/usr/local/cuda %s 2>&1 \
-// RUN:   | FileCheck %s -check-prefix COMMON -check-prefix NOLIBDEVICE
-// .. or if we explicitly passed -nocudalib
+// RUN:   | FileCheck %s -check-prefix COMMON -check-prefix MISSINGLIBDEVICE
+
+// Verify that  -nocudalib prevents linking libdevice bitcode in.
 // 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
@@ -48,6 +48,8 @@
 // CHECK: Found CUDA installation: {{.*}}/Inputs/CUDA/usr/local/cuda
 // NOCUDA-NOT: Found CUDA installation:
 
+// MISSINGLIBDEVICE: error: cannot find libdevice for sm_30.
+
 // COMMON: "-triple" "nvptx-nvidia-cuda"
 // COMMON-SAME: "-fcuda-is-device"
 // LIBDEVICE-SAME: "-mlink-cuda-bitcode"