[CUDA] Require libdevice only if needed

[Hahnfeld]

Summary

If the user passes -nocudalib, we can live without it being present.
Simplify the code by just checking whether LibDeviceMap is empty.

[tra]

The change could use a test.

[Hahnfeld]

Fix one more condition that checks for nvvm/libdevice and add a test.

[tra]

Looks good. Thank you.

cfe/trunk/lib/Driver/ToolChains/Cuda.cpp

if (CudaPath.empty() || !D.getVFS().exists(CudaPath))
       continue;
 
     InstallPath = CudaPath;
     BinPath = CudaPath + "/bin";
     IncludePath = InstallPath + "/include";
     LibDevicePath = InstallPath + "/nvvm/libdevice";
 
     auto &FS = D.getVFS();
-    if (!(FS.exists(IncludePath) && FS.exists(BinPath) &&
-          FS.exists(LibDevicePath)))
+    if (!(FS.exists(IncludePath) && FS.exists(BinPath)))
       continue;
 
     // On Linux, we have both lib and lib64 directories, and we need to choose
     // based on our triple.  On MacOS, we have only a lib directory.
     //
     // It's sufficient for our purposes to be flexible: If both lib and lib64
     // exist, we choose whichever one matches our triple.  Otherwise, if only
     // lib exists, we use it.
if (Version == CudaVersion::CUDA_90) {
             LibDeviceMap["sm_50"] = FilePath;
             LibDeviceMap["sm_52"] = FilePath;
             LibDeviceMap["sm_53"] = FilePath;
           }
         }
       }
     }
 
-    // This code prevents IsValid from being set when
-    // no libdevice has been found.
-    bool allEmpty = true;
-    std::string LibDeviceFile;
-    for (auto key : LibDeviceMap.keys()) {
-      LibDeviceFile = LibDeviceMap.lookup(key);
-      if (!LibDeviceFile.empty())
-        allEmpty = false;
-    }
-
-    if (allEmpty)
+    // Check that we have found at least one libdevice that we can link in if
+    // -nocudalib hasn't been specified.
+    if (LibDeviceMap.empty() && !Args.hasArg(options::OPT_nocudalib))
       continue;
 
     IsValid = true;
     break;
   }
 }
 
 void CudaInstallationDetector::AddCudaIncludeArgs(

cfe/trunk/test/Driver/cuda-detect.cu

 // REQUIRES: clang-driver
 // REQUIRES: x86-registered-target
 // REQUIRES: nvptx-registered-target
 //
-// # Check that we properly detect CUDA installation.
+// Check that we properly detect CUDA installation.
 // RUN: %clang -v --target=i386-unknown-linux \
 // RUN:   --sysroot=%S/no-cuda-there 2>&1 | FileCheck %s -check-prefix NOCUDA
 // RUN: %clang -v --target=i386-apple-macosx \
 // RUN:   --sysroot=%S/no-cuda-there 2>&1 | FileCheck %s -check-prefix NOCUDA
 
 // RUN: %clang -v --target=i386-unknown-linux \
 // RUN:   --sysroot=%S/Inputs/CUDA 2>&1 | FileCheck %s
 // RUN: %clang -v --target=i386-apple-macosx \
 // 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
 // RUN: %clang -v --target=i386-apple-macosx \
 // RUN:   --cuda-path=%S/Inputs/CUDA/usr/local/cuda 2>&1 | FileCheck %s
 
+// Check that we don't find a CUDA installation without libdevice ...
+// RUN: %clang -v --target=i386-unknown-linux \
+// RUN:   --sysroot=%S/Inputs/CUDA-nolibdevice 2>&1 | FileCheck %s -check-prefix NOCUDA
+// RUN: %clang -v --target=i386-apple-macosx \
+// RUN:   --sysroot=%S/Inputs/CUDA-nolibdevice 2>&1 | FileCheck %s -check-prefix NOCUDA
+
+// ... unless the user doesn't need libdevice
+// RUN: %clang -v --target=i386-unknown-linux -nocudalib \
+// RUN:   --sysroot=%S/Inputs/CUDA-nolibdevice 2>&1 | FileCheck %s -check-prefix NO-LIBDEVICE
+// RUN: %clang -v --target=i386-apple-macosx -nocudalib \
+// RUN:   --sysroot=%S/Inputs/CUDA-nolibdevice 2>&1 | FileCheck %s -check-prefix NO-LIBDEVICE
+
+
 // Make sure we map libdevice bitcode files to proper GPUs. These
 // tests use Inputs/CUDA_80 which has full set of libdevice files.
 // However, libdevice mapping only matches CUDA-7.x at the moment.
 // sm_2x, sm_32 -> compute_20
 // RUN: %clang -### -v --target=i386-unknown-linux --cuda-gpu-arch=sm_21 \
 // RUN:   --cuda-path=%S/Inputs/CUDA_80/usr/local/cuda %s 2>&1 \
 // RUN:   | FileCheck %s -check-prefix COMMON \
 // RUN:     -check-prefix LIBDEVICE -check-prefix LIBDEVICE20

 
 // Verify that C++ include paths are passed for both host and device frontends.
 // RUN: %clang -### -no-canonical-prefixes -target x86_64-linux-gnu %s \
 // RUN: --stdlib=libstdc++ --sysroot=%S/Inputs/ubuntu_14.04_multiarch_tree2 \
 // RUN: --gcc-toolchain="" 2>&1 \
 // RUN: | FileCheck %s --check-prefix CHECK-CXXINCLUDE
 
 // CHECK: Found CUDA installation: {{.*}}/Inputs/CUDA/usr/local/cuda
+// NO-LIBDEVICE: Found CUDA installation: {{.*}}/Inputs/CUDA-nolibdevice/usr/local/cuda
 // NOCUDA-NOT: Found CUDA installation:
 
 // MISSINGLIBDEVICE: error: cannot find libdevice for sm_20.
 
 // COMMON: "-triple" "nvptx-nvidia-cuda"
 // COMMON-SAME: "-fcuda-is-device"
 // LIBDEVICE-SAME: "-mlink-cuda-bitcode"
 // NOLIBDEVICE-NOT: "-mlink-cuda-bitcode"