[CUDA] Do not allow using NVPTX target for host compilation.

Differential Revision: https://reviews.llvm.org/D23042

llvm-svn: 277537

clang/include/clang/Basic/DiagnosticDriverKinds.td

@@ -30,6 +30,7 @@ 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 "
   "--no-cuda-version-check.">;
+def err_drv_cuda_nvptx_host : Error<"unsupported use of NVPTX for host compilation.">;
 def err_drv_invalid_thread_model_for_target : Error<
   "invalid thread model '%0' in '%1' for this target">;
 def err_drv_invalid_linker_name : Error<

clang/lib/Driver/Driver.cpp

@@ -1407,11 +1407,19 @@ static Action *buildCudaActions(Compilation &C, DerivedArgList &Args,
   bool CompileDeviceOnly =
       PartialCompilationArg &&
       PartialCompilationArg->getOption().matches(options::OPT_cuda_device_only);
+  const ToolChain *HostTC = C.getSingleOffloadToolChain<Action::OFK_Host>();
+  assert(HostTC && "No toolchain for host compilation.");
+  if (HostTC->getTriple().isNVPTX()) {
+    // We do not support targeting NVPTX for host compilation. Throw
+    // an error and abort pipeline construction early so we don't trip
+    // asserts that assume device-side compilation.
+    C.getDriver().Diag(diag::err_drv_cuda_nvptx_host);
+    return nullptr;
+  }
 
   if (CompileHostOnly) {
-    OffloadAction::HostDependence HDep(
-        *HostAction, *C.getSingleOffloadToolChain<Action::OFK_Host>(),
-        /*BoundArch=*/nullptr, Action::OFK_Cuda);
+    OffloadAction::HostDependence HDep(*HostAction, *HostTC,
+                                       /*BoundArch=*/nullptr, Action::OFK_Cuda);
     return C.MakeAction<OffloadAction>(HDep);
   }
 
@@ -1507,9 +1515,8 @@ static Action *buildCudaActions(Compilation &C, DerivedArgList &Args,
 
   // Return a new host action that incorporates original host action and all
   // device actions.
-  OffloadAction::HostDependence HDep(
-      *HostAction, *C.getSingleOffloadToolChain<Action::OFK_Host>(),
-      /*BoundArch=*/nullptr, Action::OFK_Cuda);
+  OffloadAction::HostDependence HDep(*HostAction, *HostTC,
+                                     /*BoundArch=*/nullptr, Action::OFK_Cuda);
   OffloadAction::DeviceDependences DDep;
   DDep.add(*FatbinAction, *CudaTC, /*BoundArch=*/nullptr, Action::OFK_Cuda);
   return C.MakeAction<OffloadAction>(HDep, DDep);

clang/test/Driver/cuda-bad-arch.cu

@@ -19,4 +19,9 @@
 // RUN: %clang -### -target x86_64-linux-gnu -c %s 2>&1 \
 // RUN: | FileCheck -check-prefix OK %s
 
+// We don't allow using NVPTX for host compilation.
+// RUN: %clang -### --cuda-host-only -target nvptx-nvidia-cuda -c %s 2>&1 \
+// RUN: | FileCheck -check-prefix HOST_NVPTX %s
+
 // OK-NOT: error: Unsupported CUDA gpu architecture
+// HOST_NVPTX: error: unsupported use of NVPTX for host compilation.

clang/test/Preprocessor/cuda-types.cu

@@ -19,9 +19,3 @@
 // RUN: grep 'define __[^ ]*\(TYPE\|MAX\|SIZEOF\|WIDTH\)' %T/powerpc64-host-defines   | grep -v '__LDBL\|_LONG_DOUBLE' > %T/powerpc64-host-defines-filtered
 // RUN: grep 'define __[^ ]*\(TYPE\|MAX\|SIZEOF\|WIDTH\)' %T/powerpc64-device-defines | grep -v '__LDBL\|_LONG_DOUBLE' > %T/powerpc64-device-defines-filtered
 // RUN: diff %T/powerpc64-host-defines-filtered %T/powerpc64-device-defines-filtered
-
-// RUN: %clang --cuda-host-only -nocudainc -target nvptx-nvidia-cuda -x cuda -E -dM -o - /dev/null > %T/nvptx-host-defines
-// RUN: %clang --cuda-device-only -nocudainc -target nvptx-nvidia-cuda -x cuda -E -dM -o - /dev/null > %T/nvptx-device-defines
-// RUN: grep 'define __[^ ]*\(TYPE\|MAX\|SIZEOF\|WIDTH\)' %T/nvptx-host-defines   | grep -v '__LDBL\|_LONG_DOUBLE' > %T/nvptx-host-defines-filtered
-// RUN: grep 'define __[^ ]*\(TYPE\|MAX\|SIZEOF\|WIDTH\)' %T/nvptx-device-defines | grep -v '__LDBL\|_LONG_DOUBLE' > %T/nvptx-device-defines-filtered
-// RUN: diff %T/nvptx-host-defines-filtered %T/nvptx-device-defines-filtered

clang/unittests/ASTMatchers/ASTMatchersTest.h

@@ -189,7 +189,7 @@ testing::AssertionResult matchesConditionallyWithCuda(
   // avoid constructing a full system triple.
   std::vector<std::string> Args = {
       "-xcuda",  "-fno-ms-extensions",      "--cuda-host-only", "-nocudainc",
-      "-target", "nvptx64-unknown-unknown", CompileArg};
+      "-target", "x86_64-unknown-unknown", CompileArg};
   if (!runToolOnCodeWithArgs(Factory->create(),
                              CudaHeader + Code, Args)) {
     return testing::AssertionFailure() << "Parsing error in \"" << Code << "\"";