3 files changed, 35 insertions, 18 deletions

diff --git a/clang/lib/Driver/ToolChains/Clang.cpp b/clang/lib/Driver/ToolChains/Clang.cpp
index eae86c05729..2f1fa4af807 100644
--- a/clang/lib/Driver/ToolChains/Clang.cpp
+++ b/clang/lib/Driver/ToolChains/Clang.cpp
@@ -5310,12 +5310,15 @@ void OffloadBundler::ConstructJob(Compilation &C, const JobAction &JA,
     if (I)
       Triples += ',';
 
+    // Find ToolChain for this input.
     Action::OffloadKind CurKind = Action::OFK_Host;
     const ToolChain *CurTC = &getToolChain();
     const Action *CurDep = JA.getInputs()[I];
 
     if (const auto *OA = dyn_cast<OffloadAction>(CurDep)) {
+      CurTC = nullptr;
       OA->doOnEachDependence([&](Action *A, const ToolChain *TC, const char *) {
+        assert(CurTC == nullptr && "Expected one dependence!");
         CurKind = A->getOffloadingDeviceKind();
         CurTC = TC;
       });
@@ -5336,7 +5339,17 @@ void OffloadBundler::ConstructJob(Compilation &C, const JobAction &JA,
   for (unsigned I = 0; I < Inputs.size(); ++I) {
     if (I)
       UB += ',';
-    UB += Inputs[I].getFilename();
+
+    // Find ToolChain for this input.
+    const ToolChain *CurTC = &getToolChain();
+    if (const auto *OA = dyn_cast<OffloadAction>(JA.getInputs()[I])) {
+      CurTC = nullptr;
+      OA->doOnEachDependence([&](Action *, const ToolChain *TC, const char *) {
+        assert(CurTC == nullptr && "Expected one dependence!");
+        CurTC = TC;
+      });
+    }
+    UB += CurTC->getInputFilename(Inputs[I]);
   }
   CmdArgs.push_back(TCArgs.MakeArgString(UB));
 
@@ -5396,13 +5409,7 @@ void OffloadBundler::ConstructJobMultipleOutputs(
   for (unsigned I = 0; I < Outputs.size(); ++I) {
     if (I)
       UB += ',';
-    SmallString<256> OutputFileName(Outputs[I].getFilename());
-    // Change extension of target files for OpenMP offloading
-    // to NVIDIA GPUs.
-    if (DepInfo[I].DependentToolChain->getTriple().isNVPTX() &&
-        JA.isOffloading(Action::OFK_OpenMP))
-      llvm::sys::path::replace_extension(OutputFileName, "cubin");
-    UB += OutputFileName;
+    UB += DepInfo[I].DependentToolChain->getInputFilename(Outputs[I]);
   }
   CmdArgs.push_back(TCArgs.MakeArgString(UB));
   CmdArgs.push_back("-unbundle");
diff --git a/clang/lib/Driver/ToolChains/Cuda.cpp b/clang/lib/Driver/ToolChains/Cuda.cpp
index 44ec16e8b86..4a5cf3dc6ae 100644
--- a/clang/lib/Driver/ToolChains/Cuda.cpp
+++ b/clang/lib/Driver/ToolChains/Cuda.cpp
@@ -301,10 +301,7 @@ void NVPTX::Assembler::ConstructJob(Compilation &C, const JobAction &JA,
   CmdArgs.push_back("--gpu-name");
   CmdArgs.push_back(Args.MakeArgString(CudaArchToString(gpu_arch)));
   CmdArgs.push_back("--output-file");
-  SmallString<256> OutputFileName(Output.getFilename());
-  if (JA.isOffloading(Action::OFK_OpenMP))
-    llvm::sys::path::replace_extension(OutputFileName, "cubin");
-  CmdArgs.push_back(Args.MakeArgString(OutputFileName));
+  CmdArgs.push_back(Args.MakeArgString(TC.getInputFilename(Output)));
   for (const auto& II : Inputs)
     CmdArgs.push_back(Args.MakeArgString(II.getFilename()));
 
@@ -431,11 +428,8 @@ void NVPTX::OpenMPLinker::ConstructJob(Compilation &C, const JobAction &JA,
     if (!II.isFilename())
       continue;
 
-    SmallString<256> Name(II.getFilename());
-    llvm::sys::path::replace_extension(Name, "cubin");
-
-    const char *CubinF =
-        C.addTempFile(C.getArgs().MakeArgString(Name));
+    const char *CubinF = C.addTempFile(
+        C.getArgs().MakeArgString(getToolChain().getInputFilename(II)));
 
     CmdArgs.push_back(CubinF);
   }
@@ -463,6 +457,20 @@ CudaToolChain::CudaToolChain(const Driver &D, const llvm::Triple &Triple,
   getProgramPaths().push_back(getDriver().Dir);
 }
 
+std::string CudaToolChain::getInputFilename(const InputInfo &Input) const {
+  // Only object files are changed, for example assembly files keep their .s
+  // extensions. CUDA also continues to use .o as they don't use nvlink but
+  // fatbinary.
+  if (!(OK == Action::OFK_OpenMP && Input.getType() == types::TY_Object))
+    return ToolChain::getInputFilename(Input);
+
+  // Replace extension for object files with cubin because nvlink relies on
+  // these particular file names.
+  SmallString<256> Filename(ToolChain::getInputFilename(Input));
+  llvm::sys::path::replace_extension(Filename, "cubin");
+  return Filename.str();
+}
+
 void CudaToolChain::addClangTargetOptions(
     const llvm::opt::ArgList &DriverArgs,
     llvm::opt::ArgStringList &CC1Args,
diff --git a/clang/lib/Driver/ToolChains/Cuda.h b/clang/lib/Driver/ToolChains/Cuda.h
index 23cca03eb20..3d08cec1643 100644
--- a/clang/lib/Driver/ToolChains/Cuda.h
+++ b/clang/lib/Driver/ToolChains/Cuda.h
@@ -137,10 +137,12 @@ public:
                 const ToolChain &HostTC, const llvm::opt::ArgList &Args,
                 const Action::OffloadKind OK);
 
-  virtual const llvm::Triple *getAuxTriple() const override {
+  const llvm::Triple *getAuxTriple() const override {
     return &HostTC.getTriple();
   }
 
+  std::string getInputFilename(const InputInfo &Input) const override;
+
   llvm::opt::DerivedArgList *
   TranslateArgs(const llvm::opt::DerivedArgList &Args, StringRef BoundArch,
                 Action::OffloadKind DeviceOffloadKind) const override;