1 files changed, 30 insertions, 9 deletions

diff --git a/contrib/llvm-project/clang/lib/Driver/Driver.cpp b/contrib/llvm-project/clang/lib/Driver/Driver.cpp
index 0da32dae2ef6..3a8400a55741 100644
--- a/contrib/llvm-project/clang/lib/Driver/Driver.cpp
+++ b/contrib/llvm-project/clang/lib/Driver/Driver.cpp
@@ -2930,7 +2930,7 @@ class OffloadingActionBuilder final {
         return false;
 
       Relocatable = Args.hasFlag(options::OPT_fgpu_rdc,
-          options::OPT_fno_gpu_rdc, /*Default=*/false);
+                                 options::OPT_fno_gpu_rdc, /*Default=*/false);
 
       const ToolChain *HostTC = C.getSingleOffloadToolChain<Action::OFK_Host>();
       assert(HostTC && "No toolchain for host compilation.");
@@ -3326,7 +3326,7 @@ class OffloadingActionBuilder final {
                                                AssociatedOffloadKind);
 
       if (CompileDeviceOnly && CurPhase == FinalPhase && BundleOutput &&
-          BundleOutput.getValue()) {
+          BundleOutput.value()) {
         for (unsigned I = 0, E = GpuArchList.size(); I != E; ++I) {
           OffloadAction::DeviceDependences DDep;
           DDep.add(*CudaDeviceActions[I], *ToolChains.front(), GpuArchList[I],
@@ -4355,7 +4355,17 @@ Driver::getOffloadArchs(Compilation &C, const llvm::opt::DerivedArgList &Args,
     return KnownArchs.lookup(TC);
 
   llvm::DenseSet<StringRef> Archs;
-  for (auto &Arg : Args) {
+  for (auto *Arg : Args) {
+    // Extract any '--[no-]offload-arch' arguments intended for this toolchain.
+    std::unique_ptr<llvm::opt::Arg> ExtractedArg = nullptr;
+    if (Arg->getOption().matches(options::OPT_Xopenmp_target_EQ) &&
+        ToolChain::getOpenMPTriple(Arg->getValue(0)) == TC->getTriple()) {
+      Arg->claim();
+      unsigned Index = Args.getBaseArgs().MakeIndex(Arg->getValue(1));
+      ExtractedArg = getOpts().ParseOneArg(Args, Index);
+      Arg = ExtractedArg.get();
+    }
+
     if (Arg->getOption().matches(options::OPT_offload_arch_EQ)) {
       for (StringRef Arch : llvm::split(Arg->getValue(), ","))
         Archs.insert(getCanonicalArchString(C, Args, Arch, TC->getTriple()));
@@ -4425,8 +4435,7 @@ Action *Driver::BuildOffloadingActions(Compilation &C,
     // Get the product of all bound architectures and toolchains.
     SmallVector<std::pair<const ToolChain *, StringRef>> TCAndArchs;
     for (const ToolChain *TC : ToolChains)
-      for (StringRef Arch : getOffloadArchs(
-               C, C.getArgsForToolChain(TC, "generic", Kind), Kind, TC))
+      for (StringRef Arch : getOffloadArchs(C, Args, Kind, TC))
         TCAndArchs.push_back(std::make_pair(TC, Arch));
 
     for (unsigned I = 0, E = TCAndArchs.size(); I != E; ++I)
@@ -4477,11 +4486,23 @@ Action *Driver::BuildOffloadingActions(Compilation &C,
   if (offloadDeviceOnly())
     return C.MakeAction<OffloadAction>(DDeps, types::TY_Nothing);
 
-  Action *OffloadPackager =
-      C.MakeAction<OffloadPackagerJobAction>(OffloadActions, types::TY_Image);
   OffloadAction::DeviceDependences DDep;
-  DDep.add(*OffloadPackager, *C.getSingleOffloadToolChain<Action::OFK_Host>(),
-           nullptr, Action::OFK_None);
+  if (C.isOffloadingHostKind(Action::OFK_Cuda) &&
+      !Args.hasFlag(options::OPT_fgpu_rdc, options::OPT_fno_gpu_rdc, false)) {
+    // If we are not in RDC-mode we just emit the final CUDA fatbinary for each
+    // translation unit without requiring any linking.
+    Action *FatbinAction =
+        C.MakeAction<LinkJobAction>(OffloadActions, types::TY_CUDA_FATBIN);
+    DDep.add(*FatbinAction, *C.getSingleOffloadToolChain<Action::OFK_Cuda>(),
+             nullptr, Action::OFK_Cuda);
+  } else {
+    // Package all the offloading actions into a single output that can be
+    // embedded in the host and linked.
+    Action *PackagerAction =
+        C.MakeAction<OffloadPackagerJobAction>(OffloadActions, types::TY_Image);
+    DDep.add(*PackagerAction, *C.getSingleOffloadToolChain<Action::OFK_Host>(),
+             nullptr, Action::OFK_None);
+  }
   OffloadAction::HostDependence HDep(
       *HostAction, *C.getSingleOffloadToolChain<Action::OFK_Host>(),
       /*BoundArch=*/nullptr, isa<CompileJobAction>(HostAction) ? DDep : DDeps);