1 files changed, 41 insertions, 10 deletions

diff --git a/clang/lib/Driver/Driver.cpp b/clang/lib/Driver/Driver.cpp
index 1580f09..ccdaa5c 100644
--- a/clang/lib/Driver/Driver.cpp
+++ b/clang/lib/Driver/Driver.cpp
@@ -2946,7 +2946,12 @@ class OffloadingActionBuilder final {
     CudaActionBuilderBase(Compilation &C, DerivedArgList &Args,
                           const Driver::InputList &Inputs,
                           Action::OffloadKind OFKind)
-        : DeviceActionBuilder(C, Args, Inputs, OFKind) {}
+        : DeviceActionBuilder(C, Args, Inputs, OFKind) {
+
+      CompileDeviceOnly = C.getDriver().offloadDeviceOnly();
+      Relocatable = Args.hasFlag(options::OPT_fgpu_rdc,
+                                 options::OPT_fno_gpu_rdc, /*Default=*/false);
+    }
 
     ActionBuilderReturnCode addDeviceDependences(Action *HostAction) override {
       // While generating code for CUDA, we only depend on the host input action
@@ -3099,9 +3104,6 @@ class OffloadingActionBuilder final {
           !C.hasOffloadToolChain<Action::OFK_HIP>())
         return false;
 
-      Relocatable = Args.hasFlag(options::OPT_fgpu_rdc,
-                                 options::OPT_fno_gpu_rdc, /*Default=*/false);
-
       const ToolChain *HostTC = C.getSingleOffloadToolChain<Action::OFK_Host>();
       assert(HostTC && "No toolchain for host compilation.");
       if (HostTC->getTriple().isNVPTX() ||
@@ -3120,7 +3122,6 @@ class OffloadingActionBuilder final {
               : C.getSingleOffloadToolChain<Action::OFK_HIP>());
 
       CompileHostOnly = C.getDriver().offloadHostOnly();
-      CompileDeviceOnly = C.getDriver().offloadDeviceOnly();
       EmitLLVM = Args.getLastArg(options::OPT_emit_llvm);
       EmitAsm = Args.getLastArg(options::OPT_S);
       FixedCUID = Args.getLastArgValue(options::OPT_cuid_EQ);
@@ -3352,16 +3353,40 @@ class OffloadingActionBuilder final {
     // only compilation. Bundle other type of output files only if
     // --gpu-bundle-output is specified for device only compilation.
     std::optional<bool> BundleOutput;
+    std::optional<bool> EmitReloc;
 
   public:
     HIPActionBuilder(Compilation &C, DerivedArgList &Args,
                      const Driver::InputList &Inputs)
         : CudaActionBuilderBase(C, Args, Inputs, Action::OFK_HIP) {
+
       DefaultCudaArch = CudaArch::GFX906;
+
+      if (Args.hasArg(options::OPT_fhip_emit_relocatable,
+                      options::OPT_fno_hip_emit_relocatable)) {
+        EmitReloc = Args.hasFlag(options::OPT_fhip_emit_relocatable,
+                                 options::OPT_fno_hip_emit_relocatable, false);
+
+        if (*EmitReloc) {
+          if (Relocatable) {
+            C.getDriver().Diag(diag::err_opt_not_valid_with_opt)
+                << "-fhip-emit-relocatable"
+                << "-fgpu-rdc";
+          }
+
+          if (!CompileDeviceOnly) {
+            C.getDriver().Diag(diag::err_opt_not_valid_without_opt)
+                << "-fhip-emit-relocatable"
+                << "--cuda-device-only";
+          }
+        }
+      }
+
       if (Args.hasArg(options::OPT_gpu_bundle_output,
                       options::OPT_no_gpu_bundle_output))
         BundleOutput = Args.hasFlag(options::OPT_gpu_bundle_output,
-                                    options::OPT_no_gpu_bundle_output, true);
+                                    options::OPT_no_gpu_bundle_output, true) &&
+                       (!EmitReloc || !*EmitReloc);
     }
 
     bool canUseBundlerUnbundler() const override { return true; }
@@ -3408,8 +3433,10 @@ class OffloadingActionBuilder final {
       assert(!CompileHostOnly &&
              "Not expecting HIP actions in host-only compilation.");
 
+      bool ShouldLink = !EmitReloc || !*EmitReloc;
+
       if (!Relocatable && CurPhase == phases::Backend && !EmitLLVM &&
-          !EmitAsm) {
+          !EmitAsm && ShouldLink) {
         // If we are in backend phase, we attempt to generate the fat binary.
         // We compile each arch to IR and use a link action to generate code
         // object containing ISA. Then we use a special "link" action to create
@@ -3485,6 +3512,8 @@ class OffloadingActionBuilder final {
 
         return CompileDeviceOnly ? ABRT_Ignore_Host : ABRT_Success;
       } else if (CurPhase == phases::Link) {
+        if (!ShouldLink)
+          return ABRT_Success;
         // Save CudaDeviceActions to DeviceLinkerInputs for each GPU subarch.
         // This happens to each device action originated from each input file.
         // Later on, device actions in DeviceLinkerInputs are used to create
@@ -3522,8 +3551,11 @@ class OffloadingActionBuilder final {
         CudaDeviceActions.clear();
       }
 
-      return (CompileDeviceOnly && CurPhase == FinalPhase) ? ABRT_Ignore_Host
-                                                           : ABRT_Success;
+      return (CompileDeviceOnly &&
+              (CurPhase == FinalPhase ||
+               (!ShouldLink && CurPhase == phases::Assemble)))
+                 ? ABRT_Ignore_Host
+                 : ABRT_Success;
     }
 
     void appendLinkDeviceActions(ActionList &AL) override {
@@ -3674,7 +3706,6 @@ public:
         ++InactiveBuilders;
         continue;
       }
-
       auto RetCode =
           SB->getDeviceDependences(DDeps, CurPhase, FinalPhase, Phases);