[HIP] Add hip offload kind

[yaxunl]

Summary

There are quite differences in HIP action builder and action job creation,
which justifies to define a separate offload kind.

[rjmccall]

Otherwise LGTM.

lib/Driver/Compilation.cpp

201 ↗

(On Diff #145290)

Mentioning only CUDA in the second clause makes me wonder whether it's *only* okay to abort a CUDA pipeline, not a HIP one. That is presumably not your intent. You could just drop "CUDA" there.

[yaxunl]

lib/Driver/Compilation.cpp

201 ↗

(On Diff #145290)

The second sentence is OK for both CUDA and HIP. Will drop CUDA in the second sentence.

[yaxunl]

Updated comments.

[rjmccall]

Thanks, LGTM.

[tra]

Small nit. LGTM otherwise.

lib/Driver/ToolChains/Clang.cpp

133–135 ↗

(On Diff #145472)

CUDA and HIP are mutually exclusive, so this should probably be else if

[yaxunl]

lib/Driver/ToolChains/Clang.cpp

133–135 ↗

(On Diff #145472)

Will do when committing.

cfe/trunk/include/clang/Driver/Action.h

enum OffloadKind {
     OFK_None = 0x00,
 
     // The host offloading tool chain.
     OFK_Host = 0x01,
 
     // The device offloading tool chains - one bit for each programming model.
     OFK_Cuda = 0x02,
     OFK_OpenMP = 0x04,
+    OFK_HIP = 0x08,
   };
 
   static const char *getClassName(ActionClass AC);
 
 private:
   ActionClass Kind;
 
   /// The output type of this action.

cfe/trunk/lib/Driver/Action.cpp

case OFK_None:
     break;
   case OFK_Host:
     llvm_unreachable("Host kind is not an offloading device kind.");
     break;
   case OFK_Cuda:
     return "device-cuda";
   case OFK_OpenMP:
     return "device-openmp";
+  case OFK_HIP:
+    return "device-hip";
 
     // TODO: Add other programming models here.
   }
 
   if (!ActiveOffloadKindMask)
     return {};
 
   std::string Res("host");
+  assert(!((ActiveOffloadKindMask & OFK_Cuda) &&
+           (ActiveOffloadKindMask & OFK_HIP)) &&
+         "Cannot offload CUDA and HIP at the same time");
   if (ActiveOffloadKindMask & OFK_Cuda)
     Res += "-cuda";
+  if (ActiveOffloadKindMask & OFK_HIP)
+    Res += "-hip";
   if (ActiveOffloadKindMask & OFK_OpenMP)
     Res += "-openmp";
 
   // TODO: Add other programming models here.
 
   return Res;
 }
 
StringRef Action::GetOffloadKindName(OffloadKind Kind) {
   switch (Kind) {
   case OFK_None:
   case OFK_Host:
     return "host";
   case OFK_Cuda:
     return "cuda";
   case OFK_OpenMP:
     return "openmp";
+  case OFK_HIP:
+    return "hip";
 
     // TODO: Add other programming models here.
   }
 
   llvm_unreachable("invalid offload kind");
 }
 
 void InputAction::anchor() {}

cfe/trunk/lib/Driver/Compilation.cpp

 
 using FailingCommandList = SmallVectorImpl<std::pair<int, const Command *>>;
 
 static bool ActionFailed(const Action *A,
                          const FailingCommandList &FailingCommands) {
   if (FailingCommands.empty())
     return false;
 
-  // CUDA can have the same input source code compiled multiple times so do not
-  // compiled again if there are already failures. It is OK to abort the CUDA
-  // pipeline on errors.
-  if (A->isOffloading(Action::OFK_Cuda))
+  // CUDA/HIP can have the same input source code compiled multiple times so do
+  // not compiled again if there are already failures. It is OK to abort the
+  // CUDA pipeline on errors.
+  if (A->isOffloading(Action::OFK_Cuda) || A->isOffloading(Action::OFK_HIP))
     return true;
 
   for (const auto &CI : FailingCommands)
     if (A == &(CI.second->getSource()))
       return true;
 
   for (const auto *AI : A->inputs())
     if (ActionFailed(AI, FailingCommands))

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

forAllAssociatedToolChains(Compilation &C, const JobAction &JA,
   Work(RegularToolChain);
 
   // Apply Work on all the offloading tool chains associated with the current
   // action.
   if (JA.isHostOffloading(Action::OFK_Cuda))
     Work(*C.getSingleOffloadToolChain<Action::OFK_Cuda>());
   else if (JA.isDeviceOffloading(Action::OFK_Cuda))
     Work(*C.getSingleOffloadToolChain<Action::OFK_Host>());
+  else if (JA.isHostOffloading(Action::OFK_HIP))
+    Work(*C.getSingleOffloadToolChain<Action::OFK_HIP>());
+  else if (JA.isDeviceOffloading(Action::OFK_HIP))
+    Work(*C.getSingleOffloadToolChain<Action::OFK_Host>());
 
   if (JA.isHostOffloading(Action::OFK_OpenMP)) {
     auto TCs = C.getOffloadToolChains<Action::OFK_OpenMP>();
     for (auto II = TCs.first, IE = TCs.second; II != IE; ++II)
       Work(*II->second);
   } else if (JA.isDeviceOffloading(Action::OFK_OpenMP))
     Work(*C.getSingleOffloadToolChain<Action::OFK_Host>());
 
void Clang::ConstructJob(Compilation &C, const JobAction &JA,
   bool KernelOrKext =
       Args.hasArg(options::OPT_mkernel, options::OPT_fapple_kext);
   const Driver &D = getToolChain().getDriver();
   ArgStringList CmdArgs;
 
   // Check number of inputs for sanity. We need at least one input.
   assert(Inputs.size() >= 1 && "Must have at least one input.");
   const InputInfo &Input = Inputs[0];
-  // CUDA compilation may have multiple inputs (source file + results of
+  // CUDA/HIP compilation may have multiple inputs (source file + results of
   // device-side compilations). OpenMP device jobs also take the host IR as a
   // second input. All other jobs are expected to have exactly one
   // input.
   bool IsCuda = JA.isOffloading(Action::OFK_Cuda);
+  bool IsHIP = JA.isOffloading(Action::OFK_HIP);
   bool IsOpenMPDevice = JA.isDeviceOffloading(Action::OFK_OpenMP);
-  assert((IsCuda || (IsOpenMPDevice && Inputs.size() == 2) ||
+  assert((IsCuda || IsHIP || (IsOpenMPDevice && Inputs.size() == 2) ||
           Inputs.size() == 1) &&
          "Unable to handle multiple inputs.");
 
   const llvm::Triple *AuxTriple =
       IsCuda ? getToolChain().getAuxTriple() : nullptr;
 
   bool IsWindowsGNU = RawTriple.isWindowsGNUEnvironment();
   bool IsWindowsCygnus = RawTriple.isWindowsCygwinEnvironment();
   bool IsWindowsMSVC = RawTriple.isWindowsMSVCEnvironment();
   bool IsIAMCU = RawTriple.isOSIAMCU();
 
-  // Adjust IsWindowsXYZ for CUDA compilations.  Even when compiling in device
-  // mode (i.e., getToolchain().getTriple() is NVPTX, not Windows), we need to
-  // pass Windows-specific flags to cc1.
-  if (IsCuda) {
+  // Adjust IsWindowsXYZ for CUDA/HIP compilations.  Even when compiling in
+  // device mode (i.e., getToolchain().getTriple() is NVPTX/AMDGCN, not
+  // Windows), we need to pass Windows-specific flags to cc1.
+  if (IsCuda || IsHIP) {
     IsWindowsMSVC |= AuxTriple && AuxTriple->isWindowsMSVCEnvironment();
     IsWindowsGNU |= AuxTriple && AuxTriple->isWindowsGNUEnvironment();
     IsWindowsCygnus |= AuxTriple && AuxTriple->isWindowsCygwinEnvironment();
   }
 
   // C++ is not supported for IAMCU.
   if (IsIAMCU && types::isCXX(Input.getType()))
     D.Diag(diag::err_drv_clang_unsupported) << "C++ for IAMCU";
 
   // Invoke ourselves in -cc1 mode.
   //
   // FIXME: Implement custom jobs for internal actions.
   CmdArgs.push_back("-cc1");
 
   // Add the "effective" target triple.
   CmdArgs.push_back("-triple");
   CmdArgs.push_back(Args.MakeArgString(TripleStr));
 
   if (const Arg *MJ = Args.getLastArg(options::OPT_MJ)) {
     DumpCompilationDatabase(C, MJ->getValue(), TripleStr, Output, Input, Args);
     Args.ClaimAllArgs(options::OPT_MJ);
   }
 
-  if (IsCuda) {
-    // We have to pass the triple of the host if compiling for a CUDA device and
-    // vice-versa.
+  if (IsCuda || IsHIP) {
+    // We have to pass the triple of the host if compiling for a CUDA/HIP device
+    // and vice-versa.
     std::string NormalizedTriple;
-    if (JA.isDeviceOffloading(Action::OFK_Cuda))
+    if (JA.isDeviceOffloading(Action::OFK_Cuda) ||
+        JA.isDeviceOffloading(Action::OFK_HIP))
       NormalizedTriple = C.getSingleOffloadToolChain<Action::OFK_Host>()
                              ->getTriple()
                              .normalize();
     else
-      NormalizedTriple = C.getSingleOffloadToolChain<Action::OFK_Cuda>()
-                             ->getTriple()
-                             .normalize();
+      NormalizedTriple =
+          (IsCuda ? C.getSingleOffloadToolChain<Action::OFK_Cuda>()
+                  : C.getSingleOffloadToolChain<Action::OFK_HIP>())
 
     CmdArgs.push_back("-aux-triple");
     CmdArgs.push_back(Args.MakeArgString(NormalizedTriple));
   }
 
   if (IsOpenMPDevice) {
     // We have to pass the triple of the host if compiling for an OpenMP device.
     std::string NormalizedTriple =