[OpenMP] Extend CLANG target options with device offloading kind.

Summary: Pass the type of the device offloading when building the tool chain for a particular target architecture. This is required when supporting multiple tool chains that target a single device type. In our particular use case, the OpenMP and CUDA tool chains will use the same ```addClangTargetOptions ``` method. This enables the reuse of common options and ensures control over options only supported by a particular tool chain.

Reviewers: arpith-jacob, caomhin, carlo.bertolli, ABataev, jlebar, hfinkel, tstellar, Hahnfeld

Reviewed By: hfinkel

Subscribers: jgravelle-google, aheejin, rengolin, jfb, dschuff, sbc100, cfe-commits

Differential Revision: https://reviews.llvm.org/D29647

git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@307272 91177308-0d34-0410-b5e6-96231b3b80d8

include/clang/Driver/ToolChain.h

@@ -411,7 +411,8 @@ class ToolChain {
 
   /// \brief Add options that need to be passed to cc1 for this target.
   virtual void addClangTargetOptions(const llvm::opt::ArgList &DriverArgs,
-                                     llvm::opt::ArgStringList &CC1Args) const;
+                                     llvm::opt::ArgStringList &CC1Args,
+                                     Action::OffloadKind DeviceOffloadKind) const;
 
   /// \brief Add warning options that need to be passed to cc1 for this target.
   virtual void addClangWarningOptions(llvm::opt::ArgStringList &CC1Args) const;

lib/Driver/ToolChain.cpp

@@ -544,9 +544,9 @@ void ToolChain::AddClangSystemIncludeArgs(const ArgList &DriverArgs,
   // Each toolchain should provide the appropriate include flags.
 }
 
-void ToolChain::addClangTargetOptions(const ArgList &DriverArgs,
-                                      ArgStringList &CC1Args) const {
-}
+void ToolChain::addClangTargetOptions(
+    const ArgList &DriverArgs, ArgStringList &CC1Args,
+    Action::OffloadKind DeviceOffloadKind) const {}
 
 void ToolChain::addClangWarningOptions(ArgStringList &CC1Args) const {}
 

lib/Driver/ToolChains/BareMetal.cpp

@@ -98,7 +98,8 @@ void BareMetal::AddClangSystemIncludeArgs(const ArgList &DriverArgs,
 }
 
 void BareMetal::addClangTargetOptions(const ArgList &DriverArgs,
-                                      ArgStringList &CC1Args) const {
+                                      ArgStringList &CC1Args,
+                                      Action::OffloadKind) const {
   CC1Args.push_back("-nostdsysteminc");
 }
 

lib/Driver/ToolChains/BareMetal.h

@@ -54,7 +54,8 @@ class LLVM_LIBRARY_VISIBILITY BareMetal : public ToolChain {
   void AddClangSystemIncludeArgs(const llvm::opt::ArgList &DriverArgs,
                                  llvm::opt::ArgStringList &CC1Args) const override;
   void addClangTargetOptions(const llvm::opt::ArgList &DriverArgs,
-                             llvm::opt::ArgStringList &CC1Args) const override;
+                             llvm::opt::ArgStringList &CC1Args,
+                             Action::OffloadKind DeviceOffloadKind) const override;
   std::string findLibCxxIncludePath(ToolChain::CXXStdlibType LibType) const;
   void AddClangCXXStdlibIncludeArgs(
       const llvm::opt::ArgList &DriverArgs,

lib/Driver/ToolChains/Clang.cpp

@@ -2544,7 +2544,8 @@ void Clang::ConstructJob(Compilation &C, const JobAction &JA,
                    AsynchronousUnwindTables))
     CmdArgs.push_back("-munwind-tables");
 
-  getToolChain().addClangTargetOptions(Args, CmdArgs);
+  getToolChain().addClangTargetOptions(Args, CmdArgs,
+                                       JA.getOffloadingDeviceKind());
 
   if (Arg *A = Args.getLastArg(options::OPT_flimited_precision_EQ)) {
     CmdArgs.push_back("-mlimit-float-precision");

lib/Driver/ToolChains/Cuda.cpp

@@ -338,24 +338,31 @@ CudaToolChain::CudaToolChain(const Driver &D, const llvm::Triple &Triple,
 
 void CudaToolChain::addClangTargetOptions(
     const llvm::opt::ArgList &DriverArgs,
-    llvm::opt::ArgStringList &CC1Args) const {
-  HostTC.addClangTargetOptions(DriverArgs, CC1Args);
+    llvm::opt::ArgStringList &CC1Args,
+    Action::OffloadKind DeviceOffloadingKind) const {
+  HostTC.addClangTargetOptions(DriverArgs, CC1Args, DeviceOffloadingKind);
 
-  CC1Args.push_back("-fcuda-is-device");
+  StringRef GpuArch = DriverArgs.getLastArgValue(options::OPT_march_EQ);
+  assert(!GpuArch.empty() && "Must have an explicit GPU arch.");
+  assert((DeviceOffloadingKind == Action::OFK_OpenMP ||
+          DeviceOffloadingKind == Action::OFK_Cuda) &&
+         "Only OpenMP or CUDA offloading kinds are supported for NVIDIA GPUs.");
 
-  if (DriverArgs.hasFlag(options::OPT_fcuda_flush_denormals_to_zero,
-                         options::OPT_fno_cuda_flush_denormals_to_zero, false))
-    CC1Args.push_back("-fcuda-flush-denormals-to-zero");
+  if (DeviceOffloadingKind == Action::OFK_Cuda) {
+    CC1Args.push_back("-fcuda-is-device");
 
-  if (DriverArgs.hasFlag(options::OPT_fcuda_approx_transcendentals,
-                         options::OPT_fno_cuda_approx_transcendentals, false))
-    CC1Args.push_back("-fcuda-approx-transcendentals");
+    if (DriverArgs.hasFlag(options::OPT_fcuda_flush_denormals_to_zero,
+                           options::OPT_fno_cuda_flush_denormals_to_zero, false))
+      CC1Args.push_back("-fcuda-flush-denormals-to-zero");
 
-  if (DriverArgs.hasArg(options::OPT_nocudalib))
-    return;
+    if (DriverArgs.hasFlag(options::OPT_fcuda_approx_transcendentals,
+                           options::OPT_fno_cuda_approx_transcendentals, false))
+      CC1Args.push_back("-fcuda-approx-transcendentals");
+
+    if (DriverArgs.hasArg(options::OPT_nocudalib))
+      return;
+  }
 
-  StringRef GpuArch = DriverArgs.getLastArgValue(options::OPT_march_EQ);
-  assert(!GpuArch.empty() && "Must have an explicit GPU arch.");
   std::string LibDeviceFile = CudaInstallation.getLibDeviceFile(GpuArch);
 
   if (LibDeviceFile.empty()) {
@@ -396,6 +403,24 @@ CudaToolChain::TranslateArgs(const llvm::opt::DerivedArgList &Args,
 
   const OptTable &Opts = getDriver().getOpts();
 
+  // For OpenMP device offloading, append derived arguments. Make sure
+  // flags are not duplicated.
+  // TODO: Append the compute capability.
+  if (DeviceOffloadKind == Action::OFK_OpenMP) {
+    for (Arg *A : Args){
+      bool IsDuplicate = false;
+      for (Arg *DALArg : *DAL){
+        if (A == DALArg) {
+          IsDuplicate = true;
+          break;
+        }
+      }
+      if (!IsDuplicate)
+        DAL->append(A);
+    }
+    return DAL;
+  }
+
   for (Arg *A : Args) {
     if (A->getOption().matches(options::OPT_Xarch__)) {
       // Skip this argument unless the architecture matches BoundArch

lib/Driver/ToolChains/Cuda.h

@@ -130,7 +130,8 @@ class LLVM_LIBRARY_VISIBILITY CudaToolChain : public ToolChain {
   TranslateArgs(const llvm::opt::DerivedArgList &Args, StringRef BoundArch,
                 Action::OffloadKind DeviceOffloadKind) const override;
   void addClangTargetOptions(const llvm::opt::ArgList &DriverArgs,
-                             llvm::opt::ArgStringList &CC1Args) const override;
+                             llvm::opt::ArgStringList &CC1Args,
+                             Action::OffloadKind DeviceOffloadKind) const override;
 
   // Never try to use the integrated assembler with CUDA; always fork out to
   // ptxas.

lib/Driver/ToolChains/Darwin.cpp

@@ -1708,7 +1708,8 @@ bool Darwin::isAlignedAllocationUnavailable() const {
 }
 
 void Darwin::addClangTargetOptions(const llvm::opt::ArgList &DriverArgs,
-                                   llvm::opt::ArgStringList &CC1Args) const {
+                                   llvm::opt::ArgStringList &CC1Args,
+                                   Action::OffloadKind DeviceOffloadKind) const {
   if (isAlignedAllocationUnavailable())
     CC1Args.push_back("-faligned-alloc-unavailable");
 }

lib/Driver/ToolChains/Darwin.h

@@ -390,7 +390,8 @@ class LLVM_LIBRARY_VISIBILITY Darwin : public MachO {
   bool isAlignedAllocationUnavailable() const;
 
   void addClangTargetOptions(const llvm::opt::ArgList &DriverArgs,
-                             llvm::opt::ArgStringList &CC1Args) const override;
+                             llvm::opt::ArgStringList &CC1Args,
+                             Action::OffloadKind DeviceOffloadKind) const override;
 
   StringRef getPlatformFamily() const;
   static StringRef getSDKName(StringRef isysroot);

lib/Driver/ToolChains/Fuchsia.cpp

@@ -172,7 +172,8 @@ Fuchsia::GetCXXStdlibType(const ArgList &Args) const {
 }
 
 void Fuchsia::addClangTargetOptions(const ArgList &DriverArgs,
-                                    ArgStringList &CC1Args) const {
+                                    ArgStringList &CC1Args,
+                                    Action::OffloadKind) const {
   if (DriverArgs.hasFlag(options::OPT_fuse_init_array,
                          options::OPT_fno_use_init_array, true))
     CC1Args.push_back("-fuse-init-array");

lib/Driver/ToolChains/Fuchsia.h

@@ -55,7 +55,8 @@ class LLVM_LIBRARY_VISIBILITY Fuchsia : public Generic_ELF {
   GetCXXStdlibType(const llvm::opt::ArgList &Args) const override;
 
   void addClangTargetOptions(const llvm::opt::ArgList &DriverArgs,
-                             llvm::opt::ArgStringList &CC1Args) const override;
+                             llvm::opt::ArgStringList &CC1Args,
+                             Action::OffloadKind DeviceOffloadKind) const override;
   void
   AddClangSystemIncludeArgs(const llvm::opt::ArgList &DriverArgs,
                             llvm::opt::ArgStringList &CC1Args) const override;

lib/Driver/ToolChains/Gnu.cpp

@@ -2461,7 +2461,8 @@ Generic_GCC::TranslateArgs(const llvm::opt::DerivedArgList &Args, StringRef,
 void Generic_ELF::anchor() {}
 
 void Generic_ELF::addClangTargetOptions(const ArgList &DriverArgs,
-                                        ArgStringList &CC1Args) const {
+                                        ArgStringList &CC1Args,
+                                        Action::OffloadKind) const {
   const Generic_GCC::GCCVersion &V = GCCInstallation.getVersion();
   bool UseInitArrayDefault =
       getTriple().getArch() == llvm::Triple::aarch64 ||

lib/Driver/ToolChains/Gnu.h

@@ -341,7 +341,8 @@ class LLVM_LIBRARY_VISIBILITY Generic_ELF : public Generic_GCC {
       : Generic_GCC(D, Triple, Args) {}
 
   void addClangTargetOptions(const llvm::opt::ArgList &DriverArgs,
-                             llvm::opt::ArgStringList &CC1Args) const override;
+                             llvm::opt::ArgStringList &CC1Args,
+                             Action::OffloadKind DeviceOffloadKind) const override;
 };
 
 } // end namespace toolchains

lib/Driver/ToolChains/Hexagon.cpp

@@ -428,7 +428,8 @@ unsigned HexagonToolChain::getOptimizationLevel(
 }
 
 void HexagonToolChain::addClangTargetOptions(const ArgList &DriverArgs,
-                                             ArgStringList &CC1Args) const {
+                                             ArgStringList &CC1Args,
+                                             Action::OffloadKind) const {
   if (DriverArgs.hasArg(options::OPT_ffp_contract))
     return;
   unsigned OptLevel = getOptimizationLevel(DriverArgs);

lib/Driver/ToolChains/Hexagon.h

@@ -69,7 +69,8 @@ class LLVM_LIBRARY_VISIBILITY HexagonToolChain : public Linux {
   ~HexagonToolChain() override;
 
   void addClangTargetOptions(const llvm::opt::ArgList &DriverArgs,
-                             llvm::opt::ArgStringList &CC1Args) const override;
+                             llvm::opt::ArgStringList &CC1Args,
+                             Action::OffloadKind DeviceOffloadKind) const override;
   void
   AddClangSystemIncludeArgs(const llvm::opt::ArgList &DriverArgs,
                             llvm::opt::ArgStringList &CC1Args) const override;

lib/Driver/ToolChains/WebAssembly.cpp

@@ -134,7 +134,8 @@ bool WebAssembly::SupportsProfiling() const { return false; }
 bool WebAssembly::HasNativeLLVMSupport() const { return true; }
 
 void WebAssembly::addClangTargetOptions(const ArgList &DriverArgs,
-                                        ArgStringList &CC1Args) const {
+                                        ArgStringList &CC1Args,
+                                        Action::OffloadKind) const {
   if (DriverArgs.hasFlag(clang::driver::options::OPT_fuse_init_array,
                          options::OPT_fno_use_init_array, true))
     CC1Args.push_back("-fuse-init-array");

lib/Driver/ToolChains/WebAssembly.h

@@ -53,7 +53,8 @@ class LLVM_LIBRARY_VISIBILITY WebAssembly final : public ToolChain {
   bool SupportsProfiling() const override;
   bool HasNativeLLVMSupport() const override;
   void addClangTargetOptions(const llvm::opt::ArgList &DriverArgs,
-                             llvm::opt::ArgStringList &CC1Args) const override;
+                             llvm::opt::ArgStringList &CC1Args,
+                             Action::OffloadKind DeviceOffloadKind) const override;
   RuntimeLibType GetDefaultRuntimeLibType() const override;
   CXXStdlibType GetCXXStdlibType(const llvm::opt::ArgList &Args) const override;
   void AddClangSystemIncludeArgs(

lib/Driver/ToolChains/XCore.cpp

@@ -124,7 +124,8 @@ void XCoreToolChain::AddClangSystemIncludeArgs(const ArgList &DriverArgs,
 }
 
 void XCoreToolChain::addClangTargetOptions(const ArgList &DriverArgs,
-                                           ArgStringList &CC1Args) const {
+                                           ArgStringList &CC1Args,
+                                           Action::OffloadKind) const {
   CC1Args.push_back("-nostdsysteminc");
 }
 

lib/Driver/ToolChains/XCore.h

@@ -67,7 +67,8 @@ class LLVM_LIBRARY_VISIBILITY XCoreToolChain : public ToolChain {
   AddClangSystemIncludeArgs(const llvm::opt::ArgList &DriverArgs,
                             llvm::opt::ArgStringList &CC1Args) const override;
   void addClangTargetOptions(const llvm::opt::ArgList &DriverArgs,
-                             llvm::opt::ArgStringList &CC1Args) const override;
+                             llvm::opt::ArgStringList &CC1Args,
+                             Action::OffloadKind DeviceOffloadKind) const override;
   void AddClangCXXStdlibIncludeArgs(
       const llvm::opt::ArgList &DriverArgs,
       llvm::opt::ArgStringList &CC1Args) const override;