[OpenMP] Accept shortened triples for -Xopenmp-target=

[jhuber6]

Summary

This patch builds on the change in D117634 that expanded the short
triples when passed in by the user. This patch adds the same
functionality for the -Xopenmp-target= flag. Previously it was
unintuitive that passing `-fopenmp-targets=nvptx64
-Xopenmp-target=nvptx64 <arg>` would not forward the arg because the
triples did not match on account of nvptx64 being expanded to
nvptx64-nvidia-cuda.

[JonChesterfield]

Do we have this same expansion logic in two places now? If so, probably want to factor it out to a function

[jdoerfert]

and test pls

[jhuber6]

Adding test and shared function.

[jdoerfert]

LG

clang/include/clang/Driver/ToolChain.h

public:
   /// Returns the output denormal handling type in the default floating point
   /// environment for the given \p FPType if given. Otherwise, the default
   /// assumed mode for any floating point type.
   virtual llvm::DenormalMode getDefaultDenormalModeForType(
       const llvm::opt::ArgList &DriverArgs, const JobAction &JA,
       const llvm::fltSemantics *FPType = nullptr) const {
     return llvm::DenormalMode::getIEEE();
   }
+
+  // We want to expand the shortened versions of the triples passed in to
+  // the values used for the bitcode libraries.
+  static llvm::Triple getOpenMPTriple(StringRef TripleStr) {
+    llvm::Triple TT(TripleStr);
+    if (TT.getVendor() == llvm::Triple::UnknownVendor ||
+        TT.getOS() == llvm::Triple::UnknownOS) {
+      if (TT.getArch() == llvm::Triple::nvptx)
+        return llvm::Triple("nvptx-nvidia-cuda");
+      if (TT.getArch() == llvm::Triple::nvptx64)
+        return llvm::Triple("nvptx64-nvidia-cuda");
+      if (TT.getArch() == llvm::Triple::amdgcn)
+        return llvm::Triple("amdgcn-amd-amdhsa");
+    }
+    return TT;
+  }
 };
 
 /// Set a ToolChain's effective triple. Reset it when the registration object
 /// is destroyed.
 class RegisterEffectiveTriple {
   const ToolChain &TC;
 
 public:

clang/lib/Driver/Driver.cpp

if (OpenMPTargets->getNumValues()) {
         OpenMPRuntimeKind OpenMPKind = getOpenMPRuntime(C.getInputArgs());
         HasValidOpenMPRuntime =
             OpenMPKind == OMPRT_OMP || OpenMPKind == OMPRT_IOMP5;
       }
 
       if (HasValidOpenMPRuntime) {
         llvm::StringMap<const char *> FoundNormalizedTriples;
         for (const char *Val : OpenMPTargets->getValues()) {
-          llvm::Triple TT(Val);
+          llvm::Triple TT(ToolChain::getOpenMPTriple(Val));
           std::string NormalizedName = TT.normalize();
 
-          // We want to expand the shortened versions of the triples passed in to
-          // the values used for the bitcode libraries for convenience.
-          if (TT.getVendor() == llvm::Triple::UnknownVendor ||
-              TT.getOS() == llvm::Triple::UnknownOS) {
-            if (TT.getArch() == llvm::Triple::nvptx)
-              TT = llvm::Triple("nvptx-nvidia-cuda");
-            else if (TT.getArch() == llvm::Triple::nvptx64)
-              TT = llvm::Triple("nvptx64-nvidia-cuda");
-            else if (TT.getArch() == llvm::Triple::amdgcn)
-              TT = llvm::Triple("amdgcn-amd-amdhsa");
-          }
-
           // Make sure we don't have a duplicate triple.
           auto Duplicate = FoundNormalizedTriples.find(NormalizedName);
           if (Duplicate != FoundNormalizedTriples.end()) {
             Diag(clang::diag::warn_drv_omp_offload_target_duplicate)
                 << Val << Duplicate->second;
             continue;
           }
 

clang/lib/Driver/ToolChain.cpp

for (auto *A : Args) {
     }
 
     unsigned Index;
     unsigned Prev;
     bool XOpenMPTargetNoTriple =
         A->getOption().matches(options::OPT_Xopenmp_target);
 
     if (A->getOption().matches(options::OPT_Xopenmp_target_EQ)) {
+      llvm::Triple TT(getOpenMPTriple(A->getValue(0)));
+
       // Passing device args: -Xopenmp-target=<triple> -opt=val.
-      if (A->getValue(0) == getTripleString())
+      if (TT.getTriple() == getTripleString())
         Index = Args.getBaseArgs().MakeIndex(A->getValue(1));
       else
         continue;
     } else if (XOpenMPTargetNoTriple) {
       // Passing device args: -Xopenmp-target -opt=val.
       Index = Args.getBaseArgs().MakeIndex(A->getValue(0));
     } else {
       DAL->append(A);

clang/test/Driver/openmp-offload-gpu.c

 // OPENMP_NVPTX_WRAPPERS: clang{{.*}}"-cc1"{{.*}}"-triple" "nvptx64-nvidia-cuda"
 // OPENMP_NVPTX_WRAPPERS-SAME: "-internal-isystem" "{{.*}}openmp_wrappers"
 
 // RUN:   %clang -### -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda \
 // RUN:          -save-temps -no-canonical-prefixes -ccc-print-bindings %s -o openmp-offload-gpu 2>&1 \
 // RUN:   | FileCheck -check-prefix=SAVE_TEMPS_NAMES %s
 
 // SAVE_TEMPS_NAMES-NOT: "GNU::Linker"{{.*}}["[[SAVE_TEMPS_INPUT1:.*\.o]]", "[[SAVE_TEMPS_INPUT1]]"]
+
+// RUN:   %clang -### -fopenmp=libomp -fopenmp-targets=nvptx64 -Xopenmp-target=nvptx64 -march=sm_35 \
+// RUN:          -save-temps -no-canonical-prefixes %s -o openmp-offload-gpu 2>&1 \
+// RUN:   | FileCheck -check-prefix=TRIPLE %s
+
+// TRIPLE: "-triple" "nvptx64-nvidia-cuda"
+// TRIPLE: "-target-cpu" "sm_35"