[OpenMP] Use the new OpenMP device static library when doing LTO

[jhuber6]

Summary

The previous patches allowed us to create a static library containing
all the device code. This patch uses that library to perform the device
runtime linking late when performing LTO. This in addition to
simplifying the libraries, allows us to transparently handle the runtime
library as-needed without needing Clang to manually pass the necessary
library in the linker wrapper job.

Depends on D125315

[jdoerfert]

LG, nice!

clang/lib/Driver/ToolChains/Clang.cpp

for (auto &I :
       TC->addClangTargetOptions(TCArgs, FeatureArgs, Action::OFK_OpenMP);
       auto FeatureIt = llvm::find(FeatureArgs, "-target-feature");
       if (FeatureIt != FeatureArgs.end())
         CmdArgs.push_back(
             Args.MakeArgString("-target-feature=" + TC->getTripleString() +
                                "=" + *(FeatureIt + 1)));
     }
 
-    // Pass in the bitcode library to be linked during LTO.
-    for (auto &I :
-         llvm::make_range(OpenMPTCRange.first, OpenMPTCRange.second)) {
-      const ToolChain *TC = I.second;
-      if (!(TC->getTriple().isNVPTX() || TC->getTriple().isAMDGPU()))
-        continue;
-
-      const Driver &TCDriver = TC->getDriver();
-      const ArgList &TCArgs = C.getArgsForToolChain(TC, "", Action::OFK_OpenMP);
-      StringRef Arch = TCArgs.getLastArgValue(options::OPT_march_EQ);
-
-      ArgStringList BitcodeLibrary;
-      addOpenMPDeviceRTL(TCDriver, TCArgs, BitcodeLibrary, Arch,
-                         TC->getTriple());
-
-      if (!BitcodeLibrary.empty())
-        CmdArgs.push_back(Args.MakeArgString(
-            "-target-library=" +
-            Action::GetOffloadKindName(Action::OFK_OpenMP) + "-" +
-            TC->getTripleString() + "-" + Arch + "=" + BitcodeLibrary.back()));
-    }
-
     // Pass in the optimization level to use for LTO.
     if (const Arg *A = Args.getLastArg(options::OPT_O_Group)) {
       StringRef OOpt;
       if (A->getOption().matches(options::OPT_O4) ||
           A->getOption().matches(options::OPT_Ofast))
         OOpt = "3";
       else if (A->getOption().matches(options::OPT_O)) {
         OOpt = A->getValue();

clang/lib/Driver/ToolChains/CommonArgs.cpp

if (ForceStaticHostRuntime)
     CmdArgs.push_back("-Bdynamic");
 
   if (RTKind == Driver::OMPRT_GOMP && GompNeedsRT)
       CmdArgs.push_back("-lrt");
 
   if (IsOffloadingHost)
     CmdArgs.push_back("-lomptarget");
 
+  if (IsOffloadingHost && TC.getDriver().isUsingLTO(/* IsOffload */ true))
+    CmdArgs.push_back("-lomptarget.devicertl");
+
   addArchSpecificRPath(TC, Args, CmdArgs);
 
   if (RTKind == Driver::OMPRT_OMP)
     addOpenMPRuntimeSpecificRPath(TC, Args, CmdArgs);
   addOpenMPRuntimeLibraryPath(TC, Args, CmdArgs);
 
   return true;
 }

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

 // RUN:     --offload-device-only -nogpulib %s 2>&1 | FileCheck %s --check-prefix=CHECK-DEVICE-ONLY
 // CHECK-DEVICE-ONLY: "x86_64-unknown-linux-gnu" - "clang", inputs: ["[[INPUT:.*]]"], output: "[[HOST_BC:.*]]"
 // CHECK-DEVICE-ONLY: "nvptx64-nvidia-cuda" - "clang", inputs: ["[[INPUT]]", "[[HOST_BC]]"], output: "[[DEVICE_ASM:.*]]"
 // CHECK-DEVICE-ONLY: "nvptx64-nvidia-cuda" - "NVPTX::Assembler", inputs: ["[[DEVICE_ASM]]"], output: "{{.*}}-openmp-nvptx64-nvidia-cuda.o"
 
 // RUN:   %clang -### --target=x86_64-unknown-linux-gnu -ccc-print-bindings -fopenmp -fopenmp-targets=nvptx64-nvidia-cuda \
 // RUN:     --offload-device-only -E -nogpulib %s 2>&1 | FileCheck %s --check-prefix=CHECK-DEVICE-ONLY-PP
 // CHECK-DEVICE-ONLY-PP: "nvptx64-nvidia-cuda" - "clang", inputs: ["[[INPUT:.*]]"], output: "-"
+
+// RUN:   %clang -### --target=x86_64-unknown-linux-gnu -fopenmp --offload-arch=sm_52 -nogpulib \
+// RUN:     -foffload-lto %s 2>&1 | FileCheck --check-prefix=CHECK-LTO-LIBRARY %s
+
+// CHECK-LTO-LIBRARY: {{.*}}-lomptarget{{.*}}-lomptarget.devicertl