Merge llvm-project release/13.x llvmorg-13.0.0-rc2-43-gf56129fe78d5

This updates llvm, clang, compiler-rt, libc++, libunwind, lld, lldb and
openmp to llvmorg-13.0.0-rc2-43-gf56129fe78d5.

PR:		258209

(cherry picked from commit 69ade1e)

contrib/llvm-project/clang/lib/AST/ASTContext.cpp

@@ -9653,11 +9653,19 @@ static QualType mergeEnumWithInteger(ASTContext &Context, const EnumType *ET,
 QualType ASTContext::mergeTypes(QualType LHS, QualType RHS,
                                 bool OfBlockPointer,
                                 bool Unqualified, bool BlockReturnType) {
+  // For C++ we will not reach this code with reference types (see below),
+  // for OpenMP variant call overloading we might.
+  //
   // C++ [expr]: If an expression initially has the type "reference to T", the
   // type is adjusted to "T" prior to any further analysis, the expression
   // designates the object or function denoted by the reference, and the
   // expression is an lvalue unless the reference is an rvalue reference and
   // the expression is a function call (possibly inside parentheses).
+  if (LangOpts.OpenMP && LHS->getAs<ReferenceType>() &&
+      RHS->getAs<ReferenceType>() && LHS->getTypeClass() == RHS->getTypeClass())
+    return mergeTypes(LHS->getAs<ReferenceType>()->getPointeeType(),
+                      RHS->getAs<ReferenceType>()->getPointeeType(),
+                      OfBlockPointer, Unqualified, BlockReturnType);
   if (LHS->getAs<ReferenceType>() || RHS->getAs<ReferenceType>())
     return {};
 

contrib/llvm-project/clang/lib/Basic/Targets/M68k.cpp

@@ -37,8 +37,8 @@ M68kTargetInfo::M68kTargetInfo(const llvm::Triple &Triple,
   // FIXME how to wire it with the used object format?
   Layout += "-m:e";
 
-  // M68k pointers are always 32 bit wide even for 16 bit cpus
-  Layout += "-p:32:32";
+  // M68k pointers are always 32 bit wide even for 16-bit CPUs
+  Layout += "-p:32:16:32";
 
   // M68k integer data types
   Layout += "-i8:8:8-i16:16:16-i32:16:32";

contrib/llvm-project/clang/lib/Basic/Targets/OSTargets.h

@@ -460,6 +460,11 @@ class LLVM_LIBRARY_VISIBILITY OpenBSDTargetInfo : public OSTargetInfo<Target> {
       Builder.defineMacro("_REENTRANT");
     if (this->HasFloat128)
       Builder.defineMacro("__FLOAT128__");
+
+    if (Opts.C11) {
+      Builder.defineMacro("__STDC_NO_ATOMICS__");
+      Builder.defineMacro("__STDC_NO_THREADS__");
+    }
   }
 
 public:

contrib/llvm-project/clang/lib/Driver/Driver.cpp

@@ -5568,7 +5568,6 @@ llvm::StringRef clang::driver::getDriverMode(StringRef ProgName,
     if (!Arg.startswith(OptName))
       continue;
     Opt = Arg;
-    break;
   }
   if (Opt.empty())
     Opt = ToolChain::getTargetAndModeFromProgramName(ProgName).DriverMode;

contrib/llvm-project/clang/lib/Driver/ToolChains/AMDGPU.cpp

@@ -893,3 +893,38 @@ bool AMDGPUToolChain::shouldSkipArgument(const llvm::opt::Arg *A) const {
     return true;
   return false;
 }
+
+llvm::SmallVector<std::string, 12>
+ROCMToolChain::getCommonDeviceLibNames(const llvm::opt::ArgList &DriverArgs,
+                                       const std::string &GPUArch) const {
+  auto Kind = llvm::AMDGPU::parseArchAMDGCN(GPUArch);
+  const StringRef CanonArch = llvm::AMDGPU::getArchNameAMDGCN(Kind);
+
+  std::string LibDeviceFile = RocmInstallation.getLibDeviceFile(CanonArch);
+  if (LibDeviceFile.empty()) {
+    getDriver().Diag(diag::err_drv_no_rocm_device_lib) << 1 << GPUArch;
+    return {};
+  }
+
+  // If --hip-device-lib is not set, add the default bitcode libraries.
+  // TODO: There are way too many flags that change this. Do we need to check
+  // them all?
+  bool DAZ = DriverArgs.hasFlag(options::OPT_fgpu_flush_denormals_to_zero,
+                                options::OPT_fno_gpu_flush_denormals_to_zero,
+                                getDefaultDenormsAreZeroForTarget(Kind));
+  bool FiniteOnly = DriverArgs.hasFlag(
+      options::OPT_ffinite_math_only, options::OPT_fno_finite_math_only, false);
+  bool UnsafeMathOpt =
+      DriverArgs.hasFlag(options::OPT_funsafe_math_optimizations,
+                         options::OPT_fno_unsafe_math_optimizations, false);
+  bool FastRelaxedMath = DriverArgs.hasFlag(options::OPT_ffast_math,
+                                            options::OPT_fno_fast_math, false);
+  bool CorrectSqrt = DriverArgs.hasFlag(
+      options::OPT_fhip_fp32_correctly_rounded_divide_sqrt,
+      options::OPT_fno_hip_fp32_correctly_rounded_divide_sqrt);
+  bool Wave64 = isWave64(DriverArgs, Kind);
+
+  return RocmInstallation.getCommonBitcodeLibs(
+      DriverArgs, LibDeviceFile, Wave64, DAZ, FiniteOnly, UnsafeMathOpt,
+      FastRelaxedMath, CorrectSqrt);
+}

contrib/llvm-project/clang/lib/Driver/ToolChains/AMDGPU.h

@@ -136,6 +136,11 @@ class LLVM_LIBRARY_VISIBILITY ROCMToolChain : public AMDGPUToolChain {
   addClangTargetOptions(const llvm::opt::ArgList &DriverArgs,
                         llvm::opt::ArgStringList &CC1Args,
                         Action::OffloadKind DeviceOffloadKind) const override;
+
+  // Returns a list of device library names shared by different languages
+  llvm::SmallVector<std::string, 12>
+  getCommonDeviceLibNames(const llvm::opt::ArgList &DriverArgs,
+                          const std::string &GPUArch) const;
 };
 
 } // end namespace toolchains

contrib/llvm-project/clang/lib/Driver/ToolChains/AMDGPUOpenMP.cpp

@@ -9,12 +9,14 @@
 #include "AMDGPUOpenMP.h"
 #include "AMDGPU.h"
 #include "CommonArgs.h"
+#include "ToolChains/ROCm.h"
 #include "clang/Basic/DiagnosticDriver.h"
 #include "clang/Driver/Compilation.h"
 #include "clang/Driver/Driver.h"
 #include "clang/Driver/DriverDiagnostic.h"
 #include "clang/Driver/InputInfo.h"
 #include "clang/Driver/Options.h"
+#include "llvm/ADT/STLExtras.h"
 #include "llvm/Support/FileSystem.h"
 #include "llvm/Support/FormatAdapters.h"
 #include "llvm/Support/FormatVariadic.h"
@@ -84,14 +86,34 @@ static bool checkSystemForAMDGPU(const ArgList &Args, const AMDGPUToolChain &TC,
 } // namespace
 
 const char *AMDGCN::OpenMPLinker::constructLLVMLinkCommand(
-    Compilation &C, const JobAction &JA, const InputInfoList &Inputs,
-    const ArgList &Args, StringRef SubArchName,
-    StringRef OutputFilePrefix) const {
+    const toolchains::AMDGPUOpenMPToolChain &AMDGPUOpenMPTC, Compilation &C,
+    const JobAction &JA, const InputInfoList &Inputs, const ArgList &Args,
+    StringRef SubArchName, StringRef OutputFilePrefix) const {
   ArgStringList CmdArgs;
 
   for (const auto &II : Inputs)
     if (II.isFilename())
       CmdArgs.push_back(II.getFilename());
+
+  if (Args.hasArg(options::OPT_l)) {
+    auto Lm = Args.getAllArgValues(options::OPT_l);
+    bool HasLibm = false;
+    for (auto &Lib : Lm) {
+      if (Lib == "m") {
+        HasLibm = true;
+        break;
+      }
+    }
+
+    if (HasLibm) {
+      SmallVector<std::string, 12> BCLibs =
+          AMDGPUOpenMPTC.getCommonDeviceLibNames(Args, SubArchName.str());
+      llvm::for_each(BCLibs, [&](StringRef BCFile) {
+        CmdArgs.push_back(Args.MakeArgString(BCFile));
+      });
+    }
+  }
+
   // Add an intermediate output file.
   CmdArgs.push_back("-o");
   const char *OutputFileName =
@@ -180,8 +202,8 @@ void AMDGCN::OpenMPLinker::ConstructJob(Compilation &C, const JobAction &JA,
   assert(Prefix.length() && "no linker inputs are files ");
 
   // Each command outputs different files.
-  const char *LLVMLinkCommand =
-      constructLLVMLinkCommand(C, JA, Inputs, Args, GPUArch, Prefix);
+  const char *LLVMLinkCommand = constructLLVMLinkCommand(
+      AMDGPUOpenMPTC, C, JA, Inputs, Args, GPUArch, Prefix);
 
   // Produce readable assembly if save-temps is enabled.
   if (C.getDriver().isSaveTempsEnabled())

contrib/llvm-project/clang/lib/Driver/ToolChains/AMDGPUOpenMP.h

@@ -16,6 +16,10 @@
 namespace clang {
 namespace driver {
 
+namespace toolchains {
+class AMDGPUOpenMPToolChain;
+}
+
 namespace tools {
 
 namespace AMDGCN {
@@ -35,11 +39,11 @@ class LLVM_LIBRARY_VISIBILITY OpenMPLinker : public Tool {
 
 private:
   /// \return llvm-link output file name.
-  const char *constructLLVMLinkCommand(Compilation &C, const JobAction &JA,
-                                       const InputInfoList &Inputs,
-                                       const llvm::opt::ArgList &Args,
-                                       llvm::StringRef SubArchName,
-                                       llvm::StringRef OutputFilePrefix) const;
+  const char *constructLLVMLinkCommand(
+      const toolchains::AMDGPUOpenMPToolChain &AMDGPUOpenMPTC, Compilation &C,
+      const JobAction &JA, const InputInfoList &Inputs,
+      const llvm::opt::ArgList &Args, llvm::StringRef SubArchName,
+      llvm::StringRef OutputFilePrefix) const;
 
   /// \return llc output file name.
   const char *constructLlcCommand(Compilation &C, const JobAction &JA,

contrib/llvm-project/clang/lib/Driver/ToolChains/Clang.cpp

@@ -1255,7 +1255,8 @@ void Clang::AddPreprocessingOptions(Compilation &C, const JobAction &JA,
   // If we are offloading to a target via OpenMP we need to include the
   // openmp_wrappers folder which contains alternative system headers.
   if (JA.isDeviceOffloading(Action::OFK_OpenMP) &&
-      getToolChain().getTriple().isNVPTX()){
+      (getToolChain().getTriple().isNVPTX() ||
+       getToolChain().getTriple().isAMDGCN())) {
     if (!Args.hasArg(options::OPT_nobuiltininc)) {
       // Add openmp_wrappers/* to our system include path.  This lets us wrap
       // standard library headers.

contrib/llvm-project/clang/lib/Driver/ToolChains/CommonArgs.cpp

@@ -775,7 +775,8 @@ void tools::linkSanitizerRuntimeDeps(const ToolChain &TC,
     CmdArgs.push_back("-ldl");
   // Required for backtrace on some OSes
   if (TC.getTriple().isOSFreeBSD() ||
-      TC.getTriple().isOSNetBSD())
+      TC.getTriple().isOSNetBSD() ||
+      TC.getTriple().isOSOpenBSD())
     CmdArgs.push_back("-lexecinfo");
 }
 

contrib/llvm-project/clang/lib/Driver/ToolChains/HIP.cpp

@@ -395,35 +395,8 @@ HIPToolChain::getHIPDeviceLibs(const llvm::opt::ArgList &DriverArgs) const {
     }
     StringRef GpuArch = getGPUArch(DriverArgs);
     assert(!GpuArch.empty() && "Must have an explicit GPU arch.");
-    (void)GpuArch;
-    auto Kind = llvm::AMDGPU::parseArchAMDGCN(GpuArch);
-    const StringRef CanonArch = llvm::AMDGPU::getArchNameAMDGCN(Kind);
-
-    std::string LibDeviceFile = RocmInstallation.getLibDeviceFile(CanonArch);
-    if (LibDeviceFile.empty()) {
-      getDriver().Diag(diag::err_drv_no_rocm_device_lib) << 1 << GpuArch;
-      return {};
-    }
 
     // If --hip-device-lib is not set, add the default bitcode libraries.
-    // TODO: There are way too many flags that change this. Do we need to check
-    // them all?
-    bool DAZ = DriverArgs.hasFlag(options::OPT_fgpu_flush_denormals_to_zero,
-                                  options::OPT_fno_gpu_flush_denormals_to_zero,
-                                  getDefaultDenormsAreZeroForTarget(Kind));
-    bool FiniteOnly =
-        DriverArgs.hasFlag(options::OPT_ffinite_math_only,
-                           options::OPT_fno_finite_math_only, false);
-    bool UnsafeMathOpt =
-        DriverArgs.hasFlag(options::OPT_funsafe_math_optimizations,
-                           options::OPT_fno_unsafe_math_optimizations, false);
-    bool FastRelaxedMath = DriverArgs.hasFlag(
-        options::OPT_ffast_math, options::OPT_fno_fast_math, false);
-    bool CorrectSqrt = DriverArgs.hasFlag(
-        options::OPT_fhip_fp32_correctly_rounded_divide_sqrt,
-        options::OPT_fno_hip_fp32_correctly_rounded_divide_sqrt);
-    bool Wave64 = isWave64(DriverArgs, Kind);
-
     if (DriverArgs.hasFlag(options::OPT_fgpu_sanitize,
                            options::OPT_fno_gpu_sanitize, false)) {
       auto AsanRTL = RocmInstallation.getAsanRTLPath();
@@ -442,10 +415,8 @@ HIPToolChain::getHIPDeviceLibs(const llvm::opt::ArgList &DriverArgs) const {
     // Add the HIP specific bitcode library.
     BCLibs.push_back(RocmInstallation.getHIPPath().str());
 
-    // Add the generic set of libraries.
-    BCLibs.append(RocmInstallation.getCommonBitcodeLibs(
-        DriverArgs, LibDeviceFile, Wave64, DAZ, FiniteOnly, UnsafeMathOpt,
-        FastRelaxedMath, CorrectSqrt));
+    // Add common device libraries like ocml etc.
+    BCLibs.append(getCommonDeviceLibNames(DriverArgs, GpuArch.str()));
 
     // Add instrument lib.
     auto InstLib =

contrib/llvm-project/clang/lib/Driver/ToolChains/OpenBSD.cpp

@@ -174,6 +174,11 @@ void openbsd::Linker::ConstructJob(Compilation &C, const JobAction &JA,
   AddLinkerInputs(ToolChain, Inputs, Args, CmdArgs, JA);
 
   if (!Args.hasArg(options::OPT_nostdlib, options::OPT_nodefaultlibs)) {
+    // Use the static OpenMP runtime with -static-openmp
+    bool StaticOpenMP = Args.hasArg(options::OPT_static_openmp) &&
+                        !Args.hasArg(options::OPT_static);
+    addOpenMPRuntime(CmdArgs, ToolChain, Args, StaticOpenMP);
+
     if (D.CCCIsCXX()) {
       if (ToolChain.ShouldLinkCXXStdlib(Args))
         ToolChain.AddCXXStdlibLibArgs(Args, CmdArgs);
@@ -221,6 +226,8 @@ void openbsd::Linker::ConstructJob(Compilation &C, const JobAction &JA,
     CmdArgs.push_back(Args.MakeArgString(ToolChain.GetFilePath(crtend)));
   }
 
+  ToolChain.addProfileRTLibs(Args, CmdArgs);
+
   const char *Exec = Args.MakeArgString(ToolChain.GetLinkerPath());
   C.addCommand(std::make_unique<Command>(JA, *this,
                                          ResponseFileSupport::AtFileCurCP(),