Merge from 'main' to 'sycl-web' (#132)

  CONFLICT (content): Merge conflict in clang/include/clang/Basic/DiagnosticDriverKinds.td

Author: dm-vodopyanov

clang/docs/ClangCommandLineReference.rst

@@ -1143,9 +1143,9 @@ Set directory to include search path with prefix
 
 Add directory to SYSTEM include search path, absolute paths are relative to -isysroot
 
-.. option:: --libomptarget-nvptx-path=<arg>
+.. option:: --libomptarget-nvptx-bc-path=<arg>
 
-Path to libomptarget-nvptx libraries
+Path to libomptarget-nvptx bitcode library
 
 .. option:: --ptxas-path=<arg>
 

clang/include/clang/Basic/DiagnosticDriverKinds.td

@@ -279,14 +279,14 @@ def err_drv_expecting_fsycl_with_sycl_opt : Error<
   "The option %0 must be used in conjunction with -fsycl to enable offloading.">;
 def err_drv_fsycl_with_c_type : Error<
   "The option '%0' must not be used in conjunction with '-fsycl', which expects C++ source.">;
-def warn_drv_omp_offload_target_duplicate : Warning<
-  "The OpenMP offloading target '%0' is similar to target '%1' already specified - will be ignored.">,
-  InGroup<OpenMPTarget>;
 def warn_drv_sycl_offload_target_duplicate : Warning<
   "The SYCL offloading target '%0' is similar to target '%1' already specified - will be ignored.">,
   InGroup<SyclTarget>;
-def warn_drv_omp_offload_target_missingbcruntime : Warning<
-  "No library '%0' found in the default clang lib directory or in LIBRARY_PATH. Expect degraded performance due to no inlining of runtime functions on target devices.">,
+def err_drv_omp_offload_target_missingbcruntime : Error<
+  "No library '%0' found in the default clang lib directory or in LIBRARY_PATH. Please use --libomptarget-nvptx-bc-path to specify nvptx bitcode library.">;
+def err_drv_omp_offload_target_bcruntime_not_found : Error<"Bitcode library '%0' does not exist.">;
+def warn_drv_omp_offload_target_duplicate : Warning<
+  "The OpenMP offloading target '%0' is similar to target '%1' already specified - will be ignored.">,
   InGroup<OpenMPTarget>;
 def err_drv_unsupported_embed_bitcode
     : Error<"%0 is not supported with -fembed-bitcode">;

clang/include/clang/Driver/Options.td

@@ -1012,8 +1012,8 @@ def gpu_max_threads_per_block_EQ : Joined<["--"], "gpu-max-threads-per-block=">,
 def gpu_instrument_lib_EQ : Joined<["--"], "gpu-instrument-lib=">,
   HelpText<"Instrument device library for HIP, which is a LLVM bitcode containing "
   "__cyg_profile_func_enter and __cyg_profile_func_exit">;
-def libomptarget_nvptx_path_EQ : Joined<["--"], "libomptarget-nvptx-path=">, Group<i_Group>,
-  HelpText<"Path to libomptarget-nvptx libraries">;
+def libomptarget_nvptx_bc_path_EQ : Joined<["--"], "libomptarget-nvptx-bc-path=">, Group<i_Group>,
+  HelpText<"Path to libomptarget-nvptx bitcode library">;
 def dD : Flag<["-"], "dD">, Group<d_Group>, Flags<[CC1Option]>,
   HelpText<"Print macro definitions in -E mode in addition to normal output">;
 def dI : Flag<["-"], "dI">, Group<d_Group>, Flags<[CC1Option]>,

clang/lib/CodeGen/CGExprConstant.cpp

@@ -58,14 +58,14 @@ struct ConstantAggregateBuilderUtils {
   }
 
   llvm::Constant *getPadding(CharUnits PadSize) const {
-    llvm::Type *Ty = CGM.Int8Ty;
+    llvm::Type *Ty = CGM.CharTy;
     if (PadSize > CharUnits::One())
       Ty = llvm::ArrayType::get(Ty, PadSize.getQuantity());
     return llvm::UndefValue::get(Ty);
   }
 
   llvm::Constant *getZeroes(CharUnits ZeroSize) const {
-    llvm::Type *Ty = llvm::ArrayType::get(CGM.Int8Ty, ZeroSize.getQuantity());
+    llvm::Type *Ty = llvm::ArrayType::get(CGM.CharTy, ZeroSize.getQuantity());
     return llvm::ConstantAggregateZero::get(Ty);
   }
 };
@@ -1069,7 +1069,7 @@ class ConstExprEmitter :
 
       assert(CurSize <= TotalSize && "Union size mismatch!");
       if (unsigned NumPadBytes = TotalSize - CurSize) {
-        llvm::Type *Ty = CGM.Int8Ty;
+        llvm::Type *Ty = CGM.CharTy;
         if (NumPadBytes > 1)
           Ty = llvm::ArrayType::get(Ty, NumPadBytes);
 

clang/lib/CodeGen/CGRecordLayoutBuilder.cpp

@@ -127,15 +127,20 @@ struct CGRecordLowering {
 
   /// Wraps llvm::Type::getIntNTy with some implicit arguments.
   llvm::Type *getIntNType(uint64_t NumBits) {
+    unsigned AlignedBits = llvm::alignTo(NumBits, Context.getCharWidth());
+    return llvm::Type::getIntNTy(Types.getLLVMContext(), AlignedBits);
+  }
+  /// Get the LLVM type sized as one character unit.
+  llvm::Type *getCharType() {
     return llvm::Type::getIntNTy(Types.getLLVMContext(),
-                                 (unsigned)llvm::alignTo(NumBits, 8));
+                                 Context.getCharWidth());
   }
-  /// Gets an llvm type of size NumBytes and alignment 1.
-  llvm::Type *getByteArrayType(CharUnits NumBytes) {
-    assert(!NumBytes.isZero() && "Empty byte arrays aren't allowed.");
-    llvm::Type *Type = llvm::Type::getInt8Ty(Types.getLLVMContext());
-    return NumBytes == CharUnits::One() ? Type :
-        (llvm::Type *)llvm::ArrayType::get(Type, NumBytes.getQuantity());
+  /// Gets an llvm type of size NumChars and alignment 1.
+  llvm::Type *getByteArrayType(CharUnits NumChars) {
+    assert(!NumChars.isZero() && "Empty byte arrays aren't allowed.");
+    llvm::Type *Type = getCharType();
+    return NumChars == CharUnits::One() ? Type :
+        (llvm::Type *)llvm::ArrayType::get(Type, NumChars.getQuantity());
   }
   /// Gets the storage type for a field decl and handles storage
   /// for itanium bitfields that are smaller than their declared type.

clang/lib/CodeGen/CodeGenModule.cpp

@@ -124,6 +124,8 @@ CodeGenModule::CodeGenModule(ASTContext &C, const HeaderSearchOptions &HSO,
     C.toCharUnitsFromBits(C.getTargetInfo().getMaxPointerWidth()).getQuantity();
   IntAlignInBytes =
     C.toCharUnitsFromBits(C.getTargetInfo().getIntAlign()).getQuantity();
+  CharTy =
+    llvm::IntegerType::get(LLVMContext, C.getTargetInfo().getCharWidth());
   IntTy = llvm::IntegerType::get(LLVMContext, C.getTargetInfo().getIntWidth());
   IntPtrTy = llvm::IntegerType::get(LLVMContext,
     C.getTargetInfo().getMaxPointerWidth());

clang/lib/CodeGen/CodeGenTypeCache.h

@@ -41,6 +41,9 @@ struct CodeGenTypeCache {
   /// int
   llvm::IntegerType *IntTy;
 
+  /// char
+  llvm::IntegerType *CharTy;
+
   /// intptr_t, size_t, and ptrdiff_t, which we assume are the same size.
   union {
     llvm::IntegerType *IntPtrTy;

clang/lib/CodeGen/TargetInfo.cpp

@@ -4709,13 +4709,12 @@ Address PPC32_SVR4_ABIInfo::EmitVAArg(CodeGenFunction &CGF, Address VAList,
   // };
 
   bool isI64 = Ty->isIntegerType() && getContext().getTypeSize(Ty) == 64;
-  bool isInt =
-      Ty->isIntegerType() || Ty->isPointerType() || Ty->isAggregateType();
+  bool isInt = !Ty->isFloatingType();
   bool isF64 = Ty->isFloatingType() && getContext().getTypeSize(Ty) == 64;
 
   // All aggregates are passed indirectly?  That doesn't seem consistent
   // with the argument-lowering code.
-  bool isIndirect = Ty->isAggregateType();
+  bool isIndirect = isAggregateTypeForABI(Ty);
 
   CGBuilderTy &Builder = CGF.Builder;
 

clang/lib/Driver/ToolChains/Arch/RISCV.cpp

@@ -58,10 +58,10 @@ static StringRef getExtensionType(StringRef Ext) {
 // extension that the compiler currently supports.
 static Optional<RISCVExtensionVersion>
 isExperimentalExtension(StringRef Ext) {
-  if (Ext == "b" || Ext == "zbb" || Ext == "zbc" || Ext == "zbe" ||
-      Ext == "zbf" || Ext == "zbm" || Ext == "zbp" || Ext == "zbr" ||
-      Ext == "zbs" || Ext == "zbt" || Ext == "zbproposedc")
-    return RISCVExtensionVersion{"0", "92"};
+  if (Ext == "b" || Ext == "zba" || Ext == "zbb" || Ext == "zbc" ||
+      Ext == "zbe" || Ext == "zbf" || Ext == "zbm" || Ext == "zbp" ||
+      Ext == "zbr" || Ext == "zbs" || Ext == "zbt" || Ext == "zbproposedc")
+    return RISCVExtensionVersion{"0", "93"};
   if (Ext == "v")
     return RISCVExtensionVersion{"0", "9"};
   if (Ext == "zfh")

clang/lib/Driver/ToolChains/Cuda.cpp

@@ -600,11 +600,6 @@ void NVPTX::OpenMPLinker::ConstructJob(Compilation &C, const JobAction &JA,
   CmdArgs.push_back("-arch");
   CmdArgs.push_back(Args.MakeArgString(GPUArch));
 
-  // Assume that the directory specified with --libomptarget_nvptx_path
-  // contains the static library libomptarget-nvptx.a.
-  if (const Arg *A = Args.getLastArg(options::OPT_libomptarget_nvptx_path_EQ))
-    CmdArgs.push_back(Args.MakeArgString(Twine("-L") + A->getValue()));
-
   // Add paths specified in LIBRARY_PATH environment variable as -L options.
   addDirectoryList(Args, CmdArgs, "-L", "LIBRARY_PATH");
 
@@ -614,9 +609,6 @@ void NVPTX::OpenMPLinker::ConstructJob(Compilation &C, const JobAction &JA,
   llvm::sys::path::append(DefaultLibPath, "lib" CLANG_LIBDIR_SUFFIX);
   CmdArgs.push_back(Args.MakeArgString(Twine("-L") + DefaultLibPath));
 
-  // Add linking against library implementing OpenMP calls on NVPTX target.
-  CmdArgs.push_back("-lomptarget-nvptx");
-
   for (const auto &II : Inputs) {
     if (II.getType() == types::TY_LLVM_IR ||
         II.getType() == types::TY_LTO_IR ||
@@ -810,9 +802,6 @@ void CudaToolChain::addClangTargetOptions(
 
   if (DeviceOffloadingKind == Action::OFK_OpenMP) {
     SmallVector<StringRef, 8> LibraryPaths;
-    if (const Arg *A = DriverArgs.getLastArg(options::OPT_libomptarget_nvptx_path_EQ))
-      LibraryPaths.push_back(A->getValue());
-
     // Add user defined library paths from LIBRARY_PATH.
     llvm::Optional<std::string> LibPath =
         llvm::sys::Process::GetEnv("LIBRARY_PATH");
@@ -830,22 +819,37 @@ void CudaToolChain::addClangTargetOptions(
     llvm::sys::path::append(DefaultLibPath, Twine("lib") + CLANG_LIBDIR_SUFFIX);
     LibraryPaths.emplace_back(DefaultLibPath.c_str());
 
-    std::string LibOmpTargetName =
-      "libomptarget-nvptx-" + GpuArch.str() + ".bc";
-    bool FoundBCLibrary = false;
-    for (StringRef LibraryPath : LibraryPaths) {
-      SmallString<128> LibOmpTargetFile(LibraryPath);
-      llvm::sys::path::append(LibOmpTargetFile, LibOmpTargetName);
-      if (llvm::sys::fs::exists(LibOmpTargetFile)) {
+    // First check whether user specifies bc library
+    if (const Arg *A =
+            DriverArgs.getLastArg(options::OPT_libomptarget_nvptx_bc_path_EQ)) {
+      std::string LibOmpTargetName(A->getValue());
+      if (llvm::sys::fs::exists(LibOmpTargetName)) {
         CC1Args.push_back("-mlink-builtin-bitcode");
-        CC1Args.push_back(DriverArgs.MakeArgString(LibOmpTargetFile));
-        FoundBCLibrary = true;
-        break;
+        CC1Args.push_back(DriverArgs.MakeArgString(LibOmpTargetName));
+      } else {
+        getDriver().Diag(diag::err_drv_omp_offload_target_bcruntime_not_found)
+            << LibOmpTargetName;
+      }
+    } else {
+      bool FoundBCLibrary = false;
+
+      std::string LibOmpTargetName =
+          "libomptarget-nvptx-" + GpuArch.str() + ".bc";
+
+      for (StringRef LibraryPath : LibraryPaths) {
+        SmallString<128> LibOmpTargetFile(LibraryPath);
+        llvm::sys::path::append(LibOmpTargetFile, LibOmpTargetName);
+        if (llvm::sys::fs::exists(LibOmpTargetFile)) {
+          CC1Args.push_back("-mlink-builtin-bitcode");
+          CC1Args.push_back(DriverArgs.MakeArgString(LibOmpTargetFile));
+          FoundBCLibrary = true;
+          break;
+        }
       }
+      if (!FoundBCLibrary)
+        getDriver().Diag(diag::err_drv_omp_offload_target_missingbcruntime)
+            << LibOmpTargetName;
     }
-    if (!FoundBCLibrary)
-      getDriver().Diag(diag::warn_drv_omp_offload_target_missingbcruntime)
-          << LibOmpTargetName;
   }
 }