diff options
Diffstat (limited to 'contrib/llvm-project/clang')
22 files changed, 349 insertions, 407 deletions
diff --git a/contrib/llvm-project/clang/include/clang/Basic/Builtins.def b/contrib/llvm-project/clang/include/clang/Basic/Builtins.def index d2cb14d2fd8c..a17d2e59f5d8 100644 --- a/contrib/llvm-project/clang/include/clang/Basic/Builtins.def +++ b/contrib/llvm-project/clang/include/clang/Basic/Builtins.def @@ -1625,50 +1625,50 @@ LANGBUILTIN(__builtin_coro_suspend, "cIb", "n", COR_LANG) // OpenCL v2.0 s6.13.16, s9.17.3.5 - Pipe functions. // We need the generic prototype, since the packet type could be anything. -LANGBUILTIN(read_pipe, "i.", "tn", OCLC20_LANG) -LANGBUILTIN(write_pipe, "i.", "tn", OCLC20_LANG) +LANGBUILTIN(read_pipe, "i.", "tn", OCL_PIPE) +LANGBUILTIN(write_pipe, "i.", "tn", OCL_PIPE) -LANGBUILTIN(reserve_read_pipe, "i.", "tn", OCLC20_LANG) -LANGBUILTIN(reserve_write_pipe, "i.", "tn", OCLC20_LANG) +LANGBUILTIN(reserve_read_pipe, "i.", "tn", OCL_PIPE) +LANGBUILTIN(reserve_write_pipe, "i.", "tn", OCL_PIPE) -LANGBUILTIN(commit_write_pipe, "v.", "tn", OCLC20_LANG) -LANGBUILTIN(commit_read_pipe, "v.", "tn", OCLC20_LANG) +LANGBUILTIN(commit_write_pipe, "v.", "tn", OCL_PIPE) +LANGBUILTIN(commit_read_pipe, "v.", "tn", OCL_PIPE) -LANGBUILTIN(sub_group_reserve_read_pipe, "i.", "tn", OCLC20_LANG) -LANGBUILTIN(sub_group_reserve_write_pipe, "i.", "tn", OCLC20_LANG) +LANGBUILTIN(sub_group_reserve_read_pipe, "i.", "tn", OCL_PIPE) +LANGBUILTIN(sub_group_reserve_write_pipe, "i.", "tn", OCL_PIPE) -LANGBUILTIN(sub_group_commit_read_pipe, "v.", "tn", OCLC20_LANG) -LANGBUILTIN(sub_group_commit_write_pipe, "v.", "tn", OCLC20_LANG) +LANGBUILTIN(sub_group_commit_read_pipe, "v.", "tn", OCL_PIPE) +LANGBUILTIN(sub_group_commit_write_pipe, "v.", "tn", OCL_PIPE) -LANGBUILTIN(work_group_reserve_read_pipe, "i.", "tn", OCLC20_LANG) -LANGBUILTIN(work_group_reserve_write_pipe, "i.", "tn", OCLC20_LANG) +LANGBUILTIN(work_group_reserve_read_pipe, "i.", "tn", OCL_PIPE) +LANGBUILTIN(work_group_reserve_write_pipe, "i.", "tn", OCL_PIPE) -LANGBUILTIN(work_group_commit_read_pipe, "v.", "tn", OCLC20_LANG) -LANGBUILTIN(work_group_commit_write_pipe, "v.", "tn", OCLC20_LANG) +LANGBUILTIN(work_group_commit_read_pipe, "v.", "tn", OCL_PIPE) +LANGBUILTIN(work_group_commit_write_pipe, "v.", "tn", OCL_PIPE) -LANGBUILTIN(get_pipe_num_packets, "Ui.", "tn", OCLC20_LANG) -LANGBUILTIN(get_pipe_max_packets, "Ui.", "tn", OCLC20_LANG) +LANGBUILTIN(get_pipe_num_packets, "Ui.", "tn", OCL_PIPE) +LANGBUILTIN(get_pipe_max_packets, "Ui.", "tn", OCL_PIPE) // OpenCL v2.0 s6.13.17 - Enqueue kernel functions. // Custom builtin check allows to perform special check of passed block arguments. -LANGBUILTIN(enqueue_kernel, "i.", "tn", OCLC20_LANG) -LANGBUILTIN(get_kernel_work_group_size, "Ui.", "tn", OCLC20_LANG) -LANGBUILTIN(get_kernel_preferred_work_group_size_multiple, "Ui.", "tn", OCLC20_LANG) -LANGBUILTIN(get_kernel_max_sub_group_size_for_ndrange, "Ui.", "tn", OCLC20_LANG) -LANGBUILTIN(get_kernel_sub_group_count_for_ndrange, "Ui.", "tn", OCLC20_LANG) +LANGBUILTIN(enqueue_kernel, "i.", "tn", OCL_DSE) +LANGBUILTIN(get_kernel_work_group_size, "Ui.", "tn", OCL_DSE) +LANGBUILTIN(get_kernel_preferred_work_group_size_multiple, "Ui.", "tn", OCL_DSE) +LANGBUILTIN(get_kernel_max_sub_group_size_for_ndrange, "Ui.", "tn", OCL_DSE) +LANGBUILTIN(get_kernel_sub_group_count_for_ndrange, "Ui.", "tn", OCL_DSE) // OpenCL v2.0 s6.13.9 - Address space qualifier functions. // FIXME: Pointer parameters of OpenCL builtins should have their address space // requirement defined. -LANGBUILTIN(to_global, "v*v*", "tn", OCLC20_LANG) -LANGBUILTIN(to_local, "v*v*", "tn", OCLC20_LANG) -LANGBUILTIN(to_private, "v*v*", "tn", OCLC20_LANG) +LANGBUILTIN(to_global, "v*v*", "tn", OCL_GAS) +LANGBUILTIN(to_local, "v*v*", "tn", OCL_GAS) +LANGBUILTIN(to_private, "v*v*", "tn", OCL_GAS) // OpenCL half load/store builtin -LANGBUILTIN(__builtin_store_half, "vdh*", "n", ALL_OCLC_LANGUAGES) -LANGBUILTIN(__builtin_store_halff, "vfh*", "n", ALL_OCLC_LANGUAGES) -LANGBUILTIN(__builtin_load_half, "dhC*", "nc", ALL_OCLC_LANGUAGES) -LANGBUILTIN(__builtin_load_halff, "fhC*", "nc", ALL_OCLC_LANGUAGES) +LANGBUILTIN(__builtin_store_half, "vdh*", "n", ALL_OCL_LANGUAGES) +LANGBUILTIN(__builtin_store_halff, "vfh*", "n", ALL_OCL_LANGUAGES) +LANGBUILTIN(__builtin_load_half, "dhC*", "nc", ALL_OCL_LANGUAGES) +LANGBUILTIN(__builtin_load_halff, "fhC*", "nc", ALL_OCL_LANGUAGES) // Builtins for os_log/os_trace BUILTIN(__builtin_os_log_format_buffer_size, "zcC*.", "p:0:nut") diff --git a/contrib/llvm-project/clang/include/clang/Basic/Builtins.h b/contrib/llvm-project/clang/include/clang/Basic/Builtins.h index cdaaee48c32d..1dabafce54f3 100644 --- a/contrib/llvm-project/clang/include/clang/Basic/Builtins.h +++ b/contrib/llvm-project/clang/include/clang/Basic/Builtins.h @@ -28,20 +28,21 @@ class IdentifierTable; class LangOptions; enum LanguageID { - GNU_LANG = 0x1, // builtin requires GNU mode. - C_LANG = 0x2, // builtin for c only. - CXX_LANG = 0x4, // builtin for cplusplus only. - OBJC_LANG = 0x8, // builtin for objective-c and objective-c++ - MS_LANG = 0x10, // builtin requires MS mode. - OCLC20_LANG = 0x20, // builtin for OpenCL C 2.0 only. - OCLC1X_LANG = 0x40, // builtin for OpenCL C 1.x only. - OMP_LANG = 0x80, // builtin requires OpenMP. - CUDA_LANG = 0x100, // builtin requires CUDA. - COR_LANG = 0x200, // builtin requires use of 'fcoroutine-ts' option. + GNU_LANG = 0x1, // builtin requires GNU mode. + C_LANG = 0x2, // builtin for c only. + CXX_LANG = 0x4, // builtin for cplusplus only. + OBJC_LANG = 0x8, // builtin for objective-c and objective-c++ + MS_LANG = 0x10, // builtin requires MS mode. + OMP_LANG = 0x20, // builtin requires OpenMP. + CUDA_LANG = 0x40, // builtin requires CUDA. + COR_LANG = 0x80, // builtin requires use of 'fcoroutine-ts' option. + OCL_GAS = 0x100, // builtin requires OpenCL generic address space. + OCL_PIPE = 0x200, // builtin requires OpenCL pipe. + OCL_DSE = 0x400, // builtin requires OpenCL device side enqueue. + ALL_OCL_LANGUAGES = 0x800, // builtin for OCL languages. ALL_LANGUAGES = C_LANG | CXX_LANG | OBJC_LANG, // builtin for all languages. ALL_GNU_LANGUAGES = ALL_LANGUAGES | GNU_LANG, // builtin requires GNU mode. - ALL_MS_LANGUAGES = ALL_LANGUAGES | MS_LANG, // builtin requires MS mode. - ALL_OCLC_LANGUAGES = OCLC1X_LANG | OCLC20_LANG // builtin for OCLC languages. + ALL_MS_LANGUAGES = ALL_LANGUAGES | MS_LANG // builtin requires MS mode. }; namespace Builtin { diff --git a/contrib/llvm-project/clang/include/clang/Basic/DiagnosticCommonKinds.td b/contrib/llvm-project/clang/include/clang/Basic/DiagnosticCommonKinds.td index 5ea55b0fd31b..421527827a4b 100644 --- a/contrib/llvm-project/clang/include/clang/Basic/DiagnosticCommonKinds.td +++ b/contrib/llvm-project/clang/include/clang/Basic/DiagnosticCommonKinds.td @@ -145,8 +145,8 @@ def warn_conflicting_nullability_attr_overriding_param_types : Warning< def err_nullability_conflicting : Error< "nullability specifier %0 conflicts with existing specifier %1">; -def warn_target_unsupported_branch_protection_option: Warning < - "ignoring '-mbranch-protection=' option because the '%0' architecture does not support it">, +def warn_incompatible_branch_protection_option: Warning < + "'-mbranch-protection=' option is incompatible with the '%0' architecture">, InGroup<BranchProtection>; def warn_target_unsupported_branch_protection_attribute: Warning < diff --git a/contrib/llvm-project/clang/include/clang/Basic/TargetInfo.h b/contrib/llvm-project/clang/include/clang/Basic/TargetInfo.h index a49342a34f3e..e7db877f4e2b 100644 --- a/contrib/llvm-project/clang/include/clang/Basic/TargetInfo.h +++ b/contrib/llvm-project/clang/include/clang/Basic/TargetInfo.h @@ -644,8 +644,8 @@ public: } /// Return the largest alignment for which a suitably-sized allocation with - /// '::operator new(size_t)' or 'malloc' is guaranteed to produce a - /// correctly-aligned pointer. + /// '::operator new(size_t)' is guaranteed to produce a correctly-aligned + /// pointer. unsigned getNewAlign() const { return NewAlign ? NewAlign : std::max(LongDoubleAlign, LongLongAlign); } diff --git a/contrib/llvm-project/clang/lib/Basic/Builtins.cpp b/contrib/llvm-project/clang/lib/Basic/Builtins.cpp index 2b0f4071662c..6d278e9c4a22 100644 --- a/contrib/llvm-project/clang/lib/Basic/Builtins.cpp +++ b/contrib/llvm-project/clang/lib/Basic/Builtins.cpp @@ -69,22 +69,26 @@ bool Builtin::Context::builtinIsSupported(const Builtin::Info &BuiltinInfo, bool MSModeUnsupported = !LangOpts.MicrosoftExt && (BuiltinInfo.Langs & MS_LANG); bool ObjCUnsupported = !LangOpts.ObjC && BuiltinInfo.Langs == OBJC_LANG; - bool OclC1Unsupported = (LangOpts.OpenCLVersion / 100) != 1 && - (BuiltinInfo.Langs & ALL_OCLC_LANGUAGES ) == OCLC1X_LANG; - bool OclC2Unsupported = - (LangOpts.getOpenCLCompatibleVersion() != 200) && - (BuiltinInfo.Langs & ALL_OCLC_LANGUAGES) == OCLC20_LANG; - bool OclCUnsupported = !LangOpts.OpenCL && - (BuiltinInfo.Langs & ALL_OCLC_LANGUAGES); + bool OclCUnsupported = + !LangOpts.OpenCL && (BuiltinInfo.Langs & ALL_OCL_LANGUAGES); + bool OclGASUnsupported = + !LangOpts.OpenCLGenericAddressSpace && (BuiltinInfo.Langs & OCL_GAS); + bool OclPipeUnsupported = + !LangOpts.OpenCLPipes && (BuiltinInfo.Langs & OCL_PIPE); + // Device side enqueue is not supported until OpenCL 2.0. In 2.0 and higher + // support is indicated with language option for blocks. + bool OclDSEUnsupported = + (LangOpts.getOpenCLCompatibleVersion() < 200 || !LangOpts.Blocks) && + (BuiltinInfo.Langs & OCL_DSE); bool OpenMPUnsupported = !LangOpts.OpenMP && BuiltinInfo.Langs == OMP_LANG; bool CUDAUnsupported = !LangOpts.CUDA && BuiltinInfo.Langs == CUDA_LANG; bool CPlusPlusUnsupported = !LangOpts.CPlusPlus && BuiltinInfo.Langs == CXX_LANG; return !BuiltinsUnsupported && !CorBuiltinsUnsupported && - !MathBuiltinsUnsupported && !OclCUnsupported && !OclC1Unsupported && - !OclC2Unsupported && !OpenMPUnsupported && !GnuModeUnsupported && - !MSModeUnsupported && !ObjCUnsupported && !CPlusPlusUnsupported && - !CUDAUnsupported; + !MathBuiltinsUnsupported && !OclCUnsupported && !OclGASUnsupported && + !OclPipeUnsupported && !OclDSEUnsupported && !OpenMPUnsupported && + !GnuModeUnsupported && !MSModeUnsupported && !ObjCUnsupported && + !CPlusPlusUnsupported && !CUDAUnsupported; } /// initializeBuiltins - Mark the identifiers for all the builtins with their diff --git a/contrib/llvm-project/clang/lib/CodeGen/CodeGenModule.cpp b/contrib/llvm-project/clang/lib/CodeGen/CodeGenModule.cpp index 2346176a1562..29806b65e984 100644 --- a/contrib/llvm-project/clang/lib/CodeGen/CodeGenModule.cpp +++ b/contrib/llvm-project/clang/lib/CodeGen/CodeGenModule.cpp @@ -4381,6 +4381,14 @@ LangAS CodeGenModule::GetGlobalConstantAddressSpace() const { return LangAS::opencl_constant; if (LangOpts.SYCLIsDevice) return LangAS::sycl_global; + if (LangOpts.HIP && LangOpts.CUDAIsDevice && getTriple().isSPIRV()) + // For HIPSPV map literals to cuda_device (maps to CrossWorkGroup in SPIR-V) + // instead of default AS (maps to Generic in SPIR-V). Otherwise, we end up + // with OpVariable instructions with Generic storage class which is not + // allowed (SPIR-V V1.6 s3.42.8). Also, mapping literals to SPIR-V + // UniformConstant storage class is not viable as pointers to it may not be + // casted to Generic pointers which are used to model HIP's "flat" pointers. + return LangAS::cuda_device; if (auto AS = getTarget().getConstantAddressSpace()) return AS.getValue(); return LangAS::Default; diff --git a/contrib/llvm-project/clang/lib/CodeGen/TargetInfo.cpp b/contrib/llvm-project/clang/lib/CodeGen/TargetInfo.cpp index 8a0150218a7a..9af3004ebcc5 100644 --- a/contrib/llvm-project/clang/lib/CodeGen/TargetInfo.cpp +++ b/contrib/llvm-project/clang/lib/CodeGen/TargetInfo.cpp @@ -9474,6 +9474,28 @@ class SparcV8TargetCodeGenInfo : public TargetCodeGenInfo { public: SparcV8TargetCodeGenInfo(CodeGenTypes &CGT) : TargetCodeGenInfo(std::make_unique<SparcV8ABIInfo>(CGT)) {} + + llvm::Value *decodeReturnAddress(CodeGen::CodeGenFunction &CGF, + llvm::Value *Address) const override { + int Offset; + if (isAggregateTypeForABI(CGF.CurFnInfo->getReturnType())) + Offset = 12; + else + Offset = 8; + return CGF.Builder.CreateGEP(CGF.Int8Ty, Address, + llvm::ConstantInt::get(CGF.Int32Ty, Offset)); + } + + llvm::Value *encodeReturnAddress(CodeGen::CodeGenFunction &CGF, + llvm::Value *Address) const override { + int Offset; + if (isAggregateTypeForABI(CGF.CurFnInfo->getReturnType())) + Offset = -12; + else + Offset = -8; + return CGF.Builder.CreateGEP(CGF.Int8Ty, Address, + llvm::ConstantInt::get(CGF.Int32Ty, Offset)); + } }; } // end anonymous namespace @@ -9748,6 +9770,18 @@ public: bool initDwarfEHRegSizeTable(CodeGen::CodeGenFunction &CGF, llvm::Value *Address) const override; + + llvm::Value *decodeReturnAddress(CodeGen::CodeGenFunction &CGF, + llvm::Value *Address) const override { + return CGF.Builder.CreateGEP(CGF.Int8Ty, Address, + llvm::ConstantInt::get(CGF.Int32Ty, 8)); + } + + llvm::Value *encodeReturnAddress(CodeGen::CodeGenFunction &CGF, + llvm::Value *Address) const override { + return CGF.Builder.CreateGEP(CGF.Int8Ty, Address, + llvm::ConstantInt::get(CGF.Int32Ty, -8)); + } }; } // end anonymous namespace diff --git a/contrib/llvm-project/clang/lib/Driver/ToolChains/Clang.cpp b/contrib/llvm-project/clang/lib/Driver/ToolChains/Clang.cpp index 7aac977209eb..f2f18e901ab0 100644 --- a/contrib/llvm-project/clang/lib/Driver/ToolChains/Clang.cpp +++ b/contrib/llvm-project/clang/lib/Driver/ToolChains/Clang.cpp @@ -1639,7 +1639,7 @@ static void CollectARMPACBTIOptions(const ToolChain &TC, const ArgList &Args, const Driver &D = TC.getDriver(); const llvm::Triple &Triple = TC.getEffectiveTriple(); if (!(isAArch64 || (Triple.isArmT32() && Triple.isArmMClass()))) - D.Diag(diag::warn_target_unsupported_branch_protection_option) + D.Diag(diag::warn_incompatible_branch_protection_option) << Triple.getArchName(); StringRef Scope, Key; @@ -8148,11 +8148,25 @@ void LinkerWrapper::ConstructJob(Compilation &C, const JobAction &JA, const InputInfoList &Inputs, const ArgList &Args, const char *LinkingOutput) const { + const Driver &D = getToolChain().getDriver(); + const llvm::Triple TheTriple = getToolChain().getTriple(); + auto OpenMPTCRange = C.getOffloadToolChains<Action::OFK_OpenMP>(); ArgStringList CmdArgs; - if (getToolChain().getDriver().isUsingLTO(/* IsOffload */ true)) { + // Pass the CUDA path to the linker wrapper tool. + for (auto &I : llvm::make_range(OpenMPTCRange.first, OpenMPTCRange.second)) { + const ToolChain *TC = I.second; + if (TC->getTriple().isNVPTX()) { + CudaInstallationDetector CudaInstallation(D, TheTriple, Args); + if (CudaInstallation.isValid()) + CmdArgs.push_back(Args.MakeArgString( + "--cuda-path=" + CudaInstallation.getInstallPath())); + break; + } + } + + if (D.isUsingLTO(/* IsOffload */ true)) { // Pass in target features for each toolchain. - auto OpenMPTCRange = C.getOffloadToolChains<Action::OFK_OpenMP>(); for (auto &I : llvm::make_range(OpenMPTCRange.first, OpenMPTCRange.second)) { const ToolChain *TC = I.second; @@ -8165,9 +8179,10 @@ void LinkerWrapper::ConstructJob(Compilation &C, const JobAction &JA, } // Pass in the bitcode library to be linked during LTO. - for (auto &I : llvm::make_range(OpenMPTCRange.first, OpenMPTCRange.second)) { + for (auto &I : + llvm::make_range(OpenMPTCRange.first, OpenMPTCRange.second)) { const ToolChain *TC = I.second; - const Driver &D = TC->getDriver(); + const Driver &TCDriver = TC->getDriver(); const ArgList &TCArgs = C.getArgsForToolChain(TC, "", Action::OFK_OpenMP); StringRef Arch = TCArgs.getLastArgValue(options::OPT_march_EQ); @@ -8182,7 +8197,7 @@ void LinkerWrapper::ConstructJob(Compilation &C, const JobAction &JA, BitcodeSuffix += Arch; ArgStringList BitcodeLibrary; - addOpenMPDeviceRTL(D, TCArgs, BitcodeLibrary, BitcodeSuffix, + addOpenMPDeviceRTL(TCDriver, TCArgs, BitcodeLibrary, BitcodeSuffix, TC->getTriple()); if (!BitcodeLibrary.empty()) @@ -8210,12 +8225,8 @@ void LinkerWrapper::ConstructJob(Compilation &C, const JobAction &JA, } } - // Construct the link job so we can wrap around it. - Linker->ConstructJob(C, JA, Output, Inputs, Args, LinkingOutput); - const auto &LinkCommand = C.getJobs().getJobs().back(); - CmdArgs.push_back("-host-triple"); - CmdArgs.push_back(Args.MakeArgString(getToolChain().getTripleString())); + CmdArgs.push_back(Args.MakeArgString(TheTriple.getTriple())); if (Args.hasArg(options::OPT_v)) CmdArgs.push_back("-v"); @@ -8246,6 +8257,10 @@ void LinkerWrapper::ConstructJob(Compilation &C, const JobAction &JA, if (Args.getLastArg(options::OPT_save_temps_EQ)) CmdArgs.push_back("-save-temps"); + // Construct the link job so we can wrap around it. + Linker->ConstructJob(C, JA, Output, Inputs, Args, LinkingOutput); + const auto &LinkCommand = C.getJobs().getJobs().back(); + // Add the linker arguments to be forwarded by the wrapper. CmdArgs.push_back("-linker-path"); CmdArgs.push_back(LinkCommand->getExecutable()); diff --git a/contrib/llvm-project/clang/lib/Driver/ToolChains/Hexagon.cpp b/contrib/llvm-project/clang/lib/Driver/ToolChains/Hexagon.cpp index ba3040636604..e772122f5ff5 100644 --- a/contrib/llvm-project/clang/lib/Driver/ToolChains/Hexagon.cpp +++ b/contrib/llvm-project/clang/lib/Driver/ToolChains/Hexagon.cpp @@ -72,23 +72,25 @@ static void handleHVXTargetFeatures(const Driver &D, const ArgList &Args, (Cpu.back() == 'T' || Cpu.back() == 't' ? Cpu.drop_back(1) : Cpu).str(); HasHVX = false; - // Handle -mhvx, -mhvx=, -mno-hvx. If both present, -mhvx= wins over -mhvx. - auto argOrNull = [&Args](auto FlagOn, auto FlagOff) -> Arg* { - if (Arg *A = Args.getLastArg(FlagOn, FlagOff)) { - if (A->getOption().matches(FlagOn)) - return A; - } - return nullptr; - }; - - Arg *HvxBareA = - argOrNull(options::OPT_mhexagon_hvx, options::OPT_mno_hexagon_hvx); - Arg *HvxVerA = - argOrNull(options::OPT_mhexagon_hvx_EQ, options::OPT_mno_hexagon_hvx); + // Handle -mhvx, -mhvx=, -mno-hvx. If versioned and versionless flags + // are both present, the last one wins. + Arg *HvxEnablingArg = + Args.getLastArg(options::OPT_mhexagon_hvx, options::OPT_mhexagon_hvx_EQ, + options::OPT_mno_hexagon_hvx); + if (HvxEnablingArg) { + if (HvxEnablingArg->getOption().matches(options::OPT_mno_hexagon_hvx)) + HvxEnablingArg = nullptr; + } - if (Arg *A = HvxVerA ? HvxVerA : HvxBareA) { - if (A->getOption().matches(options::OPT_mhexagon_hvx_EQ)) - HvxVer = StringRef(A->getValue()).lower(); // lower produces std:string + if (HvxEnablingArg) { + // If -mhvx[=] was given, it takes precedence. + if (Arg *A = Args.getLastArg(options::OPT_mhexagon_hvx, + options::OPT_mhexagon_hvx_EQ)) { + // If the version was given, set HvxVer. Otherwise HvxVer + // will remain equal to the CPU version. + if (A->getOption().matches(options::OPT_mhexagon_hvx_EQ)) + HvxVer = StringRef(A->getValue()).lower(); + } HasHVX = true; Features.push_back(makeFeature(Twine("hvx") + HvxVer, true)); } else if (Arg *A = Args.getLastArg(options::OPT_mno_hexagon_hvx)) { diff --git a/contrib/llvm-project/clang/lib/Driver/ToolChains/MSVC.cpp b/contrib/llvm-project/clang/lib/Driver/ToolChains/MSVC.cpp index 18cef288f018..9f4751167ac1 100644 --- a/contrib/llvm-project/clang/lib/Driver/ToolChains/MSVC.cpp +++ b/contrib/llvm-project/clang/lib/Driver/ToolChains/MSVC.cpp @@ -1393,8 +1393,8 @@ VersionTuple MSVCToolChain::computeMSVCVersion(const Driver *D, if (MSVT.empty() && Args.hasFlag(options::OPT_fms_extensions, options::OPT_fno_ms_extensions, IsWindowsMSVC)) { - // -fms-compatibility-version=19.14 is default, aka 2017, 15.7 - MSVT = VersionTuple(19, 14); + // -fms-compatibility-version=19.20 is default, aka 2019, 16.x + MSVT = VersionTuple(19, 20); } return MSVT; } diff --git a/contrib/llvm-project/clang/lib/Driver/ToolChains/MinGW.cpp b/contrib/llvm-project/clang/lib/Driver/ToolChains/MinGW.cpp index 0501f9737404..ceeaa79bc202 100644 --- a/contrib/llvm-project/clang/lib/Driver/ToolChains/MinGW.cpp +++ b/contrib/llvm-project/clang/lib/Driver/ToolChains/MinGW.cpp @@ -86,7 +86,9 @@ void tools::MinGW::Linker::AddLibGCC(const ArgList &Args, CmdArgs.push_back("-lmoldname"); CmdArgs.push_back("-lmingwex"); for (auto Lib : Args.getAllArgValues(options::OPT_l)) - if (StringRef(Lib).startswith("msvcr") || StringRef(Lib).startswith("ucrt")) + if (StringRef(Lib).startswith("msvcr") || + StringRef(Lib).startswith("ucrt") || + StringRef(Lib).startswith("crtdll")) return; CmdArgs.push_back("-lmsvcrt"); } diff --git a/contrib/llvm-project/clang/lib/Driver/ToolChains/MinGW.h b/contrib/llvm-project/clang/lib/Driver/ToolChains/MinGW.h index c3de19b97724..c9553b4f4652 100644 --- a/contrib/llvm-project/clang/lib/Driver/ToolChains/MinGW.h +++ b/contrib/llvm-project/clang/lib/Driver/ToolChains/MinGW.h @@ -90,6 +90,8 @@ public: void printVerboseInfo(raw_ostream &OS) const override; + unsigned GetDefaultDwarfVersion() const override { return 4; } + protected: Tool *getTool(Action::ActionClass AC) const override; Tool *buildLinker() const override; diff --git a/contrib/llvm-project/clang/lib/Driver/ToolChains/OpenBSD.cpp b/contrib/llvm-project/clang/lib/Driver/ToolChains/OpenBSD.cpp index 96abac57764f..bcd54bedfa89 100644 --- a/contrib/llvm-project/clang/lib/Driver/ToolChains/OpenBSD.cpp +++ b/contrib/llvm-project/clang/lib/Driver/ToolChains/OpenBSD.cpp @@ -160,7 +160,8 @@ void openbsd::Linker::ConstructJob(Compilation &C, const JobAction &JA, assert(Output.isNothing() && "Invalid output."); } - if (!Args.hasArg(options::OPT_nostdlib, options::OPT_nostartfiles)) { + if (!Args.hasArg(options::OPT_nostdlib, options::OPT_nostartfiles, + options::OPT_r)) { const char *crt0 = nullptr; const char *crtbegin = nullptr; if (!Args.hasArg(options::OPT_shared)) { @@ -191,7 +192,8 @@ void openbsd::Linker::ConstructJob(Compilation &C, const JobAction &JA, bool NeedsXRayDeps = addXRayRuntime(ToolChain, Args, CmdArgs); AddLinkerInputs(ToolChain, Inputs, Args, CmdArgs, JA); - if (!Args.hasArg(options::OPT_nostdlib, options::OPT_nodefaultlibs)) { + if (!Args.hasArg(options::OPT_nostdlib, options::OPT_nodefaultlibs, + options::OPT_r)) { // Use the static OpenMP runtime with -static-openmp bool StaticOpenMP = Args.hasArg(options::OPT_static_openmp) && !Args.hasArg(options::OPT_static); @@ -234,7 +236,8 @@ void openbsd::Linker::ConstructJob(Compilation &C, const JobAction &JA, CmdArgs.push_back("-lcompiler_rt"); } - if (!Args.hasArg(options::OPT_nostdlib, options::OPT_nostartfiles)) { + if (!Args.hasArg(options::OPT_nostdlib, options::OPT_nostartfiles, + options::OPT_r)) { const char *crtend = nullptr; if (!Args.hasArg(options::OPT_shared)) crtend = "crtend.o"; diff --git a/contrib/llvm-project/clang/lib/Format/DefinitionBlockSeparator.cpp b/contrib/llvm-project/clang/lib/Format/DefinitionBlockSeparator.cpp index 827564357f78..cfb019a471dc 100644 --- a/contrib/llvm-project/clang/lib/Format/DefinitionBlockSeparator.cpp +++ b/contrib/llvm-project/clang/lib/Format/DefinitionBlockSeparator.cpp @@ -35,19 +35,31 @@ void DefinitionBlockSeparator::separateBlocks( const bool IsNeverStyle = Style.SeparateDefinitionBlocks == FormatStyle::SDS_Never; const AdditionalKeywords &ExtraKeywords = Tokens.getKeywords(); - auto LikelyDefinition = [this, ExtraKeywords](const AnnotatedLine *Line, - bool ExcludeEnum = false) { + auto GetBracketLevelChange = [](const FormatToken *Tok) { + if (Tok->isOneOf(tok::l_brace, tok::l_paren, tok::l_square)) + return 1; + if (Tok->isOneOf(tok::r_brace, tok::r_paren, tok::r_square)) + return -1; + return 0; + }; + auto LikelyDefinition = [&](const AnnotatedLine *Line, + bool ExcludeEnum = false) { if ((Line->MightBeFunctionDecl && Line->mightBeFunctionDefinition()) || Line->startsWithNamespace()) return true; - FormatToken *CurrentToken = Line->First; - while (CurrentToken) { - if (CurrentToken->isOneOf(tok::kw_class, tok::kw_struct) || - (Style.isJavaScript() && CurrentToken->is(ExtraKeywords.kw_function))) - return true; - if (!ExcludeEnum && CurrentToken->is(tok::kw_enum)) - return true; - CurrentToken = CurrentToken->Next; + int BracketLevel = 0; + for (const FormatToken *CurrentToken = Line->First; CurrentToken; + CurrentToken = CurrentToken->Next) { + if (BracketLevel == 0) { + if ((CurrentToken->isOneOf(tok::kw_class, tok::kw_struct, + tok::kw_union) || + (Style.isJavaScript() && + CurrentToken->is(ExtraKeywords.kw_function)))) + return true; + if (!ExcludeEnum && CurrentToken->is(tok::kw_enum)) + return true; + } + BracketLevel += GetBracketLevelChange(CurrentToken); } return false; }; @@ -102,14 +114,17 @@ void DefinitionBlockSeparator::separateBlocks( IsPPConditional(OpeningLineIndex - 1); }; const auto HasEnumOnLine = [&]() { - FormatToken *CurrentToken = CurrentLine->First; bool FoundEnumKeyword = false; - while (CurrentToken) { - if (CurrentToken->is(tok::kw_enum)) - FoundEnumKeyword = true; - else if (FoundEnumKeyword && CurrentToken->is(tok::l_brace)) - return true; - CurrentToken = CurrentToken->Next; + int BracketLevel = 0; + for (const FormatToken *CurrentToken = CurrentLine->First; CurrentToken; + CurrentToken = CurrentToken->Next) { + if (BracketLevel == 0) { + if (CurrentToken->is(tok::kw_enum)) + FoundEnumKeyword = true; + else if (FoundEnumKeyword && CurrentToken->is(tok::l_brace)) + return true; + } + BracketLevel += GetBracketLevelChange(CurrentToken); } return FoundEnumKeyword && I + 1 < Lines.size() && Lines[I + 1]->First->is(tok::l_brace); diff --git a/contrib/llvm-project/clang/lib/Format/QualifierAlignmentFixer.cpp b/contrib/llvm-project/clang/lib/Format/QualifierAlignmentFixer.cpp index b3a4684bead1..0142a6c08ed3 100644 --- a/contrib/llvm-project/clang/lib/Format/QualifierAlignmentFixer.cpp +++ b/contrib/llvm-project/clang/lib/Format/QualifierAlignmentFixer.cpp @@ -396,6 +396,10 @@ LeftRightQualifierAlignmentFixer::analyze( for (AnnotatedLine *Line : AnnotatedLines) { FormatToken *First = Line->First; + assert(First); + if (First->Finalized) + continue; + const auto *Last = Line->Last; for (const auto *Tok = First; Tok && Tok != Last && Tok->Next; diff --git a/contrib/llvm-project/clang/lib/Format/UnwrappedLineParser.cpp b/contrib/llvm-project/clang/lib/Format/UnwrappedLineParser.cpp index 642679128409..2e2293c6d58b 100644 --- a/contrib/llvm-project/clang/lib/Format/UnwrappedLineParser.cpp +++ b/contrib/llvm-project/clang/lib/Format/UnwrappedLineParser.cpp @@ -3102,7 +3102,8 @@ void UnwrappedLineParser::parseRecord(bool ParseAsExpr) { } if (FormatTok->is(tok::l_square)) { FormatToken *Previous = FormatTok->Previous; - if (!Previous || Previous->isNot(tok::r_paren)) { + if (!Previous || + !(Previous->is(tok::r_paren) || Previous->isTypeOrIdentifier())) { // Don't try parsing a lambda if we had a closing parenthesis before, // it was probably a pointer to an array: int (*)[]. if (!tryToParseLambda()) diff --git a/contrib/llvm-project/clang/lib/Headers/opencl-c-base.h b/contrib/llvm-project/clang/lib/Headers/opencl-c-base.h index ad276dc0f6aa..5191c41bcd05 100644 --- a/contrib/llvm-project/clang/lib/Headers/opencl-c-base.h +++ b/contrib/llvm-project/clang/lib/Headers/opencl-c-base.h @@ -67,6 +67,8 @@ #if (__OPENCL_CPP_VERSION__ == 202100 || __OPENCL_C_VERSION__ == 300) // For the SPIR and SPIR-V target all features are supported. #if defined(__SPIR__) || defined(__SPIRV__) +#define __opencl_c_atomic_order_seq_cst 1 +#define __opencl_c_atomic_scope_device 1 #define __opencl_c_atomic_scope_all_devices 1 #define __opencl_c_read_write_images 1 #endif // defined(__SPIR__) diff --git a/contrib/llvm-project/clang/lib/Headers/opencl-c.h b/contrib/llvm-project/clang/lib/Headers/opencl-c.h index 059a2ec2371b..c7bb77716ac4 100644 --- a/contrib/llvm-project/clang/lib/Headers/opencl-c.h +++ b/contrib/llvm-project/clang/lib/Headers/opencl-c.h @@ -13832,6 +13832,7 @@ float __ovld atomic_fetch_max_explicit(volatile atomic_float *object, #endif // defined(__opencl_c_ext_fp32_global_atomic_min_max) && \ defined(__opencl_c_ext_fp32_local_atomic_min_max) +#if defined(cl_khr_int64_base_atomics) && defined(cl_khr_int64_extended_atomics) #if defined(__opencl_c_ext_fp64_global_atomic_min_max) double __ovld atomic_fetch_min(volatile __global atomic_double *object, double operand); @@ -13882,6 +13883,8 @@ double __ovld atomic_fetch_max_explicit(volatile atomic_double *object, memory_scope scope); #endif // defined(__opencl_c_ext_fp64_global_atomic_min_max) && \ defined(__opencl_c_ext_fp64_local_atomic_min_max) +#endif // defined(cl_khr_int64_base_atomics) && \ + defined(cl_khr_int64_extended_atomics) #if defined(__opencl_c_ext_fp16_global_atomic_add) half __ovld atomic_fetch_add(volatile __global atomic_half *object, @@ -13985,6 +13988,7 @@ float __ovld atomic_fetch_sub_explicit(volatile atomic_float *object, #endif // defined(__opencl_c_ext_fp32_global_atomic_add) && \ defined(__opencl_c_ext_fp32_local_atomic_add) +#if defined(cl_khr_int64_base_atomics) && defined(cl_khr_int64_extended_atomics) #if defined(__opencl_c_ext_fp64_global_atomic_add) double __ovld atomic_fetch_add(volatile __global atomic_double *object, double operand); @@ -14035,6 +14039,8 @@ double __ovld atomic_fetch_sub_explicit(volatile atomic_double *object, memory_scope scope); #endif // defined(__opencl_c_ext_fp64_global_atomic_add) && \ defined(__opencl_c_ext_fp64_local_atomic_add) +#endif // defined(cl_khr_int64_base_atomics) && \ + defined(cl_khr_int64_extended_atomics) #endif // cl_ext_float_atomics diff --git a/contrib/llvm-project/clang/lib/Headers/ppc_wrappers/mm_malloc.h b/contrib/llvm-project/clang/lib/Headers/ppc_wrappers/mm_malloc.h index 86cf1a0f7618..b6bf22f92887 100644 --- a/contrib/llvm-project/clang/lib/Headers/ppc_wrappers/mm_malloc.h +++ b/contrib/llvm-project/clang/lib/Headers/ppc_wrappers/mm_malloc.h @@ -19,7 +19,7 @@ #ifndef __cplusplus extern int posix_memalign (void **, size_t, size_t); #else -extern "C" int posix_memalign (void **, size_t, size_t) throw (); +extern "C" int posix_memalign (void **, size_t, size_t); #endif static __inline void * diff --git a/contrib/llvm-project/clang/lib/Sema/OpenCLBuiltins.td b/contrib/llvm-project/clang/lib/Sema/OpenCLBuiltins.td index cd704ba2df13..ab3055300572 100644 --- a/contrib/llvm-project/clang/lib/Sema/OpenCLBuiltins.td +++ b/contrib/llvm-project/clang/lib/Sema/OpenCLBuiltins.td @@ -57,6 +57,23 @@ class FunctionExtension<string _Ext> : AbstractExtension<_Ext>; // disabled. class TypeExtension<string _Ext> : AbstractExtension<_Ext>; +// Concatenate zero or more space-separated extensions in NewExts to Base and +// return the resulting FunctionExtension in ret. +class concatExtension<FunctionExtension Base, string NewExts> { + FunctionExtension ret = FunctionExtension< + !cond( + // Return Base extension if NewExts is empty, + !empty(NewExts) : Base.ExtName, + + // otherwise, return NewExts if Base extension is empty, + !empty(Base.ExtName) : NewExts, + + // otherwise, concatenate NewExts to Base. + true : Base.ExtName # " " # NewExts + ) + >; +} + // TypeExtension definitions. def NoTypeExt : TypeExtension<"">; def Fp16TypeExt : TypeExtension<"cl_khr_fp16">; @@ -90,27 +107,27 @@ def FuncExtOpenCLCNamedAddressSpaceBuiltins : FunctionExtension<"__opencl_c_name def FuncExtOpenCLCPipes : FunctionExtension<"__opencl_c_pipes">; def FuncExtOpenCLCWGCollectiveFunctions : FunctionExtension<"__opencl_c_work_group_collective_functions">; def FuncExtOpenCLCReadWriteImages : FunctionExtension<"__opencl_c_read_write_images">; -def FuncExtFloatAtomicsFp16GlobalLoadStore : FunctionExtension<"cl_ext_float_atomics __opencl_c_ext_fp16_global_atomic_load_store">; -def FuncExtFloatAtomicsFp16LocalLoadStore : FunctionExtension<"cl_ext_float_atomics __opencl_c_ext_fp16_local_atomic_load_store">; -def FuncExtFloatAtomicsFp16GenericLoadStore : FunctionExtension<"cl_ext_float_atomics __opencl_c_ext_fp16_global_atomic_load_store __opencl_c_ext_fp16_local_atomic_load_store">; -def FuncExtFloatAtomicsFp16GlobalAdd : FunctionExtension<"cl_ext_float_atomics __opencl_c_ext_fp16_global_atomic_add">; -def FuncExtFloatAtomicsFp32GlobalAdd : FunctionExtension<"cl_ext_float_atomics __opencl_c_ext_fp32_global_atomic_add">; -def FuncExtFloatAtomicsFp64GlobalAdd : FunctionExtension<"cl_ext_float_atomics __opencl_c_ext_fp64_global_atomic_add">; -def FuncExtFloatAtomicsFp16LocalAdd : FunctionExtension<"cl_ext_float_atomics __opencl_c_ext_fp16_local_atomic_add">; -def FuncExtFloatAtomicsFp32LocalAdd : FunctionExtension<"cl_ext_float_atomics __opencl_c_ext_fp32_local_atomic_add">; -def FuncExtFloatAtomicsFp64LocalAdd : FunctionExtension<"cl_ext_float_atomics __opencl_c_ext_fp64_local_atomic_add">; -def FuncExtFloatAtomicsFp16GenericAdd : FunctionExtension<"cl_ext_float_atomics __opencl_c_ext_fp16_local_atomic_add __opencl_c_ext_fp16_global_atomic_add">; -def FuncExtFloatAtomicsFp32GenericAdd : FunctionExtension<"cl_ext_float_atomics __opencl_c_ext_fp32_local_atomic_add __opencl_c_ext_fp32_global_atomic_add">; -def FuncExtFloatAtomicsFp64GenericAdd : FunctionExtension<"cl_ext_float_atomics __opencl_c_ext_fp64_local_atomic_add __opencl_c_ext_fp64_global_atomic_add">; -def FuncExtFloatAtomicsFp16GlobalMinMax : FunctionExtension<"cl_ext_float_atomics __opencl_c_ext_fp16_global_atomic_min_max">; -def FuncExtFloatAtomicsFp32GlobalMinMax : FunctionExtension<"cl_ext_float_atomics __opencl_c_ext_fp32_global_atomic_min_max">; -def FuncExtFloatAtomicsFp64GlobalMinMax : FunctionExtension<"cl_ext_float_atomics __opencl_c_ext_fp64_global_atomic_min_max">; -def FuncExtFloatAtomicsFp16LocalMinMax : FunctionExtension<"cl_ext_float_atomics __opencl_c_ext_fp16_local_atomic_min_max">; -def FuncExtFloatAtomicsFp32LocalMinMax : FunctionExtension<"cl_ext_float_atomics __opencl_c_ext_fp32_local_atomic_min_max">; -def FuncExtFloatAtomicsFp64LocalMinMax : FunctionExtension<"cl_ext_float_atomics __opencl_c_ext_fp64_local_atomic_min_max">; -def FuncExtFloatAtomicsFp16GenericMinMax : FunctionExtension<"cl_ext_float_atomics __opencl_c_ext_fp16_local_atomic_min_max __opencl_c_ext_fp16_global_atomic_min_max">; -def FuncExtFloatAtomicsFp32GenericMinMax : FunctionExtension<"cl_ext_float_atomics __opencl_c_ext_fp32_local_atomic_min_max __opencl_c_ext_fp32_global_atomic_min_max">; -def FuncExtFloatAtomicsFp64GenericMinMax : FunctionExtension<"cl_ext_float_atomics __opencl_c_ext_fp64_local_atomic_min_max __opencl_c_ext_fp64_global_atomic_min_max">; +def FuncExtFloatAtomicsFp16GlobalASLoadStore : FunctionExtension<"cl_ext_float_atomics __opencl_c_ext_fp16_global_atomic_load_store">; +def FuncExtFloatAtomicsFp16LocalASLoadStore : FunctionExtension<"cl_ext_float_atomics __opencl_c_ext_fp16_local_atomic_load_store">; +def FuncExtFloatAtomicsFp16GenericASLoadStore : FunctionExtension<"cl_ext_float_atomics __opencl_c_ext_fp16_global_atomic_load_store __opencl_c_ext_fp16_local_atomic_load_store">; +def FuncExtFloatAtomicsFp16GlobalASAdd : FunctionExtension<"cl_ext_float_atomics __opencl_c_ext_fp16_global_atomic_add">; +def FuncExtFloatAtomicsFp32GlobalASAdd : FunctionExtension<"cl_ext_float_atomics __opencl_c_ext_fp32_global_atomic_add">; +def FuncExtFloatAtomicsFp64GlobalASAdd : FunctionExtension<"cl_ext_float_atomics __opencl_c_ext_fp64_global_atomic_add">; +def FuncExtFloatAtomicsFp16LocalASAdd : FunctionExtension<"cl_ext_float_atomics __opencl_c_ext_fp16_local_atomic_add">; +def FuncExtFloatAtomicsFp32LocalASAdd : FunctionExtension<"cl_ext_float_atomics __opencl_c_ext_fp32_local_atomic_add">; +def FuncExtFloatAtomicsFp64LocalASAdd : FunctionExtension<"cl_ext_float_atomics __opencl_c_ext_fp64_local_atomic_add">; +def FuncExtFloatAtomicsFp16GenericASAdd : FunctionExtension<"cl_ext_float_atomics __opencl_c_ext_fp16_local_atomic_add __opencl_c_ext_fp16_global_atomic_add">; +def FuncExtFloatAtomicsFp32GenericASAdd : FunctionExtension<"cl_ext_float_atomics __opencl_c_ext_fp32_local_atomic_add __opencl_c_ext_fp32_global_atomic_add">; +def FuncExtFloatAtomicsFp64GenericASAdd : FunctionExtension<"cl_ext_float_atomics __opencl_c_ext_fp64_local_atomic_add __opencl_c_ext_fp64_global_atomic_add">; +def FuncExtFloatAtomicsFp16GlobalASMinMax : FunctionExtension<"cl_ext_float_atomics __opencl_c_ext_fp16_global_atomic_min_max">; +def FuncExtFloatAtomicsFp32GlobalASMinMax : FunctionExtension<"cl_ext_float_atomics __opencl_c_ext_fp32_global_atomic_min_max">; +def FuncExtFloatAtomicsFp64GlobalASMinMax : FunctionExtension<"cl_ext_float_atomics __opencl_c_ext_fp64_global_atomic_min_max">; +def FuncExtFloatAtomicsFp16LocalASMinMax : FunctionExtension<"cl_ext_float_atomics __opencl_c_ext_fp16_local_atomic_min_max">; +def FuncExtFloatAtomicsFp32LocalASMinMax : FunctionExtension<"cl_ext_float_atomics __opencl_c_ext_fp32_local_atomic_min_max">; +def FuncExtFloatAtomicsFp64LocalASMinMax : FunctionExtension<"cl_ext_float_atomics __opencl_c_ext_fp64_local_atomic_min_max">; +def FuncExtFloatAtomicsFp16GenericASMinMax : FunctionExtension<"cl_ext_float_atomics __opencl_c_ext_fp16_local_atomic_min_max __opencl_c_ext_fp16_global_atomic_min_max">; +def FuncExtFloatAtomicsFp32GenericASMinMax : FunctionExtension<"cl_ext_float_atomics __opencl_c_ext_fp32_local_atomic_min_max __opencl_c_ext_fp32_global_atomic_min_max">; +def FuncExtFloatAtomicsFp64GenericASMinMax : FunctionExtension<"cl_ext_float_atomics __opencl_c_ext_fp64_local_atomic_min_max __opencl_c_ext_fp64_global_atomic_min_max">; // Not a real extension, but a workaround to add C++ for OpenCL specific builtins. def FuncExtOpenCLCxx : FunctionExtension<"__cplusplus">; @@ -1041,42 +1058,59 @@ let Extension = FuncExtOpenCLCxx in { } // OpenCL v2.0 s6.13.11 - Atomic Functions. -let MinVersion = CL20 in { - def : Builtin<"atomic_work_item_fence", [Void, MemFenceFlags, MemoryOrder, MemoryScope]>; +// An atomic builtin with 2 additional _explicit variants. +multiclass BuiltinAtomicExplicit<string Name, list<Type> Types, FunctionExtension BaseExt> { + // Without explicit MemoryOrder or MemoryScope. + let Extension = concatExtension<BaseExt, "__opencl_c_atomic_order_seq_cst __opencl_c_atomic_scope_device">.ret in { + def : Builtin<Name, Types>; + } + + // With an explicit MemoryOrder argument. + let Extension = concatExtension<BaseExt, "__opencl_c_atomic_scope_device">.ret in { + def : Builtin<Name # "_explicit", !listconcat(Types, [MemoryOrder])>; + } + + // With explicit MemoryOrder and MemoryScope arguments. + let Extension = BaseExt in { + def : Builtin<Name # "_explicit", !listconcat(Types, [MemoryOrder, MemoryScope])>; + } +} + +// OpenCL 2.0 atomic functions that have a pointer argument in a given address space. +multiclass OpenCL2Atomics<AddressSpace addrspace, FunctionExtension BaseExt> { foreach TypePair = [[AtomicInt, Int], [AtomicUInt, UInt], [AtomicLong, Long], [AtomicULong, ULong], [AtomicFloat, Float], [AtomicDouble, Double]] in { def : Builtin<"atomic_init", - [Void, PointerType<VolatileType<TypePair[0]>, GenericAS>, TypePair[1]]>; - def : Builtin<"atomic_store", - [Void, PointerType<VolatileType<TypePair[0]>, GenericAS>, TypePair[1]]>; - def : Builtin<"atomic_store_explicit", - [Void, PointerType<VolatileType<TypePair[0]>, GenericAS>, TypePair[1], MemoryOrder]>; - def : Builtin<"atomic_store_explicit", - [Void, PointerType<VolatileType<TypePair[0]>, GenericAS>, TypePair[1], MemoryOrder, MemoryScope]>; - def : Builtin<"atomic_load", - [TypePair[1], PointerType<VolatileType<TypePair[0]>, GenericAS>]>; - def : Builtin<"atomic_load_explicit", - [TypePair[1], PointerType<VolatileType<TypePair[0]>, GenericAS>, MemoryOrder]>; - def : Builtin<"atomic_load_explicit", - [TypePair[1], PointerType<VolatileType<TypePair[0]>, GenericAS>, MemoryOrder, MemoryScope]>; - def : Builtin<"atomic_exchange", - [TypePair[1], PointerType<VolatileType<TypePair[0]>, GenericAS>, TypePair[1]]>; - def : Builtin<"atomic_exchange_explicit", - [TypePair[1], PointerType<VolatileType<TypePair[0]>, GenericAS>, TypePair[1], MemoryOrder]>; - def : Builtin<"atomic_exchange_explicit", - [TypePair[1], PointerType<VolatileType<TypePair[0]>, GenericAS>, TypePair[1], MemoryOrder, MemoryScope]>; + [Void, PointerType<VolatileType<TypePair[0]>, addrspace>, TypePair[1]]>; + defm : BuiltinAtomicExplicit<"atomic_store", + [Void, PointerType<VolatileType<TypePair[0]>, addrspace>, TypePair[1]], BaseExt>; + defm : BuiltinAtomicExplicit<"atomic_load", + [TypePair[1], PointerType<VolatileType<TypePair[0]>, addrspace>], BaseExt>; + defm : BuiltinAtomicExplicit<"atomic_exchange", + [TypePair[1], PointerType<VolatileType<TypePair[0]>, addrspace>, TypePair[1]], BaseExt>; foreach Variant = ["weak", "strong"] in { - def : Builtin<"atomic_compare_exchange_" # Variant, - [Bool, PointerType<VolatileType<TypePair[0]>, GenericAS>, - PointerType<TypePair[1], GenericAS>, TypePair[1]]>; - def : Builtin<"atomic_compare_exchange_" # Variant # "_explicit", - [Bool, PointerType<VolatileType<TypePair[0]>, GenericAS>, - PointerType<TypePair[1], GenericAS>, TypePair[1], MemoryOrder, MemoryOrder]>; - def : Builtin<"atomic_compare_exchange_" # Variant # "_explicit", - [Bool, PointerType<VolatileType<TypePair[0]>, GenericAS>, - PointerType<TypePair[1], GenericAS>, TypePair[1], MemoryOrder, MemoryOrder, MemoryScope]>; + foreach exp_ptr_addrspace = !cond( + !eq(BaseExt, FuncExtOpenCLCGenericAddressSpace): [GenericAS], + !eq(BaseExt, FuncExtOpenCLCNamedAddressSpaceBuiltins): [GlobalAS, LocalAS, PrivateAS]) + in { + let Extension = concatExtension<BaseExt, "__opencl_c_atomic_order_seq_cst __opencl_c_atomic_scope_device">.ret in { + def : Builtin<"atomic_compare_exchange_" # Variant, + [Bool, PointerType<VolatileType<TypePair[0]>, addrspace>, + PointerType<TypePair[1], exp_ptr_addrspace>, TypePair[1]]>; + } + let Extension = concatExtension<BaseExt, "__opencl_c_atomic_scope_device">.ret in { + def : Builtin<"atomic_compare_exchange_" # Variant # "_explicit", + [Bool, PointerType<VolatileType<TypePair[0]>, addrspace>, + PointerType<TypePair[1], exp_ptr_addrspace>, TypePair[1], MemoryOrder, MemoryOrder]>; + } + let Extension = BaseExt in { + def : Builtin<"atomic_compare_exchange_" # Variant # "_explicit", + [Bool, PointerType<VolatileType<TypePair[0]>, addrspace>, + PointerType<TypePair[1], exp_ptr_addrspace>, TypePair[1], MemoryOrder, MemoryOrder, MemoryScope]>; + } + } } } @@ -1084,249 +1118,69 @@ let MinVersion = CL20 in { [AtomicLong, Long, Long], [AtomicULong, ULong, ULong], [AtomicUIntPtr, UIntPtr, PtrDiff]] in { foreach ModOp = ["add", "sub"] in { - def : Builtin<"atomic_fetch_" # ModOp, - [TypePair[1], PointerType<VolatileType<TypePair[0]>, GenericAS>, TypePair[2]]>; - def : Builtin<"atomic_fetch_" # ModOp # "_explicit", - [TypePair[1], PointerType<VolatileType<TypePair[0]>, GenericAS>, TypePair[2], MemoryOrder]>; - def : Builtin<"atomic_fetch_" # ModOp # "_explicit", - [TypePair[1], PointerType<VolatileType<TypePair[0]>, GenericAS>, TypePair[2], MemoryOrder, MemoryScope]>; + defm : BuiltinAtomicExplicit<"atomic_fetch_" # ModOp, + [TypePair[1], PointerType<VolatileType<TypePair[0]>, addrspace>, TypePair[2]], BaseExt>; } } foreach TypePair = [[AtomicInt, Int, Int], [AtomicUInt, UInt, UInt], [AtomicLong, Long, Long], [AtomicULong, ULong, ULong]] in { foreach ModOp = ["or", "xor", "and", "min", "max"] in { - def : Builtin<"atomic_fetch_" # ModOp, - [TypePair[1], PointerType<VolatileType<TypePair[0]>, GenericAS>, TypePair[2]]>; - def : Builtin<"atomic_fetch_" # ModOp # "_explicit", - [TypePair[1], PointerType<VolatileType<TypePair[0]>, GenericAS>, TypePair[2], MemoryOrder]>; - def : Builtin<"atomic_fetch_" # ModOp # "_explicit", - [TypePair[1], PointerType<VolatileType<TypePair[0]>, GenericAS>, TypePair[2], MemoryOrder, MemoryScope]>; + defm : BuiltinAtomicExplicit<"atomic_fetch_" # ModOp, + [TypePair[1], PointerType<VolatileType<TypePair[0]>, addrspace>, TypePair[2]], BaseExt>; } } - def : Builtin<"atomic_flag_clear", - [Void, PointerType<VolatileType<AtomicFlag>, GenericAS>]>; - def : Builtin<"atomic_flag_clear_explicit", - [Void, PointerType<VolatileType<AtomicFlag>, GenericAS>, MemoryOrder]>; - def : Builtin<"atomic_flag_clear_explicit", - [Void, PointerType<VolatileType<AtomicFlag>, GenericAS>, MemoryOrder, MemoryScope]>; + defm : BuiltinAtomicExplicit<"atomic_flag_clear", + [Void, PointerType<VolatileType<AtomicFlag>, addrspace>], BaseExt>; + + defm : BuiltinAtomicExplicit<"atomic_flag_test_and_set", + [Bool, PointerType<VolatileType<AtomicFlag>, addrspace>], BaseExt>; +} + +let MinVersion = CL20 in { + def : Builtin<"atomic_work_item_fence", [Void, MemFenceFlags, MemoryOrder, MemoryScope]>; - def : Builtin<"atomic_flag_test_and_set", - [Bool, PointerType<VolatileType<AtomicFlag>, GenericAS>]>; - def : Builtin<"atomic_flag_test_and_set_explicit", - [Bool, PointerType<VolatileType<AtomicFlag>, GenericAS>, MemoryOrder]>; - def : Builtin<"atomic_flag_test_and_set_explicit", - [Bool, PointerType<VolatileType<AtomicFlag>, GenericAS>, MemoryOrder, MemoryScope]>; + defm : OpenCL2Atomics<GenericAS, FuncExtOpenCLCGenericAddressSpace>; + defm : OpenCL2Atomics<GlobalAS, FuncExtOpenCLCNamedAddressSpaceBuiltins>; + defm : OpenCL2Atomics<LocalAS, FuncExtOpenCLCNamedAddressSpaceBuiltins>; } // The functionality added by cl_ext_float_atomics extension let MinVersion = CL20 in { - let Extension = FuncExtFloatAtomicsFp16GlobalLoadStore in { - def : Builtin<"atomic_store", - [Void, PointerType<VolatileType<AtomicHalf>, GlobalAS>, AtomicHalf]>; - def : Builtin<"atomic_store_explicit", - [Void, PointerType<VolatileType<AtomicHalf>, GlobalAS>, AtomicHalf, MemoryOrder]>; - def : Builtin<"atomic_store_explicit", - [Void, PointerType<VolatileType<AtomicHalf>, GlobalAS>, AtomicHalf, MemoryOrder, MemoryScope]>; - def : Builtin<"atomic_load", - [Half, PointerType<VolatileType<AtomicHalf>, GlobalAS>]>; - def : Builtin<"atomic_load_explicit", - [Half, PointerType<VolatileType<AtomicHalf>, GlobalAS>, MemoryOrder]>; - def : Builtin<"atomic_load_explicit", - [Half, PointerType<VolatileType<AtomicHalf>, GlobalAS>, MemoryOrder, MemoryScope]>; - def : Builtin<"atomic_exchange", - [Half, PointerType<VolatileType<AtomicHalf>, GlobalAS>, Half]>; - def : Builtin<"atomic_exchange_explicit", - [Half, PointerType<VolatileType<AtomicHalf>, GlobalAS>, Half, MemoryOrder]>; - def : Builtin<"atomic_exchange_explicit", - [Half, PointerType<VolatileType<AtomicHalf>, GlobalAS>, Half, MemoryOrder, MemoryScope]>; - } - let Extension = FuncExtFloatAtomicsFp16LocalLoadStore in { - def : Builtin<"atomic_store", - [Void, PointerType<VolatileType<AtomicHalf>, LocalAS>, AtomicHalf]>; - def : Builtin<"atomic_store_explicit", - [Void, PointerType<VolatileType<AtomicHalf>, LocalAS>, AtomicHalf, MemoryOrder]>; - def : Builtin<"atomic_store_explicit", - [Void, PointerType<VolatileType<AtomicHalf>, LocalAS>, AtomicHalf, MemoryOrder, MemoryScope]>; - def : Builtin<"atomic_load", - [Half, PointerType<VolatileType<AtomicHalf>, LocalAS>]>; - def : Builtin<"atomic_load_explicit", - [Half, PointerType<VolatileType<AtomicHalf>, LocalAS>, MemoryOrder]>; - def : Builtin<"atomic_load_explicit", - [Half, PointerType<VolatileType<AtomicHalf>, LocalAS>, MemoryOrder, MemoryScope]>; - def : Builtin<"atomic_exchange", - [Half, PointerType<VolatileType<AtomicHalf>, LocalAS>, Half]>; - def : Builtin<"atomic_exchange_explicit", - [Half, PointerType<VolatileType<AtomicHalf>, LocalAS>, Half, MemoryOrder]>; - def : Builtin<"atomic_exchange_explicit", - [Half, PointerType<VolatileType<AtomicHalf>, LocalAS>, Half, MemoryOrder, MemoryScope]>; - } - let Extension = FuncExtFloatAtomicsFp16GenericLoadStore in { - def : Builtin<"atomic_store", - [Void, PointerType<VolatileType<AtomicHalf>, GenericAS>, AtomicHalf]>; - def : Builtin<"atomic_store_explicit", - [Void, PointerType<VolatileType<AtomicHalf>, GenericAS>, AtomicHalf, MemoryOrder]>; - def : Builtin<"atomic_store_explicit", - [Void, PointerType<VolatileType<AtomicHalf>, GenericAS>, AtomicHalf, MemoryOrder, MemoryScope]>; - def : Builtin<"atomic_load", - [Half, PointerType<VolatileType<AtomicHalf>, GenericAS>]>; - def : Builtin<"atomic_load_explicit", - [Half, PointerType<VolatileType<AtomicHalf>, GenericAS>, MemoryOrder]>; - def : Builtin<"atomic_load_explicit", - [Half, PointerType<VolatileType<AtomicHalf>, GenericAS>, MemoryOrder, MemoryScope]>; - def : Builtin<"atomic_exchange", - [Half, PointerType<VolatileType<AtomicHalf>, GenericAS>, Half]>; - def : Builtin<"atomic_exchange_explicit", - [Half, PointerType<VolatileType<AtomicHalf>, GenericAS>, Half, MemoryOrder]>; - def : Builtin<"atomic_exchange_explicit", - [Half, PointerType<VolatileType<AtomicHalf>, GenericAS>, Half, MemoryOrder, MemoryScope]>; - } - foreach ModOp = ["add", "sub"] in { - let Extension = FuncExtFloatAtomicsFp16GlobalAdd in { - def : Builtin<"atomic_fetch_" # ModOp, - [Half, PointerType<VolatileType<AtomicFloat>, GlobalAS>, Half]>; - def : Builtin<"atomic_fetch_" # ModOp # "_explicit", - [Half, PointerType<VolatileType<AtomicFloat>, GlobalAS>, Half, MemoryOrder]>; - def : Builtin<"atomic_fetch_" # ModOp # "_explicit", - [Half, PointerType<VolatileType<AtomicFloat>, GlobalAS>, Half, MemoryOrder, MemoryScope]>; - } - let Extension = FuncExtFloatAtomicsFp32GlobalAdd in { - def : Builtin<"atomic_fetch_" # ModOp, - [Float, PointerType<VolatileType<AtomicFloat>, GlobalAS>, Float]>; - def : Builtin<"atomic_fetch_" # ModOp # "_explicit", - [Float, PointerType<VolatileType<AtomicFloat>, GlobalAS>, Float, MemoryOrder]>; - def : Builtin<"atomic_fetch_" # ModOp # "_explicit", - [Float, PointerType<VolatileType<AtomicFloat>, GlobalAS>, Float, MemoryOrder, MemoryScope]>; - } - let Extension = FuncExtFloatAtomicsFp64GlobalAdd in { - def : Builtin<"atomic_fetch_" # ModOp, - [Double, PointerType<VolatileType<AtomicDouble>, GlobalAS>, Double]>; - def : Builtin<"atomic_fetch_" # ModOp # "_explicit", - [Double, PointerType<VolatileType<AtomicDouble>, GlobalAS>, Double, MemoryOrder]>; - def : Builtin<"atomic_fetch_" # ModOp # "_explicit", - [Double, PointerType<VolatileType<AtomicDouble>, GlobalAS>, Double, MemoryOrder, MemoryScope]>; - } - let Extension = FuncExtFloatAtomicsFp16LocalAdd in { - def : Builtin<"atomic_fetch_" # ModOp, - [Half, PointerType<VolatileType<AtomicFloat>, LocalAS>, Half]>; - def : Builtin<"atomic_fetch_" # ModOp # "_explicit", - [Half, PointerType<VolatileType<AtomicFloat>, LocalAS>, Half, MemoryOrder]>; - def : Builtin<"atomic_fetch_" # ModOp # "_explicit", - [Half, PointerType<VolatileType<AtomicFloat>, LocalAS>, Half, MemoryOrder, MemoryScope]>; - } - let Extension = FuncExtFloatAtomicsFp32LocalAdd in { - def : Builtin<"atomic_fetch_" # ModOp, - [Float, PointerType<VolatileType<AtomicFloat>, LocalAS>, Float]>; - def : Builtin<"atomic_fetch_" # ModOp # "_explicit", - [Float, PointerType<VolatileType<AtomicFloat>, LocalAS>, Float, MemoryOrder]>; - def : Builtin<"atomic_fetch_" # ModOp # "_explicit", - [Float, PointerType<VolatileType<AtomicFloat>, LocalAS>, Float, MemoryOrder, MemoryScope]>; - } - let Extension = FuncExtFloatAtomicsFp64LocalAdd in { - def : Builtin<"atomic_fetch_" # ModOp, - [Double, PointerType<VolatileType<AtomicDouble>, LocalAS>, Double]>; - def : Builtin<"atomic_fetch_" # ModOp # "_explicit", - [Double, PointerType<VolatileType<AtomicDouble>, LocalAS>, Double, MemoryOrder]>; - def : Builtin<"atomic_fetch_" # ModOp # "_explicit", - [Double, PointerType<VolatileType<AtomicDouble>, LocalAS>, Double, MemoryOrder, MemoryScope]>; - } - let Extension = FuncExtFloatAtomicsFp16GenericAdd in { - def : Builtin<"atomic_fetch_" # ModOp, - [Half, PointerType<VolatileType<AtomicFloat>, GenericAS>, Half]>; - def : Builtin<"atomic_fetch_" # ModOp # "_explicit", - [Half, PointerType<VolatileType<AtomicFloat>, GenericAS>, Half, MemoryOrder]>; - def : Builtin<"atomic_fetch_" # ModOp # "_explicit", - [Half, PointerType<VolatileType<AtomicFloat>, GenericAS>, Half, MemoryOrder, MemoryScope]>; - } - let Extension = FuncExtFloatAtomicsFp32GenericAdd in { - def : Builtin<"atomic_fetch_" # ModOp, - [Float, PointerType<VolatileType<AtomicFloat>, GenericAS>, Float]>; - def : Builtin<"atomic_fetch_" # ModOp # "_explicit", - [Float, PointerType<VolatileType<AtomicFloat>, GenericAS>, Float, MemoryOrder]>; - def : Builtin<"atomic_fetch_" # ModOp # "_explicit", - [Float, PointerType<VolatileType<AtomicFloat>, GenericAS>, Float, MemoryOrder, MemoryScope]>; - } - let Extension = FuncExtFloatAtomicsFp64GenericAdd in { - def : Builtin<"atomic_fetch_" # ModOp, - [Double, PointerType<VolatileType<AtomicDouble>, GenericAS>, Double]>; - def : Builtin<"atomic_fetch_" # ModOp # "_explicit", - [Double, PointerType<VolatileType<AtomicDouble>, GenericAS>, Double, MemoryOrder]>; - def : Builtin<"atomic_fetch_" # ModOp # "_explicit", - [Double, PointerType<VolatileType<AtomicDouble>, GenericAS>, Double, MemoryOrder, MemoryScope]>; - } - } - foreach ModOp = ["min", "max"] in { - let Extension = FuncExtFloatAtomicsFp16GlobalMinMax in { - def : Builtin<"atomic_fetch_" # ModOp, - [Half, PointerType<VolatileType<AtomicHalf>, GlobalAS>, Half]>; - def : Builtin<"atomic_fetch_" # ModOp # "_explicit", - [Half, PointerType<VolatileType<AtomicHalf>, GlobalAS>, Half, MemoryOrder]>; - def : Builtin<"atomic_fetch_" # ModOp # "_explicit", - [Half, PointerType<VolatileType<AtomicHalf>, GlobalAS>, Half, MemoryOrder, MemoryScope]>; - } - let Extension = FuncExtFloatAtomicsFp32GlobalMinMax in { - def : Builtin<"atomic_fetch_" # ModOp, - [Float, PointerType<VolatileType<AtomicFloat>, GlobalAS>, Float]>; - def : Builtin<"atomic_fetch_" # ModOp # "_explicit", - [Float, PointerType<VolatileType<AtomicFloat>, GlobalAS>, Float, MemoryOrder]>; - def : Builtin<"atomic_fetch_" # ModOp # "_explicit", - [Float, PointerType<VolatileType<AtomicFloat>, GlobalAS>, Float, MemoryOrder, MemoryScope]>; - } - let Extension = FuncExtFloatAtomicsFp64GlobalMinMax in { - def : Builtin<"atomic_fetch_" # ModOp, - [Double, PointerType<VolatileType<AtomicDouble>, GlobalAS>, Double]>; - def : Builtin<"atomic_fetch_" # ModOp # "_explicit", - [Double, PointerType<VolatileType<AtomicDouble>, GlobalAS>, Double, MemoryOrder]>; - def : Builtin<"atomic_fetch_" # ModOp # "_explicit", - [Double, PointerType<VolatileType<AtomicDouble>, GlobalAS>, Double, MemoryOrder, MemoryScope]>; - } - let Extension = FuncExtFloatAtomicsFp16LocalMinMax in { - def : Builtin<"atomic_fetch_" # ModOp, - [Half, PointerType<VolatileType<AtomicHalf>, LocalAS>, Half]>; - def : Builtin<"atomic_fetch_" # ModOp # "_explicit", - [Half, PointerType<VolatileType<AtomicHalf>, LocalAS>, Half, MemoryOrder]>; - def : Builtin<"atomic_fetch_" # ModOp # "_explicit", - [Half, PointerType<VolatileType<AtomicHalf>, LocalAS>, Half, MemoryOrder, MemoryScope]>; - } - let Extension = FuncExtFloatAtomicsFp32LocalMinMax in { - def : Builtin<"atomic_fetch_" # ModOp, - [Float, PointerType<VolatileType<AtomicFloat>, LocalAS>, Float]>; - def : Builtin<"atomic_fetch_" # ModOp # "_explicit", - [Float, PointerType<VolatileType<AtomicFloat>, LocalAS>, Float, MemoryOrder]>; - def : Builtin<"atomic_fetch_" # ModOp # "_explicit", - [Float, PointerType<VolatileType<AtomicFloat>, LocalAS>, Float, MemoryOrder, MemoryScope]>; - } - let Extension = FuncExtFloatAtomicsFp64LocalMinMax in { - def : Builtin<"atomic_fetch_" # ModOp, - [Double, PointerType<VolatileType<AtomicDouble>, LocalAS>, Double]>; - def : Builtin<"atomic_fetch_" # ModOp # "_explicit", - [Double, PointerType<VolatileType<AtomicDouble>, LocalAS>, Double, MemoryOrder]>; - def : Builtin<"atomic_fetch_" # ModOp # "_explicit", - [Double, PointerType<VolatileType<AtomicDouble>, LocalAS>, Double, MemoryOrder, MemoryScope]>; - } - let Extension = FuncExtFloatAtomicsFp16GenericMinMax in { - def : Builtin<"atomic_fetch_" # ModOp, - [Half, PointerType<VolatileType<AtomicHalf>, GenericAS>, Half]>; - def : Builtin<"atomic_fetch_" # ModOp # "_explicit", - [Half, PointerType<VolatileType<AtomicHalf>, GenericAS>, Half, MemoryOrder]>; - def : Builtin<"atomic_fetch_" # ModOp # "_explicit", - [Half, PointerType<VolatileType<AtomicHalf>, GenericAS>, Half, MemoryOrder, MemoryScope]>; - } - let Extension = FuncExtFloatAtomicsFp32GenericMinMax in { - def : Builtin<"atomic_fetch_" # ModOp, - [Float, PointerType<VolatileType<AtomicFloat>, GenericAS>, Float]>; - def : Builtin<"atomic_fetch_" # ModOp # "_explicit", - [Float, PointerType<VolatileType<AtomicFloat>, GenericAS>, Float, MemoryOrder]>; - def : Builtin<"atomic_fetch_" # ModOp # "_explicit", - [Float, PointerType<VolatileType<AtomicFloat>, GenericAS>, Float, MemoryOrder, MemoryScope]>; - } - let Extension = FuncExtFloatAtomicsFp64GenericMinMax in { - def : Builtin<"atomic_fetch_" # ModOp, - [Double, PointerType<VolatileType<AtomicDouble>, GenericAS>, Double]>; - def : Builtin<"atomic_fetch_" # ModOp # "_explicit", - [Double, PointerType<VolatileType<AtomicDouble>, GenericAS>, Double, MemoryOrder]>; - def : Builtin<"atomic_fetch_" # ModOp # "_explicit", - [Double, PointerType<VolatileType<AtomicDouble>, GenericAS>, Double, MemoryOrder, MemoryScope]>; + foreach addrspace = [GlobalAS, LocalAS, GenericAS] in { + defvar extension_fp16 = !cast<FunctionExtension>("FuncExtFloatAtomicsFp16" # addrspace # "LoadStore"); + + defm : BuiltinAtomicExplicit<"atomic_store", + [Void, PointerType<VolatileType<AtomicHalf>, addrspace>, AtomicHalf], extension_fp16>; + defm : BuiltinAtomicExplicit<"atomic_load", + [Half, PointerType<VolatileType<AtomicHalf>, addrspace>], extension_fp16>; + defm : BuiltinAtomicExplicit<"atomic_exchange", + [Half, PointerType<VolatileType<AtomicHalf>, addrspace>, Half], extension_fp16>; + + foreach ModOp = ["add", "sub"] in { + defvar extension_fp16 = !cast<FunctionExtension>("FuncExtFloatAtomicsFp16" # addrspace # "Add"); + defvar extension_fp32 = !cast<FunctionExtension>("FuncExtFloatAtomicsFp32" # addrspace # "Add"); + defvar extension_fp64 = !cast<FunctionExtension>("FuncExtFloatAtomicsFp64" # addrspace # "Add"); + + defm : BuiltinAtomicExplicit<"atomic_fetch_" # ModOp, + [Half, PointerType<VolatileType<AtomicFloat>, addrspace>, Half], extension_fp16>; + defm : BuiltinAtomicExplicit<"atomic_fetch_" # ModOp, + [Float, PointerType<VolatileType<AtomicFloat>, addrspace>, Float], extension_fp32>; + defm : BuiltinAtomicExplicit<"atomic_fetch_" # ModOp, + [Double, PointerType<VolatileType<AtomicDouble>, addrspace>, Double], extension_fp64>; + } + + foreach ModOp = ["min", "max"] in { + defvar extension_fp16 = !cast<FunctionExtension>("FuncExtFloatAtomicsFp16" # addrspace # "MinMax"); + defvar extension_fp32 = !cast<FunctionExtension>("FuncExtFloatAtomicsFp32" # addrspace # "MinMax"); + defvar extension_fp64 = !cast<FunctionExtension>("FuncExtFloatAtomicsFp64" # addrspace # "MinMax"); + + defm : BuiltinAtomicExplicit<"atomic_fetch_" # ModOp, + [Half, PointerType<VolatileType<AtomicHalf>, addrspace>, Half], extension_fp16>; + defm : BuiltinAtomicExplicit<"atomic_fetch_" # ModOp, + [Float, PointerType<VolatileType<AtomicFloat>, addrspace>, Float], extension_fp32>; + defm : BuiltinAtomicExplicit<"atomic_fetch_" # ModOp, + [Double, PointerType<VolatileType<AtomicDouble>, addrspace>, Double], extension_fp64>; } } } diff --git a/contrib/llvm-project/clang/lib/Sema/SemaChecking.cpp b/contrib/llvm-project/clang/lib/Sema/SemaChecking.cpp index dfbf4cdc89cb..69dcc3aaaaf3 100644 --- a/contrib/llvm-project/clang/lib/Sema/SemaChecking.cpp +++ b/contrib/llvm-project/clang/lib/Sema/SemaChecking.cpp @@ -1042,9 +1042,15 @@ static bool checkOpenCLBlockArgs(Sema &S, Expr *BlockArg) { } static bool checkOpenCLSubgroupExt(Sema &S, CallExpr *Call) { - if (!S.getOpenCLOptions().isSupported("cl_khr_subgroups", S.getLangOpts())) { + // OpenCL device can support extension but not the feature as extension + // requires subgroup independent forward progress, but subgroup independent + // forward progress is optional in OpenCL C 3.0 __opencl_c_subgroups feature. + if (!S.getOpenCLOptions().isSupported("cl_khr_subgroups", S.getLangOpts()) && + !S.getOpenCLOptions().isSupported("__opencl_c_subgroups", + S.getLangOpts())) { S.Diag(Call->getBeginLoc(), diag::err_opencl_requires_extension) - << 1 << Call->getDirectCallee() << "cl_khr_subgroups"; + << 1 << Call->getDirectCallee() + << "cl_khr_subgroups or __opencl_c_subgroups"; return true; } return false; diff --git a/contrib/llvm-project/clang/lib/Sema/SemaDecl.cpp b/contrib/llvm-project/clang/lib/Sema/SemaDecl.cpp index cbd9df4d6a7b..bcadf4139046 100644 --- a/contrib/llvm-project/clang/lib/Sema/SemaDecl.cpp +++ b/contrib/llvm-project/clang/lib/Sema/SemaDecl.cpp @@ -15319,24 +15319,7 @@ void Sema::AddKnownFunctionAttributes(FunctionDecl *FD) { if (!FD->hasAttr<AllocAlignAttr>()) FD->addAttr(AllocAlignAttr::CreateImplicit(Context, ParamIdx(1, FD), FD->getLocation())); - LLVM_FALLTHROUGH; - case Builtin::BIcalloc: - case Builtin::BImalloc: - case Builtin::BImemalign: - case Builtin::BIrealloc: - case Builtin::BIstrdup: - case Builtin::BIstrndup: { - if (!FD->hasAttr<AssumeAlignedAttr>()) { - unsigned NewAlign = Context.getTargetInfo().getNewAlign() / - Context.getTargetInfo().getCharWidth(); - IntegerLiteral *Alignment = IntegerLiteral::Create( - Context, Context.MakeIntValue(NewAlign, Context.UnsignedIntTy), - Context.UnsignedIntTy, FD->getLocation()); - FD->addAttr(AssumeAlignedAttr::CreateImplicit( - Context, Alignment, /*Offset=*/nullptr, FD->getLocation())); - } break; - } default: break; } |