Index: include/clang/AST/Expr.h =================================================================== --- include/clang/AST/Expr.h +++ include/clang/AST/Expr.h @@ -2919,7 +2919,7 @@ // This is only meaningful for operations on floating point types and 0 // otherwise. - unsigned FPFeatures : 1; + unsigned FPFeatures : 2; SourceLocation OpLoc; enum { LHS, RHS, END_EXPR }; @@ -3077,8 +3077,8 @@ // Get the FP contractability status of this operator. Only meaningful for // operations on floating point types. - bool isFPContractable() const { - return FPOptions(FPFeatures).isFPContractable(); + bool isFPContractableWithinStatement() const { + return FPOptions(FPFeatures).allowFPContractWithinStatement(); } protected: Index: include/clang/AST/ExprCXX.h =================================================================== --- include/clang/AST/ExprCXX.h +++ include/clang/AST/ExprCXX.h @@ -118,7 +118,9 @@ // Get the FP contractability status of this operator. Only meaningful for // operations on floating point types. - bool isFPContractable() const { return FPFeatures.isFPContractable(); } + bool isFPContractableWithinStatement() const { + return FPFeatures.allowFPContractWithinStatement(); + } friend class ASTStmtReader; friend class ASTStmtWriter; Index: include/clang/Basic/LangOptions.h =================================================================== --- include/clang/Basic/LangOptions.h +++ include/clang/Basic/LangOptions.h @@ -88,6 +88,12 @@ MSVC2015 = 19 }; + enum FPContractModeKind { + FPC_Off, // Form fused FP ops only where result will not be affected. + FPC_On, // Form fused FP ops according to FP_CONTRACT rules. + FPC_Fast // Aggressively fuse FP ops (E.g. FMA). + }; + public: /// \brief Set of enabled sanitizers. SanitizerSet Sanitize; @@ -175,22 +181,35 @@ /// \brief Floating point control options class FPOptions { public: - FPOptions() : fp_contract(0) {} + FPOptions() : fp_contract(LangOptions::FPC_Off) {} - explicit FPOptions(uint64_t I) : fp_contract(I) {} + // Used for serializing. + explicit FPOptions(uint64_t I) + : fp_contract(static_cast(I)) {} FPOptions(const LangOptions &LangOpts) - : fp_contract(LangOpts.DefaultFPContract) {} + : fp_contract(LangOpts.getDefaultFPContractMode()) {} - void setFPContractable(bool V) { fp_contract = V; } - bool isFPContractable() const { return fp_contract; } + bool allowFPContractWithinStatement() const { + return fp_contract == LangOptions::FPC_On; + } + bool allowFPContractAcrossStatement() const { + return fp_contract == LangOptions::FPC_Fast; + } + void setAllowFPContractWithinStatement() { + fp_contract = LangOptions::FPC_On; + } + void setAllowFPContractAcrossStatement() { + fp_contract = LangOptions::FPC_Fast; + } + void setDisallowFPContract() { fp_contract = LangOptions::FPC_Off; } /// Used to serialize this. uint64_t getInt() const { return fp_contract; } private: /// Adjust BinaryOperator::FPFeatures to match the bit-field size of this. - unsigned fp_contract : 1; + LangOptions::FPContractModeKind fp_contract : 2; }; /// \brief Describes the kind of translation unit being processed. Index: include/clang/Basic/LangOptions.def =================================================================== --- include/clang/Basic/LangOptions.def +++ include/clang/Basic/LangOptions.def @@ -216,7 +216,8 @@ BENIGN_LANGOPT(SpellChecking , 1, 1, "spell-checking") LANGOPT(SinglePrecisionConstants , 1, 0, "treating double-precision floating point constants as single precision constants") LANGOPT(FastRelaxedMath , 1, 0, "OpenCL fast relaxed math") -LANGOPT(DefaultFPContract , 1, 0, "FP_CONTRACT") +/// \brief FP_CONTRACT mode (on/off/fast). +ENUM_LANGOPT(DefaultFPContractMode, FPContractModeKind, 2, FPC_Off, "FP contraction type") LANGOPT(NoBitFieldTypeAlign , 1, 0, "bit-field type alignment") LANGOPT(HexagonQdsp6Compat , 1, 0, "hexagon-qdsp6 backward compatibility") LANGOPT(ObjCAutoRefCount , 1, 0, "Objective-C automated reference counting") Index: include/clang/Frontend/CodeGenOptions.h =================================================================== --- include/clang/Frontend/CodeGenOptions.h +++ include/clang/Frontend/CodeGenOptions.h @@ -69,12 +69,6 @@ LocalExecTLSModel }; - enum FPContractModeKind { - FPC_Off, // Form fused FP ops only where result will not be affected. - FPC_On, // Form fused FP ops according to FP_CONTRACT rules. - FPC_Fast // Aggressively fuse FP ops (E.g. FMA). - }; - enum StructReturnConventionKind { SRCK_Default, // No special option was passed. SRCK_OnStack, // Small structs on the stack (-fpcc-struct-return). Index: include/clang/Frontend/CodeGenOptions.def =================================================================== --- include/clang/Frontend/CodeGenOptions.def +++ include/clang/Frontend/CodeGenOptions.def @@ -65,8 +65,6 @@ CODEGENOPT(EmitGcovNotes , 1, 0) ///< Emit coverage "notes" files, aka GCNO. CODEGENOPT(EmitOpenCLArgMetadata , 1, 0) ///< Emit OpenCL kernel arg metadata. CODEGENOPT(EmulatedTLS , 1, 0) ///< Set when -femulated-tls is enabled. -/// \brief FP_CONTRACT mode (on/off/fast). -ENUM_CODEGENOPT(FPContractMode, FPContractModeKind, 2, FPC_On) /// \brief Embed Bitcode mode (off/all/bitcode/marker). ENUM_CODEGENOPT(EmbedBitcode, EmbedBitcodeKind, 2, Embed_Off) CODEGENOPT(ForbidGuardVariables , 1, 0) ///< Issue errors if C++ guard variables Index: lib/CodeGen/BackendUtil.cpp =================================================================== --- lib/CodeGen/BackendUtil.cpp +++ lib/CodeGen/BackendUtil.cpp @@ -556,14 +556,14 @@ .Default(llvm::FloatABI::Default); // Set FP fusion mode. - switch (CodeGenOpts.getFPContractMode()) { - case CodeGenOptions::FPC_Off: + switch (LangOpts.getDefaultFPContractMode()) { + case LangOptions::FPC_Off: Options.AllowFPOpFusion = llvm::FPOpFusion::Strict; break; - case CodeGenOptions::FPC_On: + case LangOptions::FPC_On: Options.AllowFPOpFusion = llvm::FPOpFusion::Standard; break; - case CodeGenOptions::FPC_Fast: + case LangOptions::FPC_Fast: Options.AllowFPOpFusion = llvm::FPOpFusion::Fast; break; } Index: lib/CodeGen/CGExprScalar.cpp =================================================================== --- lib/CodeGen/CGExprScalar.cpp +++ lib/CodeGen/CGExprScalar.cpp @@ -2663,12 +2663,7 @@ "Only fadd/fsub can be the root of an fmuladd."); // Check whether this op is marked as fusable. - if (!op.FPFeatures.isFPContractable()) - return nullptr; - - // Check whether -ffp-contract=on. (If -ffp-contract=off/fast, fusing is - // either disabled, or handled entirely by the LLVM backend). - if (CGF.CGM.getCodeGenOpts().getFPContractMode() != CodeGenOptions::FPC_On) + if (!op.FPFeatures.allowFPContractWithinStatement()) return nullptr; // We have a potentially fusable op. Look for a mul on one of the operands. Index: lib/Frontend/CompilerInvocation.cpp =================================================================== --- lib/Frontend/CompilerInvocation.cpp +++ lib/Frontend/CompilerInvocation.cpp @@ -811,18 +811,6 @@ } } - if (Arg *A = Args.getLastArg(OPT_ffp_contract)) { - StringRef Val = A->getValue(); - if (Val == "fast") - Opts.setFPContractMode(CodeGenOptions::FPC_Fast); - else if (Val == "on") - Opts.setFPContractMode(CodeGenOptions::FPC_On); - else if (Val == "off") - Opts.setFPContractMode(CodeGenOptions::FPC_Off); - else - Diags.Report(diag::err_drv_invalid_value) << A->getAsString(Args) << Val; - } - if (Arg *A = Args.getLastArg(OPT_fdenormal_fp_math_EQ)) { StringRef Val = A->getValue(); if (Val == "ieee") @@ -1625,7 +1613,7 @@ Opts.ZVector = 0; Opts.CXXOperatorNames = 1; Opts.LaxVectorConversions = 0; - Opts.DefaultFPContract = 1; + Opts.setDefaultFPContractMode(LangOptions::FPC_On); Opts.NativeHalfType = 1; Opts.NativeHalfArgsAndReturns = 1; // Include default header file for OpenCL. @@ -1636,6 +1624,9 @@ Opts.CUDA = IK == IK_CUDA || IK == IK_PreprocessedCuda || LangStd == LangStandard::lang_cuda; + if (Opts.CUDA) + // Set default FP_CONTRACT to FAST. + Opts.setDefaultFPContractMode(LangOptions::FPC_Fast); Opts.RenderScript = IK == IK_RenderScript; if (Opts.RenderScript) { @@ -2263,6 +2254,18 @@ Args.hasArg(OPT_cl_unsafe_math_optimizations) || Args.hasArg(OPT_cl_fast_relaxed_math); + if (Arg *A = Args.getLastArg(OPT_ffp_contract)) { + StringRef Val = A->getValue(); + if (Val == "fast") + Opts.setDefaultFPContractMode(LangOptions::FPC_Fast); + else if (Val == "on") + Opts.setDefaultFPContractMode(LangOptions::FPC_On); + else if (Val == "off") + Opts.setDefaultFPContractMode(LangOptions::FPC_Off); + else + Diags.Report(diag::err_drv_invalid_value) << A->getAsString(Args) << Val; + } + Opts.RetainCommentsFromSystemHeaders = Args.hasArg(OPT_fretain_comments_from_system_headers); @@ -2516,10 +2519,6 @@ // triple used for host compilation. if (LangOpts.CUDAIsDevice) Res.getTargetOpts().HostTriple = Res.getFrontendOpts().AuxTriple; - - // Set default FP_CONTRACT to FAST. - if (!Args.hasArg(OPT_ffp_contract)) - Res.getCodeGenOpts().setFPContractMode(CodeGenOptions::FPC_Fast); } // FIXME: Override value name discarding when asan or msan is used because the Index: lib/Sema/SemaAttr.cpp =================================================================== --- lib/Sema/SemaAttr.cpp +++ lib/Sema/SemaAttr.cpp @@ -450,13 +450,16 @@ void Sema::ActOnPragmaFPContract(tok::OnOffSwitch OOS) { switch (OOS) { case tok::OOS_ON: - FPFeatures.setFPContractable(true); + FPFeatures.setAllowFPContractWithinStatement(); break; case tok::OOS_OFF: - FPFeatures.setFPContractable(false); + FPFeatures.setDisallowFPContract(); break; case tok::OOS_DEFAULT: - FPFeatures.setFPContractable(getLangOpts().DefaultFPContract); + if (getLangOpts().getDefaultFPContractMode() == LangOptions::FPC_On) + FPFeatures.setAllowFPContractWithinStatement(); + else + FPFeatures.setDisallowFPContract(); break; } }