diff options
Diffstat (limited to 'clang/lib')
| -rw-r--r-- | clang/lib/CodeGen/CGCall.cpp | 3 | ||||
| -rw-r--r-- | clang/lib/CodeGen/CGExprScalar.cpp | 9 | ||||
| -rw-r--r-- | clang/lib/Driver/Tools.cpp | 3 | ||||
| -rw-r--r-- | clang/lib/Frontend/CompilerInvocation.cpp | 2 |
4 files changed, 15 insertions, 2 deletions
diff --git a/clang/lib/CodeGen/CGCall.cpp b/clang/lib/CodeGen/CGCall.cpp index 242b5962070..fdd83ea2720 100644 --- a/clang/lib/CodeGen/CGCall.cpp +++ b/clang/lib/CodeGen/CGCall.cpp @@ -1734,6 +1734,9 @@ void CodeGenModule::ConstructAttributeList( llvm::utostr(CodeGenOpts.SSPBufferSize)); FuncAttrs.addAttribute("no-signed-zeros-fp-math", llvm::toStringRef(CodeGenOpts.NoSignedZeros)); + FuncAttrs.addAttribute( + "correctly-rounded-divide-sqrt-fp-math", + llvm::toStringRef(CodeGenOpts.CorrectlyRoundedDivSqrt)); if (CodeGenOpts.StackRealignment) FuncAttrs.addAttribute("stackrealign"); diff --git a/clang/lib/CodeGen/CGExprScalar.cpp b/clang/lib/CodeGen/CGExprScalar.cpp index 343d3fb5aa6..f3936873359 100644 --- a/clang/lib/CodeGen/CGExprScalar.cpp +++ b/clang/lib/CodeGen/CGExprScalar.cpp @@ -2276,8 +2276,13 @@ Value *ScalarExprEmitter::EmitDiv(const BinOpInfo &Ops) { if (Ops.LHS->getType()->isFPOrFPVectorTy()) { llvm::Value *Val = Builder.CreateFDiv(Ops.LHS, Ops.RHS, "div"); - if (CGF.getLangOpts().OpenCL) { - // OpenCL 1.1 7.4: minimum accuracy of single precision / is 2.5ulp + if (CGF.getLangOpts().OpenCL && + !CGF.CGM.getCodeGenOpts().CorrectlyRoundedDivSqrt) { + // OpenCL v1.1 s7.4: minimum accuracy of single precision / is 2.5ulp + // OpenCL v1.2 s5.6.4.2: The -cl-fp32-correctly-rounded-divide-sqrt + // build option allows an application to specify that single precision + // floating-point divide (x/y and 1/x) and sqrt used in the program + // source are correctly rounded. llvm::Type *ValTy = Val->getType(); if (ValTy->isFloatTy() || (isa<llvm::VectorType>(ValTy) && diff --git a/clang/lib/Driver/Tools.cpp b/clang/lib/Driver/Tools.cpp index a9d940f2a67..141d12e9a2f 100644 --- a/clang/lib/Driver/Tools.cpp +++ b/clang/lib/Driver/Tools.cpp @@ -5282,6 +5282,9 @@ void Clang::ConstructJob(Compilation &C, const JobAction &JA, if (Args.getLastArg(options::OPT_cl_denorms_are_zero)) { CmdArgs.push_back("-cl-denorms-are-zero"); } + if (Args.getLastArg(options::OPT_cl_fp32_correctly_rounded_divide_sqrt)) { + CmdArgs.push_back("-cl-fp32-correctly-rounded-divide-sqrt"); + } // Forward -f options with positive and negative forms; we translate // these by hand. diff --git a/clang/lib/Frontend/CompilerInvocation.cpp b/clang/lib/Frontend/CompilerInvocation.cpp index bbb7f2b7356..e19b612b6e7 100644 --- a/clang/lib/Frontend/CompilerInvocation.cpp +++ b/clang/lib/Frontend/CompilerInvocation.cpp @@ -572,6 +572,8 @@ static bool ParseCodeGenArgs(CodeGenOptions &Opts, ArgList &Args, InputKind IK, Opts.NoSignedZeros = (Args.hasArg(OPT_fno_signed_zeros) || Args.hasArg(OPT_cl_no_signed_zeros)); Opts.FlushDenorm = Args.hasArg(OPT_cl_denorms_are_zero); + Opts.CorrectlyRoundedDivSqrt = + Args.hasArg(OPT_cl_fp32_correctly_rounded_divide_sqrt); Opts.ReciprocalMath = Args.hasArg(OPT_freciprocal_math); Opts.NoZeroInitializedInBSS = Args.hasArg(OPT_mno_zero_initialized_in_bss); Opts.BackendOptions = Args.getAllArgValues(OPT_backend_option); |
