From d3a44f68854e3e093662117621c607e3361716ec Mon Sep 17 00:00:00 2001 From: Justin Lebar Date: Tue, 5 Apr 2016 18:26:20 +0000 Subject: [CUDA] Add -fcuda-flush-denormals-to-zero. Summary: Setting this flag causes all functions are annotated with the "nvvm-f32ftz" = "true" attribute. In addition, we annotate the module with "nvvm-reflect-ftz" set to 0 or 1, depending on whether -cuda-flush-denormals-to-zero is set. This is read by the NVVMReflect pass. Reviewers: tra, rnk Subscribers: cfe-commits Differential Revision: http://reviews.llvm.org/D18671 llvm-svn: 265435 --- clang/lib/CodeGen/CodeGenModule.cpp | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'clang/lib/CodeGen/CodeGenModule.cpp') diff --git a/clang/lib/CodeGen/CodeGenModule.cpp b/clang/lib/CodeGen/CodeGenModule.cpp index 11f5bea..f525246 100644 --- a/clang/lib/CodeGen/CodeGenModule.cpp +++ b/clang/lib/CodeGen/CodeGenModule.cpp @@ -472,6 +472,14 @@ void CodeGenModule::Release() { getModule().addModuleFlag(llvm::Module::Override, "Cross-DSO CFI", 1); } + if (LangOpts.CUDAIsDevice && getTarget().getTriple().isNVPTX()) { + // Indicate whether __nvvm_reflect should be configured to flush denormal + // floating point values to 0. (This corresponds to its "__CUDA_FTZ" + // property.) + getModule().addModuleFlag(llvm::Module::Override, "nvvm-reflect-ftz", + LangOpts.CUDADeviceFlushDenormalsToZero ? 1 : 0); + } + if (uint32_t PLevel = Context.getLangOpts().PICLevel) { llvm::PICLevel::Level PL = llvm::PICLevel::Default; switch (PLevel) { -- cgit v1.1