3 files changed, 5 insertions, 6 deletions
diff --git a/clang/lib/CodeGen/CGCall.cpp b/clang/lib/CodeGen/CGCall.cpp
index fcc8a3e5f64..f60136c2f17 100644
--- a/clang/lib/CodeGen/CGCall.cpp
+++ b/clang/lib/CodeGen/CGCall.cpp
@@ -1800,7 +1800,7 @@ void CodeGenModule::ConstructDefaultFnAttrList(StringRef Name, bool HasOptnone,
     FuncAttrs.addAttribute(llvm::Attribute::NoUnwind);
 
     // Respect -fcuda-flush-denormals-to-zero.
-    if (getLangOpts().CUDADeviceFlushDenormalsToZero)
+    if (CodeGenOpts.FlushDenorm)
       FuncAttrs.addAttribute("nvptx-f32ftz", "true");
   }
 }
diff --git a/clang/lib/CodeGen/CodeGenModule.cpp b/clang/lib/CodeGen/CodeGenModule.cpp
index 627a33d8b55..ecdf78d4b34 100644
--- a/clang/lib/CodeGen/CodeGenModule.cpp
+++ b/clang/lib/CodeGen/CodeGenModule.cpp
@@ -526,7 +526,7 @@ void CodeGenModule::Release() {
     // floating point values to 0.  (This corresponds to its "__CUDA_FTZ"
     // property.)
     getModule().addModuleFlag(llvm::Module::Override, "nvvm-reflect-ftz",
-                              LangOpts.CUDADeviceFlushDenormalsToZero ? 1 : 0);
+                              CodeGenOpts.FlushDenorm ? 1 : 0);
   }
 
   // Emit OpenCL specific module metadata: OpenCL/SPIR version.
diff --git a/clang/lib/Frontend/CompilerInvocation.cpp b/clang/lib/Frontend/CompilerInvocation.cpp
index a494b27a39b..5878cce772b 100644
--- a/clang/lib/Frontend/CompilerInvocation.cpp
+++ b/clang/lib/Frontend/CompilerInvocation.cpp
@@ -690,7 +690,9 @@ static bool ParseCodeGenArgs(CodeGenOptions &Opts, ArgList &Args, InputKind IK,
                         Args.hasArg(OPT_cl_unsafe_math_optimizations) ||
                         Args.hasArg(OPT_cl_fast_relaxed_math));
   Opts.Reassociate = Args.hasArg(OPT_mreassociate);
-  Opts.FlushDenorm = Args.hasArg(OPT_cl_denorms_are_zero);
+  Opts.FlushDenorm = Args.hasArg(OPT_cl_denorms_are_zero) ||
+                     (Args.hasArg(OPT_fcuda_is_device) &&
+                      Args.hasArg(OPT_fcuda_flush_denormals_to_zero));
   Opts.CorrectlyRoundedDivSqrt =
       Args.hasArg(OPT_cl_fp32_correctly_rounded_divide_sqrt);
   Opts.UniformWGSize =
@@ -2191,9 +2193,6 @@ static void ParseLangArgs(LangOptions &Opts, ArgList &Args, InputKind IK,
   if (Args.hasArg(OPT_fno_cuda_host_device_constexpr))
     Opts.CUDAHostDeviceConstexpr = 0;
 
-  if (Opts.CUDAIsDevice && Args.hasArg(OPT_fcuda_flush_denormals_to_zero))
-    Opts.CUDADeviceFlushDenormalsToZero = 1;
-
   if (Opts.CUDAIsDevice && Args.hasArg(OPT_fcuda_approx_transcendentals))
     Opts.CUDADeviceApproxTranscendentals = 1;