diff --git a/clang/lib/Driver/ToolChains/Cuda.cpp b/clang/lib/Driver/ToolChains/Cuda.cpp
index a2b6db69b9284..9f15612355e6c 100644
--- a/clang/lib/Driver/ToolChains/Cuda.cpp
+++ b/clang/lib/Driver/ToolChains/Cuda.cpp
@@ -946,6 +946,15 @@ void CudaToolChain::addClangTargetOptions(
 
     if (DriverArgs.hasArg(options::OPT_fsycl_fp32_prec_sqrt))
       CC1Args.push_back("-fcuda-prec-sqrt");
+
+    bool FastRelaxedMath = DriverArgs.hasFlag(
+        options::OPT_ffast_math, options::OPT_fno_fast_math, false);
+    bool UnsafeMathOpt =
+        DriverArgs.hasFlag(options::OPT_funsafe_math_optimizations,
+                           options::OPT_fno_unsafe_math_optimizations, false);
+    if (FastRelaxedMath || UnsafeMathOpt)
+      CC1Args.append({"-mllvm", "--nvptx-prec-divf32=0", "-mllvm",
+                      "--nvptx-prec-sqrtf32=0"});
   } else {
     CC1Args.append(
         {"-fcuda-is-device", "-mllvm", "-enable-memcpyopt-without-libcalls"});
diff --git a/clang/test/Driver/sycl-nvptx-fast-math.cpp b/clang/test/Driver/sycl-nvptx-fast-math.cpp
new file mode 100644
index 0000000000000..b4593a3700148
--- /dev/null
+++ b/clang/test/Driver/sycl-nvptx-fast-math.cpp
@@ -0,0 +1,18 @@
+// REQUIRES: nvptx-registered-target
+
+// RUN: %clang -### -nocudalib \
+// RUN:   -fsycl -fsycl-targets=nvptx64-nvidia-cuda %s 2>&1 \
+// RUN: | FileCheck --check-prefix=CHECK-DEFAULT %s
+
+// RUN: %clang -### -nocudalib \
+// RUN:   -fsycl -fsycl-targets=nvptx64-nvidia-cuda -ffast-math %s 2>&1 \
+// RUN: | FileCheck --check-prefix=CHECK-FAST %s
+
+// RUN: %clang -### -nocudalib \
+// RUN:   -fsycl -fsycl-targets=nvptx64-nvidia-cuda -funsafe-math-optimizations %s 2>&1 \
+// RUN: | FileCheck --check-prefix=CHECK-FAST %s
+
+// CHECK-FAST: "-mllvm" "--nvptx-prec-divf32=0" "-mllvm" "--nvptx-prec-sqrtf32=0"
+
+// CHECK-DEFAULT-NOT: "nvptx-prec-divf32=0"
+// CHECK-DEFAULT-NOT: "nvptx-prec-sqrtf32=0"