diff --git a/clang/lib/Basic/Targets/NVPTX.cpp b/clang/lib/Basic/Targets/NVPTX.cpp
--- a/clang/lib/Basic/Targets/NVPTX.cpp
+++ b/clang/lib/Basic/Targets/NVPTX.cpp
@@ -142,6 +142,20 @@
   // we need all classes to be defined on both the host and device.
   MaxAtomicInlineWidth = HostTarget->getMaxAtomicInlineWidth();
 
+  // For certain builtin types support on the host target, claim they are
+  // support to pass the compilation of the host code during the device-side
+  // compilation.
+  //
+  // FIXME: As the side effect, we also accept `__float128` uses in the device
+  // code, but use 'double' as the underlying type, so host/device
+  // representation of the type is different. This is similar to what happens to
+  // long double.
+
+  if (HostTarget->hasFloat128Type()) {
+    HasFloat128 = true;
+    Float128Format = DoubleFormat;
+  }
+
   // Properties intentionally not copied from host:
   // - LargeArrayMinWidth, LargeArrayAlign: Not visible across the
   //   host/device boundary.
diff --git a/clang/test/SemaCUDA/amdgpu-f128.cu b/clang/test/SemaCUDA/f128.cu
rename from clang/test/SemaCUDA/amdgpu-f128.cu
rename to clang/test/SemaCUDA/f128.cu
--- a/clang/test/SemaCUDA/amdgpu-f128.cu
+++ b/clang/test/SemaCUDA/f128.cu
@@ -1,4 +1,5 @@
 // RUN: %clang_cc1 -triple amdgcn-amd-amdhsa -aux-triple x86_64-unknown-linux-gnu -fcuda-is-device -fsyntax-only -verify %s
+// RUN: %clang_cc1 -triple nvptx64 -aux-triple x86_64-unknown-linux-gnu -fcuda-is-device -fsyntax-only -verify %s
 
 // expected-no-diagnostics
 typedef __float128 f128_t;