Index: cfe/trunk/include/clang/Basic/LangOptions.def
===================================================================
--- cfe/trunk/include/clang/Basic/LangOptions.def
+++ cfe/trunk/include/clang/Basic/LangOptions.def
@@ -162,6 +162,7 @@
 LANGOPT(OpenMP            , 1, 0, "OpenMP support")
 LANGOPT(CUDAIsDevice      , 1, 0, "Compiling for CUDA device")
 LANGOPT(CUDAAllowHostCallsFromHostDevice, 1, 0, "Allow host device functions to call host functions")
+LANGOPT(CUDADisableTargetCallChecks, 1, 0, "Disable checks for call targets (host, device, etc.)")
 
 LANGOPT(AssumeSaneOperatorNew , 1, 1, "implicit __attribute__((malloc)) for C++'s new operators")
 LANGOPT(SizedDeallocation , 1, 0, "enable sized deallocation functions")
Index: cfe/trunk/include/clang/Driver/CC1Options.td
===================================================================
--- cfe/trunk/include/clang/Driver/CC1Options.td
+++ cfe/trunk/include/clang/Driver/CC1Options.td
@@ -610,6 +610,9 @@
 def fcuda_allow_host_calls_from_host_device : Flag<["-"],
     "fcuda-allow-host-calls-from-host-device">,
   HelpText<"Allow host device functions to call host functions">;
+def fcuda_disable_target_call_checks : Flag<["-"],
+    "fcuda-disable-target-call-checks">,
+  HelpText<"Disable all cross-target (host, device, etc.) call checks in CUDA">;
 
 } // let Flags = [CC1Option]
 
Index: cfe/trunk/lib/Frontend/CompilerInvocation.cpp
===================================================================
--- cfe/trunk/lib/Frontend/CompilerInvocation.cpp
+++ cfe/trunk/lib/Frontend/CompilerInvocation.cpp
@@ -1375,6 +1375,9 @@
   if (Args.hasArg(OPT_fcuda_allow_host_calls_from_host_device))
     Opts.CUDAAllowHostCallsFromHostDevice = 1;
 
+  if (Args.hasArg(OPT_fcuda_disable_target_call_checks))
+    Opts.CUDADisableTargetCallChecks = 1;
+
   if (Opts.ObjC1) {
     if (Arg *arg = Args.getLastArg(OPT_fobjc_runtime_EQ)) {
       StringRef value = arg->getValue();
Index: cfe/trunk/lib/Sema/SemaCUDA.cpp
===================================================================
--- cfe/trunk/lib/Sema/SemaCUDA.cpp
+++ cfe/trunk/lib/Sema/SemaCUDA.cpp
@@ -62,6 +62,11 @@
 
 bool Sema::CheckCUDATarget(const FunctionDecl *Caller,
                            const FunctionDecl *Callee) {
+  // The CUDADisableTargetCallChecks short-circuits this check: we assume all
+  // cross-target calls are valid.
+  if (getLangOpts().CUDADisableTargetCallChecks)
+    return false;
+
   CUDAFunctionTarget CallerTarget = IdentifyCUDATarget(Caller),
                      CalleeTarget = IdentifyCUDATarget(Callee);
 
Index: cfe/trunk/test/SemaCUDA/function-target-disabled-check.cu
===================================================================
--- cfe/trunk/test/SemaCUDA/function-target-disabled-check.cu
+++ cfe/trunk/test/SemaCUDA/function-target-disabled-check.cu
@@ -0,0 +1,26 @@
+// Test that we can disable cross-target call checks in Sema with the
+// -fcuda-disable-target-call-checks flag. Without this flag we'd get a bunch
+// of errors here, since there are invalid cross-target calls present.
+
+// RUN: %clang_cc1 -fsyntax-only -verify %s -fcuda-disable-target-call-checks
+// RUN: %clang_cc1 -fsyntax-only -fcuda-is-device -verify %s -fcuda-disable-target-call-checks
+
+// expected-no-diagnostics
+
+#define __device__ __attribute__((device))
+#define __global__ __attribute__((global))
+#define __host__ __attribute__((host))
+
+__attribute__((host)) void h1();
+
+__attribute__((device)) void d1() {
+  h1();
+}
+
+__attribute__((host)) void h2() {
+  d1();
+}
+
+__attribute__((global)) void g1() {
+  h2();
+}