[CUDA] Allow static variables in __host__ __device__ functions, so long as they're never codegen'ed for device.

[rnk]

lgtm

clang/include/clang/Basic/DiagnosticSemaKinds.td

def err_cuda_device_exceptions : Error<
   "cannot use '%0' in "
   "%select{__device__|__global__|__host__|__host__ __device__}1 function">;
 def err_dynamic_var_init : Error<
     "dynamic initialization is not supported for "
     "__device__, __constant__, and __shared__ variables.">;
 def err_shared_var_init : Error<
     "initialization is not supported for __shared__ variables.">;
 def err_device_static_local_var : Error<
-    "Within a __device__/__global__ function, "
-    "only __shared__ variables may be marked \"static\"">;
+    "within a %select{__device__|__global__|__host__|__host__ __device__}0 "
+    "function, only __shared__ variables may be marked 'static'">;
 def err_cuda_vla : Error<
     "cannot use variable-length arrays in "
     "%select{__device__|__global__|__host__|__host__ __device__}0 functions">;
 def err_cuda_extern_shared : Error<"__shared__ variable %0 cannot be 'extern'">;
 def err_cuda_host_shared : Error<
     "__shared__ local variables not allowed in "
     "%select{__device__|__global__|__host__|__host__ __device__}0 functions">;
 def err_cuda_nonglobal_constant : Error<"__constant__ variables must be global">;

clang/lib/Sema/SemaDecl.cpp

if (FunctionDecl *FD =
       if (Attr *A = getDLLAttr(FD)) {
         auto *NewAttr = cast<InheritableAttr>(A->clone(getASTContext()));
         NewAttr->setInherited(true);
         VD->addAttr(NewAttr);
       }
       // CUDA E.2.9.4: Within the body of a __device__ or __global__
       // function, only __shared__ variables may be declared with
       // static storage class.
-      if (getLangOpts().CUDA && getLangOpts().CUDAIsDevice &&
-          (FD->hasAttr<CUDADeviceAttr>() || FD->hasAttr<CUDAGlobalAttr>()) &&
-          !VD->hasAttr<CUDASharedAttr>()) {
-        Diag(VD->getLocation(), diag::err_device_static_local_var);
+      if (getLangOpts().CUDA && !VD->hasAttr<CUDASharedAttr>() &&
+          CUDADiagIfDeviceCode(VD->getLocation(),
+                               diag::err_device_static_local_var)
+              << CurrentCUDATarget())
         VD->setInvalidDecl();
-      }
-    }
-  }
 
   // Perform check for initializers of device-side global variables.
   // CUDA allows empty constructors as initializers (see E.2.3.1, CUDA
   // 7.5). We must also apply the same checks to all __shared__
   // variables whether they are local or not. CUDA also allows
   // constant initializers for __constant__ and __device__ variables.
   if (getLangOpts().CUDA) {
     const Expr *Init = VD->getInit();
     if (Init && VD->hasGlobalStorage()) {
       if (VD->hasAttr<CUDADeviceAttr>() || VD->hasAttr<CUDAConstantAttr>() ||
           VD->hasAttr<CUDASharedAttr>()) {
-        assert((!VD->isStaticLocal() || VD->hasAttr<CUDASharedAttr>()));
+        assert(!VD->isStaticLocal() || VD->hasAttr<CUDASharedAttr>());
         bool AllowedInit = false;
         if (const CXXConstructExpr *CE = dyn_cast<CXXConstructExpr>(Init))
           AllowedInit =
               isEmptyCudaConstructor(VD->getLocation(), CE->getConstructor());
         // We'll allow constant initializers even if it's a non-empty
         // constructor according to CUDA rules. This deviates from NVCC,
         // but allows us to handle things like constexpr constructors.
         if (!AllowedInit &&

clang/test/SemaCUDA/device-var-init.cu

__device__ void df_sema() {
   static __shared__ NCFS s_ncfs;
   // expected-error@-1 {{initialization is not supported for __shared__ variables.}}
   static __shared__ UC s_uc;
   // expected-error@-1 {{initialization is not supported for __shared__ variables.}}
   static __shared__ NED s_ned;
   // expected-error@-1 {{initialization is not supported for __shared__ variables.}}
 
   static __device__ int ds;
-  // expected-error@-1 {{Within a __device__/__global__ function, only __shared__ variables may be marked "static"}}
+  // expected-error@-1 {{within a __device__ function, only __shared__ variables may be marked 'static'}}
   static __constant__ int dc;
-  // expected-error@-1 {{Within a __device__/__global__ function, only __shared__ variables may be marked "static"}}
+  // expected-error@-1 {{within a __device__ function, only __shared__ variables may be marked 'static'}}
   static int v;
-  // expected-error@-1 {{Within a __device__/__global__ function, only __shared__ variables may be marked "static"}}
+  // expected-error@-1 {{within a __device__ function, only __shared__ variables may be marked 'static'}}
 }

clang/test/SemaCUDA/static-vars-hd.cu

+// RUN: %clang_cc1 -fcxx-exceptions -fcuda-is-device -S -o /dev/null -verify %s
+// RUN: %clang_cc1 -fcxx-exceptions -S -o /dev/null -D HOST -verify %s
+
+#include "Inputs/cuda.h"
+
+#ifdef HOST
+// expected-no-diagnostics
+#endif
+
+__host__ __device__ void f() {
+  static int x = 42;
+#ifndef HOST
+  // expected-error@-2 {{within a __host__ __device__ function, only __shared__ variables may be marked 'static'}}
+#endif
+}
+
+inline __host__ __device__ void g() {
+  static int x = 42; // no error on device because this is never codegen'ed there.
+}
+void call_g() { g(); }