[CUDA][HIP] Fix device template variables

Currently clang does not emit device template variables
instantiated only in host functions, however, nvcc is
able to do that:

https://godbolt.org/z/fneEfferY

This patch fixes this issue by refactoring and extending
the existing mechanism for emitting static device
var ODR-used by host only. Basically clang records
device variables ODR-used by host code and force
them to be emitted in device compilation. The existing
mechanism makes sure these device variables ODR-used
by host code are added to llvm.compiler-used, therefore
they are guaranteed not to be deleted.

It also fixes non-ODR-use of static device variable by host code
causing static device variable to be emitted and registered,
which should not.

Reviewed by: Artem Belevich

Differential Revision: https://reviews.llvm.org/D102237

1 files changed, 2 insertions, 2 deletions

diff --git a/clang/lib/CodeGen/CodeGenModule.cpp b/clang/lib/CodeGen/CodeGenModule.cpp
index c61da1c980a2..e3c843c8e9d3 100644
--- a/clang/lib/CodeGen/CodeGenModule.cpp
+++ b/clang/lib/CodeGen/CodeGenModule.cpp
@@ -2362,8 +2362,8 @@ void CodeGenModule::EmitDeferred() {
   }
 
   // Emit CUDA/HIP static device variables referenced by host code only.
-  if (getLangOpts().CUDA)
-    for (auto V : getContext().CUDAStaticDeviceVarReferencedByHost)
+  if (getLangOpts().CUDA && getLangOpts().CUDAIsDevice)
+    for (const auto *V : getContext().CUDADeviceVarODRUsedByHost)
       DeferredDeclsToEmit.push_back(V);
 
   // Stop if we're out of both deferred vtables and deferred declarations.