[PATCH] D95901: [CUDA][HIP] Fix device variable linkage

[Artem Belevich via Phabricator via cfe-commits]

tra added a comment.

> For -fgpu-rdc, shadow variables should not be internalized, otherwise they cannot be accessed by other TUs. 
> This is necessary because the shadow variable of external device variables are always emitted as undefined symbols, which need to resolve to a global symbols.

Does it mean that we always internalize shadows *now*, before this patch? That would indeed be wrong. Shadow's visibility should be the same as that of a variable without a `__device__`.

Next question is whether the behavior should be different for `-fgpu-rdc` vs non-RDC.  I think shadows should behave the same regardless of RDC mode and make things work closer to what users would expect from regular C++ code. We already have mechanisms to uniquify the variables, if necessary, so we don't need to use visibility to avoid cross-TU linking conflicts.



================
Comment at: clang/lib/AST/ASTContext.cpp:11437-11443
+  return ((!getLangOpts().GPURelocatableDeviceCode &&
+           ((D->hasAttr<CUDADeviceAttr>() &&
+             !D->getAttr<CUDADeviceAttr>()->isImplicit()) ||
+            (D->hasAttr<CUDAConstantAttr>() &&
+             !D->getAttr<CUDAConstantAttr>()->isImplicit()))) ||
           D->hasAttr<HIPManagedAttr>()) &&
          isa<VarDecl>(D) && cast<VarDecl>(D)->getStorageClass() == SC_Static;
----------------
I can't parse it. :-( Perhaps we can split it.


CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D95901/new/

https://reviews.llvm.org/D95901