[CUDA][HIP] Fix host used external kernel in archive

For -fgpu-rdc, a host function may call an external kernel
which is defined in an archive of bitcode. Since this external
kernel is only referenced in host function, the device
bitcode does not contain reference to this external
kernel, then the linker will not try to resolve this external
kernel in the archive.

To fix this issue, host-used external kernels and device
variables are tracked. A global array containing pointers
to these external kernels and variables is emitted which
serves as an artificial references to the external kernels
and variables used by host.

Reviewed by: Artem Belevich

Differential Revision: https://reviews.llvm.org/D123441

1 files changed, 24 insertions, 0 deletions

diff --git a/clang/lib/CodeGen/CodeGenModule.cpp b/clang/lib/CodeGen/CodeGenModule.cpp
index b251a4a7df3d..76094c73a927 100644
--- a/clang/lib/CodeGen/CodeGenModule.cpp
+++ b/clang/lib/CodeGen/CodeGenModule.cpp
@@ -579,6 +579,30 @@ void CodeGenModule::Release() {
     }
   }
 
+  // Emit a global array containing all external kernels or device variables
+  // used by host functions and mark it as used for CUDA/HIP. This is necessary
+  // to get kernels or device variables in archives linked in even if these
+  // kernels or device variables are only used in host functions.
+  if (!Context.CUDAExternalDeviceDeclODRUsedByHost.empty()) {
+    SmallVector<llvm::Constant *, 8> UsedArray;
+    for (auto D : Context.CUDAExternalDeviceDeclODRUsedByHost) {
+      GlobalDecl GD;
+      if (auto *FD = dyn_cast<FunctionDecl>(D))
+        GD = GlobalDecl(FD, KernelReferenceKind::Kernel);
+      else
+        GD = GlobalDecl(D);
+      UsedArray.push_back(llvm::ConstantExpr::getPointerBitCastOrAddrSpaceCast(
+          GetAddrOfGlobal(GD), Int8PtrTy));
+    }
+
+    llvm::ArrayType *ATy = llvm::ArrayType::get(Int8PtrTy, UsedArray.size());
+
+    auto *GV = new llvm::GlobalVariable(
+        getModule(), ATy, false, llvm::GlobalValue::AppendingLinkage,
+        llvm::ConstantArray::get(ATy, UsedArray), "gpu.used.external");
+    addCompilerUsedGlobal(GV);
+  }
+
   emitLLVMUsed();
   if (SanStats)
     SanStats->finish();