Index: lib/CodeGen/CGOpenMPRuntimeNVPTX.cpp
===================================================================
--- lib/CodeGen/CGOpenMPRuntimeNVPTX.cpp
+++ lib/CodeGen/CGOpenMPRuntimeNVPTX.cpp
@@ -801,6 +801,11 @@
   // Wait for parallel work
   syncCTAThreads(CGF);
 
+  // For data sharing, we need to initialize the stack for workers.
+  CGF.EmitRuntimeCall(
+      createNVPTXRuntimeFunction(
+          OMPRTL_NVPTX__kmpc_data_sharing_init_stack));
+
   Address WorkFn =
       CGF.CreateDefaultAlignTempAlloca(CGF.Int8PtrTy, /*Name=*/"work_fn");
   Address ExecStatus =
Index: test/OpenMP/nvptx_data_sharing.cpp
===================================================================
--- test/OpenMP/nvptx_data_sharing.cpp
+++ test/OpenMP/nvptx_data_sharing.cpp
@@ -27,6 +27,11 @@
   }
 }
 
+/// ========= In the worker function ========= ///
+// CK1: {{.*}}define internal void @__omp_offloading{{.*}}test_ds{{.*}}_worker()
+// CK1: call void @llvm.nvvm.barrier0()
+// CK1: call void @__kmpc_data_sharing_init_stack
+
 /// ========= In the kernel function ========= ///
 
 // CK1: {{.*}}define void @__omp_offloading{{.*}}test_ds{{.*}}()