Index: lib/CodeGen/CGOpenMPRuntimeNVPTX.cpp
===================================================================
--- lib/CodeGen/CGOpenMPRuntimeNVPTX.cpp
+++ lib/CodeGen/CGOpenMPRuntimeNVPTX.cpp
@@ -598,6 +598,11 @@
                                                   WorkerFunctionState &WST) {
   CGBuilderTy &Bld = CGF.Builder;
 
+  // For data sharing, initialize the stack for master and workers.
+  CGF.EmitRuntimeCall(
+      createNVPTXRuntimeFunction(
+          OMPRTL_NVPTX__kmpc_data_sharing_init_stack));
+
   llvm::BasicBlock *WorkerBB = CGF.createBasicBlock(".worker");
   llvm::BasicBlock *MasterCheckBB = CGF.createBasicBlock(".mastercheck");
   llvm::BasicBlock *MasterBB = CGF.createBasicBlock(".master");
@@ -626,11 +631,6 @@
   CGF.EmitRuntimeCall(
       createNVPTXRuntimeFunction(OMPRTL_NVPTX__kmpc_kernel_init), Args);
 
-  // For data sharing, we need to initialize the stack.
-  CGF.EmitRuntimeCall(
-      createNVPTXRuntimeFunction(
-          OMPRTL_NVPTX__kmpc_data_sharing_init_stack));
-
   emitGenericVarsProlog(CGF, WST.Loc);
 }
 
Index: test/OpenMP/nvptx_data_sharing.cpp
===================================================================
--- test/OpenMP/nvptx_data_sharing.cpp
+++ test/OpenMP/nvptx_data_sharing.cpp
@@ -30,8 +30,9 @@
 // CK1: {{.*}}define void @__omp_offloading{{.*}}test_ds{{.*}}()
 // CK1: [[SHAREDARGS1:%.+]] = alloca i8**
 // CK1: [[SHAREDARGS2:%.+]] = alloca i8**
-// CK1: call void @__kmpc_kernel_init
 // CK1: call void @__kmpc_data_sharing_init_stack
+// CK1: call void @__omp_offloading{{.*}}_worker()
+// CK1: call void @__kmpc_kernel_init
 // CK1: [[GLOBALSTACK:%.+]] = call i8* @__kmpc_data_sharing_push_stack(i64 8, i16 0)
 // CK1: [[GLOBALSTACK2:%.+]] = bitcast i8* [[GLOBALSTACK]] to %struct._globalized_locals_ty*
 // CK1: [[A:%.+]] = getelementptr inbounds %struct._globalized_locals_ty, %struct._globalized_locals_ty* [[GLOBALSTACK2]], i32 0, i32 0