diff --git a/clang/include/clang/Basic/LangOptions.def b/clang/include/clang/Basic/LangOptions.def
--- a/clang/include/clang/Basic/LangOptions.def
+++ b/clang/include/clang/Basic/LangOptions.def
@@ -231,6 +231,7 @@
 LANGOPT(OpenMPCUDABlocksPerSM  , 32, 0, "Number of blocks per SM for CUDA devices.")
 LANGOPT(OpenMPCUDAReductionBufNum , 32, 1024, "Number of the reduction records in the intermediate reduction buffer used for the teams reductions.")
 LANGOPT(OpenMPOptimisticCollapse  , 1, 0, "Use at most 32 bits to represent the collapsed loop nest counter.")
+LANGOPT(OpenMPCUDATargetParallel, 1, 0, "Support parallel execution of target region on Cuda-based devices.")
 LANGOPT(RenderScript      , 1, 0, "RenderScript")
 
 LANGOPT(CUDAIsDevice      , 1, 0, "compiling for CUDA device")
diff --git a/clang/include/clang/Driver/Options.td b/clang/include/clang/Driver/Options.td
--- a/clang/include/clang/Driver/Options.td
+++ b/clang/include/clang/Driver/Options.td
@@ -1687,6 +1687,12 @@
   Flags<[CC1Option, NoArgumentUnused, HelpHidden]>;
 def fno_openmp_optimistic_collapse : Flag<["-"], "fno-openmp-optimistic-collapse">, Group<f_Group>,
   Flags<[NoArgumentUnused, HelpHidden]>;
+def fopenmp_cuda_parallel_target_regions : Flag<["-"], "fopenmp-cuda-parallel-target-regions">, Group<f_Group>,
+  Flags<[CC1Option, NoArgumentUnused, HelpHidden]>,
+  HelpText<"Support parallel execution of target regions on Cuda-based devices.">;
+def fno_openmp_cuda_parallel_target_regions : Flag<["-"], "fno-openmp-cuda-parallel-target-regions">, Group<f_Group>,
+  Flags<[NoArgumentUnused, HelpHidden]>,
+  HelpText<"Support only serial execution of target regions on Cuda-based devices.">;
 def static_openmp: Flag<["-"], "static-openmp">,
   HelpText<"Use the static host OpenMP runtime while linking.">;
 def fno_optimize_sibling_calls : Flag<["-"], "fno-optimize-sibling-calls">, Group<f_Group>;
diff --git a/clang/lib/CodeGen/CGOpenMPRuntimeNVPTX.cpp b/clang/lib/CodeGen/CGOpenMPRuntimeNVPTX.cpp
--- a/clang/lib/CodeGen/CGOpenMPRuntimeNVPTX.cpp
+++ b/clang/lib/CodeGen/CGOpenMPRuntimeNVPTX.cpp
@@ -85,6 +85,9 @@
   /// Call to void* __kmpc_data_sharing_coalesced_push_stack(size_t size,
   /// int16_t UseSharedMemory);
   OMPRTL_NVPTX__kmpc_data_sharing_coalesced_push_stack,
+  /// Call to void* __kmpc_data_sharing_push_stack(size_t size, int16_t
+  /// UseSharedMemory);
+  OMPRTL_NVPTX__kmpc_data_sharing_push_stack,
   /// Call to void __kmpc_data_sharing_pop_stack(void *a);
   OMPRTL_NVPTX__kmpc_data_sharing_pop_stack,
   /// Call to void __kmpc_begin_sharing_variables(void ***args,
@@ -1753,6 +1756,16 @@
         FnTy, /*Name=*/"__kmpc_data_sharing_coalesced_push_stack");
     break;
   }
+  case OMPRTL_NVPTX__kmpc_data_sharing_push_stack: {
+    // Build void *__kmpc_data_sharing_push_stack(size_t size, int16_t
+    // UseSharedMemory);
+    llvm::Type *TypeParams[] = {CGM.SizeTy, CGM.Int16Ty};
+    auto *FnTy =
+        llvm::FunctionType::get(CGM.VoidPtrTy, TypeParams, /*isVarArg=*/false);
+    RTLFn = CGM.CreateRuntimeFunction(
+        FnTy, /*Name=*/"__kmpc_data_sharing_push_stack");
+    break;
+  }
   case OMPRTL_NVPTX__kmpc_data_sharing_pop_stack: {
     // Build void __kmpc_data_sharing_pop_stack(void *a);
     llvm::Type *TypeParams[] = {CGM.VoidPtrTy};
@@ -2210,7 +2223,7 @@
       GlobalRecCastAddr = Phi;
       I->getSecond().GlobalRecordAddr = Phi;
       I->getSecond().IsInSPMDModeFlag = IsSPMD;
-    } else if (IsInTTDRegion) {
+    } else if (!CGM.getLangOpts().OpenMPCUDATargetParallel && IsInTTDRegion) {
       assert(GlobalizedRecords.back().Records.size() < 2 &&
              "Expected less than 2 globalized records: one for target and one "
              "for teams.");
@@ -2283,12 +2296,16 @@
     } else {
       // TODO: allow the usage of shared memory to be controlled by
       // the user, for now, default to global.
+      bool UseSharedMemory =
+          IsInTTDRegion && GlobalRecordSize <= SharedMemorySize;
       llvm::Value *GlobalRecordSizeArg[] = {
           llvm::ConstantInt::get(CGM.SizeTy, GlobalRecordSize),
-          CGF.Builder.getInt16(/*UseSharedMemory=*/0)};
+          CGF.Builder.getInt16(UseSharedMemory ? 1 : 0)};
       llvm::Value *GlobalRecValue = CGF.EmitRuntimeCall(
           createNVPTXRuntimeFunction(
-              OMPRTL_NVPTX__kmpc_data_sharing_coalesced_push_stack),
+              IsInTTDRegion
+                  ? OMPRTL_NVPTX__kmpc_data_sharing_push_stack
+                  : OMPRTL_NVPTX__kmpc_data_sharing_coalesced_push_stack),
           GlobalRecordSizeArg);
       GlobalRecCastAddr = Bld.CreatePointerBitCastOrAddrSpaceCast(
           GlobalRecValue, GlobalRecPtrTy);
@@ -2435,7 +2452,7 @@
                 OMPRTL_NVPTX__kmpc_data_sharing_pop_stack),
             CGF.EmitCastToVoidPtr(I->getSecond().GlobalRecordAddr));
         CGF.EmitBlock(ExitBB);
-      } else if (IsInTTDRegion) {
+      } else if (!CGM.getLangOpts().OpenMPCUDATargetParallel && IsInTTDRegion) {
         assert(GlobalizedRecords.back().RegionCounter > 0 &&
                "region counter must be > 0.");
         --GlobalizedRecords.back().RegionCounter;
@@ -5085,7 +5102,8 @@
 }
 
 void CGOpenMPRuntimeNVPTX::clear() {
-  if (!GlobalizedRecords.empty()) {
+  if (!GlobalizedRecords.empty() &&
+      !CGM.getLangOpts().OpenMPCUDATargetParallel) {
     ASTContext &C = CGM.getContext();
     llvm::SmallVector<const GlobalPtrSizeRecsTy *, 4> GlobalRecs;
     llvm::SmallVector<const GlobalPtrSizeRecsTy *, 4> SharedRecs;
diff --git a/clang/lib/Driver/ToolChains/Clang.cpp b/clang/lib/Driver/ToolChains/Clang.cpp
--- a/clang/lib/Driver/ToolChains/Clang.cpp
+++ b/clang/lib/Driver/ToolChains/Clang.cpp
@@ -5257,6 +5257,13 @@
                        options::OPT_fno_openmp_cuda_mode, /*Default=*/false))
         CmdArgs.push_back("-fopenmp-cuda-mode");
 
+      // When in OpenMP offloading mode with NVPTX target, forward
+      // cuda-parallel-target-regions flag
+      if (Args.hasFlag(options::OPT_fopenmp_cuda_parallel_target_regions,
+                       options::OPT_fno_openmp_cuda_parallel_target_regions,
+                       /*Default=*/true))
+        CmdArgs.push_back("-fopenmp-cuda-parallel-target-regions");
+
       // When in OpenMP offloading mode with NVPTX target, check if full runtime
       // is required.
       if (Args.hasFlag(options::OPT_fopenmp_cuda_force_full_runtime,
diff --git a/clang/lib/Frontend/CompilerInvocation.cpp b/clang/lib/Frontend/CompilerInvocation.cpp
--- a/clang/lib/Frontend/CompilerInvocation.cpp
+++ b/clang/lib/Frontend/CompilerInvocation.cpp
@@ -3195,6 +3195,12 @@
   Opts.OpenMPCUDAMode = Opts.OpenMPIsDevice && (T.isNVPTX() || T.isAMDGCN()) &&
                         Args.hasArg(options::OPT_fopenmp_cuda_mode);
 
+  // Set CUDA support for parallel execution of target regions for OpenMP target
+  // NVPTX/AMDGCN if specified in options.
+  Opts.OpenMPCUDATargetParallel =
+      Opts.OpenMPIsDevice && (T.isNVPTX() || T.isAMDGCN()) &&
+      Args.hasArg(options::OPT_fopenmp_cuda_parallel_target_regions);
+
   // Set CUDA mode for OpenMP target NVPTX/AMDGCN if specified in options
   Opts.OpenMPCUDAForceFullRuntime =
       Opts.OpenMPIsDevice && (T.isNVPTX() || T.isAMDGCN()) &&
diff --git a/clang/test/OpenMP/nvptx_data_sharing.cpp b/clang/test/OpenMP/nvptx_data_sharing.cpp
--- a/clang/test/OpenMP/nvptx_data_sharing.cpp
+++ b/clang/test/OpenMP/nvptx_data_sharing.cpp
@@ -2,7 +2,8 @@
 ///==========================================================================///
 
 // RUN: %clang_cc1 -verify -fopenmp -x c++ -triple powerpc64le-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm-bc %s -o %t-ppc-host.bc
-// RUN: %clang_cc1 -verify -fopenmp -x c++ -triple nvptx64-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o - -disable-llvm-optzns | FileCheck %s --check-prefix CK1
+// RUN: %clang_cc1 -verify -fopenmp -x c++ -triple nvptx64-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o - -disable-llvm-optzns | FileCheck %s --check-prefix CK1 --check-prefix SEQ
+// RUN: %clang_cc1 -verify -fopenmp -x c++ -triple nvptx64-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o - -disable-llvm-optzns -fopenmp-cuda-parallel-target-regions | FileCheck %s --check-prefix CK1 --check-prefix PAR
 
 // expected-no-diagnostics
 
@@ -26,11 +27,11 @@
     }
   }
 }
-// CK1: [[MEM_TY:%.+]] = type { [128 x i8] }
-// CK1-DAG: [[SHARED_GLOBAL_RD:@.+]] = common addrspace(3) global [[MEM_TY]] zeroinitializer
-// CK1-DAG: [[KERNEL_PTR:@.+]] = internal addrspace(3) global i8* null
-// CK1-DAG: [[KERNEL_SIZE:@.+]] = internal unnamed_addr constant i64 8
-// CK1-DAG: [[KERNEL_SHARED:@.+]] = internal unnamed_addr constant i16 1
+// SEQ: [[MEM_TY:%.+]] = type { [128 x i8] }
+// SEQ-DAG: [[SHARED_GLOBAL_RD:@.+]] = common addrspace(3) global [[MEM_TY]] zeroinitializer
+// SEQ-DAG: [[KERNEL_PTR:@.+]] = internal addrspace(3) global i8* null
+// SEQ-DAG: [[KERNEL_SIZE:@.+]] = internal unnamed_addr constant i64 8
+// SEQ-DAG: [[KERNEL_SHARED:@.+]] = internal unnamed_addr constant i16 1
 
 /// ========= In the worker function ========= ///
 // CK1: {{.*}}define internal void @__omp_offloading{{.*}}test_ds{{.*}}_worker()
@@ -44,11 +45,12 @@
 // CK1: [[SHAREDARGS2:%.+]] = alloca i8**
 // CK1: call void @__kmpc_kernel_init
 // CK1: call void @__kmpc_data_sharing_init_stack
-// CK1: [[SHARED_MEM_FLAG:%.+]] = load i16, i16* [[KERNEL_SHARED]],
-// CK1: [[SIZE:%.+]] = load i64, i64* [[KERNEL_SIZE]],
-// CK1: call void @__kmpc_get_team_static_memory(i16 0, i8* addrspacecast (i8 addrspace(3)* getelementptr inbounds ([[MEM_TY]], [[MEM_TY]] addrspace(3)* [[SHARED_GLOBAL_RD]], i32 0, i32 0, i32 0) to i8*), i64 [[SIZE]], i16 [[SHARED_MEM_FLAG]], i8** addrspacecast (i8* addrspace(3)* [[KERNEL_PTR]] to i8**))
-// CK1: [[KERNEL_RD:%.+]] = load i8*, i8* addrspace(3)* [[KERNEL_PTR]],
-// CK1: [[GLOBALSTACK:%.+]] = getelementptr inbounds i8, i8* [[KERNEL_RD]], i64 0
+// SEQ: [[SHARED_MEM_FLAG:%.+]] = load i16, i16* [[KERNEL_SHARED]],
+// SEQ: [[SIZE:%.+]] = load i64, i64* [[KERNEL_SIZE]],
+// SEQ: call void @__kmpc_get_team_static_memory(i16 0, i8* addrspacecast (i8 addrspace(3)* getelementptr inbounds ([[MEM_TY]], [[MEM_TY]] addrspace(3)* [[SHARED_GLOBAL_RD]], i32 0, i32 0, i32 0) to i8*), i64 [[SIZE]], i16 [[SHARED_MEM_FLAG]], i8** addrspacecast (i8* addrspace(3)* [[KERNEL_PTR]] to i8**))
+// SEQ: [[KERNEL_RD:%.+]] = load i8*, i8* addrspace(3)* [[KERNEL_PTR]],
+// SEQ: [[GLOBALSTACK:%.+]] = getelementptr inbounds i8, i8* [[KERNEL_RD]], i64 0
+// PAR: [[GLOBALSTACK:%.+]] = call i8* @__kmpc_data_sharing_push_stack(i{{32|64}} 8, i16 1)
 // 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
 // CK1: [[B:%.+]] = getelementptr inbounds %struct._globalized_locals_ty, %struct._globalized_locals_ty* [[GLOBALSTACK2]], i32 0, i32 1
@@ -75,8 +77,9 @@
 // CK1: call void @__kmpc_barrier_simple_spmd(%struct.ident_t* null, i32 0)
 // CK1: call void @__kmpc_barrier_simple_spmd(%struct.ident_t* null, i32 0)
 // CK1: call void @__kmpc_end_sharing_variables()
-// CK1: [[SHARED_MEM_FLAG:%.+]] = load i16, i16* [[KERNEL_SHARED]],
-// CK1: call void @__kmpc_restore_team_static_memory(i16 0, i16 [[SHARED_MEM_FLAG]])
+// SEQ: [[SHARED_MEM_FLAG:%.+]] = load i16, i16* [[KERNEL_SHARED]],
+// SEQ: call void @__kmpc_restore_team_static_memory(i16 0, i16 [[SHARED_MEM_FLAG]])
+// PAR: call void @__kmpc_data_sharing_pop_stack(i8* [[GLOBALSTACK]])
 // CK1: call void @__kmpc_kernel_deinit(i16 1)
 
 /// ========= In the data sharing wrapper function ========= ///
diff --git a/clang/test/OpenMP/nvptx_distribute_parallel_generic_mode_codegen.cpp b/clang/test/OpenMP/nvptx_distribute_parallel_generic_mode_codegen.cpp
--- a/clang/test/OpenMP/nvptx_distribute_parallel_generic_mode_codegen.cpp
+++ b/clang/test/OpenMP/nvptx_distribute_parallel_generic_mode_codegen.cpp
@@ -1,9 +1,12 @@
 // Test target codegen - host bc file has to be created first.
 // RUN: %clang_cc1 -verify -fopenmp -fopenmp-version=45 -x c++ -triple powerpc64le-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm-bc %s -o %t-ppc-host.bc
-// RUN: %clang_cc1 -verify -fopenmp -fopenmp-version=45 -x c++ -triple nvptx64-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o - -disable-llvm-optzns | FileCheck %s --check-prefix CHECK --check-prefix CHECK-64
+// RUN: %clang_cc1 -verify -fopenmp -fopenmp-version=45 -x c++ -triple nvptx64-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o - -disable-llvm-optzns | FileCheck %s --check-prefix CHECK --check-prefix CHECK-64 --check-prefix SEQ
+// RUN: %clang_cc1 -verify -fopenmp -fopenmp-version=45 -x c++ -triple nvptx64-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o - -disable-llvm-optzns -fopenmp-cuda-parallel-target-regions | FileCheck %s --check-prefix CHECK --check-prefix CHECK-64 --check-prefix PAR
 // RUN: %clang_cc1 -verify -fopenmp -fopenmp-version=45 -x c++ -triple i386-unknown-unknown -fopenmp-targets=nvptx-nvidia-cuda -emit-llvm-bc %s -o %t-x86-host.bc
-// RUN: %clang_cc1 -verify -fopenmp -fopenmp-version=45 -x c++ -triple nvptx-unknown-unknown -fopenmp-targets=nvptx-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-x86-host.bc -o - -disable-llvm-optzns | FileCheck %s --check-prefix CHECK --check-prefix CHECK-32
-// RUN: %clang_cc1 -verify -fopenmp -fopenmp-version=45 -fexceptions -fcxx-exceptions -x c++ -triple nvptx-unknown-unknown -fopenmp-targets=nvptx-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-x86-host.bc -o - -disable-llvm-optzns | FileCheck %s --check-prefix CHECK --check-prefix CHECK-32
+// RUN: %clang_cc1 -verify -fopenmp -fopenmp-version=45 -x c++ -triple nvptx-unknown-unknown -fopenmp-targets=nvptx-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-x86-host.bc -o - -disable-llvm-optzns | FileCheck %s --check-prefix CHECK --check-prefix CHECK-32 --check-prefix SEQ
+// RUN: %clang_cc1 -verify -fopenmp -fopenmp-version=45 -fexceptions -fcxx-exceptions -x c++ -triple nvptx-unknown-unknown -fopenmp-targets=nvptx-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-x86-host.bc -o - -disable-llvm-optzns | FileCheck %s --check-prefix CHECK --check-prefix CHECK-32 --check-prefix SEQ
+// RUN: %clang_cc1 -verify -fopenmp -fopenmp-version=45 -x c++ -triple nvptx-unknown-unknown -fopenmp-targets=nvptx-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-x86-host.bc -o - -disable-llvm-optzns -fopenmp-cuda-parallel-target-regions | FileCheck %s --check-prefix CHECK --check-prefix CHECK-32 --check-prefix PAR
+// RUN: %clang_cc1 -verify -fopenmp -fopenmp-version=45 -fexceptions -fcxx-exceptions -x c++ -triple nvptx-unknown-unknown -fopenmp-targets=nvptx-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-x86-host.bc -o - -disable-llvm-optzns -fopenmp-cuda-parallel-target-regions | FileCheck %s --check-prefix CHECK --check-prefix CHECK-32 --check-prefix PAR
 // expected-no-diagnostics
 #ifndef HEADER
 #define HEADER
@@ -21,19 +24,20 @@
   return 0;
 }
 
-// CHECK: [[MEM_TY:%.+]] = type { [128 x i8] }
-// CHECK-DAG: [[SHARED_GLOBAL_RD:@.+]] = common addrspace(3) global [[MEM_TY]] zeroinitializer
-// CHECK-DAG: [[KERNEL_PTR:@.+]] = internal addrspace(3) global i8* null
-// CHECK-DAG: [[KERNEL_SIZE:@.+]] = internal unnamed_addr constant i{{64|32}} 40
-// CHECK-DAG: [[KERNEL_SHARED:@.+]] = internal unnamed_addr constant i16 1
-// CHECK-DAG: @__omp_offloading_{{.*}}_main_l17_exec_mode = weak constant i8 0
-
-// CHECK: define weak void @__omp_offloading_{{.*}}_main_l17([10 x i32]* nonnull align 4 dereferenceable(40) %{{.+}}, [10 x i32]* nonnull align 4 dereferenceable(40) %{{.+}}, i32* nonnull align 4 dereferenceable(4) %{{.+}}, i{{64|32}} %{{.+}}, [10 x i32]* nonnull align 4 dereferenceable(40) %{{.+}})
-// CHECK: [[SHARED:%.+]] = load i16, i16* [[KERNEL_SHARED]],
-// CHECK: [[SIZE:%.+]] = load i{{64|32}}, i{{64|32}}* [[KERNEL_SIZE]],
-// CHECK: call void @__kmpc_get_team_static_memory(i16 1, i8* addrspacecast (i8 addrspace(3)* getelementptr inbounds ([[MEM_TY]], [[MEM_TY]] addrspace(3)* [[SHARED_GLOBAL_RD]], i32 0, i32 0, i32 0) to i8*), i{{64|32}} [[SIZE]], i16 [[SHARED]], i8** addrspacecast (i8* addrspace(3)* [[KERNEL_PTR]] to i8**))
-// CHECK: [[PTR:%.+]] = load i8*, i8* addrspace(3)* [[KERNEL_PTR]],
-// CHECK: [[GEP:%.+]] = getelementptr inbounds i8, i8* [[PTR]], i{{64|32}} 0
+// SEQ: [[MEM_TY:%.+]] = type { [128 x i8] }
+// SEQ-DAG: [[SHARED_GLOBAL_RD:@.+]] = common addrspace(3) global [[MEM_TY]] zeroinitializer
+// SEQ-DAG: [[KERNEL_PTR:@.+]] = internal addrspace(3) global i8* null
+// SEQ-DAG: [[KERNEL_SIZE:@.+]] = internal unnamed_addr constant i{{64|32}} 40
+// SEQ-DAG: [[KERNEL_SHARED:@.+]] = internal unnamed_addr constant i16 1
+// CHECK-DAG: @__omp_offloading_{{.*}}_main_l20_exec_mode = weak constant i8 0
+
+// CHECK: define weak void @__omp_offloading_{{.*}}_main_l20([10 x i32]* nonnull align 4 dereferenceable(40) %{{.+}}, [10 x i32]* nonnull align 4 dereferenceable(40) %{{.+}}, i32* nonnull align 4 dereferenceable(4) %{{.+}}, i{{64|32}} %{{.+}}, [10 x i32]* nonnull align 4 dereferenceable(40) %{{.+}})
+// SEQ: [[SHARED:%.+]] = load i16, i16* [[KERNEL_SHARED]],
+// SEQ: [[SIZE:%.+]] = load i{{64|32}}, i{{64|32}}* [[KERNEL_SIZE]],
+// SEQ: call void @__kmpc_get_team_static_memory(i16 1, i8* addrspacecast (i8 addrspace(3)* getelementptr inbounds ([[MEM_TY]], [[MEM_TY]] addrspace(3)* [[SHARED_GLOBAL_RD]], i32 0, i32 0, i32 0) to i8*), i{{64|32}} [[SIZE]], i16 [[SHARED]], i8** addrspacecast (i8* addrspace(3)* [[KERNEL_PTR]] to i8**))
+// SEQ: [[PTR:%.+]] = load i8*, i8* addrspace(3)* [[KERNEL_PTR]],
+// SEQ: [[GEP:%.+]] = getelementptr inbounds i8, i8* [[PTR]], i{{64|32}} 0
+// PAR: [[GEP:%.+]] = call i8* @__kmpc_data_sharing_push_stack(i{{32|64}} 40, i16 1)
 // CHECK: [[STACK:%.+]] = bitcast i8* [[GEP]] to %struct._globalized_locals_ty*
 // CHECK: getelementptr inbounds %struct._globalized_locals_ty, %struct._globalized_locals_ty* [[STACK]], i{{32|64}} 0, i{{32|64}} 0
 // CHECK-NOT: getelementptr inbounds %struct._globalized_locals_ty, %struct._globalized_locals_ty* [[STACK]],
@@ -43,8 +47,9 @@
 
 // CHECK: call void @__kmpc_for_static_fini(%struct.ident_t* @
 
-// CHECK: [[SHARED:%.+]] = load i16, i16* [[KERNEL_SHARED]],
-// CHECK: call void @__kmpc_restore_team_static_memory(i16 1, i16 [[SHARED]])
+// SEQ: [[SHARED:%.+]] = load i16, i16* [[KERNEL_SHARED]],
+// SEQ: call void @__kmpc_restore_team_static_memory(i16 1, i16 [[SHARED]])
+// PAR: call void @__kmpc_data_sharing_pop_stack(i8* [[GEP]])
 
 // CHECK: define internal void [[PARALLEL]](
 // CHECK-NOT: call i8* @__kmpc_data_sharing_push_stack(
diff --git a/clang/test/OpenMP/nvptx_parallel_codegen.cpp b/clang/test/OpenMP/nvptx_parallel_codegen.cpp
--- a/clang/test/OpenMP/nvptx_parallel_codegen.cpp
+++ b/clang/test/OpenMP/nvptx_parallel_codegen.cpp
@@ -1,9 +1,12 @@
 // Test target codegen - host bc file has to be created first.
 // RUN: %clang_cc1 -verify -fopenmp -x c++ -triple powerpc64le-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm-bc %s -o %t-ppc-host.bc
-// RUN: %clang_cc1 -verify -fopenmp -x c++ -triple nvptx64-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o - -disable-llvm-optzns | FileCheck %s --check-prefix CHECK --check-prefix CHECK-64
+// RUN: %clang_cc1 -verify -fopenmp -x c++ -triple nvptx64-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o - -disable-llvm-optzns | FileCheck %s --check-prefix CHECK --check-prefix CHECK-64 --check-prefix SEQ
+// RUN: %clang_cc1 -verify -fopenmp -x c++ -triple nvptx64-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o - -disable-llvm-optzns -fopenmp-cuda-parallel-target-regions | FileCheck %s --check-prefix CHECK --check-prefix CHECK-64 --check-prefix PAR
 // RUN: %clang_cc1 -verify -fopenmp -x c++ -triple i386-unknown-unknown -fopenmp-targets=nvptx-nvidia-cuda -emit-llvm-bc %s -o %t-x86-host.bc
-// RUN: %clang_cc1 -verify -fopenmp -x c++ -triple nvptx-unknown-unknown -fopenmp-targets=nvptx-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-x86-host.bc -o - -disable-llvm-optzns | FileCheck %s --check-prefix CHECK --check-prefix CHECK-32
-// RUN: %clang_cc1 -verify -fopenmp -fexceptions -fcxx-exceptions -x c++ -triple nvptx-unknown-unknown -fopenmp-targets=nvptx-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-x86-host.bc -o - -disable-llvm-optzns | FileCheck %s --check-prefix CHECK --check-prefix CHECK-32
+// RUN: %clang_cc1 -verify -fopenmp -x c++ -triple nvptx-unknown-unknown -fopenmp-targets=nvptx-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-x86-host.bc -o - -disable-llvm-optzns | FileCheck %s --check-prefix CHECK --check-prefix CHECK-32 --check-prefix SEQ
+// RUN: %clang_cc1 -verify -fopenmp -fexceptions -fcxx-exceptions -x c++ -triple nvptx-unknown-unknown -fopenmp-targets=nvptx-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-x86-host.bc -o - -disable-llvm-optzns | FileCheck %s --check-prefix CHECK --check-prefix CHECK-32 --check-prefix SEQ
+// RUN: %clang_cc1 -verify -fopenmp -x c++ -triple nvptx-unknown-unknown -fopenmp-targets=nvptx-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-x86-host.bc -o - -disable-llvm-optzns -fopenmp-cuda-parallel-target-regions | FileCheck %s --check-prefix CHECK --check-prefix CHECK-32 --check-prefix PAR
+// RUN: %clang_cc1 -verify -fopenmp -fexceptions -fcxx-exceptions -x c++ -triple nvptx-unknown-unknown -fopenmp-targets=nvptx-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-x86-host.bc -o - -disable-llvm-optzns -fopenmp-cuda-parallel-target-regions | FileCheck %s --check-prefix CHECK --check-prefix CHECK-32 --check-prefix PAR
 // expected-no-diagnostics
 #ifndef HEADER
 #define HEADER
@@ -72,15 +75,15 @@
   return a;
 }
 
-// CHECK: [[MEM_TY:%.+]] = type { [128 x i8] }
-// CHECK-DAG: [[SHARED_GLOBAL_RD:@.+]] = common addrspace(3) global [[MEM_TY]] zeroinitializer
-// CHECK-DAG: [[KERNEL_PTR:@.+]] = internal addrspace(3) global i8* null
-// CHECK-DAG: [[KERNEL_SIZE:@.+]] = internal unnamed_addr constant i{{64|32}} 4
-// CHECK-DAG: [[KERNEL_SHARED:@.+]] = internal unnamed_addr constant i16 1
+// SEQ: [[MEM_TY:%.+]] = type { [128 x i8] }
+// SEQ-DAG: [[SHARED_GLOBAL_RD:@.+]] = common addrspace(3) global [[MEM_TY]] zeroinitializer
+// SEQ-DAG: [[KERNEL_PTR:@.+]] = internal addrspace(3) global i8* null
+// SEQ-DAG: [[KERNEL_SIZE:@.+]] = internal unnamed_addr constant i{{64|32}} 4
+// SEQ-DAG: [[KERNEL_SHARED:@.+]] = internal unnamed_addr constant i16 1
 
-// CHECK-NOT: define {{.*}}void {{@__omp_offloading_.+template.+l17}}_worker()
+// CHECK-NOT: define {{.*}}void {{@__omp_offloading_.+template.+l20}}_worker()
 
-// CHECK-LABEL: define {{.*}}void {{@__omp_offloading_.+template.+l26}}_worker()
+// CHECK-LABEL: define {{.*}}void {{@__omp_offloading_.+template.+l29}}_worker()
 // CHECK-DAG: [[OMP_EXEC_STATUS:%.+]] = alloca i8,
 // CHECK-DAG: [[OMP_WORK_FN:%.+]] = alloca i8*,
 // CHECK: store i8* null, i8** [[OMP_WORK_FN]],
@@ -133,7 +136,7 @@
 // CHECK: [[EXIT]]
 // CHECK: ret void
 
-// CHECK: define {{.*}}void [[T6:@__omp_offloading_.+template.+l26]](i[[SZ:32|64]]
+// CHECK: define {{.*}}void [[T6:@__omp_offloading_.+template.+l29]](i[[SZ:32|64]]
 // Create local storage for each capture.
 // CHECK:  [[LOCAL_A:%.+]] = alloca i[[SZ]],
 // CHECK-DAG:  store i[[SZ]] [[ARG_A:%.+]], i[[SZ]]* [[LOCAL_A]]
@@ -199,7 +202,7 @@
 // CHECK: store i[[SZ]] 44, i[[SZ]]* %a,
 // CHECK: ret void
 
-// CHECK-LABEL: define {{.*}}void {{@__omp_offloading_.+template.+l43}}_worker()
+// CHECK-LABEL: define {{.*}}void {{@__omp_offloading_.+template.+l46}}_worker()
 // CHECK-DAG: [[OMP_EXEC_STATUS:%.+]] = alloca i8,
 // CHECK-DAG: [[OMP_WORK_FN:%.+]] = alloca i8*,
 // CHECK: store i8* null, i8** [[OMP_WORK_FN]],
@@ -243,7 +246,7 @@
 // CHECK: [[EXIT]]
 // CHECK: ret void
 
-// CHECK: define {{.*}}void [[T6:@__omp_offloading_.+template.+l43]](i[[SZ:32|64]]
+// CHECK: define {{.*}}void [[T6:@__omp_offloading_.+template.+l46]](i[[SZ:32|64]]
 // Create local storage for each capture.
 // CHECK:  [[LOCAL_N:%.+]] = alloca i[[SZ]],
 // CHECK:  [[LOCAL_A:%.+]] = alloca i[[SZ]],
@@ -323,23 +326,25 @@
 
 // CHECK: declare void @__kmpc_barrier(%struct.ident_t*, i32) #[[#CONVERGENT]]
 
-// CHECK-LABEL: define {{.*}}void {{@__omp_offloading_.+template.+l55}}_worker()
-// CHECK-LABEL: define {{.*}}void {{@__omp_offloading_.+template.+l55}}(
+// CHECK-LABEL: define {{.*}}void {{@__omp_offloading_.+template.+l58}}_worker()
+// CHECK-LABEL: define {{.*}}void {{@__omp_offloading_.+template.+l58}}(
 // CHECK-32: [[A_ADDR:%.+]] = alloca i32,
 // CHECK-64: [[A_ADDR:%.+]] = alloca i64,
 // CHECK-64: [[CONV:%.+]] = bitcast i64* [[A_ADDR]] to i32*
-// CHECK: [[IS_SHARED:%.+]] = load i16, i16* [[KERNEL_SHARED]],
-// CHECK: [[SIZE:%.+]] = load i{{64|32}}, i{{64|32}}* [[KERNEL_SIZE]],
-// CHECK: call void @__kmpc_get_team_static_memory(i16 0, i8* addrspacecast (i8 addrspace(3)* getelementptr inbounds ([[MEM_TY]], [[MEM_TY]] addrspace(3)* [[SHARED_GLOBAL_RD]], i32 0, i32 0, i32 0) to i8*), i{{64|32}} [[SIZE]], i16 [[IS_SHARED]], i8** addrspacecast (i8* addrspace(3)* [[KERNEL_PTR]] to i8**))
-// CHECK: [[KERNEL_RD:%.+]] = load i8*, i8* addrspace(3)* [[KERNEL_PTR]],
-// CHECK: [[STACK:%.+]] = getelementptr inbounds i8, i8* [[KERNEL_RD]], i{{64|32}} 0
+// SEQ: [[IS_SHARED:%.+]] = load i16, i16* [[KERNEL_SHARED]],
+// SEQ: [[SIZE:%.+]] = load i{{64|32}}, i{{64|32}}* [[KERNEL_SIZE]],
+// SEQ: call void @__kmpc_get_team_static_memory(i16 0, i8* addrspacecast (i8 addrspace(3)* getelementptr inbounds ([[MEM_TY]], [[MEM_TY]] addrspace(3)* [[SHARED_GLOBAL_RD]], i32 0, i32 0, i32 0) to i8*), i{{64|32}} [[SIZE]], i16 [[IS_SHARED]], i8** addrspacecast (i8* addrspace(3)* [[KERNEL_PTR]] to i8**))
+// SEQ: [[KERNEL_RD:%.+]] = load i8*, i8* addrspace(3)* [[KERNEL_PTR]],
+// SEQ: [[STACK:%.+]] = getelementptr inbounds i8, i8* [[KERNEL_RD]], i{{64|32}} 0
+// PAR: [[STACK:%.+]] = call i8* @__kmpc_data_sharing_push_stack(i{{32|64}} 4, i16 1)
 // CHECK: [[BC:%.+]] = bitcast i8* [[STACK]] to %struct._globalized_locals_ty*
 // CHECK-32: [[A:%.+]] = load i32, i32* [[A_ADDR]],
 // CHECK-64: [[A:%.+]] = load i32, i32* [[CONV]],
 // CHECK: [[GLOBAL_A_ADDR:%.+]] = getelementptr inbounds %struct._globalized_locals_ty, %struct._globalized_locals_ty* [[BC]], i{{[0-9]+}} 0, i{{[0-9]+}} 0
 // CHECK: store i32 [[A]], i32* [[GLOBAL_A_ADDR]],
-// CHECK: [[IS_SHARED:%.+]] = load i16, i16* [[KERNEL_SHARED]],
-// CHECK: call void @__kmpc_restore_team_static_memory(i16 0, i16 [[IS_SHARED]])
+// SEQ: [[IS_SHARED:%.+]] = load i16, i16* [[KERNEL_SHARED]],
+// SEQ: call void @__kmpc_restore_team_static_memory(i16 0, i16 [[IS_SHARED]])
+// PAR: call void @__kmpc_data_sharing_pop_stack(i8* [[STACK]])
 
 // CHECK-LABEL: define internal void @{{.+}}(i32* noalias %{{.+}}, i32* noalias %{{.+}}, i32* nonnull align {{[0-9]+}} dereferenceable{{.*}})
 // CHECK:  [[CC:%.+]] = alloca i32,
diff --git a/clang/test/OpenMP/nvptx_parallel_for_codegen.cpp b/clang/test/OpenMP/nvptx_parallel_for_codegen.cpp
--- a/clang/test/OpenMP/nvptx_parallel_for_codegen.cpp
+++ b/clang/test/OpenMP/nvptx_parallel_for_codegen.cpp
@@ -1,6 +1,7 @@
 // Test target codegen - host bc file has to be created first.
 // RUN: %clang_cc1 -verify -fopenmp -x c++ -triple powerpc64le-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm-bc %s -o %t-ppc-host.bc
-// RUN: %clang_cc1 -verify -fopenmp -x c++ -triple nvptx64-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o - -disable-llvm-optzns | FileCheck %s --check-prefix CHECK --check-prefix CHECK-64
+// RUN: %clang_cc1 -verify -fopenmp -x c++ -triple nvptx64-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o - -disable-llvm-optzns | FileCheck %s --check-prefix CHECK --check-prefix CHECK-64 --check-prefix SEQ
+// RUN: %clang_cc1 -verify -fopenmp -x c++ -triple nvptx64-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o - -disable-llvm-optzns -fopenmp-cuda-parallel-target-regions | FileCheck %s --check-prefix CHECK --check-prefix CHECK-64 --check-prefix PAR
 // expected-no-diagnostics
 #ifndef HEADER
 #define HEADER
@@ -30,33 +31,35 @@
   return a;
 }
 
-// CHECK: [[MEM_TY:%.+]] = type { [128 x i8] }
-// CHECK-DAG: [[SHARED_GLOBAL_RD:@.+]] = common addrspace(3) global [[MEM_TY]] zeroinitializer
-// CHECK-DAG: [[KERNEL_PTR:@.+]] = internal addrspace(3) global i8* null
-// CHECK-DAG: [[KERNEL_SIZE:@.+]] = internal unnamed_addr constant i{{64|32}} 4
-// CHECK-DAG: [[KERNEL_SHARED:@.+]] = internal unnamed_addr constant i16 1
+// SEQ: [[MEM_TY:%.+]] = type { [128 x i8] }
+// SEQ-DAG: [[SHARED_GLOBAL_RD:@.+]] = common addrspace(3) global [[MEM_TY]] zeroinitializer
+// SEQ-DAG: [[KERNEL_PTR:@.+]] = internal addrspace(3) global i8* null
+// SEQ-DAG: [[KERNEL_SIZE:@.+]] = internal unnamed_addr constant i{{64|32}} 4
+// SEQ-DAG: [[KERNEL_SHARED:@.+]] = internal unnamed_addr constant i16 1
 
-// CHECK-LABEL: define {{.*}}void {{@__omp_offloading_.+template.+l12}}_worker()
+// CHECK-LABEL: define {{.*}}void {{@__omp_offloading_.+template.+l13}}_worker()
 // CHECK: call void @__kmpc_barrier_simple_spmd(%struct.ident_t* null, i32 0)
 // CHECK: call i1 @__kmpc_kernel_parallel(
 // CHECK: call void @__omp_outlined___wrapper(
 
-// CHECK: define weak void @__omp_offloading_{{.*}}l12(
-// CHECK: call void @__omp_offloading_{{.*}}l12_worker()
+// CHECK: define weak void @__omp_offloading_{{.*}}l13(
+// CHECK: call void @__omp_offloading_{{.*}}l13_worker()
 // CHECK: call void @__kmpc_kernel_init(
 // CHECK: call void @__kmpc_data_sharing_init_stack()
-// CHECK: [[IS_SHARED:%.+]] = load i16, i16* [[KERNEL_SHARED]],
-// CHECK: [[SIZE:%.+]] = load i{{64|32}}, i{{64|32}}* [[KERNEL_SIZE]],
-// CHECK: call void @__kmpc_get_team_static_memory(i16 0, i8* addrspacecast (i8 addrspace(3)* getelementptr inbounds ([[MEM_TY]], [[MEM_TY]] addrspace(3)* [[SHARED_GLOBAL_RD]], i32 0, i32 0, i32 0) to i8*), i64 %7, i16 %6, i8** addrspacecast (i8* addrspace(3)* [[KERNEL_PTR]] to i8**))
-// CHECK: [[KERNEL_RD:%.+]] = load i8*, i8* addrspace(3)* [[KERNEL_PTR]],
-// CHECK: [[STACK:%.+]] = getelementptr inbounds i8, i8* [[KERNEL_RD]], i{{64|32}} 0
+// SEQ: [[IS_SHARED:%.+]] = load i16, i16* [[KERNEL_SHARED]],
+// SEQ: [[SIZE:%.+]] = load i{{64|32}}, i{{64|32}}* [[KERNEL_SIZE]],
+// SEQ: call void @__kmpc_get_team_static_memory(i16 0, i8* addrspacecast (i8 addrspace(3)* getelementptr inbounds ([[MEM_TY]], [[MEM_TY]] addrspace(3)* [[SHARED_GLOBAL_RD]], i32 0, i32 0, i32 0) to i8*), i64 %7, i16 %6, i8** addrspacecast (i8* addrspace(3)* [[KERNEL_PTR]] to i8**))
+// SEQ: [[KERNEL_RD:%.+]] = load i8*, i8* addrspace(3)* [[KERNEL_PTR]],
+// SEQ: [[STACK:%.+]] = getelementptr inbounds i8, i8* [[KERNEL_RD]], i{{64|32}} 0
+// PAR: [[STACK:%.+]] = call i8* @__kmpc_data_sharing_push_stack(i{{32|64}} 4, i16 1)
 // CHECK: call void @__kmpc_kernel_prepare_parallel(
 // CHECK: call void @__kmpc_begin_sharing_variables({{.*}}, i64 2)
 // CHECK: call void @__kmpc_barrier_simple_spmd(%struct.ident_t* null, i32 0)
 // CHECK: call void @__kmpc_barrier_simple_spmd(%struct.ident_t* null, i32 0)
 // CHECK: call void @__kmpc_end_sharing_variables()
-// CHECK: [[IS_SHARED:%.+]] = load i16, i16* [[KERNEL_SHARED]],
-// CHECK: call void @__kmpc_restore_team_static_memory(i16 0, i16 [[IS_SHARED]])
+// SEQ: [[IS_SHARED:%.+]] = load i16, i16* [[KERNEL_SHARED]],
+// SEQ: call void @__kmpc_restore_team_static_memory(i16 0, i16 [[IS_SHARED]])
+// PAR: call void @__kmpc_data_sharing_pop_stack(i8* [[STACK]])
 // CHECK: call void @__kmpc_kernel_deinit(i16 1)
 
 // CHECK: define internal void @__omp_outlined__(
diff --git a/clang/test/OpenMP/nvptx_target_teams_distribute_codegen.cpp b/clang/test/OpenMP/nvptx_target_teams_distribute_codegen.cpp
--- a/clang/test/OpenMP/nvptx_target_teams_distribute_codegen.cpp
+++ b/clang/test/OpenMP/nvptx_target_teams_distribute_codegen.cpp
@@ -1,17 +1,20 @@
 // Test target codegen - host bc file has to be created first.
 // RUN: %clang_cc1 -verify -fopenmp -x c++ -triple powerpc64le-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm-bc %s -o %t-ppc-host.bc
-// RUN: %clang_cc1 -verify -fopenmp -x c++ -triple nvptx64-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o - | FileCheck %s --check-prefix CHECK --check-prefix CHECK-64
+// RUN: %clang_cc1 -verify -fopenmp -x c++ -triple nvptx64-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o - | FileCheck %s --check-prefix CHECK --check-prefix CHECK-64 --check-prefix SEQ
+// RUN: %clang_cc1 -verify -fopenmp -x c++ -triple nvptx64-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o - -fopenmp-cuda-parallel-target-regions | FileCheck %s --check-prefix CHECK --check-prefix CHECK-64 --check-prefix PAR
 // RUN: %clang_cc1 -verify -fopenmp -x c++ -triple i386-unknown-unknown -fopenmp-targets=nvptx-nvidia-cuda -emit-llvm-bc %s -o %t-x86-host.bc
-// RUN: %clang_cc1 -verify -fopenmp -x c++ -triple nvptx-unknown-unknown -fopenmp-targets=nvptx-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-x86-host.bc -o - | FileCheck %s --check-prefix CHECK --check-prefix CHECK-32
-// RUN: %clang_cc1 -verify -fopenmp -fexceptions -fcxx-exceptions -x c++ -triple nvptx-unknown-unknown -fopenmp-targets=nvptx-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-x86-host.bc -o - | FileCheck %s --check-prefix CHECK --check-prefix CHECK-32
+// RUN: %clang_cc1 -verify -fopenmp -x c++ -triple nvptx-unknown-unknown -fopenmp-targets=nvptx-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-x86-host.bc -o - | FileCheck %s --check-prefix CHECK --check-prefix CHECK-32 --check-prefix SEQ
+// RUN: %clang_cc1 -verify -fopenmp -fexceptions -fcxx-exceptions -x c++ -triple nvptx-unknown-unknown -fopenmp-targets=nvptx-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-x86-host.bc -o - | FileCheck %s --check-prefix CHECK --check-prefix CHECK-32 --check-prefix SEQ
+// RUN: %clang_cc1 -verify -fopenmp -x c++ -triple nvptx-unknown-unknown -fopenmp-targets=nvptx-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-x86-host.bc -o - -fopenmp-cuda-parallel-target-regions | FileCheck %s --check-prefix CHECK --check-prefix CHECK-32 --check-prefix PAR
+// RUN: %clang_cc1 -verify -fopenmp -fexceptions -fcxx-exceptions -x c++ -triple nvptx-unknown-unknown -fopenmp-targets=nvptx-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-x86-host.bc -o - -fopenmp-cuda-parallel-target-regions | FileCheck %s --check-prefix CHECK --check-prefix CHECK-32 --check-prefix PAR
 // expected-no-diagnostics
 #ifndef HEADER
 #define HEADER
 
-// CHECK: [[MEM_TY:%.+]] = type { [128 x i8] }
-// CHECK-DAG: {{@__omp_offloading_.+}}_l20_exec_mode = weak constant i8 1
-// CHECK-DAG: [[KERNEL_SIZE:@.+]] = internal unnamed_addr constant i{{64|32}} 4
-// CHECK-DAG: [[KERNEL_SHARED:@.+]] = internal unnamed_addr constant i16 1
+// SEQ: [[MEM_TY:%.+]] = type { [128 x i8] }
+// SEQ-DAG: {{@__omp_offloading_.+}}_l23_exec_mode = weak constant i8 1
+// SEQ-DAG: [[KERNEL_SIZE:@.+]] = internal unnamed_addr constant i{{64|32}} 4
+// SEQ-DAG: [[KERNEL_SHARED:@.+]] = internal unnamed_addr constant i16 1
 
 template<typename tx>
 tx ftemplate(int n) {
@@ -35,10 +38,10 @@
   return a;
 }
 
-  // CHECK-LABEL: define {{.*}}void {{@__omp_offloading_.+template.+l20}}_worker()
+  // CHECK-LABEL: define {{.*}}void {{@__omp_offloading_.+template.+l23}}_worker()
   // CHECK: ret void
 
-  // CHECK: define {{.*}}void {{@__omp_offloading_.+template.+l20}}()
+  // CHECK: define {{.*}}void {{@__omp_offloading_.+template.+l23}}()
 
   // CHECK-DAG: [[TID:%.+]] = call i32 @llvm.nvvm.read.ptx.sreg.tid.x()
   // CHECK-DAG: [[NTH:%.+]] = call i32 @llvm.nvvm.read.ptx.sreg.ntid.x()
@@ -48,7 +51,7 @@
   // CHECK: br i1 [[IS_WORKER]], label {{%?}}[[WORKER:.+]], label {{%?}}[[CHECK_MASTER:.+]]
   //
   // CHECK: [[WORKER]]
-  // CHECK: {{call|invoke}} void {{@__omp_offloading_.+template.+l20}}_worker()
+  // CHECK: {{call|invoke}} void {{@__omp_offloading_.+template.+l23}}_worker()
   // CHECK: br label {{%?}}[[EXIT:.+]]
   //
   // CHECK: [[CHECK_MASTER]]
@@ -75,11 +78,12 @@
   // CHECK: ret void
 
   // CHECK: define internal void [[PARALLEL]](i32* noalias %{{.+}}, i32* noalias %{{.+}})
-  // CHECK: [[SHARED:%.+]] = load i16, i16* [[KERNEL_SHARED]],
-  // CHECK: [[SIZE:%.+]] = load i{{64|32}}, i{{64|32}}* [[KERNEL_SIZE]],
-  // CHECK: call void @__kmpc_get_team_static_memory(i16 0, i8* addrspacecast (i8 addrspace(3)* getelementptr inbounds ([[MEM_TY]], [[MEM_TY]] addrspace(3)* @{{.+}}, i32 0, i32 0, i32 0) to i8*), i{{64|32}} [[SIZE]], i16 [[SHARED]], i8** addrspacecast (i8* addrspace(3)* [[BUF:@.+]] to i8**))
-  // CHECK: [[PTR:%.+]] = load i8*, i8* addrspace(3)* [[BUF]],
-  // CHECK: [[ADDR:%.+]] = getelementptr inbounds i8, i8* [[PTR]], i{{64|32}} 0
+  // SEQ: [[SHARED:%.+]] = load i16, i16* [[KERNEL_SHARED]],
+  // SEQ: [[SIZE:%.+]] = load i{{64|32}}, i{{64|32}}* [[KERNEL_SIZE]],
+  // SEQ: call void @__kmpc_get_team_static_memory(i16 0, i8* addrspacecast (i8 addrspace(3)* getelementptr inbounds ([[MEM_TY]], [[MEM_TY]] addrspace(3)* @{{.+}}, i32 0, i32 0, i32 0) to i8*), i{{64|32}} [[SIZE]], i16 [[SHARED]], i8** addrspacecast (i8* addrspace(3)* [[BUF:@.+]] to i8**))
+  // SEQ: [[PTR:%.+]] = load i8*, i8* addrspace(3)* [[BUF]],
+  // SEQ: [[ADDR:%.+]] = getelementptr inbounds i8, i8* [[PTR]], i{{64|32}} 0
+  // PAR: [[ADDR:%.+]] = call i8* @__kmpc_data_sharing_push_stack(i{{32|64}} 4, i16 1)
   // CHECK: [[RD:%.+]] = bitcast i8* [[ADDR]] to [[GLOB_TY:%.+]]*
   // CHECK: [[I_ADDR:%.+]] = getelementptr inbounds [[GLOB_TY]], [[GLOB_TY]]* [[RD]], i32 0, i32 0
   //
diff --git a/clang/test/OpenMP/nvptx_target_teams_distribute_parallel_for_codegen.cpp b/clang/test/OpenMP/nvptx_target_teams_distribute_parallel_for_codegen.cpp
--- a/clang/test/OpenMP/nvptx_target_teams_distribute_parallel_for_codegen.cpp
+++ b/clang/test/OpenMP/nvptx_target_teams_distribute_parallel_for_codegen.cpp
@@ -1,21 +1,25 @@
 // Test target codegen - host bc file has to be created first.
 // RUN: %clang_cc1 -verify -fopenmp -fopenmp-version=45 -fopenmp-cuda-mode -x c++ -triple powerpc64le-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm-bc %s -o %t-ppc-host.bc
-// RUN: %clang_cc1 -verify -fopenmp -fopenmp-version=45 -fopenmp-cuda-mode -x c++ -triple nvptx64-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o - | FileCheck %s --check-prefix CHECK --check-prefix CHECK-64 --check-prefix CHECK-DIV64
-// RUN: %clang_cc1 -verify -fopenmp -fopenmp-version=45 -fopenmp-cuda-mode -x c++ -triple nvptx64-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -fopenmp-optimistic-collapse -o - | FileCheck %s --check-prefix CHECK --check-prefix CHECK-DIV32
+// RUN: %clang_cc1 -verify -fopenmp -fopenmp-version=45 -fopenmp-cuda-mode -x c++ -triple nvptx64-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o - | FileCheck %s --check-prefix CHECK --check-prefix CHECK-64 --check-prefix CHECK-DIV64 --check-prefix SEQ
+// RUN: %clang_cc1 -verify -fopenmp -fopenmp-version=45 -fopenmp-cuda-mode -x c++ -triple nvptx64-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o - -fopenmp-cuda-parallel-target-regions | FileCheck %s --check-prefix CHECK --check-prefix CHECK-64 --check-prefix CHECK-DIV64 --check-prefix PAR
+// RUN: %clang_cc1 -verify -fopenmp -fopenmp-version=45 -fopenmp-cuda-mode -x c++ -triple nvptx64-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -fopenmp-optimistic-collapse -o - | FileCheck %s --check-prefix CHECK --check-prefix CHECK-DIV32 --check-prefix SEQ
+// RUN: %clang_cc1 -verify -fopenmp -fopenmp-version=45 -fopenmp-cuda-mode -x c++ -triple nvptx64-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -fopenmp-optimistic-collapse -o - -fopenmp-cuda-parallel-target-regions | FileCheck %s --check-prefix CHECK --check-prefix CHECK-DIV32 --check-prefix PAR
 // RUN: %clang_cc1 -verify -fopenmp -fopenmp-version=45 -fopenmp-cuda-mode -x c++ -triple i386-unknown-unknown -fopenmp-targets=nvptx-nvidia-cuda -emit-llvm-bc %s -o %t-x86-host.bc
-// RUN: %clang_cc1 -verify -fopenmp -fopenmp-version=45 -fopenmp-cuda-mode -x c++ -triple nvptx-unknown-unknown -fopenmp-targets=nvptx-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-x86-host.bc -o - | FileCheck %s --check-prefix CHECK --check-prefix CHECK-32
-// RUN: %clang_cc1 -verify -fopenmp -fopenmp-version=45 -fopenmp-cuda-mode -fexceptions -fcxx-exceptions -x c++ -triple nvptx-unknown-unknown -fopenmp-targets=nvptx-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-x86-host.bc -o - | FileCheck %s --check-prefix CHECK --check-prefix CHECK-32
+// RUN: %clang_cc1 -verify -fopenmp -fopenmp-version=45 -fopenmp-cuda-mode -x c++ -triple nvptx-unknown-unknown -fopenmp-targets=nvptx-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-x86-host.bc -o - | FileCheck %s --check-prefix CHECK --check-prefix CHECK-32 --check-prefix SEQ
+// RUN: %clang_cc1 -verify -fopenmp -fopenmp-version=45 -fopenmp-cuda-mode -fexceptions -fcxx-exceptions -x c++ -triple nvptx-unknown-unknown -fopenmp-targets=nvptx-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-x86-host.bc -o - | FileCheck %s --check-prefix CHECK --check-prefix CHECK-32 --check-prefix SEQ
+// RUN: %clang_cc1 -verify -fopenmp -fopenmp-version=45 -fopenmp-cuda-mode -x c++ -triple nvptx-unknown-unknown -fopenmp-targets=nvptx-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-x86-host.bc -o - -fopenmp-cuda-parallel-target-regions | FileCheck %s --check-prefix CHECK --check-prefix CHECK-32 --check-prefix PAR
+// RUN: %clang_cc1 -verify -fopenmp -fopenmp-version=45 -fopenmp-cuda-mode -fexceptions -fcxx-exceptions -x c++ -triple nvptx-unknown-unknown -fopenmp-targets=nvptx-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-x86-host.bc -o - -fopenmp-cuda-parallel-target-regions | FileCheck %s --check-prefix CHECK --check-prefix CHECK-32 --check-prefix PAR
 // expected-no-diagnostics
 #ifndef HEADER
 #define HEADER
 
 // Check that the execution mode of all 5 target regions on the gpu is set to SPMD Mode.
-// CHECK-DAG: {{@__omp_offloading_.+l34}}_exec_mode = weak constant i8 0
-// CHECK-DAG: {{@__omp_offloading_.+l40}}_exec_mode = weak constant i8 0
-// CHECK-DAG: {{@__omp_offloading_.+l45}}_exec_mode = weak constant i8 0
-// CHECK-DAG: {{@__omp_offloading_.+l50}}_exec_mode = weak constant i8 0
-// CHECK-DAG: {{@__omp_offloading_.+l58}}_exec_mode = weak constant i8 0
-// CHECK-DAG: {{@__omp_offloading_.+l65}}_exec_mode = weak constant i8 0
+// CHECK-DAG: {{@__omp_offloading_.+l38}}_exec_mode = weak constant i8 0
+// CHECK-DAG: {{@__omp_offloading_.+l44}}_exec_mode = weak constant i8 0
+// CHECK-DAG: {{@__omp_offloading_.+l49}}_exec_mode = weak constant i8 0
+// CHECK-DAG: {{@__omp_offloading_.+l54}}_exec_mode = weak constant i8 0
+// CHECK-DAG: {{@__omp_offloading_.+l62}}_exec_mode = weak constant i8 0
+// CHECK-DAG: {{@__omp_offloading_.+l69}}_exec_mode = weak constant i8 0
 
 #define N 1000
 #define M 10
@@ -76,31 +80,33 @@
   return a;
 }
 
-// CHECK-DAG: [[MEM_TY:%.+]] = type { [128 x i8] }
-// CHECK-DAG: [[SHARED_GLOBAL_RD:@.+]] = common addrspace(3) global [[MEM_TY]] zeroinitializer
-// CHECK-DAG: [[KERNEL_PTR:@.+]] = internal addrspace(3) global i8* null
-// CHECK-DAG: [[KERNEL_SIZE:@.+]] = internal unnamed_addr constant i{{64|32}} 4
-// CHECK-DAG: [[KERNEL_SHARED:@.+]] = internal unnamed_addr constant i16 1
+// SEQ-DAG: [[MEM_TY:%.+]] = type { [128 x i8] }
+// SEQ-DAG: [[SHARED_GLOBAL_RD:@.+]] = common addrspace(3) global [[MEM_TY]] zeroinitializer
+// SEQ-DAG: [[KERNEL_PTR:@.+]] = internal addrspace(3) global i8* null
+// SEQ-DAG: [[KERNEL_SIZE:@.+]] = internal unnamed_addr constant i{{64|32}} 4
+// SEQ-DAG: [[KERNEL_SHARED:@.+]] = internal unnamed_addr constant i16 1
 
-// CHECK-LABEL: define {{.*}}void {{@__omp_offloading_.+}}_l34(
+// CHECK-LABEL: define {{.*}}void {{@__omp_offloading_.+}}_l38(
 // CHECK-DAG: [[THREAD_LIMIT:%.+]] = call i32 @llvm.nvvm.read.ptx.sreg.ntid.x()
 // CHECK: call void @__kmpc_spmd_kernel_init(i32 [[THREAD_LIMIT]], i16 0, i16 0)
 // CHECK: call void [[PARALLEL:@.+]](
 // CHECK: call void @__kmpc_spmd_kernel_deinit_v2(i16 0)
 
 // CHECK: define internal void [[PARALLEL]](
-// CHECK: [[SHARED:%.+]] = load i16, i16* [[KERNEL_SHARED]],
-// CHECK: [[SIZE:%.+]] = load i{{64|32}}, i{{64|32}}* [[KERNEL_SIZE]],
-// CHECK: call void @__kmpc_get_team_static_memory(i16 1, i8* addrspacecast (i8 addrspace(3)* getelementptr inbounds ([[MEM_TY]], [[MEM_TY]] addrspace(3)* [[SHARED_GLOBAL_RD]], i32 0, i32 0, i32 0) to i8*), i{{64|32}} [[SIZE]], i16 [[SHARED]], i8** addrspacecast (i8* addrspace(3)* [[KERNEL_PTR]] to i8**))
-// CHECK: [[TEAM_ALLOC:%.+]] = load i8*, i8* addrspace(3)* [[KERNEL_PTR]],
-// CHECK: [[ADDR:%.+]] = getelementptr inbounds i8, i8* [[TEAM_ALLOC]], i{{64|32}} 0
+// SEQ: [[SHARED:%.+]] = load i16, i16* [[KERNEL_SHARED]],
+// SEQ: [[SIZE:%.+]] = load i{{64|32}}, i{{64|32}}* [[KERNEL_SIZE]],
+// SEQ: call void @__kmpc_get_team_static_memory(i16 1, i8* addrspacecast (i8 addrspace(3)* getelementptr inbounds ([[MEM_TY]], [[MEM_TY]] addrspace(3)* [[SHARED_GLOBAL_RD]], i32 0, i32 0, i32 0) to i8*), i{{64|32}} [[SIZE]], i16 [[SHARED]], i8** addrspacecast (i8* addrspace(3)* [[KERNEL_PTR]] to i8**))
+// SEQ: [[TEAM_ALLOC:%.+]] = load i8*, i8* addrspace(3)* [[KERNEL_PTR]],
+// SEQ: [[ADDR:%.+]] = getelementptr inbounds i8, i8* [[TEAM_ALLOC]], i{{64|32}} 0
+// PAR: [[ADDR:%.+]] = call i8* @__kmpc_data_sharing_push_stack(i{{32|64}} 4, i16 1)
 // CHECK: [[BC:%.+]] = bitcast i8* [[ADDR]] to [[REC:%.+]]*
 // CHECK: getelementptr inbounds [[REC]], [[REC]]* [[BC]], i{{[0-9]+}} 0, i{{[0-9]+}} 0
 // CHECK: call void @__kmpc_for_static_init_4({{.+}}, {{.+}}, {{.+}} 91,
 // CHECK: {{call|invoke}} void [[OUTL1:@.+]](
 // CHECK: call void @__kmpc_for_static_fini(
-// CHECK: [[SHARED:%.+]] = load i16, i16* [[KERNEL_SHARED]],
-// CHECK: call void @__kmpc_restore_team_static_memory(i16 1, i16 [[SHARED]])
+// SEQ: [[SHARED:%.+]] = load i16, i16* [[KERNEL_SHARED]],
+// SEQ: call void @__kmpc_restore_team_static_memory(i16 1, i16 [[SHARED]])
+// PAR: call void @__kmpc_data_sharing_pop_stack(i8* [[ADDR]])
 // CHECK: ret void
 
 // CHECK: define internal void [[OUTL1]](
@@ -233,13 +239,13 @@
 // CHECK: call void @__kmpc_for_static_fini(
 // CHECK: ret void
 
-// CHECK: define weak void @__omp_offloading_{{.*}}_l58(i[[SZ:64|32]] %{{[^,]+}}, [10 x [10 x i32]]* nonnull align {{[0-9]+}} dereferenceable{{.*}})
+// CHECK: define weak void @__omp_offloading_{{.*}}_l62(i[[SZ:64|32]] %{{[^,]+}}, [10 x [10 x i32]]* nonnull align {{[0-9]+}} dereferenceable{{.*}})
 // CHECK: call void [[OUTLINED:@__omp_outlined.*]](i32* %{{.+}}, i32* %{{.+}}, i[[SZ]] %{{.*}}, i[[SZ]] %{{.*}}, i[[SZ]] %{{.*}}, [10 x [10 x i32]]* %{{.*}})
 // CHECK: define internal void [[OUTLINED]](i32* noalias %{{.*}}, i32* noalias %{{.*}} i[[SZ]] %{{.+}}, i[[SZ]] %{{.+}}, i[[SZ]] %{{.+}}, [10 x [10 x i32]]* nonnull align {{[0-9]+}} dereferenceable{{.*}})
 // CHECK-DIV64: div i64
 // CHECK-DIV32-NO: div i64
 
-// CHECK: define weak void @__omp_offloading_{{.*}}_l65(i[[SZ:64|32]] %{{[^,]+}}, [1000 x i32]* nonnull align {{[0-9]+}} dereferenceable{{.*}}, i32* %{{[^)]+}})
+// CHECK: define weak void @__omp_offloading_{{.*}}_l69(i[[SZ:64|32]] %{{[^,]+}}, [1000 x i32]* nonnull align {{[0-9]+}} dereferenceable{{.*}}, i32* %{{[^)]+}})
 // CHECK: call void [[OUTLINED:@__omp_outlined.*]](i32* %{{.+}}, i32* %{{.+}}, i[[SZ]] %{{.*}}, i[[SZ]] %{{.*}}, i[[SZ]] %{{.*}}, [1000 x i32]* %{{.*}}, i32* %{{.*}})
 // CHECK: define internal void [[OUTLINED]](i32* noalias %{{.*}}, i32* noalias %{{.*}} i[[SZ]] %{{.+}}, i[[SZ]] %{{.+}}, i[[SZ]] %{{.+}}, [1000 x i32]* nonnull align {{[0-9]+}} dereferenceable{{.*}}, i32* %{{.*}})
 
diff --git a/clang/test/OpenMP/nvptx_target_teams_distribute_parallel_for_simd_codegen.cpp b/clang/test/OpenMP/nvptx_target_teams_distribute_parallel_for_simd_codegen.cpp
--- a/clang/test/OpenMP/nvptx_target_teams_distribute_parallel_for_simd_codegen.cpp
+++ b/clang/test/OpenMP/nvptx_target_teams_distribute_parallel_for_simd_codegen.cpp
@@ -1,18 +1,21 @@
 // Test target codegen - host bc file has to be created first.
 // RUN: %clang_cc1 -verify -fopenmp -fopenmp-version=45 -fopenmp-cuda-mode -x c++ -triple powerpc64le-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm-bc %s -o %t-ppc-host.bc
-// RUN: %clang_cc1 -verify -fopenmp -fopenmp-version=45 -fopenmp-cuda-mode -x c++ -triple nvptx64-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o - | FileCheck %s --check-prefix CHECK --check-prefix CHECK-64
+// RUN: %clang_cc1 -verify -fopenmp -fopenmp-version=45 -fopenmp-cuda-mode -x c++ -triple nvptx64-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o - | FileCheck %s --check-prefix CHECK --check-prefix CHECK-64 --check-prefix SEQ
+// RUN: %clang_cc1 -verify -fopenmp -fopenmp-version=45 -fopenmp-cuda-mode -x c++ -triple nvptx64-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o - -fopenmp-cuda-parallel-target-regions | FileCheck %s --check-prefix CHECK --check-prefix CHECK-64 --check-prefix PAR
 // RUN: %clang_cc1 -verify -fopenmp -fopenmp-version=45 -fopenmp-cuda-mode -x c++ -triple i386-unknown-unknown -fopenmp-targets=nvptx-nvidia-cuda -emit-llvm-bc %s -o %t-x86-host.bc
-// RUN: %clang_cc1 -verify -fopenmp -fopenmp-version=45 -fopenmp-cuda-mode -x c++ -triple nvptx-unknown-unknown -fopenmp-targets=nvptx-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-x86-host.bc -o - | FileCheck %s --check-prefix CHECK --check-prefix CHECK-32
-// RUN: %clang_cc1 -verify -fopenmp -fopenmp-version=45 -fopenmp-cuda-mode -fexceptions -fcxx-exceptions -x c++ -triple nvptx-unknown-unknown -fopenmp-targets=nvptx-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-x86-host.bc -o - | FileCheck %s --check-prefix CHECK --check-prefix CHECK-32
+// RUN: %clang_cc1 -verify -fopenmp -fopenmp-version=45 -fopenmp-cuda-mode -x c++ -triple nvptx-unknown-unknown -fopenmp-targets=nvptx-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-x86-host.bc -o - | FileCheck %s --check-prefix CHECK --check-prefix CHECK-32 --check-prefix SEQ
+// RUN: %clang_cc1 -verify -fopenmp -fopenmp-version=45 -fopenmp-cuda-mode -fexceptions -fcxx-exceptions -x c++ -triple nvptx-unknown-unknown -fopenmp-targets=nvptx-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-x86-host.bc -o - | FileCheck %s --check-prefix CHECK --check-prefix CHECK-32 --check-prefix SEQ
+// RUN: %clang_cc1 -verify -fopenmp -fopenmp-version=45 -fopenmp-cuda-mode -x c++ -triple nvptx-unknown-unknown -fopenmp-targets=nvptx-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-x86-host.bc -o - -fopenmp-cuda-parallel-target-regions | FileCheck %s --check-prefix CHECK --check-prefix CHECK-32 --check-prefix PAR
+// RUN: %clang_cc1 -verify -fopenmp -fopenmp-version=45 -fopenmp-cuda-mode -fexceptions -fcxx-exceptions -x c++ -triple nvptx-unknown-unknown -fopenmp-targets=nvptx-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-x86-host.bc -o - -fopenmp-cuda-parallel-target-regions | FileCheck %s --check-prefix CHECK --check-prefix CHECK-32 --check-prefix PAR
 // expected-no-diagnostics
 #ifndef HEADER
 #define HEADER
 
 // Check that the execution mode of all 4 target regions on the gpu is set to SPMD Mode.
-// CHECK-DAG: {{@__omp_offloading_.+l30}}_exec_mode = weak constant i8 0
-// CHECK-DAG: {{@__omp_offloading_.+l36}}_exec_mode = weak constant i8 0
-// CHECK-DAG: {{@__omp_offloading_.+l41}}_exec_mode = weak constant i8 0
-// CHECK-DAG: {{@__omp_offloading_.+l46}}_exec_mode = weak constant i8 0
+// CHECK-DAG: {{@__omp_offloading_.+l33}}_exec_mode = weak constant i8 0
+// CHECK-DAG: {{@__omp_offloading_.+l39}}_exec_mode = weak constant i8 0
+// CHECK-DAG: {{@__omp_offloading_.+l44}}_exec_mode = weak constant i8 0
+// CHECK-DAG: {{@__omp_offloading_.+l49}}_exec_mode = weak constant i8 0
 
 #define N 1000
 #define M 10
@@ -62,29 +65,31 @@
   return a;
 }
 
-// CHECK-DAG: [[MEM_TY:%.+]] = type { [128 x i8] }
-// CHECK-DAG: [[SHARED_GLOBAL_RD:@.+]] = common addrspace(3) global [[MEM_TY]] zeroinitializer
-// CHECK-DAG: [[KERNEL_PTR:@.+]] = internal addrspace(3) global i8* null
-// CHECK-DAG: [[KERNEL_SIZE:@.+]] = internal unnamed_addr constant i{{64|32}} 4
-// CHECK-DAG: [[KERNEL_SHARED:@.+]] = internal unnamed_addr constant i16 1
+// SEQ-DAG: [[MEM_TY:%.+]] = type { [128 x i8] }
+// SEQ-DAG: [[SHARED_GLOBAL_RD:@.+]] = common addrspace(3) global [[MEM_TY]] zeroinitializer
+// SEQ-DAG: [[KERNEL_PTR:@.+]] = internal addrspace(3) global i8* null
+// SEQ-DAG: [[KERNEL_SIZE:@.+]] = internal unnamed_addr constant i{{64|32}} 4
+// SEQ-DAG: [[KERNEL_SHARED:@.+]] = internal unnamed_addr constant i16 1
 
-// CHECK-LABEL: define {{.*}}void {{@__omp_offloading_.+}}_l30(
+// CHECK-LABEL: define {{.*}}void {{@__omp_offloading_.+}}_l33(
 // CHECK-DAG: [[THREAD_LIMIT:%.+]] = call i32 @llvm.nvvm.read.ptx.sreg.ntid.x()
 // CHECK: call void @__kmpc_spmd_kernel_init(i32 [[THREAD_LIMIT]], i16 0, i16 0)
 // CHECK: call void @__kmpc_spmd_kernel_deinit_v2(i16 0)
 
-// CHECK: [[SHARED:%.+]] = load i16, i16* [[KERNEL_SHARED]],
-// CHECK: [[SIZE:%.+]] = load i{{64|32}}, i{{64|32}}* [[KERNEL_SIZE]],
-// CHECK: call void @__kmpc_get_team_static_memory(i16 1, i8* addrspacecast (i8 addrspace(3)* getelementptr inbounds ([[MEM_TY]], [[MEM_TY]] addrspace(3)* [[SHARED_GLOBAL_RD]], i32 0, i32 0, i32 0) to i8*), i{{64|32}} [[SIZE]], i16 [[SHARED]], i8** addrspacecast (i8* addrspace(3)* [[KERNEL_PTR]] to i8**))
-// CHECK: [[TEAM_ALLOC:%.+]] = load i8*, i8* addrspace(3)* [[KERNEL_PTR]],
-// CHECK: [[PTR:%.+]] = getelementptr inbounds i8, i8* [[TEAM_ALLOC]], i{{64|32}} 0
+// SEQ: [[SHARED:%.+]] = load i16, i16* [[KERNEL_SHARED]],
+// SEQ: [[SIZE:%.+]] = load i{{64|32}}, i{{64|32}}* [[KERNEL_SIZE]],
+// SEQ: call void @__kmpc_get_team_static_memory(i16 1, i8* addrspacecast (i8 addrspace(3)* getelementptr inbounds ([[MEM_TY]], [[MEM_TY]] addrspace(3)* [[SHARED_GLOBAL_RD]], i32 0, i32 0, i32 0) to i8*), i{{64|32}} [[SIZE]], i16 [[SHARED]], i8** addrspacecast (i8* addrspace(3)* [[KERNEL_PTR]] to i8**))
+// SEQ: [[TEAM_ALLOC:%.+]] = load i8*, i8* addrspace(3)* [[KERNEL_PTR]],
+// SEQ: [[PTR:%.+]] = getelementptr inbounds i8, i8* [[TEAM_ALLOC]], i{{64|32}} 0
+// PAR: [[PTR:%.+]] = call i8* @__kmpc_data_sharing_push_stack(i{{32|64}} 4, i16 1)
 // CHECK: [[BC:%.+]] = bitcast i8* [[PTR]] to [[REC:%.+]]*
 // CHECK: getelementptr inbounds [[REC]], [[REC]]* [[BC]], i{{[0-9]+}} 0, i{{[0-9]+}} 0
 // CHECK: call void @__kmpc_for_static_init_4({{.+}}, {{.+}}, {{.+}} 91,
 // CHECK: {{call|invoke}} void [[OUTL1:@.+]](
 // CHECK: call void @__kmpc_for_static_fini(
-// CHECK: [[SHARED:%.+]] = load i16, i16* [[KERNEL_SHARED]],
-// CHECK: call void @__kmpc_restore_team_static_memory(i16 1, i16 [[SHARED]])
+// SEQ: [[SHARED:%.+]] = load i16, i16* [[KERNEL_SHARED]],
+// SEQ: call void @__kmpc_restore_team_static_memory(i16 1, i16 [[SHARED]])
+// PAR: call void @__kmpc_data_sharing_pop_stack(i8* [[PTR]])
 // CHECK: ret void
 
 // CHECK: define internal void [[OUTL1]](
diff --git a/clang/test/OpenMP/nvptx_teams_codegen.cpp b/clang/test/OpenMP/nvptx_teams_codegen.cpp
--- a/clang/test/OpenMP/nvptx_teams_codegen.cpp
+++ b/clang/test/OpenMP/nvptx_teams_codegen.cpp
@@ -1,8 +1,10 @@
 // Test target codegen - host bc file has to be created first.
 // RUN: %clang_cc1 -DCK1 -verify -fopenmp -x c++ -triple powerpc64le-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm-bc %s -o %t-ppc-host.bc
-// RUN: %clang_cc1 -DCK1 -verify -fopenmp -x c++ -triple nvptx64-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o - | FileCheck %s --check-prefix CK1 --check-prefix CK1-64
+// RUN: %clang_cc1 -DCK1 -verify -fopenmp -x c++ -triple nvptx64-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o - | FileCheck %s --check-prefix CK1 --check-prefix CK1-64 --check-prefix SEQ
+// RUN: %clang_cc1 -DCK1 -verify -fopenmp -x c++ -triple nvptx64-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o - -fopenmp-cuda-parallel-target-regions | FileCheck %s --check-prefix CK1 --check-prefix CK1-64 --check-prefix PAR
 // RUN: %clang_cc1 -DCK1 -verify -fopenmp -x c++ -triple i386-unknown-unknown -fopenmp-targets=nvptx-nvidia-cuda -emit-llvm-bc %s -o %t-x86-host.bc
-// RUN: %clang_cc1 -DCK1 -verify -fopenmp -x c++ -triple nvptx-unknown-unknown -fopenmp-targets=nvptx-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-x86-host.bc -o - | FileCheck %s --check-prefix CK1 --check-prefix CK1-32
+// RUN: %clang_cc1 -DCK1 -verify -fopenmp -x c++ -triple nvptx-unknown-unknown -fopenmp-targets=nvptx-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-x86-host.bc -o - | FileCheck %s --check-prefix CK1 --check-prefix CK1-32 --check-prefix SEQ
+// RUN: %clang_cc1 -DCK1 -verify -fopenmp -x c++ -triple nvptx-unknown-unknown -fopenmp-targets=nvptx-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-x86-host.bc -o - -fopenmp-cuda-parallel-target-regions | FileCheck %s --check-prefix CK1 --check-prefix CK1-32 --check-prefix PAR
 // expected-no-diagnostics
 #ifndef HEADER
 #define HEADER
@@ -27,13 +29,13 @@
   return tmain(argv);
 }
 
-// CK1: [[MEM_TY:%.+]] = type { [128 x i8] }
-// CK1-DAG: [[SHARED_GLOBAL_RD:@.+]] = common addrspace(3) global [[MEM_TY]] zeroinitializer
-// CK1-DAG: [[KERNEL_PTR:@.+]] = internal addrspace(3) global i8* null
-// CK1-DAG: [[KERNEL_SIZE1:@.+]] = internal unnamed_addr constant i{{64|32}} 4
-// CK1-DAG: [[KERNEL_SIZE2:@.+]] = internal unnamed_addr constant i{{64|32}} {{8|4}}
-// CK1-DAG: [[KERNEL_SHARED1:@.+]] = internal unnamed_addr constant i16 1
-// CK1-DAG: [[KERNEL_SHARED2:@.+]] = internal unnamed_addr constant i16 1
+// SEQ: [[MEM_TY:%.+]] = type { [128 x i8] }
+// SEQ-DAG: [[SHARED_GLOBAL_RD:@.+]] = common addrspace(3) global [[MEM_TY]] zeroinitializer
+// SEQ-DAG: [[KERNEL_PTR:@.+]] = internal addrspace(3) global i8* null
+// SEQ-DAG: [[KERNEL_SIZE1:@.+]] = internal unnamed_addr constant i{{64|32}} 4
+// SEQ-DAG: [[KERNEL_SIZE2:@.+]] = internal unnamed_addr constant i{{64|32}} {{8|4}}
+// SEQ-DAG: [[KERNEL_SHARED1:@.+]] = internal unnamed_addr constant i16 1
+// SEQ-DAG: [[KERNEL_SHARED2:@.+]] = internal unnamed_addr constant i16 1
 
 // only nvptx side: do not outline teams region and do not call fork_teams
 // CK1:  define {{.*}}void @{{[^,]+}}(i{{[0-9]+}} [[ARGC:%.+]])
@@ -41,11 +43,12 @@
 // CK1:  store {{.+}} 0, {{.+}},
 // CK1:  store i{{[0-9]+}} [[ARGC]], i{{[0-9]+}}* [[ARGCADDR]],
 // CK1-64:  [[CONV:%.+]] = bitcast i{{[0-9]+}}* [[ARGCADDR]] to i{{[0-9]+}}*
-// CK1: [[IS_SHARED:%.+]] = load i16, i16* [[KERNEL_SHARED1]],
-// CK1: [[SIZE:%.+]] = load i{{64|32}}, i{{64|32}}* [[KERNEL_SIZE1]],
-// CK1: call void @__kmpc_get_team_static_memory(i16 0, i8* addrspacecast (i8 addrspace(3)* getelementptr inbounds ([[MEM_TY]], [[MEM_TY]] addrspace(3)* [[SHARED_GLOBAL_RD]], i32 0, i32 0, i32 0) to i8*), i{{64|32}} [[SIZE]], i16 [[IS_SHARED]], i8** addrspacecast (i8* addrspace(3)* [[KERNEL_PTR]] to i8**))
-// CK1: [[KERNEL_RD:%.+]] = load i8*, i8* addrspace(3)* [[KERNEL_PTR]],
-// CK1: [[GLOBALSTACK:%.+]] = getelementptr inbounds i8, i8* [[KERNEL_RD]], i{{64|32}} 0
+// SEQ: [[IS_SHARED:%.+]] = load i16, i16* [[KERNEL_SHARED1]],
+// SEQ: [[SIZE:%.+]] = load i{{64|32}}, i{{64|32}}* [[KERNEL_SIZE1]],
+// SEQ: call void @__kmpc_get_team_static_memory(i16 0, i8* addrspacecast (i8 addrspace(3)* getelementptr inbounds ([[MEM_TY]], [[MEM_TY]] addrspace(3)* [[SHARED_GLOBAL_RD]], i32 0, i32 0, i32 0) to i8*), i{{64|32}} [[SIZE]], i16 [[IS_SHARED]], i8** addrspacecast (i8* addrspace(3)* [[KERNEL_PTR]] to i8**))
+// SEQ: [[KERNEL_RD:%.+]] = load i8*, i8* addrspace(3)* [[KERNEL_PTR]],
+// SEQ: [[GLOBALSTACK:%.+]] = getelementptr inbounds i8, i8* [[KERNEL_RD]], i{{64|32}} 0
+// PAR: [[GLOBALSTACK:%.+]] = call i8* @__kmpc_data_sharing_push_stack(i{{32|64}} 4, i16 1)
 // CK1-64:  [[ARG:%.+]] = load i{{[0-9]+}}, i{{[0-9]+}}* [[CONV]]
 // CK1-32:  [[ARG:%.+]] = load i{{[0-9]+}}, i{{[0-9]+}}* [[ARGCADDR]]
 // CK1:  [[ARGCADDR:%.+]] = getelementptr inbounds %struct.{{.*}}, %struct.{{.*}}* %{{.*}}, i{{[0-9]+}} 0, i{{[0-9]+}} 0
@@ -62,11 +65,12 @@
 // CK1: define {{.*}}void @{{[^,]+}}(i{{.+}}** [[ARGC:%.+]])
 // CK1: [[ARGCADDR:%.+]] = alloca i{{.+}}**,
 // CK1: store i{{.+}}** [[ARGC]], i{{.+}}*** [[ARGCADDR]]
-// CK1: [[IS_SHARED:%.+]] = load i16, i16* [[KERNEL_SHARED2]],
-// CK1: [[SIZE:%.+]] = load i{{64|32}}, i{{64|32}}* [[KERNEL_SIZE2]],
-// CK1: call void @__kmpc_get_team_static_memory(i16 0, i8* addrspacecast (i8 addrspace(3)* getelementptr inbounds ([[MEM_TY]], [[MEM_TY]] addrspace(3)* [[SHARED_GLOBAL_RD]], i32 0, i32 0, i32 0) to i8*), i{{64|32}} [[SIZE]], i16 [[IS_SHARED]], i8** addrspacecast (i8* addrspace(3)* [[KERNEL_PTR]] to i8**))
-// CK1: [[KERNEL_RD:%.+]] = load i8*, i8* addrspace(3)* [[KERNEL_PTR]],
-// CK1: [[GLOBALSTACK:%.+]] = getelementptr inbounds i8, i8* [[KERNEL_RD]], i{{64|32}} 0
+// SEQ: [[IS_SHARED:%.+]] = load i16, i16* [[KERNEL_SHARED2]],
+// SEQ: [[SIZE:%.+]] = load i{{64|32}}, i{{64|32}}* [[KERNEL_SIZE2]],
+// SEQ: call void @__kmpc_get_team_static_memory(i16 0, i8* addrspacecast (i8 addrspace(3)* getelementptr inbounds ([[MEM_TY]], [[MEM_TY]] addrspace(3)* [[SHARED_GLOBAL_RD]], i32 0, i32 0, i32 0) to i8*), i{{64|32}} [[SIZE]], i16 [[IS_SHARED]], i8** addrspacecast (i8* addrspace(3)* [[KERNEL_PTR]] to i8**))
+// SEQ: [[KERNEL_RD:%.+]] = load i8*, i8* addrspace(3)* [[KERNEL_PTR]],
+// SEQ: [[GLOBALSTACK:%.+]] = getelementptr inbounds i8, i8* [[KERNEL_RD]], i{{64|32}} 0
+// PAR: [[GLOBALSTACK:%.+]] = call i8* @__kmpc_data_sharing_push_stack(i{{32|64}} {{4|8}}, i16 1)
 // CK1: [[ARG:%.+]] = load i{{[0-9]+}}**, i{{[0-9]+}}*** [[ARGCADDR]]
 // CK1: [[ARGCADDR:%.+]] = getelementptr inbounds %struct.{{.*}}, %struct.{{.*}}* %{{.*}}, i{{[0-9]+}} 0, i{{[0-9]+}} 0
 // CK1: store i{{[0-9]+}}** [[ARG]], i{{[0-9]+}}*** [[ARGCADDR]],
@@ -83,9 +87,11 @@
 
 // Test target codegen - host bc file has to be created first.
 // RUN: %clang_cc1 -DCK2 -verify -fopenmp -x c++ -triple powerpc64le-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm-bc %s -o %t-ppc-host.bc
-// RUN: %clang_cc1 -DCK2 -verify -fopenmp -x c++ -triple nvptx64-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o - | FileCheck %s --check-prefix CK2 --check-prefix CK2-64
+// RUN: %clang_cc1 -DCK2 -verify -fopenmp -x c++ -triple nvptx64-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o - | FileCheck %s --check-prefix CK2 --check-prefix CK2-64 --check-prefix SEQ2
+// RUN: %clang_cc1 -DCK2 -verify -fopenmp -x c++ -triple nvptx64-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o - -fopenmp-cuda-parallel-target-regions | FileCheck %s --check-prefix CK2 --check-prefix CK2-64 --check-prefix PAR2
 // RUN: %clang_cc1 -DCK2 -verify -fopenmp -x c++ -triple i386-unknown-unknown -fopenmp-targets=nvptx-nvidia-cuda -emit-llvm-bc %s -o %t-x86-host.bc
-// RUN: %clang_cc1 -DCK2 -verify -fopenmp -x c++ -triple nvptx-unknown-unknown -fopenmp-targets=nvptx-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-x86-host.bc -o - | FileCheck %s --check-prefix CK2 --check-prefix CK2-32
+// RUN: %clang_cc1 -DCK2 -verify -fopenmp -x c++ -triple nvptx-unknown-unknown -fopenmp-targets=nvptx-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-x86-host.bc -o - | FileCheck %s --check-prefix CK2 --check-prefix CK2-32 --check-prefix SEQ2
+// RUN: %clang_cc1 -DCK2 -verify -fopenmp -x c++ -triple nvptx-unknown-unknown -fopenmp-targets=nvptx-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-x86-host.bc -o - -fopenmp-cuda-parallel-target-regions | FileCheck %s --check-prefix CK2 --check-prefix CK2-32 --check-prefix PAR2
 // expected-no-diagnostics
 #ifdef CK2
 
@@ -112,13 +118,13 @@
   return tmain(argv);
 }
 
-// CK2: [[MEM_TY:%.+]] = type { [128 x i8] }
-// CK2-DAG: [[SHARED_GLOBAL_RD:@.+]] = common addrspace(3) global [[MEM_TY]] zeroinitializer
-// CK2-DAG: [[KERNEL_PTR:@.+]] = internal addrspace(3) global i8* null
-// CK2-DAG: [[KERNEL_SIZE1:@.+]] = internal unnamed_addr constant i{{64|32}} 4
-// CK2-DAG: [[KERNEL_SIZE2:@.+]] = internal unnamed_addr constant i{{64|32}} {{8|4}}
-// CK2-DAG: [[KERNEL_SHARED1:@.+]] = internal unnamed_addr constant i16 1
-// CK2-DAG: [[KERNEL_SHARED2:@.+]] = internal unnamed_addr constant i16 1
+// SEQ2: [[MEM_TY:%.+]] = type { [128 x i8] }
+// SEQ2-DAG: [[SHARED_GLOBAL_RD:@.+]] = common addrspace(3) global [[MEM_TY]] zeroinitializer
+// SEQ2-DAG: [[KERNEL_PTR:@.+]] = internal addrspace(3) global i8* null
+// SEQ2-DAG: [[KERNEL_SIZE1:@.+]] = internal unnamed_addr constant i{{64|32}} 4
+// SEQ2-DAG: [[KERNEL_SIZE2:@.+]] = internal unnamed_addr constant i{{64|32}} {{8|4}}
+// SEQ2-DAG: [[KERNEL_SHARED1:@.+]] = internal unnamed_addr constant i16 1
+// SEQ2-DAG: [[KERNEL_SHARED2:@.+]] = internal unnamed_addr constant i16 1
 
 // CK2: define {{.*}}void @{{[^,]+}}(i{{[0-9]+}} [[A_IN:%.+]], i{{[0-9]+}} [[B_IN:%.+]], i{{[0-9]+}} [[ARGC_IN:.+]])
 // CK2: [[AADDR:%.+]] = alloca i{{[0-9]+}},
@@ -130,11 +136,12 @@
 // CK2-64: [[ACONV:%.+]] = bitcast i64* [[AADDR]] to i32*
 // CK2-64: [[BCONV:%.+]] = bitcast i64* [[BADDR]] to i32*
 // CK2-64: [[CONV:%.+]] = bitcast i64* [[ARGCADDR]] to i32*
-// CK2: [[IS_SHARED:%.+]] = load i16, i16* [[KERNEL_SHARED1]],
-// CK2: [[SIZE:%.+]] = load i{{64|32}}, i{{64|32}}* [[KERNEL_SIZE1]],
-// CK2: call void @__kmpc_get_team_static_memory(i16 0, i8* addrspacecast (i8 addrspace(3)* getelementptr inbounds ([[MEM_TY]], [[MEM_TY]] addrspace(3)* [[SHARED_GLOBAL_RD]], i32 0, i32 0, i32 0) to i8*), i{{64|32}} [[SIZE]], i16 [[IS_SHARED]], i8** addrspacecast (i8* addrspace(3)* [[KERNEL_PTR]] to i8**))
-// CK2: [[KERNEL_RD:%.+]] = load i8*, i8* addrspace(3)* [[KERNEL_PTR]],
-// CK2: [[GLOBALSTACK:%.+]] = getelementptr inbounds i8, i8* [[KERNEL_RD]], i{{64|32}} 0
+// SEQ2: [[IS_SHARED:%.+]] = load i16, i16* [[KERNEL_SHARED1]],
+// SEQ2: [[SIZE:%.+]] = load i{{64|32}}, i{{64|32}}* [[KERNEL_SIZE1]],
+// SEQ2: call void @__kmpc_get_team_static_memory(i16 0, i8* addrspacecast (i8 addrspace(3)* getelementptr inbounds ([[MEM_TY]], [[MEM_TY]] addrspace(3)* [[SHARED_GLOBAL_RD]], i32 0, i32 0, i32 0) to i8*), i{{64|32}} [[SIZE]], i16 [[IS_SHARED]], i8** addrspacecast (i8* addrspace(3)* [[KERNEL_PTR]] to i8**))
+// SEQ2: [[KERNEL_RD:%.+]] = load i8*, i8* addrspace(3)* [[KERNEL_PTR]],
+// SEQ2: [[GLOBALSTACK:%.+]] = getelementptr inbounds i8, i8* [[KERNEL_RD]], i{{64|32}} 0
+// PAR2: [[GLOBALSTACK:%.+]] = call i8* @__kmpc_data_sharing_push_stack(i{{32|64}} 4, i16 1)
 // CK2-64:  [[ARG:%.+]] = load i{{[0-9]+}}, i{{[0-9]+}}* [[CONV]]
 // CK2-32:  [[ARG:%.+]] = load i{{[0-9]+}}, i{{[0-9]+}}* [[ARGCADDR]]
 // CK2:  [[ARGCADDR:%.+]] = getelementptr inbounds %struct.{{.*}}, %struct.{{.*}}* %{{.*}}, i{{[0-9]+}} 0, i{{[0-9]+}} 0
@@ -155,11 +162,12 @@
 // CK2: store i{{[0-9]+}} [[A_IN]], i{{[0-9]+}}* [[AADDR]],
 // CK2: store i{{[0-9]+}} [[B_IN]], i{{[0-9]+}}* [[BADDR]],
 // CK2: store i{{[0-9]+}}** [[ARGC]], i{{[0-9]+}}*** [[ARGCADDR]],
-// CK2: [[IS_SHARED:%.+]] = load i16, i16* [[KERNEL_SHARED2]],
-// CK2: [[SIZE:%.+]] = load i{{64|32}}, i{{64|32}}* [[KERNEL_SIZE2]],
-// CK2: call void @__kmpc_get_team_static_memory(i16 0, i8* addrspacecast (i8 addrspace(3)* getelementptr inbounds ([[MEM_TY]], [[MEM_TY]] addrspace(3)* [[SHARED_GLOBAL_RD]], i32 0, i32 0, i32 0) to i8*), i{{64|32}} [[SIZE]], i16 [[IS_SHARED]], i8** addrspacecast (i8* addrspace(3)* [[KERNEL_PTR]] to i8**))
-// CK2: [[KERNEL_RD:%.+]] = load i8*, i8* addrspace(3)* [[KERNEL_PTR]],
-// CK2: [[GLOBALSTACK:%.+]] = getelementptr inbounds i8, i8* [[KERNEL_RD]], i{{64|32}} 0
+// SEQ2: [[IS_SHARED:%.+]] = load i16, i16* [[KERNEL_SHARED2]],
+// SEQ2: [[SIZE:%.+]] = load i{{64|32}}, i{{64|32}}* [[KERNEL_SIZE2]],
+// SEQ2: call void @__kmpc_get_team_static_memory(i16 0, i8* addrspacecast (i8 addrspace(3)* getelementptr inbounds ([[MEM_TY]], [[MEM_TY]] addrspace(3)* [[SHARED_GLOBAL_RD]], i32 0, i32 0, i32 0) to i8*), i{{64|32}} [[SIZE]], i16 [[IS_SHARED]], i8** addrspacecast (i8* addrspace(3)* [[KERNEL_PTR]] to i8**))
+// SEQ2: [[KERNEL_RD:%.+]] = load i8*, i8* addrspace(3)* [[KERNEL_PTR]],
+// SEQ2: [[GLOBALSTACK:%.+]] = getelementptr inbounds i8, i8* [[KERNEL_RD]], i{{64|32}} 0
+// PAR2: [[GLOBALSTACK:%.+]] = call i8* @__kmpc_data_sharing_push_stack(i{{32|64}} {{4|8}}, i16 1)
 // CK2: [[ARG:%.+]] = load i{{[0-9]+}}**, i{{[0-9]+}}*** [[ARGCADDR]]
 // CK2: [[ARGCADDR:%.+]] = getelementptr inbounds %struct.{{.*}}, %struct.{{.*}}* %{{.*}}, i{{[0-9]+}} 0, i{{[0-9]+}} 0
 // CK2: store i{{[0-9]+}}** [[ARG]], i{{[0-9]+}}*** [[ARGCADDR]],
diff --git a/clang/test/OpenMP/nvptx_teams_reduction_codegen.cpp b/clang/test/OpenMP/nvptx_teams_reduction_codegen.cpp
--- a/clang/test/OpenMP/nvptx_teams_reduction_codegen.cpp
+++ b/clang/test/OpenMP/nvptx_teams_reduction_codegen.cpp
@@ -1,9 +1,12 @@
 // Test target codegen - host bc file has to be created first.
 // RUN: %clang_cc1 -verify -fopenmp -x c++ -triple powerpc64le-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm-bc %s -o %t-ppc-host.bc
-// RUN: %clang_cc1 -verify -fopenmp -x c++ -triple nvptx64-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o - | FileCheck %s --check-prefix CHECK --check-prefix CHECK-64
+// RUN: %clang_cc1 -verify -fopenmp -x c++ -triple nvptx64-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o - | FileCheck %s --check-prefix CHECK --check-prefix CHECK-64 --check-prefix SEQ
+// RUN: %clang_cc1 -verify -fopenmp -x c++ -triple nvptx64-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o - -fopenmp-cuda-parallel-target-regions | FileCheck %s --check-prefix CHECK --check-prefix CHECK-64 --check-prefix  PAR
 // RUN: %clang_cc1 -verify -fopenmp -x c++ -triple i386-unknown-unknown -fopenmp-targets=nvptx-nvidia-cuda -emit-llvm-bc %s -o %t-x86-host.bc
-// RUN: %clang_cc1 -verify -fopenmp -x c++ -triple nvptx-unknown-unknown -fopenmp-targets=nvptx-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-x86-host.bc -o - | FileCheck %s --check-prefix CHECK --check-prefix CHECK-32
-// RUN: %clang_cc1 -verify -fopenmp -fexceptions -fcxx-exceptions -x c++ -triple nvptx-unknown-unknown -fopenmp-targets=nvptx-nvidia-cuda -fopenmp-cuda-teams-reduction-recs-num=2048 -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-x86-host.bc -o - | FileCheck %s --check-prefix CHECK --check-prefix CHECK-32
+// RUN: %clang_cc1 -verify -fopenmp -x c++ -triple nvptx-unknown-unknown -fopenmp-targets=nvptx-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-x86-host.bc -o - | FileCheck %s --check-prefix CHECK --check-prefix CHECK-32 --check-prefix SEQ
+// RUN: %clang_cc1 -verify -fopenmp -fexceptions -fcxx-exceptions -x c++ -triple nvptx-unknown-unknown -fopenmp-targets=nvptx-nvidia-cuda -fopenmp-cuda-teams-reduction-recs-num=2048 -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-x86-host.bc -o - | FileCheck %s --check-prefix CHECK --check-prefix CHECK-32 --check-prefix SEQ
+// RUN: %clang_cc1 -verify -fopenmp -x c++ -triple nvptx-unknown-unknown -fopenmp-targets=nvptx-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-x86-host.bc -o - -fopenmp-cuda-parallel-target-regions | FileCheck %s --check-prefix CHECK --check-prefix CHECK-32 --check-prefix PAR
+// RUN: %clang_cc1 -verify -fopenmp -fexceptions -fcxx-exceptions -x c++ -triple nvptx-unknown-unknown -fopenmp-targets=nvptx-nvidia-cuda -fopenmp-cuda-teams-reduction-recs-num=2048 -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-x86-host.bc -o - -fopenmp-cuda-parallel-target-regions | FileCheck %s --check-prefix CHECK --check-prefix CHECK-32 --check-prefix PAR
 // expected-no-diagnostics
 #ifndef HEADER
 #define HEADER
@@ -12,21 +15,21 @@
 // CHECK-DAG: [[TEAM2_REDUCE_TY:%.+]] = type { [{{1024|2048}} x i8], [{{1024|2048}} x float] }
 // CHECK-DAG: [[TEAM3_REDUCE_TY:%.+]] = type { [{{1024|2048}} x i32], [{{1024|2048}} x i16] }
 // CHECK-DAG: [[TEAMS_REDUCE_UNION_TY:%.+]] = type { [[TEAM1_REDUCE_TY]] }
-// CHECK-DAG: [[MAP_TY:%.+]] = type { [128 x i8] }
+// SEQ-DAG: [[MAP_TY:%.+]] = type { [128 x i8] }
 
-// CHECK-DAG: [[KERNEL_PTR:@.+]] = internal addrspace(3) global i8* null
-// CHECK-DAG: [[KERNEL_SHARED1:@.+]] = internal unnamed_addr constant i16 1
-// CHECK-DAG: [[KERNEL_SHARED2:@.+]] = internal unnamed_addr constant i16 1
-// CHECK-DAG: [[KERNEL_SIZE1:@.+]] = internal unnamed_addr constant i{{64|32}} {{16|8}}
-// CHECK-DAG: [[KERNEL_SIZE2:@.+]] = internal unnamed_addr constant i{{64|32}} 16
+// SEQ-DAG: [[KERNEL_PTR:@.+]] = internal addrspace(3) global i8* null
+// SEQ-DAG: [[KERNEL_SHARED1:@.+]] = internal unnamed_addr constant i16 1
+// SEQ-DAG: [[KERNEL_SHARED2:@.+]] = internal unnamed_addr constant i16 1
+// SEQ-DAG: [[KERNEL_SIZE1:@.+]] = internal unnamed_addr constant i{{64|32}} {{16|8}}
+// SEQ-DAG: [[KERNEL_SIZE2:@.+]] = internal unnamed_addr constant i{{64|32}} 16
 
 // Check for the data transfer medium in shared memory to transfer the reduction list to the first warp.
 // CHECK-DAG: [[TRANSFER_STORAGE:@.+]] = common addrspace([[SHARED_ADDRSPACE:[0-9]+]]) global [32 x i32]
 
 // Check that the execution mode of 2 target regions is set to Non-SPMD and the 3rd is in SPMD.
-// CHECK-DAG: {{@__omp_offloading_.+l41}}_exec_mode = weak constant i8 1
-// CHECK-DAG: {{@__omp_offloading_.+l47}}_exec_mode = weak constant i8 1
-// CHECK-DAG: {{@__omp_offloading_.+l54}}_exec_mode = weak constant i8 0
+// CHECK-DAG: {{@__omp_offloading_.+l44}}_exec_mode = weak constant i8 1
+// CHECK-DAG: {{@__omp_offloading_.+l50}}_exec_mode = weak constant i8 1
+// CHECK-DAG: {{@__omp_offloading_.+l57}}_exec_mode = weak constant i8 0
 
 // CHECK-DAG: [[TEAMS_RED_BUFFER:@.+]] = internal global [[TEAMS_REDUCE_UNION_TY]] zeroinitializer
 
@@ -70,9 +73,9 @@
   return a;
 }
 
-  // CHECK-LABEL: define {{.*}}void {{@__omp_offloading_.+template.+l41}}_worker()
+  // CHECK-LABEL: define {{.*}}void {{@__omp_offloading_.+template.+l44}}_worker()
 
-  // CHECK: define {{.*}}void [[T1:@__omp_offloading_.+template.+l41]](
+  // CHECK: define {{.*}}void [[T1:@__omp_offloading_.+template.+l44]](
   //
   // CHECK: {{call|invoke}} void [[T1]]_worker()
   //
@@ -337,9 +340,9 @@
   // CHECK: call void [[REDUCTION_FUNC]](i8* [[RL_BC]], i8* [[LOCAL_RL_BC]])
   // CHECK: ret void
 
-  // CHECK-LABEL: define {{.*}}void {{@__omp_offloading_.+template.+l47}}_worker()
+  // CHECK-LABEL: define {{.*}}void {{@__omp_offloading_.+template.+l50}}_worker()
 
-  // CHECK: define {{.*}}void [[T2:@__omp_offloading_.+template.+l47]](
+  // CHECK: define {{.*}}void [[T2:@__omp_offloading_.+template.+l50]](
   //
   // CHECK: {{call|invoke}} void [[T2]]_worker()
 
@@ -704,13 +707,13 @@
   // CHECK: call void [[REDUCTION_FUNC]](i8* [[RL_BC]], i8* [[LOCAL_RL_BC]])
   // CHECK: ret void
 
-  // CHECK-LABEL: define {{.*}}void {{@__omp_offloading_.+template.+l54}}(
+  // CHECK-LABEL: define {{.*}}void {{@__omp_offloading_.+template.+l57}}(
   //
   // CHECK: call void @__kmpc_spmd_kernel_init(
   // CHECK: call void @__kmpc_data_sharing_init_stack_spmd()
   // CHECK: call void @__kmpc_spmd_kernel_deinit_v2(i16 1)
 
-  // CHECK-NOT: call void @__kmpc_get_team_static_memory
+  // CHECK-NOT: call void @{{__kmpc_get_team_static_memory|__kmpc_data_sharing_push_stack}}
   // CHECK: store i32 0,
   // CHECK: store i32 0,
   // CHECK: store i32 0, i32* [[A_ADDR:%.+]], align