[OpenMP] Add a new version of the SPMD deinit kernel function

[gtbercea]

Summary

This patch adds a new runtime for the SPMD deinit kernel function which replaces the previous function. The new function takes as argument the flag which signals whether the runtime is required or not. This enables the compiler to optimize out the part of the deinit function which are not needed.

[gtbercea]

Delete old function.

[ABataev]

test/OpenMP/nvptx_target_parallel_codegen.cpp

71

Add the argument checks in all updated tests.

[gtbercea]

Add constant values to function calls.

[ABataev]

LG

lib/CodeGen/CGOpenMPRuntimeNVPTX.cpp

enum OpenMPRTLFunctionNVPTX {
   /// Call to void __kmpc_kernel_init(kmp_int32 thread_limit,
   /// int16_t RequiresOMPRuntime);
   OMPRTL_NVPTX__kmpc_kernel_init,
   /// Call to void __kmpc_kernel_deinit(int16_t IsOMPRuntimeInitialized);
   OMPRTL_NVPTX__kmpc_kernel_deinit,
   /// Call to void __kmpc_spmd_kernel_init(kmp_int32 thread_limit,
   /// int16_t RequiresOMPRuntime, int16_t RequiresDataSharing);
   OMPRTL_NVPTX__kmpc_spmd_kernel_init,
-  /// Call to void __kmpc_spmd_kernel_deinit();
-  OMPRTL_NVPTX__kmpc_spmd_kernel_deinit,
+  /// Call to void __kmpc_spmd_kernel_deinit_v2(int16_t RequiresOMPRuntime);
+  OMPRTL_NVPTX__kmpc_spmd_kernel_deinit_v2,
   /// Call to void __kmpc_kernel_prepare_parallel(void
   /// *outlined_function, int16_t
   /// IsOMPRuntimeInitialized);
   OMPRTL_NVPTX__kmpc_kernel_prepare_parallel,
   /// Call to bool __kmpc_kernel_parallel(void **outlined_function,
   /// int16_t IsOMPRuntimeInitialized);
   OMPRTL_NVPTX__kmpc_kernel_parallel,
   /// Call to void __kmpc_kernel_end_parallel();
void CGOpenMPRuntimeNVPTX::emitSPMDEntryFooter(CodeGenFunction &CGF,
   if (!EST.ExitBB)
     EST.ExitBB = CGF.createBasicBlock(".exit");
 
   llvm::BasicBlock *OMPDeInitBB = CGF.createBasicBlock(".omp.deinit");
   CGF.EmitBranch(OMPDeInitBB);
 
   CGF.EmitBlock(OMPDeInitBB);
   // DeInitialize the OMP state in the runtime; called by all active threads.
+  llvm::Value *Args[] = {/*RequiresOMPRuntime=*/
+                         CGF.Builder.getInt16(RequiresFullRuntime ? 1 : 0)};
   CGF.EmitRuntimeCall(
-      createNVPTXRuntimeFunction(OMPRTL_NVPTX__kmpc_spmd_kernel_deinit), None);
+      createNVPTXRuntimeFunction(
+          OMPRTL_NVPTX__kmpc_spmd_kernel_deinit_v2), Args);
   CGF.EmitBranch(EST.ExitBB);
 
   CGF.EmitBlock(EST.ExitBB);
   EST.ExitBB = nullptr;
 }
 
 // Create a unique global variable to indicate the execution mode of this target
 // region. The execution mode is either 'generic', or 'spmd' depending on the
case OMPRTL_NVPTX__kmpc_spmd_kernel_init: {
     // Build void __kmpc_spmd_kernel_init(kmp_int32 thread_limit,
     // int16_t RequiresOMPRuntime, int16_t RequiresDataSharing);
     llvm::Type *TypeParams[] = {CGM.Int32Ty, CGM.Int16Ty, CGM.Int16Ty};
     auto *FnTy =
         llvm::FunctionType::get(CGM.VoidTy, TypeParams, /*isVarArg*/ false);
     RTLFn = CGM.CreateRuntimeFunction(FnTy, "__kmpc_spmd_kernel_init");
     break;
   }
-  case OMPRTL_NVPTX__kmpc_spmd_kernel_deinit: {
-    // Build void __kmpc_spmd_kernel_deinit();
+  case OMPRTL_NVPTX__kmpc_spmd_kernel_deinit_v2: {
+    // Build void __kmpc_spmd_kernel_deinit_v2(int16_t RequiresOMPRuntime);
+    llvm::Type *TypeParams[] = {CGM.Int16Ty};
     auto *FnTy =
-        llvm::FunctionType::get(CGM.VoidTy, llvm::None, /*isVarArg*/ false);
-    RTLFn = CGM.CreateRuntimeFunction(FnTy, "__kmpc_spmd_kernel_deinit");
+        llvm::FunctionType::get(CGM.VoidTy, TypeParams, /*isVarArg*/ false);
+    RTLFn = CGM.CreateRuntimeFunction(FnTy, "__kmpc_spmd_kernel_deinit_v2");
     break;
   }
   case OMPRTL_NVPTX__kmpc_kernel_prepare_parallel: {
     /// Build void __kmpc_kernel_prepare_parallel(
     /// void *outlined_function, int16_t IsOMPRuntimeInitialized);
     llvm::Type *TypeParams[] = {CGM.Int8PtrTy, CGM.Int16Ty};
     auto *FnTy =
         llvm::FunctionType::get(CGM.VoidTy, TypeParams, /*isVarArg*/ false);

test/OpenMP/nvptx_target_parallel_codegen.cpp

int bar(int n){
   // CHECK: call void @__kmpc_data_sharing_init_stack_spmd
   // CHECK: br label {{%?}}[[EXEC:.+]]
   //
   // CHECK: [[EXEC]]
   // CHECK: {{call|invoke}} void [[OP1:@.+]]({{.+}}, {{.+}}, i16* [[AA]])
   // CHECK: br label {{%?}}[[DONE:.+]]
   //
   // CHECK: [[DONE]]
-  // CHECK: call void @__kmpc_spmd_kernel_deinit()
+  // CHECK: call void @__kmpc_spmd_kernel_deinit_v2(i16 1)
   // CHECK: br label {{%?}}[[EXIT:.+]]
   //
   // CHECK: [[EXIT]]
   // CHECK: ret void
   // CHECK: }
 
   // CHECK: define internal void [[OP1]](i32* noalias %.global_tid., i32* noalias %.bound_tid., i16* {{[^%]*}}[[ARG:%.+]])
   // CHECK: = alloca i32*, align
int bar(int n){
   // CHECK: call void @__kmpc_data_sharing_init_stack_spmd
   // CHECK: br label {{%?}}[[EXEC:.+]]
   //
   // CHECK: [[EXEC]]
   // CHECK: {{call|invoke}} void [[OP2:@.+]]({{.+}}, {{.+}}, i32* [[A]], i16* [[AA]], [10 x i32]* [[B]])
   // CHECK: br label {{%?}}[[DONE:.+]]
   //
   // CHECK: [[DONE]]
-  // CHECK: call void @__kmpc_spmd_kernel_deinit()
+  // CHECK: call void @__kmpc_spmd_kernel_deinit_v2(i16 1)
   // CHECK: br label {{%?}}[[EXIT:.+]]
   //
   // CHECK: [[EXIT]]
   // CHECK: ret void
   // CHECK: }
 
   // CHECK: define internal void [[OP2]](i32* noalias %.global_tid., i32* noalias %.bound_tid., i32* {{[^%]*}}[[ARG1:%.+]], i16* {{[^%]*}}[[ARG2:%.+]], [10 x i32]* {{[^%]*}}[[ARG3:%.+]])
   // CHECK: = alloca i32*, align

test/OpenMP/nvptx_target_parallel_proc_bind_codegen.cpp

int bar(int n){
   // CHECK: br label {{%?}}[[EXEC:.+]]
   //
   // CHECK: [[EXEC]]
   // CHECK-NOT: call void @__kmpc_push_proc_bind
   // CHECK: {{call|invoke}} void [[OP1:@.+]](
   // CHECK: br label {{%?}}[[DONE:.+]]
   //
   // CHECK: [[DONE]]
-  // CHECK: call void @__kmpc_spmd_kernel_deinit()
+  // CHECK: call void @__kmpc_spmd_kernel_deinit_v2(i16 1)
   // CHECK: br label {{%?}}[[EXIT:.+]]
   //
   // CHECK: [[EXIT]]
   // CHECK: ret void
   // CHECK: }
 
 
 
 
 
   // CHECK-LABEL: define {{.*}}void {{@__omp_offloading_.+template.+l26}}(
   // CHECK: call void @__kmpc_spmd_kernel_init(i32 {{.+}}, i16 1, i16 0)
   // CHECK: call void @__kmpc_data_sharing_init_stack_spmd
   // CHECK: br label {{%?}}[[EXEC:.+]]
   //
   // CHECK: [[EXEC]]
   // CHECK-NOT: call void @__kmpc_push_proc_bind
   // CHECK: {{call|invoke}} void [[OP1:@.+]](
   // CHECK: br label {{%?}}[[DONE:.+]]
   //
   // CHECK: [[DONE]]
-  // CHECK: call void @__kmpc_spmd_kernel_deinit()
+  // CHECK: call void @__kmpc_spmd_kernel_deinit_v2(i16 1)
   // CHECK: br label {{%?}}[[EXIT:.+]]
   //
   // CHECK: [[EXIT]]
   // CHECK: ret void
   // CHECK: }
 
 
 
 
   // CHECK-LABEL: define {{.*}}void {{@__omp_offloading_.+template.+l31}}(
   // CHECK: call void @__kmpc_spmd_kernel_init(i32 {{.+}}, i16 1, i16 0)
   // CHECK: call void @__kmpc_data_sharing_init_stack_spmd
   // CHECK: br label {{%?}}[[EXEC:.+]]
   //
   // CHECK: [[EXEC]]
   // CHECK-NOT: call void @__kmpc_push_proc_bind
   // CHECK: {{call|invoke}} void [[OP1:@.+]](
   // CHECK: br label {{%?}}[[DONE:.+]]
   //
   // CHECK: [[DONE]]
-  // CHECK: call void @__kmpc_spmd_kernel_deinit()
+  // CHECK: call void @__kmpc_spmd_kernel_deinit_v2(i16 1)
   // CHECK: br label {{%?}}[[EXIT:.+]]
   //
   // CHECK: [[EXIT]]
   // CHECK: ret void
   // CHECK: }
 #endif

test/OpenMP/nvptx_target_parallel_reduction_codegen.cpp

int bar(int n){
   // CHECK: define {{.*}}void {{@__omp_offloading_.+template.+l27}}(
   //
   // CHECK: call void @__kmpc_spmd_kernel_init(i32 {{.+}}, i16 1, i16 0)
   // CHECK: call void @__kmpc_data_sharing_init_stack_spmd
   // CHECK: br label {{%?}}[[EXECUTE:.+]]
   //
   // CHECK: [[EXECUTE]]
   // CHECK: {{call|invoke}} void [[PFN:@.+]](i32*
-  // CHECK: call void @__kmpc_spmd_kernel_deinit()
+  // CHECK: call void @__kmpc_spmd_kernel_deinit_v2(i16 1)
   //
   //
   // define internal void [[PFN]](
   // CHECK: store double {{[0\.e\+]+}}, double* [[E:%.+]], align
   // CHECK: [[EV:%.+]] = load double, double* [[E]], align
   // CHECK: [[ADD:%.+]] = fadd double [[EV]], 5
   // CHECK: store double [[ADD]], double* [[E]], align
   // CHECK: [[PTR1:%.+]] = getelementptr inbounds [[RLT:.+]], [1 x i8*]* [[RL:%.+]], i{{32|64}} 0, i{{32|64}} 0
int bar(int n){
   // CHECK: define {{.*}}void {{@__omp_offloading_.+template.+l32}}(
   //
   // CHECK: call void @__kmpc_spmd_kernel_init(i32 {{.+}}, i16 1, i16 0)
   // CHECK: call void @__kmpc_data_sharing_init_stack_spmd
   // CHECK: br label {{%?}}[[EXECUTE:.+]]
   //
   // CHECK: [[EXECUTE]]
   // CHECK: {{call|invoke}} void [[PFN1:@.+]](i32*
-  // CHECK: call void @__kmpc_spmd_kernel_deinit()
+  // CHECK: call void @__kmpc_spmd_kernel_deinit_v2(i16 1)
   //
   //
   // define internal void [[PFN1]](
   // CHECK: store float {{1\.[0e\+]+}}, float* [[D:%.+]], align
   // CHECK: [[C_VAL:%.+]] = load i8, i8* [[C:%.+]], align
   // CHECK: [[CONV:%.+]] = sext i8 [[C_VAL]] to i32
   // CHECK: [[XOR:%.+]] = xor i32 [[CONV]], 2
   // CHECK: [[TRUNC:%.+]] = trunc i32 [[XOR]] to i8
int bar(int n){
   // CHECK: define {{.*}}void {{@__omp_offloading_.+template.+l38}}(
   //
   // CHECK: call void @__kmpc_spmd_kernel_init(i32 {{.+}}, i16 1, i16 0)
   // CHECK: call void @__kmpc_data_sharing_init_stack_spmd
   // CHECK: br label {{%?}}[[EXECUTE:.+]]
   //
   // CHECK: [[EXECUTE]]
   // CHECK: {{call|invoke}} void [[PFN2:@.+]](i32*
-  // CHECK: call void @__kmpc_spmd_kernel_deinit()
+  // CHECK: call void @__kmpc_spmd_kernel_deinit_v2(i16 1)
   //
   //
   // define internal void [[PFN2]](
   // CHECK: store i32 0, i32* [[A:%.+]], align
   // CHECK: store i16 -32768, i16* [[B:%.+]], align
   // CHECK: [[A_VAL:%.+]] = load i32, i32* [[A:%.+]], align
   // CHECK: [[OR:%.+]] = or i32 [[A_VAL]], 1
   // CHECK: store i32 [[OR]], i32* [[A]], align

test/OpenMP/nvptx_target_teams_codegen.cpp

 // CHECK: define weak void @__omp_offloading_{{.*}}ftemplate{{.*}}_l37(
 // CHECK: call void @__kmpc_spmd_kernel_init(i32 {{.+}}, i16 1, i16 0)
 // CHECK: call void @__kmpc_data_sharing_init_stack_spmd
 // CHECK-NOT: call i8* @__kmpc_data_sharing_push_stack(
 // CHECK-NOT: call void @__kmpc_serialized_parallel(
 // CHECK: call void [[L0:@.+]](i32* %{{.+}}, i32* %{{.+}}, i16* %{{.*}})
 // CHECK-NOT: call void @__kmpc_end_serialized_parallel(
 // CHECK-NOT: call void @__kmpc_data_sharing_pop_stack(
-// CHECK: call void @__kmpc_spmd_kernel_deinit()
+// CHECK: call void @__kmpc_spmd_kernel_deinit_v2(i16 1)
 // CHECK: ret
 
 // CHECK: define internal void [[L0]](i32* noalias %{{.+}}, i32* noalias %{{.+}}, i16* dereferenceable
 // CHECK: call void @__kmpc_serialized_parallel(
 // CHECK: call void [[L1:@.+]](i32* %{{.+}}, i32* %{{.+}}, i16* %{{.+}})
 // CHECK: call void @__kmpc_end_serialized_parallel(
 // CHECK: ret void
 
 // CHECK: define internal void [[L1]](i32* noalias %{{.+}}, i32* noalias %{{.+}}, i16* dereferenceable
 // CHECK: store i16 1, i16* %
 // CHECK: ret void
 
 #endif

test/OpenMP/nvptx_target_teams_distribute_parallel_for_codegen.cpp

 // CHECK: call void @__kmpc_get_team_static_memory(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}} 4, i16 1, i8** addrspacecast (i8* addrspace(3)* [[KERNEL_PTR]] to i8**))
 // CHECK: [[TEAM_ALLOC:%.+]] = load i8*, i8* addrspace(3)* [[KERNEL_PTR]],
 // CHECK: [[BC:%.+]] = bitcast i8* [[TEAM_ALLOC]] 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: call void @__kmpc_restore_team_static_memory(i16 1)
-// CHECK: call void @__kmpc_spmd_kernel_deinit()
+// CHECK: call void @__kmpc_spmd_kernel_deinit_v2(i16 0)
 // CHECK: ret void
 
 // CHECK: define internal void [[OUTL1]](
 // CHECK: call void @__kmpc_for_static_init_4({{.+}}, {{.+}}, {{.+}} 33,
 // CHECK: call void @__kmpc_for_static_fini(
 // CHECK: ret void
 
 // CHECK-LABEL: define {{.*}}void {{@__omp_offloading_.+}}(
 // 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_for_static_init_4({{.+}}, {{.+}}, {{.+}} 91,
 // CHECK: {{call|invoke}} void [[OUTL2:@.+]](
 // CHECK: call void @__kmpc_for_static_fini(
-// CHECK: call void @__kmpc_spmd_kernel_deinit()
+// CHECK: call void @__kmpc_spmd_kernel_deinit_v2(i16 0)
 // CHECK: ret void
 
 // CHECK: define internal void [[OUTL2]](
 // CHECK: call void @__kmpc_for_static_init_4({{.+}}, {{.+}}, {{.+}} 33,
 // CHECK: call void @__kmpc_for_static_fini(
 // CHECK: ret void
 
 // CHECK-LABEL: define {{.*}}void {{@__omp_offloading_.+}}(
 // 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_for_static_init_4({{.+}}, {{.+}}, {{.+}} 91,
 // CHECK: {{call|invoke}} void [[OUTL3:@.+]](
 // CHECK: call void @__kmpc_for_static_fini(
-// CHECK: call void @__kmpc_spmd_kernel_deinit()
+// CHECK: call void @__kmpc_spmd_kernel_deinit_v2(i16 0)
 // CHECK: ret void
 
 // CHECK: define internal void [[OUTL3]](
 // CHECK: call void @__kmpc_for_static_init_4({{.+}}, {{.+}}, {{.+}} 33,
 // CHECK: call void @__kmpc_for_static_fini(
 // CHECK: ret void
 
 // Distribute with collapse(2)

 // CHECK: store{{.+}} [[EUB_RES_1]], {{.+}}* [[OMP_UB]],
 
 // Store LB in IV
 // CHECK-DAG: [[OMP_LB_VAL_3:%.+]] = load{{.+}}, {{.+}} [[OMP_LB]],
 // CHECK: store{{.+}} [[OMP_LB_VAL_3]], {{.+}}* [[OMP_IV]],
 
 // CHECK: [[DIST_INNER_LOOP_END]]:
 // CHECK: call void @__kmpc_for_static_fini(
-// CHECK: call void @__kmpc_spmd_kernel_deinit()
+// CHECK: call void @__kmpc_spmd_kernel_deinit_v2(i16 0)
 // CHECK: ret void
 
 // CHECK: define internal void [[OUTL4]](
 // CHECK: call void @__kmpc_for_static_init_4({{.+}}, {{.+}}, {{.+}} 33,
 // CHECK: call void @__kmpc_for_static_fini(
 // CHECK: ret void
 
 // CHECK: define weak void @__omp_offloading_{{.*}}_l56(i[[SZ:64|32]] %{{[^,]+}}, [1000 x i32]* 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]* dereferenceable{{.*}}, i32* %{{.*}})
 
 #endif

test/OpenMP/nvptx_target_teams_distribute_parallel_for_generic_mode_codegen.cpp

 // CHECK: call void @__kmpc_for_static_init_4(
 
 // CHECK: call void [[PARALLEL:@.+]](i32* %{{.*}}, i32* %{{.+}}, i{{64|32}} %{{.+}}, i{{64|32}} %{{.*}}, i{{64|32}} %{{.*}}, i32* %{{.*}})
 // CHECK: br label %
 
 
 // CHECK: call void @__kmpc_for_static_fini(%struct.ident_t* @
 
-// CHECK: call void @__kmpc_spmd_kernel_deinit()
+// CHECK: call void @__kmpc_spmd_kernel_deinit_v2(i16 0)
 
 // CHECK: define internal void [[PARALLEL]](i32* noalias %{{.+}}, i32* noalias %{{.+}}, i{{64|32}} %{{.+}}, i{{64|32}} %{{.+}}, i{{64|32}} [[ARGC:%.+]], i32* dereferenceable{{.*}})
 // CHECK-NOT: call i8* @__kmpc_data_sharing_push_stack(
 // CHECK: alloca i{{[0-9]+}},
 // CHECK: alloca i{{[0-9]+}},
 // CHECK: [[ARGC_ADDR:%.+]] = alloca i{{32|64}},
 // CHECK: alloca i{{[0-9]+}},
 // CHECK: alloca i{{[0-9]+}},

test/OpenMP/nvptx_target_teams_distribute_parallel_for_simd_codegen.cpp

 // CHECK: call void @__kmpc_get_team_static_memory(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}} 4, i16 1, i8** addrspacecast (i8* addrspace(3)* [[KERNEL_PTR]] to i8**))
 // CHECK: [[TEAM_ALLOC:%.+]] = load i8*, i8* addrspace(3)* [[KERNEL_PTR]],
 // CHECK: [[BC:%.+]] = bitcast i8* [[TEAM_ALLOC]] 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: call void @__kmpc_restore_team_static_memory(i16 1)
-// CHECK: call void @__kmpc_spmd_kernel_deinit()
+// CHECK: call void @__kmpc_spmd_kernel_deinit_v2(i16 0)
 // CHECK: ret void
 
 // CHECK: define internal void [[OUTL1]](
 // CHECK: call void @__kmpc_for_static_init_4({{.+}}, {{.+}}, {{.+}} 33,
 // CHECK: call void @__kmpc_for_static_fini(
 // CHECK: ret void
 
 // CHECK-LABEL: define {{.*}}void {{@__omp_offloading_.+}}(
 // 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_for_static_init_4({{.+}}, {{.+}}, {{.+}} 91,
 // CHECK: {{call|invoke}} void [[OUTL2:@.+]](
 // CHECK: call void @__kmpc_for_static_fini(
-// CHECK: call void @__kmpc_spmd_kernel_deinit()
+// CHECK: call void @__kmpc_spmd_kernel_deinit_v2(i16 0)
 // CHECK: ret void
 
 // CHECK: define internal void [[OUTL2]](
 // CHECK: call void @__kmpc_for_static_init_4({{.+}}, {{.+}}, {{.+}} 33,
 // CHECK: call void @__kmpc_for_static_fini(
 // CHECK: ret void
 
 // CHECK-LABEL: define {{.*}}void {{@__omp_offloading_.+}}(
 // 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_for_static_init_4({{.+}}, {{.+}}, {{.+}} 91,
 // CHECK: {{call|invoke}} void [[OUTL3:@.+]](
 // CHECK: call void @__kmpc_for_static_fini(
-// CHECK: call void @__kmpc_spmd_kernel_deinit()
+// CHECK: call void @__kmpc_spmd_kernel_deinit_v2(i16 0)
 // CHECK: ret void
 
 // CHECK: define internal void [[OUTL3]](
 // CHECK: call void @__kmpc_for_static_init_4({{.+}}, {{.+}}, {{.+}} 33,
 // CHECK: call void @__kmpc_for_static_fini(
 // CHECK: ret void
 
 // CHECK: define {{.*}}void {{@__omp_offloading_.+}}({{.+}}, i{{32|64}} [[F_IN:%.+]])
 // CHECK: store {{.+}} [[F_IN]], {{.+}}* {{.+}},
 // 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: store {{.+}} 99, {{.+}}* [[COMB_UB:%.+]], align
 // CHECK: call void @__kmpc_for_static_init_4({{.+}}, {{.+}}, {{.+}} 91, {{.+}}, {{.+}}, {{.+}}* [[COMB_UB]],
 // CHECK: {{call|invoke}} void [[OUTL4:@.+]](
 // CHECK: call void @__kmpc_for_static_fini(
-// CHECK: call void @__kmpc_spmd_kernel_deinit()
+// CHECK: call void @__kmpc_spmd_kernel_deinit_v2(i16 0)
 // CHECK: ret void
 
 // CHECK: define internal void [[OUTL4]](
 // CHECK: call void @__kmpc_for_static_init_4({{.+}}, {{.+}}, {{.+}} 33,
 // CHECK: call void @__kmpc_for_static_fini(
 // CHECK: ret void
 
 #endif

test/OpenMP/nvptx_teams_reduction_codegen.cpp

int bar(int n){
   // CHECK: [[EXIT]]
   // CHECK: call void @__kmpc_kernel_deinit(
 
   // CHECK-LABEL: define {{.*}}void {{@__omp_offloading_.+template.+l43}}_worker()
 
   // CHECK: define {{.*}}void [[T2:@__omp_offloading_.+template.+l43]](
   //
   // CHECK: {{call|invoke}} void [[T2]]_worker()
+
   //
   // CHECK: call void @__kmpc_kernel_init(
   //
   // CHECK: store float {{1\.[0e\+]+}}, float* [[D:%.+]], align
   // CHECK: [[C_VAL:%.+]] = load i8, i8* [[C:%.+]], align
   // CHECK: [[CONV:%.+]] = sext i8 [[C_VAL]] to i32
   // CHECK: [[XOR:%.+]] = xor i32 [[CONV]], 2
   // CHECK: [[TRUNC:%.+]] = trunc i32 [[XOR]] to i8
int bar(int n){
   // CHECK: [[MAX_CONT]]
   // CHECK: [[B_MAX:%.+]] = phi i16 [ [[MAX1]], %[[DO_MAX]] ], [ [[MAX2]], %[[MAX_ELSE]] ]
   // CHECK: store i16 [[B_MAX]], i16* [[B_IN]], align
   // CHECK: call void @__kmpc_nvptx_teams_end_reduce_nowait_simple(%struct.ident_t* [[LOC]], i32 [[GTID]], [8 x i32]* [[LOCK]])
   // CHECK: br label %[[EXIT]]
   //
   // CHECK: [[EXIT]]
   // call void @__kmpc_restore_team_static_memory(i16 1)
-  // CHECK: call void @__kmpc_spmd_kernel_deinit(
+  // CHECK: call void @__kmpc_spmd_kernel_deinit_v2(i16 1)
 
   // CHECK: define internal void [[OUTLINED]](i32* noalias %{{.+}}, i32* noalias %{{.+}}, i32* dereferenceable{{.+}}, i16* dereferenceable{{.+}})
   //
   // CHECK: store i32 0, i32* [[A:%.+]], align
   // CHECK: store i16 -32768, i16* [[B:%.+]], align
   // CHECK: [[A_VAL:%.+]] = load i32, i32* [[A:%.+]], align
   // CHECK: [[OR:%.+]] = or i32 [[A_VAL]], 1
   // CHECK: store i32 [[OR]], i32* [[A]], align
int bar(int n){
   // CHECK: [[MAX_ELSE]]
   // CHECK: [[MAX2:%.+]] = load i16, i16* [[VAR2_RHS]], align
   // CHECK: br label {{%?}}[[MAX_CONT]]
   //
   // CHECK: [[MAX_CONT]]
   // CHECK: [[MAXV:%.+]] = phi i16 [ [[MAX1]], %[[DO_MAX]] ], [ [[MAX2]], %[[MAX_ELSE]] ]
   // CHECK: store i16 [[MAXV]], i16* [[VAR2_LHS]],
   // CHECK: ret void
-
   //
   // Shuffle and reduce function
   // CHECK: define internal void [[PAR_SHUFFLE_REDUCE_FN]](i8*, i16 {{.*}}, i16 {{.*}}, i16 {{.*}})
   // CHECK: [[REMOTE_RED_LIST:%.+]] = alloca [[RLT]], align
   // CHECK: [[REMOTE_ELT1:%.+]] = alloca i32
   // CHECK: [[REMOTE_ELT2:%.+]] = alloca i16
   //
   // CHECK: [[LANEID:%.+]] = load i16, i16* {{.+}}, align