[OpenMP][deviceRTLs] Update return type of function __kmpc_parallel_level

[tianshilei1992]

Summary

In deviceRTLs, the parallel level is stored in a shared variable of type uint8_t.
__kmpc_parallel_level currently returns a 16-bit interger. This patch first
changes the return type of the function to uint8_t, same as the shared variable,
and then corrects function type which was updated in D105955.

[tianshilei1992]

update

[jdoerfert]

LG

llvm/include/llvm/Frontend/OpenMP/OMPKinds.def

 
 __OMP_RTL(__kmpc_shuffle_int64, false, Int64, Int64, Int16, Int16)
 
 __OMP_RTL(__kmpc_alloc_shared, false, VoidPtr, SizeTy)
 __OMP_RTL(__kmpc_free_shared, false, Void, VoidPtr)
 __OMP_RTL(__kmpc_begin_sharing_variables, false, Void, VoidPtrPtrPtr, SizeTy)
 __OMP_RTL(__kmpc_end_sharing_variables, false, Void, )
 __OMP_RTL(__kmpc_get_shared_variables, false, Void, VoidPtrPtrPtr)
-__OMP_RTL(__kmpc_parallel_level, false, Int16, IdentPtr, Int32)
+__OMP_RTL(__kmpc_parallel_level, false, Int8, )
 __OMP_RTL(__kmpc_is_spmd_exec_mode, false, Int8, )
 __OMP_RTL(__kmpc_barrier_simple_spmd, false, Void, IdentPtr, Int32)
 
 __OMP_RTL(__kmpc_warp_active_thread_mask, false, LanemaskTy,)
 __OMP_RTL(__kmpc_syncwarp, false, Void, LanemaskTy)
 
 __OMP_RTL(__last, false, Void, )
 

openmp/libomptarget/deviceRTLs/common/src/parallel.cu

EXTERN void __kmpc_end_serialized_parallel(kmp_Ident *loc,
   omptarget_nvptx_threadPrivateContext->SetTopLevelTaskDescr(
       threadId, currTaskDescr->GetPrevTaskDescr());
   // free
   SafeFree(currTaskDescr, "new seq parallel task");
   currTaskDescr = getMyTopTaskDescriptor(threadId);
   currTaskDescr->RestoreLoopData();
 }
 
-EXTERN uint16_t __kmpc_parallel_level() {
+EXTERN uint8_t __kmpc_parallel_level() {
   return parallelLevel[GetWarpId()] & (OMP_ACTIVE_PARALLEL_LEVEL - 1);
 }
 
 // This kmpc call returns the thread id across all teams. It's value is
 // cached by the compiler and used when calling the runtime. On nvptx
 // it's cheap to recalculate this value so we never use the result
 // of this call.
 EXTERN int32_t __kmpc_global_thread_num(kmp_Ident *loc) {

openmp/libomptarget/deviceRTLs/interface.h

 typedef enum omp_proc_bind_t {
   omp_proc_bind_false = 0,
   omp_proc_bind_true = 1,
   omp_proc_bind_master = 2,
   omp_proc_bind_close = 3,
   omp_proc_bind_spread = 4
 } omp_proc_bind_t;
 
 EXTERN double omp_get_wtick(void);
 EXTERN double omp_get_wtime(void);
 
 EXTERN void omp_set_num_threads(int num);
 EXTERN int omp_get_num_threads(void);
 EXTERN int omp_get_max_threads(void);
 EXTERN int omp_get_thread_limit(void);
 EXTERN int omp_get_thread_num(void);
 EXTERN int omp_get_num_procs(void);
 EXTERN int omp_in_parallel(void);
 EXTERN int omp_in_final(void);
 EXTERN void omp_set_dynamic(int flag);
 EXTERN int omp_get_dynamic(void);
 EXTERN void omp_set_nested(int flag);
 EXTERN int omp_get_nested(void);
 EXTERN void omp_set_max_active_levels(int level);
 EXTERN int omp_get_max_active_levels(void);
 EXTERN int omp_get_level(void);
 EXTERN int omp_get_active_level(void);
 EXTERN int omp_get_ancestor_thread_num(int level);
 EXTERN int omp_get_team_size(int level);
 
 EXTERN void omp_init_lock(omp_lock_t *lock);
 EXTERN void omp_init_nest_lock(omp_nest_lock_t *lock);
 EXTERN void omp_destroy_lock(omp_lock_t *lock);
 EXTERN void omp_destroy_nest_lock(omp_nest_lock_t *lock);
 EXTERN void omp_set_lock(omp_lock_t *lock);
 EXTERN void omp_set_nest_lock(omp_nest_lock_t *lock);

 ////////////////////////////////////////////////////////////////////////////////
 
 // parallel
 EXTERN int32_t __kmpc_global_thread_num(kmp_Ident *loc);
 EXTERN void __kmpc_push_num_threads(kmp_Ident *loc, int32_t global_tid,
                                     int32_t num_threads);
 EXTERN void __kmpc_serialized_parallel(kmp_Ident *loc, uint32_t global_tid);
 EXTERN void __kmpc_end_serialized_parallel(kmp_Ident *loc, uint32_t global_tid);
-EXTERN uint16_t __kmpc_parallel_level();
+EXTERN uint8_t __kmpc_parallel_level();
 
 // proc bind
 EXTERN void __kmpc_push_proc_bind(kmp_Ident *loc, uint32_t global_tid,
                                   int proc_bind);
 EXTERN int omp_get_num_places(void);
 EXTERN int omp_get_place_num_procs(int place_num);
 EXTERN void omp_get_place_proc_ids(int place_num, int *ids);
 EXTERN int omp_get_place_num(void);