[Libomptarget] Introduce new main thread ID runtime function

[jhuber6]

Summary

This patch introduces __kmpc_is_generic_main_thread_id which splits the old
comparison into its own runtime function. The purpose of this is so we can fold
this part independently, so when both this and is_spmd_mode are folded the
final function will be folded as well.

[jdoerfert]

LG, one nit.

openmp/libomptarget/deviceRTLs/interface.h

457

[jhuber6]

Fixing nit.

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

 __OMP_RTL(__kmpc_get_shared_variables, false, Void, VoidPtrPtrPtr)
 __OMP_RTL(__kmpc_parallel_level, false, Int16, IdentPtr, Int32)
 __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(__kmpc_is_generic_main_thread_id, false, Int8, Int32)
+
 __OMP_RTL(__last, false, Void, )
 
 #undef __OMP_RTL
 #undef OMP_RTL
 
 #define ParamAttrs(...) ArrayRef<AttributeSet>({__VA_ARGS__})
 #define EnumAttr(Kind) Attribute::get(Ctx, Attribute::AttrKind::Kind)
 #define EnumAttrInt(Kind, N) Attribute::get(Ctx, Attribute::AttrKind::Kind, N)

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

 }
 
 // Return true if the current target region is executed in SPMD mode.
 EXTERN int8_t __kmpc_is_spmd_exec_mode() {
   return (execution_param & ModeMask) == Spmd;
 }
 
 EXTERN int8_t __kmpc_is_generic_main_thread(kmp_int32 Tid) {
-  return !__kmpc_is_spmd_exec_mode() && GetMasterThreadID() == Tid;
+  return !__kmpc_is_spmd_exec_mode() && __kmpc_is_generic_main_thread_id(Tid);
+}
+
+NOINLINE EXTERN int8_t __kmpc_is_generic_main_thread_id(kmp_int32 Tid) {
+  return GetMasterThreadID() == Tid;
 }
 
 EXTERN bool __kmpc_kernel_parallel(void**WorkFn);
 
 static void __kmpc_target_region_state_machine(ident_t *Ident) {
 
   int TId = GetThreadIdInBlock();
   do {

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);

 
 // SPMD execution mode interrogation function.
 EXTERN int8_t __kmpc_is_spmd_exec_mode();
 
 /// Return true if the hardware thread id \p Tid represents the OpenMP main
 /// thread in generic mode outside of a parallel region.
 EXTERN int8_t __kmpc_is_generic_main_thread(kmp_int32 Tid);
 
+/// Return true if the hardware thread id \p Tid represents the OpenMP main
+/// thread in generic mode.
+EXTERN int8_t __kmpc_is_generic_main_thread_id(kmp_int32 Tid);
+
 EXTERN void __kmpc_get_team_static_memory(int16_t isSPMDExecutionMode,
                                           const void *buf, size_t size,
                                           int16_t is_shared, const void **res);
 
 EXTERN void __kmpc_restore_team_static_memory(int16_t isSPMDExecutionMode,
                                               int16_t is_shared);
 
 /// Allocate \p Bytes in "shareable" memory and return the address. Needs to be