[OpenMP][Offloading] Remove task wait in nowait interfaces

[tianshilei1992]

Summary

All nowait series of interfaces in libomptarget accept four more arguments (int32_t depNum, void *depList, int32_t noAliasDepNum, void *noAliasDepList) compared with their counterparts w/o nowait. These extra arguments were expected for dependence resolution, potentially lowered to device side. Current implementation calls libomp function __kmpc_omp_taskwait. However, the front end simply ignores them, that these four arguments are not emitted at all. As a consequence, the depNum and noAliasDepNum are garbage, which could lead to unnecessary task wait.

[grokos]

Now that target nowait operations are handled via hidden helper tasks which make sure that dependencies are satisfied, these calls to __kmpc_omp_taskwait are not only redundant but also hurt performance as they serialize execution unconditionally. LGTM. Can you edit the patch description and explain exactly what you mean and why this patch is needed? Thanks!

openmp/libomptarget/src/interface.cpp

 
 EXTERN void __tgt_target_data_begin_nowait(int64_t device_id, int32_t arg_num,
                                            void **args_base, void **args,
                                            int64_t *arg_sizes,
                                            int64_t *arg_types, int32_t depNum,
                                            void *depList, int32_t noAliasDepNum,
                                            void *noAliasDepList) {
   TIMESCOPE();
-  if (depNum + noAliasDepNum > 0)
-    __kmpc_omp_taskwait(NULL, __kmpc_global_thread_num(NULL));
 
   __tgt_target_data_begin_mapper(nullptr, device_id, arg_num, args_base, args,
                                  arg_sizes, arg_types, nullptr, nullptr);
 }
 
 EXTERN void __tgt_target_data_begin_mapper(ident_t *loc, int64_t device_id,
                                            int32_t arg_num, void **args_base,
                                            void **args, int64_t *arg_sizes,

 }
 
 EXTERN void __tgt_target_data_begin_nowait_mapper(
     ident_t *loc, int64_t device_id, int32_t arg_num, void **args_base,
     void **args, int64_t *arg_sizes, int64_t *arg_types,
     map_var_info_t *arg_names, void **arg_mappers, int32_t depNum,
     void *depList, int32_t noAliasDepNum, void *noAliasDepList) {
   TIMESCOPE_WITH_IDENT(loc);
-  if (depNum + noAliasDepNum > 0)
-    __kmpc_omp_taskwait(loc, __kmpc_global_thread_num(loc));
 
   __tgt_target_data_begin_mapper(loc, device_id, arg_num, args_base, args,
                                  arg_sizes, arg_types, arg_names, arg_mappers);
 }
 
 /// passes data from the target, releases target memory and destroys
 /// the host-target mapping (top entry from the stack of data maps)
 /// created by the last __tgt_target_data_begin.
 EXTERN void __tgt_target_data_end(int64_t device_id, int32_t arg_num,
                                   void **args_base, void **args,
                                   int64_t *arg_sizes, int64_t *arg_types) {
   TIMESCOPE();
   __tgt_target_data_end_mapper(nullptr, device_id, arg_num, args_base, args,
                                arg_sizes, arg_types, nullptr, nullptr);
 }
 
 EXTERN void __tgt_target_data_end_nowait(int64_t device_id, int32_t arg_num,
                                          void **args_base, void **args,
                                          int64_t *arg_sizes, int64_t *arg_types,
                                          int32_t depNum, void *depList,
                                          int32_t noAliasDepNum,
                                          void *noAliasDepList) {
   TIMESCOPE();
-  if (depNum + noAliasDepNum > 0)
-    __kmpc_omp_taskwait(NULL, __kmpc_global_thread_num(NULL));
 
   __tgt_target_data_end_mapper(nullptr, device_id, arg_num, args_base, args,
                                arg_sizes, arg_types, nullptr, nullptr);
 }
 
 EXTERN void __tgt_target_data_end_mapper(ident_t *loc, int64_t device_id,
                                          int32_t arg_num, void **args_base,
                                          void **args, int64_t *arg_sizes,

 }
 
 EXTERN void __tgt_target_data_end_nowait_mapper(
     ident_t *loc, int64_t device_id, int32_t arg_num, void **args_base,
     void **args, int64_t *arg_sizes, int64_t *arg_types,
     map_var_info_t *arg_names, void **arg_mappers, int32_t depNum,
     void *depList, int32_t noAliasDepNum, void *noAliasDepList) {
   TIMESCOPE_WITH_IDENT(loc);
-  if (depNum + noAliasDepNum > 0)
-    __kmpc_omp_taskwait(loc, __kmpc_global_thread_num(loc));
 
   __tgt_target_data_end_mapper(loc, device_id, arg_num, args_base, args,
                                arg_sizes, arg_types, arg_names, arg_mappers);
 }
 
 EXTERN void __tgt_target_data_update(int64_t device_id, int32_t arg_num,
                                      void **args_base, void **args,
                                      int64_t *arg_sizes, int64_t *arg_types) {
   TIMESCOPE();
   __tgt_target_data_update_mapper(nullptr, device_id, arg_num, args_base, args,
                                   arg_sizes, arg_types, nullptr, nullptr);
 }
 
 EXTERN void __tgt_target_data_update_nowait(
     int64_t device_id, int32_t arg_num, void **args_base, void **args,
     int64_t *arg_sizes, int64_t *arg_types, int32_t depNum, void *depList,
     int32_t noAliasDepNum, void *noAliasDepList) {
   TIMESCOPE();
-  if (depNum + noAliasDepNum > 0)
-    __kmpc_omp_taskwait(NULL, __kmpc_global_thread_num(NULL));
 
   __tgt_target_data_update_mapper(nullptr, device_id, arg_num, args_base, args,
                                   arg_sizes, arg_types, nullptr, nullptr);
 }
 
 EXTERN void __tgt_target_data_update_mapper(ident_t *loc, int64_t device_id,
                                             int32_t arg_num, void **args_base,
                                             void **args, int64_t *arg_sizes,

 }
 
 EXTERN void __tgt_target_data_update_nowait_mapper(
     ident_t *loc, int64_t device_id, int32_t arg_num, void **args_base,
     void **args, int64_t *arg_sizes, int64_t *arg_types,
     map_var_info_t *arg_names, void **arg_mappers, int32_t depNum,
     void *depList, int32_t noAliasDepNum, void *noAliasDepList) {
   TIMESCOPE_WITH_IDENT(loc);
-  if (depNum + noAliasDepNum > 0)
-    __kmpc_omp_taskwait(loc, __kmpc_global_thread_num(loc));
 
   __tgt_target_data_update_mapper(loc, device_id, arg_num, args_base, args,
                                   arg_sizes, arg_types, arg_names, arg_mappers);
 }
 
 EXTERN int __tgt_target(int64_t device_id, void *host_ptr, int32_t arg_num,
                         void **args_base, void **args, int64_t *arg_sizes,
                         int64_t *arg_types) {
   TIMESCOPE();
   return __tgt_target_mapper(nullptr, device_id, host_ptr, arg_num, args_base,
                              args, arg_sizes, arg_types, nullptr, nullptr);
 }
 
 EXTERN int __tgt_target_nowait(int64_t device_id, void *host_ptr,
                                int32_t arg_num, void **args_base, void **args,
                                int64_t *arg_sizes, int64_t *arg_types,
                                int32_t depNum, void *depList,
                                int32_t noAliasDepNum, void *noAliasDepList) {
   TIMESCOPE();
-  if (depNum + noAliasDepNum > 0)
-    __kmpc_omp_taskwait(NULL, __kmpc_global_thread_num(NULL));
 
   return __tgt_target_mapper(nullptr, device_id, host_ptr, arg_num, args_base,
                              args, arg_sizes, arg_types, nullptr, nullptr);
 }
 
 EXTERN int __tgt_target_mapper(ident_t *loc, int64_t device_id, void *host_ptr,
                                int32_t arg_num, void **args_base, void **args,
                                int64_t *arg_sizes, int64_t *arg_types,

 }
 
 EXTERN int __tgt_target_nowait_mapper(
     ident_t *loc, int64_t device_id, void *host_ptr, int32_t arg_num,
     void **args_base, void **args, int64_t *arg_sizes, int64_t *arg_types,
     map_var_info_t *arg_names, void **arg_mappers, int32_t depNum,
     void *depList, int32_t noAliasDepNum, void *noAliasDepList) {
   TIMESCOPE_WITH_IDENT(loc);
-  if (depNum + noAliasDepNum > 0)
-    __kmpc_omp_taskwait(loc, __kmpc_global_thread_num(loc));
 
   return __tgt_target_mapper(loc, device_id, host_ptr, arg_num, args_base, args,
                              arg_sizes, arg_types, arg_names, arg_mappers);
 }
 
 EXTERN int __tgt_target_teams(int64_t device_id, void *host_ptr,
                               int32_t arg_num, void **args_base, void **args,
                               int64_t *arg_sizes, int64_t *arg_types,
                               int32_t team_num, int32_t thread_limit) {
   TIMESCOPE();
   return __tgt_target_teams_mapper(nullptr, device_id, host_ptr, arg_num,
                                    args_base, args, arg_sizes, arg_types,
                                    nullptr, nullptr, team_num, thread_limit);
 }
 
 EXTERN int __tgt_target_teams_nowait(int64_t device_id, void *host_ptr,
                                      int32_t arg_num, void **args_base,
                                      void **args, int64_t *arg_sizes,
                                      int64_t *arg_types, int32_t team_num,
                                      int32_t thread_limit, int32_t depNum,
                                      void *depList, int32_t noAliasDepNum,
                                      void *noAliasDepList) {
   TIMESCOPE();
-  if (depNum + noAliasDepNum > 0)
-    __kmpc_omp_taskwait(NULL, __kmpc_global_thread_num(NULL));
 
   return __tgt_target_teams_mapper(nullptr, device_id, host_ptr, arg_num,
                                    args_base, args, arg_sizes, arg_types,
                                    nullptr, nullptr, team_num, thread_limit);
 }
 
 EXTERN int __tgt_target_teams_mapper(ident_t *loc, int64_t device_id,
                                      void *host_ptr, int32_t arg_num,

 
 EXTERN int __tgt_target_teams_nowait_mapper(
     ident_t *loc, int64_t device_id, void *host_ptr, int32_t arg_num,
     void **args_base, void **args, int64_t *arg_sizes, int64_t *arg_types,
     map_var_info_t *arg_names, void **arg_mappers, int32_t team_num,
     int32_t thread_limit, int32_t depNum, void *depList, int32_t noAliasDepNum,
     void *noAliasDepList) {
   TIMESCOPE_WITH_IDENT(loc);
-  if (depNum + noAliasDepNum > 0)
-    __kmpc_omp_taskwait(loc, __kmpc_global_thread_num(loc));
 
   return __tgt_target_teams_mapper(loc, device_id, host_ptr, arg_num, args_base,
                                    args, arg_sizes, arg_types, arg_names,
                                    arg_mappers, team_num, thread_limit);
 }
 
 // Get the current number of components for a user-defined mapper.
 EXTERN int64_t __tgt_mapper_num_components(void *rt_mapper_handle) {

openmp/libomptarget/src/private.h

typedef int (*TargetDataFuncPtrTy)(ident_t *, DeviceTy &, int32_t, void **,
                                    bool);
 
 // Implemented in libomp, they are called from within __tgt_* functions.
 #ifdef __cplusplus
 extern "C" {
 #endif
 // functions that extract info from libomp; keep in sync
 int omp_get_default_device(void) __attribute__((weak));
-int32_t __kmpc_omp_taskwait(void *loc_ref, int32_t gtid) __attribute__((weak));
 int32_t __kmpc_global_thread_num(void *) __attribute__((weak));
 int __kmpc_get_target_offload(void) __attribute__((weak));
 #ifdef __cplusplus
 }
 #endif
 
 #define TARGET_NAME Libomptarget
 #define DEBUG_PREFIX GETNAME(TARGET_NAME)