[OpenMP][NFC] Unify `target` API with other by passing a `__tgt_async_info` pointer

[tianshilei1992]

openmp/libomptarget/src/omptarget.cpp

14

Do we need this header here?

[tianshilei1992]

One nit ^^^^

[jdoerfert]

openmp/libomptarget/src/omptarget.cpp

14

strictly speaking, no. but we should include what we use.

openmp/libomptarget/src/interface.cpp

EXTERN void __tgt_target_data_update_mapper(ident_t *loc, int64_t device_id,
   }
 
   if (getInfoLevel() & OMP_INFOTYPE_KERNEL_ARGS)
     printKernelArguments(loc, device_id, arg_num, arg_sizes, arg_types,
                          arg_names, "Updating OpenMP data");
 
   DeviceTy &Device = PM->Devices[device_id];
   int rc = targetDataUpdate(loc, Device, arg_num, args_base, args, arg_sizes,
-                            arg_types, arg_names, arg_mappers);
+                            arg_types, arg_names, arg_mappers, nullptr);
   HandleTargetOutcome(rc == OFFLOAD_SUCCESS, loc);
 }
 
 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) {
for (int i = 0; i < arg_num; ++i) {
     DP("Entry %2d: Base=" DPxMOD ", Begin=" DPxMOD ", Size=%" PRId64
        ", Type=0x%" PRIx64 ", Name=%s\n",
        i, DPxPTR(args_base[i]), DPxPTR(args[i]), arg_sizes[i], arg_types[i],
        (arg_names) ? getNameFromMapping(arg_names[i]).c_str() : "unknown");
   }
 #endif
 
   DeviceTy &Device = PM->Devices[device_id];
-  int rc = target(loc, Device, host_ptr, arg_num, args_base, args, arg_sizes,
-                  arg_types, arg_names, arg_mappers, 0, 0, false /*team*/);
+  int rc =
+      target(loc, Device, host_ptr, arg_num, args_base, args, arg_sizes,
+             arg_types, arg_names, arg_mappers, 0, 0, false /*team*/, nullptr);
   HandleTargetOutcome(rc == OFFLOAD_SUCCESS, loc);
   return rc;
 }
 
 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,
DP("Entry %2d: Base=" DPxMOD ", Begin=" DPxMOD ", Size=%" PRId64
        i, DPxPTR(args_base[i]), DPxPTR(args[i]), arg_sizes[i], arg_types[i],
        (arg_names) ? getNameFromMapping(arg_names[i]).c_str() : "unknown");
   }
 #endif
 
   DeviceTy &Device = PM->Devices[device_id];
   int rc = target(loc, Device, host_ptr, arg_num, args_base, args, arg_sizes,
                   arg_types, arg_names, arg_mappers, team_num, thread_limit,
-                  true /*team*/);
+                  true /*team*/, nullptr);
   HandleTargetOutcome(rc == OFFLOAD_SUCCESS, loc);
   return rc;
 }
 
 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,

openmp/libomptarget/src/omptarget.cpp

 //===------ omptarget.cpp - Target independent OpenMP target RTL -- C++ -*-===//
 //
 // Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
 // See https://llvm.org/LICENSE.txt for license information.
 // SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
 //
 //===----------------------------------------------------------------------===//
 //
 // Implementation of the interface to be used by Clang during the codegen of a
 // target region.
 //
 //===----------------------------------------------------------------------===//
 
+#include "omptarget.h"
 #include "device.h"
 #include "private.h"
 #include "rtl.h"
 
 #include <cassert>
 #include <vector>
 
 /* All begin addresses for partially mapped structs must be 8-aligned in order
static int InitLibrary(DeviceTy &Device) {
    */
   if (!Device.PendingCtorsDtors.empty()) {
     // Call all ctors for all libraries registered so far
     for (auto &lib : Device.PendingCtorsDtors) {
       if (!lib.second.PendingCtors.empty()) {
         DP("Has pending ctors... call now\n");
         for (auto &entry : lib.second.PendingCtors) {
           void *ctor = entry;
-          int rc = target(nullptr, Device, ctor, 0, nullptr, nullptr, nullptr,
-                          nullptr, nullptr, nullptr, 1, 1, true /*team*/);
+          int rc =
+              target(nullptr, Device, ctor, 0, nullptr, nullptr, nullptr,
+                     nullptr, nullptr, nullptr, 1, 1, true /*team*/, nullptr);
           if (rc != OFFLOAD_SUCCESS) {
             REPORT("Running ctor " DPxMOD " failed.\n", DPxPTR(ctor));
             Device.PendingGlobalsMtx.unlock();
             return OFFLOAD_FAIL;
           }
         }
         // Clear the list to indicate that this device has been used
         lib.second.PendingCtors.clear();
int targetDataMapper(ident_t *loc, DeviceTy &Device, void *arg_base, void *arg,
 
   return rc;
 }
 
 /// Internal function to do the mapping and transfer the data to the device
 int targetDataBegin(ident_t *loc, DeviceTy &Device, 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, __tgt_async_info *async_info_ptr) {
+                    void **arg_mappers, __tgt_async_info *AsyncInfo) {
   // process each input.
   for (int32_t i = 0; i < arg_num; ++i) {
     // Ignore private variables and arrays - there is no mapping for them.
     if ((arg_types[i] & OMP_TGT_MAPTYPE_LITERAL) ||
         (arg_types[i] & OMP_TGT_MAPTYPE_PRIVATE))
       continue;
 
     if (arg_mappers && arg_mappers[i]) {
if (arg_types[i] & OMP_TGT_MAPTYPE_TO) {
             copy = true;
           }
         }
       }
 
       if (copy && !IsHostPtr) {
         DP("Moving %" PRId64 " bytes (hst:" DPxMOD ") -> (tgt:" DPxMOD ")\n",
            data_size, DPxPTR(HstPtrBegin), DPxPTR(TgtPtrBegin));
-        int rt = Device.submitData(TgtPtrBegin, HstPtrBegin, data_size,
-                                   async_info_ptr);
+        int rt =
+            Device.submitData(TgtPtrBegin, HstPtrBegin, data_size, AsyncInfo);
         if (rt != OFFLOAD_SUCCESS) {
           REPORT("Copying data to device failed.\n");
           return OFFLOAD_FAIL;
         }
       }
     }
 
     if (arg_types[i] & OMP_TGT_MAPTYPE_PTR_AND_OBJ && !IsHostPtr) {
       DP("Update pointer (" DPxMOD ") -> [" DPxMOD "]\n",
          DPxPTR(PointerTgtPtrBegin), DPxPTR(TgtPtrBegin));
       uint64_t Delta = (uint64_t)HstPtrBegin - (uint64_t)HstPtrBase;
       void *TgtPtrBase = (void *)((uint64_t)TgtPtrBegin - Delta);
       int rt = Device.submitData(PointerTgtPtrBegin, &TgtPtrBase,
-                                 sizeof(void *), async_info_ptr);
+                                 sizeof(void *), AsyncInfo);
       if (rt != OFFLOAD_SUCCESS) {
         REPORT("Copying data to device failed.\n");
         return OFFLOAD_FAIL;
       }
       // create shadow pointers for this entry
       Device.ShadowMtx.lock();
       Device.ShadowPtrMap[Pointer_HstPtrBegin] = {
           HstPtrBase, PointerTgtPtrBegin, TgtPtrBase};
static int getNonContigMergedDimension(__tgt_target_non_contig *NonContig,
   for (int I = DimSize - 1; I > 0; --I) {
     if (NonContig[I].Count * NonContig[I].Stride == NonContig[I - 1].Stride)
       RemovedDim++;
   }
   return RemovedDim;
 }
 
 /// Internal function to pass data to/from the target.
-// async_info_ptr is currently unused, added here so targetDataUpdate has the
+// AsyncInfo is currently unused, added here so targetDataUpdate has the
 // same signature as targetDataBegin and targetDataEnd.
 int targetDataUpdate(ident_t *loc, DeviceTy &Device, int32_t ArgNum,
                      void **ArgsBase, void **Args, int64_t *ArgSizes,
                      int64_t *ArgTypes, map_var_info_t *ArgNames,
-                     void **ArgMappers, __tgt_async_info *AsyncInfoPtr) {
+                     void **ArgMappers, __tgt_async_info *AsyncInfo) {
   // process each input.
   for (int32_t I = 0; I < ArgNum; ++I) {
     if ((ArgTypes[I] & OMP_TGT_MAPTYPE_LITERAL) ||
         (ArgTypes[I] & OMP_TGT_MAPTYPE_PRIVATE))
       continue;
 
     if (ArgMappers && ArgMappers[I]) {
       // Instead of executing the regular path of targetDataUpdate, call the

 /// non-zero and initiates run of the offloaded region on the target platform;
 /// if arg_num is non-zero after the region execution is done it also
 /// performs the same action as data_update and data_end above. This function
 /// returns 0 if it was able to transfer the execution to a target and an
 /// integer different from zero otherwise.
 int target(ident_t *loc, DeviceTy &Device, void *HostPtr, int32_t ArgNum,
            void **ArgBases, void **Args, int64_t *ArgSizes, int64_t *ArgTypes,
            map_var_info_t *ArgNames, void **ArgMappers, int32_t TeamNum,
-           int32_t ThreadLimit, int IsTeamConstruct) {
+           int32_t ThreadLimit, int IsTeamConstruct,
+           __tgt_async_info *AsyncInfo) {
   int32_t DeviceId = Device.DeviceID;
 
   TableMap *TM = getTableMap(HostPtr);
   // No map for this host pointer found!
   if (!TM) {
     REPORT("Host ptr " DPxMOD " does not have a matching target pointer.\n",
            DPxPTR(HostPtr));
     return OFFLOAD_FAIL;
   }
 
   // get target table.
   __tgt_target_table *TargetTable = nullptr;
   {
     std::lock_guard<std::mutex> TrlTblLock(PM->TrlTblMtx);
     assert(TM->Table->TargetsTable.size() > (size_t)DeviceId &&
            "Not expecting a device ID outside the table's bounds!");
     TargetTable = TM->Table->TargetsTable[DeviceId];
   }
   assert(TargetTable && "Global data has not been mapped\n");
 
-  __tgt_async_info AsyncInfo;
+  // TODO: This will go away as soon as we consequently pass in async info
+  // objects (as references).
+  __tgt_async_info InternalAsyncInfo;
+  if (!AsyncInfo)
+    AsyncInfo = &InternalAsyncInfo;
 
   std::vector<void *> TgtArgs;
   std::vector<ptrdiff_t> TgtOffsets;
 
-  PrivateArgumentManagerTy PrivateArgumentManager(Device, &AsyncInfo);
+  PrivateArgumentManagerTy PrivateArgumentManager(Device, AsyncInfo);
 
   int Ret;
   if (ArgNum) {
     // Process data, such as data mapping, before launching the kernel
     Ret = processDataBefore(loc, DeviceId, HostPtr, ArgNum, ArgBases, Args,
                             ArgSizes, ArgTypes, ArgNames, ArgMappers, TgtArgs,
-                            TgtOffsets, PrivateArgumentManager, &AsyncInfo);
+                            TgtOffsets, PrivateArgumentManager, AsyncInfo);
     if (Ret != OFFLOAD_SUCCESS) {
       REPORT("Failed to process data before launching the kernel.\n");
       return OFFLOAD_FAIL;
     }
   }
 
   // Get loop trip count
   uint64_t LoopTripCount = getLoopTripCount(DeviceId);
 
   // Launch device execution.
   void *TgtEntryPtr = TargetTable->EntriesBegin[TM->Index].addr;
   DP("Launching target execution %s with pointer " DPxMOD " (index=%d).\n",
      TargetTable->EntriesBegin[TM->Index].name, DPxPTR(TgtEntryPtr), TM->Index);
 
   {
     TIMESCOPE_WITH_NAME_AND_IDENT(
         IsTeamConstruct ? "runTargetTeamRegion" : "runTargetRegion", loc);
     if (IsTeamConstruct)
       Ret = Device.runTeamRegion(TgtEntryPtr, &TgtArgs[0], &TgtOffsets[0],
                                  TgtArgs.size(), TeamNum, ThreadLimit,
-                                 LoopTripCount, &AsyncInfo);
+                                 LoopTripCount, AsyncInfo);
     else
       Ret = Device.runRegion(TgtEntryPtr, &TgtArgs[0], &TgtOffsets[0],
-                             TgtArgs.size(), &AsyncInfo);
+                             TgtArgs.size(), AsyncInfo);
   }
 
   if (Ret != OFFLOAD_SUCCESS) {
     REPORT("Executing target region abort target.\n");
     return OFFLOAD_FAIL;
   }
 
   if (ArgNum) {
     // Transfer data back and deallocate target memory for (first-)private
     // variables
     Ret = processDataAfter(loc, DeviceId, HostPtr, ArgNum, ArgBases, Args,
                            ArgSizes, ArgTypes, ArgNames, ArgMappers,
-                           PrivateArgumentManager, &AsyncInfo);
+                           PrivateArgumentManager, AsyncInfo);
     if (Ret != OFFLOAD_SUCCESS) {
       REPORT("Failed to process data after launching the kernel.\n");
       return OFFLOAD_FAIL;
     }
-  } else if (AsyncInfo.Queue) {
+  } else if (AsyncInfo->Queue) {
     // If ArgNum is zero, but AsyncInfo.Queue is valid, then the kernel doesn't
     // hava any argument, and the device supports async operations, so we need a
     // sync at this point.
-    return syncDevice(Device, &AsyncInfo);
+    return syncDevice(Device, AsyncInfo);
   }
 
   return OFFLOAD_SUCCESS;
 }

openmp/libomptarget/src/private.h

 #include <SourceInfo.h>
 #include <omptarget.h>
 
 #include <cstdint>
 
 extern int targetDataBegin(ident_t *loc, DeviceTy &Device, 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,
-                           __tgt_async_info *async_info_ptr);
+                           void **arg_mappers, __tgt_async_info *AsyncInfo);
 
 extern int targetDataEnd(ident_t *loc, DeviceTy &Device, int32_t ArgNum,
                          void **ArgBases, void **Args, int64_t *ArgSizes,
                          int64_t *ArgTypes, map_var_info_t *arg_names,
                          void **ArgMappers, __tgt_async_info *AsyncInfo);
 
 extern int targetDataUpdate(ident_t *loc, DeviceTy &Device, 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,
-                            __tgt_async_info *async_info_ptr = nullptr);
+                            void **arg_mappers, __tgt_async_info *AsyncInfo);
 
 extern int target(ident_t *loc, DeviceTy &Device, void *HostPtr, int32_t ArgNum,
                   void **ArgBases, void **Args, int64_t *ArgSizes,
                   int64_t *ArgTypes, map_var_info_t *arg_names,
                   void **ArgMappers, int32_t TeamNum, int32_t ThreadLimit,
-                  int IsTeamConstruct);
+                  int IsTeamConstruct, __tgt_async_info *AsyncInfo);
 
 extern int CheckDeviceAndCtors(int64_t device_id);
 
 // This structure stores information of a mapped memory region.
 struct MapComponentInfoTy {
   void *Base;
   void *Begin;
   int64_t Size;

openmp/libomptarget/src/rtl.cpp

for (auto *R : UsedRTLs) {
 
       // Execute dtors for static objects if the device has been used, i.e.
       // if its PendingCtors list has been emptied.
       for (int32_t i = 0; i < FoundRTL->NumberOfDevices; ++i) {
         DeviceTy &Device = PM->Devices[FoundRTL->Idx + i];
         Device.PendingGlobalsMtx.lock();
         if (Device.PendingCtorsDtors[desc].PendingCtors.empty()) {
           for (auto &dtor : Device.PendingCtorsDtors[desc].PendingDtors) {
-            int rc = target(nullptr, Device, dtor, 0, nullptr, nullptr, nullptr,
-                            nullptr, nullptr, nullptr, 1, 1, true /*team*/);
+            int rc =
+                target(nullptr, Device, dtor, 0, nullptr, nullptr, nullptr,
+                       nullptr, nullptr, nullptr, 1, 1, true /*team*/, nullptr);
             if (rc != OFFLOAD_SUCCESS) {
               DP("Running destructor " DPxMOD " failed.\n", DPxPTR(dtor));
             }
           }
           // Remove this library's entry from PendingCtorsDtors
           Device.PendingCtorsDtors.erase(desc);
         }
         Device.PendingGlobalsMtx.unlock();