[libomptarget] Remove duplicate RTLRequiresFlags per device

[Hahnfeld]

Summary

We have one global RTLs.RequiresFlags, I don't see a need to make a
copy per device that the runtime manages. This was problematic anyway
because the copy happened during the first __tgt_register_lib(). This
made it impossible to call __tgt_register_requires() from normal
functions for testing.
Hence, this change also fixes unified_shared_memory/shared_update.c for
older versions of Clang that don't call __tgt_register_requires() before
__tgt_register_lib().

[gtbercea]

I see what you mean! I was working on a patch for adding a new method for manually setting the flag but this works too if we don't have to have a per device flag.

openmp/libomptarget/src/api.cpp

EXTERN int omp_target_is_present(void *ptr, int device_num) {
   bool IsLast; // not used
   bool IsHostPtr;
   void *TgtPtr = Device.getTgtPtrBegin(ptr, 0, IsLast, false, IsHostPtr);
   int rc = (TgtPtr != NULL);
   // Under unified memory the host pointer can be returned by the
   // getTgtPtrBegin() function which means that there is no device
   // corresponding point for ptr. This function should return false
   // in that situation.
-  if (Device.RTLRequiresFlags & OMP_REQ_UNIFIED_SHARED_MEMORY)
+  if (RTLs.RequiresFlags & OMP_REQ_UNIFIED_SHARED_MEMORY)
     rc = !IsHostPtr;
   DP("Call to omp_target_is_present returns %d\n", rc);
   return rc;
 }
 
 EXTERN int omp_target_memcpy(void *dst, void *src, size_t length,
     size_t dst_offset, size_t src_offset, int dst_device, int src_device) {
   DP("Call to omp_target_memcpy, dst device %d, src device %d, "

openmp/libomptarget/src/device.h

struct DeviceTy {
   ShadowPtrListTy ShadowPtrMap;
 
   std::mutex DataMapMtx, PendingGlobalsMtx, ShadowMtx;
 
   // NOTE: Once libomp gains full target-task support, this state should be
   // moved into the target task in libomp.
   std::map<int32_t, uint64_t> LoopTripCnt;
 
-  int64_t RTLRequiresFlags;
-
   DeviceTy(RTLInfoTy *RTL)
       : DeviceID(-1), RTL(RTL), RTLDeviceID(-1), IsInit(false), InitFlag(),
-        HasPendingGlobals(false), HostDataToTargetMap(),
-        PendingCtorsDtors(), ShadowPtrMap(), DataMapMtx(), PendingGlobalsMtx(),
-        ShadowMtx(), RTLRequiresFlags(0) {}
+        HasPendingGlobals(false), HostDataToTargetMap(), PendingCtorsDtors(),
+        ShadowPtrMap(), DataMapMtx(), PendingGlobalsMtx(), ShadowMtx() {}
 
   // The existence of mutexes makes DeviceTy non-copyable. We need to
   // provide a copy constructor and an assignment operator explicitly.
   DeviceTy(const DeviceTy &d)
       : DeviceID(d.DeviceID), RTL(d.RTL), RTLDeviceID(d.RTLDeviceID),
         IsInit(d.IsInit), InitFlag(), HasPendingGlobals(d.HasPendingGlobals),
         HostDataToTargetMap(d.HostDataToTargetMap),
         PendingCtorsDtors(d.PendingCtorsDtors), ShadowPtrMap(d.ShadowPtrMap),
-        DataMapMtx(), PendingGlobalsMtx(),
-        ShadowMtx(), LoopTripCnt(d.LoopTripCnt),
-        RTLRequiresFlags(d.RTLRequiresFlags) {}
+        DataMapMtx(), PendingGlobalsMtx(), ShadowMtx(),
+        LoopTripCnt(d.LoopTripCnt) {}
 
   DeviceTy& operator=(const DeviceTy &d) {
     DeviceID = d.DeviceID;
     RTL = d.RTL;
     RTLDeviceID = d.RTLDeviceID;
     IsInit = d.IsInit;
     HasPendingGlobals = d.HasPendingGlobals;
     HostDataToTargetMap = d.HostDataToTargetMap;
     PendingCtorsDtors = d.PendingCtorsDtors;
     ShadowPtrMap = d.ShadowPtrMap;
     LoopTripCnt = d.LoopTripCnt;
-    RTLRequiresFlags = d.RTLRequiresFlags;
 
     return *this;
   }
 
   long getMapEntryRefCnt(void *HstPtrBegin);
   LookupResult lookupMapping(void *HstPtrBegin, int64_t Size);
   void *getOrAllocTgtPtr(void *HstPtrBegin, void *HstPtrBase, int64_t Size,
       bool &IsNew, bool &IsHostPtr, bool IsImplicit, bool UpdateRefCount = true);

openmp/libomptarget/src/device.cpp

if (lr.Flags.IsContained ||
     DP("Explicit extension of mapping is not allowed.\n");
   } else if (Size) {
     // If unified shared memory is active, implicitly mapped variables that are not
     // privatized use host address. Any explicitly mapped variables also use
     // host address where correctness is not impeded. In all other cases
     // maps are respected.
     // TODO: In addition to the mapping rules above, when the close map
     // modifier is implemented, foce the mapping of the variable to the device.
-    if (RTLRequiresFlags & OMP_REQ_UNIFIED_SHARED_MEMORY) {
+    if (RTLs.RequiresFlags & OMP_REQ_UNIFIED_SHARED_MEMORY) {
       DP("Return HstPtrBegin " DPxMOD " Size=%ld RefCount=%s\n",
          DPxPTR((uintptr_t)HstPtrBegin), Size, (UpdateRefCount ? " updated" : ""));
       IsHostPtr = true;
       rc = HstPtrBegin;
     } else {
       // If it is not contained and Size > 0 we should create a new entry for it.
       IsNew = true;
       uintptr_t tp = (uintptr_t)RTL->data_alloc(RTLDeviceID, Size, HstPtrBegin);
if (lr.Flags.IsContained || lr.Flags.ExtendsBefore || lr.Flags.ExtendsAfter) {
 
     uintptr_t tp = HT.TgtPtrBegin + ((uintptr_t)HstPtrBegin - HT.HstPtrBegin);
     DP("Mapping exists with HstPtrBegin=" DPxMOD ", TgtPtrBegin=" DPxMOD ", "
         "Size=%ld,%s RefCount=%s\n", DPxPTR(HstPtrBegin), DPxPTR(tp), Size,
         (UpdateRefCount ? " updated" : ""),
         (CONSIDERED_INF(HT.RefCount)) ? "INF" :
             std::to_string(HT.RefCount).c_str());
     rc = (void *)tp;
-  } else if (RTLRequiresFlags & OMP_REQ_UNIFIED_SHARED_MEMORY) {
+  } else if (RTLs.RequiresFlags & OMP_REQ_UNIFIED_SHARED_MEMORY) {
     // If the value isn't found in the mapping and unified shared memory
     // is on then it means we have stumbled upon a value which we need to
     // use directly from the host.
     DP("Get HstPtrBegin " DPxMOD " Size=%ld RefCount=%s\n",
        DPxPTR((uintptr_t)HstPtrBegin), Size, (UpdateRefCount ? " updated" : ""));
     IsHostPtr = true;
     rc = HstPtrBegin;
   }
if (lr.Flags.IsContained || lr.Flags.ExtendsBefore || lr.Flags.ExtendsAfter) {
     uintptr_t tp = HT.TgtPtrBegin + (hp - HT.HstPtrBegin);
     return (void *)tp;
   }
 
   return NULL;
 }
 
 int DeviceTy::deallocTgtPtr(void *HstPtrBegin, int64_t Size, bool ForceDelete) {
-  if (RTLRequiresFlags & OMP_REQ_UNIFIED_SHARED_MEMORY)
+  if (RTLs.RequiresFlags & OMP_REQ_UNIFIED_SHARED_MEMORY)
     return OFFLOAD_SUCCESS;
   // Check if the pointer is contained in any sub-nodes.
   int rc;
   DataMapMtx.lock();
   LookupResult lr = lookupMapping(HstPtrBegin, Size);
   if (lr.Flags.IsContained || lr.Flags.ExtendsBefore || lr.Flags.ExtendsAfter) {
     auto &HT = *lr.Entry;
     if (ForceDelete)
int DeviceTy::deallocTgtPtr(void *HstPtrBegin, int64_t Size, bool ForceDelete) {
   DataMapMtx.unlock();
   return rc;
 }
 
 /// Init device, should not be called directly.
 void DeviceTy::init() {
   // Make call to init_requires if it exists for this plugin.
   if (RTL->init_requires)
-    RTL->init_requires(RTLRequiresFlags);
+    RTL->init_requires(RTLs.RequiresFlags);
   int32_t rc = RTL->init_device(RTLDeviceID);
   if (rc == OFFLOAD_SUCCESS) {
     IsInit = true;
   }
 }
 
 /// Thread-safe method to initialize the device only once.
 int32_t DeviceTy::initOnce() {

openmp/libomptarget/src/omptarget.cpp

if (arg_types[i] & OMP_TGT_MAPTYPE_RETURN_PARAM) {
       uintptr_t Delta = (uintptr_t)HstPtrBegin - (uintptr_t)HstPtrBase;
       void *TgtPtrBase = (void *)((uintptr_t)TgtPtrBegin - Delta);
       DP("Returning device pointer " DPxMOD "\n", DPxPTR(TgtPtrBase));
       args_base[i] = TgtPtrBase;
     }
 
     if (arg_types[i] & OMP_TGT_MAPTYPE_TO) {
       bool copy = false;
-      if (!(Device.RTLRequiresFlags & OMP_REQ_UNIFIED_SHARED_MEMORY)) {
+      if (!(RTLs.RequiresFlags & OMP_REQ_UNIFIED_SHARED_MEMORY)) {
         if (IsNew || (arg_types[i] & OMP_TGT_MAPTYPE_ALWAYS)) {
           copy = true;
         } else if (arg_types[i] & OMP_TGT_MAPTYPE_MEMBER_OF) {
           // Copy data only if the "parent" struct has RefCount==1.
           int32_t parent_idx = member_of(arg_types[i]);
           long parent_rc = Device.getMapEntryRefCnt(args[parent_idx]);
           assert(parent_rc > 0 && "parent struct not found");
           if (parent_rc == 1) {
if ((arg_types[i] & OMP_TGT_MAPTYPE_MEMBER_OF) &&
       DelEntry = false; // protect parent struct from being deallocated
     }
 
     if ((arg_types[i] & OMP_TGT_MAPTYPE_FROM) || DelEntry) {
       // Move data back to the host
       if (arg_types[i] & OMP_TGT_MAPTYPE_FROM) {
         bool Always = arg_types[i] & OMP_TGT_MAPTYPE_ALWAYS;
         bool CopyMember = false;
-        if (!(Device.RTLRequiresFlags & OMP_REQ_UNIFIED_SHARED_MEMORY)) {
+        if (!(RTLs.RequiresFlags & OMP_REQ_UNIFIED_SHARED_MEMORY)) {
           if ((arg_types[i] & OMP_TGT_MAPTYPE_MEMBER_OF) &&
               !(arg_types[i] & OMP_TGT_MAPTYPE_PTR_AND_OBJ)) {
             // Copy data only if the "parent" struct has RefCount==1.
             int32_t parent_idx = member_of(arg_types[i]);
             long parent_rc = Device.getMapEntryRefCnt(args[parent_idx]);
             assert(parent_rc > 0 && "parent struct not found");
             if (parent_rc == 1) {
               CopyMember = true;
             }
           }
         }
 
         if ((DelEntry || Always || CopyMember) &&
-            !(Device.RTLRequiresFlags & OMP_REQ_UNIFIED_SHARED_MEMORY &&
+            !(RTLs.RequiresFlags & OMP_REQ_UNIFIED_SHARED_MEMORY &&
               TgtPtrBegin == HstPtrBegin)) {
           DP("Moving %" PRId64 " bytes (tgt:" DPxMOD ") -> (hst:" DPxMOD ")\n",
               data_size, DPxPTR(TgtPtrBegin), DPxPTR(HstPtrBegin));
           int rt = Device.data_retrieve(HstPtrBegin, TgtPtrBegin, data_size);
           if (rt != OFFLOAD_SUCCESS) {
             DP("Copying data from device failed.\n");
             return OFFLOAD_FAIL;
           }
for (int32_t i = 0; i < arg_num; ++i) {
     bool IsLast, IsHostPtr;
     void *TgtPtrBegin = Device.getTgtPtrBegin(HstPtrBegin, MapSize, IsLast,
         false, IsHostPtr);
     if (!TgtPtrBegin) {
       DP("hst data:" DPxMOD " not found, becomes a noop\n", DPxPTR(HstPtrBegin));
       continue;
     }
 
-    if (Device.RTLRequiresFlags & OMP_REQ_UNIFIED_SHARED_MEMORY &&
+    if (RTLs.RequiresFlags & OMP_REQ_UNIFIED_SHARED_MEMORY &&
         TgtPtrBegin == HstPtrBegin) {
       DP("hst data:" DPxMOD " unified and shared, becomes a noop\n",
          DPxPTR(HstPtrBegin));
       continue;
     }
 
     if (arg_types[i] & OMP_TGT_MAPTYPE_FROM) {
       DP("Moving %" PRId64 " bytes (tgt:" DPxMOD ") -> (hst:" DPxMOD ")\n",
if (!(arg_types[i] & OMP_TGT_MAPTYPE_TARGET_PARAM)) {
         void *Pointer_TgtPtrBegin =
             Device.getTgtPtrBegin(HstPtrVal, arg_sizes[i], IsLast, false,
                                   IsHostPtr);
         if (!Pointer_TgtPtrBegin) {
           DP("No lambda captured variable mapped (" DPxMOD ") - ignored\n",
              DPxPTR(HstPtrVal));
           continue;
         }
-        if (Device.RTLRequiresFlags & OMP_REQ_UNIFIED_SHARED_MEMORY &&
+        if (RTLs.RequiresFlags & OMP_REQ_UNIFIED_SHARED_MEMORY &&
             TgtPtrBegin == HstPtrBegin) {
           DP("Unified memory is active, no need to map lambda captured"
              "variable (" DPxMOD ")\n", DPxPTR(HstPtrVal));
           continue;
         }
         DP("Update lambda reference (" DPxMOD ") -> [" DPxMOD "]\n",
            DPxPTR(Pointer_TgtPtrBegin), DPxPTR(TgtPtrBegin));
         int rt = Device.data_submit(TgtPtrBegin, &Pointer_TgtPtrBegin,

openmp/libomptarget/src/rtl.cpp

for (auto &R : RTLs.AllRTLs) {
         size_t start = Devices.size();
         Devices.resize(start + R.NumberOfDevices, device);
         for (int32_t device_id = 0; device_id < R.NumberOfDevices;
             device_id++) {
           // global device ID
           Devices[start + device_id].DeviceID = start + device_id;
           // RTL local device ID
           Devices[start + device_id].RTLDeviceID = device_id;
-          // RTL requires flags
-          Devices[start + device_id].RTLRequiresFlags = RequiresFlags;
         }
 
         // Initialize the index of this RTL and save it in the used RTLs.
         R.Idx = (RTLs.UsedRTLs.empty())
                     ? 0
                     : RTLs.UsedRTLs.back()->Idx +
                           RTLs.UsedRTLs.back()->NumberOfDevices;
         assert((size_t) R.Idx == start &&