diff --git a/llvm/lib/Transforms/IPO/OpenMPOpt.cpp b/llvm/lib/Transforms/IPO/OpenMPOpt.cpp
--- a/llvm/lib/Transforms/IPO/OpenMPOpt.cpp
+++ b/llvm/lib/Transforms/IPO/OpenMPOpt.cpp
@@ -689,7 +689,12 @@
       if (!RTCall)
         return false;
 
-      bool WasSplit = splitTargetDataBeginRTC(RTCall);
+      // TODO: Check if can be moved upwards.
+      bool WasSplit = false;
+      Instruction *WaitMovementPoint = canBeMovedDownwards(RTCall);
+      if (WaitMovementPoint)
+        WasSplit = splitTargetDataBeginRTC(RTCall, WaitMovementPoint);
+
       Changed |= WasSplit;
       return WasSplit;
     };
@@ -698,8 +703,54 @@
     return Changed;
   }
 
+  /// Returns the instruction where the "wait" counterpart \p RuntimeCall can be
+  /// moved. Returns nullptr if the movement is not possible, or not worth it.
+  Instruction *canBeMovedDownwards(CallInst *RuntimeCall) {
+  // FIXME: This traverses only the BasicBlock where RuntimeCall is.
+  //        Make it traverse the CFG.
+
+  // Functions that may require the data transferred or may synchronize it.
+  auto *TargetTeams = OMPInfoCache.OMPBuilder.getOrCreateRuntimeFunctionPtr(
+      llvm::omp::RuntimeFunction::OMPRTL___tgt_target_teams_mapper);
+  auto *TargetDataEnd = OMPInfoCache.OMPBuilder.getOrCreateRuntimeFunctionPtr(
+      llvm::omp::RuntimeFunction::OMPRTL___tgt_target_data_end_mapper);
+
+  Instruction *CurrentI = RuntimeCall;
+  bool IsWorthIt = false;
+  while ((CurrentI = CurrentI->getNextNode())) {
+
+    // TODO: Once we detect the regions to be offloaded we should use the
+    //       alyas analysis manager to check if CurrentI may modify one of
+    //       the offloaded regions.
+    if (CurrentI->mayHaveSideEffects() || CurrentI->mayReadFromMemory()) {
+      if (IsWorthIt)
+        return CurrentI;
+      return nullptr;
+    }
+
+    if (auto *C = dyn_cast<CallInst>(CurrentI)) {
+      auto *Callee = C->getCalledFunction();
+      if (Callee == TargetTeams || Callee == TargetDataEnd) {
+        if (IsWorthIt)
+          return CurrentI;
+        return nullptr;
+      }
+    }
+
+    // FIXME: For now if we move it over anything without side effect
+    //        is worth it.
+    IsWorthIt = true;
+  }
+
+  // Return end of BasicBlock.
+  return &*(--RuntimeCall->getParent()->end());
+}
+
   /// Splits \p RuntimeCall into its "issue" and "wait" counterparts.
-  bool splitTargetDataBeginRTC(CallInst *RuntimeCall) {
+  bool splitTargetDataBeginRTC(CallInst *RuntimeCall,
+                             Instruction *WaitMovementPoint) {
+    assert(WaitMovementPoint && "No place to move the split runtime call!");
+
     auto &IRBuilder = OMPInfoCache.OMPBuilder;
     // Add "issue" runtime call declaration:
     // declare %struct.tgt_async_info @__tgt_target_data_begin_issue(i64, i32,
@@ -726,8 +777,8 @@
         IssueCallsite->getArgOperand(0), // device_id.
         IssueCallsite // returned handle.
     };
-    CallInst::Create(WaitDecl, WaitParams, /*NameStr=*/"",
-                     IssueCallsite->getNextNode());
+    CallInst::Create(
+        WaitDecl, WaitParams, /*NameStr=*/"", WaitMovementPoint);
 
     return true;
   }
diff --git a/llvm/test/Transforms/OpenMP/hide_mem_transfer_latency.ll b/llvm/test/Transforms/OpenMP/hide_mem_transfer_latency.ll
--- a/llvm/test/Transforms/OpenMP/hide_mem_transfer_latency.ll
+++ b/llvm/test/Transforms/OpenMP/hide_mem_transfer_latency.ll
@@ -59,9 +59,11 @@
 ; CHECK-NEXT:    store double* %a, double** %4, align 8
 
 ; CHECK-NEXT:    %handle = call %struct.__tgt_async_info @__tgt_target_data_begin_mapper_issue(i64 -1, i32 1, i8** %1, i8** %3, i64* getelementptr inbounds ([1 x i64], [1 x i64]* @.offload_sizes.1, i64 0, i64 0), i64* getelementptr inbounds ([1 x i64], [1 x i64]* @.offload_maptypes, i64 0, i64 0), i8** null)
-; CHECK-NEXT:    call void @__tgt_target_data_begin_mapper_wait(i64 -1, %struct.__tgt_async_info %handle)
 
 ; CHECK-NEXT:    %5 = bitcast double* %a to i64*
+
+; CHECK-NEXT:    call void @__tgt_target_data_begin_mapper_wait(i64 -1, %struct.__tgt_async_info %handle)
+
 ; CHECK-NEXT:    %6 = load i64, i64* %5, align 8
 ; CHECK-NEXT:    %7 = getelementptr inbounds [1 x i8*], [1 x i8*]* %.offload_baseptrs4, i64 0, i64 0
 ; CHECK-NEXT:    %8 = bitcast [1 x i8*]* %.offload_baseptrs4 to i64*
@@ -184,8 +186,7 @@
 ; CHECK-NEXT:    %10 = getelementptr inbounds [2 x i64], [2 x i64]* %.offload_sizes, i64 0, i64 1
 ; CHECK-NEXT:    store i64 4, i64* %10, align 8
 
-; CHECK-NEXT:    %handle = call %struct.__tgt_async_info @__tgt_target_data_begin_mapper_issue(i64 -1, i32 2, i8** %1, i8** %3, i64* %5, i64* getelementptr inbounds ([2 x i64], [2 x i64]* @.offload_maptypes.3, i64 0, i64 0), i8** null)
-; CHECK-NEXT:    call void @__tgt_target_data_begin_mapper_wait(i64 -1, %struct.__tgt_async_info %handle)
+; CHECK-NEXT:    call void @__tgt_target_data_begin_mapper(i64 -1, i32 2, i8** nonnull %1, i8** nonnull %3, i64* nonnull %5, i64* getelementptr inbounds ([2 x i64], [2 x i64]* @.offload_maptypes.3, i64 0, i64 0), i8** null)
 
 ; CHECK-NEXT:    %11 = load i32, i32* %size.addr, align 4
 ; CHECK-NEXT:    %size.casted = zext i32 %11 to i64
@@ -325,8 +326,7 @@
 ; CHECK-NEXT:    %10 = getelementptr inbounds [2 x i64], [2 x i64]* %.offload_sizes, i64 0, i64 1
 ; CHECK-NEXT:    store i64 4, i64* %10, align 8
 
-; CHECK-NEXT:    %handle = call %struct.__tgt_async_info @__tgt_target_data_begin_mapper_issue(i64 -1, i32 2, i8** %1, i8** %3, i64* %5, i64* getelementptr inbounds ([2 x i64], [2 x i64]* @.offload_maptypes.3, i64 0, i64 0), i8** null)
-; CHECK-NEXT:    call void @__tgt_target_data_begin_mapper_wait(i64 -1, %struct.__tgt_async_info %handle)
+; CHECK-NEXT:    call void @__tgt_target_data_begin_mapper(i64 -1, i32 2, i8** nonnull %1, i8** nonnull %3, i64* nonnull %5, i64* getelementptr inbounds ([2 x i64], [2 x i64]* @.offload_maptypes.3, i64 0, i64 0), i8** null)
 
 ; CHECK-NEXT:    %11 = load i32, i32* %size.addr, align 4
 ; CHECK-NEXT:    %size.casted = zext i32 %11 to i64
@@ -453,9 +453,11 @@
 ; CHECK-NEXT:    store i64 %0, i64* %5, align 8
 
 ; CHECK-NEXT:    %handle = call %struct.__tgt_async_info @__tgt_target_data_begin_mapper_issue(i64 -1, i32 1, i8** %1, i8** %3, i64* %5, i64* getelementptr inbounds ([1 x i64], [1 x i64]* @.offload_maptypes.5, i64 0, i64 0), i8** null)
-; CHECK-NEXT:    call void @__tgt_target_data_begin_mapper_wait(i64 -1, %struct.__tgt_async_info %handle)
 
 ; CHECK-NEXT:    %rem = urem i32 %call, %size
+
+; CHECK-NEXT:    call void @__tgt_target_data_begin_mapper_wait(i64 -1, %struct.__tgt_async_info %handle)
+
 ; CHECK-NEXT:    call void @__tgt_target_data_end_mapper(i64 -1, i32 1, i8** nonnull %1, i8** nonnull %3, i64* nonnull %5, i64* getelementptr inbounds ([1 x i64], [1 x i64]* @.offload_maptypes.5, i64 0, i64 0), i8** null)
 ; CHECK-NEXT:    ret i32 %rem
 ;