Index: openmp/docs/design/Runtimes.rst
===================================================================
--- openmp/docs/design/Runtimes.rst
+++ openmp/docs/design/Runtimes.rst
@@ -1160,6 +1160,7 @@
 * ``LIBOMPTARGET_AMDGPU_TEAMS_PER_CU``
 * ``LIBOMPTARGET_AMDGPU_MAX_ASYNC_COPY_BYTES``
 * ``LIBOMPTARGET_AMDGPU_NUM_INITIAL_HSA_SIGNALS``
+* ``LIBOMPTARGET_FORCE_SYNCHRONIZE``
 
 The environment variables ``LIBOMPTARGET_SHARED_MEMORY_SIZE``,
 ``LIBOMPTARGET_STACK_SIZE`` and ``LIBOMPTARGET_HEAP_SIZE`` are described in
@@ -1238,6 +1239,14 @@
 streams. More HSA signals will be created dynamically throughout the execution
 if needed. The default value is ``64``.
 
+LIBOMPTARGET_FORCE_SYNCHRONIZE
+""""""""""""""""""""""""""""""
+
+This environment variable causes the NextGen plugin to synchronize immediately
+after a kernel is launched or after a data transfer, instead of the default
+behavior. Doing so aims to make identifying the source of code crashes
+easier.
+
 .. _remote_offloading_plugin:
 
 Remote Offloading Plugin:
Index: openmp/libomptarget/plugins-nextgen/common/PluginInterface/PluginInterface.cpp
===================================================================
--- openmp/libomptarget/plugins-nextgen/common/PluginInterface/PluginInterface.cpp
+++ openmp/libomptarget/plugins-nextgen/common/PluginInterface/PluginInterface.cpp
@@ -207,13 +207,16 @@
 
 void AsyncInfoWrapperTy::finalize(Error &Err) {
   assert(AsyncInfoPtr && "AsyncInfoWrapperTy already finalized");
+  static BoolEnvar ForceSynchronize("LIBOMPTARGET_FORCE_SYNCHRONIZE");
 
   // If we used a local async info object we want synchronous behavior. In that
   // case, and assuming the current status code is correct, we will synchronize
   // explicitly when the object is deleted. Update the error with the result of
   // the synchronize operation.
-  if (AsyncInfoPtr == &LocalAsyncInfo && LocalAsyncInfo.Queue && !Err)
-    Err = Device.synchronize(&LocalAsyncInfo);
+  // Optionally, if the LIBOMPTARGET_FORCE_SYNCHRONIZE env variable is set,
+  // synchronize regardless of the local async info.
+  if ((ForceSynchronize || AsyncInfoPtr == &LocalAsyncInfo) && AsyncInfoPtr->Queue && !Err)
+    Err = Device.synchronize(AsyncInfoPtr);
 
   // Invalidate the wrapper object.
   AsyncInfoPtr = nullptr;
@@ -926,6 +929,7 @@
   AsyncInfoWrapperTy AsyncInfoWrapper(*this, AsyncInfo);
 
   auto Err = dataSubmitImpl(TgtPtr, HstPtr, Size, AsyncInfoWrapper);
+
   AsyncInfoWrapper.finalize(Err);
   return Err;
 }
@@ -935,6 +939,7 @@
   AsyncInfoWrapperTy AsyncInfoWrapper(*this, AsyncInfo);
 
   auto Err = dataRetrieveImpl(HstPtr, TgtPtr, Size, AsyncInfoWrapper);
+
   AsyncInfoWrapper.finalize(Err);
   return Err;
 }
@@ -945,6 +950,7 @@
   AsyncInfoWrapperTy AsyncInfoWrapper(*this, AsyncInfo);
 
   auto Err = dataExchangeImpl(SrcPtr, DstDev, DstPtr, Size, AsyncInfoWrapper);
+
   AsyncInfoWrapper.finalize(Err);
   return Err;
 }