[SYCL][CUDA] Adds unimplemented cuda_piEnqueueEventsWaitWithBarrier (#3581)

Adds the function cuda_piEnqueueEventsWaitWithBarrier for
piEnqueueEventsWaitWithBarrier in PI CUDA. The underlying functionality
is currently unimplemented.

Signed-off-by: Steffen Larsen <[email protected]>

Author: steffenlarsen

sycl/plugins/cuda/pi_cuda.cpp

@@ -3320,6 +3320,28 @@ pi_result cuda_piEnqueueEventsWait(pi_queue command_queue,
   }
 }
 
+/// Enqueues a wait on the given CUstream for all specified events (See
+/// \ref enqueueEventWait.) If the events list is empty, the enqueued wait will
+/// wait on all previous events in the queue.
+/// TODO: Implement this.
+///
+/// \param[in] command_queue A valid PI queue.
+/// \param[in] num_events_in_wait_list Number of events in event_wait_list.
+/// \param[in] event_wait_list Events to wait on.
+/// \param[out] event Event for when all events in event_wait_list have finished
+/// or, if event_wait_list is empty, when all previous events in the queue have
+/// finished.
+///
+/// \return TBD
+pi_result cuda_piEnqueueEventsWaitWithBarrier(pi_queue command_queue,
+                                              pi_uint32 num_events_in_wait_list,
+                                              const pi_event *event_wait_list,
+                                              pi_event *event) {
+  cl::sycl::detail::pi::die(
+      "cuda_piEnqueueEventsWaitWithBarrier not implemented");
+  return {};
+}
+
 /// Gets the native CUDA handle of a PI event object
 ///
 /// \param[in] event The PI event to get the native CUDA object of.
@@ -4710,6 +4732,7 @@ pi_result piPluginInit(pi_plugin *PluginInit) {
   _PI_CL(piEnqueueKernelLaunch, cuda_piEnqueueKernelLaunch)
   _PI_CL(piEnqueueNativeKernel, cuda_piEnqueueNativeKernel)
   _PI_CL(piEnqueueEventsWait, cuda_piEnqueueEventsWait)
+  _PI_CL(piEnqueueEventsWaitWithBarrier, cuda_piEnqueueEventsWaitWithBarrier)
   _PI_CL(piEnqueueMemBufferRead, cuda_piEnqueueMemBufferRead)
   _PI_CL(piEnqueueMemBufferReadRect, cuda_piEnqueueMemBufferReadRect)
   _PI_CL(piEnqueueMemBufferWrite, cuda_piEnqueueMemBufferWrite)