Remove unnecessary barrier in share mem handle cuda ipc

csrc/multidevice/ipc_handle.cpp

@@ -143,6 +143,9 @@ void IpcHandleCache::exchangeHandles(
     insert(communication, std::move(ipc_handles));
   }
 
+  if (non_cached_communications.empty()) {
+    return;
+  }
   // a barrier is needed here to ensure all ranks have received the
   // memhandles and the keys are deleted from the store before the next call to
   // exchangeHandles, otherwise there is a correctness issue

tests/cpp/test_multidevice_host_ir_overlap.cpp

@@ -1261,7 +1261,9 @@ TEST_F(
   hic->addOutput(tva_j_next_slice);
   hic->addOutput(tvc_j);
 
-  hir::HostIrEvaluator hie(std::move(hic), communicator_);
+  HostIrEvaluatorParams params;
+  params.use_allocation_cache = true;
+  hir::HostIrEvaluator hie(std::move(hic), communicator_, params);
 
   at::manual_seed(getATenRandomSeed());