From f10a598e34da5ea4060ccfb8a027dd5c37c108c0 Mon Sep 17 00:00:00 2001
From: Derek Murray <mrry@google.com>
Date: Fri, 22 Dec 2017 15:39:18 -0800
Subject: [PATCH] Avoid unnecessary copying and allocation in
 `ExecutorBarrier::WhenDone()`.

Previously the code would make a copy of the `done_cb_` and update the status
on a successful completion, neither of which is necessary, and both of which
showed up in trace amounts in profiling.

PiperOrigin-RevId: 179970701
---
 tensorflow/core/common_runtime/executor.h | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/tensorflow/core/common_runtime/executor.h b/tensorflow/core/common_runtime/executor.h
index b5f4ebb0053..3fd932da5b6 100644
--- a/tensorflow/core/common_runtime/executor.h
+++ b/tensorflow/core/common_runtime/executor.h
@@ -202,11 +202,12 @@ class ExecutorBarrier {
       // below.
       if (--pending_ == 0) {
         CHECK(done_cb_ != nullptr);
-        done = done_cb_;
-        done_cb_ = nullptr;
+        std::swap(done, done_cb_);
       }
 
-      status = status_;
+      if (!status_.ok()) {
+        status = status_;
+      }
     }
 
     if (error) {