From 64f06d0b4a9e5b3b97538c7cd809531a8f7b93af Mon Sep 17 00:00:00 2001
From: cao lei <jslhcl@gmail.com>
Date: Wed, 30 Aug 2023 16:10:26 -0700
Subject: [PATCH] only Flush once for the same stream in
 copyInputAcrossDevice() (#17303)

### Description
<!-- Describe your changes. -->
In CopyInputAcrossDevice() function, we assign each feed a stream to
copy across device, once the copy is done, each stream will trigger the
Flush() function which is undesired. Same stream should be only flushed
once


### Motivation and Context
<!-- - Why is this change required? What problem does it solve?
- If it fixes an open issue, please link to the issue here. -->
This change is to address a perf issue of TLNGv4 inference which
contains subgraph with many input feeds.
---
 onnxruntime/core/framework/utils.cc | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/onnxruntime/core/framework/utils.cc b/onnxruntime/core/framework/utils.cc
index d762211f78..b6dd851734 100644
--- a/onnxruntime/core/framework/utils.cc
+++ b/onnxruntime/core/framework/utils.cc
@@ -478,9 +478,9 @@ static common::Status CopyInputsAcrossDevices(const SessionState& session_state,
   // TODO: this sync is because the graph inputs can be consumed by multiple stream,
   // but we can only place the MemCpyAsync on one of the stream. Ideally we should make
   // other stream wait on the event of the memory copy stream, instead of host sync stream.
+  std::unordered_set<Stream*> visited;
   for (auto* stream : feed_streams) {
-    if (stream)
-      stream->Flush();
+    if (stream && visited.insert(stream).second) stream->Flush();
   }
   return Status::OK();
 }