From: Tuan Ta <taquangtuan1992@gmail.com>
Date: Fri, 3 Jun 2016 20:20:08 +0000 (-0400)
Subject: gpu-compute: Fixed a bug in global memory pipeline
X-Git-Url: https://git.libre-soc.org/?a=commitdiff_plain;h=b6d20c25c39cc52bf9d9d4899dd5b7abfa418ae2;p=gem5.git

gpu-compute: Fixed a bug in global memory pipeline

Added a condition when inflightStores is incremented to prevent a deadlock
caused by many memory fence requests generated by a CU
---

diff --git a/src/gpu-compute/global_memory_pipeline.cc b/src/gpu-compute/global_memory_pipeline.cc
index 913327412..355018666 100644
--- a/src/gpu-compute/global_memory_pipeline.cc
+++ b/src/gpu-compute/global_memory_pipeline.cc
@@ -139,7 +139,7 @@ GlobalMemPipeline::exec()
         } else {
             if (inflightStores >= gmQueueSize) {
                 return;
-            } else {
+            } else if (mp->m_op == Enums::MO_ST) {
                 ++inflightStores;
             }
         }