Merge pull request #8621 from ggouaillardet/topic/gcc_builtin_workaround

gcc_builtin: fix performance regression on x86_64
open-mpi · Mar 16, 2021 · 2383393 · 2383393
2 parents bf60e2e + d7e3f87
commit 2383393
Showing 1 changed file with 4 additions and 5 deletions.
diff --git a/opal/include/opal/sys/gcc_builtin/atomic.h b/opal/include/opal/sys/gcc_builtin/atomic.h
@@ -13,8 +13,8 @@
  * Copyright (c) 2011      Sandia National Laboratories. All rights reserved.
  * Copyright (c) 2014-2018 Los Alamos National Security, LLC. All rights
  *                         reserved.
- * Copyright (c) 2016-2017 Research Organization for Information Science
- *                         and Technology (RIST). All rights reserved.
+ * Copyright (c) 2016-2021 Research Organization for Information Science
+ *                         and Technology (RIST).  All rights reserved.
  * Copyright (c) 2018      Triad National Security, LLC. All rights
  *                         reserved.
  * $COPYRIGHT$
@@ -61,9 +61,8 @@ static inline void opal_atomic_rmb(void)
 {
 #if OPAL_ASSEMBLY_ARCH == OPAL_X86_64
     /* work around a bug in older gcc versions where ACQUIRE seems to get
-     * treated as a no-op instead of being equivalent to
-     * __asm__ __volatile__("": : :"memory") */
-    __atomic_thread_fence (__ATOMIC_SEQ_CST);
+     * treated as a no-op instead */
+    __asm__ __volatile__("": : :"memory");
 #else
     __atomic_thread_fence (__ATOMIC_ACQUIRE);
 #endif