Improve ethread atomics based on GCC builtins

* Use of __atomic builtins when available.
* Improved configure test that checks for missing memory
  barrier in __sync_synchronize(). The old approach was to
  verify known working gcc versions and check gcc version at
  compile time. Besides not being very safe, the old approach
  often unnecessarily caused usage of the very expensive
  workaround.
* Introduced (no overhead) workaround for missing clobber in
  __sync_synchronize() when using buggy LLVM implementation of
  __sync_synchronize().
* Implement native memory barriers for ARM processors supporting
  the DMB instruction.
* Use of volatile store on Alpha as atomic set operation if no
  __atomic_store_n() is available (already used on x86/x86_64
  Sparc V9, PowerPC, and MIPS). Fallback used when not using
  volatile store is typically very expensive.
* Use volatile load on Alpha and ARM as atomic read operation
  if no __atomic_load_n() is available (already used on
  x86/x86_64 Sparc V9, PowerPC, and MIPS). Fallback when not
  using volatile load is typically very expensive.

1 files changed, 4 insertions, 1 deletions

diff --git a/erts/include/internal/ethread.h b/erts/include/internal/ethread.h
index ad5d05704c..ac40163a1a 100644
--- a/erts/include/internal/ethread.h
+++ b/erts/include/internal/ethread.h
@@ -1,7 +1,7 @@
 /*
  * %CopyrightBegin%
  *
- * Copyright Ericsson AB 2004-2013. All Rights Reserved.
+ * Copyright Ericsson AB 2004-2015. All Rights Reserved.
  *
  * The contents of this file are subject to the Erlang Public License,
  * Version 1.1, (the "License"); you may not use this file except in
@@ -364,6 +364,9 @@ extern ethr_runtime_t ethr_runtime__;
 #          include "sparc64/ethread.h"
 #        endif
 #      endif
+#      if ETHR_HAVE_GCC___ATOMIC_BUILTINS
+#        include "gcc/ethread.h"
+#      endif
 #      include "libatomic_ops/ethread.h"
 #      include "gcc/ethread.h"
 #    endif