[4.9] Disable inlining of memcpy for x86 with 'rep movs'.

On big length 'rep movs' are less efficient than libcall of
highly-optimized Bionic memcpy.

Change-Id: I9435b9e438e0e40c28c505c43ec7f9797384afd6

Signed-off-by: Andrew Senkevich <andrew.senkevich@intel.com>
Signed-off-by: Alexander Ivchenko <alexander.ivchenko@intel.com>
1 file changed
tree: da0742130875591093e67df1d3ce90fdd9a30b2f
  1. gcc-4.8/
  2. gcc-4.9/
  3. build-gcc.sh
  4. build.py