Messages in this thread | | | From | Andy Lutomirski <> | Date | Mon, 10 Aug 2015 13:39:39 -0700 | Subject | Re: [lkp] [x86/build] b2c51106c75: -18.1% will-it-scale.per_process_ops |
| |
On Wed, Aug 5, 2015 at 1:38 AM, Ingo Molnar <mingo@kernel.org> wrote: > > * kernel test robot <ying.huang@intel.com> wrote: > >> FYI, we noticed the below changes on >> >> git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git x86/asm >> commit b2c51106c7581866c37ffc77c5d739f3d4b7cbc9 ("x86/build: Fix detection of GCC -mpreferred-stack-boundary support") > > Does the performance regression go away reproducibly if you do: > > git revert b2c51106c7581866c37ffc77c5d739f3d4b7cbc9 > > ?
FWIW, I spot-checked the generated code. All I saw were the deletion of some dummy subtraction from rsp to align the stack for children, changes of stack frame offsets, and a couple instances in which instructions got reordered.
--Andy
| |