On Mon, 29 Jan 2018 16:47:45 +0100 Thomas Monjalon <tho...@monjalon.net> wrote:
> 15/01/2018 16:09, Konstantin Ananyev: > > On x86 it is possible to use lock-prefixed instructions to get > > the similar effect as mfence. > > As pointed by Java guys, on most modern HW that gives a better > > performance than using mfence: > > https://shipilev.net/blog/2014/on-the-fence-with-dependencies/ > > That patch adopts that technique for rte_smp_mb() implementation. > > On BDW 2.2 mb_autotest on single lcore reports 2X cycle reduction, > > i.e. from ~110 to ~55 cycles per operation. > > > > Signed-off-by: Konstantin Ananyev <konstantin.anan...@intel.com> > > Acked-by: Bruce Richardson <bruce.richard...@intel.com> > > Applied, thanks Does this change since lfence is one of the ways to block Spectre variant.
