This is the mail archive of the
gcc@gcc.gnu.org
mailing list for the GCC project.
Re: Libitm issues porting to POWER8 HTM
- From: Andi Kleen <andi at firstfloor dot org>
- To: Peter Bergner <bergner at vnet dot ibm dot com>
- Cc: Andi Kleen <andi at firstfloor dot org>, "gcc at gcc dot gnu dot org" <gcc at gcc dot gnu dot org>, Andreas Krebbel <krebbel at linux dot ibm dot com>
- Date: Wed, 19 Jun 2013 18:31:00 +0200
- Subject: Re: Libitm issues porting to POWER8 HTM
- References: <1371257094 dot 1396 dot 189 dot camel at otta> <871u7zgtx9 dot fsf at tassilo dot jf dot intel dot com> <1371581293 dot 5516 dot 7 dot camel at otta> <20130618194858 dot GQ6123 at two dot firstfloor dot org> <1371657865 dot 5516 dot 30 dot camel at otta>
On Wed, Jun 19, 2013 at 11:04:25AM -0500, Peter Bergner wrote:
> On Tue, 2013-06-18 at 21:48 +0200, Andi Kleen wrote:
> > > Given Torvald's comment, can you verify whether your hw txn succeeds
> > > (all the way to commit) or whether it is failing and somehow skips
> > > the fall through code that is hanging for us (Power and S390)?
> >
> > All the 3 transactions in reentrant.c abort.
>
> Can you please explain the above? When you say abort, do you mean
> that libitm is calling htm_abort() or that your xbegin hardware
> instruction isn't succeeding?
XBEGIN aborts, according to the hardware counters.
>
> > That's not surprising, because there are usually lots of aborts in
> > the startup phase of programs, and the test doesn't use a loop.
>
> Is this a libitm statement or an Intel RTM statement, that the
> startup phase usually has lots of aborts?
This is a Intel RTM statement.
-Andi