[Beignet] Haswell-ULT Support?

Zhigang Gong zhigang.gong at linux.intel.com
Fri Apr 10 01:56:13 PDT 2015


I think I know the cause now. Because beignet uses some new registers which
are not in the whitelist (not included in c9224f). These new registers are
to enable atomic on L3 which is disabled by KMD by default. We will fix all
of these KMD related issue in the furture. Before that, we have to live with
both the kernel patch and this trick.

Thanks for the bisecting.

On Thu, Apr 09, 2015 at 07:43:41PM +0200, Julian Simioni wrote:
> Ok, that didn't have a very surprising result. I simply confirmed that
> f0a346b is the commit that breaks things. However I can confirm again
> that c9224f does NOT fix things on its own, only disabling the command
> parser does the trick. I'm happy to test any patches you think can fix
> this, but at least thanks for pointing me back to the echo 0 ... trick
> that I had skipped over.
> 
> Julian
> 
> On 04/08, Julian Simioni wrote:
> > Ah yes, "echo 0 > /sys/module/i915/parameters/enable_cmd_parser" fixed
> > everything. Now all the tests pass and other OpenCL using programs work
> > great! If I get a chance I will spend the time to try and bisect which
> > kernel version causes issues.
> > 
> > On 04/08/2015 11:04 AM, Zhigang Gong wrote:
> > > We tested several HSW ULT machines, and they work fine.
> > > But the kernel version is not the 4.0.0-rc6.
> > > The symptom indicates the secure batch buffer feature is not disabled.
> > >
> > > CC to Mengmeng, could you help to try this issue on a HSW ULT machine with
> > > 4.0.0-rc6 kernel?
> > > I'm afraid there may be some latest changes in the kernel which make our
> > > secure batch disable patch
> > > broken now.
> > >
> > > Thanks.
> > >
> > >> -----Original Message-----
> > >> From: Rebecca N. Palmer [mailto:rebecca_palmer at zoho.com]
> > >> Sent: Wednesday, April 8, 2015 4:53 PM
> > >> To: Zhigang Gong; 'Julian Simioni'
> > >> Cc: beignet at lists.freedesktop.org
> > >> Subject: Re: [Beignet] Haswell-ULT Support?
> > >>
> > >>> with a 4.0.0-rc6 kernel
> > >> ...which includes that fix as standard.
> > >>
> > >> Has anyone else tried beignet on Haswell-ULT, and if so, did it work?
> > 
> > _______________________________________________
> > Beignet mailing list
> > Beignet at lists.freedesktop.org
> > http://lists.freedesktop.org/mailman/listinfo/beignet



> _______________________________________________
> Beignet mailing list
> Beignet at lists.freedesktop.org
> http://lists.freedesktop.org/mailman/listinfo/beignet



More information about the Beignet mailing list