From mboxrd@z Thu Jan 1 00:00:00 1970 From: Chris Wilson Subject: Re: [PATCH 0/9] gpu hang and swizzle patches Date: Fri, 11 Nov 2011 00:15:43 +0000 Message-ID: References: <1320931087-1557-1-git-send-email-daniel.vetter@ffwll.ch> Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit Return-path: Received: from mga01.intel.com (mga01.intel.com [192.55.52.88]) by gabe.freedesktop.org (Postfix) with ESMTP id 8CD9F9E7FF for ; Thu, 10 Nov 2011 16:15:51 -0800 (PST) In-Reply-To: <1320931087-1557-1-git-send-email-daniel.vetter@ffwll.ch> List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Sender: intel-gfx-bounces+gcfxdi-intel-gfx=m.gmane.org@lists.freedesktop.org Errors-To: intel-gfx-bounces+gcfxdi-intel-gfx=m.gmane.org@lists.freedesktop.org To: intel-gfx Cc: Daniel Vetter List-Id: intel-gfx@lists.freedesktop.org On Thu, 10 Nov 2011 14:17:58 +0100, Daniel Vetter wrote: > Hi all, > > This is a bit a mixed pile, but I've used all the earlier patches to test > the gen6+ swizzling patch and I like to send out patch series somewhat > resembling the setup I've tested them in. > > Patches 1-2 refactor our debugfs code a bit. > Patches 3-5 implement a debugfs interface to simulate a gpu hang Patch 6 > fixes the swizzle detection on i915G/i945G. This one is for stable and > independent of the previous patches. > Patches 7-8 add a debugfs file with information to debug swizzle issues > Patch 9 implements swizzle support for snb/ivb when in dual-channel mode > > Benchmarking on my snb is notoriously difficult, but swizzling seems to > yield a few percent in some workloads, topping out at 5% for padman. > > Review highly welcome. I've had a play and could barely detect any improvement above the noise. However, I've read through all the patches and passed on my comments and I don't see anything fundamentally wrong with them (though I see enough GPU hangs not to need to manually trigger one ;-). -Chris -- Chris Wilson, Intel Open Source Technology Centre