Daniel Vetter writes:
> On Wed, Jan 11, 2017 at 12:24:59PM +, Chris Wilson wrote:
>> On Wed, Jan 11, 2017 at 02:07:37PM +0200, Mika Kuoppala wrote:
>> > Daniel Vetter writes:
>> >
>> > > On Mon, Jan 09, 2017 at 01:07:56PM -0800, Francisco Jerez wrote:
>> > >> The WaDisableLSQCROPERFforOCL w
Daniel Vetter writes:
> On Mon, Jan 09, 2017 at 01:07:56PM -0800, Francisco Jerez wrote:
>> The WaDisableLSQCROPERFforOCL workaround has the side effect of
>> disabling an L3SQ optimization that has huge performance implications
>> and is unlikely to be necessary for the correct functioning of us
On Wed, Jan 11, 2017 at 12:24:59PM +, Chris Wilson wrote:
> On Wed, Jan 11, 2017 at 02:07:37PM +0200, Mika Kuoppala wrote:
> > Daniel Vetter writes:
> >
> > > On Mon, Jan 09, 2017 at 01:07:56PM -0800, Francisco Jerez wrote:
> > >> The WaDisableLSQCROPERFforOCL workaround has the side effect o
On Wed, Jan 11, 2017 at 02:07:37PM +0200, Mika Kuoppala wrote:
> Daniel Vetter writes:
>
> > On Mon, Jan 09, 2017 at 01:07:56PM -0800, Francisco Jerez wrote:
> >> The WaDisableLSQCROPERFforOCL workaround has the side effect of
> >> disabling an L3SQ optimization that has huge performance implicat
LGTM. Thanks.
-Original Message-
From: Beignet [mailto:beignet-boun...@lists.freedesktop.org] On Behalf Of Yang
Rong
Sent: Wednesday, January 11, 2017 6:16 PM
To: beignet@lists.freedesktop.org
Cc: Yang, Rong R
Subject: [Beignet] [PATCH] Add some pointer access check.
Signed-off-by: Yang
LGTM, pushed.
> -Original Message-
> From: Beignet [mailto:beignet-boun...@lists.freedesktop.org] On Behalf Of
> junyan...@inbox.com
> Sent: Wednesday, January 11, 2017 16:36
> To: beignet@lists.freedesktop.org
> Cc: He, Junyan
> Subject: [Beignet] [PATCH] Fix two bugs about command queue
Signed-off-by: Yang Rong
---
backend/src/backend/gen_reg_allocation.cpp | 4 ++--
src/cl_command_queue.c | 1 +
src/cl_device_enqueue.c| 3 +++
src/cl_utils.c | 2 +-
4 files changed, 7 insertions(+), 3 deletions(-)
diff --git a
From: Junyan He
1. Call finish before we destroy the command queue.
We should make sure all the commands in the queue are
finished before we really destroy the command_queue.
If not, may cause event status error. We leave the queue's
life time to user and do not ref the queue when cre
On Mon, Jan 09, 2017 at 01:07:56PM -0800, Francisco Jerez wrote:
> The WaDisableLSQCROPERFforOCL workaround has the side effect of
> disabling an L3SQ optimization that has huge performance implications
> and is unlikely to be necessary for the correct functioning of usual
> graphic workloads. Use
Move the invariant parts of context desc setup from execlist init
to context creation. This is advantageous when we need to
create different templates based on the context parametrization,
ie. for svm capable contexts.
Cc: Chris Wilson
Signed-off-by: Mika Kuoppala
---
drivers/gpu/drm/i915/i915_
Hi,
Now when the blocking problems with iommu layer have been
solved by commits 910170442944e1f8674fd5ddbeeb8ccd1877ea98
and 65ca7f5f7d1cdde6c25172fe6107cd16902f826f it is possible
to test and experiment with this code on KBL.
I have tried to accomodate all the review feedback that
was given by t
From: Jesse Barnes
We just need to pass in an address to execute and some flags, since we
don't have to worry about buffer relocation or any of the other usual
stuff. Takes in a fance and returns a fence to be used for
synchronization.
v2: add a request after batch submission (Jesse)
v3: add a
From: Jesse Barnes
Use David's new IOMMU layer functions for supporting SVM in i915.
TODO:
error record collection for failing SVM contexts
callback handling for fatal faults
scheduling
v2: integrate David's core IOMMU support
make sure we don't clobber the PASID in the context reg st
13 matches
Mail list logo