On Wed, Feb 02, 2022 at 11:15:00PM +0100, Michal Wajdeczko wrote:
>
>
> On 13.01.2022 17:27, Matthew Brost wrote:
> > Move the multi-lrc guc_id from the lower allocation partition (0 to
> > number of multi-lrc guc_ids) to upper allocation partition (number of
> > single-lrc to max guc_ids).
> >
On 13.01.2022 17:27, Matthew Brost wrote:
> Move the multi-lrc guc_id from the lower allocation partition (0 to
> number of multi-lrc guc_ids) to upper allocation partition (number of
> single-lrc to max guc_ids).
>
> This will help when a native driver transitions to a PF after driver
> load t
Move the multi-lrc guc_id from the lower allocation partition (0 to
number of multi-lrc guc_ids) to upper allocation partition (number of
single-lrc to max guc_ids).
This will help when a native driver transitions to a PF after driver
load time. If the perma-pin guc_ids (kernel contexts) are in a
On Thu, Jan 13, 2022 at 03:18:14PM +0100, Michal Wajdeczko wrote:
>
>
> On 13.01.2022 00:26, Matthew Brost wrote:
> > On Thu, Jan 13, 2022 at 12:21:17AM +0100, Michal Wajdeczko wrote:
> >> On 11.01.2022 17:30, Matthew Brost wrote:
>
> ...
>
> >>> @@ -1863,6 +1861,33 @@ static void guc_submit_re
On 13.01.2022 00:26, Matthew Brost wrote:
> On Thu, Jan 13, 2022 at 12:21:17AM +0100, Michal Wajdeczko wrote:
>> On 11.01.2022 17:30, Matthew Brost wrote:
...
>>> @@ -1863,6 +1861,33 @@ static void guc_submit_request(struct i915_request
>>> *rq)
>>> spin_unlock_irqrestore(&sched_engine->l
Move the multi-lrc guc_id from the lower allocation partition (0 to
number of multi-lrc guc_ids) to upper allocation partition (number of
single-lrc to max guc_ids).
This will help when a native driver transitions to a PF after driver
load time. If the perma-pin guc_ids (kernel contexts) are in a
On Thu, Jan 13, 2022 at 12:21:17AM +0100, Michal Wajdeczko wrote:
>
>
> On 11.01.2022 17:30, Matthew Brost wrote:
> > Move the multi-lrc guc_id from the lower allocation partition (0 to
> > number of multi-lrc guc_ids) to upper allocation partition (number of
> > single-lrc to max guc_ids).
> >
On 11.01.2022 17:30, Matthew Brost wrote:
> Move the multi-lrc guc_id from the lower allocation partition (0 to
> number of multi-lrc guc_ids) to upper allocation partition (number of
> single-lrc to max guc_ids).
>
> Signed-off-by: Matthew Brost
> ---
> .../gpu/drm/i915/gt/uc/intel_guc_submi
On Wed, Jan 12, 2022 at 06:09:06PM +0100, Piotr Piórkowski wrote:
> Tvrtko Ursulin wrote on śro [2022-sty-12
> 08:54:19 +]:
> >
> > On 11/01/2022 16:30, Matthew Brost wrote:
> > > Move the multi-lrc guc_id from the lower allocation partition (0 to
> > > number of multi-lrc guc_ids) to upper
Tvrtko Ursulin wrote on śro [2022-sty-12
08:54:19 +]:
>
> On 11/01/2022 16:30, Matthew Brost wrote:
> > Move the multi-lrc guc_id from the lower allocation partition (0 to
> > number of multi-lrc guc_ids) to upper allocation partition (number of
> > single-lrc to max guc_ids).
>
> Just a re
On 11/01/2022 16:30, Matthew Brost wrote:
Move the multi-lrc guc_id from the lower allocation partition (0 to
number of multi-lrc guc_ids) to upper allocation partition (number of
single-lrc to max guc_ids).
Just a reminder that best practice for commit messages is to include the
"why" as we
Move the multi-lrc guc_id from the lower allocation partition (0 to
number of multi-lrc guc_ids) to upper allocation partition (number of
single-lrc to max guc_ids).
Signed-off-by: Matthew Brost
---
.../gpu/drm/i915/gt/uc/intel_guc_submission.c | 57 ++-
1 file changed, 42 insert
12 matches
Mail list logo
