intel-xe.lists.freedesktop.org archive mirror
 help / color / mirror / Atom feed
From: "Dixit, Ashutosh" <ashutosh.dixit@intel.com>
To: <intel-xe@lists.freedesktop.org>
Cc: Umesh Nerlige Ramappa <umesh.nerlige.ramappa@intel.com>
Subject: Re: [PATCH 1/5] drm/xe/oa/uapi: Expose media OA units
Date: Mon, 16 Jun 2025 15:26:30 -0700	[thread overview]
Message-ID: <85zfe7jpbd.wl-ashutosh.dixit@intel.com> (raw)
In-Reply-To: <87wm9j2oim.wl-ashutosh.dixit@intel.com>

On Tue, 10 Jun 2025 15:57:37 -0700, Dixit, Ashutosh wrote:
>
> On Fri, 06 Jun 2025 12:21:11 -0700, Dixit, Ashutosh wrote:
> >
> > On Fri, 06 Jun 2025 10:37:53 -0700, Umesh Nerlige Ramappa wrote:
> > >
> > > On Fri, Jun 06, 2025 at 09:02:49AM -0700, Ashutosh Dixit wrote:
> > > > On Xe2+ platforms, media engines are attached to "SCMI" OA media (OAM)
> > > > units. One or more SCMI OAM units might be present on a platform. In
> > > > addition there is another OAM unit for global events, called
> > > > OAM-SAG. Performance metrics for media workloads can be obtained from these
> > > > OAM units, similar to OAG.
> > > >
> > > > Expose these OAM units for userspace to use. OAM-SAG is exposed as an OA
> > > > unit without any attached engines.
> > > >
> > > > Bspec: 70819, 67103, 63844, 72572, 74476, 61284
> > > >
> > > > v2: Fix xe_gt_WARN_ON in __hwe_oam_unit for < 12.7 platforms
> > > > v3: Return XE_OA_UNIT_INVALID for < 12.7 to indicate no OAM units
> > > > v4: Move xe_oa_print_oa_units() to separate patch
> > > > v5: Introduce DRM_XE_OA_UNIT_TYPE_OAM_SAG
> > > >
> > > > Signed-off-by: Ashutosh Dixit <ashutosh.dixit@intel.com>
> > >
> > > LGTM,
> > >
> > > Reviewed-by: Umesh Nerlige Ramappa <umesh.nerlige.ramappa@intel.com>
> >
> > Thanks Umesh. I also just added a DRM_XE_OA_CAPS_OAM capability also to
> > this patch. I was debating initially, since userland will see at least 2
> > OAM units after this series is merged, so that is the way to figure out if
> > correct OAM support is present in the driver. But then went ahead and added
> > DRM_XE_OA_CAPS_OAM, since that's how we've been doing things: if you change
> > uapi, you add a capability. Thanks.
>
> MDAPI PR which consumes uapi changes in this patch:
>
> https://github.com/intel/metrics-discovery/pull/35

More user space updates for this series:

- IGT xe perf tools update:

  https://patchwork.freedesktop.org/series/150274/

- gpuvis PR:

  https://github.com/mikesart/gpuvis/pull/100/

  reply	other threads:[~2025-06-16 22:26 UTC|newest]

Thread overview: 24+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2025-06-06 16:02 [PATCH v4 0/5] Enable media OA Ashutosh Dixit
2025-06-06 16:02 ` [PATCH 1/5] drm/xe/oa/uapi: Expose media OA units Ashutosh Dixit
2025-06-06 17:37   ` Umesh Nerlige Ramappa
2025-06-06 19:21     ` Dixit, Ashutosh
2025-06-10 22:57       ` Dixit, Ashutosh
2025-06-16 22:26         ` Dixit, Ashutosh [this message]
2025-06-06 16:02 ` [PATCH 2/5] drm/xe/oa: Print hwe to OA unit mapping Ashutosh Dixit
2025-06-06 16:02 ` [PATCH 3/5] drm/xe/oa: Introduce stream->oa_unit Ashutosh Dixit
2025-06-06 16:02 ` [PATCH 4/5] drm/xe/oa: Assign hwe for OAM_SAG Ashutosh Dixit
2025-06-06 17:40   ` Umesh Nerlige Ramappa
2025-06-06 16:02 ` [PATCH 5/5] drm/xe/oa: Enable OAM latency measurement Ashutosh Dixit
2025-06-06 16:08 ` ✓ CI.Patch_applied: success for Enable media OA Patchwork
2025-06-06 16:08 ` ✓ CI.checkpatch: " Patchwork
2025-06-06 16:09 ` ✓ CI.KUnit: " Patchwork
2025-06-06 16:20 ` ✓ CI.Build: " Patchwork
2025-06-06 16:23 ` ✓ CI.Hooks: " Patchwork
2025-06-06 16:25 ` ✓ CI.checksparse: " Patchwork
2025-06-06 17:10 ` ✓ Xe.CI.BAT: " Patchwork
2025-06-08 21:21 ` ✗ Xe.CI.Full: failure " Patchwork
  -- strict thread matches above, loose matches on Subject: below --
2025-06-06 19:26 [PATCH 0/5] " Ashutosh Dixit
2025-06-06 19:26 ` [PATCH 1/5] drm/xe/oa/uapi: Expose media OA units Ashutosh Dixit
2025-06-03 20:21 [PATCH v3 0/5] Enable media OA Ashutosh Dixit
2025-06-03 20:21 ` [PATCH 1/5] drm/xe/oa/uapi: Expose media OA units Ashutosh Dixit
2025-06-04 23:42   ` Umesh Nerlige Ramappa
2025-06-05 18:28     ` Dixit, Ashutosh
2025-06-06 16:42       ` Dixit, Ashutosh

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=85zfe7jpbd.wl-ashutosh.dixit@intel.com \
    --to=ashutosh.dixit@intel.com \
    --cc=intel-xe@lists.freedesktop.org \
    --cc=umesh.nerlige.ramappa@intel.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).