dri-devel Archive on lore.kernel.org
 help / color / mirror / Atom feed
From: Harry Wentland <harry.wentland@amd.com>
To: Nemesa Garg <nemesa.garg@intel.com>,
	intel-gfx@lists.freedesktop.org, dri-devel@lists.freedesktop.org
Cc: Pekka Paalanen <ppaalanen@gmail.com>,
	Sebastian Wick <sebastian.wick@redhat.com>,
	Xaver Hugl <xaver.hugl@gmail.com>
Subject: Re: [RFC 0/5] Introduce drm sharpening property
Date: Thu, 15 Feb 2024 11:37:54 -0500	[thread overview]
Message-ID: <640e06ab-73f6-450a-97c2-8ef2e9ebe8b7@amd.com> (raw)
In-Reply-To: <20240214112457.3734871-1-nemesa.garg@intel.com>

Adding a couple of compositor devs as they might be interested in this.

On 2024-02-14 06:24, Nemesa Garg wrote:
> 	Many a times images are blurred or upscaled content is also not as
> crisp as original rendered image. Traditional sharpening techniques often
> apply a uniform level of enhancement across entire image, which sometimes
> result in over-sharpening of some areas and potential loss of natural details. 
> 
> Intel has come up with Display Engine based adaptive sharpening filter 
> with minimal power and performance impact. From LNL onwards, the Display
> hardware can use one of the pipe scaler for adaptive sharpness filter.
> This can be used for both gaming and non-gaming use cases like photos,
> image viewing. It works on a region of pixels depending on the tap size.
> 
> This RFC is an attempt to introduce an adaptive sharpness solution which
> helps in improving the image quality. For this new CRTC property is added.

I don't think CRTC is the right place for this. Scaling tends to be more
of a plane thing. Planes can be scaled independently, or is that not the
case for Intel? Or does Intel HW do this sharpening operation independent
of any scaling, on the entire output?

> The user can set this property with desired sharpness strength value with
> 0-255. A value of 1 representing minimum sharpening strength and 255
> representing maximum sharpness strength. A strength value of 0 means no
> sharpening or sharpening feature disabled.
> It works on a region of pixels depending on the tap size. The coefficients
> are used to generate an alpha value which is used to blend the sharpened
> image to original image.
>  
> Userspace implementation for sharpening feature and IGT implementation
> is in progress.

It would be very helpful to have an idea how this looks in userspace, and
which compositors will implement this.

Harry

> 
> Nemesa Garg (5):
>   drm: Introduce sharpeness mode property
>   drm/i915/display/: Compute the scaler filter coefficients
>   drm/i915/dispaly/: Enable the second scaler
>   drm/i915/display/: Add registers and compute the strength
>   drm/i915/display: Load the lut values and enable sharpness
> 
>  drivers/gpu/drm/drm_atomic_uapi.c             |   4 +
>  drivers/gpu/drm/drm_crtc.c                    |  17 ++
>  drivers/gpu/drm/i915/Makefile                 |   1 +
>  drivers/gpu/drm/i915/display/intel_crtc.c     |   3 +
>  drivers/gpu/drm/i915/display/intel_display.c  |  20 +-
>  .../drm/i915/display/intel_display_types.h    |  11 +
>  .../drm/i915/display/intel_modeset_verify.c   |   1 +
>  .../drm/i915/display/intel_sharpen_filter.c   | 214 ++++++++++++++++++
>  .../drm/i915/display/intel_sharpen_filter.h   |  31 +++
>  drivers/gpu/drm/i915/display/skl_scaler.c     |  86 ++++++-
>  drivers/gpu/drm/i915/display/skl_scaler.h     |   1 +
>  drivers/gpu/drm/i915/i915_reg.h               |  19 ++
>  drivers/gpu/drm/xe/Makefile                   |   1 +
>  include/drm/drm_crtc.h                        |  17 ++
>  14 files changed, 416 insertions(+), 10 deletions(-)
>  create mode 100644 drivers/gpu/drm/i915/display/intel_sharpen_filter.c
>  create mode 100644 drivers/gpu/drm/i915/display/intel_sharpen_filter.h
> 


  parent reply	other threads:[~2024-02-15 16:38 UTC|newest]

Thread overview: 20+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2024-02-14 11:24 [RFC 0/5] Introduce drm sharpening property Nemesa Garg
2024-02-14 11:24 ` [RFC 1/5] drm: Introduce sharpeness mode property Nemesa Garg
2024-02-14 11:24 ` [RFC 2/5] drm/i915/display/: Compute the scaler filter coefficients Nemesa Garg
2024-02-14 11:24 ` [RFC 3/5] drm/i915/dispaly/: Enable the second scaler Nemesa Garg
2024-02-14 11:24 ` [RFC 4/5] drm/i915/display/: Add registers and compute the strength Nemesa Garg
2024-02-14 11:24 ` [RFC 5/5] drm/i915/display: Load the lut values and enable sharpness Nemesa Garg
2024-02-15  8:33 ` [RFC 0/5] Introduce drm sharpening property Simon Ser
2024-02-16  4:28   ` Garg, Nemesa
2024-02-16  8:36     ` Pekka Paalanen
2024-03-04 14:04       ` Garg, Nemesa
2024-03-04 14:15         ` Simon Ser
2024-03-12  8:30           ` Garg, Nemesa
2024-03-12 14:26             ` Pekka Paalanen
2024-03-13  9:36               ` Pekka Paalanen
2024-03-27  7:11                 ` Garg, Nemesa
2024-03-27 11:29                   ` Pekka Paalanen
2024-03-28 10:04                     ` Pekka Paalanen
2024-06-19 11:23                       ` Garg, Nemesa
2024-02-15 16:37 ` Harry Wentland [this message]
2024-02-15 16:48   ` Ville Syrjälä

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=640e06ab-73f6-450a-97c2-8ef2e9ebe8b7@amd.com \
    --to=harry.wentland@amd.com \
    --cc=dri-devel@lists.freedesktop.org \
    --cc=intel-gfx@lists.freedesktop.org \
    --cc=nemesa.garg@intel.com \
    --cc=ppaalanen@gmail.com \
    --cc=sebastian.wick@redhat.com \
    --cc=xaver.hugl@gmail.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