All of lore.kernel.org
 help / color / mirror / Atom feed
From: Thomas Zimmermann <tzimmermann@suse.de>
To: daniel@ffwll.ch, deller@gmx.de, javierm@redhat.com,
	geert@linux-m68k.org, sam@ravnborg.org, kraxel@redhat.com,
	ppaalanen@gmail.com
Cc: dri-devel@lists.freedesktop.org, linux-fbdev@vger.kernel.org,
	Thomas Zimmermann <tzimmermann@suse.de>
Subject: [PATCH v3 5/5] drm: Add TODO item for optimizing format helpers
Date: Wed, 23 Feb 2022 20:38:04 +0100	[thread overview]
Message-ID: <20220223193804.18636-6-tzimmermann@suse.de> (raw)
In-Reply-To: <20220223193804.18636-1-tzimmermann@suse.de>

Add a TODO item for optimizing blitting and format-conversion helpers
in DRM and fbdev. There's always demand for faster graphics output.

Signed-off-by: Thomas Zimmermann <tzimmermann@suse.de>
---
 Documentation/gpu/todo.rst | 22 ++++++++++++++++++++++
 1 file changed, 22 insertions(+)

diff --git a/Documentation/gpu/todo.rst b/Documentation/gpu/todo.rst
index 7bf7f2111696..7f113c6a02dd 100644
--- a/Documentation/gpu/todo.rst
+++ b/Documentation/gpu/todo.rst
@@ -241,6 +241,28 @@ Contact: Thomas Zimmermann <tzimmermann@suse.de>, Daniel Vetter
 
 Level: Advanced
 
+Benchmark and optimize blitting and format-conversion function
+--------------------------------------------------------------
+
+Drawing to dispay memory quickly is crucial for many applications'
+performance.
+
+On at least x86-64, sys_imageblit() is significantly slower than
+cfb_imageblit(), even though both use the same blitting algorithm and
+the latter is written for I/O memory. It turns out that cfb_imageblit()
+uses movl instructions, while sys_imageblit apparently does not. This
+seems to be a problem with gcc's optimizer. DRM's format-conversion
+heleprs might be subject to similar issues.
+
+Benchmark and optimize fbdev's sys_() helpers and DRM's format-conversion
+helpers. In cases that can be further optimized, maybe implement a different
+algorithm, For micro-optimizations, use movl/movq instructions explicitly.
+That might possibly require architecture specific helpers (e.g., storel()
+storeq()).
+
+Contact: Thomas Zimmermann <tzimmermann@suse.de>
+
+Level: Intermediate
 
 drm_framebuffer_funcs and drm_mode_config_funcs.fb_create cleanup
 -----------------------------------------------------------------
-- 
2.35.1


WARNING: multiple messages have this Message-ID (diff)
From: Thomas Zimmermann <tzimmermann@suse.de>
To: daniel@ffwll.ch, deller@gmx.de, javierm@redhat.com,
	geert@linux-m68k.org, sam@ravnborg.org, kraxel@redhat.com,
	ppaalanen@gmail.com
Cc: linux-fbdev@vger.kernel.org,
	Thomas Zimmermann <tzimmermann@suse.de>,
	dri-devel@lists.freedesktop.org
Subject: [PATCH v3 5/5] drm: Add TODO item for optimizing format helpers
Date: Wed, 23 Feb 2022 20:38:04 +0100	[thread overview]
Message-ID: <20220223193804.18636-6-tzimmermann@suse.de> (raw)
In-Reply-To: <20220223193804.18636-1-tzimmermann@suse.de>

Add a TODO item for optimizing blitting and format-conversion helpers
in DRM and fbdev. There's always demand for faster graphics output.

Signed-off-by: Thomas Zimmermann <tzimmermann@suse.de>
---
 Documentation/gpu/todo.rst | 22 ++++++++++++++++++++++
 1 file changed, 22 insertions(+)

diff --git a/Documentation/gpu/todo.rst b/Documentation/gpu/todo.rst
index 7bf7f2111696..7f113c6a02dd 100644
--- a/Documentation/gpu/todo.rst
+++ b/Documentation/gpu/todo.rst
@@ -241,6 +241,28 @@ Contact: Thomas Zimmermann <tzimmermann@suse.de>, Daniel Vetter
 
 Level: Advanced
 
+Benchmark and optimize blitting and format-conversion function
+--------------------------------------------------------------
+
+Drawing to dispay memory quickly is crucial for many applications'
+performance.
+
+On at least x86-64, sys_imageblit() is significantly slower than
+cfb_imageblit(), even though both use the same blitting algorithm and
+the latter is written for I/O memory. It turns out that cfb_imageblit()
+uses movl instructions, while sys_imageblit apparently does not. This
+seems to be a problem with gcc's optimizer. DRM's format-conversion
+heleprs might be subject to similar issues.
+
+Benchmark and optimize fbdev's sys_() helpers and DRM's format-conversion
+helpers. In cases that can be further optimized, maybe implement a different
+algorithm, For micro-optimizations, use movl/movq instructions explicitly.
+That might possibly require architecture specific helpers (e.g., storel()
+storeq()).
+
+Contact: Thomas Zimmermann <tzimmermann@suse.de>
+
+Level: Intermediate
 
 drm_framebuffer_funcs and drm_mode_config_funcs.fb_create cleanup
 -----------------------------------------------------------------
-- 
2.35.1


  parent reply	other threads:[~2022-02-23 19:38 UTC|newest]

Thread overview: 49+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2022-02-23 19:37 [PATCH v3 0/5] fbdev: Improve performance of fbdev console Thomas Zimmermann
2022-02-23 19:37 ` Thomas Zimmermann
2022-02-23 19:38 ` [PATCH v3 1/5] fbdev: Improve performance of sys_fillrect() Thomas Zimmermann
2022-02-23 19:38   ` Thomas Zimmermann
2022-02-23 19:38 ` [PATCH v3 2/5] fbdev: Improve performance of sys_imageblit() Thomas Zimmermann
2022-02-23 19:38   ` Thomas Zimmermann
2022-02-23 19:38 ` [PATCH v3 3/5] fbdev: Remove trailing whitespaces from cfbimgblt.c Thomas Zimmermann
2022-02-23 19:38   ` Thomas Zimmermann
2022-02-23 20:23   ` Sam Ravnborg
2022-02-23 20:23     ` Sam Ravnborg
2022-02-24  8:22   ` Javier Martinez Canillas
2022-02-24  8:22     ` Javier Martinez Canillas
2022-02-23 19:38 ` [PATCH v3 4/5] fbdev: Improve performance of cfb_imageblit() Thomas Zimmermann
2022-02-23 19:38   ` Thomas Zimmermann
2022-02-23 20:25   ` Sam Ravnborg
2022-02-23 20:25     ` Sam Ravnborg
2022-02-24  9:02     ` Javier Martinez Canillas
2022-02-24  9:02       ` Javier Martinez Canillas
2022-02-24 10:29       ` Sam Ravnborg
2022-02-24 10:29         ` Sam Ravnborg
2022-02-24 10:31       ` Geert Uytterhoeven
2022-02-24 10:31         ` Geert Uytterhoeven
2022-02-24  8:31   ` Javier Martinez Canillas
2022-02-24  8:31     ` Javier Martinez Canillas
2022-03-08 22:52   ` [v3,4/5] " Marek Szyprowski
2022-03-09  8:22     ` Thomas Zimmermann
2022-03-09  9:22       ` Marek Szyprowski
2022-03-09 10:39         ` Geert Uytterhoeven
2022-03-09 10:39           ` Geert Uytterhoeven
2022-03-10 19:21           ` Thomas Zimmermann
2022-03-10 19:21             ` Thomas Zimmermann
2022-03-10 19:23             ` Geert Uytterhoeven
2022-03-10 19:23               ` Geert Uytterhoeven
2022-03-13 19:23               ` Thomas Zimmermann
2022-03-13 19:23                 ` Thomas Zimmermann
2022-03-24 19:11   ` [PATCH v3 4/5] " Guenter Roeck
2022-03-24 19:11     ` Guenter Roeck
2022-03-24 19:18     ` Thomas Zimmermann
2022-03-24 19:18       ` Thomas Zimmermann
2022-03-24 21:18       ` Guenter Roeck
2022-03-24 21:18         ` Guenter Roeck
2022-02-23 19:38 ` Thomas Zimmermann [this message]
2022-02-23 19:38   ` [PATCH v3 5/5] drm: Add TODO item for optimizing format helpers Thomas Zimmermann
2022-02-23 20:34   ` Sam Ravnborg
2022-02-23 20:34     ` Sam Ravnborg
2022-02-24  8:39   ` Javier Martinez Canillas
2022-02-24  8:39     ` Javier Martinez Canillas
2022-03-02 19:30 ` [PATCH v3 0/5] fbdev: Improve performance of fbdev console Thomas Zimmermann
2022-03-02 19:30   ` Thomas Zimmermann

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=20220223193804.18636-6-tzimmermann@suse.de \
    --to=tzimmermann@suse.de \
    --cc=daniel@ffwll.ch \
    --cc=deller@gmx.de \
    --cc=dri-devel@lists.freedesktop.org \
    --cc=geert@linux-m68k.org \
    --cc=javierm@redhat.com \
    --cc=kraxel@redhat.com \
    --cc=linux-fbdev@vger.kernel.org \
    --cc=ppaalanen@gmail.com \
    --cc=sam@ravnborg.org \
    /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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.