summaryrefslogtreecommitdiffstats
path: root/Documentation/gpu/todo.rst
diff options
context:
space:
mode:
authorThomas Zimmermann <tzimmermann@suse.de>2022-02-23 20:38:04 +0100
committerThomas Zimmermann <tzimmermann@suse.de>2022-03-02 20:26:02 +0100
commit9ae2ac4d31a85ce59cc560d514a31b95f4ace154 (patch)
treea11406e9e6d448237a69c6c55a628db0394dce62 /Documentation/gpu/todo.rst
parentfbdev: Improve performance of cfb_imageblit() (diff)
downloadlinux-9ae2ac4d31a85ce59cc560d514a31b95f4ace154.tar.xz
linux-9ae2ac4d31a85ce59cc560d514a31b95f4ace154.zip
drm: Add TODO item for optimizing format helpers
Add a TODO item for optimizing blitting and format-conversion helpers in DRM and fbdev. There's always demand for faster graphics output. v4: * fix typos (Sam) Signed-off-by: Thomas Zimmermann <tzimmermann@suse.de> Reviewed-by: Javier Martinez Canillas <javierm@redhat.com> Acked-by: Sam Ravnborg <sam@ravnborg.org> Link: https://patchwork.freedesktop.org/patch/msgid/20220223193804.18636-6-tzimmermann@suse.de
Diffstat (limited to 'Documentation/gpu/todo.rst')
-rw-r--r--Documentation/gpu/todo.rst22
1 files changed, 22 insertions, 0 deletions
diff --git a/Documentation/gpu/todo.rst b/Documentation/gpu/todo.rst
index d6a7ebf717be..4260c62d751b 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
+helpers 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
-----------------------------------------------------------------