dany/meta-sunxi
1
0
Fork 0
mirror of https://github.com/linux-sunxi/meta-sunxi.git synced 2024-12-26 04:58:22 +01:00
Code Issues Packages Projects Releases Wiki Activity
Official sunxi OpenEmbedded layer for Allwinner-based boards.
236 Commits 30 Branches 0 Tags 13 MiB
C 64.5%
BitBake 18.8%
PHP 10.1%
C++ 3.9%
Batchfile 1.5%
Other 1.1%
732bb19214
Go to file
Aguirre 732bb19214 Merge pull request #84 from KristofRobot/linux-remove 
linux: replacing custom linux.inc by openembedded linux.inc reference (r...
2015-02-22 12:01:07 +01:00
classes sdcard_image-sunxi.bbclass: reverting to deploy dir instead of staging dir (resolves #81) 2015-02-01 13:22:11 +01:00
conf Add support for banapi machine 2015-02-22 11:59:46 +01:00
recipes-bsp Use u-boot.inc from OpenEmbedded directory instead of our own file 2015-02-22 11:59:46 +01:00
recipes-devtools/python python: pyA20 depend on python and only for olimex boards 2014-11-28 17:37:09 +01:00
recipes-graphics Add support for banapi machine 2015-02-22 11:59:46 +01:00
recipes-kernel/linux Merge pull request #84 from KristofRobot/linux-remove 2015-02-22 12:01:07 +01:00
recipes-multimedia/gstreamer gst-plugin-cedar: import PoC gstreamer 0.10 plugin 2014-01-16 13:52:23 +01:00
recipes-support/sunxi-tools added A20 to description 2014-09-08 12:16:10 +02:00
COPYING.MIT allwinner-a10: initial import. 2012-06-03 19:47:57 +02:00
README.md README: update email 2014-07-26 14:27:02 +02:00

README.md

meta-sunxi

Official sunxi OpenEmbedded layer for Allwinner-based boards.

This layer depends on the additional layer:

meta-openembedded: git://git.openembedded.org/meta-openembedded

Tested with core-image-base.

Maintainers:

Performance

The default machine settings are meant to be the lowest common denominator, maximizing generality. Significantly better performance (2x-3x) can be achieved with the following settings:

Allwinner A20

For Allwinner A20 (Cubieboard2/CubieTruck), the following tuning options are recommended:

Enable hardfloat, thumb2 and neon capabilities

DEFAULTTUNE = "cortexa7hf-neon-vfpv4"

This tuning profile takes advantage of the Allwinner A20 hardfloat, neon and vfpv4 capabilities.

Change CPU governor to ondemand, and tune settings

echo ondemand > /sys/devices/system/cpu/cpu0/cpufreq/scaling_governor
echo 336000 > /sys/devices/system/cpu/cpu0/cpufreq/scaling_min_freq
echo 912000 > /sys/devices/system/cpu/cpu0/cpufreq/scaling_max_freq
#More aggressive
#echo 1008000 > /sys/devices/system/cpu/cpu0/cpufreq/scaling_max_freq
echo 40 > /sys/devices/system/cpu/cpufreq/ondemand/up_threshold
echo 200000 > /sys/devices/system/cpu/cpufreq/ondemand/sampling_rate

This code changes the default CPU governor from fantasy to ondemand, and tunes its settings, as recommended at http://linux-sunxi.org/Cpufreq

For additional discussion, see https://github.com/linux-sunxi/meta-sunxi/issues/25